171 files changed, 109676 insertions, 0 deletions

diff --git a/ext/pcre/CREDITS b/ext/pcre/CREDITS
new file mode 100644
index 0000000..ae0fba3
--- /dev/null
+++ b/ext/pcre/CREDITS
@@ -0,0 +1,2 @@
+Perl Compatible Regexps
+Andrei Zmievski
diff --git a/ext/pcre/config.w32 b/ext/pcre/config.w32
new file mode 100644
index 0000000..52673f5
--- /dev/null
+++ b/ext/pcre/config.w32
@@ -0,0 +1,12 @@
+// $Id$
+// vim:ft=javascript
+
+EXTENSION("pcre", "php_pcre.c", false /* never shared */,
+		"-Iext/pcre/pcrelib");
+ADD_SOURCES("ext/pcre/pcrelib", "pcre_chartables.c pcre_ucd.c pcre_compile.c pcre_config.c pcre_exec.c pcre_fullinfo.c pcre_get.c pcre_globals.c pcre_maketables.c pcre_newline.c pcre_ord2utf8.c pcre_refcount.c pcre_study.c pcre_tables.c pcre_valid_utf8.c pcre_version.c pcre_xclass.c", "pcre");
+ADD_DEF_FILE("ext\\pcre\\php_pcre.def");
+
+AC_DEFINE('HAVE_BUNDLED_PCRE', 1, 'Using bundled PCRE library');
+AC_DEFINE('HAVE_PCRE', 1, 'Have PCRE library');
+PHP_PCRE="yes";
+PHP_INSTALL_HEADERS("ext/pcre", "php_pcre.h pcrelib/");
diff --git a/ext/pcre/config0.m4 b/ext/pcre/config0.m4
new file mode 100644
index 0000000..f1ce066
--- /dev/null
+++ b/ext/pcre/config0.m4
@@ -0,0 +1,66 @@
+dnl
+dnl $Id$
+dnl
+
+dnl By default we'll compile and link against the bundled PCRE library
+dnl if DIR is supplied, we'll use that for linking
+
+PHP_ARG_WITH(pcre-regex,,
+[  --with-pcre-regex=DIR   Include Perl Compatible Regular Expressions support.
+                          DIR is the PCRE install prefix [BUNDLED]], yes, no)
+
+  if test "$PHP_PCRE_REGEX" != "yes" && test "$PHP_PCRE_REGEX" != "no"; then
+    AC_MSG_CHECKING([for PCRE headers location])
+    for i in $PHP_PCRE_REGEX $PHP_PCRE_REGEX/include $PHP_PCRE_REGEX/include/pcre $PHP_PCRE_REGEX/local/include; do
+      test -f $i/pcre.h && PCRE_INCDIR=$i
+    done
+
+    if test -z "$PCRE_INCDIR"; then
+      AC_MSG_ERROR([Could not find pcre.h in $PHP_PCRE_REGEX])
+    fi
+    AC_MSG_RESULT([$PCRE_INCDIR])
+
+    AC_MSG_CHECKING([for PCRE library location])
+    for j in $PHP_PCRE_REGEX $PHP_PCRE_REGEX/$PHP_LIBDIR; do
+      test -f $j/libpcre.a || test -f $j/libpcre.$SHLIB_SUFFIX_NAME && PCRE_LIBDIR=$j
+    done
+    
+    if test -z "$PCRE_LIBDIR" ; then
+      AC_MSG_ERROR([Could not find libpcre.(a|$SHLIB_SUFFIX_NAME) in $PHP_PCRE_REGEX])
+    fi
+    AC_MSG_RESULT([$PCRE_LIBDIR])
+
+    changequote({,})
+    pcre_major=`grep PCRE_MAJOR $PCRE_INCDIR/pcre.h | sed -e 's/[^0-9]//g'`
+    pcre_minor=`grep PCRE_MINOR $PCRE_INCDIR/pcre.h | sed -e 's/[^0-9]//g'`
+    changequote([,])
+    pcre_minor_length=`echo "$pcre_minor" | wc -c | sed -e 's/[^0-9]//g'`
+    if test "$pcre_minor_length" -eq 2 ; then
+      pcre_minor="$pcre_minor"0
+    fi
+    pcre_version=$pcre_major$pcre_minor
+    if test "$pcre_version" -lt 660; then
+      AC_MSG_ERROR([The PCRE extension requires PCRE library version >= 6.6])
+    fi
+
+    PHP_ADD_LIBRARY_WITH_PATH(pcre, $PCRE_LIBDIR)
+    
+    AC_DEFINE(HAVE_PCRE, 1, [ ])
+    PHP_ADD_INCLUDE($PCRE_INCDIR)
+    PHP_NEW_EXTENSION(pcre, php_pcre.c, no)
+    PHP_INSTALL_HEADERS([ext/pcre], [php_pcre.h])
+  else
+    AC_MSG_CHECKING([for PCRE library to use])
+    AC_MSG_RESULT([bundled])
+    pcrelib_sources="pcrelib/pcre_chartables.c pcrelib/pcre_ucd.c \
+    				 pcrelib/pcre_compile.c pcrelib/pcre_config.c pcrelib/pcre_exec.c \
+    				 pcrelib/pcre_fullinfo.c pcrelib/pcre_get.c pcrelib/pcre_globals.c \
+    				 pcrelib/pcre_maketables.c pcrelib/pcre_newline.c \
+    				 pcrelib/pcre_ord2utf8.c pcrelib/pcre_refcount.c pcrelib/pcre_study.c \
+    				 pcrelib/pcre_tables.c pcrelib/pcre_valid_utf8.c \
+    				 pcrelib/pcre_version.c pcrelib/pcre_xclass.c"
+    PHP_NEW_EXTENSION(pcre, $pcrelib_sources php_pcre.c, no,,-I@ext_srcdir@/pcrelib)
+    PHP_ADD_BUILD_DIR($ext_builddir/pcrelib)
+    PHP_INSTALL_HEADERS([ext/pcre], [php_pcre.h pcrelib/])
+    AC_DEFINE(HAVE_BUNDLED_PCRE, 1, [ ])
+  fi
diff --git a/ext/pcre/pcrelib/AUTHORS b/ext/pcre/pcrelib/AUTHORS
new file mode 100644
index 0000000..ba4753d
--- /dev/null
+++ b/ext/pcre/pcrelib/AUTHORS
@@ -0,0 +1,45 @@
+THE MAIN PCRE LIBRARY
+---------------------
+
+Written by:       Philip Hazel
+Email local part: ph10
+Email domain:     cam.ac.uk
+
+University of Cambridge Computing Service,
+Cambridge, England.
+
+Copyright (c) 1997-2012 University of Cambridge
+All rights reserved
+
+
+PCRE JUST-IN-TIME COMPILATION SUPPORT
+-------------------------------------
+
+Written by:       Zoltan Herczeg
+Email local part: hzmester
+Emain domain:     freemail.hu
+
+Copyright(c) 2010-2012 Zoltan Herczeg
+All rights reserved.
+
+
+STACK-LESS JUST-IN-TIME COMPILER
+--------------------------------
+
+Written by:       Zoltan Herczeg
+Email local part: hzmester
+Emain domain:     freemail.hu
+
+Copyright(c) 2009-2012 Zoltan Herczeg
+All rights reserved.
+
+
+THE C++ WRAPPER LIBRARY
+-----------------------
+
+Written by:       Google Inc.
+
+Copyright (c) 2007-2012 Google Inc
+All rights reserved
+
+####
diff --git a/ext/pcre/pcrelib/COPYING b/ext/pcre/pcrelib/COPYING
new file mode 100644
index 0000000..58eed01
--- /dev/null
+++ b/ext/pcre/pcrelib/COPYING
@@ -0,0 +1,5 @@
+PCRE LICENCE
+
+Please see the file LICENCE in the PCRE distribution for licensing details.
+
+End
diff --git a/ext/pcre/pcrelib/ChangeLog b/ext/pcre/pcrelib/ChangeLog
new file mode 100644
index 0000000..fe85d67
--- /dev/null
+++ b/ext/pcre/pcrelib/ChangeLog
@@ -0,0 +1,4817 @@
+ChangeLog for PCRE
+------------------
+
+Version 8.31 06-July-2012
+-------------------------
+
+1.  Fixing a wrong JIT test case and some compiler warnings.
+
+2.  Removed a bashism from the RunTest script.
+
+3.  Add a cast to pcre_exec.c to fix the warning "unary minus operator applied
+    to unsigned type, result still unsigned" that was given by an MS compiler
+    on encountering the code "-sizeof(xxx)".
+
+4.  Partial matching support is added to the JIT compiler.
+
+5.  Fixed several bugs concerned with partial matching of items that consist
+    of more than one character:
+
+    (a) /^(..)\1/ did not partially match "aba" because checking references was
+        done on an "all or nothing" basis. This also applied to repeated
+        references.
+
+    (b) \R did not give a hard partial match if \r was found at the end of the
+        subject.
+
+    (c) \X did not give a hard partial match after matching one or more
+        characters at the end of the subject.
+
+    (d) When newline was set to CRLF, a pattern such as /a$/ did not recognize
+        a partial match for the string "\r".
+
+    (e) When newline was set to CRLF, the metacharacter "." did not recognize
+        a partial match for a CR character at the end of the subject string.
+
+6.  If JIT is requested using /S++ or -s++ (instead of just /S+ or -s+) when
+    running pcretest, the text "(JIT)" added to the output whenever JIT is
+    actually used to run the match.
+
+7.  Individual JIT compile options can be set in pcretest by following -s+[+]
+    or /S+[+] with a digit between 1 and 7.
+
+8.  OP_NOT now supports any UTF character not just single-byte ones.
+
+9.  (*MARK) control verb is now supported by the JIT compiler.
+
+10. The command "./RunTest list" lists the available tests without actually
+    running any of them. (Because I keep forgetting what they all are.)
+
+11. Add PCRE_INFO_MAXLOOKBEHIND.
+
+12. Applied a (slightly modified) user-supplied patch that improves performance
+    when the heap is used for recursion (compiled with --disable-stack-for-
+    recursion). Instead of malloc and free for each heap frame each time a
+    logical recursion happens, frames are retained on a chain and re-used where
+    possible. This sometimes gives as much as 30% improvement.
+
+13. As documented, (*COMMIT) is now confined to within a recursive subpattern
+    call.
+
+14. As documented, (*COMMIT) is now confined to within a positive assertion.
+
+15. It is now possible to link pcretest with libedit as an alternative to
+    libreadline.
+
+16. (*COMMIT) control verb is now supported by the JIT compiler.
+
+17. The Unicode data tables have been updated to Unicode 6.1.0.
+
+18. Added --file-list option to pcregrep.
+
+19. Added binary file support to pcregrep, including the -a, --binary-files,
+    -I, and --text options.
+
+20. The madvise function is renamed for posix_madvise for QNX compatibility
+    reasons. Fixed by Giuseppe D'Angelo.
+
+21. Fixed a bug for backward assertions with REVERSE 0 in the JIT compiler.
+
+22. Changed the option for creating symbolic links for 16-bit man pages from
+    -s to -sf so that re-installing does not cause issues.
+
+23. Support PCRE_NO_START_OPTIMIZE in JIT as (*MARK) support requires it.
+
+24. Fixed a very old bug in pcretest that caused errors with restarted DFA
+    matches in certain environments (the workspace was not being correctly
+    retained). Also added to pcre_dfa_exec() a simple plausibility check on
+    some of the workspace data at the beginning of a restart.
+
+25. \s*\R was auto-possessifying the \s* when it should not, whereas \S*\R
+    was not doing so when it should - probably a typo introduced by SVN 528
+    (change 8.10/14).
+
+26. When PCRE_UCP was not set, \w+\x{c4} was incorrectly auto-possessifying the
+    \w+ when the character tables indicated that \x{c4} was a word character.
+    There were several related cases, all because the tests for doing a table
+    lookup were testing for characters less than 127 instead of 255.
+
+27. If a pattern contains capturing parentheses that are not used in a match,
+    their slots in the ovector are set to -1. For those that are higher than
+    any matched groups, this happens at the end of processing. In the case when
+    there were back references that the ovector was too small to contain
+    (causing temporary malloc'd memory to be used during matching), and the
+    highest capturing number was not used, memory off the end of the ovector
+    was incorrectly being set to -1. (It was using the size of the temporary
+    memory instead of the true size.)
+
+28. To catch bugs like 27 using valgrind, when pcretest is asked to specify an
+    ovector size, it uses memory at the end of the block that it has got.
+
+29. Check for an overlong MARK name and give an error at compile time. The
+    limit is 255 for the 8-bit library and 65535 for the 16-bit library.
+
+30. JIT compiler update.
+
+31. JIT is now supported on jailbroken iOS devices. Thanks for Ruiger
+    Rill for the patch.
+
+32. Put spaces around SLJIT_PRINT_D in the JIT compiler. Required by CXX11.
+
+33. Variable renamings in the PCRE-JIT compiler. No functionality change.
+
+34. Fixed typos in pcregrep: in two places there was SUPPORT_LIBZ2 instead of
+    SUPPORT_LIBBZ2. This caused a build problem when bzip2 but not gzip (zlib)
+    was enabled.
+
+35. Improve JIT code generation for greedy plus quantifier.
+
+36. When /((?:a?)*)*c/ or /((?>a?)*)*c/ was matched against "aac", it set group
+    1 to "aa" instead of to an empty string. The bug affected repeated groups
+    that could potentially match an empty string.
+
+37. Optimizing single character iterators in JIT.
+
+38. Wide characters specified with \uxxxx in JavaScript mode are now subject to
+    the same checks as \x{...} characters in non-JavaScript mode. Specifically,
+    codepoints that are too big for the mode are faulted, and in a UTF mode,
+    disallowed codepoints are also faulted.
+
+39. If PCRE was compiled with UTF support, in three places in the DFA
+    matcher there was code that should only have been obeyed in UTF mode, but
+    was being obeyed unconditionally. In 8-bit mode this could cause incorrect
+    processing when bytes with values greater than 127 were present. In 16-bit
+    mode the bug would be provoked by values in the range 0xfc00 to 0xdc00. In
+    both cases the values are those that cannot be the first data item in a UTF
+    character. The three items that might have provoked this were recursions,
+    possessively repeated groups, and atomic groups.
+
+40. Ensure that libpcre is explicitly listed in the link commands for pcretest
+    and pcregrep, because some OS require shared objects to be explicitly
+    passed to ld, causing the link step to fail if they are not.
+
+41. There were two incorrect #ifdefs in pcre_study.c, meaning that, in 16-bit
+    mode, patterns that started with \h* or \R* might be incorrectly matched.
+
+
+Version 8.30 04-February-2012
+-----------------------------
+
+1.  Renamed "isnumber" as "is_a_number" because in some Mac environments this
+    name is defined in ctype.h.
+
+2.  Fixed a bug in fixed-length calculation for lookbehinds that would show up
+    only in quite long subpatterns.
+
+3.  Removed the function pcre_info(), which has been obsolete and deprecated
+    since it was replaced by pcre_fullinfo() in February 2000.
+
+4.  For a non-anchored pattern, if (*SKIP) was given with a name that did not
+    match a (*MARK), and the match failed at the start of the subject, a
+    reference to memory before the start of the subject could occur. This bug
+    was introduced by fix 17 of release 8.21.
+
+5.  A reference to an unset group with zero minimum repetition was giving
+    totally wrong answers (in non-JavaScript-compatibility mode). For example,
+    /(another)?(\1?)test/ matched against "hello world test". This bug was
+    introduced in release 8.13.
+
+6.  Add support for 16-bit character strings (a large amount of work involving
+    many changes and refactorings).
+
+7.  RunGrepTest failed on msys because \r\n was replaced by whitespace when the
+    command "pattern=`printf 'xxx\r\njkl'`" was run. The pattern is now taken
+    from a file.
+
+8.  Ovector size of 2 is also supported by JIT based pcre_exec (the ovector size
+    rounding is not applied in this particular case).
+
+9.  The invalid Unicode surrogate codepoints U+D800 to U+DFFF are now rejected
+    if they appear, or are escaped, in patterns.
+
+10. Get rid of a number of -Wunused-but-set-variable warnings.
+
+11. The pattern /(?=(*:x))(q|)/ matches an empty string, and returns the mark
+    "x". The similar pattern /(?=(*:x))((*:y)q|)/ did not return a mark at all.
+    Oddly, Perl behaves the same way. PCRE has been fixed so that this pattern
+    also returns the mark "x". This bug applied to capturing parentheses,
+    non-capturing parentheses, and atomic parentheses. It also applied to some
+    assertions.
+
+12. Stephen Kelly's patch to CMakeLists.txt allows it to parse the version
+    information out of configure.ac instead of relying on pcre.h.generic, which
+    is not stored in the repository.
+
+13. Applied Dmitry V. Levin's patch for a more portable method for linking with
+    -lreadline.
+
+14. ZH added PCRE_CONFIG_JITTARGET; added its output to pcretest -C.
+
+15. Applied Graycode's patch to put the top-level frame on the stack rather
+    than the heap when not using the stack for recursion. This gives a
+    performance improvement in many cases when recursion is not deep.
+
+16. Experimental code added to "pcretest -C" to output the stack frame size.
+
+
+Version 8.21 12-Dec-2011
+------------------------
+
+1.  Updating the JIT compiler.
+
+2.  JIT compiler now supports OP_NCREF, OP_RREF and OP_NRREF. New test cases
+    are added as well.
+
+3.  Fix cache-flush issue on PowerPC (It is still an experimental JIT port).
+    PCRE_EXTRA_TABLES is not suported by JIT, and should be checked before
+    calling _pcre_jit_exec. Some extra comments are added.
+
+4.  (*MARK) settings inside atomic groups that do not contain any capturing
+    parentheses, for example, (?>a(*:m)), were not being passed out. This bug
+    was introduced by change 18 for 8.20.
+
+5.  Supporting of \x, \U and \u in JavaScript compatibility mode based on the
+    ECMA-262 standard.
+
+6.  Lookbehinds such as (?<=a{2}b) that contained a fixed repetition were
+    erroneously being rejected as "not fixed length" if PCRE_CASELESS was set.
+    This bug was probably introduced by change 9 of 8.13.
+
+7.  While fixing 6 above, I noticed that a number of other items were being
+    incorrectly rejected as "not fixed length". This arose partly because newer
+    opcodes had not been added to the fixed-length checking code. I have (a)
+    corrected the bug and added tests for these items, and (b) arranged for an
+    error to occur if an unknown opcode is encountered while checking for fixed
+    length instead of just assuming "not fixed length". The items that were
+    rejected were: (*ACCEPT), (*COMMIT), (*FAIL), (*MARK), (*PRUNE), (*SKIP),
+    (*THEN), \h, \H, \v, \V, and single character negative classes with fixed
+    repetitions, e.g. [^a]{3}, with and without PCRE_CASELESS.
+
+8.  A possessively repeated conditional subpattern such as (?(?=c)c|d)++ was
+    being incorrectly compiled and would have given unpredicatble results.
+
+9.  A possessively repeated subpattern with minimum repeat count greater than
+    one behaved incorrectly. For example, (A){2,}+ behaved as if it was
+    (A)(A)++ which meant that, after a subsequent mismatch, backtracking into
+    the first (A) could occur when it should not.
+
+10. Add a cast and remove a redundant test from the code.
+
+11. JIT should use pcre_malloc/pcre_free for allocation.
+
+12. Updated pcre-config so that it no longer shows -L/usr/lib, which seems
+    best practice nowadays, and helps with cross-compiling. (If the exec_prefix
+    is anything other than /usr, -L is still shown).
+
+13. In non-UTF-8 mode, \C is now supported in lookbehinds and DFA matching.
+
+14. Perl does not support \N without a following name in a [] class; PCRE now
+    also gives an error.
+
+15. If a forward reference was repeated with an upper limit of around 2000,
+    it caused the error "internal error: overran compiling workspace". The
+    maximum number of forward references (including repeats) was limited by the
+    internal workspace, and dependent on the LINK_SIZE. The code has been
+    rewritten so that the workspace expands (via pcre_malloc) if necessary, and
+    the default depends on LINK_SIZE. There is a new upper limit (for safety)
+    of around 200,000 forward references. While doing this, I also speeded up
+    the filling in of repeated forward references.
+
+16. A repeated forward reference in a pattern such as (a)(?2){2}(.) was
+    incorrectly expecting the subject to contain another "a" after the start.
+
+17. When (*SKIP:name) is activated without a corresponding (*MARK:name) earlier
+    in the match, the SKIP should be ignored. This was not happening; instead
+    the SKIP was being treated as NOMATCH. For patterns such as
+    /A(*MARK:A)A+(*SKIP:B)Z|AAC/ this meant that the AAC branch was never
+    tested.
+
+18. The behaviour of (*MARK), (*PRUNE), and (*THEN) has been reworked and is
+    now much more compatible with Perl, in particular in cases where the result
+    is a non-match for a non-anchored pattern. For example, if
+    /b(*:m)f|a(*:n)w/ is matched against "abc", the non-match returns the name
+    "m", where previously it did not return a name. A side effect of this
+    change is that for partial matches, the last encountered mark name is
+    returned, as for non matches. A number of tests that were previously not
+    Perl-compatible have been moved into the Perl-compatible test files. The
+    refactoring has had the pleasing side effect of removing one argument from
+    the match() function, thus reducing its stack requirements.
+
+19. If the /S+ option was used in pcretest to study a pattern using JIT,
+    subsequent uses of /S (without +) incorrectly behaved like /S+.
+
+21. Retrieve executable code size support for the JIT compiler and fixing
+    some warnings.
+
+22. A caseless match of a UTF-8 character whose other case uses fewer bytes did
+    not work when the shorter character appeared right at the end of the
+    subject string.
+
+23. Added some (int) casts to non-JIT modules to reduce warnings on 64-bit
+    systems.
+
+24. Added PCRE_INFO_JITSIZE to pass on the value from (21) above, and also
+    output it when the /M option is used in pcretest.
+
+25. The CheckMan script was not being included in the distribution. Also, added
+    an explicit "perl" to run Perl scripts from the PrepareRelease script
+    because this is reportedly needed in Windows.
+
+26. If study data was being save in a file and studying had not found a set of
+    "starts with" bytes for the pattern, the data written to the file (though
+    never used) was taken from uninitialized memory and so caused valgrind to
+    complain.
+
+27. Updated RunTest.bat as provided by Sheri Pierce.
+
+28. Fixed a possible uninitialized memory bug in pcre_jit_compile.c.
+
+29. Computation of memory usage for the table of capturing group names was
+    giving an unnecessarily large value.
+
+
+Version 8.20 21-Oct-2011
+------------------------
+
+1.  Change 37 of 8.13 broke patterns like [:a]...[b:] because it thought it had
+    a POSIX class. After further experiments with Perl, which convinced me that
+    Perl has bugs and confusions, a closing square bracket is no longer allowed
+    in a POSIX name. This bug also affected patterns with classes that started
+    with full stops.
+
+2.  If a pattern such as /(a)b|ac/ is matched against "ac", there is no
+    captured substring, but while checking the failing first alternative,
+    substring 1 is temporarily captured. If the output vector supplied to
+    pcre_exec() was not big enough for this capture, the yield of the function
+    was still zero ("insufficient space for captured substrings"). This cannot
+    be totally fixed without adding another stack variable, which seems a lot
+    of expense for a edge case. However, I have improved the situation in cases
+    such as /(a)(b)x|abc/ matched against "abc", where the return code
+    indicates that fewer than the maximum number of slots in the ovector have
+    been set.
+
+3.  Related to (2) above: when there are more back references in a pattern than
+    slots in the output vector, pcre_exec() uses temporary memory during
+    matching, and copies in the captures as far as possible afterwards. It was
+    using the entire output vector, but this conflicts with the specification
+    that only 2/3 is used for passing back captured substrings. Now it uses
+    only the first 2/3, for compatibility. This is, of course, another edge
+    case.
+
+4.  Zoltan Herczeg's just-in-time compiler support has been integrated into the
+    main code base, and can be used by building with --enable-jit. When this is
+    done, pcregrep automatically uses it unless --disable-pcregrep-jit or the
+    runtime --no-jit option is given.
+
+5.  When the number of matches in a pcre_dfa_exec() run exactly filled the
+    ovector, the return from the function was zero, implying that there were
+    other matches that did not fit. The correct "exactly full" value is now
+    returned.
+
+6.  If a subpattern that was called recursively or as a subroutine contained
+    (*PRUNE) or any other control that caused it to give a non-standard return,
+    invalid errors such as "Error -26 (nested recursion at the same subject
+    position)" or even infinite loops could occur.
+
+7.  If a pattern such as /a(*SKIP)c|b(*ACCEPT)|/ was studied, it stopped
+    computing the minimum length on reaching *ACCEPT, and so ended up with the
+    wrong value of 1 rather than 0. Further investigation indicates that
+    computing a minimum subject length in the presence of *ACCEPT is difficult
+    (think back references, subroutine calls), and so I have changed the code
+    so that no minimum is registered for a pattern that contains *ACCEPT.
+
+8.  If (*THEN) was present in the first (true) branch of a conditional group,
+    it was not handled as intended. [But see 16 below.]
+
+9.  Replaced RunTest.bat and CMakeLists.txt with improved versions provided by
+    Sheri Pierce.
+
+10. A pathological pattern such as /(*ACCEPT)a/ was miscompiled, thinking that
+    the first byte in a match must be "a".
+
+11. Change 17 for 8.13 increased the recursion depth for patterns like
+    /a(?:.)*?a/ drastically. I've improved things by remembering whether a
+    pattern contains any instances of (*THEN). If it does not, the old
+    optimizations are restored. It would be nice to do this on a per-group
+    basis, but at the moment that is not feasible.
+
+12. In some environments, the output of pcretest -C is CRLF terminated. This
+    broke RunTest's code that checks for the link size. A single white space
+    character after the value is now allowed for.
+
+13. RunTest now checks for the "fr" locale as well as for "fr_FR" and "french".
+    For "fr", it uses the Windows-specific input and output files.
+
+14. If (*THEN) appeared in a group that was called recursively or as a
+    subroutine, it did not work as intended. [But see next item.]
+
+15. Consider the pattern /A (B(*THEN)C) | D/ where A, B, C, and D are complex
+    pattern fragments (but not containing any | characters). If A and B are
+    matched, but there is a failure in C so that it backtracks to (*THEN), PCRE
+    was behaving differently to Perl. PCRE backtracked into A, but Perl goes to
+    D. In other words, Perl considers parentheses that do not contain any |
+    characters to be part of a surrounding alternative, whereas PCRE was
+    treading (B(*THEN)C) the same as (B(*THEN)C|(*FAIL)) -- which Perl handles
+    differently. PCRE now behaves in the same way as Perl, except in the case
+    of subroutine/recursion calls such as (?1) which have in any case always
+    been different (but PCRE had them first :-).
+
+16. Related to 15 above: Perl does not treat the | in a conditional group as
+    creating alternatives. Such a group is treated in the same way as an
+    ordinary group without any | characters when processing (*THEN). PCRE has
+    been changed to match Perl's behaviour.
+
+17. If a user had set PCREGREP_COLO(U)R to something other than 1:31, the
+    RunGrepTest script failed.
+
+18. Change 22 for version 13 caused atomic groups to use more stack. This is
+    inevitable for groups that contain captures, but it can lead to a lot of
+    stack use in large patterns. The old behaviour has been restored for atomic
+    groups that do not contain any capturing parentheses.
+
+19. If the PCRE_NO_START_OPTIMIZE option was set for pcre_compile(), it did not
+    suppress the check for a minimum subject length at run time. (If it was
+    given to pcre_exec() or pcre_dfa_exec() it did work.)
+
+20. Fixed an ASCII-dependent infelicity in pcretest that would have made it
+    fail to work when decoding hex characters in data strings in EBCDIC
+    environments.
+
+21. It appears that in at least one Mac OS environment, the isxdigit() function
+    is implemented as a macro that evaluates to its argument more than once,
+    contravening the C 90 Standard (I haven't checked a later standard). There
+    was an instance in pcretest which caused it to go wrong when processing
+    \x{...} escapes in subject strings. The has been rewritten to avoid using
+    things like p++ in the argument of isxdigit().
+
+
+Version 8.13 16-Aug-2011
+------------------------
+
+1.  The Unicode data tables have been updated to Unicode 6.0.0.
+
+2.  Two minor typos in pcre_internal.h have been fixed.
+
+3.  Added #include <string.h> to pcre_scanner_unittest.cc, pcrecpp.cc, and
+    pcrecpp_unittest.cc. They are needed for strcmp(), memset(), and strchr()
+    in some environments (e.g. Solaris 10/SPARC using Sun Studio 12U2).
+
+4.  There were a number of related bugs in the code for matching backrefences
+    caselessly in UTF-8 mode when codes for the characters concerned were
+    different numbers of bytes. For example, U+023A and U+2C65 are an upper
+    and lower case pair, using 2 and 3 bytes, respectively. The main bugs were:
+    (a) A reference to 3 copies of a 2-byte code matched only 2 of a 3-byte
+    code. (b) A reference to 2 copies of a 3-byte code would not match 2 of a
+    2-byte code at the end of the subject (it thought there wasn't enough data
+    left).
+
+5.  Comprehensive information about what went wrong is now returned by
+    pcre_exec() and pcre_dfa_exec() when the UTF-8 string check fails, as long
+    as the output vector has at least 2 elements. The offset of the start of
+    the failing character and a reason code are placed in the vector.
+
+6.  When the UTF-8 string check fails for pcre_compile(), the offset that is
+    now returned is for the first byte of the failing character, instead of the
+    last byte inspected. This is an incompatible change, but I hope it is small
+    enough not to be a problem. It makes the returned offset consistent with
+    pcre_exec() and pcre_dfa_exec().
+
+7.  pcretest now gives a text phrase as well as the error number when
+    pcre_exec() or pcre_dfa_exec() fails; if the error is a UTF-8 check
+    failure, the offset and reason code are output.
+
+8.  When \R was used with a maximizing quantifier it failed to skip backwards
+    over a \r\n pair if the subsequent match failed. Instead, it just skipped
+    back over a single character (\n). This seems wrong (because it treated the
+    two characters as a single entity when going forwards), conflicts with the
+    documentation that \R is equivalent to (?>\r\n|\n|...etc), and makes the
+    behaviour of \R* different to (\R)*, which also seems wrong. The behaviour
+    has been changed.
+
+9.  Some internal refactoring has changed the processing so that the handling
+    of the PCRE_CASELESS and PCRE_MULTILINE options is done entirely at compile
+    time (the PCRE_DOTALL option was changed this way some time ago: version
+    7.7 change 16). This has made it possible to abolish the OP_OPT op code,
+    which was always a bit of a fudge. It also means that there is one less
+    argument for the match() function, which reduces its stack requirements
+    slightly. This change also fixes an incompatibility with Perl: the pattern
+    (?i:([^b]))(?1) should not match "ab", but previously PCRE gave a match.
+
+10. More internal refactoring has drastically reduced the number of recursive
+    calls to match() for possessively repeated groups such as (abc)++ when
+    using pcre_exec().
+
+11. While implementing 10, a number of bugs in the handling of groups were
+    discovered and fixed:
+
+    (?<=(a)+) was not diagnosed as invalid (non-fixed-length lookbehind).
+    (a|)*(?1) gave a compile-time internal error.
+    ((a|)+)+  did not notice that the outer group could match an empty string.
+    (^a|^)+   was not marked as anchored.
+    (.*a|.*)+ was not marked as matching at start or after a newline.
+
+12. Yet more internal refactoring has removed another argument from the match()
+    function. Special calls to this function are now indicated by setting a
+    value in a variable in the "match data" data block.
+
+13. Be more explicit in pcre_study() instead of relying on "default" for
+    opcodes that mean there is no starting character; this means that when new
+    ones are added and accidentally left out of pcre_study(), testing should
+    pick them up.
+
+14. The -s option of pcretest has been documented for ages as being an old
+    synonym of -m (show memory usage). I have changed it to mean "force study
+    for every regex", that is, assume /S for every regex. This is similar to -i
+    and -d etc. It's slightly incompatible, but I'm hoping nobody is still
+    using it. It makes it easier to run collections of tests with and without
+    study enabled, and thereby test pcre_study() more easily. All the standard
+    tests are now run with and without -s (but some patterns can be marked as
+    "never study" - see 20 below).
+
+15. When (*ACCEPT) was used in a subpattern that was called recursively, the
+    restoration of the capturing data to the outer values was not happening
+    correctly.
+
+16. If a recursively called subpattern ended with (*ACCEPT) and matched an
+    empty string, and PCRE_NOTEMPTY was set, pcre_exec() thought the whole
+    pattern had matched an empty string, and so incorrectly returned a no
+    match.
+
+17. There was optimizing code for the last branch of non-capturing parentheses,
+    and also for the obeyed branch of a conditional subexpression, which used
+    tail recursion to cut down on stack usage. Unfortunately, now that there is
+    the possibility of (*THEN) occurring in these branches, tail recursion is
+    no longer possible because the return has to be checked for (*THEN). These
+    two optimizations have therefore been removed. [But see 8.20/11 above.]
+
+18. If a pattern containing \R was studied, it was assumed that \R always
+    matched two bytes, thus causing the minimum subject length to be
+    incorrectly computed because \R can also match just one byte.
+
+19. If a pattern containing (*ACCEPT) was studied, the minimum subject length
+    was incorrectly computed.
+
+20. If /S is present twice on a test pattern in pcretest input, it now
+    *disables* studying, thereby overriding the use of -s on the command line
+    (see 14 above). This is necessary for one or two tests to keep the output
+    identical in both cases.
+
+21. When (*ACCEPT) was used in an assertion that matched an empty string and
+    PCRE_NOTEMPTY was set, PCRE applied the non-empty test to the assertion.
+
+22. When an atomic group that contained a capturing parenthesis was
+    successfully matched, but the branch in which it appeared failed, the
+    capturing was not being forgotten if a higher numbered group was later
+    captured. For example, /(?>(a))b|(a)c/ when matching "ac" set capturing
+    group 1 to "a", when in fact it should be unset. This applied to multi-
+    branched capturing and non-capturing groups, repeated or not, and also to
+    positive assertions (capturing in negative assertions does not happen
+    in PCRE) and also to nested atomic groups.
+
+23. Add the ++ qualifier feature to pcretest, to show the remainder of the
+    subject after a captured substring, to make it easier to tell which of a
+    number of identical substrings has been captured.
+
+24. The way atomic groups are processed by pcre_exec() has been changed so that
+    if they are repeated, backtracking one repetition now resets captured
+    values correctly. For example, if ((?>(a+)b)+aabab) is matched against
+    "aaaabaaabaabab" the value of captured group 2 is now correctly recorded as
+    "aaa". Previously, it would have been "a". As part of this code
+    refactoring, the way recursive calls are handled has also been changed.
+
+25. If an assertion condition captured any substrings, they were not passed
+    back unless some other capturing happened later. For example, if
+    (?(?=(a))a) was matched against "a", no capturing was returned.
+
+26. When studying a pattern that contained subroutine calls or assertions,
+    the code for finding the minimum length of a possible match was handling
+    direct recursions such as (xxx(?1)|yyy) but not mutual recursions (where
+    group 1 called group 2 while simultaneously a separate group 2 called group
+    1). A stack overflow occurred in this case. I have fixed this by limiting
+    the recursion depth to 10.
+
+27. Updated RunTest.bat in the distribution to the version supplied by Tom
+    Fortmann. This supports explicit test numbers on the command line, and has
+    argument validation and error reporting.
+
+28. An instance of \X with an unlimited repeat could fail if at any point the
+    first character it looked at was a mark character.
+
+29. Some minor code refactoring concerning Unicode properties and scripts
+    should reduce the stack requirement of match() slightly.
+
+30. Added the '=' option to pcretest to check the setting of unused capturing
+    slots at the end of the pattern, which are documented as being -1, but are
+    not included in the return count.
+
+31. If \k was not followed by a braced, angle-bracketed, or quoted name, PCRE
+    compiled something random. Now it gives a compile-time error (as does
+    Perl).
+
+32. A *MARK encountered during the processing of a positive assertion is now
+    recorded and passed back (compatible with Perl).
+
+33. If --only-matching or --colour was set on a pcregrep call whose pattern
+    had alternative anchored branches, the search for a second match in a line
+    was done as if at the line start. Thus, for example, /^01|^02/ incorrectly
+    matched the line "0102" twice. The same bug affected patterns that started
+    with a backwards assertion. For example /\b01|\b02/ also matched "0102"
+    twice.
+
+34. Previously, PCRE did not allow quantification of assertions. However, Perl
+    does, and because of capturing effects, quantifying parenthesized
+    assertions may at times be useful. Quantifiers are now allowed for
+    parenthesized assertions.
+
+35. A minor code tidy in pcre_compile() when checking options for \R usage.
+
+36. \g was being checked for fancy things in a character class, when it should
+    just be a literal "g".
+
+37. PCRE was rejecting [:a[:digit:]] whereas Perl was not. It seems that the
+    appearance of a nested POSIX class supersedes an apparent external class.
+    For example, [:a[:digit:]b:] matches "a", "b", ":", or a digit. Also,
+    unescaped square brackets may also appear as part of class names. For
+    example, [:a[:abc]b:] gives unknown class "[:abc]b:]". PCRE now behaves
+    more like Perl. (But see 8.20/1 above.)
+
+38. PCRE was giving an error for \N with a braced quantifier such as {1,} (this
+    was because it thought it was \N{name}, which is not supported).
+
+39. Add minix to OS list not supporting the -S option in pcretest.
+
+40. PCRE tries to detect cases of infinite recursion at compile time, but it
+    cannot analyze patterns in sufficient detail to catch mutual recursions
+    such as ((?1))((?2)). There is now a runtime test that gives an error if a
+    subgroup is called recursively as a subpattern for a second time at the
+    same position in the subject string. In previous releases this might have
+    been caught by the recursion limit, or it might have run out of stack.
+
+41. A pattern such as /(?(R)a+|(?R)b)/ is quite safe, as the recursion can
+    happen only once. PCRE was, however incorrectly giving a compile time error
+    "recursive call could loop indefinitely" because it cannot analyze the
+    pattern in sufficient detail. The compile time test no longer happens when
+    PCRE is compiling a conditional subpattern, but actual runaway loops are
+    now caught at runtime (see 40 above).
+
+42. It seems that Perl allows any characters other than a closing parenthesis
+    to be part of the NAME in (*MARK:NAME) and other backtracking verbs. PCRE
+    has been changed to be the same.
+
+43. Updated configure.ac to put in more quoting round AC_LANG_PROGRAM etc. so
+    as not to get warnings when autogen.sh is called. Also changed
+    AC_PROG_LIBTOOL (deprecated) to LT_INIT (the current macro).
+
+44. To help people who use pcregrep to scan files containing exceedingly long
+    lines, the following changes have been made:
+
+    (a) The default value of the buffer size parameter has been increased from
+        8K to 20K. (The actual buffer used is three times this size.)
+
+    (b) The default can be changed by ./configure --with-pcregrep-bufsize when
+        PCRE is built.
+
+    (c) A --buffer-size=n option has been added to pcregrep, to allow the size
+        to be set at run time.
+
+    (d) Numerical values in pcregrep options can be followed by K or M, for
+        example --buffer-size=50K.
+
+    (e) If a line being scanned overflows pcregrep's buffer, an error is now
+        given and the return code is set to 2.
+
+45. Add a pointer to the latest mark to the callout data block.
+
+46. The pattern /.(*F)/, when applied to "abc" with PCRE_PARTIAL_HARD, gave a
+    partial match of an empty string instead of no match. This was specific to
+    the use of ".".
+
+47. The pattern /f.*/8s, when applied to "for" with PCRE_PARTIAL_HARD, gave a
+    complete match instead of a partial match. This bug was dependent on both
+    the PCRE_UTF8 and PCRE_DOTALL options being set.
+
+48. For a pattern such as /\babc|\bdef/ pcre_study() was failing to set up the
+    starting byte set, because \b was not being ignored.
+
+
+Version 8.12 15-Jan-2011
+------------------------
+
+1.  Fixed some typos in the markup of the man pages, and wrote a script that
+    checks for such things as part of the documentation building process.
+
+2.  On a big-endian 64-bit system, pcregrep did not correctly process the
+    --match-limit and --recursion-limit options (added for 8.11). In
+    particular, this made one of the standard tests fail. (The integer value
+    went into the wrong half of a long int.)
+
+3.  If the --colour option was given to pcregrep with -v (invert match), it
+    did strange things, either producing crazy output, or crashing. It should,
+    of course, ignore a request for colour when reporting lines that do not
+    match.
+
+4.  Another pcregrep bug caused similar problems if --colour was specified with
+    -M (multiline) and the pattern match finished with a line ending.
+
+5.  In pcregrep, when a pattern that ended with a literal newline sequence was
+    matched in multiline mode, the following line was shown as part of the
+    match. This seems wrong, so I have changed it.
+
+6.  Another pcregrep bug in multiline mode, when --colour was specified, caused
+    the check for further matches in the same line (so they could be coloured)
+    to overrun the end of the current line. If another match was found, it was
+    incorrectly shown (and then shown again when found in the next line).
+
+7.  If pcregrep was compiled under Windows, there was a reference to the
+    function pcregrep_exit() before it was defined. I am assuming this was
+    the cause of the "error C2371: 'pcregrep_exit' : redefinition;" that was
+    reported by a user. I've moved the definition above the reference.
+
+
+Version 8.11 10-Dec-2010
+------------------------
+
+1.  (*THEN) was not working properly if there were untried alternatives prior
+    to it in the current branch. For example, in ((a|b)(*THEN)(*F)|c..) it
+    backtracked to try for "b" instead of moving to the next alternative branch
+    at the same level (in this case, to look for "c"). The Perl documentation
+    is clear that when (*THEN) is backtracked onto, it goes to the "next
+    alternative in the innermost enclosing group".
+
+2.  (*COMMIT) was not overriding (*THEN), as it does in Perl. In a pattern
+    such as   (A(*COMMIT)B(*THEN)C|D)  any failure after matching A should
+    result in overall failure. Similarly, (*COMMIT) now overrides (*PRUNE) and
+    (*SKIP), (*SKIP) overrides (*PRUNE) and (*THEN), and (*PRUNE) overrides
+    (*THEN).
+
+3.  If \s appeared in a character class, it removed the VT character from
+    the class, even if it had been included by some previous item, for example
+    in [\x00-\xff\s]. (This was a bug related to the fact that VT is not part
+    of \s, but is part of the POSIX "space" class.)
+
+4.  A partial match never returns an empty string (because you can always
+    match an empty string at the end of the subject); however the checking for
+    an empty string was starting at the "start of match" point. This has been
+    changed to the "earliest inspected character" point, because the returned
+    data for a partial match starts at this character. This means that, for
+    example, /(?<=abc)def/ gives a partial match for the subject "abc"
+    (previously it gave "no match").
+
+5.  Changes have been made to the way PCRE_PARTIAL_HARD affects the matching
+    of $, \z, \Z, \b, and \B. If the match point is at the end of the string,
+    previously a full match would be given. However, setting PCRE_PARTIAL_HARD
+    has an implication that the given string is incomplete (because a partial
+    match is preferred over a full match). For this reason, these items now
+    give a partial match in this situation. [Aside: previously, the one case
+    /t\b/ matched against "cat" with PCRE_PARTIAL_HARD set did return a partial
+    match rather than a full match, which was wrong by the old rules, but is
+    now correct.]
+
+6.  There was a bug in the handling of #-introduced comments, recognized when
+    PCRE_EXTENDED is set, when PCRE_NEWLINE_ANY and PCRE_UTF8 were also set.
+    If a UTF-8 multi-byte character included the byte 0x85 (e.g. +U0445, whose
+    UTF-8 encoding is 0xd1,0x85), this was misinterpreted as a newline when
+    scanning for the end of the comment. (*Character* 0x85 is an "any" newline,
+    but *byte* 0x85 is not, in UTF-8 mode). This bug was present in several
+    places in pcre_compile().
+
+7.  Related to (6) above, when pcre_compile() was skipping #-introduced
+    comments when looking ahead for named forward references to subpatterns,
+    the only newline sequence it recognized was NL. It now handles newlines
+    according to the set newline convention.
+
+8.  SunOS4 doesn't have strerror() or strtoul(); pcregrep dealt with the
+    former, but used strtoul(), whereas pcretest avoided strtoul() but did not
+    cater for a lack of strerror(). These oversights have been fixed.
+
+9.  Added --match-limit and --recursion-limit to pcregrep.
+
+10. Added two casts needed to build with Visual Studio when NO_RECURSE is set.
+
+11. When the -o option was used, pcregrep was setting a return code of 1, even
+    when matches were found, and --line-buffered was not being honoured.
+
+12. Added an optional parentheses number to the -o and --only-matching options
+    of pcregrep.
+
+13. Imitating Perl's /g action for multiple matches is tricky when the pattern
+    can match an empty string. The code to do it in pcretest and pcredemo
+    needed fixing:
+
+    (a) When the newline convention was "crlf", pcretest got it wrong, skipping
+        only one byte after an empty string match just before CRLF (this case
+        just got forgotten; "any" and "anycrlf" were OK).
+
+    (b) The pcretest code also had a bug, causing it to loop forever in UTF-8
+        mode when an empty string match preceded an ASCII character followed by
+        a non-ASCII character. (The code for advancing by one character rather
+        than one byte was nonsense.)
+
+    (c) The pcredemo.c sample program did not have any code at all to handle
+        the cases when CRLF is a valid newline sequence.
+
+14. Neither pcre_exec() nor pcre_dfa_exec() was checking that the value given
+    as a starting offset was within the subject string. There is now a new
+    error, PCRE_ERROR_BADOFFSET, which is returned if the starting offset is
+    negative or greater than the length of the string. In order to test this,
+    pcretest is extended to allow the setting of negative starting offsets.
+
+15. In both pcre_exec() and pcre_dfa_exec() the code for checking that the
+    starting offset points to the beginning of a UTF-8 character was
+    unnecessarily clumsy. I tidied it up.
+
+16. Added PCRE_ERROR_SHORTUTF8 to make it possible to distinguish between a
+    bad UTF-8 sequence and one that is incomplete when using PCRE_PARTIAL_HARD.
+
+17. Nobody had reported that the --include_dir option, which was added in
+    release 7.7 should have been called --include-dir (hyphen, not underscore)
+    for compatibility with GNU grep. I have changed it to --include-dir, but
+    left --include_dir as an undocumented synonym, and the same for
+    --exclude-dir, though that is not available in GNU grep, at least as of
+    release 2.5.4.
+
+18. At a user's suggestion, the macros GETCHAR and friends (which pick up UTF-8
+    characters from a string of bytes) have been redefined so as not to use
+    loops, in order to improve performance in some environments. At the same
+    time, I abstracted some of the common code into auxiliary macros to save
+    repetition (this should not affect the compiled code).
+
+19. If \c was followed by a multibyte UTF-8 character, bad things happened. A
+    compile-time error is now given if \c is not followed by an ASCII
+    character, that is, a byte less than 128. (In EBCDIC mode, the code is
+    different, and any byte value is allowed.)
+
+20. Recognize (*NO_START_OPT) at the start of a pattern to set the PCRE_NO_
+    START_OPTIMIZE option, which is now allowed at compile time - but just
+    passed through to pcre_exec() or pcre_dfa_exec(). This makes it available
+    to pcregrep and other applications that have no direct access to PCRE
+    options. The new /Y option in pcretest sets this option when calling
+    pcre_compile().
+
+21. Change 18 of release 8.01 broke the use of named subpatterns for recursive
+    back references. Groups containing recursive back references were forced to
+    be atomic by that change, but in the case of named groups, the amount of
+    memory required was incorrectly computed, leading to "Failed: internal
+    error: code overflow". This has been fixed.
+
+22. Some patches to pcre_stringpiece.h, pcre_stringpiece_unittest.cc, and
+    pcretest.c, to avoid build problems in some Borland environments.
+
+
+Version 8.10 25-Jun-2010
+------------------------
+
+1.  Added support for (*MARK:ARG) and for ARG additions to PRUNE, SKIP, and
+    THEN.
+
+2.  (*ACCEPT) was not working when inside an atomic group.
+
+3.  Inside a character class, \B is treated as a literal by default, but
+    faulted if PCRE_EXTRA is set. This mimics Perl's behaviour (the -w option
+    causes the error). The code is unchanged, but I tidied the documentation.
+
+4.  Inside a character class, PCRE always treated \R and \X as literals,
+    whereas Perl faults them if its -w option is set. I have changed PCRE so
+    that it faults them when PCRE_EXTRA is set.
+
+5.  Added support for \N, which always matches any character other than
+    newline. (It is the same as "." when PCRE_DOTALL is not set.)
+
+6.  When compiling pcregrep with newer versions of gcc which may have
+    FORTIFY_SOURCE set, several warnings "ignoring return value of 'fwrite',
+    declared with attribute warn_unused_result" were given. Just casting the
+    result to (void) does not stop the warnings; a more elaborate fudge is
+    needed. I've used a macro to implement this.
+
+7.  Minor change to pcretest.c to avoid a compiler warning.
+
+8.  Added four artifical Unicode properties to help with an option to make
+    \s etc use properties (see next item). The new properties are: Xan
+    (alphanumeric), Xsp (Perl space), Xps (POSIX space), and Xwd (word).
+
+9.  Added PCRE_UCP to make \b, \d, \s, \w, and certain POSIX character classes
+    use Unicode properties. (*UCP) at the start of a pattern can be used to set
+    this option. Modified pcretest to add /W to test this facility. Added
+    REG_UCP to make it available via the POSIX interface.
+
+10. Added --line-buffered to pcregrep.
+
+11. In UTF-8 mode, if a pattern that was compiled with PCRE_CASELESS was
+    studied, and the match started with a letter with a code point greater than
+    127 whose first byte was different to the first byte of the other case of
+    the letter, the other case of this starting letter was not recognized
+    (#976).
+
+12. If a pattern that was studied started with a repeated Unicode property
+    test, for example, \p{Nd}+, there was the theoretical possibility of
+    setting up an incorrect bitmap of starting bytes, but fortunately it could
+    not have actually happened in practice until change 8 above was made (it
+    added property types that matched character-matching opcodes).
+
+13. pcre_study() now recognizes \h, \v, and \R when constructing a bit map of
+    possible starting bytes for non-anchored patterns.
+
+14. Extended the "auto-possessify" feature of pcre_compile(). It now recognizes
+    \R, and also a number of cases that involve Unicode properties, both
+    explicit and implicit when PCRE_UCP is set.
+
+15. If a repeated Unicode property match (e.g. \p{Lu}*) was used with non-UTF-8
+    input, it could crash or give wrong results if characters with values
+    greater than 0xc0 were present in the subject string. (Detail: it assumed
+    UTF-8 input when processing these items.)
+
+16. Added a lot of (int) casts to avoid compiler warnings in systems where
+    size_t is 64-bit (#991).
+
+17. Added a check for running out of memory when PCRE is compiled with
+    --disable-stack-for-recursion (#990).
+
+18. If the last data line in a file for pcretest does not have a newline on
+    the end, a newline was missing in the output.
+
+19. The default pcre_chartables.c file recognizes only ASCII characters (values
+    less than 128) in its various bitmaps. However, there is a facility for
+    generating tables according to the current locale when PCRE is compiled. It
+    turns out that in some environments, 0x85 and 0xa0, which are Unicode space
+    characters, are recognized by isspace() and therefore were getting set in
+    these tables, and indeed these tables seem to approximate to ISO 8859. This
+    caused a problem in UTF-8 mode when pcre_study() was used to create a list
+    of bytes that can start a match. For \s, it was including 0x85 and 0xa0,
+    which of course cannot start UTF-8 characters. I have changed the code so
+    that only real ASCII characters (less than 128) and the correct starting
+    bytes for UTF-8 encodings are set for characters greater than 127 when in
+    UTF-8 mode. (When PCRE_UCP is set - see 9 above - the code is different
+    altogether.)
+
+20. Added the /T option to pcretest so as to be able to run tests with non-
+    standard character tables, thus making it possible to include the tests
+    used for 19 above in the standard set of tests.
+
+21. A pattern such as (?&t)(?#()(?(DEFINE)(?<t>a)) which has a forward
+    reference to a subpattern the other side of a comment that contains an
+    opening parenthesis caused either an internal compiling error, or a
+    reference to the wrong subpattern.
+
+
+Version 8.02 19-Mar-2010
+------------------------
+
+1.  The Unicode data tables have been updated to Unicode 5.2.0.
+
+2.  Added the option --libs-cpp to pcre-config, but only when C++ support is
+    configured.
+
+3.  Updated the licensing terms in the pcregexp.pas file, as agreed with the
+    original author of that file, following a query about its status.
+
+4.  On systems that do not have stdint.h (e.g. Solaris), check for and include
+    inttypes.h instead. This fixes a bug that was introduced by change 8.01/8.
+
+5.  A pattern such as (?&t)*+(?(DEFINE)(?<t>.)) which has a possessive
+    quantifier applied to a forward-referencing subroutine call, could compile
+    incorrect code or give the error "internal error: previously-checked
+    referenced subpattern not found".
+
+6.  Both MS Visual Studio and Symbian OS have problems with initializing
+    variables to point to external functions. For these systems, therefore,
+    pcre_malloc etc. are now initialized to local functions that call the
+    relevant global functions.
+
+7.  There were two entries missing in the vectors called coptable and poptable
+    in pcre_dfa_exec.c. This could lead to memory accesses outsize the vectors.
+    I've fixed the data, and added a kludgy way of testing at compile time that
+    the lengths are correct (equal to the number of opcodes).
+
+8.  Following on from 7, I added a similar kludge to check the length of the
+    eint vector in pcreposix.c.
+
+9.  Error texts for pcre_compile() are held as one long string to avoid too
+    much relocation at load time. To find a text, the string is searched,
+    counting zeros. There was no check for running off the end of the string,
+    which could happen if a new error number was added without updating the
+    string.
+
+10. \K gave a compile-time error if it appeared in a lookbehind assersion.
+
+11. \K was not working if it appeared in an atomic group or in a group that
+    was called as a "subroutine", or in an assertion. Perl 5.11 documents that
+    \K is "not well defined" if used in an assertion. PCRE now accepts it if
+    the assertion is positive, but not if it is negative.
+
+12. Change 11 fortuitously reduced the size of the stack frame used in the
+    "match()" function of pcre_exec.c by one pointer. Forthcoming
+    implementation of support for (*MARK) will need an extra pointer on the
+    stack; I have reserved it now, so that the stack frame size does not
+    decrease.
+
+13. A pattern such as (?P<L1>(?P<L2>0)|(?P>L2)(?P>L1)) in which the only other
+    item in branch that calls a recursion is a subroutine call - as in the
+    second branch in the above example - was incorrectly given the compile-
+    time error "recursive call could loop indefinitely" because pcre_compile()
+    was not correctly checking the subroutine for matching a non-empty string.
+
+14. The checks for overrunning compiling workspace could trigger after an
+    overrun had occurred. This is a "should never occur" error, but it can be
+    triggered by pathological patterns such as hundreds of nested parentheses.
+    The checks now trigger 100 bytes before the end of the workspace.
+
+15. Fix typo in configure.ac: "srtoq" should be "strtoq".
+
+
+Version 8.01 19-Jan-2010
+------------------------
+
+1.  If a pattern contained a conditional subpattern with only one branch (in
+    particular, this includes all (*DEFINE) patterns), a call to pcre_study()
+    computed the wrong minimum data length (which is of course zero for such
+    subpatterns). This could cause incorrect "no match" results.
+
+2.  For patterns such as (?i)a(?-i)b|c where an option setting at the start of
+    the pattern is reset in the first branch, pcre_compile() failed with
+    "internal error: code overflow at offset...". This happened only when
+    the reset was to the original external option setting. (An optimization
+    abstracts leading options settings into an external setting, which was the
+    cause of this.)
+
+3.  A pattern such as ^(?!a(*SKIP)b) where a negative assertion contained one
+    of the verbs SKIP, PRUNE, or COMMIT, did not work correctly. When the
+    assertion pattern did not match (meaning that the assertion was true), it
+    was incorrectly treated as false if the SKIP had been reached during the
+    matching. This also applied to assertions used as conditions.
+
+4.  If an item that is not supported by pcre_dfa_exec() was encountered in an
+    assertion subpattern, including such a pattern used as a condition,
+    unpredictable results occurred, instead of the error return
+    PCRE_ERROR_DFA_UITEM.
+
+5.  The C++ GlobalReplace function was not working like Perl for the special
+    situation when an empty string is matched. It now does the fancy magic
+    stuff that is necessary.
+
+6.  In pcre_internal.h, obsolete includes to setjmp.h and stdarg.h have been
+    removed. (These were left over from very, very early versions of PCRE.)
+
+7.  Some cosmetic changes to the code to make life easier when compiling it
+    as part of something else:
+
+    (a) Change DEBUG to PCRE_DEBUG.
+
+    (b) In pcre_compile(), rename the member of the "branch_chain" structure
+        called "current" as "current_branch", to prevent a collision with the
+        Linux macro when compiled as a kernel module.
+
+    (c) In pcre_study(), rename the function set_bit() as set_table_bit(), to
+        prevent a collision with the Linux macro when compiled as a kernel
+        module.
+
+8.  In pcre_compile() there are some checks for integer overflows that used to
+    cast potentially large values to (double). This has been changed to that
+    when building, a check for int64_t is made, and if it is found, it is used
+    instead, thus avoiding the use of floating point arithmetic. (There is no
+    other use of FP in PCRE.) If int64_t is not found, the fallback is to
+    double.
+
+9.  Added two casts to avoid signed/unsigned warnings from VS Studio Express
+    2005 (difference between two addresses compared to an unsigned value).
+
+10. Change the standard AC_CHECK_LIB test for libbz2 in configure.ac to a
+    custom one, because of the following reported problem in Windows:
+
+      - libbz2 uses the Pascal calling convention (WINAPI) for the functions
+          under Win32.
+      - The standard autoconf AC_CHECK_LIB fails to include "bzlib.h",
+          therefore missing the function definition.
+      - The compiler thus generates a "C" signature for the test function.
+      - The linker fails to find the "C" function.
+      - PCRE fails to configure if asked to do so against libbz2.
+
+11. When running libtoolize from libtool-2.2.6b as part of autogen.sh, these
+    messages were output:
+
+      Consider adding `AC_CONFIG_MACRO_DIR([m4])' to configure.ac and
+      rerunning libtoolize, to keep the correct libtool macros in-tree.
+      Consider adding `-I m4' to ACLOCAL_AMFLAGS in Makefile.am.
+
+    I have done both of these things.
+
+12. Although pcre_dfa_exec() does not use nearly as much stack as pcre_exec()
+    most of the time, it *can* run out if it is given a pattern that contains a
+    runaway infinite recursion. I updated the discussion in the pcrestack man
+    page.
+
+13. Now that we have gone to the x.xx style of version numbers, the minor
+    version may start with zero. Using 08 or 09 is a bad idea because users
+    might check the value of PCRE_MINOR in their code, and 08 or 09 may be
+    interpreted as invalid octal numbers. I've updated the previous comment in
+    configure.ac, and also added a check that gives an error if 08 or 09 are
+    used.
+
+14. Change 8.00/11 was not quite complete: code had been accidentally omitted,
+    causing partial matching to fail when the end of the subject matched \W
+    in a UTF-8 pattern where \W was quantified with a minimum of 3.
+
+15. There were some discrepancies between the declarations in pcre_internal.h
+    of _pcre_is_newline(), _pcre_was_newline(), and _pcre_valid_utf8() and
+    their definitions. The declarations used "const uschar *" and the
+    definitions used USPTR. Even though USPTR is normally defined as "const
+    unsigned char *" (and uschar is typedeffed as "unsigned char"), it was
+    reported that: "This difference in casting confuses some C++ compilers, for
+    example, SunCC recognizes above declarations as different functions and
+    generates broken code for hbpcre." I have changed the declarations to use
+    USPTR.
+
+16. GNU libtool is named differently on some systems. The autogen.sh script now
+    tries several variants such as glibtoolize (MacOSX) and libtoolize1x
+    (FreeBSD).
+
+17. Applied Craig's patch that fixes an HP aCC compile error in pcre 8.00
+    (strtoXX undefined when compiling pcrecpp.cc). The patch contains this
+    comment: "Figure out how to create a longlong from a string: strtoll and
+    equivalent. It's not enough to call AC_CHECK_FUNCS: hpux has a strtoll, for
+    instance, but it only takes 2 args instead of 3!"
+
+18. A subtle bug concerned with back references has been fixed by a change of
+    specification, with a corresponding code fix. A pattern such as
+    ^(xa|=?\1a)+$ which contains a back reference inside the group to which it
+    refers, was giving matches when it shouldn't. For example, xa=xaaa would
+    match that pattern. Interestingly, Perl (at least up to 5.11.3) has the
+    same bug. Such groups have to be quantified to be useful, or contained
+    inside another quantified group. (If there's no repetition, the reference
+    can never match.) The problem arises because, having left the group and
+    moved on to the rest of the pattern, a later failure that backtracks into
+    the group uses the captured value from the final iteration of the group
+    rather than the correct earlier one. I have fixed this in PCRE by forcing
+    any group that contains a reference to itself to be an atomic group; that
+    is, there cannot be any backtracking into it once it has completed. This is
+    similar to recursive and subroutine calls.
+
+
+Version 8.00 19-Oct-09
+----------------------
+
+1.  The table for translating pcre_compile() error codes into POSIX error codes
+    was out-of-date, and there was no check on the pcre_compile() error code
+    being within the table. This could lead to an OK return being given in
+    error.
+
+2.  Changed the call to open a subject file in pcregrep from fopen(pathname,
+    "r") to fopen(pathname, "rb"), which fixed a problem with some of the tests
+    in a Windows environment.
+
+3.  The pcregrep --count option prints the count for each file even when it is
+    zero, as does GNU grep. However, pcregrep was also printing all files when
+    --files-with-matches was added. Now, when both options are given, it prints
+    counts only for those files that have at least one match. (GNU grep just
+    prints the file name in this circumstance, but including the count seems
+    more useful - otherwise, why use --count?) Also ensured that the
+    combination -clh just lists non-zero counts, with no names.
+
+4.  The long form of the pcregrep -F option was incorrectly implemented as
+    --fixed_strings instead of --fixed-strings. This is an incompatible change,
+    but it seems right to fix it, and I didn't think it was worth preserving
+    the old behaviour.
+
+5.  The command line items --regex=pattern and --regexp=pattern were not
+    recognized by pcregrep, which required --regex pattern or --regexp pattern
+    (with a space rather than an '='). The man page documented the '=' forms,
+    which are compatible with GNU grep; these now work.
+
+6.  No libpcreposix.pc file was created for pkg-config; there was just
+    libpcre.pc and libpcrecpp.pc. The omission has been rectified.
+
+7.  Added #ifndef SUPPORT_UCP into the pcre_ucd.c module, to reduce its size
+    when UCP support is not needed, by modifying the Python script that
+    generates it from Unicode data files. This should not matter if the module
+    is correctly used as a library, but I received one complaint about 50K of
+    unwanted data. My guess is that the person linked everything into his
+    program rather than using a library. Anyway, it does no harm.
+
+8.  A pattern such as /\x{123}{2,2}+/8 was incorrectly compiled; the trigger
+    was a minimum greater than 1 for a wide character in a possessive
+    repetition. The same bug could also affect patterns like /(\x{ff}{0,2})*/8
+    which had an unlimited repeat of a nested, fixed maximum repeat of a wide
+    character. Chaos in the form of incorrect output or a compiling loop could
+    result.
+
+9.  The restrictions on what a pattern can contain when partial matching is
+    requested for pcre_exec() have been removed. All patterns can now be
+    partially matched by this function. In addition, if there are at least two
+    slots in the offset vector, the offset of the earliest inspected character
+    for the match and the offset of the end of the subject are set in them when
+    PCRE_ERROR_PARTIAL is returned.
+
+10. Partial matching has been split into two forms: PCRE_PARTIAL_SOFT, which is
+    synonymous with PCRE_PARTIAL, for backwards compatibility, and
+    PCRE_PARTIAL_HARD, which causes a partial match to supersede a full match,
+    and may be more useful for multi-segment matching.
+
+11. Partial matching with pcre_exec() is now more intuitive. A partial match
+    used to be given if ever the end of the subject was reached; now it is
+    given only if matching could not proceed because another character was
+    needed. This makes a difference in some odd cases such as Z(*FAIL) with the
+    string "Z", which now yields "no match" instead of "partial match". In the
+    case of pcre_dfa_exec(), "no match" is given if every matching path for the
+    final character ended with (*FAIL).
+
+12. Restarting a match using pcre_dfa_exec() after a partial match did not work
+    if the pattern had a "must contain" character that was already found in the
+    earlier partial match, unless partial matching was again requested. For
+    example, with the pattern /dog.(body)?/, the "must contain" character is
+    "g". If the first part-match was for the string "dog", restarting with
+    "sbody" failed. This bug has been fixed.
+
+13. The string returned by pcre_dfa_exec() after a partial match has been
+    changed so that it starts at the first inspected character rather than the
+    first character of the match. This makes a difference only if the pattern
+    starts with a lookbehind assertion or \b or \B (\K is not supported by
+    pcre_dfa_exec()). It's an incompatible change, but it makes the two
+    matching functions compatible, and I think it's the right thing to do.
+
+14. Added a pcredemo man page, created automatically from the pcredemo.c file,
+    so that the demonstration program is easily available in environments where
+    PCRE has not been installed from source.
+
+15. Arranged to add -DPCRE_STATIC to cflags in libpcre.pc, libpcreposix.cp,
+    libpcrecpp.pc and pcre-config when PCRE is not compiled as a shared
+    library.
+
+16. Added REG_UNGREEDY to the pcreposix interface, at the request of a user.
+    It maps to PCRE_UNGREEDY. It is not, of course, POSIX-compatible, but it
+    is not the first non-POSIX option to be added. Clearly some people find
+    these options useful.
+
+17. If a caller to the POSIX matching function regexec() passes a non-zero
+    value for nmatch with a NULL value for pmatch, the value of
+    nmatch is forced to zero.
+
+18. RunGrepTest did not have a test for the availability of the -u option of
+    the diff command, as RunTest does. It now checks in the same way as
+    RunTest, and also checks for the -b option.
+
+19. If an odd number of negated classes containing just a single character
+    interposed, within parentheses, between a forward reference to a named
+    subpattern and the definition of the subpattern, compilation crashed with
+    an internal error, complaining that it could not find the referenced
+    subpattern. An example of a crashing pattern is /(?&A)(([^m])(?<A>))/.
+    [The bug was that it was starting one character too far in when skipping
+    over the character class, thus treating the ] as data rather than
+    terminating the class. This meant it could skip too much.]
+
+20. Added PCRE_NOTEMPTY_ATSTART in order to be able to correctly implement the
+    /g option in pcretest when the pattern contains \K, which makes it possible
+    to have an empty string match not at the start, even when the pattern is
+    anchored. Updated pcretest and pcredemo to use this option.
+
+21. If the maximum number of capturing subpatterns in a recursion was greater
+    than the maximum at the outer level, the higher number was returned, but
+    with unset values at the outer level. The correct (outer level) value is
+    now given.
+
+22. If (*ACCEPT) appeared inside capturing parentheses, previous releases of
+    PCRE did not set those parentheses (unlike Perl). I have now found a way to
+    make it do so. The string so far is captured, making this feature
+    compatible with Perl.
+
+23. The tests have been re-organized, adding tests 11 and 12, to make it
+    possible to check the Perl 5.10 features against Perl 5.10.
+
+24. Perl 5.10 allows subroutine calls in lookbehinds, as long as the subroutine
+    pattern matches a fixed length string. PCRE did not allow this; now it
+    does. Neither allows recursion.
+
+25. I finally figured out how to implement a request to provide the minimum
+    length of subject string that was needed in order to match a given pattern.
+    (It was back references and recursion that I had previously got hung up
+    on.) This code has now been added to pcre_study(); it finds a lower bound
+    to the length of subject needed. It is not necessarily the greatest lower
+    bound, but using it to avoid searching strings that are too short does give
+    some useful speed-ups. The value is available to calling programs via
+    pcre_fullinfo().
+
+26. While implementing 25, I discovered to my embarrassment that pcretest had
+    not been passing the result of pcre_study() to pcre_dfa_exec(), so the
+    study optimizations had never been tested with that matching function.
+    Oops. What is worse, even when it was passed study data, there was a bug in
+    pcre_dfa_exec() that meant it never actually used it. Double oops. There
+    were also very few tests of studied patterns with pcre_dfa_exec().
+
+27. If (?| is used to create subpatterns with duplicate numbers, they are now
+    allowed to have the same name, even if PCRE_DUPNAMES is not set. However,
+    on the other side of the coin, they are no longer allowed to have different
+    names, because these cannot be distinguished in PCRE, and this has caused
+    confusion. (This is a difference from Perl.)
+
+28. When duplicate subpattern names are present (necessarily with different
+    numbers, as required by 27 above), and a test is made by name in a
+    conditional pattern, either for a subpattern having been matched, or for
+    recursion in such a pattern, all the associated numbered subpatterns are
+    tested, and the overall condition is true if the condition is true for any
+    one of them. This is the way Perl works, and is also more like the way
+    testing by number works.
+
+
+Version 7.9 11-Apr-09
+---------------------
+
+1.  When building with support for bzlib/zlib (pcregrep) and/or readline
+    (pcretest), all targets were linked against these libraries. This included
+    libpcre, libpcreposix, and libpcrecpp, even though they do not use these
+    libraries. This caused unwanted dependencies to be created. This problem
+    has been fixed, and now only pcregrep is linked with bzlib/zlib and only
+    pcretest is linked with readline.
+
+2.  The "typedef int BOOL" in pcre_internal.h that was included inside the
+    "#ifndef FALSE" condition by an earlier change (probably 7.8/18) has been
+    moved outside it again, because FALSE and TRUE are already defined in AIX,
+    but BOOL is not.
+
+3.  The pcre_config() function was treating the PCRE_MATCH_LIMIT and
+    PCRE_MATCH_LIMIT_RECURSION values as ints, when they should be long ints.
+
+4.  The pcregrep documentation said spaces were inserted as well as colons (or
+    hyphens) following file names and line numbers when outputting matching
+    lines. This is not true; no spaces are inserted. I have also clarified the
+    wording for the --colour (or --color) option.
+
+5.  In pcregrep, when --colour was used with -o, the list of matching strings
+    was not coloured; this is different to GNU grep, so I have changed it to be
+    the same.
+
+6.  When --colo(u)r was used in pcregrep, only the first matching substring in
+    each matching line was coloured. Now it goes on to look for further matches
+    of any of the test patterns, which is the same behaviour as GNU grep.
+
+7.  A pattern that could match an empty string could cause pcregrep to loop; it
+    doesn't make sense to accept an empty string match in pcregrep, so I have
+    locked it out (using PCRE's PCRE_NOTEMPTY option). By experiment, this
+    seems to be how GNU grep behaves.
+
+8.  The pattern (?(?=.*b)b|^) was incorrectly compiled as "match must be at
+    start or after a newline", because the conditional assertion was not being
+    correctly handled. The rule now is that both the assertion and what follows
+    in the first alternative must satisfy the test.
+
+9.  If auto-callout was enabled in a pattern with a conditional group whose
+    condition was an assertion, PCRE could crash during matching, both with
+    pcre_exec() and pcre_dfa_exec().
+
+10. The PCRE_DOLLAR_ENDONLY option was not working when pcre_dfa_exec() was
+    used for matching.
+
+11. Unicode property support in character classes was not working for
+    characters (bytes) greater than 127 when not in UTF-8 mode.
+
+12. Added the -M command line option to pcretest.
+
+14. Added the non-standard REG_NOTEMPTY option to the POSIX interface.
+
+15. Added the PCRE_NO_START_OPTIMIZE match-time option.
+
+16. Added comments and documentation about mis-use of no_arg in the C++
+    wrapper.
+
+17. Implemented support for UTF-8 encoding in EBCDIC environments, a patch
+    from Martin Jerabek that uses macro names for all relevant character and
+    string constants.
+
+18. Added to pcre_internal.h two configuration checks: (a) If both EBCDIC and
+    SUPPORT_UTF8 are set, give an error; (b) If SUPPORT_UCP is set without
+    SUPPORT_UTF8, define SUPPORT_UTF8. The "configure" script handles both of
+    these, but not everybody uses configure.
+
+19. A conditional group that had only one branch was not being correctly
+    recognized as an item that could match an empty string. This meant that an
+    enclosing group might also not be so recognized, causing infinite looping
+    (and probably a segfault) for patterns such as ^"((?(?=[a])[^"])|b)*"$
+    with the subject "ab", where knowledge that the repeated group can match
+    nothing is needed in order to break the loop.
+
+20. If a pattern that was compiled with callouts was matched using pcre_dfa_
+    exec(), but without supplying a callout function, matching went wrong.
+
+21. If PCRE_ERROR_MATCHLIMIT occurred during a recursion, there was a memory
+    leak if the size of the offset vector was greater than 30. When the vector
+    is smaller, the saved offsets during recursion go onto a local stack
+    vector, but for larger vectors malloc() is used. It was failing to free
+    when the recursion yielded PCRE_ERROR_MATCH_LIMIT (or any other "abnormal"
+    error, in fact).
+
+22. There was a missing #ifdef SUPPORT_UTF8 round one of the variables in the
+    heapframe that is used only when UTF-8 support is enabled. This caused no
+    problem, but was untidy.
+
+23. Steven Van Ingelgem's patch to CMakeLists.txt to change the name
+    CMAKE_BINARY_DIR to PROJECT_BINARY_DIR so that it works when PCRE is
+    included within another project.
+
+24. Steven Van Ingelgem's patches to add more options to the CMake support,
+    slightly modified by me:
+
+      (a) PCRE_BUILD_TESTS can be set OFF not to build the tests, including
+          not building pcregrep.
+
+      (b) PCRE_BUILD_PCREGREP can be see OFF not to build pcregrep, but only
+          if PCRE_BUILD_TESTS is also set OFF, because the tests use pcregrep.
+
+25. Forward references, both numeric and by name, in patterns that made use of
+    duplicate group numbers, could behave incorrectly or give incorrect errors,
+    because when scanning forward to find the reference group, PCRE was not
+    taking into account the duplicate group numbers. A pattern such as
+    ^X(?3)(a)(?|(b)|(q))(Y) is an example.
+
+26. Changed a few more instances of "const unsigned char *" to USPTR, making
+    the feature of a custom pointer more persuasive (as requested by a user).
+
+27. Wrapped the definitions of fileno and isatty for Windows, which appear in
+    pcretest.c, inside #ifndefs, because it seems they are sometimes already
+    pre-defined.
+
+28. Added support for (*UTF8) at the start of a pattern.
+
+29. Arrange for flags added by the "release type" setting in CMake to be shown
+    in the configuration summary.
+
+
+Version 7.8 05-Sep-08
+---------------------
+
+1.  Replaced UCP searching code with optimized version as implemented for Ad
+    Muncher (http://www.admuncher.com/) by Peter Kankowski. This uses a two-
+    stage table and inline lookup instead of a function, giving speed ups of 2
+    to 5 times on some simple patterns that I tested. Permission was given to
+    distribute the MultiStage2.py script that generates the tables (it's not in
+    the tarball, but is in the Subversion repository).
+
+2.  Updated the Unicode datatables to Unicode 5.1.0. This adds yet more
+    scripts.
+
+3.  Change 12 for 7.7 introduced a bug in pcre_study() when a pattern contained
+    a group with a zero qualifier. The result of the study could be incorrect,
+    or the function might crash, depending on the pattern.
+
+4.  Caseless matching was not working for non-ASCII characters in back
+    references. For example, /(\x{de})\1/8i was not matching \x{de}\x{fe}.
+    It now works when Unicode Property Support is available.
+
+5.  In pcretest, an escape such as \x{de} in the data was always generating
+    a UTF-8 string, even in non-UTF-8 mode. Now it generates a single byte in
+    non-UTF-8 mode. If the value is greater than 255, it gives a warning about
+    truncation.
+
+6.  Minor bugfix in pcrecpp.cc (change "" == ... to NULL == ...).
+
+7.  Added two (int) casts to pcregrep when printing the difference of two
+    pointers, in case they are 64-bit values.
+
+8.  Added comments about Mac OS X stack usage to the pcrestack man page and to
+    test 2 if it fails.
+
+9.  Added PCRE_CALL_CONVENTION just before the names of all exported functions,
+    and a #define of that name to empty if it is not externally set. This is to
+    allow users of MSVC to set it if necessary.
+
+10. The PCRE_EXP_DEFN macro which precedes exported functions was missing from
+    the convenience functions in the pcre_get.c source file.
+
+11. An option change at the start of a pattern that had top-level alternatives
+    could cause overwriting and/or a crash. This command provoked a crash in
+    some environments:
+
+      printf "/(?i)[\xc3\xa9\xc3\xbd]|[\xc3\xa9\xc3\xbdA]/8\n" | pcretest
+
+    This potential security problem was recorded as CVE-2008-2371.
+
+12. For a pattern where the match had to start at the beginning or immediately
+    after a newline (e.g /.*anything/ without the DOTALL flag), pcre_exec() and
+    pcre_dfa_exec() could read past the end of the passed subject if there was
+    no match. To help with detecting such bugs (e.g. with valgrind), I modified
+    pcretest so that it places the subject at the end of its malloc-ed buffer.
+
+13. The change to pcretest in 12 above threw up a couple more cases when pcre_
+    exec() might read past the end of the data buffer in UTF-8 mode.
+
+14. A similar bug to 7.3/2 existed when the PCRE_FIRSTLINE option was set and
+    the data contained the byte 0x85 as part of a UTF-8 character within its
+    first line. This applied both to normal and DFA matching.
+
+15. Lazy qualifiers were not working in some cases in UTF-8 mode. For example,
+    /^[^d]*?$/8 failed to match "abc".
+
+16. Added a missing copyright notice to pcrecpp_internal.h.
+
+17. Make it more clear in the documentation that values returned from
+    pcre_exec() in ovector are byte offsets, not character counts.
+
+18. Tidied a few places to stop certain compilers from issuing warnings.
+
+19. Updated the Virtual Pascal + BCC files to compile the latest v7.7, as
+    supplied by Stefan Weber. I made a further small update for 7.8 because
+    there is a change of source arrangements: the pcre_searchfuncs.c module is
+    replaced by pcre_ucd.c.
+
+
+Version 7.7 07-May-08
+---------------------
+
+1.  Applied Craig's patch to sort out a long long problem: "If we can't convert
+    a string to a long long, pretend we don't even have a long long." This is
+    done by checking for the strtoq, strtoll, and _strtoi64 functions.
+
+2.  Applied Craig's patch to pcrecpp.cc to restore ABI compatibility with
+    pre-7.6 versions, which defined a global no_arg variable instead of putting
+    it in the RE class. (See also #8 below.)
+
+3.  Remove a line of dead code, identified by coverity and reported by Nuno
+    Lopes.
+
+4.  Fixed two related pcregrep bugs involving -r with --include or --exclude:
+
+    (1) The include/exclude patterns were being applied to the whole pathnames
+        of files, instead of just to the final components.
+
+    (2) If there was more than one level of directory, the subdirectories were
+        skipped unless they satisfied the include/exclude conditions. This is
+        inconsistent with GNU grep (and could even be seen as contrary to the
+        pcregrep specification - which I improved to make it absolutely clear).
+        The action now is always to scan all levels of directory, and just
+        apply the include/exclude patterns to regular files.
+
+5.  Added the --include_dir and --exclude_dir patterns to pcregrep, and used
+    --exclude_dir in the tests to avoid scanning .svn directories.
+
+6.  Applied Craig's patch to the QuoteMeta function so that it escapes the
+    NUL character as backslash + 0 rather than backslash + NUL, because PCRE
+    doesn't support NULs in patterns.
+
+7.  Added some missing "const"s to declarations of static tables in
+    pcre_compile.c and pcre_dfa_exec.c.
+
+8.  Applied Craig's patch to pcrecpp.cc to fix a problem in OS X that was
+    caused by fix #2  above. (Subsequently also a second patch to fix the
+    first patch. And a third patch - this was a messy problem.)
+
+9.  Applied Craig's patch to remove the use of push_back().
+
+10. Applied Alan Lehotsky's patch to add REG_STARTEND support to the POSIX
+    matching function regexec().
+
+11. Added support for the Oniguruma syntax \g<name>, \g<n>, \g'name', \g'n',
+    which, however, unlike Perl's \g{...}, are subroutine calls, not back
+    references. PCRE supports relative numbers with this syntax (I don't think
+    Oniguruma does).
+
+12. Previously, a group with a zero repeat such as (...){0} was completely
+    omitted from the compiled regex. However, this means that if the group
+    was called as a subroutine from elsewhere in the pattern, things went wrong
+    (an internal error was given). Such groups are now left in the compiled
+    pattern, with a new opcode that causes them to be skipped at execution
+    time.
+
+13. Added the PCRE_JAVASCRIPT_COMPAT option. This makes the following changes
+    to the way PCRE behaves:
+
+    (a) A lone ] character is dis-allowed (Perl treats it as data).
+
+    (b) A back reference to an unmatched subpattern matches an empty string
+        (Perl fails the current match path).
+
+    (c) A data ] in a character class must be notated as \] because if the
+        first data character in a class is ], it defines an empty class. (In
+        Perl it is not possible to have an empty class.) The empty class []
+        never matches; it forces failure and is equivalent to (*FAIL) or (?!).
+        The negative empty class [^] matches any one character, independently
+        of the DOTALL setting.
+
+14. A pattern such as /(?2)[]a()b](abc)/ which had a forward reference to a
+    non-existent subpattern following a character class starting with ']' and
+    containing () gave an internal compiling error instead of "reference to
+    non-existent subpattern". Fortunately, when the pattern did exist, the
+    compiled code was correct. (When scanning forwards to check for the
+    existencd of the subpattern, it was treating the data ']' as terminating
+    the class, so got the count wrong. When actually compiling, the reference
+    was subsequently set up correctly.)
+
+15. The "always fail" assertion (?!) is optimzed to (*FAIL) by pcre_compile;
+    it was being rejected as not supported by pcre_dfa_exec(), even though
+    other assertions are supported. I have made pcre_dfa_exec() support
+    (*FAIL).
+
+16. The implementation of 13c above involved the invention of a new opcode,
+    OP_ALLANY, which is like OP_ANY but doesn't check the /s flag. Since /s
+    cannot be changed at match time, I realized I could make a small
+    improvement to matching performance by compiling OP_ALLANY instead of
+    OP_ANY for "." when DOTALL was set, and then removing the runtime tests
+    on the OP_ANY path.
+
+17. Compiling pcretest on Windows with readline support failed without the
+    following two fixes: (1) Make the unistd.h include conditional on
+    HAVE_UNISTD_H; (2) #define isatty and fileno as _isatty and _fileno.
+
+18. Changed CMakeLists.txt and cmake/FindReadline.cmake to arrange for the
+    ncurses library to be included for pcretest when ReadLine support is
+    requested, but also to allow for it to be overridden. This patch came from
+    Daniel Bergström.
+
+19. There was a typo in the file ucpinternal.h where f0_rangeflag was defined
+    as 0x00f00000 instead of 0x00800000. Luckily, this would not have caused
+    any errors with the current Unicode tables. Thanks to Peter Kankowski for
+    spotting this.
+
+
+Version 7.6 28-Jan-08
+---------------------
+
+1.  A character class containing a very large number of characters with
+    codepoints greater than 255 (in UTF-8 mode, of course) caused a buffer
+    overflow.
+
+2.  Patch to cut out the "long long" test in pcrecpp_unittest when
+    HAVE_LONG_LONG is not defined.
+
+3.  Applied Christian Ehrlicher's patch to update the CMake build files to
+    bring them up to date and include new features. This patch includes:
+
+    - Fixed PH's badly added libz and libbz2 support.
+    - Fixed a problem with static linking.
+    - Added pcredemo. [But later removed - see 7 below.]
+    - Fixed dftables problem and added an option.
+    - Added a number of HAVE_XXX tests, including HAVE_WINDOWS_H and
+        HAVE_LONG_LONG.
+    - Added readline support for pcretest.
+    - Added an listing of the option settings after cmake has run.
+
+4.  A user submitted a patch to Makefile that makes it easy to create
+    "pcre.dll" under mingw when using Configure/Make. I added stuff to
+    Makefile.am that cause it to include this special target, without
+    affecting anything else. Note that the same mingw target plus all
+    the other distribution libraries and programs are now supported
+    when configuring with CMake (see 6 below) instead of with
+    Configure/Make.
+
+5.  Applied Craig's patch that moves no_arg into the RE class in the C++ code.
+    This is an attempt to solve the reported problem "pcrecpp::no_arg is not
+    exported in the Windows port". It has not yet been confirmed that the patch
+    solves the problem, but it does no harm.
+
+6.  Applied Sheri's patch to CMakeLists.txt to add NON_STANDARD_LIB_PREFIX and
+    NON_STANDARD_LIB_SUFFIX for dll names built with mingw when configured
+    with CMake, and also correct the comment about stack recursion.
+
+7.  Remove the automatic building of pcredemo from the ./configure system and
+    from CMakeLists.txt. The whole idea of pcredemo.c is that it is an example
+    of a program that users should build themselves after PCRE is installed, so
+    building it automatically is not really right. What is more, it gave
+    trouble in some build environments.
+
+8.  Further tidies to CMakeLists.txt from Sheri and Christian.
+
+
+Version 7.5 10-Jan-08
+---------------------
+
+1.  Applied a patch from Craig: "This patch makes it possible to 'ignore'
+    values in parens when parsing an RE using the C++ wrapper."
+
+2.  Negative specials like \S did not work in character classes in UTF-8 mode.
+    Characters greater than 255 were excluded from the class instead of being
+    included.
+
+3.  The same bug as (2) above applied to negated POSIX classes such as
+    [:^space:].
+
+4.  PCRECPP_STATIC was referenced in pcrecpp_internal.h, but nowhere was it
+    defined or documented. It seems to have been a typo for PCRE_STATIC, so
+    I have changed it.
+
+5.  The construct (?&) was not diagnosed as a syntax error (it referenced the
+    first named subpattern) and a construct such as (?&a) would reference the
+    first named subpattern whose name started with "a" (in other words, the
+    length check was missing). Both these problems are fixed. "Subpattern name
+    expected" is now given for (?&) (a zero-length name), and this patch also
+    makes it give the same error for \k'' (previously it complained that that
+    was a reference to a non-existent subpattern).
+
+6.  The erroneous patterns (?+-a) and (?-+a) give different error messages;
+    this is right because (?- can be followed by option settings as well as by
+    digits. I have, however, made the messages clearer.
+
+7.  Patterns such as (?(1)a|b) (a pattern that contains fewer subpatterns
+    than the number used in the conditional) now cause a compile-time error.
+    This is actually not compatible with Perl, which accepts such patterns, but
+    treats the conditional as always being FALSE (as PCRE used to), but it
+    seems to me that giving a diagnostic is better.
+
+8.  Change "alphameric" to the more common word "alphanumeric" in comments
+    and messages.
+
+9.  Fix two occurrences of "backslash" in comments that should have been
+    "backspace".
+
+10. Remove two redundant lines of code that can never be obeyed (their function
+    was moved elsewhere).
+
+11. The program that makes PCRE's Unicode character property table had a bug
+    which caused it to generate incorrect table entries for sequences of
+    characters that have the same character type, but are in different scripts.
+    It amalgamated them into a single range, with the script of the first of
+    them. In other words, some characters were in the wrong script. There were
+    thirteen such cases, affecting characters in the following ranges:
+
+      U+002b0 - U+002c1
+      U+0060c - U+0060d
+      U+0061e - U+00612
+      U+0064b - U+0065e
+      U+0074d - U+0076d
+      U+01800 - U+01805
+      U+01d00 - U+01d77
+      U+01d9b - U+01dbf
+      U+0200b - U+0200f
+      U+030fc - U+030fe
+      U+03260 - U+0327f
+      U+0fb46 - U+0fbb1
+      U+10450 - U+1049d
+
+12. The -o option (show only the matching part of a line) for pcregrep was not
+    compatible with GNU grep in that, if there was more than one match in a
+    line, it showed only the first of them. It now behaves in the same way as
+    GNU grep.
+
+13. If the -o and -v options were combined for pcregrep, it printed a blank
+    line for every non-matching line. GNU grep prints nothing, and pcregrep now
+    does the same. The return code can be used to tell if there were any
+    non-matching lines.
+
+14. Added --file-offsets and --line-offsets to pcregrep.
+
+15. The pattern (?=something)(?R) was not being diagnosed as a potentially
+    infinitely looping recursion. The bug was that positive lookaheads were not
+    being skipped when checking for a possible empty match (negative lookaheads
+    and both kinds of lookbehind were skipped).
+
+16. Fixed two typos in the Windows-only code in pcregrep.c, and moved the
+    inclusion of <windows.h> to before rather than after the definition of
+    INVALID_FILE_ATTRIBUTES (patch from David Byron).
+
+17. Specifying a possessive quantifier with a specific limit for a Unicode
+    character property caused pcre_compile() to compile bad code, which led at
+    runtime to PCRE_ERROR_INTERNAL (-14). Examples of patterns that caused this
+    are: /\p{Zl}{2,3}+/8 and /\p{Cc}{2}+/8. It was the possessive "+" that
+    caused the error; without that there was no problem.
+
+18. Added --enable-pcregrep-libz and --enable-pcregrep-libbz2.
+
+19. Added --enable-pcretest-libreadline.
+
+20. In pcrecpp.cc, the variable 'count' was incremented twice in
+    RE::GlobalReplace(). As a result, the number of replacements returned was
+    double what it should be. I removed one of the increments, but Craig sent a
+    later patch that removed the other one (the right fix) and added unit tests
+    that check the return values (which was not done before).
+
+21. Several CMake things:
+
+    (1) Arranged that, when cmake is used on Unix, the libraries end up with
+        the names libpcre and libpcreposix, not just pcre and pcreposix.
+
+    (2) The above change means that pcretest and pcregrep are now correctly
+        linked with the newly-built libraries, not previously installed ones.
+
+    (3) Added PCRE_SUPPORT_LIBREADLINE, PCRE_SUPPORT_LIBZ, PCRE_SUPPORT_LIBBZ2.
+
+22. In UTF-8 mode, with newline set to "any", a pattern such as .*a.*=.b.*
+    crashed when matching a string such as a\x{2029}b (note that \x{2029} is a
+    UTF-8 newline character). The key issue is that the pattern starts .*;
+    this means that the match must be either at the beginning, or after a
+    newline. The bug was in the code for advancing after a failed match and
+    checking that the new position followed a newline. It was not taking
+    account of UTF-8 characters correctly.
+
+23. PCRE was behaving differently from Perl in the way it recognized POSIX
+    character classes. PCRE was not treating the sequence [:...:] as a
+    character class unless the ... were all letters. Perl, however, seems to
+    allow any characters between [: and :], though of course it rejects as
+    unknown any "names" that contain non-letters, because all the known class
+    names consist only of letters. Thus, Perl gives an error for [[:1234:]],
+    for example, whereas PCRE did not - it did not recognize a POSIX character
+    class. This seemed a bit dangerous, so the code has been changed to be
+    closer to Perl. The behaviour is not identical to Perl, because PCRE will
+    diagnose an unknown class for, for example, [[:l\ower:]] where Perl will
+    treat it as [[:lower:]]. However, PCRE does now give "unknown" errors where
+    Perl does, and where it didn't before.
+
+24. Rewrite so as to remove the single use of %n from pcregrep because in some
+    Windows environments %n is disabled by default.
+
+
+Version 7.4 21-Sep-07
+---------------------
+
+1.  Change 7.3/28 was implemented for classes by looking at the bitmap. This
+    means that a class such as [\s] counted as "explicit reference to CR or
+    LF". That isn't really right - the whole point of the change was to try to
+    help when there was an actual mention of one of the two characters. So now
+    the change happens only if \r or \n (or a literal CR or LF) character is
+    encountered.
+
+2.  The 32-bit options word was also used for 6 internal flags, but the numbers
+    of both had grown to the point where there were only 3 bits left.
+    Fortunately, there was spare space in the data structure, and so I have
+    moved the internal flags into a new 16-bit field to free up more option
+    bits.
+
+3.  The appearance of (?J) at the start of a pattern set the DUPNAMES option,
+    but did not set the internal JCHANGED flag - either of these is enough to
+    control the way the "get" function works - but the PCRE_INFO_JCHANGED
+    facility is supposed to tell if (?J) was ever used, so now (?J) at the
+    start sets both bits.
+
+4.  Added options (at build time, compile time, exec time) to change \R from
+    matching any Unicode line ending sequence to just matching CR, LF, or CRLF.
+
+5.  doc/pcresyntax.html was missing from the distribution.
+
+6.  Put back the definition of PCRE_ERROR_NULLWSLIMIT, for backward
+    compatibility, even though it is no longer used.
+
+7.  Added macro for snprintf to pcrecpp_unittest.cc and also for strtoll and
+    strtoull to pcrecpp.cc to select the available functions in WIN32 when the
+    windows.h file is present (where different names are used). [This was
+    reversed later after testing - see 16 below.]
+
+8.  Changed all #include <config.h> to #include "config.h". There were also
+    some further <pcre.h> cases that I changed to "pcre.h".
+
+9.  When pcregrep was used with the --colour option, it missed the line ending
+    sequence off the lines that it output.
+
+10. It was pointed out to me that arrays of string pointers cause lots of
+    relocations when a shared library is dynamically loaded. A technique of
+    using a single long string with a table of offsets can drastically reduce
+    these. I have refactored PCRE in four places to do this. The result is
+    dramatic:
+
+      Originally:                          290
+      After changing UCP table:            187
+      After changing error message table:   43
+      After changing table of "verbs"       36
+      After changing table of Posix names   22
+
+    Thanks to the folks working on Gregex for glib for this insight.
+
+11. --disable-stack-for-recursion caused compiling to fail unless -enable-
+    unicode-properties was also set.
+
+12. Updated the tests so that they work when \R is defaulted to ANYCRLF.
+
+13. Added checks for ANY and ANYCRLF to pcrecpp.cc where it previously
+    checked only for CRLF.
+
+14. Added casts to pcretest.c to avoid compiler warnings.
+
+15. Added Craig's patch to various pcrecpp modules to avoid compiler warnings.
+
+16. Added Craig's patch to remove the WINDOWS_H tests, that were not working,
+    and instead check for _strtoi64 explicitly, and avoid the use of snprintf()
+    entirely. This removes changes made in 7 above.
+
+17. The CMake files have been updated, and there is now more information about
+    building with CMake in the NON-UNIX-USE document.
+
+
+Version 7.3 28-Aug-07
+---------------------
+
+ 1. In the rejigging of the build system that eventually resulted in 7.1, the
+    line "#include <pcre.h>" was included in pcre_internal.h. The use of angle
+    brackets there is not right, since it causes compilers to look for an
+    installed pcre.h, not the version that is in the source that is being
+    compiled (which of course may be different). I have changed it back to:
+
+      #include "pcre.h"
+
+    I have a vague recollection that the change was concerned with compiling in
+    different directories, but in the new build system, that is taken care of
+    by the VPATH setting the Makefile.
+
+ 2. The pattern .*$ when run in not-DOTALL UTF-8 mode with newline=any failed
+    when the subject happened to end in the byte 0x85 (e.g. if the last
+    character was \x{1ec5}). *Character* 0x85 is one of the "any" newline
+    characters but of course it shouldn't be taken as a newline when it is part
+    of another character. The bug was that, for an unlimited repeat of . in
+    not-DOTALL UTF-8 mode, PCRE was advancing by bytes rather than by
+    characters when looking for a newline.
+
+ 3. A small performance improvement in the DOTALL UTF-8 mode .* case.
+
+ 4. Debugging: adjusted the names of opcodes for different kinds of parentheses
+    in debug output.
+
+ 5. Arrange to use "%I64d" instead of "%lld" and "%I64u" instead of "%llu" for
+    long printing in the pcrecpp unittest when running under MinGW.
+
+ 6. ESC_K was left out of the EBCDIC table.
+
+ 7. Change 7.0/38 introduced a new limit on the number of nested non-capturing
+    parentheses; I made it 1000, which seemed large enough. Unfortunately, the
+    limit also applies to "virtual nesting" when a pattern is recursive, and in
+    this case 1000 isn't so big. I have been able to remove this limit at the
+    expense of backing off one optimization in certain circumstances. Normally,
+    when pcre_exec() would call its internal match() function recursively and
+    immediately return the result unconditionally, it uses a "tail recursion"
+    feature to save stack. However, when a subpattern that can match an empty
+    string has an unlimited repetition quantifier, it no longer makes this
+    optimization. That gives it a stack frame in which to save the data for
+    checking that an empty string has been matched. Previously this was taken
+    from the 1000-entry workspace that had been reserved. So now there is no
+    explicit limit, but more stack is used.
+
+ 8. Applied Daniel's patches to solve problems with the import/export magic
+    syntax that is required for Windows, and which was going wrong for the
+    pcreposix and pcrecpp parts of the library. These were overlooked when this
+    problem was solved for the main library.
+
+ 9. There were some crude static tests to avoid integer overflow when computing
+    the size of patterns that contain repeated groups with explicit upper
+    limits. As the maximum quantifier is 65535, the maximum group length was
+    set at 30,000 so that the product of these two numbers did not overflow a
+    32-bit integer. However, it turns out that people want to use groups that
+    are longer than 30,000 bytes (though not repeat them that many times).
+    Change 7.0/17 (the refactoring of the way the pattern size is computed) has
+    made it possible to implement the integer overflow checks in a much more
+    dynamic way, which I have now done. The artificial limitation on group
+    length has been removed - we now have only the limit on the total length of
+    the compiled pattern, which depends on the LINK_SIZE setting.
+
+10. Fixed a bug in the documentation for get/copy named substring when
+    duplicate names are permitted. If none of the named substrings are set, the
+    functions return PCRE_ERROR_NOSUBSTRING (7); the doc said they returned an
+    empty string.
+
+11. Because Perl interprets \Q...\E at a high level, and ignores orphan \E
+    instances, patterns such as [\Q\E] or [\E] or even [^\E] cause an error,
+    because the ] is interpreted as the first data character and the
+    terminating ] is not found. PCRE has been made compatible with Perl in this
+    regard. Previously, it interpreted [\Q\E] as an empty class, and [\E] could
+    cause memory overwriting.
+
+10. Like Perl, PCRE automatically breaks an unlimited repeat after an empty
+    string has been matched (to stop an infinite loop). It was not recognizing
+    a conditional subpattern that could match an empty string if that
+    subpattern was within another subpattern. For example, it looped when
+    trying to match  (((?(1)X|))*)  but it was OK with  ((?(1)X|)*)  where the
+    condition was not nested. This bug has been fixed.
+
+12. A pattern like \X?\d or \P{L}?\d in non-UTF-8 mode could cause a backtrack
+    past the start of the subject in the presence of bytes with the top bit
+    set, for example "\x8aBCD".
+
+13. Added Perl 5.10 experimental backtracking controls (*FAIL), (*F), (*PRUNE),
+    (*SKIP), (*THEN), (*COMMIT), and (*ACCEPT).
+
+14. Optimized (?!) to (*FAIL).
+
+15. Updated the test for a valid UTF-8 string to conform to the later RFC 3629.
+    This restricts code points to be within the range 0 to 0x10FFFF, excluding
+    the "low surrogate" sequence 0xD800 to 0xDFFF. Previously, PCRE allowed the
+    full range 0 to 0x7FFFFFFF, as defined by RFC 2279. Internally, it still
+    does: it's just the validity check that is more restrictive.
+
+16. Inserted checks for integer overflows during escape sequence (backslash)
+    processing, and also fixed erroneous offset values for syntax errors during
+    backslash processing.
+
+17. Fixed another case of looking too far back in non-UTF-8 mode (cf 12 above)
+    for patterns like [\PPP\x8a]{1,}\x80 with the subject "A\x80".
+
+18. An unterminated class in a pattern like (?1)\c[ with a "forward reference"
+    caused an overrun.
+
+19. A pattern like (?:[\PPa*]*){8,} which had an "extended class" (one with
+    something other than just ASCII characters) inside a group that had an
+    unlimited repeat caused a loop at compile time (while checking to see
+    whether the group could match an empty string).
+
+20. Debugging a pattern containing \p or \P could cause a crash. For example,
+    [\P{Any}] did so. (Error in the code for printing property names.)
+
+21. An orphan \E inside a character class could cause a crash.
+
+22. A repeated capturing bracket such as (A)? could cause a wild memory
+    reference during compilation.
+
+23. There are several functions in pcre_compile() that scan along a compiled
+    expression for various reasons (e.g. to see if it's fixed length for look
+    behind). There were bugs in these functions when a repeated \p or \P was
+    present in the pattern. These operators have additional parameters compared
+    with \d, etc, and these were not being taken into account when moving along
+    the compiled data. Specifically:
+
+    (a) A item such as \p{Yi}{3} in a lookbehind was not treated as fixed
+        length.
+
+    (b) An item such as \pL+ within a repeated group could cause crashes or
+        loops.
+
+    (c) A pattern such as \p{Yi}+(\P{Yi}+)(?1) could give an incorrect
+        "reference to non-existent subpattern" error.
+
+    (d) A pattern like (\P{Yi}{2}\277)? could loop at compile time.
+
+24. A repeated \S or \W in UTF-8 mode could give wrong answers when multibyte
+    characters were involved (for example /\S{2}/8g with "A\x{a3}BC").
+
+25. Using pcregrep in multiline, inverted mode (-Mv) caused it to loop.
+
+26. Patterns such as [\P{Yi}A] which include \p or \P and just one other
+    character were causing crashes (broken optimization).
+
+27. Patterns such as (\P{Yi}*\277)* (group with possible zero repeat containing
+    \p or \P) caused a compile-time loop.
+
+28. More problems have arisen in unanchored patterns when CRLF is a valid line
+    break. For example, the unstudied pattern [\r\n]A does not match the string
+    "\r\nA" because change 7.0/46 below moves the current point on by two
+    characters after failing to match at the start. However, the pattern \nA
+    *does* match, because it doesn't start till \n, and if [\r\n]A is studied,
+    the same is true. There doesn't seem any very clean way out of this, but
+    what I have chosen to do makes the common cases work: PCRE now takes note
+    of whether there can be an explicit match for \r or \n anywhere in the
+    pattern, and if so, 7.0/46 no longer applies. As part of this change,
+    there's a new PCRE_INFO_HASCRORLF option for finding out whether a compiled
+    pattern has explicit CR or LF references.
+
+29. Added (*CR) etc for changing newline setting at start of pattern.
+
+
+Version 7.2 19-Jun-07
+---------------------
+
+ 1. If the fr_FR locale cannot be found for test 3, try the "french" locale,
+    which is apparently normally available under Windows.
+
+ 2. Re-jig the pcregrep tests with different newline settings in an attempt
+    to make them independent of the local environment's newline setting.
+
+ 3. Add code to configure.ac to remove -g from the CFLAGS default settings.
+
+ 4. Some of the "internals" tests were previously cut out when the link size
+    was not 2, because the output contained actual offsets. The recent new
+    "Z" feature of pcretest means that these can be cut out, making the tests
+    usable with all link sizes.
+
+ 5. Implemented Stan Switzer's goto replacement for longjmp() when not using
+    stack recursion. This gives a massive performance boost under BSD, but just
+    a small improvement under Linux. However, it saves one field in the frame
+    in all cases.
+
+ 6. Added more features from the forthcoming Perl 5.10:
+
+    (a) (?-n) (where n is a string of digits) is a relative subroutine or
+        recursion call. It refers to the nth most recently opened parentheses.
+
+    (b) (?+n) is also a relative subroutine call; it refers to the nth next
+        to be opened parentheses.
+
+    (c) Conditions that refer to capturing parentheses can be specified
+        relatively, for example, (?(-2)... or (?(+3)...
+
+    (d) \K resets the start of the current match so that everything before
+        is not part of it.
+
+    (e) \k{name} is synonymous with \k<name> and \k'name' (.NET compatible).
+
+    (f) \g{name} is another synonym - part of Perl 5.10's unification of
+        reference syntax.
+
+    (g) (?| introduces a group in which the numbering of parentheses in each
+        alternative starts with the same number.
+
+    (h) \h, \H, \v, and \V match horizontal and vertical whitespace.
+
+ 7. Added two new calls to pcre_fullinfo(): PCRE_INFO_OKPARTIAL and
+    PCRE_INFO_JCHANGED.
+
+ 8. A pattern such as  (.*(.)?)*  caused pcre_exec() to fail by either not
+    terminating or by crashing. Diagnosed by Viktor Griph; it was in the code
+    for detecting groups that can match an empty string.
+
+ 9. A pattern with a very large number of alternatives (more than several
+    hundred) was running out of internal workspace during the pre-compile
+    phase, where pcre_compile() figures out how much memory will be needed. A
+    bit of new cunning has reduced the workspace needed for groups with
+    alternatives. The 1000-alternative test pattern now uses 12 bytes of
+    workspace instead of running out of the 4096 that are available.
+
+10. Inserted some missing (unsigned int) casts to get rid of compiler warnings.
+
+11. Applied patch from Google to remove an optimization that didn't quite work.
+    The report of the bug said:
+
+      pcrecpp::RE("a*").FullMatch("aaa") matches, while
+      pcrecpp::RE("a*?").FullMatch("aaa") does not, and
+      pcrecpp::RE("a*?\\z").FullMatch("aaa") does again.
+
+12. If \p or \P was used in non-UTF-8 mode on a character greater than 127
+    it matched the wrong number of bytes.
+
+
+Version 7.1 24-Apr-07
+---------------------
+
+ 1. Applied Bob Rossi and Daniel G's patches to convert the build system to one
+    that is more "standard", making use of automake and other Autotools. There
+    is some re-arrangement of the files and adjustment of comments consequent
+    on this.
+
+ 2. Part of the patch fixed a problem with the pcregrep tests. The test of -r
+    for recursive directory scanning broke on some systems because the files
+    are not scanned in any specific order and on different systems the order
+    was different. A call to "sort" has been inserted into RunGrepTest for the
+    approprate test as a short-term fix. In the longer term there may be an
+    alternative.
+
+ 3. I had an email from Eric Raymond about problems translating some of PCRE's
+    man pages to HTML (despite the fact that I distribute HTML pages, some
+    people do their own conversions for various reasons). The problems
+    concerned the use of low-level troff macros .br and .in. I have therefore
+    removed all such uses from the man pages (some were redundant, some could
+    be replaced by .nf/.fi pairs). The 132html script that I use to generate
+    HTML has been updated to handle .nf/.fi and to complain if it encounters
+    .br or .in.
+
+ 4. Updated comments in configure.ac that get placed in config.h.in and also
+    arranged for config.h to be included in the distribution, with the name
+    config.h.generic, for the benefit of those who have to compile without
+    Autotools (compare pcre.h, which is now distributed as pcre.h.generic).
+
+ 5. Updated the support (such as it is) for Virtual Pascal, thanks to Stefan
+    Weber: (1) pcre_internal.h was missing some function renames; (2) updated
+    makevp.bat for the current PCRE, using the additional files
+    makevp_c.txt, makevp_l.txt, and pcregexp.pas.
+
+ 6. A Windows user reported a minor discrepancy with test 2, which turned out
+    to be caused by a trailing space on an input line that had got lost in his
+    copy. The trailing space was an accident, so I've just removed it.
+
+ 7. Add -Wl,-R... flags in pcre-config.in for *BSD* systems, as I'm told
+    that is needed.
+
+ 8. Mark ucp_table (in ucptable.h) and ucp_gentype (in pcre_ucp_searchfuncs.c)
+    as "const" (a) because they are and (b) because it helps the PHP
+    maintainers who have recently made a script to detect big data structures
+    in the php code that should be moved to the .rodata section. I remembered
+    to update Builducptable as well, so it won't revert if ucptable.h is ever
+    re-created.
+
+ 9. Added some extra #ifdef SUPPORT_UTF8 conditionals into pcretest.c,
+    pcre_printint.src, pcre_compile.c, pcre_study.c, and pcre_tables.c, in
+    order to be able to cut out the UTF-8 tables in the latter when UTF-8
+    support is not required. This saves 1.5-2K of code, which is important in
+    some applications.
+
+    Later: more #ifdefs are needed in pcre_ord2utf8.c and pcre_valid_utf8.c
+    so as not to refer to the tables, even though these functions will never be
+    called when UTF-8 support is disabled. Otherwise there are problems with a
+    shared library.
+
+10. Fixed two bugs in the emulated memmove() function in pcre_internal.h:
+
+    (a) It was defining its arguments as char * instead of void *.
+
+    (b) It was assuming that all moves were upwards in memory; this was true
+        a long time ago when I wrote it, but is no longer the case.
+
+    The emulated memove() is provided for those environments that have neither
+    memmove() nor bcopy(). I didn't think anyone used it these days, but that
+    is clearly not the case, as these two bugs were recently reported.
+
+11. The script PrepareRelease is now distributed: it calls 132html, CleanTxt,
+    and Detrail to create the HTML documentation, the .txt form of the man
+    pages, and it removes trailing spaces from listed files. It also creates
+    pcre.h.generic and config.h.generic from pcre.h and config.h. In the latter
+    case, it wraps all the #defines with #ifndefs. This script should be run
+    before "make dist".
+
+12. Fixed two fairly obscure bugs concerned with quantified caseless matching
+    with Unicode property support.
+
+    (a) For a maximizing quantifier, if the two different cases of the
+        character were of different lengths in their UTF-8 codings (there are
+        some cases like this - I found 11), and the matching function had to
+        back up over a mixture of the two cases, it incorrectly assumed they
+        were both the same length.
+
+    (b) When PCRE was configured to use the heap rather than the stack for
+        recursion during matching, it was not correctly preserving the data for
+        the other case of a UTF-8 character when checking ahead for a match
+        while processing a minimizing repeat. If the check also involved
+        matching a wide character, but failed, corruption could cause an
+        erroneous result when trying to check for a repeat of the original
+        character.
+
+13. Some tidying changes to the testing mechanism:
+
+    (a) The RunTest script now detects the internal link size and whether there
+        is UTF-8 and UCP support by running ./pcretest -C instead of relying on
+        values substituted by "configure". (The RunGrepTest script already did
+        this for UTF-8.) The configure.ac script no longer substitutes the
+        relevant variables.
+
+    (b) The debugging options /B and /D in pcretest show the compiled bytecode
+        with length and offset values. This means that the output is different
+        for different internal link sizes. Test 2 is skipped for link sizes
+        other than 2 because of this, bypassing the problem. Unfortunately,
+        there was also a test in test 3 (the locale tests) that used /B and
+        failed for link sizes other than 2. Rather than cut the whole test out,
+        I have added a new /Z option to pcretest that replaces the length and
+        offset values with spaces. This is now used to make test 3 independent
+        of link size. (Test 2 will be tidied up later.)
+
+14. If erroroffset was passed as NULL to pcre_compile, it provoked a
+    segmentation fault instead of returning the appropriate error message.
+
+15. In multiline mode when the newline sequence was set to "any", the pattern
+    ^$ would give a match between the \r and \n of a subject such as "A\r\nB".
+    This doesn't seem right; it now treats the CRLF combination as the line
+    ending, and so does not match in that case. It's only a pattern such as ^$
+    that would hit this one: something like ^ABC$ would have failed after \r
+    and then tried again after \r\n.
+
+16. Changed the comparison command for RunGrepTest from "diff -u" to "diff -ub"
+    in an attempt to make files that differ only in their line terminators
+    compare equal. This works on Linux.
+
+17. Under certain error circumstances pcregrep might try to free random memory
+    as it exited. This is now fixed, thanks to valgrind.
+
+19. In pcretest, if the pattern /(?m)^$/g<any> was matched against the string
+    "abc\r\n\r\n", it found an unwanted second match after the second \r. This
+    was because its rules for how to advance for /g after matching an empty
+    string at the end of a line did not allow for this case. They now check for
+    it specially.
+
+20. pcretest is supposed to handle patterns and data of any length, by
+    extending its buffers when necessary. It was getting this wrong when the
+    buffer for a data line had to be extended.
+
+21. Added PCRE_NEWLINE_ANYCRLF which is like ANY, but matches only CR, LF, or
+    CRLF as a newline sequence.
+
+22. Code for handling Unicode properties in pcre_dfa_exec() wasn't being cut
+    out by #ifdef SUPPORT_UCP. This did no harm, as it could never be used, but
+    I have nevertheless tidied it up.
+
+23. Added some casts to kill warnings from HP-UX ia64 compiler.
+
+24. Added a man page for pcre-config.
+
+
+Version 7.0 19-Dec-06
+---------------------
+
+ 1. Fixed a signed/unsigned compiler warning in pcre_compile.c, shown up by
+    moving to gcc 4.1.1.
+
+ 2. The -S option for pcretest uses setrlimit(); I had omitted to #include
+    sys/time.h, which is documented as needed for this function. It doesn't
+    seem to matter on Linux, but it showed up on some releases of OS X.
+
+ 3. It seems that there are systems where bytes whose values are greater than
+    127 match isprint() in the "C" locale. The "C" locale should be the
+    default when a C program starts up. In most systems, only ASCII printing
+    characters match isprint(). This difference caused the output from pcretest
+    to vary, making some of the tests fail. I have changed pcretest so that:
+
+    (a) When it is outputting text in the compiled version of a pattern, bytes
+        other than 32-126 are always shown as hex escapes.
+
+    (b) When it is outputting text that is a matched part of a subject string,
+        it does the same, unless a different locale has been set for the match
+        (using the /L modifier). In this case, it uses isprint() to decide.
+
+ 4. Fixed a major bug that caused incorrect computation of the amount of memory
+    required for a compiled pattern when options that changed within the
+    pattern affected the logic of the preliminary scan that determines the
+    length. The relevant options are -x, and -i in UTF-8 mode. The result was
+    that the computed length was too small. The symptoms of this bug were
+    either the PCRE error "internal error: code overflow" from pcre_compile(),
+    or a glibc crash with a message such as "pcretest: free(): invalid next
+    size (fast)". Examples of patterns that provoked this bug (shown in
+    pcretest format) are:
+
+      /(?-x: )/x
+      /(?x)(?-x: \s*#\s*)/
+      /((?i)[\x{c0}])/8
+      /(?i:[\x{c0}])/8
+
+    HOWEVER: Change 17 below makes this fix obsolete as the memory computation
+    is now done differently.
+
+ 5. Applied patches from Google to: (a) add a QuoteMeta function to the C++
+    wrapper classes; (b) implement a new function in the C++ scanner that is
+    more efficient than the old way of doing things because it avoids levels of
+    recursion in the regex matching; (c) add a paragraph to the documentation
+    for the FullMatch() function.
+
+ 6. The escape sequence \n was being treated as whatever was defined as
+    "newline". Not only was this contrary to the documentation, which states
+    that \n is character 10 (hex 0A), but it also went horribly wrong when
+    "newline" was defined as CRLF. This has been fixed.
+
+ 7. In pcre_dfa_exec.c the value of an unsigned integer (the variable called c)
+    was being set to -1 for the "end of line" case (supposedly a value that no
+    character can have). Though this value is never used (the check for end of
+    line is "zero bytes in current character"), it caused compiler complaints.
+    I've changed it to 0xffffffff.
+
+ 8. In pcre_version.c, the version string was being built by a sequence of
+    C macros that, in the event of PCRE_PRERELEASE being defined as an empty
+    string (as it is for production releases) called a macro with an empty
+    argument. The C standard says the result of this is undefined. The gcc
+    compiler treats it as an empty string (which was what was wanted) but it is
+    reported that Visual C gives an error. The source has been hacked around to
+    avoid this problem.
+
+ 9. On the advice of a Windows user, included <io.h> and <fcntl.h> in Windows
+    builds of pcretest, and changed the call to _setmode() to use _O_BINARY
+    instead of 0x8000. Made all the #ifdefs test both _WIN32 and WIN32 (not all
+    of them did).
+
+10. Originally, pcretest opened its input and output without "b"; then I was
+    told that "b" was needed in some environments, so it was added for release
+    5.0 to both the input and output. (It makes no difference on Unix-like
+    systems.) Later I was told that it is wrong for the input on Windows. I've
+    now abstracted the modes into two macros, to make it easier to fiddle with
+    them, and removed "b" from the input mode under Windows.
+
+11. Added pkgconfig support for the C++ wrapper library, libpcrecpp.
+
+12. Added -help and --help to pcretest as an official way of being reminded
+    of the options.
+
+13. Removed some redundant semicolons after macro calls in pcrecpparg.h.in
+    and pcrecpp.cc because they annoy compilers at high warning levels.
+
+14. A bit of tidying/refactoring in pcre_exec.c in the main bumpalong loop.
+
+15. Fixed an occurrence of == in configure.ac that should have been = (shell
+    scripts are not C programs :-) and which was not noticed because it works
+    on Linux.
+
+16. pcretest is supposed to handle any length of pattern and data line (as one
+    line or as a continued sequence of lines) by extending its input buffer if
+    necessary. This feature was broken for very long pattern lines, leading to
+    a string of junk being passed to pcre_compile() if the pattern was longer
+    than about 50K.
+
+17. I have done a major re-factoring of the way pcre_compile() computes the
+    amount of memory needed for a compiled pattern. Previously, there was code
+    that made a preliminary scan of the pattern in order to do this. That was
+    OK when PCRE was new, but as the facilities have expanded, it has become
+    harder and harder to keep it in step with the real compile phase, and there
+    have been a number of bugs (see for example, 4 above). I have now found a
+    cunning way of running the real compile function in a "fake" mode that
+    enables it to compute how much memory it would need, while actually only
+    ever using a few hundred bytes of working memory and without too many
+    tests of the mode. This should make future maintenance and development
+    easier. A side effect of this work is that the limit of 200 on the nesting
+    depth of parentheses has been removed (though this was never a serious
+    limitation, I suspect). However, there is a downside: pcre_compile() now
+    runs more slowly than before (30% or more, depending on the pattern). I
+    hope this isn't a big issue. There is no effect on runtime performance.
+
+18. Fixed a minor bug in pcretest: if a pattern line was not terminated by a
+    newline (only possible for the last line of a file) and it was a
+    pattern that set a locale (followed by /Lsomething), pcretest crashed.
+
+19. Added additional timing features to pcretest. (1) The -tm option now times
+    matching only, not compiling. (2) Both -t and -tm can be followed, as a
+    separate command line item, by a number that specifies the number of
+    repeats to use when timing. The default is 50000; this gives better
+    precision, but takes uncomfortably long for very large patterns.
+
+20. Extended pcre_study() to be more clever in cases where a branch of a
+    subpattern has no definite first character. For example, (a*|b*)[cd] would
+    previously give no result from pcre_study(). Now it recognizes that the
+    first character must be a, b, c, or d.
+
+21. There was an incorrect error "recursive call could loop indefinitely" if
+    a subpattern (or the entire pattern) that was being tested for matching an
+    empty string contained only one non-empty item after a nested subpattern.
+    For example, the pattern (?>\x{100}*)\d(?R) provoked this error
+    incorrectly, because the \d was being skipped in the check.
+
+22. The pcretest program now has a new pattern option /B and a command line
+    option -b, which is equivalent to adding /B to every pattern. This causes
+    it to show the compiled bytecode, without the additional information that
+    -d shows. The effect of -d is now the same as -b with -i (and similarly, /D
+    is the same as /B/I).
+
+23. A new optimization is now able automatically to treat some sequences such
+    as a*b as a*+b. More specifically, if something simple (such as a character
+    or a simple class like \d) has an unlimited quantifier, and is followed by
+    something that cannot possibly match the quantified thing, the quantifier
+    is automatically "possessified".
+
+24. A recursive reference to a subpattern whose number was greater than 39
+    went wrong under certain circumstances in UTF-8 mode. This bug could also
+    have affected the operation of pcre_study().
+
+25. Realized that a little bit of performance could be had by replacing
+    (c & 0xc0) == 0xc0 with c >= 0xc0 when processing UTF-8 characters.
+
+26. Timing data from pcretest is now shown to 4 decimal places instead of 3.
+
+27. Possessive quantifiers such as a++ were previously implemented by turning
+    them into atomic groups such as ($>a+). Now they have their own opcodes,
+    which improves performance. This includes the automatically created ones
+    from 23 above.
+
+28. A pattern such as (?=(\w+))\1: which simulates an atomic group using a
+    lookahead was broken if it was not anchored. PCRE was mistakenly expecting
+    the first matched character to be a colon. This applied both to named and
+    numbered groups.
+
+29. The ucpinternal.h header file was missing its idempotency #ifdef.
+
+30. I was sent a "project" file called libpcre.a.dev which I understand makes
+    building PCRE on Windows easier, so I have included it in the distribution.
+
+31. There is now a check in pcretest against a ridiculously large number being
+    returned by pcre_exec() or pcre_dfa_exec(). If this happens in a /g or /G
+    loop, the loop is abandoned.
+
+32. Forward references to subpatterns in conditions such as (?(2)...) where
+    subpattern 2 is defined later cause pcre_compile() to search forwards in
+    the pattern for the relevant set of parentheses. This search went wrong
+    when there were unescaped parentheses in a character class, parentheses
+    escaped with \Q...\E, or parentheses in a #-comment in /x mode.
+
+33. "Subroutine" calls and backreferences were previously restricted to
+    referencing subpatterns earlier in the regex. This restriction has now
+    been removed.
+
+34. Added a number of extra features that are going to be in Perl 5.10. On the
+    whole, these are just syntactic alternatives for features that PCRE had
+    previously implemented using the Python syntax or my own invention. The
+    other formats are all retained for compatibility.
+
+    (a) Named groups can now be defined as (?<name>...) or (?'name'...) as well
+        as (?P<name>...). The new forms, as well as being in Perl 5.10, are
+        also .NET compatible.
+
+    (b) A recursion or subroutine call to a named group can now be defined as
+        (?&name) as well as (?P>name).
+
+    (c) A backreference to a named group can now be defined as \k<name> or
+        \k'name' as well as (?P=name). The new forms, as well as being in Perl
+        5.10, are also .NET compatible.
+
+    (d) A conditional reference to a named group can now use the syntax
+        (?(<name>) or (?('name') as well as (?(name).
+
+    (e) A "conditional group" of the form (?(DEFINE)...) can be used to define
+        groups (named and numbered) that are never evaluated inline, but can be
+        called as "subroutines" from elsewhere. In effect, the DEFINE condition
+        is always false. There may be only one alternative in such a group.
+
+    (f) A test for recursion can be given as (?(R1).. or (?(R&name)... as well
+        as the simple (?(R). The condition is true only if the most recent
+        recursion is that of the given number or name. It does not search out
+        through the entire recursion stack.
+
+    (g) The escape \gN or \g{N} has been added, where N is a positive or
+        negative number, specifying an absolute or relative reference.
+
+35. Tidied to get rid of some further signed/unsigned compiler warnings and
+    some "unreachable code" warnings.
+
+36. Updated the Unicode property tables to Unicode version 5.0.0. Amongst other
+    things, this adds five new scripts.
+
+37. Perl ignores orphaned \E escapes completely. PCRE now does the same.
+    There were also incompatibilities regarding the handling of \Q..\E inside
+    character classes, for example with patterns like [\Qa\E-\Qz\E] where the
+    hyphen was adjacent to \Q or \E. I hope I've cleared all this up now.
+
+38. Like Perl, PCRE detects when an indefinitely repeated parenthesized group
+    matches an empty string, and forcibly breaks the loop. There were bugs in
+    this code in non-simple cases. For a pattern such as  ^(a()*)*  matched
+    against  aaaa  the result was just "a" rather than "aaaa", for example. Two
+    separate and independent bugs (that affected different cases) have been
+    fixed.
+
+39. Refactored the code to abolish the use of different opcodes for small
+    capturing bracket numbers. This is a tidy that I avoided doing when I
+    removed the limit on the number of capturing brackets for 3.5 back in 2001.
+    The new approach is not only tidier, it makes it possible to reduce the
+    memory needed to fix the previous bug (38).
+
+40. Implemented PCRE_NEWLINE_ANY to recognize any of the Unicode newline
+    sequences (http://unicode.org/unicode/reports/tr18/) as "newline" when
+    processing dot, circumflex, or dollar metacharacters, or #-comments in /x
+    mode.
+
+41. Add \R to match any Unicode newline sequence, as suggested in the Unicode
+    report.
+
+42. Applied patch, originally from Ari Pollak, modified by Google, to allow
+    copy construction and assignment in the C++ wrapper.
+
+43. Updated pcregrep to support "--newline=any". In the process, I fixed a
+    couple of bugs that could have given wrong results in the "--newline=crlf"
+    case.
+
+44. Added a number of casts and did some reorganization of signed/unsigned int
+    variables following suggestions from Dair Grant. Also renamed the variable
+    "this" as "item" because it is a C++ keyword.
+
+45. Arranged for dftables to add
+
+      #include "pcre_internal.h"
+
+    to pcre_chartables.c because without it, gcc 4.x may remove the array
+    definition from the final binary if PCRE is built into a static library and
+    dead code stripping is activated.
+
+46. For an unanchored pattern, if a match attempt fails at the start of a
+    newline sequence, and the newline setting is CRLF or ANY, and the next two
+    characters are CRLF, advance by two characters instead of one.
+
+
+Version 6.7 04-Jul-06
+---------------------
+
+ 1. In order to handle tests when input lines are enormously long, pcretest has
+    been re-factored so that it automatically extends its buffers when
+    necessary. The code is crude, but this _is_ just a test program. The
+    default size has been increased from 32K to 50K.
+
+ 2. The code in pcre_study() was using the value of the re argument before
+    testing it for NULL. (Of course, in any sensible call of the function, it
+    won't be NULL.)
+
+ 3. The memmove() emulation function in pcre_internal.h, which is used on
+    systems that lack both memmove() and bcopy() - that is, hardly ever -
+    was missing a "static" storage class specifier.
+
+ 4. When UTF-8 mode was not set, PCRE looped when compiling certain patterns
+    containing an extended class (one that cannot be represented by a bitmap
+    because it contains high-valued characters or Unicode property items, e.g.
+    [\pZ]). Almost always one would set UTF-8 mode when processing such a
+    pattern, but PCRE should not loop if you do not (it no longer does).
+    [Detail: two cases were found: (a) a repeated subpattern containing an
+    extended class; (b) a recursive reference to a subpattern that followed a
+    previous extended class. It wasn't skipping over the extended class
+    correctly when UTF-8 mode was not set.]
+
+ 5. A negated single-character class was not being recognized as fixed-length
+    in lookbehind assertions such as (?<=[^f]), leading to an incorrect
+    compile error "lookbehind assertion is not fixed length".
+
+ 6. The RunPerlTest auxiliary script was showing an unexpected difference
+    between PCRE and Perl for UTF-8 tests. It turns out that it is hard to
+    write a Perl script that can interpret lines of an input file either as
+    byte characters or as UTF-8, which is what "perltest" was being required to
+    do for the non-UTF-8 and UTF-8 tests, respectively. Essentially what you
+    can't do is switch easily at run time between having the "use utf8;" pragma
+    or not. In the end, I fudged it by using the RunPerlTest script to insert
+    "use utf8;" explicitly for the UTF-8 tests.
+
+ 7. In multiline (/m) mode, PCRE was matching ^ after a terminating newline at
+    the end of the subject string, contrary to the documentation and to what
+    Perl does. This was true of both matching functions. Now it matches only at
+    the start of the subject and immediately after *internal* newlines.
+
+ 8. A call of pcre_fullinfo() from pcretest to get the option bits was passing
+    a pointer to an int instead of a pointer to an unsigned long int. This
+    caused problems on 64-bit systems.
+
+ 9. Applied a patch from the folks at Google to pcrecpp.cc, to fix "another
+    instance of the 'standard' template library not being so standard".
+
+10. There was no check on the number of named subpatterns nor the maximum
+    length of a subpattern name. The product of these values is used to compute
+    the size of the memory block for a compiled pattern. By supplying a very
+    long subpattern name and a large number of named subpatterns, the size
+    computation could be caused to overflow. This is now prevented by limiting
+    the length of names to 32 characters, and the number of named subpatterns
+    to 10,000.
+
+11. Subpatterns that are repeated with specific counts have to be replicated in
+    the compiled pattern. The size of memory for this was computed from the
+    length of the subpattern and the repeat count. The latter is limited to
+    65535, but there was no limit on the former, meaning that integer overflow
+    could in principle occur. The compiled length of a repeated subpattern is
+    now limited to 30,000 bytes in order to prevent this.
+
+12. Added the optional facility to have named substrings with the same name.
+
+13. Added the ability to use a named substring as a condition, using the
+    Python syntax: (?(name)yes|no). This overloads (?(R)... and names that
+    are numbers (not recommended). Forward references are permitted.
+
+14. Added forward references in named backreferences (if you see what I mean).
+
+15. In UTF-8 mode, with the PCRE_DOTALL option set, a quantified dot in the
+    pattern could run off the end of the subject. For example, the pattern
+    "(?s)(.{1,5})"8 did this with the subject "ab".
+
+16. If PCRE_DOTALL or PCRE_MULTILINE were set, pcre_dfa_exec() behaved as if
+    PCRE_CASELESS was set when matching characters that were quantified with ?
+    or *.
+
+17. A character class other than a single negated character that had a minimum
+    but no maximum quantifier - for example [ab]{6,} - was not handled
+    correctly by pce_dfa_exec(). It would match only one character.
+
+18. A valid (though odd) pattern that looked like a POSIX character
+    class but used an invalid character after [ (for example [[,abc,]]) caused
+    pcre_compile() to give the error "Failed: internal error: code overflow" or
+    in some cases to crash with a glibc free() error. This could even happen if
+    the pattern terminated after [[ but there just happened to be a sequence of
+    letters, a binary zero, and a closing ] in the memory that followed.
+
+19. Perl's treatment of octal escapes in the range \400 to \777 has changed
+    over the years. Originally (before any Unicode support), just the bottom 8
+    bits were taken. Thus, for example, \500 really meant \100. Nowadays the
+    output from "man perlunicode" includes this:
+
+      The regular expression compiler produces polymorphic opcodes.  That
+      is, the pattern adapts to the data and automatically switches to
+      the Unicode character scheme when presented with Unicode data--or
+      instead uses a traditional byte scheme when presented with byte
+      data.
+
+    Sadly, a wide octal escape does not cause a switch, and in a string with
+    no other multibyte characters, these octal escapes are treated as before.
+    Thus, in Perl, the pattern  /\500/ actually matches \100 but the pattern
+    /\500|\x{1ff}/ matches \500 or \777 because the whole thing is treated as a
+    Unicode string.
+
+    I have not perpetrated such confusion in PCRE. Up till now, it took just
+    the bottom 8 bits, as in old Perl. I have now made octal escapes with
+    values greater than \377 illegal in non-UTF-8 mode. In UTF-8 mode they
+    translate to the appropriate multibyte character.
+
+29. Applied some refactoring to reduce the number of warnings from Microsoft
+    and Borland compilers. This has included removing the fudge introduced
+    seven years ago for the OS/2 compiler (see 2.02/2 below) because it caused
+    a warning about an unused variable.
+
+21. PCRE has not included VT (character 0x0b) in the set of whitespace
+    characters since release 4.0, because Perl (from release 5.004) does not.
+    [Or at least, is documented not to: some releases seem to be in conflict
+    with the documentation.] However, when a pattern was studied with
+    pcre_study() and all its branches started with \s, PCRE still included VT
+    as a possible starting character. Of course, this did no harm; it just
+    caused an unnecessary match attempt.
+
+22. Removed a now-redundant internal flag bit that recorded the fact that case
+    dependency changed within the pattern. This was once needed for "required
+    byte" processing, but is no longer used. This recovers a now-scarce options
+    bit. Also moved the least significant internal flag bit to the most-
+    significant bit of the word, which was not previously used (hangover from
+    the days when it was an int rather than a uint) to free up another bit for
+    the future.
+
+23. Added support for CRLF line endings as well as CR and LF. As well as the
+    default being selectable at build time, it can now be changed at runtime
+    via the PCRE_NEWLINE_xxx flags. There are now options for pcregrep to
+    specify that it is scanning data with non-default line endings.
+
+24. Changed the definition of CXXLINK to make it agree with the definition of
+    LINK in the Makefile, by replacing LDFLAGS to CXXFLAGS.
+
+25. Applied Ian Taylor's patches to avoid using another stack frame for tail
+    recursions. This makes a big different to stack usage for some patterns.
+
+26. If a subpattern containing a named recursion or subroutine reference such
+    as (?P>B) was quantified, for example (xxx(?P>B)){3}, the calculation of
+    the space required for the compiled pattern went wrong and gave too small a
+    value. Depending on the environment, this could lead to "Failed: internal
+    error: code overflow at offset 49" or "glibc detected double free or
+    corruption" errors.
+
+27. Applied patches from Google (a) to support the new newline modes and (b) to
+    advance over multibyte UTF-8 characters in GlobalReplace.
+
+28. Change free() to pcre_free() in pcredemo.c. Apparently this makes a
+    difference for some implementation of PCRE in some Windows version.
+
+29. Added some extra testing facilities to pcretest:
+
+    \q<number>   in a data line sets the "match limit" value
+    \Q<number>   in a data line sets the "match recursion limt" value
+    -S <number>  sets the stack size, where <number> is in megabytes
+
+    The -S option isn't available for Windows.
+
+
+Version 6.6 06-Feb-06
+---------------------
+
+ 1. Change 16(a) for 6.5 broke things, because PCRE_DATA_SCOPE was not defined
+    in pcreposix.h. I have copied the definition from pcre.h.
+
+ 2. Change 25 for 6.5 broke compilation in a build directory out-of-tree
+    because pcre.h is no longer a built file.
+
+ 3. Added Jeff Friedl's additional debugging patches to pcregrep. These are
+    not normally included in the compiled code.
+
+
+Version 6.5 01-Feb-06
+---------------------
+
+ 1. When using the partial match feature with pcre_dfa_exec(), it was not
+    anchoring the second and subsequent partial matches at the new starting
+    point. This could lead to incorrect results. For example, with the pattern
+    /1234/, partially matching against "123" and then "a4" gave a match.
+
+ 2. Changes to pcregrep:
+
+    (a) All non-match returns from pcre_exec() were being treated as failures
+        to match the line. Now, unless the error is PCRE_ERROR_NOMATCH, an
+        error message is output. Some extra information is given for the
+        PCRE_ERROR_MATCHLIMIT and PCRE_ERROR_RECURSIONLIMIT errors, which are
+        probably the only errors that are likely to be caused by users (by
+        specifying a regex that has nested indefinite repeats, for instance).
+        If there are more than 20 of these errors, pcregrep is abandoned.
+
+    (b) A binary zero was treated as data while matching, but terminated the
+        output line if it was written out. This has been fixed: binary zeroes
+        are now no different to any other data bytes.
+
+    (c) Whichever of the LC_ALL or LC_CTYPE environment variables is set is
+        used to set a locale for matching. The --locale=xxxx long option has
+        been added (no short equivalent) to specify a locale explicitly on the
+        pcregrep command, overriding the environment variables.
+
+    (d) When -B was used with -n, some line numbers in the output were one less
+        than they should have been.
+
+    (e) Added the -o (--only-matching) option.
+
+    (f) If -A or -C was used with -c (count only), some lines of context were
+        accidentally printed for the final match.
+
+    (g) Added the -H (--with-filename) option.
+
+    (h) The combination of options -rh failed to suppress file names for files
+        that were found from directory arguments.
+
+    (i) Added the -D (--devices) and -d (--directories) options.
+
+    (j) Added the -F (--fixed-strings) option.
+
+    (k) Allow "-" to be used as a file name for -f as well as for a data file.
+
+    (l) Added the --colo(u)r option.
+
+    (m) Added Jeffrey Friedl's -S testing option, but within #ifdefs so that it
+        is not present by default.
+
+ 3. A nasty bug was discovered in the handling of recursive patterns, that is,
+    items such as (?R) or (?1), when the recursion could match a number of
+    alternatives. If it matched one of the alternatives, but subsequently,
+    outside the recursion, there was a failure, the code tried to back up into
+    the recursion. However, because of the way PCRE is implemented, this is not
+    possible, and the result was an incorrect result from the match.
+
+    In order to prevent this happening, the specification of recursion has
+    been changed so that all such subpatterns are automatically treated as
+    atomic groups. Thus, for example, (?R) is treated as if it were (?>(?R)).
+
+ 4. I had overlooked the fact that, in some locales, there are characters for
+    which isalpha() is true but neither isupper() nor islower() are true. In
+    the fr_FR locale, for instance, the \xAA and \xBA characters (ordmasculine
+    and ordfeminine) are like this. This affected the treatment of \w and \W
+    when they appeared in character classes, but not when they appeared outside
+    a character class. The bit map for "word" characters is now created
+    separately from the results of isalnum() instead of just taking it from the
+    upper, lower, and digit maps. (Plus the underscore character, of course.)
+
+ 5. The above bug also affected the handling of POSIX character classes such as
+    [[:alpha:]] and [[:alnum:]]. These do not have their own bit maps in PCRE's
+    permanent tables. Instead, the bit maps for such a class were previously
+    created as the appropriate unions of the upper, lower, and digit bitmaps.
+    Now they are created by subtraction from the [[:word:]] class, which has
+    its own bitmap.
+
+ 6. The [[:blank:]] character class matches horizontal, but not vertical space.
+    It is created by subtracting the vertical space characters (\x09, \x0a,
+    \x0b, \x0c) from the [[:space:]] bitmap. Previously, however, the
+    subtraction was done in the overall bitmap for a character class, meaning
+    that a class such as [\x0c[:blank:]] was incorrect because \x0c would not
+    be recognized. This bug has been fixed.
+
+ 7. Patches from the folks at Google:
+
+      (a) pcrecpp.cc: "to handle a corner case that may or may not happen in
+      real life, but is still worth protecting against".
+
+      (b) pcrecpp.cc: "corrects a bug when negative radixes are used with
+      regular expressions".
+
+      (c) pcre_scanner.cc: avoid use of std::count() because not all systems
+      have it.
+
+      (d) Split off pcrecpparg.h from pcrecpp.h and had the former built by
+      "configure" and the latter not, in order to fix a problem somebody had
+      with compiling the Arg class on HP-UX.
+
+      (e) Improve the error-handling of the C++ wrapper a little bit.
+
+      (f) New tests for checking recursion limiting.
+
+ 8. The pcre_memmove() function, which is used only if the environment does not
+    have a standard memmove() function (and is therefore rarely compiled),
+    contained two bugs: (a) use of int instead of size_t, and (b) it was not
+    returning a result (though PCRE never actually uses the result).
+
+ 9. In the POSIX regexec() interface, if nmatch is specified as a ridiculously
+    large number - greater than INT_MAX/(3*sizeof(int)) - REG_ESPACE is
+    returned instead of calling malloc() with an overflowing number that would
+    most likely cause subsequent chaos.
+
+10. The debugging option of pcretest was not showing the NO_AUTO_CAPTURE flag.
+
+11. The POSIX flag REG_NOSUB is now supported. When a pattern that was compiled
+    with this option is matched, the nmatch and pmatch options of regexec() are
+    ignored.
+
+12. Added REG_UTF8 to the POSIX interface. This is not defined by POSIX, but is
+    provided in case anyone wants to the the POSIX interface with UTF-8
+    strings.
+
+13. Added CXXLDFLAGS to the Makefile parameters to provide settings only on the
+    C++ linking (needed for some HP-UX environments).
+
+14. Avoid compiler warnings in get_ucpname() when compiled without UCP support
+    (unused parameter) and in the pcre_printint() function (omitted "default"
+    switch label when the default is to do nothing).
+
+15. Added some code to make it possible, when PCRE is compiled as a C++
+    library, to replace subject pointers for pcre_exec() with a smart pointer
+    class, thus making it possible to process discontinuous strings.
+
+16. The two macros PCRE_EXPORT and PCRE_DATA_SCOPE are confusing, and perform
+    much the same function. They were added by different people who were trying
+    to make PCRE easy to compile on non-Unix systems. It has been suggested
+    that PCRE_EXPORT be abolished now that there is more automatic apparatus
+    for compiling on Windows systems. I have therefore replaced it with
+    PCRE_DATA_SCOPE. This is set automatically for Windows; if not set it
+    defaults to "extern" for C or "extern C" for C++, which works fine on
+    Unix-like systems. It is now possible to override the value of PCRE_DATA_
+    SCOPE with something explicit in config.h. In addition:
+
+    (a) pcreposix.h still had just "extern" instead of either of these macros;
+        I have replaced it with PCRE_DATA_SCOPE.
+
+    (b) Functions such as _pcre_xclass(), which are internal to the library,
+        but external in the C sense, all had PCRE_EXPORT in their definitions.
+        This is apparently wrong for the Windows case, so I have removed it.
+        (It makes no difference on Unix-like systems.)
+
+17. Added a new limit, MATCH_LIMIT_RECURSION, which limits the depth of nesting
+    of recursive calls to match(). This is different to MATCH_LIMIT because
+    that limits the total number of calls to match(), not all of which increase
+    the depth of recursion. Limiting the recursion depth limits the amount of
+    stack (or heap if NO_RECURSE is set) that is used. The default can be set
+    when PCRE is compiled, and changed at run time. A patch from Google adds
+    this functionality to the C++ interface.
+
+18. Changes to the handling of Unicode character properties:
+
+    (a) Updated the table to Unicode 4.1.0.
+
+    (b) Recognize characters that are not in the table as "Cn" (undefined).
+
+    (c) I revised the way the table is implemented to a much improved format
+        which includes recognition of ranges. It now supports the ranges that
+        are defined in UnicodeData.txt, and it also amalgamates other
+        characters into ranges. This has reduced the number of entries in the
+        table from around 16,000 to around 3,000, thus reducing its size
+        considerably. I realized I did not need to use a tree structure after
+        all - a binary chop search is just as efficient. Having reduced the
+        number of entries, I extended their size from 6 bytes to 8 bytes to
+        allow for more data.
+
+    (d) Added support for Unicode script names via properties such as \p{Han}.
+
+19. In UTF-8 mode, a backslash followed by a non-Ascii character was not
+    matching that character.
+
+20. When matching a repeated Unicode property with a minimum greater than zero,
+    (for example \pL{2,}), PCRE could look past the end of the subject if it
+    reached it while seeking the minimum number of characters. This could
+    happen only if some of the characters were more than one byte long, because
+    there is a check for at least the minimum number of bytes.
+
+21. Refactored the implementation of \p and \P so as to be more general, to
+    allow for more different types of property in future. This has changed the
+    compiled form incompatibly. Anybody with saved compiled patterns that use
+    \p or \P will have to recompile them.
+
+22. Added "Any" and "L&" to the supported property types.
+
+23. Recognize \x{...} as a code point specifier, even when not in UTF-8 mode,
+    but give a compile time error if the value is greater than 0xff.
+
+24. The man pages for pcrepartial, pcreprecompile, and pcre_compile2 were
+    accidentally not being installed or uninstalled.
+
+25. The pcre.h file was built from pcre.h.in, but the only changes that were
+    made were to insert the current release number. This seemed silly, because
+    it made things harder for people building PCRE on systems that don't run
+    "configure". I have turned pcre.h into a distributed file, no longer built
+    by "configure", with the version identification directly included. There is
+    no longer a pcre.h.in file.
+
+    However, this change necessitated a change to the pcre-config script as
+    well. It is built from pcre-config.in, and one of the substitutions was the
+    release number. I have updated configure.ac so that ./configure now finds
+    the release number by grepping pcre.h.
+
+26. Added the ability to run the tests under valgrind.
+
+
+Version 6.4 05-Sep-05
+---------------------
+
+ 1. Change 6.0/10/(l) to pcregrep introduced a bug that caused separator lines
+    "--" to be printed when multiple files were scanned, even when none of the
+    -A, -B, or -C options were used. This is not compatible with Gnu grep, so I
+    consider it to be a bug, and have restored the previous behaviour.
+
+ 2. A couple of code tidies to get rid of compiler warnings.
+
+ 3. The pcretest program used to cheat by referring to symbols in the library
+    whose names begin with _pcre_. These are internal symbols that are not
+    really supposed to be visible externally, and in some environments it is
+    possible to suppress them. The cheating is now confined to including
+    certain files from the library's source, which is a bit cleaner.
+
+ 4. Renamed pcre.in as pcre.h.in to go with pcrecpp.h.in; it also makes the
+    file's purpose clearer.
+
+ 5. Reorganized pcre_ucp_findchar().
+
+
+Version 6.3 15-Aug-05
+---------------------
+
+ 1. The file libpcre.pc.in did not have general read permission in the tarball.
+
+ 2. There were some problems when building without C++ support:
+
+    (a) If C++ support was not built, "make install" and "make test" still
+        tried to test it.
+
+    (b) There were problems when the value of CXX was explicitly set. Some
+        changes have been made to try to fix these, and ...
+
+    (c) --disable-cpp can now be used to explicitly disable C++ support.
+
+    (d) The use of @CPP_OBJ@ directly caused a blank line preceded by a
+        backslash in a target when C++ was disabled. This confuses some
+        versions of "make", apparently. Using an intermediate variable solves
+        this. (Same for CPP_LOBJ.)
+
+ 3. $(LINK_FOR_BUILD) now includes $(CFLAGS_FOR_BUILD) and $(LINK)
+    (non-Windows) now includes $(CFLAGS) because these flags are sometimes
+    necessary on certain architectures.
+
+ 4. Added a setting of -export-symbols-regex to the link command to remove
+    those symbols that are exported in the C sense, but actually are local
+    within the library, and not documented. Their names all begin with
+    "_pcre_". This is not a perfect job, because (a) we have to except some
+    symbols that pcretest ("illegally") uses, and (b) the facility isn't always
+    available (and never for static libraries). I have made a note to try to
+    find a way round (a) in the future.
+
+
+Version 6.2 01-Aug-05
+---------------------
+
+ 1. There was no test for integer overflow of quantifier values. A construction
+    such as {1111111111111111} would give undefined results. What is worse, if
+    a minimum quantifier for a parenthesized subpattern overflowed and became
+    negative, the calculation of the memory size went wrong. This could have
+    led to memory overwriting.
+
+ 2. Building PCRE using VPATH was broken. Hopefully it is now fixed.
+
+ 3. Added "b" to the 2nd argument of fopen() in dftables.c, for non-Unix-like
+    operating environments where this matters.
+
+ 4. Applied Giuseppe Maxia's patch to add additional features for controlling
+    PCRE options from within the C++ wrapper.
+
+ 5. Named capturing subpatterns were not being correctly counted when a pattern
+    was compiled. This caused two problems: (a) If there were more than 100
+    such subpatterns, the calculation of the memory needed for the whole
+    compiled pattern went wrong, leading to an overflow error. (b) Numerical
+    back references of the form \12, where the number was greater than 9, were
+    not recognized as back references, even though there were sufficient
+    previous subpatterns.
+
+ 6. Two minor patches to pcrecpp.cc in order to allow it to compile on older
+    versions of gcc, e.g. 2.95.4.
+
+
+Version 6.1 21-Jun-05
+---------------------
+
+ 1. There was one reference to the variable "posix" in pcretest.c that was not
+    surrounded by "#if !defined NOPOSIX".
+
+ 2. Make it possible to compile pcretest without DFA support, UTF8 support, or
+    the cross-check on the old pcre_info() function, for the benefit of the
+    cut-down version of PCRE that is currently imported into Exim.
+
+ 3. A (silly) pattern starting with (?i)(?-i) caused an internal space
+    allocation error. I've done the easy fix, which wastes 2 bytes for sensible
+    patterns that start (?i) but I don't think that matters. The use of (?i) is
+    just an example; this all applies to the other options as well.
+
+ 4. Since libtool seems to echo the compile commands it is issuing, the output
+    from "make" can be reduced a bit by putting "@" in front of each libtool
+    compile command.
+
+ 5. Patch from the folks at Google for configure.in to be a bit more thorough
+    in checking for a suitable C++ installation before trying to compile the
+    C++ stuff. This should fix a reported problem when a compiler was present,
+    but no suitable headers.
+
+ 6. The man pages all had just "PCRE" as their title. I have changed them to
+    be the relevant file name. I have also arranged that these names are
+    retained in the file doc/pcre.txt, which is a concatenation in text format
+    of all the man pages except the little individual ones for each function.
+
+ 7. The NON-UNIX-USE file had not been updated for the different set of source
+    files that come with release 6. I also added a few comments about the C++
+    wrapper.
+
+
+Version 6.0 07-Jun-05
+---------------------
+
+ 1. Some minor internal re-organization to help with my DFA experiments.
+
+ 2. Some missing #ifdef SUPPORT_UCP conditionals in pcretest and printint that
+    didn't matter for the library itself when fully configured, but did matter
+    when compiling without UCP support, or within Exim, where the ucp files are
+    not imported.
+
+ 3. Refactoring of the library code to split up the various functions into
+    different source modules. The addition of the new DFA matching code (see
+    below) to a single monolithic source would have made it really too
+    unwieldy, quite apart from causing all the code to be include in a
+    statically linked application, when only some functions are used. This is
+    relevant even without the DFA addition now that patterns can be compiled in
+    one application and matched in another.
+
+    The downside of splitting up is that there have to be some external
+    functions and data tables that are used internally in different modules of
+    the library but which are not part of the API. These have all had their
+    names changed to start with "_pcre_" so that they are unlikely to clash
+    with other external names.
+
+ 4. Added an alternate matching function, pcre_dfa_exec(), which matches using
+    a different (DFA) algorithm. Although it is slower than the original
+    function, it does have some advantages for certain types of matching
+    problem.
+
+ 5. Upgrades to pcretest in order to test the features of pcre_dfa_exec(),
+    including restarting after a partial match.
+
+ 6. A patch for pcregrep that defines INVALID_FILE_ATTRIBUTES if it is not
+    defined when compiling for Windows was sent to me. I have put it into the
+    code, though I have no means of testing or verifying it.
+
+ 7. Added the pcre_refcount() auxiliary function.
+
+ 8. Added the PCRE_FIRSTLINE option. This constrains an unanchored pattern to
+    match before or at the first newline in the subject string. In pcretest,
+    the /f option on a pattern can be used to set this.
+
+ 9. A repeated \w when used in UTF-8 mode with characters greater than 256
+    would behave wrongly. This has been present in PCRE since release 4.0.
+
+10. A number of changes to the pcregrep command:
+
+    (a) Refactored how -x works; insert ^(...)$ instead of setting
+        PCRE_ANCHORED and checking the length, in preparation for adding
+        something similar for -w.
+
+    (b) Added the -w (match as a word) option.
+
+    (c) Refactored the way lines are read and buffered so as to have more
+        than one at a time available.
+
+    (d) Implemented a pcregrep test script.
+
+    (e) Added the -M (multiline match) option. This allows patterns to match
+        over several lines of the subject. The buffering ensures that at least
+        8K, or the rest of the document (whichever is the shorter) is available
+        for matching (and similarly the previous 8K for lookbehind assertions).
+
+    (f) Changed the --help output so that it now says
+
+          -w, --word-regex(p)
+
+        instead of two lines, one with "regex" and the other with "regexp"
+        because that confused at least one person since the short forms are the
+        same. (This required a bit of code, as the output is generated
+        automatically from a table. It wasn't just a text change.)
+
+    (g) -- can be used to terminate pcregrep options if the next thing isn't an
+        option but starts with a hyphen. Could be a pattern or a path name
+        starting with a hyphen, for instance.
+
+    (h) "-" can be given as a file name to represent stdin.
+
+    (i) When file names are being printed, "(standard input)" is used for
+        the standard input, for compatibility with GNU grep. Previously
+        "<stdin>" was used.
+
+    (j) The option --label=xxx can be used to supply a name to be used for
+        stdin when file names are being printed. There is no short form.
+
+    (k) Re-factored the options decoding logic because we are going to add
+        two more options that take data. Such options can now be given in four
+        different ways, e.g. "-fname", "-f name", "--file=name", "--file name".
+
+    (l) Added the -A, -B, and -C options for requesting that lines of context
+        around matches be printed.
+
+    (m) Added the -L option to print the names of files that do not contain
+        any matching lines, that is, the complement of -l.
+
+    (n) The return code is 2 if any file cannot be opened, but pcregrep does
+        continue to scan other files.
+
+    (o) The -s option was incorrectly implemented. For compatibility with other
+        greps, it now suppresses the error message for a non-existent or non-
+        accessible file (but not the return code). There is a new option called
+        -q that suppresses the output of matching lines, which was what -s was
+        previously doing.
+
+    (p) Added --include and --exclude options to specify files for inclusion
+        and exclusion when recursing.
+
+11. The Makefile was not using the Autoconf-supported LDFLAGS macro properly.
+    Hopefully, it now does.
+
+12. Missing cast in pcre_study().
+
+13. Added an "uninstall" target to the makefile.
+
+14. Replaced "extern" in the function prototypes in Makefile.in with
+    "PCRE_DATA_SCOPE", which defaults to 'extern' or 'extern "C"' in the Unix
+    world, but is set differently for Windows.
+
+15. Added a second compiling function called pcre_compile2(). The only
+    difference is that it has an extra argument, which is a pointer to an
+    integer error code. When there is a compile-time failure, this is set
+    non-zero, in addition to the error test pointer being set to point to an
+    error message. The new argument may be NULL if no error number is required
+    (but then you may as well call pcre_compile(), which is now just a
+    wrapper). This facility is provided because some applications need a
+    numeric error indication, but it has also enabled me to tidy up the way
+    compile-time errors are handled in the POSIX wrapper.
+
+16. Added VPATH=.libs to the makefile; this should help when building with one
+    prefix path and installing with another. (Or so I'm told by someone who
+    knows more about this stuff than I do.)
+
+17. Added a new option, REG_DOTALL, to the POSIX function regcomp(). This
+    passes PCRE_DOTALL to the pcre_compile() function, making the "." character
+    match everything, including newlines. This is not POSIX-compatible, but
+    somebody wanted the feature. From pcretest it can be activated by using
+    both the P and the s flags.
+
+18. AC_PROG_LIBTOOL appeared twice in Makefile.in. Removed one.
+
+19. libpcre.pc was being incorrectly installed as executable.
+
+20. A couple of places in pcretest check for end-of-line by looking for '\n';
+    it now also looks for '\r' so that it will work unmodified on Windows.
+
+21. Added Google's contributed C++ wrapper to the distribution.
+
+22. Added some untidy missing memory free() calls in pcretest, to keep
+    Electric Fence happy when testing.
+
+
+
+Version 5.0 13-Sep-04
+---------------------
+
+ 1. Internal change: literal characters are no longer packed up into items
+    containing multiple characters in a single byte-string. Each character
+    is now matched using a separate opcode. However, there may be more than one
+    byte in the character in UTF-8 mode.
+
+ 2. The pcre_callout_block structure has two new fields: pattern_position and
+    next_item_length. These contain the offset in the pattern to the next match
+    item, and its length, respectively.
+
+ 3. The PCRE_AUTO_CALLOUT option for pcre_compile() requests the automatic
+    insertion of callouts before each pattern item. Added the /C option to
+    pcretest to make use of this.
+
+ 4. On the advice of a Windows user, the lines
+
+      #if defined(_WIN32) || defined(WIN32)
+      _setmode( _fileno( stdout ), 0x8000 );
+      #endif  /* defined(_WIN32) || defined(WIN32) */
+
+    have been added to the source of pcretest. This apparently does useful
+    magic in relation to line terminators.
+
+ 5. Changed "r" and "w" in the calls to fopen() in pcretest to "rb" and "wb"
+    for the benefit of those environments where the "b" makes a difference.
+
+ 6. The icc compiler has the same options as gcc, but "configure" doesn't seem
+    to know about it. I have put a hack into configure.in that adds in code
+    to set GCC=yes if CC=icc. This seems to end up at a point in the
+    generated configure script that is early enough to affect the setting of
+    compiler options, which is what is needed, but I have no means of testing
+    whether it really works. (The user who reported this had patched the
+    generated configure script, which of course I cannot do.)
+
+    LATER: After change 22 below (new libtool files), the configure script
+    seems to know about icc (and also ecc). Therefore, I have commented out
+    this hack in configure.in.
+
+ 7. Added support for pkg-config (2 patches were sent in).
+
+ 8. Negated POSIX character classes that used a combination of internal tables
+    were completely broken. These were [[:^alpha:]], [[:^alnum:]], and
+    [[:^ascii]]. Typically, they would match almost any characters. The other
+    POSIX classes were not broken in this way.
+
+ 9. Matching the pattern "\b.*?" against "ab cd", starting at offset 1, failed
+    to find the match, as PCRE was deluded into thinking that the match had to
+    start at the start point or following a newline. The same bug applied to
+    patterns with negative forward assertions or any backward assertions
+    preceding ".*" at the start, unless the pattern required a fixed first
+    character. This was a failing pattern: "(?!.bcd).*". The bug is now fixed.
+
+10. In UTF-8 mode, when moving forwards in the subject after a failed match
+    starting at the last subject character, bytes beyond the end of the subject
+    string were read.
+
+11. Renamed the variable "class" as "classbits" to make life easier for C++
+    users. (Previously there was a macro definition, but it apparently wasn't
+    enough.)
+
+12. Added the new field "tables" to the extra data so that tables can be passed
+    in at exec time, or the internal tables can be re-selected. This allows
+    a compiled regex to be saved and re-used at a later time by a different
+    program that might have everything at different addresses.
+
+13. Modified the pcre-config script so that, when run on Solaris, it shows a
+    -R library as well as a -L library.
+
+14. The debugging options of pcretest (-d on the command line or D on a
+    pattern) showed incorrect output for anything following an extended class
+    that contained multibyte characters and which was followed by a quantifier.
+
+15. Added optional support for general category Unicode character properties
+    via the \p, \P, and \X escapes. Unicode property support implies UTF-8
+    support. It adds about 90K to the size of the library. The meanings of the
+    inbuilt class escapes such as \d and \s have NOT been changed.
+
+16. Updated pcredemo.c to include calls to free() to release the memory for the
+    compiled pattern.
+
+17. The generated file chartables.c was being created in the source directory
+    instead of in the building directory. This caused the build to fail if the
+    source directory was different from the building directory, and was
+    read-only.
+
+18. Added some sample Win commands from Mark Tetrode into the NON-UNIX-USE
+    file. No doubt somebody will tell me if they don't make sense... Also added
+    Dan Mooney's comments about building on OpenVMS.
+
+19. Added support for partial matching via the PCRE_PARTIAL option for
+    pcre_exec() and the \P data escape in pcretest.
+
+20. Extended pcretest with 3 new pattern features:
+
+    (i)   A pattern option of the form ">rest-of-line" causes pcretest to
+          write the compiled pattern to the file whose name is "rest-of-line".
+          This is a straight binary dump of the data, with the saved pointer to
+          the character tables forced to be NULL. The study data, if any, is
+          written too. After writing, pcretest reads a new pattern.
+
+    (ii)  If, instead of a pattern, "<rest-of-line" is given, pcretest reads a
+          compiled pattern from the given file. There must not be any
+          occurrences of "<" in the file name (pretty unlikely); if there are,
+          pcretest will instead treat the initial "<" as a pattern delimiter.
+          After reading in the pattern, pcretest goes on to read data lines as
+          usual.
+
+    (iii) The F pattern option causes pcretest to flip the bytes in the 32-bit
+          and 16-bit fields in a compiled pattern, to simulate a pattern that
+          was compiled on a host of opposite endianness.
+
+21. The pcre-exec() function can now cope with patterns that were compiled on
+    hosts of opposite endianness, with this restriction:
+
+      As for any compiled expression that is saved and used later, the tables
+      pointer field cannot be preserved; the extra_data field in the arguments
+      to pcre_exec() should be used to pass in a tables address if a value
+      other than the default internal tables were used at compile time.
+
+22. Calling pcre_exec() with a negative value of the "ovecsize" parameter is
+    now diagnosed as an error. Previously, most of the time, a negative number
+    would have been treated as zero, but if in addition "ovector" was passed as
+    NULL, a crash could occur.
+
+23. Updated the files ltmain.sh, config.sub, config.guess, and aclocal.m4 with
+    new versions from the libtool 1.5 distribution (the last one is a copy of
+    a file called libtool.m4). This seems to have fixed the need to patch
+    "configure" to support Darwin 1.3 (which I used to do). However, I still
+    had to patch ltmain.sh to ensure that ${SED} is set (it isn't on my
+    workstation).
+
+24. Changed the PCRE licence to be the more standard "BSD" licence.
+
+
+Version 4.5 01-Dec-03
+---------------------
+
+ 1. There has been some re-arrangement of the code for the match() function so
+    that it can be compiled in a version that does not call itself recursively.
+    Instead, it keeps those local variables that need separate instances for
+    each "recursion" in a frame on the heap, and gets/frees frames whenever it
+    needs to "recurse". Keeping track of where control must go is done by means
+    of setjmp/longjmp. The whole thing is implemented by a set of macros that
+    hide most of the details from the main code, and operates only if
+    NO_RECURSE is defined while compiling pcre.c. If PCRE is built using the
+    "configure" mechanism, "--disable-stack-for-recursion" turns on this way of
+    operating.
+
+    To make it easier for callers to provide specially tailored get/free
+    functions for this usage, two new functions, pcre_stack_malloc, and
+    pcre_stack_free, are used. They are always called in strict stacking order,
+    and the size of block requested is always the same.
+
+    The PCRE_CONFIG_STACKRECURSE info parameter can be used to find out whether
+    PCRE has been compiled to use the stack or the heap for recursion. The
+    -C option of pcretest uses this to show which version is compiled.
+
+    A new data escape \S, is added to pcretest; it causes the amounts of store
+    obtained and freed by both kinds of malloc/free at match time to be added
+    to the output.
+
+ 2. Changed the locale test to use "fr_FR" instead of "fr" because that's
+    what's available on my current Linux desktop machine.
+
+ 3. When matching a UTF-8 string, the test for a valid string at the start has
+    been extended. If start_offset is not zero, PCRE now checks that it points
+    to a byte that is the start of a UTF-8 character. If not, it returns
+    PCRE_ERROR_BADUTF8_OFFSET (-11). Note: the whole string is still checked;
+    this is necessary because there may be backward assertions in the pattern.
+    When matching the same subject several times, it may save resources to use
+    PCRE_NO_UTF8_CHECK on all but the first call if the string is long.
+
+ 4. The code for checking the validity of UTF-8 strings has been tightened so
+    that it rejects (a) strings containing 0xfe or 0xff bytes and (b) strings
+    containing "overlong sequences".
+
+ 5. Fixed a bug (appearing twice) that I could not find any way of exploiting!
+    I had written "if ((digitab[*p++] && chtab_digit) == 0)" where the "&&"
+    should have been "&", but it just so happened that all the cases this let
+    through by mistake were picked up later in the function.
+
+ 6. I had used a variable called "isblank" - this is a C99 function, causing
+    some compilers to warn. To avoid this, I renamed it (as "blankclass").
+
+ 7. Cosmetic: (a) only output another newline at the end of pcretest if it is
+    prompting; (b) run "./pcretest /dev/null" at the start of the test script
+    so the version is shown; (c) stop "make test" echoing "./RunTest".
+
+ 8. Added patches from David Burgess to enable PCRE to run on EBCDIC systems.
+
+ 9. The prototype for memmove() for systems that don't have it was using
+    size_t, but the inclusion of the header that defines size_t was later. I've
+    moved the #includes for the C headers earlier to avoid this.
+
+10. Added some adjustments to the code to make it easier to compiler on certain
+    special systems:
+
+      (a) Some "const" qualifiers were missing.
+      (b) Added the macro EXPORT before all exported functions; by default this
+          is defined to be empty.
+      (c) Changed the dftables auxiliary program (that builds chartables.c) so
+          that it reads its output file name as an argument instead of writing
+          to the standard output and assuming this can be redirected.
+
+11. In UTF-8 mode, if a recursive reference (e.g. (?1)) followed a character
+    class containing characters with values greater than 255, PCRE compilation
+    went into a loop.
+
+12. A recursive reference to a subpattern that was within another subpattern
+    that had a minimum quantifier of zero caused PCRE to crash. For example,
+    (x(y(?2))z)? provoked this bug with a subject that got as far as the
+    recursion. If the recursively-called subpattern itself had a zero repeat,
+    that was OK.
+
+13. In pcretest, the buffer for reading a data line was set at 30K, but the
+    buffer into which it was copied (for escape processing) was still set at
+    1024, so long lines caused crashes.
+
+14. A pattern such as /[ab]{1,3}+/ failed to compile, giving the error
+    "internal error: code overflow...". This applied to any character class
+    that was followed by a possessive quantifier.
+
+15. Modified the Makefile to add libpcre.la as a prerequisite for
+    libpcreposix.la because I was told this is needed for a parallel build to
+    work.
+
+16. If a pattern that contained .* following optional items at the start was
+    studied, the wrong optimizing data was generated, leading to matching
+    errors. For example, studying /[ab]*.*c/ concluded, erroneously, that any
+    matching string must start with a or b or c. The correct conclusion for
+    this pattern is that a match can start with any character.
+
+
+Version 4.4 13-Aug-03
+---------------------
+
+ 1. In UTF-8 mode, a character class containing characters with values between
+    127 and 255 was not handled correctly if the compiled pattern was studied.
+    In fixing this, I have also improved the studying algorithm for such
+    classes (slightly).
+
+ 2. Three internal functions had redundant arguments passed to them. Removal
+    might give a very teeny performance improvement.
+
+ 3. Documentation bug: the value of the capture_top field in a callout is *one
+    more than* the number of the hightest numbered captured substring.
+
+ 4. The Makefile linked pcretest and pcregrep with -lpcre, which could result
+    in incorrectly linking with a previously installed version. They now link
+    explicitly with libpcre.la.
+
+ 5. configure.in no longer needs to recognize Cygwin specially.
+
+ 6. A problem in pcre.in for Windows platforms is fixed.
+
+ 7. If a pattern was successfully studied, and the -d (or /D) flag was given to
+    pcretest, it used to include the size of the study block as part of its
+    output. Unfortunately, the structure contains a field that has a different
+    size on different hardware architectures. This meant that the tests that
+    showed this size failed. As the block is currently always of a fixed size,
+    this information isn't actually particularly useful in pcretest output, so
+    I have just removed it.
+
+ 8. Three pre-processor statements accidentally did not start in column 1.
+    Sadly, there are *still* compilers around that complain, even though
+    standard C has not required this for well over a decade. Sigh.
+
+ 9. In pcretest, the code for checking callouts passed small integers in the
+    callout_data field, which is a void * field. However, some picky compilers
+    complained about the casts involved for this on 64-bit systems. Now
+    pcretest passes the address of the small integer instead, which should get
+    rid of the warnings.
+
+10. By default, when in UTF-8 mode, PCRE now checks for valid UTF-8 strings at
+    both compile and run time, and gives an error if an invalid UTF-8 sequence
+    is found. There is a option for disabling this check in cases where the
+    string is known to be correct and/or the maximum performance is wanted.
+
+11. In response to a bug report, I changed one line in Makefile.in from
+
+        -Wl,--out-implib,.libs/lib@WIN_PREFIX@pcreposix.dll.a \
+    to
+        -Wl,--out-implib,.libs/@WIN_PREFIX@libpcreposix.dll.a \
+
+    to look similar to other lines, but I have no way of telling whether this
+    is the right thing to do, as I do not use Windows. No doubt I'll get told
+    if it's wrong...
+
+
+Version 4.3 21-May-03
+---------------------
+
+1. Two instances of @WIN_PREFIX@ omitted from the Windows targets in the
+   Makefile.
+
+2. Some refactoring to improve the quality of the code:
+
+   (i)   The utf8_table... variables are now declared "const".
+
+   (ii)  The code for \cx, which used the "case flipping" table to upper case
+         lower case letters, now just substracts 32. This is ASCII-specific,
+         but the whole concept of \cx is ASCII-specific, so it seems
+         reasonable.
+
+   (iii) PCRE was using its character types table to recognize decimal and
+         hexadecimal digits in the pattern. This is silly, because it handles
+         only 0-9, a-f, and A-F, but the character types table is locale-
+         specific, which means strange things might happen. A private
+         table is now used for this - though it costs 256 bytes, a table is
+         much faster than multiple explicit tests. Of course, the standard
+         character types table is still used for matching digits in subject
+         strings against \d.
+
+   (iv)  Strictly, the identifier ESC_t is reserved by POSIX (all identifiers
+         ending in _t are). So I've renamed it as ESC_tee.
+
+3. The first argument for regexec() in the POSIX wrapper should have been
+   defined as "const".
+
+4. Changed pcretest to use malloc() for its buffers so that they can be
+   Electric Fenced for debugging.
+
+5. There were several places in the code where, in UTF-8 mode, PCRE would try
+   to read one or more bytes before the start of the subject string. Often this
+   had no effect on PCRE's behaviour, but in some circumstances it could
+   provoke a segmentation fault.
+
+6. A lookbehind at the start of a pattern in UTF-8 mode could also cause PCRE
+   to try to read one or more bytes before the start of the subject string.
+
+7. A lookbehind in a pattern matched in non-UTF-8 mode on a PCRE compiled with
+   UTF-8 support could misbehave in various ways if the subject string
+   contained bytes with the 0x80 bit set and the 0x40 bit unset in a lookbehind
+   area. (PCRE was not checking for the UTF-8 mode flag, and trying to move
+   back over UTF-8 characters.)
+
+
+Version 4.2 14-Apr-03
+---------------------
+
+1. Typo "#if SUPPORT_UTF8" instead of "#ifdef SUPPORT_UTF8" fixed.
+
+2. Changes to the building process, supplied by Ronald Landheer-Cieslak
+     [ON_WINDOWS]: new variable, "#" on non-Windows platforms
+     [NOT_ON_WINDOWS]: new variable, "#" on Windows platforms
+     [WIN_PREFIX]: new variable, "cyg" for Cygwin
+     * Makefile.in: use autoconf substitution for OBJEXT, EXEEXT, BUILD_OBJEXT
+       and BUILD_EXEEXT
+     Note: automatic setting of the BUILD variables is not yet working
+     set CPPFLAGS and BUILD_CPPFLAGS (but don't use yet) - should be used at
+       compile-time but not at link-time
+     [LINK]: use for linking executables only
+     make different versions for Windows and non-Windows
+     [LINKLIB]: new variable, copy of UNIX-style LINK, used for linking
+       libraries
+     [LINK_FOR_BUILD]: new variable
+     [OBJEXT]: use throughout
+     [EXEEXT]: use throughout
+     <winshared>: new target
+     <wininstall>: new target
+     <dftables.o>: use native compiler
+     <dftables>: use native linker
+     <install>: handle Windows platform correctly
+     <clean>: ditto
+     <check>: ditto
+     copy DLL to top builddir before testing
+
+   As part of these changes, -no-undefined was removed again. This was reported
+   to give trouble on HP-UX 11.0, so getting rid of it seems like a good idea
+   in any case.
+
+3. Some tidies to get rid of compiler warnings:
+
+   . In the match_data structure, match_limit was an unsigned long int, whereas
+     match_call_count was an int. I've made them both unsigned long ints.
+
+   . In pcretest the fact that a const uschar * doesn't automatically cast to
+     a void * provoked a warning.
+
+   . Turning on some more compiler warnings threw up some "shadow" variables
+     and a few more missing casts.
+
+4. If PCRE was complied with UTF-8 support, but called without the PCRE_UTF8
+   option, a class that contained a single character with a value between 128
+   and 255 (e.g. /[\xFF]/) caused PCRE to crash.
+
+5. If PCRE was compiled with UTF-8 support, but called without the PCRE_UTF8
+   option, a class that contained several characters, but with at least one
+   whose value was between 128 and 255 caused PCRE to crash.
+
+
+Version 4.1 12-Mar-03
+---------------------
+
+1. Compiling with gcc -pedantic found a couple of places where casts were
+needed, and a string in dftables.c that was longer than standard compilers are
+required to support.
+
+2. Compiling with Sun's compiler found a few more places where the code could
+be tidied up in order to avoid warnings.
+
+3. The variables for cross-compiling were called HOST_CC and HOST_CFLAGS; the
+first of these names is deprecated in the latest Autoconf in favour of the name
+CC_FOR_BUILD, because "host" is typically used to mean the system on which the
+compiled code will be run. I can't find a reference for HOST_CFLAGS, but by
+analogy I have changed it to CFLAGS_FOR_BUILD.
+
+4. Added -no-undefined to the linking command in the Makefile, because this is
+apparently helpful for Windows. To make it work, also added "-L. -lpcre" to the
+linking step for the pcreposix library.
+
+5. PCRE was failing to diagnose the case of two named groups with the same
+name.
+
+6. A problem with one of PCRE's optimizations was discovered. PCRE remembers a
+literal character that is needed in the subject for a match, and scans along to
+ensure that it is present before embarking on the full matching process. This
+saves time in cases of nested unlimited repeats that are never going to match.
+Problem: the scan can take a lot of time if the subject is very long (e.g.
+megabytes), thus penalizing straightforward matches. It is now done only if the
+amount of subject to be scanned is less than 1000 bytes.
+
+7. A lesser problem with the same optimization is that it was recording the
+first character of an anchored pattern as "needed", thus provoking a search
+right along the subject, even when the first match of the pattern was going to
+fail. The "needed" character is now not set for anchored patterns, unless it
+follows something in the pattern that is of non-fixed length. Thus, it still
+fulfils its original purpose of finding quick non-matches in cases of nested
+unlimited repeats, but isn't used for simple anchored patterns such as /^abc/.
+
+
+Version 4.0 17-Feb-03
+---------------------
+
+1. If a comment in an extended regex that started immediately after a meta-item
+extended to the end of string, PCRE compiled incorrect data. This could lead to
+all kinds of weird effects. Example: /#/ was bad; /()#/ was bad; /a#/ was not.
+
+2. Moved to autoconf 2.53 and libtool 1.4.2.
+
+3. Perl 5.8 no longer needs "use utf8" for doing UTF-8 things. Consequently,
+the special perltest8 script is no longer needed - all the tests can be run
+from a single perltest script.
+
+4. From 5.004, Perl has not included the VT character (0x0b) in the set defined
+by \s. It has now been removed in PCRE. This means it isn't recognized as
+whitespace in /x regexes too, which is the same as Perl. Note that the POSIX
+class [:space:] *does* include VT, thereby creating a mess.
+
+5. Added the class [:blank:] (a GNU extension from Perl 5.8) to match only
+space and tab.
+
+6. Perl 5.005 was a long time ago. It's time to amalgamate the tests that use
+its new features into the main test script, reducing the number of scripts.
+
+7. Perl 5.8 has changed the meaning of patterns like /a(?i)b/. Earlier versions
+were backward compatible, and made the (?i) apply to the whole pattern, as if
+/i were given. Now it behaves more logically, and applies the option setting
+only to what follows. PCRE has been changed to follow suit. However, if it
+finds options settings right at the start of the pattern, it extracts them into
+the global options, as before. Thus, they show up in the info data.
+
+8. Added support for the \Q...\E escape sequence. Characters in between are
+treated as literals. This is slightly different from Perl in that $ and @ are
+also handled as literals inside the quotes. In Perl, they will cause variable
+interpolation. Note the following examples:
+
+    Pattern            PCRE matches      Perl matches
+
+    \Qabc$xyz\E        abc$xyz           abc followed by the contents of $xyz
+    \Qabc\$xyz\E       abc\$xyz          abc\$xyz
+    \Qabc\E\$\Qxyz\E   abc$xyz           abc$xyz
+
+For compatibility with Perl, \Q...\E sequences are recognized inside character
+classes as well as outside them.
+
+9. Re-organized 3 code statements in pcretest to avoid "overflow in
+floating-point constant arithmetic" warnings from a Microsoft compiler. Added a
+(size_t) cast to one statement in pcretest and one in pcreposix to avoid
+signed/unsigned warnings.
+
+10. SunOS4 doesn't have strtoul(). This was used only for unpicking the -o
+option for pcretest, so I've replaced it by a simple function that does just
+that job.
+
+11. pcregrep was ending with code 0 instead of 2 for the commands "pcregrep" or
+"pcregrep -".
+
+12. Added "possessive quantifiers" ?+, *+, ++, and {,}+ which come from Sun's
+Java package. This provides some syntactic sugar for simple cases of what my
+documentation calls "once-only subpatterns". A pattern such as x*+ is the same
+as (?>x*). In other words, if what is inside (?>...) is just a single repeated
+item, you can use this simplified notation. Note that only makes sense with
+greedy quantifiers. Consequently, the use of the possessive quantifier forces
+greediness, whatever the setting of the PCRE_UNGREEDY option.
+
+13. A change of greediness default within a pattern was not taking effect at
+the current level for patterns like /(b+(?U)a+)/. It did apply to parenthesized
+subpatterns that followed. Patterns like /b+(?U)a+/ worked because the option
+was abstracted outside.
+
+14. PCRE now supports the \G assertion. It is true when the current matching
+position is at the start point of the match. This differs from \A when the
+starting offset is non-zero. Used with the /g option of pcretest (or similar
+code), it works in the same way as it does for Perl's /g option. If all
+alternatives of a regex begin with \G, the expression is anchored to the start
+match position, and the "anchored" flag is set in the compiled expression.
+
+15. Some bugs concerning the handling of certain option changes within patterns
+have been fixed. These applied to options other than (?ims). For example,
+"a(?x: b c )d" did not match "XabcdY" but did match "Xa b c dY". It should have
+been the other way round. Some of this was related to change 7 above.
+
+16. PCRE now gives errors for /[.x.]/ and /[=x=]/ as unsupported POSIX
+features, as Perl does. Previously, PCRE gave the warnings only for /[[.x.]]/
+and /[[=x=]]/. PCRE now also gives an error for /[:name:]/ because it supports
+POSIX classes only within a class (e.g. /[[:alpha:]]/).
+
+17. Added support for Perl's \C escape. This matches one byte, even in UTF8
+mode. Unlike ".", it always matches newline, whatever the setting of
+PCRE_DOTALL. However, PCRE does not permit \C to appear in lookbehind
+assertions. Perl allows it, but it doesn't (in general) work because it can't
+calculate the length of the lookbehind. At least, that's the case for Perl
+5.8.0 - I've been told they are going to document that it doesn't work in
+future.
+
+18. Added an error diagnosis for escapes that PCRE does not support: these are
+\L, \l, \N, \P, \p, \U, \u, and \X.
+
+19. Although correctly diagnosing a missing ']' in a character class, PCRE was
+reading past the end of the pattern in cases such as /[abcd/.
+
+20. PCRE was getting more memory than necessary for patterns with classes that
+contained both POSIX named classes and other characters, e.g. /[[:space:]abc/.
+
+21. Added some code, conditional on #ifdef VPCOMPAT, to make life easier for
+compiling PCRE for use with Virtual Pascal.
+
+22. Small fix to the Makefile to make it work properly if the build is done
+outside the source tree.
+
+23. Added a new extension: a condition to go with recursion. If a conditional
+subpattern starts with (?(R) the "true" branch is used if recursion has
+happened, whereas the "false" branch is used only at the top level.
+
+24. When there was a very long string of literal characters (over 255 bytes
+without UTF support, over 250 bytes with UTF support), the computation of how
+much memory was required could be incorrect, leading to segfaults or other
+strange effects.
+
+25. PCRE was incorrectly assuming anchoring (either to start of subject or to
+start of line for a non-DOTALL pattern) when a pattern started with (.*) and
+there was a subsequent back reference to those brackets. This meant that, for
+example, /(.*)\d+\1/ failed to match "abc123bc". Unfortunately, it isn't
+possible to check for precisely this case. All we can do is abandon the
+optimization if .* occurs inside capturing brackets when there are any back
+references whatsoever. (See below for a better fix that came later.)
+
+26. The handling of the optimization for finding the first character of a
+non-anchored pattern, and for finding a character that is required later in the
+match were failing in some cases. This didn't break the matching; it just
+failed to optimize when it could. The way this is done has been re-implemented.
+
+27. Fixed typo in error message for invalid (?R item (it said "(?p").
+
+28. Added a new feature that provides some of the functionality that Perl
+provides with (?{...}). The facility is termed a "callout". The way it is done
+in PCRE is for the caller to provide an optional function, by setting
+pcre_callout to its entry point. Like pcre_malloc and pcre_free, this is a
+global variable. By default it is unset, which disables all calling out. To get
+the function called, the regex must include (?C) at appropriate points. This
+is, in fact, equivalent to (?C0), and any number <= 255 may be given with (?C).
+This provides a means of identifying different callout points. When PCRE
+reaches such a point in the regex, if pcre_callout has been set, the external
+function is called. It is provided with data in a structure called
+pcre_callout_block, which is defined in pcre.h. If the function returns 0,
+matching continues; if it returns a non-zero value, the match at the current
+point fails. However, backtracking will occur if possible. [This was changed
+later and other features added - see item 49 below.]
+
+29. pcretest is upgraded to test the callout functionality. It provides a
+callout function that displays information. By default, it shows the start of
+the match and the current position in the text. There are some new data escapes
+to vary what happens:
+
+    \C+         in addition, show current contents of captured substrings
+    \C-         do not supply a callout function
+    \C!n        return 1 when callout number n is reached
+    \C!n!m      return 1 when callout number n is reached for the mth time
+
+30. If pcregrep was called with the -l option and just a single file name, it
+output "<stdin>" if a match was found, instead of the file name.
+
+31. Improve the efficiency of the POSIX API to PCRE. If the number of capturing
+slots is less than POSIX_MALLOC_THRESHOLD, use a block on the stack to pass to
+pcre_exec(). This saves a malloc/free per call. The default value of
+POSIX_MALLOC_THRESHOLD is 10; it can be changed by --with-posix-malloc-threshold
+when configuring.
+
+32. The default maximum size of a compiled pattern is 64K. There have been a
+few cases of people hitting this limit. The code now uses macros to handle the
+storing of links as offsets within the compiled pattern. It defaults to 2-byte
+links, but this can be changed to 3 or 4 bytes by --with-link-size when
+configuring. Tests 2 and 5 work only with 2-byte links because they output
+debugging information about compiled patterns.
+
+33. Internal code re-arrangements:
+
+(a) Moved the debugging function for printing out a compiled regex into
+    its own source file (printint.c) and used #include to pull it into
+    pcretest.c and, when DEBUG is defined, into pcre.c, instead of having two
+    separate copies.
+
+(b) Defined the list of op-code names for debugging as a macro in
+    internal.h so that it is next to the definition of the opcodes.
+
+(c) Defined a table of op-code lengths for simpler skipping along compiled
+    code. This is again a macro in internal.h so that it is next to the
+    definition of the opcodes.
+
+34. Added support for recursive calls to individual subpatterns, along the
+lines of Robin Houston's patch (but implemented somewhat differently).
+
+35. Further mods to the Makefile to help Win32. Also, added code to pcregrep to
+allow it to read and process whole directories in Win32. This code was
+contributed by Lionel Fourquaux; it has not been tested by me.
+
+36. Added support for named subpatterns. The Python syntax (?P<name>...) is
+used to name a group. Names consist of alphanumerics and underscores, and must
+be unique. Back references use the syntax (?P=name) and recursive calls use
+(?P>name) which is a PCRE extension to the Python extension. Groups still have
+numbers. The function pcre_fullinfo() can be used after compilation to extract
+a name/number map. There are three relevant calls:
+
+  PCRE_INFO_NAMEENTRYSIZE        yields the size of each entry in the map
+  PCRE_INFO_NAMECOUNT            yields the number of entries
+  PCRE_INFO_NAMETABLE            yields a pointer to the map.
+
+The map is a vector of fixed-size entries. The size of each entry depends on
+the length of the longest name used. The first two bytes of each entry are the
+group number, most significant byte first. There follows the corresponding
+name, zero terminated. The names are in alphabetical order.
+
+37. Make the maximum literal string in the compiled code 250 for the non-UTF-8
+case instead of 255. Making it the same both with and without UTF-8 support
+means that the same test output works with both.
+
+38. There was a case of malloc(0) in the POSIX testing code in pcretest. Avoid
+calling malloc() with a zero argument.
+
+39. Change 25 above had to resort to a heavy-handed test for the .* anchoring
+optimization. I've improved things by keeping a bitmap of backreferences with
+numbers 1-31 so that if .* occurs inside capturing brackets that are not in
+fact referenced, the optimization can be applied. It is unlikely that a
+relevant occurrence of .* (i.e. one which might indicate anchoring or forcing
+the match to follow \n) will appear inside brackets with a number greater than
+31, but if it does, any back reference > 31 suppresses the optimization.
+
+40. Added a new compile-time option PCRE_NO_AUTO_CAPTURE. This has the effect
+of disabling numbered capturing parentheses. Any opening parenthesis that is
+not followed by ? behaves as if it were followed by ?: but named parentheses
+can still be used for capturing (and they will acquire numbers in the usual
+way).
+
+41. Redesigned the return codes from the match() function into yes/no/error so
+that errors can be passed back from deep inside the nested calls. A malloc
+failure while inside a recursive subpattern call now causes the
+PCRE_ERROR_NOMEMORY return instead of quietly going wrong.
+
+42. It is now possible to set a limit on the number of times the match()
+function is called in a call to pcre_exec(). This facility makes it possible to
+limit the amount of recursion and backtracking, though not in a directly
+obvious way, because the match() function is used in a number of different
+circumstances. The count starts from zero for each position in the subject
+string (for non-anchored patterns). The default limit is, for compatibility, a
+large number, namely 10 000 000. You can change this in two ways:
+
+(a) When configuring PCRE before making, you can use --with-match-limit=n
+    to set a default value for the compiled library.
+
+(b) For each call to pcre_exec(), you can pass a pcre_extra block in which
+    a different value is set. See 45 below.
+
+If the limit is exceeded, pcre_exec() returns PCRE_ERROR_MATCHLIMIT.
+
+43. Added a new function pcre_config(int, void *) to enable run-time extraction
+of things that can be changed at compile time. The first argument specifies
+what is wanted and the second points to where the information is to be placed.
+The current list of available information is:
+
+  PCRE_CONFIG_UTF8
+
+The output is an integer that is set to one if UTF-8 support is available;
+otherwise it is set to zero.
+
+  PCRE_CONFIG_NEWLINE
+
+The output is an integer that it set to the value of the code that is used for
+newline. It is either LF (10) or CR (13).
+
+  PCRE_CONFIG_LINK_SIZE
+
+The output is an integer that contains the number of bytes used for internal
+linkage in compiled expressions. The value is 2, 3, or 4. See item 32 above.
+
+  PCRE_CONFIG_POSIX_MALLOC_THRESHOLD
+
+The output is an integer that contains the threshold above which the POSIX
+interface uses malloc() for output vectors. See item 31 above.
+
+  PCRE_CONFIG_MATCH_LIMIT
+
+The output is an unsigned integer that contains the default limit of the number
+of match() calls in a pcre_exec() execution. See 42 above.
+
+44. pcretest has been upgraded by the addition of the -C option. This causes it
+to extract all the available output from the new pcre_config() function, and to
+output it. The program then exits immediately.
+
+45. A need has arisen to pass over additional data with calls to pcre_exec() in
+order to support additional features. One way would have been to define
+pcre_exec2() (for example) with extra arguments, but this would not have been
+extensible, and would also have required all calls to the original function to
+be mapped to the new one. Instead, I have chosen to extend the mechanism that
+is used for passing in "extra" data from pcre_study().
+
+The pcre_extra structure is now exposed and defined in pcre.h. It currently
+contains the following fields:
+
+  flags         a bitmap indicating which of the following fields are set
+  study_data    opaque data from pcre_study()
+  match_limit   a way of specifying a limit on match() calls for a specific
+                  call to pcre_exec()
+  callout_data  data for callouts (see 49 below)
+
+The flag bits are also defined in pcre.h, and are
+
+  PCRE_EXTRA_STUDY_DATA
+  PCRE_EXTRA_MATCH_LIMIT
+  PCRE_EXTRA_CALLOUT_DATA
+
+The pcre_study() function now returns one of these new pcre_extra blocks, with
+the actual study data pointed to by the study_data field, and the
+PCRE_EXTRA_STUDY_DATA flag set. This can be passed directly to pcre_exec() as
+before. That is, this change is entirely upwards-compatible and requires no
+change to existing code.
+
+If you want to pass in additional data to pcre_exec(), you can either place it
+in a pcre_extra block provided by pcre_study(), or create your own pcre_extra
+block.
+
+46. pcretest has been extended to test the PCRE_EXTRA_MATCH_LIMIT feature. If a
+data string contains the escape sequence \M, pcretest calls pcre_exec() several
+times with different match limits, until it finds the minimum value needed for
+pcre_exec() to complete. The value is then output. This can be instructive; for
+most simple matches the number is quite small, but for pathological cases it
+gets very large very quickly.
+
+47. There's a new option for pcre_fullinfo() called PCRE_INFO_STUDYSIZE. It
+returns the size of the data block pointed to by the study_data field in a
+pcre_extra block, that is, the value that was passed as the argument to
+pcre_malloc() when PCRE was getting memory in which to place the information
+created by pcre_study(). The fourth argument should point to a size_t variable.
+pcretest has been extended so that this information is shown after a successful
+pcre_study() call when information about the compiled regex is being displayed.
+
+48. Cosmetic change to Makefile: there's no need to have / after $(DESTDIR)
+because what follows is always an absolute path. (Later: it turns out that this
+is more than cosmetic for MinGW, because it doesn't like empty path
+components.)
+
+49. Some changes have been made to the callout feature (see 28 above):
+
+(i)  A callout function now has three choices for what it returns:
+
+       0  =>  success, carry on matching
+     > 0  =>  failure at this point, but backtrack if possible
+     < 0  =>  serious error, return this value from pcre_exec()
+
+     Negative values should normally be chosen from the set of PCRE_ERROR_xxx
+     values. In particular, returning PCRE_ERROR_NOMATCH forces a standard
+     "match failed" error. The error number PCRE_ERROR_CALLOUT is reserved for
+     use by callout functions. It will never be used by PCRE itself.
+
+(ii) The pcre_extra structure (see 45 above) has a void * field called
+     callout_data, with corresponding flag bit PCRE_EXTRA_CALLOUT_DATA. The
+     pcre_callout_block structure has a field of the same name. The contents of
+     the field passed in the pcre_extra structure are passed to the callout
+     function in the corresponding field in the callout block. This makes it
+     easier to use the same callout-containing regex from multiple threads. For
+     testing, the pcretest program has a new data escape
+
+       \C*n        pass the number n (may be negative) as callout_data
+
+     If the callout function in pcretest receives a non-zero value as
+     callout_data, it returns that value.
+
+50. Makefile wasn't handling CFLAGS properly when compiling dftables. Also,
+there were some redundant $(CFLAGS) in commands that are now specified as
+$(LINK), which already includes $(CFLAGS).
+
+51. Extensions to UTF-8 support are listed below. These all apply when (a) PCRE
+has been compiled with UTF-8 support *and* pcre_compile() has been compiled
+with the PCRE_UTF8 flag. Patterns that are compiled without that flag assume
+one-byte characters throughout. Note that case-insensitive matching applies
+only to characters whose values are less than 256. PCRE doesn't support the
+notion of cases for higher-valued characters.
+
+(i)   A character class whose characters are all within 0-255 is handled as
+      a bit map, and the map is inverted for negative classes. Previously, a
+      character > 255 always failed to match such a class; however it should
+      match if the class was a negative one (e.g. [^ab]). This has been fixed.
+
+(ii)  A negated character class with a single character < 255 is coded as
+      "not this character" (OP_NOT). This wasn't working properly when the test
+      character was multibyte, either singly or repeated.
+
+(iii) Repeats of multibyte characters are now handled correctly in UTF-8
+      mode, for example: \x{100}{2,3}.
+
+(iv)  The character escapes \b, \B, \d, \D, \s, \S, \w, and \W (either
+      singly or repeated) now correctly test multibyte characters. However,
+      PCRE doesn't recognize any characters with values greater than 255 as
+      digits, spaces, or word characters. Such characters always match \D, \S,
+      and \W, and never match \d, \s, or \w.
+
+(v)   Classes may now contain characters and character ranges with values
+      greater than 255. For example: [ab\x{100}-\x{400}].
+
+(vi)  pcregrep now has a --utf-8 option (synonym -u) which makes it call
+      PCRE in UTF-8 mode.
+
+52. The info request value PCRE_INFO_FIRSTCHAR has been renamed
+PCRE_INFO_FIRSTBYTE because it is a byte value. However, the old name is
+retained for backwards compatibility. (Note that LASTLITERAL is also a byte
+value.)
+
+53. The single man page has become too large. I have therefore split it up into
+a number of separate man pages. These also give rise to individual HTML pages;
+these are now put in a separate directory, and there is an index.html page that
+lists them all. Some hyperlinking between the pages has been installed.
+
+54. Added convenience functions for handling named capturing parentheses.
+
+55. Unknown escapes inside character classes (e.g. [\M]) and escapes that
+aren't interpreted therein (e.g. [\C]) are literals in Perl. This is now also
+true in PCRE, except when the PCRE_EXTENDED option is set, in which case they
+are faulted.
+
+56. Introduced HOST_CC and HOST_CFLAGS which can be set in the environment when
+calling configure. These values are used when compiling the dftables.c program
+which is run to generate the source of the default character tables. They
+default to the values of CC and CFLAGS. If you are cross-compiling PCRE,
+you will need to set these values.
+
+57. Updated the building process for Windows DLL, as provided by Fred Cox.
+
+
+Version 3.9 02-Jan-02
+---------------------
+
+1. A bit of extraneous text had somehow crept into the pcregrep documentation.
+
+2. If --disable-static was given, the building process failed when trying to
+build pcretest and pcregrep. (For some reason it was using libtool to compile
+them, which is not right, as they aren't part of the library.)
+
+
+Version 3.8 18-Dec-01
+---------------------
+
+1. The experimental UTF-8 code was completely screwed up. It was packing the
+bytes in the wrong order. How dumb can you get?
+
+
+Version 3.7 29-Oct-01
+---------------------
+
+1. In updating pcretest to check change 1 of version 3.6, I screwed up.
+This caused pcretest, when used on the test data, to segfault. Unfortunately,
+this didn't happen under Solaris 8, where I normally test things.
+
+2. The Makefile had to be changed to make it work on BSD systems, where 'make'
+doesn't seem to recognize that ./xxx and xxx are the same file. (This entry
+isn't in ChangeLog distributed with 3.7 because I forgot when I hastily made
+this fix an hour or so after the initial 3.7 release.)
+
+
+Version 3.6 23-Oct-01
+---------------------
+
+1. Crashed with /(sens|respons)e and \1ibility/ and "sense and sensibility" if
+offsets passed as NULL with zero offset count.
+
+2. The config.guess and config.sub files had not been updated when I moved to
+the latest autoconf.
+
+
+Version 3.5 15-Aug-01
+---------------------
+
+1. Added some missing #if !defined NOPOSIX conditionals in pcretest.c that
+had been forgotten.
+
+2. By using declared but undefined structures, we can avoid using "void"
+definitions in pcre.h while keeping the internal definitions of the structures
+private.
+
+3. The distribution is now built using autoconf 2.50 and libtool 1.4. From a
+user point of view, this means that both static and shared libraries are built
+by default, but this can be individually controlled. More of the work of
+handling this static/shared cases is now inside libtool instead of PCRE's make
+file.
+
+4. The pcretest utility is now installed along with pcregrep because it is
+useful for users (to test regexs) and by doing this, it automatically gets
+relinked by libtool. The documentation has been turned into a man page, so
+there are now .1, .txt, and .html versions in /doc.
+
+5. Upgrades to pcregrep:
+   (i)   Added long-form option names like gnu grep.
+   (ii)  Added --help to list all options with an explanatory phrase.
+   (iii) Added -r, --recursive to recurse into sub-directories.
+   (iv)  Added -f, --file to read patterns from a file.
+
+6. pcre_exec() was referring to its "code" argument before testing that
+argument for NULL (and giving an error if it was NULL).
+
+7. Upgraded Makefile.in to allow for compiling in a different directory from
+the source directory.
+
+8. Tiny buglet in pcretest: when pcre_fullinfo() was called to retrieve the
+options bits, the pointer it was passed was to an int instead of to an unsigned
+long int. This mattered only on 64-bit systems.
+
+9. Fixed typo (3.4/1) in pcre.h again. Sigh. I had changed pcre.h (which is
+generated) instead of pcre.in, which it its source. Also made the same change
+in several of the .c files.
+
+10. A new release of gcc defines printf() as a macro, which broke pcretest
+because it had an ifdef in the middle of a string argument for printf(). Fixed
+by using separate calls to printf().
+
+11. Added --enable-newline-is-cr and --enable-newline-is-lf to the configure
+script, to force use of CR or LF instead of \n in the source. On non-Unix
+systems, the value can be set in config.h.
+
+12. The limit of 200 on non-capturing parentheses is a _nesting_ limit, not an
+absolute limit. Changed the text of the error message to make this clear, and
+likewise updated the man page.
+
+13. The limit of 99 on the number of capturing subpatterns has been removed.
+The new limit is 65535, which I hope will not be a "real" limit.
+
+
+Version 3.4 22-Aug-00
+---------------------
+
+1. Fixed typo in pcre.h: unsigned const char * changed to const unsigned char *.
+
+2. Diagnose condition (?(0) as an error instead of crashing on matching.
+
+
+Version 3.3 01-Aug-00
+---------------------
+
+1. If an octal character was given, but the value was greater than \377, it
+was not getting masked to the least significant bits, as documented. This could
+lead to crashes in some systems.
+
+2. Perl 5.6 (if not earlier versions) accepts classes like [a-\d] and treats
+the hyphen as a literal. PCRE used to give an error; it now behaves like Perl.
+
+3. Added the functions pcre_free_substring() and pcre_free_substring_list().
+These just pass their arguments on to (pcre_free)(), but they are provided
+because some uses of PCRE bind it to non-C systems that can call its functions,
+but cannot call free() or pcre_free() directly.
+
+4. Add "make test" as a synonym for "make check". Corrected some comments in
+the Makefile.
+
+5. Add $(DESTDIR)/ in front of all the paths in the "install" target in the
+Makefile.
+
+6. Changed the name of pgrep to pcregrep, because Solaris has introduced a
+command called pgrep for grepping around the active processes.
+
+7. Added the beginnings of support for UTF-8 character strings.
+
+8. Arranged for the Makefile to pass over the settings of CC, CFLAGS, and
+RANLIB to ./ltconfig so that they are used by libtool. I think these are all
+the relevant ones. (AR is not passed because ./ltconfig does its own figuring
+out for the ar command.)
+
+
+Version 3.2 12-May-00
+---------------------
+
+This is purely a bug fixing release.
+
+1. If the pattern /((Z)+|A)*/ was matched agained ZABCDEFG it matched Z instead
+of ZA. This was just one example of several cases that could provoke this bug,
+which was introduced by change 9 of version 2.00. The code for breaking
+infinite loops after an iteration that matches an empty string was't working
+correctly.
+
+2. The pcretest program was not imitating Perl correctly for the pattern /a*/g
+when matched against abbab (for example). After matching an empty string, it
+wasn't forcing anchoring when setting PCRE_NOTEMPTY for the next attempt; this
+caused it to match further down the string than it should.
+
+3. The code contained an inclusion of sys/types.h. It isn't clear why this
+was there because it doesn't seem to be needed, and it causes trouble on some
+systems, as it is not a Standard C header. It has been removed.
+
+4. Made 4 silly changes to the source to avoid stupid compiler warnings that
+were reported on the Macintosh. The changes were from
+
+  while ((c = *(++ptr)) != 0 && c != '\n');
+to
+  while ((c = *(++ptr)) != 0 && c != '\n') ;
+
+Totally extraordinary, but if that's what it takes...
+
+5. PCRE is being used in one environment where neither memmove() nor bcopy() is
+available. Added HAVE_BCOPY and an autoconf test for it; if neither
+HAVE_MEMMOVE nor HAVE_BCOPY is set, use a built-in emulation function which
+assumes the way PCRE uses memmove() (always moving upwards).
+
+6. PCRE is being used in one environment where strchr() is not available. There
+was only one use in pcre.c, and writing it out to avoid strchr() probably gives
+faster code anyway.
+
+
+Version 3.1 09-Feb-00
+---------------------
+
+The only change in this release is the fixing of some bugs in Makefile.in for
+the "install" target:
+
+(1) It was failing to install pcreposix.h.
+
+(2) It was overwriting the pcre.3 man page with the pcreposix.3 man page.
+
+
+Version 3.0 01-Feb-00
+---------------------
+
+1. Add support for the /+ modifier to perltest (to output $` like it does in
+pcretest).
+
+2. Add support for the /g modifier to perltest.
+
+3. Fix pcretest so that it behaves even more like Perl for /g when the pattern
+matches null strings.
+
+4. Fix perltest so that it doesn't do unwanted things when fed an empty
+pattern. Perl treats empty patterns specially - it reuses the most recent
+pattern, which is not what we want. Replace // by /(?#)/ in order to avoid this
+effect.
+
+5. The POSIX interface was broken in that it was just handing over the POSIX
+captured string vector to pcre_exec(), but (since release 2.00) PCRE has
+required a bigger vector, with some working space on the end. This means that
+the POSIX wrapper now has to get and free some memory, and copy the results.
+
+6. Added some simple autoconf support, placing the test data and the
+documentation in separate directories, re-organizing some of the
+information files, and making it build pcre-config (a GNU standard). Also added
+libtool support for building PCRE as a shared library, which is now the
+default.
+
+7. Got rid of the leading zero in the definition of PCRE_MINOR because 08 and
+09 are not valid octal constants. Single digits will be used for minor values
+less than 10.
+
+8. Defined REG_EXTENDED and REG_NOSUB as zero in the POSIX header, so that
+existing programs that set these in the POSIX interface can use PCRE without
+modification.
+
+9. Added a new function, pcre_fullinfo() with an extensible interface. It can
+return all that pcre_info() returns, plus additional data. The pcre_info()
+function is retained for compatibility, but is considered to be obsolete.
+
+10. Added experimental recursion feature (?R) to handle one common case that
+Perl 5.6 will be able to do with (?p{...}).
+
+11. Added support for POSIX character classes like [:alpha:], which Perl is
+adopting.
+
+
+Version 2.08 31-Aug-99
+----------------------
+
+1. When startoffset was not zero and the pattern began with ".*", PCRE was not
+trying to match at the startoffset position, but instead was moving forward to
+the next newline as if a previous match had failed.
+
+2. pcretest was not making use of PCRE_NOTEMPTY when repeating for /g and /G,
+and could get into a loop if a null string was matched other than at the start
+of the subject.
+
+3. Added definitions of PCRE_MAJOR and PCRE_MINOR to pcre.h so the version can
+be distinguished at compile time, and for completeness also added PCRE_DATE.
+
+5. Added Paul Sokolovsky's minor changes to make it easy to compile a Win32 DLL
+in GnuWin32 environments.
+
+
+Version 2.07 29-Jul-99
+----------------------
+
+1. The documentation is now supplied in plain text form and HTML as well as in
+the form of man page sources.
+
+2. C++ compilers don't like assigning (void *) values to other pointer types.
+In particular this affects malloc(). Although there is no problem in Standard
+C, I've put in casts to keep C++ compilers happy.
+
+3. Typo on pcretest.c; a cast of (unsigned char *) in the POSIX regexec() call
+should be (const char *).
+
+4. If NOPOSIX is defined, pcretest.c compiles without POSIX support. This may
+be useful for non-Unix systems who don't want to bother with the POSIX stuff.
+However, I haven't made this a standard facility. The documentation doesn't
+mention it, and the Makefile doesn't support it.
+
+5. The Makefile now contains an "install" target, with editable destinations at
+the top of the file. The pcretest program is not installed.
+
+6. pgrep -V now gives the PCRE version number and date.
+
+7. Fixed bug: a zero repetition after a literal string (e.g. /abcde{0}/) was
+causing the entire string to be ignored, instead of just the last character.
+
+8. If a pattern like /"([^\\"]+|\\.)*"/ is applied in the normal way to a
+non-matching string, it can take a very, very long time, even for strings of
+quite modest length, because of the nested recursion. PCRE now does better in
+some of these cases. It does this by remembering the last required literal
+character in the pattern, and pre-searching the subject to ensure it is present
+before running the real match. In other words, it applies a heuristic to detect
+some types of certain failure quickly, and in the above example, if presented
+with a string that has no trailing " it gives "no match" very quickly.
+
+9. A new runtime option PCRE_NOTEMPTY causes null string matches to be ignored;
+other alternatives are tried instead.
+
+
+Version 2.06 09-Jun-99
+----------------------
+
+1. Change pcretest's output for amount of store used to show just the code
+space, because the remainder (the data block) varies in size between 32-bit and
+64-bit systems.
+
+2. Added an extra argument to pcre_exec() to supply an offset in the subject to
+start matching at. This allows lookbehinds to work when searching for multiple
+occurrences in a string.
+
+3. Added additional options to pcretest for testing multiple occurrences:
+
+   /+   outputs the rest of the string that follows a match
+   /g   loops for multiple occurrences, using the new startoffset argument
+   /G   loops for multiple occurrences by passing an incremented pointer
+
+4. PCRE wasn't doing the "first character" optimization for patterns starting
+with \b or \B, though it was doing it for other lookbehind assertions. That is,
+it wasn't noticing that a match for a pattern such as /\bxyz/ has to start with
+the letter 'x'. On long subject strings, this gives a significant speed-up.
+
+
+Version 2.05 21-Apr-99
+----------------------
+
+1. Changed the type of magic_number from int to long int so that it works
+properly on 16-bit systems.
+
+2. Fixed a bug which caused patterns starting with .* not to work correctly
+when the subject string contained newline characters. PCRE was assuming
+anchoring for such patterns in all cases, which is not correct because .* will
+not pass a newline unless PCRE_DOTALL is set. It now assumes anchoring only if
+DOTALL is set at top level; otherwise it knows that patterns starting with .*
+must be retried after every newline in the subject.
+
+
+Version 2.04 18-Feb-99
+----------------------
+
+1. For parenthesized subpatterns with repeats whose minimum was zero, the
+computation of the store needed to hold the pattern was incorrect (too large).
+If such patterns were nested a few deep, this could multiply and become a real
+problem.
+
+2. Added /M option to pcretest to show the memory requirement of a specific
+pattern. Made -m a synonym of -s (which does this globally) for compatibility.
+
+3. Subpatterns of the form (regex){n,m} (i.e. limited maximum) were being
+compiled in such a way that the backtracking after subsequent failure was
+pessimal. Something like (a){0,3} was compiled as (a)?(a)?(a)? instead of
+((a)((a)(a)?)?)? with disastrous performance if the maximum was of any size.
+
+
+Version 2.03 02-Feb-99
+----------------------
+
+1. Fixed typo and small mistake in man page.
+
+2. Added 4th condition (GPL supersedes if conflict) and created separate
+LICENCE file containing the conditions.
+
+3. Updated pcretest so that patterns such as /abc\/def/ work like they do in
+Perl, that is the internal \ allows the delimiter to be included in the
+pattern. Locked out the use of \ as a delimiter. If \ immediately follows
+the final delimiter, add \ to the end of the pattern (to test the error).
+
+4. Added the convenience functions for extracting substrings after a successful
+match. Updated pcretest to make it able to test these functions.
+
+
+Version 2.02 14-Jan-99
+----------------------
+
+1. Initialized the working variables associated with each extraction so that
+their saving and restoring doesn't refer to uninitialized store.
+
+2. Put dummy code into study.c in order to trick the optimizer of the IBM C
+compiler for OS/2 into generating correct code. Apparently IBM isn't going to
+fix the problem.
+
+3. Pcretest: the timing code wasn't using LOOPREPEAT for timing execution
+calls, and wasn't printing the correct value for compiling calls. Increased the
+default value of LOOPREPEAT, and the number of significant figures in the
+times.
+
+4. Changed "/bin/rm" in the Makefile to "-rm" so it works on Windows NT.
+
+5. Renamed "deftables" as "dftables" to get it down to 8 characters, to avoid
+a building problem on Windows NT with a FAT file system.
+
+
+Version 2.01 21-Oct-98
+----------------------
+
+1. Changed the API for pcre_compile() to allow for the provision of a pointer
+to character tables built by pcre_maketables() in the current locale. If NULL
+is passed, the default tables are used.
+
+
+Version 2.00 24-Sep-98
+----------------------
+
+1. Since the (>?) facility is in Perl 5.005, don't require PCRE_EXTRA to enable
+it any more.
+
+2. Allow quantification of (?>) groups, and make it work correctly.
+
+3. The first character computation wasn't working for (?>) groups.
+
+4. Correct the implementation of \Z (it is permitted to match on the \n at the
+end of the subject) and add 5.005's \z, which really does match only at the
+very end of the subject.
+
+5. Remove the \X "cut" facility; Perl doesn't have it, and (?> is neater.
+
+6. Remove the ability to specify CASELESS, MULTILINE, DOTALL, and
+DOLLAR_END_ONLY at runtime, to make it possible to implement the Perl 5.005
+localized options. All options to pcre_study() were also removed.
+
+7. Add other new features from 5.005:
+
+   $(?<=           positive lookbehind
+   $(?<!           negative lookbehind
+   (?imsx-imsx)    added the unsetting capability
+                   such a setting is global if at outer level; local otherwise
+   (?imsx-imsx:)   non-capturing groups with option setting
+   (?(cond)re|re)  conditional pattern matching
+
+   A backreference to itself in a repeated group matches the previous
+   captured string.
+
+8. General tidying up of studying (both automatic and via "study")
+consequential on the addition of new assertions.
+
+9. As in 5.005, unlimited repeated groups that could match an empty substring
+are no longer faulted at compile time. Instead, the loop is forcibly broken at
+runtime if any iteration does actually match an empty substring.
+
+10. Include the RunTest script in the distribution.
+
+11. Added tests from the Perl 5.005_02 distribution. This showed up a few
+discrepancies, some of which were old and were also with respect to 5.004. They
+have now been fixed.
+
+
+Version 1.09 28-Apr-98
+----------------------
+
+1. A negated single character class followed by a quantifier with a minimum
+value of one (e.g.  [^x]{1,6}  ) was not compiled correctly. This could lead to
+program crashes, or just wrong answers. This did not apply to negated classes
+containing more than one character, or to minima other than one.
+
+
+Version 1.08 27-Mar-98
+----------------------
+
+1. Add PCRE_UNGREEDY to invert the greediness of quantifiers.
+
+2. Add (?U) and (?X) to set PCRE_UNGREEDY and PCRE_EXTRA respectively. The
+latter must appear before anything that relies on it in the pattern.
+
+
+Version 1.07 16-Feb-98
+----------------------
+
+1. A pattern such as /((a)*)*/ was not being diagnosed as in error (unlimited
+repeat of a potentially empty string).
+
+
+Version 1.06 23-Jan-98
+----------------------
+
+1. Added Markus Oberhumer's little patches for C++.
+
+2. Literal strings longer than 255 characters were broken.
+
+
+Version 1.05 23-Dec-97
+----------------------
+
+1. Negated character classes containing more than one character were failing if
+PCRE_CASELESS was set at run time.
+
+
+Version 1.04 19-Dec-97
+----------------------
+
+1. Corrected the man page, where some "const" qualifiers had been omitted.
+
+2. Made debugging output print "{0,xxx}" instead of just "{,xxx}" to agree with
+input syntax.
+
+3. Fixed memory leak which occurred when a regex with back references was
+matched with an offsets vector that wasn't big enough. The temporary memory
+that is used in this case wasn't being freed if the match failed.
+
+4. Tidied pcretest to ensure it frees memory that it gets.
+
+5. Temporary memory was being obtained in the case where the passed offsets
+vector was exactly big enough.
+
+6. Corrected definition of offsetof() from change 5 below.
+
+7. I had screwed up change 6 below and broken the rules for the use of
+setjmp(). Now fixed.
+
+
+Version 1.03 18-Dec-97
+----------------------
+
+1. A erroneous regex with a missing opening parenthesis was correctly
+diagnosed, but PCRE attempted to access brastack[-1], which could cause crashes
+on some systems.
+
+2. Replaced offsetof(real_pcre, code) by offsetof(real_pcre, code[0]) because
+it was reported that one broken compiler failed on the former because "code" is
+also an independent variable.
+
+3. The erroneous regex a[]b caused an array overrun reference.
+
+4. A regex ending with a one-character negative class (e.g. /[^k]$/) did not
+fail on data ending with that character. (It was going on too far, and checking
+the next character, typically a binary zero.) This was specific to the
+optimized code for single-character negative classes.
+
+5. Added a contributed patch from the TIN world which does the following:
+
+  + Add an undef for memmove, in case the the system defines a macro for it.
+
+  + Add a definition of offsetof(), in case there isn't one. (I don't know
+    the reason behind this - offsetof() is part of the ANSI standard - but
+    it does no harm).
+
+  + Reduce the ifdef's in pcre.c using macro DPRINTF, thereby eliminating
+    most of the places where whitespace preceded '#'. I have given up and
+    allowed the remaining 2 cases to be at the margin.
+
+  + Rename some variables in pcre to eliminate shadowing. This seems very
+    pedantic, but does no harm, of course.
+
+6. Moved the call to setjmp() into its own function, to get rid of warnings
+from gcc -Wall, and avoided calling it at all unless PCRE_EXTRA is used.
+
+7. Constructs such as \d{8,} were compiling into the equivalent of
+\d{8}\d{0,65527} instead of \d{8}\d* which didn't make much difference to the
+outcome, but in this particular case used more store than had been allocated,
+which caused the bug to be discovered because it threw up an internal error.
+
+8. The debugging code in both pcre and pcretest for outputting the compiled
+form of a regex was going wrong in the case of back references followed by
+curly-bracketed repeats.
+
+
+Version 1.02 12-Dec-97
+----------------------
+
+1. Typos in pcre.3 and comments in the source fixed.
+
+2. Applied a contributed patch to get rid of places where it used to remove
+'const' from variables, and fixed some signed/unsigned and uninitialized
+variable warnings.
+
+3. Added the "runtest" target to Makefile.
+
+4. Set default compiler flag to -O2 rather than just -O.
+
+
+Version 1.01 19-Nov-97
+----------------------
+
+1. PCRE was failing to diagnose unlimited repeat of empty string for patterns
+like /([ab]*)*/, that is, for classes with more than one character in them.
+
+2. Likewise, it wasn't diagnosing patterns with "once-only" subpatterns, such
+as /((?>a*))*/ (a PCRE_EXTRA facility).
+
+
+Version 1.00 18-Nov-97
+----------------------
+
+1. Added compile-time macros to support systems such as SunOS4 which don't have
+memmove() or strerror() but have other things that can be used instead.
+
+2. Arranged that "make clean" removes the executables.
+
+
+Version 0.99 27-Oct-97
+----------------------
+
+1. Fixed bug in code for optimizing classes with only one character. It was
+initializing a 32-byte map regardless, which could cause it to run off the end
+of the memory it had got.
+
+2. Added, conditional on PCRE_EXTRA, the proposed (?>REGEX) construction.
+
+
+Version 0.98 22-Oct-97
+----------------------
+
+1. Fixed bug in code for handling temporary memory usage when there are more
+back references than supplied space in the ovector. This could cause segfaults.
+
+
+Version 0.97 21-Oct-97
+----------------------
+
+1. Added the \X "cut" facility, conditional on PCRE_EXTRA.
+
+2. Optimized negated single characters not to use a bit map.
+
+3. Brought error texts together as macro definitions; clarified some of them;
+fixed one that was wrong - it said "range out of order" when it meant "invalid
+escape sequence".
+
+4. Changed some char * arguments to const char *.
+
+5. Added PCRE_NOTBOL and PCRE_NOTEOL (from POSIX).
+
+6. Added the POSIX-style API wrapper in pcreposix.a and testing facilities in
+pcretest.
+
+
+Version 0.96 16-Oct-97
+----------------------
+
+1. Added a simple "pgrep" utility to the distribution.
+
+2. Fixed an incompatibility with Perl: "{" is now treated as a normal character
+unless it appears in one of the precise forms "{ddd}", "{ddd,}", or "{ddd,ddd}"
+where "ddd" means "one or more decimal digits".
+
+3. Fixed serious bug. If a pattern had a back reference, but the call to
+pcre_exec() didn't supply a large enough ovector to record the related
+identifying subpattern, the match always failed. PCRE now remembers the number
+of the largest back reference, and gets some temporary memory in which to save
+the offsets during matching if necessary, in order to ensure that
+backreferences always work.
+
+4. Increased the compatibility with Perl in a number of ways:
+
+  (a) . no longer matches \n by default; an option PCRE_DOTALL is provided
+      to request this handling. The option can be set at compile or exec time.
+
+  (b) $ matches before a terminating newline by default; an option
+      PCRE_DOLLAR_ENDONLY is provided to override this (but not in multiline
+      mode). The option can be set at compile or exec time.
+
+  (c) The handling of \ followed by a digit other than 0 is now supposed to be
+      the same as Perl's. If the decimal number it represents is less than 10
+      or there aren't that many previous left capturing parentheses, an octal
+      escape is read. Inside a character class, it's always an octal escape,
+      even if it is a single digit.
+
+  (d) An escaped but undefined alphabetic character is taken as a literal,
+      unless PCRE_EXTRA is set. Currently this just reserves the remaining
+      escapes.
+
+  (e) {0} is now permitted. (The previous item is removed from the compiled
+      pattern).
+
+5. Changed all the names of code files so that the basic parts are no longer
+than 10 characters, and abolished the teeny "globals.c" file.
+
+6. Changed the handling of character classes; they are now done with a 32-byte
+bit map always.
+
+7. Added the -d and /D options to pcretest to make it possible to look at the
+internals of compilation without having to recompile pcre.
+
+
+Version 0.95 23-Sep-97
+----------------------
+
+1. Fixed bug in pre-pass concerning escaped "normal" characters such as \x5c or
+\x20 at the start of a run of normal characters. These were being treated as
+real characters, instead of the source characters being re-checked.
+
+
+Version 0.94 18-Sep-97
+----------------------
+
+1. The functions are now thread-safe, with the caveat that the global variables
+containing pointers to malloc() and free() or alternative functions are the
+same for all threads.
+
+2. Get pcre_study() to generate a bitmap of initial characters for non-
+anchored patterns when this is possible, and use it if passed to pcre_exec().
+
+
+Version 0.93 15-Sep-97
+----------------------
+
+1. /(b)|(:+)/ was computing an incorrect first character.
+
+2. Add pcre_study() to the API and the passing of pcre_extra to pcre_exec(),
+but not actually doing anything yet.
+
+3. Treat "-" characters in classes that cannot be part of ranges as literals,
+as Perl does (e.g. [-az] or [az-]).
+
+4. Set the anchored flag if a branch starts with .* or .*? because that tests
+all possible positions.
+
+5. Split up into different modules to avoid including unneeded functions in a
+compiled binary. However, compile and exec are still in one module. The "study"
+function is split off.
+
+6. The character tables are now in a separate module whose source is generated
+by an auxiliary program - but can then be edited by hand if required. There are
+now no calls to isalnum(), isspace(), isdigit(), isxdigit(), tolower() or
+toupper() in the code.
+
+7. Turn the malloc/free funtions variables into pcre_malloc and pcre_free and
+make them global. Abolish the function for setting them, as the caller can now
+set them directly.
+
+
+Version 0.92 11-Sep-97
+----------------------
+
+1. A repeat with a fixed maximum and a minimum of 1 for an ordinary character
+(e.g. /a{1,3}/) was broken (I mis-optimized it).
+
+2. Caseless matching was not working in character classes if the characters in
+the pattern were in upper case.
+
+3. Make ranges like [W-c] work in the same way as Perl for caseless matching.
+
+4. Make PCRE_ANCHORED public and accept as a compile option.
+
+5. Add an options word to pcre_exec() and accept PCRE_ANCHORED and
+PCRE_CASELESS at run time. Add escapes \A and \I to pcretest to cause it to
+pass them.
+
+6. Give an error if bad option bits passed at compile or run time.
+
+7. Add PCRE_MULTILINE at compile and exec time, and (?m) as well. Add \M to
+pcretest to cause it to pass that flag.
+
+8. Add pcre_info(), to get the number of identifying subpatterns, the stored
+options, and the first character, if set.
+
+9. Recognize C+ or C{n,m} where n >= 1 as providing a fixed starting character.
+
+
+Version 0.91 10-Sep-97
+----------------------
+
+1. PCRE was failing to diagnose unlimited repeats of subpatterns that could
+match the empty string as in /(a*)*/. It was looping and ultimately crashing.
+
+2. PCRE was looping on encountering an indefinitely repeated back reference to
+a subpattern that had matched an empty string, e.g. /(a|)\1*/. It now does what
+Perl does - treats the match as successful.
+
+****
diff --git a/ext/pcre/pcrelib/HACKING b/ext/pcre/pcrelib/HACKING
new file mode 100644
index 0000000..87b8819
--- /dev/null
+++ b/ext/pcre/pcrelib/HACKING
@@ -0,0 +1,468 @@
+Technical Notes about PCRE
+--------------------------
+
+These are very rough technical notes that record potentially useful information 
+about PCRE internals. For information about testing PCRE, see the pcretest 
+documentation and the comment at the head of the RunTest file.
+
+
+Historical note 1
+-----------------
+
+Many years ago I implemented some regular expression functions to an algorithm
+suggested by Martin Richards. These were not Unix-like in form, and were quite
+restricted in what they could do by comparison with Perl. The interesting part
+about the algorithm was that the amount of space required to hold the compiled
+form of an expression was known in advance. The code to apply an expression did
+not operate by backtracking, as the original Henry Spencer code and current
+Perl code does, but instead checked all possibilities simultaneously by keeping
+a list of current states and checking all of them as it advanced through the
+subject string. In the terminology of Jeffrey Friedl's book, it was a "DFA
+algorithm", though it was not a traditional Finite State Machine (FSM). When
+the pattern was all used up, all remaining states were possible matches, and
+the one matching the longest subset of the subject string was chosen. This did
+not necessarily maximize the individual wild portions of the pattern, as is
+expected in Unix and Perl-style regular expressions.
+
+
+Historical note 2
+-----------------
+
+By contrast, the code originally written by Henry Spencer (which was
+subsequently heavily modified for Perl) compiles the expression twice: once in
+a dummy mode in order to find out how much store will be needed, and then for
+real. (The Perl version probably doesn't do this any more; I'm talking about
+the original library.) The execution function operates by backtracking and
+maximizing (or, optionally, minimizing in Perl) the amount of the subject that
+matches individual wild portions of the pattern. This is an "NFA algorithm" in
+Friedl's terminology.
+
+
+OK, here's the real stuff
+-------------------------
+
+For the set of functions that form the "basic" PCRE library (which are
+unrelated to those mentioned above), I tried at first to invent an algorithm
+that used an amount of store bounded by a multiple of the number of characters
+in the pattern, to save on compiling time. However, because of the greater
+complexity in Perl regular expressions, I couldn't do this. In any case, a
+first pass through the pattern is helpful for other reasons. 
+
+
+Support for 16-bit data strings
+-------------------------------
+
+From release 8.30, PCRE supports 16-bit as well as 8-bit data strings, by being 
+compilable in either 8-bit or 16-bit modes, or both. Thus, two different 
+libraries can be created. In the description that follows, the word "short" is 
+used for a 16-bit data quantity, and the word "unit" is used for a quantity
+that is a byte in 8-bit mode and a short in 16-bit mode. However, so as not to
+over-complicate the text, the names of PCRE functions are given in 8-bit form
+only.
+
+
+Computing the memory requirement: how it was
+--------------------------------------------
+
+Up to and including release 6.7, PCRE worked by running a very degenerate first
+pass to calculate a maximum store size, and then a second pass to do the real
+compile - which might use a bit less than the predicted amount of memory. The
+idea was that this would turn out faster than the Henry Spencer code because
+the first pass is degenerate and the second pass can just store stuff straight
+into the vector, which it knows is big enough.
+
+
+Computing the memory requirement: how it is
+-------------------------------------------
+
+By the time I was working on a potential 6.8 release, the degenerate first pass
+had become very complicated and hard to maintain. Indeed one of the early
+things I did for 6.8 was to fix Yet Another Bug in the memory computation. Then
+I had a flash of inspiration as to how I could run the real compile function in
+a "fake" mode that enables it to compute how much memory it would need, while
+actually only ever using a few hundred bytes of working memory, and without too
+many tests of the mode that might slow it down. So I refactored the compiling
+functions to work this way. This got rid of about 600 lines of source. It
+should make future maintenance and development easier. As this was such a major 
+change, I never released 6.8, instead upping the number to 7.0 (other quite 
+major changes were also present in the 7.0 release).
+
+A side effect of this work was that the previous limit of 200 on the nesting
+depth of parentheses was removed. However, there is a downside: pcre_compile()
+runs more slowly than before (30% or more, depending on the pattern) because it
+is doing a full analysis of the pattern. My hope was that this would not be a
+big issue, and in the event, nobody has commented on it.
+
+
+Traditional matching function
+-----------------------------
+
+The "traditional", and original, matching function is called pcre_exec(), and 
+it implements an NFA algorithm, similar to the original Henry Spencer algorithm 
+and the way that Perl works. This is not surprising, since it is intended to be
+as compatible with Perl as possible. This is the function most users of PCRE
+will use most of the time. From release 8.20, if PCRE is compiled with 
+just-in-time (JIT) support, and studying a compiled pattern with JIT is 
+successful, the JIT code is run instead of the normal pcre_exec() code, but the 
+result is the same.
+
+
+Supplementary matching function
+-------------------------------
+
+From PCRE 6.0, there is also a supplementary matching function called 
+pcre_dfa_exec(). This implements a DFA matching algorithm that searches 
+simultaneously for all possible matches that start at one point in the subject 
+string. (Going back to my roots: see Historical Note 1 above.) This function 
+intreprets the same compiled pattern data as pcre_exec(); however, not all the 
+facilities are available, and those that are do not always work in quite the 
+same way. See the user documentation for details.
+
+The algorithm that is used for pcre_dfa_exec() is not a traditional FSM, 
+because it may have a number of states active at one time. More work would be 
+needed at compile time to produce a traditional FSM where only one state is 
+ever active at once. I believe some other regex matchers work this way.
+
+
+Changeable options
+------------------
+
+The /i, /m, or /s options (PCRE_CASELESS, PCRE_MULTILINE, PCRE_DOTALL) may
+change in the middle of patterns. From PCRE 8.13, their processing is handled
+entirely at compile time by generating different opcodes for the different
+settings. The runtime functions do not need to keep track of an options state 
+any more.
+
+
+Format of compiled patterns
+---------------------------
+
+The compiled form of a pattern is a vector of units (bytes in 8-bit mode, or
+shorts in 16-bit mode), containing items of variable length. The first unit in
+an item contains an opcode, and the length of the item is either implicit in
+the opcode or contained in the data that follows it.
+
+In many cases listed below, LINK_SIZE data values are specified for offsets
+within the compiled pattern. LINK_SIZE always specifies a number of bytes. The
+default value for LINK_SIZE is 2, but PCRE can be compiled to use 3-byte or
+4-byte values for these offsets, although this impairs the performance. (3-byte
+LINK_SIZE values are available only in 8-bit mode.) Specifing a LINK_SIZE
+larger than 2 is necessary only when patterns whose compiled length is greater
+than 64K are going to be processed. In this description, we assume the "normal"
+compilation options. Data values that are counts (e.g. for quantifiers) are
+always just two bytes long (one short in 16-bit mode).
+
+Opcodes with no following data
+------------------------------
+
+These items are all just one unit long
+
+  OP_END                 end of pattern
+  OP_ANY                 match any one character other than newline
+  OP_ALLANY              match any one character, including newline
+  OP_ANYBYTE             match any single byte, even in UTF-8 mode
+  OP_SOD                 match start of data: \A
+  OP_SOM,                start of match (subject + offset): \G
+  OP_SET_SOM,            set start of match (\K) 
+  OP_CIRC                ^ (start of data)
+  OP_CIRCM               ^ multiline mode (start of data or after newline)
+  OP_NOT_WORD_BOUNDARY   \W
+  OP_WORD_BOUNDARY       \w
+  OP_NOT_DIGIT           \D
+  OP_DIGIT               \d
+  OP_NOT_HSPACE          \H
+  OP_HSPACE              \h  
+  OP_NOT_WHITESPACE      \S
+  OP_WHITESPACE          \s
+  OP_NOT_VSPACE          \V
+  OP_VSPACE              \v  
+  OP_NOT_WORDCHAR        \W
+  OP_WORDCHAR            \w
+  OP_EODN                match end of data or \n at end: \Z
+  OP_EOD                 match end of data: \z
+  OP_DOLL                $ (end of data, or before final newline)
+  OP_DOLLM               $ multiline mode (end of data or before newline)
+  OP_EXTUNI              match an extended Unicode character 
+  OP_ANYNL               match any Unicode newline sequence 
+  
+  OP_ACCEPT              ) These are Perl 5.10's "backtracking control   
+  OP_COMMIT              ) verbs". If OP_ACCEPT is inside capturing
+  OP_FAIL                ) parentheses, it may be preceded by one or more
+  OP_PRUNE               ) OP_CLOSE, followed by a 2-byte number,
+  OP_SKIP                ) indicating which parentheses must be closed.
+  
+
+Backtracking control verbs with (optional) data
+-----------------------------------------------
+
+(*THEN) without an argument generates the opcode OP_THEN and no following data.
+OP_MARK is followed by the mark name, preceded by a one-unit length, and
+followed by a binary zero. For (*PRUNE), (*SKIP), and (*THEN) with arguments,
+the opcodes OP_PRUNE_ARG, OP_SKIP_ARG, and OP_THEN_ARG are used, with the name
+following in the same format.
+  
+
+Matching literal characters
+---------------------------
+
+The OP_CHAR opcode is followed by a single character that is to be matched 
+casefully. For caseless matching, OP_CHARI is used. In UTF-8 or UTF-16 modes,
+the character may be more than one unit long.
+
+
+Repeating single characters
+---------------------------
+
+The common repeats (*, +, ?), when applied to a single character, use the
+following opcodes, which come in caseful and caseless versions:
+
+  Caseful         Caseless
+  OP_STAR         OP_STARI      
+  OP_MINSTAR      OP_MINSTARI   
+  OP_POSSTAR      OP_POSSTARI   
+  OP_PLUS         OP_PLUSI      
+  OP_MINPLUS      OP_MINPLUSI   
+  OP_POSPLUS      OP_POSPLUSI   
+  OP_QUERY        OP_QUERYI     
+  OP_MINQUERY     OP_MINQUERYI  
+  OP_POSQUERY     OP_POSQUERYI  
+
+Each opcode is followed by the character that is to be repeated. In ASCII mode,
+these are two-unit items; in UTF-8 or UTF-16 modes, the length is variable.
+Those with "MIN" in their names are the minimizing versions. Those with "POS"
+in their names are possessive versions. Other repeats make use of these
+opcodes:
+
+  Caseful         Caseless
+  OP_UPTO         OP_UPTOI    
+  OP_MINUPTO      OP_MINUPTOI 
+  OP_POSUPTO      OP_POSUPTOI 
+  OP_EXACT        OP_EXACTI   
+
+Each of these is followed by a two-byte (one short) count (most significant
+byte first in 8-bit mode) and then the repeated character. OP_UPTO matches from
+0 to the given number. A repeat with a non-zero minimum and a fixed maximum is
+coded as an OP_EXACT followed by an OP_UPTO (or OP_MINUPTO or OPT_POSUPTO).
+
+
+Repeating character types
+-------------------------
+
+Repeats of things like \d are done exactly as for single characters, except
+that instead of a character, the opcode for the type is stored in the data
+unit. The opcodes are:
+
+  OP_TYPESTAR
+  OP_TYPEMINSTAR
+  OP_TYPEPOSSTAR 
+  OP_TYPEPLUS
+  OP_TYPEMINPLUS
+  OP_TYPEPOSPLUS 
+  OP_TYPEQUERY
+  OP_TYPEMINQUERY
+  OP_TYPEPOSQUERY 
+  OP_TYPEUPTO
+  OP_TYPEMINUPTO
+  OP_TYPEPOSUPTO 
+  OP_TYPEEXACT
+
+
+Match by Unicode property
+-------------------------
+
+OP_PROP and OP_NOTPROP are used for positive and negative matches of a 
+character by testing its Unicode property (the \p and \P escape sequences).
+Each is followed by two units that encode the desired property as a type and a
+value.
+
+Repeats of these items use the OP_TYPESTAR etc. set of opcodes, followed by
+three units: OP_PROP or OP_NOTPROP, and then the desired property type and
+value.
+
+
+Character classes
+-----------------
+
+If there is only one character in the class, OP_CHAR or OP_CHARI is used for a
+positive class, and OP_NOT or OP_NOTI for a negative one (that is, for
+something like [^a]). 
+
+Another set of 13 repeating opcodes (called OP_NOTSTAR etc.) are used for
+repeated, negated, single-character classes. The normal single-character
+opcodes (OP_STAR, etc.) are used for repeated positive single-character
+classes.
+
+When there is more than one character in a class and all the characters are
+less than 256, OP_CLASS is used for a positive class, and OP_NCLASS for a
+negative one. In either case, the opcode is followed by a 32-byte (16-short)
+bit map containing a 1 bit for every character that is acceptable. The bits are
+counted from the least significant end of each unit. In caseless mode, bits for
+both cases are set.
+
+The reason for having both OP_CLASS and OP_NCLASS is so that, in UTF-8/16 mode,
+subject characters with values greater than 255 can be handled correctly. For
+OP_CLASS they do not match, whereas for OP_NCLASS they do.
+
+For classes containing characters with values greater than 255, OP_XCLASS is
+used. It optionally uses a bit map (if any characters lie within it), followed
+by a list of pairs (for a range) and single characters. In caseless mode, both
+cases are explicitly listed. There is a flag character than indicates whether
+it is a positive or a negative class.
+
+
+Back references
+---------------
+
+OP_REF (caseful) or OP_REFI (caseless) is followed by two bytes (one short)
+containing the reference number.
+
+
+Repeating character classes and back references
+-----------------------------------------------
+
+Single-character classes are handled specially (see above). This section
+applies to OP_CLASS and OP_REF[I]. In both cases, the repeat information
+follows the base item. The matching code looks at the following opcode to see
+if it is one of
+
+  OP_CRSTAR
+  OP_CRMINSTAR
+  OP_CRPLUS
+  OP_CRMINPLUS
+  OP_CRQUERY
+  OP_CRMINQUERY
+  OP_CRRANGE
+  OP_CRMINRANGE
+
+All but the last two are just single-unit items. The others are followed by
+four bytes (two shorts) of data, comprising the minimum and maximum repeat
+counts. There are no special possessive opcodes for these repeats; a possessive
+repeat is compiled into an atomic group.
+
+
+Brackets and alternation
+------------------------
+
+A pair of non-capturing (round) brackets is wrapped round each expression at
+compile time, so alternation always happens in the context of brackets.
+
+[Note for North Americans: "bracket" to some English speakers, including
+myself, can be round, square, curly, or pointy. Hence this usage rather than 
+"parentheses".]
+
+Non-capturing brackets use the opcode OP_BRA. Originally PCRE was limited to 99
+capturing brackets and it used a different opcode for each one. From release
+3.5, the limit was removed by putting the bracket number into the data for
+higher-numbered brackets. From release 7.0 all capturing brackets are handled
+this way, using the single opcode OP_CBRA.
+
+A bracket opcode is followed by LINK_SIZE bytes which give the offset to the
+next alternative OP_ALT or, if there aren't any branches, to the matching
+OP_KET opcode. Each OP_ALT is followed by LINK_SIZE bytes giving the offset to
+the next one, or to the OP_KET opcode. For capturing brackets, the bracket 
+number immediately follows the offset, always as a 2-byte (one short) item.
+
+OP_KET is used for subpatterns that do not repeat indefinitely, and
+OP_KETRMIN and OP_KETRMAX are used for indefinite repetitions, minimally or
+maximally respectively (see below for possessive repetitions). All three are
+followed by LINK_SIZE bytes giving (as a positive number) the offset back to
+the matching bracket opcode.
+
+If a subpattern is quantified such that it is permitted to match zero times, it
+is preceded by one of OP_BRAZERO, OP_BRAMINZERO, or OP_SKIPZERO. These are
+single-unit opcodes that tell the matcher that skipping the following
+subpattern entirely is a valid branch. In the case of the first two, not 
+skipping the pattern is also valid (greedy and non-greedy). The third is used 
+when a pattern has the quantifier {0,0}. It cannot be entirely discarded, 
+because it may be called as a subroutine from elsewhere in the regex.
+
+A subpattern with an indefinite maximum repetition is replicated in the
+compiled data its minimum number of times (or once with OP_BRAZERO if the
+minimum is zero), with the final copy terminating with OP_KETRMIN or OP_KETRMAX
+as appropriate.
+
+A subpattern with a bounded maximum repetition is replicated in a nested
+fashion up to the maximum number of times, with OP_BRAZERO or OP_BRAMINZERO
+before each replication after the minimum, so that, for example, (abc){2,5} is
+compiled as (abc)(abc)((abc)((abc)(abc)?)?)?, except that each bracketed group 
+has the same number.
+
+When a repeated subpattern has an unbounded upper limit, it is checked to see 
+whether it could match an empty string. If this is the case, the opcode in the 
+final replication is changed to OP_SBRA or OP_SCBRA. This tells the matcher
+that it needs to check for matching an empty string when it hits OP_KETRMIN or
+OP_KETRMAX, and if so, to break the loop.
+
+Possessive brackets
+-------------------
+
+When a repeated group (capturing or non-capturing) is marked as possessive by
+the "+" notation, e.g. (abc)++, different opcodes are used. Their names all
+have POS on the end, e.g. OP_BRAPOS instead of OP_BRA and OP_SCPBRPOS instead 
+of OP_SCBRA. The end of such a group is marked by OP_KETRPOS. If the minimum 
+repetition is zero, the group is preceded by OP_BRAPOSZERO.
+
+
+Assertions
+----------
+
+Forward assertions are just like other subpatterns, but starting with one of
+the opcodes OP_ASSERT or OP_ASSERT_NOT. Backward assertions use the opcodes
+OP_ASSERTBACK and OP_ASSERTBACK_NOT, and the first opcode inside the assertion
+is OP_REVERSE, followed by a two byte (one short) count of the number of
+characters to move back the pointer in the subject string. In ASCII mode, the 
+count is a number of units, but in UTF-8/16 mode each character may occupy more
+than one unit. A separate count is present in each alternative of a lookbehind
+assertion, allowing them to have different fixed lengths.
+
+
+Once-only (atomic) subpatterns
+------------------------------
+
+These are also just like other subpatterns, but they start with the opcode
+OP_ONCE. The check for matching an empty string in an unbounded repeat is 
+handled entirely at runtime, so there is just this one opcode.
+
+
+Conditional subpatterns
+-----------------------
+
+These are like other subpatterns, but they start with the opcode OP_COND, or
+OP_SCOND for one that might match an empty string in an unbounded repeat. If
+the condition is a back reference, this is stored at the start of the
+subpattern using the opcode OP_CREF followed by two bytes (one short)
+containing the reference number. OP_NCREF is used instead if the reference was
+generated by name (so that the runtime code knows to check for duplicate
+names).
+
+If the condition is "in recursion" (coded as "(?(R)"), or "in recursion of
+group x" (coded as "(?(Rx)"), the group number is stored at the start of the
+subpattern using the opcode OP_RREF or OP_NRREF (cf OP_NCREF), and a value of
+zero for "the whole pattern". For a DEFINE condition, just the single unit
+OP_DEF is used (it has no associated data). Otherwise, a conditional subpattern
+always starts with one of the assertions.
+
+
+Recursion
+---------
+
+Recursion either matches the current regex, or some subexpression. The opcode
+OP_RECURSE is followed by an value which is the offset to the starting bracket
+from the start of the whole pattern. From release 6.5, OP_RECURSE is 
+automatically wrapped inside OP_ONCE brackets (because otherwise some patterns 
+broke it). OP_RECURSE is also used for "subroutine" calls, even though they 
+are not strictly a recursion.
+
+
+Callout
+-------
+
+OP_CALLOUT is followed by one unit of data that holds a callout number in the
+range 0 to 254 for manual callouts, or 255 for an automatic callout. In both 
+cases there follows a two-byte (one short) value giving the offset in the
+pattern to the start of the following item, and another two-byte (one short)
+item giving the length of the next item.
+
+
+Philip Hazel
+February 2012
diff --git a/ext/pcre/pcrelib/LICENCE b/ext/pcre/pcrelib/LICENCE
new file mode 100644
index 0000000..5ce31a8
--- /dev/null
+++ b/ext/pcre/pcrelib/LICENCE
@@ -0,0 +1,92 @@
+PCRE LICENCE
+------------
+
+PCRE is a library of functions to support regular expressions whose syntax
+and semantics are as close as possible to those of the Perl 5 language.
+
+Release 8 of PCRE is distributed under the terms of the "BSD" licence, as
+specified below. The documentation for PCRE, supplied in the "doc"
+directory, is distributed under the same terms as the software itself.
+
+The basic library functions are written in C and are freestanding. Also
+included in the distribution is a set of C++ wrapper functions, and a
+just-in-time compiler that can be used to optimize pattern matching. These
+are both optional features that can be omitted when the library is built.
+
+
+THE BASIC LIBRARY FUNCTIONS
+---------------------------
+
+Written by:       Philip Hazel
+Email local part: ph10
+Email domain:     cam.ac.uk
+
+University of Cambridge Computing Service,
+Cambridge, England.
+
+Copyright (c) 1997-2012 University of Cambridge
+All rights reserved.
+
+
+PCRE JUST-IN-TIME COMPILATION SUPPORT
+-------------------------------------
+
+Written by:       Zoltan Herczeg
+Email local part: hzmester
+Emain domain:     freemail.hu
+
+Copyright(c) 2010-2012 Zoltan Herczeg
+All rights reserved.
+
+
+STACK-LESS JUST-IN-TIME COMPILER
+--------------------------------
+
+Written by:       Zoltan Herczeg
+Email local part: hzmester
+Emain domain:     freemail.hu
+
+Copyright(c) 2009-2012 Zoltan Herczeg
+All rights reserved.
+
+
+THE C++ WRAPPER FUNCTIONS
+-------------------------
+
+Contributed by:   Google Inc.
+
+Copyright (c) 2007-2012, Google Inc.
+All rights reserved.
+
+
+THE "BSD" LICENCE
+-----------------
+
+Redistribution and use in source and binary forms, with or without
+modification, are permitted provided that the following conditions are met:
+
+    * Redistributions of source code must retain the above copyright notice,
+      this list of conditions and the following disclaimer.
+
+    * Redistributions in binary form must reproduce the above copyright
+      notice, this list of conditions and the following disclaimer in the
+      documentation and/or other materials provided with the distribution.
+
+    * Neither the name of the University of Cambridge nor the name of Google
+      Inc. nor the names of their contributors may be used to endorse or
+      promote products derived from this software without specific prior
+      written permission.
+
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+POSSIBILITY OF SUCH DAMAGE.
+
+End
diff --git a/ext/pcre/pcrelib/NEWS b/ext/pcre/pcrelib/NEWS
new file mode 100644
index 0000000..3c932a4
--- /dev/null
+++ b/ext/pcre/pcrelib/NEWS
@@ -0,0 +1,571 @@
+News about PCRE releases
+------------------------
+
+Release 8.31 06-July-2012
+-------------------------
+
+This is mainly a bug-fixing release, with a small number of developments:
+
+. The JIT compiler now supports partial matching and the (*MARK) and
+  (*COMMIT) verbs.
+
+. PCRE_INFO_MAXLOOKBEHIND can be used to find the longest lookbehing in a
+  pattern.
+
+. There should be a performance improvement when using the heap instead of the
+  stack for recursion.
+
+. pcregrep can now be linked with libedit as an alternative to libreadline.
+
+. pcregrep now has a --file-list option where the list of files to scan is
+  given as a file.
+
+. pcregrep now recognizes binary files and there are related options.
+
+. The Unicode tables have been updated to 6.1.0.
+
+As always, the full list of changes is in the ChangeLog file.
+
+
+Release 8.30 04-February-2012
+-----------------------------
+
+Release 8.30 introduces a major new feature: support for 16-bit character
+strings, compiled as a separate library. There are a few changes to the
+8-bit library, in addition to some bug fixes.
+
+. The pcre_info() function, which has been obsolete for over 10 years, has
+  been removed.
+
+. When a compiled pattern was saved to a file and later reloaded on a host
+  with different endianness, PCRE used automatically to swap the bytes in some
+  of the data fields. With the advent of the 16-bit library, where more of this
+  swapping is needed, it is no longer done automatically. Instead, the bad
+  endianness is detected and a specific error is given. The user can then call
+  a new function called pcre_pattern_to_host_byte_order() (or an equivalent
+  16-bit function) to do the swap.
+
+. In UTF-8 mode, the values 0xd800 to 0xdfff are not legal Unicode
+  code points and are now faulted. (They are the so-called "surrogates"
+  that are reserved for coding high values in UTF-16.)
+
+
+Release 8.21 12-Dec-2011
+------------------------
+
+This is almost entirely a bug-fix release. The only new feature is the ability
+to obtain the size of the memory used by the JIT compiler.
+
+
+Release 8.20 21-Oct-2011
+------------------------
+
+The main change in this release is the inclusion of Zoltan Herczeg's
+just-in-time compiler support, which can be accessed by building PCRE with
+--enable-jit. Large performance benefits can be had in many situations. 8.20
+also fixes an unfortunate bug that was introduced in 8.13 as well as tidying up
+a number of infelicities and differences from Perl.
+
+
+Release 8.13 16-Aug-2011
+------------------------
+
+This is mainly a bug-fix release. There has been a lot of internal refactoring.
+The Unicode tables have been updated. The only new feature in the library is
+the passing of *MARK information to callouts. Some additions have been made to
+pcretest to make testing easier and more comprehensive. There is a new option
+for pcregrep to adjust its internal buffer size.
+
+
+Release 8.12 15-Jan-2011
+------------------------
+
+This release fixes some bugs in pcregrep, one of which caused the tests to fail
+on 64-bit big-endian systems. There are no changes to the code of the library.
+
+
+Release 8.11 10-Dec-2010
+------------------------
+
+A number of bugs in the library and in pcregrep have been fixed. As always, see
+ChangeLog for details. The following are the non-bug-fix changes:
+
+. Added --match-limit and --recursion-limit to pcregrep.
+
+. Added an optional parentheses number to the -o and --only-matching options
+  of pcregrep.
+
+. Changed the way PCRE_PARTIAL_HARD affects the matching of $, \z, \Z, \b, and
+  \B.
+
+. Added PCRE_ERROR_SHORTUTF8 to make it possible to distinguish between a
+  bad UTF-8 sequence and one that is incomplete when using PCRE_PARTIAL_HARD.
+
+. Recognize (*NO_START_OPT) at the start of a pattern to set the PCRE_NO_
+  START_OPTIMIZE option, which is now allowed at compile time
+
+
+Release 8.10 25-Jun-2010
+------------------------
+
+There are two major additions: support for (*MARK) and friends, and the option
+PCRE_UCP, which changes the behaviour of \b, \d, \s, and \w (and their
+opposites) so that they make use of Unicode properties. There are also a number
+of lesser new features, and several bugs have been fixed. A new option,
+--line-buffered, has been added to pcregrep, for use when it is connected to
+pipes.
+
+
+Release 8.02 19-Mar-2010
+------------------------
+
+Another bug-fix release.
+
+
+Release 8.01 19-Jan-2010
+------------------------
+
+This is a bug-fix release. Several bugs in the code itself and some bugs and
+infelicities in the build system have been fixed.
+
+
+Release 8.00 19-Oct-09
+----------------------
+
+Bugs have been fixed in the library and in pcregrep. There are also some
+enhancements. Restrictions on patterns used for partial matching have been
+removed, extra information is given for partial matches, the partial matching
+process has been improved, and an option to make a partial match override a
+full match is available. The "study" process has been enhanced by finding a
+lower bound matching length. Groups with duplicate numbers may now have
+duplicated names without the use of PCRE_DUPNAMES. However, they may not have
+different names. The documentation has been revised to reflect these changes.
+The version number has been expanded to 3 digits as it is clear that the rate
+of change is not slowing down.
+
+
+Release 7.9 11-Apr-09
+---------------------
+
+Mostly bugfixes and tidies with just a couple of minor functional additions.
+
+
+Release 7.8 05-Sep-08
+---------------------
+
+More bug fixes, plus a performance improvement in Unicode character property
+lookup.
+
+
+Release 7.7 07-May-08
+---------------------
+
+This is once again mainly a bug-fix release, but there are a couple of new
+features.
+
+
+Release 7.6 28-Jan-08
+---------------------
+
+The main reason for having this release so soon after 7.5 is because it fixes a
+potential buffer overflow problem in pcre_compile() when run in UTF-8 mode. In
+addition, the CMake configuration files have been brought up to date.
+
+
+Release 7.5 10-Jan-08
+---------------------
+
+This is mainly a bug-fix release. However the ability to link pcregrep with
+libz or libbz2 and the ability to link pcretest with libreadline have been
+added. Also the --line-offsets and --file-offsets options were added to
+pcregrep.
+
+
+Release 7.4 21-Sep-07
+---------------------
+
+The only change of specification is the addition of options to control whether
+\R matches any Unicode line ending (the default) or just CR, LF, and CRLF.
+Otherwise, the changes are bug fixes and a refactoring to reduce the number of
+relocations needed in a shared library. There have also been some documentation
+updates, in particular, some more information about using CMake to build PCRE
+has been added to the NON-UNIX-USE file.
+
+
+Release 7.3 28-Aug-07
+---------------------
+
+Most changes are bug fixes. Some that are not:
+
+1. There is some support for Perl 5.10's experimental "backtracking control
+   verbs" such as (*PRUNE).
+
+2. UTF-8 checking is now as per RFC 3629 instead of RFC 2279; this is more
+   restrictive in the strings it accepts.
+
+3. Checking for potential integer overflow has been made more dynamic, and as a
+   consequence there is no longer a hard limit on the size of a subpattern that
+   has a limited repeat count.
+
+4. When CRLF is a valid line-ending sequence, pcre_exec() and pcre_dfa_exec()
+   no longer advance by two characters instead of one when an unanchored match
+   fails at CRLF if there are explicit CR or LF matches within the pattern.
+   This gets rid of some anomalous effects that previously occurred.
+
+5. Some PCRE-specific settings for varying the newline options at the start of
+   a pattern have been added.
+
+
+Release 7.2 19-Jun-07
+---------------------
+
+WARNING: saved patterns that were compiled by earlier versions of PCRE must be
+recompiled for use with 7.2 (necessitated by the addition of \K, \h, \H, \v,
+and \V).
+
+Correction to the notes for 7.1: the note about shared libraries for Windows is
+wrong. Previously, three libraries were built, but each could function
+independently. For example, the pcreposix library also included all the
+functions from the basic pcre library. The change is that the three libraries
+are no longer independent. They are like the Unix libraries. To use the
+pcreposix functions, for example, you need to link with both the pcreposix and
+the basic pcre library.
+
+Some more features from Perl 5.10 have been added:
+
+  (?-n) and (?+n) relative references for recursion and subroutines.
+
+  (?(-n) and (?(+n) relative references as conditions.
+
+  \k{name} and \g{name} are synonyms for \k<name>.
+
+  \K to reset the start of the matched string; for example, (foo)\Kbar
+  matches bar preceded by foo, but only sets bar as the matched string.
+
+  (?| introduces a group where the capturing parentheses in each alternative
+  start from the same number; for example, (?|(abc)|(xyz)) sets capturing
+  parentheses number 1 in both cases.
+
+  \h, \H, \v, \V match horizontal and vertical whitespace, respectively.
+
+
+Release 7.1 24-Apr-07
+---------------------
+
+There is only one new feature in this release: a linebreak setting of
+PCRE_NEWLINE_ANYCRLF. It is a cut-down version of PCRE_NEWLINE_ANY, which
+recognizes only CRLF, CR, and LF as linebreaks.
+
+A few bugs are fixed (see ChangeLog for details), but the major change is a
+complete re-implementation of the build system. This now has full Autotools
+support and so is now "standard" in some sense. It should help with compiling
+PCRE in a wide variety of environments.
+
+NOTE: when building shared libraries for Windows, three dlls are now built,
+called libpcre, libpcreposix, and libpcrecpp. Previously, everything was
+included in a single dll.
+
+Another important change is that the dftables auxiliary program is no longer
+compiled and run at "make" time by default. Instead, a default set of character
+tables (assuming ASCII coding) is used. If you want to use dftables to generate
+the character tables as previously, add --enable-rebuild-chartables to the
+"configure" command. You must do this if you are compiling PCRE to run on a
+system that uses EBCDIC code.
+
+There is a discussion about character tables in the README file. The default is
+not to use dftables so that that there is no problem when cross-compiling.
+
+
+Release 7.0 19-Dec-06
+---------------------
+
+This release has a new major number because there have been some internal
+upheavals to facilitate the addition of new optimizations and other facilities,
+and to make subsequent maintenance and extension easier. Compilation is likely
+to be a bit slower, but there should be no major effect on runtime performance.
+Previously compiled patterns are NOT upwards compatible with this release. If
+you have saved compiled patterns from a previous release, you will have to
+re-compile them. Important changes that are visible to users are:
+
+1. The Unicode property tables have been updated to Unicode 5.0.0, which adds
+   some more scripts.
+
+2. The option PCRE_NEWLINE_ANY causes PCRE to recognize any Unicode newline
+   sequence as a newline.
+
+3. The \R escape matches a single Unicode newline sequence as a single unit.
+
+4. New features that will appear in Perl 5.10 are now in PCRE. These include
+   alternative Perl syntax for named parentheses, and Perl syntax for
+   recursion.
+
+5. The C++ wrapper interface has been extended by the addition of a
+   QuoteMeta function and the ability to allow copy construction and
+   assignment.
+
+For a complete list of changes, see the ChangeLog file.
+
+
+Release 6.7 04-Jul-06
+---------------------
+
+The main additions to this release are the ability to use the same name for
+multiple sets of parentheses, and support for CRLF line endings in both the
+library and pcregrep (and in pcretest for testing).
+
+Thanks to Ian Taylor, the stack usage for many kinds of pattern has been
+significantly reduced for certain subject strings.
+
+
+Release 6.5 01-Feb-06
+---------------------
+
+Important changes in this release:
+
+1. A number of new features have been added to pcregrep.
+
+2. The Unicode property tables have been updated to Unicode 4.1.0, and the
+   supported properties have been extended with script names such as "Arabic",
+   and the derived properties "Any" and "L&". This has necessitated a change to
+   the interal format of compiled patterns. Any saved compiled patterns that
+   use \p or \P must be recompiled.
+
+3. The specification of recursion in patterns has been changed so that all
+   recursive subpatterns are automatically treated as atomic groups. Thus, for
+   example, (?R) is treated as if it were (?>(?R)). This is necessary because
+   otherwise there are situations where recursion does not work.
+
+See the ChangeLog for a complete list of changes, which include a number of bug
+fixes and tidies.
+
+
+Release 6.0 07-Jun-05
+---------------------
+
+The release number has been increased to 6.0 because of the addition of several
+major new pieces of functionality.
+
+A new function, pcre_dfa_exec(), which implements pattern matching using a DFA
+algorithm, has been added. This has a number of advantages for certain cases,
+though it does run more slowly, and lacks the ability to capture substrings. On
+the other hand, it does find all matches, not just the first, and it works
+better for partial matching. The pcrematching man page discusses the
+differences.
+
+The pcretest program has been enhanced so that it can make use of the new
+pcre_dfa_exec() matching function and the extra features it provides.
+
+The distribution now includes a C++ wrapper library. This is built
+automatically if a C++ compiler is found. The pcrecpp man page discusses this
+interface.
+
+The code itself has been re-organized into many more files, one for each
+function, so it no longer requires everything to be linked in when static
+linkage is used. As a consequence, some internal functions have had to have
+their names exposed. These functions all have names starting with _pcre_. They
+are undocumented, and are not intended for use by outside callers.
+
+The pcregrep program has been enhanced with new functionality such as
+multiline-matching and options for output more matching context. See the
+ChangeLog for a complete list of changes to the library and the utility
+programs.
+
+
+Release 5.0 13-Sep-04
+---------------------
+
+The licence under which PCRE is released has been changed to the more
+conventional "BSD" licence.
+
+In the code, some bugs have been fixed, and there are also some major changes
+in this release (which is why I've increased the number to 5.0). Some changes
+are internal rearrangements, and some provide a number of new facilities. The
+new features are:
+
+1. There's an "automatic callout" feature that inserts callouts before every
+   item in the regex, and there's a new callout field that gives the position
+   in the pattern - useful for debugging and tracing.
+
+2. The extra_data structure can now be used to pass in a set of character
+   tables at exec time. This is useful if compiled regex are saved and re-used
+   at a later time when the tables may not be at the same address. If the
+   default internal tables are used, the pointer saved with the compiled
+   pattern is now set to NULL, which means that you don't need to do anything
+   special unless you are using custom tables.
+
+3. It is possible, with some restrictions on the content of the regex, to
+   request "partial" matching. A special return code is given if all of the
+   subject string matched part of the regex. This could be useful for testing
+   an input field as it is being typed.
+
+4. There is now some optional support for Unicode character properties, which
+   means that the patterns items such as \p{Lu} and \X can now be used. Only
+   the general category properties are supported. If PCRE is compiled with this
+   support, an additional 90K data structure is include, which increases the
+   size of the library dramatically.
+
+5. There is support for saving compiled patterns and re-using them later.
+
+6. There is support for running regular expressions that were compiled on a
+   different host with the opposite endianness.
+
+7. The pcretest program has been extended to accommodate the new features.
+
+The main internal rearrangement is that sequences of literal characters are no
+longer handled as strings. Instead, each character is handled on its own. This
+makes some UTF-8 handling easier, and makes the support of partial matching
+possible. Compiled patterns containing long literal strings will be larger as a
+result of this change; I hope that performance will not be much affected.
+
+
+Release 4.5 01-Dec-03
+---------------------
+
+Again mainly a bug-fix and tidying release, with only a couple of new features:
+
+1. It's possible now to compile PCRE so that it does not use recursive
+function calls when matching. Instead it gets memory from the heap. This slows
+things down, but may be necessary on systems with limited stacks.
+
+2. UTF-8 string checking has been tightened to reject overlong sequences and to
+check that a starting offset points to the start of a character. Failure of the
+latter returns a new error code: PCRE_ERROR_BADUTF8_OFFSET.
+
+3. PCRE can now be compiled for systems that use EBCDIC code.
+
+
+Release 4.4 21-Aug-03
+---------------------
+
+This is mainly a bug-fix and tidying release. The only new feature is that PCRE
+checks UTF-8 strings for validity by default. There is an option to suppress
+this, just in case anybody wants that teeny extra bit of performance.
+
+
+Releases 4.1 - 4.3
+------------------
+
+Sorry, I forgot about updating the NEWS file for these releases. Please take a
+look at ChangeLog.
+
+
+Release 4.0 17-Feb-03
+---------------------
+
+There have been a lot of changes for the 4.0 release, adding additional
+functionality and mending bugs. Below is a list of the highlights of the new
+functionality. For full details of these features, please consult the
+documentation. For a complete list of changes, see the ChangeLog file.
+
+1. Support for Perl's \Q...\E escapes.
+
+2. "Possessive quantifiers" ?+, *+, ++, and {,}+ which come from Sun's Java
+package. They provide some syntactic sugar for simple cases of "atomic
+grouping".
+
+3. Support for the \G assertion. It is true when the current matching position
+is at the start point of the match.
+
+4. A new feature that provides some of the functionality that Perl provides
+with (?{...}). The facility is termed a "callout". The way it is done in PCRE
+is for the caller to provide an optional function, by setting pcre_callout to
+its entry point. To get the function called, the regex must include (?C) at
+appropriate points.
+
+5. Support for recursive calls to individual subpatterns. This makes it really
+easy to get totally confused.
+
+6. Support for named subpatterns. The Python syntax (?P<name>...) is used to
+name a group.
+
+7. Several extensions to UTF-8 support; it is now fairly complete. There is an
+option for pcregrep to make it operate in UTF-8 mode.
+
+8. The single man page has been split into a number of separate man pages.
+These also give rise to individual HTML pages which are put in a separate
+directory. There is an index.html page that lists them all. Some hyperlinking
+between the pages has been installed.
+
+
+Release 3.5 15-Aug-01
+---------------------
+
+1. The configuring system has been upgraded to use later versions of autoconf
+and libtool. By default it builds both a shared and a static library if the OS
+supports it. You can use --disable-shared or --disable-static on the configure
+command if you want only one of them.
+
+2. The pcretest utility is now installed along with pcregrep because it is
+useful for users (to test regexs) and by doing this, it automatically gets
+relinked by libtool. The documentation has been turned into a man page, so
+there are now .1, .txt, and .html versions in /doc.
+
+3. Upgrades to pcregrep:
+   (i)   Added long-form option names like gnu grep.
+   (ii)  Added --help to list all options with an explanatory phrase.
+   (iii) Added -r, --recursive to recurse into sub-directories.
+   (iv)  Added -f, --file to read patterns from a file.
+
+4. Added --enable-newline-is-cr and --enable-newline-is-lf to the configure
+script, to force use of CR or LF instead of \n in the source. On non-Unix
+systems, the value can be set in config.h.
+
+5. The limit of 200 on non-capturing parentheses is a _nesting_ limit, not an
+absolute limit. Changed the text of the error message to make this clear, and
+likewise updated the man page.
+
+6. The limit of 99 on the number of capturing subpatterns has been removed.
+The new limit is 65535, which I hope will not be a "real" limit.
+
+
+Release 3.3 01-Aug-00
+---------------------
+
+There is some support for UTF-8 character strings. This is incomplete and
+experimental. The documentation describes what is and what is not implemented.
+Otherwise, this is just a bug-fixing release.
+
+
+Release 3.0 01-Feb-00
+---------------------
+
+1. A "configure" script is now used to configure PCRE for Unix systems. It
+builds a Makefile, a config.h file, and the pcre-config script.
+
+2. PCRE is built as a shared library by default.
+
+3. There is support for POSIX classes such as [:alpha:].
+
+5. There is an experimental recursion feature.
+
+----------------------------------------------------------------------------
+          IMPORTANT FOR THOSE UPGRADING FROM VERSIONS BEFORE 2.00
+
+Please note that there has been a change in the API such that a larger
+ovector is required at matching time, to provide some additional workspace.
+The new man page has details. This change was necessary in order to support
+some of the new functionality in Perl 5.005.
+
+          IMPORTANT FOR THOSE UPGRADING FROM VERSION 2.00
+
+Another (I hope this is the last!) change has been made to the API for the
+pcre_compile() function. An additional argument has been added to make it
+possible to pass over a pointer to character tables built in the current
+locale by pcre_maketables(). To use the default tables, this new arguement
+should be passed as NULL.
+
+          IMPORTANT FOR THOSE UPGRADING FROM VERSION 2.05
+
+Yet another (and again I hope this really is the last) change has been made
+to the API for the pcre_exec() function. An additional argument has been
+added to make it possible to start the match other than at the start of the
+subject string. This is important if there are lookbehinds. The new man
+page has the details, but you just want to convert existing programs, all
+you need to do is to stick in a new fifth argument to pcre_exec(), with a
+value of zero. For example, change
+
+  pcre_exec(pattern, extra, subject, length, options, ovec, ovecsize)
+to
+  pcre_exec(pattern, extra, subject, length, 0, options, ovec, ovecsize)
+
+****
diff --git a/ext/pcre/pcrelib/NON-UNIX-USE b/ext/pcre/pcrelib/NON-UNIX-USE
new file mode 100644
index 0000000..a25546b
--- /dev/null
+++ b/ext/pcre/pcrelib/NON-UNIX-USE
@@ -0,0 +1,7 @@
+Compiling PCRE on non-Unix systems
+----------------------------------
+
+This has been renamed to better reflect its contents. Please see the file
+NON-AUTOTOOLS-BUILD for details of how to build PCRE without using autotools.
+
+####
diff --git a/ext/pcre/pcrelib/README b/ext/pcre/pcrelib/README
new file mode 100644
index 0000000..8b67f10
--- /dev/null
+++ b/ext/pcre/pcrelib/README
@@ -0,0 +1,898 @@
+README file for PCRE (Perl-compatible regular expression library)
+-----------------------------------------------------------------
+
+The latest release of PCRE is always available in three alternative formats
+from:
+
+  ftp://ftp.csx.cam.ac.uk/pub/software/programming/pcre/pcre-xxx.tar.gz
+  ftp://ftp.csx.cam.ac.uk/pub/software/programming/pcre/pcre-xxx.tar.bz2
+  ftp://ftp.csx.cam.ac.uk/pub/software/programming/pcre/pcre-xxx.zip
+
+There is a mailing list for discussion about the development of PCRE at
+
+  pcre-dev@exim.org
+
+Please read the NEWS file if you are upgrading from a previous release.
+The contents of this README file are:
+
+  The PCRE APIs
+  Documentation for PCRE
+  Contributions by users of PCRE
+  Building PCRE on non-Unix-like systems
+  Building PCRE without using autotools
+  Building PCRE using autotools
+  Retrieving configuration information
+  Shared libraries
+  Cross-compiling using autotools
+  Using HP's ANSI C++ compiler (aCC)
+  Using PCRE from MySQL
+  Making new tarballs
+  Testing PCRE
+  Character tables
+  File manifest
+
+
+The PCRE APIs
+-------------
+
+PCRE is written in C, and it has its own API. There are two sets of functions,
+one for the 8-bit library, which processes strings of bytes, and one for the
+16-bit library, which processes strings of 16-bit values. The distribution also
+includes a set of C++ wrapper functions (see the pcrecpp man page for details),
+courtesy of Google Inc., which can be used to call the 8-bit PCRE library from
+C++.
+
+In addition, there is a set of C wrapper functions (again, just for the 8-bit
+library) that are based on the POSIX regular expression API (see the pcreposix
+man page). These end up in the library called libpcreposix. Note that this just
+provides a POSIX calling interface to PCRE; the regular expressions themselves
+still follow Perl syntax and semantics. The POSIX API is restricted, and does
+not give full access to all of PCRE's facilities.
+
+The header file for the POSIX-style functions is called pcreposix.h. The
+official POSIX name is regex.h, but I did not want to risk possible problems
+with existing files of that name by distributing it that way. To use PCRE with
+an existing program that uses the POSIX API, pcreposix.h will have to be
+renamed or pointed at by a link.
+
+If you are using the POSIX interface to PCRE and there is already a POSIX regex
+library installed on your system, as well as worrying about the regex.h header
+file (as mentioned above), you must also take care when linking programs to
+ensure that they link with PCRE's libpcreposix library. Otherwise they may pick
+up the POSIX functions of the same name from the other library.
+
+One way of avoiding this confusion is to compile PCRE with the addition of
+-Dregcomp=PCREregcomp (and similarly for the other POSIX functions) to the
+compiler flags (CFLAGS if you are using "configure" -- see below). This has the
+effect of renaming the functions so that the names no longer clash. Of course,
+you have to do the same thing for your applications, or write them using the
+new names.
+
+
+Documentation for PCRE
+----------------------
+
+If you install PCRE in the normal way on a Unix-like system, you will end up
+with a set of man pages whose names all start with "pcre". The one that is just
+called "pcre" lists all the others. In addition to these man pages, the PCRE
+documentation is supplied in two other forms:
+
+  1. There are files called doc/pcre.txt, doc/pcregrep.txt, and
+     doc/pcretest.txt in the source distribution. The first of these is a
+     concatenation of the text forms of all the section 3 man pages except
+     those that summarize individual functions. The other two are the text
+     forms of the section 1 man pages for the pcregrep and pcretest commands.
+     These text forms are provided for ease of scanning with text editors or
+     similar tools. They are installed in <prefix>/share/doc/pcre, where
+     <prefix> is the installation prefix (defaulting to /usr/local).
+
+  2. A set of files containing all the documentation in HTML form, hyperlinked
+     in various ways, and rooted in a file called index.html, is distributed in
+     doc/html and installed in <prefix>/share/doc/pcre/html.
+
+Users of PCRE have contributed files containing the documentation for various
+releases in CHM format. These can be found in the Contrib directory of the FTP
+site (see next section).
+
+
+Contributions by users of PCRE
+------------------------------
+
+You can find contributions from PCRE users in the directory
+
+  ftp://ftp.csx.cam.ac.uk/pub/software/programming/pcre/Contrib
+
+There is a README file giving brief descriptions of what they are. Some are
+complete in themselves; others are pointers to URLs containing relevant files.
+Some of this material is likely to be well out-of-date. Several of the earlier
+contributions provided support for compiling PCRE on various flavours of
+Windows (I myself do not use Windows). Nowadays there is more Windows support
+in the standard distribution, so these contibutions have been archived.
+
+
+Building PCRE on non-Unix-like systems
+--------------------------------------
+
+For a non-Unix-like system, please read the comments in the file
+NON-AUTOTOOLS-BUILD, though if your system supports the use of "configure" and
+"make" you may be able to build PCRE using autotools in the same way as for
+many Unix-like systems.
+
+PCRE can also be configured using the GUI facility provided by CMake's
+cmake-gui command. This creates Makefiles, solution files, etc. The file
+NON-AUTOTOOLS-BUILD has information about CMake.
+
+PCRE has been compiled on many different operating systems. It should be
+straightforward to build PCRE on any system that has a Standard C compiler and
+library, because it uses only Standard C functions.
+
+
+Building PCRE without using autotools
+-------------------------------------
+
+The use of autotools (in particular, libtool) is problematic in some
+environments, even some that are Unix or Unix-like. See the NON-AUTOTOOLS-BUILD
+file for ways of building PCRE without using autotools.
+
+
+Building PCRE using autotools
+-----------------------------
+
+If you are using HP's ANSI C++ compiler (aCC), please see the special note
+in the section entitled "Using HP's ANSI C++ compiler (aCC)" below.
+
+The following instructions assume the use of the widely used "configure; make;
+make install" (autotools) process.
+
+To build PCRE on system that supports autotools, first run the "configure"
+command from the PCRE distribution directory, with your current directory set
+to the directory where you want the files to be created. This command is a
+standard GNU "autoconf" configuration script, for which generic instructions
+are supplied in the file INSTALL.
+
+Most commonly, people build PCRE within its own distribution directory, and in
+this case, on many systems, just running "./configure" is sufficient. However,
+the usual methods of changing standard defaults are available. For example:
+
+CFLAGS='-O2 -Wall' ./configure --prefix=/opt/local
+
+This command specifies that the C compiler should be run with the flags '-O2
+-Wall' instead of the default, and that "make install" should install PCRE
+under /opt/local instead of the default /usr/local.
+
+If you want to build in a different directory, just run "configure" with that
+directory as current. For example, suppose you have unpacked the PCRE source
+into /source/pcre/pcre-xxx, but you want to build it in /build/pcre/pcre-xxx:
+
+cd /build/pcre/pcre-xxx
+/source/pcre/pcre-xxx/configure
+
+PCRE is written in C and is normally compiled as a C library. However, it is
+possible to build it as a C++ library, though the provided building apparatus
+does not have any features to support this.
+
+There are some optional features that can be included or omitted from the PCRE
+library. They are also documented in the pcrebuild man page.
+
+. By default, both shared and static libraries are built. You can change this
+  by adding one of these options to the "configure" command:
+
+  --disable-shared
+  --disable-static
+
+  (See also "Shared libraries on Unix-like systems" below.)
+
+. By default, only the 8-bit library is built. If you add --enable-pcre16 to
+  the "configure" command, the 16-bit library is also built. If you want only
+  the 16-bit library, use "./configure --enable-pcre16 --disable-pcre8".
+
+. If you are building the 8-bit library and want to suppress the building of
+  the C++ wrapper library, you can add --disable-cpp to the "configure"
+  command. Otherwise, when "configure" is run without --disable-pcre8, it will
+  try to find a C++ compiler and C++ header files, and if it succeeds, it will
+  try to build the C++ wrapper.
+
+. If you want to include support for just-in-time compiling, which can give
+  large performance improvements on certain platforms, add --enable-jit to the
+  "configure" command. This support is available only for certain hardware
+  architectures. If you try to enable it on an unsupported architecture, there
+  will be a compile time error.
+
+. When JIT support is enabled, pcregrep automatically makes use of it, unless
+  you add --disable-pcregrep-jit to the "configure" command.
+
+. If you want to make use of the support for UTF-8 Unicode character strings in
+  the 8-bit library, or UTF-16 Unicode character strings in the 16-bit library,
+  you must add --enable-utf to the "configure" command. Without it, the code
+  for handling UTF-8 and UTF-16 is not included in the relevant library. Even
+  when --enable-utf is included, the use of a UTF encoding still has to be
+  enabled by an option at run time. When PCRE is compiled with this option, its
+  input can only either be ASCII or UTF-8/16, even when running on EBCDIC
+  platforms. It is not possible to use both --enable-utf and --enable-ebcdic at
+  the same time.
+
+. There are no separate options for enabling UTF-8 and UTF-16 independently
+  because that would allow ridiculous settings such as requesting UTF-16
+  support while building only the 8-bit library. However, the option
+  --enable-utf8 is retained for backwards compatibility with earlier releases
+  that did not support 16-bit character strings. It is synonymous with
+  --enable-utf. It is not possible to configure one library with UTF support
+  and the other without in the same configuration.
+
+. If, in addition to support for UTF-8/16 character strings, you want to
+  include support for the \P, \p, and \X sequences that recognize Unicode
+  character properties, you must add --enable-unicode-properties to the
+  "configure" command. This adds about 30K to the size of the library (in the
+  form of a property table); only the basic two-letter properties such as Lu
+  are supported.
+
+. You can build PCRE to recognize either CR or LF or the sequence CRLF or any
+  of the preceding, or any of the Unicode newline sequences as indicating the
+  end of a line. Whatever you specify at build time is the default; the caller
+  of PCRE can change the selection at run time. The default newline indicator
+  is a single LF character (the Unix standard). You can specify the default
+  newline indicator by adding --enable-newline-is-cr or --enable-newline-is-lf
+  or --enable-newline-is-crlf or --enable-newline-is-anycrlf or
+  --enable-newline-is-any to the "configure" command, respectively.
+
+  If you specify --enable-newline-is-cr or --enable-newline-is-crlf, some of
+  the standard tests will fail, because the lines in the test files end with
+  LF. Even if the files are edited to change the line endings, there are likely
+  to be some failures. With --enable-newline-is-anycrlf or
+  --enable-newline-is-any, many tests should succeed, but there may be some
+  failures.
+
+. By default, the sequence \R in a pattern matches any Unicode line ending
+  sequence. This is independent of the option specifying what PCRE considers to
+  be the end of a line (see above). However, the caller of PCRE can restrict \R
+  to match only CR, LF, or CRLF. You can make this the default by adding
+  --enable-bsr-anycrlf to the "configure" command (bsr = "backslash R").
+
+. When called via the POSIX interface, PCRE uses malloc() to get additional
+  storage for processing capturing parentheses if there are more than 10 of
+  them in a pattern. You can increase this threshold by setting, for example,
+
+  --with-posix-malloc-threshold=20
+
+  on the "configure" command.
+
+. PCRE has a counter that can be set to limit the amount of resources it uses.
+  If the limit is exceeded during a match, the match fails. The default is ten
+  million. You can change the default by setting, for example,
+
+  --with-match-limit=500000
+
+  on the "configure" command. This is just the default; individual calls to
+  pcre_exec() can supply their own value. There is more discussion on the
+  pcreapi man page.
+
+. There is a separate counter that limits the depth of recursive function calls
+  during a matching process. This also has a default of ten million, which is
+  essentially "unlimited". You can change the default by setting, for example,
+
+  --with-match-limit-recursion=500000
+
+  Recursive function calls use up the runtime stack; running out of stack can
+  cause programs to crash in strange ways. There is a discussion about stack
+  sizes in the pcrestack man page.
+
+. The default maximum compiled pattern size is around 64K. You can increase
+  this by adding --with-link-size=3 to the "configure" command. In the 8-bit
+  library, PCRE then uses three bytes instead of two for offsets to different
+  parts of the compiled pattern. In the 16-bit library, --with-link-size=3 is
+  the same as --with-link-size=4, which (in both libraries) uses four-byte
+  offsets. Increasing the internal link size reduces performance.
+
+. You can build PCRE so that its internal match() function that is called from
+  pcre_exec() does not call itself recursively. Instead, it uses memory blocks
+  obtained from the heap via the special functions pcre_stack_malloc() and
+  pcre_stack_free() to save data that would otherwise be saved on the stack. To
+  build PCRE like this, use
+
+  --disable-stack-for-recursion
+
+  on the "configure" command. PCRE runs more slowly in this mode, but it may be
+  necessary in environments with limited stack sizes. This applies only to the
+  normal execution of the pcre_exec() function; if JIT support is being
+  successfully used, it is not relevant. Equally, it does not apply to
+  pcre_dfa_exec(), which does not use deeply nested recursion. There is a
+  discussion about stack sizes in the pcrestack man page.
+
+. For speed, PCRE uses four tables for manipulating and identifying characters
+  whose code point values are less than 256. By default, it uses a set of
+  tables for ASCII encoding that is part of the distribution. If you specify
+
+  --enable-rebuild-chartables
+
+  a program called dftables is compiled and run in the default C locale when
+  you obey "make". It builds a source file called pcre_chartables.c. If you do
+  not specify this option, pcre_chartables.c is created as a copy of
+  pcre_chartables.c.dist. See "Character tables" below for further information.
+
+. It is possible to compile PCRE for use on systems that use EBCDIC as their
+  character code (as opposed to ASCII) by specifying
+
+  --enable-ebcdic
+
+  This automatically implies --enable-rebuild-chartables (see above). However,
+  when PCRE is built this way, it always operates in EBCDIC. It cannot support
+  both EBCDIC and UTF-8/16.
+
+. The pcregrep program currently supports only 8-bit data files, and so
+  requires the 8-bit PCRE library. It is possible to compile pcregrep to use
+  libz and/or libbz2, in order to read .gz and .bz2 files (respectively), by
+  specifying one or both of
+
+  --enable-pcregrep-libz
+  --enable-pcregrep-libbz2
+
+  Of course, the relevant libraries must be installed on your system.
+
+. The default size of internal buffer used by pcregrep can be set by, for
+  example:
+
+  --with-pcregrep-bufsize=50K
+
+  The default value is 20K.
+
+. It is possible to compile pcretest so that it links with the libreadline
+  or libedit libraries, by specifying, respectively,
+
+  --enable-pcretest-libreadline or --enable-pcretest-libedit
+
+  If this is done, when pcretest's input is from a terminal, it reads it using
+  the readline() function. This provides line-editing and history facilities.
+  Note that libreadline is GPL-licenced, so if you distribute a binary of
+  pcretest linked in this way, there may be licensing issues. These can be
+  avoided by linking with libedit (which has a BSD licence) instead.
+
+  Enabling libreadline causes the -lreadline option to be added to the pcretest
+  build. In many operating environments with a sytem-installed readline
+  library this is sufficient. However, in some environments (e.g. if an
+  unmodified distribution version of readline is in use), it may be necessary
+  to specify something like LIBS="-lncurses" as well. This is because, to quote
+  the readline INSTALL, "Readline uses the termcap functions, but does not link
+  with the termcap or curses library itself, allowing applications which link
+  with readline the to choose an appropriate library." If you get error
+  messages about missing functions tgetstr, tgetent, tputs, tgetflag, or tgoto,
+  this is the problem, and linking with the ncurses library should fix it.
+
+The "configure" script builds the following files for the basic C library:
+
+. Makefile             the makefile that builds the library
+. config.h             build-time configuration options for the library
+. pcre.h               the public PCRE header file
+. pcre-config          script that shows the building settings such as CFLAGS
+                         that were set for "configure"
+. libpcre.pc         ) data for the pkg-config command
+. libpcre16.pc       )
+. libpcreposix.pc    )
+. libtool              script that builds shared and/or static libraries
+
+Versions of config.h and pcre.h are distributed in the PCRE tarballs under the
+names config.h.generic and pcre.h.generic. These are provided for those who
+have to built PCRE without using "configure" or CMake. If you use "configure"
+or CMake, the .generic versions are not used.
+
+When building the 8-bit library, if a C++ compiler is found, the following
+files are also built:
+
+. libpcrecpp.pc        data for the pkg-config command
+. pcrecpparg.h         header file for calling PCRE via the C++ wrapper
+. pcre_stringpiece.h   header for the C++ "stringpiece" functions
+
+The "configure" script also creates config.status, which is an executable
+script that can be run to recreate the configuration, and config.log, which
+contains compiler output from tests that "configure" runs.
+
+Once "configure" has run, you can run "make". This builds either or both of the
+libraries libpcre and libpcre16, and a test program called pcretest. If you
+enabled JIT support with --enable-jit, a test program called pcre_jit_test is
+built as well.
+
+If the 8-bit library is built, libpcreposix and the pcregrep command are also
+built, and if a C++ compiler was found on your system, and you did not disable
+it with --disable-cpp, "make" builds the C++ wrapper library, which is called
+libpcrecpp, as well as some test programs called pcrecpp_unittest,
+pcre_scanner_unittest, and pcre_stringpiece_unittest.
+
+The command "make check" runs all the appropriate tests. Details of the PCRE
+tests are given below in a separate section of this document.
+
+You can use "make install" to install PCRE into live directories on your
+system. The following are installed (file names are all relative to the
+<prefix> that is set when "configure" is run):
+
+  Commands (bin):
+    pcretest
+    pcregrep (if 8-bit support is enabled)
+    pcre-config
+
+  Libraries (lib):
+    libpcre16     (if 16-bit support is enabled)
+    libpcre       (if 8-bit support is enabled)
+    libpcreposix  (if 8-bit support is enabled)
+    libpcrecpp    (if 8-bit and C++ support is enabled)
+
+  Configuration information (lib/pkgconfig):
+    libpcre16.pc
+    libpcre.pc
+    libpcreposix.pc
+    libpcrecpp.pc (if C++ support is enabled)
+
+  Header files (include):
+    pcre.h
+    pcreposix.h
+    pcre_scanner.h      )
+    pcre_stringpiece.h  ) if C++ support is enabled
+    pcrecpp.h           )
+    pcrecpparg.h        )
+
+  Man pages (share/man/man{1,3}):
+    pcregrep.1
+    pcretest.1
+    pcre-config.1
+    pcre.3
+    pcre*.3 (lots more pages, all starting "pcre")
+
+  HTML documentation (share/doc/pcre/html):
+    index.html
+    *.html (lots more pages, hyperlinked from index.html)
+
+  Text file documentation (share/doc/pcre):
+    AUTHORS
+    COPYING
+    ChangeLog
+    LICENCE
+    NEWS
+    README
+    pcre.txt         (a concatenation of the man(3) pages)
+    pcretest.txt     the pcretest man page
+    pcregrep.txt     the pcregrep man page
+    pcre-config.txt  the pcre-config man page
+
+If you want to remove PCRE from your system, you can run "make uninstall".
+This removes all the files that "make install" installed. However, it does not
+remove any directories, because these are often shared with other programs.
+
+
+Retrieving configuration information
+------------------------------------
+
+Running "make install" installs the command pcre-config, which can be used to
+recall information about the PCRE configuration and installation. For example:
+
+  pcre-config --version
+
+prints the version number, and
+
+  pcre-config --libs
+
+outputs information about where the library is installed. This command can be
+included in makefiles for programs that use PCRE, saving the programmer from
+having to remember too many details.
+
+The pkg-config command is another system for saving and retrieving information
+about installed libraries. Instead of separate commands for each library, a
+single command is used. For example:
+
+  pkg-config --cflags pcre
+
+The data is held in *.pc files that are installed in a directory called
+<prefix>/lib/pkgconfig.
+
+
+Shared libraries
+----------------
+
+The default distribution builds PCRE as shared libraries and static libraries,
+as long as the operating system supports shared libraries. Shared library
+support relies on the "libtool" script which is built as part of the
+"configure" process.
+
+The libtool script is used to compile and link both shared and static
+libraries. They are placed in a subdirectory called .libs when they are newly
+built. The programs pcretest and pcregrep are built to use these uninstalled
+libraries (by means of wrapper scripts in the case of shared libraries). When
+you use "make install" to install shared libraries, pcregrep and pcretest are
+automatically re-built to use the newly installed shared libraries before being
+installed themselves. However, the versions left in the build directory still
+use the uninstalled libraries.
+
+To build PCRE using static libraries only you must use --disable-shared when
+configuring it. For example:
+
+./configure --prefix=/usr/gnu --disable-shared
+
+Then run "make" in the usual way. Similarly, you can use --disable-static to
+build only shared libraries.
+
+
+Cross-compiling using autotools
+-------------------------------
+
+You can specify CC and CFLAGS in the normal way to the "configure" command, in
+order to cross-compile PCRE for some other host. However, you should NOT
+specify --enable-rebuild-chartables, because if you do, the dftables.c source
+file is compiled and run on the local host, in order to generate the inbuilt
+character tables (the pcre_chartables.c file). This will probably not work,
+because dftables.c needs to be compiled with the local compiler, not the cross
+compiler.
+
+When --enable-rebuild-chartables is not specified, pcre_chartables.c is created
+by making a copy of pcre_chartables.c.dist, which is a default set of tables
+that assumes ASCII code. Cross-compiling with the default tables should not be
+a problem.
+
+If you need to modify the character tables when cross-compiling, you should
+move pcre_chartables.c.dist out of the way, then compile dftables.c by hand and
+run it on the local host to make a new version of pcre_chartables.c.dist.
+Then when you cross-compile PCRE this new version of the tables will be used.
+
+
+Using HP's ANSI C++ compiler (aCC)
+----------------------------------
+
+Unless C++ support is disabled by specifying the "--disable-cpp" option of the
+"configure" script, you must include the "-AA" option in the CXXFLAGS
+environment variable in order for the C++ components to compile correctly.
+
+Also, note that the aCC compiler on PA-RISC platforms may have a defect whereby
+needed libraries fail to get included when specifying the "-AA" compiler
+option. If you experience unresolved symbols when linking the C++ programs,
+use the workaround of specifying the following environment variable prior to
+running the "configure" script:
+
+  CXXLDFLAGS="-lstd_v2 -lCsup_v2"
+
+
+Using Sun's compilers for Solaris
+---------------------------------
+
+A user reports that the following configurations work on Solaris 9 sparcv9 and
+Solaris 9 x86 (32-bit):
+
+  Solaris 9 sparcv9: ./configure --disable-cpp CC=/bin/cc CFLAGS="-m64 -g"
+  Solaris 9 x86:     ./configure --disable-cpp CC=/bin/cc CFLAGS="-g"
+
+
+Using PCRE from MySQL
+---------------------
+
+On systems where both PCRE and MySQL are installed, it is possible to make use
+of PCRE from within MySQL, as an alternative to the built-in pattern matching.
+There is a web page that tells you how to do this:
+
+  http://www.mysqludf.org/lib_mysqludf_preg/index.php
+
+
+Making new tarballs
+-------------------
+
+The command "make dist" creates three PCRE tarballs, in tar.gz, tar.bz2, and
+zip formats. The command "make distcheck" does the same, but then does a trial
+build of the new distribution to ensure that it works.
+
+If you have modified any of the man page sources in the doc directory, you
+should first run the PrepareRelease script before making a distribution. This
+script creates the .txt and HTML forms of the documentation from the man pages.
+
+
+Testing PCRE
+------------
+
+To test the basic PCRE library on a Unix-like system, run the RunTest script.
+There is another script called RunGrepTest that tests the options of the
+pcregrep command. If the C++ wrapper library is built, three test programs
+called pcrecpp_unittest, pcre_scanner_unittest, and pcre_stringpiece_unittest
+are also built. When JIT support is enabled, another test program called
+pcre_jit_test is built.
+
+Both the scripts and all the program tests are run if you obey "make check" or
+"make test". For other environments, see the instructions in
+NON-AUTOTOOLS-BUILD.
+
+The RunTest script runs the pcretest test program (which is documented in its
+own man page) on each of the relevant testinput files in the testdata
+directory, and compares the output with the contents of the corresponding
+testoutput files. Some tests are relevant only when certain build-time options
+were selected. For example, the tests for UTF-8/16 support are run only if
+--enable-utf was used. RunTest outputs a comment when it skips a test.
+
+Many of the tests that are not skipped are run up to three times. The second
+run forces pcre_study() to be called for all patterns except for a few in some
+tests that are marked "never study" (see the pcretest program for how this is
+done). If JIT support is available, the non-DFA tests are run a third time,
+this time with a forced pcre_study() with the PCRE_STUDY_JIT_COMPILE option.
+
+When both 8-bit and 16-bit support is enabled, the entire set of tests is run
+twice, once for each library. If you want to run just one set of tests, call
+RunTest with either the -8 or -16 option.
+
+RunTest uses a file called testtry to hold the main output from pcretest.
+Other files whose names begin with "test" are used as working files in some
+tests. To run pcretest on just one or more specific test files, give their
+numbers as arguments to RunTest, for example:
+
+  RunTest 2 7 11
+
+You can also call RunTest with the single argument "list" to cause it to output
+a list of tests.
+
+The first test file can be fed directly into the perltest.pl script to check
+that Perl gives the same results. The only difference you should see is in the
+first few lines, where the Perl version is given instead of the PCRE version.
+
+The second set of tests check pcre_fullinfo(), pcre_study(),
+pcre_copy_substring(), pcre_get_substring(), pcre_get_substring_list(), error
+detection, and run-time flags that are specific to PCRE, as well as the POSIX
+wrapper API. It also uses the debugging flags to check some of the internals of
+pcre_compile().
+
+If you build PCRE with a locale setting that is not the standard C locale, the
+character tables may be different (see next paragraph). In some cases, this may
+cause failures in the second set of tests. For example, in a locale where the
+isprint() function yields TRUE for characters in the range 128-255, the use of
+[:isascii:] inside a character class defines a different set of characters, and
+this shows up in this test as a difference in the compiled code, which is being
+listed for checking. Where the comparison test output contains [\x00-\x7f] the
+test will contain [\x00-\xff], and similarly in some other cases. This is not a
+bug in PCRE.
+
+The third set of tests checks pcre_maketables(), the facility for building a
+set of character tables for a specific locale and using them instead of the
+default tables. The tests make use of the "fr_FR" (French) locale. Before
+running the test, the script checks for the presence of this locale by running
+the "locale" command. If that command fails, or if it doesn't include "fr_FR"
+in the list of available locales, the third test cannot be run, and a comment
+is output to say why. If running this test produces instances of the error
+
+  ** Failed to set locale "fr_FR"
+
+in the comparison output, it means that locale is not available on your system,
+despite being listed by "locale". This does not mean that PCRE is broken.
+
+[If you are trying to run this test on Windows, you may be able to get it to
+work by changing "fr_FR" to "french" everywhere it occurs. Alternatively, use
+RunTest.bat. The version of RunTest.bat included with PCRE 7.4 and above uses
+Windows versions of test 2. More info on using RunTest.bat is included in the
+document entitled NON-UNIX-USE.]
+
+The fourth and fifth tests check the UTF-8/16 support and error handling and
+internal UTF features of PCRE that are not relevant to Perl, respectively. The
+sixth and seventh tests do the same for Unicode character properties support.
+
+The eighth, ninth, and tenth tests check the pcre_dfa_exec() alternative
+matching function, in non-UTF-8/16 mode, UTF-8/16 mode, and UTF-8/16 mode with
+Unicode property support, respectively.
+
+The eleventh test checks some internal offsets and code size features; it is
+run only when the default "link size" of 2 is set (in other cases the sizes
+change) and when Unicode property support is enabled.
+
+The twelfth test is run only when JIT support is available, and the thirteenth
+test is run only when JIT support is not available. They test some JIT-specific
+features such as information output from pcretest about JIT compilation.
+
+The fourteenth, fifteenth, and sixteenth tests are run only in 8-bit mode, and
+the seventeenth, eighteenth, and nineteenth tests are run only in 16-bit mode.
+These are tests that generate different output in the two modes. They are for
+general cases, UTF-8/16 support, and Unicode property support, respectively.
+
+The twentieth test is run only in 16-bit mode. It tests some specific 16-bit
+features of the DFA matching engine.
+
+The twenty-first and twenty-second tests are run only in 16-bit mode, when the
+link size is set to 2. They test reloading pre-compiled patterns.
+
+
+Character tables
+----------------
+
+For speed, PCRE uses four tables for manipulating and identifying characters
+whose code point values are less than 256. The final argument of the
+pcre_compile() function is a pointer to a block of memory containing the
+concatenated tables. A call to pcre_maketables() can be used to generate a set
+of tables in the current locale. If the final argument for pcre_compile() is
+passed as NULL, a set of default tables that is built into the binary is used.
+
+The source file called pcre_chartables.c contains the default set of tables. By
+default, this is created as a copy of pcre_chartables.c.dist, which contains
+tables for ASCII coding. However, if --enable-rebuild-chartables is specified
+for ./configure, a different version of pcre_chartables.c is built by the
+program dftables (compiled from dftables.c), which uses the ANSI C character
+handling functions such as isalnum(), isalpha(), isupper(), islower(), etc. to
+build the table sources. This means that the default C locale which is set for
+your system will control the contents of these default tables. You can change
+the default tables by editing pcre_chartables.c and then re-building PCRE. If
+you do this, you should take care to ensure that the file does not get
+automatically re-generated. The best way to do this is to move
+pcre_chartables.c.dist out of the way and replace it with your customized
+tables.
+
+When the dftables program is run as a result of --enable-rebuild-chartables,
+it uses the default C locale that is set on your system. It does not pay
+attention to the LC_xxx environment variables. In other words, it uses the
+system's default locale rather than whatever the compiling user happens to have
+set. If you really do want to build a source set of character tables in a
+locale that is specified by the LC_xxx variables, you can run the dftables
+program by hand with the -L option. For example:
+
+  ./dftables -L pcre_chartables.c.special
+
+The first two 256-byte tables provide lower casing and case flipping functions,
+respectively. The next table consists of three 32-byte bit maps which identify
+digits, "word" characters, and white space, respectively. These are used when
+building 32-byte bit maps that represent character classes for code points less
+than 256.
+
+The final 256-byte table has bits indicating various character types, as
+follows:
+
+    1   white space character
+    2   letter
+    4   decimal digit
+    8   hexadecimal digit
+   16   alphanumeric or '_'
+  128   regular expression metacharacter or binary zero
+
+You should not alter the set of characters that contain the 128 bit, as that
+will cause PCRE to malfunction.
+
+
+File manifest
+-------------
+
+The distribution should contain the files listed below. Where a file name is
+given as pcre[16]_xxx it means that there are two files, one with the name
+pcre_xxx and the other with the name pcre16_xxx.
+
+(A) Source files of the PCRE library functions and their headers:
+
+  dftables.c              auxiliary program for building pcre_chartables.c
+                            when --enable-rebuild-chartables is specified
+
+  pcre_chartables.c.dist  a default set of character tables that assume ASCII
+                            coding; used, unless --enable-rebuild-chartables is
+                            specified, by copying to pcre[16]_chartables.c
+
+  pcreposix.c             )
+  pcre[16]_byte_order.c   )
+  pcre[16]_compile.c      )
+  pcre[16]_config.c       )
+  pcre[16]_dfa_exec.c     )
+  pcre[16]_exec.c         )
+  pcre[16]_fullinfo.c     )
+  pcre[16]_get.c          ) sources for the functions in the library,
+  pcre[16]_globals.c      )   and some internal functions that they use
+  pcre[16]_jit_compile.c  )
+  pcre[16]_maketables.c   )
+  pcre[16]_newline.c      )
+  pcre[16]_refcount.c     )
+  pcre[16]_string_utils.c )
+  pcre[16]_study.c        )
+  pcre[16]_tables.c       )
+  pcre[16]_ucd.c          )
+  pcre[16]_version.c      )
+  pcre[16]_xclass.c       )
+  pcre_ord2utf8.c         )
+  pcre_valid_utf8.c       )
+  pcre16_ord2utf16.c      )
+  pcre16_utf16_utils.c    )
+  pcre16_valid_utf16.c    )
+
+  pcre[16]_printint.c     ) debugging function that is used by pcretest,
+                          )   and can also be #included in pcre_compile()
+
+  pcre.h.in               template for pcre.h when built by "configure"
+  pcreposix.h             header for the external POSIX wrapper API
+  pcre_internal.h         header for internal use
+  sljit/*                 16 files that make up the JIT compiler
+  ucp.h                   header for Unicode property handling
+
+  config.h.in             template for config.h, which is built by "configure"
+
+  pcrecpp.h               public header file for the C++ wrapper
+  pcrecpparg.h.in         template for another C++ header file
+  pcre_scanner.h          public header file for C++ scanner functions
+  pcrecpp.cc              )
+  pcre_scanner.cc         ) source for the C++ wrapper library
+
+  pcre_stringpiece.h.in   template for pcre_stringpiece.h, the header for the
+                            C++ stringpiece functions
+  pcre_stringpiece.cc     source for the C++ stringpiece functions
+
+(B) Source files for programs that use PCRE:
+
+  pcredemo.c              simple demonstration of coding calls to PCRE
+  pcregrep.c              source of a grep utility that uses PCRE
+  pcretest.c              comprehensive test program
+
+(C) Auxiliary files:
+
+  132html                 script to turn "man" pages into HTML
+  AUTHORS                 information about the author of PCRE
+  ChangeLog               log of changes to the code
+  CleanTxt                script to clean nroff output for txt man pages
+  Detrail                 script to remove trailing spaces
+  HACKING                 some notes about the internals of PCRE
+  INSTALL                 generic installation instructions
+  LICENCE                 conditions for the use of PCRE
+  COPYING                 the same, using GNU's standard name
+  Makefile.in             ) template for Unix Makefile, which is built by
+                          )   "configure"
+  Makefile.am             ) the automake input that was used to create
+                          )   Makefile.in
+  NEWS                    important changes in this release
+  NON-UNIX-USE            the previous name for NON-AUTOTOOLS-BUILD
+  NON-AUTOTOOLS-BUILD     notes on building PCRE without using autotools
+  PrepareRelease          script to make preparations for "make dist"
+  README                  this file
+  RunTest                 a Unix shell script for running tests
+  RunGrepTest             a Unix shell script for pcregrep tests
+  aclocal.m4              m4 macros (generated by "aclocal")
+  config.guess            ) files used by libtool,
+  config.sub              )   used only when building a shared library
+  configure               a configuring shell script (built by autoconf)
+  configure.ac            ) the autoconf input that was used to build
+                          )   "configure" and config.h
+  depcomp                 ) script to find program dependencies, generated by
+                          )   automake
+  doc/*.3                 man page sources for PCRE
+  doc/*.1                 man page sources for pcregrep and pcretest
+  doc/index.html.src      the base HTML page
+  doc/html/*              HTML documentation
+  doc/pcre.txt            plain text version of the man pages
+  doc/pcretest.txt        plain text documentation of test program
+  doc/perltest.txt        plain text documentation of Perl test program
+  install-sh              a shell script for installing files
+  libpcre16.pc.in         template for libpcre16.pc for pkg-config
+  libpcre.pc.in           template for libpcre.pc for pkg-config
+  libpcreposix.pc.in      template for libpcreposix.pc for pkg-config
+  libpcrecpp.pc.in        template for libpcrecpp.pc for pkg-config
+  ltmain.sh               file used to build a libtool script
+  missing                 ) common stub for a few missing GNU programs while
+                          )   installing, generated by automake
+  mkinstalldirs           script for making install directories
+  perltest.pl             Perl test program
+  pcre-config.in          source of script which retains PCRE information
+  pcre_jit_test.c         test program for the JIT compiler
+  pcrecpp_unittest.cc          )
+  pcre_scanner_unittest.cc     ) test programs for the C++ wrapper
+  pcre_stringpiece_unittest.cc )
+  testdata/testinput*     test data for main library tests
+  testdata/testoutput*    expected test results
+  testdata/grep*          input and output for pcregrep tests
+  testdata/*              other supporting test files
+
+(D) Auxiliary files for cmake support
+
+  cmake/COPYING-CMAKE-SCRIPTS
+  cmake/FindPackageHandleStandardArgs.cmake
+  cmake/FindEditline.cmake
+  cmake/FindReadline.cmake
+  CMakeLists.txt
+  config-cmake.h.in
+
+(E) Auxiliary files for VPASCAL
+
+  makevp.bat
+  makevp_c.txt
+  makevp_l.txt
+  pcregexp.pas
+
+(F) Auxiliary files for building PCRE "by hand"
+
+  pcre.h.generic          ) a version of the public PCRE header file
+                          )   for use in non-"configure" environments
+  config.h.generic        ) a version of config.h for use in non-"configure"
+                          )   environments
+
+(F) Miscellaneous
+
+  RunTest.bat            a script for running tests under Windows
+
+Philip Hazel
+Email local part: ph10
+Email domain: cam.ac.uk
+Last updated: 18 June 2012
diff --git a/ext/pcre/pcrelib/config.h b/ext/pcre/pcrelib/config.h
new file mode 100644
index 0000000..64e1557
--- /dev/null
+++ b/ext/pcre/pcrelib/config.h
@@ -0,0 +1,361 @@
+
+#include <php_compat.h>
+
+#ifndef PHP_WIN32
+# include <php_config.h>
+#endif
+
+#undef PACKAGE_NAME
+#undef PACKAGE_VERSION
+#undef PACKAGE_TARNAME
+#undef PACKAGE_STRING
+
+#define SUPPORT_UCP
+#define SUPPORT_UTF8
+
+#if defined(__GNUC__) && __GNUC__ >= 4
+# ifdef __cplusplus
+#  define PCRE_EXP_DECL		extern "C" __attribute__ ((visibility("default")))
+# else
+#  define PCRE_EXP_DECL		extern __attribute__ ((visibility("default")))
+# endif
+# define PCRE_EXP_DEFN		__attribute__ ((visibility("default")))
+# define PCRE_EXP_DATA_DEFN	__attribute__ ((visibility("default")))
+#endif
+
+
+/* Exclude these below definitions when building within PHP */
+#ifndef ZEND_API
+
+/* config.h.  Generated from config.h.in by configure.  */
+/* config.h.in.  Generated from configure.ac by autoheader.  */
+
+
+/* On Unix-like systems config.h.in is converted by "configure" into config.h.
+Some other environments also support the use of "configure". PCRE is written in
+Standard C, but there are a few non-standard things it can cope with, allowing
+it to run on SunOS4 and other "close to standard" systems.
+
+If you are going to build PCRE "by hand" on a system without "configure" you
+should copy the distributed config.h.generic to config.h, and then set up the
+macro definitions the way you need them. You must then add -DHAVE_CONFIG_H to
+all of your compile commands, so that config.h is included at the start of
+every source.
+
+Alternatively, you can avoid editing by using -D on the compiler command line
+to set the macro values. In this case, you do not have to set -DHAVE_CONFIG_H.
+
+PCRE uses memmove() if HAVE_MEMMOVE is set to 1; otherwise it uses bcopy() if
+HAVE_BCOPY is set to 1. If your system has neither bcopy() nor memmove(), set
+them both to 0; an emulation function will be used. */
+
+/* By default, the \R escape sequence matches any Unicode line ending
+   character or sequence of characters. If BSR_ANYCRLF is defined, this is
+   changed so that backslash-R matches only CR, LF, or CRLF. The build- time
+   default can be overridden by the user of PCRE at runtime. On systems that
+   support it, "configure" can be used to override the default. */
+/* #undef BSR_ANYCRLF */
+
+/* If you are compiling for a system that uses EBCDIC instead of ASCII
+   character codes, define this macro as 1. On systems that can use
+   "configure", this can be done via --enable-ebcdic. PCRE will then assume
+   that all input strings are in EBCDIC. If you do not define this macro, PCRE
+   will assume input strings are ASCII or UTF-8 Unicode. It is not possible to
+   build a version of PCRE that supports both EBCDIC and UTF-8. */
+/* #undef EBCDIC */
+
+/* Define to 1 if you have the `bcopy' function. */
+#ifndef HAVE_BCOPY
+#define HAVE_BCOPY 1
+#endif
+
+/* Define to 1 if you have the <bits/type_traits.h> header file. */
+/* #undef HAVE_BITS_TYPE_TRAITS_H */
+
+/* Define to 1 if you have the <bzlib.h> header file. */
+#ifndef HAVE_BZLIB_H
+#define HAVE_BZLIB_H 1
+#endif
+
+/* Define to 1 if you have the <dirent.h> header file. */
+#ifndef HAVE_DIRENT_H
+#define HAVE_DIRENT_H 1
+#endif
+
+/* Define to 1 if you have the <dlfcn.h> header file. */
+#ifndef HAVE_DLFCN_H
+#define HAVE_DLFCN_H 1
+#endif
+
+/* Define to 1 if you have the <inttypes.h> header file. */
+#ifndef HAVE_INTTYPES_H
+#define HAVE_INTTYPES_H 1
+#endif
+
+/* Define to 1 if you have the <limits.h> header file. */
+#ifndef HAVE_LIMITS_H
+#define HAVE_LIMITS_H 1
+#endif
+
+/* Define to 1 if the system has the type `long long'. */
+#ifndef HAVE_LONG_LONG
+#define HAVE_LONG_LONG 1
+#endif
+
+/* Define to 1 if you have the `memmove' function. */
+#ifndef HAVE_MEMMOVE
+#define HAVE_MEMMOVE 1
+#endif
+
+/* Define to 1 if you have the <memory.h> header file. */
+#ifndef HAVE_MEMORY_H
+#define HAVE_MEMORY_H 1
+#endif
+
+/* Define to 1 if you have the <readline/history.h> header file. */
+#ifndef HAVE_READLINE_HISTORY_H
+#define HAVE_READLINE_HISTORY_H 1
+#endif
+
+/* Define to 1 if you have the <readline/readline.h> header file. */
+#ifndef HAVE_READLINE_READLINE_H
+#define HAVE_READLINE_READLINE_H 1
+#endif
+
+/* Define to 1 if you have the <stdint.h> header file. */
+#ifndef HAVE_STDINT_H
+#define HAVE_STDINT_H 1
+#endif
+
+/* Define to 1 if you have the <stdlib.h> header file. */
+#ifndef HAVE_STDLIB_H
+#define HAVE_STDLIB_H 1
+#endif
+
+/* Define to 1 if you have the `strerror' function. */
+#ifndef HAVE_STRERROR
+#define HAVE_STRERROR 1
+#endif
+
+/* Define to 1 if you have the <string> header file. */
+#ifndef HAVE_STRING
+#define HAVE_STRING 1
+#endif
+
+/* Define to 1 if you have the <strings.h> header file. */
+#ifndef HAVE_STRINGS_H
+#define HAVE_STRINGS_H 1
+#endif
+
+/* Define to 1 if you have the <string.h> header file. */
+#ifndef HAVE_STRING_H
+#define HAVE_STRING_H 1
+#endif
+
+/* Define to 1 if you have `strtoimax'. */
+/* #undef HAVE_STRTOIMAX */
+
+/* Define to 1 if you have `strtoll'. */
+/* #undef HAVE_STRTOLL */
+
+/* Define to 1 if you have `strtoq'. */
+#ifndef HAVE_STRTOQ
+#define HAVE_STRTOQ 1
+#endif
+
+/* Define to 1 if you have the <sys/stat.h> header file. */
+#ifndef HAVE_SYS_STAT_H
+#define HAVE_SYS_STAT_H 1
+#endif
+
+/* Define to 1 if you have the <sys/types.h> header file. */
+#ifndef HAVE_SYS_TYPES_H
+#define HAVE_SYS_TYPES_H 1
+#endif
+
+/* Define to 1 if you have the <type_traits.h> header file. */
+/* #undef HAVE_TYPE_TRAITS_H */
+
+/* Define to 1 if you have the <unistd.h> header file. */
+#ifndef HAVE_UNISTD_H
+#define HAVE_UNISTD_H 1
+#endif
+
+/* Define to 1 if the system has the type `unsigned long long'. */
+#ifndef HAVE_UNSIGNED_LONG_LONG
+#define HAVE_UNSIGNED_LONG_LONG 1
+#endif
+
+/* Define to 1 if you have the <windows.h> header file. */
+/* #undef HAVE_WINDOWS_H */
+
+/* Define to 1 if you have the <zlib.h> header file. */
+#ifndef HAVE_ZLIB_H
+#define HAVE_ZLIB_H 1
+#endif
+
+/* Define to 1 if you have `_strtoi64'. */
+/* #undef HAVE__STRTOI64 */
+
+/* Exclude these above definitions when building within PHP */
+#endif
+
+/* The value of LINK_SIZE determines the number of bytes used to store links
+   as offsets within the compiled regex. The default is 2, which allows for
+   compiled patterns up to 64K long. This covers the vast majority of cases.
+   However, PCRE can also be compiled to use 3 or 4 bytes instead. This allows
+   for longer patterns in extreme cases. On systems that support it,
+   "configure" can be used to override this default. */
+#ifndef LINK_SIZE
+#define LINK_SIZE 2
+#endif
+
+/* Define to the sub-directory in which libtool stores uninstalled libraries.
+   */
+#ifndef LT_OBJDIR
+#define LT_OBJDIR ".libs/"
+#endif
+
+/* The value of MATCH_LIMIT determines the default number of times the
+   internal match() function can be called during a single execution of
+   pcre_exec(). There is a runtime interface for setting a different limit.
+   The limit exists in order to catch runaway regular expressions that take
+   for ever to determine that they do not match. The default is set very large
+   so that it does not accidentally catch legitimate cases. On systems that
+   support it, "configure" can be used to override this default default. */
+#ifndef MATCH_LIMIT
+#define MATCH_LIMIT 10000000
+#endif
+
+/* The above limit applies to all calls of match(), whether or not they
+   increase the recursion depth. In some environments it is desirable to limit
+   the depth of recursive calls of match() more strictly, in order to restrict
+   the maximum amount of stack (or heap, if NO_RECURSE is defined) that is
+   used. The value of MATCH_LIMIT_RECURSION applies only to recursive calls of
+   match(). To have any useful effect, it must be less than the value of
+   MATCH_LIMIT. The default is to use the same value as MATCH_LIMIT. There is
+   a runtime method for setting a different limit. On systems that support it,
+   "configure" can be used to override the default. */
+#ifndef MATCH_LIMIT_RECURSION
+#define MATCH_LIMIT_RECURSION MATCH_LIMIT
+#endif
+
+/* This limit is parameterized just in case anybody ever wants to change it.
+   Care must be taken if it is increased, because it guards against integer
+   overflow caused by enormously large patterns. */
+#ifndef MAX_NAME_COUNT
+#define MAX_NAME_COUNT 10000
+#endif
+
+/* This limit is parameterized just in case anybody ever wants to change it.
+   Care must be taken if it is increased, because it guards against integer
+   overflow caused by enormously large patterns. */
+#ifndef MAX_NAME_SIZE
+#define MAX_NAME_SIZE 32
+#endif
+
+/* The value of NEWLINE determines the newline character sequence. On systems
+   that support it, "configure" can be used to override the default, which is
+   10. The possible values are 10 (LF), 13 (CR), 3338 (CRLF), -1 (ANY), or -2
+   (ANYCRLF). */
+#ifndef NEWLINE
+#define NEWLINE 10
+#endif
+
+/* PCRE uses recursive function calls to handle backtracking while matching.
+   This can sometimes be a problem on systems that have stacks of limited
+   size. Define NO_RECURSE to get a version that doesn't use recursion in the
+   match() function; instead it creates its own stack by steam using
+   pcre_recurse_malloc() to obtain memory from the heap. For more detail, see
+   the comments and other stuff just above the match() function. On systems
+   that support it, "configure" can be used to set this in the Makefile (use
+   --disable-stack-for-recursion). */
+/* #undef NO_RECURSE */
+
+/* Name of package */
+#define PACKAGE "pcre"
+
+/* Define to the address where bug reports for this package should be sent. */
+#define PACKAGE_BUGREPORT ""
+
+/* Define to the full name of this package. */
+#define PACKAGE_NAME "PCRE"
+
+/* Define to the full name and version of this package. */
+#define PACKAGE_STRING "PCRE 8.31"
+
+/* Define to the one symbol short name of this package. */
+#define PACKAGE_TARNAME "pcre"
+
+/* Define to the home page for this package. */
+#define PACKAGE_URL ""
+
+/* Define to the version of this package. */
+#define PACKAGE_VERSION "8.31"
+
+
+/* If you are compiling for a system other than a Unix-like system or
+   Win32, and it needs some magic to be inserted before the definition
+   of a function that is exported by the library, define this macro to
+   contain the relevant magic. If you do not define this macro, it
+   defaults to "extern" for a C compiler and "extern C" for a C++
+   compiler on non-Win32 systems. This macro apears at the start of
+   every exported function that is part of the external API. It does
+   not appear on functions that are "external" in the C sense, but
+   which are internal to the library. */
+/* #undef PCRE_EXP_DEFN */
+
+/* Define if linking statically (TODO: make nice with Libtool) */
+/* #undef PCRE_STATIC */
+
+/* When calling PCRE via the POSIX interface, additional working storage is
+   required for holding the pointers to capturing substrings because PCRE
+   requires three integers per substring, whereas the POSIX interface provides
+   only two. If the number of expected substrings is small, the wrapper
+   function uses space on the stack, because this is faster than using
+   malloc() for each call. The threshold above which the stack is no longer
+   used is defined by POSIX_MALLOC_THRESHOLD. On systems that support it,
+   "configure" can be used to override this default. */
+#ifndef POSIX_MALLOC_THRESHOLD
+#define POSIX_MALLOC_THRESHOLD 10
+#endif
+
+/* Define to 1 if you have the ANSI C header files. */
+#ifndef STDC_HEADERS
+#define STDC_HEADERS 1
+#endif
+
+/* Define to allow pcregrep to be linked with libbz2, so that it is able to
+   handle .bz2 files. */
+/* #undef SUPPORT_LIBBZ2 */
+
+/* Define to allow pcretest to be linked with libreadline. */
+/* #undef SUPPORT_LIBREADLINE */
+
+/* Define to allow pcregrep to be linked with libz, so that it is able to
+   handle .gz files. */
+/* #undef SUPPORT_LIBZ */
+
+/* Define to enable support for Unicode properties */
+/* #undef SUPPORT_UCP */
+
+/* Define to enable support for the UTF-8 Unicode encoding. This will work
+   even in an EBCDIC environment, but it is incompatible with the EBCDIC
+   macro. That is, PCRE can support *either* EBCDIC code *or* ASCII/UTF-8, but
+   not both at once. */
+/* #undef SUPPORT_UTF8 */
+
+/* Version number of package */
+#ifndef VERSION
+#define VERSION "8.31"
+#endif
+
+/* Define to empty if `const' does not conform to ANSI C. */
+/* #undef const */
+
+/* Define to the type of a signed integer type of width exactly 64 bits if
+   such a type exists and the standard includes do not define it. */
+/* #undef int64_t */
+
+/* Define to `unsigned int' if <sys/types.h> does not define. */
+/* #undef size_t */
diff --git a/ext/pcre/pcrelib/dftables.c b/ext/pcre/pcrelib/dftables.c
new file mode 100644
index 0000000..763ac8c
--- /dev/null
+++ b/ext/pcre/pcrelib/dftables.c
@@ -0,0 +1,197 @@
+/*************************************************
+*      Perl-Compatible Regular Expressions       *
+*************************************************/
+
+/* PCRE is a library of functions to support regular expressions whose syntax
+and semantics are as close as possible to those of the Perl 5 language.
+
+                       Written by Philip Hazel
+           Copyright (c) 1997-2012 University of Cambridge
+
+-----------------------------------------------------------------------------
+Redistribution and use in source and binary forms, with or without
+modification, are permitted provided that the following conditions are met:
+
+    * Redistributions of source code must retain the above copyright notice,
+      this list of conditions and the following disclaimer.
+
+    * Redistributions in binary form must reproduce the above copyright
+      notice, this list of conditions and the following disclaimer in the
+      documentation and/or other materials provided with the distribution.
+
+    * Neither the name of the University of Cambridge nor the names of its
+      contributors may be used to endorse or promote products derived from
+      this software without specific prior written permission.
+
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+POSSIBILITY OF SUCH DAMAGE.
+-----------------------------------------------------------------------------
+*/
+
+
+/* This is a freestanding support program to generate a file containing
+character tables for PCRE. The tables are built according to the current
+locale. Now that pcre_maketables is a function visible to the outside world, we
+make use of its code from here in order to be consistent. */
+
+#include "config.h"
+
+#include <ctype.h>
+#include <stdio.h>
+#include <string.h>
+#include <locale.h>
+
+#include "pcre_internal.h"
+
+#define DFTABLES          /* pcre_maketables.c notices this */
+#include "pcre_maketables.c"
+
+
+int main(int argc, char **argv)
+{
+FILE *f;
+int i = 1;
+const unsigned char *tables;
+const unsigned char *base_of_tables;
+
+/* By default, the default C locale is used rather than what the building user
+happens to have set. However, if the -L option is given, set the locale from
+the LC_xxx environment variables. */
+
+if (argc > 1 && strcmp(argv[1], "-L") == 0)
+  {
+  setlocale(LC_ALL, "");        /* Set from environment variables */
+  i++;
+  }
+
+if (argc < i + 1)
+  {
+  fprintf(stderr, "dftables: one filename argument is required\n");
+  return 1;
+  }
+
+tables = pcre_maketables();
+base_of_tables = tables;
+
+f = fopen(argv[i], "wb");
+if (f == NULL)
+  {
+  fprintf(stderr, "dftables: failed to open %s for writing\n", argv[1]);
+  return 1;
+  }
+
+/* There are several fprintf() calls here, because gcc in pedantic mode
+complains about the very long string otherwise. */
+
+fprintf(f,
+  "/*************************************************\n"
+  "*      Perl-Compatible Regular Expressions       *\n"
+  "*************************************************/\n\n"
+  "/* This file was automatically written by the dftables auxiliary\n"
+  "program. It contains character tables that are used when no external\n"
+  "tables are passed to PCRE by the application that calls it. The tables\n"
+  "are used only for characters whose code values are less than 256.\n\n");
+fprintf(f,
+  "The following #includes are present because without them gcc 4.x may remove\n"
+  "the array definition from the final binary if PCRE is built into a static\n"
+  "library and dead code stripping is activated. This leads to link errors.\n"
+  "Pulling in the header ensures that the array gets flagged as \"someone\n"
+  "outside this compilation unit might reference this\" and so it will always\n"
+  "be supplied to the linker. */\n\n"
+  "#ifdef HAVE_CONFIG_H\n"
+  "#include \"config.h\"\n"
+  "#endif\n\n"
+  "#include \"pcre_internal.h\"\n\n");
+fprintf(f,
+  "const pcre_uint8 PRIV(default_tables)[] = {\n\n"
+  "/* This table is a lower casing table. */\n\n");
+
+fprintf(f, "  ");
+for (i = 0; i < 256; i++)
+  {
+  if ((i & 7) == 0 && i != 0) fprintf(f, "\n  ");
+  fprintf(f, "%3d", *tables++);
+  if (i != 255) fprintf(f, ",");
+  }
+fprintf(f, ",\n\n");
+
+fprintf(f, "/* This table is a case flipping table. */\n\n");
+
+fprintf(f, "  ");
+for (i = 0; i < 256; i++)
+  {
+  if ((i & 7) == 0 && i != 0) fprintf(f, "\n  ");
+  fprintf(f, "%3d", *tables++);
+  if (i != 255) fprintf(f, ",");
+  }
+fprintf(f, ",\n\n");
+
+fprintf(f,
+  "/* This table contains bit maps for various character classes.\n"
+  "Each map is 32 bytes long and the bits run from the least\n"
+  "significant end of each byte. The classes that have their own\n"
+  "maps are: space, xdigit, digit, upper, lower, word, graph\n"
+  "print, punct, and cntrl. Other classes are built from combinations. */\n\n");
+
+fprintf(f, "  ");
+for (i = 0; i < cbit_length; i++)
+  {
+  if ((i & 7) == 0 && i != 0)
+    {
+    if ((i & 31) == 0) fprintf(f, "\n");
+    fprintf(f, "\n  ");
+    }
+  fprintf(f, "0x%02x", *tables++);
+  if (i != cbit_length - 1) fprintf(f, ",");
+  }
+fprintf(f, ",\n\n");
+
+fprintf(f,
+  "/* This table identifies various classes of character by individual bits:\n"
+  "  0x%02x   white space character\n"
+  "  0x%02x   letter\n"
+  "  0x%02x   decimal digit\n"
+  "  0x%02x   hexadecimal digit\n"
+  "  0x%02x   alphanumeric or '_'\n"
+  "  0x%02x   regular expression metacharacter or binary zero\n*/\n\n",
+  ctype_space, ctype_letter, ctype_digit, ctype_xdigit, ctype_word,
+  ctype_meta);
+
+fprintf(f, "  ");
+for (i = 0; i < 256; i++)
+  {
+  if ((i & 7) == 0 && i != 0)
+    {
+    fprintf(f, " /* ");
+    if (isprint(i-8)) fprintf(f, " %c -", i-8);
+      else fprintf(f, "%3d-", i-8);
+    if (isprint(i-1)) fprintf(f, " %c ", i-1);
+      else fprintf(f, "%3d", i-1);
+    fprintf(f, " */\n  ");
+    }
+  fprintf(f, "0x%02x", *tables++);
+  if (i != 255) fprintf(f, ",");
+  }
+
+fprintf(f, "};/* ");
+if (isprint(i-8)) fprintf(f, " %c -", i-8);
+  else fprintf(f, "%3d-", i-8);
+if (isprint(i-1)) fprintf(f, " %c ", i-1);
+  else fprintf(f, "%3d", i-1);
+fprintf(f, " */\n\n/* End of pcre_chartables.c */\n");
+
+fclose(f);
+free((void *)base_of_tables);
+return 0;
+}
+
+/* End of dftables.c */
diff --git a/ext/pcre/pcrelib/doc/pcre.txt b/ext/pcre/pcrelib/doc/pcre.txt
new file mode 100644
index 0000000..19f04f2
--- /dev/null
+++ b/ext/pcre/pcrelib/doc/pcre.txt
@@ -0,0 +1,9160 @@
+-----------------------------------------------------------------------------
+This file contains a concatenation of the PCRE man pages, converted to plain
+text format for ease of searching with a text editor, or for use on systems
+that do not have a man page processor. The small individual files that give
+synopses of each function in the library have not been included. Neither has
+the pcredemo program. There are separate text files for the pcregrep and
+pcretest commands.
+-----------------------------------------------------------------------------
+
+
+PCRE(3)                                                                PCRE(3)
+
+
+NAME
+       PCRE - Perl-compatible regular expressions
+
+
+INTRODUCTION
+
+       The  PCRE  library is a set of functions that implement regular expres-
+       sion pattern matching using the same syntax and semantics as Perl, with
+       just  a few differences. Some features that appeared in Python and PCRE
+       before they appeared in Perl are also available using the  Python  syn-
+       tax,  there  is  some  support for one or two .NET and Oniguruma syntax
+       items, and there is an option for requesting some  minor  changes  that
+       give better JavaScript compatibility.
+
+       Starting with release 8.30, it is possible to compile two separate PCRE
+       libraries:  the  original,  which  supports  8-bit  character   strings
+       (including  UTF-8  strings),  and a second library that supports 16-bit
+       character strings (including UTF-16 strings). The build process  allows
+       either  one  or both to be built. The majority of the work to make this
+       possible was done by Zoltan Herczeg.
+
+       The two libraries contain identical sets of functions, except that  the
+       names  in  the  16-bit  library start with pcre16_ instead of pcre_. To
+       avoid over-complication and reduce the documentation maintenance  load,
+       most of the documentation describes the 8-bit library, with the differ-
+       ences for the 16-bit library described separately in the  pcre16  page.
+       References  to  functions or structures of the form pcre[16]_xxx should
+       be  read  as  meaning  "pcre_xxx  when  using  the  8-bit  library  and
+       pcre16_xxx when using the 16-bit library".
+
+       The  current implementation of PCRE corresponds approximately with Perl
+       5.12, including support for UTF-8/16 encoded strings and  Unicode  gen-
+       eral  category properties. However, UTF-8/16 and Unicode support has to
+       be explicitly enabled; it is not the default. The Unicode tables corre-
+       spond to Unicode release 6.0.0.
+
+       In  addition to the Perl-compatible matching function, PCRE contains an
+       alternative function that matches the same compiled patterns in a  dif-
+       ferent way. In certain circumstances, the alternative function has some
+       advantages.  For a discussion of the two matching algorithms,  see  the
+       pcrematching page.
+
+       PCRE  is  written  in C and released as a C library. A number of people
+       have written wrappers and interfaces of various kinds.  In  particular,
+       Google  Inc.   have  provided a comprehensive C++ wrapper for the 8-bit
+       library. This is now included as part of  the  PCRE  distribution.  The
+       pcrecpp  page  has  details of this interface. Other people's contribu-
+       tions can be found in the Contrib directory at the  primary  FTP  site,
+       which is:
+
+       ftp://ftp.csx.cam.ac.uk/pub/software/programming/pcre
+
+       Details  of  exactly which Perl regular expression features are and are
+       not supported by PCRE are given in separate documents. See the pcrepat-
+       tern  and pcrecompat pages. There is a syntax summary in the pcresyntax
+       page.
+
+       Some features of PCRE can be included, excluded, or  changed  when  the
+       library  is  built.  The pcre_config() function makes it possible for a
+       client to discover which features are  available.  The  features  them-
+       selves  are described in the pcrebuild page. Documentation about build-
+       ing PCRE for various operating systems can be found in the  README  and
+       NON-UNIX-USE files in the source distribution.
+
+       The  libraries contains a number of undocumented internal functions and
+       data tables that are used by more than one  of  the  exported  external
+       functions,  but  which  are  not  intended for use by external callers.
+       Their names all begin with "_pcre_" or "_pcre16_", which hopefully will
+       not  provoke  any name clashes. In some environments, it is possible to
+       control which external symbols are exported when a  shared  library  is
+       built, and in these cases the undocumented symbols are not exported.
+
+
+USER DOCUMENTATION
+
+       The  user  documentation  for PCRE comprises a number of different sec-
+       tions. In the "man" format, each of these is a separate "man page".  In
+       the  HTML  format, each is a separate page, linked from the index page.
+       In the plain text format, all the sections, except  the  pcredemo  sec-
+       tion, are concatenated, for ease of searching. The sections are as fol-
+       lows:
+
+         pcre              this document
+         pcre16            details of the 16-bit library
+         pcre-config       show PCRE installation configuration information
+         pcreapi           details of PCRE's native C API
+         pcrebuild         options for building PCRE
+         pcrecallout       details of the callout feature
+         pcrecompat        discussion of Perl compatibility
+         pcrecpp           details of the C++ wrapper for the 8-bit library
+         pcredemo          a demonstration C program that uses PCRE
+         pcregrep          description of the pcregrep command (8-bit only)
+         pcrejit           discussion of the just-in-time optimization support
+         pcrelimits        details of size and other limits
+         pcrematching      discussion of the two matching algorithms
+         pcrepartial       details of the partial matching facility
+         pcrepattern       syntax and semantics of supported
+                             regular expressions
+         pcreperform       discussion of performance issues
+         pcreposix         the POSIX-compatible C API for the 8-bit library
+         pcreprecompile    details of saving and re-using precompiled patterns
+         pcresample        discussion of the pcredemo program
+         pcrestack         discussion of stack usage
+         pcresyntax        quick syntax reference
+         pcretest          description of the pcretest testing command
+         pcreunicode       discussion of Unicode and UTF-8/16 support
+
+       In addition, in the "man" and HTML formats, there is a short  page  for
+       each 8-bit C library function, listing its arguments and results.
+
+
+AUTHOR
+
+       Philip Hazel
+       University Computing Service
+       Cambridge CB2 3QH, England.
+
+       Putting  an actual email address here seems to have been a spam magnet,
+       so I've taken it away. If you want to email me, use  my  two  initials,
+       followed by the two digits 10, at the domain cam.ac.uk.
+
+
+REVISION
+
+       Last updated: 10 January 2012
+       Copyright (c) 1997-2012 University of Cambridge.
+------------------------------------------------------------------------------
+
+
+PCRE(3)                                                                PCRE(3)
+
+
+NAME
+       PCRE - Perl-compatible regular expressions
+
+       #include <pcre.h>
+
+
+PCRE 16-BIT API BASIC FUNCTIONS
+
+       pcre16 *pcre16_compile(PCRE_SPTR16 pattern, int options,
+            const char **errptr, int *erroffset,
+            const unsigned char *tableptr);
+
+       pcre16 *pcre16_compile2(PCRE_SPTR16 pattern, int options,
+            int *errorcodeptr,
+            const char **errptr, int *erroffset,
+            const unsigned char *tableptr);
+
+       pcre16_extra *pcre16_study(const pcre16 *code, int options,
+            const char **errptr);
+
+       void pcre16_free_study(pcre16_extra *extra);
+
+       int pcre16_exec(const pcre16 *code, const pcre16_extra *extra,
+            PCRE_SPTR16 subject, int length, int startoffset,
+            int options, int *ovector, int ovecsize);
+
+       int pcre16_dfa_exec(const pcre16 *code, const pcre16_extra *extra,
+            PCRE_SPTR16 subject, int length, int startoffset,
+            int options, int *ovector, int ovecsize,
+            int *workspace, int wscount);
+
+
+PCRE 16-BIT API STRING EXTRACTION FUNCTIONS
+
+       int pcre16_copy_named_substring(const pcre16 *code,
+            PCRE_SPTR16 subject, int *ovector,
+            int stringcount, PCRE_SPTR16 stringname,
+            PCRE_UCHAR16 *buffer, int buffersize);
+
+       int pcre16_copy_substring(PCRE_SPTR16 subject, int *ovector,
+            int stringcount, int stringnumber, PCRE_UCHAR16 *buffer,
+            int buffersize);
+
+       int pcre16_get_named_substring(const pcre16 *code,
+            PCRE_SPTR16 subject, int *ovector,
+            int stringcount, PCRE_SPTR16 stringname,
+            PCRE_SPTR16 *stringptr);
+
+       int pcre16_get_stringnumber(const pcre16 *code,
+            PCRE_SPTR16 name);
+
+       int pcre16_get_stringtable_entries(const pcre16 *code,
+            PCRE_SPTR16 name, PCRE_UCHAR16 **first, PCRE_UCHAR16 **last);
+
+       int pcre16_get_substring(PCRE_SPTR16 subject, int *ovector,
+            int stringcount, int stringnumber,
+            PCRE_SPTR16 *stringptr);
+
+       int pcre16_get_substring_list(PCRE_SPTR16 subject,
+            int *ovector, int stringcount, PCRE_SPTR16 **listptr);
+
+       void pcre16_free_substring(PCRE_SPTR16 stringptr);
+
+       void pcre16_free_substring_list(PCRE_SPTR16 *stringptr);
+
+
+PCRE 16-BIT API AUXILIARY FUNCTIONS
+
+       pcre16_jit_stack *pcre16_jit_stack_alloc(int startsize, int maxsize);
+
+       void pcre16_jit_stack_free(pcre16_jit_stack *stack);
+
+       void pcre16_assign_jit_stack(pcre16_extra *extra,
+            pcre16_jit_callback callback, void *data);
+
+       const unsigned char *pcre16_maketables(void);
+
+       int pcre16_fullinfo(const pcre16 *code, const pcre16_extra *extra,
+            int what, void *where);
+
+       int pcre16_refcount(pcre16 *code, int adjust);
+
+       int pcre16_config(int what, void *where);
+
+       const char *pcre16_version(void);
+
+       int pcre16_pattern_to_host_byte_order(pcre16 *code,
+            pcre16_extra *extra, const unsigned char *tables);
+
+
+PCRE 16-BIT API INDIRECTED FUNCTIONS
+
+       void *(*pcre16_malloc)(size_t);
+
+       void (*pcre16_free)(void *);
+
+       void *(*pcre16_stack_malloc)(size_t);
+
+       void (*pcre16_stack_free)(void *);
+
+       int (*pcre16_callout)(pcre16_callout_block *);
+
+
+PCRE 16-BIT API 16-BIT-ONLY FUNCTION
+
+       int pcre16_utf16_to_host_byte_order(PCRE_UCHAR16 *output,
+            PCRE_SPTR16 input, int length, int *byte_order,
+            int keep_boms);
+
+
+THE PCRE 16-BIT LIBRARY
+
+       Starting  with  release  8.30, it is possible to compile a PCRE library
+       that supports 16-bit character strings, including  UTF-16  strings,  as
+       well  as  or instead of the original 8-bit library. The majority of the
+       work to make  this  possible  was  done  by  Zoltan  Herczeg.  The  two
+       libraries contain identical sets of functions, used in exactly the same
+       way. Only the names of the functions and the data types of their  argu-
+       ments  and results are different. To avoid over-complication and reduce
+       the documentation maintenance load,  most  of  the  PCRE  documentation
+       describes  the  8-bit  library,  with only occasional references to the
+       16-bit library. This page describes what is different when you use  the
+       16-bit library.
+
+       WARNING:  A  single  application can be linked with both libraries, but
+       you must take care when processing any particular pattern to use  func-
+       tions  from  just one library. For example, if you want to study a pat-
+       tern that was compiled with  pcre16_compile(),  you  must  do  so  with
+       pcre16_study(), not pcre_study(), and you must free the study data with
+       pcre16_free_study().
+
+
+THE HEADER FILE
+
+       There is only one header file, pcre.h. It contains prototypes  for  all
+       the  functions  in  both  libraries,  as  well as definitions of flags,
+       structures, error codes, etc.
+
+
+THE LIBRARY NAME
+
+       In Unix-like systems, the 16-bit library is called libpcre16,  and  can
+       normally  be  accesss  by adding -lpcre16 to the command for linking an
+       application that uses PCRE.
+
+
+STRING TYPES
+
+       In the 8-bit library, strings are passed to PCRE library  functions  as
+       vectors  of  bytes  with  the  C  type "char *". In the 16-bit library,
+       strings are passed as vectors of unsigned 16-bit quantities. The  macro
+       PCRE_UCHAR16  specifies  an  appropriate  data type, and PCRE_SPTR16 is
+       defined as "const PCRE_UCHAR16 *". In very  many  environments,  "short
+       int" is a 16-bit data type. When PCRE is built, it defines PCRE_UCHAR16
+       as "short int", but checks that it really is a 16-bit data type. If  it
+       is not, the build fails with an error message telling the maintainer to
+       modify the definition appropriately.
+
+
+STRUCTURE TYPES
+
+       The types of the opaque structures that are used  for  compiled  16-bit
+       patterns  and  JIT stacks are pcre16 and pcre16_jit_stack respectively.
+       The  type  of  the  user-accessible  structure  that  is  returned   by
+       pcre16_study()  is  pcre16_extra, and the type of the structure that is
+       used for passing data to a callout  function  is  pcre16_callout_block.
+       These structures contain the same fields, with the same names, as their
+       8-bit counterparts. The only difference is that pointers  to  character
+       strings are 16-bit instead of 8-bit types.
+
+
+16-BIT FUNCTIONS
+
+       For  every function in the 8-bit library there is a corresponding func-
+       tion in the 16-bit library with a name that starts with pcre16_ instead
+       of  pcre_.  The  prototypes are listed above. In addition, there is one
+       extra function, pcre16_utf16_to_host_byte_order(). This  is  a  utility
+       function  that converts a UTF-16 character string to host byte order if
+       necessary. The other 16-bit  functions  expect  the  strings  they  are
+       passed to be in host byte order.
+
+       The input and output arguments of pcre16_utf16_to_host_byte_order() may
+       point to the same address, that is, conversion in place  is  supported.
+       The output buffer must be at least as long as the input.
+
+       The  length  argument  specifies the number of 16-bit data units in the
+       input string; a negative value specifies a zero-terminated string.
+
+       If byte_order is NULL, it is assumed that the string starts off in host
+       byte  order. This may be changed by byte-order marks (BOMs) anywhere in
+       the string (commonly as the first character).
+
+       If byte_order is not NULL, a non-zero value of the integer to which  it
+       points  means  that  the input starts off in host byte order, otherwise
+       the opposite order is assumed. Again, BOMs in  the  string  can  change
+       this. The final byte order is passed back at the end of processing.
+
+       If  keep_boms  is  not  zero,  byte-order  mark characters (0xfeff) are
+       copied into the output string. Otherwise they are discarded.
+
+       The result of the function is the number of 16-bit  units  placed  into
+       the  output  buffer,  including  the  zero terminator if the string was
+       zero-terminated.
+
+
+SUBJECT STRING OFFSETS
+
+       The offsets within subject strings that are returned  by  the  matching
+       functions are in 16-bit units rather than bytes.
+
+
+NAMED SUBPATTERNS
+
+       The  name-to-number translation table that is maintained for named sub-
+       patterns uses 16-bit characters.  The  pcre16_get_stringtable_entries()
+       function returns the length of each entry in the table as the number of
+       16-bit data units.
+
+
+OPTION NAMES
+
+       There   are   two   new   general   option   names,   PCRE_UTF16    and
+       PCRE_NO_UTF16_CHECK,     which     correspond    to    PCRE_UTF8    and
+       PCRE_NO_UTF8_CHECK in the 8-bit library. In  fact,  these  new  options
+       define  the  same bits in the options word. There is a discussion about
+       the validity of UTF-16 strings in the pcreunicode page.
+
+       For the pcre16_config() function there is an  option  PCRE_CONFIG_UTF16
+       that  returns  1  if UTF-16 support is configured, otherwise 0. If this
+       option is given to pcre_config(), or if the PCRE_CONFIG_UTF8 option  is
+       given to pcre16_config(), the result is the PCRE_ERROR_BADOPTION error.
+
+
+CHARACTER CODES
+
+       In  16-bit  mode,  when  PCRE_UTF16  is  not  set, character values are
+       treated in the same way as in 8-bit, non UTF-8 mode, except, of course,
+       that  they  can  range from 0 to 0xffff instead of 0 to 0xff. Character
+       types for characters less than 0xff can therefore be influenced by  the
+       locale  in  the  same way as before.  Characters greater than 0xff have
+       only one case, and no "type" (such as letter or digit).
+
+       In UTF-16 mode, the character code  is  Unicode,  in  the  range  0  to
+       0x10ffff,  with  the  exception of values in the range 0xd800 to 0xdfff
+       because those are "surrogate" values that are used in pairs  to  encode
+       values greater than 0xffff.
+
+       A  UTF-16 string can indicate its endianness by special code knows as a
+       byte-order mark (BOM). The PCRE functions do not handle this, expecting
+       strings   to   be  in  host  byte  order.  A  utility  function  called
+       pcre16_utf16_to_host_byte_order() is provided to help  with  this  (see
+       above).
+
+
+ERROR NAMES
+
+       The  errors PCRE_ERROR_BADUTF16_OFFSET and PCRE_ERROR_SHORTUTF16 corre-
+       spond to their 8-bit  counterparts.  The  error  PCRE_ERROR_BADMODE  is
+       given  when  a  compiled pattern is passed to a function that processes
+       patterns in the other mode, for example, if  a  pattern  compiled  with
+       pcre_compile() is passed to pcre16_exec().
+
+       There  are  new  error  codes whose names begin with PCRE_UTF16_ERR for
+       invalid UTF-16 strings, corresponding to the  PCRE_UTF8_ERR  codes  for
+       UTF-8  strings that are described in the section entitled "Reason codes
+       for invalid UTF-8 strings" in the main pcreapi page. The UTF-16  errors
+       are:
+
+         PCRE_UTF16_ERR1  Missing low surrogate at end of string
+         PCRE_UTF16_ERR2  Invalid low surrogate follows high surrogate
+         PCRE_UTF16_ERR3  Isolated low surrogate
+         PCRE_UTF16_ERR4  Invalid character 0xfffe
+
+
+ERROR TEXTS
+
+       If  there is an error while compiling a pattern, the error text that is
+       passed back by pcre16_compile() or pcre16_compile2() is still an  8-bit
+       character string, zero-terminated.
+
+
+CALLOUTS
+
+       The  subject  and  mark fields in the callout block that is passed to a
+       callout function point to 16-bit vectors.
+
+
+TESTING
+
+       The pcretest program continues to operate with 8-bit input  and  output
+       files,  but it can be used for testing the 16-bit library. If it is run
+       with the command line option -16, patterns and subject strings are con-
+       verted from 8-bit to 16-bit before being passed to PCRE, and the 16-bit
+       library functions are used instead of the 8-bit ones.  Returned  16-bit
+       strings are converted to 8-bit for output. If the 8-bit library was not
+       compiled, pcretest defaults to 16-bit and the -16 option is ignored.
+
+       When PCRE is being built, the RunTest script that is  called  by  "make
+       check"  uses  the pcretest -C option to discover which of the 8-bit and
+       16-bit libraries has been built, and runs the tests appropriately.
+
+
+NOT SUPPORTED IN 16-BIT MODE
+
+       Not all the features of the 8-bit library are available with the 16-bit
+       library.  The  C++  and  POSIX wrapper functions support only the 8-bit
+       library, and the pcregrep program is at present 8-bit only.
+
+
+AUTHOR
+
+       Philip Hazel
+       University Computing Service
+       Cambridge CB2 3QH, England.
+
+
+REVISION
+
+       Last updated: 14 April 2012
+       Copyright (c) 1997-2012 University of Cambridge.
+------------------------------------------------------------------------------
+
+
+PCREBUILD(3)                                                      PCREBUILD(3)
+
+
+NAME
+       PCRE - Perl-compatible regular expressions
+
+
+PCRE BUILD-TIME OPTIONS
+
+       This  document  describes  the  optional  features  of PCRE that can be
+       selected when the library is compiled. It assumes use of the  configure
+       script,  where the optional features are selected or deselected by pro-
+       viding options to configure before running the make  command.  However,
+       the  same  options  can be selected in both Unix-like and non-Unix-like
+       environments using the GUI facility of cmake-gui if you are using CMake
+       instead of configure to build PCRE.
+
+       There  is  a  lot more information about building PCRE in non-Unix-like
+       environments in the file called NON_UNIX_USE, which is part of the PCRE
+       distribution.  You  should consult this file as well as the README file
+       if you are building in a non-Unix-like environment.
+
+       The complete list of options for configure (which includes the standard
+       ones  such  as  the  selection  of  the  installation directory) can be
+       obtained by running
+
+         ./configure --help
+
+       The following sections include  descriptions  of  options  whose  names
+       begin with --enable or --disable. These settings specify changes to the
+       defaults for the configure command. Because of the way  that  configure
+       works,  --enable  and --disable always come in pairs, so the complemen-
+       tary option always exists as well, but as it specifies the default,  it
+       is not described.
+
+
+BUILDING 8-BIT and 16-BIT LIBRARIES
+
+       By  default,  a  library  called libpcre is built, containing functions
+       that take string arguments contained in vectors  of  bytes,  either  as
+       single-byte  characters,  or interpreted as UTF-8 strings. You can also
+       build a separate library, called libpcre16, in which strings  are  con-
+       tained  in  vectors of 16-bit data units and interpreted either as sin-
+       gle-unit characters or UTF-16 strings, by adding
+
+         --enable-pcre16
+
+       to the configure command. If you do not want the 8-bit library, add
+
+         --disable-pcre8
+
+       as well. At least one of the two libraries must be built. Note that the
+       C++  and  POSIX wrappers are for the 8-bit library only, and that pcre-
+       grep is an 8-bit program. None of these are built if  you  select  only
+       the 16-bit library.
+
+
+BUILDING SHARED AND STATIC LIBRARIES
+
+       The  PCRE building process uses libtool to build both shared and static
+       Unix libraries by default. You can suppress one of these by adding  one
+       of
+
+         --disable-shared
+         --disable-static
+
+       to the configure command, as required.
+
+
+C++ SUPPORT
+
+       By  default,  if the 8-bit library is being built, the configure script
+       will search for a C++ compiler and C++ header files. If it finds  them,
+       it  automatically  builds  the C++ wrapper library (which supports only
+       8-bit strings). You can disable this by adding
+
+         --disable-cpp
+
+       to the configure command.
+
+
+UTF-8 and UTF-16 SUPPORT
+
+       To build PCRE with support for UTF Unicode character strings, add
+
+         --enable-utf
+
+       to the configure command.  This  setting  applies  to  both  libraries,
+       adding support for UTF-8 to the 8-bit library and support for UTF-16 to
+       the 16-bit library. There are no separate options  for  enabling  UTF-8
+       and  UTF-16  independently because that would allow ridiculous settings
+       such as  requesting  UTF-16  support  while  building  only  the  8-bit
+       library.  It  is not possible to build one library with UTF support and
+       the other without in the same configuration. (For backwards compatibil-
+       ity, --enable-utf8 is a synonym of --enable-utf.)
+
+       Of  itself,  this  setting does not make PCRE treat strings as UTF-8 or
+       UTF-16. As well as compiling PCRE with this option, you also have  have
+       to set the PCRE_UTF8 or PCRE_UTF16 option when you call one of the pat-
+       tern compiling functions.
+
+       If you set --enable-utf when compiling in an EBCDIC  environment,  PCRE
+       expects  its  input  to be either ASCII or UTF-8 (depending on the run-
+       time option). It is not possible to support both EBCDIC and UTF-8 codes
+       in  the  same  version  of  the library. Consequently, --enable-utf and
+       --enable-ebcdic are mutually exclusive.
+
+
+UNICODE CHARACTER PROPERTY SUPPORT
+
+       UTF support allows the libraries to process character codepoints up  to
+       0x10ffff  in the strings that they handle. On its own, however, it does
+       not provide any facilities for accessing the properties of such charac-
+       ters. If you want to be able to use the pattern escapes \P, \p, and \X,
+       which refer to Unicode character properties, you must add
+
+         --enable-unicode-properties
+
+       to the configure command. This implies UTF support, even  if  you  have
+       not explicitly requested it.
+
+       Including  Unicode  property  support  adds around 30K of tables to the
+       PCRE library. Only the general category properties such as  Lu  and  Nd
+       are supported. Details are given in the pcrepattern documentation.
+
+
+JUST-IN-TIME COMPILER SUPPORT
+
+       Just-in-time compiler support is included in the build by specifying
+
+         --enable-jit
+
+       This  support  is available only for certain hardware architectures. If
+       this option is set for an  unsupported  architecture,  a  compile  time
+       error  occurs.   See  the pcrejit documentation for a discussion of JIT
+       usage. When JIT support is enabled, pcregrep automatically makes use of
+       it, unless you add
+
+         --disable-pcregrep-jit
+
+       to the "configure" command.
+
+
+CODE VALUE OF NEWLINE
+
+       By  default,  PCRE interprets the linefeed (LF) character as indicating
+       the end of a line. This is the normal newline  character  on  Unix-like
+       systems.  You  can compile PCRE to use carriage return (CR) instead, by
+       adding
+
+         --enable-newline-is-cr
+
+       to the  configure  command.  There  is  also  a  --enable-newline-is-lf
+       option, which explicitly specifies linefeed as the newline character.
+
+       Alternatively, you can specify that line endings are to be indicated by
+       the two character sequence CRLF. If you want this, add
+
+         --enable-newline-is-crlf
+
+       to the configure command. There is a fourth option, specified by
+
+         --enable-newline-is-anycrlf
+
+       which causes PCRE to recognize any of the three sequences  CR,  LF,  or
+       CRLF as indicating a line ending. Finally, a fifth option, specified by
+
+         --enable-newline-is-any
+
+       causes PCRE to recognize any Unicode newline sequence.
+
+       Whatever  line  ending convention is selected when PCRE is built can be
+       overridden when the library functions are called. At build time  it  is
+       conventional to use the standard for your operating system.
+
+
+WHAT \R MATCHES
+
+       By  default,  the  sequence \R in a pattern matches any Unicode newline
+       sequence, whatever has been selected as the line  ending  sequence.  If
+       you specify
+
+         --enable-bsr-anycrlf
+
+       the  default  is changed so that \R matches only CR, LF, or CRLF. What-
+       ever is selected when PCRE is built can be overridden when the  library
+       functions are called.
+
+
+POSIX MALLOC USAGE
+
+       When  the  8-bit library is called through the POSIX interface (see the
+       pcreposix documentation), additional working storage  is  required  for
+       holding  the  pointers  to  capturing substrings, because PCRE requires
+       three integers per substring, whereas the POSIX interface provides only
+       two.  If  the number of expected substrings is small, the wrapper func-
+       tion uses space on the stack, because this is faster  than  using  mal-
+       loc()  for each call. The default threshold above which the stack is no
+       longer used is 10; it can be changed by adding a setting such as
+
+         --with-posix-malloc-threshold=20
+
+       to the configure command.
+
+
+HANDLING VERY LARGE PATTERNS
+
+       Within a compiled pattern, offset values are used  to  point  from  one
+       part  to another (for example, from an opening parenthesis to an alter-
+       nation metacharacter). By default, two-byte values are used  for  these
+       offsets,  leading  to  a  maximum size for a compiled pattern of around
+       64K. This is sufficient to handle all but the most  gigantic  patterns.
+       Nevertheless,  some  people do want to process truly enormous patterns,
+       so it is possible to compile PCRE to use three-byte or  four-byte  off-
+       sets by adding a setting such as
+
+         --with-link-size=3
+
+       to  the  configure command. The value given must be 2, 3, or 4. For the
+       16-bit library, a value of 3 is rounded up to 4. Using  longer  offsets
+       slows down the operation of PCRE because it has to load additional data
+       when handling them.
+
+
+AVOIDING EXCESSIVE STACK USAGE
+
+       When matching with the pcre_exec() function, PCRE implements backtrack-
+       ing  by  making recursive calls to an internal function called match().
+       In environments where the size of the stack is limited,  this  can  se-
+       verely  limit  PCRE's operation. (The Unix environment does not usually
+       suffer from this problem, but it may sometimes be necessary to increase
+       the  maximum  stack size.  There is a discussion in the pcrestack docu-
+       mentation.) An alternative approach to recursion that uses memory  from
+       the  heap  to remember data, instead of using recursive function calls,
+       has been implemented to work round the problem of limited  stack  size.
+       If you want to build a version of PCRE that works this way, add
+
+         --disable-stack-for-recursion
+
+       to  the  configure  command. With this configuration, PCRE will use the
+       pcre_stack_malloc and pcre_stack_free variables to call memory  manage-
+       ment  functions. By default these point to malloc() and free(), but you
+       can replace the pointers so that your own functions are used instead.
+
+       Separate functions are  provided  rather  than  using  pcre_malloc  and
+       pcre_free  because  the  usage  is  very  predictable:  the block sizes
+       requested are always the same, and  the  blocks  are  always  freed  in
+       reverse  order.  A calling program might be able to implement optimized
+       functions that perform better  than  malloc()  and  free().  PCRE  runs
+       noticeably more slowly when built in this way. This option affects only
+       the pcre_exec() function; it is not relevant for pcre_dfa_exec().
+
+
+LIMITING PCRE RESOURCE USAGE
+
+       Internally, PCRE has a function called match(), which it calls  repeat-
+       edly   (sometimes   recursively)  when  matching  a  pattern  with  the
+       pcre_exec() function. By controlling the maximum number of  times  this
+       function  may be called during a single matching operation, a limit can
+       be placed on the resources used by a single call  to  pcre_exec().  The
+       limit  can be changed at run time, as described in the pcreapi documen-
+       tation. The default is 10 million, but this can be changed by adding  a
+       setting such as
+
+         --with-match-limit=500000
+
+       to   the   configure  command.  This  setting  has  no  effect  on  the
+       pcre_dfa_exec() matching function.
+
+       In some environments it is desirable to limit the  depth  of  recursive
+       calls of match() more strictly than the total number of calls, in order
+       to restrict the maximum amount of stack (or heap,  if  --disable-stack-
+       for-recursion is specified) that is used. A second limit controls this;
+       it defaults to the value that  is  set  for  --with-match-limit,  which
+       imposes  no  additional constraints. However, you can set a lower limit
+       by adding, for example,
+
+         --with-match-limit-recursion=10000
+
+       to the configure command. This value can  also  be  overridden  at  run
+       time.
+
+
+CREATING CHARACTER TABLES AT BUILD TIME
+
+       PCRE  uses fixed tables for processing characters whose code values are
+       less than 256. By default, PCRE is built with a set of tables that  are
+       distributed  in  the  file pcre_chartables.c.dist. These tables are for
+       ASCII codes only. If you add
+
+         --enable-rebuild-chartables
+
+       to the configure command, the distributed tables are  no  longer  used.
+       Instead,  a  program  called dftables is compiled and run. This outputs
+       the source for new set of tables, created in the default locale of your
+       C  run-time  system. (This method of replacing the tables does not work
+       if you are cross compiling, because dftables is run on the local  host.
+       If you need to create alternative tables when cross compiling, you will
+       have to do so "by hand".)
+
+
+USING EBCDIC CODE
+
+       PCRE assumes by default that it will run in an  environment  where  the
+       character  code  is  ASCII  (or Unicode, which is a superset of ASCII).
+       This is the case for most computer operating systems.  PCRE  can,  how-
+       ever, be compiled to run in an EBCDIC environment by adding
+
+         --enable-ebcdic
+
+       to the configure command. This setting implies --enable-rebuild-charta-
+       bles. You should only use it if you know that  you  are  in  an  EBCDIC
+       environment  (for  example,  an  IBM  mainframe  operating system). The
+       --enable-ebcdic option is incompatible with --enable-utf.
+
+
+PCREGREP OPTIONS FOR COMPRESSED FILE SUPPORT
+
+       By default, pcregrep reads all files as plain text. You can build it so
+       that it recognizes files whose names end in .gz or .bz2, and reads them
+       with libz or libbz2, respectively, by adding one or both of
+
+         --enable-pcregrep-libz
+         --enable-pcregrep-libbz2
+
+       to the configure command. These options naturally require that the rel-
+       evant  libraries  are installed on your system. Configuration will fail
+       if they are not.
+
+
+PCREGREP BUFFER SIZE
+
+       pcregrep uses an internal buffer to hold a "window" on the file  it  is
+       scanning, in order to be able to output "before" and "after" lines when
+       it finds a match. The size of the buffer is controlled by  a  parameter
+       whose default value is 20K. The buffer itself is three times this size,
+       but because of the way it is used for holding "before" lines, the long-
+       est  line  that  is guaranteed to be processable is the parameter size.
+       You can change the default parameter value by adding, for example,
+
+         --with-pcregrep-bufsize=50K
+
+       to the configure command. The caller of pcregrep can, however, override
+       this value by specifying a run-time option.
+
+
+PCRETEST OPTION FOR LIBREADLINE SUPPORT
+
+       If you add
+
+         --enable-pcretest-libreadline
+
+       to  the  configure  command,  pcretest  is  linked with the libreadline
+       library, and when its input is from a terminal, it reads it  using  the
+       readline() function. This provides line-editing and history facilities.
+       Note that libreadline is GPL-licensed, so if you distribute a binary of
+       pcretest linked in this way, there may be licensing issues.
+
+       Setting  this  option  causes  the -lreadline option to be added to the
+       pcretest build. In many operating environments with  a  sytem-installed
+       libreadline this is sufficient. However, in some environments (e.g.  if
+       an unmodified distribution version of readline is in use),  some  extra
+       configuration  may  be necessary. The INSTALL file for libreadline says
+       this:
+
+         "Readline uses the termcap functions, but does not link with the
+         termcap or curses library itself, allowing applications which link
+         with readline the to choose an appropriate library."
+
+       If your environment has not been set up so that an appropriate  library
+       is automatically included, you may need to add something like
+
+         LIBS="-ncurses"
+
+       immediately before the configure command.
+
+
+SEE ALSO
+
+       pcreapi(3), pcre16, pcre_config(3).
+
+
+AUTHOR
+
+       Philip Hazel
+       University Computing Service
+       Cambridge CB2 3QH, England.
+
+
+REVISION
+
+       Last updated: 07 January 2012
+       Copyright (c) 1997-2012 University of Cambridge.
+------------------------------------------------------------------------------
+
+
+PCREMATCHING(3)                                                PCREMATCHING(3)
+
+
+NAME
+       PCRE - Perl-compatible regular expressions
+
+
+PCRE MATCHING ALGORITHMS
+
+       This document describes the two different algorithms that are available
+       in PCRE for matching a compiled regular expression against a given sub-
+       ject  string.  The  "standard"  algorithm  is  the  one provided by the
+       pcre_exec() and pcre16_exec() functions. These work in the same was  as
+       Perl's matching function, and provide a Perl-compatible matching opera-
+       tion. The just-in-time (JIT) optimization  that  is  described  in  the
+       pcrejit documentation is compatible with these functions.
+
+       An  alternative  algorithm  is  provided  by  the  pcre_dfa_exec()  and
+       pcre16_dfa_exec() functions; they operate in a different way,  and  are
+       not  Perl-compatible. This alternative has advantages and disadvantages
+       compared with the standard algorithm, and these are described below.
+
+       When there is only one possible way in which a given subject string can
+       match  a pattern, the two algorithms give the same answer. A difference
+       arises, however, when there are multiple possibilities. For example, if
+       the pattern
+
+         ^<.*>
+
+       is matched against the string
+
+         <something> <something else> <something further>
+
+       there are three possible answers. The standard algorithm finds only one
+       of them, whereas the alternative algorithm finds all three.
+
+
+REGULAR EXPRESSIONS AS TREES
+
+       The set of strings that are matched by a regular expression can be rep-
+       resented  as  a  tree structure. An unlimited repetition in the pattern
+       makes the tree of infinite size, but it is still a tree.  Matching  the
+       pattern  to a given subject string (from a given starting point) can be
+       thought of as a search of the tree.  There are two  ways  to  search  a
+       tree:  depth-first  and  breadth-first, and these correspond to the two
+       matching algorithms provided by PCRE.
+
+
+THE STANDARD MATCHING ALGORITHM
+
+       In the terminology of Jeffrey Friedl's book "Mastering Regular  Expres-
+       sions",  the  standard  algorithm  is an "NFA algorithm". It conducts a
+       depth-first search of the pattern tree. That is, it  proceeds  along  a
+       single path through the tree, checking that the subject matches what is
+       required. When there is a mismatch, the algorithm  tries  any  alterna-
+       tives  at  the  current point, and if they all fail, it backs up to the
+       previous branch point in the  tree,  and  tries  the  next  alternative
+       branch  at  that  level.  This often involves backing up (moving to the
+       left) in the subject string as well.  The  order  in  which  repetition
+       branches  are  tried  is controlled by the greedy or ungreedy nature of
+       the quantifier.
+
+       If a leaf node is reached, a matching string has  been  found,  and  at
+       that  point the algorithm stops. Thus, if there is more than one possi-
+       ble match, this algorithm returns the first one that it finds.  Whether
+       this  is the shortest, the longest, or some intermediate length depends
+       on the way the greedy and ungreedy repetition quantifiers are specified
+       in the pattern.
+
+       Because  it  ends  up  with a single path through the tree, it is rela-
+       tively straightforward for this algorithm to keep  track  of  the  sub-
+       strings  that  are  matched  by portions of the pattern in parentheses.
+       This provides support for capturing parentheses and back references.
+
+
+THE ALTERNATIVE MATCHING ALGORITHM
+
+       This algorithm conducts a breadth-first search of  the  tree.  Starting
+       from  the  first  matching  point  in the subject, it scans the subject
+       string from left to right, once, character by character, and as it does
+       this,  it remembers all the paths through the tree that represent valid
+       matches. In Friedl's terminology, this is a kind  of  "DFA  algorithm",
+       though  it is not implemented as a traditional finite state machine (it
+       keeps multiple states active simultaneously).
+
+       Although the general principle of this matching algorithm  is  that  it
+       scans  the subject string only once, without backtracking, there is one
+       exception: when a lookaround assertion is encountered,  the  characters
+       following  or  preceding  the  current  point  have to be independently
+       inspected.
+
+       The scan continues until either the end of the subject is  reached,  or
+       there  are  no more unterminated paths. At this point, terminated paths
+       represent the different matching possibilities (if there are none,  the
+       match  has  failed).   Thus,  if there is more than one possible match,
+       this algorithm finds all of them, and in particular, it finds the long-
+       est.  The  matches are returned in decreasing order of length. There is
+       an option to stop the algorithm after the first match (which is  neces-
+       sarily the shortest) is found.
+
+       Note that all the matches that are found start at the same point in the
+       subject. If the pattern
+
+         cat(er(pillar)?)?
+
+       is matched against the string "the caterpillar catchment",  the  result
+       will  be the three strings "caterpillar", "cater", and "cat" that start
+       at the fifth character of the subject. The algorithm does not automati-
+       cally move on to find matches that start at later positions.
+
+       There are a number of features of PCRE regular expressions that are not
+       supported by the alternative matching algorithm. They are as follows:
+
+       1. Because the algorithm finds all  possible  matches,  the  greedy  or
+       ungreedy  nature  of repetition quantifiers is not relevant. Greedy and
+       ungreedy quantifiers are treated in exactly the same way. However, pos-
+       sessive  quantifiers can make a difference when what follows could also
+       match what is quantified, for example in a pattern like this:
+
+         ^a++\w!
+
+       This pattern matches "aaab!" but not "aaa!", which would be matched  by
+       a  non-possessive quantifier. Similarly, if an atomic group is present,
+       it is matched as if it were a standalone pattern at the current  point,
+       and  the  longest match is then "locked in" for the rest of the overall
+       pattern.
+
+       2. When dealing with multiple paths through the tree simultaneously, it
+       is  not  straightforward  to  keep track of captured substrings for the
+       different matching possibilities, and  PCRE's  implementation  of  this
+       algorithm does not attempt to do this. This means that no captured sub-
+       strings are available.
+
+       3. Because no substrings are captured, back references within the  pat-
+       tern are not supported, and cause errors if encountered.
+
+       4.  For  the same reason, conditional expressions that use a backrefer-
+       ence as the condition or test for a specific group  recursion  are  not
+       supported.
+
+       5.  Because  many  paths  through the tree may be active, the \K escape
+       sequence, which resets the start of the match when encountered (but may
+       be  on  some  paths  and not on others), is not supported. It causes an
+       error if encountered.
+
+       6. Callouts are supported, but the value of the  capture_top  field  is
+       always 1, and the value of the capture_last field is always -1.
+
+       7.  The  \C  escape  sequence, which (in the standard algorithm) always
+       matches a single data unit, even in UTF-8 or UTF-16 modes, is not  sup-
+       ported  in these modes, because the alternative algorithm moves through
+       the subject string one character (not data unit) at  a  time,  for  all
+       active paths through the tree.
+
+       8.  Except for (*FAIL), the backtracking control verbs such as (*PRUNE)
+       are not supported. (*FAIL) is supported, and  behaves  like  a  failing
+       negative assertion.
+
+
+ADVANTAGES OF THE ALTERNATIVE ALGORITHM
+
+       Using  the alternative matching algorithm provides the following advan-
+       tages:
+
+       1. All possible matches (at a single point in the subject) are automat-
+       ically  found,  and  in particular, the longest match is found. To find
+       more than one match using the standard algorithm, you have to do kludgy
+       things with callouts.
+
+       2.  Because  the  alternative  algorithm  scans the subject string just
+       once, and never needs to backtrack (except for lookbehinds), it is pos-
+       sible  to  pass  very  long subject strings to the matching function in
+       several pieces, checking for partial matching each time. Although it is
+       possible  to  do multi-segment matching using the standard algorithm by
+       retaining partially matched substrings, it  is  more  complicated.  The
+       pcrepartial  documentation  gives  details of partial matching and dis-
+       cusses multi-segment matching.
+
+
+DISADVANTAGES OF THE ALTERNATIVE ALGORITHM
+
+       The alternative algorithm suffers from a number of disadvantages:
+
+       1. It is substantially slower than  the  standard  algorithm.  This  is
+       partly  because  it has to search for all possible matches, but is also
+       because it is less susceptible to optimization.
+
+       2. Capturing parentheses and back references are not supported.
+
+       3. Although atomic groups are supported, their use does not provide the
+       performance advantage that it does for the standard algorithm.
+
+
+AUTHOR
+
+       Philip Hazel
+       University Computing Service
+       Cambridge CB2 3QH, England.
+
+
+REVISION
+
+       Last updated: 08 January 2012
+       Copyright (c) 1997-2012 University of Cambridge.
+------------------------------------------------------------------------------
+
+
+PCREAPI(3)                                                          PCREAPI(3)
+
+
+NAME
+       PCRE - Perl-compatible regular expressions
+
+       #include <pcre.h>
+
+
+PCRE NATIVE API BASIC FUNCTIONS
+
+       pcre *pcre_compile(const char *pattern, int options,
+            const char **errptr, int *erroffset,
+            const unsigned char *tableptr);
+
+       pcre *pcre_compile2(const char *pattern, int options,
+            int *errorcodeptr,
+            const char **errptr, int *erroffset,
+            const unsigned char *tableptr);
+
+       pcre_extra *pcre_study(const pcre *code, int options,
+            const char **errptr);
+
+       void pcre_free_study(pcre_extra *extra);
+
+       int pcre_exec(const pcre *code, const pcre_extra *extra,
+            const char *subject, int length, int startoffset,
+            int options, int *ovector, int ovecsize);
+
+       int pcre_dfa_exec(const pcre *code, const pcre_extra *extra,
+            const char *subject, int length, int startoffset,
+            int options, int *ovector, int ovecsize,
+            int *workspace, int wscount);
+
+
+PCRE NATIVE API STRING EXTRACTION FUNCTIONS
+
+       int pcre_copy_named_substring(const pcre *code,
+            const char *subject, int *ovector,
+            int stringcount, const char *stringname,
+            char *buffer, int buffersize);
+
+       int pcre_copy_substring(const char *subject, int *ovector,
+            int stringcount, int stringnumber, char *buffer,
+            int buffersize);
+
+       int pcre_get_named_substring(const pcre *code,
+            const char *subject, int *ovector,
+            int stringcount, const char *stringname,
+            const char **stringptr);
+
+       int pcre_get_stringnumber(const pcre *code,
+            const char *name);
+
+       int pcre_get_stringtable_entries(const pcre *code,
+            const char *name, char **first, char **last);
+
+       int pcre_get_substring(const char *subject, int *ovector,
+            int stringcount, int stringnumber,
+            const char **stringptr);
+
+       int pcre_get_substring_list(const char *subject,
+            int *ovector, int stringcount, const char ***listptr);
+
+       void pcre_free_substring(const char *stringptr);
+
+       void pcre_free_substring_list(const char **stringptr);
+
+
+PCRE NATIVE API AUXILIARY FUNCTIONS
+
+       pcre_jit_stack *pcre_jit_stack_alloc(int startsize, int maxsize);
+
+       void pcre_jit_stack_free(pcre_jit_stack *stack);
+
+       void pcre_assign_jit_stack(pcre_extra *extra,
+            pcre_jit_callback callback, void *data);
+
+       const unsigned char *pcre_maketables(void);
+
+       int pcre_fullinfo(const pcre *code, const pcre_extra *extra,
+            int what, void *where);
+
+       int pcre_refcount(pcre *code, int adjust);
+
+       int pcre_config(int what, void *where);
+
+       const char *pcre_version(void);
+
+       int pcre_pattern_to_host_byte_order(pcre *code,
+            pcre_extra *extra, const unsigned char *tables);
+
+
+PCRE NATIVE API INDIRECTED FUNCTIONS
+
+       void *(*pcre_malloc)(size_t);
+
+       void (*pcre_free)(void *);
+
+       void *(*pcre_stack_malloc)(size_t);
+
+       void (*pcre_stack_free)(void *);
+
+       int (*pcre_callout)(pcre_callout_block *);
+
+
+PCRE 8-BIT AND 16-BIT LIBRARIES
+
+       From  release  8.30,  PCRE  can  be  compiled as a library for handling
+       16-bit character strings as  well  as,  or  instead  of,  the  original
+       library that handles 8-bit character strings. To avoid too much compli-
+       cation, this document describes the 8-bit versions  of  the  functions,
+       with only occasional references to the 16-bit library.
+
+       The  16-bit  functions  operate in the same way as their 8-bit counter-
+       parts; they just use different  data  types  for  their  arguments  and
+       results, and their names start with pcre16_ instead of pcre_. For every
+       option that has UTF8 in its name (for example, PCRE_UTF8), there  is  a
+       corresponding 16-bit name with UTF8 replaced by UTF16. This facility is
+       in fact just cosmetic; the 16-bit option names define the same bit val-
+       ues.
+
+       References to bytes and UTF-8 in this document should be read as refer-
+       ences to 16-bit data  quantities  and  UTF-16  when  using  the  16-bit
+       library,  unless specified otherwise. More details of the specific dif-
+       ferences for the 16-bit library are given in the pcre16 page.
+
+
+PCRE API OVERVIEW
+
+       PCRE has its own native API, which is described in this document. There
+       are  also some wrapper functions (for the 8-bit library only) that cor-
+       respond to the POSIX regular expression  API,  but  they  do  not  give
+       access  to  all  the functionality. They are described in the pcreposix
+       documentation. Both of these APIs define a set of C function  calls.  A
+       C++ wrapper (again for the 8-bit library only) is also distributed with
+       PCRE. It is documented in the pcrecpp page.
+
+       The native API C function prototypes are defined  in  the  header  file
+       pcre.h,  and  on Unix-like systems the (8-bit) library itself is called
+       libpcre. It can normally be accessed by adding -lpcre  to  the  command
+       for  linking an application that uses PCRE. The header file defines the
+       macros PCRE_MAJOR and PCRE_MINOR to contain the major and minor release
+       numbers  for the library. Applications can use these to include support
+       for different releases of PCRE.
+
+       In a Windows environment, if you want to statically link an application
+       program  against  a  non-dll  pcre.a  file, you must define PCRE_STATIC
+       before including pcre.h or pcrecpp.h, because otherwise  the  pcre_mal-
+       loc()   and   pcre_free()   exported   functions   will   be   declared
+       __declspec(dllimport), with unwanted results.
+
+       The  functions  pcre_compile(),  pcre_compile2(),   pcre_study(),   and
+       pcre_exec()  are used for compiling and matching regular expressions in
+       a Perl-compatible manner. A sample program that demonstrates  the  sim-
+       plest  way  of  using them is provided in the file called pcredemo.c in
+       the PCRE source distribution. A listing of this program is given in the
+       pcredemo  documentation, and the pcresample documentation describes how
+       to compile and run it.
+
+       Just-in-time compiler support is an optional feature of PCRE  that  can
+       be built in appropriate hardware environments. It greatly speeds up the
+       matching performance of  many  patterns.  Simple  programs  can  easily
+       request  that  it  be  used  if available, by setting an option that is
+       ignored when it is not relevant. More complicated programs  might  need
+       to     make    use    of    the    functions    pcre_jit_stack_alloc(),
+       pcre_jit_stack_free(), and pcre_assign_jit_stack() in order to  control
+       the  JIT  code's  memory  usage.   These functions are discussed in the
+       pcrejit documentation.
+
+       A second matching function, pcre_dfa_exec(), which is not Perl-compati-
+       ble,  is  also provided. This uses a different algorithm for the match-
+       ing. The alternative algorithm finds all possible matches (at  a  given
+       point  in  the  subject), and scans the subject just once (unless there
+       are lookbehind assertions). However, this  algorithm  does  not  return
+       captured  substrings.  A description of the two matching algorithms and
+       their advantages and disadvantages is given in the  pcrematching  docu-
+       mentation.
+
+       In  addition  to  the  main compiling and matching functions, there are
+       convenience functions for extracting captured substrings from a subject
+       string that is matched by pcre_exec(). They are:
+
+         pcre_copy_substring()
+         pcre_copy_named_substring()
+         pcre_get_substring()
+         pcre_get_named_substring()
+         pcre_get_substring_list()
+         pcre_get_stringnumber()
+         pcre_get_stringtable_entries()
+
+       pcre_free_substring() and pcre_free_substring_list() are also provided,
+       to free the memory used for extracted strings.
+
+       The function pcre_maketables() is used to  build  a  set  of  character
+       tables   in   the   current   locale  for  passing  to  pcre_compile(),
+       pcre_exec(), or pcre_dfa_exec(). This is an optional facility  that  is
+       provided  for  specialist  use.  Most  commonly,  no special tables are
+       passed, in which case internal tables that are generated when  PCRE  is
+       built are used.
+
+       The  function  pcre_fullinfo()  is used to find out information about a
+       compiled pattern. The function pcre_version() returns a  pointer  to  a
+       string containing the version of PCRE and its date of release.
+
+       The  function  pcre_refcount()  maintains  a  reference count in a data
+       block containing a compiled pattern. This is provided for  the  benefit
+       of object-oriented applications.
+
+       The  global  variables  pcre_malloc and pcre_free initially contain the
+       entry points of the standard malloc()  and  free()  functions,  respec-
+       tively. PCRE calls the memory management functions via these variables,
+       so a calling program can replace them if it  wishes  to  intercept  the
+       calls. This should be done before calling any PCRE functions.
+
+       The  global  variables  pcre_stack_malloc  and pcre_stack_free are also
+       indirections to memory management functions.  These  special  functions
+       are  used  only  when  PCRE is compiled to use the heap for remembering
+       data, instead of recursive function calls, when running the pcre_exec()
+       function.  See  the  pcrebuild  documentation  for details of how to do
+       this. It is a non-standard way of building PCRE, for  use  in  environ-
+       ments  that  have  limited stacks. Because of the greater use of memory
+       management, it runs more slowly. Separate  functions  are  provided  so
+       that  special-purpose  external  code  can  be used for this case. When
+       used, these functions are always called in a  stack-like  manner  (last
+       obtained,  first freed), and always for memory blocks of the same size.
+       There is a discussion about PCRE's stack usage in the  pcrestack  docu-
+       mentation.
+
+       The global variable pcre_callout initially contains NULL. It can be set
+       by the caller to a "callout" function, which PCRE  will  then  call  at
+       specified  points during a matching operation. Details are given in the
+       pcrecallout documentation.
+
+
+NEWLINES
+
+       PCRE supports five different conventions for indicating line breaks  in
+       strings:  a  single  CR (carriage return) character, a single LF (line-
+       feed) character, the two-character sequence CRLF, any of the three pre-
+       ceding,  or any Unicode newline sequence. The Unicode newline sequences
+       are the three just mentioned, plus the single characters  VT  (vertical
+       tab, U+000B), FF (form feed, U+000C), NEL (next line, U+0085), LS (line
+       separator, U+2028), and PS (paragraph separator, U+2029).
+
+       Each of the first three conventions is used by at least  one  operating
+       system  as its standard newline sequence. When PCRE is built, a default
+       can be specified.  The default default is LF, which is the  Unix  stan-
+       dard.  When  PCRE  is run, the default can be overridden, either when a
+       pattern is compiled, or when it is matched.
+
+       At compile time, the newline convention can be specified by the options
+       argument  of  pcre_compile(), or it can be specified by special text at
+       the start of the pattern itself; this overrides any other settings. See
+       the pcrepattern page for details of the special character sequences.
+
+       In the PCRE documentation the word "newline" is used to mean "the char-
+       acter or pair of characters that indicate a line break". The choice  of
+       newline  convention  affects  the  handling of the dot, circumflex, and
+       dollar metacharacters, the handling of #-comments in /x mode, and, when
+       CRLF  is a recognized line ending sequence, the match position advance-
+       ment for a non-anchored pattern. There is more detail about this in the
+       section on pcre_exec() options below.
+
+       The  choice of newline convention does not affect the interpretation of
+       the \n or \r escape sequences, nor does  it  affect  what  \R  matches,
+       which is controlled in a similar way, but by separate options.
+
+
+MULTITHREADING
+
+       The  PCRE  functions  can be used in multi-threading applications, with
+       the  proviso  that  the  memory  management  functions  pointed  to  by
+       pcre_malloc, pcre_free, pcre_stack_malloc, and pcre_stack_free, and the
+       callout function pointed to by pcre_callout, are shared by all threads.
+
+       The compiled form of a regular expression is not altered during  match-
+       ing, so the same compiled pattern can safely be used by several threads
+       at once.
+
+       If the just-in-time optimization feature is being used, it needs  sepa-
+       rate  memory stack areas for each thread. See the pcrejit documentation
+       for more details.
+
+
+SAVING PRECOMPILED PATTERNS FOR LATER USE
+
+       The compiled form of a regular expression can be saved and re-used at a
+       later  time,  possibly by a different program, and even on a host other
+       than the one on which  it  was  compiled.  Details  are  given  in  the
+       pcreprecompile  documentation,  which  includes  a  description  of the
+       pcre_pattern_to_host_byte_order() function. However, compiling a  regu-
+       lar  expression  with one version of PCRE for use with a different ver-
+       sion is not guaranteed to work and may cause crashes.
+
+
+CHECKING BUILD-TIME OPTIONS
+
+       int pcre_config(int what, void *where);
+
+       The function pcre_config() makes it possible for a PCRE client to  dis-
+       cover which optional features have been compiled into the PCRE library.
+       The pcrebuild documentation has more details about these optional  fea-
+       tures.
+
+       The  first  argument  for pcre_config() is an integer, specifying which
+       information is required; the second argument is a pointer to a variable
+       into  which  the  information  is placed. The returned value is zero on
+       success, or the negative error code PCRE_ERROR_BADOPTION if  the  value
+       in  the  first argument is not recognized. The following information is
+       available:
+
+         PCRE_CONFIG_UTF8
+
+       The output is an integer that is set to one if UTF-8 support is  avail-
+       able;  otherwise  it  is  set  to  zero. If this option is given to the
+       16-bit  version  of  this  function,  pcre16_config(),  the  result  is
+       PCRE_ERROR_BADOPTION.
+
+         PCRE_CONFIG_UTF16
+
+       The output is an integer that is set to one if UTF-16 support is avail-
+       able; otherwise it is set to zero. This value should normally be  given
+       to the 16-bit version of this function, pcre16_config(). If it is given
+       to the 8-bit version of this function, the result is  PCRE_ERROR_BADOP-
+       TION.
+
+         PCRE_CONFIG_UNICODE_PROPERTIES
+
+       The  output  is  an  integer  that is set to one if support for Unicode
+       character properties is available; otherwise it is set to zero.
+
+         PCRE_CONFIG_JIT
+
+       The output is an integer that is set to one if support for just-in-time
+       compiling is available; otherwise it is set to zero.
+
+         PCRE_CONFIG_JITTARGET
+
+       The  output is a pointer to a zero-terminated "const char *" string. If
+       JIT support is available, the string contains the name of the architec-
+       ture  for  which the JIT compiler is configured, for example "x86 32bit
+       (little endian + unaligned)". If JIT  support  is  not  available,  the
+       result is NULL.
+
+         PCRE_CONFIG_NEWLINE
+
+       The  output  is  an integer whose value specifies the default character
+       sequence that is recognized as meaning "newline". The four values  that
+       are supported are: 10 for LF, 13 for CR, 3338 for CRLF, -2 for ANYCRLF,
+       and -1 for ANY.  Though they are derived from ASCII,  the  same  values
+       are returned in EBCDIC environments. The default should normally corre-
+       spond to the standard sequence for your operating system.
+
+         PCRE_CONFIG_BSR
+
+       The output is an integer whose value indicates what character sequences
+       the  \R  escape sequence matches by default. A value of 0 means that \R
+       matches any Unicode line ending sequence; a value of 1  means  that  \R
+       matches only CR, LF, or CRLF. The default can be overridden when a pat-
+       tern is compiled or matched.
+
+         PCRE_CONFIG_LINK_SIZE
+
+       The output is an integer that contains the number  of  bytes  used  for
+       internal  linkage  in  compiled  regular  expressions.  For  the  8-bit
+       library, the value can be 2, 3, or 4. For the 16-bit library, the value
+       is either 2 or 4 and is still a number of bytes. The default value of 2
+       is sufficient for all but the most massive patterns,  since  it  allows
+       the  compiled  pattern  to  be  up to 64K in size.  Larger values allow
+       larger regular expressions to be compiled, at  the  expense  of  slower
+       matching.
+
+         PCRE_CONFIG_POSIX_MALLOC_THRESHOLD
+
+       The  output  is  an integer that contains the threshold above which the
+       POSIX interface uses malloc() for output vectors. Further  details  are
+       given in the pcreposix documentation.
+
+         PCRE_CONFIG_MATCH_LIMIT
+
+       The  output is a long integer that gives the default limit for the num-
+       ber of internal matching function calls  in  a  pcre_exec()  execution.
+       Further details are given with pcre_exec() below.
+
+         PCRE_CONFIG_MATCH_LIMIT_RECURSION
+
+       The output is a long integer that gives the default limit for the depth
+       of  recursion  when  calling  the  internal  matching  function  in   a
+       pcre_exec()  execution.  Further  details  are  given  with pcre_exec()
+       below.
+
+         PCRE_CONFIG_STACKRECURSE
+
+       The output is an integer that is set to one if internal recursion  when
+       running pcre_exec() is implemented by recursive function calls that use
+       the stack to remember their state. This is the usual way that  PCRE  is
+       compiled. The output is zero if PCRE was compiled to use blocks of data
+       on the  heap  instead  of  recursive  function  calls.  In  this  case,
+       pcre_stack_malloc  and  pcre_stack_free  are  called  to  manage memory
+       blocks on the heap, thus avoiding the use of the stack.
+
+
+COMPILING A PATTERN
+
+       pcre *pcre_compile(const char *pattern, int options,
+            const char **errptr, int *erroffset,
+            const unsigned char *tableptr);
+
+       pcre *pcre_compile2(const char *pattern, int options,
+            int *errorcodeptr,
+            const char **errptr, int *erroffset,
+            const unsigned char *tableptr);
+
+       Either of the functions pcre_compile() or pcre_compile2() can be called
+       to compile a pattern into an internal form. The only difference between
+       the two interfaces is that pcre_compile2() has an additional  argument,
+       errorcodeptr,  via  which  a  numerical  error code can be returned. To
+       avoid too much repetition, we refer just to pcre_compile()  below,  but
+       the information applies equally to pcre_compile2().
+
+       The pattern is a C string terminated by a binary zero, and is passed in
+       the pattern argument. A pointer to a single block  of  memory  that  is
+       obtained  via  pcre_malloc is returned. This contains the compiled code
+       and related data. The pcre type is defined for the returned block; this
+       is a typedef for a structure whose contents are not externally defined.
+       It is up to the caller to free the memory (via pcre_free) when it is no
+       longer required.
+
+       Although  the compiled code of a PCRE regex is relocatable, that is, it
+       does not depend on memory location, the complete pcre data block is not
+       fully  relocatable, because it may contain a copy of the tableptr argu-
+       ment, which is an address (see below).
+
+       The options argument contains various bit settings that affect the com-
+       pilation.  It  should be zero if no options are required. The available
+       options are described below. Some of them (in  particular,  those  that
+       are  compatible with Perl, but some others as well) can also be set and
+       unset from within the pattern (see  the  detailed  description  in  the
+       pcrepattern  documentation). For those options that can be different in
+       different parts of the pattern, the contents of  the  options  argument
+       specifies their settings at the start of compilation and execution. The
+       PCRE_ANCHORED, PCRE_BSR_xxx, PCRE_NEWLINE_xxx, PCRE_NO_UTF8_CHECK,  and
+       PCRE_NO_START_OPTIMIZE  options  can  be set at the time of matching as
+       well as at compile time.
+
+       If errptr is NULL, pcre_compile() returns NULL immediately.  Otherwise,
+       if  compilation  of  a  pattern fails, pcre_compile() returns NULL, and
+       sets the variable pointed to by errptr to point to a textual error mes-
+       sage. This is a static string that is part of the library. You must not
+       try to free it. Normally, the offset from the start of the  pattern  to
+       the  byte  that  was  being  processed when the error was discovered is
+       placed in the variable pointed to by erroffset, which must not be  NULL
+       (if  it is, an immediate error is given). However, for an invalid UTF-8
+       string, the offset is that of the first byte of the failing character.
+
+       Some errors are not detected until the whole pattern has been  scanned;
+       in  these  cases,  the offset passed back is the length of the pattern.
+       Note that the offset is in bytes, not characters, even in  UTF-8  mode.
+       It may sometimes point into the middle of a UTF-8 character.
+
+       If  pcre_compile2()  is  used instead of pcre_compile(), and the error-
+       codeptr argument is not NULL, a non-zero error code number is  returned
+       via  this argument in the event of an error. This is in addition to the
+       textual error message. Error codes and messages are listed below.
+
+       If the final argument, tableptr, is NULL, PCRE uses a  default  set  of
+       character  tables  that  are  built  when  PCRE  is compiled, using the
+       default C locale. Otherwise, tableptr must be an address  that  is  the
+       result  of  a  call to pcre_maketables(). This value is stored with the
+       compiled pattern, and used again by pcre_exec(), unless  another  table
+       pointer is passed to it. For more discussion, see the section on locale
+       support below.
+
+       This code fragment shows a typical straightforward  call  to  pcre_com-
+       pile():
+
+         pcre *re;
+         const char *error;
+         int erroffset;
+         re = pcre_compile(
+           "^A.*Z",          /* the pattern */
+           0,                /* default options */
+           &error,           /* for error message */
+           &erroffset,       /* for error offset */
+           NULL);            /* use default character tables */
+
+       The  following  names  for option bits are defined in the pcre.h header
+       file:
+
+         PCRE_ANCHORED
+
+       If this bit is set, the pattern is forced to be "anchored", that is, it
+       is  constrained to match only at the first matching point in the string
+       that is being searched (the "subject string"). This effect can also  be
+       achieved  by appropriate constructs in the pattern itself, which is the
+       only way to do it in Perl.
+
+         PCRE_AUTO_CALLOUT
+
+       If this bit is set, pcre_compile() automatically inserts callout items,
+       all  with  number  255, before each pattern item. For discussion of the
+       callout facility, see the pcrecallout documentation.
+
+         PCRE_BSR_ANYCRLF
+         PCRE_BSR_UNICODE
+
+       These options (which are mutually exclusive) control what the \R escape
+       sequence  matches.  The choice is either to match only CR, LF, or CRLF,
+       or to match any Unicode newline sequence. The default is specified when
+       PCRE is built. It can be overridden from within the pattern, or by set-
+       ting an option when a compiled pattern is matched.
+
+         PCRE_CASELESS
+
+       If this bit is set, letters in the pattern match both upper  and  lower
+       case  letters.  It  is  equivalent  to  Perl's /i option, and it can be
+       changed within a pattern by a (?i) option setting. In UTF-8 mode,  PCRE
+       always  understands the concept of case for characters whose values are
+       less than 128, so caseless matching is always possible. For  characters
+       with  higher  values,  the concept of case is supported if PCRE is com-
+       piled with Unicode property support, but not otherwise. If you want  to
+       use  caseless  matching  for  characters 128 and above, you must ensure
+       that PCRE is compiled with Unicode property support  as  well  as  with
+       UTF-8 support.
+
+         PCRE_DOLLAR_ENDONLY
+
+       If  this bit is set, a dollar metacharacter in the pattern matches only
+       at the end of the subject string. Without this option,  a  dollar  also
+       matches  immediately before a newline at the end of the string (but not
+       before any other newlines). The PCRE_DOLLAR_ENDONLY option  is  ignored
+       if  PCRE_MULTILINE  is  set.   There is no equivalent to this option in
+       Perl, and no way to set it within a pattern.
+
+         PCRE_DOTALL
+
+       If this bit is set, a dot metacharacter in the pattern matches a  char-
+       acter of any value, including one that indicates a newline. However, it
+       only ever matches one character, even if newlines are  coded  as  CRLF.
+       Without  this option, a dot does not match when the current position is
+       at a newline. This option is equivalent to Perl's /s option, and it can
+       be  changed within a pattern by a (?s) option setting. A negative class
+       such as [^a] always matches newline characters, independent of the set-
+       ting of this option.
+
+         PCRE_DUPNAMES
+
+       If  this  bit is set, names used to identify capturing subpatterns need
+       not be unique. This can be helpful for certain types of pattern when it
+       is  known  that  only  one instance of the named subpattern can ever be
+       matched. There are more details of named subpatterns  below;  see  also
+       the pcrepattern documentation.
+
+         PCRE_EXTENDED
+
+       If  this  bit  is  set,  white space data characters in the pattern are
+       totally ignored except when escaped or inside a character class.  White
+       space does not include the VT character (code 11). In addition, charac-
+       ters between an unescaped # outside a character class and the next new-
+       line,  inclusive,  are  also  ignored.  This is equivalent to Perl's /x
+       option, and it can be changed within a pattern by a  (?x)  option  set-
+       ting.
+
+       Which  characters  are  interpreted  as  newlines  is controlled by the
+       options passed to pcre_compile() or by a special sequence at the  start
+       of  the  pattern, as described in the section entitled "Newline conven-
+       tions" in the pcrepattern documentation. Note that the end of this type
+       of  comment  is  a  literal  newline  sequence  in  the pattern; escape
+       sequences that happen to represent a newline do not count.
+
+       This option makes it possible to include  comments  inside  complicated
+       patterns.   Note,  however,  that this applies only to data characters.
+       White space  characters  may  never  appear  within  special  character
+       sequences in a pattern, for example within the sequence (?( that intro-
+       duces a conditional subpattern.
+
+         PCRE_EXTRA
+
+       This option was invented in order to turn on  additional  functionality
+       of  PCRE  that  is  incompatible with Perl, but it is currently of very
+       little use. When set, any backslash in a pattern that is followed by  a
+       letter  that  has  no  special  meaning causes an error, thus reserving
+       these combinations for future expansion. By  default,  as  in  Perl,  a
+       backslash  followed by a letter with no special meaning is treated as a
+       literal. (Perl can, however, be persuaded to give an error for this, by
+       running  it with the -w option.) There are at present no other features
+       controlled by this option. It can also be set by a (?X) option  setting
+       within a pattern.
+
+         PCRE_FIRSTLINE
+
+       If  this  option  is  set,  an  unanchored pattern is required to match
+       before or at the first  newline  in  the  subject  string,  though  the
+       matched text may continue over the newline.
+
+         PCRE_JAVASCRIPT_COMPAT
+
+       If this option is set, PCRE's behaviour is changed in some ways so that
+       it is compatible with JavaScript rather than Perl. The changes  are  as
+       follows:
+
+       (1)  A  lone  closing square bracket in a pattern causes a compile-time
+       error, because this is illegal in JavaScript (by default it is  treated
+       as a data character). Thus, the pattern AB]CD becomes illegal when this
+       option is set.
+
+       (2) At run time, a back reference to an unset subpattern group  matches
+       an  empty  string (by default this causes the current matching alterna-
+       tive to fail). A pattern such as (\1)(a) succeeds when this  option  is
+       set  (assuming  it can find an "a" in the subject), whereas it fails by
+       default, for Perl compatibility.
+
+       (3) \U matches an upper case "U" character; by default \U causes a com-
+       pile time error (Perl uses \U to upper case subsequent characters).
+
+       (4) \u matches a lower case "u" character unless it is followed by four
+       hexadecimal digits, in which case the hexadecimal  number  defines  the
+       code  point  to match. By default, \u causes a compile time error (Perl
+       uses it to upper case the following character).
+
+       (5) \x matches a lower case "x" character unless it is followed by  two
+       hexadecimal  digits,  in  which case the hexadecimal number defines the
+       code point to match. By default, as in Perl, a  hexadecimal  number  is
+       always expected after \x, but it may have zero, one, or two digits (so,
+       for example, \xz matches a binary zero character followed by z).
+
+         PCRE_MULTILINE
+
+       By default, PCRE treats the subject string as consisting  of  a  single
+       line  of characters (even if it actually contains newlines). The "start
+       of line" metacharacter (^) matches only at the  start  of  the  string,
+       while  the  "end  of line" metacharacter ($) matches only at the end of
+       the string, or before a terminating newline (unless PCRE_DOLLAR_ENDONLY
+       is set). This is the same as Perl.
+
+       When  PCRE_MULTILINE  it  is set, the "start of line" and "end of line"
+       constructs match immediately following or immediately  before  internal
+       newlines  in  the  subject string, respectively, as well as at the very
+       start and end. This is equivalent to Perl's /m option, and  it  can  be
+       changed within a pattern by a (?m) option setting. If there are no new-
+       lines in a subject string, or no occurrences of ^ or $  in  a  pattern,
+       setting PCRE_MULTILINE has no effect.
+
+         PCRE_NEWLINE_CR
+         PCRE_NEWLINE_LF
+         PCRE_NEWLINE_CRLF
+         PCRE_NEWLINE_ANYCRLF
+         PCRE_NEWLINE_ANY
+
+       These  options  override the default newline definition that was chosen
+       when PCRE was built. Setting the first or the second specifies  that  a
+       newline  is  indicated  by a single character (CR or LF, respectively).
+       Setting PCRE_NEWLINE_CRLF specifies that a newline is indicated by  the
+       two-character  CRLF  sequence.  Setting  PCRE_NEWLINE_ANYCRLF specifies
+       that any of the three preceding sequences should be recognized. Setting
+       PCRE_NEWLINE_ANY  specifies that any Unicode newline sequence should be
+       recognized. The Unicode newline sequences are the three just mentioned,
+       plus  the  single  characters VT (vertical tab, U+000B), FF (form feed,
+       U+000C), NEL (next line, U+0085), LS (line separator, U+2028),  and  PS
+       (paragraph  separator, U+2029). For the 8-bit library, the last two are
+       recognized only in UTF-8 mode.
+
+       The newline setting in the  options  word  uses  three  bits  that  are
+       treated as a number, giving eight possibilities. Currently only six are
+       used (default plus the five values above). This means that if  you  set
+       more  than one newline option, the combination may or may not be sensi-
+       ble. For example, PCRE_NEWLINE_CR with PCRE_NEWLINE_LF is equivalent to
+       PCRE_NEWLINE_CRLF,  but other combinations may yield unused numbers and
+       cause an error.
+
+       The only time that a line break in a pattern  is  specially  recognized
+       when  compiling is when PCRE_EXTENDED is set. CR and LF are white space
+       characters, and so are ignored in this mode. Also, an unescaped #  out-
+       side  a  character class indicates a comment that lasts until after the
+       next line break sequence. In other circumstances, line break  sequences
+       in patterns are treated as literal data.
+
+       The newline option that is set at compile time becomes the default that
+       is used for pcre_exec() and pcre_dfa_exec(), but it can be overridden.
+
+         PCRE_NO_AUTO_CAPTURE
+
+       If this option is set, it disables the use of numbered capturing paren-
+       theses  in the pattern. Any opening parenthesis that is not followed by
+       ? behaves as if it were followed by ?: but named parentheses can  still
+       be  used  for  capturing  (and  they acquire numbers in the usual way).
+       There is no equivalent of this option in Perl.
+
+         NO_START_OPTIMIZE
+
+       This is an option that acts at matching time; that is, it is really  an
+       option  for  pcre_exec()  or  pcre_dfa_exec().  If it is set at compile
+       time, it is remembered with the compiled pattern and assumed at  match-
+       ing  time.  For  details  see  the discussion of PCRE_NO_START_OPTIMIZE
+       below.
+
+         PCRE_UCP
+
+       This option changes the way PCRE processes \B, \b, \D, \d, \S, \s,  \W,
+       \w,  and  some  of  the POSIX character classes. By default, only ASCII
+       characters are recognized, but if PCRE_UCP is set,  Unicode  properties
+       are  used instead to classify characters. More details are given in the
+       section on generic character types in the pcrepattern page. If you  set
+       PCRE_UCP,  matching  one of the items it affects takes much longer. The
+       option is available only if PCRE has been compiled with  Unicode  prop-
+       erty support.
+
+         PCRE_UNGREEDY
+
+       This  option  inverts  the "greediness" of the quantifiers so that they
+       are not greedy by default, but become greedy if followed by "?". It  is
+       not  compatible  with Perl. It can also be set by a (?U) option setting
+       within the pattern.
+
+         PCRE_UTF8
+
+       This option causes PCRE to regard both the pattern and the  subject  as
+       strings of UTF-8 characters instead of single-byte strings. However, it
+       is available only when PCRE is built to include UTF  support.  If  not,
+       the  use  of  this option provokes an error. Details of how this option
+       changes the behaviour of PCRE are given in the pcreunicode page.
+
+         PCRE_NO_UTF8_CHECK
+
+       When PCRE_UTF8 is set, the validity of the pattern as a UTF-8 string is
+       automatically  checked.  There  is  a  discussion about the validity of
+       UTF-8 strings in the pcreunicode page. If an invalid UTF-8 sequence  is
+       found,  pcre_compile()  returns an error. If you already know that your
+       pattern is valid, and you want to skip this check for performance  rea-
+       sons,  you  can set the PCRE_NO_UTF8_CHECK option.  When it is set, the
+       effect of passing an invalid UTF-8 string as a pattern is undefined. It
+       may  cause  your  program  to  crash. Note that this option can also be
+       passed to pcre_exec() and pcre_dfa_exec(),  to  suppress  the  validity
+       checking of subject strings.
+
+
+COMPILATION ERROR CODES
+
+       The  following  table  lists  the  error  codes than may be returned by
+       pcre_compile2(), along with the error messages that may be returned  by
+       both  compiling  functions.  Note  that error messages are always 8-bit
+       ASCII strings, even in 16-bit mode. As PCRE has developed,  some  error
+       codes  have  fallen  out of use. To avoid confusion, they have not been
+       re-used.
+
+          0  no error
+          1  \ at end of pattern
+          2  \c at end of pattern
+          3  unrecognized character follows \
+          4  numbers out of order in {} quantifier
+          5  number too big in {} quantifier
+          6  missing terminating ] for character class
+          7  invalid escape sequence in character class
+          8  range out of order in character class
+          9  nothing to repeat
+         10  [this code is not in use]
+         11  internal error: unexpected repeat
+         12  unrecognized character after (? or (?-
+         13  POSIX named classes are supported only within a class
+         14  missing )
+         15  reference to non-existent subpattern
+         16  erroffset passed as NULL
+         17  unknown option bit(s) set
+         18  missing ) after comment
+         19  [this code is not in use]
+         20  regular expression is too large
+         21  failed to get memory
+         22  unmatched parentheses
+         23  internal error: code overflow
+         24  unrecognized character after (?<
+         25  lookbehind assertion is not fixed length
+         26  malformed number or name after (?(
+         27  conditional group contains more than two branches
+         28  assertion expected after (?(
+         29  (?R or (?[+-]digits must be followed by )
+         30  unknown POSIX class name
+         31  POSIX collating elements are not supported
+         32  this version of PCRE is compiled without UTF support
+         33  [this code is not in use]
+         34  character value in \x{...} sequence is too large
+         35  invalid condition (?(0)
+         36  \C not allowed in lookbehind assertion
+         37  PCRE does not support \L, \l, \N{name}, \U, or \u
+         38  number after (?C is > 255
+         39  closing ) for (?C expected
+         40  recursive call could loop indefinitely
+         41  unrecognized character after (?P
+         42  syntax error in subpattern name (missing terminator)
+         43  two named subpatterns have the same name
+         44  invalid UTF-8 string (specifically UTF-8)
+         45  support for \P, \p, and \X has not been compiled
+         46  malformed \P or \p sequence
+         47  unknown property name after \P or \p
+         48  subpattern name is too long (maximum 32 characters)
+         49  too many named subpatterns (maximum 10000)
+         50  [this code is not in use]
+         51  octal value is greater than \377 in 8-bit non-UTF-8 mode
+         52  internal error: overran compiling workspace
+         53  internal error: previously-checked referenced subpattern
+               not found
+         54  DEFINE group contains more than one branch
+         55  repeating a DEFINE group is not allowed
+         56  inconsistent NEWLINE options
+         57  \g is not followed by a braced, angle-bracketed, or quoted
+               name/number or by a plain number
+         58  a numbered reference must not be zero
+         59  an argument is not allowed for (*ACCEPT), (*FAIL), or (*COMMIT)
+         60  (*VERB) not recognized
+         61  number is too big
+         62  subpattern name expected
+         63  digit expected after (?+
+         64  ] is an invalid data character in JavaScript compatibility mode
+         65  different names for subpatterns of the same number are
+               not allowed
+         66  (*MARK) must have an argument
+         67  this version of PCRE is not compiled with Unicode property
+               support
+         68  \c must be followed by an ASCII character
+         69  \k is not followed by a braced, angle-bracketed, or quoted name
+         70  internal error: unknown opcode in find_fixedlength()
+         71  \N is not supported in a class
+         72  too many forward references
+         73  disallowed Unicode code point (>= 0xd800 && <= 0xdfff)
+         74  invalid UTF-16 string (specifically UTF-16)
+         75  name is too long in (*MARK), (*PRUNE), (*SKIP), or (*THEN)
+         76  character value in \u.... sequence is too large
+
+       The numbers 32 and 10000 in errors 48 and 49  are  defaults;  different
+       values may be used if the limits were changed when PCRE was built.
+
+
+STUDYING A PATTERN
+
+       pcre_extra *pcre_study(const pcre *code, int options
+            const char **errptr);
+
+       If  a  compiled  pattern is going to be used several times, it is worth
+       spending more time analyzing it in order to speed up the time taken for
+       matching.  The function pcre_study() takes a pointer to a compiled pat-
+       tern as its first argument. If studying the pattern produces additional
+       information  that  will  help speed up matching, pcre_study() returns a
+       pointer to a pcre_extra block, in which the study_data field points  to
+       the results of the study.
+
+       The  returned  value  from  pcre_study()  can  be  passed  directly  to
+       pcre_exec() or pcre_dfa_exec(). However, a pcre_extra block  also  con-
+       tains  other  fields  that can be set by the caller before the block is
+       passed; these are described below in the section on matching a pattern.
+
+       If studying the  pattern  does  not  produce  any  useful  information,
+       pcre_study() returns NULL. In that circumstance, if the calling program
+       wants  to  pass  any  of   the   other   fields   to   pcre_exec()   or
+       pcre_dfa_exec(), it must set up its own pcre_extra block.
+
+       The  second  argument  of  pcre_study() contains option bits. There are
+       three options:
+
+         PCRE_STUDY_JIT_COMPILE
+         PCRE_STUDY_JIT_PARTIAL_HARD_COMPILE
+         PCRE_STUDY_JIT_PARTIAL_SOFT_COMPILE
+
+       If any of these are set, and the just-in-time  compiler  is  available,
+       the  pattern  is  further compiled into machine code that executes much
+       faster than the pcre_exec()  interpretive  matching  function.  If  the
+       just-in-time  compiler is not available, these options are ignored. All
+       other bits in the options argument must be zero.
+
+       JIT compilation is a heavyweight optimization. It can  take  some  time
+       for  patterns  to  be analyzed, and for one-off matches and simple pat-
+       terns the benefit of faster execution might be offset by a much  slower
+       study time.  Not all patterns can be optimized by the JIT compiler. For
+       those that cannot be handled, matching automatically falls back to  the
+       pcre_exec()  interpreter.  For more details, see the pcrejit documenta-
+       tion.
+
+       The third argument for pcre_study() is a pointer for an error  message.
+       If  studying  succeeds  (even  if no data is returned), the variable it
+       points to is set to NULL. Otherwise it is set to  point  to  a  textual
+       error message. This is a static string that is part of the library. You
+       must not try to free it. You should test the  error  pointer  for  NULL
+       after calling pcre_study(), to be sure that it has run successfully.
+
+       When  you are finished with a pattern, you can free the memory used for
+       the study data by calling pcre_free_study(). This function was added to
+       the  API  for  release  8.20. For earlier versions, the memory could be
+       freed with pcre_free(), just like the pattern itself. This  will  still
+       work  in  cases where JIT optimization is not used, but it is advisable
+       to change to the new function when convenient.
+
+       This is a typical way in which pcre_study() is used (except that  in  a
+       real application there should be tests for errors):
+
+         int rc;
+         pcre *re;
+         pcre_extra *sd;
+         re = pcre_compile("pattern", 0, &error, &erroroffset, NULL);
+         sd = pcre_study(
+           re,             /* result of pcre_compile() */
+           0,              /* no options */
+           &error);        /* set to NULL or points to a message */
+         rc = pcre_exec(   /* see below for details of pcre_exec() options */
+           re, sd, "subject", 7, 0, 0, ovector, 30);
+         ...
+         pcre_free_study(sd);
+         pcre_free(re);
+
+       Studying a pattern does two things: first, a lower bound for the length
+       of subject string that is needed to match the pattern is computed. This
+       does not mean that there are any strings of that length that match, but
+       it does guarantee that no shorter strings match. The value is  used  by
+       pcre_exec()  and  pcre_dfa_exec()  to  avoid  wasting time by trying to
+       match strings that are shorter than the lower bound. You can  find  out
+       the value in a calling program via the pcre_fullinfo() function.
+
+       Studying a pattern is also useful for non-anchored patterns that do not
+       have a single fixed starting character. A bitmap of  possible  starting
+       bytes  is  created. This speeds up finding a position in the subject at
+       which to start matching. (In 16-bit mode, the bitmap is used for 16-bit
+       values less than 256.)
+
+       These  two optimizations apply to both pcre_exec() and pcre_dfa_exec(),
+       and the information is also used by the JIT  compiler.   The  optimiza-
+       tions can be disabled by setting the PCRE_NO_START_OPTIMIZE option when
+       calling pcre_exec() or pcre_dfa_exec(), but if this is done, JIT execu-
+       tion  is  also disabled. You might want to do this if your pattern con-
+       tains callouts or (*MARK) and you want to make use of these  facilities
+       in    cases    where    matching   fails.   See   the   discussion   of
+       PCRE_NO_START_OPTIMIZE below.
+
+
+LOCALE SUPPORT
+
+       PCRE handles caseless matching, and determines whether  characters  are
+       letters,  digits, or whatever, by reference to a set of tables, indexed
+       by character value. When running in UTF-8 mode, this  applies  only  to
+       characters  with  codes  less than 128. By default, higher-valued codes
+       never match escapes such as \w or \d, but they can be tested with \p if
+       PCRE  is  built with Unicode character property support. Alternatively,
+       the PCRE_UCP option can be set at compile  time;  this  causes  \w  and
+       friends to use Unicode property support instead of built-in tables. The
+       use of locales with Unicode is discouraged. If you are handling charac-
+       ters  with codes greater than 128, you should either use UTF-8 and Uni-
+       code, or use locales, but not try to mix the two.
+
+       PCRE contains an internal set of tables that are used  when  the  final
+       argument  of  pcre_compile()  is  NULL.  These  are sufficient for many
+       applications.  Normally, the internal tables recognize only ASCII char-
+       acters. However, when PCRE is built, it is possible to cause the inter-
+       nal tables to be rebuilt in the default "C" locale of the local system,
+       which may cause them to be different.
+
+       The  internal tables can always be overridden by tables supplied by the
+       application that calls PCRE. These may be created in a different locale
+       from  the  default.  As more and more applications change to using Uni-
+       code, the need for this locale support is expected to die away.
+
+       External tables are built by calling  the  pcre_maketables()  function,
+       which  has no arguments, in the relevant locale. The result can then be
+       passed to pcre_compile() or pcre_exec()  as  often  as  necessary.  For
+       example,  to  build  and use tables that are appropriate for the French
+       locale (where accented characters with  values  greater  than  128  are
+       treated as letters), the following code could be used:
+
+         setlocale(LC_CTYPE, "fr_FR");
+         tables = pcre_maketables();
+         re = pcre_compile(..., tables);
+
+       The  locale  name "fr_FR" is used on Linux and other Unix-like systems;
+       if you are using Windows, the name for the French locale is "french".
+
+       When pcre_maketables() runs, the tables are built  in  memory  that  is
+       obtained  via  pcre_malloc. It is the caller's responsibility to ensure
+       that the memory containing the tables remains available for as long  as
+       it is needed.
+
+       The pointer that is passed to pcre_compile() is saved with the compiled
+       pattern, and the same tables are used via this pointer by  pcre_study()
+       and normally also by pcre_exec(). Thus, by default, for any single pat-
+       tern, compilation, studying and matching all happen in the same locale,
+       but different patterns can be compiled in different locales.
+
+       It  is  possible to pass a table pointer or NULL (indicating the use of
+       the internal tables) to pcre_exec(). Although  not  intended  for  this
+       purpose,  this facility could be used to match a pattern in a different
+       locale from the one in which it was compiled. Passing table pointers at
+       run time is discussed below in the section on matching a pattern.
+
+
+INFORMATION ABOUT A PATTERN
+
+       int pcre_fullinfo(const pcre *code, const pcre_extra *extra,
+            int what, void *where);
+
+       The  pcre_fullinfo() function returns information about a compiled pat-
+       tern. It replaces the pcre_info() function, which was removed from  the
+       library at version 8.30, after more than 10 years of obsolescence.
+
+       The  first  argument  for  pcre_fullinfo() is a pointer to the compiled
+       pattern. The second argument is the result of pcre_study(), or NULL  if
+       the  pattern  was not studied. The third argument specifies which piece
+       of information is required, and the fourth argument is a pointer  to  a
+       variable  to  receive  the  data. The yield of the function is zero for
+       success, or one of the following negative numbers:
+
+         PCRE_ERROR_NULL           the argument code was NULL
+                                   the argument where was NULL
+         PCRE_ERROR_BADMAGIC       the "magic number" was not found
+         PCRE_ERROR_BADENDIANNESS  the pattern was compiled with different
+                                   endianness
+         PCRE_ERROR_BADOPTION      the value of what was invalid
+
+       The "magic number" is placed at the start of each compiled  pattern  as
+       an  simple check against passing an arbitrary memory pointer. The endi-
+       anness error can occur if a compiled pattern is saved and reloaded on a
+       different  host.  Here  is a typical call of pcre_fullinfo(), to obtain
+       the length of the compiled pattern:
+
+         int rc;
+         size_t length;
+         rc = pcre_fullinfo(
+           re,               /* result of pcre_compile() */
+           sd,               /* result of pcre_study(), or NULL */
+           PCRE_INFO_SIZE,   /* what is required */
+           &length);         /* where to put the data */
+
+       The possible values for the third argument are defined in  pcre.h,  and
+       are as follows:
+
+         PCRE_INFO_BACKREFMAX
+
+       Return  the  number  of  the highest back reference in the pattern. The
+       fourth argument should point to an int variable. Zero  is  returned  if
+       there are no back references.
+
+         PCRE_INFO_CAPTURECOUNT
+
+       Return  the  number of capturing subpatterns in the pattern. The fourth
+       argument should point to an int variable.
+
+         PCRE_INFO_DEFAULT_TABLES
+
+       Return a pointer to the internal default character tables within  PCRE.
+       The  fourth  argument should point to an unsigned char * variable. This
+       information call is provided for internal use by the pcre_study() func-
+       tion.  External  callers  can  cause PCRE to use its internal tables by
+       passing a NULL table pointer.
+
+         PCRE_INFO_FIRSTBYTE
+
+       Return information about the first data unit of any matched string, for
+       a  non-anchored  pattern.  (The name of this option refers to the 8-bit
+       library, where data units are bytes.) The fourth argument should  point
+       to an int variable.
+
+       If  there  is  a  fixed first value, for example, the letter "c" from a
+       pattern such as (cat|cow|coyote), its value is returned. In  the  8-bit
+       library,  the  value is always less than 256; in the 16-bit library the
+       value can be up to 0xffff.
+
+       If there is no fixed first value, and if either
+
+       (a) the pattern was compiled with the PCRE_MULTILINE option, and  every
+       branch starts with "^", or
+
+       (b) every branch of the pattern starts with ".*" and PCRE_DOTALL is not
+       set (if it were set, the pattern would be anchored),
+
+       -1 is returned, indicating that the pattern matches only at  the  start
+       of  a  subject string or after any newline within the string. Otherwise
+       -2 is returned. For anchored patterns, -2 is returned.
+
+         PCRE_INFO_FIRSTTABLE
+
+       If the pattern was studied, and this resulted in the construction of  a
+       256-bit  table indicating a fixed set of values for the first data unit
+       in any matching string, a pointer to the table is  returned.  Otherwise
+       NULL  is returned. The fourth argument should point to an unsigned char
+       * variable.
+
+         PCRE_INFO_HASCRORLF
+
+       Return 1 if the pattern contains any explicit  matches  for  CR  or  LF
+       characters,  otherwise  0.  The  fourth argument should point to an int
+       variable. An explicit match is either a literal CR or LF character,  or
+       \r or \n.
+
+         PCRE_INFO_JCHANGED
+
+       Return  1  if  the (?J) or (?-J) option setting is used in the pattern,
+       otherwise 0. The fourth argument should point to an int variable.  (?J)
+       and (?-J) set and unset the local PCRE_DUPNAMES option, respectively.
+
+         PCRE_INFO_JIT
+
+       Return  1  if  the pattern was studied with one of the JIT options, and
+       just-in-time compiling was successful. The fourth argument should point
+       to  an  int variable. A return value of 0 means that JIT support is not
+       available in this version of PCRE, or that the pattern was not  studied
+       with  a JIT option, or that the JIT compiler could not handle this par-
+       ticular pattern. See the pcrejit documentation for details of what  can
+       and cannot be handled.
+
+         PCRE_INFO_JITSIZE
+
+       If  the  pattern was successfully studied with a JIT option, return the
+       size of the JIT compiled code, otherwise return zero. The fourth  argu-
+       ment should point to a size_t variable.
+
+         PCRE_INFO_LASTLITERAL
+
+       Return  the value of the rightmost literal data unit that must exist in
+       any matched string, other than at its start, if such a value  has  been
+       recorded. The fourth argument should point to an int variable. If there
+       is no such value, -1 is returned. For anchored patterns, a last literal
+       value  is recorded only if it follows something of variable length. For
+       example, for the pattern /^a\d+z\d+/ the returned value is "z", but for
+       /^a\dz\d/ the returned value is -1.
+
+         PCRE_INFO_MAXLOOKBEHIND
+
+       Return  the  number of characters (NB not bytes) in the longest lookbe-
+       hind assertion in the pattern. Note that the simple assertions  \b  and
+       \B  require a one-character lookbehind. This information is useful when
+       doing multi-segment matching using the partial matching facilities.
+
+         PCRE_INFO_MINLENGTH
+
+       If the pattern was studied and a minimum length  for  matching  subject
+       strings  was  computed,  its  value is returned. Otherwise the returned
+       value is -1. The value is a number of characters, which in  UTF-8  mode
+       may  be  different from the number of bytes. The fourth argument should
+       point to an int variable. A non-negative value is a lower bound to  the
+       length  of  any  matching  string. There may not be any strings of that
+       length that do actually match, but every string that does match  is  at
+       least that long.
+
+         PCRE_INFO_NAMECOUNT
+         PCRE_INFO_NAMEENTRYSIZE
+         PCRE_INFO_NAMETABLE
+
+       PCRE  supports the use of named as well as numbered capturing parenthe-
+       ses. The names are just an additional way of identifying the  parenthe-
+       ses, which still acquire numbers. Several convenience functions such as
+       pcre_get_named_substring() are provided for  extracting  captured  sub-
+       strings  by  name. It is also possible to extract the data directly, by
+       first converting the name to a number in order to  access  the  correct
+       pointers in the output vector (described with pcre_exec() below). To do
+       the conversion, you need  to  use  the  name-to-number  map,  which  is
+       described by these three values.
+
+       The map consists of a number of fixed-size entries. PCRE_INFO_NAMECOUNT
+       gives the number of entries, and PCRE_INFO_NAMEENTRYSIZE gives the size
+       of  each  entry;  both  of  these  return  an int value. The entry size
+       depends on the length of the longest name. PCRE_INFO_NAMETABLE  returns
+       a pointer to the first entry of the table. This is a pointer to char in
+       the 8-bit library, where the first two bytes of each entry are the num-
+       ber  of  the capturing parenthesis, most significant byte first. In the
+       16-bit library, the pointer points to 16-bit data units, the  first  of
+       which  contains  the  parenthesis  number. The rest of the entry is the
+       corresponding name, zero terminated.
+
+       The names are in alphabetical order. Duplicate names may appear if  (?|
+       is used to create multiple groups with the same number, as described in
+       the section on duplicate subpattern numbers in  the  pcrepattern  page.
+       Duplicate  names  for  subpatterns with different numbers are permitted
+       only if PCRE_DUPNAMES is set. In all cases  of  duplicate  names,  they
+       appear  in  the table in the order in which they were found in the pat-
+       tern. In the absence of (?| this is the  order  of  increasing  number;
+       when (?| is used this is not necessarily the case because later subpat-
+       terns may have lower numbers.
+
+       As a simple example of the name/number table,  consider  the  following
+       pattern after compilation by the 8-bit library (assume PCRE_EXTENDED is
+       set, so white space - including newlines - is ignored):
+
+         (?<date> (?<year>(\d\d)?\d\d) -
+         (?<month>\d\d) - (?<day>\d\d) )
+
+       There are four named subpatterns, so the table has  four  entries,  and
+       each  entry  in the table is eight bytes long. The table is as follows,
+       with non-printing bytes shows in hexadecimal, and undefined bytes shown
+       as ??:
+
+         00 01 d  a  t  e  00 ??
+         00 05 d  a  y  00 ?? ??
+         00 04 m  o  n  t  h  00
+         00 02 y  e  a  r  00 ??
+
+       When  writing  code  to  extract  data from named subpatterns using the
+       name-to-number map, remember that the length of the entries  is  likely
+       to be different for each compiled pattern.
+
+         PCRE_INFO_OKPARTIAL
+
+       Return  1  if  the  pattern  can  be  used  for  partial  matching with
+       pcre_exec(), otherwise 0. The fourth argument should point  to  an  int
+       variable.  From  release  8.00,  this  always  returns  1,  because the
+       restrictions that previously applied  to  partial  matching  have  been
+       lifted.  The  pcrepartial documentation gives details of partial match-
+       ing.
+
+         PCRE_INFO_OPTIONS
+
+       Return a copy of the options with which the pattern was  compiled.  The
+       fourth  argument  should  point to an unsigned long int variable. These
+       option bits are those specified in the call to pcre_compile(), modified
+       by any top-level option settings at the start of the pattern itself. In
+       other words, they are the options that will be in force  when  matching
+       starts.  For  example, if the pattern /(?im)abc(?-i)d/ is compiled with
+       the PCRE_EXTENDED option, the result is PCRE_CASELESS,  PCRE_MULTILINE,
+       and PCRE_EXTENDED.
+
+       A  pattern  is  automatically  anchored by PCRE if all of its top-level
+       alternatives begin with one of the following:
+
+         ^     unless PCRE_MULTILINE is set
+         \A    always
+         \G    always
+         .*    if PCRE_DOTALL is set and there are no back
+                 references to the subpattern in which .* appears
+
+       For such patterns, the PCRE_ANCHORED bit is set in the options returned
+       by pcre_fullinfo().
+
+         PCRE_INFO_SIZE
+
+       Return  the size of the compiled pattern in bytes (for both libraries).
+       The fourth argument should point to a size_t variable. This value  does
+       not  include  the  size  of  the  pcre  structure  that  is returned by
+       pcre_compile(). The value that is passed as the argument  to  pcre_mal-
+       loc()  when pcre_compile() is getting memory in which to place the com-
+       piled data is the value returned by this option plus the  size  of  the
+       pcre  structure. Studying a compiled pattern, with or without JIT, does
+       not alter the value returned by this option.
+
+         PCRE_INFO_STUDYSIZE
+
+       Return the size in bytes of the data block pointed to by the study_data
+       field  in  a  pcre_extra  block.  If pcre_extra is NULL, or there is no
+       study data, zero is returned. The fourth argument  should  point  to  a
+       size_t  variable. The study_data field is set by pcre_study() to record
+       information that will speed  up  matching  (see  the  section  entitled
+       "Studying a pattern" above). The format of the study_data block is pri-
+       vate, but its length is made available via this option so that  it  can
+       be  saved  and  restored  (see  the  pcreprecompile  documentation  for
+       details).
+
+
+REFERENCE COUNTS
+
+       int pcre_refcount(pcre *code, int adjust);
+
+       The pcre_refcount() function is used to maintain a reference  count  in
+       the data block that contains a compiled pattern. It is provided for the
+       benefit of applications that  operate  in  an  object-oriented  manner,
+       where different parts of the application may be using the same compiled
+       pattern, but you want to free the block when they are all done.
+
+       When a pattern is compiled, the reference count field is initialized to
+       zero.   It is changed only by calling this function, whose action is to
+       add the adjust value (which may be positive or  negative)  to  it.  The
+       yield of the function is the new value. However, the value of the count
+       is constrained to lie between 0 and 65535, inclusive. If the new  value
+       is outside these limits, it is forced to the appropriate limit value.
+
+       Except  when it is zero, the reference count is not correctly preserved
+       if a pattern is compiled on one host and then  transferred  to  a  host
+       whose byte-order is different. (This seems a highly unlikely scenario.)
+
+
+MATCHING A PATTERN: THE TRADITIONAL FUNCTION
+
+       int pcre_exec(const pcre *code, const pcre_extra *extra,
+            const char *subject, int length, int startoffset,
+            int options, int *ovector, int ovecsize);
+
+       The  function pcre_exec() is called to match a subject string against a
+       compiled pattern, which is passed in the code argument. If the  pattern
+       was  studied,  the  result  of  the study should be passed in the extra
+       argument. You can call pcre_exec() with the same code and  extra  argu-
+       ments  as  many  times as you like, in order to match different subject
+       strings with the same pattern.
+
+       This function is the main matching facility  of  the  library,  and  it
+       operates  in  a  Perl-like  manner. For specialist use there is also an
+       alternative matching function, which is described below in the  section
+       about the pcre_dfa_exec() function.
+
+       In  most applications, the pattern will have been compiled (and option-
+       ally studied) in the same process that calls pcre_exec().  However,  it
+       is possible to save compiled patterns and study data, and then use them
+       later in different processes, possibly even on different hosts.  For  a
+       discussion about this, see the pcreprecompile documentation.
+
+       Here is an example of a simple call to pcre_exec():
+
+         int rc;
+         int ovector[30];
+         rc = pcre_exec(
+           re,             /* result of pcre_compile() */
+           NULL,           /* we didn't study the pattern */
+           "some string",  /* the subject string */
+           11,             /* the length of the subject string */
+           0,              /* start at offset 0 in the subject */
+           0,              /* default options */
+           ovector,        /* vector of integers for substring information */
+           30);            /* number of elements (NOT size in bytes) */
+
+   Extra data for pcre_exec()
+
+       If  the  extra argument is not NULL, it must point to a pcre_extra data
+       block. The pcre_study() function returns such a block (when it  doesn't
+       return  NULL), but you can also create one for yourself, and pass addi-
+       tional information in it. The pcre_extra block contains  the  following
+       fields (not necessarily in this order):
+
+         unsigned long int flags;
+         void *study_data;
+         void *executable_jit;
+         unsigned long int match_limit;
+         unsigned long int match_limit_recursion;
+         void *callout_data;
+         const unsigned char *tables;
+         unsigned char **mark;
+
+       In  the  16-bit  version  of  this  structure,  the mark field has type
+       "PCRE_UCHAR16 **".
+
+       The flags field is used to specify which of the other fields  are  set.
+       The flag bits are:
+
+         PCRE_EXTRA_CALLOUT_DATA
+         PCRE_EXTRA_EXECUTABLE_JIT
+         PCRE_EXTRA_MARK
+         PCRE_EXTRA_MATCH_LIMIT
+         PCRE_EXTRA_MATCH_LIMIT_RECURSION
+         PCRE_EXTRA_STUDY_DATA
+         PCRE_EXTRA_TABLES
+
+       Other  flag  bits should be set to zero. The study_data field and some-
+       times the executable_jit field are set in the pcre_extra block that  is
+       returned  by pcre_study(), together with the appropriate flag bits. You
+       should not set these yourself, but you may add to the block by  setting
+       other fields and their corresponding flag bits.
+
+       The match_limit field provides a means of preventing PCRE from using up
+       a vast amount of resources when running patterns that are not going  to
+       match,  but  which  have  a very large number of possibilities in their
+       search trees. The classic example is a pattern that uses nested  unlim-
+       ited repeats.
+
+       Internally,  pcre_exec() uses a function called match(), which it calls
+       repeatedly (sometimes recursively). The limit  set  by  match_limit  is
+       imposed  on the number of times this function is called during a match,
+       which has the effect of limiting the amount of  backtracking  that  can
+       take place. For patterns that are not anchored, the count restarts from
+       zero for each position in the subject string.
+
+       When pcre_exec() is called with a pattern that was successfully studied
+       with  a  JIT  option, the way that the matching is executed is entirely
+       different.  However, there is still the possibility of runaway matching
+       that goes on for a very long time, and so the match_limit value is also
+       used in this case (but in a different way) to limit how long the match-
+       ing can continue.
+
+       The  default  value  for  the  limit can be set when PCRE is built; the
+       default default is 10 million, which handles all but the  most  extreme
+       cases.  You  can  override  the  default by suppling pcre_exec() with a
+       pcre_extra    block    in    which    match_limit    is    set,     and
+       PCRE_EXTRA_MATCH_LIMIT  is  set  in  the  flags  field. If the limit is
+       exceeded, pcre_exec() returns PCRE_ERROR_MATCHLIMIT.
+
+       The match_limit_recursion field is similar to match_limit, but  instead
+       of limiting the total number of times that match() is called, it limits
+       the depth of recursion. The recursion depth is a  smaller  number  than
+       the  total number of calls, because not all calls to match() are recur-
+       sive.  This limit is of use only if it is set smaller than match_limit.
+
+       Limiting the recursion depth limits the amount of  machine  stack  that
+       can  be used, or, when PCRE has been compiled to use memory on the heap
+       instead of the stack, the amount of heap memory that can be used.  This
+       limit  is not relevant, and is ignored, when matching is done using JIT
+       compiled code.
+
+       The default value for match_limit_recursion can be  set  when  PCRE  is
+       built;  the  default  default  is  the  same  value  as the default for
+       match_limit. You can override the default by suppling pcre_exec()  with
+       a   pcre_extra   block  in  which  match_limit_recursion  is  set,  and
+       PCRE_EXTRA_MATCH_LIMIT_RECURSION is set in  the  flags  field.  If  the
+       limit is exceeded, pcre_exec() returns PCRE_ERROR_RECURSIONLIMIT.
+
+       The  callout_data  field is used in conjunction with the "callout" fea-
+       ture, and is described in the pcrecallout documentation.
+
+       The tables field  is  used  to  pass  a  character  tables  pointer  to
+       pcre_exec();  this overrides the value that is stored with the compiled
+       pattern. A non-NULL value is stored with the compiled pattern  only  if
+       custom  tables  were  supplied to pcre_compile() via its tableptr argu-
+       ment.  If NULL is passed to pcre_exec() using this mechanism, it forces
+       PCRE's  internal  tables  to be used. This facility is helpful when re-
+       using patterns that have been saved after compiling  with  an  external
+       set  of  tables,  because  the  external tables might be at a different
+       address when pcre_exec() is called. See the  pcreprecompile  documenta-
+       tion for a discussion of saving compiled patterns for later use.
+
+       If  PCRE_EXTRA_MARK  is  set in the flags field, the mark field must be
+       set to point to a suitable variable. If the pattern contains any  back-
+       tracking  control verbs such as (*MARK:NAME), and the execution ends up
+       with a name to pass back, a pointer to the  name  string  (zero  termi-
+       nated)  is  placed  in  the  variable pointed to by the mark field. The
+       names are within the compiled pattern; if you wish  to  retain  such  a
+       name  you must copy it before freeing the memory of a compiled pattern.
+       If there is no name to pass back, the variable pointed to by  the  mark
+       field  is  set  to NULL. For details of the backtracking control verbs,
+       see the section entitled "Backtracking control" in the pcrepattern doc-
+       umentation.
+
+   Option bits for pcre_exec()
+
+       The  unused  bits of the options argument for pcre_exec() must be zero.
+       The only bits that may  be  set  are  PCRE_ANCHORED,  PCRE_NEWLINE_xxx,
+       PCRE_NOTBOL,    PCRE_NOTEOL,    PCRE_NOTEMPTY,   PCRE_NOTEMPTY_ATSTART,
+       PCRE_NO_START_OPTIMIZE,  PCRE_NO_UTF8_CHECK,   PCRE_PARTIAL_HARD,   and
+       PCRE_PARTIAL_SOFT.
+
+       If  the  pattern  was successfully studied with one of the just-in-time
+       (JIT) compile options, the only supported options for JIT execution are
+       PCRE_NO_UTF8_CHECK,     PCRE_NOTBOL,     PCRE_NOTEOL,    PCRE_NOTEMPTY,
+       PCRE_NOTEMPTY_ATSTART, PCRE_PARTIAL_HARD, and PCRE_PARTIAL_SOFT. If  an
+       unsupported  option  is  used, JIT execution is disabled and the normal
+       interpretive code in pcre_exec() is run.
+
+         PCRE_ANCHORED
+
+       The PCRE_ANCHORED option limits pcre_exec() to matching  at  the  first
+       matching  position.  If  a  pattern was compiled with PCRE_ANCHORED, or
+       turned out to be anchored by virtue of its contents, it cannot be  made
+       unachored at matching time.
+
+         PCRE_BSR_ANYCRLF
+         PCRE_BSR_UNICODE
+
+       These options (which are mutually exclusive) control what the \R escape
+       sequence matches. The choice is either to match only CR, LF,  or  CRLF,
+       or  to  match  any Unicode newline sequence. These options override the
+       choice that was made or defaulted when the pattern was compiled.
+
+         PCRE_NEWLINE_CR
+         PCRE_NEWLINE_LF
+         PCRE_NEWLINE_CRLF
+         PCRE_NEWLINE_ANYCRLF
+         PCRE_NEWLINE_ANY
+
+       These options override  the  newline  definition  that  was  chosen  or
+       defaulted  when the pattern was compiled. For details, see the descrip-
+       tion of pcre_compile()  above.  During  matching,  the  newline  choice
+       affects  the  behaviour  of the dot, circumflex, and dollar metacharac-
+       ters. It may also alter the way the match position is advanced after  a
+       match failure for an unanchored pattern.
+
+       When  PCRE_NEWLINE_CRLF,  PCRE_NEWLINE_ANYCRLF,  or PCRE_NEWLINE_ANY is
+       set, and a match attempt for an unanchored pattern fails when the  cur-
+       rent  position  is  at  a  CRLF  sequence,  and the pattern contains no
+       explicit matches for  CR  or  LF  characters,  the  match  position  is
+       advanced by two characters instead of one, in other words, to after the
+       CRLF.
+
+       The above rule is a compromise that makes the most common cases work as
+       expected.  For  example,  if  the  pattern  is .+A (and the PCRE_DOTALL
+       option is not set), it does not match the string "\r\nA" because, after
+       failing  at the start, it skips both the CR and the LF before retrying.
+       However, the pattern [\r\n]A does match that string,  because  it  con-
+       tains an explicit CR or LF reference, and so advances only by one char-
+       acter after the first failure.
+
+       An explicit match for CR of LF is either a literal appearance of one of
+       those  characters,  or  one  of the \r or \n escape sequences. Implicit
+       matches such as [^X] do not count, nor does \s (which includes  CR  and
+       LF in the characters that it matches).
+
+       Notwithstanding  the above, anomalous effects may still occur when CRLF
+       is a valid newline sequence and explicit \r or \n escapes appear in the
+       pattern.
+
+         PCRE_NOTBOL
+
+       This option specifies that first character of the subject string is not
+       the beginning of a line, so the  circumflex  metacharacter  should  not
+       match  before it. Setting this without PCRE_MULTILINE (at compile time)
+       causes circumflex never to match. This option affects only  the  behav-
+       iour of the circumflex metacharacter. It does not affect \A.
+
+         PCRE_NOTEOL
+
+       This option specifies that the end of the subject string is not the end
+       of a line, so the dollar metacharacter should not match it nor  (except
+       in  multiline mode) a newline immediately before it. Setting this with-
+       out PCRE_MULTILINE (at compile time) causes dollar never to match. This
+       option  affects only the behaviour of the dollar metacharacter. It does
+       not affect \Z or \z.
+
+         PCRE_NOTEMPTY
+
+       An empty string is not considered to be a valid match if this option is
+       set.  If  there are alternatives in the pattern, they are tried. If all
+       the alternatives match the empty string, the entire  match  fails.  For
+       example, if the pattern
+
+         a?b?
+
+       is  applied  to  a  string not beginning with "a" or "b", it matches an
+       empty string at the start of the subject. With PCRE_NOTEMPTY set,  this
+       match is not valid, so PCRE searches further into the string for occur-
+       rences of "a" or "b".
+
+         PCRE_NOTEMPTY_ATSTART
+
+       This is like PCRE_NOTEMPTY, except that an empty string match  that  is
+       not  at  the  start  of  the  subject  is  permitted. If the pattern is
+       anchored, such a match can occur only if the pattern contains \K.
+
+       Perl    has    no    direct    equivalent    of    PCRE_NOTEMPTY     or
+       PCRE_NOTEMPTY_ATSTART,  but  it  does  make a special case of a pattern
+       match of the empty string within its split() function, and  when  using
+       the  /g  modifier.  It  is  possible  to emulate Perl's behaviour after
+       matching a null string by first trying the match again at the same off-
+       set  with  PCRE_NOTEMPTY_ATSTART  and  PCRE_ANCHORED,  and then if that
+       fails, by advancing the starting offset (see below) and trying an ordi-
+       nary  match  again. There is some code that demonstrates how to do this
+       in the pcredemo sample program. In the most general case, you  have  to
+       check  to  see  if the newline convention recognizes CRLF as a newline,
+       and if so, and the current character is CR followed by LF, advance  the
+       starting offset by two characters instead of one.
+
+         PCRE_NO_START_OPTIMIZE
+
+       There  are a number of optimizations that pcre_exec() uses at the start
+       of a match, in order to speed up the process. For  example,  if  it  is
+       known that an unanchored match must start with a specific character, it
+       searches the subject for that character, and fails  immediately  if  it
+       cannot  find  it,  without actually running the main matching function.
+       This means that a special item such as (*COMMIT) at the start of a pat-
+       tern  is  not  considered until after a suitable starting point for the
+       match has been found. When callouts or (*MARK) items are in use,  these
+       "start-up" optimizations can cause them to be skipped if the pattern is
+       never actually used. The start-up optimizations are in  effect  a  pre-
+       scan of the subject that takes place before the pattern is run.
+
+       The  PCRE_NO_START_OPTIMIZE option disables the start-up optimizations,
+       possibly causing performance to suffer,  but  ensuring  that  in  cases
+       where  the  result is "no match", the callouts do occur, and that items
+       such as (*COMMIT) and (*MARK) are considered at every possible starting
+       position  in  the  subject  string. If PCRE_NO_START_OPTIMIZE is set at
+       compile time,  it  cannot  be  unset  at  matching  time.  The  use  of
+       PCRE_NO_START_OPTIMIZE disables JIT execution; when it is set, matching
+       is always done using interpretively.
+
+       Setting PCRE_NO_START_OPTIMIZE can change the  outcome  of  a  matching
+       operation.  Consider the pattern
+
+         (*COMMIT)ABC
+
+       When  this  is  compiled, PCRE records the fact that a match must start
+       with the character "A". Suppose the subject  string  is  "DEFABC".  The
+       start-up  optimization  scans along the subject, finds "A" and runs the
+       first match attempt from there. The (*COMMIT) item means that the  pat-
+       tern  must  match the current starting position, which in this case, it
+       does. However, if the same match  is  run  with  PCRE_NO_START_OPTIMIZE
+       set,  the  initial  scan  along the subject string does not happen. The
+       first match attempt is run starting  from  "D"  and  when  this  fails,
+       (*COMMIT)  prevents  any  further  matches  being tried, so the overall
+       result is "no match". If the pattern is studied,  more  start-up  opti-
+       mizations  may  be  used. For example, a minimum length for the subject
+       may be recorded. Consider the pattern
+
+         (*MARK:A)(X|Y)
+
+       The minimum length for a match is one  character.  If  the  subject  is
+       "ABC",  there  will  be  attempts  to  match "ABC", "BC", "C", and then
+       finally an empty string.  If the pattern is studied, the final  attempt
+       does  not take place, because PCRE knows that the subject is too short,
+       and so the (*MARK) is never encountered.  In this  case,  studying  the
+       pattern  does  not  affect the overall match result, which is still "no
+       match", but it does affect the auxiliary information that is returned.
+
+         PCRE_NO_UTF8_CHECK
+
+       When PCRE_UTF8 is set at compile time, the validity of the subject as a
+       UTF-8  string is automatically checked when pcre_exec() is subsequently
+       called.  The entire string is checked before any other processing takes
+       place.  The  value  of  startoffset  is  also checked to ensure that it
+       points to the start of a UTF-8 character. There is a  discussion  about
+       the  validity  of  UTF-8 strings in the pcreunicode page. If an invalid
+       sequence  of  bytes   is   found,   pcre_exec()   returns   the   error
+       PCRE_ERROR_BADUTF8 or, if PCRE_PARTIAL_HARD is set and the problem is a
+       truncated character at the end of the subject, PCRE_ERROR_SHORTUTF8. In
+       both  cases, information about the precise nature of the error may also
+       be returned (see the descriptions of these errors in the section  enti-
+       tled  Error return values from pcre_exec() below).  If startoffset con-
+       tains a value that does not point to the start of a UTF-8 character (or
+       to the end of the subject), PCRE_ERROR_BADUTF8_OFFSET is returned.
+
+       If  you  already  know that your subject is valid, and you want to skip
+       these   checks   for   performance   reasons,   you   can    set    the
+       PCRE_NO_UTF8_CHECK  option  when calling pcre_exec(). You might want to
+       do this for the second and subsequent calls to pcre_exec() if  you  are
+       making  repeated  calls  to  find  all  the matches in a single subject
+       string. However, you should be  sure  that  the  value  of  startoffset
+       points  to  the  start of a character (or the end of the subject). When
+       PCRE_NO_UTF8_CHECK is set, the effect of passing an invalid string as a
+       subject  or  an invalid value of startoffset is undefined. Your program
+       may crash.
+
+         PCRE_PARTIAL_HARD
+         PCRE_PARTIAL_SOFT
+
+       These options turn on the partial matching feature. For backwards  com-
+       patibility,  PCRE_PARTIAL is a synonym for PCRE_PARTIAL_SOFT. A partial
+       match occurs if the end of the subject string is reached  successfully,
+       but  there  are not enough subject characters to complete the match. If
+       this happens when PCRE_PARTIAL_SOFT (but not PCRE_PARTIAL_HARD) is set,
+       matching  continues  by  testing any remaining alternatives. Only if no
+       complete match can be found is PCRE_ERROR_PARTIAL returned  instead  of
+       PCRE_ERROR_NOMATCH.  In  other  words,  PCRE_PARTIAL_SOFT says that the
+       caller is prepared to handle a partial match, but only if  no  complete
+       match can be found.
+
+       If  PCRE_PARTIAL_HARD  is  set, it overrides PCRE_PARTIAL_SOFT. In this
+       case, if a partial match  is  found,  pcre_exec()  immediately  returns
+       PCRE_ERROR_PARTIAL,  without  considering  any  other  alternatives. In
+       other words, when PCRE_PARTIAL_HARD is set, a partial match is  consid-
+       ered to be more important that an alternative complete match.
+
+       In  both  cases,  the portion of the string that was inspected when the
+       partial match was found is set as the first matching string. There is a
+       more  detailed  discussion  of partial and multi-segment matching, with
+       examples, in the pcrepartial documentation.
+
+   The string to be matched by pcre_exec()
+
+       The subject string is passed to pcre_exec() as a pointer in subject,  a
+       length  in  bytes in length, and a starting byte offset in startoffset.
+       If this is  negative  or  greater  than  the  length  of  the  subject,
+       pcre_exec()  returns  PCRE_ERROR_BADOFFSET. When the starting offset is
+       zero, the search for a match starts at the beginning  of  the  subject,
+       and this is by far the most common case. In UTF-8 mode, the byte offset
+       must point to the start of a UTF-8 character (or the end  of  the  sub-
+       ject).  Unlike  the pattern string, the subject may contain binary zero
+       bytes.
+
+       A non-zero starting offset is useful when searching for  another  match
+       in  the same subject by calling pcre_exec() again after a previous suc-
+       cess.  Setting startoffset differs from just passing over  a  shortened
+       string  and  setting  PCRE_NOTBOL  in the case of a pattern that begins
+       with any kind of lookbehind. For example, consider the pattern
+
+         \Biss\B
+
+       which finds occurrences of "iss" in the middle of  words.  (\B  matches
+       only  if  the  current position in the subject is not a word boundary.)
+       When applied to the string "Mississipi" the first call  to  pcre_exec()
+       finds  the  first  occurrence. If pcre_exec() is called again with just
+       the remainder of the subject,  namely  "issipi",  it  does  not  match,
+       because \B is always false at the start of the subject, which is deemed
+       to be a word boundary. However, if pcre_exec()  is  passed  the  entire
+       string again, but with startoffset set to 4, it finds the second occur-
+       rence of "iss" because it is able to look behind the starting point  to
+       discover that it is preceded by a letter.
+
+       Finding  all  the  matches  in a subject is tricky when the pattern can
+       match an empty string. It is possible to emulate Perl's /g behaviour by
+       first   trying   the   match   again  at  the  same  offset,  with  the
+       PCRE_NOTEMPTY_ATSTART and  PCRE_ANCHORED  options,  and  then  if  that
+       fails,  advancing  the  starting  offset  and  trying an ordinary match
+       again. There is some code that demonstrates how to do this in the pcre-
+       demo sample program. In the most general case, you have to check to see
+       if the newline convention recognizes CRLF as a newline, and if so,  and
+       the current character is CR followed by LF, advance the starting offset
+       by two characters instead of one.
+
+       If a non-zero starting offset is passed when the pattern  is  anchored,
+       one attempt to match at the given offset is made. This can only succeed
+       if the pattern does not require the match to be at  the  start  of  the
+       subject.
+
+   How pcre_exec() returns captured substrings
+
+       In  general, a pattern matches a certain portion of the subject, and in
+       addition, further substrings from the subject  may  be  picked  out  by
+       parts  of  the  pattern.  Following the usage in Jeffrey Friedl's book,
+       this is called "capturing" in what follows, and the  phrase  "capturing
+       subpattern"  is  used for a fragment of a pattern that picks out a sub-
+       string. PCRE supports several other kinds of  parenthesized  subpattern
+       that do not cause substrings to be captured.
+
+       Captured substrings are returned to the caller via a vector of integers
+       whose address is passed in ovector. The number of elements in the  vec-
+       tor  is  passed in ovecsize, which must be a non-negative number. Note:
+       this argument is NOT the size of ovector in bytes.
+
+       The first two-thirds of the vector is used to pass back  captured  sub-
+       strings,  each  substring using a pair of integers. The remaining third
+       of the vector is used as workspace by pcre_exec() while  matching  cap-
+       turing  subpatterns, and is not available for passing back information.
+       The number passed in ovecsize should always be a multiple of three.  If
+       it is not, it is rounded down.
+
+       When  a  match  is successful, information about captured substrings is
+       returned in pairs of integers, starting at the  beginning  of  ovector,
+       and  continuing  up  to two-thirds of its length at the most. The first
+       element of each pair is set to the byte offset of the  first  character
+       in  a  substring, and the second is set to the byte offset of the first
+       character after the end of a substring. Note: these values  are  always
+       byte offsets, even in UTF-8 mode. They are not character counts.
+
+       The  first  pair  of  integers, ovector[0] and ovector[1], identify the
+       portion of the subject string matched by the entire pattern.  The  next
+       pair  is  used for the first capturing subpattern, and so on. The value
+       returned by pcre_exec() is one more than the highest numbered pair that
+       has  been  set.  For example, if two substrings have been captured, the
+       returned value is 3. If there are no capturing subpatterns, the  return
+       value from a successful match is 1, indicating that just the first pair
+       of offsets has been set.
+
+       If a capturing subpattern is matched repeatedly, it is the last portion
+       of the string that it matched that is returned.
+
+       If  the vector is too small to hold all the captured substring offsets,
+       it is used as far as possible (up to two-thirds of its length), and the
+       function  returns a value of zero. If neither the actual string matched
+       nor any captured substrings are of interest, pcre_exec() may be  called
+       with  ovector passed as NULL and ovecsize as zero. However, if the pat-
+       tern contains back references and the ovector  is  not  big  enough  to
+       remember  the related substrings, PCRE has to get additional memory for
+       use during matching. Thus it is usually advisable to supply an  ovector
+       of reasonable size.
+
+       There  are  some  cases where zero is returned (indicating vector over-
+       flow) when in fact the vector is exactly the right size for  the  final
+       match. For example, consider the pattern
+
+         (a)(?:(b)c|bd)
+
+       If  a  vector of 6 elements (allowing for only 1 captured substring) is
+       given with subject string "abd", pcre_exec() will try to set the second
+       captured string, thereby recording a vector overflow, before failing to
+       match "c" and backing up  to  try  the  second  alternative.  The  zero
+       return,  however,  does  correctly  indicate that the maximum number of
+       slots (namely 2) have been filled. In similar cases where there is tem-
+       porary  overflow,  but  the final number of used slots is actually less
+       than the maximum, a non-zero value is returned.
+
+       The pcre_fullinfo() function can be used to find out how many capturing
+       subpatterns  there  are  in  a  compiled pattern. The smallest size for
+       ovector that will allow for n captured substrings, in addition  to  the
+       offsets of the substring matched by the whole pattern, is (n+1)*3.
+
+       It  is  possible for capturing subpattern number n+1 to match some part
+       of the subject when subpattern n has not been used at all. For example,
+       if  the  string  "abc"  is  matched against the pattern (a|(z))(bc) the
+       return from the function is 4, and subpatterns 1 and 3 are matched, but
+       2  is  not.  When  this happens, both values in the offset pairs corre-
+       sponding to unused subpatterns are set to -1.
+
+       Offset values that correspond to unused subpatterns at the end  of  the
+       expression  are  also  set  to  -1. For example, if the string "abc" is
+       matched against the pattern (abc)(x(yz)?)? subpatterns 2 and 3 are  not
+       matched.  The  return  from the function is 2, because the highest used
+       capturing subpattern number is 1, and the offsets for  for  the  second
+       and  third  capturing subpatterns (assuming the vector is large enough,
+       of course) are set to -1.
+
+       Note: Elements in the first two-thirds of ovector that  do  not  corre-
+       spond  to  capturing parentheses in the pattern are never changed. That
+       is, if a pattern contains n capturing parentheses, no more  than  ovec-
+       tor[0]  to ovector[2n+1] are set by pcre_exec(). The other elements (in
+       the first two-thirds) retain whatever values they previously had.
+
+       Some convenience functions are provided  for  extracting  the  captured
+       substrings as separate strings. These are described below.
+
+   Error return values from pcre_exec()
+
+       If  pcre_exec()  fails, it returns a negative number. The following are
+       defined in the header file:
+
+         PCRE_ERROR_NOMATCH        (-1)
+
+       The subject string did not match the pattern.
+
+         PCRE_ERROR_NULL           (-2)
+
+       Either code or subject was passed as NULL,  or  ovector  was  NULL  and
+       ovecsize was not zero.
+
+         PCRE_ERROR_BADOPTION      (-3)
+
+       An unrecognized bit was set in the options argument.
+
+         PCRE_ERROR_BADMAGIC       (-4)
+
+       PCRE  stores a 4-byte "magic number" at the start of the compiled code,
+       to catch the case when it is passed a junk pointer and to detect when a
+       pattern that was compiled in an environment of one endianness is run in
+       an environment with the other endianness. This is the error  that  PCRE
+       gives when the magic number is not present.
+
+         PCRE_ERROR_UNKNOWN_OPCODE (-5)
+
+       While running the pattern match, an unknown item was encountered in the
+       compiled pattern. This error could be caused by a bug  in  PCRE  or  by
+       overwriting of the compiled pattern.
+
+         PCRE_ERROR_NOMEMORY       (-6)
+
+       If  a  pattern contains back references, but the ovector that is passed
+       to pcre_exec() is not big enough to remember the referenced substrings,
+       PCRE  gets  a  block of memory at the start of matching to use for this
+       purpose. If the call via pcre_malloc() fails, this error is given.  The
+       memory is automatically freed at the end of matching.
+
+       This  error  is also given if pcre_stack_malloc() fails in pcre_exec().
+       This can happen only when PCRE has been compiled with  --disable-stack-
+       for-recursion.
+
+         PCRE_ERROR_NOSUBSTRING    (-7)
+
+       This  error is used by the pcre_copy_substring(), pcre_get_substring(),
+       and  pcre_get_substring_list()  functions  (see  below).  It  is  never
+       returned by pcre_exec().
+
+         PCRE_ERROR_MATCHLIMIT     (-8)
+
+       The  backtracking  limit,  as  specified  by the match_limit field in a
+       pcre_extra structure (or defaulted) was reached.  See  the  description
+       above.
+
+         PCRE_ERROR_CALLOUT        (-9)
+
+       This error is never generated by pcre_exec() itself. It is provided for
+       use by callout functions that want to yield a distinctive  error  code.
+       See the pcrecallout documentation for details.
+
+         PCRE_ERROR_BADUTF8        (-10)
+
+       A  string  that contains an invalid UTF-8 byte sequence was passed as a
+       subject, and the PCRE_NO_UTF8_CHECK option was not set. If the size  of
+       the  output  vector  (ovecsize)  is  at least 2, the byte offset to the
+       start of the the invalid UTF-8 character is placed in  the  first  ele-
+       ment,  and  a  reason  code is placed in the second element. The reason
+       codes are listed in the following section.  For backward compatibility,
+       if  PCRE_PARTIAL_HARD is set and the problem is a truncated UTF-8 char-
+       acter  at  the  end  of  the   subject   (reason   codes   1   to   5),
+       PCRE_ERROR_SHORTUTF8 is returned instead of PCRE_ERROR_BADUTF8.
+
+         PCRE_ERROR_BADUTF8_OFFSET (-11)
+
+       The  UTF-8  byte  sequence that was passed as a subject was checked and
+       found to be valid (the PCRE_NO_UTF8_CHECK option was not set), but  the
+       value  of startoffset did not point to the beginning of a UTF-8 charac-
+       ter or the end of the subject.
+
+         PCRE_ERROR_PARTIAL        (-12)
+
+       The subject string did not match, but it did match partially.  See  the
+       pcrepartial documentation for details of partial matching.
+
+         PCRE_ERROR_BADPARTIAL     (-13)
+
+       This  code  is  no  longer  in  use.  It was formerly returned when the
+       PCRE_PARTIAL option was used with a compiled pattern  containing  items
+       that  were  not  supported  for  partial  matching.  From  release 8.00
+       onwards, there are no restrictions on partial matching.
+
+         PCRE_ERROR_INTERNAL       (-14)
+
+       An unexpected internal error has occurred. This error could  be  caused
+       by a bug in PCRE or by overwriting of the compiled pattern.
+
+         PCRE_ERROR_BADCOUNT       (-15)
+
+       This error is given if the value of the ovecsize argument is negative.
+
+         PCRE_ERROR_RECURSIONLIMIT (-21)
+
+       The internal recursion limit, as specified by the match_limit_recursion
+       field in a pcre_extra structure (or defaulted)  was  reached.  See  the
+       description above.
+
+         PCRE_ERROR_BADNEWLINE     (-23)
+
+       An invalid combination of PCRE_NEWLINE_xxx options was given.
+
+         PCRE_ERROR_BADOFFSET      (-24)
+
+       The value of startoffset was negative or greater than the length of the
+       subject, that is, the value in length.
+
+         PCRE_ERROR_SHORTUTF8      (-25)
+
+       This error is returned instead of PCRE_ERROR_BADUTF8 when  the  subject
+       string  ends with a truncated UTF-8 character and the PCRE_PARTIAL_HARD
+       option is set.  Information  about  the  failure  is  returned  as  for
+       PCRE_ERROR_BADUTF8.  It  is in fact sufficient to detect this case, but
+       this special error code for PCRE_PARTIAL_HARD precedes the  implementa-
+       tion  of returned information; it is retained for backwards compatibil-
+       ity.
+
+         PCRE_ERROR_RECURSELOOP    (-26)
+
+       This error is returned when pcre_exec() detects a recursion loop within
+       the  pattern. Specifically, it means that either the whole pattern or a
+       subpattern has been called recursively for the second time at the  same
+       position in the subject string. Some simple patterns that might do this
+       are detected and faulted at compile time, but more  complicated  cases,
+       in particular mutual recursions between two different subpatterns, can-
+       not be detected until run time.
+
+         PCRE_ERROR_JIT_STACKLIMIT (-27)
+
+       This error is returned when a pattern  that  was  successfully  studied
+       using  a  JIT compile option is being matched, but the memory available
+       for the just-in-time processing stack is  not  large  enough.  See  the
+       pcrejit documentation for more details.
+
+         PCRE_ERROR_BADMODE        (-28)
+
+       This error is given if a pattern that was compiled by the 8-bit library
+       is passed to a 16-bit library function, or vice versa.
+
+         PCRE_ERROR_BADENDIANNESS  (-29)
+
+       This error is given if  a  pattern  that  was  compiled  and  saved  is
+       reloaded  on  a  host  with  different endianness. The utility function
+       pcre_pattern_to_host_byte_order() can be used to convert such a pattern
+       so that it runs on the new host.
+
+       Error numbers -16 to -20, -22, and -30 are not used by pcre_exec().
+
+   Reason codes for invalid UTF-8 strings
+
+       This  section  applies  only  to  the  8-bit library. The corresponding
+       information for the 16-bit library is given in the pcre16 page.
+
+       When pcre_exec() returns either PCRE_ERROR_BADUTF8 or PCRE_ERROR_SHORT-
+       UTF8,  and  the size of the output vector (ovecsize) is at least 2, the
+       offset of the start of the invalid UTF-8 character  is  placed  in  the
+       first output vector element (ovector[0]) and a reason code is placed in
+       the second element (ovector[1]). The reason codes are  given  names  in
+       the pcre.h header file:
+
+         PCRE_UTF8_ERR1
+         PCRE_UTF8_ERR2
+         PCRE_UTF8_ERR3
+         PCRE_UTF8_ERR4
+         PCRE_UTF8_ERR5
+
+       The  string  ends  with a truncated UTF-8 character; the code specifies
+       how many bytes are missing (1 to 5). Although RFC 3629 restricts  UTF-8
+       characters  to  be  no longer than 4 bytes, the encoding scheme (origi-
+       nally defined by RFC 2279) allows for  up  to  6  bytes,  and  this  is
+       checked first; hence the possibility of 4 or 5 missing bytes.
+
+         PCRE_UTF8_ERR6
+         PCRE_UTF8_ERR7
+         PCRE_UTF8_ERR8
+         PCRE_UTF8_ERR9
+         PCRE_UTF8_ERR10
+
+       The two most significant bits of the 2nd, 3rd, 4th, 5th, or 6th byte of
+       the character do not have the binary value 0b10 (that  is,  either  the
+       most significant bit is 0, or the next bit is 1).
+
+         PCRE_UTF8_ERR11
+         PCRE_UTF8_ERR12
+
+       A  character that is valid by the RFC 2279 rules is either 5 or 6 bytes
+       long; these code points are excluded by RFC 3629.
+
+         PCRE_UTF8_ERR13
+
+       A 4-byte character has a value greater than 0x10fff; these code  points
+       are excluded by RFC 3629.
+
+         PCRE_UTF8_ERR14
+
+       A  3-byte  character  has  a  value in the range 0xd800 to 0xdfff; this
+       range of code points are reserved by RFC 3629 for use with UTF-16,  and
+       so are excluded from UTF-8.
+
+         PCRE_UTF8_ERR15
+         PCRE_UTF8_ERR16
+         PCRE_UTF8_ERR17
+         PCRE_UTF8_ERR18
+         PCRE_UTF8_ERR19
+
+       A  2-, 3-, 4-, 5-, or 6-byte character is "overlong", that is, it codes
+       for a value that can be represented by fewer bytes, which  is  invalid.
+       For  example,  the two bytes 0xc0, 0xae give the value 0x2e, whose cor-
+       rect coding uses just one byte.
+
+         PCRE_UTF8_ERR20
+
+       The two most significant bits of the first byte of a character have the
+       binary  value 0b10 (that is, the most significant bit is 1 and the sec-
+       ond is 0). Such a byte can only validly occur as the second  or  subse-
+       quent byte of a multi-byte character.
+
+         PCRE_UTF8_ERR21
+
+       The  first byte of a character has the value 0xfe or 0xff. These values
+       can never occur in a valid UTF-8 string.
+
+
+EXTRACTING CAPTURED SUBSTRINGS BY NUMBER
+
+       int pcre_copy_substring(const char *subject, int *ovector,
+            int stringcount, int stringnumber, char *buffer,
+            int buffersize);
+
+       int pcre_get_substring(const char *subject, int *ovector,
+            int stringcount, int stringnumber,
+            const char **stringptr);
+
+       int pcre_get_substring_list(const char *subject,
+            int *ovector, int stringcount, const char ***listptr);
+
+       Captured substrings can be  accessed  directly  by  using  the  offsets
+       returned  by  pcre_exec()  in  ovector.  For convenience, the functions
+       pcre_copy_substring(),    pcre_get_substring(),    and    pcre_get_sub-
+       string_list()  are  provided for extracting captured substrings as new,
+       separate, zero-terminated strings. These functions identify  substrings
+       by  number.  The  next section describes functions for extracting named
+       substrings.
+
+       A substring that contains a binary zero is correctly extracted and  has
+       a  further zero added on the end, but the result is not, of course, a C
+       string.  However, you can process such a string  by  referring  to  the
+       length  that  is  returned  by  pcre_copy_substring() and pcre_get_sub-
+       string().  Unfortunately, the interface to pcre_get_substring_list() is
+       not  adequate for handling strings containing binary zeros, because the
+       end of the final string is not independently indicated.
+
+       The first three arguments are the same for all  three  of  these  func-
+       tions:  subject  is  the subject string that has just been successfully
+       matched, ovector is a pointer to the vector of integer offsets that was
+       passed to pcre_exec(), and stringcount is the number of substrings that
+       were captured by the match, including the substring  that  matched  the
+       entire regular expression. This is the value returned by pcre_exec() if
+       it is greater than zero. If pcre_exec() returned zero, indicating  that
+       it  ran out of space in ovector, the value passed as stringcount should
+       be the number of elements in the vector divided by three.
+
+       The functions pcre_copy_substring() and pcre_get_substring() extract  a
+       single  substring,  whose  number  is given as stringnumber. A value of
+       zero extracts the substring that matched the  entire  pattern,  whereas
+       higher  values  extract  the  captured  substrings.  For pcre_copy_sub-
+       string(), the string is placed in buffer,  whose  length  is  given  by
+       buffersize,  while  for  pcre_get_substring()  a new block of memory is
+       obtained via pcre_malloc, and its address is  returned  via  stringptr.
+       The  yield  of  the function is the length of the string, not including
+       the terminating zero, or one of these error codes:
+
+         PCRE_ERROR_NOMEMORY       (-6)
+
+       The buffer was too small for pcre_copy_substring(), or the  attempt  to
+       get memory failed for pcre_get_substring().
+
+         PCRE_ERROR_NOSUBSTRING    (-7)
+
+       There is no substring whose number is stringnumber.
+
+       The  pcre_get_substring_list()  function  extracts  all  available sub-
+       strings and builds a list of pointers to them. All this is  done  in  a
+       single block of memory that is obtained via pcre_malloc. The address of
+       the memory block is returned via listptr, which is also  the  start  of
+       the  list  of  string pointers. The end of the list is marked by a NULL
+       pointer. The yield of the function is zero if all  went  well,  or  the
+       error code
+
+         PCRE_ERROR_NOMEMORY       (-6)
+
+       if the attempt to get the memory block failed.
+
+       When  any of these functions encounter a substring that is unset, which
+       can happen when capturing subpattern number n+1 matches  some  part  of
+       the  subject, but subpattern n has not been used at all, they return an
+       empty string. This can be distinguished from a genuine zero-length sub-
+       string  by inspecting the appropriate offset in ovector, which is nega-
+       tive for unset substrings.
+
+       The two convenience functions pcre_free_substring() and  pcre_free_sub-
+       string_list()  can  be  used  to free the memory returned by a previous
+       call  of  pcre_get_substring()  or  pcre_get_substring_list(),  respec-
+       tively.  They  do  nothing  more  than  call the function pointed to by
+       pcre_free, which of course could be called directly from a  C  program.
+       However,  PCRE is used in some situations where it is linked via a spe-
+       cial  interface  to  another  programming  language  that  cannot   use
+       pcre_free  directly;  it is for these cases that the functions are pro-
+       vided.
+
+
+EXTRACTING CAPTURED SUBSTRINGS BY NAME
+
+       int pcre_get_stringnumber(const pcre *code,
+            const char *name);
+
+       int pcre_copy_named_substring(const pcre *code,
+            const char *subject, int *ovector,
+            int stringcount, const char *stringname,
+            char *buffer, int buffersize);
+
+       int pcre_get_named_substring(const pcre *code,
+            const char *subject, int *ovector,
+            int stringcount, const char *stringname,
+            const char **stringptr);
+
+       To extract a substring by name, you first have to find associated  num-
+       ber.  For example, for this pattern
+
+         (a+)b(?<xxx>\d+)...
+
+       the number of the subpattern called "xxx" is 2. If the name is known to
+       be unique (PCRE_DUPNAMES was not set), you can find the number from the
+       name by calling pcre_get_stringnumber(). The first argument is the com-
+       piled pattern, and the second is the name. The yield of the function is
+       the  subpattern  number,  or PCRE_ERROR_NOSUBSTRING (-7) if there is no
+       subpattern of that name.
+
+       Given the number, you can extract the substring directly, or use one of
+       the functions described in the previous section. For convenience, there
+       are also two functions that do the whole job.
+
+       Most   of   the   arguments    of    pcre_copy_named_substring()    and
+       pcre_get_named_substring()  are  the  same  as  those for the similarly
+       named functions that extract by number. As these are described  in  the
+       previous  section,  they  are not re-described here. There are just two
+       differences:
+
+       First, instead of a substring number, a substring name is  given.  Sec-
+       ond, there is an extra argument, given at the start, which is a pointer
+       to the compiled pattern. This is needed in order to gain access to  the
+       name-to-number translation table.
+
+       These  functions call pcre_get_stringnumber(), and if it succeeds, they
+       then call pcre_copy_substring() or pcre_get_substring(),  as  appropri-
+       ate.  NOTE:  If PCRE_DUPNAMES is set and there are duplicate names, the
+       behaviour may not be what you want (see the next section).
+
+       Warning: If the pattern uses the (?| feature to set up multiple subpat-
+       terns  with  the  same number, as described in the section on duplicate
+       subpattern numbers in the pcrepattern page, you  cannot  use  names  to
+       distinguish  the  different subpatterns, because names are not included
+       in the compiled code. The matching process uses only numbers. For  this
+       reason,  the  use of different names for subpatterns of the same number
+       causes an error at compile time.
+
+
+DUPLICATE SUBPATTERN NAMES
+
+       int pcre_get_stringtable_entries(const pcre *code,
+            const char *name, char **first, char **last);
+
+       When a pattern is compiled with the  PCRE_DUPNAMES  option,  names  for
+       subpatterns  are not required to be unique. (Duplicate names are always
+       allowed for subpatterns with the same number, created by using the  (?|
+       feature.  Indeed,  if  such subpatterns are named, they are required to
+       use the same names.)
+
+       Normally, patterns with duplicate names are such that in any one match,
+       only  one of the named subpatterns participates. An example is shown in
+       the pcrepattern documentation.
+
+       When   duplicates   are   present,   pcre_copy_named_substring()    and
+       pcre_get_named_substring()  return the first substring corresponding to
+       the given name that is set. If  none  are  set,  PCRE_ERROR_NOSUBSTRING
+       (-7)  is  returned;  no  data  is returned. The pcre_get_stringnumber()
+       function returns one of the numbers that are associated with the  name,
+       but it is not defined which it is.
+
+       If  you want to get full details of all captured substrings for a given
+       name, you must use  the  pcre_get_stringtable_entries()  function.  The
+       first argument is the compiled pattern, and the second is the name. The
+       third and fourth are pointers to variables which  are  updated  by  the
+       function. After it has run, they point to the first and last entries in
+       the name-to-number table  for  the  given  name.  The  function  itself
+       returns  the  length  of  each entry, or PCRE_ERROR_NOSUBSTRING (-7) if
+       there are none. The format of the table is described above in the  sec-
+       tion  entitled  Information about a pattern above.  Given all the rele-
+       vant entries for the name, you can extract each of their  numbers,  and
+       hence the captured data, if any.
+
+
+FINDING ALL POSSIBLE MATCHES
+
+       The  traditional  matching  function  uses a similar algorithm to Perl,
+       which stops when it finds the first match, starting at a given point in
+       the  subject.  If you want to find all possible matches, or the longest
+       possible match, consider using the alternative matching  function  (see
+       below)  instead.  If you cannot use the alternative function, but still
+       need to find all possible matches, you can kludge it up by  making  use
+       of the callout facility, which is described in the pcrecallout documen-
+       tation.
+
+       What you have to do is to insert a callout right at the end of the pat-
+       tern.   When your callout function is called, extract and save the cur-
+       rent matched substring. Then return  1,  which  forces  pcre_exec()  to
+       backtrack  and  try other alternatives. Ultimately, when it runs out of
+       matches, pcre_exec() will yield PCRE_ERROR_NOMATCH.
+
+
+OBTAINING AN ESTIMATE OF STACK USAGE
+
+       Matching certain patterns using pcre_exec() can use a  lot  of  process
+       stack,  which  in  certain  environments can be rather limited in size.
+       Some users find it helpful to have an estimate of the amount  of  stack
+       that  is  used  by  pcre_exec(),  to help them set recursion limits, as
+       described in the pcrestack documentation. The estimate that  is  output
+       by pcretest when called with the -m and -C options is obtained by call-
+       ing pcre_exec with the values NULL, NULL, NULL, -999, and -999 for  its
+       first five arguments.
+
+       Normally,  if  its  first  argument  is  NULL,  pcre_exec() immediately
+       returns the negative error code PCRE_ERROR_NULL, but with this  special
+       combination  of  arguments,  it returns instead a negative number whose
+       absolute value is the approximate stack frame size in bytes.  (A  nega-
+       tive  number  is  used so that it is clear that no match has happened.)
+       The value is approximate because in  some  cases,  recursive  calls  to
+       pcre_exec() occur when there are one or two additional variables on the
+       stack.
+
+       If PCRE has been compiled to use the heap  instead  of  the  stack  for
+       recursion,  the  value  returned  is  the  size  of  each block that is
+       obtained from the heap.
+
+
+MATCHING A PATTERN: THE ALTERNATIVE FUNCTION
+
+       int pcre_dfa_exec(const pcre *code, const pcre_extra *extra,
+            const char *subject, int length, int startoffset,
+            int options, int *ovector, int ovecsize,
+            int *workspace, int wscount);
+
+       The function pcre_dfa_exec()  is  called  to  match  a  subject  string
+       against  a  compiled pattern, using a matching algorithm that scans the
+       subject string just once, and does not backtrack.  This  has  different
+       characteristics  to  the  normal  algorithm, and is not compatible with
+       Perl. Some of the features of PCRE patterns are not  supported.  Never-
+       theless,  there are times when this kind of matching can be useful. For
+       a discussion of the two matching algorithms, and  a  list  of  features
+       that  pcre_dfa_exec() does not support, see the pcrematching documenta-
+       tion.
+
+       The arguments for the pcre_dfa_exec() function  are  the  same  as  for
+       pcre_exec(), plus two extras. The ovector argument is used in a differ-
+       ent way, and this is described below. The other  common  arguments  are
+       used  in  the  same way as for pcre_exec(), so their description is not
+       repeated here.
+
+       The two additional arguments provide workspace for  the  function.  The
+       workspace  vector  should  contain at least 20 elements. It is used for
+       keeping  track  of  multiple  paths  through  the  pattern  tree.  More
+       workspace  will  be  needed for patterns and subjects where there are a
+       lot of potential matches.
+
+       Here is an example of a simple call to pcre_dfa_exec():
+
+         int rc;
+         int ovector[10];
+         int wspace[20];
+         rc = pcre_dfa_exec(
+           re,             /* result of pcre_compile() */
+           NULL,           /* we didn't study the pattern */
+           "some string",  /* the subject string */
+           11,             /* the length of the subject string */
+           0,              /* start at offset 0 in the subject */
+           0,              /* default options */
+           ovector,        /* vector of integers for substring information */
+           10,             /* number of elements (NOT size in bytes) */
+           wspace,         /* working space vector */
+           20);            /* number of elements (NOT size in bytes) */
+
+   Option bits for pcre_dfa_exec()
+
+       The unused bits of the options argument  for  pcre_dfa_exec()  must  be
+       zero.  The  only  bits  that  may  be  set are PCRE_ANCHORED, PCRE_NEW-
+       LINE_xxx,        PCRE_NOTBOL,        PCRE_NOTEOL,        PCRE_NOTEMPTY,
+       PCRE_NOTEMPTY_ATSTART,       PCRE_NO_UTF8_CHECK,      PCRE_BSR_ANYCRLF,
+       PCRE_BSR_UNICODE, PCRE_NO_START_OPTIMIZE, PCRE_PARTIAL_HARD,  PCRE_PAR-
+       TIAL_SOFT,  PCRE_DFA_SHORTEST,  and PCRE_DFA_RESTART.  All but the last
+       four of these are  exactly  the  same  as  for  pcre_exec(),  so  their
+       description is not repeated here.
+
+         PCRE_PARTIAL_HARD
+         PCRE_PARTIAL_SOFT
+
+       These  have the same general effect as they do for pcre_exec(), but the
+       details are slightly  different.  When  PCRE_PARTIAL_HARD  is  set  for
+       pcre_dfa_exec(),  it  returns PCRE_ERROR_PARTIAL if the end of the sub-
+       ject is reached and there is still at least  one  matching  possibility
+       that requires additional characters. This happens even if some complete
+       matches have also been found. When PCRE_PARTIAL_SOFT is set, the return
+       code PCRE_ERROR_NOMATCH is converted into PCRE_ERROR_PARTIAL if the end
+       of the subject is reached, there have been  no  complete  matches,  but
+       there  is  still  at least one matching possibility. The portion of the
+       string that was inspected when the longest partial match was  found  is
+       set  as  the  first  matching  string  in  both cases.  There is a more
+       detailed discussion of partial and multi-segment matching,  with  exam-
+       ples, in the pcrepartial documentation.
+
+         PCRE_DFA_SHORTEST
+
+       Setting  the  PCRE_DFA_SHORTEST option causes the matching algorithm to
+       stop as soon as it has found one match. Because of the way the alterna-
+       tive  algorithm  works, this is necessarily the shortest possible match
+       at the first possible matching point in the subject string.
+
+         PCRE_DFA_RESTART
+
+       When pcre_dfa_exec() returns a partial match, it is possible to call it
+       again,  with  additional  subject characters, and have it continue with
+       the same match. The PCRE_DFA_RESTART option requests this action;  when
+       it  is  set,  the workspace and wscount options must reference the same
+       vector as before because data about the match so far is  left  in  them
+       after a partial match. There is more discussion of this facility in the
+       pcrepartial documentation.
+
+   Successful returns from pcre_dfa_exec()
+
+       When pcre_dfa_exec() succeeds, it may have matched more than  one  sub-
+       string in the subject. Note, however, that all the matches from one run
+       of the function start at the same point in  the  subject.  The  shorter
+       matches  are all initial substrings of the longer matches. For example,
+       if the pattern
+
+         <.*>
+
+       is matched against the string
+
+         This is <something> <something else> <something further> no more
+
+       the three matched strings are
+
+         <something>
+         <something> <something else>
+         <something> <something else> <something further>
+
+       On success, the yield of the function is a number  greater  than  zero,
+       which  is  the  number of matched substrings. The substrings themselves
+       are returned in ovector. Each string uses two elements;  the  first  is
+       the  offset  to  the start, and the second is the offset to the end. In
+       fact, all the strings have the same start  offset.  (Space  could  have
+       been  saved by giving this only once, but it was decided to retain some
+       compatibility with the way pcre_exec() returns data,  even  though  the
+       meaning of the strings is different.)
+
+       The strings are returned in reverse order of length; that is, the long-
+       est matching string is given first. If there were too many  matches  to
+       fit  into ovector, the yield of the function is zero, and the vector is
+       filled with the longest matches.  Unlike  pcre_exec(),  pcre_dfa_exec()
+       can use the entire ovector for returning matched strings.
+
+   Error returns from pcre_dfa_exec()
+
+       The  pcre_dfa_exec()  function returns a negative number when it fails.
+       Many of the errors are the same  as  for  pcre_exec(),  and  these  are
+       described  above.   There are in addition the following errors that are
+       specific to pcre_dfa_exec():
+
+         PCRE_ERROR_DFA_UITEM      (-16)
+
+       This return is given if pcre_dfa_exec() encounters an item in the  pat-
+       tern  that  it  does not support, for instance, the use of \C or a back
+       reference.
+
+         PCRE_ERROR_DFA_UCOND      (-17)
+
+       This return is given if pcre_dfa_exec()  encounters  a  condition  item
+       that  uses  a back reference for the condition, or a test for recursion
+       in a specific group. These are not supported.
+
+         PCRE_ERROR_DFA_UMLIMIT    (-18)
+
+       This return is given if pcre_dfa_exec() is called with an  extra  block
+       that  contains  a  setting  of the match_limit or match_limit_recursion
+       fields. This is not supported (these fields  are  meaningless  for  DFA
+       matching).
+
+         PCRE_ERROR_DFA_WSSIZE     (-19)
+
+       This  return  is  given  if  pcre_dfa_exec()  runs  out of space in the
+       workspace vector.
+
+         PCRE_ERROR_DFA_RECURSE    (-20)
+
+       When a recursive subpattern is processed, the matching  function  calls
+       itself  recursively,  using  private vectors for ovector and workspace.
+       This error is given if the output vector  is  not  large  enough.  This
+       should be extremely rare, as a vector of size 1000 is used.
+
+         PCRE_ERROR_DFA_BADRESTART (-30)
+
+       When  pcre_dfa_exec()  is called with the PCRE_DFA_RESTART option, some
+       plausibility checks are made on the contents of  the  workspace,  which
+       should  contain  data about the previous partial match. If any of these
+       checks fail, this error is given.
+
+
+SEE ALSO
+
+       pcre16(3),  pcrebuild(3),  pcrecallout(3),  pcrecpp(3)(3),   pcrematch-
+       ing(3), pcrepartial(3), pcreposix(3), pcreprecompile(3), pcresample(3),
+       pcrestack(3).
+
+
+AUTHOR
+
+       Philip Hazel
+       University Computing Service
+       Cambridge CB2 3QH, England.
+
+
+REVISION
+
+       Last updated: 17 June 2012
+       Copyright (c) 1997-2012 University of Cambridge.
+------------------------------------------------------------------------------
+
+
+PCRECALLOUT(3)                                                  PCRECALLOUT(3)
+
+
+NAME
+       PCRE - Perl-compatible regular expressions
+
+
+PCRE CALLOUTS
+
+       int (*pcre_callout)(pcre_callout_block *);
+
+       int (*pcre16_callout)(pcre16_callout_block *);
+
+       PCRE provides a feature called "callout", which is a means of temporar-
+       ily passing control to the caller of PCRE  in  the  middle  of  pattern
+       matching.  The  caller of PCRE provides an external function by putting
+       its entry point in the global variable pcre_callout (pcre16_callout for
+       the  16-bit  library).  By  default, this variable contains NULL, which
+       disables all calling out.
+
+       Within a regular expression, (?C) indicates the  points  at  which  the
+       external  function  is  to  be  called. Different callout points can be
+       identified by putting a number less than 256 after the  letter  C.  The
+       default  value  is  zero.   For  example,  this pattern has two callout
+       points:
+
+         (?C1)abc(?C2)def
+
+       If the PCRE_AUTO_CALLOUT option bit is set when a pattern is  compiled,
+       PCRE  automatically  inserts callouts, all with number 255, before each
+       item in the pattern. For example, if PCRE_AUTO_CALLOUT is used with the
+       pattern
+
+         A(\d{2}|--)
+
+       it is processed as if it were
+
+       (?C255)A(?C255)((?C255)\d{2}(?C255)|(?C255)-(?C255)-(?C255))(?C255)
+
+       Notice  that  there  is a callout before and after each parenthesis and
+       alternation bar. Automatic  callouts  can  be  used  for  tracking  the
+       progress  of  pattern matching. The pcretest command has an option that
+       sets automatic callouts; when it is used, the output indicates how  the
+       pattern  is  matched. This is useful information when you are trying to
+       optimize the performance of a particular pattern.
+
+       The use of callouts in a pattern makes it ineligible  for  optimization
+       by  the  just-in-time  compiler.  Studying  such  a  pattern  with  the
+       PCRE_STUDY_JIT_COMPILE option always fails.
+
+
+MISSING CALLOUTS
+
+       You should be aware that, because of  optimizations  in  the  way  PCRE
+       matches  patterns  by  default,  callouts  sometimes do not happen. For
+       example, if the pattern is
+
+         ab(?C4)cd
+
+       PCRE knows that any matching string must contain the letter "d". If the
+       subject  string  is "abyz", the lack of "d" means that matching doesn't
+       ever start, and the callout is never  reached.  However,  with  "abyd",
+       though the result is still no match, the callout is obeyed.
+
+       If  the pattern is studied, PCRE knows the minimum length of a matching
+       string, and will immediately give a "no match" return without  actually
+       running  a  match if the subject is not long enough, or, for unanchored
+       patterns, if it has been scanned far enough.
+
+       You can disable these optimizations by passing the  PCRE_NO_START_OPTI-
+       MIZE  option  to the matching function, or by starting the pattern with
+       (*NO_START_OPT). This slows down the matching process, but does  ensure
+       that callouts such as the example above are obeyed.
+
+
+THE CALLOUT INTERFACE
+
+       During  matching, when PCRE reaches a callout point, the external func-
+       tion defined by pcre_callout or pcre16_callout  is  called  (if  it  is
+       set).   This applies to both normal and DFA matching. The only argument
+       to the callout function is a pointer to a pcre_callout or  pcre16_call-
+       out block.  These structures contains the following fields:
+
+         int           version;
+         int           callout_number;
+         int          *offset_vector;
+         const char   *subject;           (8-bit version)
+         PCRE_SPTR16   subject;           (16-bit version)
+         int           subject_length;
+         int           start_match;
+         int           current_position;
+         int           capture_top;
+         int           capture_last;
+         void         *callout_data;
+         int           pattern_position;
+         int           next_item_length;
+         const unsigned char *mark;       (8-bit version)
+         const PCRE_UCHAR16  *mark;       (16-bit version)
+
+       The  version  field  is an integer containing the version number of the
+       block format. The initial version was 0; the current version is 2.  The
+       version  number  will  change  again in future if additional fields are
+       added, but the intention is never to remove any of the existing fields.
+
+       The callout_number field contains the number of the  callout,  as  com-
+       piled  into  the pattern (that is, the number after ?C for manual call-
+       outs, and 255 for automatically generated callouts).
+
+       The offset_vector field is a pointer to the vector of offsets that  was
+       passed  by  the  caller  to  the matching function. When pcre_exec() or
+       pcre16_exec() is used, the contents  can  be  inspected,  in  order  to
+       extract  substrings  that  have been matched so far, in the same way as
+       for extracting substrings after a match  has  completed.  For  the  DFA
+       matching functions, this field is not useful.
+
+       The subject and subject_length fields contain copies of the values that
+       were passed to the matching function.
+
+       The start_match field normally contains the offset within  the  subject
+       at  which  the  current  match  attempt started. However, if the escape
+       sequence \K has been encountered, this value is changed to reflect  the
+       modified  starting  point.  If the pattern is not anchored, the callout
+       function may be called several times from the same point in the pattern
+       for different starting points in the subject.
+
+       The  current_position  field  contains the offset within the subject of
+       the current match pointer.
+
+       When the pcre_exec() or pcre16_exec() is used,  the  capture_top  field
+       contains one more than the number of the highest numbered captured sub-
+       string so far. If no substrings have been captured, the value  of  cap-
+       ture_top  is  one.  This  is always the case when the DFA functions are
+       used, because they do not support captured substrings.
+
+       The capture_last field contains the number of the  most  recently  cap-
+       tured  substring. If no substrings have been captured, its value is -1.
+       This is always the case for the DFA matching functions.
+
+       The callout_data field contains a value that is passed  to  a  matching
+       function  specifically so that it can be passed back in callouts. It is
+       passed in the callout_data field of a pcre_extra or  pcre16_extra  data
+       structure.  If  no such data was passed, the value of callout_data in a
+       callout block is NULL. There is a description of the pcre_extra  struc-
+       ture in the pcreapi documentation.
+
+       The  pattern_position  field  is  present from version 1 of the callout
+       structure. It contains the offset to the next item to be matched in the
+       pattern string.
+
+       The  next_item_length  field  is  present from version 1 of the callout
+       structure. It contains the length of the next item to be matched in the
+       pattern  string.  When  the callout immediately precedes an alternation
+       bar, a closing parenthesis, or the end of the pattern,  the  length  is
+       zero.  When  the callout precedes an opening parenthesis, the length is
+       that of the entire subpattern.
+
+       The pattern_position and next_item_length fields are intended  to  help
+       in  distinguishing between different automatic callouts, which all have
+       the same callout number. However, they are set for all callouts.
+
+       The mark field is present from version 2 of the callout  structure.  In
+       callouts from pcre_exec() or pcre16_exec() it contains a pointer to the
+       zero-terminated name of the most recently passed (*MARK), (*PRUNE),  or
+       (*THEN)  item  in the match, or NULL if no such items have been passed.
+       Instances of (*PRUNE) or (*THEN) without a name  do  not  obliterate  a
+       previous  (*MARK).  In  callouts  from  the DFA matching functions this
+       field always contains NULL.
+
+
+RETURN VALUES
+
+       The external callout function returns an integer to PCRE. If the  value
+       is  zero,  matching  proceeds  as  normal. If the value is greater than
+       zero, matching fails at the current point, but  the  testing  of  other
+       matching possibilities goes ahead, just as if a lookahead assertion had
+       failed. If the value is less than zero, the  match  is  abandoned,  the
+       matching function returns the negative value.
+
+       Negative   values   should   normally   be   chosen  from  the  set  of
+       PCRE_ERROR_xxx values. In particular, PCRE_ERROR_NOMATCH forces a stan-
+       dard  "no  match"  failure.   The  error  number  PCRE_ERROR_CALLOUT is
+       reserved for use by callout functions; it will never be  used  by  PCRE
+       itself.
+
+
+AUTHOR
+
+       Philip Hazel
+       University Computing Service
+       Cambridge CB2 3QH, England.
+
+
+REVISION
+
+       Last updated: 08 Janurary 2012
+       Copyright (c) 1997-2012 University of Cambridge.
+------------------------------------------------------------------------------
+
+
+PCRECOMPAT(3)                                                    PCRECOMPAT(3)
+
+
+NAME
+       PCRE - Perl-compatible regular expressions
+
+
+DIFFERENCES BETWEEN PCRE AND PERL
+
+       This  document describes the differences in the ways that PCRE and Perl
+       handle regular expressions. The differences  described  here  are  with
+       respect to Perl versions 5.10 and above.
+
+       1. PCRE has only a subset of Perl's Unicode support. Details of what it
+       does have are given in the pcreunicode page.
+
+       2. PCRE allows repeat quantifiers only on parenthesized assertions, but
+       they  do  not mean what you might think. For example, (?!a){3} does not
+       assert that the next three characters are not "a". It just asserts that
+       the next character is not "a" three times (in principle: PCRE optimizes
+       this to run the assertion just once). Perl allows repeat quantifiers on
+       other assertions such as \b, but these do not seem to have any use.
+
+       3.  Capturing  subpatterns  that occur inside negative lookahead asser-
+       tions are counted, but their entries in the offsets  vector  are  never
+       set.  Perl sets its numerical variables from any such patterns that are
+       matched before the assertion fails to match something (thereby succeed-
+       ing),  but  only  if the negative lookahead assertion contains just one
+       branch.
+
+       4. Though binary zero characters are supported in the  subject  string,
+       they are not allowed in a pattern string because it is passed as a nor-
+       mal C string, terminated by zero. The escape sequence \0 can be used in
+       the pattern to represent a binary zero.
+
+       5.  The  following Perl escape sequences are not supported: \l, \u, \L,
+       \U, and \N when followed by a character name or Unicode value.  (\N  on
+       its own, matching a non-newline character, is supported.) In fact these
+       are implemented by Perl's general string-handling and are not  part  of
+       its  pattern  matching engine. If any of these are encountered by PCRE,
+       an error is generated by default. However, if the  PCRE_JAVASCRIPT_COM-
+       PAT  option  is set, \U and \u are interpreted as JavaScript interprets
+       them.
+
+       6. The Perl escape sequences \p, \P, and \X are supported only if  PCRE
+       is  built  with Unicode character property support. The properties that
+       can be tested with \p and \P are limited to the general category  prop-
+       erties  such  as  Lu and Nd, script names such as Greek or Han, and the
+       derived properties Any and L&. PCRE does  support  the  Cs  (surrogate)
+       property,  which  Perl  does  not; the Perl documentation says "Because
+       Perl hides the need for the user to understand the internal representa-
+       tion  of Unicode characters, there is no need to implement the somewhat
+       messy concept of surrogates."
+
+       7. PCRE implements a simpler version of \X than Perl, which changed  to
+       make  \X  match what Unicode calls an "extended grapheme cluster". This
+       is more complicated than an extended Unicode sequence,  which  is  what
+       PCRE matches.
+
+       8. PCRE does support the \Q...\E escape for quoting substrings. Charac-
+       ters in between are treated as literals.  This  is  slightly  different
+       from  Perl  in  that  $  and  @ are also handled as literals inside the
+       quotes. In Perl, they cause variable interpolation (but of course  PCRE
+       does not have variables). Note the following examples:
+
+           Pattern            PCRE matches      Perl matches
+
+           \Qabc$xyz\E        abc$xyz           abc followed by the
+                                                  contents of $xyz
+           \Qabc\$xyz\E       abc\$xyz          abc\$xyz
+           \Qabc\E\$\Qxyz\E   abc$xyz           abc$xyz
+
+       The  \Q...\E  sequence  is recognized both inside and outside character
+       classes.
+
+       9. Fairly obviously, PCRE does not support the (?{code}) and (??{code})
+       constructions.  However,  there is support for recursive patterns. This
+       is not available in Perl 5.8, but it is in Perl 5.10.  Also,  the  PCRE
+       "callout"  feature allows an external function to be called during pat-
+       tern matching. See the pcrecallout documentation for details.
+
+       10. Subpatterns that are called as subroutines (whether or  not  recur-
+       sively)  are  always  treated  as  atomic  groups in PCRE. This is like
+       Python, but unlike Perl.  Captured values that are set outside  a  sub-
+       routine  call  can  be  reference from inside in PCRE, but not in Perl.
+       There is a discussion that explains these differences in more detail in
+       the section on recursion differences from Perl in the pcrepattern page.
+
+       11.  If  any of the backtracking control verbs are used in an assertion
+       or in a subpattern that is called  as  a  subroutine  (whether  or  not
+       recursively),  their effect is confined to that subpattern; it does not
+       extend to the surrounding pattern. This is not always the case in Perl.
+       In  particular,  if  (*THEN)  is present in a group that is called as a
+       subroutine, its action is limited to that group, even if the group does
+       not  contain any | characters. There is one exception to this: the name
+       from a *(MARK), (*PRUNE), or (*THEN) that is encountered in a  success-
+       ful  positive  assertion  is passed back when a match succeeds (compare
+       capturing parentheses in assertions). Note that  such  subpatterns  are
+       processed as anchored at the point where they are tested.
+
+       12.  There are some differences that are concerned with the settings of
+       captured strings when part of  a  pattern  is  repeated.  For  example,
+       matching  "aba"  against  the  pattern  /^(a(b)?)+$/  in Perl leaves $2
+       unset, but in PCRE it is set to "b".
+
+       13. PCRE's handling of duplicate subpattern numbers and duplicate  sub-
+       pattern names is not as general as Perl's. This is a consequence of the
+       fact the PCRE works internally just with numbers, using an external ta-
+       ble  to  translate  between numbers and names. In particular, a pattern
+       such as (?|(?<a>A)|(?<b)B), where the two  capturing  parentheses  have
+       the  same  number  but different names, is not supported, and causes an
+       error at compile time. If it were allowed, it would not be possible  to
+       distinguish  which  parentheses matched, because both names map to cap-
+       turing subpattern number 1. To avoid this confusing situation, an error
+       is given at compile time.
+
+       14.  Perl  recognizes  comments  in some places that PCRE does not, for
+       example, between the ( and ? at the start of a subpattern.  If  the  /x
+       modifier is set, Perl allows white space between ( and ? but PCRE never
+       does, even if the PCRE_EXTENDED option is set.
+
+       15. PCRE provides some extensions to the Perl regular expression facil-
+       ities.   Perl  5.10  includes new features that are not in earlier ver-
+       sions of Perl, some of which (such as named parentheses) have  been  in
+       PCRE for some time. This list is with respect to Perl 5.10:
+
+       (a)  Although  lookbehind  assertions  in  PCRE must match fixed length
+       strings, each alternative branch of a lookbehind assertion can match  a
+       different  length  of  string.  Perl requires them all to have the same
+       length.
+
+       (b) If PCRE_DOLLAR_ENDONLY is set and PCRE_MULTILINE is not set, the  $
+       meta-character matches only at the very end of the string.
+
+       (c) If PCRE_EXTRA is set, a backslash followed by a letter with no spe-
+       cial meaning is faulted. Otherwise, like Perl, the backslash is quietly
+       ignored.  (Perl can be made to issue a warning.)
+
+       (d)  If  PCRE_UNGREEDY is set, the greediness of the repetition quanti-
+       fiers is inverted, that is, by default they are not greedy, but if fol-
+       lowed by a question mark they are.
+
+       (e) PCRE_ANCHORED can be used at matching time to force a pattern to be
+       tried only at the first matching position in the subject string.
+
+       (f) The PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, PCRE_NOTEMPTY_ATSTART,
+       and  PCRE_NO_AUTO_CAPTURE  options for pcre_exec() have no Perl equiva-
+       lents.
+
+       (g) The \R escape sequence can be restricted to match only CR,  LF,  or
+       CRLF by the PCRE_BSR_ANYCRLF option.
+
+       (h) The callout facility is PCRE-specific.
+
+       (i) The partial matching facility is PCRE-specific.
+
+       (j) Patterns compiled by PCRE can be saved and re-used at a later time,
+       even on different hosts that have the other endianness.  However,  this
+       does not apply to optimized data created by the just-in-time compiler.
+
+       (k)   The   alternative   matching   functions   (pcre_dfa_exec()   and
+       pcre16_dfa_exec()) match in a different way and are  not  Perl-compati-
+       ble.
+
+       (l)  PCRE  recognizes some special sequences such as (*CR) at the start
+       of a pattern that set overall options that cannot be changed within the
+       pattern.
+
+
+AUTHOR
+
+       Philip Hazel
+       University Computing Service
+       Cambridge CB2 3QH, England.
+
+
+REVISION
+
+       Last updated: 01 June 2012
+       Copyright (c) 1997-2012 University of Cambridge.
+------------------------------------------------------------------------------
+
+
+PCREPATTERN(3)                                                  PCREPATTERN(3)
+
+
+NAME
+       PCRE - Perl-compatible regular expressions
+
+
+PCRE REGULAR EXPRESSION DETAILS
+
+       The  syntax and semantics of the regular expressions that are supported
+       by PCRE are described in detail below. There is a quick-reference  syn-
+       tax summary in the pcresyntax page. PCRE tries to match Perl syntax and
+       semantics as closely as it can. PCRE  also  supports  some  alternative
+       regular  expression  syntax (which does not conflict with the Perl syn-
+       tax) in order to provide some compatibility with regular expressions in
+       Python, .NET, and Oniguruma.
+
+       Perl's  regular expressions are described in its own documentation, and
+       regular expressions in general are covered in a number of  books,  some
+       of  which  have  copious  examples. Jeffrey Friedl's "Mastering Regular
+       Expressions", published by  O'Reilly,  covers  regular  expressions  in
+       great  detail.  This  description  of  PCRE's  regular  expressions  is
+       intended as reference material.
+
+       The original operation of PCRE was on strings of  one-byte  characters.
+       However,  there  is  now also support for UTF-8 strings in the original
+       library, and a second library that supports 16-bit and UTF-16 character
+       strings. To use these features, PCRE must be built to include appropri-
+       ate support. When using UTF strings you must either call the  compiling
+       function  with  the PCRE_UTF8 or PCRE_UTF16 option, or the pattern must
+       start with one of these special sequences:
+
+         (*UTF8)
+         (*UTF16)
+
+       Starting a pattern with such a sequence is equivalent  to  setting  the
+       relevant option. This feature is not Perl-compatible. How setting a UTF
+       mode affects pattern matching is mentioned  in  several  places  below.
+       There is also a summary of features in the pcreunicode page.
+
+       Another  special  sequence that may appear at the start of a pattern or
+       in combination with (*UTF8) or (*UTF16) is:
+
+         (*UCP)
+
+       This has the same effect as setting  the  PCRE_UCP  option:  it  causes
+       sequences  such  as  \d  and  \w to use Unicode properties to determine
+       character types, instead of recognizing only characters with codes less
+       than 128 via a lookup table.
+
+       If  a  pattern  starts  with (*NO_START_OPT), it has the same effect as
+       setting the PCRE_NO_START_OPTIMIZE option either at compile or matching
+       time. There are also some more of these special sequences that are con-
+       cerned with the handling of newlines; they are described below.
+
+       The remainder of this document discusses the  patterns  that  are  sup-
+       ported  by  PCRE  when  one  its  main  matching functions, pcre_exec()
+       (8-bit) or pcre16_exec() (16-bit), is used. PCRE also  has  alternative
+       matching  functions, pcre_dfa_exec() and pcre16_dfa_exec(), which match
+       using a different algorithm that is not Perl-compatible.  Some  of  the
+       features  discussed  below are not available when DFA matching is used.
+       The advantages and disadvantages of the alternative functions, and  how
+       they  differ from the normal functions, are discussed in the pcrematch-
+       ing page.
+
+
+NEWLINE CONVENTIONS
+
+       PCRE supports five different conventions for indicating line breaks  in
+       strings:  a  single  CR (carriage return) character, a single LF (line-
+       feed) character, the two-character sequence CRLF, any of the three pre-
+       ceding,  or  any Unicode newline sequence. The pcreapi page has further
+       discussion about newlines, and shows how to set the newline  convention
+       in the options arguments for the compiling and matching functions.
+
+       It  is also possible to specify a newline convention by starting a pat-
+       tern string with one of the following five sequences:
+
+         (*CR)        carriage return
+         (*LF)        linefeed
+         (*CRLF)      carriage return, followed by linefeed
+         (*ANYCRLF)   any of the three above
+         (*ANY)       all Unicode newline sequences
+
+       These override the default and the options given to the compiling func-
+       tion.  For  example,  on  a Unix system where LF is the default newline
+       sequence, the pattern
+
+         (*CR)a.b
+
+       changes the convention to CR. That pattern matches "a\nb" because LF is
+       no  longer  a  newline. Note that these special settings, which are not
+       Perl-compatible, are recognized only at the very start  of  a  pattern,
+       and  that  they  must  be  in  upper  case. If more than one of them is
+       present, the last one is used.
+
+       The newline convention affects the interpretation of the dot  metachar-
+       acter  when  PCRE_DOTALL is not set, and also the behaviour of \N. How-
+       ever, it does not affect  what  the  \R  escape  sequence  matches.  By
+       default,  this is any Unicode newline sequence, for Perl compatibility.
+       However, this can be changed; see the description of \R in the  section
+       entitled  "Newline sequences" below. A change of \R setting can be com-
+       bined with a change of newline convention.
+
+
+CHARACTERS AND METACHARACTERS
+
+       A regular expression is a pattern that is  matched  against  a  subject
+       string  from  left  to right. Most characters stand for themselves in a
+       pattern, and match the corresponding characters in the  subject.  As  a
+       trivial example, the pattern
+
+         The quick brown fox
+
+       matches a portion of a subject string that is identical to itself. When
+       caseless matching is specified (the PCRE_CASELESS option), letters  are
+       matched  independently  of case. In a UTF mode, PCRE always understands
+       the concept of case for characters whose values are less than  128,  so
+       caseless  matching  is always possible. For characters with higher val-
+       ues, the concept of case is supported if PCRE is compiled with  Unicode
+       property  support,  but  not  otherwise.   If  you want to use caseless
+       matching for characters 128 and above, you must  ensure  that  PCRE  is
+       compiled with Unicode property support as well as with UTF support.
+
+       The  power  of  regular  expressions  comes from the ability to include
+       alternatives and repetitions in the pattern. These are encoded  in  the
+       pattern by the use of metacharacters, which do not stand for themselves
+       but instead are interpreted in some special way.
+
+       There are two different sets of metacharacters: those that  are  recog-
+       nized  anywhere in the pattern except within square brackets, and those
+       that are recognized within square brackets.  Outside  square  brackets,
+       the metacharacters are as follows:
+
+         \      general escape character with several uses
+         ^      assert start of string (or line, in multiline mode)
+         $      assert end of string (or line, in multiline mode)
+         .      match any character except newline (by default)
+         [      start character class definition
+         |      start of alternative branch
+         (      start subpattern
+         )      end subpattern
+         ?      extends the meaning of (
+                also 0 or 1 quantifier
+                also quantifier minimizer
+         *      0 or more quantifier
+         +      1 or more quantifier
+                also "possessive quantifier"
+         {      start min/max quantifier
+
+       Part  of  a  pattern  that is in square brackets is called a "character
+       class". In a character class the only metacharacters are:
+
+         \      general escape character
+         ^      negate the class, but only if the first character
+         -      indicates character range
+         [      POSIX character class (only if followed by POSIX
+                  syntax)
+         ]      terminates the character class
+
+       The following sections describe the use of each of the metacharacters.
+
+
+BACKSLASH
+
+       The backslash character has several uses. Firstly, if it is followed by
+       a character that is not a number or a letter, it takes away any special
+       meaning that character may have. This use of  backslash  as  an  escape
+       character applies both inside and outside character classes.
+
+       For  example,  if  you want to match a * character, you write \* in the
+       pattern.  This escaping action applies whether  or  not  the  following
+       character  would  otherwise be interpreted as a metacharacter, so it is
+       always safe to precede a non-alphanumeric  with  backslash  to  specify
+       that  it stands for itself. In particular, if you want to match a back-
+       slash, you write \\.
+
+       In a UTF mode, only ASCII numbers and letters have any special  meaning
+       after  a  backslash.  All  other characters (in particular, those whose
+       codepoints are greater than 127) are treated as literals.
+
+       If a pattern is compiled with the PCRE_EXTENDED option, white space  in
+       the  pattern (other than in a character class) and characters between a
+       # outside a character class and the next newline are ignored. An escap-
+       ing  backslash  can  be used to include a white space or # character as
+       part of the pattern.
+
+       If you want to remove the special meaning from a  sequence  of  charac-
+       ters,  you can do so by putting them between \Q and \E. This is differ-
+       ent from Perl in that $ and  @  are  handled  as  literals  in  \Q...\E
+       sequences  in  PCRE, whereas in Perl, $ and @ cause variable interpola-
+       tion. Note the following examples:
+
+         Pattern            PCRE matches   Perl matches
+
+         \Qabc$xyz\E        abc$xyz        abc followed by the
+                                             contents of $xyz
+         \Qabc\$xyz\E       abc\$xyz       abc\$xyz
+         \Qabc\E\$\Qxyz\E   abc$xyz        abc$xyz
+
+       The \Q...\E sequence is recognized both inside  and  outside  character
+       classes.   An  isolated \E that is not preceded by \Q is ignored. If \Q
+       is not followed by \E later in the pattern, the literal  interpretation
+       continues  to  the  end  of  the pattern (that is, \E is assumed at the
+       end). If the isolated \Q is inside a character class,  this  causes  an
+       error, because the character class is not terminated.
+
+   Non-printing characters
+
+       A second use of backslash provides a way of encoding non-printing char-
+       acters in patterns in a visible manner. There is no restriction on  the
+       appearance  of non-printing characters, apart from the binary zero that
+       terminates a pattern, but when a pattern  is  being  prepared  by  text
+       editing,  it  is  often  easier  to  use  one  of  the following escape
+       sequences than the binary character it represents:
+
+         \a        alarm, that is, the BEL character (hex 07)
+         \cx       "control-x", where x is any ASCII character
+         \e        escape (hex 1B)
+         \f        form feed (hex 0C)
+         \n        linefeed (hex 0A)
+         \r        carriage return (hex 0D)
+         \t        tab (hex 09)
+         \ddd      character with octal code ddd, or back reference
+         \xhh      character with hex code hh
+         \x{hhh..} character with hex code hhh.. (non-JavaScript mode)
+         \uhhhh    character with hex code hhhh (JavaScript mode only)
+
+       The precise effect of \cx is as follows: if x is a lower  case  letter,
+       it  is converted to upper case. Then bit 6 of the character (hex 40) is
+       inverted.  Thus \cz becomes hex 1A (z is 7A), but \c{ becomes hex 3B ({
+       is  7B),  while  \c; becomes hex 7B (; is 3B). If the byte following \c
+       has a value greater than 127, a compile-time error occurs.  This  locks
+       out non-ASCII characters in all modes. (When PCRE is compiled in EBCDIC
+       mode, all byte values are valid. A lower case letter  is  converted  to
+       upper case, and then the 0xc0 bits are flipped.)
+
+       By  default,  after  \x,  from  zero to two hexadecimal digits are read
+       (letters can be in upper or lower case). Any number of hexadecimal dig-
+       its may appear between \x{ and }, but the character code is constrained
+       as follows:
+
+         8-bit non-UTF mode    less than 0x100
+         8-bit UTF-8 mode      less than 0x10ffff and a valid codepoint
+         16-bit non-UTF mode   less than 0x10000
+         16-bit UTF-16 mode    less than 0x10ffff and a valid codepoint
+
+       Invalid Unicode codepoints are the range  0xd800  to  0xdfff  (the  so-
+       called "surrogate" codepoints).
+
+       If  characters  other than hexadecimal digits appear between \x{ and },
+       or if there is no terminating }, this form of escape is not recognized.
+       Instead,  the  initial  \x  will  be interpreted as a basic hexadecimal
+       escape, with no following digits, giving a  character  whose  value  is
+       zero.
+
+       If  the  PCRE_JAVASCRIPT_COMPAT option is set, the interpretation of \x
+       is as just described only when it is followed by two  hexadecimal  dig-
+       its.   Otherwise,  it  matches  a  literal "x" character. In JavaScript
+       mode, support for code points greater than 256 is provided by \u, which
+       must  be  followed  by  four hexadecimal digits; otherwise it matches a
+       literal "u" character.  Character codes specified by \u  in  JavaScript
+       mode  are  constrained in the same was as those specified by \x in non-
+       JavaScript mode.
+
+       Characters whose value is less than 256 can be defined by either of the
+       two  syntaxes for \x (or by \u in JavaScript mode). There is no differ-
+       ence in the way they are handled. For example, \xdc is exactly the same
+       as \x{dc} (or \u00dc in JavaScript mode).
+
+       After  \0  up  to two further octal digits are read. If there are fewer
+       than two digits, just  those  that  are  present  are  used.  Thus  the
+       sequence \0\x\07 specifies two binary zeros followed by a BEL character
+       (code value 7). Make sure you supply two digits after the initial  zero
+       if the pattern character that follows is itself an octal digit.
+
+       The handling of a backslash followed by a digit other than 0 is compli-
+       cated.  Outside a character class, PCRE reads it and any following dig-
+       its  as  a  decimal  number. If the number is less than 10, or if there
+       have been at least that many previous capturing left parentheses in the
+       expression,  the  entire  sequence  is  taken  as  a  back reference. A
+       description of how this works is given later, following the  discussion
+       of parenthesized subpatterns.
+
+       Inside  a  character  class, or if the decimal number is greater than 9
+       and there have not been that many capturing subpatterns, PCRE  re-reads
+       up to three octal digits following the backslash, and uses them to gen-
+       erate a data character. Any subsequent digits stand for themselves. The
+       value  of  the  character  is constrained in the same way as characters
+       specified in hexadecimal.  For example:
+
+         \040   is another way of writing a space
+         \40    is the same, provided there are fewer than 40
+                   previous capturing subpatterns
+         \7     is always a back reference
+         \11    might be a back reference, or another way of
+                   writing a tab
+         \011   is always a tab
+         \0113  is a tab followed by the character "3"
+         \113   might be a back reference, otherwise the
+                   character with octal code 113
+         \377   might be a back reference, otherwise
+                   the value 255 (decimal)
+         \81    is either a back reference, or a binary zero
+                   followed by the two characters "8" and "1"
+
+       Note that octal values of 100 or greater must not be  introduced  by  a
+       leading zero, because no more than three octal digits are ever read.
+
+       All the sequences that define a single character value can be used both
+       inside and outside character classes. In addition, inside  a  character
+       class, \b is interpreted as the backspace character (hex 08).
+
+       \N  is not allowed in a character class. \B, \R, and \X are not special
+       inside a character class. Like  other  unrecognized  escape  sequences,
+       they  are  treated  as  the  literal  characters  "B",  "R", and "X" by
+       default, but cause an error if the PCRE_EXTRA option is set. Outside  a
+       character class, these sequences have different meanings.
+
+   Unsupported escape sequences
+
+       In  Perl, the sequences \l, \L, \u, and \U are recognized by its string
+       handler and used  to  modify  the  case  of  following  characters.  By
+       default,  PCRE does not support these escape sequences. However, if the
+       PCRE_JAVASCRIPT_COMPAT option is set, \U matches a "U"  character,  and
+       \u can be used to define a character by code point, as described in the
+       previous section.
+
+   Absolute and relative back references
+
+       The sequence \g followed by an unsigned or a negative  number,  option-
+       ally  enclosed  in braces, is an absolute or relative back reference. A
+       named back reference can be coded as \g{name}. Back references are dis-
+       cussed later, following the discussion of parenthesized subpatterns.
+
+   Absolute and relative subroutine calls
+
+       For  compatibility with Oniguruma, the non-Perl syntax \g followed by a
+       name or a number enclosed either in angle brackets or single quotes, is
+       an  alternative  syntax for referencing a subpattern as a "subroutine".
+       Details are discussed later.   Note  that  \g{...}  (Perl  syntax)  and
+       \g<...>  (Oniguruma  syntax)  are  not synonymous. The former is a back
+       reference; the latter is a subroutine call.
+
+   Generic character types
+
+       Another use of backslash is for specifying generic character types:
+
+         \d     any decimal digit
+         \D     any character that is not a decimal digit
+         \h     any horizontal white space character
+         \H     any character that is not a horizontal white space character
+         \s     any white space character
+         \S     any character that is not a white space character
+         \v     any vertical white space character
+         \V     any character that is not a vertical white space character
+         \w     any "word" character
+         \W     any "non-word" character
+
+       There is also the single sequence \N, which matches a non-newline char-
+       acter.   This  is the same as the "." metacharacter when PCRE_DOTALL is
+       not set. Perl also uses \N to match characters by name; PCRE  does  not
+       support this.
+
+       Each  pair of lower and upper case escape sequences partitions the com-
+       plete set of characters into two disjoint  sets.  Any  given  character
+       matches  one, and only one, of each pair. The sequences can appear both
+       inside and outside character classes. They each match one character  of
+       the  appropriate  type.  If the current matching point is at the end of
+       the subject string, all of them fail, because there is no character  to
+       match.
+
+       For  compatibility  with Perl, \s does not match the VT character (code
+       11).  This makes it different from the the POSIX "space" class. The  \s
+       characters  are  HT  (9), LF (10), FF (12), CR (13), and space (32). If
+       "use locale;" is included in a Perl script, \s may match the VT charac-
+       ter. In PCRE, it never does.
+
+       A  "word"  character is an underscore or any character that is a letter
+       or digit.  By default, the definition of letters  and  digits  is  con-
+       trolled  by PCRE's low-valued character tables, and may vary if locale-
+       specific matching is taking place (see "Locale support" in the  pcreapi
+       page).  For  example,  in  a French locale such as "fr_FR" in Unix-like
+       systems, or "french" in Windows, some character codes greater than  128
+       are  used  for  accented letters, and these are then matched by \w. The
+       use of locales with Unicode is discouraged.
+
+       By default, in a UTF mode, characters  with  values  greater  than  128
+       never  match  \d,  \s,  or  \w,  and always match \D, \S, and \W. These
+       sequences retain their original meanings from before  UTF  support  was
+       available,  mainly for efficiency reasons. However, if PCRE is compiled
+       with Unicode property support, and the PCRE_UCP option is set, the  be-
+       haviour  is  changed  so  that Unicode properties are used to determine
+       character types, as follows:
+
+         \d  any character that \p{Nd} matches (decimal digit)
+         \s  any character that \p{Z} matches, plus HT, LF, FF, CR
+         \w  any character that \p{L} or \p{N} matches, plus underscore
+
+       The upper case escapes match the inverse sets of characters. Note  that
+       \d  matches  only decimal digits, whereas \w matches any Unicode digit,
+       as well as any Unicode letter, and underscore. Note also that  PCRE_UCP
+       affects  \b,  and  \B  because  they are defined in terms of \w and \W.
+       Matching these sequences is noticeably slower when PCRE_UCP is set.
+
+       The sequences \h, \H, \v, and \V are features that were added  to  Perl
+       at  release  5.10. In contrast to the other sequences, which match only
+       ASCII characters by default, these  always  match  certain  high-valued
+       codepoints,  whether or not PCRE_UCP is set. The horizontal space char-
+       acters are:
+
+         U+0009     Horizontal tab
+         U+0020     Space
+         U+00A0     Non-break space
+         U+1680     Ogham space mark
+         U+180E     Mongolian vowel separator
+         U+2000     En quad
+         U+2001     Em quad
+         U+2002     En space
+         U+2003     Em space
+         U+2004     Three-per-em space
+         U+2005     Four-per-em space
+         U+2006     Six-per-em space
+         U+2007     Figure space
+         U+2008     Punctuation space
+         U+2009     Thin space
+         U+200A     Hair space
+         U+202F     Narrow no-break space
+         U+205F     Medium mathematical space
+         U+3000     Ideographic space
+
+       The vertical space characters are:
+
+         U+000A     Linefeed
+         U+000B     Vertical tab
+         U+000C     Form feed
+         U+000D     Carriage return
+         U+0085     Next line
+         U+2028     Line separator
+         U+2029     Paragraph separator
+
+       In 8-bit, non-UTF-8 mode, only the characters with codepoints less than
+       256 are relevant.
+
+   Newline sequences
+
+       Outside  a  character class, by default, the escape sequence \R matches
+       any Unicode newline sequence. In 8-bit non-UTF-8 mode \R is  equivalent
+       to the following:
+
+         (?>\r\n|\n|\x0b|\f|\r|\x85)
+
+       This  is  an  example  of an "atomic group", details of which are given
+       below.  This particular group matches either the two-character sequence
+       CR  followed  by  LF,  or  one  of  the single characters LF (linefeed,
+       U+000A), VT (vertical tab, U+000B), FF (form feed,  U+000C),  CR  (car-
+       riage  return,  U+000D),  or NEL (next line, U+0085). The two-character
+       sequence is treated as a single unit that cannot be split.
+
+       In other modes, two additional characters whose codepoints are  greater
+       than 255 are added: LS (line separator, U+2028) and PS (paragraph sepa-
+       rator, U+2029).  Unicode character property support is not  needed  for
+       these characters to be recognized.
+
+       It is possible to restrict \R to match only CR, LF, or CRLF (instead of
+       the complete set  of  Unicode  line  endings)  by  setting  the  option
+       PCRE_BSR_ANYCRLF either at compile time or when the pattern is matched.
+       (BSR is an abbrevation for "backslash R".) This can be made the default
+       when  PCRE  is  built;  if this is the case, the other behaviour can be
+       requested via the PCRE_BSR_UNICODE option.   It  is  also  possible  to
+       specify  these  settings  by  starting a pattern string with one of the
+       following sequences:
+
+         (*BSR_ANYCRLF)   CR, LF, or CRLF only
+         (*BSR_UNICODE)   any Unicode newline sequence
+
+       These override the default and the options given to the compiling func-
+       tion,  but  they  can  themselves  be  overridden by options given to a
+       matching function. Note that these  special  settings,  which  are  not
+       Perl-compatible,  are  recognized  only at the very start of a pattern,
+       and that they must be in upper case.  If  more  than  one  of  them  is
+       present,  the  last  one is used. They can be combined with a change of
+       newline convention; for example, a pattern can start with:
+
+         (*ANY)(*BSR_ANYCRLF)
+
+       They can also be combined with the (*UTF8), (*UTF16), or (*UCP) special
+       sequences.  Inside  a character class, \R is treated as an unrecognized
+       escape sequence, and so matches the letter "R" by default,  but  causes
+       an error if PCRE_EXTRA is set.
+
+   Unicode character properties
+
+       When PCRE is built with Unicode character property support, three addi-
+       tional escape sequences that match characters with specific  properties
+       are  available.   When  in 8-bit non-UTF-8 mode, these sequences are of
+       course limited to testing characters whose  codepoints  are  less  than
+       256, but they do work in this mode.  The extra escape sequences are:
+
+         \p{xx}   a character with the xx property
+         \P{xx}   a character without the xx property
+         \X       an extended Unicode sequence
+
+       The  property  names represented by xx above are limited to the Unicode
+       script names, the general category properties, "Any", which matches any
+       character   (including  newline),  and  some  special  PCRE  properties
+       (described in the next section).  Other Perl properties such as  "InMu-
+       sicalSymbols"  are  not  currently supported by PCRE. Note that \P{Any}
+       does not match any characters, so always causes a match failure.
+
+       Sets of Unicode characters are defined as belonging to certain scripts.
+       A  character from one of these sets can be matched using a script name.
+       For example:
+
+         \p{Greek}
+         \P{Han}
+
+       Those that are not part of an identified script are lumped together  as
+       "Common". The current list of scripts is:
+
+       Arabic,  Armenian,  Avestan, Balinese, Bamum, Batak, Bengali, Bopomofo,
+       Brahmi, Braille, Buginese, Buhid, Canadian_Aboriginal, Carian,  Chakma,
+       Cham,  Cherokee, Common, Coptic, Cuneiform, Cypriot, Cyrillic, Deseret,
+       Devanagari,  Egyptian_Hieroglyphs,  Ethiopic,   Georgian,   Glagolitic,
+       Gothic,  Greek, Gujarati, Gurmukhi, Han, Hangul, Hanunoo, Hebrew, Hira-
+       gana,  Imperial_Aramaic,  Inherited,  Inscriptional_Pahlavi,   Inscrip-
+       tional_Parthian,   Javanese,   Kaithi,   Kannada,  Katakana,  Kayah_Li,
+       Kharoshthi, Khmer, Lao, Latin, Lepcha, Limbu, Linear_B,  Lisu,  Lycian,
+       Lydian,    Malayalam,    Mandaic,    Meetei_Mayek,    Meroitic_Cursive,
+       Meroitic_Hieroglyphs,  Miao,  Mongolian,  Myanmar,  New_Tai_Lue,   Nko,
+       Ogham,    Old_Italic,   Old_Persian,   Old_South_Arabian,   Old_Turkic,
+       Ol_Chiki, Oriya, Osmanya, Phags_Pa, Phoenician, Rejang, Runic,  Samari-
+       tan,  Saurashtra,  Sharada,  Shavian, Sinhala, Sora_Sompeng, Sundanese,
+       Syloti_Nagri, Syriac, Tagalog, Tagbanwa,  Tai_Le,  Tai_Tham,  Tai_Viet,
+       Takri,  Tamil,  Telugu, Thaana, Thai, Tibetan, Tifinagh, Ugaritic, Vai,
+       Yi.
+
+       Each character has exactly one Unicode general category property, spec-
+       ified  by a two-letter abbreviation. For compatibility with Perl, nega-
+       tion can be specified by including a  circumflex  between  the  opening
+       brace  and  the  property  name.  For  example,  \p{^Lu} is the same as
+       \P{Lu}.
+
+       If only one letter is specified with \p or \P, it includes all the gen-
+       eral  category properties that start with that letter. In this case, in
+       the absence of negation, the curly brackets in the escape sequence  are
+       optional; these two examples have the same effect:
+
+         \p{L}
+         \pL
+
+       The following general category property codes are supported:
+
+         C     Other
+         Cc    Control
+         Cf    Format
+         Cn    Unassigned
+         Co    Private use
+         Cs    Surrogate
+
+         L     Letter
+         Ll    Lower case letter
+         Lm    Modifier letter
+         Lo    Other letter
+         Lt    Title case letter
+         Lu    Upper case letter
+
+         M     Mark
+         Mc    Spacing mark
+         Me    Enclosing mark
+         Mn    Non-spacing mark
+
+         N     Number
+         Nd    Decimal number
+         Nl    Letter number
+         No    Other number
+
+         P     Punctuation
+         Pc    Connector punctuation
+         Pd    Dash punctuation
+         Pe    Close punctuation
+         Pf    Final punctuation
+         Pi    Initial punctuation
+         Po    Other punctuation
+         Ps    Open punctuation
+
+         S     Symbol
+         Sc    Currency symbol
+         Sk    Modifier symbol
+         Sm    Mathematical symbol
+         So    Other symbol
+
+         Z     Separator
+         Zl    Line separator
+         Zp    Paragraph separator
+         Zs    Space separator
+
+       The  special property L& is also supported: it matches a character that
+       has the Lu, Ll, or Lt property, in other words, a letter  that  is  not
+       classified as a modifier or "other".
+
+       The  Cs  (Surrogate)  property  applies only to characters in the range
+       U+D800 to U+DFFF. Such characters are not valid in Unicode strings  and
+       so  cannot  be  tested  by  PCRE, unless UTF validity checking has been
+       turned   off   (see   the   discussion   of   PCRE_NO_UTF8_CHECK    and
+       PCRE_NO_UTF16_CHECK  in the pcreapi page). Perl does not support the Cs
+       property.
+
+       The long synonyms for  property  names  that  Perl  supports  (such  as
+       \p{Letter})  are  not  supported by PCRE, nor is it permitted to prefix
+       any of these properties with "Is".
+
+       No character that is in the Unicode table has the Cn (unassigned) prop-
+       erty.  Instead, this property is assumed for any code point that is not
+       in the Unicode table.
+
+       Specifying caseless matching does not affect  these  escape  sequences.
+       For example, \p{Lu} always matches only upper case letters.
+
+       The  \X  escape  matches  any number of Unicode characters that form an
+       extended Unicode sequence. \X is equivalent to
+
+         (?>\PM\pM*)
+
+       That is, it matches a character without the "mark"  property,  followed
+       by  zero  or  more  characters with the "mark" property, and treats the
+       sequence as an atomic group (see below).  Characters  with  the  "mark"
+       property  are  typically  accents  that affect the preceding character.
+       None of them have codepoints less than 256, so in 8-bit non-UTF-8  mode
+       \X matches any one character.
+
+       Note that recent versions of Perl have changed \X to match what Unicode
+       calls an "extended grapheme cluster", which has a more complicated def-
+       inition.
+
+       Matching  characters  by Unicode property is not fast, because PCRE has
+       to search a structure that contains  data  for  over  fifteen  thousand
+       characters. That is why the traditional escape sequences such as \d and
+       \w do not use Unicode properties in PCRE by  default,  though  you  can
+       make  them do so by setting the PCRE_UCP option or by starting the pat-
+       tern with (*UCP).
+
+   PCRE's additional properties
+
+       As well as the standard Unicode properties described  in  the  previous
+       section,  PCRE supports four more that make it possible to convert tra-
+       ditional escape sequences such as \w and \s and POSIX character classes
+       to use Unicode properties. PCRE uses these non-standard, non-Perl prop-
+       erties internally when PCRE_UCP is set. They are:
+
+         Xan   Any alphanumeric character
+         Xps   Any POSIX space character
+         Xsp   Any Perl space character
+         Xwd   Any Perl "word" character
+
+       Xan matches characters that have either the L (letter) or the  N  (num-
+       ber)  property. Xps matches the characters tab, linefeed, vertical tab,
+       form feed, or carriage return, and any other character that has  the  Z
+       (separator) property.  Xsp is the same as Xps, except that vertical tab
+       is excluded. Xwd matches the same characters as Xan, plus underscore.
+
+   Resetting the match start
+
+       The escape sequence \K causes any previously matched characters not  to
+       be included in the final matched sequence. For example, the pattern:
+
+         foo\Kbar
+
+       matches  "foobar",  but reports that it has matched "bar". This feature
+       is similar to a lookbehind assertion (described  below).   However,  in
+       this  case, the part of the subject before the real match does not have
+       to be of fixed length, as lookbehind assertions do. The use of \K  does
+       not  interfere  with  the setting of captured substrings.  For example,
+       when the pattern
+
+         (foo)\Kbar
+
+       matches "foobar", the first substring is still set to "foo".
+
+       Perl documents that the use  of  \K  within  assertions  is  "not  well
+       defined".  In  PCRE,  \K  is  acted upon when it occurs inside positive
+       assertions, but is ignored in negative assertions.
+
+   Simple assertions
+
+       The final use of backslash is for certain simple assertions. An  asser-
+       tion  specifies a condition that has to be met at a particular point in
+       a match, without consuming any characters from the subject string.  The
+       use  of subpatterns for more complicated assertions is described below.
+       The backslashed assertions are:
+
+         \b     matches at a word boundary
+         \B     matches when not at a word boundary
+         \A     matches at the start of the subject
+         \Z     matches at the end of the subject
+                 also matches before a newline at the end of the subject
+         \z     matches only at the end of the subject
+         \G     matches at the first matching position in the subject
+
+       Inside a character class, \b has a different meaning;  it  matches  the
+       backspace  character.  If  any  other  of these assertions appears in a
+       character class, by default it matches the corresponding literal  char-
+       acter  (for  example,  \B  matches  the  letter  B).  However,  if  the
+       PCRE_EXTRA option is set, an "invalid escape sequence" error is  gener-
+       ated instead.
+
+       A  word  boundary is a position in the subject string where the current
+       character and the previous character do not both match \w or  \W  (i.e.
+       one  matches  \w  and the other matches \W), or the start or end of the
+       string if the first or last character matches \w,  respectively.  In  a
+       UTF  mode,  the  meanings  of  \w  and \W can be changed by setting the
+       PCRE_UCP option. When this is done, it also affects \b and \B.  Neither
+       PCRE  nor  Perl has a separate "start of word" or "end of word" metase-
+       quence. However, whatever follows \b normally determines which  it  is.
+       For example, the fragment \ba matches "a" at the start of a word.
+
+       The  \A,  \Z,  and \z assertions differ from the traditional circumflex
+       and dollar (described in the next section) in that they only ever match
+       at  the  very start and end of the subject string, whatever options are
+       set. Thus, they are independent of multiline mode. These  three  asser-
+       tions are not affected by the PCRE_NOTBOL or PCRE_NOTEOL options, which
+       affect only the behaviour of the circumflex and dollar  metacharacters.
+       However,  if the startoffset argument of pcre_exec() is non-zero, indi-
+       cating that matching is to start at a point other than the beginning of
+       the  subject,  \A  can never match. The difference between \Z and \z is
+       that \Z matches before a newline at the end of the string as well as at
+       the very end, whereas \z matches only at the end.
+
+       The  \G assertion is true only when the current matching position is at
+       the start point of the match, as specified by the startoffset  argument
+       of  pcre_exec().  It  differs  from \A when the value of startoffset is
+       non-zero. By calling pcre_exec() multiple times with appropriate  argu-
+       ments, you can mimic Perl's /g option, and it is in this kind of imple-
+       mentation where \G can be useful.
+
+       Note, however, that PCRE's interpretation of \G, as the  start  of  the
+       current match, is subtly different from Perl's, which defines it as the
+       end of the previous match. In Perl, these can  be  different  when  the
+       previously  matched  string was empty. Because PCRE does just one match
+       at a time, it cannot reproduce this behaviour.
+
+       If all the alternatives of a pattern begin with \G, the  expression  is
+       anchored to the starting match position, and the "anchored" flag is set
+       in the compiled regular expression.
+
+
+CIRCUMFLEX AND DOLLAR
+
+       Outside a character class, in the default matching mode, the circumflex
+       character  is  an  assertion  that is true only if the current matching
+       point is at the start of the subject string. If the  startoffset  argu-
+       ment  of  pcre_exec()  is  non-zero,  circumflex can never match if the
+       PCRE_MULTILINE option is unset. Inside a  character  class,  circumflex
+       has an entirely different meaning (see below).
+
+       Circumflex  need  not be the first character of the pattern if a number
+       of alternatives are involved, but it should be the first thing in  each
+       alternative  in  which  it appears if the pattern is ever to match that
+       branch. If all possible alternatives start with a circumflex, that  is,
+       if  the  pattern  is constrained to match only at the start of the sub-
+       ject, it is said to be an "anchored" pattern.  (There  are  also  other
+       constructs that can cause a pattern to be anchored.)
+
+       A  dollar  character  is  an assertion that is true only if the current
+       matching point is at the end of  the  subject  string,  or  immediately
+       before a newline at the end of the string (by default). Dollar need not
+       be the last character of the pattern if a number  of  alternatives  are
+       involved,  but  it  should  be  the last item in any branch in which it
+       appears. Dollar has no special meaning in a character class.
+
+       The meaning of dollar can be changed so that it  matches  only  at  the
+       very  end  of  the string, by setting the PCRE_DOLLAR_ENDONLY option at
+       compile time. This does not affect the \Z assertion.
+
+       The meanings of the circumflex and dollar characters are changed if the
+       PCRE_MULTILINE  option  is  set.  When  this  is the case, a circumflex
+       matches immediately after internal newlines as well as at the start  of
+       the  subject  string.  It  does not match after a newline that ends the
+       string. A dollar matches before any newlines in the string, as well  as
+       at  the very end, when PCRE_MULTILINE is set. When newline is specified
+       as the two-character sequence CRLF, isolated CR and  LF  characters  do
+       not indicate newlines.
+
+       For  example, the pattern /^abc$/ matches the subject string "def\nabc"
+       (where \n represents a newline) in multiline mode, but  not  otherwise.
+       Consequently,  patterns  that  are anchored in single line mode because
+       all branches start with ^ are not anchored in  multiline  mode,  and  a
+       match  for  circumflex  is  possible  when  the startoffset argument of
+       pcre_exec() is non-zero. The PCRE_DOLLAR_ENDONLY option is  ignored  if
+       PCRE_MULTILINE is set.
+
+       Note  that  the sequences \A, \Z, and \z can be used to match the start
+       and end of the subject in both modes, and if all branches of a  pattern
+       start  with  \A it is always anchored, whether or not PCRE_MULTILINE is
+       set.
+
+
+FULL STOP (PERIOD, DOT) AND \N
+
+       Outside a character class, a dot in the pattern matches any one charac-
+       ter  in  the subject string except (by default) a character that signi-
+       fies the end of a line.
+
+       When a line ending is defined as a single character, dot never  matches
+       that  character; when the two-character sequence CRLF is used, dot does
+       not match CR if it is immediately followed  by  LF,  but  otherwise  it
+       matches  all characters (including isolated CRs and LFs). When any Uni-
+       code line endings are being recognized, dot does not match CR or LF  or
+       any of the other line ending characters.
+
+       The  behaviour  of  dot  with regard to newlines can be changed. If the
+       PCRE_DOTALL option is set, a dot matches  any  one  character,  without
+       exception. If the two-character sequence CRLF is present in the subject
+       string, it takes two dots to match it.
+
+       The handling of dot is entirely independent of the handling of  circum-
+       flex  and  dollar,  the  only relationship being that they both involve
+       newlines. Dot has no special meaning in a character class.
+
+       The escape sequence \N behaves like  a  dot,  except  that  it  is  not
+       affected  by  the  PCRE_DOTALL  option.  In other words, it matches any
+       character except one that signifies the end of a line. Perl  also  uses
+       \N to match characters by name; PCRE does not support this.
+
+
+MATCHING A SINGLE DATA UNIT
+
+       Outside  a character class, the escape sequence \C matches any one data
+       unit, whether or not a UTF mode is set. In the 8-bit library, one  data
+       unit  is  one byte; in the 16-bit library it is a 16-bit unit. Unlike a
+       dot, \C always matches line-ending characters. The feature is  provided
+       in  Perl  in  order  to match individual bytes in UTF-8 mode, but it is
+       unclear how it can usefully be used. Because \C  breaks  up  characters
+       into  individual  data  units,  matching one unit with \C in a UTF mode
+       means that the rest of the string may start with a malformed UTF  char-
+       acter.  This  has  undefined  results,  because PCRE assumes that it is
+       dealing with valid UTF strings (and by default it checks  this  at  the
+       start     of    processing    unless    the    PCRE_NO_UTF8_CHECK    or
+       PCRE_NO_UTF16_CHECK option is used).
+
+       PCRE does not allow \C to appear in  lookbehind  assertions  (described
+       below)  in  a UTF mode, because this would make it impossible to calcu-
+       late the length of the lookbehind.
+
+       In general, the \C escape sequence is best avoided. However, one way of
+       using  it that avoids the problem of malformed UTF characters is to use
+       a lookahead to check the length of the next character, as in this  pat-
+       tern,  which  could be used with a UTF-8 string (ignore white space and
+       line breaks):
+
+         (?| (?=[\x00-\x7f])(\C) |
+             (?=[\x80-\x{7ff}])(\C)(\C) |
+             (?=[\x{800}-\x{ffff}])(\C)(\C)(\C) |
+             (?=[\x{10000}-\x{1fffff}])(\C)(\C)(\C)(\C))
+
+       A group that starts with (?| resets the capturing  parentheses  numbers
+       in  each  alternative  (see  "Duplicate Subpattern Numbers" below). The
+       assertions at the start of each branch check the next  UTF-8  character
+       for  values  whose encoding uses 1, 2, 3, or 4 bytes, respectively. The
+       character's individual bytes are then captured by the appropriate  num-
+       ber of groups.
+
+
+SQUARE BRACKETS AND CHARACTER CLASSES
+
+       An opening square bracket introduces a character class, terminated by a
+       closing square bracket. A closing square bracket on its own is not spe-
+       cial by default.  However, if the PCRE_JAVASCRIPT_COMPAT option is set,
+       a lone closing square bracket causes a compile-time error. If a closing
+       square  bracket  is required as a member of the class, it should be the
+       first data character in the class  (after  an  initial  circumflex,  if
+       present) or escaped with a backslash.
+
+       A  character  class matches a single character in the subject. In a UTF
+       mode, the character may be more than one  data  unit  long.  A  matched
+       character must be in the set of characters defined by the class, unless
+       the first character in the class definition is a circumflex,  in  which
+       case the subject character must not be in the set defined by the class.
+       If a circumflex is actually required as a member of the  class,  ensure
+       it is not the first character, or escape it with a backslash.
+
+       For  example, the character class [aeiou] matches any lower case vowel,
+       while [^aeiou] matches any character that is not a  lower  case  vowel.
+       Note that a circumflex is just a convenient notation for specifying the
+       characters that are in the class by enumerating those that are  not.  A
+       class  that starts with a circumflex is not an assertion; it still con-
+       sumes a character from the subject string, and therefore  it  fails  if
+       the current pointer is at the end of the string.
+
+       In  UTF-8  (UTF-16)  mode,  characters  with  values  greater  than 255
+       (0xffff) can be included in a class as a literal string of data  units,
+       or by using the \x{ escaping mechanism.
+
+       When  caseless  matching  is set, any letters in a class represent both
+       their upper case and lower case versions, so for  example,  a  caseless
+       [aeiou]  matches  "A"  as well as "a", and a caseless [^aeiou] does not
+       match "A", whereas a caseful version would. In a UTF mode, PCRE  always
+       understands  the  concept  of case for characters whose values are less
+       than 128, so caseless matching is always possible. For characters  with
+       higher  values,  the  concept  of case is supported if PCRE is compiled
+       with Unicode property support, but not otherwise.  If you want  to  use
+       caseless  matching in a UTF mode for characters 128 and above, you must
+       ensure that PCRE is compiled with Unicode property support as  well  as
+       with UTF support.
+
+       Characters  that  might  indicate  line breaks are never treated in any
+       special way  when  matching  character  classes,  whatever  line-ending
+       sequence  is  in  use,  and  whatever  setting  of  the PCRE_DOTALL and
+       PCRE_MULTILINE options is used. A class such as [^a] always matches one
+       of these characters.
+
+       The  minus (hyphen) character can be used to specify a range of charac-
+       ters in a character  class.  For  example,  [d-m]  matches  any  letter
+       between  d  and  m,  inclusive.  If  a minus character is required in a
+       class, it must be escaped with a backslash  or  appear  in  a  position
+       where  it cannot be interpreted as indicating a range, typically as the
+       first or last character in the class.
+
+       It is not possible to have the literal character "]" as the end charac-
+       ter  of a range. A pattern such as [W-]46] is interpreted as a class of
+       two characters ("W" and "-") followed by a literal string "46]", so  it
+       would  match  "W46]"  or  "-46]". However, if the "]" is escaped with a
+       backslash it is interpreted as the end of range, so [W-\]46] is  inter-
+       preted  as a class containing a range followed by two other characters.
+       The octal or hexadecimal representation of "]" can also be used to  end
+       a range.
+
+       Ranges  operate in the collating sequence of character values. They can
+       also  be  used  for  characters  specified  numerically,  for   example
+       [\000-\037].  Ranges  can include any characters that are valid for the
+       current mode.
+
+       If a range that includes letters is used when caseless matching is set,
+       it matches the letters in either case. For example, [W-c] is equivalent
+       to [][\\^_`wxyzabc], matched caselessly, and  in  a  non-UTF  mode,  if
+       character  tables  for  a French locale are in use, [\xc8-\xcb] matches
+       accented E characters in both cases. In UTF modes,  PCRE  supports  the
+       concept  of  case for characters with values greater than 128 only when
+       it is compiled with Unicode property support.
+
+       The character escape sequences \d, \D, \h, \H, \p, \P, \s, \S, \v,  \V,
+       \w, and \W may appear in a character class, and add the characters that
+       they match to the class. For example, [\dABCDEF] matches any  hexadeci-
+       mal  digit.  In  UTF modes, the PCRE_UCP option affects the meanings of
+       \d, \s, \w and their upper case partners, just as  it  does  when  they
+       appear  outside a character class, as described in the section entitled
+       "Generic character types" above. The escape sequence \b has a different
+       meaning  inside  a character class; it matches the backspace character.
+       The sequences \B, \N, \R, and \X are not  special  inside  a  character
+       class.  Like  any other unrecognized escape sequences, they are treated
+       as the literal characters "B", "N", "R", and "X" by default, but  cause
+       an error if the PCRE_EXTRA option is set.
+
+       A  circumflex  can  conveniently  be used with the upper case character
+       types to specify a more restricted set of characters than the  matching
+       lower  case  type.  For example, the class [^\W_] matches any letter or
+       digit, but not underscore, whereas [\w] includes underscore. A positive
+       character class should be read as "something OR something OR ..." and a
+       negative class as "NOT something AND NOT something AND NOT ...".
+
+       The only metacharacters that are recognized in  character  classes  are
+       backslash,  hyphen  (only  where  it can be interpreted as specifying a
+       range), circumflex (only at the start), opening  square  bracket  (only
+       when  it can be interpreted as introducing a POSIX class name - see the
+       next section), and the terminating  closing  square  bracket.  However,
+       escaping other non-alphanumeric characters does no harm.
+
+
+POSIX CHARACTER CLASSES
+
+       Perl supports the POSIX notation for character classes. This uses names
+       enclosed by [: and :] within the enclosing square brackets.  PCRE  also
+       supports this notation. For example,
+
+         [01[:alpha:]%]
+
+       matches "0", "1", any alphabetic character, or "%". The supported class
+       names are:
+
+         alnum    letters and digits
+         alpha    letters
+         ascii    character codes 0 - 127
+         blank    space or tab only
+         cntrl    control characters
+         digit    decimal digits (same as \d)
+         graph    printing characters, excluding space
+         lower    lower case letters
+         print    printing characters, including space
+         punct    printing characters, excluding letters and digits and space
+         space    white space (not quite the same as \s)
+         upper    upper case letters
+         word     "word" characters (same as \w)
+         xdigit   hexadecimal digits
+
+       The "space" characters are HT (9), LF (10), VT (11), FF (12), CR  (13),
+       and  space  (32). Notice that this list includes the VT character (code
+       11). This makes "space" different to \s, which does not include VT (for
+       Perl compatibility).
+
+       The  name  "word"  is  a Perl extension, and "blank" is a GNU extension
+       from Perl 5.8. Another Perl extension is negation, which  is  indicated
+       by a ^ character after the colon. For example,
+
+         [12[:^digit:]]
+
+       matches  "1", "2", or any non-digit. PCRE (and Perl) also recognize the
+       POSIX syntax [.ch.] and [=ch=] where "ch" is a "collating element", but
+       these are not supported, and an error is given if they are encountered.
+
+       By  default,  in  UTF modes, characters with values greater than 128 do
+       not match any of the POSIX character classes. However, if the  PCRE_UCP
+       option  is passed to pcre_compile(), some of the classes are changed so
+       that Unicode character properties are used. This is achieved by replac-
+       ing the POSIX classes by other sequences, as follows:
+
+         [:alnum:]  becomes  \p{Xan}
+         [:alpha:]  becomes  \p{L}
+         [:blank:]  becomes  \h
+         [:digit:]  becomes  \p{Nd}
+         [:lower:]  becomes  \p{Ll}
+         [:space:]  becomes  \p{Xps}
+         [:upper:]  becomes  \p{Lu}
+         [:word:]   becomes  \p{Xwd}
+
+       Negated  versions,  such  as [:^alpha:] use \P instead of \p. The other
+       POSIX classes are unchanged, and match only characters with code points
+       less than 128.
+
+
+VERTICAL BAR
+
+       Vertical  bar characters are used to separate alternative patterns. For
+       example, the pattern
+
+         gilbert|sullivan
+
+       matches either "gilbert" or "sullivan". Any number of alternatives  may
+       appear,  and  an  empty  alternative  is  permitted (matching the empty
+       string). The matching process tries each alternative in turn, from left
+       to  right, and the first one that succeeds is used. If the alternatives
+       are within a subpattern (defined below), "succeeds" means matching  the
+       rest of the main pattern as well as the alternative in the subpattern.
+
+
+INTERNAL OPTION SETTING
+
+       The  settings  of  the  PCRE_CASELESS, PCRE_MULTILINE, PCRE_DOTALL, and
+       PCRE_EXTENDED options (which are Perl-compatible) can be  changed  from
+       within  the  pattern  by  a  sequence  of  Perl option letters enclosed
+       between "(?" and ")".  The option letters are
+
+         i  for PCRE_CASELESS
+         m  for PCRE_MULTILINE
+         s  for PCRE_DOTALL
+         x  for PCRE_EXTENDED
+
+       For example, (?im) sets caseless, multiline matching. It is also possi-
+       ble to unset these options by preceding the letter with a hyphen, and a
+       combined setting and unsetting such as (?im-sx), which sets  PCRE_CASE-
+       LESS  and PCRE_MULTILINE while unsetting PCRE_DOTALL and PCRE_EXTENDED,
+       is also permitted. If a  letter  appears  both  before  and  after  the
+       hyphen, the option is unset.
+
+       The  PCRE-specific options PCRE_DUPNAMES, PCRE_UNGREEDY, and PCRE_EXTRA
+       can be changed in the same way as the Perl-compatible options by  using
+       the characters J, U and X respectively.
+
+       When  one  of  these  option  changes occurs at top level (that is, not
+       inside subpattern parentheses), the change applies to the remainder  of
+       the pattern that follows. If the change is placed right at the start of
+       a pattern, PCRE extracts it into the global options (and it will there-
+       fore show up in data extracted by the pcre_fullinfo() function).
+
+       An  option  change  within a subpattern (see below for a description of
+       subpatterns) affects only that part of the subpattern that follows  it,
+       so
+
+         (a(?i)b)c
+
+       matches abc and aBc and no other strings (assuming PCRE_CASELESS is not
+       used).  By this means, options can be made to have  different  settings
+       in  different parts of the pattern. Any changes made in one alternative
+       do carry on into subsequent branches within the  same  subpattern.  For
+       example,
+
+         (a(?i)b|c)
+
+       matches  "ab",  "aB",  "c",  and "C", even though when matching "C" the
+       first branch is abandoned before the option setting.  This  is  because
+       the  effects  of option settings happen at compile time. There would be
+       some very weird behaviour otherwise.
+
+       Note: There are other PCRE-specific options that  can  be  set  by  the
+       application  when  the  compiling  or matching functions are called. In
+       some cases the pattern can contain special leading  sequences  such  as
+       (*CRLF)  to  override  what  the  application  has set or what has been
+       defaulted.  Details  are  given  in  the  section   entitled   "Newline
+       sequences"  above.  There  are  also  the (*UTF8), (*UTF16), and (*UCP)
+       leading sequences that can be used to  set  UTF  and  Unicode  property
+       modes;  they  are  equivalent to setting the PCRE_UTF8, PCRE_UTF16, and
+       the PCRE_UCP options, respectively.
+
+
+SUBPATTERNS
+
+       Subpatterns are delimited by parentheses (round brackets), which can be
+       nested.  Turning part of a pattern into a subpattern does two things:
+
+       1. It localizes a set of alternatives. For example, the pattern
+
+         cat(aract|erpillar|)
+
+       matches  "cataract",  "caterpillar", or "cat". Without the parentheses,
+       it would match "cataract", "erpillar" or an empty string.
+
+       2. It sets up the subpattern as  a  capturing  subpattern.  This  means
+       that,  when  the  whole  pattern  matches,  that portion of the subject
+       string that matched the subpattern is passed back to the caller via the
+       ovector  argument  of  the matching function. (This applies only to the
+       traditional matching functions; the DFA matching functions do not  sup-
+       port capturing.)
+
+       Opening parentheses are counted from left to right (starting from 1) to
+       obtain numbers for the  capturing  subpatterns.  For  example,  if  the
+       string "the red king" is matched against the pattern
+
+         the ((red|white) (king|queen))
+
+       the captured substrings are "red king", "red", and "king", and are num-
+       bered 1, 2, and 3, respectively.
+
+       The fact that plain parentheses fulfil  two  functions  is  not  always
+       helpful.   There are often times when a grouping subpattern is required
+       without a capturing requirement. If an opening parenthesis is  followed
+       by  a question mark and a colon, the subpattern does not do any captur-
+       ing, and is not counted when computing the  number  of  any  subsequent
+       capturing  subpatterns. For example, if the string "the white queen" is
+       matched against the pattern
+
+         the ((?:red|white) (king|queen))
+
+       the captured substrings are "white queen" and "queen", and are numbered
+       1 and 2. The maximum number of capturing subpatterns is 65535.
+
+       As  a  convenient shorthand, if any option settings are required at the
+       start of a non-capturing subpattern,  the  option  letters  may  appear
+       between the "?" and the ":". Thus the two patterns
+
+         (?i:saturday|sunday)
+         (?:(?i)saturday|sunday)
+
+       match exactly the same set of strings. Because alternative branches are
+       tried from left to right, and options are not reset until  the  end  of
+       the  subpattern is reached, an option setting in one branch does affect
+       subsequent branches, so the above patterns match "SUNDAY"  as  well  as
+       "Saturday".
+
+
+DUPLICATE SUBPATTERN NUMBERS
+
+       Perl 5.10 introduced a feature whereby each alternative in a subpattern
+       uses the same numbers for its capturing parentheses. Such a  subpattern
+       starts  with (?| and is itself a non-capturing subpattern. For example,
+       consider this pattern:
+
+         (?|(Sat)ur|(Sun))day
+
+       Because the two alternatives are inside a (?| group, both sets of  cap-
+       turing  parentheses  are  numbered one. Thus, when the pattern matches,
+       you can look at captured substring number  one,  whichever  alternative
+       matched.  This  construct  is useful when you want to capture part, but
+       not all, of one of a number of alternatives. Inside a (?| group, paren-
+       theses  are  numbered as usual, but the number is reset at the start of
+       each branch. The numbers of any capturing parentheses that  follow  the
+       subpattern  start after the highest number used in any branch. The fol-
+       lowing example is taken from the Perl documentation. The numbers under-
+       neath show in which buffer the captured content will be stored.
+
+         # before  ---------------branch-reset----------- after
+         / ( a )  (?| x ( y ) z | (p (q) r) | (t) u (v) ) ( z ) /x
+         # 1            2         2  3        2     3     4
+
+       A  back  reference  to a numbered subpattern uses the most recent value
+       that is set for that number by any subpattern.  The  following  pattern
+       matches "abcabc" or "defdef":
+
+         /(?|(abc)|(def))\1/
+
+       In  contrast,  a subroutine call to a numbered subpattern always refers
+       to the first one in the pattern with the given  number.  The  following
+       pattern matches "abcabc" or "defabc":
+
+         /(?|(abc)|(def))(?1)/
+
+       If  a condition test for a subpattern's having matched refers to a non-
+       unique number, the test is true if any of the subpatterns of that  num-
+       ber have matched.
+
+       An  alternative approach to using this "branch reset" feature is to use
+       duplicate named subpatterns, as described in the next section.
+
+
+NAMED SUBPATTERNS
+
+       Identifying capturing parentheses by number is simple, but  it  can  be
+       very  hard  to keep track of the numbers in complicated regular expres-
+       sions. Furthermore, if an  expression  is  modified,  the  numbers  may
+       change.  To help with this difficulty, PCRE supports the naming of sub-
+       patterns. This feature was not added to Perl until release 5.10. Python
+       had  the  feature earlier, and PCRE introduced it at release 4.0, using
+       the Python syntax. PCRE now supports both the Perl and the Python  syn-
+       tax.  Perl  allows  identically  numbered subpatterns to have different
+       names, but PCRE does not.
+
+       In PCRE, a subpattern can be named in one of three  ways:  (?<name>...)
+       or  (?'name'...)  as in Perl, or (?P<name>...) as in Python. References
+       to capturing parentheses from other parts of the pattern, such as  back
+       references,  recursion,  and conditions, can be made by name as well as
+       by number.
+
+       Names consist of up to  32  alphanumeric  characters  and  underscores.
+       Named  capturing  parentheses  are  still  allocated numbers as well as
+       names, exactly as if the names were not present. The PCRE API  provides
+       function calls for extracting the name-to-number translation table from
+       a compiled pattern. There is also a convenience function for extracting
+       a captured substring by name.
+
+       By  default, a name must be unique within a pattern, but it is possible
+       to relax this constraint by setting the PCRE_DUPNAMES option at compile
+       time.  (Duplicate  names are also always permitted for subpatterns with
+       the same number, set up as described in the previous  section.)  Dupli-
+       cate  names  can  be useful for patterns where only one instance of the
+       named parentheses can match. Suppose you want to match the  name  of  a
+       weekday,  either as a 3-letter abbreviation or as the full name, and in
+       both cases you want to extract the abbreviation. This pattern (ignoring
+       the line breaks) does the job:
+
+         (?<DN>Mon|Fri|Sun)(?:day)?|
+         (?<DN>Tue)(?:sday)?|
+         (?<DN>Wed)(?:nesday)?|
+         (?<DN>Thu)(?:rsday)?|
+         (?<DN>Sat)(?:urday)?
+
+       There  are  five capturing substrings, but only one is ever set after a
+       match.  (An alternative way of solving this problem is to use a "branch
+       reset" subpattern, as described in the previous section.)
+
+       The  convenience  function  for extracting the data by name returns the
+       substring for the first (and in this example, the only)  subpattern  of
+       that  name  that  matched.  This saves searching to find which numbered
+       subpattern it was.
+
+       If you make a back reference to  a  non-unique  named  subpattern  from
+       elsewhere  in the pattern, the one that corresponds to the first occur-
+       rence of the name is used. In the absence of duplicate numbers (see the
+       previous  section) this is the one with the lowest number. If you use a
+       named reference in a condition test (see the section  about  conditions
+       below),  either  to check whether a subpattern has matched, or to check
+       for recursion, all subpatterns with the same name are  tested.  If  the
+       condition  is  true for any one of them, the overall condition is true.
+       This is the same behaviour as testing by number. For further details of
+       the interfaces for handling named subpatterns, see the pcreapi documen-
+       tation.
+
+       Warning: You cannot use different names to distinguish between two sub-
+       patterns  with  the same number because PCRE uses only the numbers when
+       matching. For this reason, an error is given at compile time if differ-
+       ent  names  are given to subpatterns with the same number. However, you
+       can give the same name to subpatterns with the same number,  even  when
+       PCRE_DUPNAMES is not set.
+
+
+REPETITION
+
+       Repetition  is  specified  by  quantifiers, which can follow any of the
+       following items:
+
+         a literal data character
+         the dot metacharacter
+         the \C escape sequence
+         the \X escape sequence
+         the \R escape sequence
+         an escape such as \d or \pL that matches a single character
+         a character class
+         a back reference (see next section)
+         a parenthesized subpattern (including assertions)
+         a subroutine call to a subpattern (recursive or otherwise)
+
+       The general repetition quantifier specifies a minimum and maximum  num-
+       ber  of  permitted matches, by giving the two numbers in curly brackets
+       (braces), separated by a comma. The numbers must be  less  than  65536,
+       and the first must be less than or equal to the second. For example:
+
+         z{2,4}
+
+       matches  "zz",  "zzz",  or  "zzzz". A closing brace on its own is not a
+       special character. If the second number is omitted, but  the  comma  is
+       present,  there  is  no upper limit; if the second number and the comma
+       are both omitted, the quantifier specifies an exact number of  required
+       matches. Thus
+
+         [aeiou]{3,}
+
+       matches at least 3 successive vowels, but may match many more, while
+
+         \d{8}
+
+       matches  exactly  8  digits. An opening curly bracket that appears in a
+       position where a quantifier is not allowed, or one that does not  match
+       the  syntax of a quantifier, is taken as a literal character. For exam-
+       ple, {,6} is not a quantifier, but a literal string of four characters.
+
+       In UTF modes, quantifiers apply to characters rather than to individual
+       data  units. Thus, for example, \x{100}{2} matches two characters, each
+       of which is represented by a two-byte sequence in a UTF-8 string. Simi-
+       larly,  \X{3}  matches  three Unicode extended sequences, each of which
+       may be several data units long (and they may be of different lengths).
+
+       The quantifier {0} is permitted, causing the expression to behave as if
+       the previous item and the quantifier were not present. This may be use-
+       ful for subpatterns that are referenced as subroutines  from  elsewhere
+       in the pattern (but see also the section entitled "Defining subpatterns
+       for use by reference only" below). Items other  than  subpatterns  that
+       have a {0} quantifier are omitted from the compiled pattern.
+
+       For  convenience, the three most common quantifiers have single-charac-
+       ter abbreviations:
+
+         *    is equivalent to {0,}
+         +    is equivalent to {1,}
+         ?    is equivalent to {0,1}
+
+       It is possible to construct infinite loops by  following  a  subpattern
+       that can match no characters with a quantifier that has no upper limit,
+       for example:
+
+         (a?)*
+
+       Earlier versions of Perl and PCRE used to give an error at compile time
+       for  such  patterns. However, because there are cases where this can be
+       useful, such patterns are now accepted, but if any  repetition  of  the
+       subpattern  does in fact match no characters, the loop is forcibly bro-
+       ken.
+
+       By default, the quantifiers are "greedy", that is, they match  as  much
+       as  possible  (up  to  the  maximum number of permitted times), without
+       causing the rest of the pattern to fail. The classic example  of  where
+       this gives problems is in trying to match comments in C programs. These
+       appear between /* and */ and within the comment,  individual  *  and  /
+       characters  may  appear. An attempt to match C comments by applying the
+       pattern
+
+         /\*.*\*/
+
+       to the string
+
+         /* first comment */  not comment  /* second comment */
+
+       fails, because it matches the entire string owing to the greediness  of
+       the .*  item.
+
+       However,  if  a quantifier is followed by a question mark, it ceases to
+       be greedy, and instead matches the minimum number of times possible, so
+       the pattern
+
+         /\*.*?\*/
+
+       does  the  right  thing with the C comments. The meaning of the various
+       quantifiers is not otherwise changed,  just  the  preferred  number  of
+       matches.   Do  not  confuse this use of question mark with its use as a
+       quantifier in its own right. Because it has two uses, it can  sometimes
+       appear doubled, as in
+
+         \d??\d
+
+       which matches one digit by preference, but can match two if that is the
+       only way the rest of the pattern matches.
+
+       If the PCRE_UNGREEDY option is set (an option that is not available  in
+       Perl),  the  quantifiers are not greedy by default, but individual ones
+       can be made greedy by following them with a  question  mark.  In  other
+       words, it inverts the default behaviour.
+
+       When  a  parenthesized  subpattern  is quantified with a minimum repeat
+       count that is greater than 1 or with a limited maximum, more memory  is
+       required  for  the  compiled  pattern, in proportion to the size of the
+       minimum or maximum.
+
+       If a pattern starts with .* or .{0,} and the PCRE_DOTALL option (equiv-
+       alent  to  Perl's  /s) is set, thus allowing the dot to match newlines,
+       the pattern is implicitly anchored, because whatever  follows  will  be
+       tried  against every character position in the subject string, so there
+       is no point in retrying the overall match at  any  position  after  the
+       first.  PCRE  normally treats such a pattern as though it were preceded
+       by \A.
+
+       In cases where it is known that the subject  string  contains  no  new-
+       lines,  it  is  worth setting PCRE_DOTALL in order to obtain this opti-
+       mization, or alternatively using ^ to indicate anchoring explicitly.
+
+       However, there is one situation where the optimization cannot be  used.
+       When .*  is inside capturing parentheses that are the subject of a back
+       reference elsewhere in the pattern, a match at the start may fail where
+       a later one succeeds. Consider, for example:
+
+         (.*)abc\1
+
+       If  the subject is "xyz123abc123" the match point is the fourth charac-
+       ter. For this reason, such a pattern is not implicitly anchored.
+
+       When a capturing subpattern is repeated, the value captured is the sub-
+       string that matched the final iteration. For example, after
+
+         (tweedle[dume]{3}\s*)+
+
+       has matched "tweedledum tweedledee" the value of the captured substring
+       is "tweedledee". However, if there are  nested  capturing  subpatterns,
+       the  corresponding captured values may have been set in previous itera-
+       tions. For example, after
+
+         /(a|(b))+/
+
+       matches "aba" the value of the second captured substring is "b".
+
+
+ATOMIC GROUPING AND POSSESSIVE QUANTIFIERS
+
+       With both maximizing ("greedy") and minimizing ("ungreedy"  or  "lazy")
+       repetition,  failure  of what follows normally causes the repeated item
+       to be re-evaluated to see if a different number of repeats  allows  the
+       rest  of  the pattern to match. Sometimes it is useful to prevent this,
+       either to change the nature of the match, or to cause it  fail  earlier
+       than  it otherwise might, when the author of the pattern knows there is
+       no point in carrying on.
+
+       Consider, for example, the pattern \d+foo when applied to  the  subject
+       line
+
+         123456bar
+
+       After matching all 6 digits and then failing to match "foo", the normal
+       action of the matcher is to try again with only 5 digits  matching  the
+       \d+  item,  and  then  with  4,  and  so on, before ultimately failing.
+       "Atomic grouping" (a term taken from Jeffrey  Friedl's  book)  provides
+       the  means for specifying that once a subpattern has matched, it is not
+       to be re-evaluated in this way.
+
+       If we use atomic grouping for the previous example, the  matcher  gives
+       up  immediately  on failing to match "foo" the first time. The notation
+       is a kind of special parenthesis, starting with (?> as in this example:
+
+         (?>\d+)foo
+
+       This kind of parenthesis "locks up" the  part of the  pattern  it  con-
+       tains  once  it  has matched, and a failure further into the pattern is
+       prevented from backtracking into it. Backtracking past it  to  previous
+       items, however, works as normal.
+
+       An  alternative  description  is that a subpattern of this type matches
+       the string of characters that an  identical  standalone  pattern  would
+       match, if anchored at the current point in the subject string.
+
+       Atomic grouping subpatterns are not capturing subpatterns. Simple cases
+       such as the above example can be thought of as a maximizing repeat that
+       must  swallow  everything  it can. So, while both \d+ and \d+? are pre-
+       pared to adjust the number of digits they match in order  to  make  the
+       rest of the pattern match, (?>\d+) can only match an entire sequence of
+       digits.
+
+       Atomic groups in general can of course contain arbitrarily  complicated
+       subpatterns,  and  can  be  nested. However, when the subpattern for an
+       atomic group is just a single repeated item, as in the example above, a
+       simpler  notation,  called  a "possessive quantifier" can be used. This
+       consists of an additional + character  following  a  quantifier.  Using
+       this notation, the previous example can be rewritten as
+
+         \d++foo
+
+       Note that a possessive quantifier can be used with an entire group, for
+       example:
+
+         (abc|xyz){2,3}+
+
+       Possessive  quantifiers  are  always  greedy;  the   setting   of   the
+       PCRE_UNGREEDY option is ignored. They are a convenient notation for the
+       simpler forms of atomic group. However, there is no difference  in  the
+       meaning  of  a  possessive  quantifier and the equivalent atomic group,
+       though there may be a performance  difference;  possessive  quantifiers
+       should be slightly faster.
+
+       The  possessive  quantifier syntax is an extension to the Perl 5.8 syn-
+       tax.  Jeffrey Friedl originated the idea (and the name)  in  the  first
+       edition of his book. Mike McCloskey liked it, so implemented it when he
+       built Sun's Java package, and PCRE copied it from there. It  ultimately
+       found its way into Perl at release 5.10.
+
+       PCRE has an optimization that automatically "possessifies" certain sim-
+       ple pattern constructs. For example, the sequence  A+B  is  treated  as
+       A++B  because  there is no point in backtracking into a sequence of A's
+       when B must follow.
+
+       When a pattern contains an unlimited repeat inside  a  subpattern  that
+       can  itself  be  repeated  an  unlimited number of times, the use of an
+       atomic group is the only way to avoid some  failing  matches  taking  a
+       very long time indeed. The pattern
+
+         (\D+|<\d+>)*[!?]
+
+       matches  an  unlimited number of substrings that either consist of non-
+       digits, or digits enclosed in <>, followed by either ! or  ?.  When  it
+       matches, it runs quickly. However, if it is applied to
+
+         aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+
+       it  takes  a  long  time  before reporting failure. This is because the
+       string can be divided between the internal \D+ repeat and the  external
+       *  repeat  in  a  large  number of ways, and all have to be tried. (The
+       example uses [!?] rather than a single character at  the  end,  because
+       both  PCRE  and  Perl have an optimization that allows for fast failure
+       when a single character is used. They remember the last single  charac-
+       ter  that  is required for a match, and fail early if it is not present
+       in the string.) If the pattern is changed so that  it  uses  an  atomic
+       group, like this:
+
+         ((?>\D+)|<\d+>)*[!?]
+
+       sequences of non-digits cannot be broken, and failure happens quickly.
+
+
+BACK REFERENCES
+
+       Outside a character class, a backslash followed by a digit greater than
+       0 (and possibly further digits) is a back reference to a capturing sub-
+       pattern  earlier  (that is, to its left) in the pattern, provided there
+       have been that many previous capturing left parentheses.
+
+       However, if the decimal number following the backslash is less than 10,
+       it  is  always  taken  as a back reference, and causes an error only if
+       there are not that many capturing left parentheses in the  entire  pat-
+       tern.  In  other words, the parentheses that are referenced need not be
+       to the left of the reference for numbers less than 10. A "forward  back
+       reference"  of  this  type can make sense when a repetition is involved
+       and the subpattern to the right has participated in an  earlier  itera-
+       tion.
+
+       It  is  not  possible to have a numerical "forward back reference" to a
+       subpattern whose number is 10 or  more  using  this  syntax  because  a
+       sequence  such  as  \50 is interpreted as a character defined in octal.
+       See the subsection entitled "Non-printing characters" above for further
+       details  of  the  handling of digits following a backslash. There is no
+       such problem when named parentheses are used. A back reference  to  any
+       subpattern is possible using named parentheses (see below).
+
+       Another  way  of  avoiding  the ambiguity inherent in the use of digits
+       following a backslash is to use the \g  escape  sequence.  This  escape
+       must be followed by an unsigned number or a negative number, optionally
+       enclosed in braces. These examples are all identical:
+
+         (ring), \1
+         (ring), \g1
+         (ring), \g{1}
+
+       An unsigned number specifies an absolute reference without the  ambigu-
+       ity that is present in the older syntax. It is also useful when literal
+       digits follow the reference. A negative number is a relative reference.
+       Consider this example:
+
+         (abc(def)ghi)\g{-1}
+
+       The sequence \g{-1} is a reference to the most recently started captur-
+       ing subpattern before \g, that is, is it equivalent to \2 in this exam-
+       ple.   Similarly, \g{-2} would be equivalent to \1. The use of relative
+       references can be helpful in long patterns, and also in  patterns  that
+       are  created  by  joining  together  fragments  that contain references
+       within themselves.
+
+       A back reference matches whatever actually matched the  capturing  sub-
+       pattern  in  the  current subject string, rather than anything matching
+       the subpattern itself (see "Subpatterns as subroutines" below for a way
+       of doing that). So the pattern
+
+         (sens|respons)e and \1ibility
+
+       matches  "sense and sensibility" and "response and responsibility", but
+       not "sense and responsibility". If caseful matching is in force at  the
+       time  of the back reference, the case of letters is relevant. For exam-
+       ple,
+
+         ((?i)rah)\s+\1
+
+       matches "rah rah" and "RAH RAH", but not "RAH  rah",  even  though  the
+       original capturing subpattern is matched caselessly.
+
+       There  are  several  different ways of writing back references to named
+       subpatterns. The .NET syntax \k{name} and the Perl syntax  \k<name>  or
+       \k'name'  are supported, as is the Python syntax (?P=name). Perl 5.10's
+       unified back reference syntax, in which \g can be used for both numeric
+       and  named  references,  is  also supported. We could rewrite the above
+       example in any of the following ways:
+
+         (?<p1>(?i)rah)\s+\k<p1>
+         (?'p1'(?i)rah)\s+\k{p1}
+         (?P<p1>(?i)rah)\s+(?P=p1)
+         (?<p1>(?i)rah)\s+\g{p1}
+
+       A subpattern that is referenced by  name  may  appear  in  the  pattern
+       before or after the reference.
+
+       There  may be more than one back reference to the same subpattern. If a
+       subpattern has not actually been used in a particular match,  any  back
+       references to it always fail by default. For example, the pattern
+
+         (a|(bc))\2
+
+       always  fails  if  it starts to match "a" rather than "bc". However, if
+       the PCRE_JAVASCRIPT_COMPAT option is set at compile time, a back refer-
+       ence to an unset value matches an empty string.
+
+       Because  there may be many capturing parentheses in a pattern, all dig-
+       its following a backslash are taken as part of a potential back  refer-
+       ence  number.   If  the  pattern continues with a digit character, some
+       delimiter must  be  used  to  terminate  the  back  reference.  If  the
+       PCRE_EXTENDED  option  is  set, this can be white space. Otherwise, the
+       \g{ syntax or an empty comment (see "Comments" below) can be used.
+
+   Recursive back references
+
+       A back reference that occurs inside the parentheses to which it  refers
+       fails  when  the subpattern is first used, so, for example, (a\1) never
+       matches.  However, such references can be useful inside  repeated  sub-
+       patterns. For example, the pattern
+
+         (a|b\1)+
+
+       matches any number of "a"s and also "aba", "ababbaa" etc. At each iter-
+       ation of the subpattern,  the  back  reference  matches  the  character
+       string  corresponding  to  the previous iteration. In order for this to
+       work, the pattern must be such that the first iteration does  not  need
+       to  match the back reference. This can be done using alternation, as in
+       the example above, or by a quantifier with a minimum of zero.
+
+       Back references of this type cause the group that they reference to  be
+       treated  as  an atomic group.  Once the whole group has been matched, a
+       subsequent matching failure cannot cause backtracking into  the  middle
+       of the group.
+
+
+ASSERTIONS
+
+       An  assertion  is  a  test on the characters following or preceding the
+       current matching point that does not actually consume  any  characters.
+       The  simple  assertions  coded  as  \b, \B, \A, \G, \Z, \z, ^ and $ are
+       described above.
+
+       More complicated assertions are coded as  subpatterns.  There  are  two
+       kinds:  those  that  look  ahead of the current position in the subject
+       string, and those that look  behind  it.  An  assertion  subpattern  is
+       matched  in  the  normal way, except that it does not cause the current
+       matching position to be changed.
+
+       Assertion subpatterns are not capturing subpatterns. If such an  asser-
+       tion  contains  capturing  subpatterns within it, these are counted for
+       the purposes of numbering the capturing subpatterns in the  whole  pat-
+       tern.  However,  substring  capturing  is carried out only for positive
+       assertions, because it does not make sense for negative assertions.
+
+       For compatibility with Perl, assertion  subpatterns  may  be  repeated;
+       though  it  makes  no sense to assert the same thing several times, the
+       side effect of capturing parentheses may  occasionally  be  useful.  In
+       practice, there only three cases:
+
+       (1)  If  the  quantifier  is  {0}, the assertion is never obeyed during
+       matching.  However, it may  contain  internal  capturing  parenthesized
+       groups that are called from elsewhere via the subroutine mechanism.
+
+       (2)  If quantifier is {0,n} where n is greater than zero, it is treated
+       as if it were {0,1}. At run time, the rest  of  the  pattern  match  is
+       tried with and without the assertion, the order depending on the greed-
+       iness of the quantifier.
+
+       (3) If the minimum repetition is greater than zero, the  quantifier  is
+       ignored.   The  assertion  is  obeyed just once when encountered during
+       matching.
+
+   Lookahead assertions
+
+       Lookahead assertions start with (?= for positive assertions and (?! for
+       negative assertions. For example,
+
+         \w+(?=;)
+
+       matches  a word followed by a semicolon, but does not include the semi-
+       colon in the match, and
+
+         foo(?!bar)
+
+       matches any occurrence of "foo" that is not  followed  by  "bar".  Note
+       that the apparently similar pattern
+
+         (?!foo)bar
+
+       does  not  find  an  occurrence  of "bar" that is preceded by something
+       other than "foo"; it finds any occurrence of "bar" whatsoever,  because
+       the assertion (?!foo) is always true when the next three characters are
+       "bar". A lookbehind assertion is needed to achieve the other effect.
+
+       If you want to force a matching failure at some point in a pattern, the
+       most  convenient  way  to  do  it  is with (?!) because an empty string
+       always matches, so an assertion that requires there not to be an  empty
+       string must always fail.  The backtracking control verb (*FAIL) or (*F)
+       is a synonym for (?!).
+
+   Lookbehind assertions
+
+       Lookbehind assertions start with (?<= for positive assertions and  (?<!
+       for negative assertions. For example,
+
+         (?<!foo)bar
+
+       does  find  an  occurrence  of "bar" that is not preceded by "foo". The
+       contents of a lookbehind assertion are restricted  such  that  all  the
+       strings it matches must have a fixed length. However, if there are sev-
+       eral top-level alternatives, they do not all  have  to  have  the  same
+       fixed length. Thus
+
+         (?<=bullock|donkey)
+
+       is permitted, but
+
+         (?<!dogs?|cats?)
+
+       causes  an  error at compile time. Branches that match different length
+       strings are permitted only at the top level of a lookbehind  assertion.
+       This is an extension compared with Perl, which requires all branches to
+       match the same length of string. An assertion such as
+
+         (?<=ab(c|de))
+
+       is not permitted, because its single top-level  branch  can  match  two
+       different lengths, but it is acceptable to PCRE if rewritten to use two
+       top-level branches:
+
+         (?<=abc|abde)
+
+       In some cases, the escape sequence \K (see above) can be  used  instead
+       of a lookbehind assertion to get round the fixed-length restriction.
+
+       The  implementation  of lookbehind assertions is, for each alternative,
+       to temporarily move the current position back by the fixed  length  and
+       then try to match. If there are insufficient characters before the cur-
+       rent position, the assertion fails.
+
+       In a UTF mode, PCRE does not allow the \C escape (which matches a  sin-
+       gle  data  unit even in a UTF mode) to appear in lookbehind assertions,
+       because it makes it impossible to calculate the length of  the  lookbe-
+       hind.  The \X and \R escapes, which can match different numbers of data
+       units, are also not permitted.
+
+       "Subroutine" calls (see below) such as (?2) or (?&X) are  permitted  in
+       lookbehinds,  as  long as the subpattern matches a fixed-length string.
+       Recursion, however, is not supported.
+
+       Possessive quantifiers can  be  used  in  conjunction  with  lookbehind
+       assertions to specify efficient matching of fixed-length strings at the
+       end of subject strings. Consider a simple pattern such as
+
+         abcd$
+
+       when applied to a long string that does  not  match.  Because  matching
+       proceeds from left to right, PCRE will look for each "a" in the subject
+       and then see if what follows matches the rest of the  pattern.  If  the
+       pattern is specified as
+
+         ^.*abcd$
+
+       the  initial .* matches the entire string at first, but when this fails
+       (because there is no following "a"), it backtracks to match all but the
+       last  character,  then all but the last two characters, and so on. Once
+       again the search for "a" covers the entire string, from right to  left,
+       so we are no better off. However, if the pattern is written as
+
+         ^.*+(?<=abcd)
+
+       there  can  be  no backtracking for the .*+ item; it can match only the
+       entire string. The subsequent lookbehind assertion does a  single  test
+       on  the last four characters. If it fails, the match fails immediately.
+       For long strings, this approach makes a significant difference  to  the
+       processing time.
+
+   Using multiple assertions
+
+       Several assertions (of any sort) may occur in succession. For example,
+
+         (?<=\d{3})(?<!999)foo
+
+       matches  "foo" preceded by three digits that are not "999". Notice that
+       each of the assertions is applied independently at the  same  point  in
+       the  subject  string.  First  there  is a check that the previous three
+       characters are all digits, and then there is  a  check  that  the  same
+       three characters are not "999".  This pattern does not match "foo" pre-
+       ceded by six characters, the first of which are  digits  and  the  last
+       three  of  which  are not "999". For example, it doesn't match "123abc-
+       foo". A pattern to do that is
+
+         (?<=\d{3}...)(?<!999)foo
+
+       This time the first assertion looks at the  preceding  six  characters,
+       checking that the first three are digits, and then the second assertion
+       checks that the preceding three characters are not "999".
+
+       Assertions can be nested in any combination. For example,
+
+         (?<=(?<!foo)bar)baz
+
+       matches an occurrence of "baz" that is preceded by "bar" which in  turn
+       is not preceded by "foo", while
+
+         (?<=\d{3}(?!999)...)foo
+
+       is  another pattern that matches "foo" preceded by three digits and any
+       three characters that are not "999".
+
+
+CONDITIONAL SUBPATTERNS
+
+       It is possible to cause the matching process to obey a subpattern  con-
+       ditionally  or to choose between two alternative subpatterns, depending
+       on the result of an assertion, or whether a specific capturing  subpat-
+       tern  has  already  been matched. The two possible forms of conditional
+       subpattern are:
+
+         (?(condition)yes-pattern)
+         (?(condition)yes-pattern|no-pattern)
+
+       If the condition is satisfied, the yes-pattern is used;  otherwise  the
+       no-pattern  (if  present)  is used. If there are more than two alterna-
+       tives in the subpattern, a compile-time error occurs. Each of  the  two
+       alternatives may itself contain nested subpatterns of any form, includ-
+       ing  conditional  subpatterns;  the  restriction  to  two  alternatives
+       applies only at the level of the condition. This pattern fragment is an
+       example where the alternatives are complex:
+
+         (?(1) (A|B|C) | (D | (?(2)E|F) | E) )
+
+
+       There are four kinds of condition: references  to  subpatterns,  refer-
+       ences to recursion, a pseudo-condition called DEFINE, and assertions.
+
+   Checking for a used subpattern by number
+
+       If  the  text between the parentheses consists of a sequence of digits,
+       the condition is true if a capturing subpattern of that number has pre-
+       viously  matched.  If  there is more than one capturing subpattern with
+       the same number (see the earlier  section  about  duplicate  subpattern
+       numbers),  the condition is true if any of them have matched. An alter-
+       native notation is to precede the digits with a plus or minus sign.  In
+       this  case, the subpattern number is relative rather than absolute. The
+       most recently opened parentheses can be referenced by (?(-1), the  next
+       most  recent  by (?(-2), and so on. Inside loops it can also make sense
+       to refer to subsequent groups. The next parentheses to be opened can be
+       referenced  as (?(+1), and so on. (The value zero in any of these forms
+       is not used; it provokes a compile-time error.)
+
+       Consider the following pattern, which  contains  non-significant  white
+       space to make it more readable (assume the PCRE_EXTENDED option) and to
+       divide it into three parts for ease of discussion:
+
+         ( \( )?    [^()]+    (?(1) \) )
+
+       The first part matches an optional opening  parenthesis,  and  if  that
+       character is present, sets it as the first captured substring. The sec-
+       ond part matches one or more characters that are not  parentheses.  The
+       third  part  is  a conditional subpattern that tests whether or not the
+       first set of parentheses matched. If they  did,  that  is,  if  subject
+       started  with an opening parenthesis, the condition is true, and so the
+       yes-pattern is executed and a closing parenthesis is  required.  Other-
+       wise,  since no-pattern is not present, the subpattern matches nothing.
+       In other words, this pattern matches  a  sequence  of  non-parentheses,
+       optionally enclosed in parentheses.
+
+       If  you  were  embedding  this pattern in a larger one, you could use a
+       relative reference:
+
+         ...other stuff... ( \( )?    [^()]+    (?(-1) \) ) ...
+
+       This makes the fragment independent of the parentheses  in  the  larger
+       pattern.
+
+   Checking for a used subpattern by name
+
+       Perl  uses  the  syntax  (?(<name>)...) or (?('name')...) to test for a
+       used subpattern by name. For compatibility  with  earlier  versions  of
+       PCRE,  which  had this facility before Perl, the syntax (?(name)...) is
+       also recognized. However, there is a possible ambiguity with this  syn-
+       tax,  because  subpattern  names  may  consist entirely of digits. PCRE
+       looks first for a named subpattern; if it cannot find one and the  name
+       consists  entirely  of digits, PCRE looks for a subpattern of that num-
+       ber, which must be greater than zero. Using subpattern names that  con-
+       sist entirely of digits is not recommended.
+
+       Rewriting the above example to use a named subpattern gives this:
+
+         (?<OPEN> \( )?    [^()]+    (?(<OPEN>) \) )
+
+       If  the  name used in a condition of this kind is a duplicate, the test
+       is applied to all subpatterns of the same name, and is true if any  one
+       of them has matched.
+
+   Checking for pattern recursion
+
+       If the condition is the string (R), and there is no subpattern with the
+       name R, the condition is true if a recursive call to the whole  pattern
+       or any subpattern has been made. If digits or a name preceded by amper-
+       sand follow the letter R, for example:
+
+         (?(R3)...) or (?(R&name)...)
+
+       the condition is true if the most recent recursion is into a subpattern
+       whose number or name is given. This condition does not check the entire
+       recursion stack. If the name used in a condition  of  this  kind  is  a
+       duplicate, the test is applied to all subpatterns of the same name, and
+       is true if any one of them is the most recent recursion.
+
+       At "top level", all these recursion test  conditions  are  false.   The
+       syntax for recursive patterns is described below.
+
+   Defining subpatterns for use by reference only
+
+       If  the  condition  is  the string (DEFINE), and there is no subpattern
+       with the name DEFINE, the condition is  always  false.  In  this  case,
+       there  may  be  only  one  alternative  in the subpattern. It is always
+       skipped if control reaches this point  in  the  pattern;  the  idea  of
+       DEFINE  is that it can be used to define subroutines that can be refer-
+       enced from elsewhere. (The use of subroutines is described below.)  For
+       example,  a  pattern  to match an IPv4 address such as "192.168.23.245"
+       could be written like this (ignore white space and line breaks):
+
+         (?(DEFINE) (?<byte> 2[0-4]\d | 25[0-5] | 1\d\d | [1-9]?\d) )
+         \b (?&byte) (\.(?&byte)){3} \b
+
+       The first part of the pattern is a DEFINE group inside which a  another
+       group  named "byte" is defined. This matches an individual component of
+       an IPv4 address (a number less than 256). When  matching  takes  place,
+       this  part  of  the pattern is skipped because DEFINE acts like a false
+       condition. The rest of the pattern uses references to the  named  group
+       to  match the four dot-separated components of an IPv4 address, insist-
+       ing on a word boundary at each end.
+
+   Assertion conditions
+
+       If the condition is not in any of the above  formats,  it  must  be  an
+       assertion.   This may be a positive or negative lookahead or lookbehind
+       assertion. Consider  this  pattern,  again  containing  non-significant
+       white space, and with the two alternatives on the second line:
+
+         (?(?=[^a-z]*[a-z])
+         \d{2}-[a-z]{3}-\d{2}  |  \d{2}-\d{2}-\d{2} )
+
+       The  condition  is  a  positive  lookahead  assertion  that  matches an
+       optional sequence of non-letters followed by a letter. In other  words,
+       it  tests  for the presence of at least one letter in the subject. If a
+       letter is found, the subject is matched against the first  alternative;
+       otherwise  it  is  matched  against  the  second.  This pattern matches
+       strings in one of the two forms dd-aaa-dd or dd-dd-dd,  where  aaa  are
+       letters and dd are digits.
+
+
+COMMENTS
+
+       There are two ways of including comments in patterns that are processed
+       by PCRE. In both cases, the start of the comment must not be in a char-
+       acter class, nor in the middle of any other sequence of related charac-
+       ters such as (?: or a subpattern name or number.  The  characters  that
+       make up a comment play no part in the pattern matching.
+
+       The  sequence (?# marks the start of a comment that continues up to the
+       next closing parenthesis. Nested parentheses are not permitted. If  the
+       PCRE_EXTENDED option is set, an unescaped # character also introduces a
+       comment, which in this case continues to  immediately  after  the  next
+       newline  character  or character sequence in the pattern. Which charac-
+       ters are interpreted as newlines is controlled by the options passed to
+       a  compiling function or by a special sequence at the start of the pat-
+       tern, as described in the section entitled "Newline conventions" above.
+       Note that the end of this type of comment is a literal newline sequence
+       in the pattern; escape sequences that happen to represent a newline  do
+       not  count.  For  example,  consider this pattern when PCRE_EXTENDED is
+       set, and the default newline convention is in force:
+
+         abc #comment \n still comment
+
+       On encountering the # character, pcre_compile()  skips  along,  looking
+       for  a newline in the pattern. The sequence \n is still literal at this
+       stage, so it does not terminate the comment. Only an  actual  character
+       with the code value 0x0a (the default newline) does so.
+
+
+RECURSIVE PATTERNS
+
+       Consider  the problem of matching a string in parentheses, allowing for
+       unlimited nested parentheses. Without the use of  recursion,  the  best
+       that  can  be  done  is  to use a pattern that matches up to some fixed
+       depth of nesting. It is not possible to  handle  an  arbitrary  nesting
+       depth.
+
+       For some time, Perl has provided a facility that allows regular expres-
+       sions to recurse (amongst other things). It does this by  interpolating
+       Perl  code in the expression at run time, and the code can refer to the
+       expression itself. A Perl pattern using code interpolation to solve the
+       parentheses problem can be created like this:
+
+         $re = qr{\( (?: (?>[^()]+) | (?p{$re}) )* \)}x;
+
+       The (?p{...}) item interpolates Perl code at run time, and in this case
+       refers recursively to the pattern in which it appears.
+
+       Obviously, PCRE cannot support the interpolation of Perl code. Instead,
+       it  supports  special  syntax  for recursion of the entire pattern, and
+       also for individual subpattern recursion.  After  its  introduction  in
+       PCRE  and  Python,  this  kind of recursion was subsequently introduced
+       into Perl at release 5.10.
+
+       A special item that consists of (? followed by a  number  greater  than
+       zero  and  a  closing parenthesis is a recursive subroutine call of the
+       subpattern of the given number, provided that  it  occurs  inside  that
+       subpattern.  (If  not,  it is a non-recursive subroutine call, which is
+       described in the next section.) The special item  (?R)  or  (?0)  is  a
+       recursive call of the entire regular expression.
+
+       This  PCRE  pattern  solves  the nested parentheses problem (assume the
+       PCRE_EXTENDED option is set so that white space is ignored):
+
+         \( ( [^()]++ | (?R) )* \)
+
+       First it matches an opening parenthesis. Then it matches any number  of
+       substrings  which  can  either  be  a sequence of non-parentheses, or a
+       recursive match of the pattern itself (that is, a  correctly  parenthe-
+       sized substring).  Finally there is a closing parenthesis. Note the use
+       of a possessive quantifier to avoid backtracking into sequences of non-
+       parentheses.
+
+       If  this  were  part of a larger pattern, you would not want to recurse
+       the entire pattern, so instead you could use this:
+
+         ( \( ( [^()]++ | (?1) )* \) )
+
+       We have put the pattern into parentheses, and caused the  recursion  to
+       refer to them instead of the whole pattern.
+
+       In  a  larger  pattern,  keeping  track  of  parenthesis numbers can be
+       tricky. This is made easier by the use of relative references.  Instead
+       of (?1) in the pattern above you can write (?-2) to refer to the second
+       most recently opened parentheses  preceding  the  recursion.  In  other
+       words,  a  negative  number counts capturing parentheses leftwards from
+       the point at which it is encountered.
+
+       It is also possible to refer to  subsequently  opened  parentheses,  by
+       writing  references  such  as (?+2). However, these cannot be recursive
+       because the reference is not inside the  parentheses  that  are  refer-
+       enced.  They are always non-recursive subroutine calls, as described in
+       the next section.
+
+       An alternative approach is to use named parentheses instead.  The  Perl
+       syntax  for  this  is (?&name); PCRE's earlier syntax (?P>name) is also
+       supported. We could rewrite the above example as follows:
+
+         (?<pn> \( ( [^()]++ | (?&pn) )* \) )
+
+       If there is more than one subpattern with the same name,  the  earliest
+       one is used.
+
+       This  particular  example pattern that we have been looking at contains
+       nested unlimited repeats, and so the use of a possessive quantifier for
+       matching strings of non-parentheses is important when applying the pat-
+       tern to strings that do not match. For example, when  this  pattern  is
+       applied to
+
+         (aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa()
+
+       it  yields  "no  match" quickly. However, if a possessive quantifier is
+       not used, the match runs for a very long time indeed because there  are
+       so  many  different  ways the + and * repeats can carve up the subject,
+       and all have to be tested before failure can be reported.
+
+       At the end of a match, the values of capturing  parentheses  are  those
+       from  the outermost level. If you want to obtain intermediate values, a
+       callout function can be used (see below and the pcrecallout  documenta-
+       tion). If the pattern above is matched against
+
+         (ab(cd)ef)
+
+       the  value  for  the  inner capturing parentheses (numbered 2) is "ef",
+       which is the last value taken on at the top level. If a capturing  sub-
+       pattern  is  not  matched at the top level, its final captured value is
+       unset, even if it was (temporarily) set at a deeper  level  during  the
+       matching process.
+
+       If  there are more than 15 capturing parentheses in a pattern, PCRE has
+       to obtain extra memory to store data during a recursion, which it  does
+       by using pcre_malloc, freeing it via pcre_free afterwards. If no memory
+       can be obtained, the match fails with the PCRE_ERROR_NOMEMORY error.
+
+       Do not confuse the (?R) item with the condition (R),  which  tests  for
+       recursion.   Consider  this pattern, which matches text in angle brack-
+       ets, allowing for arbitrary nesting. Only digits are allowed in  nested
+       brackets  (that is, when recursing), whereas any characters are permit-
+       ted at the outer level.
+
+         < (?: (?(R) \d++  | [^<>]*+) | (?R)) * >
+
+       In this pattern, (?(R) is the start of a conditional  subpattern,  with
+       two  different  alternatives for the recursive and non-recursive cases.
+       The (?R) item is the actual recursive call.
+
+   Differences in recursion processing between PCRE and Perl
+
+       Recursion processing in PCRE differs from Perl in two  important  ways.
+       In  PCRE (like Python, but unlike Perl), a recursive subpattern call is
+       always treated as an atomic group. That is, once it has matched some of
+       the subject string, it is never re-entered, even if it contains untried
+       alternatives and there is a subsequent matching failure.  This  can  be
+       illustrated  by the following pattern, which purports to match a palin-
+       dromic string that contains an odd number of characters  (for  example,
+       "a", "aba", "abcba", "abcdcba"):
+
+         ^(.|(.)(?1)\2)$
+
+       The idea is that it either matches a single character, or two identical
+       characters surrounding a sub-palindrome. In Perl, this  pattern  works;
+       in  PCRE  it  does  not if the pattern is longer than three characters.
+       Consider the subject string "abcba":
+
+       At the top level, the first character is matched, but as it is  not  at
+       the end of the string, the first alternative fails; the second alterna-
+       tive is taken and the recursion kicks in. The recursive call to subpat-
+       tern  1  successfully  matches the next character ("b"). (Note that the
+       beginning and end of line tests are not part of the recursion).
+
+       Back at the top level, the next character ("c") is compared  with  what
+       subpattern  2 matched, which was "a". This fails. Because the recursion
+       is treated as an atomic group, there are now  no  backtracking  points,
+       and  so  the  entire  match fails. (Perl is able, at this point, to re-
+       enter the recursion and try the second alternative.)  However,  if  the
+       pattern is written with the alternatives in the other order, things are
+       different:
+
+         ^((.)(?1)\2|.)$
+
+       This time, the recursing alternative is tried first, and  continues  to
+       recurse  until  it runs out of characters, at which point the recursion
+       fails. But this time we do have  another  alternative  to  try  at  the
+       higher  level.  That  is  the  big difference: in the previous case the
+       remaining alternative is at a deeper recursion level, which PCRE cannot
+       use.
+
+       To  change  the pattern so that it matches all palindromic strings, not
+       just those with an odd number of characters, it is tempting  to  change
+       the pattern to this:
+
+         ^((.)(?1)\2|.?)$
+
+       Again,  this  works  in Perl, but not in PCRE, and for the same reason.
+       When a deeper recursion has matched a single character,  it  cannot  be
+       entered  again  in  order  to match an empty string. The solution is to
+       separate the two cases, and write out the odd and even cases as  alter-
+       natives at the higher level:
+
+         ^(?:((.)(?1)\2|)|((.)(?3)\4|.))
+
+       If  you  want  to match typical palindromic phrases, the pattern has to
+       ignore all non-word characters, which can be done like this:
+
+         ^\W*+(?:((.)\W*+(?1)\W*+\2|)|((.)\W*+(?3)\W*+\4|\W*+.\W*+))\W*+$
+
+       If run with the PCRE_CASELESS option, this pattern matches phrases such
+       as "A man, a plan, a canal: Panama!" and it works well in both PCRE and
+       Perl. Note the use of the possessive quantifier *+ to avoid  backtrack-
+       ing  into  sequences of non-word characters. Without this, PCRE takes a
+       great deal longer (ten times or more) to  match  typical  phrases,  and
+       Perl takes so long that you think it has gone into a loop.
+
+       WARNING:  The  palindrome-matching patterns above work only if the sub-
+       ject string does not start with a palindrome that is shorter  than  the
+       entire  string.  For example, although "abcba" is correctly matched, if
+       the subject is "ababa", PCRE finds the palindrome "aba" at  the  start,
+       then  fails at top level because the end of the string does not follow.
+       Once again, it cannot jump back into the recursion to try other  alter-
+       natives, so the entire match fails.
+
+       The  second  way  in which PCRE and Perl differ in their recursion pro-
+       cessing is in the handling of captured values. In Perl, when a  subpat-
+       tern  is  called recursively or as a subpattern (see the next section),
+       it has no access to any values that were captured  outside  the  recur-
+       sion,  whereas  in  PCRE  these values can be referenced. Consider this
+       pattern:
+
+         ^(.)(\1|a(?2))
+
+       In PCRE, this pattern matches "bab". The  first  capturing  parentheses
+       match  "b",  then in the second group, when the back reference \1 fails
+       to match "b", the second alternative matches "a" and then recurses.  In
+       the  recursion,  \1 does now match "b" and so the whole match succeeds.
+       In Perl, the pattern fails to match because inside the  recursive  call
+       \1 cannot access the externally set value.
+
+
+SUBPATTERNS AS SUBROUTINES
+
+       If  the  syntax for a recursive subpattern call (either by number or by
+       name) is used outside the parentheses to which it refers,  it  operates
+       like  a subroutine in a programming language. The called subpattern may
+       be defined before or after the reference. A numbered reference  can  be
+       absolute or relative, as in these examples:
+
+         (...(absolute)...)...(?2)...
+         (...(relative)...)...(?-1)...
+         (...(?+1)...(relative)...
+
+       An earlier example pointed out that the pattern
+
+         (sens|respons)e and \1ibility
+
+       matches  "sense and sensibility" and "response and responsibility", but
+       not "sense and responsibility". If instead the pattern
+
+         (sens|respons)e and (?1)ibility
+
+       is used, it does match "sense and responsibility" as well as the  other
+       two  strings.  Another  example  is  given  in the discussion of DEFINE
+       above.
+
+       All subroutine calls, whether recursive or not, are always  treated  as
+       atomic  groups. That is, once a subroutine has matched some of the sub-
+       ject string, it is never re-entered, even if it contains untried alter-
+       natives  and  there  is  a  subsequent  matching failure. Any capturing
+       parentheses that are set during the subroutine  call  revert  to  their
+       previous values afterwards.
+
+       Processing  options  such as case-independence are fixed when a subpat-
+       tern is defined, so if it is used as a subroutine, such options  cannot
+       be changed for different calls. For example, consider this pattern:
+
+         (abc)(?i:(?-1))
+
+       It  matches  "abcabc". It does not match "abcABC" because the change of
+       processing option does not affect the called subpattern.
+
+
+ONIGURUMA SUBROUTINE SYNTAX
+
+       For compatibility with Oniguruma, the non-Perl syntax \g followed by  a
+       name or a number enclosed either in angle brackets or single quotes, is
+       an alternative syntax for referencing a  subpattern  as  a  subroutine,
+       possibly  recursively. Here are two of the examples used above, rewrit-
+       ten using this syntax:
+
+         (?<pn> \( ( (?>[^()]+) | \g<pn> )* \) )
+         (sens|respons)e and \g'1'ibility
+
+       PCRE supports an extension to Oniguruma: if a number is preceded  by  a
+       plus or a minus sign it is taken as a relative reference. For example:
+
+         (abc)(?i:\g<-1>)
+
+       Note  that \g{...} (Perl syntax) and \g<...> (Oniguruma syntax) are not
+       synonymous. The former is a back reference; the latter is a  subroutine
+       call.
+
+
+CALLOUTS
+
+       Perl has a feature whereby using the sequence (?{...}) causes arbitrary
+       Perl code to be obeyed in the middle of matching a regular  expression.
+       This makes it possible, amongst other things, to extract different sub-
+       strings that match the same pair of parentheses when there is a repeti-
+       tion.
+
+       PCRE provides a similar feature, but of course it cannot obey arbitrary
+       Perl code. The feature is called "callout". The caller of PCRE provides
+       an  external function by putting its entry point in the global variable
+       pcre_callout (8-bit library) or  pcre16_callout  (16-bit  library).  By
+       default, this variable contains NULL, which disables all calling out.
+
+       Within  a  regular  expression,  (?C) indicates the points at which the
+       external function is to be called. If you want  to  identify  different
+       callout  points, you can put a number less than 256 after the letter C.
+       The default value is zero.  For example, this pattern has  two  callout
+       points:
+
+         (?C1)abc(?C2)def
+
+       If  the PCRE_AUTO_CALLOUT flag is passed to a compiling function, call-
+       outs are automatically installed before each item in the pattern.  They
+       are all numbered 255.
+
+       During  matching, when PCRE reaches a callout point, the external func-
+       tion is called. It is provided with the  number  of  the  callout,  the
+       position  in  the pattern, and, optionally, one item of data originally
+       supplied by the caller of the matching function. The  callout  function
+       may  cause  matching to proceed, to backtrack, or to fail altogether. A
+       complete description of the interface to the callout function is  given
+       in the pcrecallout documentation.
+
+
+BACKTRACKING CONTROL
+
+       Perl  5.10 introduced a number of "Special Backtracking Control Verbs",
+       which are described in the Perl documentation as "experimental and sub-
+       ject  to  change or removal in a future version of Perl". It goes on to
+       say: "Their usage in production code should be noted to avoid  problems
+       during upgrades." The same remarks apply to the PCRE features described
+       in this section.
+
+       Since these verbs are specifically related  to  backtracking,  most  of
+       them  can  be  used only when the pattern is to be matched using one of
+       the traditional matching functions, which use a backtracking algorithm.
+       With  the  exception  of (*FAIL), which behaves like a failing negative
+       assertion, they cause an error if encountered by a DFA  matching  func-
+       tion.
+
+       If  any of these verbs are used in an assertion or in a subpattern that
+       is called as a subroutine (whether or not recursively), their effect is
+       confined to that subpattern; it does not extend to the surrounding pat-
+       tern, with one exception: the name from a *(MARK), (*PRUNE), or (*THEN)
+       that  is  encountered in a successful positive assertion is passed back
+       when a match succeeds (compare capturing  parentheses  in  assertions).
+       Note that such subpatterns are processed as anchored at the point where
+       they are tested. Note also that Perl's  treatment  of  subroutines  and
+       assertions is different in some cases.
+
+       The  new verbs make use of what was previously invalid syntax: an open-
+       ing parenthesis followed by an asterisk. They are generally of the form
+       (*VERB)  or (*VERB:NAME). Some may take either form, with differing be-
+       haviour, depending on whether or not an argument is present. A name  is
+       any sequence of characters that does not include a closing parenthesis.
+       The maximum length of name is 255 in the 8-bit library and 65535 in the
+       16-bit library. If the name is empty, that is, if the closing parenthe-
+       sis immediately follows the colon, the effect is as if the  colon  were
+       not there. Any number of these verbs may occur in a pattern.
+
+   Optimizations that affect backtracking verbs
+
+       PCRE  contains some optimizations that are used to speed up matching by
+       running some checks at the start of each match attempt. For example, it
+       may  know  the minimum length of matching subject, or that a particular
+       character must be present. When one of these  optimizations  suppresses
+       the  running  of  a match, any included backtracking verbs will not, of
+       course, be processed. You can suppress the start-of-match optimizations
+       by  setting  the  PCRE_NO_START_OPTIMIZE  option when calling pcre_com-
+       pile() or pcre_exec(), or by starting the pattern with (*NO_START_OPT).
+       There is more discussion of this option in the section entitled "Option
+       bits for pcre_exec()" in the pcreapi documentation.
+
+       Experiments with Perl suggest that it too  has  similar  optimizations,
+       sometimes leading to anomalous results.
+
+   Verbs that act immediately
+
+       The  following  verbs act as soon as they are encountered. They may not
+       be followed by a name.
+
+          (*ACCEPT)
+
+       This verb causes the match to end successfully, skipping the  remainder
+       of  the pattern. However, when it is inside a subpattern that is called
+       as a subroutine, only that subpattern is ended  successfully.  Matching
+       then  continues  at  the  outer level. If (*ACCEPT) is inside capturing
+       parentheses, the data so far is captured. For example:
+
+         A((?:A|B(*ACCEPT)|C)D)
+
+       This matches "AB", "AAD", or "ACD"; when it matches "AB", "B"  is  cap-
+       tured by the outer parentheses.
+
+         (*FAIL) or (*F)
+
+       This  verb causes a matching failure, forcing backtracking to occur. It
+       is equivalent to (?!) but easier to read. The Perl documentation  notes
+       that  it  is  probably  useful only when combined with (?{}) or (??{}).
+       Those are, of course, Perl features that are not present in  PCRE.  The
+       nearest  equivalent is the callout feature, as for example in this pat-
+       tern:
+
+         a+(?C)(*FAIL)
+
+       A match with the string "aaaa" always fails, but the callout  is  taken
+       before each backtrack happens (in this example, 10 times).
+
+   Recording which path was taken
+
+       There  is  one  verb  whose  main  purpose  is to track how a match was
+       arrived at, though it also has a  secondary  use  in  conjunction  with
+       advancing the match starting point (see (*SKIP) below).
+
+         (*MARK:NAME) or (*:NAME)
+
+       A  name  is  always  required  with  this  verb.  There  may be as many
+       instances of (*MARK) as you like in a pattern, and their names  do  not
+       have to be unique.
+
+       When  a match succeeds, the name of the last-encountered (*MARK) on the
+       matching path is passed back to the caller as described in the  section
+       entitled  "Extra  data  for  pcre_exec()" in the pcreapi documentation.
+       Here is an example of pcretest output, where the /K  modifier  requests
+       the retrieval and outputting of (*MARK) data:
+
+           re> /X(*MARK:A)Y|X(*MARK:B)Z/K
+         data> XY
+          0: XY
+         MK: A
+         XZ
+          0: XZ
+         MK: B
+
+       The (*MARK) name is tagged with "MK:" in this output, and in this exam-
+       ple it indicates which of the two alternatives matched. This is a  more
+       efficient  way of obtaining this information than putting each alterna-
+       tive in its own capturing parentheses.
+
+       If (*MARK) is encountered in a positive assertion, its name is recorded
+       and passed back if it is the last-encountered. This does not happen for
+       negative assertions.
+
+       After a partial match or a failed match, the name of the  last  encoun-
+       tered (*MARK) in the entire match process is returned. For example:
+
+           re> /X(*MARK:A)Y|X(*MARK:B)Z/K
+         data> XP
+         No match, mark = B
+
+       Note  that  in  this  unanchored  example the mark is retained from the
+       match attempt that started at the letter "X" in the subject. Subsequent
+       match attempts starting at "P" and then with an empty string do not get
+       as far as the (*MARK) item, but nevertheless do not reset it.
+
+       If you are interested in  (*MARK)  values  after  failed  matches,  you
+       should  probably  set  the PCRE_NO_START_OPTIMIZE option (see above) to
+       ensure that the match is always attempted.
+
+   Verbs that act after backtracking
+
+       The following verbs do nothing when they are encountered. Matching con-
+       tinues  with what follows, but if there is no subsequent match, causing
+       a backtrack to the verb, a failure is  forced.  That  is,  backtracking
+       cannot  pass  to the left of the verb. However, when one of these verbs
+       appears inside an atomic group, its effect is confined to  that  group,
+       because  once the group has been matched, there is never any backtrack-
+       ing into it. In this situation, backtracking can  "jump  back"  to  the
+       left  of the entire atomic group. (Remember also, as stated above, that
+       this localization also applies in subroutine calls and assertions.)
+
+       These verbs differ in exactly what kind of failure  occurs  when  back-
+       tracking reaches them.
+
+         (*COMMIT)
+
+       This  verb, which may not be followed by a name, causes the whole match
+       to fail outright if the rest of the pattern does not match. Even if the
+       pattern is unanchored, no further attempts to find a match by advancing
+       the  starting  point  take  place.  Once  (*COMMIT)  has  been  passed,
+       pcre_exec()  is  committed  to  finding a match at the current starting
+       point, or not at all. For example:
+
+         a+(*COMMIT)b
+
+       This matches "xxaab" but not "aacaab". It can be thought of as  a  kind
+       of dynamic anchor, or "I've started, so I must finish." The name of the
+       most recently passed (*MARK) in the path is passed back when  (*COMMIT)
+       forces a match failure.
+
+       Note  that  (*COMMIT)  at  the start of a pattern is not the same as an
+       anchor, unless PCRE's start-of-match optimizations are turned  off,  as
+       shown in this pcretest example:
+
+           re> /(*COMMIT)abc/
+         data> xyzabc
+          0: abc
+         xyzabc\Y
+         No match
+
+       PCRE  knows  that  any  match  must start with "a", so the optimization
+       skips along the subject to "a" before running the first match  attempt,
+       which  succeeds.  When the optimization is disabled by the \Y escape in
+       the second subject, the match starts at "x" and so the (*COMMIT) causes
+       it to fail without trying any other starting points.
+
+         (*PRUNE) or (*PRUNE:NAME)
+
+       This  verb causes the match to fail at the current starting position in
+       the subject if the rest of the pattern does not match. If  the  pattern
+       is  unanchored,  the  normal  "bumpalong"  advance to the next starting
+       character then happens. Backtracking can occur as usual to the left  of
+       (*PRUNE),  before  it  is  reached,  or  when  matching to the right of
+       (*PRUNE), but if there is no match to the  right,  backtracking  cannot
+       cross  (*PRUNE). In simple cases, the use of (*PRUNE) is just an alter-
+       native to an atomic group or possessive quantifier, but there are  some
+       uses of (*PRUNE) that cannot be expressed in any other way.  The behav-
+       iour of (*PRUNE:NAME)  is  the  same  as  (*MARK:NAME)(*PRUNE).  In  an
+       anchored pattern (*PRUNE) has the same effect as (*COMMIT).
+
+         (*SKIP)
+
+       This  verb, when given without a name, is like (*PRUNE), except that if
+       the pattern is unanchored, the "bumpalong" advance is not to  the  next
+       character, but to the position in the subject where (*SKIP) was encoun-
+       tered. (*SKIP) signifies that whatever text was matched leading  up  to
+       it cannot be part of a successful match. Consider:
+
+         a+(*SKIP)b
+
+       If  the  subject  is  "aaaac...",  after  the first match attempt fails
+       (starting at the first character in the  string),  the  starting  point
+       skips on to start the next attempt at "c". Note that a possessive quan-
+       tifer does not have the same effect as this example; although it  would
+       suppress  backtracking  during  the  first  match  attempt,  the second
+       attempt would start at the second character instead of skipping  on  to
+       "c".
+
+         (*SKIP:NAME)
+
+       When  (*SKIP) has an associated name, its behaviour is modified. If the
+       following pattern fails to match, the previous path through the pattern
+       is  searched for the most recent (*MARK) that has the same name. If one
+       is found, the "bumpalong" advance is to the subject position that  cor-
+       responds  to  that (*MARK) instead of to where (*SKIP) was encountered.
+       If no (*MARK) with a matching name is found, the (*SKIP) is ignored.
+
+         (*THEN) or (*THEN:NAME)
+
+       This verb causes a skip to the next innermost alternative if  the  rest
+       of  the  pattern does not match. That is, it cancels pending backtrack-
+       ing, but only within the current alternative. Its name comes  from  the
+       observation that it can be used for a pattern-based if-then-else block:
+
+         ( COND1 (*THEN) FOO | COND2 (*THEN) BAR | COND3 (*THEN) BAZ ) ...
+
+       If  the COND1 pattern matches, FOO is tried (and possibly further items
+       after the end of the group if FOO succeeds); on  failure,  the  matcher
+       skips  to  the second alternative and tries COND2, without backtracking
+       into COND1. The behaviour  of  (*THEN:NAME)  is  exactly  the  same  as
+       (*MARK:NAME)(*THEN).   If (*THEN) is not inside an alternation, it acts
+       like (*PRUNE).
+
+       Note that a subpattern that does not contain a | character  is  just  a
+       part  of the enclosing alternative; it is not a nested alternation with
+       only one alternative. The effect of (*THEN) extends beyond such a  sub-
+       pattern  to  the enclosing alternative. Consider this pattern, where A,
+       B, etc. are complex pattern fragments that do not contain any | charac-
+       ters at this level:
+
+         A (B(*THEN)C) | D
+
+       If  A and B are matched, but there is a failure in C, matching does not
+       backtrack into A; instead it moves to the next alternative, that is, D.
+       However,  if the subpattern containing (*THEN) is given an alternative,
+       it behaves differently:
+
+         A (B(*THEN)C | (*FAIL)) | D
+
+       The effect of (*THEN) is now confined to the inner subpattern. After  a
+       failure in C, matching moves to (*FAIL), which causes the whole subpat-
+       tern to fail because there are no more alternatives  to  try.  In  this
+       case, matching does now backtrack into A.
+
+       Note also that a conditional subpattern is not considered as having two
+       alternatives, because only one is ever used.  In  other  words,  the  |
+       character in a conditional subpattern has a different meaning. Ignoring
+       white space, consider:
+
+         ^.*? (?(?=a) a | b(*THEN)c )
+
+       If the subject is "ba", this pattern does not  match.  Because  .*?  is
+       ungreedy,  it  initially  matches  zero characters. The condition (?=a)
+       then fails, the character "b" is matched,  but  "c"  is  not.  At  this
+       point,  matching does not backtrack to .*? as might perhaps be expected
+       from the presence of the | character.  The  conditional  subpattern  is
+       part of the single alternative that comprises the whole pattern, and so
+       the match fails. (If there was a backtrack into  .*?,  allowing  it  to
+       match "b", the match would succeed.)
+
+       The  verbs just described provide four different "strengths" of control
+       when subsequent matching fails. (*THEN) is the weakest, carrying on the
+       match  at  the next alternative. (*PRUNE) comes next, failing the match
+       at the current starting position, but allowing an advance to  the  next
+       character  (for an unanchored pattern). (*SKIP) is similar, except that
+       the advance may be more than one character. (*COMMIT) is the strongest,
+       causing the entire match to fail.
+
+       If more than one such verb is present in a pattern, the "strongest" one
+       wins.  For example, consider this pattern, where A, B, etc. are complex
+       pattern fragments:
+
+         (A(*COMMIT)B(*THEN)C|D)
+
+       Once  A  has  matched,  PCRE is committed to this match, at the current
+       starting position. If subsequently B matches, but C does not, the  nor-
+       mal (*THEN) action of trying the next alternative (that is, D) does not
+       happen because (*COMMIT) overrides.
+
+
+SEE ALSO
+
+       pcreapi(3), pcrecallout(3),  pcrematching(3),  pcresyntax(3),  pcre(3),
+       pcre16(3).
+
+
+AUTHOR
+
+       Philip Hazel
+       University Computing Service
+       Cambridge CB2 3QH, England.
+
+
+REVISION
+
+       Last updated: 17 June 2012
+       Copyright (c) 1997-2012 University of Cambridge.
+------------------------------------------------------------------------------
+
+
+PCRESYNTAX(3)                                                    PCRESYNTAX(3)
+
+
+NAME
+       PCRE - Perl-compatible regular expressions
+
+
+PCRE REGULAR EXPRESSION SYNTAX SUMMARY
+
+       The  full syntax and semantics of the regular expressions that are sup-
+       ported by PCRE are described in  the  pcrepattern  documentation.  This
+       document contains a quick-reference summary of the syntax.
+
+
+QUOTING
+
+         \x         where x is non-alphanumeric is a literal x
+         \Q...\E    treat enclosed characters as literal
+
+
+CHARACTERS
+
+         \a         alarm, that is, the BEL character (hex 07)
+         \cx        "control-x", where x is any ASCII character
+         \e         escape (hex 1B)
+         \f         form feed (hex 0C)
+         \n         newline (hex 0A)
+         \r         carriage return (hex 0D)
+         \t         tab (hex 09)
+         \ddd       character with octal code ddd, or backreference
+         \xhh       character with hex code hh
+         \x{hhh..}  character with hex code hhh..
+
+
+CHARACTER TYPES
+
+         .          any character except newline;
+                      in dotall mode, any character whatsoever
+         \C         one data unit, even in UTF mode (best avoided)
+         \d         a decimal digit
+         \D         a character that is not a decimal digit
+         \h         a horizontal white space character
+         \H         a character that is not a horizontal white space character
+         \N         a character that is not a newline
+         \p{xx}     a character with the xx property
+         \P{xx}     a character without the xx property
+         \R         a newline sequence
+         \s         a white space character
+         \S         a character that is not a white space character
+         \v         a vertical white space character
+         \V         a character that is not a vertical white space character
+         \w         a "word" character
+         \W         a "non-word" character
+         \X         an extended Unicode sequence
+
+       In  PCRE,  by  default, \d, \D, \s, \S, \w, and \W recognize only ASCII
+       characters, even in a UTF mode. However, this can be changed by setting
+       the PCRE_UCP option.
+
+
+GENERAL CATEGORY PROPERTIES FOR \p and \P
+
+         C          Other
+         Cc         Control
+         Cf         Format
+         Cn         Unassigned
+         Co         Private use
+         Cs         Surrogate
+
+         L          Letter
+         Ll         Lower case letter
+         Lm         Modifier letter
+         Lo         Other letter
+         Lt         Title case letter
+         Lu         Upper case letter
+         L&         Ll, Lu, or Lt
+
+         M          Mark
+         Mc         Spacing mark
+         Me         Enclosing mark
+         Mn         Non-spacing mark
+
+         N          Number
+         Nd         Decimal number
+         Nl         Letter number
+         No         Other number
+
+         P          Punctuation
+         Pc         Connector punctuation
+         Pd         Dash punctuation
+         Pe         Close punctuation
+         Pf         Final punctuation
+         Pi         Initial punctuation
+         Po         Other punctuation
+         Ps         Open punctuation
+
+         S          Symbol
+         Sc         Currency symbol
+         Sk         Modifier symbol
+         Sm         Mathematical symbol
+         So         Other symbol
+
+         Z          Separator
+         Zl         Line separator
+         Zp         Paragraph separator
+         Zs         Space separator
+
+
+PCRE SPECIAL CATEGORY PROPERTIES FOR \p and \P
+
+         Xan        Alphanumeric: union of properties L and N
+         Xps        POSIX space: property Z or tab, NL, VT, FF, CR
+         Xsp        Perl space: property Z or tab, NL, FF, CR
+         Xwd        Perl word: property Xan or underscore
+
+
+SCRIPT NAMES FOR \p AND \P
+
+       Arabic,  Armenian,  Avestan, Balinese, Bamum, Batak, Bengali, Bopomofo,
+       Brahmi, Braille, Buginese, Buhid, Canadian_Aboriginal, Carian,  Chakma,
+       Cham,  Cherokee, Common, Coptic, Cuneiform, Cypriot, Cyrillic, Deseret,
+       Devanagari,  Egyptian_Hieroglyphs,  Ethiopic,   Georgian,   Glagolitic,
+       Gothic,  Greek, Gujarati, Gurmukhi, Han, Hangul, Hanunoo, Hebrew, Hira-
+       gana,  Imperial_Aramaic,  Inherited,  Inscriptional_Pahlavi,   Inscrip-
+       tional_Parthian,   Javanese,   Kaithi,   Kannada,  Katakana,  Kayah_Li,
+       Kharoshthi, Khmer, Lao, Latin, Lepcha, Limbu, Linear_B,  Lisu,  Lycian,
+       Lydian,    Malayalam,    Mandaic,    Meetei_Mayek,    Meroitic_Cursive,
+       Meroitic_Hieroglyphs,  Miao,  Mongolian,  Myanmar,  New_Tai_Lue,   Nko,
+       Ogham,    Old_Italic,   Old_Persian,   Old_South_Arabian,   Old_Turkic,
+       Ol_Chiki, Oriya, Osmanya, Phags_Pa, Phoenician, Rejang, Runic,  Samari-
+       tan,  Saurashtra,  Sharada,  Shavian, Sinhala, Sora_Sompeng, Sundanese,
+       Syloti_Nagri, Syriac, Tagalog, Tagbanwa,  Tai_Le,  Tai_Tham,  Tai_Viet,
+       Takri,  Tamil,  Telugu, Thaana, Thai, Tibetan, Tifinagh, Ugaritic, Vai,
+       Yi.
+
+
+CHARACTER CLASSES
+
+         [...]       positive character class
+         [^...]      negative character class
+         [x-y]       range (can be used for hex characters)
+         [[:xxx:]]   positive POSIX named set
+         [[:^xxx:]]  negative POSIX named set
+
+         alnum       alphanumeric
+         alpha       alphabetic
+         ascii       0-127
+         blank       space or tab
+         cntrl       control character
+         digit       decimal digit
+         graph       printing, excluding space
+         lower       lower case letter
+         print       printing, including space
+         punct       printing, excluding alphanumeric
+         space       white space
+         upper       upper case letter
+         word        same as \w
+         xdigit      hexadecimal digit
+
+       In PCRE, POSIX character set names recognize only ASCII  characters  by
+       default,  but  some  of them use Unicode properties if PCRE_UCP is set.
+       You can use \Q...\E inside a character class.
+
+
+QUANTIFIERS
+
+         ?           0 or 1, greedy
+         ?+          0 or 1, possessive
+         ??          0 or 1, lazy
+         *           0 or more, greedy
+         *+          0 or more, possessive
+         *?          0 or more, lazy
+         +           1 or more, greedy
+         ++          1 or more, possessive
+         +?          1 or more, lazy
+         {n}         exactly n
+         {n,m}       at least n, no more than m, greedy
+         {n,m}+      at least n, no more than m, possessive
+         {n,m}?      at least n, no more than m, lazy
+         {n,}        n or more, greedy
+         {n,}+       n or more, possessive
+         {n,}?       n or more, lazy
+
+
+ANCHORS AND SIMPLE ASSERTIONS
+
+         \b          word boundary
+         \B          not a word boundary
+         ^           start of subject
+                      also after internal newline in multiline mode
+         \A          start of subject
+         $           end of subject
+                      also before newline at end of subject
+                      also before internal newline in multiline mode
+         \Z          end of subject
+                      also before newline at end of subject
+         \z          end of subject
+         \G          first matching position in subject
+
+
+MATCH POINT RESET
+
+         \K          reset start of match
+
+
+ALTERNATION
+
+         expr|expr|expr...
+
+
+CAPTURING
+
+         (...)           capturing group
+         (?<name>...)    named capturing group (Perl)
+         (?'name'...)    named capturing group (Perl)
+         (?P<name>...)   named capturing group (Python)
+         (?:...)         non-capturing group
+         (?|...)         non-capturing group; reset group numbers for
+                          capturing groups in each alternative
+
+
+ATOMIC GROUPS
+
+         (?>...)         atomic, non-capturing group
+
+
+COMMENT
+
+         (?#....)        comment (not nestable)
+
+
+OPTION SETTING
+
+         (?i)            caseless
+         (?J)            allow duplicate names
+         (?m)            multiline
+         (?s)            single line (dotall)
+         (?U)            default ungreedy (lazy)
+         (?x)            extended (ignore white space)
+         (?-...)         unset option(s)
+
+       The following are recognized only at the start of a  pattern  or  after
+       one of the newline-setting options with similar syntax:
+
+         (*NO_START_OPT) no start-match optimization (PCRE_NO_START_OPTIMIZE)
+         (*UTF8)         set UTF-8 mode: 8-bit library (PCRE_UTF8)
+         (*UTF16)        set UTF-16 mode: 16-bit library (PCRE_UTF16)
+         (*UCP)          set PCRE_UCP (use Unicode properties for \d etc)
+
+
+LOOKAHEAD AND LOOKBEHIND ASSERTIONS
+
+         (?=...)         positive look ahead
+         (?!...)         negative look ahead
+         (?<=...)        positive look behind
+         (?<!...)        negative look behind
+
+       Each top-level branch of a look behind must be of a fixed length.
+
+
+BACKREFERENCES
+
+         \n              reference by number (can be ambiguous)
+         \gn             reference by number
+         \g{n}           reference by number
+         \g{-n}          relative reference by number
+         \k<name>        reference by name (Perl)
+         \k'name'        reference by name (Perl)
+         \g{name}        reference by name (Perl)
+         \k{name}        reference by name (.NET)
+         (?P=name)       reference by name (Python)
+
+
+SUBROUTINE REFERENCES (POSSIBLY RECURSIVE)
+
+         (?R)            recurse whole pattern
+         (?n)            call subpattern by absolute number
+         (?+n)           call subpattern by relative number
+         (?-n)           call subpattern by relative number
+         (?&name)        call subpattern by name (Perl)
+         (?P>name)       call subpattern by name (Python)
+         \g<name>        call subpattern by name (Oniguruma)
+         \g'name'        call subpattern by name (Oniguruma)
+         \g<n>           call subpattern by absolute number (Oniguruma)
+         \g'n'           call subpattern by absolute number (Oniguruma)
+         \g<+n>          call subpattern by relative number (PCRE extension)
+         \g'+n'          call subpattern by relative number (PCRE extension)
+         \g<-n>          call subpattern by relative number (PCRE extension)
+         \g'-n'          call subpattern by relative number (PCRE extension)
+
+
+CONDITIONAL PATTERNS
+
+         (?(condition)yes-pattern)
+         (?(condition)yes-pattern|no-pattern)
+
+         (?(n)...        absolute reference condition
+         (?(+n)...       relative reference condition
+         (?(-n)...       relative reference condition
+         (?(<name>)...   named reference condition (Perl)
+         (?('name')...   named reference condition (Perl)
+         (?(name)...     named reference condition (PCRE)
+         (?(R)...        overall recursion condition
+         (?(Rn)...       specific group recursion condition
+         (?(R&name)...   specific recursion condition
+         (?(DEFINE)...   define subpattern for reference
+         (?(assert)...   assertion condition
+
+
+BACKTRACKING CONTROL
+
+       The following act immediately they are reached:
+
+         (*ACCEPT)       force successful match
+         (*FAIL)         force backtrack; synonym (*F)
+         (*MARK:NAME)    set name to be passed back; synonym (*:NAME)
+
+       The  following  act only when a subsequent match failure causes a back-
+       track to reach them. They all force a match failure, but they differ in
+       what happens afterwards. Those that advance the start-of-match point do
+       so only if the pattern is not anchored.
+
+         (*COMMIT)       overall failure, no advance of starting point
+         (*PRUNE)        advance to next starting character
+         (*PRUNE:NAME)   equivalent to (*MARK:NAME)(*PRUNE)
+         (*SKIP)         advance to current matching position
+         (*SKIP:NAME)    advance to position corresponding to an earlier
+                         (*MARK:NAME); if not found, the (*SKIP) is ignored
+         (*THEN)         local failure, backtrack to next alternation
+         (*THEN:NAME)    equivalent to (*MARK:NAME)(*THEN)
+
+
+NEWLINE CONVENTIONS
+
+       These are recognized only at the very start of the pattern or  after  a
+       (*BSR_...), (*UTF8), (*UTF16) or (*UCP) option.
+
+         (*CR)           carriage return only
+         (*LF)           linefeed only
+         (*CRLF)         carriage return followed by linefeed
+         (*ANYCRLF)      all three of the above
+         (*ANY)          any Unicode newline sequence
+
+
+WHAT \R MATCHES
+
+       These  are  recognized only at the very start of the pattern or after a
+       (*...) option that sets the newline convention or a UTF or UCP mode.
+
+         (*BSR_ANYCRLF)  CR, LF, or CRLF
+         (*BSR_UNICODE)  any Unicode newline sequence
+
+
+CALLOUTS
+
+         (?C)      callout
+         (?Cn)     callout with data n
+
+
+SEE ALSO
+
+       pcrepattern(3), pcreapi(3), pcrecallout(3), pcrematching(3), pcre(3).
+
+
+AUTHOR
+
+       Philip Hazel
+       University Computing Service
+       Cambridge CB2 3QH, England.
+
+
+REVISION
+
+       Last updated: 10 January 2012
+       Copyright (c) 1997-2012 University of Cambridge.
+------------------------------------------------------------------------------
+
+
+PCREUNICODE(3)                                                  PCREUNICODE(3)
+
+
+NAME
+       PCRE - Perl-compatible regular expressions
+
+
+UTF-8, UTF-16, AND UNICODE PROPERTY SUPPORT
+
+       From Release 8.30, in addition to its previous UTF-8 support, PCRE also
+       supports UTF-16 by means of a separate  16-bit  library.  This  can  be
+       built as well as, or instead of, the 8-bit library.
+
+
+UTF-8 SUPPORT
+
+       In  order  process  UTF-8  strings, you must build PCRE's 8-bit library
+       with UTF support, and, in addition, you must call  pcre_compile()  with
+       the  PCRE_UTF8 option flag, or the pattern must start with the sequence
+       (*UTF8). When either of these is the case, both  the  pattern  and  any
+       subject  strings  that  are  matched  against  it  are treated as UTF-8
+       strings instead of strings of 1-byte characters.
+
+
+UTF-16 SUPPORT
+
+       In order process UTF-16 strings, you must build PCRE's  16-bit  library
+       with UTF support, and, in addition, you must call pcre16_compile() with
+       the PCRE_UTF16 option flag, or the pattern must start with the sequence
+       (*UTF16).  When  either  of these is the case, both the pattern and any
+       subject strings that are matched  against  it  are  treated  as  UTF-16
+       strings instead of strings of 16-bit characters.
+
+
+UTF SUPPORT OVERHEAD
+
+       If  you  compile  PCRE with UTF support, but do not use it at run time,
+       the library will be a bit bigger, but the additional run time  overhead
+       is limited to testing the PCRE_UTF8/16 flag occasionally, so should not
+       be very big.
+
+
+UNICODE PROPERTY SUPPORT
+
+       If PCRE is built with Unicode character property support (which implies
+       UTF  support), the escape sequences \p{..}, \P{..}, and \X can be used.
+       The available properties that can be tested are limited to the  general
+       category  properties  such  as  Lu for an upper case letter or Nd for a
+       decimal number, the Unicode script names such as Arabic or Han, and the
+       derived  properties Any and L&. A full list is given in the pcrepattern
+       documentation. Only the short names for properties are  supported.  For
+       example,  \p{L}  matches a letter. Its Perl synonym, \p{Letter}, is not
+       supported.  Furthermore, in Perl, many  properties  may  optionally  be
+       prefixed  by  "Is", for compatibility with Perl 5.6. PCRE does not sup-
+       port this.
+
+   Validity of UTF-8 strings
+
+       When you set the PCRE_UTF8 flag, the byte strings  passed  as  patterns
+       and subjects are (by default) checked for validity on entry to the rel-
+       evant functions. The entire string is checked before any other process-
+       ing  takes  place. From release 7.3 of PCRE, the check is according the
+       rules of RFC 3629, which are themselves derived from the Unicode speci-
+       fication.  Earlier  releases  of  PCRE  followed the rules of RFC 2279,
+       which allows the full range of 31-bit values  (0  to  0x7FFFFFFF).  The
+       current  check allows only values in the range U+0 to U+10FFFF, exclud-
+       ing U+D800 to U+DFFF.
+
+       The excluded code points are the "Surrogate Area" of Unicode. They  are
+       reserved  for  use  by  UTF-16,  where they are used in pairs to encode
+       codepoints with values greater than 0xFFFF. The code  points  that  are
+       encoded by UTF-16 pairs are available independently in the UTF-8 encod-
+       ing. (In other words, the whole surrogate thing is a fudge  for  UTF-16
+       which unfortunately messes up UTF-8.)
+
+       If an invalid UTF-8 string is passed to PCRE, an error return is given.
+       At compile time, the only additional information is the offset  to  the
+       first byte of the failing character. The run-time functions pcre_exec()
+       and pcre_dfa_exec() also pass back this information, as well as a  more
+       detailed  reason  code if the caller has provided memory in which to do
+       this.
+
+       In some situations, you may already know that your strings  are  valid,
+       and  therefore  want  to  skip these checks in order to improve perfor-
+       mance, for example in the case of a long subject string that  is  being
+       scanned   repeatedly   with   different   patterns.   If  you  set  the
+       PCRE_NO_UTF8_CHECK flag at compile time or at run  time,  PCRE  assumes
+       that  the  pattern  or subject it is given (respectively) contains only
+       valid UTF-8 codes. In this case, it does not diagnose an invalid  UTF-8
+       string.
+
+       If  you  pass  an  invalid UTF-8 string when PCRE_NO_UTF8_CHECK is set,
+       what happens depends on why the string is invalid. If the  string  con-
+       forms to the "old" definition of UTF-8 (RFC 2279), it is processed as a
+       string of characters in the range 0 to  0x7FFFFFFF  by  pcre_dfa_exec()
+       and  the interpreted version of pcre_exec(). In other words, apart from
+       the initial validity test, these functions (when in UTF-8 mode)  handle
+       strings  according  to the more liberal rules of RFC 2279. However, the
+       just-in-time (JIT) optimization for pcre_exec() supports only RFC 3629.
+       If  you are using JIT optimization, or if the string does not even con-
+       form to RFC 2279, the result is undefined. Your program may crash.
+
+       If you want to process strings  of  values  in  the  full  range  0  to
+       0x7FFFFFFF,  encoded in a UTF-8-like manner as per the old RFC, you can
+       set PCRE_NO_UTF8_CHECK to bypass the more restrictive test. However, in
+       this  situation,  you  will  have to apply your own validity check, and
+       avoid the use of JIT optimization.
+
+   Validity of UTF-16 strings
+
+       When you set the PCRE_UTF16 flag, the strings of 16-bit data units that
+       are passed as patterns and subjects are (by default) checked for valid-
+       ity on entry to the relevant functions. Values other than those in  the
+       surrogate range U+D800 to U+DFFF are independent code points. Values in
+       the surrogate range must be used in pairs in the correct manner.
+
+       If an invalid UTF-16 string is passed  to  PCRE,  an  error  return  is
+       given.  At  compile time, the only additional information is the offset
+       to the first data unit of the failing character. The run-time functions
+       pcre16_exec() and pcre16_dfa_exec() also pass back this information, as
+       well as a more detailed reason code if the caller has  provided  memory
+       in which to do this.
+
+       In  some  situations, you may already know that your strings are valid,
+       and therefore want to skip these checks in  order  to  improve  perfor-
+       mance.  If  you  set the PCRE_NO_UTF16_CHECK flag at compile time or at
+       run time, PCRE assumes that the pattern or subject it is given (respec-
+       tively) contains only valid UTF-16 sequences. In this case, it does not
+       diagnose an invalid UTF-16 string.
+
+   General comments about UTF modes
+
+       1. Codepoints less than 256  can  be  specified  by  either  braced  or
+       unbraced  hexadecimal  escape  sequences (for example, \x{b3} or \xb3).
+       Larger values have to use braced sequences.
+
+       2. Octal numbers up to \777 are recognized, and  in  UTF-8  mode,  they
+       match two-byte characters for values greater than \177.
+
+       3. Repeat quantifiers apply to complete UTF characters, not to individ-
+       ual data units, for example: \x{100}{3}.
+
+       4. The dot metacharacter matches one UTF character instead of a  single
+       data unit.
+
+       5.  The  escape sequence \C can be used to match a single byte in UTF-8
+       mode, or a single 16-bit data unit in UTF-16 mode, but its use can lead
+       to some strange effects because it breaks up multi-unit characters (see
+       the description of \C in the pcrepattern documentation). The use of  \C
+       is    not    supported    in    the   alternative   matching   function
+       pcre[16]_dfa_exec(), nor is it supported in UTF mode by the  JIT  opti-
+       mization of pcre[16]_exec(). If JIT optimization is requested for a UTF
+       pattern that contains \C, it will not succeed, and so the matching will
+       be carried out by the normal interpretive function.
+
+       6.  The  character escapes \b, \B, \d, \D, \s, \S, \w, and \W correctly
+       test characters of any code value, but, by default, the characters that
+       PCRE  recognizes  as digits, spaces, or word characters remain the same
+       set as in non-UTF mode, all with values less  than  256.  This  remains
+       true  even  when  PCRE  is  built  to include Unicode property support,
+       because to do otherwise would slow down PCRE in many common cases. Note
+       in  particular that this applies to \b and \B, because they are defined
+       in terms of \w and \W. If you really want to test for a wider sense of,
+       say,  "digit",  you  can  use  explicit  Unicode property tests such as
+       \p{Nd}. Alternatively, if you set the PCRE_UCP option, the way that the
+       character  escapes  work is changed so that Unicode properties are used
+       to determine which characters match. There are more details in the sec-
+       tion on generic character types in the pcrepattern documentation.
+
+       7.  Similarly,  characters that match the POSIX named character classes
+       are all low-valued characters, unless the PCRE_UCP option is set.
+
+       8. However, the horizontal and vertical white  space  matching  escapes
+       (\h,  \H,  \v, and \V) do match all the appropriate Unicode characters,
+       whether or not PCRE_UCP is set.
+
+       9. Case-insensitive matching applies only to  characters  whose  values
+       are  less than 128, unless PCRE is built with Unicode property support.
+       Even when Unicode property support is available, PCRE  still  uses  its
+       own  character  tables when checking the case of low-valued characters,
+       so as not to degrade performance.  The Unicode property information  is
+       used only for characters with higher values. Furthermore, PCRE supports
+       case-insensitive matching only  when  there  is  a  one-to-one  mapping
+       between  a letter's cases. There are a small number of many-to-one map-
+       pings in Unicode; these are not supported by PCRE.
+
+
+AUTHOR
+
+       Philip Hazel
+       University Computing Service
+       Cambridge CB2 3QH, England.
+
+
+REVISION
+
+       Last updated: 14 April 2012
+       Copyright (c) 1997-2012 University of Cambridge.
+------------------------------------------------------------------------------
+
+
+PCREJIT(3)                                                          PCREJIT(3)
+
+
+NAME
+       PCRE - Perl-compatible regular expressions
+
+
+PCRE JUST-IN-TIME COMPILER SUPPORT
+
+       Just-in-time  compiling  is a heavyweight optimization that can greatly
+       speed up pattern matching. However, it comes at the cost of extra  pro-
+       cessing before the match is performed. Therefore, it is of most benefit
+       when the same pattern is going to be matched many times. This does  not
+       necessarily  mean  many calls of a matching function; if the pattern is
+       not anchored, matching attempts may take place many  times  at  various
+       positions  in  the  subject, even for a single call.  Therefore, if the
+       subject string is very long, it may still pay to use  JIT  for  one-off
+       matches.
+
+       JIT  support  applies  only to the traditional Perl-compatible matching
+       function.  It does not apply when the DFA matching  function  is  being
+       used. The code for this support was written by Zoltan Herczeg.
+
+
+8-BIT and 16-BIT SUPPORT
+
+       JIT  support is available for both the 8-bit and 16-bit PCRE libraries.
+       To  keep  this  documentation  simple,  only  the  8-bit  interface  is
+       described in what follows. If you are using the 16-bit library, substi-
+       tute  the  16-bit  functions  and  16-bit  structures   (for   example,
+       pcre16_jit_stack instead of pcre_jit_stack).
+
+
+AVAILABILITY OF JIT SUPPORT
+
+       JIT  support  is  an  optional  feature of PCRE. The "configure" option
+       --enable-jit (or equivalent CMake option) must  be  set  when  PCRE  is
+       built  if  you want to use JIT. The support is limited to the following
+       hardware platforms:
+
+         ARM v5, v7, and Thumb2
+         Intel x86 32-bit and 64-bit
+         MIPS 32-bit
+         Power PC 32-bit and 64-bit
+
+       If --enable-jit is set on an unsupported platform, compilation fails.
+
+       A program that is linked with PCRE 8.20 or later can tell if  JIT  sup-
+       port  is  available  by  calling pcre_config() with the PCRE_CONFIG_JIT
+       option. The result is 1 when JIT is available, and  0  otherwise.  How-
+       ever, a simple program does not need to check this in order to use JIT.
+       The API is implemented in a way that falls  back  to  the  interpretive
+       code if JIT is not available.
+
+       If  your program may sometimes be linked with versions of PCRE that are
+       older than 8.20, but you want to use JIT when it is available, you  can
+       test the values of PCRE_MAJOR and PCRE_MINOR, or the existence of a JIT
+       macro such as PCRE_CONFIG_JIT, for compile-time control of your code.
+
+
+SIMPLE USE OF JIT
+
+       You have to do two things to make use of the JIT support  in  the  sim-
+       plest way:
+
+         (1) Call pcre_study() with the PCRE_STUDY_JIT_COMPILE option for
+             each compiled pattern, and pass the resulting pcre_extra block to
+             pcre_exec().
+
+         (2) Use pcre_free_study() to free the pcre_extra block when it is
+             no longer needed, instead of just freeing it yourself. This
+             ensures that any JIT data is also freed.
+
+       For  a  program  that may be linked with pre-8.20 versions of PCRE, you
+       can insert
+
+         #ifndef PCRE_STUDY_JIT_COMPILE
+         #define PCRE_STUDY_JIT_COMPILE 0
+         #endif
+
+       so that no option is passed to pcre_study(),  and  then  use  something
+       like this to free the study data:
+
+         #ifdef PCRE_CONFIG_JIT
+             pcre_free_study(study_ptr);
+         #else
+             pcre_free(study_ptr);
+         #endif
+
+       PCRE_STUDY_JIT_COMPILE  requests  the JIT compiler to generate code for
+       complete matches.  If  you  want  to  run  partial  matches  using  the
+       PCRE_PARTIAL_HARD  or  PCRE_PARTIAL_SOFT  options  of  pcre_exec(), you
+       should set one or both of the following  options  in  addition  to,  or
+       instead of, PCRE_STUDY_JIT_COMPILE when you call pcre_study():
+
+         PCRE_STUDY_JIT_PARTIAL_HARD_COMPILE
+         PCRE_STUDY_JIT_PARTIAL_SOFT_COMPILE
+
+       The  JIT  compiler  generates  different optimized code for each of the
+       three modes (normal, soft partial, hard partial). When  pcre_exec()  is
+       called,  the appropriate code is run if it is available. Otherwise, the
+       pattern is matched using interpretive code.
+
+       In some circumstances you may need to call additional functions.  These
+       are  described  in  the  section  entitled  "Controlling the JIT stack"
+       below.
+
+       If JIT  support  is  not  available,  PCRE_STUDY_JIT_COMPILE  etc.  are
+       ignored, and no JIT data is created. Otherwise, the compiled pattern is
+       passed to the JIT compiler, which turns it into machine code that  exe-
+       cutes  much  faster than the normal interpretive code. When pcre_exec()
+       is passed a pcre_extra block containing a pointer to JIT  code  of  the
+       appropriate  mode  (normal  or  hard/soft  partial), it obeys that code
+       instead of running the interpreter. The result is  identical,  but  the
+       compiled JIT code runs much faster.
+
+       There  are some pcre_exec() options that are not supported for JIT exe-
+       cution. There are also some  pattern  items  that  JIT  cannot  handle.
+       Details  are  given below. In both cases, execution automatically falls
+       back to the interpretive code. If you want  to  know  whether  JIT  was
+       actually  used  for  a  particular  match, you should arrange for a JIT
+       callback function to be set up as described  in  the  section  entitled
+       "Controlling  the JIT stack" below, even if you do not need to supply a
+       non-default JIT stack. Such a callback function is called whenever  JIT
+       code  is about to be obeyed. If the execution options are not right for
+       JIT execution, the callback function is not obeyed.
+
+       If the JIT compiler finds an unsupported item, no JIT  data  is  gener-
+       ated.  You  can find out if JIT execution is available after studying a
+       pattern by calling pcre_fullinfo() with  the  PCRE_INFO_JIT  option.  A
+       result  of  1  means that JIT compilation was successful. A result of 0
+       means that JIT support is not available, or the pattern was not studied
+       with  PCRE_STUDY_JIT_COMPILE  etc., or the JIT compiler was not able to
+       handle the pattern.
+
+       Once a pattern has been studied, with or without JIT, it can be used as
+       many times as you like for matching different subject strings.
+
+
+UNSUPPORTED OPTIONS AND PATTERN ITEMS
+
+       The  only  pcre_exec() options that are supported for JIT execution are
+       PCRE_NO_UTF8_CHECK,  PCRE_NO_UTF16_CHECK,   PCRE_NOTBOL,   PCRE_NOTEOL,
+       PCRE_NOTEMPTY,  PCRE_NOTEMPTY_ATSTART, PCRE_PARTIAL_HARD, and PCRE_PAR-
+       TIAL_SOFT.
+
+       The unsupported pattern items are:
+
+         \C             match a single byte; not supported in UTF-8 mode
+         (?Cn)          callouts
+         (*PRUNE)       )
+         (*SKIP)        ) backtracking control verbs
+         (*THEN)        )
+
+       Support for some of these may be added in future.
+
+
+RETURN VALUES FROM JIT EXECUTION
+
+       When a pattern is matched using JIT execution, the  return  values  are
+       the  same as those given by the interpretive pcre_exec() code, with the
+       addition of one new error code: PCRE_ERROR_JIT_STACKLIMIT.  This  means
+       that  the memory used for the JIT stack was insufficient. See "Control-
+       ling the JIT stack" below for a discussion of JIT stack usage. For com-
+       patibility  with  the  interpretive pcre_exec() code, no more than two-
+       thirds of the ovector argument is used for passing back  captured  sub-
+       strings.
+
+       The  error  code  PCRE_ERROR_MATCHLIMIT  is returned by the JIT code if
+       searching a very large pattern tree goes on for too long, as it  is  in
+       the  same circumstance when JIT is not used, but the details of exactly
+       what is counted are not the same. The  PCRE_ERROR_RECURSIONLIMIT  error
+       code is never returned by JIT execution.
+
+
+SAVING AND RESTORING COMPILED PATTERNS
+
+       The  code  that  is  generated by the JIT compiler is architecture-spe-
+       cific, and is also position dependent. For those reasons it  cannot  be
+       saved  (in a file or database) and restored later like the bytecode and
+       other data of a compiled pattern. Saving and  restoring  compiled  pat-
+       terns  is not something many people do. More detail about this facility
+       is given in the pcreprecompile documentation. It should be possible  to
+       run  pcre_study() on a saved and restored pattern, and thereby recreate
+       the JIT data, but because JIT compilation uses  significant  resources,
+       it  is  probably  not worth doing this; you might as well recompile the
+       original pattern.
+
+
+CONTROLLING THE JIT STACK
+
+       When the compiled JIT code runs, it needs a block of memory to use as a
+       stack.   By  default,  it  uses 32K on the machine stack. However, some
+       large  or  complicated  patterns  need  more  than  this.   The   error
+       PCRE_ERROR_JIT_STACKLIMIT  is  given  when  there  is not enough stack.
+       Three functions are provided for managing blocks of memory for  use  as
+       JIT  stacks. There is further discussion about the use of JIT stacks in
+       the section entitled "JIT stack FAQ" below.
+
+       The pcre_jit_stack_alloc() function creates a JIT stack. Its  arguments
+       are  a starting size and a maximum size, and it returns a pointer to an
+       opaque structure of type pcre_jit_stack, or NULL if there is an  error.
+       The  pcre_jit_stack_free() function can be used to free a stack that is
+       no longer needed. (For the technically minded:  the  address  space  is
+       allocated by mmap or VirtualAlloc.)
+
+       JIT  uses far less memory for recursion than the interpretive code, and
+       a maximum stack size of 512K to 1M should be more than enough  for  any
+       pattern.
+
+       The  pcre_assign_jit_stack()  function  specifies  which stack JIT code
+       should use. Its arguments are as follows:
+
+         pcre_extra         *extra
+         pcre_jit_callback  callback
+         void               *data
+
+       The extra argument must be  the  result  of  studying  a  pattern  with
+       PCRE_STUDY_JIT_COMPILE etc. There are three cases for the values of the
+       other two options:
+
+         (1) If callback is NULL and data is NULL, an internal 32K block
+             on the machine stack is used.
+
+         (2) If callback is NULL and data is not NULL, data must be
+             a valid JIT stack, the result of calling pcre_jit_stack_alloc().
+
+         (3) If callback is not NULL, it must point to a function that is
+             called with data as an argument at the start of matching, in
+             order to set up a JIT stack. If the return from the callback
+             function is NULL, the internal 32K stack is used; otherwise the
+             return value must be a valid JIT stack, the result of calling
+             pcre_jit_stack_alloc().
+
+       A callback function is obeyed whenever JIT code is about to be run;  it
+       is  not  obeyed when pcre_exec() is called with options that are incom-
+       patible for JIT execution. A callback function can therefore be used to
+       determine  whether  a  match  operation  was  executed by JIT or by the
+       interpreter.
+
+       You may safely use the same JIT stack for more than one pattern (either
+       by  assigning directly or by callback), as long as the patterns are all
+       matched sequentially in the same thread. In a multithread  application,
+       if  you  do not specify a JIT stack, or if you assign or pass back NULL
+       from a callback, that is thread-safe, because each thread has  its  own
+       machine  stack.  However,  if  you  assign  or pass back a non-NULL JIT
+       stack, this must be a different stack  for  each  thread  so  that  the
+       application is thread-safe.
+
+       Strictly  speaking,  even more is allowed. You can assign the same non-
+       NULL stack to any number of patterns as long as they are not  used  for
+       matching  by  multiple  threads  at the same time. For example, you can
+       assign the same stack to all compiled patterns, and use a global  mutex
+       in  the callback to wait until the stack is available for use. However,
+       this is an inefficient solution, and not recommended.
+
+       This is a suggestion for how a multithreaded program that needs to  set
+       up non-default JIT stacks might operate:
+
+         During thread initalization
+           thread_local_var = pcre_jit_stack_alloc(...)
+
+         During thread exit
+           pcre_jit_stack_free(thread_local_var)
+
+         Use a one-line callback function
+           return thread_local_var
+
+       All  the  functions  described in this section do nothing if JIT is not
+       available, and pcre_assign_jit_stack() does nothing  unless  the  extra
+       argument  is  non-NULL  and  points  to  a pcre_extra block that is the
+       result of a successful study with PCRE_STUDY_JIT_COMPILE etc.
+
+
+JIT STACK FAQ
+
+       (1) Why do we need JIT stacks?
+
+       PCRE (and JIT) is a recursive, depth-first engine, so it needs a  stack
+       where  the local data of the current node is pushed before checking its
+       child nodes.  Allocating real machine stack on some platforms is diffi-
+       cult. For example, the stack chain needs to be updated every time if we
+       extend the stack on PowerPC.  Although it  is  possible,  its  updating
+       time overhead decreases performance. So we do the recursion in memory.
+
+       (2) Why don't we simply allocate blocks of memory with malloc()?
+
+       Modern  operating  systems  have  a  nice  feature: they can reserve an
+       address space instead of allocating memory. We can safely allocate mem-
+       ory  pages  inside  this address space, so the stack could grow without
+       moving memory data (this is important because of pointers). Thus we can
+       allocate  1M  address space, and use only a single memory page (usually
+       4K) if that is enough. However, we can still grow up to 1M  anytime  if
+       needed.
+
+       (3) Who "owns" a JIT stack?
+
+       The owner of the stack is the user program, not the JIT studied pattern
+       or anything else. The user program must ensure that if a stack is  used
+       by  pcre_exec(), (that is, it is assigned to the pattern currently run-
+       ning), that stack must not be used by any other threads (to avoid over-
+       writing the same memory area). The best practice for multithreaded pro-
+       grams is to allocate a stack for each thread,  and  return  this  stack
+       through the JIT callback function.
+
+       (4) When should a JIT stack be freed?
+
+       You can free a JIT stack at any time, as long as it will not be used by
+       pcre_exec() again. When you assign the  stack  to  a  pattern,  only  a
+       pointer  is set. There is no reference counting or any other magic. You
+       can free the patterns and stacks in any order,  anytime.  Just  do  not
+       call  pcre_exec() with a pattern pointing to an already freed stack, as
+       that will cause SEGFAULT. (Also, do not free a stack currently used  by
+       pcre_exec()  in  another  thread). You can also replace the stack for a
+       pattern at any time. You  can  even  free  the  previous  stack  before
+       assigning a replacement.
+
+       (5)  Should  I  allocate/free  a  stack every time before/after calling
+       pcre_exec()?
+
+       No, because this is too costly in  terms  of  resources.  However,  you
+       could  implement  some clever idea which release the stack if it is not
+       used in let's say two minutes. The JIT callback can help to achive this
+       without keeping a list of the currently JIT studied patterns.
+
+       (6)  OK, the stack is for long term memory allocation. But what happens
+       if a pattern causes stack overflow with a stack of 1M? Is that 1M  kept
+       until the stack is freed?
+
+       Especially  on embedded sytems, it might be a good idea to release mem-
+       ory sometimes without freeing the stack. There is no API  for  this  at
+       the  moment.  Probably a function call which returns with the currently
+       allocated memory for any stack and another which allows releasing  mem-
+       ory (shrinking the stack) would be a good idea if someone needs this.
+
+       (7) This is too much of a headache. Isn't there any better solution for
+       JIT stack handling?
+
+       No, thanks to Windows. If POSIX threads were used everywhere, we  could
+       throw out this complicated API.
+
+
+EXAMPLE CODE
+
+       This  is  a  single-threaded example that specifies a JIT stack without
+       using a callback.
+
+         int rc;
+         int ovector[30];
+         pcre *re;
+         pcre_extra *extra;
+         pcre_jit_stack *jit_stack;
+
+         re = pcre_compile(pattern, 0, &error, &erroffset, NULL);
+         /* Check for errors */
+         extra = pcre_study(re, PCRE_STUDY_JIT_COMPILE, &error);
+         jit_stack = pcre_jit_stack_alloc(32*1024, 512*1024);
+         /* Check for error (NULL) */
+         pcre_assign_jit_stack(extra, NULL, jit_stack);
+         rc = pcre_exec(re, extra, subject, length, 0, 0, ovector, 30);
+         /* Check results */
+         pcre_free(re);
+         pcre_free_study(extra);
+         pcre_jit_stack_free(jit_stack);
+
+
+SEE ALSO
+
+       pcreapi(3)
+
+
+AUTHOR
+
+       Philip Hazel (FAQ by Zoltan Herczeg)
+       University Computing Service
+       Cambridge CB2 3QH, England.
+
+
+REVISION
+
+       Last updated: 04 May 2012
+       Copyright (c) 1997-2012 University of Cambridge.
+------------------------------------------------------------------------------
+
+
+PCREPARTIAL(3)                                                  PCREPARTIAL(3)
+
+
+NAME
+       PCRE - Perl-compatible regular expressions
+
+
+PARTIAL MATCHING IN PCRE
+
+       In normal use of PCRE, if the subject string that is passed to a match-
+       ing function matches as far as it goes, but is too short to  match  the
+       entire pattern, PCRE_ERROR_NOMATCH is returned. There are circumstances
+       where it might be helpful to distinguish this case from other cases  in
+       which there is no match.
+
+       Consider, for example, an application where a human is required to type
+       in data for a field with specific formatting requirements.  An  example
+       might be a date in the form ddmmmyy, defined by this pattern:
+
+         ^\d?\d(jan|feb|mar|apr|may|jun|jul|aug|sep|oct|nov|dec)\d\d$
+
+       If the application sees the user's keystrokes one by one, and can check
+       that what has been typed so far is potentially valid,  it  is  able  to
+       raise  an  error  as  soon  as  a  mistake  is made, by beeping and not
+       reflecting the character that has been typed, for example. This immedi-
+       ate  feedback is likely to be a better user interface than a check that
+       is delayed until the entire string has been entered.  Partial  matching
+       can  also be useful when the subject string is very long and is not all
+       available at once.
+
+       PCRE supports partial matching by means of  the  PCRE_PARTIAL_SOFT  and
+       PCRE_PARTIAL_HARD  options,  which  can  be set when calling any of the
+       matching functions. For backwards compatibility, PCRE_PARTIAL is a syn-
+       onym  for  PCRE_PARTIAL_SOFT.  The essential difference between the two
+       options is whether or not a partial match is preferred to  an  alterna-
+       tive complete match, though the details differ between the two types of
+       matching function. If both options  are  set,  PCRE_PARTIAL_HARD  takes
+       precedence.
+
+       If  you  want to use partial matching with just-in-time optimized code,
+       you must call pcre_study() or pcre16_study() with one or both of  these
+       options:
+
+         PCRE_STUDY_JIT_PARTIAL_SOFT_COMPILE
+         PCRE_STUDY_JIT_PARTIAL_HARD_COMPILE
+
+       PCRE_STUDY_JIT_COMPILE  should also be set if you are going to run non-
+       partial matches on the same pattern. If the appropriate JIT study  mode
+       has not been set for a match, the interpretive matching code is used.
+
+       Setting a partial matching option disables two of PCRE's standard opti-
+       mizations. PCRE remembers the last literal data unit in a pattern,  and
+       abandons  matching  immediately  if  it  is  not present in the subject
+       string. This optimization cannot be used  for  a  subject  string  that
+       might  match only partially. If the pattern was studied, PCRE knows the
+       minimum length of a matching string, and does not  bother  to  run  the
+       matching  function  on  shorter strings. This optimization is also dis-
+       abled for partial matching.
+
+
+PARTIAL MATCHING USING pcre_exec() OR pcre16_exec()
+
+       A partial match occurs during a call to  pcre_exec()  or  pcre16_exec()
+       when  the end of the subject string is reached successfully, but match-
+       ing cannot continue because more characters  are  needed.  However,  at
+       least one character in the subject must have been inspected. This char-
+       acter need not form part of the final matched string; lookbehind asser-
+       tions  and the \K escape sequence provide ways of inspecting characters
+       before the start of a matched substring. The requirement for inspecting
+       at  least  one  character  exists because an empty string can always be
+       matched; without such a restriction there would  always  be  a  partial
+       match of an empty string at the end of the subject.
+
+       If  there  are  at least two slots in the offsets vector when a partial
+       match is returned, the first slot is set to the offset of the  earliest
+       character that was inspected. For convenience, the second offset points
+       to the end of the subject so that a substring can easily be identified.
+
+       For the majority of patterns, the first offset identifies the start  of
+       the  partially matched string. However, for patterns that contain look-
+       behind assertions, or \K, or begin with \b or  \B,  earlier  characters
+       have been inspected while carrying out the match. For example:
+
+         /(?<=abc)123/
+
+       This pattern matches "123", but only if it is preceded by "abc". If the
+       subject string is "xyzabc12", the offsets after a partial match are for
+       the  substring  "abc12",  because  all  these  characters are needed if
+       another match is tried with extra characters added to the subject.
+
+       What happens when a partial match is identified depends on which of the
+       two partial matching options are set.
+
+   PCRE_PARTIAL_SOFT WITH pcre_exec() OR pcre16_exec()
+
+       If  PCRE_PARTIAL_SOFT  is set when pcre_exec() or pcre16_exec() identi-
+       fies a partial match, the partial match  is  remembered,  but  matching
+       continues  as  normal, and other alternatives in the pattern are tried.
+       If no complete match  can  be  found,  PCRE_ERROR_PARTIAL  is  returned
+       instead of PCRE_ERROR_NOMATCH.
+
+       This  option  is "soft" because it prefers a complete match over a par-
+       tial match.  All the various matching items in a pattern behave  as  if
+       the  subject string is potentially complete. For example, \z, \Z, and $
+       match at the end of the subject, as normal, and for \b and \B  the  end
+       of the subject is treated as a non-alphanumeric.
+
+       If  there  is more than one partial match, the first one that was found
+       provides the data that is returned. Consider this pattern:
+
+         /123\w+X|dogY/
+
+       If this is matched against the subject string "abc123dog", both  alter-
+       natives  fail  to  match,  but the end of the subject is reached during
+       matching, so PCRE_ERROR_PARTIAL is returned. The offsets are set  to  3
+       and  9, identifying "123dog" as the first partial match that was found.
+       (In this example, there are two partial matches, because "dog"  on  its
+       own partially matches the second alternative.)
+
+   PCRE_PARTIAL_HARD WITH pcre_exec() OR pcre16_exec()
+
+       If   PCRE_PARTIAL_HARD   is   set  for  pcre_exec()  or  pcre16_exec(),
+       PCRE_ERROR_PARTIAL is returned as soon as a  partial  match  is  found,
+       without continuing to search for possible complete matches. This option
+       is "hard" because it prefers an earlier partial match over a later com-
+       plete  match.  For  this reason, the assumption is made that the end of
+       the supplied subject string may not be the true end  of  the  available
+       data, and so, if \z, \Z, \b, \B, or $ are encountered at the end of the
+       subject, the result is PCRE_ERROR_PARTIAL, provided that at  least  one
+       character in the subject has been inspected.
+
+       Setting PCRE_PARTIAL_HARD also affects the way UTF-8 and UTF-16 subject
+       strings are checked for validity. Normally, an invalid sequence  causes
+       the  error  PCRE_ERROR_BADUTF8  or PCRE_ERROR_BADUTF16. However, in the
+       special case of a truncated  character  at  the  end  of  the  subject,
+       PCRE_ERROR_SHORTUTF8   or   PCRE_ERROR_SHORTUTF16   is   returned  when
+       PCRE_PARTIAL_HARD is set.
+
+   Comparing hard and soft partial matching
+
+       The difference between the two partial matching options can  be  illus-
+       trated by a pattern such as:
+
+         /dog(sbody)?/
+
+       This  matches either "dog" or "dogsbody", greedily (that is, it prefers
+       the longer string if possible). If it is  matched  against  the  string
+       "dog"  with  PCRE_PARTIAL_SOFT,  it  yields a complete match for "dog".
+       However, if PCRE_PARTIAL_HARD is set, the result is PCRE_ERROR_PARTIAL.
+       On  the  other hand, if the pattern is made ungreedy the result is dif-
+       ferent:
+
+         /dog(sbody)??/
+
+       In this case the result is always a  complete  match  because  that  is
+       found  first,  and  matching  never  continues after finding a complete
+       match. It might be easier to follow this explanation by thinking of the
+       two patterns like this:
+
+         /dog(sbody)?/    is the same as  /dogsbody|dog/
+         /dog(sbody)??/   is the same as  /dog|dogsbody/
+
+       The  second pattern will never match "dogsbody", because it will always
+       find the shorter match first.
+
+
+PARTIAL MATCHING USING pcre_dfa_exec() OR pcre16_dfa_exec()
+
+       The DFA functions move along the subject string character by character,
+       without  backtracking,  searching  for  all possible matches simultane-
+       ously. If the end of the subject is reached before the end of the  pat-
+       tern,  there is the possibility of a partial match, again provided that
+       at least one character has been inspected.
+
+       When PCRE_PARTIAL_SOFT is set, PCRE_ERROR_PARTIAL is returned  only  if
+       there  have  been  no complete matches. Otherwise, the complete matches
+       are returned.  However, if PCRE_PARTIAL_HARD is set,  a  partial  match
+       takes  precedence  over any complete matches. The portion of the string
+       that was inspected when the longest partial match was found is  set  as
+       the first matching string, provided there are at least two slots in the
+       offsets vector.
+
+       Because the DFA functions always search for all possible  matches,  and
+       there  is  no  difference between greedy and ungreedy repetition, their
+       behaviour is different  from  the  standard  functions  when  PCRE_PAR-
+       TIAL_HARD  is  set.  Consider  the  string  "dog"  matched  against the
+       ungreedy pattern shown above:
+
+         /dog(sbody)??/
+
+       Whereas the standard functions stop as soon as they find  the  complete
+       match  for  "dog",  the  DFA  functions also find the partial match for
+       "dogsbody", and so return that when PCRE_PARTIAL_HARD is set.
+
+
+PARTIAL MATCHING AND WORD BOUNDARIES
+
+       If a pattern ends with one of sequences \b or \B, which test  for  word
+       boundaries,  partial  matching with PCRE_PARTIAL_SOFT can give counter-
+       intuitive results. Consider this pattern:
+
+         /\bcat\b/
+
+       This matches "cat", provided there is a word boundary at either end. If
+       the subject string is "the cat", the comparison of the final "t" with a
+       following character cannot take place, so a  partial  match  is  found.
+       However,  normal  matching carries on, and \b matches at the end of the
+       subject when the last character is a letter, so  a  complete  match  is
+       found.   The   result,  therefore,  is  not  PCRE_ERROR_PARTIAL.  Using
+       PCRE_PARTIAL_HARD in this case does yield  PCRE_ERROR_PARTIAL,  because
+       then the partial match takes precedence.
+
+
+FORMERLY RESTRICTED PATTERNS
+
+       For releases of PCRE prior to 8.00, because of the way certain internal
+       optimizations  were  implemented  in  the  pcre_exec()  function,   the
+       PCRE_PARTIAL  option  (predecessor  of  PCRE_PARTIAL_SOFT) could not be
+       used with all patterns. From release 8.00 onwards, the restrictions  no
+       longer  apply,  and partial matching with can be requested for any pat-
+       tern.
+
+       Items that were formerly restricted were repeated single characters and
+       repeated  metasequences. If PCRE_PARTIAL was set for a pattern that did
+       not conform to the restrictions, pcre_exec() returned  the  error  code
+       PCRE_ERROR_BADPARTIAL  (-13).  This error code is no longer in use. The
+       PCRE_INFO_OKPARTIAL call to pcre_fullinfo() to find out if  a  compiled
+       pattern can be used for partial matching now always returns 1.
+
+
+EXAMPLE OF PARTIAL MATCHING USING PCRETEST
+
+       If  the  escape  sequence  \P  is  present in a pcretest data line, the
+       PCRE_PARTIAL_SOFT option is used for  the  match.  Here  is  a  run  of
+       pcretest that uses the date example quoted above:
+
+           re> /^\d?\d(jan|feb|mar|apr|may|jun|jul|aug|sep|oct|nov|dec)\d\d$/
+         data> 25jun04\P
+          0: 25jun04
+          1: jun
+         data> 25dec3\P
+         Partial match: 23dec3
+         data> 3ju\P
+         Partial match: 3ju
+         data> 3juj\P
+         No match
+         data> j\P
+         No match
+
+       The  first  data  string  is  matched completely, so pcretest shows the
+       matched substrings. The remaining four strings do not  match  the  com-
+       plete pattern, but the first two are partial matches. Similar output is
+       obtained if DFA matching is used.
+
+       If the escape sequence \P is present more than once in a pcretest  data
+       line, the PCRE_PARTIAL_HARD option is set for the match.
+
+
+MULTI-SEGMENT MATCHING WITH pcre_dfa_exec() OR pcre16_dfa_exec()
+
+       When  a  partial match has been found using a DFA matching function, it
+       is possible to continue the match by providing additional subject  data
+       and  calling  the function again with the same compiled regular expres-
+       sion, this time setting the PCRE_DFA_RESTART option. You must pass  the
+       same working space as before, because this is where details of the pre-
+       vious partial match are stored. Here  is  an  example  using  pcretest,
+       using  the  \R  escape  sequence to set the PCRE_DFA_RESTART option (\D
+       specifies the use of the DFA matching function):
+
+           re> /^\d?\d(jan|feb|mar|apr|may|jun|jul|aug|sep|oct|nov|dec)\d\d$/
+         data> 23ja\P\D
+         Partial match: 23ja
+         data> n05\R\D
+          0: n05
+
+       The first call has "23ja" as the subject, and requests  partial  match-
+       ing;  the  second  call  has  "n05"  as  the  subject for the continued
+       (restarted) match.  Notice that when the match is  complete,  only  the
+       last  part  is  shown;  PCRE  does not retain the previously partially-
+       matched string. It is up to the calling program to do that if it  needs
+       to.
+
+       You  can  set  the  PCRE_PARTIAL_SOFT or PCRE_PARTIAL_HARD options with
+       PCRE_DFA_RESTART to continue partial matching over  multiple  segments.
+       This  facility can be used to pass very long subject strings to the DFA
+       matching functions.
+
+
+MULTI-SEGMENT MATCHING WITH pcre_exec() OR pcre16_exec()
+
+       From release 8.00, the standard matching functions can also be used  to
+       do multi-segment matching. Unlike the DFA functions, it is not possible
+       to restart the previous match with a new segment of data. Instead,  new
+       data must be added to the previous subject string, and the entire match
+       re-run, starting from the point where the partial match occurred.  Ear-
+       lier data can be discarded.
+
+       It  is best to use PCRE_PARTIAL_HARD in this situation, because it does
+       not treat the end of a segment as the end of the subject when  matching
+       \z,  \Z,  \b,  \B,  and  $. Consider an unanchored pattern that matches
+       dates:
+
+           re> /\d?\d(jan|feb|mar|apr|may|jun|jul|aug|sep|oct|nov|dec)\d\d/
+         data> The date is 23ja\P\P
+         Partial match: 23ja
+
+       At this stage, an application could discard the text preceding  "23ja",
+       add  on  text  from  the  next  segment, and call the matching function
+       again. Unlike the DFA matching functions, the  entire  matching  string
+       must  always be available, and the complete matching process occurs for
+       each call, so more memory and more processing time is needed.
+
+       Note: If the pattern contains lookbehind assertions, or \K,  or  starts
+       with \b or \B, the string that is returned for a partial match includes
+       characters that precede the partially matched  string  itself,  because
+       these  must be retained when adding on more characters for a subsequent
+       matching attempt.  However, in some cases you may need to  retain  even
+       earlier characters, as discussed in the next section.
+
+
+ISSUES WITH MULTI-SEGMENT MATCHING
+
+       Certain types of pattern may give problems with multi-segment matching,
+       whichever matching function is used.
+
+       1. If the pattern contains a test for the beginning of a line, you need
+       to  pass  the  PCRE_NOTBOL  option when the subject string for any call
+       does start at the beginning of a line.  There  is  also  a  PCRE_NOTEOL
+       option, but in practice when doing multi-segment matching you should be
+       using PCRE_PARTIAL_HARD, which includes the effect of PCRE_NOTEOL.
+
+       2. Lookbehind assertions that have already been obeyed are catered  for
+       in the offsets that are returned for a partial match. However a lookbe-
+       hind assertion later in the pattern could require even earlier  charac-
+       ters   to  be  inspected.  You  can  handle  this  case  by  using  the
+       PCRE_INFO_MAXLOOKBEHIND    option    of    the    pcre_fullinfo()    or
+       pcre16_fullinfo() functions to obtain the length of the largest lookbe-
+       hind in the pattern. This length is given in characters, not bytes.  If
+       you  always  retain  at least that many characters before the partially
+       matched string, all should be well. (Of course, near the start  of  the
+       subject,  fewer  characters may be present; in that case all characters
+       should be retained.)
+
+       3. Because a partial match must always contain at least one  character,
+       what  might  be  considered a partial match of an empty string actually
+       gives a "no match" result. For example:
+
+           re> /c(?<=abc)x/
+         data> ab\P
+         No match
+
+       If the next segment begins "cx", a match should be found, but this will
+       only  happen  if characters from the previous segment are retained. For
+       this reason, a "no match" result  should  be  interpreted  as  "partial
+       match of an empty string" when the pattern contains lookbehinds.
+
+       4.  Matching  a subject string that is split into multiple segments may
+       not always produce exactly the same result as matching over one  single
+       long  string,  especially  when  PCRE_PARTIAL_SOFT is used. The section
+       "Partial Matching and Word Boundaries" above describes  an  issue  that
+       arises  if  the  pattern ends with \b or \B. Another kind of difference
+       may occur when there are multiple matching possibilities, because  (for
+       PCRE_PARTIAL_SOFT)  a partial match result is given only when there are
+       no completed matches. This means that as soon as the shortest match has
+       been  found,  continuation to a new subject segment is no longer possi-
+       ble. Consider again this pcretest example:
+
+           re> /dog(sbody)?/
+         data> dogsb\P
+          0: dog
+         data> do\P\D
+         Partial match: do
+         data> gsb\R\P\D
+          0: g
+         data> dogsbody\D
+          0: dogsbody
+          1: dog
+
+       The first data line passes the string "dogsb" to  a  standard  matching
+       function,  setting the PCRE_PARTIAL_SOFT option. Although the string is
+       a partial match for "dogsbody", the result is  not  PCRE_ERROR_PARTIAL,
+       because  the  shorter string "dog" is a complete match. Similarly, when
+       the subject is presented to a DFA matching function  in  several  parts
+       ("do"  and  "gsb"  being  the first two) the match stops when "dog" has
+       been found, and it is not possible to continue.  On the other hand,  if
+       "dogsbody"  is  presented  as  a single string, a DFA matching function
+       finds both matches.
+
+       Because of these problems, it is best  to  use  PCRE_PARTIAL_HARD  when
+       matching  multi-segment  data.  The  example above then behaves differ-
+       ently:
+
+           re> /dog(sbody)?/
+         data> dogsb\P\P
+         Partial match: dogsb
+         data> do\P\D
+         Partial match: do
+         data> gsb\R\P\P\D
+         Partial match: gsb
+
+       5. Patterns that contain alternatives at the top level which do not all
+       start  with  the  same  pattern  item  may  not  work  as expected when
+       PCRE_DFA_RESTART is used. For example, consider this pattern:
+
+         1234|3789
+
+       If the first part of the subject is "ABC123", a partial  match  of  the
+       first  alternative  is found at offset 3. There is no partial match for
+       the second alternative, because such a match does not start at the same
+       point  in  the  subject  string. Attempting to continue with the string
+       "7890" does not yield a match  because  only  those  alternatives  that
+       match  at  one  point in the subject are remembered. The problem arises
+       because the start of the second alternative matches  within  the  first
+       alternative.  There  is  no  problem with anchored patterns or patterns
+       such as:
+
+         1234|ABCD
+
+       where no string can be a partial match for both alternatives.  This  is
+       not  a  problem  if  a  standard matching function is used, because the
+       entire match has to be rerun each time:
+
+           re> /1234|3789/
+         data> ABC123\P\P
+         Partial match: 123
+         data> 1237890
+          0: 3789
+
+       Of course, instead of using PCRE_DFA_RESTART, the same technique of re-
+       running  the  entire match can also be used with the DFA matching func-
+       tions. Another possibility is to work with two buffers.  If  a  partial
+       match  at  offset  n in the first buffer is followed by "no match" when
+       PCRE_DFA_RESTART is used on the second buffer, you can then try  a  new
+       match starting at offset n+1 in the first buffer.
+
+
+AUTHOR
+
+       Philip Hazel
+       University Computing Service
+       Cambridge CB2 3QH, England.
+
+
+REVISION
+
+       Last updated: 24 February 2012
+       Copyright (c) 1997-2012 University of Cambridge.
+------------------------------------------------------------------------------
+
+
+PCREPRECOMPILE(3)                                            PCREPRECOMPILE(3)
+
+
+NAME
+       PCRE - Perl-compatible regular expressions
+
+
+SAVING AND RE-USING PRECOMPILED PCRE PATTERNS
+
+       If  you  are running an application that uses a large number of regular
+       expression patterns, it may be useful to store them  in  a  precompiled
+       form  instead  of  having to compile them every time the application is
+       run.  If you are not  using  any  private  character  tables  (see  the
+       pcre_maketables()  documentation),  this is relatively straightforward.
+       If you are using private tables, it is a little bit  more  complicated.
+       However,  if you are using the just-in-time optimization feature, it is
+       not possible to save and reload the JIT data.
+
+       If you save compiled patterns to a file, you can copy them to a differ-
+       ent host and run them there. If the two hosts have different endianness
+       (byte order), you should run the  pcre[16]_pattern_to_host_byte_order()
+       function on the new host before trying to match the pattern. The match-
+       ing functions return PCRE_ERROR_BADENDIANNESS if they detect a  pattern
+       with the wrong endianness.
+
+       Compiling  regular  expressions with one version of PCRE for use with a
+       different version is not guaranteed to work and may cause crashes,  and
+       saving  and  restoring  a  compiled  pattern loses any JIT optimization
+       data.
+
+
+SAVING A COMPILED PATTERN
+
+       The value returned by pcre[16]_compile() points to a  single  block  of
+       memory  that  holds  the  compiled pattern and associated data. You can
+       find the length of this block in bytes by  calling  pcre[16]_fullinfo()
+       with  an  argument of PCRE_INFO_SIZE. You can then save the data in any
+       appropriate manner. Here is sample code for the 8-bit library that com-
+       piles  a  pattern and writes it to a file. It assumes that the variable
+       fd refers to a file that is open for output:
+
+         int erroroffset, rc, size;
+         char *error;
+         pcre *re;
+
+         re = pcre_compile("my pattern", 0, &error, &erroroffset, NULL);
+         if (re == NULL) { ... handle errors ... }
+         rc = pcre_fullinfo(re, NULL, PCRE_INFO_SIZE, &size);
+         if (rc < 0) { ... handle errors ... }
+         rc = fwrite(re, 1, size, fd);
+         if (rc != size) { ... handle errors ... }
+
+       In this example, the bytes  that  comprise  the  compiled  pattern  are
+       copied  exactly.  Note that this is binary data that may contain any of
+       the 256 possible byte  values.  On  systems  that  make  a  distinction
+       between binary and non-binary data, be sure that the file is opened for
+       binary output.
+
+       If you want to write more than one pattern to a file, you will have  to
+       devise  a  way of separating them. For binary data, preceding each pat-
+       tern with its length is probably  the  most  straightforward  approach.
+       Another  possibility is to write out the data in hexadecimal instead of
+       binary, one pattern to a line.
+
+       Saving compiled patterns in a file is only one possible way of  storing
+       them  for later use. They could equally well be saved in a database, or
+       in the memory of some daemon process that passes them  via  sockets  to
+       the processes that want them.
+
+       If the pattern has been studied, it is also possible to save the normal
+       study data in a similar way to the compiled pattern itself. However, if
+       the PCRE_STUDY_JIT_COMPILE was used, the just-in-time data that is cre-
+       ated cannot be saved because it is too dependent on the  current  envi-
+       ronment.    When    studying    generates    additional    information,
+       pcre[16]_study() returns a pointer to a pcre[16]_extra data block.  Its
+       format  is  defined in the section on matching a pattern in the pcreapi
+       documentation. The study_data field points to the  binary  study  data,
+       and  this  is what you must save (not the pcre[16]_extra block itself).
+       The  length  of  the  study   data   can   be   obtained   by   calling
+       pcre[16]_fullinfo()  with  an argument of PCRE_INFO_STUDYSIZE. Remember
+       to check that pcre[16]_study() did return a non-NULL value before  try-
+       ing to save the study data.
+
+
+RE-USING A PRECOMPILED PATTERN
+
+       Re-using  a  precompiled pattern is straightforward. Having reloaded it
+       into main memory, called pcre[16]_pattern_to_host_byte_order() if  nec-
+       essary,  you pass its pointer to pcre[16]_exec() or pcre[16]_dfa_exec()
+       in the usual way.
+
+       However, if you passed a pointer to custom character  tables  when  the
+       pattern was compiled (the tableptr argument of pcre[16]_compile()), you
+       must   now   pass   a   similar   pointer   to    pcre[16]_exec()    or
+       pcre[16]_dfa_exec(),  because the value saved with the compiled pattern
+       will obviously be nonsense. A field in a pcre[16]_extra() block is used
+       to pass this data, as described in the section on matching a pattern in
+       the pcreapi documentation.
+
+       If you did not provide custom character tables  when  the  pattern  was
+       compiled, the pointer in the compiled pattern is NULL, which causes the
+       matching functions to use PCRE's internal tables. Thus, you do not need
+       to take any special action at run time in this case.
+
+       If  you  saved study data with the compiled pattern, you need to create
+       your own pcre[16]_extra data block and  set  the  study_data  field  to
+       point   to   the   reloaded   study   data.   You  must  also  set  the
+       PCRE_EXTRA_STUDY_DATA bit in the flags field  to  indicate  that  study
+       data  is  present.  Then  pass the pcre[16]_extra block to the matching
+       function in the usual way. If the pattern was studied for  just-in-time
+       optimization,  that  data  cannot  be  saved,  and  so  is  lost  by  a
+       save/restore cycle.
+
+
+COMPATIBILITY WITH DIFFERENT PCRE RELEASES
+
+       In general, it is safest to  recompile  all  saved  patterns  when  you
+       update  to  a new PCRE release, though not all updates actually require
+       this.
+
+
+AUTHOR
+
+       Philip Hazel
+       University Computing Service
+       Cambridge CB2 3QH, England.
+
+
+REVISION
+
+       Last updated: 10 January 2012
+       Copyright (c) 1997-2012 University of Cambridge.
+------------------------------------------------------------------------------
+
+
+PCREPERFORM(3)                                                  PCREPERFORM(3)
+
+
+NAME
+       PCRE - Perl-compatible regular expressions
+
+
+PCRE PERFORMANCE
+
+       Two  aspects  of performance are discussed below: memory usage and pro-
+       cessing time. The way you express your pattern as a regular  expression
+       can affect both of them.
+
+
+COMPILED PATTERN MEMORY USAGE
+
+       Patterns  are compiled by PCRE into a reasonably efficient interpretive
+       code, so that most simple patterns do not  use  much  memory.  However,
+       there  is  one case where the memory usage of a compiled pattern can be
+       unexpectedly large. If a parenthesized subpattern has a quantifier with
+       a minimum greater than 1 and/or a limited maximum, the whole subpattern
+       is repeated in the compiled code. For example, the pattern
+
+         (abc|def){2,4}
+
+       is compiled as if it were
+
+         (abc|def)(abc|def)((abc|def)(abc|def)?)?
+
+       (Technical aside: It is done this way so that backtrack  points  within
+       each of the repetitions can be independently maintained.)
+
+       For  regular expressions whose quantifiers use only small numbers, this
+       is not usually a problem. However, if the numbers are large,  and  par-
+       ticularly  if  such repetitions are nested, the memory usage can become
+       an embarrassment. For example, the very simple pattern
+
+         ((ab){1,1000}c){1,3}
+
+       uses 51K bytes when compiled using the 8-bit library. When PCRE is com-
+       piled  with  its  default  internal pointer size of two bytes, the size
+       limit on a compiled pattern is 64K data units, and this is reached with
+       the  above  pattern  if  the outer repetition is increased from 3 to 4.
+       PCRE can be compiled to use larger internal pointers  and  thus  handle
+       larger  compiled patterns, but it is better to try to rewrite your pat-
+       tern to use less memory if you can.
+
+       One way of reducing the memory usage for such patterns is to  make  use
+       of PCRE's "subroutine" facility. Re-writing the above pattern as
+
+         ((ab)(?2){0,999}c)(?1){0,2}
+
+       reduces the memory requirements to 18K, and indeed it remains under 20K
+       even with the outer repetition increased to 100. However, this  pattern
+       is  not  exactly equivalent, because the "subroutine" calls are treated
+       as atomic groups into which there can be no backtracking if there is  a
+       subsequent  matching  failure.  Therefore,  PCRE cannot do this kind of
+       rewriting automatically.  Furthermore, there is a  noticeable  loss  of
+       speed  when executing the modified pattern. Nevertheless, if the atomic
+       grouping is not a problem and the loss of  speed  is  acceptable,  this
+       kind  of  rewriting will allow you to process patterns that PCRE cannot
+       otherwise handle.
+
+
+STACK USAGE AT RUN TIME
+
+       When pcre_exec() or pcre16_exec() is used for matching,  certain  kinds
+       of  pattern  can cause it to use large amounts of the process stack. In
+       some environments the default process stack is quite small, and  if  it
+       runs  out  the result is often SIGSEGV. This issue is probably the most
+       frequently raised problem with PCRE. Rewriting your pattern  can  often
+       help. The pcrestack documentation discusses this issue in detail.
+
+
+PROCESSING TIME
+
+       Certain  items  in regular expression patterns are processed more effi-
+       ciently than others. It is more efficient to use a character class like
+       [aeiou]   than   a   set   of  single-character  alternatives  such  as
+       (a|e|i|o|u). In general, the simplest construction  that  provides  the
+       required behaviour is usually the most efficient. Jeffrey Friedl's book
+       contains a lot of useful general discussion  about  optimizing  regular
+       expressions  for  efficient  performance.  This document contains a few
+       observations about PCRE.
+
+       Using Unicode character properties (the \p,  \P,  and  \X  escapes)  is
+       slow,  because PCRE has to scan a structure that contains data for over
+       fifteen thousand characters whenever it needs a  character's  property.
+       If  you  can  find  an  alternative pattern that does not use character
+       properties, it will probably be faster.
+
+       By default, the escape sequences \b, \d, \s,  and  \w,  and  the  POSIX
+       character  classes  such  as  [:alpha:]  do not use Unicode properties,
+       partly for backwards compatibility, and partly for performance reasons.
+       However,  you can set PCRE_UCP if you want Unicode character properties
+       to be used. This can double the matching time for  items  such  as  \d,
+       when matched with a traditional matching function; the performance loss
+       is less with a DFA matching function, and in both cases  there  is  not
+       much difference for \b.
+
+       When  a  pattern  begins  with .* not in parentheses, or in parentheses
+       that are not the subject of a backreference, and the PCRE_DOTALL option
+       is  set, the pattern is implicitly anchored by PCRE, since it can match
+       only at the start of a subject string. However, if PCRE_DOTALL  is  not
+       set,  PCRE  cannot  make this optimization, because the . metacharacter
+       does not then match a newline, and if the subject string contains  new-
+       lines,  the  pattern may match from the character immediately following
+       one of them instead of from the very start. For example, the pattern
+
+         .*second
+
+       matches the subject "first\nand second" (where \n stands for a  newline
+       character),  with the match starting at the seventh character. In order
+       to do this, PCRE has to retry the match starting after every newline in
+       the subject.
+
+       If  you  are using such a pattern with subject strings that do not con-
+       tain newlines, the best performance is obtained by setting PCRE_DOTALL,
+       or  starting  the pattern with ^.* or ^.*? to indicate explicit anchor-
+       ing. That saves PCRE from having to scan along the subject looking  for
+       a newline to restart at.
+
+       Beware  of  patterns  that contain nested indefinite repeats. These can
+       take a long time to run when applied to a string that does  not  match.
+       Consider the pattern fragment
+
+         ^(a+)*
+
+       This  can  match "aaaa" in 16 different ways, and this number increases
+       very rapidly as the string gets longer. (The * repeat can match  0,  1,
+       2,  3, or 4 times, and for each of those cases other than 0 or 4, the +
+       repeats can match different numbers of times.) When  the  remainder  of
+       the pattern is such that the entire match is going to fail, PCRE has in
+       principle to try  every  possible  variation,  and  this  can  take  an
+       extremely long time, even for relatively short strings.
+
+       An optimization catches some of the more simple cases such as
+
+         (a+)*b
+
+       where  a  literal  character  follows. Before embarking on the standard
+       matching procedure, PCRE checks that there is a "b" later in  the  sub-
+       ject  string, and if there is not, it fails the match immediately. How-
+       ever, when there is no following literal this  optimization  cannot  be
+       used. You can see the difference by comparing the behaviour of
+
+         (a+)*\d
+
+       with  the  pattern  above.  The former gives a failure almost instantly
+       when applied to a whole line of  "a"  characters,  whereas  the  latter
+       takes an appreciable time with strings longer than about 20 characters.
+
+       In many cases, the solution to this kind of performance issue is to use
+       an atomic group or a possessive quantifier.
+
+
+AUTHOR
+
+       Philip Hazel
+       University Computing Service
+       Cambridge CB2 3QH, England.
+
+
+REVISION
+
+       Last updated: 09 January 2012
+       Copyright (c) 1997-2012 University of Cambridge.
+------------------------------------------------------------------------------
+
+
+PCREPOSIX(3)                                                      PCREPOSIX(3)
+
+
+NAME
+       PCRE - Perl-compatible regular expressions.
+
+
+SYNOPSIS OF POSIX API
+
+       #include <pcreposix.h>
+
+       int regcomp(regex_t *preg, const char *pattern,
+            int cflags);
+
+       int regexec(regex_t *preg, const char *string,
+            size_t nmatch, regmatch_t pmatch[], int eflags);
+
+       size_t regerror(int errcode, const regex_t *preg,
+            char *errbuf, size_t errbuf_size);
+
+       void regfree(regex_t *preg);
+
+
+DESCRIPTION
+
+       This  set  of functions provides a POSIX-style API for the PCRE regular
+       expression 8-bit library. See the pcreapi documentation for a  descrip-
+       tion  of  PCRE's native API, which contains much additional functional-
+       ity. There is no POSIX-style wrapper for PCRE's 16-bit library.
+
+       The functions described here are just wrapper functions that ultimately
+       call  the  PCRE  native  API.  Their  prototypes  are  defined  in  the
+       pcreposix.h header file, and on Unix  systems  the  library  itself  is
+       called  pcreposix.a,  so  can  be accessed by adding -lpcreposix to the
+       command for linking an application that uses them.  Because  the  POSIX
+       functions call the native ones, it is also necessary to add -lpcre.
+
+       I  have implemented only those POSIX option bits that can be reasonably
+       mapped to PCRE native options. In addition, the option REG_EXTENDED  is
+       defined  with  the  value  zero. This has no effect, but since programs
+       that are written to the POSIX interface often use  it,  this  makes  it
+       easier  to  slot  in PCRE as a replacement library. Other POSIX options
+       are not even defined.
+
+       There are also some other options that are not defined by POSIX.  These
+       have been added at the request of users who want to make use of certain
+       PCRE-specific features via the POSIX calling interface.
+
+       When PCRE is called via these functions, it is only  the  API  that  is
+       POSIX-like  in  style.  The syntax and semantics of the regular expres-
+       sions themselves are still those of Perl, subject  to  the  setting  of
+       various  PCRE  options, as described below. "POSIX-like in style" means
+       that the API approximates to the POSIX  definition;  it  is  not  fully
+       POSIX-compatible,  and  in  multi-byte  encoding domains it is probably
+       even less compatible.
+
+       The header for these functions is supplied as pcreposix.h to avoid  any
+       potential  clash  with  other  POSIX  libraries.  It can, of course, be
+       renamed or aliased as regex.h, which is the "correct" name. It provides
+       two  structure  types,  regex_t  for  compiled internal forms, and reg-
+       match_t for returning captured substrings. It also  defines  some  con-
+       stants  whose  names  start  with  "REG_";  these  are used for setting
+       options and identifying error codes.
+
+
+COMPILING A PATTERN
+
+       The function regcomp() is called to compile a pattern into an  internal
+       form.  The  pattern  is  a C string terminated by a binary zero, and is
+       passed in the argument pattern. The preg argument is  a  pointer  to  a
+       regex_t  structure that is used as a base for storing information about
+       the compiled regular expression.
+
+       The argument cflags is either zero, or contains one or more of the bits
+       defined by the following macros:
+
+         REG_DOTALL
+
+       The PCRE_DOTALL option is set when the regular expression is passed for
+       compilation to the native function. Note that REG_DOTALL is not part of
+       the POSIX standard.
+
+         REG_ICASE
+
+       The  PCRE_CASELESS  option is set when the regular expression is passed
+       for compilation to the native function.
+
+         REG_NEWLINE
+
+       The PCRE_MULTILINE option is set when the regular expression is  passed
+       for  compilation  to the native function. Note that this does not mimic
+       the defined POSIX behaviour for REG_NEWLINE  (see  the  following  sec-
+       tion).
+
+         REG_NOSUB
+
+       The  PCRE_NO_AUTO_CAPTURE  option is set when the regular expression is
+       passed for compilation to the native function. In addition, when a pat-
+       tern  that is compiled with this flag is passed to regexec() for match-
+       ing, the nmatch and pmatch  arguments  are  ignored,  and  no  captured
+       strings are returned.
+
+         REG_UCP
+
+       The  PCRE_UCP  option  is set when the regular expression is passed for
+       compilation to the native function. This causes  PCRE  to  use  Unicode
+       properties  when  matchine  \d,  \w,  etc., instead of just recognizing
+       ASCII values. Note that REG_UTF8 is not part of the POSIX standard.
+
+         REG_UNGREEDY
+
+       The PCRE_UNGREEDY option is set when the regular expression  is  passed
+       for  compilation  to the native function. Note that REG_UNGREEDY is not
+       part of the POSIX standard.
+
+         REG_UTF8
+
+       The PCRE_UTF8 option is set when the regular expression is  passed  for
+       compilation  to the native function. This causes the pattern itself and
+       all data strings used for matching it to be treated as  UTF-8  strings.
+       Note that REG_UTF8 is not part of the POSIX standard.
+
+       In  the  absence  of  these  flags, no options are passed to the native
+       function.  This means the the  regex  is  compiled  with  PCRE  default
+       semantics.  In particular, the way it handles newline characters in the
+       subject string is the Perl way, not the POSIX way.  Note  that  setting
+       PCRE_MULTILINE  has only some of the effects specified for REG_NEWLINE.
+       It does not affect the way newlines are matched by . (they are not)  or
+       by a negative class such as [^a] (they are).
+
+       The  yield of regcomp() is zero on success, and non-zero otherwise. The
+       preg structure is filled in on success, and one member of the structure
+       is  public: re_nsub contains the number of capturing subpatterns in the
+       regular expression. Various error codes are defined in the header file.
+
+       NOTE: If the yield of regcomp() is non-zero, you must  not  attempt  to
+       use the contents of the preg structure. If, for example, you pass it to
+       regexec(), the result is undefined and your program is likely to crash.
+
+
+MATCHING NEWLINE CHARACTERS
+
+       This area is not simple, because POSIX and Perl take different views of
+       things.   It  is  not possible to get PCRE to obey POSIX semantics, but
+       then PCRE was never intended to be a POSIX engine. The following  table
+       lists  the  different  possibilities for matching newline characters in
+       PCRE:
+
+                                 Default   Change with
+
+         . matches newline          no     PCRE_DOTALL
+         newline matches [^a]       yes    not changeable
+         $ matches \n at end        yes    PCRE_DOLLARENDONLY
+         $ matches \n in middle     no     PCRE_MULTILINE
+         ^ matches \n in middle     no     PCRE_MULTILINE
+
+       This is the equivalent table for POSIX:
+
+                                 Default   Change with
+
+         . matches newline          yes    REG_NEWLINE
+         newline matches [^a]       yes    REG_NEWLINE
+         $ matches \n at end        no     REG_NEWLINE
+         $ matches \n in middle     no     REG_NEWLINE
+         ^ matches \n in middle     no     REG_NEWLINE
+
+       PCRE's behaviour is the same as Perl's, except that there is no equiva-
+       lent  for  PCRE_DOLLAR_ENDONLY in Perl. In both PCRE and Perl, there is
+       no way to stop newline from matching [^a].
+
+       The  default  POSIX  newline  handling  can  be  obtained  by   setting
+       PCRE_DOTALL  and  PCRE_DOLLAR_ENDONLY, but there is no way to make PCRE
+       behave exactly as for the REG_NEWLINE action.
+
+
+MATCHING A PATTERN
+
+       The function regexec() is called  to  match  a  compiled  pattern  preg
+       against  a  given string, which is by default terminated by a zero byte
+       (but see REG_STARTEND below), subject to the options in  eflags.  These
+       can be:
+
+         REG_NOTBOL
+
+       The PCRE_NOTBOL option is set when calling the underlying PCRE matching
+       function.
+
+         REG_NOTEMPTY
+
+       The PCRE_NOTEMPTY option is set when calling the underlying PCRE match-
+       ing function. Note that REG_NOTEMPTY is not part of the POSIX standard.
+       However, setting this option can give more POSIX-like behaviour in some
+       situations.
+
+         REG_NOTEOL
+
+       The PCRE_NOTEOL option is set when calling the underlying PCRE matching
+       function.
+
+         REG_STARTEND
+
+       The string is considered to start at string +  pmatch[0].rm_so  and  to
+       have  a terminating NUL located at string + pmatch[0].rm_eo (there need
+       not actually be a NUL at that location), regardless  of  the  value  of
+       nmatch.  This  is a BSD extension, compatible with but not specified by
+       IEEE Standard 1003.2 (POSIX.2), and should  be  used  with  caution  in
+       software intended to be portable to other systems. Note that a non-zero
+       rm_so does not imply REG_NOTBOL; REG_STARTEND affects only the location
+       of the string, not how it is matched.
+
+       If  the pattern was compiled with the REG_NOSUB flag, no data about any
+       matched strings  is  returned.  The  nmatch  and  pmatch  arguments  of
+       regexec() are ignored.
+
+       If the value of nmatch is zero, or if the value pmatch is NULL, no data
+       about any matched strings is returned.
+
+       Otherwise,the portion of the string that was matched, and also any cap-
+       tured substrings, are returned via the pmatch argument, which points to
+       an array of nmatch structures of type regmatch_t, containing  the  mem-
+       bers  rm_so  and rm_eo. These contain the offset to the first character
+       of each substring and the offset to the first character after  the  end
+       of  each substring, respectively. The 0th element of the vector relates
+       to the entire portion of string that was matched;  subsequent  elements
+       relate  to  the capturing subpatterns of the regular expression. Unused
+       entries in the array have both structure members set to -1.
+
+       A successful match yields  a  zero  return;  various  error  codes  are
+       defined  in  the  header  file,  of which REG_NOMATCH is the "expected"
+       failure code.
+
+
+ERROR MESSAGES
+
+       The regerror() function maps a non-zero errorcode from either regcomp()
+       or  regexec()  to  a  printable message. If preg is not NULL, the error
+       should have arisen from the use of that structure. A message terminated
+       by  a  binary  zero  is  placed  in  errbuf. The length of the message,
+       including the zero, is limited to errbuf_size. The yield of  the  func-
+       tion is the size of buffer needed to hold the whole message.
+
+
+MEMORY USAGE
+
+       Compiling  a regular expression causes memory to be allocated and asso-
+       ciated with the preg structure. The function regfree() frees  all  such
+       memory,  after  which  preg may no longer be used as a compiled expres-
+       sion.
+
+
+AUTHOR
+
+       Philip Hazel
+       University Computing Service
+       Cambridge CB2 3QH, England.
+
+
+REVISION
+
+       Last updated: 09 January 2012
+       Copyright (c) 1997-2012 University of Cambridge.
+------------------------------------------------------------------------------
+
+
+PCRECPP(3)                                                          PCRECPP(3)
+
+
+NAME
+       PCRE - Perl-compatible regular expressions.
+
+
+SYNOPSIS OF C++ WRAPPER
+
+       #include <pcrecpp.h>
+
+
+DESCRIPTION
+
+       The  C++  wrapper  for PCRE was provided by Google Inc. Some additional
+       functionality was added by Giuseppe Maxia. This brief man page was con-
+       structed  from  the  notes  in the pcrecpp.h file, which should be con-
+       sulted for further details. Note that the C++ wrapper supports only the
+       original 8-bit PCRE library. There is no 16-bit support at present.
+
+
+MATCHING INTERFACE
+
+       The  "FullMatch" operation checks that supplied text matches a supplied
+       pattern exactly. If pointer arguments are supplied, it  copies  matched
+       sub-strings that match sub-patterns into them.
+
+         Example: successful match
+            pcrecpp::RE re("h.*o");
+            re.FullMatch("hello");
+
+         Example: unsuccessful match (requires full match):
+            pcrecpp::RE re("e");
+            !re.FullMatch("hello");
+
+         Example: creating a temporary RE object:
+            pcrecpp::RE("h.*o").FullMatch("hello");
+
+       You  can pass in a "const char*" or a "string" for "text". The examples
+       below tend to use a const char*. You can, as in the different  examples
+       above,  store the RE object explicitly in a variable or use a temporary
+       RE object. The examples below use one mode or  the  other  arbitrarily.
+       Either could correctly be used for any of these examples.
+
+       You must supply extra pointer arguments to extract matched subpieces.
+
+         Example: extracts "ruby" into "s" and 1234 into "i"
+            int i;
+            string s;
+            pcrecpp::RE re("(\\w+):(\\d+)");
+            re.FullMatch("ruby:1234", &s, &i);
+
+         Example: does not try to extract any extra sub-patterns
+            re.FullMatch("ruby:1234", &s);
+
+         Example: does not try to extract into NULL
+            re.FullMatch("ruby:1234", NULL, &i);
+
+         Example: integer overflow causes failure
+            !re.FullMatch("ruby:1234567891234", NULL, &i);
+
+         Example: fails because there aren't enough sub-patterns:
+            !pcrecpp::RE("\\w+:\\d+").FullMatch("ruby:1234", &s);
+
+         Example: fails because string cannot be stored in integer
+            !pcrecpp::RE("(.*)").FullMatch("ruby", &i);
+
+       The  provided  pointer  arguments can be pointers to any scalar numeric
+       type, or one of:
+
+          string        (matched piece is copied to string)
+          StringPiece   (StringPiece is mutated to point to matched piece)
+          T             (where "bool T::ParseFrom(const char*, int)" exists)
+          NULL          (the corresponding matched sub-pattern is not copied)
+
+       The function returns true iff all of the following conditions are  sat-
+       isfied:
+
+         a. "text" matches "pattern" exactly;
+
+         b. The number of matched sub-patterns is >= number of supplied
+            pointers;
+
+         c. The "i"th argument has a suitable type for holding the
+            string captured as the "i"th sub-pattern. If you pass in
+            void * NULL for the "i"th argument, or a non-void * NULL
+            of the correct type, or pass fewer arguments than the
+            number of sub-patterns, "i"th captured sub-pattern is
+            ignored.
+
+       CAVEAT:  An  optional  sub-pattern  that  does not exist in the matched
+       string is assigned the empty  string.  Therefore,  the  following  will
+       return false (because the empty string is not a valid number):
+
+          int number;
+          pcrecpp::RE::FullMatch("abc", "[a-z]+(\\d+)?", &number);
+
+       The  matching interface supports at most 16 arguments per call.  If you
+       need   more,   consider    using    the    more    general    interface
+       pcrecpp::RE::DoMatch. See pcrecpp.h for the signature for DoMatch.
+
+       NOTE:  Do not use no_arg, which is used internally to mark the end of a
+       list of optional arguments, as a placeholder for missing arguments,  as
+       this can lead to segfaults.
+
+
+QUOTING METACHARACTERS
+
+       You  can use the "QuoteMeta" operation to insert backslashes before all
+       potentially meaningful characters in a  string.  The  returned  string,
+       used as a regular expression, will exactly match the original string.
+
+         Example:
+            string quoted = RE::QuoteMeta(unquoted);
+
+       Note  that  it's  legal to escape a character even if it has no special
+       meaning in a regular expression -- so this function  does  that.  (This
+       also  makes  it  identical  to  the perl function of the same name; see
+       "perldoc   -f   quotemeta".)    For   example,    "1.5-2.0?"    becomes
+       "1\.5\-2\.0\?".
+
+
+PARTIAL MATCHES
+
+       You  can  use the "PartialMatch" operation when you want the pattern to
+       match any substring of the text.
+
+         Example: simple search for a string:
+            pcrecpp::RE("ell").PartialMatch("hello");
+
+         Example: find first number in a string:
+            int number;
+            pcrecpp::RE re("(\\d+)");
+            re.PartialMatch("x*100 + 20", &number);
+            assert(number == 100);
+
+
+UTF-8 AND THE MATCHING INTERFACE
+
+       By default, pattern and text are plain text, one  byte  per  character.
+       The  UTF8  flag,  passed  to  the  constructor, causes both pattern and
+       string to be treated as UTF-8 text, still a byte stream but potentially
+       multiple  bytes  per character. In practice, the text is likelier to be
+       UTF-8 than the pattern, but the match returned may depend on  the  UTF8
+       flag,  so  always use it when matching UTF8 text. For example, "." will
+       match one byte normally but with UTF8 set may match up to  three  bytes
+       of a multi-byte character.
+
+         Example:
+            pcrecpp::RE_Options options;
+            options.set_utf8();
+            pcrecpp::RE re(utf8_pattern, options);
+            re.FullMatch(utf8_string);
+
+         Example: using the convenience function UTF8():
+            pcrecpp::RE re(utf8_pattern, pcrecpp::UTF8());
+            re.FullMatch(utf8_string);
+
+       NOTE: The UTF8 flag is ignored if pcre was not configured with the
+             --enable-utf8 flag.
+
+
+PASSING MODIFIERS TO THE REGULAR EXPRESSION ENGINE
+
+       PCRE  defines  some  modifiers  to  change  the behavior of the regular
+       expression  engine.  The  C++  wrapper  defines  an  auxiliary   class,
+       RE_Options,  as  a  vehicle  to pass such modifiers to a RE class. Cur-
+       rently, the following modifiers are supported:
+
+          modifier              description               Perl corresponding
+
+          PCRE_CASELESS         case insensitive match      /i
+          PCRE_MULTILINE        multiple lines match        /m
+          PCRE_DOTALL           dot matches newlines        /s
+          PCRE_DOLLAR_ENDONLY   $ matches only at end       N/A
+          PCRE_EXTRA            strict escape parsing       N/A
+          PCRE_EXTENDED         ignore white spaces         /x
+          PCRE_UTF8             handles UTF8 chars          built-in
+          PCRE_UNGREEDY         reverses * and *?           N/A
+          PCRE_NO_AUTO_CAPTURE  disables capturing parens   N/A (*)
+
+       (*) Both Perl and PCRE allow non capturing parentheses by means of  the
+       "?:"  modifier  within the pattern itself. e.g. (?:ab|cd) does not cap-
+       ture, while (ab|cd) does.
+
+       For a full account on how each modifier works, please  check  the  PCRE
+       API reference page.
+
+       For  each  modifier,  there are two member functions whose name is made
+       out of the modifier in  lowercase,  without  the  "PCRE_"  prefix.  For
+       instance, PCRE_CASELESS is handled by
+
+         bool caseless()
+
+       which returns true if the modifier is set, and
+
+         RE_Options & set_caseless(bool)
+
+       which sets or unsets the modifier. Moreover, PCRE_EXTRA_MATCH_LIMIT can
+       be accessed through  the  set_match_limit()  and  match_limit()  member
+       functions.  Setting match_limit to a non-zero value will limit the exe-
+       cution of pcre to keep it from doing bad things like blowing the  stack
+       or  taking  an  eternity  to  return  a result. A value of 5000 is good
+       enough to stop stack blowup in a 2MB thread stack. Setting  match_limit
+       to   zero   disables   match  limiting.  Alternatively,  you  can  call
+       match_limit_recursion() which uses PCRE_EXTRA_MATCH_LIMIT_RECURSION  to
+       limit  how  much  PCRE  recurses.  match_limit()  limits  the number of
+       matches PCRE does; match_limit_recursion() limits the depth of internal
+       recursion, and therefore the amount of stack that is used.
+
+       Normally,  to  pass  one or more modifiers to a RE class, you declare a
+       RE_Options object, set the appropriate options, and pass this object to
+       a RE constructor. Example:
+
+          RE_Options opt;
+          opt.set_caseless(true);
+          if (RE("HELLO", opt).PartialMatch("hello world")) ...
+
+       RE_options has two constructors. The default constructor takes no argu-
+       ments and creates a set of flags that are off by default. The  optional
+       parameter  option_flags is to facilitate transfer of legacy code from C
+       programs.  This lets you do
+
+          RE(pattern,
+            RE_Options(PCRE_CASELESS|PCRE_MULTILINE)).PartialMatch(str);
+
+       However, new code is better off doing
+
+          RE(pattern,
+            RE_Options().set_caseless(true).set_multiline(true))
+              .PartialMatch(str);
+
+       If you are going to pass one of the most used modifiers, there are some
+       convenience functions that return a RE_Options class with the appropri-
+       ate modifier already set: CASELESS(),  UTF8(),  MULTILINE(),  DOTALL(),
+       and EXTENDED().
+
+       If  you  need  to set several options at once, and you don't want to go
+       through the pains of declaring a RE_Options object and setting  several
+       options,  there  is a parallel method that give you such ability on the
+       fly. You can concatenate several set_xxxxx()  member  functions,  since
+       each  of  them returns a reference to its class object. For example, to
+       pass PCRE_CASELESS, PCRE_EXTENDED, and PCRE_MULTILINE to a RE with  one
+       statement, you may write:
+
+          RE(" ^ xyz \\s+ .* blah$",
+            RE_Options()
+              .set_caseless(true)
+              .set_extended(true)
+              .set_multiline(true)).PartialMatch(sometext);
+
+
+SCANNING TEXT INCREMENTALLY
+
+       The  "Consume"  operation may be useful if you want to repeatedly match
+       regular expressions at the front of a string and skip over them as they
+       match.  This requires use of the "StringPiece" type, which represents a
+       sub-range of a real string. Like RE,  StringPiece  is  defined  in  the
+       pcrecpp namespace.
+
+         Example: read lines of the form "var = value" from a string.
+            string contents = ...;                 // Fill string somehow
+            pcrecpp::StringPiece input(contents);  // Wrap in a StringPiece
+
+            string var;
+            int value;
+            pcrecpp::RE re("(\\w+) = (\\d+)\n");
+            while (re.Consume(&input, &var, &value)) {
+              ...;
+            }
+
+       Each  successful  call  to  "Consume"  will  set  "var/value", and also
+       advance "input" so it points past the matched text.
+
+       The "FindAndConsume" operation is similar to  "Consume"  but  does  not
+       anchor  your  match  at  the  beginning of the string. For example, you
+       could extract all words from a string by repeatedly calling
+
+         pcrecpp::RE("(\\w+)").FindAndConsume(&input, &word)
+
+
+PARSING HEX/OCTAL/C-RADIX NUMBERS
+
+       By default, if you pass a pointer to a numeric value, the corresponding
+       text  is  interpreted  as  a  base-10  number. You can instead wrap the
+       pointer with a call to one of the operators Hex(), Octal(), or CRadix()
+       to  interpret  the text in another base. The CRadix operator interprets
+       C-style "0" (base-8) and  "0x"  (base-16)  prefixes,  but  defaults  to
+       base-10.
+
+         Example:
+           int a, b, c, d;
+           pcrecpp::RE re("(.*) (.*) (.*) (.*)");
+           re.FullMatch("100 40 0100 0x40",
+                        pcrecpp::Octal(&a), pcrecpp::Hex(&b),
+                        pcrecpp::CRadix(&c), pcrecpp::CRadix(&d));
+
+       will leave 64 in a, b, c, and d.
+
+
+REPLACING PARTS OF STRINGS
+
+       You  can  replace the first match of "pattern" in "str" with "rewrite".
+       Within "rewrite", backslash-escaped digits (\1 to \9) can  be  used  to
+       insert  text  matching  corresponding parenthesized group from the pat-
+       tern. \0 in "rewrite" refers to the entire matching text. For example:
+
+         string s = "yabba dabba doo";
+         pcrecpp::RE("b+").Replace("d", &s);
+
+       will leave "s" containing "yada dabba doo". The result is true  if  the
+       pattern matches and a replacement occurs, false otherwise.
+
+       GlobalReplace  is  like Replace except that it replaces all occurrences
+       of the pattern in the string with the  rewrite.  Replacements  are  not
+       subject to re-matching. For example:
+
+         string s = "yabba dabba doo";
+         pcrecpp::RE("b+").GlobalReplace("d", &s);
+
+       will  leave  "s"  containing  "yada dada doo". It returns the number of
+       replacements made.
+
+       Extract is like Replace, except that if the pattern matches,  "rewrite"
+       is  copied into "out" (an additional argument) with substitutions.  The
+       non-matching portions of "text" are ignored. Returns true iff  a  match
+       occurred and the extraction happened successfully;  if no match occurs,
+       the string is left unaffected.
+
+
+AUTHOR
+
+       The C++ wrapper was contributed by Google Inc.
+       Copyright (c) 2007 Google Inc.
+
+
+REVISION
+
+       Last updated: 08 January 2012
+------------------------------------------------------------------------------
+
+
+PCRESAMPLE(3)                                                    PCRESAMPLE(3)
+
+
+NAME
+       PCRE - Perl-compatible regular expressions
+
+
+PCRE SAMPLE PROGRAM
+
+       A simple, complete demonstration program, to get you started with using
+       PCRE, is supplied in the file pcredemo.c in the  PCRE  distribution.  A
+       listing  of this program is given in the pcredemo documentation. If you
+       do not have a copy of the PCRE distribution, you can save this  listing
+       to re-create pcredemo.c.
+
+       The  demonstration program, which uses the original PCRE 8-bit library,
+       compiles the regular expression that is its first argument, and matches
+       it  against  the subject string in its second argument. No PCRE options
+       are set, and default character tables are used. If  matching  succeeds,
+       the  program  outputs the portion of the subject that matched, together
+       with the contents of any captured substrings.
+
+       If the -g option is given on the command line, the program then goes on
+       to check for further matches of the same regular expression in the same
+       subject string. The logic is a little bit tricky because of the  possi-
+       bility  of  matching an empty string. Comments in the code explain what
+       is going on.
+
+       If PCRE is installed in the standard include  and  library  directories
+       for your operating system, you should be able to compile the demonstra-
+       tion program using this command:
+
+         gcc -o pcredemo pcredemo.c -lpcre
+
+       If PCRE is installed elsewhere, you may need to add additional  options
+       to  the  command line. For example, on a Unix-like system that has PCRE
+       installed in /usr/local, you  can  compile  the  demonstration  program
+       using a command like this:
+
+         gcc -o pcredemo -I/usr/local/include pcredemo.c \
+             -L/usr/local/lib -lpcre
+
+       In  a  Windows  environment, if you want to statically link the program
+       against a non-dll pcre.a file, you must uncomment the line that defines
+       PCRE_STATIC  before  including  pcre.h, because otherwise the pcre_mal-
+       loc()   and   pcre_free()   exported   functions   will   be   declared
+       __declspec(dllimport), with unwanted results.
+
+       Once  you  have  compiled and linked the demonstration program, you can
+       run simple tests like this:
+
+         ./pcredemo 'cat|dog' 'the cat sat on the mat'
+         ./pcredemo -g 'cat|dog' 'the dog sat on the cat'
+
+       Note that there is a  much  more  comprehensive  test  program,  called
+       pcretest,  which  supports  many  more  facilities  for testing regular
+       expressions and both PCRE libraries. The pcredemo program  is  provided
+       as a simple coding example.
+
+       If  you  try to run pcredemo when PCRE is not installed in the standard
+       library directory, you may get an error like  this  on  some  operating
+       systems (e.g. Solaris):
+
+         ld.so.1:  a.out:  fatal:  libpcre.so.0:  open failed: No such file or
+       directory
+
+       This is caused by the way shared library support works  on  those  sys-
+       tems. You need to add
+
+         -R/usr/local/lib
+
+       (for example) to the compile command to get round this problem.
+
+
+AUTHOR
+
+       Philip Hazel
+       University Computing Service
+       Cambridge CB2 3QH, England.
+
+
+REVISION
+
+       Last updated: 10 January 2012
+       Copyright (c) 1997-2012 University of Cambridge.
+------------------------------------------------------------------------------
+PCRELIMITS(3)                                                    PCRELIMITS(3)
+
+
+NAME
+       PCRE - Perl-compatible regular expressions
+
+
+SIZE AND OTHER LIMITATIONS
+
+       There  are some size limitations in PCRE but it is hoped that they will
+       never in practice be relevant.
+
+       The maximum length of a compiled  pattern  is  approximately  64K  data
+       units  (bytes  for  the  8-bit  library,  16-bit  units  for the 16-bit
+       library) if PCRE is compiled with the default internal linkage size  of
+       2  bytes.  If  you  want  to process regular expressions that are truly
+       enormous, you can compile PCRE with an internal linkage size of 3 or  4
+       (when  building  the  16-bit  library,  3  is rounded up to 4). See the
+       README file in the source distribution and the pcrebuild  documentation
+       for  details.  In  these cases the limit is substantially larger.  How-
+       ever, the speed of execution is slower.
+
+       All values in repeating quantifiers must be less than 65536.
+
+       There is no limit to the number of parenthesized subpatterns, but there
+       can be no more than 65535 capturing subpatterns.
+
+       There is a limit to the number of forward references to subsequent sub-
+       patterns of around 200,000.  Repeated  forward  references  with  fixed
+       upper  limits,  for example, (?2){0,100} when subpattern number 2 is to
+       the right, are included in the count. There is no limit to  the  number
+       of backward references.
+
+       The maximum length of name for a named subpattern is 32 characters, and
+       the maximum number of named subpatterns is 10000.
+
+       The maximum length of a  name  in  a  (*MARK),  (*PRUNE),  (*SKIP),  or
+       (*THEN)  verb  is  255  for  the 8-bit library and 65535 for the 16-bit
+       library.
+
+       The maximum length of a subject string is the largest  positive  number
+       that  an integer variable can hold. However, when using the traditional
+       matching function, PCRE uses recursion to handle subpatterns and indef-
+       inite  repetition.  This means that the available stack space may limit
+       the size of a subject string that can be processed by certain patterns.
+       For a discussion of stack issues, see the pcrestack documentation.
+
+
+AUTHOR
+
+       Philip Hazel
+       University Computing Service
+       Cambridge CB2 3QH, England.
+
+
+REVISION
+
+       Last updated: 04 May 2012
+       Copyright (c) 1997-2012 University of Cambridge.
+------------------------------------------------------------------------------
+
+
+PCRESTACK(3)                                                      PCRESTACK(3)
+
+
+NAME
+       PCRE - Perl-compatible regular expressions
+
+
+PCRE DISCUSSION OF STACK USAGE
+
+       When  you  call  pcre[16]_exec(),  it makes use of an internal function
+       called match(). This calls itself recursively at branch points  in  the
+       pattern,  in  order  to  remember the state of the match so that it can
+       back up and try a different alternative if  the  first  one  fails.  As
+       matching proceeds deeper and deeper into the tree of possibilities, the
+       recursion depth increases. The match() function is also called in other
+       circumstances,  for  example,  whenever  a parenthesized sub-pattern is
+       entered, and in certain cases of repetition.
+
+       Not all calls of match() increase the recursion depth; for an item such
+       as  a* it may be called several times at the same level, after matching
+       different numbers of a's. Furthermore, in a number of cases  where  the
+       result  of  the  recursive call would immediately be passed back as the
+       result of the current call (a "tail recursion"), the function  is  just
+       restarted instead.
+
+       The  above  comments  apply  when  pcre[16]_exec() is run in its normal
+       interpretive  manner.   If   the   pattern   was   studied   with   the
+       PCRE_STUDY_JIT_COMPILE  option, and just-in-time compiling was success-
+       ful, and the options passed to pcre[16]_exec() were  not  incompatible,
+       the  matching process uses the JIT-compiled code instead of the match()
+       function. In this case, the memory requirements  are  handled  entirely
+       differently. See the pcrejit documentation for details.
+
+       The pcre[16]_dfa_exec() function operates in an entirely different way,
+       and uses recursion only when there is a regular expression recursion or
+       subroutine  call in the pattern. This includes the processing of asser-
+       tion and "once-only" subpatterns, which  are  handled  like  subroutine
+       calls.  Normally,  these are never very deep, and the limit on the com-
+       plexity of pcre[16]_dfa_exec() is controlled by the amount of workspace
+       it  is  given.   However, it is possible to write patterns with runaway
+       infinite recursions; such patterns will  cause  pcre[16]_dfa_exec()  to
+       run out of stack. At present, there is no protection against this.
+
+       The  comments that follow do NOT apply to pcre[16]_dfa_exec(); they are
+       relevant only for pcre[16]_exec() without the JIT optimization.
+
+   Reducing pcre[16]_exec()'s stack usage
+
+       Each time that match() is actually called recursively, it  uses  memory
+       from  the  process  stack.  For certain kinds of pattern and data, very
+       large amounts of stack may be needed, despite the recognition of  "tail
+       recursion".   You  can often reduce the amount of recursion, and there-
+       fore the amount of stack used, by modifying the pattern that  is  being
+       matched. Consider, for example, this pattern:
+
+         ([^<]|<(?!inet))+
+
+       It  matches  from wherever it starts until it encounters "<inet" or the
+       end of the data, and is the kind of pattern that  might  be  used  when
+       processing an XML file. Each iteration of the outer parentheses matches
+       either one character that is not "<" or a "<" that is not  followed  by
+       "inet".  However,  each  time  a  parenthesis is processed, a recursion
+       occurs, so this formulation uses a stack frame for each matched charac-
+       ter.  For  a long string, a lot of stack is required. Consider now this
+       rewritten pattern, which matches exactly the same strings:
+
+         ([^<]++|<(?!inet))+
+
+       This uses very much less stack, because runs of characters that do  not
+       contain  "<" are "swallowed" in one item inside the parentheses. Recur-
+       sion happens only when a "<" character that is not followed  by  "inet"
+       is  encountered  (and  we assume this is relatively rare). A possessive
+       quantifier is used to stop any backtracking into the  runs  of  non-"<"
+       characters, but that is not related to stack usage.
+
+       This  example shows that one way of avoiding stack problems when match-
+       ing long subject strings is to write repeated parenthesized subpatterns
+       to match more than one character whenever possible.
+
+   Compiling PCRE to use heap instead of stack for pcre[16]_exec()
+
+       In  environments  where  stack memory is constrained, you might want to
+       compile PCRE to use heap memory instead of stack for remembering  back-
+       up points when pcre[16]_exec() is running. This makes it run a lot more
+       slowly, however.  Details of how to do this are given in the  pcrebuild
+       documentation. When built in this way, instead of using the stack, PCRE
+       obtains and frees memory by calling the functions that are  pointed  to
+       by  the  pcre[16]_stack_malloc  and  pcre[16]_stack_free  variables. By
+       default, these point to malloc() and free(), but you  can  replace  the
+       pointers to cause PCRE to use your own functions. Since the block sizes
+       are always the same, and are always freed in reverse order, it  may  be
+       possible  to  implement  customized memory handlers that are more effi-
+       cient than the standard functions.
+
+   Limiting pcre[16]_exec()'s stack usage
+
+       You can set limits on the number of times that match() is called,  both
+       in  total  and  recursively.  If  a  limit is exceeded, pcre[16]_exec()
+       returns an error code. Setting suitable limits should prevent  it  from
+       running  out of stack. The default values of the limits are very large,
+       and unlikely ever to operate. They can be changed when PCRE  is  built,
+       and they can also be set when pcre[16]_exec() is called. For details of
+       these interfaces, see the pcrebuild documentation and  the  section  on
+       extra data for pcre[16]_exec() in the pcreapi documentation.
+
+       As a very rough rule of thumb, you should reckon on about 500 bytes per
+       recursion. Thus, if you want to limit your  stack  usage  to  8Mb,  you
+       should  set  the  limit at 16000 recursions. A 64Mb stack, on the other
+       hand, can support around 128000 recursions.
+
+       In Unix-like environments, the pcretest test program has a command line
+       option (-S) that can be used to increase the size of its stack. As long
+       as the stack is large enough, another option (-M) can be used  to  find
+       the  smallest  limits  that allow a particular pattern to match a given
+       subject string. This is done by calling pcre[16]_exec() repeatedly with
+       different limits.
+
+   Obtaining an estimate of stack usage
+
+       The  actual  amount  of  stack used per recursion can vary quite a lot,
+       depending on the compiler that was used to build PCRE and the optimiza-
+       tion or debugging options that were set for it. The rule of thumb value
+       of 500 bytes mentioned above may be larger  or  smaller  than  what  is
+       actually needed. A better approximation can be obtained by running this
+       command:
+
+         pcretest -m -C
+
+       The -C option causes pcretest to output information about  the  options
+       with which PCRE was compiled. When -m is also given (before -C), infor-
+       mation about stack use is given in a line like this:
+
+         Match recursion uses stack: approximate frame size = 640 bytes
+
+       The value is approximate because some recursions need a bit more (up to
+       perhaps 16 more bytes).
+
+       If  the  above  command  is given when PCRE is compiled to use the heap
+       instead of the stack for recursion, the value that  is  output  is  the
+       size of each block that is obtained from the heap.
+
+   Changing stack size in Unix-like systems
+
+       In  Unix-like environments, there is not often a problem with the stack
+       unless very long strings are involved,  though  the  default  limit  on
+       stack  size  varies  from system to system. Values from 8Mb to 64Mb are
+       common. You can find your default limit by running the command:
+
+         ulimit -s
+
+       Unfortunately, the effect of running out of  stack  is  often  SIGSEGV,
+       though  sometimes  a more explicit error message is given. You can nor-
+       mally increase the limit on stack size by code such as this:
+
+         struct rlimit rlim;
+         getrlimit(RLIMIT_STACK, &rlim);
+         rlim.rlim_cur = 100*1024*1024;
+         setrlimit(RLIMIT_STACK, &rlim);
+
+       This reads the current limits (soft and hard) using  getrlimit(),  then
+       attempts  to  increase  the  soft limit to 100Mb using setrlimit(). You
+       must do this before calling pcre[16]_exec().
+
+   Changing stack size in Mac OS X
+
+       Using setrlimit(), as described above, should also work on Mac OS X. It
+       is also possible to set a stack size when linking a program. There is a
+       discussion  about  stack  sizes  in  Mac  OS  X  at  this   web   site:
+       http://developer.apple.com/qa/qa2005/qa1419.html.
+
+
+AUTHOR
+
+       Philip Hazel
+       University Computing Service
+       Cambridge CB2 3QH, England.
+
+
+REVISION
+
+       Last updated: 21 January 2012
+       Copyright (c) 1997-2012 University of Cambridge.
+------------------------------------------------------------------------------
+
+
diff --git a/ext/pcre/pcrelib/pcre.h b/ext/pcre/pcrelib/pcre.h
new file mode 100644
index 0000000..b71ead3
--- /dev/null
+++ b/ext/pcre/pcrelib/pcre.h
@@ -0,0 +1,507 @@
+/*************************************************
+*       Perl-Compatible Regular Expressions      *
+*************************************************/
+
+/* This is the public header file for the PCRE library, to be #included by
+applications that call the PCRE functions.
+
+           Copyright (c) 1997-2012 University of Cambridge
+
+-----------------------------------------------------------------------------
+Redistribution and use in source and binary forms, with or without
+modification, are permitted provided that the following conditions are met:
+
+    * Redistributions of source code must retain the above copyright notice,
+      this list of conditions and the following disclaimer.
+
+    * Redistributions in binary form must reproduce the above copyright
+      notice, this list of conditions and the following disclaimer in the
+      documentation and/or other materials provided with the distribution.
+
+    * Neither the name of the University of Cambridge nor the names of its
+      contributors may be used to endorse or promote products derived from
+      this software without specific prior written permission.
+
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+POSSIBILITY OF SUCH DAMAGE.
+-----------------------------------------------------------------------------
+*/
+
+#ifndef _PCRE_H
+#define _PCRE_H
+
+/* The current PCRE version information. */
+
+#define PCRE_MAJOR          8
+#define PCRE_MINOR          31
+#define PCRE_PRERELEASE     
+#define PCRE_DATE           2012-07-06
+
+/* When an application links to a PCRE DLL in Windows, the symbols that are
+imported have to be identified as such. When building PCRE, the appropriate
+export setting is defined in pcre_internal.h, which includes this file. So we
+don't change existing definitions of PCRE_EXP_DECL and PCRECPP_EXP_DECL. */
+
+#if defined(_WIN32) && !defined(PCRE_STATIC)
+#  ifndef PCRE_EXP_DECL
+#    define PCRE_EXP_DECL  extern __declspec(dllimport)
+#  endif
+#  ifdef __cplusplus
+#    ifndef PCRECPP_EXP_DECL
+#      define PCRECPP_EXP_DECL  extern __declspec(dllimport)
+#    endif
+#    ifndef PCRECPP_EXP_DEFN
+#      define PCRECPP_EXP_DEFN  __declspec(dllimport)
+#    endif
+#  endif
+#endif
+
+/* By default, we use the standard "extern" declarations. */
+
+#ifndef PCRE_EXP_DECL
+#  ifdef __cplusplus
+#    define PCRE_EXP_DECL  extern "C"
+#  else
+#    define PCRE_EXP_DECL  extern
+#  endif
+#endif
+
+#ifdef __cplusplus
+#  ifndef PCRECPP_EXP_DECL
+#    define PCRECPP_EXP_DECL  extern
+#  endif
+#  ifndef PCRECPP_EXP_DEFN
+#    define PCRECPP_EXP_DEFN
+#  endif
+#endif
+
+/* Have to include stdlib.h in order to ensure that size_t is defined;
+it is needed here for malloc. */
+
+#include <stdlib.h>
+
+/* Allow for C++ users */
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+/* Options. Some are compile-time only, some are run-time only, and some are
+both, so we keep them all distinct. However, almost all the bits in the options
+word are now used. In the long run, we may have to re-use some of the
+compile-time only bits for runtime options, or vice versa. In the comments
+below, "compile", "exec", and "DFA exec" mean that the option is permitted to
+be set for those functions; "used in" means that an option may be set only for
+compile, but is subsequently referenced in exec and/or DFA exec. Any of the
+compile-time options may be inspected during studying (and therefore JIT
+compiling). */
+
+#define PCRE_CASELESS           0x00000001  /* Compile */
+#define PCRE_MULTILINE          0x00000002  /* Compile */
+#define PCRE_DOTALL             0x00000004  /* Compile */
+#define PCRE_EXTENDED           0x00000008  /* Compile */
+#define PCRE_ANCHORED           0x00000010  /* Compile, exec, DFA exec */
+#define PCRE_DOLLAR_ENDONLY     0x00000020  /* Compile, used in exec, DFA exec */
+#define PCRE_EXTRA              0x00000040  /* Compile */
+#define PCRE_NOTBOL             0x00000080  /* Exec, DFA exec */
+#define PCRE_NOTEOL             0x00000100  /* Exec, DFA exec */
+#define PCRE_UNGREEDY           0x00000200  /* Compile */
+#define PCRE_NOTEMPTY           0x00000400  /* Exec, DFA exec */
+/* The next two are also used in exec and DFA exec */
+#define PCRE_UTF8               0x00000800  /* Compile (same as PCRE_UTF16) */
+#define PCRE_UTF16              0x00000800  /* Compile (same as PCRE_UTF8) */
+#define PCRE_NO_AUTO_CAPTURE    0x00001000  /* Compile */
+/* The next two are also used in exec and DFA exec */
+#define PCRE_NO_UTF8_CHECK      0x00002000  /* Compile (same as PCRE_NO_UTF16_CHECK) */
+#define PCRE_NO_UTF16_CHECK     0x00002000  /* Compile (same as PCRE_NO_UTF8_CHECK) */
+#define PCRE_AUTO_CALLOUT       0x00004000  /* Compile */
+#define PCRE_PARTIAL_SOFT       0x00008000  /* Exec, DFA exec */
+#define PCRE_PARTIAL            0x00008000  /* Backwards compatible synonym */
+#define PCRE_DFA_SHORTEST       0x00010000  /* DFA exec */
+#define PCRE_DFA_RESTART        0x00020000  /* DFA exec */
+#define PCRE_FIRSTLINE          0x00040000  /* Compile, used in exec, DFA exec */
+#define PCRE_DUPNAMES           0x00080000  /* Compile */
+#define PCRE_NEWLINE_CR         0x00100000  /* Compile, exec, DFA exec */
+#define PCRE_NEWLINE_LF         0x00200000  /* Compile, exec, DFA exec */
+#define PCRE_NEWLINE_CRLF       0x00300000  /* Compile, exec, DFA exec */
+#define PCRE_NEWLINE_ANY        0x00400000  /* Compile, exec, DFA exec */
+#define PCRE_NEWLINE_ANYCRLF    0x00500000  /* Compile, exec, DFA exec */
+#define PCRE_BSR_ANYCRLF        0x00800000  /* Compile, exec, DFA exec */
+#define PCRE_BSR_UNICODE        0x01000000  /* Compile, exec, DFA exec */
+#define PCRE_JAVASCRIPT_COMPAT  0x02000000  /* Compile, used in exec */
+#define PCRE_NO_START_OPTIMIZE  0x04000000  /* Compile, exec, DFA exec */
+#define PCRE_NO_START_OPTIMISE  0x04000000  /* Synonym */
+#define PCRE_PARTIAL_HARD       0x08000000  /* Exec, DFA exec */
+#define PCRE_NOTEMPTY_ATSTART   0x10000000  /* Exec, DFA exec */
+#define PCRE_UCP                0x20000000  /* Compile, used in exec, DFA exec */
+
+/* Exec-time and get/set-time error codes */
+
+#define PCRE_ERROR_NOMATCH          (-1)
+#define PCRE_ERROR_NULL             (-2)
+#define PCRE_ERROR_BADOPTION        (-3)
+#define PCRE_ERROR_BADMAGIC         (-4)
+#define PCRE_ERROR_UNKNOWN_OPCODE   (-5)
+#define PCRE_ERROR_UNKNOWN_NODE     (-5)  /* For backward compatibility */
+#define PCRE_ERROR_NOMEMORY         (-6)
+#define PCRE_ERROR_NOSUBSTRING      (-7)
+#define PCRE_ERROR_MATCHLIMIT       (-8)
+#define PCRE_ERROR_CALLOUT          (-9)  /* Never used by PCRE itself */
+#define PCRE_ERROR_BADUTF8         (-10)  /* Same for 8/16 */
+#define PCRE_ERROR_BADUTF16        (-10)  /* Same for 8/16 */
+#define PCRE_ERROR_BADUTF8_OFFSET  (-11)  /* Same for 8/16 */
+#define PCRE_ERROR_BADUTF16_OFFSET (-11)  /* Same for 8/16 */
+#define PCRE_ERROR_PARTIAL         (-12)
+#define PCRE_ERROR_BADPARTIAL      (-13)
+#define PCRE_ERROR_INTERNAL        (-14)
+#define PCRE_ERROR_BADCOUNT        (-15)
+#define PCRE_ERROR_DFA_UITEM       (-16)
+#define PCRE_ERROR_DFA_UCOND       (-17)
+#define PCRE_ERROR_DFA_UMLIMIT     (-18)
+#define PCRE_ERROR_DFA_WSSIZE      (-19)
+#define PCRE_ERROR_DFA_RECURSE     (-20)
+#define PCRE_ERROR_RECURSIONLIMIT  (-21)
+#define PCRE_ERROR_NULLWSLIMIT     (-22)  /* No longer actually used */
+#define PCRE_ERROR_BADNEWLINE      (-23)
+#define PCRE_ERROR_BADOFFSET       (-24)
+#define PCRE_ERROR_SHORTUTF8       (-25)
+#define PCRE_ERROR_SHORTUTF16      (-25)  /* Same for 8/16 */
+#define PCRE_ERROR_RECURSELOOP     (-26)
+#define PCRE_ERROR_JIT_STACKLIMIT  (-27)
+#define PCRE_ERROR_BADMODE         (-28)
+#define PCRE_ERROR_BADENDIANNESS   (-29)
+#define PCRE_ERROR_DFA_BADRESTART  (-30)
+
+/* Specific error codes for UTF-8 validity checks */
+
+#define PCRE_UTF8_ERR0               0
+#define PCRE_UTF8_ERR1               1
+#define PCRE_UTF8_ERR2               2
+#define PCRE_UTF8_ERR3               3
+#define PCRE_UTF8_ERR4               4
+#define PCRE_UTF8_ERR5               5
+#define PCRE_UTF8_ERR6               6
+#define PCRE_UTF8_ERR7               7
+#define PCRE_UTF8_ERR8               8
+#define PCRE_UTF8_ERR9               9
+#define PCRE_UTF8_ERR10             10
+#define PCRE_UTF8_ERR11             11
+#define PCRE_UTF8_ERR12             12
+#define PCRE_UTF8_ERR13             13
+#define PCRE_UTF8_ERR14             14
+#define PCRE_UTF8_ERR15             15
+#define PCRE_UTF8_ERR16             16
+#define PCRE_UTF8_ERR17             17
+#define PCRE_UTF8_ERR18             18
+#define PCRE_UTF8_ERR19             19
+#define PCRE_UTF8_ERR20             20
+#define PCRE_UTF8_ERR21             21
+
+/* Specific error codes for UTF-16 validity checks */
+
+#define PCRE_UTF16_ERR0              0
+#define PCRE_UTF16_ERR1              1
+#define PCRE_UTF16_ERR2              2
+#define PCRE_UTF16_ERR3              3
+#define PCRE_UTF16_ERR4              4
+
+/* Request types for pcre_fullinfo() */
+
+#define PCRE_INFO_OPTIONS            0
+#define PCRE_INFO_SIZE               1
+#define PCRE_INFO_CAPTURECOUNT       2
+#define PCRE_INFO_BACKREFMAX         3
+#define PCRE_INFO_FIRSTBYTE          4
+#define PCRE_INFO_FIRSTCHAR          4  /* For backwards compatibility */
+#define PCRE_INFO_FIRSTTABLE         5
+#define PCRE_INFO_LASTLITERAL        6
+#define PCRE_INFO_NAMEENTRYSIZE      7
+#define PCRE_INFO_NAMECOUNT          8
+#define PCRE_INFO_NAMETABLE          9
+#define PCRE_INFO_STUDYSIZE         10
+#define PCRE_INFO_DEFAULT_TABLES    11
+#define PCRE_INFO_OKPARTIAL         12
+#define PCRE_INFO_JCHANGED          13
+#define PCRE_INFO_HASCRORLF         14
+#define PCRE_INFO_MINLENGTH         15
+#define PCRE_INFO_JIT               16
+#define PCRE_INFO_JITSIZE           17
+#define PCRE_INFO_MAXLOOKBEHIND     18
+
+/* Request types for pcre_config(). Do not re-arrange, in order to remain
+compatible. */
+
+#define PCRE_CONFIG_UTF8                    0
+#define PCRE_CONFIG_NEWLINE                 1
+#define PCRE_CONFIG_LINK_SIZE               2
+#define PCRE_CONFIG_POSIX_MALLOC_THRESHOLD  3
+#define PCRE_CONFIG_MATCH_LIMIT             4
+#define PCRE_CONFIG_STACKRECURSE            5
+#define PCRE_CONFIG_UNICODE_PROPERTIES      6
+#define PCRE_CONFIG_MATCH_LIMIT_RECURSION   7
+#define PCRE_CONFIG_BSR                     8
+#define PCRE_CONFIG_JIT                     9
+#define PCRE_CONFIG_UTF16                  10
+#define PCRE_CONFIG_JITTARGET              11
+
+/* Request types for pcre_study(). Do not re-arrange, in order to remain
+compatible. */
+
+#define PCRE_STUDY_JIT_COMPILE                0x0001
+#define PCRE_STUDY_JIT_PARTIAL_SOFT_COMPILE   0x0002
+#define PCRE_STUDY_JIT_PARTIAL_HARD_COMPILE   0x0004
+
+/* Bit flags for the pcre[16]_extra structure. Do not re-arrange or redefine
+these bits, just add new ones on the end, in order to remain compatible. */
+
+#define PCRE_EXTRA_STUDY_DATA             0x0001
+#define PCRE_EXTRA_MATCH_LIMIT            0x0002
+#define PCRE_EXTRA_CALLOUT_DATA           0x0004
+#define PCRE_EXTRA_TABLES                 0x0008
+#define PCRE_EXTRA_MATCH_LIMIT_RECURSION  0x0010
+#define PCRE_EXTRA_MARK                   0x0020
+#define PCRE_EXTRA_EXECUTABLE_JIT         0x0040
+
+/* Types */
+
+struct real_pcre;                 /* declaration; the definition is private  */
+typedef struct real_pcre pcre;
+
+struct real_pcre16;               /* declaration; the definition is private  */
+typedef struct real_pcre16 pcre16;
+
+struct real_pcre_jit_stack;       /* declaration; the definition is private  */
+typedef struct real_pcre_jit_stack pcre_jit_stack;
+
+struct real_pcre16_jit_stack;     /* declaration; the definition is private  */
+typedef struct real_pcre16_jit_stack pcre16_jit_stack;
+
+/* If PCRE is compiled with 16 bit character support, PCRE_UCHAR16 must contain
+a 16 bit wide signed data type. Otherwise it can be a dummy data type since
+pcre16 functions are not implemented. There is a check for this in pcre_internal.h. */
+#ifndef PCRE_UCHAR16
+#define PCRE_UCHAR16 unsigned short
+#endif
+
+#ifndef PCRE_SPTR16
+#define PCRE_SPTR16 const PCRE_UCHAR16 *
+#endif
+
+/* When PCRE is compiled as a C++ library, the subject pointer type can be
+replaced with a custom type. For conventional use, the public interface is a
+const char *. */
+
+#ifndef PCRE_SPTR
+#define PCRE_SPTR const char *
+#endif
+
+/* The structure for passing additional data to pcre_exec(). This is defined in
+such as way as to be extensible. Always add new fields at the end, in order to
+remain compatible. */
+
+typedef struct pcre_extra {
+  unsigned long int flags;        /* Bits for which fields are set */
+  void *study_data;               /* Opaque data from pcre_study() */
+  unsigned long int match_limit;  /* Maximum number of calls to match() */
+  void *callout_data;             /* Data passed back in callouts */
+  const unsigned char *tables;    /* Pointer to character tables */
+  unsigned long int match_limit_recursion; /* Max recursive calls to match() */
+  unsigned char **mark;           /* For passing back a mark pointer */
+  void *executable_jit;           /* Contains a pointer to a compiled jit code */
+} pcre_extra;
+
+/* Same structure as above, but with 16 bit char pointers. */
+
+typedef struct pcre16_extra {
+  unsigned long int flags;        /* Bits for which fields are set */
+  void *study_data;               /* Opaque data from pcre_study() */
+  unsigned long int match_limit;  /* Maximum number of calls to match() */
+  void *callout_data;             /* Data passed back in callouts */
+  const unsigned char *tables;    /* Pointer to character tables */
+  unsigned long int match_limit_recursion; /* Max recursive calls to match() */
+  PCRE_UCHAR16 **mark;            /* For passing back a mark pointer */
+  void *executable_jit;           /* Contains a pointer to a compiled jit code */
+} pcre16_extra;
+
+/* The structure for passing out data via the pcre_callout_function. We use a
+structure so that new fields can be added on the end in future versions,
+without changing the API of the function, thereby allowing old clients to work
+without modification. */
+
+typedef struct pcre_callout_block {
+  int          version;           /* Identifies version of block */
+  /* ------------------------ Version 0 ------------------------------- */
+  int          callout_number;    /* Number compiled into pattern */
+  int         *offset_vector;     /* The offset vector */
+  PCRE_SPTR    subject;           /* The subject being matched */
+  int          subject_length;    /* The length of the subject */
+  int          start_match;       /* Offset to start of this match attempt */
+  int          current_position;  /* Where we currently are in the subject */
+  int          capture_top;       /* Max current capture */
+  int          capture_last;      /* Most recently closed capture */
+  void        *callout_data;      /* Data passed in with the call */
+  /* ------------------- Added for Version 1 -------------------------- */
+  int          pattern_position;  /* Offset to next item in the pattern */
+  int          next_item_length;  /* Length of next item in the pattern */
+  /* ------------------- Added for Version 2 -------------------------- */
+  const unsigned char *mark;      /* Pointer to current mark or NULL    */
+  /* ------------------------------------------------------------------ */
+} pcre_callout_block;
+
+/* Same structure as above, but with 16 bit char pointers. */
+
+typedef struct pcre16_callout_block {
+  int          version;           /* Identifies version of block */
+  /* ------------------------ Version 0 ------------------------------- */
+  int          callout_number;    /* Number compiled into pattern */
+  int         *offset_vector;     /* The offset vector */
+  PCRE_SPTR16  subject;           /* The subject being matched */
+  int          subject_length;    /* The length of the subject */
+  int          start_match;       /* Offset to start of this match attempt */
+  int          current_position;  /* Where we currently are in the subject */
+  int          capture_top;       /* Max current capture */
+  int          capture_last;      /* Most recently closed capture */
+  void        *callout_data;      /* Data passed in with the call */
+  /* ------------------- Added for Version 1 -------------------------- */
+  int          pattern_position;  /* Offset to next item in the pattern */
+  int          next_item_length;  /* Length of next item in the pattern */
+  /* ------------------- Added for Version 2 -------------------------- */
+  const PCRE_UCHAR16 *mark;       /* Pointer to current mark or NULL    */
+  /* ------------------------------------------------------------------ */
+} pcre16_callout_block;
+
+/* Indirection for store get and free functions. These can be set to
+alternative malloc/free functions if required. Special ones are used in the
+non-recursive case for "frames". There is also an optional callout function
+that is triggered by the (?) regex item. For Virtual Pascal, these definitions
+have to take another form. */
+
+#ifndef VPCOMPAT
+PCRE_EXP_DECL void *(*pcre_malloc)(size_t);
+PCRE_EXP_DECL void  (*pcre_free)(void *);
+PCRE_EXP_DECL void *(*pcre_stack_malloc)(size_t);
+PCRE_EXP_DECL void  (*pcre_stack_free)(void *);
+PCRE_EXP_DECL int   (*pcre_callout)(pcre_callout_block *);
+
+PCRE_EXP_DECL void *(*pcre16_malloc)(size_t);
+PCRE_EXP_DECL void  (*pcre16_free)(void *);
+PCRE_EXP_DECL void *(*pcre16_stack_malloc)(size_t);
+PCRE_EXP_DECL void  (*pcre16_stack_free)(void *);
+PCRE_EXP_DECL int   (*pcre16_callout)(pcre16_callout_block *);
+#else   /* VPCOMPAT */
+PCRE_EXP_DECL void *pcre_malloc(size_t);
+PCRE_EXP_DECL void  pcre_free(void *);
+PCRE_EXP_DECL void *pcre_stack_malloc(size_t);
+PCRE_EXP_DECL void  pcre_stack_free(void *);
+PCRE_EXP_DECL int   pcre_callout(pcre_callout_block *);
+
+PCRE_EXP_DECL void *pcre16_malloc(size_t);
+PCRE_EXP_DECL void  pcre16_free(void *);
+PCRE_EXP_DECL void *pcre16_stack_malloc(size_t);
+PCRE_EXP_DECL void  pcre16_stack_free(void *);
+PCRE_EXP_DECL int   pcre16_callout(pcre16_callout_block *);
+#endif  /* VPCOMPAT */
+
+/* User defined callback which provides a stack just before the match starts. */
+
+typedef pcre_jit_stack *(*pcre_jit_callback)(void *);
+typedef pcre16_jit_stack *(*pcre16_jit_callback)(void *);
+
+/* Exported PCRE functions */
+
+PCRE_EXP_DECL pcre *pcre_compile(const char *, int, const char **, int *,
+                  const unsigned char *);
+PCRE_EXP_DECL pcre16 *pcre16_compile(PCRE_SPTR16, int, const char **, int *,
+                  const unsigned char *);
+PCRE_EXP_DECL pcre *pcre_compile2(const char *, int, int *, const char **,
+                  int *, const unsigned char *);
+PCRE_EXP_DECL pcre16 *pcre16_compile2(PCRE_SPTR16, int, int *, const char **,
+                  int *, const unsigned char *);
+PCRE_EXP_DECL int  pcre_config(int, void *);
+PCRE_EXP_DECL int  pcre16_config(int, void *);
+PCRE_EXP_DECL int  pcre_copy_named_substring(const pcre *, const char *,
+                  int *, int, const char *, char *, int);
+PCRE_EXP_DECL int  pcre16_copy_named_substring(const pcre16 *, PCRE_SPTR16,
+                  int *, int, PCRE_SPTR16, PCRE_UCHAR16 *, int);
+PCRE_EXP_DECL int  pcre_copy_substring(const char *, int *, int, int,
+                  char *, int);
+PCRE_EXP_DECL int  pcre16_copy_substring(PCRE_SPTR16, int *, int, int,
+                  PCRE_UCHAR16 *, int);
+PCRE_EXP_DECL int  pcre_dfa_exec(const pcre *, const pcre_extra *,
+                  const char *, int, int, int, int *, int , int *, int);
+PCRE_EXP_DECL int  pcre16_dfa_exec(const pcre16 *, const pcre16_extra *,
+                  PCRE_SPTR16, int, int, int, int *, int , int *, int);
+PCRE_EXP_DECL int  pcre_exec(const pcre *, const pcre_extra *, PCRE_SPTR,
+                   int, int, int, int *, int);
+PCRE_EXP_DECL int  pcre16_exec(const pcre16 *, const pcre16_extra *,
+                   PCRE_SPTR16, int, int, int, int *, int);
+PCRE_EXP_DECL void pcre_free_substring(const char *);
+PCRE_EXP_DECL void pcre16_free_substring(PCRE_SPTR16);
+PCRE_EXP_DECL void pcre_free_substring_list(const char **);
+PCRE_EXP_DECL void pcre16_free_substring_list(PCRE_SPTR16 *);
+PCRE_EXP_DECL int  pcre_fullinfo(const pcre *, const pcre_extra *, int,
+                  void *);
+PCRE_EXP_DECL int  pcre16_fullinfo(const pcre16 *, const pcre16_extra *, int,
+                  void *);
+PCRE_EXP_DECL int  pcre_get_named_substring(const pcre *, const char *,
+                  int *, int, const char *, const char **);
+PCRE_EXP_DECL int  pcre16_get_named_substring(const pcre16 *, PCRE_SPTR16,
+                  int *, int, PCRE_SPTR16, PCRE_SPTR16 *);
+PCRE_EXP_DECL int  pcre_get_stringnumber(const pcre *, const char *);
+PCRE_EXP_DECL int  pcre16_get_stringnumber(const pcre16 *, PCRE_SPTR16);
+PCRE_EXP_DECL int  pcre_get_stringtable_entries(const pcre *, const char *,
+                  char **, char **);
+PCRE_EXP_DECL int  pcre16_get_stringtable_entries(const pcre16 *, PCRE_SPTR16,
+                  PCRE_UCHAR16 **, PCRE_UCHAR16 **);
+PCRE_EXP_DECL int  pcre_get_substring(const char *, int *, int, int,
+                  const char **);
+PCRE_EXP_DECL int  pcre16_get_substring(PCRE_SPTR16, int *, int, int,
+                  PCRE_SPTR16 *);
+PCRE_EXP_DECL int  pcre_get_substring_list(const char *, int *, int,
+                  const char ***);
+PCRE_EXP_DECL int  pcre16_get_substring_list(PCRE_SPTR16, int *, int,
+                  PCRE_SPTR16 **);
+PCRE_EXP_DECL const unsigned char *pcre_maketables(void);
+PCRE_EXP_DECL const unsigned char *pcre16_maketables(void);
+PCRE_EXP_DECL int  pcre_refcount(pcre *, int);
+PCRE_EXP_DECL int  pcre16_refcount(pcre16 *, int);
+PCRE_EXP_DECL pcre_extra *pcre_study(const pcre *, int, const char **);
+PCRE_EXP_DECL pcre16_extra *pcre16_study(const pcre16 *, int, const char **);
+PCRE_EXP_DECL void pcre_free_study(pcre_extra *);
+PCRE_EXP_DECL void pcre16_free_study(pcre16_extra *);
+PCRE_EXP_DECL const char *pcre_version(void);
+PCRE_EXP_DECL const char *pcre16_version(void);
+
+/* Utility functions for byte order swaps. */
+PCRE_EXP_DECL int  pcre_pattern_to_host_byte_order(pcre *, pcre_extra *,
+                  const unsigned char *);
+PCRE_EXP_DECL int  pcre16_pattern_to_host_byte_order(pcre16 *, pcre16_extra *,
+                  const unsigned char *);
+PCRE_EXP_DECL int  pcre16_utf16_to_host_byte_order(PCRE_UCHAR16 *,
+                  PCRE_SPTR16, int, int *, int);
+
+/* JIT compiler related functions. */
+
+PCRE_EXP_DECL pcre_jit_stack *pcre_jit_stack_alloc(int, int);
+PCRE_EXP_DECL pcre16_jit_stack *pcre16_jit_stack_alloc(int, int);
+PCRE_EXP_DECL void pcre_jit_stack_free(pcre_jit_stack *);
+PCRE_EXP_DECL void pcre16_jit_stack_free(pcre16_jit_stack *);
+PCRE_EXP_DECL void pcre_assign_jit_stack(pcre_extra *,
+                  pcre_jit_callback, void *);
+PCRE_EXP_DECL void pcre16_assign_jit_stack(pcre16_extra *,
+                  pcre16_jit_callback, void *);
+
+#ifdef __cplusplus
+}  /* extern "C" */
+#endif
+
+#endif /* End of pcre.h */
diff --git a/ext/pcre/pcrelib/pcre_chartables.c b/ext/pcre/pcrelib/pcre_chartables.c
new file mode 100644
index 0000000..980c23f
--- /dev/null
+++ b/ext/pcre/pcrelib/pcre_chartables.c
@@ -0,0 +1,196 @@
+/*************************************************
+*      Perl-Compatible Regular Expressions       *
+*************************************************/
+
+/* This file contains character tables that are used when no external tables
+are passed to PCRE by the application that calls it. The tables are used only
+for characters whose code values are less than 256.
+
+This is a default version of the tables that assumes ASCII encoding. A program
+called dftables (which is distributed with PCRE) can be used to build
+alternative versions of this file. This is necessary if you are running in an
+EBCDIC environment, or if you want to default to a different encoding, for
+example ISO-8859-1. When dftables is run, it creates these tables in the
+current locale. If PCRE is configured with --enable-rebuild-chartables, this
+happens automatically.
+
+The following #includes are present because without them gcc 4.x may remove the
+array definition from the final binary if PCRE is built into a static library
+and dead code stripping is activated. This leads to link errors. Pulling in the
+header ensures that the array gets flagged as "someone outside this compilation
+unit might reference this" and so it will always be supplied to the linker. */
+
+#include "config.h"
+
+#include "pcre_internal.h"
+
+const unsigned char _pcre_default_tables[] = {
+
+/* This table is a lower casing table. */
+
+    0,  1,  2,  3,  4,  5,  6,  7,
+    8,  9, 10, 11, 12, 13, 14, 15,
+   16, 17, 18, 19, 20, 21, 22, 23,
+   24, 25, 26, 27, 28, 29, 30, 31,
+   32, 33, 34, 35, 36, 37, 38, 39,
+   40, 41, 42, 43, 44, 45, 46, 47,
+   48, 49, 50, 51, 52, 53, 54, 55,
+   56, 57, 58, 59, 60, 61, 62, 63,
+   64, 97, 98, 99,100,101,102,103,
+  104,105,106,107,108,109,110,111,
+  112,113,114,115,116,117,118,119,
+  120,121,122, 91, 92, 93, 94, 95,
+   96, 97, 98, 99,100,101,102,103,
+  104,105,106,107,108,109,110,111,
+  112,113,114,115,116,117,118,119,
+  120,121,122,123,124,125,126,127,
+  128,129,130,131,132,133,134,135,
+  136,137,138,139,140,141,142,143,
+  144,145,146,147,148,149,150,151,
+  152,153,154,155,156,157,158,159,
+  160,161,162,163,164,165,166,167,
+  168,169,170,171,172,173,174,175,
+  176,177,178,179,180,181,182,183,
+  184,185,186,187,188,189,190,191,
+  192,193,194,195,196,197,198,199,
+  200,201,202,203,204,205,206,207,
+  208,209,210,211,212,213,214,215,
+  216,217,218,219,220,221,222,223,
+  224,225,226,227,228,229,230,231,
+  232,233,234,235,236,237,238,239,
+  240,241,242,243,244,245,246,247,
+  248,249,250,251,252,253,254,255,
+
+/* This table is a case flipping table. */
+
+    0,  1,  2,  3,  4,  5,  6,  7,
+    8,  9, 10, 11, 12, 13, 14, 15,
+   16, 17, 18, 19, 20, 21, 22, 23,
+   24, 25, 26, 27, 28, 29, 30, 31,
+   32, 33, 34, 35, 36, 37, 38, 39,
+   40, 41, 42, 43, 44, 45, 46, 47,
+   48, 49, 50, 51, 52, 53, 54, 55,
+   56, 57, 58, 59, 60, 61, 62, 63,
+   64, 97, 98, 99,100,101,102,103,
+  104,105,106,107,108,109,110,111,
+  112,113,114,115,116,117,118,119,
+  120,121,122, 91, 92, 93, 94, 95,
+   96, 65, 66, 67, 68, 69, 70, 71,
+   72, 73, 74, 75, 76, 77, 78, 79,
+   80, 81, 82, 83, 84, 85, 86, 87,
+   88, 89, 90,123,124,125,126,127,
+  128,129,130,131,132,133,134,135,
+  136,137,138,139,140,141,142,143,
+  144,145,146,147,148,149,150,151,
+  152,153,154,155,156,157,158,159,
+  160,161,162,163,164,165,166,167,
+  168,169,170,171,172,173,174,175,
+  176,177,178,179,180,181,182,183,
+  184,185,186,187,188,189,190,191,
+  192,193,194,195,196,197,198,199,
+  200,201,202,203,204,205,206,207,
+  208,209,210,211,212,213,214,215,
+  216,217,218,219,220,221,222,223,
+  224,225,226,227,228,229,230,231,
+  232,233,234,235,236,237,238,239,
+  240,241,242,243,244,245,246,247,
+  248,249,250,251,252,253,254,255,
+
+/* This table contains bit maps for various character classes. Each map is 32
+bytes long and the bits run from the least significant end of each byte. The
+classes that have their own maps are: space, xdigit, digit, upper, lower, word,
+graph, print, punct, and cntrl. Other classes are built from combinations. */
+
+  0x00,0x3e,0x00,0x00,0x01,0x00,0x00,0x00,
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
+
+  0x00,0x00,0x00,0x00,0x00,0x00,0xff,0x03,
+  0x7e,0x00,0x00,0x00,0x7e,0x00,0x00,0x00,
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
+
+  0x00,0x00,0x00,0x00,0x00,0x00,0xff,0x03,
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
+
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
+  0xfe,0xff,0xff,0x07,0x00,0x00,0x00,0x00,
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
+
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
+  0x00,0x00,0x00,0x00,0xfe,0xff,0xff,0x07,
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
+
+  0x00,0x00,0x00,0x00,0x00,0x00,0xff,0x03,
+  0xfe,0xff,0xff,0x87,0xfe,0xff,0xff,0x07,
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
+
+  0x00,0x00,0x00,0x00,0xfe,0xff,0xff,0xff,
+  0xff,0xff,0xff,0xff,0xff,0xff,0xff,0x7f,
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
+
+  0x00,0x00,0x00,0x00,0xff,0xff,0xff,0xff,
+  0xff,0xff,0xff,0xff,0xff,0xff,0xff,0x7f,
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
+
+  0x00,0x00,0x00,0x00,0xfe,0xff,0x00,0xfc,
+  0x01,0x00,0x00,0xf8,0x01,0x00,0x00,0x78,
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
+
+  0xff,0xff,0xff,0xff,0x00,0x00,0x00,0x00,
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x80,
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
+
+/* This table identifies various classes of character by individual bits:
+  0x01   white space character
+  0x02   letter
+  0x04   decimal digit
+  0x08   hexadecimal digit
+  0x10   alphanumeric or '_'
+  0x80   regular expression metacharacter or binary zero
+*/
+
+  0x80,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /*   0-  7 */
+  0x00,0x01,0x01,0x00,0x01,0x01,0x00,0x00, /*   8- 15 */
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /*  16- 23 */
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /*  24- 31 */
+  0x01,0x00,0x00,0x00,0x80,0x00,0x00,0x00, /*    - '  */
+  0x80,0x80,0x80,0x80,0x00,0x00,0x80,0x00, /*  ( - /  */
+  0x1c,0x1c,0x1c,0x1c,0x1c,0x1c,0x1c,0x1c, /*  0 - 7  */
+  0x1c,0x1c,0x00,0x00,0x00,0x00,0x00,0x80, /*  8 - ?  */
+  0x00,0x1a,0x1a,0x1a,0x1a,0x1a,0x1a,0x12, /*  @ - G  */
+  0x12,0x12,0x12,0x12,0x12,0x12,0x12,0x12, /*  H - O  */
+  0x12,0x12,0x12,0x12,0x12,0x12,0x12,0x12, /*  P - W  */
+  0x12,0x12,0x12,0x80,0x80,0x00,0x80,0x10, /*  X - _  */
+  0x00,0x1a,0x1a,0x1a,0x1a,0x1a,0x1a,0x12, /*  ` - g  */
+  0x12,0x12,0x12,0x12,0x12,0x12,0x12,0x12, /*  h - o  */
+  0x12,0x12,0x12,0x12,0x12,0x12,0x12,0x12, /*  p - w  */
+  0x12,0x12,0x12,0x80,0x80,0x00,0x00,0x00, /*  x -127 */
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 128-135 */
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 136-143 */
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 144-151 */
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 152-159 */
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 160-167 */
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 168-175 */
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 176-183 */
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 184-191 */
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 192-199 */
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 200-207 */
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 208-215 */
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 216-223 */
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 224-231 */
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 232-239 */
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 240-247 */
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00};/* 248-255 */
+
+/* End of pcre_chartables.c */
diff --git a/ext/pcre/pcrelib/pcre_compile.c b/ext/pcre/pcrelib/pcre_compile.c
new file mode 100644
index 0000000..999ff80
--- /dev/null
+++ b/ext/pcre/pcrelib/pcre_compile.c
@@ -0,0 +1,8207 @@
+/*************************************************
+*      Perl-Compatible Regular Expressions       *
+*************************************************/
+
+/* PCRE is a library of functions to support regular expressions whose syntax
+and semantics are as close as possible to those of the Perl 5 language.
+
+                       Written by Philip Hazel
+           Copyright (c) 1997-2012 University of Cambridge
+
+-----------------------------------------------------------------------------
+Redistribution and use in source and binary forms, with or without
+modification, are permitted provided that the following conditions are met:
+
+    * Redistributions of source code must retain the above copyright notice,
+      this list of conditions and the following disclaimer.
+
+    * Redistributions in binary form must reproduce the above copyright
+      notice, this list of conditions and the following disclaimer in the
+      documentation and/or other materials provided with the distribution.
+
+    * Neither the name of the University of Cambridge nor the names of its
+      contributors may be used to endorse or promote products derived from
+      this software without specific prior written permission.
+
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+POSSIBILITY OF SUCH DAMAGE.
+-----------------------------------------------------------------------------
+*/
+
+
+/* This module contains the external function pcre_compile(), along with
+supporting internal functions that are not used by other modules. */
+
+
+#include "config.h"
+
+#define NLBLOCK cd             /* Block containing newline information */
+#define PSSTART start_pattern  /* Field containing processed string start */
+#define PSEND   end_pattern    /* Field containing processed string end */
+
+#include "pcre_internal.h"
+
+
+/* When PCRE_DEBUG is defined, we need the pcre(16)_printint() function, which
+is also used by pcretest. PCRE_DEBUG is not defined when building a production
+library. We do not need to select pcre16_printint.c specially, because the
+COMPILE_PCREx macro will already be appropriately set. */
+
+#ifdef PCRE_DEBUG
+/* pcre_printint.c should not include any headers */
+#define PCRE_INCLUDED
+#include "pcre_printint.c"
+#undef PCRE_INCLUDED
+#endif
+
+
+/* Macro for setting individual bits in class bitmaps. */
+
+#define SETBIT(a,b) a[b/8] |= (1 << (b%8))
+
+/* Maximum length value to check against when making sure that the integer that
+holds the compiled pattern length does not overflow. We make it a bit less than
+INT_MAX to allow for adding in group terminating bytes, so that we don't have
+to check them every time. */
+
+#define OFLOW_MAX (INT_MAX - 20)
+
+
+/*************************************************
+*      Code parameters and static tables         *
+*************************************************/
+
+/* This value specifies the size of stack workspace that is used during the
+first pre-compile phase that determines how much memory is required. The regex
+is partly compiled into this space, but the compiled parts are discarded as
+soon as they can be, so that hopefully there will never be an overrun. The code
+does, however, check for an overrun. The largest amount I've seen used is 218,
+so this number is very generous.
+
+The same workspace is used during the second, actual compile phase for
+remembering forward references to groups so that they can be filled in at the
+end. Each entry in this list occupies LINK_SIZE bytes, so even when LINK_SIZE
+is 4 there is plenty of room for most patterns. However, the memory can get
+filled up by repetitions of forward references, for example patterns like
+/(?1){0,1999}(b)/, and one user did hit the limit. The code has been changed so
+that the workspace is expanded using malloc() in this situation. The value
+below is therefore a minimum, and we put a maximum on it for safety. The
+minimum is now also defined in terms of LINK_SIZE so that the use of malloc()
+kicks in at the same number of forward references in all cases. */
+
+#define COMPILE_WORK_SIZE (2048*LINK_SIZE)
+#define COMPILE_WORK_SIZE_MAX (100*COMPILE_WORK_SIZE)
+
+/* The overrun tests check for a slightly smaller size so that they detect the
+overrun before it actually does run off the end of the data block. */
+
+#define WORK_SIZE_SAFETY_MARGIN (100)
+
+/* Private flags added to firstchar and reqchar. */
+
+#define REQ_CASELESS   0x10000000l      /* Indicates caselessness */
+#define REQ_VARY       0x20000000l      /* Reqchar followed non-literal item */
+
+/* Repeated character flags. */
+
+#define UTF_LENGTH     0x10000000l      /* The char contains its length. */
+
+/* Table for handling escaped characters in the range '0'-'z'. Positive returns
+are simple data values; negative values are for special things like \d and so
+on. Zero means further processing is needed (for things like \x), or the escape
+is invalid. */
+
+#ifndef EBCDIC
+
+/* This is the "normal" table for ASCII systems or for EBCDIC systems running
+in UTF-8 mode. */
+
+static const short int escapes[] = {
+     0,                       0,
+     0,                       0,
+     0,                       0,
+     0,                       0,
+     0,                       0,
+     CHAR_COLON,              CHAR_SEMICOLON,
+     CHAR_LESS_THAN_SIGN,     CHAR_EQUALS_SIGN,
+     CHAR_GREATER_THAN_SIGN,  CHAR_QUESTION_MARK,
+     CHAR_COMMERCIAL_AT,      -ESC_A,
+     -ESC_B,                  -ESC_C,
+     -ESC_D,                  -ESC_E,
+     0,                       -ESC_G,
+     -ESC_H,                  0,
+     0,                       -ESC_K,
+     0,                       0,
+     -ESC_N,                  0,
+     -ESC_P,                  -ESC_Q,
+     -ESC_R,                  -ESC_S,
+     0,                       0,
+     -ESC_V,                  -ESC_W,
+     -ESC_X,                  0,
+     -ESC_Z,                  CHAR_LEFT_SQUARE_BRACKET,
+     CHAR_BACKSLASH,          CHAR_RIGHT_SQUARE_BRACKET,
+     CHAR_CIRCUMFLEX_ACCENT,  CHAR_UNDERSCORE,
+     CHAR_GRAVE_ACCENT,       7,
+     -ESC_b,                  0,
+     -ESC_d,                  ESC_e,
+     ESC_f,                   0,
+     -ESC_h,                  0,
+     0,                       -ESC_k,
+     0,                       0,
+     ESC_n,                   0,
+     -ESC_p,                  0,
+     ESC_r,                   -ESC_s,
+     ESC_tee,                 0,
+     -ESC_v,                  -ESC_w,
+     0,                       0,
+     -ESC_z
+};
+
+#else
+
+/* This is the "abnormal" table for EBCDIC systems without UTF-8 support. */
+
+static const short int escapes[] = {
+/*  48 */     0,     0,      0,     '.',    '<',   '(',    '+',    '|',
+/*  50 */   '&',     0,      0,       0,      0,     0,      0,      0,
+/*  58 */     0,     0,    '!',     '$',    '*',   ')',    ';',    '~',
+/*  60 */   '-',   '/',      0,       0,      0,     0,      0,      0,
+/*  68 */     0,     0,    '|',     ',',    '%',   '_',    '>',    '?',
+/*  70 */     0,     0,      0,       0,      0,     0,      0,      0,
+/*  78 */     0,   '`',    ':',     '#',    '@',  '\'',    '=',    '"',
+/*  80 */     0,     7, -ESC_b,       0, -ESC_d, ESC_e,  ESC_f,      0,
+/*  88 */-ESC_h,     0,      0,     '{',      0,     0,      0,      0,
+/*  90 */     0,     0, -ESC_k,     'l',      0, ESC_n,      0, -ESC_p,
+/*  98 */     0, ESC_r,      0,     '}',      0,     0,      0,      0,
+/*  A0 */     0,   '~', -ESC_s, ESC_tee,      0,-ESC_v, -ESC_w,      0,
+/*  A8 */     0,-ESC_z,      0,       0,      0,   '[',      0,      0,
+/*  B0 */     0,     0,      0,       0,      0,     0,      0,      0,
+/*  B8 */     0,     0,      0,       0,      0,   ']',    '=',    '-',
+/*  C0 */   '{',-ESC_A, -ESC_B,  -ESC_C, -ESC_D,-ESC_E,      0, -ESC_G,
+/*  C8 */-ESC_H,     0,      0,       0,      0,     0,      0,      0,
+/*  D0 */   '}',     0, -ESC_K,       0,      0,-ESC_N,      0, -ESC_P,
+/*  D8 */-ESC_Q,-ESC_R,      0,       0,      0,     0,      0,      0,
+/*  E0 */  '\\',     0, -ESC_S,       0,      0,-ESC_V, -ESC_W, -ESC_X,
+/*  E8 */     0,-ESC_Z,      0,       0,      0,     0,      0,      0,
+/*  F0 */     0,     0,      0,       0,      0,     0,      0,      0,
+/*  F8 */     0,     0,      0,       0,      0,     0,      0,      0
+};
+#endif
+
+
+/* Table of special "verbs" like (*PRUNE). This is a short table, so it is
+searched linearly. Put all the names into a single string, in order to reduce
+the number of relocations when a shared library is dynamically linked. The
+string is built from string macros so that it works in UTF-8 mode on EBCDIC
+platforms. */
+
+typedef struct verbitem {
+  int   len;                 /* Length of verb name */
+  int   op;                  /* Op when no arg, or -1 if arg mandatory */
+  int   op_arg;              /* Op when arg present, or -1 if not allowed */
+} verbitem;
+
+static const char verbnames[] =
+  "\0"                       /* Empty name is a shorthand for MARK */
+  STRING_MARK0
+  STRING_ACCEPT0
+  STRING_COMMIT0
+  STRING_F0
+  STRING_FAIL0
+  STRING_PRUNE0
+  STRING_SKIP0
+  STRING_THEN;
+
+static const verbitem verbs[] = {
+  { 0, -1,        OP_MARK },
+  { 4, -1,        OP_MARK },
+  { 6, OP_ACCEPT, -1 },
+  { 6, OP_COMMIT, -1 },
+  { 1, OP_FAIL,   -1 },
+  { 4, OP_FAIL,   -1 },
+  { 5, OP_PRUNE,  OP_PRUNE_ARG },
+  { 4, OP_SKIP,   OP_SKIP_ARG  },
+  { 4, OP_THEN,   OP_THEN_ARG  }
+};
+
+static const int verbcount = sizeof(verbs)/sizeof(verbitem);
+
+
+/* Tables of names of POSIX character classes and their lengths. The names are
+now all in a single string, to reduce the number of relocations when a shared
+library is dynamically loaded. The list of lengths is terminated by a zero
+length entry. The first three must be alpha, lower, upper, as this is assumed
+for handling case independence. */
+
+static const char posix_names[] =
+  STRING_alpha0 STRING_lower0 STRING_upper0 STRING_alnum0
+  STRING_ascii0 STRING_blank0 STRING_cntrl0 STRING_digit0
+  STRING_graph0 STRING_print0 STRING_punct0 STRING_space0
+  STRING_word0  STRING_xdigit;
+
+static const pcre_uint8 posix_name_lengths[] = {
+  5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 4, 6, 0 };
+
+/* Table of class bit maps for each POSIX class. Each class is formed from a
+base map, with an optional addition or removal of another map. Then, for some
+classes, there is some additional tweaking: for [:blank:] the vertical space
+characters are removed, and for [:alpha:] and [:alnum:] the underscore
+character is removed. The triples in the table consist of the base map offset,
+second map offset or -1 if no second map, and a non-negative value for map
+addition or a negative value for map subtraction (if there are two maps). The
+absolute value of the third field has these meanings: 0 => no tweaking, 1 =>
+remove vertical space characters, 2 => remove underscore. */
+
+static const int posix_class_maps[] = {
+  cbit_word,  cbit_digit, -2,             /* alpha */
+  cbit_lower, -1,          0,             /* lower */
+  cbit_upper, -1,          0,             /* upper */
+  cbit_word,  -1,          2,             /* alnum - word without underscore */
+  cbit_print, cbit_cntrl,  0,             /* ascii */
+  cbit_space, -1,          1,             /* blank - a GNU extension */
+  cbit_cntrl, -1,          0,             /* cntrl */
+  cbit_digit, -1,          0,             /* digit */
+  cbit_graph, -1,          0,             /* graph */
+  cbit_print, -1,          0,             /* print */
+  cbit_punct, -1,          0,             /* punct */
+  cbit_space, -1,          0,             /* space */
+  cbit_word,  -1,          0,             /* word - a Perl extension */
+  cbit_xdigit,-1,          0              /* xdigit */
+};
+
+/* Table of substitutes for \d etc when PCRE_UCP is set. The POSIX class
+substitutes must be in the order of the names, defined above, and there are
+both positive and negative cases. NULL means no substitute. */
+
+#ifdef SUPPORT_UCP
+static const pcre_uchar string_PNd[]  = {
+  CHAR_BACKSLASH, CHAR_P, CHAR_LEFT_CURLY_BRACKET,
+  CHAR_N, CHAR_d, CHAR_RIGHT_CURLY_BRACKET, '\0' };
+static const pcre_uchar string_pNd[]  = {
+  CHAR_BACKSLASH, CHAR_p, CHAR_LEFT_CURLY_BRACKET,
+  CHAR_N, CHAR_d, CHAR_RIGHT_CURLY_BRACKET, '\0' };
+static const pcre_uchar string_PXsp[] = {
+  CHAR_BACKSLASH, CHAR_P, CHAR_LEFT_CURLY_BRACKET,
+  CHAR_X, CHAR_s, CHAR_p, CHAR_RIGHT_CURLY_BRACKET, '\0' };
+static const pcre_uchar string_pXsp[] = {
+  CHAR_BACKSLASH, CHAR_p, CHAR_LEFT_CURLY_BRACKET,
+  CHAR_X, CHAR_s, CHAR_p, CHAR_RIGHT_CURLY_BRACKET, '\0' };
+static const pcre_uchar string_PXwd[] = {
+  CHAR_BACKSLASH, CHAR_P, CHAR_LEFT_CURLY_BRACKET,
+  CHAR_X, CHAR_w, CHAR_d, CHAR_RIGHT_CURLY_BRACKET, '\0' };
+static const pcre_uchar string_pXwd[] = {
+  CHAR_BACKSLASH, CHAR_p, CHAR_LEFT_CURLY_BRACKET,
+  CHAR_X, CHAR_w, CHAR_d, CHAR_RIGHT_CURLY_BRACKET, '\0' };
+
+static const pcre_uchar *substitutes[] = {
+  string_PNd,           /* \D */
+  string_pNd,           /* \d */
+  string_PXsp,          /* \S */       /* NOTE: Xsp is Perl space */
+  string_pXsp,          /* \s */
+  string_PXwd,          /* \W */
+  string_pXwd           /* \w */
+};
+
+static const pcre_uchar string_pL[] =   {
+  CHAR_BACKSLASH, CHAR_p, CHAR_LEFT_CURLY_BRACKET,
+  CHAR_L, CHAR_RIGHT_CURLY_BRACKET, '\0' };
+static const pcre_uchar string_pLl[] =  {
+  CHAR_BACKSLASH, CHAR_p, CHAR_LEFT_CURLY_BRACKET,
+  CHAR_L, CHAR_l, CHAR_RIGHT_CURLY_BRACKET, '\0' };
+static const pcre_uchar string_pLu[] =  {
+  CHAR_BACKSLASH, CHAR_p, CHAR_LEFT_CURLY_BRACKET,
+  CHAR_L, CHAR_u, CHAR_RIGHT_CURLY_BRACKET, '\0' };
+static const pcre_uchar string_pXan[] = {
+  CHAR_BACKSLASH, CHAR_p, CHAR_LEFT_CURLY_BRACKET,
+  CHAR_X, CHAR_a, CHAR_n, CHAR_RIGHT_CURLY_BRACKET, '\0' };
+static const pcre_uchar string_h[] =    {
+  CHAR_BACKSLASH, CHAR_h, '\0' };
+static const pcre_uchar string_pXps[] = {
+  CHAR_BACKSLASH, CHAR_p, CHAR_LEFT_CURLY_BRACKET,
+  CHAR_X, CHAR_p, CHAR_s, CHAR_RIGHT_CURLY_BRACKET, '\0' };
+static const pcre_uchar string_PL[] =   {
+  CHAR_BACKSLASH, CHAR_P, CHAR_LEFT_CURLY_BRACKET,
+  CHAR_L, CHAR_RIGHT_CURLY_BRACKET, '\0' };
+static const pcre_uchar string_PLl[] =  {
+  CHAR_BACKSLASH, CHAR_P, CHAR_LEFT_CURLY_BRACKET,
+  CHAR_L, CHAR_l, CHAR_RIGHT_CURLY_BRACKET, '\0' };
+static const pcre_uchar string_PLu[] =  {
+  CHAR_BACKSLASH, CHAR_P, CHAR_LEFT_CURLY_BRACKET,
+  CHAR_L, CHAR_u, CHAR_RIGHT_CURLY_BRACKET, '\0' };
+static const pcre_uchar string_PXan[] = {
+  CHAR_BACKSLASH, CHAR_P, CHAR_LEFT_CURLY_BRACKET,
+  CHAR_X, CHAR_a, CHAR_n, CHAR_RIGHT_CURLY_BRACKET, '\0' };
+static const pcre_uchar string_H[] =    {
+  CHAR_BACKSLASH, CHAR_H, '\0' };
+static const pcre_uchar string_PXps[] = {
+  CHAR_BACKSLASH, CHAR_P, CHAR_LEFT_CURLY_BRACKET,
+  CHAR_X, CHAR_p, CHAR_s, CHAR_RIGHT_CURLY_BRACKET, '\0' };
+
+static const pcre_uchar *posix_substitutes[] = {
+  string_pL,            /* alpha */
+  string_pLl,           /* lower */
+  string_pLu,           /* upper */
+  string_pXan,          /* alnum */
+  NULL,                 /* ascii */
+  string_h,             /* blank */
+  NULL,                 /* cntrl */
+  string_pNd,           /* digit */
+  NULL,                 /* graph */
+  NULL,                 /* print */
+  NULL,                 /* punct */
+  string_pXps,          /* space */    /* NOTE: Xps is POSIX space */
+  string_pXwd,          /* word */
+  NULL,                 /* xdigit */
+  /* Negated cases */
+  string_PL,            /* ^alpha */
+  string_PLl,           /* ^lower */
+  string_PLu,           /* ^upper */
+  string_PXan,          /* ^alnum */
+  NULL,                 /* ^ascii */
+  string_H,             /* ^blank */
+  NULL,                 /* ^cntrl */
+  string_PNd,           /* ^digit */
+  NULL,                 /* ^graph */
+  NULL,                 /* ^print */
+  NULL,                 /* ^punct */
+  string_PXps,          /* ^space */   /* NOTE: Xps is POSIX space */
+  string_PXwd,          /* ^word */
+  NULL                  /* ^xdigit */
+};
+#define POSIX_SUBSIZE (sizeof(posix_substitutes) / sizeof(pcre_uchar *))
+#endif
+
+#define STRING(a)  # a
+#define XSTRING(s) STRING(s)
+
+/* The texts of compile-time error messages. These are "char *" because they
+are passed to the outside world. Do not ever re-use any error number, because
+they are documented. Always add a new error instead. Messages marked DEAD below
+are no longer used. This used to be a table of strings, but in order to reduce
+the number of relocations needed when a shared library is loaded dynamically,
+it is now one long string. We cannot use a table of offsets, because the
+lengths of inserts such as XSTRING(MAX_NAME_SIZE) are not known. Instead, we
+simply count through to the one we want - this isn't a performance issue
+because these strings are used only when there is a compilation error.
+
+Each substring ends with \0 to insert a null character. This includes the final
+substring, so that the whole string ends with \0\0, which can be detected when
+counting through. */
+
+static const char error_texts[] =
+  "no error\0"
+  "\\ at end of pattern\0"
+  "\\c at end of pattern\0"
+  "unrecognized character follows \\\0"
+  "numbers out of order in {} quantifier\0"
+  /* 5 */
+  "number too big in {} quantifier\0"
+  "missing terminating ] for character class\0"
+  "invalid escape sequence in character class\0"
+  "range out of order in character class\0"
+  "nothing to repeat\0"
+  /* 10 */
+  "operand of unlimited repeat could match the empty string\0"  /** DEAD **/
+  "internal error: unexpected repeat\0"
+  "unrecognized character after (? or (?-\0"
+  "POSIX named classes are supported only within a class\0"
+  "missing )\0"
+  /* 15 */
+  "reference to non-existent subpattern\0"
+  "erroffset passed as NULL\0"
+  "unknown option bit(s) set\0"
+  "missing ) after comment\0"
+  "parentheses nested too deeply\0"  /** DEAD **/
+  /* 20 */
+  "regular expression is too large\0"
+  "failed to get memory\0"
+  "unmatched parentheses\0"
+  "internal error: code overflow\0"
+  "unrecognized character after (?<\0"
+  /* 25 */
+  "lookbehind assertion is not fixed length\0"
+  "malformed number or name after (?(\0"
+  "conditional group contains more than two branches\0"
+  "assertion expected after (?(\0"
+  "(?R or (?[+-]digits must be followed by )\0"
+  /* 30 */
+  "unknown POSIX class name\0"
+  "POSIX collating elements are not supported\0"
+  "this version of PCRE is compiled without UTF support\0"
+  "spare error\0"  /** DEAD **/
+  "character value in \\x{...} sequence is too large\0"
+  /* 35 */
+  "invalid condition (?(0)\0"
+  "\\C not allowed in lookbehind assertion\0"
+  "PCRE does not support \\L, \\l, \\N{name}, \\U, or \\u\0"
+  "number after (?C is > 255\0"
+  "closing ) for (?C expected\0"
+  /* 40 */
+  "recursive call could loop indefinitely\0"
+  "unrecognized character after (?P\0"
+  "syntax error in subpattern name (missing terminator)\0"
+  "two named subpatterns have the same name\0"
+  "invalid UTF-8 string\0"
+  /* 45 */
+  "support for \\P, \\p, and \\X has not been compiled\0"
+  "malformed \\P or \\p sequence\0"
+  "unknown property name after \\P or \\p\0"
+  "subpattern name is too long (maximum " XSTRING(MAX_NAME_SIZE) " characters)\0"
+  "too many named subpatterns (maximum " XSTRING(MAX_NAME_COUNT) ")\0"
+  /* 50 */
+  "repeated subpattern is too long\0"    /** DEAD **/
+  "octal value is greater than \\377 in 8-bit non-UTF-8 mode\0"
+  "internal error: overran compiling workspace\0"
+  "internal error: previously-checked referenced subpattern not found\0"
+  "DEFINE group contains more than one branch\0"
+  /* 55 */
+  "repeating a DEFINE group is not allowed\0"  /** DEAD **/
+  "inconsistent NEWLINE options\0"
+  "\\g is not followed by a braced, angle-bracketed, or quoted name/number or by a plain number\0"
+  "a numbered reference must not be zero\0"
+  "an argument is not allowed for (*ACCEPT), (*FAIL), or (*COMMIT)\0"
+  /* 60 */
+  "(*VERB) not recognized\0"
+  "number is too big\0"
+  "subpattern name expected\0"
+  "digit expected after (?+\0"
+  "] is an invalid data character in JavaScript compatibility mode\0"
+  /* 65 */
+  "different names for subpatterns of the same number are not allowed\0"
+  "(*MARK) must have an argument\0"
+  "this version of PCRE is not compiled with Unicode property support\0"
+  "\\c must be followed by an ASCII character\0"
+  "\\k is not followed by a braced, angle-bracketed, or quoted name\0"
+  /* 70 */
+  "internal error: unknown opcode in find_fixedlength()\0"
+  "\\N is not supported in a class\0"
+  "too many forward references\0"
+  "disallowed Unicode code point (>= 0xd800 && <= 0xdfff)\0"
+  "invalid UTF-16 string\0"
+  /* 75 */
+  "name is too long in (*MARK), (*PRUNE), (*SKIP), or (*THEN)\0"
+  "character value in \\u.... sequence is too large\0"
+  ;
+
+/* Table to identify digits and hex digits. This is used when compiling
+patterns. Note that the tables in chartables are dependent on the locale, and
+may mark arbitrary characters as digits - but the PCRE compiling code expects
+to handle only 0-9, a-z, and A-Z as digits when compiling. That is why we have
+a private table here. It costs 256 bytes, but it is a lot faster than doing
+character value tests (at least in some simple cases I timed), and in some
+applications one wants PCRE to compile efficiently as well as match
+efficiently.
+
+For convenience, we use the same bit definitions as in chartables:
+
+  0x04   decimal digit
+  0x08   hexadecimal digit
+
+Then we can use ctype_digit and ctype_xdigit in the code. */
+
+/* Using a simple comparison for decimal numbers rather than a memory read
+is much faster, and the resulting code is simpler (the compiler turns it
+into a subtraction and unsigned comparison). */
+
+#define IS_DIGIT(x) ((x) >= CHAR_0 && (x) <= CHAR_9)
+
+#ifndef EBCDIC
+
+/* This is the "normal" case, for ASCII systems, and EBCDIC systems running in
+UTF-8 mode. */
+
+static const pcre_uint8 digitab[] =
+  {
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /*   0-  7 */
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /*   8- 15 */
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /*  16- 23 */
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /*  24- 31 */
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /*    - '  */
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /*  ( - /  */
+  0x0c,0x0c,0x0c,0x0c,0x0c,0x0c,0x0c,0x0c, /*  0 - 7  */
+  0x0c,0x0c,0x00,0x00,0x00,0x00,0x00,0x00, /*  8 - ?  */
+  0x00,0x08,0x08,0x08,0x08,0x08,0x08,0x00, /*  @ - G  */
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /*  H - O  */
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /*  P - W  */
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /*  X - _  */
+  0x00,0x08,0x08,0x08,0x08,0x08,0x08,0x00, /*  ` - g  */
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /*  h - o  */
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /*  p - w  */
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /*  x -127 */
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 128-135 */
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 136-143 */
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 144-151 */
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 152-159 */
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 160-167 */
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 168-175 */
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 176-183 */
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 184-191 */
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 192-199 */
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 200-207 */
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 208-215 */
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 216-223 */
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 224-231 */
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 232-239 */
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 240-247 */
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00};/* 248-255 */
+
+#else
+
+/* This is the "abnormal" case, for EBCDIC systems not running in UTF-8 mode. */
+
+static const pcre_uint8 digitab[] =
+  {
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /*   0-  7  0 */
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /*   8- 15    */
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /*  16- 23 10 */
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /*  24- 31    */
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /*  32- 39 20 */
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /*  40- 47    */
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /*  48- 55 30 */
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /*  56- 63    */
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /*    - 71 40 */
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /*  72- |     */
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /*  & - 87 50 */
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /*  88- 95    */
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /*  - -103 60 */
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 104- ?     */
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 112-119 70 */
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 120- "     */
+  0x00,0x08,0x08,0x08,0x08,0x08,0x08,0x00, /* 128- g  80 */
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /*  h -143    */
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 144- p  90 */
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /*  q -159    */
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 160- x  A0 */
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /*  y -175    */
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /*  ^ -183 B0 */
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 184-191    */
+  0x00,0x08,0x08,0x08,0x08,0x08,0x08,0x00, /*  { - G  C0 */
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /*  H -207    */
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /*  } - P  D0 */
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /*  Q -223    */
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /*  \ - X  E0 */
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /*  Y -239    */
+  0x0c,0x0c,0x0c,0x0c,0x0c,0x0c,0x0c,0x0c, /*  0 - 7  F0 */
+  0x0c,0x0c,0x00,0x00,0x00,0x00,0x00,0x00};/*  8 -255    */
+
+static const pcre_uint8 ebcdic_chartab[] = { /* chartable partial dup */
+  0x80,0x00,0x00,0x00,0x00,0x01,0x00,0x00, /*   0-  7 */
+  0x00,0x00,0x00,0x00,0x01,0x01,0x00,0x00, /*   8- 15 */
+  0x00,0x00,0x00,0x00,0x00,0x01,0x00,0x00, /*  16- 23 */
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /*  24- 31 */
+  0x00,0x00,0x00,0x00,0x00,0x01,0x00,0x00, /*  32- 39 */
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /*  40- 47 */
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /*  48- 55 */
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /*  56- 63 */
+  0x01,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /*    - 71 */
+  0x00,0x00,0x00,0x80,0x00,0x80,0x80,0x80, /*  72- |  */
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /*  & - 87 */
+  0x00,0x00,0x00,0x80,0x80,0x80,0x00,0x00, /*  88- 95 */
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /*  - -103 */
+  0x00,0x00,0x00,0x00,0x00,0x10,0x00,0x80, /* 104- ?  */
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 112-119 */
+  0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 120- "  */
+  0x00,0x1a,0x1a,0x1a,0x1a,0x1a,0x1a,0x12, /* 128- g  */
+  0x12,0x12,0x00,0x00,0x00,0x00,0x00,0x00, /*  h -143 */
+  0x00,0x12,0x12,0x12,0x12,0x12,0x12,0x12, /* 144- p  */
+  0x12,0x12,0x00,0x00,0x00,0x00,0x00,0x00, /*  q -159 */
+  0x00,0x00,0x12,0x12,0x12,0x12,0x12,0x12, /* 160- x  */
+  0x12,0x12,0x00,0x00,0x00,0x00,0x00,0x00, /*  y -175 */
+  0x80,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /*  ^ -183 */
+  0x00,0x00,0x80,0x00,0x00,0x00,0x00,0x00, /* 184-191 */
+  0x80,0x1a,0x1a,0x1a,0x1a,0x1a,0x1a,0x12, /*  { - G  */
+  0x12,0x12,0x00,0x00,0x00,0x00,0x00,0x00, /*  H -207 */
+  0x00,0x12,0x12,0x12,0x12,0x12,0x12,0x12, /*  } - P  */
+  0x12,0x12,0x00,0x00,0x00,0x00,0x00,0x00, /*  Q -223 */
+  0x00,0x00,0x12,0x12,0x12,0x12,0x12,0x12, /*  \ - X  */
+  0x12,0x12,0x00,0x00,0x00,0x00,0x00,0x00, /*  Y -239 */
+  0x1c,0x1c,0x1c,0x1c,0x1c,0x1c,0x1c,0x1c, /*  0 - 7  */
+  0x1c,0x1c,0x00,0x00,0x00,0x00,0x00,0x00};/*  8 -255 */
+#endif
+
+
+/* Definition to allow mutual recursion */
+
+static BOOL
+  compile_regex(int, pcre_uchar **, const pcre_uchar **, int *, BOOL, BOOL, int, int,
+    int *, int *, branch_chain *, compile_data *, int *);
+
+
+
+/*************************************************
+*            Find an error text                  *
+*************************************************/
+
+/* The error texts are now all in one long string, to save on relocations. As
+some of the text is of unknown length, we can't use a table of offsets.
+Instead, just count through the strings. This is not a performance issue
+because it happens only when there has been a compilation error.
+
+Argument:   the error number
+Returns:    pointer to the error string
+*/
+
+static const char *
+find_error_text(int n)
+{
+const char *s = error_texts;
+for (; n > 0; n--)
+  {
+  while (*s++ != 0) {};
+  if (*s == 0) return "Error text not found (please report)";
+  }
+return s;
+}
+
+
+/*************************************************
+*           Expand the workspace                 *
+*************************************************/
+
+/* This function is called during the second compiling phase, if the number of
+forward references fills the existing workspace, which is originally a block on
+the stack. A larger block is obtained from malloc() unless the ultimate limit
+has been reached or the increase will be rather small.
+
+Argument: pointer to the compile data block
+Returns:  0 if all went well, else an error number
+*/
+
+static int
+expand_workspace(compile_data *cd)
+{
+pcre_uchar *newspace;
+int newsize = cd->workspace_size * 2;
+
+if (newsize > COMPILE_WORK_SIZE_MAX) newsize = COMPILE_WORK_SIZE_MAX;
+if (cd->workspace_size >= COMPILE_WORK_SIZE_MAX ||
+    newsize - cd->workspace_size < WORK_SIZE_SAFETY_MARGIN)
+ return ERR72;
+
+newspace = (PUBL(malloc))(IN_UCHARS(newsize));
+if (newspace == NULL) return ERR21;
+memcpy(newspace, cd->start_workspace, cd->workspace_size * sizeof(pcre_uchar));
+cd->hwm = (pcre_uchar *)newspace + (cd->hwm - cd->start_workspace);
+if (cd->workspace_size > COMPILE_WORK_SIZE)
+  (PUBL(free))((void *)cd->start_workspace);
+cd->start_workspace = newspace;
+cd->workspace_size = newsize;
+return 0;
+}
+
+
+
+/*************************************************
+*            Check for counted repeat            *
+*************************************************/
+
+/* This function is called when a '{' is encountered in a place where it might
+start a quantifier. It looks ahead to see if it really is a quantifier or not.
+It is only a quantifier if it is one of the forms {ddd} {ddd,} or {ddd,ddd}
+where the ddds are digits.
+
+Arguments:
+  p         pointer to the first char after '{'
+
+Returns:    TRUE or FALSE
+*/
+
+static BOOL
+is_counted_repeat(const pcre_uchar *p)
+{
+if (!IS_DIGIT(*p)) return FALSE;
+p++;
+while (IS_DIGIT(*p)) p++;
+if (*p == CHAR_RIGHT_CURLY_BRACKET) return TRUE;
+
+if (*p++ != CHAR_COMMA) return FALSE;
+if (*p == CHAR_RIGHT_CURLY_BRACKET) return TRUE;
+
+if (!IS_DIGIT(*p)) return FALSE;
+p++;
+while (IS_DIGIT(*p)) p++;
+
+return (*p == CHAR_RIGHT_CURLY_BRACKET);
+}
+
+
+
+/*************************************************
+*            Handle escapes                      *
+*************************************************/
+
+/* This function is called when a \ has been encountered. It either returns a
+positive value for a simple escape such as \n, or a negative value which
+encodes one of the more complicated things such as \d. A backreference to group
+n is returned as -(ESC_REF + n); ESC_REF is the highest ESC_xxx macro. When
+UTF-8 is enabled, a positive value greater than 255 may be returned. On entry,
+ptr is pointing at the \. On exit, it is on the final character of the escape
+sequence.
+
+Arguments:
+  ptrptr         points to the pattern position pointer
+  errorcodeptr   points to the errorcode variable
+  bracount       number of previous extracting brackets
+  options        the options bits
+  isclass        TRUE if inside a character class
+
+Returns:         zero or positive => a data character
+                 negative => a special escape sequence
+                 on error, errorcodeptr is set
+*/
+
+static int
+check_escape(const pcre_uchar **ptrptr, int *errorcodeptr, int bracount,
+  int options, BOOL isclass)
+{
+/* PCRE_UTF16 has the same value as PCRE_UTF8. */
+BOOL utf = (options & PCRE_UTF8) != 0;
+const pcre_uchar *ptr = *ptrptr + 1;
+pcre_int32 c;
+int i;
+
+GETCHARINCTEST(c, ptr);           /* Get character value, increment pointer */
+ptr--;                            /* Set pointer back to the last byte */
+
+/* If backslash is at the end of the pattern, it's an error. */
+
+if (c == 0) *errorcodeptr = ERR1;
+
+/* Non-alphanumerics are literals. For digits or letters, do an initial lookup
+in a table. A non-zero result is something that can be returned immediately.
+Otherwise further processing may be required. */
+
+#ifndef EBCDIC  /* ASCII/UTF-8 coding */
+/* Not alphanumeric */
+else if (c < CHAR_0 || c > CHAR_z) {}
+else if ((i = escapes[c - CHAR_0]) != 0) c = i;
+
+#else           /* EBCDIC coding */
+/* Not alphanumeric */
+else if (c < 'a' || (!MAX_255(c) || (ebcdic_chartab[c] & 0x0E) == 0)) {}
+else if ((i = escapes[c - 0x48]) != 0)  c = i;
+#endif
+
+/* Escapes that need further processing, or are illegal. */
+
+else
+  {
+  const pcre_uchar *oldptr;
+  BOOL braced, negated;
+
+  switch (c)
+    {
+    /* A number of Perl escapes are not handled by PCRE. We give an explicit
+    error. */
+
+    case CHAR_l:
+    case CHAR_L:
+    *errorcodeptr = ERR37;
+    break;
+
+    case CHAR_u:
+    if ((options & PCRE_JAVASCRIPT_COMPAT) != 0)
+      {
+      /* In JavaScript, \u must be followed by four hexadecimal numbers.
+      Otherwise it is a lowercase u letter. */
+      if (MAX_255(ptr[1]) && (digitab[ptr[1]] & ctype_xdigit) != 0
+        && MAX_255(ptr[2]) && (digitab[ptr[2]] & ctype_xdigit) != 0
+        && MAX_255(ptr[3]) && (digitab[ptr[3]] & ctype_xdigit) != 0
+        && MAX_255(ptr[4]) && (digitab[ptr[4]] & ctype_xdigit) != 0)
+        {
+        c = 0;
+        for (i = 0; i < 4; ++i)
+          {
+          register int cc = *(++ptr);
+#ifndef EBCDIC  /* ASCII/UTF-8 coding */
+          if (cc >= CHAR_a) cc -= 32;               /* Convert to upper case */
+          c = (c << 4) + cc - ((cc < CHAR_A)? CHAR_0 : (CHAR_A - 10));
+#else           /* EBCDIC coding */
+          if (cc >= CHAR_a && cc <= CHAR_z) cc += 64;  /* Convert to upper case */
+          c = (c << 4) + cc - ((cc >= CHAR_0)? CHAR_0 : (CHAR_A - 10));
+#endif
+          }
+
+#ifdef COMPILE_PCRE8
+        if (c > (utf ? 0x10ffff : 0xff))
+#else
+#ifdef COMPILE_PCRE16
+        if (c > (utf ? 0x10ffff : 0xffff))
+#endif
+#endif
+          {
+          *errorcodeptr = ERR76;
+          }
+        else if (utf && c >= 0xd800 && c <= 0xdfff) *errorcodeptr = ERR73;
+        }
+      }
+    else
+      *errorcodeptr = ERR37;
+    break;
+
+    case CHAR_U:
+    /* In JavaScript, \U is an uppercase U letter. */
+    if ((options & PCRE_JAVASCRIPT_COMPAT) == 0) *errorcodeptr = ERR37;
+    break;
+
+    /* In a character class, \g is just a literal "g". Outside a character
+    class, \g must be followed by one of a number of specific things:
+
+    (1) A number, either plain or braced. If positive, it is an absolute
+    backreference. If negative, it is a relative backreference. This is a Perl
+    5.10 feature.
+
+    (2) Perl 5.10 also supports \g{name} as a reference to a named group. This
+    is part of Perl's movement towards a unified syntax for back references. As
+    this is synonymous with \k{name}, we fudge it up by pretending it really
+    was \k.
+
+    (3) For Oniguruma compatibility we also support \g followed by a name or a
+    number either in angle brackets or in single quotes. However, these are
+    (possibly recursive) subroutine calls, _not_ backreferences. Just return
+    the -ESC_g code (cf \k). */
+
+    case CHAR_g:
+    if (isclass) break;
+    if (ptr[1] == CHAR_LESS_THAN_SIGN || ptr[1] == CHAR_APOSTROPHE)
+      {
+      c = -ESC_g;
+      break;
+      }
+
+    /* Handle the Perl-compatible cases */
+
+    if (ptr[1] == CHAR_LEFT_CURLY_BRACKET)
+      {
+      const pcre_uchar *p;
+      for (p = ptr+2; *p != 0 && *p != CHAR_RIGHT_CURLY_BRACKET; p++)
+        if (*p != CHAR_MINUS && !IS_DIGIT(*p)) break;
+      if (*p != 0 && *p != CHAR_RIGHT_CURLY_BRACKET)
+        {
+        c = -ESC_k;
+        break;
+        }
+      braced = TRUE;
+      ptr++;
+      }
+    else braced = FALSE;
+
+    if (ptr[1] == CHAR_MINUS)
+      {
+      negated = TRUE;
+      ptr++;
+      }
+    else negated = FALSE;
+
+    /* The integer range is limited by the machine's int representation. */
+    c = 0;
+    while (IS_DIGIT(ptr[1]))
+      {
+      if (((unsigned int)c) > INT_MAX / 10) /* Integer overflow */
+        {
+        c = -1;
+        break;
+        }
+      c = c * 10 + *(++ptr) - CHAR_0;
+      }
+    if (((unsigned int)c) > INT_MAX) /* Integer overflow */
+      {
+      while (IS_DIGIT(ptr[1]))
+        ptr++;
+      *errorcodeptr = ERR61;
+      break;
+      }
+
+    if (braced && *(++ptr) != CHAR_RIGHT_CURLY_BRACKET)
+      {
+      *errorcodeptr = ERR57;
+      break;
+      }
+
+    if (c == 0)
+      {
+      *errorcodeptr = ERR58;
+      break;
+      }
+
+    if (negated)
+      {
+      if (c > bracount)
+        {
+        *errorcodeptr = ERR15;
+        break;
+        }
+      c = bracount - (c - 1);
+      }
+
+    c = -(ESC_REF + c);
+    break;
+
+    /* The handling of escape sequences consisting of a string of digits
+    starting with one that is not zero is not straightforward. By experiment,
+    the way Perl works seems to be as follows:
+
+    Outside a character class, the digits are read as a decimal number. If the
+    number is less than 10, or if there are that many previous extracting
+    left brackets, then it is a back reference. Otherwise, up to three octal
+    digits are read to form an escaped byte. Thus \123 is likely to be octal
+    123 (cf \0123, which is octal 012 followed by the literal 3). If the octal
+    value is greater than 377, the least significant 8 bits are taken. Inside a
+    character class, \ followed by a digit is always an octal number. */
+
+    case CHAR_1: case CHAR_2: case CHAR_3: case CHAR_4: case CHAR_5:
+    case CHAR_6: case CHAR_7: case CHAR_8: case CHAR_9:
+
+    if (!isclass)
+      {
+      oldptr = ptr;
+      /* The integer range is limited by the machine's int representation. */
+      c -= CHAR_0;
+      while (IS_DIGIT(ptr[1]))
+        {
+        if (((unsigned int)c) > INT_MAX / 10) /* Integer overflow */
+          {
+          c = -1;
+          break;
+          }
+        c = c * 10 + *(++ptr) - CHAR_0;
+        }
+      if (((unsigned int)c) > INT_MAX) /* Integer overflow */
+        {
+        while (IS_DIGIT(ptr[1]))
+          ptr++;
+        *errorcodeptr = ERR61;
+        break;
+        }
+      if (c < 10 || c <= bracount)
+        {
+        c = -(ESC_REF + c);
+        break;
+        }
+      ptr = oldptr;      /* Put the pointer back and fall through */
+      }
+
+    /* Handle an octal number following \. If the first digit is 8 or 9, Perl
+    generates a binary zero byte and treats the digit as a following literal.
+    Thus we have to pull back the pointer by one. */
+
+    if ((c = *ptr) >= CHAR_8)
+      {
+      ptr--;
+      c = 0;
+      break;
+      }
+
+    /* \0 always starts an octal number, but we may drop through to here with a
+    larger first octal digit. The original code used just to take the least
+    significant 8 bits of octal numbers (I think this is what early Perls used
+    to do). Nowadays we allow for larger numbers in UTF-8 mode and 16-bit mode,
+    but no more than 3 octal digits. */
+
+    case CHAR_0:
+    c -= CHAR_0;
+    while(i++ < 2 && ptr[1] >= CHAR_0 && ptr[1] <= CHAR_7)
+        c = c * 8 + *(++ptr) - CHAR_0;
+#ifdef COMPILE_PCRE8
+    if (!utf && c > 0xff) *errorcodeptr = ERR51;
+#endif
+    break;
+
+    /* \x is complicated. \x{ddd} is a character number which can be greater
+    than 0xff in utf or non-8bit mode, but only if the ddd are hex digits.
+    If not, { is treated as a data character. */
+
+    case CHAR_x:
+    if ((options & PCRE_JAVASCRIPT_COMPAT) != 0)
+      {
+      /* In JavaScript, \x must be followed by two hexadecimal numbers.
+      Otherwise it is a lowercase x letter. */
+      if (MAX_255(ptr[1]) && (digitab[ptr[1]] & ctype_xdigit) != 0
+        && MAX_255(ptr[2]) && (digitab[ptr[2]] & ctype_xdigit) != 0)
+        {
+        c = 0;
+        for (i = 0; i < 2; ++i)
+          {
+          register int cc = *(++ptr);
+#ifndef EBCDIC  /* ASCII/UTF-8 coding */
+          if (cc >= CHAR_a) cc -= 32;               /* Convert to upper case */
+          c = (c << 4) + cc - ((cc < CHAR_A)? CHAR_0 : (CHAR_A - 10));
+#else           /* EBCDIC coding */
+          if (cc >= CHAR_a && cc <= CHAR_z) cc += 64;  /* Convert to upper case */
+          c = (c << 4) + cc - ((cc >= CHAR_0)? CHAR_0 : (CHAR_A - 10));
+#endif
+          }
+        }
+      break;
+      }
+
+    if (ptr[1] == CHAR_LEFT_CURLY_BRACKET)
+      {
+      const pcre_uchar *pt = ptr + 2;
+
+      c = 0;
+      while (MAX_255(*pt) && (digitab[*pt] & ctype_xdigit) != 0)
+        {
+        register int cc = *pt++;
+        if (c == 0 && cc == CHAR_0) continue;     /* Leading zeroes */
+
+#ifndef EBCDIC  /* ASCII/UTF-8 coding */
+        if (cc >= CHAR_a) cc -= 32;               /* Convert to upper case */
+        c = (c << 4) + cc - ((cc < CHAR_A)? CHAR_0 : (CHAR_A - 10));
+#else           /* EBCDIC coding */
+        if (cc >= CHAR_a && cc <= CHAR_z) cc += 64;  /* Convert to upper case */
+        c = (c << 4) + cc - ((cc >= CHAR_0)? CHAR_0 : (CHAR_A - 10));
+#endif
+
+#ifdef COMPILE_PCRE8
+        if (c > (utf ? 0x10ffff : 0xff)) { c = -1; break; }
+#else
+#ifdef COMPILE_PCRE16
+        if (c > (utf ? 0x10ffff : 0xffff)) { c = -1; break; }
+#endif
+#endif
+        }
+
+      if (c < 0)
+        {
+        while (MAX_255(*pt) && (digitab[*pt] & ctype_xdigit) != 0) pt++;
+        *errorcodeptr = ERR34;
+        }
+
+      if (*pt == CHAR_RIGHT_CURLY_BRACKET)
+        {
+        if (utf && c >= 0xd800 && c <= 0xdfff) *errorcodeptr = ERR73;
+        ptr = pt;
+        break;
+        }
+
+      /* If the sequence of hex digits does not end with '}', then we don't
+      recognize this construct; fall through to the normal \x handling. */
+      }
+
+    /* Read just a single-byte hex-defined char */
+
+    c = 0;
+    while (i++ < 2 && MAX_255(ptr[1]) && (digitab[ptr[1]] & ctype_xdigit) != 0)
+      {
+      int cc;                                  /* Some compilers don't like */
+      cc = *(++ptr);                           /* ++ in initializers */
+#ifndef EBCDIC  /* ASCII/UTF-8 coding */
+      if (cc >= CHAR_a) cc -= 32;              /* Convert to upper case */
+      c = c * 16 + cc - ((cc < CHAR_A)? CHAR_0 : (CHAR_A - 10));
+#else           /* EBCDIC coding */
+      if (cc <= CHAR_z) cc += 64;              /* Convert to upper case */
+      c = c * 16 + cc - ((cc >= CHAR_0)? CHAR_0 : (CHAR_A - 10));
+#endif
+      }
+    break;
+
+    /* For \c, a following letter is upper-cased; then the 0x40 bit is flipped.
+    An error is given if the byte following \c is not an ASCII character. This
+    coding is ASCII-specific, but then the whole concept of \cx is
+    ASCII-specific. (However, an EBCDIC equivalent has now been added.) */
+
+    case CHAR_c:
+    c = *(++ptr);
+    if (c == 0)
+      {
+      *errorcodeptr = ERR2;
+      break;
+      }
+#ifndef EBCDIC    /* ASCII/UTF-8 coding */
+    if (c > 127)  /* Excludes all non-ASCII in either mode */
+      {
+      *errorcodeptr = ERR68;
+      break;
+      }
+    if (c >= CHAR_a && c <= CHAR_z) c -= 32;
+    c ^= 0x40;
+#else             /* EBCDIC coding */
+    if (c >= CHAR_a && c <= CHAR_z) c += 64;
+    c ^= 0xC0;
+#endif
+    break;
+
+    /* PCRE_EXTRA enables extensions to Perl in the matter of escapes. Any
+    other alphanumeric following \ is an error if PCRE_EXTRA was set;
+    otherwise, for Perl compatibility, it is a literal. This code looks a bit
+    odd, but there used to be some cases other than the default, and there may
+    be again in future, so I haven't "optimized" it. */
+
+    default:
+    if ((options & PCRE_EXTRA) != 0) switch(c)
+      {
+      default:
+      *errorcodeptr = ERR3;
+      break;
+      }
+    break;
+    }
+  }
+
+/* Perl supports \N{name} for character names, as well as plain \N for "not
+newline". PCRE does not support \N{name}. However, it does support
+quantification such as \N{2,3}. */
+
+if (c == -ESC_N && ptr[1] == CHAR_LEFT_CURLY_BRACKET &&
+     !is_counted_repeat(ptr+2))
+  *errorcodeptr = ERR37;
+
+/* If PCRE_UCP is set, we change the values for \d etc. */
+
+if ((options & PCRE_UCP) != 0 && c <= -ESC_D && c >= -ESC_w)
+  c -= (ESC_DU - ESC_D);
+
+/* Set the pointer to the final character before returning. */
+
+*ptrptr = ptr;
+return c;
+}
+
+
+
+#ifdef SUPPORT_UCP
+/*************************************************
+*               Handle \P and \p                 *
+*************************************************/
+
+/* This function is called after \P or \p has been encountered, provided that
+PCRE is compiled with support for Unicode properties. On entry, ptrptr is
+pointing at the P or p. On exit, it is pointing at the final character of the
+escape sequence.
+
+Argument:
+  ptrptr         points to the pattern position pointer
+  negptr         points to a boolean that is set TRUE for negation else FALSE
+  dptr           points to an int that is set to the detailed property value
+  errorcodeptr   points to the error code variable
+
+Returns:         type value from ucp_type_table, or -1 for an invalid type
+*/
+
+static int
+get_ucp(const pcre_uchar **ptrptr, BOOL *negptr, int *dptr, int *errorcodeptr)
+{
+int c, i, bot, top;
+const pcre_uchar *ptr = *ptrptr;
+pcre_uchar name[32];
+
+c = *(++ptr);
+if (c == 0) goto ERROR_RETURN;
+
+*negptr = FALSE;
+
+/* \P or \p can be followed by a name in {}, optionally preceded by ^ for
+negation. */
+
+if (c == CHAR_LEFT_CURLY_BRACKET)
+  {
+  if (ptr[1] == CHAR_CIRCUMFLEX_ACCENT)
+    {
+    *negptr = TRUE;
+    ptr++;
+    }
+  for (i = 0; i < (int)(sizeof(name) / sizeof(pcre_uchar)) - 1; i++)
+    {
+    c = *(++ptr);
+    if (c == 0) goto ERROR_RETURN;
+    if (c == CHAR_RIGHT_CURLY_BRACKET) break;
+    name[i] = c;
+    }
+  if (c != CHAR_RIGHT_CURLY_BRACKET) goto ERROR_RETURN;
+  name[i] = 0;
+  }
+
+/* Otherwise there is just one following character */
+
+else
+  {
+  name[0] = c;
+  name[1] = 0;
+  }
+
+*ptrptr = ptr;
+
+/* Search for a recognized property name using binary chop */
+
+bot = 0;
+top = PRIV(utt_size);
+
+while (bot < top)
+  {
+  i = (bot + top) >> 1;
+  c = STRCMP_UC_C8(name, PRIV(utt_names) + PRIV(utt)[i].name_offset);
+  if (c == 0)
+    {
+    *dptr = PRIV(utt)[i].value;
+    return PRIV(utt)[i].type;
+    }
+  if (c > 0) bot = i + 1; else top = i;
+  }
+
+*errorcodeptr = ERR47;
+*ptrptr = ptr;
+return -1;
+
+ERROR_RETURN:
+*errorcodeptr = ERR46;
+*ptrptr = ptr;
+return -1;
+}
+#endif
+
+
+
+
+/*************************************************
+*         Read repeat counts                     *
+*************************************************/
+
+/* Read an item of the form {n,m} and return the values. This is called only
+after is_counted_repeat() has confirmed that a repeat-count quantifier exists,
+so the syntax is guaranteed to be correct, but we need to check the values.
+
+Arguments:
+  p              pointer to first char after '{'
+  minp           pointer to int for min
+  maxp           pointer to int for max
+                 returned as -1 if no max
+  errorcodeptr   points to error code variable
+
+Returns:         pointer to '}' on success;
+                 current ptr on error, with errorcodeptr set non-zero
+*/
+
+static const pcre_uchar *
+read_repeat_counts(const pcre_uchar *p, int *minp, int *maxp, int *errorcodeptr)
+{
+int min = 0;
+int max = -1;
+
+/* Read the minimum value and do a paranoid check: a negative value indicates
+an integer overflow. */
+
+while (IS_DIGIT(*p)) min = min * 10 + *p++ - CHAR_0;
+if (min < 0 || min > 65535)
+  {
+  *errorcodeptr = ERR5;
+  return p;
+  }
+
+/* Read the maximum value if there is one, and again do a paranoid on its size.
+Also, max must not be less than min. */
+
+if (*p == CHAR_RIGHT_CURLY_BRACKET) max = min; else
+  {
+  if (*(++p) != CHAR_RIGHT_CURLY_BRACKET)
+    {
+    max = 0;
+    while(IS_DIGIT(*p)) max = max * 10 + *p++ - CHAR_0;
+    if (max < 0 || max > 65535)
+      {
+      *errorcodeptr = ERR5;
+      return p;
+      }
+    if (max < min)
+      {
+      *errorcodeptr = ERR4;
+      return p;
+      }
+    }
+  }
+
+/* Fill in the required variables, and pass back the pointer to the terminating
+'}'. */
+
+*minp = min;
+*maxp = max;
+return p;
+}
+
+
+
+/*************************************************
+*  Subroutine for finding forward reference      *
+*************************************************/
+
+/* This recursive function is called only from find_parens() below. The
+top-level call starts at the beginning of the pattern. All other calls must
+start at a parenthesis. It scans along a pattern's text looking for capturing
+subpatterns, and counting them. If it finds a named pattern that matches the
+name it is given, it returns its number. Alternatively, if the name is NULL, it
+returns when it reaches a given numbered subpattern. Recursion is used to keep
+track of subpatterns that reset the capturing group numbers - the (?| feature.
+
+This function was originally called only from the second pass, in which we know
+that if (?< or (?' or (?P< is encountered, the name will be correctly
+terminated because that is checked in the first pass. There is now one call to
+this function in the first pass, to check for a recursive back reference by
+name (so that we can make the whole group atomic). In this case, we need check
+only up to the current position in the pattern, and that is still OK because
+and previous occurrences will have been checked. To make this work, the test
+for "end of pattern" is a check against cd->end_pattern in the main loop,
+instead of looking for a binary zero. This means that the special first-pass
+call can adjust cd->end_pattern temporarily. (Checks for binary zero while
+processing items within the loop are OK, because afterwards the main loop will
+terminate.)
+
+Arguments:
+  ptrptr       address of the current character pointer (updated)
+  cd           compile background data
+  name         name to seek, or NULL if seeking a numbered subpattern
+  lorn         name length, or subpattern number if name is NULL
+  xmode        TRUE if we are in /x mode
+  utf          TRUE if we are in UTF-8 / UTF-16 mode
+  count        pointer to the current capturing subpattern number (updated)
+
+Returns:       the number of the named subpattern, or -1 if not found
+*/
+
+static int
+find_parens_sub(pcre_uchar **ptrptr, compile_data *cd, const pcre_uchar *name, int lorn,
+  BOOL xmode, BOOL utf, int *count)
+{
+pcre_uchar *ptr = *ptrptr;
+int start_count = *count;
+int hwm_count = start_count;
+BOOL dup_parens = FALSE;
+
+/* If the first character is a parenthesis, check on the type of group we are
+dealing with. The very first call may not start with a parenthesis. */
+
+if (ptr[0] == CHAR_LEFT_PARENTHESIS)
+  {
+  /* Handle specials such as (*SKIP) or (*UTF8) etc. */
+
+  if (ptr[1] == CHAR_ASTERISK) ptr += 2;
+
+  /* Handle a normal, unnamed capturing parenthesis. */
+
+  else if (ptr[1] != CHAR_QUESTION_MARK)
+    {
+    *count += 1;
+    if (name == NULL && *count == lorn) return *count;
+    ptr++;
+    }
+
+  /* All cases now have (? at the start. Remember when we are in a group
+  where the parenthesis numbers are duplicated. */
+
+  else if (ptr[2] == CHAR_VERTICAL_LINE)
+    {
+    ptr += 3;
+    dup_parens = TRUE;
+    }
+
+  /* Handle comments; all characters are allowed until a ket is reached. */
+
+  else if (ptr[2] == CHAR_NUMBER_SIGN)
+    {
+    for (ptr += 3; *ptr != 0; ptr++) if (*ptr == CHAR_RIGHT_PARENTHESIS) break;
+    goto FAIL_EXIT;
+    }
+
+  /* Handle a condition. If it is an assertion, just carry on so that it
+  is processed as normal. If not, skip to the closing parenthesis of the
+  condition (there can't be any nested parens). */
+
+  else if (ptr[2] == CHAR_LEFT_PARENTHESIS)
+    {
+    ptr += 2;
+    if (ptr[1] != CHAR_QUESTION_MARK)
+      {
+      while (*ptr != 0 && *ptr != CHAR_RIGHT_PARENTHESIS) ptr++;
+      if (*ptr != 0) ptr++;
+      }
+    }
+
+  /* Start with (? but not a condition. */
+
+  else
+    {
+    ptr += 2;
+    if (*ptr == CHAR_P) ptr++;                      /* Allow optional P */
+
+    /* We have to disambiguate (?<! and (?<= from (?<name> for named groups */
+
+    if ((*ptr == CHAR_LESS_THAN_SIGN && ptr[1] != CHAR_EXCLAMATION_MARK &&
+        ptr[1] != CHAR_EQUALS_SIGN) || *ptr == CHAR_APOSTROPHE)
+      {
+      int term;
+      const pcre_uchar *thisname;
+      *count += 1;
+      if (name == NULL && *count == lorn) return *count;
+      term = *ptr++;
+      if (term == CHAR_LESS_THAN_SIGN) term = CHAR_GREATER_THAN_SIGN;
+      thisname = ptr;
+      while (*ptr != term) ptr++;
+      if (name != NULL && lorn == ptr - thisname &&
+          STRNCMP_UC_UC(name, thisname, lorn) == 0)
+        return *count;
+      term++;
+      }
+    }
+  }
+
+/* Past any initial parenthesis handling, scan for parentheses or vertical
+bars. Stop if we get to cd->end_pattern. Note that this is important for the
+first-pass call when this value is temporarily adjusted to stop at the current
+position. So DO NOT change this to a test for binary zero. */
+
+for (; ptr < cd->end_pattern; ptr++)
+  {
+  /* Skip over backslashed characters and also entire \Q...\E */
+
+  if (*ptr == CHAR_BACKSLASH)
+    {
+    if (*(++ptr) == 0) goto FAIL_EXIT;
+    if (*ptr == CHAR_Q) for (;;)
+      {
+      while (*(++ptr) != 0 && *ptr != CHAR_BACKSLASH) {};
+      if (*ptr == 0) goto FAIL_EXIT;
+      if (*(++ptr) == CHAR_E) break;
+      }
+    continue;
+    }
+
+  /* Skip over character classes; this logic must be similar to the way they
+  are handled for real. If the first character is '^', skip it. Also, if the
+  first few characters (either before or after ^) are \Q\E or \E we skip them
+  too. This makes for compatibility with Perl. Note the use of STR macros to
+  encode "Q\\E" so that it works in UTF-8 on EBCDIC platforms. */
+
+  if (*ptr == CHAR_LEFT_SQUARE_BRACKET)
+    {
+    BOOL negate_class = FALSE;
+    for (;;)
+      {
+      if (ptr[1] == CHAR_BACKSLASH)
+        {
+        if (ptr[2] == CHAR_E)
+          ptr+= 2;
+        else if (STRNCMP_UC_C8(ptr + 2,
+                 STR_Q STR_BACKSLASH STR_E, 3) == 0)
+          ptr += 4;
+        else
+          break;
+        }
+      else if (!negate_class && ptr[1] == CHAR_CIRCUMFLEX_ACCENT)
+        {
+        negate_class = TRUE;
+        ptr++;
+        }
+      else break;
+      }
+
+    /* If the next character is ']', it is a data character that must be
+    skipped, except in JavaScript compatibility mode. */
+
+    if (ptr[1] == CHAR_RIGHT_SQUARE_BRACKET &&
+        (cd->external_options & PCRE_JAVASCRIPT_COMPAT) == 0)
+      ptr++;
+
+    while (*(++ptr) != CHAR_RIGHT_SQUARE_BRACKET)
+      {
+      if (*ptr == 0) return -1;
+      if (*ptr == CHAR_BACKSLASH)
+        {
+        if (*(++ptr) == 0) goto FAIL_EXIT;
+        if (*ptr == CHAR_Q) for (;;)
+          {
+          while (*(++ptr) != 0 && *ptr != CHAR_BACKSLASH) {};
+          if (*ptr == 0) goto FAIL_EXIT;
+          if (*(++ptr) == CHAR_E) break;
+          }
+        continue;
+        }
+      }
+    continue;
+    }
+
+  /* Skip comments in /x mode */
+
+  if (xmode && *ptr == CHAR_NUMBER_SIGN)
+    {
+    ptr++;
+    while (*ptr != 0)
+      {
+      if (IS_NEWLINE(ptr)) { ptr += cd->nllen - 1; break; }
+      ptr++;
+#ifdef SUPPORT_UTF
+      if (utf) FORWARDCHAR(ptr);
+#endif
+      }
+    if (*ptr == 0) goto FAIL_EXIT;
+    continue;
+    }
+
+  /* Check for the special metacharacters */
+
+  if (*ptr == CHAR_LEFT_PARENTHESIS)
+    {
+    int rc = find_parens_sub(&ptr, cd, name, lorn, xmode, utf, count);
+    if (rc > 0) return rc;
+    if (*ptr == 0) goto FAIL_EXIT;
+    }
+
+  else if (*ptr == CHAR_RIGHT_PARENTHESIS)
+    {
+    if (dup_parens && *count < hwm_count) *count = hwm_count;
+    goto FAIL_EXIT;
+    }
+
+  else if (*ptr == CHAR_VERTICAL_LINE && dup_parens)
+    {
+    if (*count > hwm_count) hwm_count = *count;
+    *count = start_count;
+    }
+  }
+
+FAIL_EXIT:
+*ptrptr = ptr;
+return -1;
+}
+
+
+
+
+/*************************************************
+*       Find forward referenced subpattern       *
+*************************************************/
+
+/* This function scans along a pattern's text looking for capturing
+subpatterns, and counting them. If it finds a named pattern that matches the
+name it is given, it returns its number. Alternatively, if the name is NULL, it
+returns when it reaches a given numbered subpattern. This is used for forward
+references to subpatterns. We used to be able to start this scan from the
+current compiling point, using the current count value from cd->bracount, and
+do it all in a single loop, but the addition of the possibility of duplicate
+subpattern numbers means that we have to scan from the very start, in order to
+take account of such duplicates, and to use a recursive function to keep track
+of the different types of group.
+
+Arguments:
+  cd           compile background data
+  name         name to seek, or NULL if seeking a numbered subpattern
+  lorn         name length, or subpattern number if name is NULL
+  xmode        TRUE if we are in /x mode
+  utf          TRUE if we are in UTF-8 / UTF-16 mode
+
+Returns:       the number of the found subpattern, or -1 if not found
+*/
+
+static int
+find_parens(compile_data *cd, const pcre_uchar *name, int lorn, BOOL xmode,
+  BOOL utf)
+{
+pcre_uchar *ptr = (pcre_uchar *)cd->start_pattern;
+int count = 0;
+int rc;
+
+/* If the pattern does not start with an opening parenthesis, the first call
+to find_parens_sub() will scan right to the end (if necessary). However, if it
+does start with a parenthesis, find_parens_sub() will return when it hits the
+matching closing parens. That is why we have to have a loop. */
+
+for (;;)
+  {
+  rc = find_parens_sub(&ptr, cd, name, lorn, xmode, utf, &count);
+  if (rc > 0 || *ptr++ == 0) break;
+  }
+
+return rc;
+}
+
+
+
+
+/*************************************************
+*      Find first significant op code            *
+*************************************************/
+
+/* This is called by several functions that scan a compiled expression looking
+for a fixed first character, or an anchoring op code etc. It skips over things
+that do not influence this. For some calls, it makes sense to skip negative
+forward and all backward assertions, and also the \b assertion; for others it
+does not.
+
+Arguments:
+  code         pointer to the start of the group
+  skipassert   TRUE if certain assertions are to be skipped
+
+Returns:       pointer to the first significant opcode
+*/
+
+static const pcre_uchar*
+first_significant_code(const pcre_uchar *code, BOOL skipassert)
+{
+for (;;)
+  {
+  switch ((int)*code)
+    {
+    case OP_ASSERT_NOT:
+    case OP_ASSERTBACK:
+    case OP_ASSERTBACK_NOT:
+    if (!skipassert) return code;
+    do code += GET(code, 1); while (*code == OP_ALT);
+    code += PRIV(OP_lengths)[*code];
+    break;
+
+    case OP_WORD_BOUNDARY:
+    case OP_NOT_WORD_BOUNDARY:
+    if (!skipassert) return code;
+    /* Fall through */
+
+    case OP_CALLOUT:
+    case OP_CREF:
+    case OP_NCREF:
+    case OP_RREF:
+    case OP_NRREF:
+    case OP_DEF:
+    code += PRIV(OP_lengths)[*code];
+    break;
+
+    default:
+    return code;
+    }
+  }
+/* Control never reaches here */
+}
+
+
+
+
+/*************************************************
+*        Find the fixed length of a branch       *
+*************************************************/
+
+/* Scan a branch and compute the fixed length of subject that will match it,
+if the length is fixed. This is needed for dealing with backward assertions.
+In UTF8 mode, the result is in characters rather than bytes. The branch is
+temporarily terminated with OP_END when this function is called.
+
+This function is called when a backward assertion is encountered, so that if it
+fails, the error message can point to the correct place in the pattern.
+However, we cannot do this when the assertion contains subroutine calls,
+because they can be forward references. We solve this by remembering this case
+and doing the check at the end; a flag specifies which mode we are running in.
+
+Arguments:
+  code     points to the start of the pattern (the bracket)
+  utf      TRUE in UTF-8 / UTF-16 mode
+  atend    TRUE if called when the pattern is complete
+  cd       the "compile data" structure
+
+Returns:   the fixed length,
+             or -1 if there is no fixed length,
+             or -2 if \C was encountered (in UTF-8 mode only)
+             or -3 if an OP_RECURSE item was encountered and atend is FALSE
+             or -4 if an unknown opcode was encountered (internal error)
+*/
+
+static int
+find_fixedlength(pcre_uchar *code, BOOL utf, BOOL atend, compile_data *cd)
+{
+int length = -1;
+
+register int branchlength = 0;
+register pcre_uchar *cc = code + 1 + LINK_SIZE;
+
+/* Scan along the opcodes for this branch. If we get to the end of the
+branch, check the length against that of the other branches. */
+
+for (;;)
+  {
+  int d;
+  pcre_uchar *ce, *cs;
+  register int op = *cc;
+
+  switch (op)
+    {
+    /* We only need to continue for OP_CBRA (normal capturing bracket) and
+    OP_BRA (normal non-capturing bracket) because the other variants of these
+    opcodes are all concerned with unlimited repeated groups, which of course
+    are not of fixed length. */
+
+    case OP_CBRA:
+    case OP_BRA:
+    case OP_ONCE:
+    case OP_ONCE_NC:
+    case OP_COND:
+    d = find_fixedlength(cc + ((op == OP_CBRA)? IMM2_SIZE : 0), utf, atend, cd);
+    if (d < 0) return d;
+    branchlength += d;
+    do cc += GET(cc, 1); while (*cc == OP_ALT);
+    cc += 1 + LINK_SIZE;
+    break;
+
+    /* Reached end of a branch; if it's a ket it is the end of a nested call.
+    If it's ALT it is an alternation in a nested call. An ACCEPT is effectively
+    an ALT. If it is END it's the end of the outer call. All can be handled by
+    the same code. Note that we must not include the OP_KETRxxx opcodes here,
+    because they all imply an unlimited repeat. */
+
+    case OP_ALT:
+    case OP_KET:
+    case OP_END:
+    case OP_ACCEPT:
+    case OP_ASSERT_ACCEPT:
+    if (length < 0) length = branchlength;
+      else if (length != branchlength) return -1;
+    if (*cc != OP_ALT) return length;
+    cc += 1 + LINK_SIZE;
+    branchlength = 0;
+    break;
+
+    /* A true recursion implies not fixed length, but a subroutine call may
+    be OK. If the subroutine is a forward reference, we can't deal with
+    it until the end of the pattern, so return -3. */
+
+    case OP_RECURSE:
+    if (!atend) return -3;
+    cs = ce = (pcre_uchar *)cd->start_code + GET(cc, 1);  /* Start subpattern */
+    do ce += GET(ce, 1); while (*ce == OP_ALT);           /* End subpattern */
+    if (cc > cs && cc < ce) return -1;                    /* Recursion */
+    d = find_fixedlength(cs + IMM2_SIZE, utf, atend, cd);
+    if (d < 0) return d;
+    branchlength += d;
+    cc += 1 + LINK_SIZE;
+    break;
+
+    /* Skip over assertive subpatterns */
+
+    case OP_ASSERT:
+    case OP_ASSERT_NOT:
+    case OP_ASSERTBACK:
+    case OP_ASSERTBACK_NOT:
+    do cc += GET(cc, 1); while (*cc == OP_ALT);
+    cc += PRIV(OP_lengths)[*cc];
+    break;
+
+    /* Skip over things that don't match chars */
+
+    case OP_MARK:
+    case OP_PRUNE_ARG:
+    case OP_SKIP_ARG:
+    case OP_THEN_ARG:
+    cc += cc[1] + PRIV(OP_lengths)[*cc];
+    break;
+
+    case OP_CALLOUT:
+    case OP_CIRC:
+    case OP_CIRCM:
+    case OP_CLOSE:
+    case OP_COMMIT:
+    case OP_CREF:
+    case OP_DEF:
+    case OP_DOLL:
+    case OP_DOLLM:
+    case OP_EOD:
+    case OP_EODN:
+    case OP_FAIL:
+    case OP_NCREF:
+    case OP_NRREF:
+    case OP_NOT_WORD_BOUNDARY:
+    case OP_PRUNE:
+    case OP_REVERSE:
+    case OP_RREF:
+    case OP_SET_SOM:
+    case OP_SKIP:
+    case OP_SOD:
+    case OP_SOM:
+    case OP_THEN:
+    case OP_WORD_BOUNDARY:
+    cc += PRIV(OP_lengths)[*cc];
+    break;
+
+    /* Handle literal characters */
+
+    case OP_CHAR:
+    case OP_CHARI:
+    case OP_NOT:
+    case OP_NOTI:
+    branchlength++;
+    cc += 2;
+#ifdef SUPPORT_UTF
+    if (utf && HAS_EXTRALEN(cc[-1])) cc += GET_EXTRALEN(cc[-1]);
+#endif
+    break;
+
+    /* Handle exact repetitions. The count is already in characters, but we
+    need to skip over a multibyte character in UTF8 mode.  */
+
+    case OP_EXACT:
+    case OP_EXACTI:
+    case OP_NOTEXACT:
+    case OP_NOTEXACTI:
+    branchlength += GET2(cc,1);
+    cc += 2 + IMM2_SIZE;
+#ifdef SUPPORT_UTF
+    if (utf && HAS_EXTRALEN(cc[-1])) cc += GET_EXTRALEN(cc[-1]);
+#endif
+    break;
+
+    case OP_TYPEEXACT:
+    branchlength += GET2(cc,1);
+    if (cc[1 + IMM2_SIZE] == OP_PROP || cc[1 + IMM2_SIZE] == OP_NOTPROP) cc += 2;
+    cc += 1 + IMM2_SIZE + 1;
+    break;
+
+    /* Handle single-char matchers */
+
+    case OP_PROP:
+    case OP_NOTPROP:
+    cc += 2;
+    /* Fall through */
+
+    case OP_HSPACE:
+    case OP_VSPACE:
+    case OP_NOT_HSPACE:
+    case OP_NOT_VSPACE:
+    case OP_NOT_DIGIT:
+    case OP_DIGIT:
+    case OP_NOT_WHITESPACE:
+    case OP_WHITESPACE:
+    case OP_NOT_WORDCHAR:
+    case OP_WORDCHAR:
+    case OP_ANY:
+    case OP_ALLANY:
+    branchlength++;
+    cc++;
+    break;
+
+    /* The single-byte matcher isn't allowed. This only happens in UTF-8 mode;
+    otherwise \C is coded as OP_ALLANY. */
+
+    case OP_ANYBYTE:
+    return -2;
+
+    /* Check a class for variable quantification */
+
+#if defined SUPPORT_UTF || defined COMPILE_PCRE16
+    case OP_XCLASS:
+    cc += GET(cc, 1) - PRIV(OP_lengths)[OP_CLASS];
+    /* Fall through */
+#endif
+
+    case OP_CLASS:
+    case OP_NCLASS:
+    cc += PRIV(OP_lengths)[OP_CLASS];
+
+    switch (*cc)
+      {
+      case OP_CRPLUS:
+      case OP_CRMINPLUS:
+      case OP_CRSTAR:
+      case OP_CRMINSTAR:
+      case OP_CRQUERY:
+      case OP_CRMINQUERY:
+      return -1;
+
+      case OP_CRRANGE:
+      case OP_CRMINRANGE:
+      if (GET2(cc,1) != GET2(cc,1+IMM2_SIZE)) return -1;
+      branchlength += GET2(cc,1);
+      cc += 1 + 2 * IMM2_SIZE;
+      break;
+
+      default:
+      branchlength++;
+      }
+    break;
+
+    /* Anything else is variable length */
+
+    case OP_ANYNL:
+    case OP_BRAMINZERO:
+    case OP_BRAPOS:
+    case OP_BRAPOSZERO:
+    case OP_BRAZERO:
+    case OP_CBRAPOS:
+    case OP_EXTUNI:
+    case OP_KETRMAX:
+    case OP_KETRMIN:
+    case OP_KETRPOS:
+    case OP_MINPLUS:
+    case OP_MINPLUSI:
+    case OP_MINQUERY:
+    case OP_MINQUERYI:
+    case OP_MINSTAR:
+    case OP_MINSTARI:
+    case OP_MINUPTO:
+    case OP_MINUPTOI:
+    case OP_NOTMINPLUS:
+    case OP_NOTMINPLUSI:
+    case OP_NOTMINQUERY:
+    case OP_NOTMINQUERYI:
+    case OP_NOTMINSTAR:
+    case OP_NOTMINSTARI:
+    case OP_NOTMINUPTO:
+    case OP_NOTMINUPTOI:
+    case OP_NOTPLUS:
+    case OP_NOTPLUSI:
+    case OP_NOTPOSPLUS:
+    case OP_NOTPOSPLUSI:
+    case OP_NOTPOSQUERY:
+    case OP_NOTPOSQUERYI:
+    case OP_NOTPOSSTAR:
+    case OP_NOTPOSSTARI:
+    case OP_NOTPOSUPTO:
+    case OP_NOTPOSUPTOI:
+    case OP_NOTQUERY:
+    case OP_NOTQUERYI:
+    case OP_NOTSTAR:
+    case OP_NOTSTARI:
+    case OP_NOTUPTO:
+    case OP_NOTUPTOI:
+    case OP_PLUS:
+    case OP_PLUSI:
+    case OP_POSPLUS:
+    case OP_POSPLUSI:
+    case OP_POSQUERY:
+    case OP_POSQUERYI:
+    case OP_POSSTAR:
+    case OP_POSSTARI:
+    case OP_POSUPTO:
+    case OP_POSUPTOI:
+    case OP_QUERY:
+    case OP_QUERYI:
+    case OP_REF:
+    case OP_REFI:
+    case OP_SBRA:
+    case OP_SBRAPOS:
+    case OP_SCBRA:
+    case OP_SCBRAPOS:
+    case OP_SCOND:
+    case OP_SKIPZERO:
+    case OP_STAR:
+    case OP_STARI:
+    case OP_TYPEMINPLUS:
+    case OP_TYPEMINQUERY:
+    case OP_TYPEMINSTAR:
+    case OP_TYPEMINUPTO:
+    case OP_TYPEPLUS:
+    case OP_TYPEPOSPLUS:
+    case OP_TYPEPOSQUERY:
+    case OP_TYPEPOSSTAR:
+    case OP_TYPEPOSUPTO:
+    case OP_TYPEQUERY:
+    case OP_TYPESTAR:
+    case OP_TYPEUPTO:
+    case OP_UPTO:
+    case OP_UPTOI:
+    return -1;
+
+    /* Catch unrecognized opcodes so that when new ones are added they
+    are not forgotten, as has happened in the past. */
+
+    default:
+    return -4;
+    }
+  }
+/* Control never gets here */
+}
+
+
+
+
+/*************************************************
+*    Scan compiled regex for specific bracket    *
+*************************************************/
+
+/* This little function scans through a compiled pattern until it finds a
+capturing bracket with the given number, or, if the number is negative, an
+instance of OP_REVERSE for a lookbehind. The function is global in the C sense
+so that it can be called from pcre_study() when finding the minimum matching
+length.
+
+Arguments:
+  code        points to start of expression
+  utf         TRUE in UTF-8 / UTF-16 mode
+  number      the required bracket number or negative to find a lookbehind
+
+Returns:      pointer to the opcode for the bracket, or NULL if not found
+*/
+
+const pcre_uchar *
+PRIV(find_bracket)(const pcre_uchar *code, BOOL utf, int number)
+{
+for (;;)
+  {
+  register int c = *code;
+
+  if (c == OP_END) return NULL;
+
+  /* XCLASS is used for classes that cannot be represented just by a bit
+  map. This includes negated single high-valued characters. The length in
+  the table is zero; the actual length is stored in the compiled code. */
+
+  if (c == OP_XCLASS) code += GET(code, 1);
+
+  /* Handle recursion */
+
+  else if (c == OP_REVERSE)
+    {
+    if (number < 0) return (pcre_uchar *)code;
+    code += PRIV(OP_lengths)[c];
+    }
+
+  /* Handle capturing bracket */
+
+  else if (c == OP_CBRA || c == OP_SCBRA ||
+           c == OP_CBRAPOS || c == OP_SCBRAPOS)
+    {
+    int n = GET2(code, 1+LINK_SIZE);
+    if (n == number) return (pcre_uchar *)code;
+    code += PRIV(OP_lengths)[c];
+    }
+
+  /* Otherwise, we can get the item's length from the table, except that for
+  repeated character types, we have to test for \p and \P, which have an extra
+  two bytes of parameters, and for MARK/PRUNE/SKIP/THEN with an argument, we
+  must add in its length. */
+
+  else
+    {
+    switch(c)
+      {
+      case OP_TYPESTAR:
+      case OP_TYPEMINSTAR:
+      case OP_TYPEPLUS:
+      case OP_TYPEMINPLUS:
+      case OP_TYPEQUERY:
+      case OP_TYPEMINQUERY:
+      case OP_TYPEPOSSTAR:
+      case OP_TYPEPOSPLUS:
+      case OP_TYPEPOSQUERY:
+      if (code[1] == OP_PROP || code[1] == OP_NOTPROP) code += 2;
+      break;
+
+      case OP_TYPEUPTO:
+      case OP_TYPEMINUPTO:
+      case OP_TYPEEXACT:
+      case OP_TYPEPOSUPTO:
+      if (code[1 + IMM2_SIZE] == OP_PROP
+        || code[1 + IMM2_SIZE] == OP_NOTPROP) code += 2;
+      break;
+
+      case OP_MARK:
+      case OP_PRUNE_ARG:
+      case OP_SKIP_ARG:
+      code += code[1];
+      break;
+
+      case OP_THEN_ARG:
+      code += code[1];
+      break;
+      }
+
+    /* Add in the fixed length from the table */
+
+    code += PRIV(OP_lengths)[c];
+
+  /* In UTF-8 mode, opcodes that are followed by a character may be followed by
+  a multi-byte character. The length in the table is a minimum, so we have to
+  arrange to skip the extra bytes. */
+
+#ifdef SUPPORT_UTF
+    if (utf) switch(c)
+      {
+      case OP_CHAR:
+      case OP_CHARI:
+      case OP_EXACT:
+      case OP_EXACTI:
+      case OP_UPTO:
+      case OP_UPTOI:
+      case OP_MINUPTO:
+      case OP_MINUPTOI:
+      case OP_POSUPTO:
+      case OP_POSUPTOI:
+      case OP_STAR:
+      case OP_STARI:
+      case OP_MINSTAR:
+      case OP_MINSTARI:
+      case OP_POSSTAR:
+      case OP_POSSTARI:
+      case OP_PLUS:
+      case OP_PLUSI:
+      case OP_MINPLUS:
+      case OP_MINPLUSI:
+      case OP_POSPLUS:
+      case OP_POSPLUSI:
+      case OP_QUERY:
+      case OP_QUERYI:
+      case OP_MINQUERY:
+      case OP_MINQUERYI:
+      case OP_POSQUERY:
+      case OP_POSQUERYI:
+      if (HAS_EXTRALEN(code[-1])) code += GET_EXTRALEN(code[-1]);
+      break;
+      }
+#else
+    (void)(utf);  /* Keep compiler happy by referencing function argument */
+#endif
+    }
+  }
+}
+
+
+
+/*************************************************
+*   Scan compiled regex for recursion reference  *
+*************************************************/
+
+/* This little function scans through a compiled pattern until it finds an
+instance of OP_RECURSE.
+
+Arguments:
+  code        points to start of expression
+  utf         TRUE in UTF-8 / UTF-16 mode
+
+Returns:      pointer to the opcode for OP_RECURSE, or NULL if not found
+*/
+
+static const pcre_uchar *
+find_recurse(const pcre_uchar *code, BOOL utf)
+{
+for (;;)
+  {
+  register int c = *code;
+  if (c == OP_END) return NULL;
+  if (c == OP_RECURSE) return code;
+
+  /* XCLASS is used for classes that cannot be represented just by a bit
+  map. This includes negated single high-valued characters. The length in
+  the table is zero; the actual length is stored in the compiled code. */
+
+  if (c == OP_XCLASS) code += GET(code, 1);
+
+  /* Otherwise, we can get the item's length from the table, except that for
+  repeated character types, we have to test for \p and \P, which have an extra
+  two bytes of parameters, and for MARK/PRUNE/SKIP/THEN with an argument, we
+  must add in its length. */
+
+  else
+    {
+    switch(c)
+      {
+      case OP_TYPESTAR:
+      case OP_TYPEMINSTAR:
+      case OP_TYPEPLUS:
+      case OP_TYPEMINPLUS:
+      case OP_TYPEQUERY:
+      case OP_TYPEMINQUERY:
+      case OP_TYPEPOSSTAR:
+      case OP_TYPEPOSPLUS:
+      case OP_TYPEPOSQUERY:
+      if (code[1] == OP_PROP || code[1] == OP_NOTPROP) code += 2;
+      break;
+
+      case OP_TYPEPOSUPTO:
+      case OP_TYPEUPTO:
+      case OP_TYPEMINUPTO:
+      case OP_TYPEEXACT:
+      if (code[1 + IMM2_SIZE] == OP_PROP
+        || code[1 + IMM2_SIZE] == OP_NOTPROP) code += 2;
+      break;
+
+      case OP_MARK:
+      case OP_PRUNE_ARG:
+      case OP_SKIP_ARG:
+      code += code[1];
+      break;
+
+      case OP_THEN_ARG:
+      code += code[1];
+      break;
+      }
+
+    /* Add in the fixed length from the table */
+
+    code += PRIV(OP_lengths)[c];
+
+    /* In UTF-8 mode, opcodes that are followed by a character may be followed
+    by a multi-byte character. The length in the table is a minimum, so we have
+    to arrange to skip the extra bytes. */
+
+#ifdef SUPPORT_UTF
+    if (utf) switch(c)
+      {
+      case OP_CHAR:
+      case OP_CHARI:
+      case OP_NOT:
+      case OP_NOTI:
+      case OP_EXACT:
+      case OP_EXACTI:
+      case OP_NOTEXACT:
+      case OP_NOTEXACTI:
+      case OP_UPTO:
+      case OP_UPTOI:
+      case OP_NOTUPTO:
+      case OP_NOTUPTOI:
+      case OP_MINUPTO:
+      case OP_MINUPTOI:
+      case OP_NOTMINUPTO:
+      case OP_NOTMINUPTOI:
+      case OP_POSUPTO:
+      case OP_POSUPTOI:
+      case OP_NOTPOSUPTO:
+      case OP_NOTPOSUPTOI:
+      case OP_STAR:
+      case OP_STARI:
+      case OP_NOTSTAR:
+      case OP_NOTSTARI:
+      case OP_MINSTAR:
+      case OP_MINSTARI:
+      case OP_NOTMINSTAR:
+      case OP_NOTMINSTARI:
+      case OP_POSSTAR:
+      case OP_POSSTARI:
+      case OP_NOTPOSSTAR:
+      case OP_NOTPOSSTARI:
+      case OP_PLUS:
+      case OP_PLUSI:
+      case OP_NOTPLUS:
+      case OP_NOTPLUSI:
+      case OP_MINPLUS:
+      case OP_MINPLUSI:
+      case OP_NOTMINPLUS:
+      case OP_NOTMINPLUSI:
+      case OP_POSPLUS:
+      case OP_POSPLUSI:
+      case OP_NOTPOSPLUS:
+      case OP_NOTPOSPLUSI:
+      case OP_QUERY:
+      case OP_QUERYI:
+      case OP_NOTQUERY:
+      case OP_NOTQUERYI:
+      case OP_MINQUERY:
+      case OP_MINQUERYI:
+      case OP_NOTMINQUERY:
+      case OP_NOTMINQUERYI:
+      case OP_POSQUERY:
+      case OP_POSQUERYI:
+      case OP_NOTPOSQUERY:
+      case OP_NOTPOSQUERYI:
+      if (HAS_EXTRALEN(code[-1])) code += GET_EXTRALEN(code[-1]);
+      break;
+      }
+#else
+    (void)(utf);  /* Keep compiler happy by referencing function argument */
+#endif
+    }
+  }
+}
+
+
+
+/*************************************************
+*    Scan compiled branch for non-emptiness      *
+*************************************************/
+
+/* This function scans through a branch of a compiled pattern to see whether it
+can match the empty string or not. It is called from could_be_empty()
+below and from compile_branch() when checking for an unlimited repeat of a
+group that can match nothing. Note that first_significant_code() skips over
+backward and negative forward assertions when its final argument is TRUE. If we
+hit an unclosed bracket, we return "empty" - this means we've struck an inner
+bracket whose current branch will already have been scanned.
+
+Arguments:
+  code        points to start of search
+  endcode     points to where to stop
+  utf         TRUE if in UTF-8 / UTF-16 mode
+  cd          contains pointers to tables etc.
+
+Returns:      TRUE if what is matched could be empty
+*/
+
+static BOOL
+could_be_empty_branch(const pcre_uchar *code, const pcre_uchar *endcode,
+  BOOL utf, compile_data *cd)
+{
+register int c;
+for (code = first_significant_code(code + PRIV(OP_lengths)[*code], TRUE);
+     code < endcode;
+     code = first_significant_code(code + PRIV(OP_lengths)[c], TRUE))
+  {
+  const pcre_uchar *ccode;
+
+  c = *code;
+
+  /* Skip over forward assertions; the other assertions are skipped by
+  first_significant_code() with a TRUE final argument. */
+
+  if (c == OP_ASSERT)
+    {
+    do code += GET(code, 1); while (*code == OP_ALT);
+    c = *code;
+    continue;
+    }
+
+  /* For a recursion/subroutine call, if its end has been reached, which
+  implies a backward reference subroutine call, we can scan it. If it's a
+  forward reference subroutine call, we can't. To detect forward reference
+  we have to scan up the list that is kept in the workspace. This function is
+  called only when doing the real compile, not during the pre-compile that
+  measures the size of the compiled pattern. */
+
+  if (c == OP_RECURSE)
+    {
+    const pcre_uchar *scode;
+    BOOL empty_branch;
+
+    /* Test for forward reference */
+
+    for (scode = cd->start_workspace; scode < cd->hwm; scode += LINK_SIZE)
+      if (GET(scode, 0) == code + 1 - cd->start_code) return TRUE;
+
+    /* Not a forward reference, test for completed backward reference */
+
+    empty_branch = FALSE;
+    scode = cd->start_code + GET(code, 1);
+    if (GET(scode, 1) == 0) return TRUE;    /* Unclosed */
+
+    /* Completed backwards reference */
+
+    do
+      {
+      if (could_be_empty_branch(scode, endcode, utf, cd))
+        {
+        empty_branch = TRUE;
+        break;
+        }
+      scode += GET(scode, 1);
+      }
+    while (*scode == OP_ALT);
+
+    if (!empty_branch) return FALSE;  /* All branches are non-empty */
+    continue;
+    }
+
+  /* Groups with zero repeats can of course be empty; skip them. */
+
+  if (c == OP_BRAZERO || c == OP_BRAMINZERO || c == OP_SKIPZERO ||
+      c == OP_BRAPOSZERO)
+    {
+    code += PRIV(OP_lengths)[c];
+    do code += GET(code, 1); while (*code == OP_ALT);
+    c = *code;
+    continue;
+    }
+
+  /* A nested group that is already marked as "could be empty" can just be
+  skipped. */
+
+  if (c == OP_SBRA  || c == OP_SBRAPOS ||
+      c == OP_SCBRA || c == OP_SCBRAPOS)
+    {
+    do code += GET(code, 1); while (*code == OP_ALT);
+    c = *code;
+    continue;
+    }
+
+  /* For other groups, scan the branches. */
+
+  if (c == OP_BRA  || c == OP_BRAPOS ||
+      c == OP_CBRA || c == OP_CBRAPOS ||
+      c == OP_ONCE || c == OP_ONCE_NC ||
+      c == OP_COND)
+    {
+    BOOL empty_branch;
+    if (GET(code, 1) == 0) return TRUE;    /* Hit unclosed bracket */
+
+    /* If a conditional group has only one branch, there is a second, implied,
+    empty branch, so just skip over the conditional, because it could be empty.
+    Otherwise, scan the individual branches of the group. */
+
+    if (c == OP_COND && code[GET(code, 1)] != OP_ALT)
+      code += GET(code, 1);
+    else
+      {
+      empty_branch = FALSE;
+      do
+        {
+        if (!empty_branch && could_be_empty_branch(code, endcode, utf, cd))
+          empty_branch = TRUE;
+        code += GET(code, 1);
+        }
+      while (*code == OP_ALT);
+      if (!empty_branch) return FALSE;   /* All branches are non-empty */
+      }
+
+    c = *code;
+    continue;
+    }
+
+  /* Handle the other opcodes */
+
+  switch (c)
+    {
+    /* Check for quantifiers after a class. XCLASS is used for classes that
+    cannot be represented just by a bit map. This includes negated single
+    high-valued characters. The length in PRIV(OP_lengths)[] is zero; the
+    actual length is stored in the compiled code, so we must update "code"
+    here. */
+
+#if defined SUPPORT_UTF || !defined COMPILE_PCRE8
+    case OP_XCLASS:
+    ccode = code += GET(code, 1);
+    goto CHECK_CLASS_REPEAT;
+#endif
+
+    case OP_CLASS:
+    case OP_NCLASS:
+    ccode = code + PRIV(OP_lengths)[OP_CLASS];
+
+#if defined SUPPORT_UTF || !defined COMPILE_PCRE8
+    CHECK_CLASS_REPEAT:
+#endif
+
+    switch (*ccode)
+      {
+      case OP_CRSTAR:            /* These could be empty; continue */
+      case OP_CRMINSTAR:
+      case OP_CRQUERY:
+      case OP_CRMINQUERY:
+      break;
+
+      default:                   /* Non-repeat => class must match */
+      case OP_CRPLUS:            /* These repeats aren't empty */
+      case OP_CRMINPLUS:
+      return FALSE;
+
+      case OP_CRRANGE:
+      case OP_CRMINRANGE:
+      if (GET2(ccode, 1) > 0) return FALSE;  /* Minimum > 0 */
+      break;
+      }
+    break;
+
+    /* Opcodes that must match a character */
+
+    case OP_PROP:
+    case OP_NOTPROP:
+    case OP_EXTUNI:
+    case OP_NOT_DIGIT:
+    case OP_DIGIT:
+    case OP_NOT_WHITESPACE:
+    case OP_WHITESPACE:
+    case OP_NOT_WORDCHAR:
+    case OP_WORDCHAR:
+    case OP_ANY:
+    case OP_ALLANY:
+    case OP_ANYBYTE:
+    case OP_CHAR:
+    case OP_CHARI:
+    case OP_NOT:
+    case OP_NOTI:
+    case OP_PLUS:
+    case OP_MINPLUS:
+    case OP_POSPLUS:
+    case OP_EXACT:
+    case OP_NOTPLUS:
+    case OP_NOTMINPLUS:
+    case OP_NOTPOSPLUS:
+    case OP_NOTEXACT:
+    case OP_TYPEPLUS:
+    case OP_TYPEMINPLUS:
+    case OP_TYPEPOSPLUS:
+    case OP_TYPEEXACT:
+    return FALSE;
+
+    /* These are going to continue, as they may be empty, but we have to
+    fudge the length for the \p and \P cases. */
+
+    case OP_TYPESTAR:
+    case OP_TYPEMINSTAR:
+    case OP_TYPEPOSSTAR:
+    case OP_TYPEQUERY:
+    case OP_TYPEMINQUERY:
+    case OP_TYPEPOSQUERY:
+    if (code[1] == OP_PROP || code[1] == OP_NOTPROP) code += 2;
+    break;
+
+    /* Same for these */
+
+    case OP_TYPEUPTO:
+    case OP_TYPEMINUPTO:
+    case OP_TYPEPOSUPTO:
+    if (code[1 + IMM2_SIZE] == OP_PROP
+      || code[1 + IMM2_SIZE] == OP_NOTPROP) code += 2;
+    break;
+
+    /* End of branch */
+
+    case OP_KET:
+    case OP_KETRMAX:
+    case OP_KETRMIN:
+    case OP_KETRPOS:
+    case OP_ALT:
+    return TRUE;
+
+    /* In UTF-8 mode, STAR, MINSTAR, POSSTAR, QUERY, MINQUERY, POSQUERY, UPTO,
+    MINUPTO, and POSUPTO may be followed by a multibyte character */
+
+#ifdef SUPPORT_UTF
+    case OP_STAR:
+    case OP_STARI:
+    case OP_MINSTAR:
+    case OP_MINSTARI:
+    case OP_POSSTAR:
+    case OP_POSSTARI:
+    case OP_QUERY:
+    case OP_QUERYI:
+    case OP_MINQUERY:
+    case OP_MINQUERYI:
+    case OP_POSQUERY:
+    case OP_POSQUERYI:
+    if (utf && HAS_EXTRALEN(code[1])) code += GET_EXTRALEN(code[1]);
+    break;
+
+    case OP_UPTO:
+    case OP_UPTOI:
+    case OP_MINUPTO:
+    case OP_MINUPTOI:
+    case OP_POSUPTO:
+    case OP_POSUPTOI:
+    if (utf && HAS_EXTRALEN(code[1 + IMM2_SIZE])) code += GET_EXTRALEN(code[1 + IMM2_SIZE]);
+    break;
+#endif
+
+    /* MARK, and PRUNE/SKIP/THEN with an argument must skip over the argument
+    string. */
+
+    case OP_MARK:
+    case OP_PRUNE_ARG:
+    case OP_SKIP_ARG:
+    code += code[1];
+    break;
+
+    case OP_THEN_ARG:
+    code += code[1];
+    break;
+
+    /* None of the remaining opcodes are required to match a character. */
+
+    default:
+    break;
+    }
+  }
+
+return TRUE;
+}
+
+
+
+/*************************************************
+*    Scan compiled regex for non-emptiness       *
+*************************************************/
+
+/* This function is called to check for left recursive calls. We want to check
+the current branch of the current pattern to see if it could match the empty
+string. If it could, we must look outwards for branches at other levels,
+stopping when we pass beyond the bracket which is the subject of the recursion.
+This function is called only during the real compile, not during the
+pre-compile.
+
+Arguments:
+  code        points to start of the recursion
+  endcode     points to where to stop (current RECURSE item)
+  bcptr       points to the chain of current (unclosed) branch starts
+  utf         TRUE if in UTF-8 / UTF-16 mode
+  cd          pointers to tables etc
+
+Returns:      TRUE if what is matched could be empty
+*/
+
+static BOOL
+could_be_empty(const pcre_uchar *code, const pcre_uchar *endcode,
+  branch_chain *bcptr, BOOL utf, compile_data *cd)
+{
+while (bcptr != NULL && bcptr->current_branch >= code)
+  {
+  if (!could_be_empty_branch(bcptr->current_branch, endcode, utf, cd))
+    return FALSE;
+  bcptr = bcptr->outer;
+  }
+return TRUE;
+}
+
+
+
+/*************************************************
+*           Check for POSIX class syntax         *
+*************************************************/
+
+/* This function is called when the sequence "[:" or "[." or "[=" is
+encountered in a character class. It checks whether this is followed by a
+sequence of characters terminated by a matching ":]" or ".]" or "=]". If we
+reach an unescaped ']' without the special preceding character, return FALSE.
+
+Originally, this function only recognized a sequence of letters between the
+terminators, but it seems that Perl recognizes any sequence of characters,
+though of course unknown POSIX names are subsequently rejected. Perl gives an
+"Unknown POSIX class" error for [:f\oo:] for example, where previously PCRE
+didn't consider this to be a POSIX class. Likewise for [:1234:].
+
+The problem in trying to be exactly like Perl is in the handling of escapes. We
+have to be sure that [abc[:x\]pqr] is *not* treated as containing a POSIX
+class, but [abc[:x\]pqr:]] is (so that an error can be generated). The code
+below handles the special case of \], but does not try to do any other escape
+processing. This makes it different from Perl for cases such as [:l\ower:]
+where Perl recognizes it as the POSIX class "lower" but PCRE does not recognize
+"l\ower". This is a lesser evil that not diagnosing bad classes when Perl does,
+I think.
+
+A user pointed out that PCRE was rejecting [:a[:digit:]] whereas Perl was not.
+It seems that the appearance of a nested POSIX class supersedes an apparent
+external class. For example, [:a[:digit:]b:] matches "a", "b", ":", or
+a digit.
+
+In Perl, unescaped square brackets may also appear as part of class names. For
+example, [:a[:abc]b:] gives unknown POSIX class "[:abc]b:]". However, for
+[:a[:abc]b][b:] it gives unknown POSIX class "[:abc]b][b:]", which does not
+seem right at all. PCRE does not allow closing square brackets in POSIX class
+names.
+
+Arguments:
+  ptr      pointer to the initial [
+  endptr   where to return the end pointer
+
+Returns:   TRUE or FALSE
+*/
+
+static BOOL
+check_posix_syntax(const pcre_uchar *ptr, const pcre_uchar **endptr)
+{
+int terminator;          /* Don't combine these lines; the Solaris cc */
+terminator = *(++ptr);   /* compiler warns about "non-constant" initializer. */
+for (++ptr; *ptr != 0; ptr++)
+  {
+  if (*ptr == CHAR_BACKSLASH && ptr[1] == CHAR_RIGHT_SQUARE_BRACKET)
+    ptr++;
+  else if (*ptr == CHAR_RIGHT_SQUARE_BRACKET) return FALSE;
+  else
+    {
+    if (*ptr == terminator && ptr[1] == CHAR_RIGHT_SQUARE_BRACKET)
+      {
+      *endptr = ptr;
+      return TRUE;
+      }
+    if (*ptr == CHAR_LEFT_SQUARE_BRACKET &&
+         (ptr[1] == CHAR_COLON || ptr[1] == CHAR_DOT ||
+          ptr[1] == CHAR_EQUALS_SIGN) &&
+        check_posix_syntax(ptr, endptr))
+      return FALSE;
+    }
+  }
+return FALSE;
+}
+
+
+
+
+/*************************************************
+*          Check POSIX class name                *
+*************************************************/
+
+/* This function is called to check the name given in a POSIX-style class entry
+such as [:alnum:].
+
+Arguments:
+  ptr        points to the first letter
+  len        the length of the name
+
+Returns:     a value representing the name, or -1 if unknown
+*/
+
+static int
+check_posix_name(const pcre_uchar *ptr, int len)
+{
+const char *pn = posix_names;
+register int yield = 0;
+while (posix_name_lengths[yield] != 0)
+  {
+  if (len == posix_name_lengths[yield] &&
+    STRNCMP_UC_C8(ptr, pn, len) == 0) return yield;
+  pn += posix_name_lengths[yield] + 1;
+  yield++;
+  }
+return -1;
+}
+
+
+/*************************************************
+*    Adjust OP_RECURSE items in repeated group   *
+*************************************************/
+
+/* OP_RECURSE items contain an offset from the start of the regex to the group
+that is referenced. This means that groups can be replicated for fixed
+repetition simply by copying (because the recursion is allowed to refer to
+earlier groups that are outside the current group). However, when a group is
+optional (i.e. the minimum quantifier is zero), OP_BRAZERO or OP_SKIPZERO is
+inserted before it, after it has been compiled. This means that any OP_RECURSE
+items within it that refer to the group itself or any contained groups have to
+have their offsets adjusted. That one of the jobs of this function. Before it
+is called, the partially compiled regex must be temporarily terminated with
+OP_END.
+
+This function has been extended with the possibility of forward references for
+recursions and subroutine calls. It must also check the list of such references
+for the group we are dealing with. If it finds that one of the recursions in
+the current group is on this list, it adjusts the offset in the list, not the
+value in the reference (which is a group number).
+
+Arguments:
+  group      points to the start of the group
+  adjust     the amount by which the group is to be moved
+  utf        TRUE in UTF-8 / UTF-16 mode
+  cd         contains pointers to tables etc.
+  save_hwm   the hwm forward reference pointer at the start of the group
+
+Returns:     nothing
+*/
+
+static void
+adjust_recurse(pcre_uchar *group, int adjust, BOOL utf, compile_data *cd,
+  pcre_uchar *save_hwm)
+{
+pcre_uchar *ptr = group;
+
+while ((ptr = (pcre_uchar *)find_recurse(ptr, utf)) != NULL)
+  {
+  int offset;
+  pcre_uchar *hc;
+
+  /* See if this recursion is on the forward reference list. If so, adjust the
+  reference. */
+
+  for (hc = save_hwm; hc < cd->hwm; hc += LINK_SIZE)
+    {
+    offset = GET(hc, 0);
+    if (cd->start_code + offset == ptr + 1)
+      {
+      PUT(hc, 0, offset + adjust);
+      break;
+      }
+    }
+
+  /* Otherwise, adjust the recursion offset if it's after the start of this
+  group. */
+
+  if (hc >= cd->hwm)
+    {
+    offset = GET(ptr, 1);
+    if (cd->start_code + offset >= group) PUT(ptr, 1, offset + adjust);
+    }
+
+  ptr += 1 + LINK_SIZE;
+  }
+}
+
+
+
+/*************************************************
+*        Insert an automatic callout point       *
+*************************************************/
+
+/* This function is called when the PCRE_AUTO_CALLOUT option is set, to insert
+callout points before each pattern item.
+
+Arguments:
+  code           current code pointer
+  ptr            current pattern pointer
+  cd             pointers to tables etc
+
+Returns:         new code pointer
+*/
+
+static pcre_uchar *
+auto_callout(pcre_uchar *code, const pcre_uchar *ptr, compile_data *cd)
+{
+*code++ = OP_CALLOUT;
+*code++ = 255;
+PUT(code, 0, (int)(ptr - cd->start_pattern));  /* Pattern offset */
+PUT(code, LINK_SIZE, 0);                       /* Default length */
+return code + 2 * LINK_SIZE;
+}
+
+
+
+/*************************************************
+*         Complete a callout item                *
+*************************************************/
+
+/* A callout item contains the length of the next item in the pattern, which
+we can't fill in till after we have reached the relevant point. This is used
+for both automatic and manual callouts.
+
+Arguments:
+  previous_callout   points to previous callout item
+  ptr                current pattern pointer
+  cd                 pointers to tables etc
+
+Returns:             nothing
+*/
+
+static void
+complete_callout(pcre_uchar *previous_callout, const pcre_uchar *ptr, compile_data *cd)
+{
+int length = (int)(ptr - cd->start_pattern - GET(previous_callout, 2));
+PUT(previous_callout, 2 + LINK_SIZE, length);
+}
+
+
+
+#ifdef SUPPORT_UCP
+/*************************************************
+*           Get othercase range                  *
+*************************************************/
+
+/* This function is passed the start and end of a class range, in UTF-8 mode
+with UCP support. It searches up the characters, looking for internal ranges of
+characters in the "other" case. Each call returns the next one, updating the
+start address.
+
+Arguments:
+  cptr        points to starting character value; updated
+  d           end value
+  ocptr       where to put start of othercase range
+  odptr       where to put end of othercase range
+
+Yield:        TRUE when range returned; FALSE when no more
+*/
+
+static BOOL
+get_othercase_range(unsigned int *cptr, unsigned int d, unsigned int *ocptr,
+  unsigned int *odptr)
+{
+unsigned int c, othercase, next;
+
+for (c = *cptr; c <= d; c++)
+  { if ((othercase = UCD_OTHERCASE(c)) != c) break; }
+
+if (c > d) return FALSE;
+
+*ocptr = othercase;
+next = othercase + 1;
+
+for (++c; c <= d; c++)
+  {
+  if (UCD_OTHERCASE(c) != next) break;
+  next++;
+  }
+
+*odptr = next - 1;
+*cptr = c;
+
+return TRUE;
+}
+
+
+
+/*************************************************
+*        Check a character and a property        *
+*************************************************/
+
+/* This function is called by check_auto_possessive() when a property item
+is adjacent to a fixed character.
+
+Arguments:
+  c            the character
+  ptype        the property type
+  pdata        the data for the type
+  negated      TRUE if it's a negated property (\P or \p{^)
+
+Returns:       TRUE if auto-possessifying is OK
+*/
+
+static BOOL
+check_char_prop(int c, int ptype, int pdata, BOOL negated)
+{
+const ucd_record *prop = GET_UCD(c);
+switch(ptype)
+  {
+  case PT_LAMP:
+  return (prop->chartype == ucp_Lu ||
+          prop->chartype == ucp_Ll ||
+          prop->chartype == ucp_Lt) == negated;
+
+  case PT_GC:
+  return (pdata == PRIV(ucp_gentype)[prop->chartype]) == negated;
+
+  case PT_PC:
+  return (pdata == prop->chartype) == negated;
+
+  case PT_SC:
+  return (pdata == prop->script) == negated;
+
+  /* These are specials */
+
+  case PT_ALNUM:
+  return (PRIV(ucp_gentype)[prop->chartype] == ucp_L ||
+          PRIV(ucp_gentype)[prop->chartype] == ucp_N) == negated;
+
+  case PT_SPACE:    /* Perl space */
+  return (PRIV(ucp_gentype)[prop->chartype] == ucp_Z ||
+          c == CHAR_HT || c == CHAR_NL || c == CHAR_FF || c == CHAR_CR)
+          == negated;
+
+  case PT_PXSPACE:  /* POSIX space */
+  return (PRIV(ucp_gentype)[prop->chartype] == ucp_Z ||
+          c == CHAR_HT || c == CHAR_NL || c == CHAR_VT ||
+          c == CHAR_FF || c == CHAR_CR)
+          == negated;
+
+  case PT_WORD:
+  return (PRIV(ucp_gentype)[prop->chartype] == ucp_L ||
+          PRIV(ucp_gentype)[prop->chartype] == ucp_N ||
+          c == CHAR_UNDERSCORE) == negated;
+  }
+return FALSE;
+}
+#endif  /* SUPPORT_UCP */
+
+
+
+/*************************************************
+*     Check if auto-possessifying is possible    *
+*************************************************/
+
+/* This function is called for unlimited repeats of certain items, to see
+whether the next thing could possibly match the repeated item. If not, it makes
+sense to automatically possessify the repeated item.
+
+Arguments:
+  previous      pointer to the repeated opcode
+  utf           TRUE in UTF-8 / UTF-16 mode
+  ptr           next character in pattern
+  options       options bits
+  cd            contains pointers to tables etc.
+
+Returns:        TRUE if possessifying is wanted
+*/
+
+static BOOL
+check_auto_possessive(const pcre_uchar *previous, BOOL utf,
+  const pcre_uchar *ptr, int options, compile_data *cd)
+{
+pcre_int32 c, next;
+int op_code = *previous++;
+
+/* Skip whitespace and comments in extended mode */
+
+if ((options & PCRE_EXTENDED) != 0)
+  {
+  for (;;)
+    {
+    while (MAX_255(*ptr) && (cd->ctypes[*ptr] & ctype_space) != 0) ptr++;
+    if (*ptr == CHAR_NUMBER_SIGN)
+      {
+      ptr++;
+      while (*ptr != 0)
+        {
+        if (IS_NEWLINE(ptr)) { ptr += cd->nllen; break; }
+        ptr++;
+#ifdef SUPPORT_UTF
+        if (utf) FORWARDCHAR(ptr);
+#endif
+        }
+      }
+    else break;
+    }
+  }
+
+/* If the next item is one that we can handle, get its value. A non-negative
+value is a character, a negative value is an escape value. */
+
+if (*ptr == CHAR_BACKSLASH)
+  {
+  int temperrorcode = 0;
+  next = check_escape(&ptr, &temperrorcode, cd->bracount, options, FALSE);
+  if (temperrorcode != 0) return FALSE;
+  ptr++;    /* Point after the escape sequence */
+  }
+else if (!MAX_255(*ptr) || (cd->ctypes[*ptr] & ctype_meta) == 0)
+  {
+#ifdef SUPPORT_UTF
+  if (utf) { GETCHARINC(next, ptr); } else
+#endif
+  next = *ptr++;
+  }
+else return FALSE;
+
+/* Skip whitespace and comments in extended mode */
+
+if ((options & PCRE_EXTENDED) != 0)
+  {
+  for (;;)
+    {
+    while (MAX_255(*ptr) && (cd->ctypes[*ptr] & ctype_space) != 0) ptr++;
+    if (*ptr == CHAR_NUMBER_SIGN)
+      {
+      ptr++;
+      while (*ptr != 0)
+        {
+        if (IS_NEWLINE(ptr)) { ptr += cd->nllen; break; }
+        ptr++;
+#ifdef SUPPORT_UTF
+        if (utf) FORWARDCHAR(ptr);
+#endif
+        }
+      }
+    else break;
+    }
+  }
+
+/* If the next thing is itself optional, we have to give up. */
+
+if (*ptr == CHAR_ASTERISK || *ptr == CHAR_QUESTION_MARK ||
+  STRNCMP_UC_C8(ptr, STR_LEFT_CURLY_BRACKET STR_0 STR_COMMA, 3) == 0)
+    return FALSE;
+
+/* Now compare the next item with the previous opcode. First, handle cases when
+the next item is a character. */
+
+if (next >= 0) switch(op_code)
+  {
+  case OP_CHAR:
+#ifdef SUPPORT_UTF
+  GETCHARTEST(c, previous);
+#else
+  c = *previous;
+#endif
+  return c != next;
+
+  /* For CHARI (caseless character) we must check the other case. If we have
+  Unicode property support, we can use it to test the other case of
+  high-valued characters. */
+
+  case OP_CHARI:
+#ifdef SUPPORT_UTF
+  GETCHARTEST(c, previous);
+#else
+  c = *previous;
+#endif
+  if (c == next) return FALSE;
+#ifdef SUPPORT_UTF
+  if (utf)
+    {
+    unsigned int othercase;
+    if (next < 128) othercase = cd->fcc[next]; else
+#ifdef SUPPORT_UCP
+    othercase = UCD_OTHERCASE((unsigned int)next);
+#else
+    othercase = NOTACHAR;
+#endif
+    return (unsigned int)c != othercase;
+    }
+  else
+#endif  /* SUPPORT_UTF */
+  return (c != TABLE_GET((unsigned int)next, cd->fcc, next));  /* Non-UTF-8 mode */
+
+  case OP_NOT:
+#ifdef SUPPORT_UTF
+  GETCHARTEST(c, previous);
+#else
+  c = *previous;
+#endif
+  return c == next;
+
+  case OP_NOTI:
+#ifdef SUPPORT_UTF
+  GETCHARTEST(c, previous);
+#else
+  c = *previous;
+#endif
+  if (c == next) return TRUE;
+#ifdef SUPPORT_UTF
+  if (utf)
+    {
+    unsigned int othercase;
+    if (next < 128) othercase = cd->fcc[next]; else
+#ifdef SUPPORT_UCP
+    othercase = UCD_OTHERCASE((unsigned int)next);
+#else
+    othercase = NOTACHAR;
+#endif
+    return (unsigned int)c == othercase;
+    }
+  else
+#endif  /* SUPPORT_UTF */
+  return (c == TABLE_GET((unsigned int)next, cd->fcc, next));  /* Non-UTF-8 mode */
+
+  /* Note that OP_DIGIT etc. are generated only when PCRE_UCP is *not* set.
+  When it is set, \d etc. are converted into OP_(NOT_)PROP codes. */
+
+  case OP_DIGIT:
+  return next > 255 || (cd->ctypes[next] & ctype_digit) == 0;
+
+  case OP_NOT_DIGIT:
+  return next <= 255 && (cd->ctypes[next] & ctype_digit) != 0;
+
+  case OP_WHITESPACE:
+  return next > 255 || (cd->ctypes[next] & ctype_space) == 0;
+
+  case OP_NOT_WHITESPACE:
+  return next <= 255 && (cd->ctypes[next] & ctype_space) != 0;
+
+  case OP_WORDCHAR:
+  return next > 255 || (cd->ctypes[next] & ctype_word) == 0;
+
+  case OP_NOT_WORDCHAR:
+  return next <= 255 && (cd->ctypes[next] & ctype_word) != 0;
+
+  case OP_HSPACE:
+  case OP_NOT_HSPACE:
+  switch(next)
+    {
+    case 0x09:
+    case 0x20:
+    case 0xa0:
+    case 0x1680:
+    case 0x180e:
+    case 0x2000:
+    case 0x2001:
+    case 0x2002:
+    case 0x2003:
+    case 0x2004:
+    case 0x2005:
+    case 0x2006:
+    case 0x2007:
+    case 0x2008:
+    case 0x2009:
+    case 0x200A:
+    case 0x202f:
+    case 0x205f:
+    case 0x3000:
+    return op_code == OP_NOT_HSPACE;
+    default:
+    return op_code != OP_NOT_HSPACE;
+    }
+
+  case OP_ANYNL:
+  case OP_VSPACE:
+  case OP_NOT_VSPACE:
+  switch(next)
+    {
+    case 0x0a:
+    case 0x0b:
+    case 0x0c:
+    case 0x0d:
+    case 0x85:
+    case 0x2028:
+    case 0x2029:
+    return op_code == OP_NOT_VSPACE;
+    default:
+    return op_code != OP_NOT_VSPACE;
+    }
+
+#ifdef SUPPORT_UCP
+  case OP_PROP:
+  return check_char_prop(next, previous[0], previous[1], FALSE);
+
+  case OP_NOTPROP:
+  return check_char_prop(next, previous[0], previous[1], TRUE);
+#endif
+
+  default:
+  return FALSE;
+  }
+
+
+/* Handle the case when the next item is \d, \s, etc. Note that when PCRE_UCP
+is set, \d turns into ESC_du rather than ESC_d, etc., so ESC_d etc. are
+generated only when PCRE_UCP is *not* set, that is, when only ASCII
+characteristics are recognized. Similarly, the opcodes OP_DIGIT etc. are
+replaced by OP_PROP codes when PCRE_UCP is set. */
+
+switch(op_code)
+  {
+  case OP_CHAR:
+  case OP_CHARI:
+#ifdef SUPPORT_UTF
+  GETCHARTEST(c, previous);
+#else
+  c = *previous;
+#endif
+  switch(-next)
+    {
+    case ESC_d:
+    return c > 255 || (cd->ctypes[c] & ctype_digit) == 0;
+
+    case ESC_D:
+    return c <= 255 && (cd->ctypes[c] & ctype_digit) != 0;
+
+    case ESC_s:
+    return c > 255 || (cd->ctypes[c] & ctype_space) == 0;
+
+    case ESC_S:
+    return c <= 255 && (cd->ctypes[c] & ctype_space) != 0;
+
+    case ESC_w:
+    return c > 255 || (cd->ctypes[c] & ctype_word) == 0;
+
+    case ESC_W:
+    return c <= 255 && (cd->ctypes[c] & ctype_word) != 0;
+
+    case ESC_h:
+    case ESC_H:
+    switch(c)
+      {
+      case 0x09:
+      case 0x20:
+      case 0xa0:
+      case 0x1680:
+      case 0x180e:
+      case 0x2000:
+      case 0x2001:
+      case 0x2002:
+      case 0x2003:
+      case 0x2004:
+      case 0x2005:
+      case 0x2006:
+      case 0x2007:
+      case 0x2008:
+      case 0x2009:
+      case 0x200A:
+      case 0x202f:
+      case 0x205f:
+      case 0x3000:
+      return -next != ESC_h;
+      default:
+      return -next == ESC_h;
+      }
+
+    case ESC_v:
+    case ESC_V:
+    switch(c)
+      {
+      case 0x0a:
+      case 0x0b:
+      case 0x0c:
+      case 0x0d:
+      case 0x85:
+      case 0x2028:
+      case 0x2029:
+      return -next != ESC_v;
+      default:
+      return -next == ESC_v;
+      }
+
+    /* When PCRE_UCP is set, these values get generated for \d etc. Find
+    their substitutions and process them. The result will always be either
+    -ESC_p or -ESC_P. Then fall through to process those values. */
+
+#ifdef SUPPORT_UCP
+    case ESC_du:
+    case ESC_DU:
+    case ESC_wu:
+    case ESC_WU:
+    case ESC_su:
+    case ESC_SU:
+      {
+      int temperrorcode = 0;
+      ptr = substitutes[-next - ESC_DU];
+      next = check_escape(&ptr, &temperrorcode, 0, options, FALSE);
+      if (temperrorcode != 0) return FALSE;
+      ptr++;    /* For compatibility */
+      }
+    /* Fall through */
+
+    case ESC_p:
+    case ESC_P:
+      {
+      int ptype, pdata, errorcodeptr;
+      BOOL negated;
+
+      ptr--;      /* Make ptr point at the p or P */
+      ptype = get_ucp(&ptr, &negated, &pdata, &errorcodeptr);
+      if (ptype < 0) return FALSE;
+      ptr++;      /* Point past the final curly ket */
+
+      /* If the property item is optional, we have to give up. (When generated
+      from \d etc by PCRE_UCP, this test will have been applied much earlier,
+      to the original \d etc. At this point, ptr will point to a zero byte. */
+
+      if (*ptr == CHAR_ASTERISK || *ptr == CHAR_QUESTION_MARK ||
+        STRNCMP_UC_C8(ptr, STR_LEFT_CURLY_BRACKET STR_0 STR_COMMA, 3) == 0)
+          return FALSE;
+
+      /* Do the property check. */
+
+      return check_char_prop(c, ptype, pdata, (next == -ESC_P) != negated);
+      }
+#endif
+
+    default:
+    return FALSE;
+    }
+
+  /* In principle, support for Unicode properties should be integrated here as
+  well. It means re-organizing the above code so as to get hold of the property
+  values before switching on the op-code. However, I wonder how many patterns
+  combine ASCII \d etc with Unicode properties? (Note that if PCRE_UCP is set,
+  these op-codes are never generated.) */
+
+  case OP_DIGIT:
+  return next == -ESC_D || next == -ESC_s || next == -ESC_W ||
+         next == -ESC_h || next == -ESC_v || next == -ESC_R;
+
+  case OP_NOT_DIGIT:
+  return next == -ESC_d;
+
+  case OP_WHITESPACE:
+  return next == -ESC_S || next == -ESC_d || next == -ESC_w;
+
+  case OP_NOT_WHITESPACE:
+  return next == -ESC_s || next == -ESC_h || next == -ESC_v || next == -ESC_R;
+
+  case OP_HSPACE:
+  return next == -ESC_S || next == -ESC_H || next == -ESC_d ||
+         next == -ESC_w || next == -ESC_v || next == -ESC_R;
+
+  case OP_NOT_HSPACE:
+  return next == -ESC_h;
+
+  /* Can't have \S in here because VT matches \S (Perl anomaly) */
+  case OP_ANYNL:
+  case OP_VSPACE:
+  return next == -ESC_V || next == -ESC_d || next == -ESC_w;
+
+  case OP_NOT_VSPACE:
+  return next == -ESC_v || next == -ESC_R;
+
+  case OP_WORDCHAR:
+  return next == -ESC_W || next == -ESC_s || next == -ESC_h ||
+         next == -ESC_v || next == -ESC_R;
+
+  case OP_NOT_WORDCHAR:
+  return next == -ESC_w || next == -ESC_d;
+
+  default:
+  return FALSE;
+  }
+
+/* Control does not reach here */
+}
+
+
+
+/*************************************************
+*           Compile one branch                   *
+*************************************************/
+
+/* Scan the pattern, compiling it into the a vector. If the options are
+changed during the branch, the pointer is used to change the external options
+bits. This function is used during the pre-compile phase when we are trying
+to find out the amount of memory needed, as well as during the real compile
+phase. The value of lengthptr distinguishes the two phases.
+
+Arguments:
+  optionsptr     pointer to the option bits
+  codeptr        points to the pointer to the current code point
+  ptrptr         points to the current pattern pointer
+  errorcodeptr   points to error code variable
+  firstcharptr   set to initial literal character, or < 0 (REQ_UNSET, REQ_NONE)
+  reqcharptr     set to the last literal character required, else < 0
+  bcptr          points to current branch chain
+  cond_depth     conditional nesting depth
+  cd             contains pointers to tables etc.
+  lengthptr      NULL during the real compile phase
+                 points to length accumulator during pre-compile phase
+
+Returns:         TRUE on success
+                 FALSE, with *errorcodeptr set non-zero on error
+*/
+
+static BOOL
+compile_branch(int *optionsptr, pcre_uchar **codeptr,
+  const pcre_uchar **ptrptr, int *errorcodeptr, pcre_int32 *firstcharptr,
+  pcre_int32 *reqcharptr, branch_chain *bcptr, int cond_depth,
+  compile_data *cd, int *lengthptr)
+{
+int repeat_type, op_type;
+int repeat_min = 0, repeat_max = 0;      /* To please picky compilers */
+int bravalue = 0;
+int greedy_default, greedy_non_default;
+pcre_int32 firstchar, reqchar;
+pcre_int32 zeroreqchar, zerofirstchar;
+pcre_int32 req_caseopt, reqvary, tempreqvary;
+int options = *optionsptr;               /* May change dynamically */
+int after_manual_callout = 0;
+int length_prevgroup = 0;
+register int c;
+register pcre_uchar *code = *codeptr;
+pcre_uchar *last_code = code;
+pcre_uchar *orig_code = code;
+pcre_uchar *tempcode;
+BOOL inescq = FALSE;
+BOOL groupsetfirstchar = FALSE;
+const pcre_uchar *ptr = *ptrptr;
+const pcre_uchar *tempptr;
+const pcre_uchar *nestptr = NULL;
+pcre_uchar *previous = NULL;
+pcre_uchar *previous_callout = NULL;
+pcre_uchar *save_hwm = NULL;
+pcre_uint8 classbits[32];
+
+/* We can fish out the UTF-8 setting once and for all into a BOOL, but we
+must not do this for other options (e.g. PCRE_EXTENDED) because they may change
+dynamically as we process the pattern. */
+
+#ifdef SUPPORT_UTF
+/* PCRE_UTF16 has the same value as PCRE_UTF8. */
+BOOL utf = (options & PCRE_UTF8) != 0;
+pcre_uchar utf_chars[6];
+#else
+BOOL utf = FALSE;
+#endif
+
+/* Helper variables for OP_XCLASS opcode (for characters > 255). */
+
+#if defined SUPPORT_UTF || !defined COMPILE_PCRE8
+BOOL xclass;
+pcre_uchar *class_uchardata;
+pcre_uchar *class_uchardata_base;
+#endif
+
+#ifdef PCRE_DEBUG
+if (lengthptr != NULL) DPRINTF((">> start branch\n"));
+#endif
+
+/* Set up the default and non-default settings for greediness */
+
+greedy_default = ((options & PCRE_UNGREEDY) != 0);
+greedy_non_default = greedy_default ^ 1;
+
+/* Initialize no first byte, no required byte. REQ_UNSET means "no char
+matching encountered yet". It gets changed to REQ_NONE if we hit something that
+matches a non-fixed char first char; reqchar just remains unset if we never
+find one.
+
+When we hit a repeat whose minimum is zero, we may have to adjust these values
+to take the zero repeat into account. This is implemented by setting them to
+zerofirstbyte and zeroreqchar when such a repeat is encountered. The individual
+item types that can be repeated set these backoff variables appropriately. */
+
+firstchar = reqchar = zerofirstchar = zeroreqchar = REQ_UNSET;
+
+/* The variable req_caseopt contains either the REQ_CASELESS value
+or zero, according to the current setting of the caseless flag. The
+REQ_CASELESS leaves the lower 28 bit empty. It is added into the
+firstchar or reqchar variables to record the case status of the
+value. This is used only for ASCII characters. */
+
+req_caseopt = ((options & PCRE_CASELESS) != 0)? REQ_CASELESS:0;
+
+/* Switch on next character until the end of the branch */
+
+for (;; ptr++)
+  {
+  BOOL negate_class;
+  BOOL should_flip_negation;
+  BOOL possessive_quantifier;
+  BOOL is_quantifier;
+  BOOL is_recurse;
+  BOOL reset_bracount;
+  int class_has_8bitchar;
+  int class_single_char;
+  int newoptions;
+  int recno;
+  int refsign;
+  int skipbytes;
+  int subreqchar;
+  int subfirstchar;
+  int terminator;
+  int mclength;
+  int tempbracount;
+  pcre_uchar mcbuffer[8];
+
+  /* Get next character in the pattern */
+
+  c = *ptr;
+
+  /* If we are at the end of a nested substitution, revert to the outer level
+  string. Nesting only happens one level deep. */
+
+  if (c == 0 && nestptr != NULL)
+    {
+    ptr = nestptr;
+    nestptr = NULL;
+    c = *ptr;
+    }
+
+  /* If we are in the pre-compile phase, accumulate the length used for the
+  previous cycle of this loop. */
+
+  if (lengthptr != NULL)
+    {
+#ifdef PCRE_DEBUG
+    if (code > cd->hwm) cd->hwm = code;                 /* High water info */
+#endif
+    if (code > cd->start_workspace + cd->workspace_size -
+        WORK_SIZE_SAFETY_MARGIN)                       /* Check for overrun */
+      {
+      *errorcodeptr = ERR52;
+      goto FAILED;
+      }
+
+    /* There is at least one situation where code goes backwards: this is the
+    case of a zero quantifier after a class (e.g. [ab]{0}). At compile time,
+    the class is simply eliminated. However, it is created first, so we have to
+    allow memory for it. Therefore, don't ever reduce the length at this point.
+    */
+
+    if (code < last_code) code = last_code;
+
+    /* Paranoid check for integer overflow */
+
+    if (OFLOW_MAX - *lengthptr < code - last_code)
+      {
+      *errorcodeptr = ERR20;
+      goto FAILED;
+      }
+
+    *lengthptr += (int)(code - last_code);
+    DPRINTF(("length=%d added %d c=%c (0x%x)\n", *lengthptr,
+      (int)(code - last_code), c, c));
+
+    /* If "previous" is set and it is not at the start of the work space, move
+    it back to there, in order to avoid filling up the work space. Otherwise,
+    if "previous" is NULL, reset the current code pointer to the start. */
+
+    if (previous != NULL)
+      {
+      if (previous > orig_code)
+        {
+        memmove(orig_code, previous, IN_UCHARS(code - previous));
+        code -= previous - orig_code;
+        previous = orig_code;
+        }
+      }
+    else code = orig_code;
+
+    /* Remember where this code item starts so we can pick up the length
+    next time round. */
+
+    last_code = code;
+    }
+
+  /* In the real compile phase, just check the workspace used by the forward
+  reference list. */
+
+  else if (cd->hwm > cd->start_workspace + cd->workspace_size -
+           WORK_SIZE_SAFETY_MARGIN)
+    {
+    *errorcodeptr = ERR52;
+    goto FAILED;
+    }
+
+  /* If in \Q...\E, check for the end; if not, we have a literal */
+
+  if (inescq && c != 0)
+    {
+    if (c == CHAR_BACKSLASH && ptr[1] == CHAR_E)
+      {
+      inescq = FALSE;
+      ptr++;
+      continue;
+      }
+    else
+      {
+      if (previous_callout != NULL)
+        {
+        if (lengthptr == NULL)  /* Don't attempt in pre-compile phase */
+          complete_callout(previous_callout, ptr, cd);
+        previous_callout = NULL;
+        }
+      if ((options & PCRE_AUTO_CALLOUT) != 0)
+        {
+        previous_callout = code;
+        code = auto_callout(code, ptr, cd);
+        }
+      goto NORMAL_CHAR;
+      }
+    }
+
+  /* Fill in length of a previous callout, except when the next thing is
+  a quantifier. */
+
+  is_quantifier =
+    c == CHAR_ASTERISK || c == CHAR_PLUS || c == CHAR_QUESTION_MARK ||
+    (c == CHAR_LEFT_CURLY_BRACKET && is_counted_repeat(ptr+1));
+
+  if (!is_quantifier && previous_callout != NULL &&
+       after_manual_callout-- <= 0)
+    {
+    if (lengthptr == NULL)      /* Don't attempt in pre-compile phase */
+      complete_callout(previous_callout, ptr, cd);
+    previous_callout = NULL;
+    }
+
+  /* In extended mode, skip white space and comments. */
+
+  if ((options & PCRE_EXTENDED) != 0)
+    {
+    if (MAX_255(*ptr) && (cd->ctypes[c] & ctype_space) != 0) continue;
+    if (c == CHAR_NUMBER_SIGN)
+      {
+      ptr++;
+      while (*ptr != 0)
+        {
+        if (IS_NEWLINE(ptr)) { ptr += cd->nllen - 1; break; }
+        ptr++;
+#ifdef SUPPORT_UTF
+        if (utf) FORWARDCHAR(ptr);
+#endif
+        }
+      if (*ptr != 0) continue;
+
+      /* Else fall through to handle end of string */
+      c = 0;
+      }
+    }
+
+  /* No auto callout for quantifiers. */
+
+  if ((options & PCRE_AUTO_CALLOUT) != 0 && !is_quantifier)
+    {
+    previous_callout = code;
+    code = auto_callout(code, ptr, cd);
+    }
+
+  switch(c)
+    {
+    /* ===================================================================*/
+    case 0:                        /* The branch terminates at string end */
+    case CHAR_VERTICAL_LINE:       /* or | or ) */
+    case CHAR_RIGHT_PARENTHESIS:
+    *firstcharptr = firstchar;
+    *reqcharptr = reqchar;
+    *codeptr = code;
+    *ptrptr = ptr;
+    if (lengthptr != NULL)
+      {
+      if (OFLOW_MAX - *lengthptr < code - last_code)
+        {
+        *errorcodeptr = ERR20;
+        goto FAILED;
+        }
+      *lengthptr += (int)(code - last_code);   /* To include callout length */
+      DPRINTF((">> end branch\n"));
+      }
+    return TRUE;
+
+
+    /* ===================================================================*/
+    /* Handle single-character metacharacters. In multiline mode, ^ disables
+    the setting of any following char as a first character. */
+
+    case CHAR_CIRCUMFLEX_ACCENT:
+    previous = NULL;
+    if ((options & PCRE_MULTILINE) != 0)
+      {
+      if (firstchar == REQ_UNSET) firstchar = REQ_NONE;
+      *code++ = OP_CIRCM;
+      }
+    else *code++ = OP_CIRC;
+    break;
+
+    case CHAR_DOLLAR_SIGN:
+    previous = NULL;
+    *code++ = ((options & PCRE_MULTILINE) != 0)? OP_DOLLM : OP_DOLL;
+    break;
+
+    /* There can never be a first char if '.' is first, whatever happens about
+    repeats. The value of reqchar doesn't change either. */
+
+    case CHAR_DOT:
+    if (firstchar == REQ_UNSET) firstchar = REQ_NONE;
+    zerofirstchar = firstchar;
+    zeroreqchar = reqchar;
+    previous = code;
+    *code++ = ((options & PCRE_DOTALL) != 0)? OP_ALLANY: OP_ANY;
+    break;
+
+
+    /* ===================================================================*/
+    /* Character classes. If the included characters are all < 256, we build a
+    32-byte bitmap of the permitted characters, except in the special case
+    where there is only one such character. For negated classes, we build the
+    map as usual, then invert it at the end. However, we use a different opcode
+    so that data characters > 255 can be handled correctly.
+
+    If the class contains characters outside the 0-255 range, a different
+    opcode is compiled. It may optionally have a bit map for characters < 256,
+    but those above are are explicitly listed afterwards. A flag byte tells
+    whether the bitmap is present, and whether this is a negated class or not.
+
+    In JavaScript compatibility mode, an isolated ']' causes an error. In
+    default (Perl) mode, it is treated as a data character. */
+
+    case CHAR_RIGHT_SQUARE_BRACKET:
+    if ((cd->external_options & PCRE_JAVASCRIPT_COMPAT) != 0)
+      {
+      *errorcodeptr = ERR64;
+      goto FAILED;
+      }
+    goto NORMAL_CHAR;
+
+    case CHAR_LEFT_SQUARE_BRACKET:
+    previous = code;
+
+    /* PCRE supports POSIX class stuff inside a class. Perl gives an error if
+    they are encountered at the top level, so we'll do that too. */
+
+    if ((ptr[1] == CHAR_COLON || ptr[1] == CHAR_DOT ||
+         ptr[1] == CHAR_EQUALS_SIGN) &&
+        check_posix_syntax(ptr, &tempptr))
+      {
+      *errorcodeptr = (ptr[1] == CHAR_COLON)? ERR13 : ERR31;
+      goto FAILED;
+      }
+
+    /* If the first character is '^', set the negation flag and skip it. Also,
+    if the first few characters (either before or after ^) are \Q\E or \E we
+    skip them too. This makes for compatibility with Perl. */
+
+    negate_class = FALSE;
+    for (;;)
+      {
+      c = *(++ptr);
+      if (c == CHAR_BACKSLASH)
+        {
+        if (ptr[1] == CHAR_E)
+          ptr++;
+        else if (STRNCMP_UC_C8(ptr + 1, STR_Q STR_BACKSLASH STR_E, 3) == 0)
+          ptr += 3;
+        else
+          break;
+        }
+      else if (!negate_class && c == CHAR_CIRCUMFLEX_ACCENT)
+        negate_class = TRUE;
+      else break;
+      }
+
+    /* Empty classes are allowed in JavaScript compatibility mode. Otherwise,
+    an initial ']' is taken as a data character -- the code below handles
+    that. In JS mode, [] must always fail, so generate OP_FAIL, whereas
+    [^] must match any character, so generate OP_ALLANY. */
+
+    if (c == CHAR_RIGHT_SQUARE_BRACKET &&
+        (cd->external_options & PCRE_JAVASCRIPT_COMPAT) != 0)
+      {
+      *code++ = negate_class? OP_ALLANY : OP_FAIL;
+      if (firstchar == REQ_UNSET) firstchar = REQ_NONE;
+      zerofirstchar = firstchar;
+      break;
+      }
+
+    /* If a class contains a negative special such as \S, we need to flip the
+    negation flag at the end, so that support for characters > 255 works
+    correctly (they are all included in the class). */
+
+    should_flip_negation = FALSE;
+
+    /* For optimization purposes, we track some properties of the class.
+    class_has_8bitchar will be non-zero, if the class contains at least one
+    < 256 character. class_single_char will be 1 if the class contains only
+    a single character. */
+
+    class_has_8bitchar = 0;
+    class_single_char = 0;
+
+    /* Initialize the 32-char bit map to all zeros. We build the map in a
+    temporary bit of memory, in case the class contains only 1 character (less
+    than 256), because in that case the compiled code doesn't use the bit map.
+    */
+
+    memset(classbits, 0, 32 * sizeof(pcre_uint8));
+
+#if defined SUPPORT_UTF || !defined COMPILE_PCRE8
+    xclass = FALSE;                           /* No chars >= 256 */
+    class_uchardata = code + LINK_SIZE + 2;   /* For UTF-8 items */
+    class_uchardata_base = class_uchardata;   /* For resetting in pass 1 */
+#endif
+
+    /* Process characters until ] is reached. By writing this as a "do" it
+    means that an initial ] is taken as a data character. At the start of the
+    loop, c contains the first byte of the character. */
+
+    if (c != 0) do
+      {
+      const pcre_uchar *oldptr;
+
+#ifdef SUPPORT_UTF
+      if (utf && HAS_EXTRALEN(c))
+        {                           /* Braces are required because the */
+        GETCHARLEN(c, ptr, ptr);    /* macro generates multiple statements */
+        }
+#endif
+
+#if defined SUPPORT_UTF || !defined COMPILE_PCRE8
+      /* In the pre-compile phase, accumulate the length of any extra
+      data and reset the pointer. This is so that very large classes that
+      contain a zillion > 255 characters no longer overwrite the work space
+      (which is on the stack). */
+
+      if (lengthptr != NULL)
+        {
+        *lengthptr += class_uchardata - class_uchardata_base;
+        class_uchardata = class_uchardata_base;
+        }
+#endif
+
+      /* Inside \Q...\E everything is literal except \E */
+
+      if (inescq)
+        {
+        if (c == CHAR_BACKSLASH && ptr[1] == CHAR_E)  /* If we are at \E */
+          {
+          inescq = FALSE;                   /* Reset literal state */
+          ptr++;                            /* Skip the 'E' */
+          continue;                         /* Carry on with next */
+          }
+        goto CHECK_RANGE;                   /* Could be range if \E follows */
+        }
+
+      /* Handle POSIX class names. Perl allows a negation extension of the
+      form [:^name:]. A square bracket that doesn't match the syntax is
+      treated as a literal. We also recognize the POSIX constructions
+      [.ch.] and [=ch=] ("collating elements") and fault them, as Perl
+      5.6 and 5.8 do. */
+
+      if (c == CHAR_LEFT_SQUARE_BRACKET &&
+          (ptr[1] == CHAR_COLON || ptr[1] == CHAR_DOT ||
+           ptr[1] == CHAR_EQUALS_SIGN) && check_posix_syntax(ptr, &tempptr))
+        {
+        BOOL local_negate = FALSE;
+        int posix_class, taboffset, tabopt;
+        register const pcre_uint8 *cbits = cd->cbits;
+        pcre_uint8 pbits[32];
+
+        if (ptr[1] != CHAR_COLON)
+          {
+          *errorcodeptr = ERR31;
+          goto FAILED;
+          }
+
+        ptr += 2;
+        if (*ptr == CHAR_CIRCUMFLEX_ACCENT)
+          {
+          local_negate = TRUE;
+          should_flip_negation = TRUE;  /* Note negative special */
+          ptr++;
+          }
+
+        posix_class = check_posix_name(ptr, (int)(tempptr - ptr));
+        if (posix_class < 0)
+          {
+          *errorcodeptr = ERR30;
+          goto FAILED;
+          }
+
+        /* If matching is caseless, upper and lower are converted to
+        alpha. This relies on the fact that the class table starts with
+        alpha, lower, upper as the first 3 entries. */
+
+        if ((options & PCRE_CASELESS) != 0 && posix_class <= 2)
+          posix_class = 0;
+
+        /* When PCRE_UCP is set, some of the POSIX classes are converted to
+        different escape sequences that use Unicode properties. */
+
+#ifdef SUPPORT_UCP
+        if ((options & PCRE_UCP) != 0)
+          {
+          int pc = posix_class + ((local_negate)? POSIX_SUBSIZE/2 : 0);
+          if (posix_substitutes[pc] != NULL)
+            {
+            nestptr = tempptr + 1;
+            ptr = posix_substitutes[pc] - 1;
+            continue;
+            }
+          }
+#endif
+        /* In the non-UCP case, we build the bit map for the POSIX class in a
+        chunk of local store because we may be adding and subtracting from it,
+        and we don't want to subtract bits that may be in the main map already.
+        At the end we or the result into the bit map that is being built. */
+
+        posix_class *= 3;
+
+        /* Copy in the first table (always present) */
+
+        memcpy(pbits, cbits + posix_class_maps[posix_class],
+          32 * sizeof(pcre_uint8));
+
+        /* If there is a second table, add or remove it as required. */
+
+        taboffset = posix_class_maps[posix_class + 1];
+        tabopt = posix_class_maps[posix_class + 2];
+
+        if (taboffset >= 0)
+          {
+          if (tabopt >= 0)
+            for (c = 0; c < 32; c++) pbits[c] |= cbits[c + taboffset];
+          else
+            for (c = 0; c < 32; c++) pbits[c] &= ~cbits[c + taboffset];
+          }
+
+        /* Not see if we need to remove any special characters. An option
+        value of 1 removes vertical space and 2 removes underscore. */
+
+        if (tabopt < 0) tabopt = -tabopt;
+        if (tabopt == 1) pbits[1] &= ~0x3c;
+          else if (tabopt == 2) pbits[11] &= 0x7f;
+
+        /* Add the POSIX table or its complement into the main table that is
+        being built and we are done. */
+
+        if (local_negate)
+          for (c = 0; c < 32; c++) classbits[c] |= ~pbits[c];
+        else
+          for (c = 0; c < 32; c++) classbits[c] |= pbits[c];
+
+        ptr = tempptr + 1;
+        /* Every class contains at least one < 256 characters. */
+        class_has_8bitchar = 1;
+        /* Every class contains at least two characters. */
+        class_single_char = 2;
+        continue;    /* End of POSIX syntax handling */
+        }
+
+      /* Backslash may introduce a single character, or it may introduce one
+      of the specials, which just set a flag. The sequence \b is a special
+      case. Inside a class (and only there) it is treated as backspace. We
+      assume that other escapes have more than one character in them, so
+      speculatively set both class_has_8bitchar and class_single_char bigger
+      than one. Unrecognized escapes fall through and are either treated
+      as literal characters (by default), or are faulted if
+      PCRE_EXTRA is set. */
+
+      if (c == CHAR_BACKSLASH)
+        {
+        c = check_escape(&ptr, errorcodeptr, cd->bracount, options, TRUE);
+        if (*errorcodeptr != 0) goto FAILED;
+
+        if (-c == ESC_b) c = CHAR_BS;    /* \b is backspace in a class */
+        else if (-c == ESC_N)            /* \N is not supported in a class */
+          {
+          *errorcodeptr = ERR71;
+          goto FAILED;
+          }
+        else if (-c == ESC_Q)            /* Handle start of quoted string */
+          {
+          if (ptr[1] == CHAR_BACKSLASH && ptr[2] == CHAR_E)
+            {
+            ptr += 2; /* avoid empty string */
+            }
+          else inescq = TRUE;
+          continue;
+          }
+        else if (-c == ESC_E) continue;  /* Ignore orphan \E */
+
+        if (c < 0)
+          {
+          register const pcre_uint8 *cbits = cd->cbits;
+          /* Every class contains at least two < 256 characters. */
+          class_has_8bitchar++;
+          /* Every class contains at least two characters. */
+          class_single_char += 2;
+
+          switch (-c)
+            {
+#ifdef SUPPORT_UCP
+            case ESC_du:     /* These are the values given for \d etc */
+            case ESC_DU:     /* when PCRE_UCP is set. We replace the */
+            case ESC_wu:     /* escape sequence with an appropriate \p */
+            case ESC_WU:     /* or \P to test Unicode properties instead */
+            case ESC_su:     /* of the default ASCII testing. */
+            case ESC_SU:
+            nestptr = ptr;
+            ptr = substitutes[-c - ESC_DU] - 1;  /* Just before substitute */
+            class_has_8bitchar--;                /* Undo! */
+            continue;
+#endif
+            case ESC_d:
+            for (c = 0; c < 32; c++) classbits[c] |= cbits[c+cbit_digit];
+            continue;
+
+            case ESC_D:
+            should_flip_negation = TRUE;
+            for (c = 0; c < 32; c++) classbits[c] |= ~cbits[c+cbit_digit];
+            continue;
+
+            case ESC_w:
+            for (c = 0; c < 32; c++) classbits[c] |= cbits[c+cbit_word];
+            continue;
+
+            case ESC_W:
+            should_flip_negation = TRUE;
+            for (c = 0; c < 32; c++) classbits[c] |= ~cbits[c+cbit_word];
+            continue;
+
+            /* Perl 5.004 onwards omits VT from \s, but we must preserve it
+            if it was previously set by something earlier in the character
+            class. */
+
+            case ESC_s:
+            classbits[0] |= cbits[cbit_space];
+            classbits[1] |= cbits[cbit_space+1] & ~0x08;
+            for (c = 2; c < 32; c++) classbits[c] |= cbits[c+cbit_space];
+            continue;
+
+            case ESC_S:
+            should_flip_negation = TRUE;
+            for (c = 0; c < 32; c++) classbits[c] |= ~cbits[c+cbit_space];
+            classbits[1] |= 0x08;    /* Perl 5.004 onwards omits VT from \s */
+            continue;
+
+            case ESC_h:
+            SETBIT(classbits, 0x09); /* VT */
+            SETBIT(classbits, 0x20); /* SPACE */
+            SETBIT(classbits, 0xa0); /* NSBP */
+#ifndef COMPILE_PCRE8
+            xclass = TRUE;
+            *class_uchardata++ = XCL_SINGLE;
+            *class_uchardata++ = 0x1680;
+            *class_uchardata++ = XCL_SINGLE;
+            *class_uchardata++ = 0x180e;
+            *class_uchardata++ = XCL_RANGE;
+            *class_uchardata++ = 0x2000;
+            *class_uchardata++ = 0x200a;
+            *class_uchardata++ = XCL_SINGLE;
+            *class_uchardata++ = 0x202f;
+            *class_uchardata++ = XCL_SINGLE;
+            *class_uchardata++ = 0x205f;
+            *class_uchardata++ = XCL_SINGLE;
+            *class_uchardata++ = 0x3000;
+#elif defined SUPPORT_UTF
+            if (utf)
+              {
+              xclass = TRUE;
+              *class_uchardata++ = XCL_SINGLE;
+              class_uchardata += PRIV(ord2utf)(0x1680, class_uchardata);
+              *class_uchardata++ = XCL_SINGLE;
+              class_uchardata += PRIV(ord2utf)(0x180e, class_uchardata);
+              *class_uchardata++ = XCL_RANGE;
+              class_uchardata += PRIV(ord2utf)(0x2000, class_uchardata);
+              class_uchardata += PRIV(ord2utf)(0x200a, class_uchardata);
+              *class_uchardata++ = XCL_SINGLE;
+              class_uchardata += PRIV(ord2utf)(0x202f, class_uchardata);
+              *class_uchardata++ = XCL_SINGLE;
+              class_uchardata += PRIV(ord2utf)(0x205f, class_uchardata);
+              *class_uchardata++ = XCL_SINGLE;
+              class_uchardata += PRIV(ord2utf)(0x3000, class_uchardata);
+              }
+#endif
+            continue;
+
+            case ESC_H:
+            for (c = 0; c < 32; c++)
+              {
+              int x = 0xff;
+              switch (c)
+                {
+                case 0x09/8: x ^= 1 << (0x09%8); break;
+                case 0x20/8: x ^= 1 << (0x20%8); break;
+                case 0xa0/8: x ^= 1 << (0xa0%8); break;
+                default: break;
+                }
+              classbits[c] |= x;
+              }
+#ifndef COMPILE_PCRE8
+            xclass = TRUE;
+            *class_uchardata++ = XCL_RANGE;
+            *class_uchardata++ = 0x0100;
+            *class_uchardata++ = 0x167f;
+            *class_uchardata++ = XCL_RANGE;
+            *class_uchardata++ = 0x1681;
+            *class_uchardata++ = 0x180d;
+            *class_uchardata++ = XCL_RANGE;
+            *class_uchardata++ = 0x180f;
+            *class_uchardata++ = 0x1fff;
+            *class_uchardata++ = XCL_RANGE;
+            *class_uchardata++ = 0x200b;
+            *class_uchardata++ = 0x202e;
+            *class_uchardata++ = XCL_RANGE;
+            *class_uchardata++ = 0x2030;
+            *class_uchardata++ = 0x205e;
+            *class_uchardata++ = XCL_RANGE;
+            *class_uchardata++ = 0x2060;
+            *class_uchardata++ = 0x2fff;
+            *class_uchardata++ = XCL_RANGE;
+            *class_uchardata++ = 0x3001;
+#ifdef SUPPORT_UTF
+            if (utf)
+              class_uchardata += PRIV(ord2utf)(0x10ffff, class_uchardata);
+            else
+#endif
+              *class_uchardata++ = 0xffff;
+#elif defined SUPPORT_UTF
+            if (utf)
+              {
+              xclass = TRUE;
+              *class_uchardata++ = XCL_RANGE;
+              class_uchardata += PRIV(ord2utf)(0x0100, class_uchardata);
+              class_uchardata += PRIV(ord2utf)(0x167f, class_uchardata);
+              *class_uchardata++ = XCL_RANGE;
+              class_uchardata += PRIV(ord2utf)(0x1681, class_uchardata);
+              class_uchardata += PRIV(ord2utf)(0x180d, class_uchardata);
+              *class_uchardata++ = XCL_RANGE;
+              class_uchardata += PRIV(ord2utf)(0x180f, class_uchardata);
+              class_uchardata += PRIV(ord2utf)(0x1fff, class_uchardata);
+              *class_uchardata++ = XCL_RANGE;
+              class_uchardata += PRIV(ord2utf)(0x200b, class_uchardata);
+              class_uchardata += PRIV(ord2utf)(0x202e, class_uchardata);
+              *class_uchardata++ = XCL_RANGE;
+              class_uchardata += PRIV(ord2utf)(0x2030, class_uchardata);
+              class_uchardata += PRIV(ord2utf)(0x205e, class_uchardata);
+              *class_uchardata++ = XCL_RANGE;
+              class_uchardata += PRIV(ord2utf)(0x2060, class_uchardata);
+              class_uchardata += PRIV(ord2utf)(0x2fff, class_uchardata);
+              *class_uchardata++ = XCL_RANGE;
+              class_uchardata += PRIV(ord2utf)(0x3001, class_uchardata);
+              class_uchardata += PRIV(ord2utf)(0x10ffff, class_uchardata);
+              }
+#endif
+            continue;
+
+            case ESC_v:
+            SETBIT(classbits, 0x0a); /* LF */
+            SETBIT(classbits, 0x0b); /* VT */
+            SETBIT(classbits, 0x0c); /* FF */
+            SETBIT(classbits, 0x0d); /* CR */
+            SETBIT(classbits, 0x85); /* NEL */
+#ifndef COMPILE_PCRE8
+            xclass = TRUE;
+            *class_uchardata++ = XCL_RANGE;
+            *class_uchardata++ = 0x2028;
+            *class_uchardata++ = 0x2029;
+#elif defined SUPPORT_UTF
+            if (utf)
+              {
+              xclass = TRUE;
+              *class_uchardata++ = XCL_RANGE;
+              class_uchardata += PRIV(ord2utf)(0x2028, class_uchardata);
+              class_uchardata += PRIV(ord2utf)(0x2029, class_uchardata);
+              }
+#endif
+            continue;
+
+            case ESC_V:
+            for (c = 0; c < 32; c++)
+              {
+              int x = 0xff;
+              switch (c)
+                {
+                case 0x0a/8: x ^= 1 << (0x0a%8);
+                             x ^= 1 << (0x0b%8);
+                             x ^= 1 << (0x0c%8);
+                             x ^= 1 << (0x0d%8);
+                             break;
+                case 0x85/8: x ^= 1 << (0x85%8); break;
+                default: break;
+                }
+              classbits[c] |= x;
+              }
+
+#ifndef COMPILE_PCRE8
+            xclass = TRUE;
+            *class_uchardata++ = XCL_RANGE;
+            *class_uchardata++ = 0x0100;
+            *class_uchardata++ = 0x2027;
+            *class_uchardata++ = XCL_RANGE;
+            *class_uchardata++ = 0x202a;
+#ifdef SUPPORT_UTF
+            if (utf)
+              class_uchardata += PRIV(ord2utf)(0x10ffff, class_uchardata);
+            else
+#endif
+              *class_uchardata++ = 0xffff;
+#elif defined SUPPORT_UTF
+            if (utf)
+              {
+              xclass = TRUE;
+              *class_uchardata++ = XCL_RANGE;
+              class_uchardata += PRIV(ord2utf)(0x0100, class_uchardata);
+              class_uchardata += PRIV(ord2utf)(0x2027, class_uchardata);
+              *class_uchardata++ = XCL_RANGE;
+              class_uchardata += PRIV(ord2utf)(0x202a, class_uchardata);
+              class_uchardata += PRIV(ord2utf)(0x10ffff, class_uchardata);
+              }
+#endif
+            continue;
+
+#ifdef SUPPORT_UCP
+            case ESC_p:
+            case ESC_P:
+              {
+              BOOL negated;
+              int pdata;
+              int ptype = get_ucp(&ptr, &negated, &pdata, errorcodeptr);
+              if (ptype < 0) goto FAILED;
+              xclass = TRUE;
+              *class_uchardata++ = ((-c == ESC_p) != negated)?
+                XCL_PROP : XCL_NOTPROP;
+              *class_uchardata++ = ptype;
+              *class_uchardata++ = pdata;
+              class_has_8bitchar--;                /* Undo! */
+              continue;
+              }
+#endif
+            /* Unrecognized escapes are faulted if PCRE is running in its
+            strict mode. By default, for compatibility with Perl, they are
+            treated as literals. */
+
+            default:
+            if ((options & PCRE_EXTRA) != 0)
+              {
+              *errorcodeptr = ERR7;
+              goto FAILED;
+              }
+            class_has_8bitchar--;    /* Undo the speculative increase. */
+            class_single_char -= 2;  /* Undo the speculative increase. */
+            c = *ptr;                /* Get the final character and fall through */
+            break;
+            }
+          }
+
+        /* Fall through if we have a single character (c >= 0). This may be
+        greater than 256. */
+
+        }   /* End of backslash handling */
+
+      /* A single character may be followed by '-' to form a range. However,
+      Perl does not permit ']' to be the end of the range. A '-' character
+      at the end is treated as a literal. Perl ignores orphaned \E sequences
+      entirely. The code for handling \Q and \E is messy. */
+
+      CHECK_RANGE:
+      while (ptr[1] == CHAR_BACKSLASH && ptr[2] == CHAR_E)
+        {
+        inescq = FALSE;
+        ptr += 2;
+        }
+
+      oldptr = ptr;
+
+      /* Remember \r or \n */
+
+      if (c == CHAR_CR || c == CHAR_NL) cd->external_flags |= PCRE_HASCRORLF;
+
+      /* Check for range */
+
+      if (!inescq && ptr[1] == CHAR_MINUS)
+        {
+        int d;
+        ptr += 2;
+        while (*ptr == CHAR_BACKSLASH && ptr[1] == CHAR_E) ptr += 2;
+
+        /* If we hit \Q (not followed by \E) at this point, go into escaped
+        mode. */
+
+        while (*ptr == CHAR_BACKSLASH && ptr[1] == CHAR_Q)
+          {
+          ptr += 2;
+          if (*ptr == CHAR_BACKSLASH && ptr[1] == CHAR_E)
+            { ptr += 2; continue; }
+          inescq = TRUE;
+          break;
+          }
+
+        if (*ptr == 0 || (!inescq && *ptr == CHAR_RIGHT_SQUARE_BRACKET))
+          {
+          ptr = oldptr;
+          goto LONE_SINGLE_CHARACTER;
+          }
+
+#ifdef SUPPORT_UTF
+        if (utf)
+          {                           /* Braces are required because the */
+          GETCHARLEN(d, ptr, ptr);    /* macro generates multiple statements */
+          }
+        else
+#endif
+        d = *ptr;  /* Not UTF-8 mode */
+
+        /* The second part of a range can be a single-character escape, but
+        not any of the other escapes. Perl 5.6 treats a hyphen as a literal
+        in such circumstances. */
+
+        if (!inescq && d == CHAR_BACKSLASH)
+          {
+          d = check_escape(&ptr, errorcodeptr, cd->bracount, options, TRUE);
+          if (*errorcodeptr != 0) goto FAILED;
+
+          /* \b is backspace; any other special means the '-' was literal */
+
+          if (d < 0)
+            {
+            if (d == -ESC_b) d = CHAR_BS; else
+              {
+              ptr = oldptr;
+              goto LONE_SINGLE_CHARACTER;  /* A few lines below */
+              }
+            }
+          }
+
+        /* Check that the two values are in the correct order. Optimize
+        one-character ranges */
+
+        if (d < c)
+          {
+          *errorcodeptr = ERR8;
+          goto FAILED;
+          }
+
+        if (d == c) goto LONE_SINGLE_CHARACTER;  /* A few lines below */
+
+        /* Remember \r or \n */
+
+        if (d == CHAR_CR || d == CHAR_NL) cd->external_flags |= PCRE_HASCRORLF;
+
+        /* Since we found a character range, single character optimizations
+        cannot be done anymore. */
+        class_single_char = 2;
+
+        /* In UTF-8 mode, if the upper limit is > 255, or > 127 for caseless
+        matching, we have to use an XCLASS with extra data items. Caseless
+        matching for characters > 127 is available only if UCP support is
+        available. */
+
+#if defined SUPPORT_UTF && !(defined COMPILE_PCRE8)
+        if ((d > 255) || (utf && ((options & PCRE_CASELESS) != 0 && d > 127)))
+#elif defined  SUPPORT_UTF
+        if (utf && (d > 255 || ((options & PCRE_CASELESS) != 0 && d > 127)))
+#elif !(defined COMPILE_PCRE8)
+        if (d > 255)
+#endif
+#if defined SUPPORT_UTF || !(defined COMPILE_PCRE8)
+          {
+          xclass = TRUE;
+
+          /* With UCP support, we can find the other case equivalents of
+          the relevant characters. There may be several ranges. Optimize how
+          they fit with the basic range. */
+
+#ifdef SUPPORT_UCP
+#ifndef COMPILE_PCRE8
+          if (utf && (options & PCRE_CASELESS) != 0)
+#else
+          if ((options & PCRE_CASELESS) != 0)
+#endif
+            {
+            unsigned int occ, ocd;
+            unsigned int cc = c;
+            unsigned int origd = d;
+            while (get_othercase_range(&cc, origd, &occ, &ocd))
+              {
+              if (occ >= (unsigned int)c &&
+                  ocd <= (unsigned int)d)
+                continue;                          /* Skip embedded ranges */
+
+              if (occ < (unsigned int)c  &&
+                  ocd >= (unsigned int)c - 1)      /* Extend the basic range */
+                {                                  /* if there is overlap,   */
+                c = occ;                           /* noting that if occ < c */
+                continue;                          /* we can't have ocd > d  */
+                }                                  /* because a subrange is  */
+              if (ocd > (unsigned int)d &&
+                  occ <= (unsigned int)d + 1)      /* always shorter than    */
+                {                                  /* the basic range.       */
+                d = ocd;
+                continue;
+                }
+
+              if (occ == ocd)
+                {
+                *class_uchardata++ = XCL_SINGLE;
+                }
+              else
+                {
+                *class_uchardata++ = XCL_RANGE;
+                class_uchardata += PRIV(ord2utf)(occ, class_uchardata);
+                }
+              class_uchardata += PRIV(ord2utf)(ocd, class_uchardata);
+              }
+            }
+#endif  /* SUPPORT_UCP */
+
+          /* Now record the original range, possibly modified for UCP caseless
+          overlapping ranges. */
+
+          *class_uchardata++ = XCL_RANGE;
+#ifdef SUPPORT_UTF
+#ifndef COMPILE_PCRE8
+          if (utf)
+            {
+            class_uchardata += PRIV(ord2utf)(c, class_uchardata);
+            class_uchardata += PRIV(ord2utf)(d, class_uchardata);
+            }
+          else
+            {
+            *class_uchardata++ = c;
+            *class_uchardata++ = d;
+            }
+#else
+          class_uchardata += PRIV(ord2utf)(c, class_uchardata);
+          class_uchardata += PRIV(ord2utf)(d, class_uchardata);
+#endif
+#else /* SUPPORT_UTF */
+          *class_uchardata++ = c;
+          *class_uchardata++ = d;
+#endif /* SUPPORT_UTF */
+
+          /* With UCP support, we are done. Without UCP support, there is no
+          caseless matching for UTF characters > 127; we can use the bit map
+          for the smaller ones. As for 16 bit characters without UTF, we
+          can still use  */
+
+#ifdef SUPPORT_UCP
+#ifndef COMPILE_PCRE8
+          if (utf)
+#endif
+            continue;    /* With next character in the class */
+#endif  /* SUPPORT_UCP */
+
+#if defined SUPPORT_UTF && !defined(SUPPORT_UCP) && !(defined COMPILE_PCRE8)
+          if (utf)
+            {
+            if ((options & PCRE_CASELESS) == 0 || c > 127) continue;
+            /* Adjust upper limit and fall through to set up the map */
+            d = 127;
+            }
+          else
+            {
+            if (c > 255) continue;
+            /* Adjust upper limit and fall through to set up the map */
+            d = 255;
+            }
+#elif defined SUPPORT_UTF && !defined(SUPPORT_UCP)
+          if ((options & PCRE_CASELESS) == 0 || c > 127) continue;
+          /* Adjust upper limit and fall through to set up the map */
+          d = 127;
+#else
+          if (c > 255) continue;
+          /* Adjust upper limit and fall through to set up the map */
+          d = 255;
+#endif  /* SUPPORT_UTF && !SUPPORT_UCP && !COMPILE_PCRE8 */
+          }
+#endif  /* SUPPORT_UTF || !COMPILE_PCRE8 */
+
+        /* We use the bit map for 8 bit mode, or when the characters fall
+        partially or entirely to [0-255] ([0-127] for UCP) ranges. */
+
+        class_has_8bitchar = 1;
+
+        /* We can save a bit of time by skipping this in the pre-compile. */
+
+        if (lengthptr == NULL) for (; c <= d; c++)
+          {
+          classbits[c/8] |= (1 << (c&7));
+          if ((options & PCRE_CASELESS) != 0)
+            {
+            int uc = cd->fcc[c]; /* flip case */
+            classbits[uc/8] |= (1 << (uc&7));
+            }
+          }
+
+        continue;   /* Go get the next char in the class */
+        }
+
+      /* Handle a lone single character - we can get here for a normal
+      non-escape char, or after \ that introduces a single character or for an
+      apparent range that isn't. */
+
+      LONE_SINGLE_CHARACTER:
+
+      /* Only the value of 1 matters for class_single_char. */
+
+      if (class_single_char < 2) class_single_char++;
+
+      /* If class_charcount is 1, we saw precisely one character. As long as
+      there was no use of \p or \P, in other words, no use of any XCLASS
+      features, we can optimize.
+
+      The optimization throws away the bit map. We turn the item into a
+      1-character OP_CHAR[I] if it's positive, or OP_NOT[I] if it's negative.
+      In the positive case, it can cause firstchar to be set. Otherwise, there
+      can be no first char if this item is first, whatever repeat count may
+      follow. In the case of reqchar, save the previous value for reinstating. */
+
+      if (class_single_char == 1 && ptr[1] == CHAR_RIGHT_SQUARE_BRACKET)
+        {
+        ptr++;
+        zeroreqchar = reqchar;
+
+        if (negate_class)
+          {
+          if (firstchar == REQ_UNSET) firstchar = REQ_NONE;
+          zerofirstchar = firstchar;
+          *code++ = ((options & PCRE_CASELESS) != 0)? OP_NOTI: OP_NOT;
+#ifdef SUPPORT_UTF
+          if (utf && c > MAX_VALUE_FOR_SINGLE_CHAR)
+            code += PRIV(ord2utf)(c, code);
+          else
+#endif
+            *code++ = c;
+          goto NOT_CHAR;
+          }
+
+        /* For a single, positive character, get the value into mcbuffer, and
+        then we can handle this with the normal one-character code. */
+
+#ifdef SUPPORT_UTF
+        if (utf && c > MAX_VALUE_FOR_SINGLE_CHAR)
+          mclength = PRIV(ord2utf)(c, mcbuffer);
+        else
+#endif
+          {
+          mcbuffer[0] = c;
+          mclength = 1;
+          }
+        goto ONE_CHAR;
+        }       /* End of 1-char optimization */
+
+      /* Handle a character that cannot go in the bit map. */
+
+#if defined SUPPORT_UTF && !(defined COMPILE_PCRE8)
+      if ((c > 255) || (utf && ((options & PCRE_CASELESS) != 0 && c > 127)))
+#elif defined SUPPORT_UTF
+      if (utf && (c > 255 || ((options & PCRE_CASELESS) != 0 && c > 127)))
+#elif !(defined COMPILE_PCRE8)
+      if (c > 255)
+#endif
+
+#if defined SUPPORT_UTF || !(defined COMPILE_PCRE8)
+        {
+        xclass = TRUE;
+        *class_uchardata++ = XCL_SINGLE;
+#ifdef SUPPORT_UTF
+#ifndef COMPILE_PCRE8
+        /* In non 8 bit mode, we can get here even if we are not in UTF mode. */
+        if (!utf)
+          *class_uchardata++ = c;
+        else
+#endif
+          class_uchardata += PRIV(ord2utf)(c, class_uchardata);
+#else /* SUPPORT_UTF */
+        *class_uchardata++ = c;
+#endif /* SUPPORT_UTF */
+
+#ifdef SUPPORT_UCP
+#ifdef COMPILE_PCRE8
+        if ((options & PCRE_CASELESS) != 0)
+#else
+        /* In non 8 bit mode, we can get here even if we are not in UTF mode. */
+        if (utf && (options & PCRE_CASELESS) != 0)
+#endif
+          {
+          unsigned int othercase;
+          if ((int)(othercase = UCD_OTHERCASE(c)) != c)
+            {
+            *class_uchardata++ = XCL_SINGLE;
+            class_uchardata += PRIV(ord2utf)(othercase, class_uchardata);
+            }
+          }
+#endif  /* SUPPORT_UCP */
+
+        }
+      else
+#endif  /* SUPPORT_UTF || COMPILE_PCRE16 */
+
+      /* Handle a single-byte character */
+        {
+        class_has_8bitchar = 1;
+        classbits[c/8] |= (1 << (c&7));
+        if ((options & PCRE_CASELESS) != 0)
+          {
+          c = cd->fcc[c]; /* flip case */
+          classbits[c/8] |= (1 << (c&7));
+          }
+        }
+      }
+
+    /* Loop until ']' reached. This "while" is the end of the "do" far above.
+    If we are at the end of an internal nested string, revert to the outer
+    string. */
+
+    while (((c = *(++ptr)) != 0 ||
+           (nestptr != NULL &&
+             (ptr = nestptr, nestptr = NULL, c = *(++ptr)) != 0)) &&
+           (c != CHAR_RIGHT_SQUARE_BRACKET || inescq));
+
+    /* Check for missing terminating ']' */
+
+    if (c == 0)
+      {
+      *errorcodeptr = ERR6;
+      goto FAILED;
+      }
+
+    /* If this is the first thing in the branch, there can be no first char
+    setting, whatever the repeat count. Any reqchar setting must remain
+    unchanged after any kind of repeat. */
+
+    if (firstchar == REQ_UNSET) firstchar = REQ_NONE;
+    zerofirstchar = firstchar;
+    zeroreqchar = reqchar;
+
+    /* If there are characters with values > 255, we have to compile an
+    extended class, with its own opcode, unless there was a negated special
+    such as \S in the class, and PCRE_UCP is not set, because in that case all
+    characters > 255 are in the class, so any that were explicitly given as
+    well can be ignored. If (when there are explicit characters > 255 that must
+    be listed) there are no characters < 256, we can omit the bitmap in the
+    actual compiled code. */
+
+#ifdef SUPPORT_UTF
+    if (xclass && (!should_flip_negation || (options & PCRE_UCP) != 0))
+#elif !defined COMPILE_PCRE8
+    if (xclass && !should_flip_negation)
+#endif
+#if defined SUPPORT_UTF || !defined COMPILE_PCRE8
+      {
+      *class_uchardata++ = XCL_END;    /* Marks the end of extra data */
+      *code++ = OP_XCLASS;
+      code += LINK_SIZE;
+      *code = negate_class? XCL_NOT:0;
+
+      /* If the map is required, move up the extra data to make room for it;
+      otherwise just move the code pointer to the end of the extra data. */
+
+      if (class_has_8bitchar > 0)
+        {
+        *code++ |= XCL_MAP;
+        memmove(code + (32 / sizeof(pcre_uchar)), code,
+          IN_UCHARS(class_uchardata - code));
+        memcpy(code, classbits, 32);
+        code = class_uchardata + (32 / sizeof(pcre_uchar));
+        }
+      else code = class_uchardata;
+
+      /* Now fill in the complete length of the item */
+
+      PUT(previous, 1, (int)(code - previous));
+      break;   /* End of class handling */
+      }
+#endif
+
+    /* If there are no characters > 255, or they are all to be included or
+    excluded, set the opcode to OP_CLASS or OP_NCLASS, depending on whether the
+    whole class was negated and whether there were negative specials such as \S
+    (non-UCP) in the class. Then copy the 32-byte map into the code vector,
+    negating it if necessary. */
+
+    *code++ = (negate_class == should_flip_negation) ? OP_CLASS : OP_NCLASS;
+    if (lengthptr == NULL)    /* Save time in the pre-compile phase */
+      {
+      if (negate_class)
+        for (c = 0; c < 32; c++) classbits[c] = ~classbits[c];
+      memcpy(code, classbits, 32);
+      }
+    code += 32 / sizeof(pcre_uchar);
+    NOT_CHAR:
+    break;
+
+
+    /* ===================================================================*/
+    /* Various kinds of repeat; '{' is not necessarily a quantifier, but this
+    has been tested above. */
+
+    case CHAR_LEFT_CURLY_BRACKET:
+    if (!is_quantifier) goto NORMAL_CHAR;
+    ptr = read_repeat_counts(ptr+1, &repeat_min, &repeat_max, errorcodeptr);
+    if (*errorcodeptr != 0) goto FAILED;
+    goto REPEAT;
+
+    case CHAR_ASTERISK:
+    repeat_min = 0;
+    repeat_max = -1;
+    goto REPEAT;
+
+    case CHAR_PLUS:
+    repeat_min = 1;
+    repeat_max = -1;
+    goto REPEAT;
+
+    case CHAR_QUESTION_MARK:
+    repeat_min = 0;
+    repeat_max = 1;
+
+    REPEAT:
+    if (previous == NULL)
+      {
+      *errorcodeptr = ERR9;
+      goto FAILED;
+      }
+
+    if (repeat_min == 0)
+      {
+      firstchar = zerofirstchar;    /* Adjust for zero repeat */
+      reqchar = zeroreqchar;        /* Ditto */
+      }
+
+    /* Remember whether this is a variable length repeat */
+
+    reqvary = (repeat_min == repeat_max)? 0 : REQ_VARY;
+
+    op_type = 0;                    /* Default single-char op codes */
+    possessive_quantifier = FALSE;  /* Default not possessive quantifier */
+
+    /* Save start of previous item, in case we have to move it up in order to
+    insert something before it. */
+
+    tempcode = previous;
+
+    /* If the next character is '+', we have a possessive quantifier. This
+    implies greediness, whatever the setting of the PCRE_UNGREEDY option.
+    If the next character is '?' this is a minimizing repeat, by default,
+    but if PCRE_UNGREEDY is set, it works the other way round. We change the
+    repeat type to the non-default. */
+
+    if (ptr[1] == CHAR_PLUS)
+      {
+      repeat_type = 0;                  /* Force greedy */
+      possessive_quantifier = TRUE;
+      ptr++;
+      }
+    else if (ptr[1] == CHAR_QUESTION_MARK)
+      {
+      repeat_type = greedy_non_default;
+      ptr++;
+      }
+    else repeat_type = greedy_default;
+
+    /* If previous was a recursion call, wrap it in atomic brackets so that
+    previous becomes the atomic group. All recursions were so wrapped in the
+    past, but it no longer happens for non-repeated recursions. In fact, the
+    repeated ones could be re-implemented independently so as not to need this,
+    but for the moment we rely on the code for repeating groups. */
+
+    if (*previous == OP_RECURSE)
+      {
+      memmove(previous + 1 + LINK_SIZE, previous, IN_UCHARS(1 + LINK_SIZE));
+      *previous = OP_ONCE;
+      PUT(previous, 1, 2 + 2*LINK_SIZE);
+      previous[2 + 2*LINK_SIZE] = OP_KET;
+      PUT(previous, 3 + 2*LINK_SIZE, 2 + 2*LINK_SIZE);
+      code += 2 + 2 * LINK_SIZE;
+      length_prevgroup = 3 + 3*LINK_SIZE;
+
+      /* When actually compiling, we need to check whether this was a forward
+      reference, and if so, adjust the offset. */
+
+      if (lengthptr == NULL && cd->hwm >= cd->start_workspace + LINK_SIZE)
+        {
+        int offset = GET(cd->hwm, -LINK_SIZE);
+        if (offset == previous + 1 - cd->start_code)
+          PUT(cd->hwm, -LINK_SIZE, offset + 1 + LINK_SIZE);
+        }
+      }
+
+    /* Now handle repetition for the different types of item. */
+
+    /* If previous was a character or negated character match, abolish the item
+    and generate a repeat item instead. If a char item has a minimum of more
+    than one, ensure that it is set in reqchar - it might not be if a sequence
+    such as x{3} is the first thing in a branch because the x will have gone
+    into firstchar instead.  */
+
+    if (*previous == OP_CHAR || *previous == OP_CHARI
+        || *previous == OP_NOT || *previous == OP_NOTI)
+      {
+      switch (*previous)
+        {
+        default: /* Make compiler happy. */
+        case OP_CHAR:  op_type = OP_STAR - OP_STAR; break;
+        case OP_CHARI: op_type = OP_STARI - OP_STAR; break;
+        case OP_NOT:   op_type = OP_NOTSTAR - OP_STAR; break;
+        case OP_NOTI:  op_type = OP_NOTSTARI - OP_STAR; break;
+        }
+
+      /* Deal with UTF characters that take up more than one character. It's
+      easier to write this out separately than try to macrify it. Use c to
+      hold the length of the character in bytes, plus UTF_LENGTH to flag that
+      it's a length rather than a small character. */
+
+#ifdef SUPPORT_UTF
+      if (utf && NOT_FIRSTCHAR(code[-1]))
+        {
+        pcre_uchar *lastchar = code - 1;
+        BACKCHAR(lastchar);
+        c = (int)(code - lastchar);     /* Length of UTF-8 character */
+        memcpy(utf_chars, lastchar, IN_UCHARS(c)); /* Save the char */
+        c |= UTF_LENGTH;                /* Flag c as a length */
+        }
+      else
+#endif /* SUPPORT_UTF */
+
+      /* Handle the case of a single charater - either with no UTF support, or
+      with UTF disabled, or for a single character UTF character. */
+        {
+        c = code[-1];
+        if (*previous <= OP_CHARI && repeat_min > 1)
+          reqchar = c | req_caseopt | cd->req_varyopt;
+        }
+
+      /* If the repetition is unlimited, it pays to see if the next thing on
+      the line is something that cannot possibly match this character. If so,
+      automatically possessifying this item gains some performance in the case
+      where the match fails. */
+
+      if (!possessive_quantifier &&
+          repeat_max < 0 &&
+          check_auto_possessive(previous, utf, ptr + 1, options, cd))
+        {
+        repeat_type = 0;    /* Force greedy */
+        possessive_quantifier = TRUE;
+        }
+
+      goto OUTPUT_SINGLE_REPEAT;   /* Code shared with single character types */
+      }
+
+    /* If previous was a character type match (\d or similar), abolish it and
+    create a suitable repeat item. The code is shared with single-character
+    repeats by setting op_type to add a suitable offset into repeat_type. Note
+    the the Unicode property types will be present only when SUPPORT_UCP is
+    defined, but we don't wrap the little bits of code here because it just
+    makes it horribly messy. */
+
+    else if (*previous < OP_EODN)
+      {
+      pcre_uchar *oldcode;
+      int prop_type, prop_value;
+      op_type = OP_TYPESTAR - OP_STAR;  /* Use type opcodes */
+      c = *previous;
+
+      if (!possessive_quantifier &&
+          repeat_max < 0 &&
+          check_auto_possessive(previous, utf, ptr + 1, options, cd))
+        {
+        repeat_type = 0;    /* Force greedy */
+        possessive_quantifier = TRUE;
+        }
+
+      OUTPUT_SINGLE_REPEAT:
+      if (*previous == OP_PROP || *previous == OP_NOTPROP)
+        {
+        prop_type = previous[1];
+        prop_value = previous[2];
+        }
+      else prop_type = prop_value = -1;
+
+      oldcode = code;
+      code = previous;                  /* Usually overwrite previous item */
+
+      /* If the maximum is zero then the minimum must also be zero; Perl allows
+      this case, so we do too - by simply omitting the item altogether. */
+
+      if (repeat_max == 0) goto END_REPEAT;
+
+      /*--------------------------------------------------------------------*/
+      /* This code is obsolete from release 8.00; the restriction was finally
+      removed: */
+
+      /* All real repeats make it impossible to handle partial matching (maybe
+      one day we will be able to remove this restriction). */
+
+      /* if (repeat_max != 1) cd->external_flags |= PCRE_NOPARTIAL; */
+      /*--------------------------------------------------------------------*/
+
+      /* Combine the op_type with the repeat_type */
+
+      repeat_type += op_type;
+
+      /* A minimum of zero is handled either as the special case * or ?, or as
+      an UPTO, with the maximum given. */
+
+      if (repeat_min == 0)
+        {
+        if (repeat_max == -1) *code++ = OP_STAR + repeat_type;
+          else if (repeat_max == 1) *code++ = OP_QUERY + repeat_type;
+        else
+          {
+          *code++ = OP_UPTO + repeat_type;
+          PUT2INC(code, 0, repeat_max);
+          }
+        }
+
+      /* A repeat minimum of 1 is optimized into some special cases. If the
+      maximum is unlimited, we use OP_PLUS. Otherwise, the original item is
+      left in place and, if the maximum is greater than 1, we use OP_UPTO with
+      one less than the maximum. */
+
+      else if (repeat_min == 1)
+        {
+        if (repeat_max == -1)
+          *code++ = OP_PLUS + repeat_type;
+        else
+          {
+          code = oldcode;                 /* leave previous item in place */
+          if (repeat_max == 1) goto END_REPEAT;
+          *code++ = OP_UPTO + repeat_type;
+          PUT2INC(code, 0, repeat_max - 1);
+          }
+        }
+
+      /* The case {n,n} is just an EXACT, while the general case {n,m} is
+      handled as an EXACT followed by an UPTO. */
+
+      else
+        {
+        *code++ = OP_EXACT + op_type;  /* NB EXACT doesn't have repeat_type */
+        PUT2INC(code, 0, repeat_min);
+
+        /* If the maximum is unlimited, insert an OP_STAR. Before doing so,
+        we have to insert the character for the previous code. For a repeated
+        Unicode property match, there are two extra bytes that define the
+        required property. In UTF-8 mode, long characters have their length in
+        c, with the UTF_LENGTH bit as a flag. */
+
+        if (repeat_max < 0)
+          {
+#ifdef SUPPORT_UTF
+          if (utf && (c & UTF_LENGTH) != 0)
+            {
+            memcpy(code, utf_chars, IN_UCHARS(c & 7));
+            code += c & 7;
+            }
+          else
+#endif
+            {
+            *code++ = c;
+            if (prop_type >= 0)
+              {
+              *code++ = prop_type;
+              *code++ = prop_value;
+              }
+            }
+          *code++ = OP_STAR + repeat_type;
+          }
+
+        /* Else insert an UPTO if the max is greater than the min, again
+        preceded by the character, for the previously inserted code. If the
+        UPTO is just for 1 instance, we can use QUERY instead. */
+
+        else if (repeat_max != repeat_min)
+          {
+#ifdef SUPPORT_UTF
+          if (utf && (c & UTF_LENGTH) != 0)
+            {
+            memcpy(code, utf_chars, IN_UCHARS(c & 7));
+            code += c & 7;
+            }
+          else
+#endif
+          *code++ = c;
+          if (prop_type >= 0)
+            {
+            *code++ = prop_type;
+            *code++ = prop_value;
+            }
+          repeat_max -= repeat_min;
+
+          if (repeat_max == 1)
+            {
+            *code++ = OP_QUERY + repeat_type;
+            }
+          else
+            {
+            *code++ = OP_UPTO + repeat_type;
+            PUT2INC(code, 0, repeat_max);
+            }
+          }
+        }
+
+      /* The character or character type itself comes last in all cases. */
+
+#ifdef SUPPORT_UTF
+      if (utf && (c & UTF_LENGTH) != 0)
+        {
+        memcpy(code, utf_chars, IN_UCHARS(c & 7));
+        code += c & 7;
+        }
+      else
+#endif
+      *code++ = c;
+
+      /* For a repeated Unicode property match, there are two extra bytes that
+      define the required property. */
+
+#ifdef SUPPORT_UCP
+      if (prop_type >= 0)
+        {
+        *code++ = prop_type;
+        *code++ = prop_value;
+        }
+#endif
+      }
+
+    /* If previous was a character class or a back reference, we put the repeat
+    stuff after it, but just skip the item if the repeat was {0,0}. */
+
+    else if (*previous == OP_CLASS ||
+             *previous == OP_NCLASS ||
+#if defined SUPPORT_UTF || !defined COMPILE_PCRE8
+             *previous == OP_XCLASS ||
+#endif
+             *previous == OP_REF ||
+             *previous == OP_REFI)
+      {
+      if (repeat_max == 0)
+        {
+        code = previous;
+        goto END_REPEAT;
+        }
+
+      /*--------------------------------------------------------------------*/
+      /* This code is obsolete from release 8.00; the restriction was finally
+      removed: */
+
+      /* All real repeats make it impossible to handle partial matching (maybe
+      one day we will be able to remove this restriction). */
+
+      /* if (repeat_max != 1) cd->external_flags |= PCRE_NOPARTIAL; */
+      /*--------------------------------------------------------------------*/
+
+      if (repeat_min == 0 && repeat_max == -1)
+        *code++ = OP_CRSTAR + repeat_type;
+      else if (repeat_min == 1 && repeat_max == -1)
+        *code++ = OP_CRPLUS + repeat_type;
+      else if (repeat_min == 0 && repeat_max == 1)
+        *code++ = OP_CRQUERY + repeat_type;
+      else
+        {
+        *code++ = OP_CRRANGE + repeat_type;
+        PUT2INC(code, 0, repeat_min);
+        if (repeat_max == -1) repeat_max = 0;  /* 2-byte encoding for max */
+        PUT2INC(code, 0, repeat_max);
+        }
+      }
+
+    /* If previous was a bracket group, we may have to replicate it in certain
+    cases. Note that at this point we can encounter only the "basic" bracket
+    opcodes such as BRA and CBRA, as this is the place where they get converted
+    into the more special varieties such as BRAPOS and SBRA. A test for >=
+    OP_ASSERT and <= OP_COND includes ASSERT, ASSERT_NOT, ASSERTBACK,
+    ASSERTBACK_NOT, ONCE, BRA, CBRA, and COND. Originally, PCRE did not allow
+    repetition of assertions, but now it does, for Perl compatibility. */
+
+    else if (*previous >= OP_ASSERT && *previous <= OP_COND)
+      {
+      register int i;
+      int len = (int)(code - previous);
+      pcre_uchar *bralink = NULL;
+      pcre_uchar *brazeroptr = NULL;
+
+      /* Repeating a DEFINE group is pointless, but Perl allows the syntax, so
+      we just ignore the repeat. */
+
+      if (*previous == OP_COND && previous[LINK_SIZE+1] == OP_DEF)
+        goto END_REPEAT;
+
+      /* There is no sense in actually repeating assertions. The only potential
+      use of repetition is in cases when the assertion is optional. Therefore,
+      if the minimum is greater than zero, just ignore the repeat. If the
+      maximum is not not zero or one, set it to 1. */
+
+      if (*previous < OP_ONCE)    /* Assertion */
+        {
+        if (repeat_min > 0) goto END_REPEAT;
+        if (repeat_max < 0 || repeat_max > 1) repeat_max = 1;
+        }
+
+      /* The case of a zero minimum is special because of the need to stick
+      OP_BRAZERO in front of it, and because the group appears once in the
+      data, whereas in other cases it appears the minimum number of times. For
+      this reason, it is simplest to treat this case separately, as otherwise
+      the code gets far too messy. There are several special subcases when the
+      minimum is zero. */
+
+      if (repeat_min == 0)
+        {
+        /* If the maximum is also zero, we used to just omit the group from the
+        output altogether, like this:
+
+        ** if (repeat_max == 0)
+        **   {
+        **   code = previous;
+        **   goto END_REPEAT;
+        **   }
+
+        However, that fails when a group or a subgroup within it is referenced
+        as a subroutine from elsewhere in the pattern, so now we stick in
+        OP_SKIPZERO in front of it so that it is skipped on execution. As we
+        don't have a list of which groups are referenced, we cannot do this
+        selectively.
+
+        If the maximum is 1 or unlimited, we just have to stick in the BRAZERO
+        and do no more at this point. However, we do need to adjust any
+        OP_RECURSE calls inside the group that refer to the group itself or any
+        internal or forward referenced group, because the offset is from the
+        start of the whole regex. Temporarily terminate the pattern while doing
+        this. */
+
+        if (repeat_max <= 1)    /* Covers 0, 1, and unlimited */
+          {
+          *code = OP_END;
+          adjust_recurse(previous, 1, utf, cd, save_hwm);
+          memmove(previous + 1, previous, IN_UCHARS(len));
+          code++;
+          if (repeat_max == 0)
+            {
+            *previous++ = OP_SKIPZERO;
+            goto END_REPEAT;
+            }
+          brazeroptr = previous;    /* Save for possessive optimizing */
+          *previous++ = OP_BRAZERO + repeat_type;
+          }
+
+        /* If the maximum is greater than 1 and limited, we have to replicate
+        in a nested fashion, sticking OP_BRAZERO before each set of brackets.
+        The first one has to be handled carefully because it's the original
+        copy, which has to be moved up. The remainder can be handled by code
+        that is common with the non-zero minimum case below. We have to
+        adjust the value or repeat_max, since one less copy is required. Once
+        again, we may have to adjust any OP_RECURSE calls inside the group. */
+
+        else
+          {
+          int offset;
+          *code = OP_END;
+          adjust_recurse(previous, 2 + LINK_SIZE, utf, cd, save_hwm);
+          memmove(previous + 2 + LINK_SIZE, previous, IN_UCHARS(len));
+          code += 2 + LINK_SIZE;
+          *previous++ = OP_BRAZERO + repeat_type;
+          *previous++ = OP_BRA;
+
+          /* We chain together the bracket offset fields that have to be
+          filled in later when the ends of the brackets are reached. */
+
+          offset = (bralink == NULL)? 0 : (int)(previous - bralink);
+          bralink = previous;
+          PUTINC(previous, 0, offset);
+          }
+
+        repeat_max--;
+        }
+
+      /* If the minimum is greater than zero, replicate the group as many
+      times as necessary, and adjust the maximum to the number of subsequent
+      copies that we need. If we set a first char from the group, and didn't
+      set a required char, copy the latter from the former. If there are any
+      forward reference subroutine calls in the group, there will be entries on
+      the workspace list; replicate these with an appropriate increment. */
+
+      else
+        {
+        if (repeat_min > 1)
+          {
+          /* In the pre-compile phase, we don't actually do the replication. We
+          just adjust the length as if we had. Do some paranoid checks for
+          potential integer overflow. The INT64_OR_DOUBLE type is a 64-bit
+          integer type when available, otherwise double. */
+
+          if (lengthptr != NULL)
+            {
+            int delta = (repeat_min - 1)*length_prevgroup;
+            if ((INT64_OR_DOUBLE)(repeat_min - 1)*
+                  (INT64_OR_DOUBLE)length_prevgroup >
+                    (INT64_OR_DOUBLE)INT_MAX ||
+                OFLOW_MAX - *lengthptr < delta)
+              {
+              *errorcodeptr = ERR20;
+              goto FAILED;
+              }
+            *lengthptr += delta;
+            }
+
+          /* This is compiling for real. If there is a set first byte for
+          the group, and we have not yet set a "required byte", set it. Make
+          sure there is enough workspace for copying forward references before
+          doing the copy. */
+
+          else
+            {
+            if (groupsetfirstchar && reqchar < 0) reqchar = firstchar;
+
+            for (i = 1; i < repeat_min; i++)
+              {
+              pcre_uchar *hc;
+              pcre_uchar *this_hwm = cd->hwm;
+              memcpy(code, previous, IN_UCHARS(len));
+
+              while (cd->hwm > cd->start_workspace + cd->workspace_size -
+                     WORK_SIZE_SAFETY_MARGIN - (this_hwm - save_hwm))
+                {
+                int save_offset = save_hwm - cd->start_workspace;
+                int this_offset = this_hwm - cd->start_workspace;
+                *errorcodeptr = expand_workspace(cd);
+                if (*errorcodeptr != 0) goto FAILED;
+                save_hwm = (pcre_uchar *)cd->start_workspace + save_offset;
+                this_hwm = (pcre_uchar *)cd->start_workspace + this_offset;
+                }
+
+              for (hc = save_hwm; hc < this_hwm; hc += LINK_SIZE)
+                {
+                PUT(cd->hwm, 0, GET(hc, 0) + len);
+                cd->hwm += LINK_SIZE;
+                }
+              save_hwm = this_hwm;
+              code += len;
+              }
+            }
+          }
+
+        if (repeat_max > 0) repeat_max -= repeat_min;
+        }
+
+      /* This code is common to both the zero and non-zero minimum cases. If
+      the maximum is limited, it replicates the group in a nested fashion,
+      remembering the bracket starts on a stack. In the case of a zero minimum,
+      the first one was set up above. In all cases the repeat_max now specifies
+      the number of additional copies needed. Again, we must remember to
+      replicate entries on the forward reference list. */
+
+      if (repeat_max >= 0)
+        {
+        /* In the pre-compile phase, we don't actually do the replication. We
+        just adjust the length as if we had. For each repetition we must add 1
+        to the length for BRAZERO and for all but the last repetition we must
+        add 2 + 2*LINKSIZE to allow for the nesting that occurs. Do some
+        paranoid checks to avoid integer overflow. The INT64_OR_DOUBLE type is
+        a 64-bit integer type when available, otherwise double. */
+
+        if (lengthptr != NULL && repeat_max > 0)
+          {
+          int delta = repeat_max * (length_prevgroup + 1 + 2 + 2*LINK_SIZE) -
+                      2 - 2*LINK_SIZE;   /* Last one doesn't nest */
+          if ((INT64_OR_DOUBLE)repeat_max *
+                (INT64_OR_DOUBLE)(length_prevgroup + 1 + 2 + 2*LINK_SIZE)
+                  > (INT64_OR_DOUBLE)INT_MAX ||
+              OFLOW_MAX - *lengthptr < delta)
+            {
+            *errorcodeptr = ERR20;
+            goto FAILED;
+            }
+          *lengthptr += delta;
+          }
+
+        /* This is compiling for real */
+
+        else for (i = repeat_max - 1; i >= 0; i--)
+          {
+          pcre_uchar *hc;
+          pcre_uchar *this_hwm = cd->hwm;
+
+          *code++ = OP_BRAZERO + repeat_type;
+
+          /* All but the final copy start a new nesting, maintaining the
+          chain of brackets outstanding. */
+
+          if (i != 0)
+            {
+            int offset;
+            *code++ = OP_BRA;
+            offset = (bralink == NULL)? 0 : (int)(code - bralink);
+            bralink = code;
+            PUTINC(code, 0, offset);
+            }
+
+          memcpy(code, previous, IN_UCHARS(len));
+
+          /* Ensure there is enough workspace for forward references before
+          copying them. */
+
+          while (cd->hwm > cd->start_workspace + cd->workspace_size -
+                 WORK_SIZE_SAFETY_MARGIN - (this_hwm - save_hwm))
+            {
+            int save_offset = save_hwm - cd->start_workspace;
+            int this_offset = this_hwm - cd->start_workspace;
+            *errorcodeptr = expand_workspace(cd);
+            if (*errorcodeptr != 0) goto FAILED;
+            save_hwm = (pcre_uchar *)cd->start_workspace + save_offset;
+            this_hwm = (pcre_uchar *)cd->start_workspace + this_offset;
+            }
+
+          for (hc = save_hwm; hc < this_hwm; hc += LINK_SIZE)
+            {
+            PUT(cd->hwm, 0, GET(hc, 0) + len + ((i != 0)? 2+LINK_SIZE : 1));
+            cd->hwm += LINK_SIZE;
+            }
+          save_hwm = this_hwm;
+          code += len;
+          }
+
+        /* Now chain through the pending brackets, and fill in their length
+        fields (which are holding the chain links pro tem). */
+
+        while (bralink != NULL)
+          {
+          int oldlinkoffset;
+          int offset = (int)(code - bralink + 1);
+          pcre_uchar *bra = code - offset;
+          oldlinkoffset = GET(bra, 1);
+          bralink = (oldlinkoffset == 0)? NULL : bralink - oldlinkoffset;
+          *code++ = OP_KET;
+          PUTINC(code, 0, offset);
+          PUT(bra, 1, offset);
+          }
+        }
+
+      /* If the maximum is unlimited, set a repeater in the final copy. For
+      ONCE brackets, that's all we need to do. However, possessively repeated
+      ONCE brackets can be converted into non-capturing brackets, as the
+      behaviour of (?:xx)++ is the same as (?>xx)++ and this saves having to
+      deal with possessive ONCEs specially.
+
+      Otherwise, when we are doing the actual compile phase, check to see
+      whether this group is one that could match an empty string. If so,
+      convert the initial operator to the S form (e.g. OP_BRA -> OP_SBRA) so
+      that runtime checking can be done. [This check is also applied to ONCE
+      groups at runtime, but in a different way.]
+
+      Then, if the quantifier was possessive and the bracket is not a
+      conditional, we convert the BRA code to the POS form, and the KET code to
+      KETRPOS. (It turns out to be convenient at runtime to detect this kind of
+      subpattern at both the start and at the end.) The use of special opcodes
+      makes it possible to reduce greatly the stack usage in pcre_exec(). If
+      the group is preceded by OP_BRAZERO, convert this to OP_BRAPOSZERO.
+
+      Then, if the minimum number of matches is 1 or 0, cancel the possessive
+      flag so that the default action below, of wrapping everything inside
+      atomic brackets, does not happen. When the minimum is greater than 1,
+      there will be earlier copies of the group, and so we still have to wrap
+      the whole thing. */
+
+      else
+        {
+        pcre_uchar *ketcode = code - 1 - LINK_SIZE;
+        pcre_uchar *bracode = ketcode - GET(ketcode, 1);
+
+        /* Convert possessive ONCE brackets to non-capturing */
+
+        if ((*bracode == OP_ONCE || *bracode == OP_ONCE_NC) &&
+            possessive_quantifier) *bracode = OP_BRA;
+
+        /* For non-possessive ONCE brackets, all we need to do is to
+        set the KET. */
+
+        if (*bracode == OP_ONCE || *bracode == OP_ONCE_NC)
+          *ketcode = OP_KETRMAX + repeat_type;
+
+        /* Handle non-ONCE brackets and possessive ONCEs (which have been
+        converted to non-capturing above). */
+
+        else
+          {
+          /* In the compile phase, check for empty string matching. */
+
+          if (lengthptr == NULL)
+            {
+            pcre_uchar *scode = bracode;
+            do
+              {
+              if (could_be_empty_branch(scode, ketcode, utf, cd))
+                {
+                *bracode += OP_SBRA - OP_BRA;
+                break;
+                }
+              scode += GET(scode, 1);
+              }
+            while (*scode == OP_ALT);
+            }
+
+          /* Handle possessive quantifiers. */
+
+          if (possessive_quantifier)
+            {
+            /* For COND brackets, we wrap the whole thing in a possessively
+            repeated non-capturing bracket, because we have not invented POS
+            versions of the COND opcodes. Because we are moving code along, we
+            must ensure that any pending recursive references are updated. */
+
+            if (*bracode == OP_COND || *bracode == OP_SCOND)
+              {
+              int nlen = (int)(code - bracode);
+              *code = OP_END;
+              adjust_recurse(bracode, 1 + LINK_SIZE, utf, cd, save_hwm);
+              memmove(bracode + 1 + LINK_SIZE, bracode, IN_UCHARS(nlen));
+              code += 1 + LINK_SIZE;
+              nlen += 1 + LINK_SIZE;
+              *bracode = OP_BRAPOS;
+              *code++ = OP_KETRPOS;
+              PUTINC(code, 0, nlen);
+              PUT(bracode, 1, nlen);
+              }
+
+            /* For non-COND brackets, we modify the BRA code and use KETRPOS. */
+
+            else
+              {
+              *bracode += 1;              /* Switch to xxxPOS opcodes */
+              *ketcode = OP_KETRPOS;
+              }
+
+            /* If the minimum is zero, mark it as possessive, then unset the
+            possessive flag when the minimum is 0 or 1. */
+
+            if (brazeroptr != NULL) *brazeroptr = OP_BRAPOSZERO;
+            if (repeat_min < 2) possessive_quantifier = FALSE;
+            }
+
+          /* Non-possessive quantifier */
+
+          else *ketcode = OP_KETRMAX + repeat_type;
+          }
+        }
+      }
+
+    /* If previous is OP_FAIL, it was generated by an empty class [] in
+    JavaScript mode. The other ways in which OP_FAIL can be generated, that is
+    by (*FAIL) or (?!) set previous to NULL, which gives a "nothing to repeat"
+    error above. We can just ignore the repeat in JS case. */
+
+    else if (*previous == OP_FAIL) goto END_REPEAT;
+
+    /* Else there's some kind of shambles */
+
+    else
+      {
+      *errorcodeptr = ERR11;
+      goto FAILED;
+      }
+
+    /* If the character following a repeat is '+', or if certain optimization
+    tests above succeeded, possessive_quantifier is TRUE. For some opcodes,
+    there are special alternative opcodes for this case. For anything else, we
+    wrap the entire repeated item inside OP_ONCE brackets. Logically, the '+'
+    notation is just syntactic sugar, taken from Sun's Java package, but the
+    special opcodes can optimize it.
+
+    Some (but not all) possessively repeated subpatterns have already been
+    completely handled in the code just above. For them, possessive_quantifier
+    is always FALSE at this stage.
+
+    Note that the repeated item starts at tempcode, not at previous, which
+    might be the first part of a string whose (former) last char we repeated.
+
+    Possessifying an 'exact' quantifier has no effect, so we can ignore it. But
+    an 'upto' may follow. We skip over an 'exact' item, and then test the
+    length of what remains before proceeding. */
+
+    if (possessive_quantifier)
+      {
+      int len;
+
+      if (*tempcode == OP_TYPEEXACT)
+        tempcode += PRIV(OP_lengths)[*tempcode] +
+          ((tempcode[1 + IMM2_SIZE] == OP_PROP
+          || tempcode[1 + IMM2_SIZE] == OP_NOTPROP)? 2 : 0);
+
+      else if (*tempcode == OP_EXACT || *tempcode == OP_NOTEXACT)
+        {
+        tempcode += PRIV(OP_lengths)[*tempcode];
+#ifdef SUPPORT_UTF
+        if (utf && HAS_EXTRALEN(tempcode[-1]))
+          tempcode += GET_EXTRALEN(tempcode[-1]);
+#endif
+        }
+
+      len = (int)(code - tempcode);
+      if (len > 0) switch (*tempcode)
+        {
+        case OP_STAR:  *tempcode = OP_POSSTAR; break;
+        case OP_PLUS:  *tempcode = OP_POSPLUS; break;
+        case OP_QUERY: *tempcode = OP_POSQUERY; break;
+        case OP_UPTO:  *tempcode = OP_POSUPTO; break;
+
+        case OP_STARI:  *tempcode = OP_POSSTARI; break;
+        case OP_PLUSI:  *tempcode = OP_POSPLUSI; break;
+        case OP_QUERYI: *tempcode = OP_POSQUERYI; break;
+        case OP_UPTOI:  *tempcode = OP_POSUPTOI; break;
+
+        case OP_NOTSTAR:  *tempcode = OP_NOTPOSSTAR; break;
+        case OP_NOTPLUS:  *tempcode = OP_NOTPOSPLUS; break;
+        case OP_NOTQUERY: *tempcode = OP_NOTPOSQUERY; break;
+        case OP_NOTUPTO:  *tempcode = OP_NOTPOSUPTO; break;
+
+        case OP_NOTSTARI:  *tempcode = OP_NOTPOSSTARI; break;
+        case OP_NOTPLUSI:  *tempcode = OP_NOTPOSPLUSI; break;
+        case OP_NOTQUERYI: *tempcode = OP_NOTPOSQUERYI; break;
+        case OP_NOTUPTOI:  *tempcode = OP_NOTPOSUPTOI; break;
+
+        case OP_TYPESTAR:  *tempcode = OP_TYPEPOSSTAR; break;
+        case OP_TYPEPLUS:  *tempcode = OP_TYPEPOSPLUS; break;
+        case OP_TYPEQUERY: *tempcode = OP_TYPEPOSQUERY; break;
+        case OP_TYPEUPTO:  *tempcode = OP_TYPEPOSUPTO; break;
+
+        /* Because we are moving code along, we must ensure that any
+        pending recursive references are updated. */
+
+        default:
+        *code = OP_END;
+        adjust_recurse(tempcode, 1 + LINK_SIZE, utf, cd, save_hwm);
+        memmove(tempcode + 1 + LINK_SIZE, tempcode, IN_UCHARS(len));
+        code += 1 + LINK_SIZE;
+        len += 1 + LINK_SIZE;
+        tempcode[0] = OP_ONCE;
+        *code++ = OP_KET;
+        PUTINC(code, 0, len);
+        PUT(tempcode, 1, len);
+        break;
+        }
+      }
+
+    /* In all case we no longer have a previous item. We also set the
+    "follows varying string" flag for subsequently encountered reqchars if
+    it isn't already set and we have just passed a varying length item. */
+
+    END_REPEAT:
+    previous = NULL;
+    cd->req_varyopt |= reqvary;
+    break;
+
+
+    /* ===================================================================*/
+    /* Start of nested parenthesized sub-expression, or comment or lookahead or
+    lookbehind or option setting or condition or all the other extended
+    parenthesis forms.  */
+
+    case CHAR_LEFT_PARENTHESIS:
+    newoptions = options;
+    skipbytes = 0;
+    bravalue = OP_CBRA;
+    save_hwm = cd->hwm;
+    reset_bracount = FALSE;
+
+    /* First deal with various "verbs" that can be introduced by '*'. */
+
+    ptr++;
+    if (ptr[0] == CHAR_ASTERISK && (ptr[1] == ':'
+         || (MAX_255(ptr[1]) && ((cd->ctypes[ptr[1]] & ctype_letter) != 0))))
+      {
+      int i, namelen;
+      int arglen = 0;
+      const char *vn = verbnames;
+      const pcre_uchar *name = ptr + 1;
+      const pcre_uchar *arg = NULL;
+      previous = NULL;
+      ptr++;
+      while (MAX_255(*ptr) && (cd->ctypes[*ptr] & ctype_letter) != 0) ptr++;
+      namelen = (int)(ptr - name);
+
+      /* It appears that Perl allows any characters whatsoever, other than
+      a closing parenthesis, to appear in arguments, so we no longer insist on
+      letters, digits, and underscores. */
+
+      if (*ptr == CHAR_COLON)
+        {
+        arg = ++ptr;
+        while (*ptr != 0 && *ptr != CHAR_RIGHT_PARENTHESIS) ptr++;
+        arglen = (int)(ptr - arg);
+        if (arglen > (int)MAX_MARK)
+          {
+          *errorcodeptr = ERR75;
+          goto FAILED;
+          }
+        }
+
+      if (*ptr != CHAR_RIGHT_PARENTHESIS)
+        {
+        *errorcodeptr = ERR60;
+        goto FAILED;
+        }
+
+      /* Scan the table of verb names */
+
+      for (i = 0; i < verbcount; i++)
+        {
+        if (namelen == verbs[i].len &&
+            STRNCMP_UC_C8(name, vn, namelen) == 0)
+          {
+          /* Check for open captures before ACCEPT and convert it to
+          ASSERT_ACCEPT if in an assertion. */
+
+          if (verbs[i].op == OP_ACCEPT)
+            {
+            open_capitem *oc;
+            if (arglen != 0)
+              {
+              *errorcodeptr = ERR59;
+              goto FAILED;
+              }
+            cd->had_accept = TRUE;
+            for (oc = cd->open_caps; oc != NULL; oc = oc->next)
+              {
+              *code++ = OP_CLOSE;
+              PUT2INC(code, 0, oc->number);
+              }
+            *code++ = (cd->assert_depth > 0)? OP_ASSERT_ACCEPT : OP_ACCEPT;
+
+            /* Do not set firstchar after *ACCEPT */
+            if (firstchar == REQ_UNSET) firstchar = REQ_NONE;
+            }
+
+          /* Handle other cases with/without an argument */
+
+          else if (arglen == 0)
+            {
+            if (verbs[i].op < 0)   /* Argument is mandatory */
+              {
+              *errorcodeptr = ERR66;
+              goto FAILED;
+              }
+            *code = verbs[i].op;
+            if (*code++ == OP_THEN) cd->external_flags |= PCRE_HASTHEN;
+            }
+
+          else
+            {
+            if (verbs[i].op_arg < 0)   /* Argument is forbidden */
+              {
+              *errorcodeptr = ERR59;
+              goto FAILED;
+              }
+            *code = verbs[i].op_arg;
+            if (*code++ == OP_THEN_ARG) cd->external_flags |= PCRE_HASTHEN;
+            *code++ = arglen;
+            memcpy(code, arg, IN_UCHARS(arglen));
+            code += arglen;
+            *code++ = 0;
+            }
+
+          break;  /* Found verb, exit loop */
+          }
+
+        vn += verbs[i].len + 1;
+        }
+
+      if (i < verbcount) continue;    /* Successfully handled a verb */
+      *errorcodeptr = ERR60;          /* Verb not recognized */
+      goto FAILED;
+      }
+
+    /* Deal with the extended parentheses; all are introduced by '?', and the
+    appearance of any of them means that this is not a capturing group. */
+
+    else if (*ptr == CHAR_QUESTION_MARK)
+      {
+      int i, set, unset, namelen;
+      int *optset;
+      const pcre_uchar *name;
+      pcre_uchar *slot;
+
+      switch (*(++ptr))
+        {
+        case CHAR_NUMBER_SIGN:                 /* Comment; skip to ket */
+        ptr++;
+        while (*ptr != 0 && *ptr != CHAR_RIGHT_PARENTHESIS) ptr++;
+        if (*ptr == 0)
+          {
+          *errorcodeptr = ERR18;
+          goto FAILED;
+          }
+        continue;
+
+
+        /* ------------------------------------------------------------ */
+        case CHAR_VERTICAL_LINE:  /* Reset capture count for each branch */
+        reset_bracount = TRUE;
+        /* Fall through */
+
+        /* ------------------------------------------------------------ */
+        case CHAR_COLON:          /* Non-capturing bracket */
+        bravalue = OP_BRA;
+        ptr++;
+        break;
+
+
+        /* ------------------------------------------------------------ */
+        case CHAR_LEFT_PARENTHESIS:
+        bravalue = OP_COND;       /* Conditional group */
+
+        /* A condition can be an assertion, a number (referring to a numbered
+        group), a name (referring to a named group), or 'R', referring to
+        recursion. R<digits> and R&name are also permitted for recursion tests.
+
+        There are several syntaxes for testing a named group: (?(name)) is used
+        by Python; Perl 5.10 onwards uses (?(<name>) or (?('name')).
+
+        There are two unfortunate ambiguities, caused by history. (a) 'R' can
+        be the recursive thing or the name 'R' (and similarly for 'R' followed
+        by digits), and (b) a number could be a name that consists of digits.
+        In both cases, we look for a name first; if not found, we try the other
+        cases. */
+
+        /* For conditions that are assertions, check the syntax, and then exit
+        the switch. This will take control down to where bracketed groups,
+        including assertions, are processed. */
+
+        if (ptr[1] == CHAR_QUESTION_MARK && (ptr[2] == CHAR_EQUALS_SIGN ||
+            ptr[2] == CHAR_EXCLAMATION_MARK || ptr[2] == CHAR_LESS_THAN_SIGN))
+          break;
+
+        /* Most other conditions use OP_CREF (a couple change to OP_RREF
+        below), and all need to skip 1+IMM2_SIZE bytes at the start of the group. */
+
+        code[1+LINK_SIZE] = OP_CREF;
+        skipbytes = 1+IMM2_SIZE;
+        refsign = -1;
+
+        /* Check for a test for recursion in a named group. */
+
+        if (ptr[1] == CHAR_R && ptr[2] == CHAR_AMPERSAND)
+          {
+          terminator = -1;
+          ptr += 2;
+          code[1+LINK_SIZE] = OP_RREF;    /* Change the type of test */
+          }
+
+        /* Check for a test for a named group's having been set, using the Perl
+        syntax (?(<name>) or (?('name') */
+
+        else if (ptr[1] == CHAR_LESS_THAN_SIGN)
+          {
+          terminator = CHAR_GREATER_THAN_SIGN;
+          ptr++;
+          }
+        else if (ptr[1] == CHAR_APOSTROPHE)
+          {
+          terminator = CHAR_APOSTROPHE;
+          ptr++;
+          }
+        else
+          {
+          terminator = 0;
+          if (ptr[1] == CHAR_MINUS || ptr[1] == CHAR_PLUS) refsign = *(++ptr);
+          }
+
+        /* We now expect to read a name; any thing else is an error */
+
+        if (!MAX_255(ptr[1]) || (cd->ctypes[ptr[1]] & ctype_word) == 0)
+          {
+          ptr += 1;  /* To get the right offset */
+          *errorcodeptr = ERR28;
+          goto FAILED;
+          }
+
+        /* Read the name, but also get it as a number if it's all digits */
+
+        recno = 0;
+        name = ++ptr;
+        while (MAX_255(*ptr) && (cd->ctypes[*ptr] & ctype_word) != 0)
+          {
+          if (recno >= 0)
+            recno = (IS_DIGIT(*ptr))? recno * 10 + *ptr - CHAR_0 : -1;
+          ptr++;
+          }
+        namelen = (int)(ptr - name);
+
+        if ((terminator > 0 && *ptr++ != terminator) ||
+            *ptr++ != CHAR_RIGHT_PARENTHESIS)
+          {
+          ptr--;      /* Error offset */
+          *errorcodeptr = ERR26;
+          goto FAILED;
+          }
+
+        /* Do no further checking in the pre-compile phase. */
+
+        if (lengthptr != NULL) break;
+
+        /* In the real compile we do the work of looking for the actual
+        reference. If the string started with "+" or "-" we require the rest to
+        be digits, in which case recno will be set. */
+
+        if (refsign > 0)
+          {
+          if (recno <= 0)
+            {
+            *errorcodeptr = ERR58;
+            goto FAILED;
+            }
+          recno = (refsign == CHAR_MINUS)?
+            cd->bracount - recno + 1 : recno +cd->bracount;
+          if (recno <= 0 || recno > cd->final_bracount)
+            {
+            *errorcodeptr = ERR15;
+            goto FAILED;
+            }
+          PUT2(code, 2+LINK_SIZE, recno);
+          break;
+          }
+
+        /* Otherwise (did not start with "+" or "-"), start by looking for the
+        name. If we find a name, add one to the opcode to change OP_CREF or
+        OP_RREF into OP_NCREF or OP_NRREF. These behave exactly the same,
+        except they record that the reference was originally to a name. The
+        information is used to check duplicate names. */
+
+        slot = cd->name_table;
+        for (i = 0; i < cd->names_found; i++)
+          {
+          if (STRNCMP_UC_UC(name, slot+IMM2_SIZE, namelen) == 0) break;
+          slot += cd->name_entry_size;
+          }
+
+        /* Found a previous named subpattern */
+
+        if (i < cd->names_found)
+          {
+          recno = GET2(slot, 0);
+          PUT2(code, 2+LINK_SIZE, recno);
+          code[1+LINK_SIZE]++;
+          }
+
+        /* Search the pattern for a forward reference */
+
+        else if ((i = find_parens(cd, name, namelen,
+                        (options & PCRE_EXTENDED) != 0, utf)) > 0)
+          {
+          PUT2(code, 2+LINK_SIZE, i);
+          code[1+LINK_SIZE]++;
+          }
+
+        /* If terminator == 0 it means that the name followed directly after
+        the opening parenthesis [e.g. (?(abc)...] and in this case there are
+        some further alternatives to try. For the cases where terminator != 0
+        [things like (?(<name>... or (?('name')... or (?(R&name)... ] we have
+        now checked all the possibilities, so give an error. */
+
+        else if (terminator != 0)
+          {
+          *errorcodeptr = ERR15;
+          goto FAILED;
+          }
+
+        /* Check for (?(R) for recursion. Allow digits after R to specify a
+        specific group number. */
+
+        else if (*name == CHAR_R)
+          {
+          recno = 0;
+          for (i = 1; i < namelen; i++)
+            {
+            if (!IS_DIGIT(name[i]))
+              {
+              *errorcodeptr = ERR15;
+              goto FAILED;
+              }
+            recno = recno * 10 + name[i] - CHAR_0;
+            }
+          if (recno == 0) recno = RREF_ANY;
+          code[1+LINK_SIZE] = OP_RREF;      /* Change test type */
+          PUT2(code, 2+LINK_SIZE, recno);
+          }
+
+        /* Similarly, check for the (?(DEFINE) "condition", which is always
+        false. */
+
+        else if (namelen == 6 && STRNCMP_UC_C8(name, STRING_DEFINE, 6) == 0)
+          {
+          code[1+LINK_SIZE] = OP_DEF;
+          skipbytes = 1;
+          }
+
+        /* Check for the "name" actually being a subpattern number. We are
+        in the second pass here, so final_bracount is set. */
+
+        else if (recno > 0 && recno <= cd->final_bracount)
+          {
+          PUT2(code, 2+LINK_SIZE, recno);
+          }
+
+        /* Either an unidentified subpattern, or a reference to (?(0) */
+
+        else
+          {
+          *errorcodeptr = (recno == 0)? ERR35: ERR15;
+          goto FAILED;
+          }
+        break;
+
+
+        /* ------------------------------------------------------------ */
+        case CHAR_EQUALS_SIGN:                 /* Positive lookahead */
+        bravalue = OP_ASSERT;
+        cd->assert_depth += 1;
+        ptr++;
+        break;
+
+
+        /* ------------------------------------------------------------ */
+        case CHAR_EXCLAMATION_MARK:            /* Negative lookahead */
+        ptr++;
+        if (*ptr == CHAR_RIGHT_PARENTHESIS)    /* Optimize (?!) */
+          {
+          *code++ = OP_FAIL;
+          previous = NULL;
+          continue;
+          }
+        bravalue = OP_ASSERT_NOT;
+        cd->assert_depth += 1;
+        break;
+
+
+        /* ------------------------------------------------------------ */
+        case CHAR_LESS_THAN_SIGN:              /* Lookbehind or named define */
+        switch (ptr[1])
+          {
+          case CHAR_EQUALS_SIGN:               /* Positive lookbehind */
+          bravalue = OP_ASSERTBACK;
+          cd->assert_depth += 1;
+          ptr += 2;
+          break;
+
+          case CHAR_EXCLAMATION_MARK:          /* Negative lookbehind */
+          bravalue = OP_ASSERTBACK_NOT;
+          cd->assert_depth += 1;
+          ptr += 2;
+          break;
+
+          default:                /* Could be name define, else bad */
+          if (MAX_255(ptr[1]) && (cd->ctypes[ptr[1]] & ctype_word) != 0)
+            goto DEFINE_NAME;
+          ptr++;                  /* Correct offset for error */
+          *errorcodeptr = ERR24;
+          goto FAILED;
+          }
+        break;
+
+
+        /* ------------------------------------------------------------ */
+        case CHAR_GREATER_THAN_SIGN:           /* One-time brackets */
+        bravalue = OP_ONCE;
+        ptr++;
+        break;
+
+
+        /* ------------------------------------------------------------ */
+        case CHAR_C:                 /* Callout - may be followed by digits; */
+        previous_callout = code;     /* Save for later completion */
+        after_manual_callout = 1;    /* Skip one item before completing */
+        *code++ = OP_CALLOUT;
+          {
+          int n = 0;
+          ptr++;
+          while(IS_DIGIT(*ptr))
+            n = n * 10 + *ptr++ - CHAR_0;
+          if (*ptr != CHAR_RIGHT_PARENTHESIS)
+            {
+            *errorcodeptr = ERR39;
+            goto FAILED;
+            }
+          if (n > 255)
+            {
+            *errorcodeptr = ERR38;
+            goto FAILED;
+            }
+          *code++ = n;
+          PUT(code, 0, (int)(ptr - cd->start_pattern + 1)); /* Pattern offset */
+          PUT(code, LINK_SIZE, 0);                          /* Default length */
+          code += 2 * LINK_SIZE;
+          }
+        previous = NULL;
+        continue;
+
+
+        /* ------------------------------------------------------------ */
+        case CHAR_P:              /* Python-style named subpattern handling */
+        if (*(++ptr) == CHAR_EQUALS_SIGN ||
+            *ptr == CHAR_GREATER_THAN_SIGN)  /* Reference or recursion */
+          {
+          is_recurse = *ptr == CHAR_GREATER_THAN_SIGN;
+          terminator = CHAR_RIGHT_PARENTHESIS;
+          goto NAMED_REF_OR_RECURSE;
+          }
+        else if (*ptr != CHAR_LESS_THAN_SIGN)  /* Test for Python-style defn */
+          {
+          *errorcodeptr = ERR41;
+          goto FAILED;
+          }
+        /* Fall through to handle (?P< as (?< is handled */
+
+
+        /* ------------------------------------------------------------ */
+        DEFINE_NAME:    /* Come here from (?< handling */
+        case CHAR_APOSTROPHE:
+          {
+          terminator = (*ptr == CHAR_LESS_THAN_SIGN)?
+            CHAR_GREATER_THAN_SIGN : CHAR_APOSTROPHE;
+          name = ++ptr;
+
+          while (MAX_255(*ptr) && (cd->ctypes[*ptr] & ctype_word) != 0) ptr++;
+          namelen = (int)(ptr - name);
+
+          /* In the pre-compile phase, just do a syntax check. */
+
+          if (lengthptr != NULL)
+            {
+            if (*ptr != terminator)
+              {
+              *errorcodeptr = ERR42;
+              goto FAILED;
+              }
+            if (cd->names_found >= MAX_NAME_COUNT)
+              {
+              *errorcodeptr = ERR49;
+              goto FAILED;
+              }
+            if (namelen + IMM2_SIZE + 1 > cd->name_entry_size)
+              {
+              cd->name_entry_size = namelen + IMM2_SIZE + 1;
+              if (namelen > MAX_NAME_SIZE)
+                {
+                *errorcodeptr = ERR48;
+                goto FAILED;
+                }
+              }
+            }
+
+          /* In the real compile, create the entry in the table, maintaining
+          alphabetical order. Duplicate names for different numbers are
+          permitted only if PCRE_DUPNAMES is set. Duplicate names for the same
+          number are always OK. (An existing number can be re-used if (?|
+          appears in the pattern.) In either event, a duplicate name results in
+          a duplicate entry in the table, even if the number is the same. This
+          is because the number of names, and hence the table size, is computed
+          in the pre-compile, and it affects various numbers and pointers which
+          would all have to be modified, and the compiled code moved down, if
+          duplicates with the same number were omitted from the table. This
+          doesn't seem worth the hassle. However, *different* names for the
+          same number are not permitted. */
+
+          else
+            {
+            BOOL dupname = FALSE;
+            slot = cd->name_table;
+
+            for (i = 0; i < cd->names_found; i++)
+              {
+              int crc = memcmp(name, slot+IMM2_SIZE, IN_UCHARS(namelen));
+              if (crc == 0)
+                {
+                if (slot[IMM2_SIZE+namelen] == 0)
+                  {
+                  if (GET2(slot, 0) != cd->bracount + 1 &&
+                      (options & PCRE_DUPNAMES) == 0)
+                    {
+                    *errorcodeptr = ERR43;
+                    goto FAILED;
+                    }
+                  else dupname = TRUE;
+                  }
+                else crc = -1;      /* Current name is a substring */
+                }
+
+              /* Make space in the table and break the loop for an earlier
+              name. For a duplicate or later name, carry on. We do this for
+              duplicates so that in the simple case (when ?(| is not used) they
+              are in order of their numbers. */
+
+              if (crc < 0)
+                {
+                memmove(slot + cd->name_entry_size, slot,
+                  IN_UCHARS((cd->names_found - i) * cd->name_entry_size));
+                break;
+                }
+
+              /* Continue the loop for a later or duplicate name */
+
+              slot += cd->name_entry_size;
+              }
+
+            /* For non-duplicate names, check for a duplicate number before
+            adding the new name. */
+
+            if (!dupname)
+              {
+              pcre_uchar *cslot = cd->name_table;
+              for (i = 0; i < cd->names_found; i++)
+                {
+                if (cslot != slot)
+                  {
+                  if (GET2(cslot, 0) == cd->bracount + 1)
+                    {
+                    *errorcodeptr = ERR65;
+                    goto FAILED;
+                    }
+                  }
+                else i--;
+                cslot += cd->name_entry_size;
+                }
+              }
+
+            PUT2(slot, 0, cd->bracount + 1);
+            memcpy(slot + IMM2_SIZE, name, IN_UCHARS(namelen));
+            slot[IMM2_SIZE + namelen] = 0;
+            }
+          }
+
+        /* In both pre-compile and compile, count the number of names we've
+        encountered. */
+
+        cd->names_found++;
+        ptr++;                    /* Move past > or ' */
+        goto NUMBERED_GROUP;
+
+
+        /* ------------------------------------------------------------ */
+        case CHAR_AMPERSAND:            /* Perl recursion/subroutine syntax */
+        terminator = CHAR_RIGHT_PARENTHESIS;
+        is_recurse = TRUE;
+        /* Fall through */
+
+        /* We come here from the Python syntax above that handles both
+        references (?P=name) and recursion (?P>name), as well as falling
+        through from the Perl recursion syntax (?&name). We also come here from
+        the Perl \k<name> or \k'name' back reference syntax and the \k{name}
+        .NET syntax, and the Oniguruma \g<...> and \g'...' subroutine syntax. */
+
+        NAMED_REF_OR_RECURSE:
+        name = ++ptr;
+        while (MAX_255(*ptr) && (cd->ctypes[*ptr] & ctype_word) != 0) ptr++;
+        namelen = (int)(ptr - name);
+
+        /* In the pre-compile phase, do a syntax check. We used to just set
+        a dummy reference number, because it was not used in the first pass.
+        However, with the change of recursive back references to be atomic,
+        we have to look for the number so that this state can be identified, as
+        otherwise the incorrect length is computed. If it's not a backwards
+        reference, the dummy number will do. */
+
+        if (lengthptr != NULL)
+          {
+          const pcre_uchar *temp;
+
+          if (namelen == 0)
+            {
+            *errorcodeptr = ERR62;
+            goto FAILED;
+            }
+          if (*ptr != terminator)
+            {
+            *errorcodeptr = ERR42;
+            goto FAILED;
+            }
+          if (namelen > MAX_NAME_SIZE)
+            {
+            *errorcodeptr = ERR48;
+            goto FAILED;
+            }
+
+          /* The name table does not exist in the first pass, so we cannot
+          do a simple search as in the code below. Instead, we have to scan the
+          pattern to find the number. It is important that we scan it only as
+          far as we have got because the syntax of named subpatterns has not
+          been checked for the rest of the pattern, and find_parens() assumes
+          correct syntax. In any case, it's a waste of resources to scan
+          further. We stop the scan at the current point by temporarily
+          adjusting the value of cd->endpattern. */
+
+          temp = cd->end_pattern;
+          cd->end_pattern = ptr;
+          recno = find_parens(cd, name, namelen,
+            (options & PCRE_EXTENDED) != 0, utf);
+          cd->end_pattern = temp;
+          if (recno < 0) recno = 0;    /* Forward ref; set dummy number */
+          }
+
+        /* In the real compile, seek the name in the table. We check the name
+        first, and then check that we have reached the end of the name in the
+        table. That way, if the name that is longer than any in the table,
+        the comparison will fail without reading beyond the table entry. */
+
+        else
+          {
+          slot = cd->name_table;
+          for (i = 0; i < cd->names_found; i++)
+            {
+            if (STRNCMP_UC_UC(name, slot+IMM2_SIZE, namelen) == 0 &&
+                slot[IMM2_SIZE+namelen] == 0)
+              break;
+            slot += cd->name_entry_size;
+            }
+
+          if (i < cd->names_found)         /* Back reference */
+            {
+            recno = GET2(slot, 0);
+            }
+          else if ((recno =                /* Forward back reference */
+                    find_parens(cd, name, namelen,
+                      (options & PCRE_EXTENDED) != 0, utf)) <= 0)
+            {
+            *errorcodeptr = ERR15;
+            goto FAILED;
+            }
+          }
+
+        /* In both phases, we can now go to the code than handles numerical
+        recursion or backreferences. */
+
+        if (is_recurse) goto HANDLE_RECURSION;
+          else goto HANDLE_REFERENCE;
+
+
+        /* ------------------------------------------------------------ */
+        case CHAR_R:              /* Recursion */
+        ptr++;                    /* Same as (?0)      */
+        /* Fall through */
+
+
+        /* ------------------------------------------------------------ */
+        case CHAR_MINUS: case CHAR_PLUS:  /* Recursion or subroutine */
+        case CHAR_0: case CHAR_1: case CHAR_2: case CHAR_3: case CHAR_4:
+        case CHAR_5: case CHAR_6: case CHAR_7: case CHAR_8: case CHAR_9:
+          {
+          const pcre_uchar *called;
+          terminator = CHAR_RIGHT_PARENTHESIS;
+
+          /* Come here from the \g<...> and \g'...' code (Oniguruma
+          compatibility). However, the syntax has been checked to ensure that
+          the ... are a (signed) number, so that neither ERR63 nor ERR29 will
+          be called on this path, nor with the jump to OTHER_CHAR_AFTER_QUERY
+          ever be taken. */
+
+          HANDLE_NUMERICAL_RECURSION:
+
+          if ((refsign = *ptr) == CHAR_PLUS)
+            {
+            ptr++;
+            if (!IS_DIGIT(*ptr))
+              {
+              *errorcodeptr = ERR63;
+              goto FAILED;
+              }
+            }
+          else if (refsign == CHAR_MINUS)
+            {
+            if (!IS_DIGIT(ptr[1]))
+              goto OTHER_CHAR_AFTER_QUERY;
+            ptr++;
+            }
+
+          recno = 0;
+          while(IS_DIGIT(*ptr))
+            recno = recno * 10 + *ptr++ - CHAR_0;
+
+          if (*ptr != terminator)
+            {
+            *errorcodeptr = ERR29;
+            goto FAILED;
+            }
+
+          if (refsign == CHAR_MINUS)
+            {
+            if (recno == 0)
+              {
+              *errorcodeptr = ERR58;
+              goto FAILED;
+              }
+            recno = cd->bracount - recno + 1;
+            if (recno <= 0)
+              {
+              *errorcodeptr = ERR15;
+              goto FAILED;
+              }
+            }
+          else if (refsign == CHAR_PLUS)
+            {
+            if (recno == 0)
+              {
+              *errorcodeptr = ERR58;
+              goto FAILED;
+              }
+            recno += cd->bracount;
+            }
+
+          /* Come here from code above that handles a named recursion */
+
+          HANDLE_RECURSION:
+
+          previous = code;
+          called = cd->start_code;
+
+          /* When we are actually compiling, find the bracket that is being
+          referenced. Temporarily end the regex in case it doesn't exist before
+          this point. If we end up with a forward reference, first check that
+          the bracket does occur later so we can give the error (and position)
+          now. Then remember this forward reference in the workspace so it can
+          be filled in at the end. */
+
+          if (lengthptr == NULL)
+            {
+            *code = OP_END;
+            if (recno != 0)
+              called = PRIV(find_bracket)(cd->start_code, utf, recno);
+
+            /* Forward reference */
+
+            if (called == NULL)
+              {
+              if (find_parens(cd, NULL, recno,
+                    (options & PCRE_EXTENDED) != 0, utf) < 0)
+                {
+                *errorcodeptr = ERR15;
+                goto FAILED;
+                }
+
+              /* Fudge the value of "called" so that when it is inserted as an
+              offset below, what it actually inserted is the reference number
+              of the group. Then remember the forward reference. */
+
+              called = cd->start_code + recno;
+              if (cd->hwm >= cd->start_workspace + cd->workspace_size -
+                  WORK_SIZE_SAFETY_MARGIN)
+                {
+                *errorcodeptr = expand_workspace(cd);
+                if (*errorcodeptr != 0) goto FAILED;
+                }
+              PUTINC(cd->hwm, 0, (int)(code + 1 - cd->start_code));
+              }
+
+            /* If not a forward reference, and the subpattern is still open,
+            this is a recursive call. We check to see if this is a left
+            recursion that could loop for ever, and diagnose that case. We
+            must not, however, do this check if we are in a conditional
+            subpattern because the condition might be testing for recursion in
+            a pattern such as /(?(R)a+|(?R)b)/, which is perfectly valid.
+            Forever loops are also detected at runtime, so those that occur in
+            conditional subpatterns will be picked up then. */
+
+            else if (GET(called, 1) == 0 && cond_depth <= 0 &&
+                     could_be_empty(called, code, bcptr, utf, cd))
+              {
+              *errorcodeptr = ERR40;
+              goto FAILED;
+              }
+            }
+
+          /* Insert the recursion/subroutine item. It does not have a set first
+          character (relevant if it is repeated, because it will then be
+          wrapped with ONCE brackets). */
+
+          *code = OP_RECURSE;
+          PUT(code, 1, (int)(called - cd->start_code));
+          code += 1 + LINK_SIZE;
+          groupsetfirstchar = FALSE;
+          }
+
+        /* Can't determine a first byte now */
+
+        if (firstchar == REQ_UNSET) firstchar = REQ_NONE;
+        continue;
+
+
+        /* ------------------------------------------------------------ */
+        default:              /* Other characters: check option setting */
+        OTHER_CHAR_AFTER_QUERY:
+        set = unset = 0;
+        optset = &set;
+
+        while (*ptr != CHAR_RIGHT_PARENTHESIS && *ptr != CHAR_COLON)
+          {
+          switch (*ptr++)
+            {
+            case CHAR_MINUS: optset = &unset; break;
+
+            case CHAR_J:    /* Record that it changed in the external options */
+            *optset |= PCRE_DUPNAMES;
+            cd->external_flags |= PCRE_JCHANGED;
+            break;
+
+            case CHAR_i: *optset |= PCRE_CASELESS; break;
+            case CHAR_m: *optset |= PCRE_MULTILINE; break;
+            case CHAR_s: *optset |= PCRE_DOTALL; break;
+            case CHAR_x: *optset |= PCRE_EXTENDED; break;
+            case CHAR_U: *optset |= PCRE_UNGREEDY; break;
+            case CHAR_X: *optset |= PCRE_EXTRA; break;
+
+            default:  *errorcodeptr = ERR12;
+                      ptr--;    /* Correct the offset */
+                      goto FAILED;
+            }
+          }
+
+        /* Set up the changed option bits, but don't change anything yet. */
+
+        newoptions = (options | set) & (~unset);
+
+        /* If the options ended with ')' this is not the start of a nested
+        group with option changes, so the options change at this level. If this
+        item is right at the start of the pattern, the options can be
+        abstracted and made external in the pre-compile phase, and ignored in
+        the compile phase. This can be helpful when matching -- for instance in
+        caseless checking of required bytes.
+
+        If the code pointer is not (cd->start_code + 1 + LINK_SIZE), we are
+        definitely *not* at the start of the pattern because something has been
+        compiled. In the pre-compile phase, however, the code pointer can have
+        that value after the start, because it gets reset as code is discarded
+        during the pre-compile. However, this can happen only at top level - if
+        we are within parentheses, the starting BRA will still be present. At
+        any parenthesis level, the length value can be used to test if anything
+        has been compiled at that level. Thus, a test for both these conditions
+        is necessary to ensure we correctly detect the start of the pattern in
+        both phases.
+
+        If we are not at the pattern start, reset the greedy defaults and the
+        case value for firstchar and reqchar. */
+
+        if (*ptr == CHAR_RIGHT_PARENTHESIS)
+          {
+          if (code == cd->start_code + 1 + LINK_SIZE &&
+               (lengthptr == NULL || *lengthptr == 2 + 2*LINK_SIZE))
+            {
+            cd->external_options = newoptions;
+            }
+          else
+            {
+            greedy_default = ((newoptions & PCRE_UNGREEDY) != 0);
+            greedy_non_default = greedy_default ^ 1;
+            req_caseopt = ((newoptions & PCRE_CASELESS) != 0)? REQ_CASELESS:0;
+            }
+
+          /* Change options at this level, and pass them back for use
+          in subsequent branches. */
+
+          *optionsptr = options = newoptions;
+          previous = NULL;       /* This item can't be repeated */
+          continue;              /* It is complete */
+          }
+
+        /* If the options ended with ':' we are heading into a nested group
+        with possible change of options. Such groups are non-capturing and are
+        not assertions of any kind. All we need to do is skip over the ':';
+        the newoptions value is handled below. */
+
+        bravalue = OP_BRA;
+        ptr++;
+        }     /* End of switch for character following (? */
+      }       /* End of (? handling */
+
+    /* Opening parenthesis not followed by '*' or '?'. If PCRE_NO_AUTO_CAPTURE
+    is set, all unadorned brackets become non-capturing and behave like (?:...)
+    brackets. */
+
+    else if ((options & PCRE_NO_AUTO_CAPTURE) != 0)
+      {
+      bravalue = OP_BRA;
+      }
+
+    /* Else we have a capturing group. */
+
+    else
+      {
+      NUMBERED_GROUP:
+      cd->bracount += 1;
+      PUT2(code, 1+LINK_SIZE, cd->bracount);
+      skipbytes = IMM2_SIZE;
+      }
+
+    /* Process nested bracketed regex. Assertions used not to be repeatable,
+    but this was changed for Perl compatibility, so all kinds can now be
+    repeated. We copy code into a non-register variable (tempcode) in order to
+    be able to pass its address because some compilers complain otherwise. */
+
+    previous = code;                      /* For handling repetition */
+    *code = bravalue;
+    tempcode = code;
+    tempreqvary = cd->req_varyopt;        /* Save value before bracket */
+    tempbracount = cd->bracount;          /* Save value before bracket */
+    length_prevgroup = 0;                 /* Initialize for pre-compile phase */
+
+    if (!compile_regex(
+         newoptions,                      /* The complete new option state */
+         &tempcode,                       /* Where to put code (updated) */
+         &ptr,                            /* Input pointer (updated) */
+         errorcodeptr,                    /* Where to put an error message */
+         (bravalue == OP_ASSERTBACK ||
+          bravalue == OP_ASSERTBACK_NOT), /* TRUE if back assert */
+         reset_bracount,                  /* True if (?| group */
+         skipbytes,                       /* Skip over bracket number */
+         cond_depth +
+           ((bravalue == OP_COND)?1:0),   /* Depth of condition subpatterns */
+         &subfirstchar,                   /* For possible first char */
+         &subreqchar,                     /* For possible last char */
+         bcptr,                           /* Current branch chain */
+         cd,                              /* Tables block */
+         (lengthptr == NULL)? NULL :      /* Actual compile phase */
+           &length_prevgroup              /* Pre-compile phase */
+         ))
+      goto FAILED;
+
+    /* If this was an atomic group and there are no capturing groups within it,
+    generate OP_ONCE_NC instead of OP_ONCE. */
+
+    if (bravalue == OP_ONCE && cd->bracount <= tempbracount)
+      *code = OP_ONCE_NC;
+
+    if (bravalue >= OP_ASSERT && bravalue <= OP_ASSERTBACK_NOT)
+      cd->assert_depth -= 1;
+
+    /* At the end of compiling, code is still pointing to the start of the
+    group, while tempcode has been updated to point past the end of the group.
+    The pattern pointer (ptr) is on the bracket.
+
+    If this is a conditional bracket, check that there are no more than
+    two branches in the group, or just one if it's a DEFINE group. We do this
+    in the real compile phase, not in the pre-pass, where the whole group may
+    not be available. */
+
+    if (bravalue == OP_COND && lengthptr == NULL)
+      {
+      pcre_uchar *tc = code;
+      int condcount = 0;
+
+      do {
+         condcount++;
+         tc += GET(tc,1);
+         }
+      while (*tc != OP_KET);
+
+      /* A DEFINE group is never obeyed inline (the "condition" is always
+      false). It must have only one branch. */
+
+      if (code[LINK_SIZE+1] == OP_DEF)
+        {
+        if (condcount > 1)
+          {
+          *errorcodeptr = ERR54;
+          goto FAILED;
+          }
+        bravalue = OP_DEF;   /* Just a flag to suppress char handling below */
+        }
+
+      /* A "normal" conditional group. If there is just one branch, we must not
+      make use of its firstchar or reqchar, because this is equivalent to an
+      empty second branch. */
+
+      else
+        {
+        if (condcount > 2)
+          {
+          *errorcodeptr = ERR27;
+          goto FAILED;
+          }
+        if (condcount == 1) subfirstchar = subreqchar = REQ_NONE;
+        }
+      }
+
+    /* Error if hit end of pattern */
+
+    if (*ptr != CHAR_RIGHT_PARENTHESIS)
+      {
+      *errorcodeptr = ERR14;
+      goto FAILED;
+      }
+
+    /* In the pre-compile phase, update the length by the length of the group,
+    less the brackets at either end. Then reduce the compiled code to just a
+    set of non-capturing brackets so that it doesn't use much memory if it is
+    duplicated by a quantifier.*/
+
+    if (lengthptr != NULL)
+      {
+      if (OFLOW_MAX - *lengthptr < length_prevgroup - 2 - 2*LINK_SIZE)
+        {
+        *errorcodeptr = ERR20;
+        goto FAILED;
+        }
+      *lengthptr += length_prevgroup - 2 - 2*LINK_SIZE;
+      code++;   /* This already contains bravalue */
+      PUTINC(code, 0, 1 + LINK_SIZE);
+      *code++ = OP_KET;
+      PUTINC(code, 0, 1 + LINK_SIZE);
+      break;    /* No need to waste time with special character handling */
+      }
+
+    /* Otherwise update the main code pointer to the end of the group. */
+
+    code = tempcode;
+
+    /* For a DEFINE group, required and first character settings are not
+    relevant. */
+
+    if (bravalue == OP_DEF) break;
+
+    /* Handle updating of the required and first characters for other types of
+    group. Update for normal brackets of all kinds, and conditions with two
+    branches (see code above). If the bracket is followed by a quantifier with
+    zero repeat, we have to back off. Hence the definition of zeroreqchar and
+    zerofirstchar outside the main loop so that they can be accessed for the
+    back off. */
+
+    zeroreqchar = reqchar;
+    zerofirstchar = firstchar;
+    groupsetfirstchar = FALSE;
+
+    if (bravalue >= OP_ONCE)
+      {
+      /* If we have not yet set a firstchar in this branch, take it from the
+      subpattern, remembering that it was set here so that a repeat of more
+      than one can replicate it as reqchar if necessary. If the subpattern has
+      no firstchar, set "none" for the whole branch. In both cases, a zero
+      repeat forces firstchar to "none". */
+
+      if (firstchar == REQ_UNSET)
+        {
+        if (subfirstchar >= 0)
+          {
+          firstchar = subfirstchar;
+          groupsetfirstchar = TRUE;
+          }
+        else firstchar = REQ_NONE;
+        zerofirstchar = REQ_NONE;
+        }
+
+      /* If firstchar was previously set, convert the subpattern's firstchar
+      into reqchar if there wasn't one, using the vary flag that was in
+      existence beforehand. */
+
+      else if (subfirstchar >= 0 && subreqchar < 0)
+        subreqchar = subfirstchar | tempreqvary;
+
+      /* If the subpattern set a required byte (or set a first byte that isn't
+      really the first byte - see above), set it. */
+
+      if (subreqchar >= 0) reqchar = subreqchar;
+      }
+
+    /* For a forward assertion, we take the reqchar, if set. This can be
+    helpful if the pattern that follows the assertion doesn't set a different
+    char. For example, it's useful for /(?=abcde).+/. We can't set firstchar
+    for an assertion, however because it leads to incorrect effect for patterns
+    such as /(?=a)a.+/ when the "real" "a" would then become a reqchar instead
+    of a firstchar. This is overcome by a scan at the end if there's no
+    firstchar, looking for an asserted first char. */
+
+    else if (bravalue == OP_ASSERT && subreqchar >= 0) reqchar = subreqchar;
+    break;     /* End of processing '(' */
+
+
+    /* ===================================================================*/
+    /* Handle metasequences introduced by \. For ones like \d, the ESC_ values
+    are arranged to be the negation of the corresponding OP_values in the
+    default case when PCRE_UCP is not set. For the back references, the values
+    are ESC_REF plus the reference number. Only back references and those types
+    that consume a character may be repeated. We can test for values between
+    ESC_b and ESC_Z for the latter; this may have to change if any new ones are
+    ever created. */
+
+    case CHAR_BACKSLASH:
+    tempptr = ptr;
+    c = check_escape(&ptr, errorcodeptr, cd->bracount, options, FALSE);
+    if (*errorcodeptr != 0) goto FAILED;
+
+    if (c < 0)
+      {
+      if (-c == ESC_Q)            /* Handle start of quoted string */
+        {
+        if (ptr[1] == CHAR_BACKSLASH && ptr[2] == CHAR_E)
+          ptr += 2;               /* avoid empty string */
+            else inescq = TRUE;
+        continue;
+        }
+
+      if (-c == ESC_E) continue;  /* Perl ignores an orphan \E */
+
+      /* For metasequences that actually match a character, we disable the
+      setting of a first character if it hasn't already been set. */
+
+      if (firstchar == REQ_UNSET && -c > ESC_b && -c < ESC_Z)
+        firstchar = REQ_NONE;
+
+      /* Set values to reset to if this is followed by a zero repeat. */
+
+      zerofirstchar = firstchar;
+      zeroreqchar = reqchar;
+
+      /* \g<name> or \g'name' is a subroutine call by name and \g<n> or \g'n'
+      is a subroutine call by number (Oniguruma syntax). In fact, the value
+      -ESC_g is returned only for these cases. So we don't need to check for <
+      or ' if the value is -ESC_g. For the Perl syntax \g{n} the value is
+      -ESC_REF+n, and for the Perl syntax \g{name} the result is -ESC_k (as
+      that is a synonym for a named back reference). */
+
+      if (-c == ESC_g)
+        {
+        const pcre_uchar *p;
+        save_hwm = cd->hwm;   /* Normally this is set when '(' is read */
+        terminator = (*(++ptr) == CHAR_LESS_THAN_SIGN)?
+          CHAR_GREATER_THAN_SIGN : CHAR_APOSTROPHE;
+
+        /* These two statements stop the compiler for warning about possibly
+        unset variables caused by the jump to HANDLE_NUMERICAL_RECURSION. In
+        fact, because we actually check for a number below, the paths that
+        would actually be in error are never taken. */
+
+        skipbytes = 0;
+        reset_bracount = FALSE;
+
+        /* Test for a name */
+
+        if (ptr[1] != CHAR_PLUS && ptr[1] != CHAR_MINUS)
+          {
+          BOOL is_a_number = TRUE;
+          for (p = ptr + 1; *p != 0 && *p != terminator; p++)
+            {
+            if (!MAX_255(*p)) { is_a_number = FALSE; break; }
+            if ((cd->ctypes[*p] & ctype_digit) == 0) is_a_number = FALSE;
+            if ((cd->ctypes[*p] & ctype_word) == 0) break;
+            }
+          if (*p != terminator)
+            {
+            *errorcodeptr = ERR57;
+            break;
+            }
+          if (is_a_number)
+            {
+            ptr++;
+            goto HANDLE_NUMERICAL_RECURSION;
+            }
+          is_recurse = TRUE;
+          goto NAMED_REF_OR_RECURSE;
+          }
+
+        /* Test a signed number in angle brackets or quotes. */
+
+        p = ptr + 2;
+        while (IS_DIGIT(*p)) p++;
+        if (*p != terminator)
+          {
+          *errorcodeptr = ERR57;
+          break;
+          }
+        ptr++;
+        goto HANDLE_NUMERICAL_RECURSION;
+        }
+
+      /* \k<name> or \k'name' is a back reference by name (Perl syntax).
+      We also support \k{name} (.NET syntax).  */
+
+      if (-c == ESC_k)
+        {
+        if ((ptr[1] != CHAR_LESS_THAN_SIGN &&
+          ptr[1] != CHAR_APOSTROPHE && ptr[1] != CHAR_LEFT_CURLY_BRACKET))
+          {
+          *errorcodeptr = ERR69;
+          break;
+          }
+        is_recurse = FALSE;
+        terminator = (*(++ptr) == CHAR_LESS_THAN_SIGN)?
+          CHAR_GREATER_THAN_SIGN : (*ptr == CHAR_APOSTROPHE)?
+          CHAR_APOSTROPHE : CHAR_RIGHT_CURLY_BRACKET;
+        goto NAMED_REF_OR_RECURSE;
+        }
+
+      /* Back references are handled specially; must disable firstchar if
+      not set to cope with cases like (?=(\w+))\1: which would otherwise set
+      ':' later. */
+
+      if (-c >= ESC_REF)
+        {
+        open_capitem *oc;
+        recno = -c - ESC_REF;
+
+        HANDLE_REFERENCE:    /* Come here from named backref handling */
+        if (firstchar == REQ_UNSET) firstchar = REQ_NONE;
+        previous = code;
+        *code++ = ((options & PCRE_CASELESS) != 0)? OP_REFI : OP_REF;
+        PUT2INC(code, 0, recno);
+        cd->backref_map |= (recno < 32)? (1 << recno) : 1;
+        if (recno > cd->top_backref) cd->top_backref = recno;
+
+        /* Check to see if this back reference is recursive, that it, it
+        is inside the group that it references. A flag is set so that the
+        group can be made atomic. */
+
+        for (oc = cd->open_caps; oc != NULL; oc = oc->next)
+          {
+          if (oc->number == recno)
+            {
+            oc->flag = TRUE;
+            break;
+            }
+          }
+        }
+
+      /* So are Unicode property matches, if supported. */
+
+#ifdef SUPPORT_UCP
+      else if (-c == ESC_P || -c == ESC_p)
+        {
+        BOOL negated;
+        int pdata;
+        int ptype = get_ucp(&ptr, &negated, &pdata, errorcodeptr);
+        if (ptype < 0) goto FAILED;
+        previous = code;
+        *code++ = ((-c == ESC_p) != negated)? OP_PROP : OP_NOTPROP;
+        *code++ = ptype;
+        *code++ = pdata;
+        }
+#else
+
+      /* If Unicode properties are not supported, \X, \P, and \p are not
+      allowed. */
+
+      else if (-c == ESC_X || -c == ESC_P || -c == ESC_p)
+        {
+        *errorcodeptr = ERR45;
+        goto FAILED;
+        }
+#endif
+
+      /* For the rest (including \X when Unicode properties are supported), we
+      can obtain the OP value by negating the escape value in the default
+      situation when PCRE_UCP is not set. When it *is* set, we substitute
+      Unicode property tests. Note that \b and \B do a one-character
+      lookbehind. */
+
+      else
+        {
+        if ((-c == ESC_b || -c == ESC_B) && cd->max_lookbehind == 0)
+          cd->max_lookbehind = 1;
+#ifdef SUPPORT_UCP
+        if (-c >= ESC_DU && -c <= ESC_wu)
+          {
+          nestptr = ptr + 1;                   /* Where to resume */
+          ptr = substitutes[-c - ESC_DU] - 1;  /* Just before substitute */
+          }
+        else
+#endif
+        /* In non-UTF-8 mode, we turn \C into OP_ALLANY instead of OP_ANYBYTE
+        so that it works in DFA mode and in lookbehinds. */
+
+          {
+          previous = (-c > ESC_b && -c < ESC_Z)? code : NULL;
+          *code++ = (!utf && c == -ESC_C)? OP_ALLANY : -c;
+          }
+        }
+      continue;
+      }
+
+    /* We have a data character whose value is in c. In UTF-8 mode it may have
+    a value > 127. We set its representation in the length/buffer, and then
+    handle it as a data character. */
+
+#ifdef SUPPORT_UTF
+    if (utf && c > MAX_VALUE_FOR_SINGLE_CHAR)
+      mclength = PRIV(ord2utf)(c, mcbuffer);
+    else
+#endif
+
+     {
+     mcbuffer[0] = c;
+     mclength = 1;
+     }
+    goto ONE_CHAR;
+
+
+    /* ===================================================================*/
+    /* Handle a literal character. It is guaranteed not to be whitespace or #
+    when the extended flag is set. If we are in UTF-8 mode, it may be a
+    multi-byte literal character. */
+
+    default:
+    NORMAL_CHAR:
+    mclength = 1;
+    mcbuffer[0] = c;
+
+#ifdef SUPPORT_UTF
+    if (utf && HAS_EXTRALEN(c))
+      ACROSSCHAR(TRUE, ptr[1], mcbuffer[mclength++] = *(++ptr));
+#endif
+
+    /* At this point we have the character's bytes in mcbuffer, and the length
+    in mclength. When not in UTF-8 mode, the length is always 1. */
+
+    ONE_CHAR:
+    previous = code;
+    *code++ = ((options & PCRE_CASELESS) != 0)? OP_CHARI : OP_CHAR;
+    for (c = 0; c < mclength; c++) *code++ = mcbuffer[c];
+
+    /* Remember if \r or \n were seen */
+
+    if (mcbuffer[0] == CHAR_CR || mcbuffer[0] == CHAR_NL)
+      cd->external_flags |= PCRE_HASCRORLF;
+
+    /* Set the first and required bytes appropriately. If no previous first
+    byte, set it from this character, but revert to none on a zero repeat.
+    Otherwise, leave the firstchar value alone, and don't change it on a zero
+    repeat. */
+
+    if (firstchar == REQ_UNSET)
+      {
+      zerofirstchar = REQ_NONE;
+      zeroreqchar = reqchar;
+
+      /* If the character is more than one byte long, we can set firstchar
+      only if it is not to be matched caselessly. */
+
+      if (mclength == 1 || req_caseopt == 0)
+        {
+        firstchar = mcbuffer[0] | req_caseopt;
+        if (mclength != 1) reqchar = code[-1] | cd->req_varyopt;
+        }
+      else firstchar = reqchar = REQ_NONE;
+      }
+
+    /* firstchar was previously set; we can set reqchar only if the length is
+    1 or the matching is caseful. */
+
+    else
+      {
+      zerofirstchar = firstchar;
+      zeroreqchar = reqchar;
+      if (mclength == 1 || req_caseopt == 0)
+        reqchar = code[-1] | req_caseopt | cd->req_varyopt;
+      }
+
+    break;            /* End of literal character handling */
+    }
+  }                   /* end of big loop */
+
+
+/* Control never reaches here by falling through, only by a goto for all the
+error states. Pass back the position in the pattern so that it can be displayed
+to the user for diagnosing the error. */
+
+FAILED:
+*ptrptr = ptr;
+return FALSE;
+}
+
+
+
+
+/*************************************************
+*     Compile sequence of alternatives           *
+*************************************************/
+
+/* On entry, ptr is pointing past the bracket character, but on return it
+points to the closing bracket, or vertical bar, or end of string. The code
+variable is pointing at the byte into which the BRA operator has been stored.
+This function is used during the pre-compile phase when we are trying to find
+out the amount of memory needed, as well as during the real compile phase. The
+value of lengthptr distinguishes the two phases.
+
+Arguments:
+  options        option bits, including any changes for this subpattern
+  codeptr        -> the address of the current code pointer
+  ptrptr         -> the address of the current pattern pointer
+  errorcodeptr   -> pointer to error code variable
+  lookbehind     TRUE if this is a lookbehind assertion
+  reset_bracount TRUE to reset the count for each branch
+  skipbytes      skip this many bytes at start (for brackets and OP_COND)
+  cond_depth     depth of nesting for conditional subpatterns
+  firstcharptr   place to put the first required character, or a negative number
+  reqcharptr     place to put the last required character, or a negative number
+  bcptr          pointer to the chain of currently open branches
+  cd             points to the data block with tables pointers etc.
+  lengthptr      NULL during the real compile phase
+                 points to length accumulator during pre-compile phase
+
+Returns:         TRUE on success
+*/
+
+static BOOL
+compile_regex(int options, pcre_uchar **codeptr, const pcre_uchar **ptrptr,
+  int *errorcodeptr, BOOL lookbehind, BOOL reset_bracount, int skipbytes,
+  int cond_depth, pcre_int32 *firstcharptr, pcre_int32 *reqcharptr,
+  branch_chain *bcptr, compile_data *cd, int *lengthptr)
+{
+const pcre_uchar *ptr = *ptrptr;
+pcre_uchar *code = *codeptr;
+pcre_uchar *last_branch = code;
+pcre_uchar *start_bracket = code;
+pcre_uchar *reverse_count = NULL;
+open_capitem capitem;
+int capnumber = 0;
+pcre_int32 firstchar, reqchar;
+pcre_int32 branchfirstchar, branchreqchar;
+int length;
+int orig_bracount;
+int max_bracount;
+branch_chain bc;
+
+bc.outer = bcptr;
+bc.current_branch = code;
+
+firstchar = reqchar = REQ_UNSET;
+
+/* Accumulate the length for use in the pre-compile phase. Start with the
+length of the BRA and KET and any extra bytes that are required at the
+beginning. We accumulate in a local variable to save frequent testing of
+lenthptr for NULL. We cannot do this by looking at the value of code at the
+start and end of each alternative, because compiled items are discarded during
+the pre-compile phase so that the work space is not exceeded. */
+
+length = 2 + 2*LINK_SIZE + skipbytes;
+
+/* WARNING: If the above line is changed for any reason, you must also change
+the code that abstracts option settings at the start of the pattern and makes
+them global. It tests the value of length for (2 + 2*LINK_SIZE) in the
+pre-compile phase to find out whether anything has yet been compiled or not. */
+
+/* If this is a capturing subpattern, add to the chain of open capturing items
+so that we can detect them if (*ACCEPT) is encountered. This is also used to
+detect groups that contain recursive back references to themselves. Note that
+only OP_CBRA need be tested here; changing this opcode to one of its variants,
+e.g. OP_SCBRAPOS, happens later, after the group has been compiled. */
+
+if (*code == OP_CBRA)
+  {
+  capnumber = GET2(code, 1 + LINK_SIZE);
+  capitem.number = capnumber;
+  capitem.next = cd->open_caps;
+  capitem.flag = FALSE;
+  cd->open_caps = &capitem;
+  }
+
+/* Offset is set zero to mark that this bracket is still open */
+
+PUT(code, 1, 0);
+code += 1 + LINK_SIZE + skipbytes;
+
+/* Loop for each alternative branch */
+
+orig_bracount = max_bracount = cd->bracount;
+for (;;)
+  {
+  /* For a (?| group, reset the capturing bracket count so that each branch
+  uses the same numbers. */
+
+  if (reset_bracount) cd->bracount = orig_bracount;
+
+  /* Set up dummy OP_REVERSE if lookbehind assertion */
+
+  if (lookbehind)
+    {
+    *code++ = OP_REVERSE;
+    reverse_count = code;
+    PUTINC(code, 0, 0);
+    length += 1 + LINK_SIZE;
+    }
+
+  /* Now compile the branch; in the pre-compile phase its length gets added
+  into the length. */
+
+  if (!compile_branch(&options, &code, &ptr, errorcodeptr, &branchfirstchar,
+        &branchreqchar, &bc, cond_depth, cd,
+        (lengthptr == NULL)? NULL : &length))
+    {
+    *ptrptr = ptr;
+    return FALSE;
+    }
+
+  /* Keep the highest bracket count in case (?| was used and some branch
+  has fewer than the rest. */
+
+  if (cd->bracount > max_bracount) max_bracount = cd->bracount;
+
+  /* In the real compile phase, there is some post-processing to be done. */
+
+  if (lengthptr == NULL)
+    {
+    /* If this is the first branch, the firstchar and reqchar values for the
+    branch become the values for the regex. */
+
+    if (*last_branch != OP_ALT)
+      {
+      firstchar = branchfirstchar;
+      reqchar = branchreqchar;
+      }
+
+    /* If this is not the first branch, the first char and reqchar have to
+    match the values from all the previous branches, except that if the
+    previous value for reqchar didn't have REQ_VARY set, it can still match,
+    and we set REQ_VARY for the regex. */
+
+    else
+      {
+      /* If we previously had a firstchar, but it doesn't match the new branch,
+      we have to abandon the firstchar for the regex, but if there was
+      previously no reqchar, it takes on the value of the old firstchar. */
+
+      if (firstchar >= 0 && firstchar != branchfirstchar)
+        {
+        if (reqchar < 0) reqchar = firstchar;
+        firstchar = REQ_NONE;
+        }
+
+      /* If we (now or from before) have no firstchar, a firstchar from the
+      branch becomes a reqchar if there isn't a branch reqchar. */
+
+      if (firstchar < 0 && branchfirstchar >= 0 && branchreqchar < 0)
+          branchreqchar = branchfirstchar;
+
+      /* Now ensure that the reqchars match */
+
+      if ((reqchar & ~REQ_VARY) != (branchreqchar & ~REQ_VARY))
+        reqchar = REQ_NONE;
+      else reqchar |= branchreqchar;   /* To "or" REQ_VARY */
+      }
+
+    /* If lookbehind, check that this branch matches a fixed-length string, and
+    put the length into the OP_REVERSE item. Temporarily mark the end of the
+    branch with OP_END. If the branch contains OP_RECURSE, the result is -3
+    because there may be forward references that we can't check here. Set a
+    flag to cause another lookbehind check at the end. Why not do it all at the
+    end? Because common, erroneous checks are picked up here and the offset of
+    the problem can be shown. */
+
+    if (lookbehind)
+      {
+      int fixed_length;
+      *code = OP_END;
+      fixed_length = find_fixedlength(last_branch,  (options & PCRE_UTF8) != 0,
+        FALSE, cd);
+      DPRINTF(("fixed length = %d\n", fixed_length));
+      if (fixed_length == -3)
+        {
+        cd->check_lookbehind = TRUE;
+        }
+      else if (fixed_length < 0)
+        {
+        *errorcodeptr = (fixed_length == -2)? ERR36 :
+                        (fixed_length == -4)? ERR70: ERR25;
+        *ptrptr = ptr;
+        return FALSE;
+        }
+      else
+        {
+        if (fixed_length > cd->max_lookbehind)
+          cd->max_lookbehind = fixed_length;
+        PUT(reverse_count, 0, fixed_length);
+        }
+      }
+    }
+
+  /* Reached end of expression, either ')' or end of pattern. In the real
+  compile phase, go back through the alternative branches and reverse the chain
+  of offsets, with the field in the BRA item now becoming an offset to the
+  first alternative. If there are no alternatives, it points to the end of the
+  group. The length in the terminating ket is always the length of the whole
+  bracketed item. Return leaving the pointer at the terminating char. */
+
+  if (*ptr != CHAR_VERTICAL_LINE)
+    {
+    if (lengthptr == NULL)
+      {
+      int branch_length = (int)(code - last_branch);
+      do
+        {
+        int prev_length = GET(last_branch, 1);
+        PUT(last_branch, 1, branch_length);
+        branch_length = prev_length;
+        last_branch -= branch_length;
+        }
+      while (branch_length > 0);
+      }
+
+    /* Fill in the ket */
+
+    *code = OP_KET;
+    PUT(code, 1, (int)(code - start_bracket));
+    code += 1 + LINK_SIZE;
+
+    /* If it was a capturing subpattern, check to see if it contained any
+    recursive back references. If so, we must wrap it in atomic brackets.
+    In any event, remove the block from the chain. */
+
+    if (capnumber > 0)
+      {
+      if (cd->open_caps->flag)
+        {
+        memmove(start_bracket + 1 + LINK_SIZE, start_bracket,
+          IN_UCHARS(code - start_bracket));
+        *start_bracket = OP_ONCE;
+        code += 1 + LINK_SIZE;
+        PUT(start_bracket, 1, (int)(code - start_bracket));
+        *code = OP_KET;
+        PUT(code, 1, (int)(code - start_bracket));
+        code += 1 + LINK_SIZE;
+        length += 2 + 2*LINK_SIZE;
+        }
+      cd->open_caps = cd->open_caps->next;
+      }
+
+    /* Retain the highest bracket number, in case resetting was used. */
+
+    cd->bracount = max_bracount;
+
+    /* Set values to pass back */
+
+    *codeptr = code;
+    *ptrptr = ptr;
+    *firstcharptr = firstchar;
+    *reqcharptr = reqchar;
+    if (lengthptr != NULL)
+      {
+      if (OFLOW_MAX - *lengthptr < length)
+        {
+        *errorcodeptr = ERR20;
+        return FALSE;
+        }
+      *lengthptr += length;
+      }
+    return TRUE;
+    }
+
+  /* Another branch follows. In the pre-compile phase, we can move the code
+  pointer back to where it was for the start of the first branch. (That is,
+  pretend that each branch is the only one.)
+
+  In the real compile phase, insert an ALT node. Its length field points back
+  to the previous branch while the bracket remains open. At the end the chain
+  is reversed. It's done like this so that the start of the bracket has a
+  zero offset until it is closed, making it possible to detect recursion. */
+
+  if (lengthptr != NULL)
+    {
+    code = *codeptr + 1 + LINK_SIZE + skipbytes;
+    length += 1 + LINK_SIZE;
+    }
+  else
+    {
+    *code = OP_ALT;
+    PUT(code, 1, (int)(code - last_branch));
+    bc.current_branch = last_branch = code;
+    code += 1 + LINK_SIZE;
+    }
+
+  ptr++;
+  }
+/* Control never reaches here */
+}
+
+
+
+
+/*************************************************
+*          Check for anchored expression         *
+*************************************************/
+
+/* Try to find out if this is an anchored regular expression. Consider each
+alternative branch. If they all start with OP_SOD or OP_CIRC, or with a bracket
+all of whose alternatives start with OP_SOD or OP_CIRC (recurse ad lib), then
+it's anchored. However, if this is a multiline pattern, then only OP_SOD will
+be found, because ^ generates OP_CIRCM in that mode.
+
+We can also consider a regex to be anchored if OP_SOM starts all its branches.
+This is the code for \G, which means "match at start of match position, taking
+into account the match offset".
+
+A branch is also implicitly anchored if it starts with .* and DOTALL is set,
+because that will try the rest of the pattern at all possible matching points,
+so there is no point trying again.... er ....
+
+.... except when the .* appears inside capturing parentheses, and there is a
+subsequent back reference to those parentheses. We haven't enough information
+to catch that case precisely.
+
+At first, the best we could do was to detect when .* was in capturing brackets
+and the highest back reference was greater than or equal to that level.
+However, by keeping a bitmap of the first 31 back references, we can catch some
+of the more common cases more precisely.
+
+Arguments:
+  code           points to start of expression (the bracket)
+  bracket_map    a bitmap of which brackets we are inside while testing; this
+                  handles up to substring 31; after that we just have to take
+                  the less precise approach
+  backref_map    the back reference bitmap
+
+Returns:     TRUE or FALSE
+*/
+
+static BOOL
+is_anchored(register const pcre_uchar *code, unsigned int bracket_map,
+  unsigned int backref_map)
+{
+do {
+   const pcre_uchar *scode = first_significant_code(
+     code + PRIV(OP_lengths)[*code], FALSE);
+   register int op = *scode;
+
+   /* Non-capturing brackets */
+
+   if (op == OP_BRA  || op == OP_BRAPOS ||
+       op == OP_SBRA || op == OP_SBRAPOS)
+     {
+     if (!is_anchored(scode, bracket_map, backref_map)) return FALSE;
+     }
+
+   /* Capturing brackets */
+
+   else if (op == OP_CBRA  || op == OP_CBRAPOS ||
+            op == OP_SCBRA || op == OP_SCBRAPOS)
+     {
+     int n = GET2(scode, 1+LINK_SIZE);
+     int new_map = bracket_map | ((n < 32)? (1 << n) : 1);
+     if (!is_anchored(scode, new_map, backref_map)) return FALSE;
+     }
+
+   /* Other brackets */
+
+   else if (op == OP_ASSERT || op == OP_ONCE || op == OP_ONCE_NC ||
+            op == OP_COND)
+     {
+     if (!is_anchored(scode, bracket_map, backref_map)) return FALSE;
+     }
+
+   /* .* is not anchored unless DOTALL is set (which generates OP_ALLANY) and
+   it isn't in brackets that are or may be referenced. */
+
+   else if ((op == OP_TYPESTAR || op == OP_TYPEMINSTAR ||
+             op == OP_TYPEPOSSTAR))
+     {
+     if (scode[1] != OP_ALLANY || (bracket_map & backref_map) != 0)
+       return FALSE;
+     }
+
+   /* Check for explicit anchoring */
+
+   else if (op != OP_SOD && op != OP_SOM && op != OP_CIRC) return FALSE;
+   code += GET(code, 1);
+   }
+while (*code == OP_ALT);   /* Loop for each alternative */
+return TRUE;
+}
+
+
+
+/*************************************************
+*         Check for starting with ^ or .*        *
+*************************************************/
+
+/* This is called to find out if every branch starts with ^ or .* so that
+"first char" processing can be done to speed things up in multiline
+matching and for non-DOTALL patterns that start with .* (which must start at
+the beginning or after \n). As in the case of is_anchored() (see above), we
+have to take account of back references to capturing brackets that contain .*
+because in that case we can't make the assumption.
+
+Arguments:
+  code           points to start of expression (the bracket)
+  bracket_map    a bitmap of which brackets we are inside while testing; this
+                  handles up to substring 31; after that we just have to take
+                  the less precise approach
+  backref_map    the back reference bitmap
+
+Returns:         TRUE or FALSE
+*/
+
+static BOOL
+is_startline(const pcre_uchar *code, unsigned int bracket_map,
+  unsigned int backref_map)
+{
+do {
+   const pcre_uchar *scode = first_significant_code(
+     code + PRIV(OP_lengths)[*code], FALSE);
+   register int op = *scode;
+
+   /* If we are at the start of a conditional assertion group, *both* the
+   conditional assertion *and* what follows the condition must satisfy the test
+   for start of line. Other kinds of condition fail. Note that there may be an
+   auto-callout at the start of a condition. */
+
+   if (op == OP_COND)
+     {
+     scode += 1 + LINK_SIZE;
+     if (*scode == OP_CALLOUT) scode += PRIV(OP_lengths)[OP_CALLOUT];
+     switch (*scode)
+       {
+       case OP_CREF:
+       case OP_NCREF:
+       case OP_RREF:
+       case OP_NRREF:
+       case OP_DEF:
+       return FALSE;
+
+       default:     /* Assertion */
+       if (!is_startline(scode, bracket_map, backref_map)) return FALSE;
+       do scode += GET(scode, 1); while (*scode == OP_ALT);
+       scode += 1 + LINK_SIZE;
+       break;
+       }
+     scode = first_significant_code(scode, FALSE);
+     op = *scode;
+     }
+
+   /* Non-capturing brackets */
+
+   if (op == OP_BRA  || op == OP_BRAPOS ||
+       op == OP_SBRA || op == OP_SBRAPOS)
+     {
+     if (!is_startline(scode, bracket_map, backref_map)) return FALSE;
+     }
+
+   /* Capturing brackets */
+
+   else if (op == OP_CBRA  || op == OP_CBRAPOS ||
+            op == OP_SCBRA || op == OP_SCBRAPOS)
+     {
+     int n = GET2(scode, 1+LINK_SIZE);
+     int new_map = bracket_map | ((n < 32)? (1 << n) : 1);
+     if (!is_startline(scode, new_map, backref_map)) return FALSE;
+     }
+
+   /* Other brackets */
+
+   else if (op == OP_ASSERT || op == OP_ONCE || op == OP_ONCE_NC)
+     {
+     if (!is_startline(scode, bracket_map, backref_map)) return FALSE;
+     }
+
+   /* .* means "start at start or after \n" if it isn't in brackets that
+   may be referenced. */
+
+   else if (op == OP_TYPESTAR || op == OP_TYPEMINSTAR || op == OP_TYPEPOSSTAR)
+     {
+     if (scode[1] != OP_ANY || (bracket_map & backref_map) != 0) return FALSE;
+     }
+
+   /* Check for explicit circumflex */
+
+   else if (op != OP_CIRC && op != OP_CIRCM) return FALSE;
+
+   /* Move on to the next alternative */
+
+   code += GET(code, 1);
+   }
+while (*code == OP_ALT);  /* Loop for each alternative */
+return TRUE;
+}
+
+
+
+/*************************************************
+*       Check for asserted fixed first char      *
+*************************************************/
+
+/* During compilation, the "first char" settings from forward assertions are
+discarded, because they can cause conflicts with actual literals that follow.
+However, if we end up without a first char setting for an unanchored pattern,
+it is worth scanning the regex to see if there is an initial asserted first
+char. If all branches start with the same asserted char, or with a bracket all
+of whose alternatives start with the same asserted char (recurse ad lib), then
+we return that char, otherwise -1.
+
+Arguments:
+  code       points to start of expression (the bracket)
+  inassert   TRUE if in an assertion
+
+Returns:     -1 or the fixed first char
+*/
+
+static int
+find_firstassertedchar(const pcre_uchar *code, BOOL inassert)
+{
+register int c = -1;
+do {
+   int d;
+   int xl = (*code == OP_CBRA || *code == OP_SCBRA ||
+             *code == OP_CBRAPOS || *code == OP_SCBRAPOS)? IMM2_SIZE:0;
+   const pcre_uchar *scode = first_significant_code(code + 1+LINK_SIZE + xl,
+     TRUE);
+   register int op = *scode;
+
+   switch(op)
+     {
+     default:
+     return -1;
+
+     case OP_BRA:
+     case OP_BRAPOS:
+     case OP_CBRA:
+     case OP_SCBRA:
+     case OP_CBRAPOS:
+     case OP_SCBRAPOS:
+     case OP_ASSERT:
+     case OP_ONCE:
+     case OP_ONCE_NC:
+     case OP_COND:
+     if ((d = find_firstassertedchar(scode, op == OP_ASSERT)) < 0)
+       return -1;
+     if (c < 0) c = d; else if (c != d) return -1;
+     break;
+
+     case OP_EXACT:
+     scode += IMM2_SIZE;
+     /* Fall through */
+
+     case OP_CHAR:
+     case OP_PLUS:
+     case OP_MINPLUS:
+     case OP_POSPLUS:
+     if (!inassert) return -1;
+     if (c < 0) c = scode[1];
+       else if (c != scode[1]) return -1;
+     break;
+
+     case OP_EXACTI:
+     scode += IMM2_SIZE;
+     /* Fall through */
+
+     case OP_CHARI:
+     case OP_PLUSI:
+     case OP_MINPLUSI:
+     case OP_POSPLUSI:
+     if (!inassert) return -1;
+     if (c < 0) c = scode[1] | REQ_CASELESS;
+       else if (c != scode[1]) return -1;
+     break;
+     }
+
+   code += GET(code, 1);
+   }
+while (*code == OP_ALT);
+return c;
+}
+
+
+
+/*************************************************
+*        Compile a Regular Expression            *
+*************************************************/
+
+/* This function takes a string and returns a pointer to a block of store
+holding a compiled version of the expression. The original API for this
+function had no error code return variable; it is retained for backwards
+compatibility. The new function is given a new name.
+
+Arguments:
+  pattern       the regular expression
+  options       various option bits
+  errorcodeptr  pointer to error code variable (pcre_compile2() only)
+                  can be NULL if you don't want a code value
+  errorptr      pointer to pointer to error text
+  erroroffset   ptr offset in pattern where error was detected
+  tables        pointer to character tables or NULL
+
+Returns:        pointer to compiled data block, or NULL on error,
+                with errorptr and erroroffset set
+*/
+
+#ifdef COMPILE_PCRE8
+PCRE_EXP_DEFN pcre * PCRE_CALL_CONVENTION
+pcre_compile(const char *pattern, int options, const char **errorptr,
+  int *erroroffset, const unsigned char *tables)
+#else
+PCRE_EXP_DEFN pcre16 * PCRE_CALL_CONVENTION
+pcre16_compile(PCRE_SPTR16 pattern, int options, const char **errorptr,
+  int *erroroffset, const unsigned char *tables)
+#endif
+{
+#ifdef COMPILE_PCRE8
+return pcre_compile2(pattern, options, NULL, errorptr, erroroffset, tables);
+#else
+return pcre16_compile2(pattern, options, NULL, errorptr, erroroffset, tables);
+#endif
+}
+
+
+#ifdef COMPILE_PCRE8
+PCRE_EXP_DEFN pcre * PCRE_CALL_CONVENTION
+pcre_compile2(const char *pattern, int options, int *errorcodeptr,
+  const char **errorptr, int *erroroffset, const unsigned char *tables)
+#else
+PCRE_EXP_DEFN pcre16 * PCRE_CALL_CONVENTION
+pcre16_compile2(PCRE_SPTR16 pattern, int options, int *errorcodeptr,
+  const char **errorptr, int *erroroffset, const unsigned char *tables)
+#endif
+{
+REAL_PCRE *re;
+int length = 1;  /* For final END opcode */
+pcre_int32 firstchar, reqchar;
+int newline;
+int errorcode = 0;
+int skipatstart = 0;
+BOOL utf;
+size_t size;
+pcre_uchar *code;
+const pcre_uchar *codestart;
+const pcre_uchar *ptr;
+compile_data compile_block;
+compile_data *cd = &compile_block;
+
+/* This space is used for "compiling" into during the first phase, when we are
+computing the amount of memory that is needed. Compiled items are thrown away
+as soon as possible, so that a fairly large buffer should be sufficient for
+this purpose. The same space is used in the second phase for remembering where
+to fill in forward references to subpatterns. That may overflow, in which case
+new memory is obtained from malloc(). */
+
+pcre_uchar cworkspace[COMPILE_WORK_SIZE];
+
+/* Set this early so that early errors get offset 0. */
+
+ptr = (const pcre_uchar *)pattern;
+
+/* We can't pass back an error message if errorptr is NULL; I guess the best we
+can do is just return NULL, but we can set a code value if there is a code
+pointer. */
+
+if (errorptr == NULL)
+  {
+  if (errorcodeptr != NULL) *errorcodeptr = 99;
+  return NULL;
+  }
+
+*errorptr = NULL;
+if (errorcodeptr != NULL) *errorcodeptr = ERR0;
+
+/* However, we can give a message for this error */
+
+if (erroroffset == NULL)
+  {
+  errorcode = ERR16;
+  goto PCRE_EARLY_ERROR_RETURN2;
+  }
+
+*erroroffset = 0;
+
+/* Set up pointers to the individual character tables */
+
+if (tables == NULL) tables = PRIV(default_tables);
+cd->lcc = tables + lcc_offset;
+cd->fcc = tables + fcc_offset;
+cd->cbits = tables + cbits_offset;
+cd->ctypes = tables + ctypes_offset;
+
+/* Check that all undefined public option bits are zero */
+
+if ((options & ~PUBLIC_COMPILE_OPTIONS) != 0)
+  {
+  errorcode = ERR17;
+  goto PCRE_EARLY_ERROR_RETURN;
+  }
+
+/* Check for global one-time settings at the start of the pattern, and remember
+the offset for later. */
+
+while (ptr[skipatstart] == CHAR_LEFT_PARENTHESIS &&
+       ptr[skipatstart+1] == CHAR_ASTERISK)
+  {
+  int newnl = 0;
+  int newbsr = 0;
+
+#ifdef COMPILE_PCRE8
+  if (STRNCMP_UC_C8(ptr+skipatstart+2, STRING_UTF_RIGHTPAR, 5) == 0)
+    { skipatstart += 7; options |= PCRE_UTF8; continue; }
+#endif
+#ifdef COMPILE_PCRE16
+  if (STRNCMP_UC_C8(ptr+skipatstart+2, STRING_UTF_RIGHTPAR, 6) == 0)
+    { skipatstart += 8; options |= PCRE_UTF16; continue; }
+#endif
+  else if (STRNCMP_UC_C8(ptr+skipatstart+2, STRING_UCP_RIGHTPAR, 4) == 0)
+    { skipatstart += 6; options |= PCRE_UCP; continue; }
+  else if (STRNCMP_UC_C8(ptr+skipatstart+2, STRING_NO_START_OPT_RIGHTPAR, 13) == 0)
+    { skipatstart += 15; options |= PCRE_NO_START_OPTIMIZE; continue; }
+
+  if (STRNCMP_UC_C8(ptr+skipatstart+2, STRING_CR_RIGHTPAR, 3) == 0)
+    { skipatstart += 5; newnl = PCRE_NEWLINE_CR; }
+  else if (STRNCMP_UC_C8(ptr+skipatstart+2, STRING_LF_RIGHTPAR, 3)  == 0)
+    { skipatstart += 5; newnl = PCRE_NEWLINE_LF; }
+  else if (STRNCMP_UC_C8(ptr+skipatstart+2, STRING_CRLF_RIGHTPAR, 5)  == 0)
+    { skipatstart += 7; newnl = PCRE_NEWLINE_CR + PCRE_NEWLINE_LF; }
+  else if (STRNCMP_UC_C8(ptr+skipatstart+2, STRING_ANY_RIGHTPAR, 4) == 0)
+    { skipatstart += 6; newnl = PCRE_NEWLINE_ANY; }
+  else if (STRNCMP_UC_C8(ptr+skipatstart+2, STRING_ANYCRLF_RIGHTPAR, 8) == 0)
+    { skipatstart += 10; newnl = PCRE_NEWLINE_ANYCRLF; }
+
+  else if (STRNCMP_UC_C8(ptr+skipatstart+2, STRING_BSR_ANYCRLF_RIGHTPAR, 12) == 0)
+    { skipatstart += 14; newbsr = PCRE_BSR_ANYCRLF; }
+  else if (STRNCMP_UC_C8(ptr+skipatstart+2, STRING_BSR_UNICODE_RIGHTPAR, 12) == 0)
+    { skipatstart += 14; newbsr = PCRE_BSR_UNICODE; }
+
+  if (newnl != 0)
+    options = (options & ~PCRE_NEWLINE_BITS) | newnl;
+  else if (newbsr != 0)
+    options = (options & ~(PCRE_BSR_ANYCRLF|PCRE_BSR_UNICODE)) | newbsr;
+  else break;
+  }
+
+/* PCRE_UTF16 has the same value as PCRE_UTF8. */
+utf = (options & PCRE_UTF8) != 0;
+
+/* Can't support UTF unless PCRE has been compiled to include the code. The
+return of an error code from PRIV(valid_utf)() is a new feature, introduced in
+release 8.13. It is passed back from pcre_[dfa_]exec(), but at the moment is
+not used here. */
+
+#ifdef SUPPORT_UTF
+if (utf && (options & PCRE_NO_UTF8_CHECK) == 0 &&
+     (errorcode = PRIV(valid_utf)((PCRE_PUCHAR)pattern, -1, erroroffset)) != 0)
+  {
+#ifdef COMPILE_PCRE8
+  errorcode = ERR44;
+#else
+  errorcode = ERR74;
+#endif
+  goto PCRE_EARLY_ERROR_RETURN2;
+  }
+#else
+if (utf)
+  {
+  errorcode = ERR32;
+  goto PCRE_EARLY_ERROR_RETURN;
+  }
+#endif
+
+/* Can't support UCP unless PCRE has been compiled to include the code. */
+
+#ifndef SUPPORT_UCP
+if ((options & PCRE_UCP) != 0)
+  {
+  errorcode = ERR67;
+  goto PCRE_EARLY_ERROR_RETURN;
+  }
+#endif
+
+/* Check validity of \R options. */
+
+if ((options & (PCRE_BSR_ANYCRLF|PCRE_BSR_UNICODE)) ==
+     (PCRE_BSR_ANYCRLF|PCRE_BSR_UNICODE))
+  {
+  errorcode = ERR56;
+  goto PCRE_EARLY_ERROR_RETURN;
+  }
+
+/* Handle different types of newline. The three bits give seven cases. The
+current code allows for fixed one- or two-byte sequences, plus "any" and
+"anycrlf". */
+
+switch (options & PCRE_NEWLINE_BITS)
+  {
+  case 0: newline = NEWLINE; break;   /* Build-time default */
+  case PCRE_NEWLINE_CR: newline = CHAR_CR; break;
+  case PCRE_NEWLINE_LF: newline = CHAR_NL; break;
+  case PCRE_NEWLINE_CR+
+       PCRE_NEWLINE_LF: newline = (CHAR_CR << 8) | CHAR_NL; break;
+  case PCRE_NEWLINE_ANY: newline = -1; break;
+  case PCRE_NEWLINE_ANYCRLF: newline = -2; break;
+  default: errorcode = ERR56; goto PCRE_EARLY_ERROR_RETURN;
+  }
+
+if (newline == -2)
+  {
+  cd->nltype = NLTYPE_ANYCRLF;
+  }
+else if (newline < 0)
+  {
+  cd->nltype = NLTYPE_ANY;
+  }
+else
+  {
+  cd->nltype = NLTYPE_FIXED;
+  if (newline > 255)
+    {
+    cd->nllen = 2;
+    cd->nl[0] = (newline >> 8) & 255;
+    cd->nl[1] = newline & 255;
+    }
+  else
+    {
+    cd->nllen = 1;
+    cd->nl[0] = newline;
+    }
+  }
+
+/* Maximum back reference and backref bitmap. The bitmap records up to 31 back
+references to help in deciding whether (.*) can be treated as anchored or not.
+*/
+
+cd->top_backref = 0;
+cd->backref_map = 0;
+
+/* Reflect pattern for debugging output */
+
+DPRINTF(("------------------------------------------------------------------\n"));
+#ifdef PCRE_DEBUG
+print_puchar(stdout, (PCRE_PUCHAR)pattern);
+#endif
+DPRINTF(("\n"));
+
+/* Pretend to compile the pattern while actually just accumulating the length
+of memory required. This behaviour is triggered by passing a non-NULL final
+argument to compile_regex(). We pass a block of workspace (cworkspace) for it
+to compile parts of the pattern into; the compiled code is discarded when it is
+no longer needed, so hopefully this workspace will never overflow, though there
+is a test for its doing so. */
+
+cd->bracount = cd->final_bracount = 0;
+cd->names_found = 0;
+cd->name_entry_size = 0;
+cd->name_table = NULL;
+cd->start_code = cworkspace;
+cd->hwm = cworkspace;
+cd->start_workspace = cworkspace;
+cd->workspace_size = COMPILE_WORK_SIZE;
+cd->start_pattern = (const pcre_uchar *)pattern;
+cd->end_pattern = (const pcre_uchar *)(pattern + STRLEN_UC((const pcre_uchar *)pattern));
+cd->req_varyopt = 0;
+cd->assert_depth = 0;
+cd->max_lookbehind = 0;
+cd->external_options = options;
+cd->external_flags = 0;
+cd->open_caps = NULL;
+
+/* Now do the pre-compile. On error, errorcode will be set non-zero, so we
+don't need to look at the result of the function here. The initial options have
+been put into the cd block so that they can be changed if an option setting is
+found within the regex right at the beginning. Bringing initial option settings
+outside can help speed up starting point checks. */
+
+ptr += skipatstart;
+code = cworkspace;
+*code = OP_BRA;
+(void)compile_regex(cd->external_options, &code, &ptr, &errorcode, FALSE,
+  FALSE, 0, 0, &firstchar, &reqchar, NULL, cd, &length);
+if (errorcode != 0) goto PCRE_EARLY_ERROR_RETURN;
+
+DPRINTF(("end pre-compile: length=%d workspace=%d\n", length,
+  (int)(cd->hwm - cworkspace)));
+
+if (length > MAX_PATTERN_SIZE)
+  {
+  errorcode = ERR20;
+  goto PCRE_EARLY_ERROR_RETURN;
+  }
+
+/* Compute the size of data block needed and get it, either from malloc or
+externally provided function. Integer overflow should no longer be possible
+because nowadays we limit the maximum value of cd->names_found and
+cd->name_entry_size. */
+
+size = sizeof(REAL_PCRE) + (length + cd->names_found * cd->name_entry_size) * sizeof(pcre_uchar);
+re = (REAL_PCRE *)(PUBL(malloc))(size);
+
+if (re == NULL)
+  {
+  errorcode = ERR21;
+  goto PCRE_EARLY_ERROR_RETURN;
+  }
+
+/* Put in the magic number, and save the sizes, initial options, internal
+flags, and character table pointer. NULL is used for the default character
+tables. The nullpad field is at the end; it's there to help in the case when a
+regex compiled on a system with 4-byte pointers is run on another with 8-byte
+pointers. */
+
+re->magic_number = MAGIC_NUMBER;
+re->size = (int)size;
+re->options = cd->external_options;
+re->flags = cd->external_flags;
+re->first_char = 0;
+re->req_char = 0;
+re->name_table_offset = sizeof(REAL_PCRE) / sizeof(pcre_uchar);
+re->name_entry_size = cd->name_entry_size;
+re->name_count = cd->names_found;
+re->ref_count = 0;
+re->tables = (tables == PRIV(default_tables))? NULL : tables;
+re->nullpad = NULL;
+
+/* The starting points of the name/number translation table and of the code are
+passed around in the compile data block. The start/end pattern and initial
+options are already set from the pre-compile phase, as is the name_entry_size
+field. Reset the bracket count and the names_found field. Also reset the hwm
+field; this time it's used for remembering forward references to subpatterns.
+*/
+
+cd->final_bracount = cd->bracount;  /* Save for checking forward references */
+cd->assert_depth = 0;
+cd->bracount = 0;
+cd->max_lookbehind = 0;
+cd->names_found = 0;
+cd->name_table = (pcre_uchar *)re + re->name_table_offset;
+codestart = cd->name_table + re->name_entry_size * re->name_count;
+cd->start_code = codestart;
+cd->hwm = (pcre_uchar *)(cd->start_workspace);
+cd->req_varyopt = 0;
+cd->had_accept = FALSE;
+cd->check_lookbehind = FALSE;
+cd->open_caps = NULL;
+
+/* Set up a starting, non-extracting bracket, then compile the expression. On
+error, errorcode will be set non-zero, so we don't need to look at the result
+of the function here. */
+
+ptr = (const pcre_uchar *)pattern + skipatstart;
+code = (pcre_uchar *)codestart;
+*code = OP_BRA;
+(void)compile_regex(re->options, &code, &ptr, &errorcode, FALSE, FALSE, 0, 0,
+  &firstchar, &reqchar, NULL, cd, NULL);
+re->top_bracket = cd->bracount;
+re->top_backref = cd->top_backref;
+re->max_lookbehind = cd->max_lookbehind;
+re->flags = cd->external_flags | PCRE_MODE;
+
+if (cd->had_accept) reqchar = REQ_NONE;   /* Must disable after (*ACCEPT) */
+
+/* If not reached end of pattern on success, there's an excess bracket. */
+
+if (errorcode == 0 && *ptr != 0) errorcode = ERR22;
+
+/* Fill in the terminating state and check for disastrous overflow, but
+if debugging, leave the test till after things are printed out. */
+
+*code++ = OP_END;
+
+#ifndef PCRE_DEBUG
+if (code - codestart > length) errorcode = ERR23;
+#endif
+
+/* Fill in any forward references that are required. There may be repeated
+references; optimize for them, as searching a large regex takes time. */
+
+if (cd->hwm > cd->start_workspace)
+  {
+  int prev_recno = -1;
+  const pcre_uchar *groupptr = NULL;
+  while (errorcode == 0 && cd->hwm > cd->start_workspace)
+    {
+    int offset, recno;
+    cd->hwm -= LINK_SIZE;
+    offset = GET(cd->hwm, 0);
+    recno = GET(codestart, offset);
+    if (recno != prev_recno)
+      {
+      groupptr = PRIV(find_bracket)(codestart, utf, recno);
+      prev_recno = recno;
+      }
+    if (groupptr == NULL) errorcode = ERR53;
+      else PUT(((pcre_uchar *)codestart), offset, (int)(groupptr - codestart));
+    }
+  }
+
+/* If the workspace had to be expanded, free the new memory. */
+
+if (cd->workspace_size > COMPILE_WORK_SIZE)
+  (PUBL(free))((void *)cd->start_workspace);
+
+/* Give an error if there's back reference to a non-existent capturing
+subpattern. */
+
+if (errorcode == 0 && re->top_backref > re->top_bracket) errorcode = ERR15;
+
+/* If there were any lookbehind assertions that contained OP_RECURSE
+(recursions or subroutine calls), a flag is set for them to be checked here,
+because they may contain forward references. Actual recursions can't be fixed
+length, but subroutine calls can. It is done like this so that those without
+OP_RECURSE that are not fixed length get a diagnosic with a useful offset. The
+exceptional ones forgo this. We scan the pattern to check that they are fixed
+length, and set their lengths. */
+
+if (cd->check_lookbehind)
+  {
+  pcre_uchar *cc = (pcre_uchar *)codestart;
+
+  /* Loop, searching for OP_REVERSE items, and process those that do not have
+  their length set. (Actually, it will also re-process any that have a length
+  of zero, but that is a pathological case, and it does no harm.) When we find
+  one, we temporarily terminate the branch it is in while we scan it. */
+
+  for (cc = (pcre_uchar *)PRIV(find_bracket)(codestart, utf, -1);
+       cc != NULL;
+       cc = (pcre_uchar *)PRIV(find_bracket)(cc, utf, -1))
+    {
+    if (GET(cc, 1) == 0)
+      {
+      int fixed_length;
+      pcre_uchar *be = cc - 1 - LINK_SIZE + GET(cc, -LINK_SIZE);
+      int end_op = *be;
+      *be = OP_END;
+      fixed_length = find_fixedlength(cc, (re->options & PCRE_UTF8) != 0, TRUE,
+        cd);
+      *be = end_op;
+      DPRINTF(("fixed length = %d\n", fixed_length));
+      if (fixed_length < 0)
+        {
+        errorcode = (fixed_length == -2)? ERR36 :
+                    (fixed_length == -4)? ERR70 : ERR25;
+        break;
+        }
+      if (fixed_length > cd->max_lookbehind) cd->max_lookbehind = fixed_length;
+      PUT(cc, 1, fixed_length);
+      }
+    cc += 1 + LINK_SIZE;
+    }
+  }
+
+/* Failed to compile, or error while post-processing */
+
+if (errorcode != 0)
+  {
+  (PUBL(free))(re);
+  PCRE_EARLY_ERROR_RETURN:
+  *erroroffset = (int)(ptr - (const pcre_uchar *)pattern);
+  PCRE_EARLY_ERROR_RETURN2:
+  *errorptr = find_error_text(errorcode);
+  if (errorcodeptr != NULL) *errorcodeptr = errorcode;
+  return NULL;
+  }
+
+/* If the anchored option was not passed, set the flag if we can determine that
+the pattern is anchored by virtue of ^ characters or \A or anything else (such
+as starting with .* when DOTALL is set).
+
+Otherwise, if we know what the first byte has to be, save it, because that
+speeds up unanchored matches no end. If not, see if we can set the
+PCRE_STARTLINE flag. This is helpful for multiline matches when all branches
+start with ^. and also when all branches start with .* for non-DOTALL matches.
+*/
+
+if ((re->options & PCRE_ANCHORED) == 0)
+  {
+  if (is_anchored(codestart, 0, cd->backref_map))
+    re->options |= PCRE_ANCHORED;
+  else
+    {
+    if (firstchar < 0)
+      firstchar = find_firstassertedchar(codestart, FALSE);
+    if (firstchar >= 0)   /* Remove caseless flag for non-caseable chars */
+      {
+#ifdef COMPILE_PCRE8
+      re->first_char = firstchar & 0xff;
+#else
+#ifdef COMPILE_PCRE16
+      re->first_char = firstchar & 0xffff;
+#endif
+#endif
+      if ((firstchar & REQ_CASELESS) != 0)
+        {
+#if defined SUPPORT_UCP && !(defined COMPILE_PCRE8)
+        /* We ignore non-ASCII first chars in 8 bit mode. */
+        if (utf)
+          {
+          if (re->first_char < 128)
+            {
+            if (cd->fcc[re->first_char] != re->first_char)
+              re->flags |= PCRE_FCH_CASELESS;
+            }
+          else if (UCD_OTHERCASE(re->first_char) != re->first_char)
+            re->flags |= PCRE_FCH_CASELESS;
+          }
+        else
+#endif
+        if (MAX_255(re->first_char)
+            && cd->fcc[re->first_char] != re->first_char)
+          re->flags |= PCRE_FCH_CASELESS;
+        }
+
+      re->flags |= PCRE_FIRSTSET;
+      }
+    else if (is_startline(codestart, 0, cd->backref_map))
+      re->flags |= PCRE_STARTLINE;
+    }
+  }
+
+/* For an anchored pattern, we use the "required byte" only if it follows a
+variable length item in the regex. Remove the caseless flag for non-caseable
+bytes. */
+
+if (reqchar >= 0 &&
+     ((re->options & PCRE_ANCHORED) == 0 || (reqchar & REQ_VARY) != 0))
+  {
+#ifdef COMPILE_PCRE8
+  re->req_char = reqchar & 0xff;
+#else
+#ifdef COMPILE_PCRE16
+  re->req_char = reqchar & 0xffff;
+#endif
+#endif
+  if ((reqchar & REQ_CASELESS) != 0)
+    {
+#if defined SUPPORT_UCP && !(defined COMPILE_PCRE8)
+    /* We ignore non-ASCII first chars in 8 bit mode. */
+    if (utf)
+      {
+      if (re->req_char < 128)
+        {
+        if (cd->fcc[re->req_char] != re->req_char)
+          re->flags |= PCRE_RCH_CASELESS;
+        }
+      else if (UCD_OTHERCASE(re->req_char) != re->req_char)
+        re->flags |= PCRE_RCH_CASELESS;
+      }
+    else
+#endif
+    if (MAX_255(re->req_char) && cd->fcc[re->req_char] != re->req_char)
+      re->flags |= PCRE_RCH_CASELESS;
+    }
+
+  re->flags |= PCRE_REQCHSET;
+  }
+
+/* Print out the compiled data if debugging is enabled. This is never the
+case when building a production library. */
+
+#ifdef PCRE_DEBUG
+printf("Length = %d top_bracket = %d top_backref = %d\n",
+  length, re->top_bracket, re->top_backref);
+
+printf("Options=%08x\n", re->options);
+
+if ((re->flags & PCRE_FIRSTSET) != 0)
+  {
+  pcre_uchar ch = re->first_char;
+  const char *caseless =
+    ((re->flags & PCRE_FCH_CASELESS) == 0)? "" : " (caseless)";
+  if (PRINTABLE(ch)) printf("First char = %c%s\n", ch, caseless);
+    else printf("First char = \\x%02x%s\n", ch, caseless);
+  }
+
+if ((re->flags & PCRE_REQCHSET) != 0)
+  {
+  pcre_uchar ch = re->req_char;
+  const char *caseless =
+    ((re->flags & PCRE_RCH_CASELESS) == 0)? "" : " (caseless)";
+  if (PRINTABLE(ch)) printf("Req char = %c%s\n", ch, caseless);
+    else printf("Req char = \\x%02x%s\n", ch, caseless);
+  }
+
+#ifdef COMPILE_PCRE8
+pcre_printint((pcre *)re, stdout, TRUE);
+#else
+pcre16_printint((pcre *)re, stdout, TRUE);
+#endif
+
+/* This check is done here in the debugging case so that the code that
+was compiled can be seen. */
+
+if (code - codestart > length)
+  {
+  (PUBL(free))(re);
+  *errorptr = find_error_text(ERR23);
+  *erroroffset = ptr - (pcre_uchar *)pattern;
+  if (errorcodeptr != NULL) *errorcodeptr = ERR23;
+  return NULL;
+  }
+#endif   /* PCRE_DEBUG */
+
+#ifdef COMPILE_PCRE8
+return (pcre *)re;
+#else
+return (pcre16 *)re;
+#endif
+}
+
+/* End of pcre_compile.c */
diff --git a/ext/pcre/pcrelib/pcre_config.c b/ext/pcre/pcrelib/pcre_config.c
new file mode 100644
index 0000000..3471959
--- /dev/null
+++ b/ext/pcre/pcrelib/pcre_config.c
@@ -0,0 +1,168 @@
+/*************************************************
+*      Perl-Compatible Regular Expressions       *
+*************************************************/
+
+/* PCRE is a library of functions to support regular expressions whose syntax
+and semantics are as close as possible to those of the Perl 5 language.
+
+                       Written by Philip Hazel
+           Copyright (c) 1997-2012 University of Cambridge
+
+-----------------------------------------------------------------------------
+Redistribution and use in source and binary forms, with or without
+modification, are permitted provided that the following conditions are met:
+
+    * Redistributions of source code must retain the above copyright notice,
+      this list of conditions and the following disclaimer.
+
+    * Redistributions in binary form must reproduce the above copyright
+      notice, this list of conditions and the following disclaimer in the
+      documentation and/or other materials provided with the distribution.
+
+    * Neither the name of the University of Cambridge nor the names of its
+      contributors may be used to endorse or promote products derived from
+      this software without specific prior written permission.
+
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+POSSIBILITY OF SUCH DAMAGE.
+-----------------------------------------------------------------------------
+*/
+
+
+/* This module contains the external function pcre_config(). */
+
+
+#include "config.h"
+
+/* Keep the original link size. */
+static int real_link_size = LINK_SIZE;
+
+#include "pcre_internal.h"
+
+
+/*************************************************
+* Return info about what features are configured *
+*************************************************/
+
+/* This function has an extensible interface so that additional items can be
+added compatibly.
+
+Arguments:
+  what             what information is required
+  where            where to put the information
+
+Returns:           0 if data returned, negative on error
+*/
+
+#ifdef COMPILE_PCRE8
+PCRE_EXP_DEFN int PCRE_CALL_CONVENTION
+pcre_config(int what, void *where)
+#else
+PCRE_EXP_DEFN int PCRE_CALL_CONVENTION
+pcre16_config(int what, void *where)
+#endif
+{
+switch (what)
+  {
+  case PCRE_CONFIG_UTF8:
+#if defined COMPILE_PCRE16
+  *((int *)where) = 0;
+  return PCRE_ERROR_BADOPTION;
+#else
+#if defined SUPPORT_UTF
+  *((int *)where) = 1;
+#else
+  *((int *)where) = 0;
+#endif
+  break;
+#endif
+
+  case PCRE_CONFIG_UTF16:
+#if defined COMPILE_PCRE8
+  *((int *)where) = 0;
+  return PCRE_ERROR_BADOPTION;
+#else
+#if defined SUPPORT_UTF
+  *((int *)where) = 1;
+#else
+  *((int *)where) = 0;
+#endif
+  break;
+#endif
+
+  case PCRE_CONFIG_UNICODE_PROPERTIES:
+#ifdef SUPPORT_UCP
+  *((int *)where) = 1;
+#else
+  *((int *)where) = 0;
+#endif
+  break;
+
+  case PCRE_CONFIG_JIT:
+#ifdef SUPPORT_JIT
+  *((int *)where) = 1;
+#else
+  *((int *)where) = 0;
+#endif
+  break;
+
+  case PCRE_CONFIG_JITTARGET:
+#ifdef SUPPORT_JIT
+  *((const char **)where) = PRIV(jit_get_target)();
+#else
+  *((const char **)where) = NULL;
+#endif
+  break;
+
+  case PCRE_CONFIG_NEWLINE:
+  *((int *)where) = NEWLINE;
+  break;
+
+  case PCRE_CONFIG_BSR:
+#ifdef BSR_ANYCRLF
+  *((int *)where) = 1;
+#else
+  *((int *)where) = 0;
+#endif
+  break;
+
+  case PCRE_CONFIG_LINK_SIZE:
+  *((int *)where) = real_link_size;
+  break;
+
+  case PCRE_CONFIG_POSIX_MALLOC_THRESHOLD:
+  *((int *)where) = POSIX_MALLOC_THRESHOLD;
+  break;
+
+  case PCRE_CONFIG_MATCH_LIMIT:
+  *((unsigned long int *)where) = MATCH_LIMIT;
+  break;
+
+  case PCRE_CONFIG_MATCH_LIMIT_RECURSION:
+  *((unsigned long int *)where) = MATCH_LIMIT_RECURSION;
+  break;
+
+  case PCRE_CONFIG_STACKRECURSE:
+#ifdef NO_RECURSE
+  *((int *)where) = 0;
+#else
+  *((int *)where) = 1;
+#endif
+  break;
+
+  default: return PCRE_ERROR_BADOPTION;
+  }
+
+return 0;
+}
+
+/* End of pcre_config.c */
diff --git a/ext/pcre/pcrelib/pcre_exec.c b/ext/pcre/pcrelib/pcre_exec.c
new file mode 100644
index 0000000..4a8f1c2
--- /dev/null
+++ b/ext/pcre/pcrelib/pcre_exec.c
@@ -0,0 +1,7147 @@
+/*************************************************
+*      Perl-Compatible Regular Expressions       *
+*************************************************/
+
+/* PCRE is a library of functions to support regular expressions whose syntax
+and semantics are as close as possible to those of the Perl 5 language.
+
+                       Written by Philip Hazel
+           Copyright (c) 1997-2012 University of Cambridge
+
+-----------------------------------------------------------------------------
+Redistribution and use in source and binary forms, with or without
+modification, are permitted provided that the following conditions are met:
+
+    * Redistributions of source code must retain the above copyright notice,
+      this list of conditions and the following disclaimer.
+
+    * Redistributions in binary form must reproduce the above copyright
+      notice, this list of conditions and the following disclaimer in the
+      documentation and/or other materials provided with the distribution.
+
+    * Neither the name of the University of Cambridge nor the names of its
+      contributors may be used to endorse or promote products derived from
+      this software without specific prior written permission.
+
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+POSSIBILITY OF SUCH DAMAGE.
+-----------------------------------------------------------------------------
+*/
+
+/* This module contains pcre_exec(), the externally visible function that does
+pattern matching using an NFA algorithm, trying to mimic Perl as closely as
+possible. There are also some static supporting functions. */
+
+#include "config.h"
+
+#define NLBLOCK md             /* Block containing newline information */
+#define PSSTART start_subject  /* Field containing processed string start */
+#define PSEND   end_subject    /* Field containing processed string end */
+
+#include "pcre_internal.h"
+
+/* Undefine some potentially clashing cpp symbols */
+
+#undef min
+#undef max
+
+/* Values for setting in md->match_function_type to indicate two special types
+of call to match(). We do it this way to save on using another stack variable,
+as stack usage is to be discouraged. */
+
+#define MATCH_CONDASSERT     1  /* Called to check a condition assertion */
+#define MATCH_CBEGROUP       2  /* Could-be-empty unlimited repeat group */
+
+/* Non-error returns from the match() function. Error returns are externally
+defined PCRE_ERROR_xxx codes, which are all negative. */
+
+#define MATCH_MATCH        1
+#define MATCH_NOMATCH      0
+
+/* Special internal returns from the match() function. Make them sufficiently
+negative to avoid the external error codes. */
+
+#define MATCH_ACCEPT       (-999)
+#define MATCH_COMMIT       (-998)
+#define MATCH_KETRPOS      (-997)
+#define MATCH_ONCE         (-996)
+#define MATCH_PRUNE        (-995)
+#define MATCH_SKIP         (-994)
+#define MATCH_SKIP_ARG     (-993)
+#define MATCH_THEN         (-992)
+
+/* Maximum number of ints of offset to save on the stack for recursive calls.
+If the offset vector is bigger, malloc is used. This should be a multiple of 3,
+because the offset vector is always a multiple of 3 long. */
+
+#define REC_STACK_SAVE_MAX 30
+
+/* Min and max values for the common repeats; for the maxima, 0 => infinity */
+
+static const char rep_min[] = { 0, 0, 1, 1, 0, 0 };
+static const char rep_max[] = { 0, 0, 0, 0, 1, 1 };
+
+
+
+#ifdef PCRE_DEBUG
+/*************************************************
+*        Debugging function to print chars       *
+*************************************************/
+
+/* Print a sequence of chars in printable format, stopping at the end of the
+subject if the requested.
+
+Arguments:
+  p           points to characters
+  length      number to print
+  is_subject  TRUE if printing from within md->start_subject
+  md          pointer to matching data block, if is_subject is TRUE
+
+Returns:     nothing
+*/
+
+static void
+pchars(const pcre_uchar *p, int length, BOOL is_subject, match_data *md)
+{
+unsigned int c;
+if (is_subject && length > md->end_subject - p) length = md->end_subject - p;
+while (length-- > 0)
+  if (isprint(c = *(p++))) printf("%c", c); else printf("\\x%02x", c);
+}
+#endif
+
+
+
+/*************************************************
+*          Match a back-reference                *
+*************************************************/
+
+/* Normally, if a back reference hasn't been set, the length that is passed is
+negative, so the match always fails. However, in JavaScript compatibility mode,
+the length passed is zero. Note that in caseless UTF-8 mode, the number of
+subject bytes matched may be different to the number of reference bytes.
+
+Arguments:
+  offset      index into the offset vector
+  eptr        pointer into the subject
+  length      length of reference to be matched (number of bytes)
+  md          points to match data block
+  caseless    TRUE if caseless
+
+Returns:      >= 0 the number of subject bytes matched
+              -1 no match
+              -2 partial match; always given if at end subject
+*/
+
+static int
+match_ref(int offset, register PCRE_PUCHAR eptr, int length, match_data *md,
+  BOOL caseless)
+{
+PCRE_PUCHAR eptr_start = eptr;
+register PCRE_PUCHAR p = md->start_subject + md->offset_vector[offset];
+
+#ifdef PCRE_DEBUG
+if (eptr >= md->end_subject)
+  printf("matching subject <null>");
+else
+  {
+  printf("matching subject ");
+  pchars(eptr, length, TRUE, md);
+  }
+printf(" against backref ");
+pchars(p, length, FALSE, md);
+printf("\n");
+#endif
+
+/* Always fail if reference not set (and not JavaScript compatible - in that
+case the length is passed as zero). */
+
+if (length < 0) return -1;
+
+/* Separate the caseless case for speed. In UTF-8 mode we can only do this
+properly if Unicode properties are supported. Otherwise, we can check only
+ASCII characters. */
+
+if (caseless)
+  {
+#ifdef SUPPORT_UTF
+#ifdef SUPPORT_UCP
+  if (md->utf)
+    {
+    /* Match characters up to the end of the reference. NOTE: the number of
+    bytes matched may differ, because there are some characters whose upper and
+    lower case versions code as different numbers of bytes. For example, U+023A
+    (2 bytes in UTF-8) is the upper case version of U+2C65 (3 bytes in UTF-8);
+    a sequence of 3 of the former uses 6 bytes, as does a sequence of two of
+    the latter. It is important, therefore, to check the length along the
+    reference, not along the subject (earlier code did this wrong). */
+
+    PCRE_PUCHAR endptr = p + length;
+    while (p < endptr)
+      {
+      int c, d;
+      if (eptr >= md->end_subject) return -2;   /* Partial match */
+      GETCHARINC(c, eptr);
+      GETCHARINC(d, p);
+      if (c != d && c != UCD_OTHERCASE(d)) return -1;
+      }
+    }
+  else
+#endif
+#endif
+
+  /* The same code works when not in UTF-8 mode and in UTF-8 mode when there
+  is no UCP support. */
+    {
+    while (length-- > 0)
+      {
+      if (eptr >= md->end_subject) return -2;   /* Partial match */
+      if (TABLE_GET(*p, md->lcc, *p) != TABLE_GET(*eptr, md->lcc, *eptr)) return -1;
+      p++;
+      eptr++;
+      }
+    }
+  }
+
+/* In the caseful case, we can just compare the bytes, whether or not we
+are in UTF-8 mode. */
+
+else
+  {
+  while (length-- > 0)
+    {
+    if (eptr >= md->end_subject) return -2;   /* Partial match */
+    if (*p++ != *eptr++) return -1;
+    }
+  }
+
+return (int)(eptr - eptr_start);
+}
+
+
+
+/***************************************************************************
+****************************************************************************
+                   RECURSION IN THE match() FUNCTION
+
+The match() function is highly recursive, though not every recursive call
+increases the recursive depth. Nevertheless, some regular expressions can cause
+it to recurse to a great depth. I was writing for Unix, so I just let it call
+itself recursively. This uses the stack for saving everything that has to be
+saved for a recursive call. On Unix, the stack can be large, and this works
+fine.
+
+It turns out that on some non-Unix-like systems there are problems with
+programs that use a lot of stack. (This despite the fact that every last chip
+has oodles of memory these days, and techniques for extending the stack have
+been known for decades.) So....
+
+There is a fudge, triggered by defining NO_RECURSE, which avoids recursive
+calls by keeping local variables that need to be preserved in blocks of memory
+obtained from malloc() instead instead of on the stack. Macros are used to
+achieve this so that the actual code doesn't look very different to what it
+always used to.
+
+The original heap-recursive code used longjmp(). However, it seems that this
+can be very slow on some operating systems. Following a suggestion from Stan
+Switzer, the use of longjmp() has been abolished, at the cost of having to
+provide a unique number for each call to RMATCH. There is no way of generating
+a sequence of numbers at compile time in C. I have given them names, to make
+them stand out more clearly.
+
+Crude tests on x86 Linux show a small speedup of around 5-8%. However, on
+FreeBSD, avoiding longjmp() more than halves the time taken to run the standard
+tests. Furthermore, not using longjmp() means that local dynamic variables
+don't have indeterminate values; this has meant that the frame size can be
+reduced because the result can be "passed back" by straight setting of the
+variable instead of being passed in the frame.
+****************************************************************************
+***************************************************************************/
+
+/* Numbers for RMATCH calls. When this list is changed, the code at HEAP_RETURN
+below must be updated in sync.  */
+
+enum { RM1=1, RM2,  RM3,  RM4,  RM5,  RM6,  RM7,  RM8,  RM9,  RM10,
+       RM11,  RM12, RM13, RM14, RM15, RM16, RM17, RM18, RM19, RM20,
+       RM21,  RM22, RM23, RM24, RM25, RM26, RM27, RM28, RM29, RM30,
+       RM31,  RM32, RM33, RM34, RM35, RM36, RM37, RM38, RM39, RM40,
+       RM41,  RM42, RM43, RM44, RM45, RM46, RM47, RM48, RM49, RM50,
+       RM51,  RM52, RM53, RM54, RM55, RM56, RM57, RM58, RM59, RM60,
+       RM61,  RM62, RM63, RM64, RM65, RM66 };
+
+/* These versions of the macros use the stack, as normal. There are debugging
+versions and production versions. Note that the "rw" argument of RMATCH isn't
+actually used in this definition. */
+
+#ifndef NO_RECURSE
+#define REGISTER register
+
+#ifdef PCRE_DEBUG
+#define RMATCH(ra,rb,rc,rd,re,rw) \
+  { \
+  printf("match() called in line %d\n", __LINE__); \
+  rrc = match(ra,rb,mstart,rc,rd,re,rdepth+1); \
+  printf("to line %d\n", __LINE__); \
+  }
+#define RRETURN(ra) \
+  { \
+  printf("match() returned %d from line %d ", ra, __LINE__); \
+  return ra; \
+  }
+#else
+#define RMATCH(ra,rb,rc,rd,re,rw) \
+  rrc = match(ra,rb,mstart,rc,rd,re,rdepth+1)
+#define RRETURN(ra) return ra
+#endif
+
+#else
+
+
+/* These versions of the macros manage a private stack on the heap. Note that
+the "rd" argument of RMATCH isn't actually used in this definition. It's the md
+argument of match(), which never changes. */
+
+#define REGISTER
+
+#define RMATCH(ra,rb,rc,rd,re,rw)\
+  {\
+  heapframe *newframe = frame->Xnextframe;\
+  if (newframe == NULL)\
+    {\
+    newframe = (heapframe *)(PUBL(stack_malloc))(sizeof(heapframe));\
+    if (newframe == NULL) RRETURN(PCRE_ERROR_NOMEMORY);\
+    newframe->Xnextframe = NULL;\
+    frame->Xnextframe = newframe;\
+    }\
+  frame->Xwhere = rw;\
+  newframe->Xeptr = ra;\
+  newframe->Xecode = rb;\
+  newframe->Xmstart = mstart;\
+  newframe->Xoffset_top = rc;\
+  newframe->Xeptrb = re;\
+  newframe->Xrdepth = frame->Xrdepth + 1;\
+  newframe->Xprevframe = frame;\
+  frame = newframe;\
+  DPRINTF(("restarting from line %d\n", __LINE__));\
+  goto HEAP_RECURSE;\
+  L_##rw:\
+  DPRINTF(("jumped back to line %d\n", __LINE__));\
+  }
+
+#define RRETURN(ra)\
+  {\
+  heapframe *oldframe = frame;\
+  frame = oldframe->Xprevframe;\
+  if (frame != NULL)\
+    {\
+    rrc = ra;\
+    goto HEAP_RETURN;\
+    }\
+  return ra;\
+  }
+
+
+/* Structure for remembering the local variables in a private frame */
+
+typedef struct heapframe {
+  struct heapframe *Xprevframe;
+  struct heapframe *Xnextframe;
+
+  /* Function arguments that may change */
+
+  PCRE_PUCHAR Xeptr;
+  const pcre_uchar *Xecode;
+  PCRE_PUCHAR Xmstart;
+  int Xoffset_top;
+  eptrblock *Xeptrb;
+  unsigned int Xrdepth;
+
+  /* Function local variables */
+
+  PCRE_PUCHAR Xcallpat;
+#ifdef SUPPORT_UTF
+  PCRE_PUCHAR Xcharptr;
+#endif
+  PCRE_PUCHAR Xdata;
+  PCRE_PUCHAR Xnext;
+  PCRE_PUCHAR Xpp;
+  PCRE_PUCHAR Xprev;
+  PCRE_PUCHAR Xsaved_eptr;
+
+  recursion_info Xnew_recursive;
+
+  BOOL Xcur_is_word;
+  BOOL Xcondition;
+  BOOL Xprev_is_word;
+
+#ifdef SUPPORT_UCP
+  int Xprop_type;
+  int Xprop_value;
+  int Xprop_fail_result;
+  int Xoclength;
+  pcre_uchar Xocchars[6];
+#endif
+
+  int Xcodelink;
+  int Xctype;
+  unsigned int Xfc;
+  int Xfi;
+  int Xlength;
+  int Xmax;
+  int Xmin;
+  int Xnumber;
+  int Xoffset;
+  int Xop;
+  int Xsave_capture_last;
+  int Xsave_offset1, Xsave_offset2, Xsave_offset3;
+  int Xstacksave[REC_STACK_SAVE_MAX];
+
+  eptrblock Xnewptrb;
+
+  /* Where to jump back to */
+
+  int Xwhere;
+
+} heapframe;
+
+#endif
+
+
+/***************************************************************************
+***************************************************************************/
+
+
+
+/*************************************************
+*         Match from current position            *
+*************************************************/
+
+/* This function is called recursively in many circumstances. Whenever it
+returns a negative (error) response, the outer incarnation must also return the
+same response. */
+
+/* These macros pack up tests that are used for partial matching, and which
+appear several times in the code. We set the "hit end" flag if the pointer is
+at the end of the subject and also past the start of the subject (i.e.
+something has been matched). For hard partial matching, we then return
+immediately. The second one is used when we already know we are past the end of
+the subject. */
+
+#define CHECK_PARTIAL()\
+  if (md->partial != 0 && eptr >= md->end_subject && \
+      eptr > md->start_used_ptr) \
+    { \
+    md->hitend = TRUE; \
+    if (md->partial > 1) RRETURN(PCRE_ERROR_PARTIAL); \
+    }
+
+#define SCHECK_PARTIAL()\
+  if (md->partial != 0 && eptr > md->start_used_ptr) \
+    { \
+    md->hitend = TRUE; \
+    if (md->partial > 1) RRETURN(PCRE_ERROR_PARTIAL); \
+    }
+
+
+/* Performance note: It might be tempting to extract commonly used fields from
+the md structure (e.g. utf, end_subject) into individual variables to improve
+performance. Tests using gcc on a SPARC disproved this; in the first case, it
+made performance worse.
+
+Arguments:
+   eptr        pointer to current character in subject
+   ecode       pointer to current position in compiled code
+   mstart      pointer to the current match start position (can be modified
+                 by encountering \K)
+   offset_top  current top pointer
+   md          pointer to "static" info for the match
+   eptrb       pointer to chain of blocks containing eptr at start of
+                 brackets - for testing for empty matches
+   rdepth      the recursion depth
+
+Returns:       MATCH_MATCH if matched            )  these values are >= 0
+               MATCH_NOMATCH if failed to match  )
+               a negative MATCH_xxx value for PRUNE, SKIP, etc
+               a negative PCRE_ERROR_xxx value if aborted by an error condition
+                 (e.g. stopped by repeated call or recursion limit)
+*/
+
+static int
+match(REGISTER PCRE_PUCHAR eptr, REGISTER const pcre_uchar *ecode,
+  PCRE_PUCHAR mstart, int offset_top, match_data *md, eptrblock *eptrb,
+  unsigned int rdepth)
+{
+/* These variables do not need to be preserved over recursion in this function,
+so they can be ordinary variables in all cases. Mark some of them with
+"register" because they are used a lot in loops. */
+
+register int  rrc;         /* Returns from recursive calls */
+register int  i;           /* Used for loops not involving calls to RMATCH() */
+register unsigned int c;   /* Character values not kept over RMATCH() calls */
+register BOOL utf;         /* Local copy of UTF flag for speed */
+
+BOOL minimize, possessive; /* Quantifier options */
+BOOL caseless;
+int condcode;
+
+/* When recursion is not being used, all "local" variables that have to be
+preserved over calls to RMATCH() are part of a "frame". We set up the top-level
+frame on the stack here; subsequent instantiations are obtained from the heap
+whenever RMATCH() does a "recursion". See the macro definitions above. Putting
+the top-level on the stack rather than malloc-ing them all gives a performance
+boost in many cases where there is not much "recursion". */
+
+#ifdef NO_RECURSE
+heapframe *frame = (heapframe *)md->match_frames_base;
+
+/* Copy in the original argument variables */
+
+frame->Xeptr = eptr;
+frame->Xecode = ecode;
+frame->Xmstart = mstart;
+frame->Xoffset_top = offset_top;
+frame->Xeptrb = eptrb;
+frame->Xrdepth = rdepth;
+
+/* This is where control jumps back to to effect "recursion" */
+
+HEAP_RECURSE:
+
+/* Macros make the argument variables come from the current frame */
+
+#define eptr               frame->Xeptr
+#define ecode              frame->Xecode
+#define mstart             frame->Xmstart
+#define offset_top         frame->Xoffset_top
+#define eptrb              frame->Xeptrb
+#define rdepth             frame->Xrdepth
+
+/* Ditto for the local variables */
+
+#ifdef SUPPORT_UTF
+#define charptr            frame->Xcharptr
+#endif
+#define callpat            frame->Xcallpat
+#define codelink           frame->Xcodelink
+#define data               frame->Xdata
+#define next               frame->Xnext
+#define pp                 frame->Xpp
+#define prev               frame->Xprev
+#define saved_eptr         frame->Xsaved_eptr
+
+#define new_recursive      frame->Xnew_recursive
+
+#define cur_is_word        frame->Xcur_is_word
+#define condition          frame->Xcondition
+#define prev_is_word       frame->Xprev_is_word
+
+#ifdef SUPPORT_UCP
+#define prop_type          frame->Xprop_type
+#define prop_value         frame->Xprop_value
+#define prop_fail_result   frame->Xprop_fail_result
+#define oclength           frame->Xoclength
+#define occhars            frame->Xocchars
+#endif
+
+#define ctype              frame->Xctype
+#define fc                 frame->Xfc
+#define fi                 frame->Xfi
+#define length             frame->Xlength
+#define max                frame->Xmax
+#define min                frame->Xmin
+#define number             frame->Xnumber
+#define offset             frame->Xoffset
+#define op                 frame->Xop
+#define save_capture_last  frame->Xsave_capture_last
+#define save_offset1       frame->Xsave_offset1
+#define save_offset2       frame->Xsave_offset2
+#define save_offset3       frame->Xsave_offset3
+#define stacksave          frame->Xstacksave
+
+#define newptrb            frame->Xnewptrb
+
+/* When recursion is being used, local variables are allocated on the stack and
+get preserved during recursion in the normal way. In this environment, fi and
+i, and fc and c, can be the same variables. */
+
+#else         /* NO_RECURSE not defined */
+#define fi i
+#define fc c
+
+/* Many of the following variables are used only in small blocks of the code.
+My normal style of coding would have declared them within each of those blocks.
+However, in order to accommodate the version of this code that uses an external
+"stack" implemented on the heap, it is easier to declare them all here, so the
+declarations can be cut out in a block. The only declarations within blocks
+below are for variables that do not have to be preserved over a recursive call
+to RMATCH(). */
+
+#ifdef SUPPORT_UTF
+const pcre_uchar *charptr;
+#endif
+const pcre_uchar *callpat;
+const pcre_uchar *data;
+const pcre_uchar *next;
+PCRE_PUCHAR       pp;
+const pcre_uchar *prev;
+PCRE_PUCHAR       saved_eptr;
+
+recursion_info new_recursive;
+
+BOOL cur_is_word;
+BOOL condition;
+BOOL prev_is_word;
+
+#ifdef SUPPORT_UCP
+int prop_type;
+int prop_value;
+int prop_fail_result;
+int oclength;
+pcre_uchar occhars[6];
+#endif
+
+int codelink;
+int ctype;
+int length;
+int max;
+int min;
+int number;
+int offset;
+int op;
+int save_capture_last;
+int save_offset1, save_offset2, save_offset3;
+int stacksave[REC_STACK_SAVE_MAX];
+
+eptrblock newptrb;
+
+/* There is a special fudge for calling match() in a way that causes it to
+measure the size of its basic stack frame when the stack is being used for
+recursion. The second argument (ecode) being NULL triggers this behaviour. It
+cannot normally ever be NULL. The return is the negated value of the frame
+size. */
+
+if (ecode == NULL)
+  {
+  if (rdepth == 0)
+    return match((PCRE_PUCHAR)&rdepth, NULL, NULL, 0, NULL, NULL, 1);
+  else
+    {
+    int len = (char *)&rdepth - (char *)eptr;
+    return (len > 0)? -len : len;
+    }
+  }
+#endif     /* NO_RECURSE */
+
+/* To save space on the stack and in the heap frame, I have doubled up on some
+of the local variables that are used only in localised parts of the code, but
+still need to be preserved over recursive calls of match(). These macros define
+the alternative names that are used. */
+
+#define allow_zero    cur_is_word
+#define cbegroup      condition
+#define code_offset   codelink
+#define condassert    condition
+#define matched_once  prev_is_word
+#define foc           number
+#define save_mark     data
+
+/* These statements are here to stop the compiler complaining about unitialized
+variables. */
+
+#ifdef SUPPORT_UCP
+prop_value = 0;
+prop_fail_result = 0;
+#endif
+
+
+/* This label is used for tail recursion, which is used in a few cases even
+when NO_RECURSE is not defined, in order to reduce the amount of stack that is
+used. Thanks to Ian Taylor for noticing this possibility and sending the
+original patch. */
+
+TAIL_RECURSE:
+
+/* OK, now we can get on with the real code of the function. Recursive calls
+are specified by the macro RMATCH and RRETURN is used to return. When
+NO_RECURSE is *not* defined, these just turn into a recursive call to match()
+and a "return", respectively (possibly with some debugging if PCRE_DEBUG is
+defined). However, RMATCH isn't like a function call because it's quite a
+complicated macro. It has to be used in one particular way. This shouldn't,
+however, impact performance when true recursion is being used. */
+
+#ifdef SUPPORT_UTF
+utf = md->utf;       /* Local copy of the flag */
+#else
+utf = FALSE;
+#endif
+
+/* First check that we haven't called match() too many times, or that we
+haven't exceeded the recursive call limit. */
+
+if (md->match_call_count++ >= md->match_limit) RRETURN(PCRE_ERROR_MATCHLIMIT);
+if (rdepth >= md->match_limit_recursion) RRETURN(PCRE_ERROR_RECURSIONLIMIT);
+
+/* At the start of a group with an unlimited repeat that may match an empty
+string, the variable md->match_function_type is set to MATCH_CBEGROUP. It is
+done this way to save having to use another function argument, which would take
+up space on the stack. See also MATCH_CONDASSERT below.
+
+When MATCH_CBEGROUP is set, add the current subject pointer to the chain of
+such remembered pointers, to be checked when we hit the closing ket, in order
+to break infinite loops that match no characters. When match() is called in
+other circumstances, don't add to the chain. The MATCH_CBEGROUP feature must
+NOT be used with tail recursion, because the memory block that is used is on
+the stack, so a new one may be required for each match(). */
+
+if (md->match_function_type == MATCH_CBEGROUP)
+  {
+  newptrb.epb_saved_eptr = eptr;
+  newptrb.epb_prev = eptrb;
+  eptrb = &newptrb;
+  md->match_function_type = 0;
+  }
+
+/* Now start processing the opcodes. */
+
+for (;;)
+  {
+  minimize = possessive = FALSE;
+  op = *ecode;
+
+  switch(op)
+    {
+    case OP_MARK:
+    md->nomatch_mark = ecode + 2;
+    md->mark = NULL;    /* In case previously set by assertion */
+    RMATCH(eptr, ecode + PRIV(OP_lengths)[*ecode] + ecode[1], offset_top, md,
+      eptrb, RM55);
+    if ((rrc == MATCH_MATCH || rrc == MATCH_ACCEPT) &&
+         md->mark == NULL) md->mark = ecode + 2;
+
+    /* A return of MATCH_SKIP_ARG means that matching failed at SKIP with an
+    argument, and we must check whether that argument matches this MARK's
+    argument. It is passed back in md->start_match_ptr (an overloading of that
+    variable). If it does match, we reset that variable to the current subject
+    position and return MATCH_SKIP. Otherwise, pass back the return code
+    unaltered. */
+
+    else if (rrc == MATCH_SKIP_ARG &&
+        STRCMP_UC_UC(ecode + 2, md->start_match_ptr) == 0)
+      {
+      md->start_match_ptr = eptr;
+      RRETURN(MATCH_SKIP);
+      }
+    RRETURN(rrc);
+
+    case OP_FAIL:
+    RRETURN(MATCH_NOMATCH);
+
+    /* COMMIT overrides PRUNE, SKIP, and THEN */
+
+    case OP_COMMIT:
+    RMATCH(eptr, ecode + PRIV(OP_lengths)[*ecode], offset_top, md,
+      eptrb, RM52);
+    if (rrc != MATCH_NOMATCH && rrc != MATCH_PRUNE &&
+        rrc != MATCH_SKIP && rrc != MATCH_SKIP_ARG &&
+        rrc != MATCH_THEN)
+      RRETURN(rrc);
+    RRETURN(MATCH_COMMIT);
+
+    /* PRUNE overrides THEN */
+
+    case OP_PRUNE:
+    RMATCH(eptr, ecode + PRIV(OP_lengths)[*ecode], offset_top, md,
+      eptrb, RM51);
+    if (rrc != MATCH_NOMATCH && rrc != MATCH_THEN) RRETURN(rrc);
+    RRETURN(MATCH_PRUNE);
+
+    case OP_PRUNE_ARG:
+    md->nomatch_mark = ecode + 2;
+    md->mark = NULL;    /* In case previously set by assertion */
+    RMATCH(eptr, ecode + PRIV(OP_lengths)[*ecode] + ecode[1], offset_top, md,
+      eptrb, RM56);
+    if ((rrc == MATCH_MATCH || rrc == MATCH_ACCEPT) &&
+         md->mark == NULL) md->mark = ecode + 2;
+    if (rrc != MATCH_NOMATCH && rrc != MATCH_THEN) RRETURN(rrc);
+    RRETURN(MATCH_PRUNE);
+
+    /* SKIP overrides PRUNE and THEN */
+
+    case OP_SKIP:
+    RMATCH(eptr, ecode + PRIV(OP_lengths)[*ecode], offset_top, md,
+      eptrb, RM53);
+    if (rrc != MATCH_NOMATCH && rrc != MATCH_PRUNE && rrc != MATCH_THEN)
+      RRETURN(rrc);
+    md->start_match_ptr = eptr;   /* Pass back current position */
+    RRETURN(MATCH_SKIP);
+
+    /* Note that, for Perl compatibility, SKIP with an argument does NOT set
+    nomatch_mark. There is a flag that disables this opcode when re-matching a
+    pattern that ended with a SKIP for which there was not a matching MARK. */
+
+    case OP_SKIP_ARG:
+    if (md->ignore_skip_arg)
+      {
+      ecode += PRIV(OP_lengths)[*ecode] + ecode[1];
+      break;
+      }
+    RMATCH(eptr, ecode + PRIV(OP_lengths)[*ecode] + ecode[1], offset_top, md,
+      eptrb, RM57);
+    if (rrc != MATCH_NOMATCH && rrc != MATCH_PRUNE && rrc != MATCH_THEN)
+      RRETURN(rrc);
+
+    /* Pass back the current skip name by overloading md->start_match_ptr and
+    returning the special MATCH_SKIP_ARG return code. This will either be
+    caught by a matching MARK, or get to the top, where it causes a rematch
+    with the md->ignore_skip_arg flag set. */
+
+    md->start_match_ptr = ecode + 2;
+    RRETURN(MATCH_SKIP_ARG);
+
+    /* For THEN (and THEN_ARG) we pass back the address of the opcode, so that
+    the branch in which it occurs can be determined. Overload the start of
+    match pointer to do this. */
+
+    case OP_THEN:
+    RMATCH(eptr, ecode + PRIV(OP_lengths)[*ecode], offset_top, md,
+      eptrb, RM54);
+    if (rrc != MATCH_NOMATCH) RRETURN(rrc);
+    md->start_match_ptr = ecode;
+    RRETURN(MATCH_THEN);
+
+    case OP_THEN_ARG:
+    md->nomatch_mark = ecode + 2;
+    md->mark = NULL;    /* In case previously set by assertion */
+    RMATCH(eptr, ecode + PRIV(OP_lengths)[*ecode] + ecode[1], offset_top,
+      md, eptrb, RM58);
+    if ((rrc == MATCH_MATCH || rrc == MATCH_ACCEPT) &&
+         md->mark == NULL) md->mark = ecode + 2;
+    if (rrc != MATCH_NOMATCH) RRETURN(rrc);
+    md->start_match_ptr = ecode;
+    RRETURN(MATCH_THEN);
+
+    /* Handle an atomic group that does not contain any capturing parentheses.
+    This can be handled like an assertion. Prior to 8.13, all atomic groups
+    were handled this way. In 8.13, the code was changed as below for ONCE, so
+    that backups pass through the group and thereby reset captured values.
+    However, this uses a lot more stack, so in 8.20, atomic groups that do not
+    contain any captures generate OP_ONCE_NC, which can be handled in the old,
+    less stack intensive way.
+
+    Check the alternative branches in turn - the matching won't pass the KET
+    for this kind of subpattern. If any one branch matches, we carry on as at
+    the end of a normal bracket, leaving the subject pointer, but resetting
+    the start-of-match value in case it was changed by \K. */
+
+    case OP_ONCE_NC:
+    prev = ecode;
+    saved_eptr = eptr;
+    save_mark = md->mark;
+    do
+      {
+      RMATCH(eptr, ecode + 1 + LINK_SIZE, offset_top, md, eptrb, RM64);
+      if (rrc == MATCH_MATCH)  /* Note: _not_ MATCH_ACCEPT */
+        {
+        mstart = md->start_match_ptr;
+        break;
+        }
+      if (rrc == MATCH_THEN)
+        {
+        next = ecode + GET(ecode,1);
+        if (md->start_match_ptr < next &&
+            (*ecode == OP_ALT || *next == OP_ALT))
+          rrc = MATCH_NOMATCH;
+        }
+
+      if (rrc != MATCH_NOMATCH) RRETURN(rrc);
+      ecode += GET(ecode,1);
+      md->mark = save_mark;
+      }
+    while (*ecode == OP_ALT);
+
+    /* If hit the end of the group (which could be repeated), fail */
+
+    if (*ecode != OP_ONCE_NC && *ecode != OP_ALT) RRETURN(MATCH_NOMATCH);
+
+    /* Continue as from after the group, updating the offsets high water
+    mark, since extracts may have been taken. */
+
+    do ecode += GET(ecode, 1); while (*ecode == OP_ALT);
+
+    offset_top = md->end_offset_top;
+    eptr = md->end_match_ptr;
+
+    /* For a non-repeating ket, just continue at this level. This also
+    happens for a repeating ket if no characters were matched in the group.
+    This is the forcible breaking of infinite loops as implemented in Perl
+    5.005. */
+
+    if (*ecode == OP_KET || eptr == saved_eptr)
+      {
+      ecode += 1+LINK_SIZE;
+      break;
+      }
+
+    /* The repeating kets try the rest of the pattern or restart from the
+    preceding bracket, in the appropriate order. The second "call" of match()
+    uses tail recursion, to avoid using another stack frame. */
+
+    if (*ecode == OP_KETRMIN)
+      {
+      RMATCH(eptr, ecode + 1 + LINK_SIZE, offset_top, md, eptrb, RM65);
+      if (rrc != MATCH_NOMATCH) RRETURN(rrc);
+      ecode = prev;
+      goto TAIL_RECURSE;
+      }
+    else  /* OP_KETRMAX */
+      {
+      RMATCH(eptr, prev, offset_top, md, eptrb, RM66);
+      if (rrc != MATCH_NOMATCH) RRETURN(rrc);
+      ecode += 1 + LINK_SIZE;
+      goto TAIL_RECURSE;
+      }
+    /* Control never gets here */
+
+    /* Handle a capturing bracket, other than those that are possessive with an
+    unlimited repeat. If there is space in the offset vector, save the current
+    subject position in the working slot at the top of the vector. We mustn't
+    change the current values of the data slot, because they may be set from a
+    previous iteration of this group, and be referred to by a reference inside
+    the group. A failure to match might occur after the group has succeeded,
+    if something later on doesn't match. For this reason, we need to restore
+    the working value and also the values of the final offsets, in case they
+    were set by a previous iteration of the same bracket.
+
+    If there isn't enough space in the offset vector, treat this as if it were
+    a non-capturing bracket. Don't worry about setting the flag for the error
+    case here; that is handled in the code for KET. */
+
+    case OP_CBRA:
+    case OP_SCBRA:
+    number = GET2(ecode, 1+LINK_SIZE);
+    offset = number << 1;
+
+#ifdef PCRE_DEBUG
+    printf("start bracket %d\n", number);
+    printf("subject=");
+    pchars(eptr, 16, TRUE, md);
+    printf("\n");
+#endif
+
+    if (offset < md->offset_max)
+      {
+      save_offset1 = md->offset_vector[offset];
+      save_offset2 = md->offset_vector[offset+1];
+      save_offset3 = md->offset_vector[md->offset_end - number];
+      save_capture_last = md->capture_last;
+      save_mark = md->mark;
+
+      DPRINTF(("saving %d %d %d\n", save_offset1, save_offset2, save_offset3));
+      md->offset_vector[md->offset_end - number] =
+        (int)(eptr - md->start_subject);
+
+      for (;;)
+        {
+        if (op >= OP_SBRA) md->match_function_type = MATCH_CBEGROUP;
+        RMATCH(eptr, ecode + PRIV(OP_lengths)[*ecode], offset_top, md,
+          eptrb, RM1);
+        if (rrc == MATCH_ONCE) break;  /* Backing up through an atomic group */
+
+        /* If we backed up to a THEN, check whether it is within the current
+        branch by comparing the address of the THEN that is passed back with
+        the end of the branch. If it is within the current branch, and the
+        branch is one of two or more alternatives (it either starts or ends
+        with OP_ALT), we have reached the limit of THEN's action, so convert
+        the return code to NOMATCH, which will cause normal backtracking to
+        happen from now on. Otherwise, THEN is passed back to an outer
+        alternative. This implements Perl's treatment of parenthesized groups,
+        where a group not containing | does not affect the current alternative,
+        that is, (X) is NOT the same as (X|(*F)). */
+
+        if (rrc == MATCH_THEN)
+          {
+          next = ecode + GET(ecode,1);
+          if (md->start_match_ptr < next &&
+              (*ecode == OP_ALT || *next == OP_ALT))
+            rrc = MATCH_NOMATCH;
+          }
+
+        /* Anything other than NOMATCH is passed back. */
+
+        if (rrc != MATCH_NOMATCH) RRETURN(rrc);
+        md->capture_last = save_capture_last;
+        ecode += GET(ecode, 1);
+        md->mark = save_mark;
+        if (*ecode != OP_ALT) break;
+        }
+
+      DPRINTF(("bracket %d failed\n", number));
+      md->offset_vector[offset] = save_offset1;
+      md->offset_vector[offset+1] = save_offset2;
+      md->offset_vector[md->offset_end - number] = save_offset3;
+
+      /* At this point, rrc will be one of MATCH_ONCE or MATCH_NOMATCH. */
+
+      RRETURN(rrc);
+      }
+
+    /* FALL THROUGH ... Insufficient room for saving captured contents. Treat
+    as a non-capturing bracket. */
+
+    /* VVVVVVVVVVVVVVVVVVVVVVVVV */
+    /* VVVVVVVVVVVVVVVVVVVVVVVVV */
+
+    DPRINTF(("insufficient capture room: treat as non-capturing\n"));
+
+    /* VVVVVVVVVVVVVVVVVVVVVVVVV */
+    /* VVVVVVVVVVVVVVVVVVVVVVVVV */
+
+    /* Non-capturing or atomic group, except for possessive with unlimited
+    repeat and ONCE group with no captures. Loop for all the alternatives.
+
+    When we get to the final alternative within the brackets, we used to return
+    the result of a recursive call to match() whatever happened so it was
+    possible to reduce stack usage by turning this into a tail recursion,
+    except in the case of a possibly empty group. However, now that there is
+    the possiblity of (*THEN) occurring in the final alternative, this
+    optimization is no longer always possible.
+
+    We can optimize if we know there are no (*THEN)s in the pattern; at present
+    this is the best that can be done.
+
+    MATCH_ONCE is returned when the end of an atomic group is successfully
+    reached, but subsequent matching fails. It passes back up the tree (causing
+    captured values to be reset) until the original atomic group level is
+    reached. This is tested by comparing md->once_target with the start of the
+    group. At this point, the return is converted into MATCH_NOMATCH so that
+    previous backup points can be taken. */
+
+    case OP_ONCE:
+    case OP_BRA:
+    case OP_SBRA:
+    DPRINTF(("start non-capturing bracket\n"));
+
+    for (;;)
+      {
+      if (op >= OP_SBRA || op == OP_ONCE)
+        md->match_function_type = MATCH_CBEGROUP;
+
+      /* If this is not a possibly empty group, and there are no (*THEN)s in
+      the pattern, and this is the final alternative, optimize as described
+      above. */
+
+      else if (!md->hasthen && ecode[GET(ecode, 1)] != OP_ALT)
+        {
+        ecode += PRIV(OP_lengths)[*ecode];
+        goto TAIL_RECURSE;
+        }
+
+      /* In all other cases, we have to make another call to match(). */
+
+      save_mark = md->mark;
+      RMATCH(eptr, ecode + PRIV(OP_lengths)[*ecode], offset_top, md, eptrb,
+        RM2);
+
+      /* See comment in the code for capturing groups above about handling
+      THEN. */
+
+      if (rrc == MATCH_THEN)
+        {
+        next = ecode + GET(ecode,1);
+        if (md->start_match_ptr < next &&
+            (*ecode == OP_ALT || *next == OP_ALT))
+          rrc = MATCH_NOMATCH;
+        }
+
+      if (rrc != MATCH_NOMATCH)
+        {
+        if (rrc == MATCH_ONCE)
+          {
+          const pcre_uchar *scode = ecode;
+          if (*scode != OP_ONCE)           /* If not at start, find it */
+            {
+            while (*scode == OP_ALT) scode += GET(scode, 1);
+            scode -= GET(scode, 1);
+            }
+          if (md->once_target == scode) rrc = MATCH_NOMATCH;
+          }
+        RRETURN(rrc);
+        }
+      ecode += GET(ecode, 1);
+      md->mark = save_mark;
+      if (*ecode != OP_ALT) break;
+      }
+
+    RRETURN(MATCH_NOMATCH);
+
+    /* Handle possessive capturing brackets with an unlimited repeat. We come
+    here from BRAZERO with allow_zero set TRUE. The offset_vector values are
+    handled similarly to the normal case above. However, the matching is
+    different. The end of these brackets will always be OP_KETRPOS, which
+    returns MATCH_KETRPOS without going further in the pattern. By this means
+    we can handle the group by iteration rather than recursion, thereby
+    reducing the amount of stack needed. */
+
+    case OP_CBRAPOS:
+    case OP_SCBRAPOS:
+    allow_zero = FALSE;
+
+    POSSESSIVE_CAPTURE:
+    number = GET2(ecode, 1+LINK_SIZE);
+    offset = number << 1;
+
+#ifdef PCRE_DEBUG
+    printf("start possessive bracket %d\n", number);
+    printf("subject=");
+    pchars(eptr, 16, TRUE, md);
+    printf("\n");
+#endif
+
+    if (offset < md->offset_max)
+      {
+      matched_once = FALSE;
+      code_offset = (int)(ecode - md->start_code);
+
+      save_offset1 = md->offset_vector[offset];
+      save_offset2 = md->offset_vector[offset+1];
+      save_offset3 = md->offset_vector[md->offset_end - number];
+      save_capture_last = md->capture_last;
+
+      DPRINTF(("saving %d %d %d\n", save_offset1, save_offset2, save_offset3));
+
+      /* Each time round the loop, save the current subject position for use
+      when the group matches. For MATCH_MATCH, the group has matched, so we
+      restart it with a new subject starting position, remembering that we had
+      at least one match. For MATCH_NOMATCH, carry on with the alternatives, as
+      usual. If we haven't matched any alternatives in any iteration, check to
+      see if a previous iteration matched. If so, the group has matched;
+      continue from afterwards. Otherwise it has failed; restore the previous
+      capture values before returning NOMATCH. */
+
+      for (;;)
+        {
+        md->offset_vector[md->offset_end - number] =
+          (int)(eptr - md->start_subject);
+        if (op >= OP_SBRA) md->match_function_type = MATCH_CBEGROUP;
+        RMATCH(eptr, ecode + PRIV(OP_lengths)[*ecode], offset_top, md,
+          eptrb, RM63);
+        if (rrc == MATCH_KETRPOS)
+          {
+          offset_top = md->end_offset_top;
+          eptr = md->end_match_ptr;
+          ecode = md->start_code + code_offset;
+          save_capture_last = md->capture_last;
+          matched_once = TRUE;
+          continue;
+          }
+
+        /* See comment in the code for capturing groups above about handling
+        THEN. */
+
+        if (rrc == MATCH_THEN)
+          {
+          next = ecode + GET(ecode,1);
+          if (md->start_match_ptr < next &&
+              (*ecode == OP_ALT || *next == OP_ALT))
+            rrc = MATCH_NOMATCH;
+          }
+
+        if (rrc != MATCH_NOMATCH) RRETURN(rrc);
+        md->capture_last = save_capture_last;
+        ecode += GET(ecode, 1);
+        if (*ecode != OP_ALT) break;
+        }
+
+      if (!matched_once)
+        {
+        md->offset_vector[offset] = save_offset1;
+        md->offset_vector[offset+1] = save_offset2;
+        md->offset_vector[md->offset_end - number] = save_offset3;
+        }
+
+      if (allow_zero || matched_once)
+        {
+        ecode += 1 + LINK_SIZE;
+        break;
+        }
+
+      RRETURN(MATCH_NOMATCH);
+      }
+
+    /* FALL THROUGH ... Insufficient room for saving captured contents. Treat
+    as a non-capturing bracket. */
+
+    /* VVVVVVVVVVVVVVVVVVVVVVVVV */
+    /* VVVVVVVVVVVVVVVVVVVVVVVVV */
+
+    DPRINTF(("insufficient capture room: treat as non-capturing\n"));
+
+    /* VVVVVVVVVVVVVVVVVVVVVVVVV */
+    /* VVVVVVVVVVVVVVVVVVVVVVVVV */
+
+    /* Non-capturing possessive bracket with unlimited repeat. We come here
+    from BRAZERO with allow_zero = TRUE. The code is similar to the above,
+    without the capturing complication. It is written out separately for speed
+    and cleanliness. */
+
+    case OP_BRAPOS:
+    case OP_SBRAPOS:
+    allow_zero = FALSE;
+
+    POSSESSIVE_NON_CAPTURE:
+    matched_once = FALSE;
+    code_offset = (int)(ecode - md->start_code);
+
+    for (;;)
+      {
+      if (op >= OP_SBRA) md->match_function_type = MATCH_CBEGROUP;
+      RMATCH(eptr, ecode + PRIV(OP_lengths)[*ecode], offset_top, md,
+        eptrb, RM48);
+      if (rrc == MATCH_KETRPOS)
+        {
+        offset_top = md->end_offset_top;
+        eptr = md->end_match_ptr;
+        ecode = md->start_code + code_offset;
+        matched_once = TRUE;
+        continue;
+        }
+
+      /* See comment in the code for capturing groups above about handling
+      THEN. */
+
+      if (rrc == MATCH_THEN)
+        {
+        next = ecode + GET(ecode,1);
+        if (md->start_match_ptr < next &&
+            (*ecode == OP_ALT || *next == OP_ALT))
+          rrc = MATCH_NOMATCH;
+        }
+
+      if (rrc != MATCH_NOMATCH) RRETURN(rrc);
+      ecode += GET(ecode, 1);
+      if (*ecode != OP_ALT) break;
+      }
+
+    if (matched_once || allow_zero)
+      {
+      ecode += 1 + LINK_SIZE;
+      break;
+      }
+    RRETURN(MATCH_NOMATCH);
+
+    /* Control never reaches here. */
+
+    /* Conditional group: compilation checked that there are no more than
+    two branches. If the condition is false, skipping the first branch takes us
+    past the end if there is only one branch, but that's OK because that is
+    exactly what going to the ket would do. */
+
+    case OP_COND:
+    case OP_SCOND:
+    codelink = GET(ecode, 1);
+
+    /* Because of the way auto-callout works during compile, a callout item is
+    inserted between OP_COND and an assertion condition. */
+
+    if (ecode[LINK_SIZE+1] == OP_CALLOUT)
+      {
+      if (PUBL(callout) != NULL)
+        {
+        PUBL(callout_block) cb;
+        cb.version          = 2;   /* Version 1 of the callout block */
+        cb.callout_number   = ecode[LINK_SIZE+2];
+        cb.offset_vector    = md->offset_vector;
+#ifdef COMPILE_PCRE8
+        cb.subject          = (PCRE_SPTR)md->start_subject;
+#else
+        cb.subject          = (PCRE_SPTR16)md->start_subject;
+#endif
+        cb.subject_length   = (int)(md->end_subject - md->start_subject);
+        cb.start_match      = (int)(mstart - md->start_subject);
+        cb.current_position = (int)(eptr - md->start_subject);
+        cb.pattern_position = GET(ecode, LINK_SIZE + 3);
+        cb.next_item_length = GET(ecode, 3 + 2*LINK_SIZE);
+        cb.capture_top      = offset_top/2;
+        cb.capture_last     = md->capture_last;
+        cb.callout_data     = md->callout_data;
+        cb.mark             = md->nomatch_mark;
+        if ((rrc = (*PUBL(callout))(&cb)) > 0) RRETURN(MATCH_NOMATCH);
+        if (rrc < 0) RRETURN(rrc);
+        }
+      ecode += PRIV(OP_lengths)[OP_CALLOUT];
+      }
+
+    condcode = ecode[LINK_SIZE+1];
+
+    /* Now see what the actual condition is */
+
+    if (condcode == OP_RREF || condcode == OP_NRREF)    /* Recursion test */
+      {
+      if (md->recursive == NULL)                /* Not recursing => FALSE */
+        {
+        condition = FALSE;
+        ecode += GET(ecode, 1);
+        }
+      else
+        {
+        int recno = GET2(ecode, LINK_SIZE + 2);   /* Recursion group number*/
+        condition = (recno == RREF_ANY || recno == md->recursive->group_num);
+
+        /* If the test is for recursion into a specific subpattern, and it is
+        false, but the test was set up by name, scan the table to see if the
+        name refers to any other numbers, and test them. The condition is true
+        if any one is set. */
+
+        if (!condition && condcode == OP_NRREF)
+          {
+          pcre_uchar *slotA = md->name_table;
+          for (i = 0; i < md->name_count; i++)
+            {
+            if (GET2(slotA, 0) == recno) break;
+            slotA += md->name_entry_size;
+            }
+
+          /* Found a name for the number - there can be only one; duplicate
+          names for different numbers are allowed, but not vice versa. First
+          scan down for duplicates. */
+
+          if (i < md->name_count)
+            {
+            pcre_uchar *slotB = slotA;
+            while (slotB > md->name_table)
+              {
+              slotB -= md->name_entry_size;
+              if (STRCMP_UC_UC(slotA + IMM2_SIZE, slotB + IMM2_SIZE) == 0)
+                {
+                condition = GET2(slotB, 0) == md->recursive->group_num;
+                if (condition) break;
+                }
+              else break;
+              }
+
+            /* Scan up for duplicates */
+
+            if (!condition)
+              {
+              slotB = slotA;
+              for (i++; i < md->name_count; i++)
+                {
+                slotB += md->name_entry_size;
+                if (STRCMP_UC_UC(slotA + IMM2_SIZE, slotB + IMM2_SIZE) == 0)
+                  {
+                  condition = GET2(slotB, 0) == md->recursive->group_num;
+                  if (condition) break;
+                  }
+                else break;
+                }
+              }
+            }
+          }
+
+        /* Chose branch according to the condition */
+
+        ecode += condition? 1 + IMM2_SIZE : GET(ecode, 1);
+        }
+      }
+
+    else if (condcode == OP_CREF || condcode == OP_NCREF)  /* Group used test */
+      {
+      offset = GET2(ecode, LINK_SIZE+2) << 1;  /* Doubled ref number */
+      condition = offset < offset_top && md->offset_vector[offset] >= 0;
+
+      /* If the numbered capture is unset, but the reference was by name,
+      scan the table to see if the name refers to any other numbers, and test
+      them. The condition is true if any one is set. This is tediously similar
+      to the code above, but not close enough to try to amalgamate. */
+
+      if (!condition && condcode == OP_NCREF)
+        {
+        int refno = offset >> 1;
+        pcre_uchar *slotA = md->name_table;
+
+        for (i = 0; i < md->name_count; i++)
+          {
+          if (GET2(slotA, 0) == refno) break;
+          slotA += md->name_entry_size;
+          }
+
+        /* Found a name for the number - there can be only one; duplicate names
+        for different numbers are allowed, but not vice versa. First scan down
+        for duplicates. */
+
+        if (i < md->name_count)
+          {
+          pcre_uchar *slotB = slotA;
+          while (slotB > md->name_table)
+            {
+            slotB -= md->name_entry_size;
+            if (STRCMP_UC_UC(slotA + IMM2_SIZE, slotB + IMM2_SIZE) == 0)
+              {
+              offset = GET2(slotB, 0) << 1;
+              condition = offset < offset_top &&
+                md->offset_vector[offset] >= 0;
+              if (condition) break;
+              }
+            else break;
+            }
+
+          /* Scan up for duplicates */
+
+          if (!condition)
+            {
+            slotB = slotA;
+            for (i++; i < md->name_count; i++)
+              {
+              slotB += md->name_entry_size;
+              if (STRCMP_UC_UC(slotA + IMM2_SIZE, slotB + IMM2_SIZE) == 0)
+                {
+                offset = GET2(slotB, 0) << 1;
+                condition = offset < offset_top &&
+                  md->offset_vector[offset] >= 0;
+                if (condition) break;
+                }
+              else break;
+              }
+            }
+          }
+        }
+
+      /* Chose branch according to the condition */
+
+      ecode += condition? 1 + IMM2_SIZE : GET(ecode, 1);
+      }
+
+    else if (condcode == OP_DEF)     /* DEFINE - always false */
+      {
+      condition = FALSE;
+      ecode += GET(ecode, 1);
+      }
+
+    /* The condition is an assertion. Call match() to evaluate it - setting
+    md->match_function_type to MATCH_CONDASSERT causes it to stop at the end of
+    an assertion. */
+
+    else
+      {
+      md->match_function_type = MATCH_CONDASSERT;
+      RMATCH(eptr, ecode + 1 + LINK_SIZE, offset_top, md, NULL, RM3);
+      if (rrc == MATCH_MATCH)
+        {
+        if (md->end_offset_top > offset_top)
+          offset_top = md->end_offset_top;  /* Captures may have happened */
+        condition = TRUE;
+        ecode += 1 + LINK_SIZE + GET(ecode, LINK_SIZE + 2);
+        while (*ecode == OP_ALT) ecode += GET(ecode, 1);
+        }
+
+      /* PCRE doesn't allow the effect of (*THEN) to escape beyond an
+      assertion; it is therefore treated as NOMATCH. */
+
+      else if (rrc != MATCH_NOMATCH && rrc != MATCH_THEN)
+        {
+        RRETURN(rrc);         /* Need braces because of following else */
+        }
+      else
+        {
+        condition = FALSE;
+        ecode += codelink;
+        }
+      }
+
+    /* We are now at the branch that is to be obeyed. As there is only one, can
+    use tail recursion to avoid using another stack frame, except when there is
+    unlimited repeat of a possibly empty group. In the latter case, a recursive
+    call to match() is always required, unless the second alternative doesn't
+    exist, in which case we can just plough on. Note that, for compatibility
+    with Perl, the | in a conditional group is NOT treated as creating two
+    alternatives. If a THEN is encountered in the branch, it propagates out to
+    the enclosing alternative (unless nested in a deeper set of alternatives,
+    of course). */
+
+    if (condition || *ecode == OP_ALT)
+      {
+      if (op != OP_SCOND)
+        {
+        ecode += 1 + LINK_SIZE;
+        goto TAIL_RECURSE;
+        }
+
+      md->match_function_type = MATCH_CBEGROUP;
+      RMATCH(eptr, ecode + 1 + LINK_SIZE, offset_top, md, eptrb, RM49);
+      RRETURN(rrc);
+      }
+
+     /* Condition false & no alternative; continue after the group. */
+
+    else
+      {
+      ecode += 1 + LINK_SIZE;
+      }
+    break;
+
+
+    /* Before OP_ACCEPT there may be any number of OP_CLOSE opcodes,
+    to close any currently open capturing brackets. */
+
+    case OP_CLOSE:
+    number = GET2(ecode, 1);
+    offset = number << 1;
+
+#ifdef PCRE_DEBUG
+      printf("end bracket %d at *ACCEPT", number);
+      printf("\n");
+#endif
+
+    md->capture_last = number;
+    if (offset >= md->offset_max) md->offset_overflow = TRUE; else
+      {
+      md->offset_vector[offset] =
+        md->offset_vector[md->offset_end - number];
+      md->offset_vector[offset+1] = (int)(eptr - md->start_subject);
+      if (offset_top <= offset) offset_top = offset + 2;
+      }
+    ecode += 1 + IMM2_SIZE;
+    break;
+
+
+    /* End of the pattern, either real or forced. */
+
+    case OP_END:
+    case OP_ACCEPT:
+    case OP_ASSERT_ACCEPT:
+
+    /* If we have matched an empty string, fail if not in an assertion and not
+    in a recursion if either PCRE_NOTEMPTY is set, or if PCRE_NOTEMPTY_ATSTART
+    is set and we have matched at the start of the subject. In both cases,
+    backtracking will then try other alternatives, if any. */
+
+    if (eptr == mstart && op != OP_ASSERT_ACCEPT &&
+         md->recursive == NULL &&
+         (md->notempty ||
+           (md->notempty_atstart &&
+             mstart == md->start_subject + md->start_offset)))
+      RRETURN(MATCH_NOMATCH);
+
+    /* Otherwise, we have a match. */
+
+    md->end_match_ptr = eptr;           /* Record where we ended */
+    md->end_offset_top = offset_top;    /* and how many extracts were taken */
+    md->start_match_ptr = mstart;       /* and the start (\K can modify) */
+
+    /* For some reason, the macros don't work properly if an expression is
+    given as the argument to RRETURN when the heap is in use. */
+
+    rrc = (op == OP_END)? MATCH_MATCH : MATCH_ACCEPT;
+    RRETURN(rrc);
+
+    /* Assertion brackets. Check the alternative branches in turn - the
+    matching won't pass the KET for an assertion. If any one branch matches,
+    the assertion is true. Lookbehind assertions have an OP_REVERSE item at the
+    start of each branch to move the current point backwards, so the code at
+    this level is identical to the lookahead case. When the assertion is part
+    of a condition, we want to return immediately afterwards. The caller of
+    this incarnation of the match() function will have set MATCH_CONDASSERT in
+    md->match_function type, and one of these opcodes will be the first opcode
+    that is processed. We use a local variable that is preserved over calls to
+    match() to remember this case. */
+
+    case OP_ASSERT:
+    case OP_ASSERTBACK:
+    save_mark = md->mark;
+    if (md->match_function_type == MATCH_CONDASSERT)
+      {
+      condassert = TRUE;
+      md->match_function_type = 0;
+      }
+    else condassert = FALSE;
+
+    do
+      {
+      RMATCH(eptr, ecode + 1 + LINK_SIZE, offset_top, md, NULL, RM4);
+      if (rrc == MATCH_MATCH || rrc == MATCH_ACCEPT)
+        {
+        mstart = md->start_match_ptr;   /* In case \K reset it */
+        break;
+        }
+      md->mark = save_mark;
+
+      /* A COMMIT failure must fail the entire assertion, without trying any
+      subsequent branches. */
+
+      if (rrc == MATCH_COMMIT) RRETURN(MATCH_NOMATCH);
+
+      /* PCRE does not allow THEN to escape beyond an assertion; it
+      is treated as NOMATCH. */
+
+      if (rrc != MATCH_NOMATCH && rrc != MATCH_THEN) RRETURN(rrc);
+      ecode += GET(ecode, 1);
+      }
+    while (*ecode == OP_ALT);
+
+    if (*ecode == OP_KET) RRETURN(MATCH_NOMATCH);
+
+    /* If checking an assertion for a condition, return MATCH_MATCH. */
+
+    if (condassert) RRETURN(MATCH_MATCH);
+
+    /* Continue from after the assertion, updating the offsets high water
+    mark, since extracts may have been taken during the assertion. */
+
+    do ecode += GET(ecode,1); while (*ecode == OP_ALT);
+    ecode += 1 + LINK_SIZE;
+    offset_top = md->end_offset_top;
+    continue;
+
+    /* Negative assertion: all branches must fail to match. Encountering SKIP,
+    PRUNE, or COMMIT means we must assume failure without checking subsequent
+    branches. */
+
+    case OP_ASSERT_NOT:
+    case OP_ASSERTBACK_NOT:
+    save_mark = md->mark;
+    if (md->match_function_type == MATCH_CONDASSERT)
+      {
+      condassert = TRUE;
+      md->match_function_type = 0;
+      }
+    else condassert = FALSE;
+
+    do
+      {
+      RMATCH(eptr, ecode + 1 + LINK_SIZE, offset_top, md, NULL, RM5);
+      md->mark = save_mark;
+      if (rrc == MATCH_MATCH || rrc == MATCH_ACCEPT) RRETURN(MATCH_NOMATCH);
+      if (rrc == MATCH_SKIP || rrc == MATCH_PRUNE || rrc == MATCH_COMMIT)
+        {
+        do ecode += GET(ecode,1); while (*ecode == OP_ALT);
+        break;
+        }
+
+      /* PCRE does not allow THEN to escape beyond an assertion; it is treated
+      as NOMATCH. */
+
+      if (rrc != MATCH_NOMATCH && rrc != MATCH_THEN) RRETURN(rrc);
+      ecode += GET(ecode,1);
+      }
+    while (*ecode == OP_ALT);
+
+    if (condassert) RRETURN(MATCH_MATCH);  /* Condition assertion */
+
+    ecode += 1 + LINK_SIZE;
+    continue;
+
+    /* Move the subject pointer back. This occurs only at the start of
+    each branch of a lookbehind assertion. If we are too close to the start to
+    move back, this match function fails. When working with UTF-8 we move
+    back a number of characters, not bytes. */
+
+    case OP_REVERSE:
+#ifdef SUPPORT_UTF
+    if (utf)
+      {
+      i = GET(ecode, 1);
+      while (i-- > 0)
+        {
+        eptr--;
+        if (eptr < md->start_subject) RRETURN(MATCH_NOMATCH);
+        BACKCHAR(eptr);
+        }
+      }
+    else
+#endif
+
+    /* No UTF-8 support, or not in UTF-8 mode: count is byte count */
+
+      {
+      eptr -= GET(ecode, 1);
+      if (eptr < md->start_subject) RRETURN(MATCH_NOMATCH);
+      }
+
+    /* Save the earliest consulted character, then skip to next op code */
+
+    if (eptr < md->start_used_ptr) md->start_used_ptr = eptr;
+    ecode += 1 + LINK_SIZE;
+    break;
+
+    /* The callout item calls an external function, if one is provided, passing
+    details of the match so far. This is mainly for debugging, though the
+    function is able to force a failure. */
+
+    case OP_CALLOUT:
+    if (PUBL(callout) != NULL)
+      {
+      PUBL(callout_block) cb;
+      cb.version          = 2;   /* Version 1 of the callout block */
+      cb.callout_number   = ecode[1];
+      cb.offset_vector    = md->offset_vector;
+#ifdef COMPILE_PCRE8
+      cb.subject          = (PCRE_SPTR)md->start_subject;
+#else
+      cb.subject          = (PCRE_SPTR16)md->start_subject;
+#endif
+      cb.subject_length   = (int)(md->end_subject - md->start_subject);
+      cb.start_match      = (int)(mstart - md->start_subject);
+      cb.current_position = (int)(eptr - md->start_subject);
+      cb.pattern_position = GET(ecode, 2);
+      cb.next_item_length = GET(ecode, 2 + LINK_SIZE);
+      cb.capture_top      = offset_top/2;
+      cb.capture_last     = md->capture_last;
+      cb.callout_data     = md->callout_data;
+      cb.mark             = md->nomatch_mark;
+      if ((rrc = (*PUBL(callout))(&cb)) > 0) RRETURN(MATCH_NOMATCH);
+      if (rrc < 0) RRETURN(rrc);
+      }
+    ecode += 2 + 2*LINK_SIZE;
+    break;
+
+    /* Recursion either matches the current regex, or some subexpression. The
+    offset data is the offset to the starting bracket from the start of the
+    whole pattern. (This is so that it works from duplicated subpatterns.)
+
+    The state of the capturing groups is preserved over recursion, and
+    re-instated afterwards. We don't know how many are started and not yet
+    finished (offset_top records the completed total) so we just have to save
+    all the potential data. There may be up to 65535 such values, which is too
+    large to put on the stack, but using malloc for small numbers seems
+    expensive. As a compromise, the stack is used when there are no more than
+    REC_STACK_SAVE_MAX values to store; otherwise malloc is used.
+
+    There are also other values that have to be saved. We use a chained
+    sequence of blocks that actually live on the stack. Thanks to Robin Houston
+    for the original version of this logic. It has, however, been hacked around
+    a lot, so he is not to blame for the current way it works. */
+
+    case OP_RECURSE:
+      {
+      recursion_info *ri;
+      int recno;
+
+      callpat = md->start_code + GET(ecode, 1);
+      recno = (callpat == md->start_code)? 0 :
+        GET2(callpat, 1 + LINK_SIZE);
+
+      /* Check for repeating a recursion without advancing the subject pointer.
+      This should catch convoluted mutual recursions. (Some simple cases are
+      caught at compile time.) */
+
+      for (ri = md->recursive; ri != NULL; ri = ri->prevrec)
+        if (recno == ri->group_num && eptr == ri->subject_position)
+          RRETURN(PCRE_ERROR_RECURSELOOP);
+
+      /* Add to "recursing stack" */
+
+      new_recursive.group_num = recno;
+      new_recursive.subject_position = eptr;
+      new_recursive.prevrec = md->recursive;
+      md->recursive = &new_recursive;
+
+      /* Where to continue from afterwards */
+
+      ecode += 1 + LINK_SIZE;
+
+      /* Now save the offset data */
+
+      new_recursive.saved_max = md->offset_end;
+      if (new_recursive.saved_max <= REC_STACK_SAVE_MAX)
+        new_recursive.offset_save = stacksave;
+      else
+        {
+        new_recursive.offset_save =
+          (int *)(PUBL(malloc))(new_recursive.saved_max * sizeof(int));
+        if (new_recursive.offset_save == NULL) RRETURN(PCRE_ERROR_NOMEMORY);
+        }
+      memcpy(new_recursive.offset_save, md->offset_vector,
+            new_recursive.saved_max * sizeof(int));
+
+      /* OK, now we can do the recursion. After processing each alternative,
+      restore the offset data. If there were nested recursions, md->recursive
+      might be changed, so reset it before looping. */
+
+      DPRINTF(("Recursing into group %d\n", new_recursive.group_num));
+      cbegroup = (*callpat >= OP_SBRA);
+      do
+        {
+        if (cbegroup) md->match_function_type = MATCH_CBEGROUP;
+        RMATCH(eptr, callpat + PRIV(OP_lengths)[*callpat], offset_top,
+          md, eptrb, RM6);
+        memcpy(md->offset_vector, new_recursive.offset_save,
+            new_recursive.saved_max * sizeof(int));
+        md->recursive = new_recursive.prevrec;
+        if (rrc == MATCH_MATCH || rrc == MATCH_ACCEPT)
+          {
+          DPRINTF(("Recursion matched\n"));
+          if (new_recursive.offset_save != stacksave)
+            (PUBL(free))(new_recursive.offset_save);
+
+          /* Set where we got to in the subject, and reset the start in case
+          it was changed by \K. This *is* propagated back out of a recursion,
+          for Perl compatibility. */
+
+          eptr = md->end_match_ptr;
+          mstart = md->start_match_ptr;
+          goto RECURSION_MATCHED;        /* Exit loop; end processing */
+          }
+
+        /* PCRE does not allow THEN or COMMIT to escape beyond a recursion; it
+        is treated as NOMATCH. */
+
+        else if (rrc != MATCH_NOMATCH && rrc != MATCH_THEN &&
+                 rrc != MATCH_COMMIT)
+          {
+          DPRINTF(("Recursion gave error %d\n", rrc));
+          if (new_recursive.offset_save != stacksave)
+            (PUBL(free))(new_recursive.offset_save);
+          RRETURN(rrc);
+          }
+
+        md->recursive = &new_recursive;
+        callpat += GET(callpat, 1);
+        }
+      while (*callpat == OP_ALT);
+
+      DPRINTF(("Recursion didn't match\n"));
+      md->recursive = new_recursive.prevrec;
+      if (new_recursive.offset_save != stacksave)
+        (PUBL(free))(new_recursive.offset_save);
+      RRETURN(MATCH_NOMATCH);
+      }
+
+    RECURSION_MATCHED:
+    break;
+
+    /* An alternation is the end of a branch; scan along to find the end of the
+    bracketed group and go to there. */
+
+    case OP_ALT:
+    do ecode += GET(ecode,1); while (*ecode == OP_ALT);
+    break;
+
+    /* BRAZERO, BRAMINZERO and SKIPZERO occur just before a bracket group,
+    indicating that it may occur zero times. It may repeat infinitely, or not
+    at all - i.e. it could be ()* or ()? or even (){0} in the pattern. Brackets
+    with fixed upper repeat limits are compiled as a number of copies, with the
+    optional ones preceded by BRAZERO or BRAMINZERO. */
+
+    case OP_BRAZERO:
+    next = ecode + 1;
+    RMATCH(eptr, next, offset_top, md, eptrb, RM10);
+    if (rrc != MATCH_NOMATCH) RRETURN(rrc);
+    do next += GET(next, 1); while (*next == OP_ALT);
+    ecode = next + 1 + LINK_SIZE;
+    break;
+
+    case OP_BRAMINZERO:
+    next = ecode + 1;
+    do next += GET(next, 1); while (*next == OP_ALT);
+    RMATCH(eptr, next + 1+LINK_SIZE, offset_top, md, eptrb, RM11);
+    if (rrc != MATCH_NOMATCH) RRETURN(rrc);
+    ecode++;
+    break;
+
+    case OP_SKIPZERO:
+    next = ecode+1;
+    do next += GET(next,1); while (*next == OP_ALT);
+    ecode = next + 1 + LINK_SIZE;
+    break;
+
+    /* BRAPOSZERO occurs before a possessive bracket group. Don't do anything
+    here; just jump to the group, with allow_zero set TRUE. */
+
+    case OP_BRAPOSZERO:
+    op = *(++ecode);
+    allow_zero = TRUE;
+    if (op == OP_CBRAPOS || op == OP_SCBRAPOS) goto POSSESSIVE_CAPTURE;
+      goto POSSESSIVE_NON_CAPTURE;
+
+    /* End of a group, repeated or non-repeating. */
+
+    case OP_KET:
+    case OP_KETRMIN:
+    case OP_KETRMAX:
+    case OP_KETRPOS:
+    prev = ecode - GET(ecode, 1);
+
+    /* If this was a group that remembered the subject start, in order to break
+    infinite repeats of empty string matches, retrieve the subject start from
+    the chain. Otherwise, set it NULL. */
+
+    if (*prev >= OP_SBRA || *prev == OP_ONCE)
+      {
+      saved_eptr = eptrb->epb_saved_eptr;   /* Value at start of group */
+      eptrb = eptrb->epb_prev;              /* Backup to previous group */
+      }
+    else saved_eptr = NULL;
+
+    /* If we are at the end of an assertion group or a non-capturing atomic
+    group, stop matching and return MATCH_MATCH, but record the current high
+    water mark for use by positive assertions. We also need to record the match
+    start in case it was changed by \K. */
+
+    if ((*prev >= OP_ASSERT && *prev <= OP_ASSERTBACK_NOT) ||
+         *prev == OP_ONCE_NC)
+      {
+      md->end_match_ptr = eptr;      /* For ONCE_NC */
+      md->end_offset_top = offset_top;
+      md->start_match_ptr = mstart;
+      RRETURN(MATCH_MATCH);         /* Sets md->mark */
+      }
+
+    /* For capturing groups we have to check the group number back at the start
+    and if necessary complete handling an extraction by setting the offsets and
+    bumping the high water mark. Whole-pattern recursion is coded as a recurse
+    into group 0, so it won't be picked up here. Instead, we catch it when the
+    OP_END is reached. Other recursion is handled here. We just have to record
+    the current subject position and start match pointer and give a MATCH
+    return. */
+
+    if (*prev == OP_CBRA || *prev == OP_SCBRA ||
+        *prev == OP_CBRAPOS || *prev == OP_SCBRAPOS)
+      {
+      number = GET2(prev, 1+LINK_SIZE);
+      offset = number << 1;
+
+#ifdef PCRE_DEBUG
+      printf("end bracket %d", number);
+      printf("\n");
+#endif
+
+      /* Handle a recursively called group. */
+
+      if (md->recursive != NULL && md->recursive->group_num == number)
+        {
+        md->end_match_ptr = eptr;
+        md->start_match_ptr = mstart;
+        RRETURN(MATCH_MATCH);
+        }
+
+      /* Deal with capturing */
+
+      md->capture_last = number;
+      if (offset >= md->offset_max) md->offset_overflow = TRUE; else
+        {
+        /* If offset is greater than offset_top, it means that we are
+        "skipping" a capturing group, and that group's offsets must be marked
+        unset. In earlier versions of PCRE, all the offsets were unset at the
+        start of matching, but this doesn't work because atomic groups and
+        assertions can cause a value to be set that should later be unset.
+        Example: matching /(?>(a))b|(a)c/ against "ac". This sets group 1 as
+        part of the atomic group, but this is not on the final matching path,
+        so must be unset when 2 is set. (If there is no group 2, there is no
+        problem, because offset_top will then be 2, indicating no capture.) */
+
+        if (offset > offset_top)
+          {
+          register int *iptr = md->offset_vector + offset_top;
+          register int *iend = md->offset_vector + offset;
+          while (iptr < iend) *iptr++ = -1;
+          }
+
+        /* Now make the extraction */
+
+        md->offset_vector[offset] =
+          md->offset_vector[md->offset_end - number];
+        md->offset_vector[offset+1] = (int)(eptr - md->start_subject);
+        if (offset_top <= offset) offset_top = offset + 2;
+        }
+      }
+
+    /* For an ordinary non-repeating ket, just continue at this level. This
+    also happens for a repeating ket if no characters were matched in the
+    group. This is the forcible breaking of infinite loops as implemented in
+    Perl 5.005. For a non-repeating atomic group that includes captures,
+    establish a backup point by processing the rest of the pattern at a lower
+    level. If this results in a NOMATCH return, pass MATCH_ONCE back to the
+    original OP_ONCE level, thereby bypassing intermediate backup points, but
+    resetting any captures that happened along the way. */
+
+    if (*ecode == OP_KET || eptr == saved_eptr)
+      {
+      if (*prev == OP_ONCE)
+        {
+        RMATCH(eptr, ecode + 1 + LINK_SIZE, offset_top, md, eptrb, RM12);
+        if (rrc != MATCH_NOMATCH) RRETURN(rrc);
+        md->once_target = prev;  /* Level at which to change to MATCH_NOMATCH */
+        RRETURN(MATCH_ONCE);
+        }
+      ecode += 1 + LINK_SIZE;    /* Carry on at this level */
+      break;
+      }
+
+    /* OP_KETRPOS is a possessive repeating ket. Remember the current position,
+    and return the MATCH_KETRPOS. This makes it possible to do the repeats one
+    at a time from the outer level, thus saving stack. */
+
+    if (*ecode == OP_KETRPOS)
+      {
+      md->end_match_ptr = eptr;
+      md->end_offset_top = offset_top;
+      RRETURN(MATCH_KETRPOS);
+      }
+
+    /* The normal repeating kets try the rest of the pattern or restart from
+    the preceding bracket, in the appropriate order. In the second case, we can
+    use tail recursion to avoid using another stack frame, unless we have an
+    an atomic group or an unlimited repeat of a group that can match an empty
+    string. */
+
+    if (*ecode == OP_KETRMIN)
+      {
+      RMATCH(eptr, ecode + 1 + LINK_SIZE, offset_top, md, eptrb, RM7);
+      if (rrc != MATCH_NOMATCH) RRETURN(rrc);
+      if (*prev == OP_ONCE)
+        {
+        RMATCH(eptr, prev, offset_top, md, eptrb, RM8);
+        if (rrc != MATCH_NOMATCH) RRETURN(rrc);
+        md->once_target = prev;  /* Level at which to change to MATCH_NOMATCH */
+        RRETURN(MATCH_ONCE);
+        }
+      if (*prev >= OP_SBRA)    /* Could match an empty string */
+        {
+        RMATCH(eptr, prev, offset_top, md, eptrb, RM50);
+        RRETURN(rrc);
+        }
+      ecode = prev;
+      goto TAIL_RECURSE;
+      }
+    else  /* OP_KETRMAX */
+      {
+      RMATCH(eptr, prev, offset_top, md, eptrb, RM13);
+      if (rrc == MATCH_ONCE && md->once_target == prev) rrc = MATCH_NOMATCH;
+      if (rrc != MATCH_NOMATCH) RRETURN(rrc);
+      if (*prev == OP_ONCE)
+        {
+        RMATCH(eptr, ecode + 1 + LINK_SIZE, offset_top, md, eptrb, RM9);
+        if (rrc != MATCH_NOMATCH) RRETURN(rrc);
+        md->once_target = prev;
+        RRETURN(MATCH_ONCE);
+        }
+      ecode += 1 + LINK_SIZE;
+      goto TAIL_RECURSE;
+      }
+    /* Control never gets here */
+
+    /* Not multiline mode: start of subject assertion, unless notbol. */
+
+    case OP_CIRC:
+    if (md->notbol && eptr == md->start_subject) RRETURN(MATCH_NOMATCH);
+
+    /* Start of subject assertion */
+
+    case OP_SOD:
+    if (eptr != md->start_subject) RRETURN(MATCH_NOMATCH);
+    ecode++;
+    break;
+
+    /* Multiline mode: start of subject unless notbol, or after any newline. */
+
+    case OP_CIRCM:
+    if (md->notbol && eptr == md->start_subject) RRETURN(MATCH_NOMATCH);
+    if (eptr != md->start_subject &&
+        (eptr == md->end_subject || !WAS_NEWLINE(eptr)))
+      RRETURN(MATCH_NOMATCH);
+    ecode++;
+    break;
+
+    /* Start of match assertion */
+
+    case OP_SOM:
+    if (eptr != md->start_subject + md->start_offset) RRETURN(MATCH_NOMATCH);
+    ecode++;
+    break;
+
+    /* Reset the start of match point */
+
+    case OP_SET_SOM:
+    mstart = eptr;
+    ecode++;
+    break;
+
+    /* Multiline mode: assert before any newline, or before end of subject
+    unless noteol is set. */
+
+    case OP_DOLLM:
+    if (eptr < md->end_subject)
+      {
+      if (!IS_NEWLINE(eptr))
+        {
+        if (md->partial != 0 &&
+            eptr + 1 >= md->end_subject &&
+            NLBLOCK->nltype == NLTYPE_FIXED &&
+            NLBLOCK->nllen == 2 &&
+            *eptr == NLBLOCK->nl[0])
+          {
+          md->hitend = TRUE;
+          if (md->partial > 1) RRETURN(PCRE_ERROR_PARTIAL);
+          }
+        RRETURN(MATCH_NOMATCH);
+        }
+      }
+    else
+      {
+      if (md->noteol) RRETURN(MATCH_NOMATCH);
+      SCHECK_PARTIAL();
+      }
+    ecode++;
+    break;
+
+    /* Not multiline mode: assert before a terminating newline or before end of
+    subject unless noteol is set. */
+
+    case OP_DOLL:
+    if (md->noteol) RRETURN(MATCH_NOMATCH);
+    if (!md->endonly) goto ASSERT_NL_OR_EOS;
+
+    /* ... else fall through for endonly */
+
+    /* End of subject assertion (\z) */
+
+    case OP_EOD:
+    if (eptr < md->end_subject) RRETURN(MATCH_NOMATCH);
+    SCHECK_PARTIAL();
+    ecode++;
+    break;
+
+    /* End of subject or ending \n assertion (\Z) */
+
+    case OP_EODN:
+    ASSERT_NL_OR_EOS:
+    if (eptr < md->end_subject &&
+        (!IS_NEWLINE(eptr) || eptr != md->end_subject - md->nllen))
+      {
+      if (md->partial != 0 &&
+          eptr + 1 >= md->end_subject &&
+          NLBLOCK->nltype == NLTYPE_FIXED &&
+          NLBLOCK->nllen == 2 &&
+          *eptr == NLBLOCK->nl[0])
+        {
+        md->hitend = TRUE;
+        if (md->partial > 1) RRETURN(PCRE_ERROR_PARTIAL);
+        }
+      RRETURN(MATCH_NOMATCH);
+      }
+
+    /* Either at end of string or \n before end. */
+
+    SCHECK_PARTIAL();
+    ecode++;
+    break;
+
+    /* Word boundary assertions */
+
+    case OP_NOT_WORD_BOUNDARY:
+    case OP_WORD_BOUNDARY:
+      {
+
+      /* Find out if the previous and current characters are "word" characters.
+      It takes a bit more work in UTF-8 mode. Characters > 255 are assumed to
+      be "non-word" characters. Remember the earliest consulted character for
+      partial matching. */
+
+#ifdef SUPPORT_UTF
+      if (utf)
+        {
+        /* Get status of previous character */
+
+        if (eptr == md->start_subject) prev_is_word = FALSE; else
+          {
+          PCRE_PUCHAR lastptr = eptr - 1;
+          BACKCHAR(lastptr);
+          if (lastptr < md->start_used_ptr) md->start_used_ptr = lastptr;
+          GETCHAR(c, lastptr);
+#ifdef SUPPORT_UCP
+          if (md->use_ucp)
+            {
+            if (c == '_') prev_is_word = TRUE; else
+              {
+              int cat = UCD_CATEGORY(c);
+              prev_is_word = (cat == ucp_L || cat == ucp_N);
+              }
+            }
+          else
+#endif
+          prev_is_word = c < 256 && (md->ctypes[c] & ctype_word) != 0;
+          }
+
+        /* Get status of next character */
+
+        if (eptr >= md->end_subject)
+          {
+          SCHECK_PARTIAL();
+          cur_is_word = FALSE;
+          }
+        else
+          {
+          GETCHAR(c, eptr);
+#ifdef SUPPORT_UCP
+          if (md->use_ucp)
+            {
+            if (c == '_') cur_is_word = TRUE; else
+              {
+              int cat = UCD_CATEGORY(c);
+              cur_is_word = (cat == ucp_L || cat == ucp_N);
+              }
+            }
+          else
+#endif
+          cur_is_word = c < 256 && (md->ctypes[c] & ctype_word) != 0;
+          }
+        }
+      else
+#endif
+
+      /* Not in UTF-8 mode, but we may still have PCRE_UCP set, and for
+      consistency with the behaviour of \w we do use it in this case. */
+
+        {
+        /* Get status of previous character */
+
+        if (eptr == md->start_subject) prev_is_word = FALSE; else
+          {
+          if (eptr <= md->start_used_ptr) md->start_used_ptr = eptr - 1;
+#ifdef SUPPORT_UCP
+          if (md->use_ucp)
+            {
+            c = eptr[-1];
+            if (c == '_') prev_is_word = TRUE; else
+              {
+              int cat = UCD_CATEGORY(c);
+              prev_is_word = (cat == ucp_L || cat == ucp_N);
+              }
+            }
+          else
+#endif
+          prev_is_word = MAX_255(eptr[-1])
+            && ((md->ctypes[eptr[-1]] & ctype_word) != 0);
+          }
+
+        /* Get status of next character */
+
+        if (eptr >= md->end_subject)
+          {
+          SCHECK_PARTIAL();
+          cur_is_word = FALSE;
+          }
+        else
+#ifdef SUPPORT_UCP
+        if (md->use_ucp)
+          {
+          c = *eptr;
+          if (c == '_') cur_is_word = TRUE; else
+            {
+            int cat = UCD_CATEGORY(c);
+            cur_is_word = (cat == ucp_L || cat == ucp_N);
+            }
+          }
+        else
+#endif
+        cur_is_word = MAX_255(*eptr)
+          && ((md->ctypes[*eptr] & ctype_word) != 0);
+        }
+
+      /* Now see if the situation is what we want */
+
+      if ((*ecode++ == OP_WORD_BOUNDARY)?
+           cur_is_word == prev_is_word : cur_is_word != prev_is_word)
+        RRETURN(MATCH_NOMATCH);
+      }
+    break;
+
+    /* Match any single character type except newline; have to take care with
+    CRLF newlines and partial matching. */
+
+    case OP_ANY:
+    if (IS_NEWLINE(eptr)) RRETURN(MATCH_NOMATCH);
+    if (md->partial != 0 &&
+        eptr + 1 >= md->end_subject &&
+        NLBLOCK->nltype == NLTYPE_FIXED &&
+        NLBLOCK->nllen == 2 &&
+        *eptr == NLBLOCK->nl[0])
+      {
+      md->hitend = TRUE;
+      if (md->partial > 1) RRETURN(PCRE_ERROR_PARTIAL);
+      }
+
+    /* Fall through */
+
+    /* Match any single character whatsoever. */
+
+    case OP_ALLANY:
+    if (eptr >= md->end_subject)   /* DO NOT merge the eptr++ here; it must */
+      {                            /* not be updated before SCHECK_PARTIAL. */
+      SCHECK_PARTIAL();
+      RRETURN(MATCH_NOMATCH);
+      }
+    eptr++;
+#ifdef SUPPORT_UTF
+    if (utf) ACROSSCHAR(eptr < md->end_subject, *eptr, eptr++);
+#endif
+    ecode++;
+    break;
+
+    /* Match a single byte, even in UTF-8 mode. This opcode really does match
+    any byte, even newline, independent of the setting of PCRE_DOTALL. */
+
+    case OP_ANYBYTE:
+    if (eptr >= md->end_subject)   /* DO NOT merge the eptr++ here; it must */
+      {                            /* not be updated before SCHECK_PARTIAL. */
+      SCHECK_PARTIAL();
+      RRETURN(MATCH_NOMATCH);
+      }
+    eptr++;
+    ecode++;
+    break;
+
+    case OP_NOT_DIGIT:
+    if (eptr >= md->end_subject)
+      {
+      SCHECK_PARTIAL();
+      RRETURN(MATCH_NOMATCH);
+      }
+    GETCHARINCTEST(c, eptr);
+    if (
+#if defined SUPPORT_UTF || !(defined COMPILE_PCRE8)
+       c < 256 &&
+#endif
+       (md->ctypes[c] & ctype_digit) != 0
+       )
+      RRETURN(MATCH_NOMATCH);
+    ecode++;
+    break;
+
+    case OP_DIGIT:
+    if (eptr >= md->end_subject)
+      {
+      SCHECK_PARTIAL();
+      RRETURN(MATCH_NOMATCH);
+      }
+    GETCHARINCTEST(c, eptr);
+    if (
+#if defined SUPPORT_UTF || !(defined COMPILE_PCRE8)
+       c > 255 ||
+#endif
+       (md->ctypes[c] & ctype_digit) == 0
+       )
+      RRETURN(MATCH_NOMATCH);
+    ecode++;
+    break;
+
+    case OP_NOT_WHITESPACE:
+    if (eptr >= md->end_subject)
+      {
+      SCHECK_PARTIAL();
+      RRETURN(MATCH_NOMATCH);
+      }
+    GETCHARINCTEST(c, eptr);
+    if (
+#if defined SUPPORT_UTF || !(defined COMPILE_PCRE8)
+       c < 256 &&
+#endif
+       (md->ctypes[c] & ctype_space) != 0
+       )
+      RRETURN(MATCH_NOMATCH);
+    ecode++;
+    break;
+
+    case OP_WHITESPACE:
+    if (eptr >= md->end_subject)
+      {
+      SCHECK_PARTIAL();
+      RRETURN(MATCH_NOMATCH);
+      }
+    GETCHARINCTEST(c, eptr);
+    if (
+#if defined SUPPORT_UTF || !(defined COMPILE_PCRE8)
+       c > 255 ||
+#endif
+       (md->ctypes[c] & ctype_space) == 0
+       )
+      RRETURN(MATCH_NOMATCH);
+    ecode++;
+    break;
+
+    case OP_NOT_WORDCHAR:
+    if (eptr >= md->end_subject)
+      {
+      SCHECK_PARTIAL();
+      RRETURN(MATCH_NOMATCH);
+      }
+    GETCHARINCTEST(c, eptr);
+    if (
+#if defined SUPPORT_UTF || !(defined COMPILE_PCRE8)
+       c < 256 &&
+#endif
+       (md->ctypes[c] & ctype_word) != 0
+       )
+      RRETURN(MATCH_NOMATCH);
+    ecode++;
+    break;
+
+    case OP_WORDCHAR:
+    if (eptr >= md->end_subject)
+      {
+      SCHECK_PARTIAL();
+      RRETURN(MATCH_NOMATCH);
+      }
+    GETCHARINCTEST(c, eptr);
+    if (
+#if defined SUPPORT_UTF || !(defined COMPILE_PCRE8)
+       c > 255 ||
+#endif
+       (md->ctypes[c] & ctype_word) == 0
+       )
+      RRETURN(MATCH_NOMATCH);
+    ecode++;
+    break;
+
+    case OP_ANYNL:
+    if (eptr >= md->end_subject)
+      {
+      SCHECK_PARTIAL();
+      RRETURN(MATCH_NOMATCH);
+      }
+    GETCHARINCTEST(c, eptr);
+    switch(c)
+      {
+      default: RRETURN(MATCH_NOMATCH);
+
+      case 0x000d:
+      if (eptr >= md->end_subject)
+        {
+        SCHECK_PARTIAL();
+        }
+      else if (*eptr == 0x0a) eptr++;
+      break;
+
+      case 0x000a:
+      break;
+
+      case 0x000b:
+      case 0x000c:
+      case 0x0085:
+      case 0x2028:
+      case 0x2029:
+      if (md->bsr_anycrlf) RRETURN(MATCH_NOMATCH);
+      break;
+      }
+    ecode++;
+    break;
+
+    case OP_NOT_HSPACE:
+    if (eptr >= md->end_subject)
+      {
+      SCHECK_PARTIAL();
+      RRETURN(MATCH_NOMATCH);
+      }
+    GETCHARINCTEST(c, eptr);
+    switch(c)
+      {
+      default: break;
+      case 0x09:      /* HT */
+      case 0x20:      /* SPACE */
+      case 0xa0:      /* NBSP */
+      case 0x1680:    /* OGHAM SPACE MARK */
+      case 0x180e:    /* MONGOLIAN VOWEL SEPARATOR */
+      case 0x2000:    /* EN QUAD */
+      case 0x2001:    /* EM QUAD */
+      case 0x2002:    /* EN SPACE */
+      case 0x2003:    /* EM SPACE */
+      case 0x2004:    /* THREE-PER-EM SPACE */
+      case 0x2005:    /* FOUR-PER-EM SPACE */
+      case 0x2006:    /* SIX-PER-EM SPACE */
+      case 0x2007:    /* FIGURE SPACE */
+      case 0x2008:    /* PUNCTUATION SPACE */
+      case 0x2009:    /* THIN SPACE */
+      case 0x200A:    /* HAIR SPACE */
+      case 0x202f:    /* NARROW NO-BREAK SPACE */
+      case 0x205f:    /* MEDIUM MATHEMATICAL SPACE */
+      case 0x3000:    /* IDEOGRAPHIC SPACE */
+      RRETURN(MATCH_NOMATCH);
+      }
+    ecode++;
+    break;
+
+    case OP_HSPACE:
+    if (eptr >= md->end_subject)
+      {
+      SCHECK_PARTIAL();
+      RRETURN(MATCH_NOMATCH);
+      }
+    GETCHARINCTEST(c, eptr);
+    switch(c)
+      {
+      default: RRETURN(MATCH_NOMATCH);
+      case 0x09:      /* HT */
+      case 0x20:      /* SPACE */
+      case 0xa0:      /* NBSP */
+      case 0x1680:    /* OGHAM SPACE MARK */
+      case 0x180e:    /* MONGOLIAN VOWEL SEPARATOR */
+      case 0x2000:    /* EN QUAD */
+      case 0x2001:    /* EM QUAD */
+      case 0x2002:    /* EN SPACE */
+      case 0x2003:    /* EM SPACE */
+      case 0x2004:    /* THREE-PER-EM SPACE */
+      case 0x2005:    /* FOUR-PER-EM SPACE */
+      case 0x2006:    /* SIX-PER-EM SPACE */
+      case 0x2007:    /* FIGURE SPACE */
+      case 0x2008:    /* PUNCTUATION SPACE */
+      case 0x2009:    /* THIN SPACE */
+      case 0x200A:    /* HAIR SPACE */
+      case 0x202f:    /* NARROW NO-BREAK SPACE */
+      case 0x205f:    /* MEDIUM MATHEMATICAL SPACE */
+      case 0x3000:    /* IDEOGRAPHIC SPACE */
+      break;
+      }
+    ecode++;
+    break;
+
+    case OP_NOT_VSPACE:
+    if (eptr >= md->end_subject)
+      {
+      SCHECK_PARTIAL();
+      RRETURN(MATCH_NOMATCH);
+      }
+    GETCHARINCTEST(c, eptr);
+    switch(c)
+      {
+      default: break;
+      case 0x0a:      /* LF */
+      case 0x0b:      /* VT */
+      case 0x0c:      /* FF */
+      case 0x0d:      /* CR */
+      case 0x85:      /* NEL */
+      case 0x2028:    /* LINE SEPARATOR */
+      case 0x2029:    /* PARAGRAPH SEPARATOR */
+      RRETURN(MATCH_NOMATCH);
+      }
+    ecode++;
+    break;
+
+    case OP_VSPACE:
+    if (eptr >= md->end_subject)
+      {
+      SCHECK_PARTIAL();
+      RRETURN(MATCH_NOMATCH);
+      }
+    GETCHARINCTEST(c, eptr);
+    switch(c)
+      {
+      default: RRETURN(MATCH_NOMATCH);
+      case 0x0a:      /* LF */
+      case 0x0b:      /* VT */
+      case 0x0c:      /* FF */
+      case 0x0d:      /* CR */
+      case 0x85:      /* NEL */
+      case 0x2028:    /* LINE SEPARATOR */
+      case 0x2029:    /* PARAGRAPH SEPARATOR */
+      break;
+      }
+    ecode++;
+    break;
+
+#ifdef SUPPORT_UCP
+    /* Check the next character by Unicode property. We will get here only
+    if the support is in the binary; otherwise a compile-time error occurs. */
+
+    case OP_PROP:
+    case OP_NOTPROP:
+    if (eptr >= md->end_subject)
+      {
+      SCHECK_PARTIAL();
+      RRETURN(MATCH_NOMATCH);
+      }
+    GETCHARINCTEST(c, eptr);
+      {
+      const ucd_record *prop = GET_UCD(c);
+
+      switch(ecode[1])
+        {
+        case PT_ANY:
+        if (op == OP_NOTPROP) RRETURN(MATCH_NOMATCH);
+        break;
+
+        case PT_LAMP:
+        if ((prop->chartype == ucp_Lu ||
+             prop->chartype == ucp_Ll ||
+             prop->chartype == ucp_Lt) == (op == OP_NOTPROP))
+          RRETURN(MATCH_NOMATCH);
+        break;
+
+        case PT_GC:
+        if ((ecode[2] != PRIV(ucp_gentype)[prop->chartype]) == (op == OP_PROP))
+          RRETURN(MATCH_NOMATCH);
+        break;
+
+        case PT_PC:
+        if ((ecode[2] != prop->chartype) == (op == OP_PROP))
+          RRETURN(MATCH_NOMATCH);
+        break;
+
+        case PT_SC:
+        if ((ecode[2] != prop->script) == (op == OP_PROP))
+          RRETURN(MATCH_NOMATCH);
+        break;
+
+        /* These are specials */
+
+        case PT_ALNUM:
+        if ((PRIV(ucp_gentype)[prop->chartype] == ucp_L ||
+             PRIV(ucp_gentype)[prop->chartype] == ucp_N) == (op == OP_NOTPROP))
+          RRETURN(MATCH_NOMATCH);
+        break;
+
+        case PT_SPACE:    /* Perl space */
+        if ((PRIV(ucp_gentype)[prop->chartype] == ucp_Z ||
+             c == CHAR_HT || c == CHAR_NL || c == CHAR_FF || c == CHAR_CR)
+               == (op == OP_NOTPROP))
+          RRETURN(MATCH_NOMATCH);
+        break;
+
+        case PT_PXSPACE:  /* POSIX space */
+        if ((PRIV(ucp_gentype)[prop->chartype] == ucp_Z ||
+             c == CHAR_HT || c == CHAR_NL || c == CHAR_VT ||
+             c == CHAR_FF || c == CHAR_CR)
+               == (op == OP_NOTPROP))
+          RRETURN(MATCH_NOMATCH);
+        break;
+
+        case PT_WORD:
+        if ((PRIV(ucp_gentype)[prop->chartype] == ucp_L ||
+             PRIV(ucp_gentype)[prop->chartype] == ucp_N ||
+             c == CHAR_UNDERSCORE) == (op == OP_NOTPROP))
+          RRETURN(MATCH_NOMATCH);
+        break;
+
+        /* This should never occur */
+
+        default:
+        RRETURN(PCRE_ERROR_INTERNAL);
+        }
+
+      ecode += 3;
+      }
+    break;
+
+    /* Match an extended Unicode sequence. We will get here only if the support
+    is in the binary; otherwise a compile-time error occurs. */
+
+    case OP_EXTUNI:
+    if (eptr >= md->end_subject)
+      {
+      SCHECK_PARTIAL();
+      RRETURN(MATCH_NOMATCH);
+      }
+    GETCHARINCTEST(c, eptr);
+    if (UCD_CATEGORY(c) == ucp_M) RRETURN(MATCH_NOMATCH);
+    while (eptr < md->end_subject)
+      {
+      int len = 1;
+      if (!utf) c = *eptr; else { GETCHARLEN(c, eptr, len); }
+      if (UCD_CATEGORY(c) != ucp_M) break;
+      eptr += len;
+      }
+    CHECK_PARTIAL();
+    ecode++;
+    break;
+#endif
+
+
+    /* Match a back reference, possibly repeatedly. Look past the end of the
+    item to see if there is repeat information following. The code is similar
+    to that for character classes, but repeated for efficiency. Then obey
+    similar code to character type repeats - written out again for speed.
+    However, if the referenced string is the empty string, always treat
+    it as matched, any number of times (otherwise there could be infinite
+    loops). */
+
+    case OP_REF:
+    case OP_REFI:
+    caseless = op == OP_REFI;
+    offset = GET2(ecode, 1) << 1;               /* Doubled ref number */
+    ecode += 1 + IMM2_SIZE;
+
+    /* If the reference is unset, there are two possibilities:
+
+    (a) In the default, Perl-compatible state, set the length negative;
+    this ensures that every attempt at a match fails. We can't just fail
+    here, because of the possibility of quantifiers with zero minima.
+
+    (b) If the JavaScript compatibility flag is set, set the length to zero
+    so that the back reference matches an empty string.
+
+    Otherwise, set the length to the length of what was matched by the
+    referenced subpattern. */
+
+    if (offset >= offset_top || md->offset_vector[offset] < 0)
+      length = (md->jscript_compat)? 0 : -1;
+    else
+      length = md->offset_vector[offset+1] - md->offset_vector[offset];
+
+    /* Set up for repetition, or handle the non-repeated case */
+
+    switch (*ecode)
+      {
+      case OP_CRSTAR:
+      case OP_CRMINSTAR:
+      case OP_CRPLUS:
+      case OP_CRMINPLUS:
+      case OP_CRQUERY:
+      case OP_CRMINQUERY:
+      c = *ecode++ - OP_CRSTAR;
+      minimize = (c & 1) != 0;
+      min = rep_min[c];                 /* Pick up values from tables; */
+      max = rep_max[c];                 /* zero for max => infinity */
+      if (max == 0) max = INT_MAX;
+      break;
+
+      case OP_CRRANGE:
+      case OP_CRMINRANGE:
+      minimize = (*ecode == OP_CRMINRANGE);
+      min = GET2(ecode, 1);
+      max = GET2(ecode, 1 + IMM2_SIZE);
+      if (max == 0) max = INT_MAX;
+      ecode += 1 + 2 * IMM2_SIZE;
+      break;
+
+      default:               /* No repeat follows */
+      if ((length = match_ref(offset, eptr, length, md, caseless)) < 0)
+        {
+        if (length == -2) eptr = md->end_subject;   /* Partial match */
+        CHECK_PARTIAL();
+        RRETURN(MATCH_NOMATCH);
+        }
+      eptr += length;
+      continue;              /* With the main loop */
+      }
+
+    /* Handle repeated back references. If the length of the reference is
+    zero, just continue with the main loop. If the length is negative, it
+    means the reference is unset in non-Java-compatible mode. If the minimum is
+    zero, we can continue at the same level without recursion. For any other
+    minimum, carrying on will result in NOMATCH. */
+
+    if (length == 0) continue;
+    if (length < 0 && min == 0) continue;
+
+    /* First, ensure the minimum number of matches are present. We get back
+    the length of the reference string explicitly rather than passing the
+    address of eptr, so that eptr can be a register variable. */
+
+    for (i = 1; i <= min; i++)
+      {
+      int slength;
+      if ((slength = match_ref(offset, eptr, length, md, caseless)) < 0)
+        {
+        if (slength == -2) eptr = md->end_subject;   /* Partial match */
+        CHECK_PARTIAL();
+        RRETURN(MATCH_NOMATCH);
+        }
+      eptr += slength;
+      }
+
+    /* If min = max, continue at the same level without recursion.
+    They are not both allowed to be zero. */
+
+    if (min == max) continue;
+
+    /* If minimizing, keep trying and advancing the pointer */
+
+    if (minimize)
+      {
+      for (fi = min;; fi++)
+        {
+        int slength;
+        RMATCH(eptr, ecode, offset_top, md, eptrb, RM14);
+        if (rrc != MATCH_NOMATCH) RRETURN(rrc);
+        if (fi >= max) RRETURN(MATCH_NOMATCH);
+        if ((slength = match_ref(offset, eptr, length, md, caseless)) < 0)
+          {
+          if (slength == -2) eptr = md->end_subject;   /* Partial match */
+          CHECK_PARTIAL();
+          RRETURN(MATCH_NOMATCH);
+          }
+        eptr += slength;
+        }
+      /* Control never gets here */
+      }
+
+    /* If maximizing, find the longest string and work backwards */
+
+    else
+      {
+      pp = eptr;
+      for (i = min; i < max; i++)
+        {
+        int slength;
+        if ((slength = match_ref(offset, eptr, length, md, caseless)) < 0)
+          {
+          /* Can't use CHECK_PARTIAL because we don't want to update eptr in
+          the soft partial matching case. */
+
+          if (slength == -2 && md->partial != 0 &&
+              md->end_subject > md->start_used_ptr)
+            {
+            md->hitend = TRUE;
+            if (md->partial > 1) RRETURN(PCRE_ERROR_PARTIAL);
+            }
+          break;
+          }
+        eptr += slength;
+        }
+
+      while (eptr >= pp)
+        {
+        RMATCH(eptr, ecode, offset_top, md, eptrb, RM15);
+        if (rrc != MATCH_NOMATCH) RRETURN(rrc);
+        eptr -= length;
+        }
+      RRETURN(MATCH_NOMATCH);
+      }
+    /* Control never gets here */
+
+    /* Match a bit-mapped character class, possibly repeatedly. This op code is
+    used when all the characters in the class have values in the range 0-255,
+    and either the matching is caseful, or the characters are in the range
+    0-127 when UTF-8 processing is enabled. The only difference between
+    OP_CLASS and OP_NCLASS occurs when a data character outside the range is
+    encountered.
+
+    First, look past the end of the item to see if there is repeat information
+    following. Then obey similar code to character type repeats - written out
+    again for speed. */
+
+    case OP_NCLASS:
+    case OP_CLASS:
+      {
+      /* The data variable is saved across frames, so the byte map needs to
+      be stored there. */
+#define BYTE_MAP ((pcre_uint8 *)data)
+      data = ecode + 1;                /* Save for matching */
+      ecode += 1 + (32 / sizeof(pcre_uchar)); /* Advance past the item */
+
+      switch (*ecode)
+        {
+        case OP_CRSTAR:
+        case OP_CRMINSTAR:
+        case OP_CRPLUS:
+        case OP_CRMINPLUS:
+        case OP_CRQUERY:
+        case OP_CRMINQUERY:
+        c = *ecode++ - OP_CRSTAR;
+        minimize = (c & 1) != 0;
+        min = rep_min[c];                 /* Pick up values from tables; */
+        max = rep_max[c];                 /* zero for max => infinity */
+        if (max == 0) max = INT_MAX;
+        break;
+
+        case OP_CRRANGE:
+        case OP_CRMINRANGE:
+        minimize = (*ecode == OP_CRMINRANGE);
+        min = GET2(ecode, 1);
+        max = GET2(ecode, 1 + IMM2_SIZE);
+        if (max == 0) max = INT_MAX;
+        ecode += 1 + 2 * IMM2_SIZE;
+        break;
+
+        default:               /* No repeat follows */
+        min = max = 1;
+        break;
+        }
+
+      /* First, ensure the minimum number of matches are present. */
+
+#ifdef SUPPORT_UTF
+      if (utf)
+        {
+        for (i = 1; i <= min; i++)
+          {
+          if (eptr >= md->end_subject)
+            {
+            SCHECK_PARTIAL();
+            RRETURN(MATCH_NOMATCH);
+            }
+          GETCHARINC(c, eptr);
+          if (c > 255)
+            {
+            if (op == OP_CLASS) RRETURN(MATCH_NOMATCH);
+            }
+          else
+            if ((BYTE_MAP[c/8] & (1 << (c&7))) == 0) RRETURN(MATCH_NOMATCH);
+          }
+        }
+      else
+#endif
+      /* Not UTF mode */
+        {
+        for (i = 1; i <= min; i++)
+          {
+          if (eptr >= md->end_subject)
+            {
+            SCHECK_PARTIAL();
+            RRETURN(MATCH_NOMATCH);
+            }
+          c = *eptr++;
+#ifndef COMPILE_PCRE8
+          if (c > 255)
+            {
+            if (op == OP_CLASS) RRETURN(MATCH_NOMATCH);
+            }
+          else
+#endif
+            if ((BYTE_MAP[c/8] & (1 << (c&7))) == 0) RRETURN(MATCH_NOMATCH);
+          }
+        }
+
+      /* If max == min we can continue with the main loop without the
+      need to recurse. */
+
+      if (min == max) continue;
+
+      /* If minimizing, keep testing the rest of the expression and advancing
+      the pointer while it matches the class. */
+
+      if (minimize)
+        {
+#ifdef SUPPORT_UTF
+        if (utf)
+          {
+          for (fi = min;; fi++)
+            {
+            RMATCH(eptr, ecode, offset_top, md, eptrb, RM16);
+            if (rrc != MATCH_NOMATCH) RRETURN(rrc);
+            if (fi >= max) RRETURN(MATCH_NOMATCH);
+            if (eptr >= md->end_subject)
+              {
+              SCHECK_PARTIAL();
+              RRETURN(MATCH_NOMATCH);
+              }
+            GETCHARINC(c, eptr);
+            if (c > 255)
+              {
+              if (op == OP_CLASS) RRETURN(MATCH_NOMATCH);
+              }
+            else
+              if ((BYTE_MAP[c/8] & (1 << (c&7))) == 0) RRETURN(MATCH_NOMATCH);
+            }
+          }
+        else
+#endif
+        /* Not UTF mode */
+          {
+          for (fi = min;; fi++)
+            {
+            RMATCH(eptr, ecode, offset_top, md, eptrb, RM17);
+            if (rrc != MATCH_NOMATCH) RRETURN(rrc);
+            if (fi >= max) RRETURN(MATCH_NOMATCH);
+            if (eptr >= md->end_subject)
+              {
+              SCHECK_PARTIAL();
+              RRETURN(MATCH_NOMATCH);
+              }
+            c = *eptr++;
+#ifndef COMPILE_PCRE8
+            if (c > 255)
+              {
+              if (op == OP_CLASS) RRETURN(MATCH_NOMATCH);
+              }
+            else
+#endif
+              if ((BYTE_MAP[c/8] & (1 << (c&7))) == 0) RRETURN(MATCH_NOMATCH);
+            }
+          }
+        /* Control never gets here */
+        }
+
+      /* If maximizing, find the longest possible run, then work backwards. */
+
+      else
+        {
+        pp = eptr;
+
+#ifdef SUPPORT_UTF
+        if (utf)
+          {
+          for (i = min; i < max; i++)
+            {
+            int len = 1;
+            if (eptr >= md->end_subject)
+              {
+              SCHECK_PARTIAL();
+              break;
+              }
+            GETCHARLEN(c, eptr, len);
+            if (c > 255)
+              {
+              if (op == OP_CLASS) break;
+              }
+            else
+              if ((BYTE_MAP[c/8] & (1 << (c&7))) == 0) break;
+            eptr += len;
+            }
+          for (;;)
+            {
+            RMATCH(eptr, ecode, offset_top, md, eptrb, RM18);
+            if (rrc != MATCH_NOMATCH) RRETURN(rrc);
+            if (eptr-- == pp) break;        /* Stop if tried at original pos */
+            BACKCHAR(eptr);
+            }
+          }
+        else
+#endif
+          /* Not UTF mode */
+          {
+          for (i = min; i < max; i++)
+            {
+            if (eptr >= md->end_subject)
+              {
+              SCHECK_PARTIAL();
+              break;
+              }
+            c = *eptr;
+#ifndef COMPILE_PCRE8
+            if (c > 255)
+              {
+              if (op == OP_CLASS) break;
+              }
+            else
+#endif
+              if ((BYTE_MAP[c/8] & (1 << (c&7))) == 0) break;
+            eptr++;
+            }
+          while (eptr >= pp)
+            {
+            RMATCH(eptr, ecode, offset_top, md, eptrb, RM19);
+            if (rrc != MATCH_NOMATCH) RRETURN(rrc);
+            eptr--;
+            }
+          }
+
+        RRETURN(MATCH_NOMATCH);
+        }
+#undef BYTE_MAP
+      }
+    /* Control never gets here */
+
+
+    /* Match an extended character class. This opcode is encountered only
+    when UTF-8 mode mode is supported. Nevertheless, we may not be in UTF-8
+    mode, because Unicode properties are supported in non-UTF-8 mode. */
+
+#if defined SUPPORT_UTF || !defined COMPILE_PCRE8
+    case OP_XCLASS:
+      {
+      data = ecode + 1 + LINK_SIZE;                /* Save for matching */
+      ecode += GET(ecode, 1);                      /* Advance past the item */
+
+      switch (*ecode)
+        {
+        case OP_CRSTAR:
+        case OP_CRMINSTAR:
+        case OP_CRPLUS:
+        case OP_CRMINPLUS:
+        case OP_CRQUERY:
+        case OP_CRMINQUERY:
+        c = *ecode++ - OP_CRSTAR;
+        minimize = (c & 1) != 0;
+        min = rep_min[c];                 /* Pick up values from tables; */
+        max = rep_max[c];                 /* zero for max => infinity */
+        if (max == 0) max = INT_MAX;
+        break;
+
+        case OP_CRRANGE:
+        case OP_CRMINRANGE:
+        minimize = (*ecode == OP_CRMINRANGE);
+        min = GET2(ecode, 1);
+        max = GET2(ecode, 1 + IMM2_SIZE);
+        if (max == 0) max = INT_MAX;
+        ecode += 1 + 2 * IMM2_SIZE;
+        break;
+
+        default:               /* No repeat follows */
+        min = max = 1;
+        break;
+        }
+
+      /* First, ensure the minimum number of matches are present. */
+
+      for (i = 1; i <= min; i++)
+        {
+        if (eptr >= md->end_subject)
+          {
+          SCHECK_PARTIAL();
+          RRETURN(MATCH_NOMATCH);
+          }
+        GETCHARINCTEST(c, eptr);
+        if (!PRIV(xclass)(c, data, utf)) RRETURN(MATCH_NOMATCH);
+        }
+
+      /* If max == min we can continue with the main loop without the
+      need to recurse. */
+
+      if (min == max) continue;
+
+      /* If minimizing, keep testing the rest of the expression and advancing
+      the pointer while it matches the class. */
+
+      if (minimize)
+        {
+        for (fi = min;; fi++)
+          {
+          RMATCH(eptr, ecode, offset_top, md, eptrb, RM20);
+          if (rrc != MATCH_NOMATCH) RRETURN(rrc);
+          if (fi >= max) RRETURN(MATCH_NOMATCH);
+          if (eptr >= md->end_subject)
+            {
+            SCHECK_PARTIAL();
+            RRETURN(MATCH_NOMATCH);
+            }
+          GETCHARINCTEST(c, eptr);
+          if (!PRIV(xclass)(c, data, utf)) RRETURN(MATCH_NOMATCH);
+          }
+        /* Control never gets here */
+        }
+
+      /* If maximizing, find the longest possible run, then work backwards. */
+
+      else
+        {
+        pp = eptr;
+        for (i = min; i < max; i++)
+          {
+          int len = 1;
+          if (eptr >= md->end_subject)
+            {
+            SCHECK_PARTIAL();
+            break;
+            }
+#ifdef SUPPORT_UTF
+          GETCHARLENTEST(c, eptr, len);
+#else
+          c = *eptr;
+#endif
+          if (!PRIV(xclass)(c, data, utf)) break;
+          eptr += len;
+          }
+        for(;;)
+          {
+          RMATCH(eptr, ecode, offset_top, md, eptrb, RM21);
+          if (rrc != MATCH_NOMATCH) RRETURN(rrc);
+          if (eptr-- == pp) break;        /* Stop if tried at original pos */
+#ifdef SUPPORT_UTF
+          if (utf) BACKCHAR(eptr);
+#endif
+          }
+        RRETURN(MATCH_NOMATCH);
+        }
+
+      /* Control never gets here */
+      }
+#endif    /* End of XCLASS */
+
+    /* Match a single character, casefully */
+
+    case OP_CHAR:
+#ifdef SUPPORT_UTF
+    if (utf)
+      {
+      length = 1;
+      ecode++;
+      GETCHARLEN(fc, ecode, length);
+      if (length > md->end_subject - eptr)
+        {
+        CHECK_PARTIAL();             /* Not SCHECK_PARTIAL() */
+        RRETURN(MATCH_NOMATCH);
+        }
+      while (length-- > 0) if (*ecode++ != *eptr++) RRETURN(MATCH_NOMATCH);
+      }
+    else
+#endif
+    /* Not UTF mode */
+      {
+      if (md->end_subject - eptr < 1)
+        {
+        SCHECK_PARTIAL();            /* This one can use SCHECK_PARTIAL() */
+        RRETURN(MATCH_NOMATCH);
+        }
+      if (ecode[1] != *eptr++) RRETURN(MATCH_NOMATCH);
+      ecode += 2;
+      }
+    break;
+
+    /* Match a single character, caselessly. If we are at the end of the
+    subject, give up immediately. */
+
+    case OP_CHARI:
+    if (eptr >= md->end_subject)
+      {
+      SCHECK_PARTIAL();
+      RRETURN(MATCH_NOMATCH);
+      }
+
+#ifdef SUPPORT_UTF
+    if (utf)
+      {
+      length = 1;
+      ecode++;
+      GETCHARLEN(fc, ecode, length);
+
+      /* If the pattern character's value is < 128, we have only one byte, and
+      we know that its other case must also be one byte long, so we can use the
+      fast lookup table. We know that there is at least one byte left in the
+      subject. */
+
+      if (fc < 128)
+        {
+        if (md->lcc[fc]
+            != TABLE_GET(*eptr, md->lcc, *eptr)) RRETURN(MATCH_NOMATCH);
+        ecode++;
+        eptr++;
+        }
+
+      /* Otherwise we must pick up the subject character. Note that we cannot
+      use the value of "length" to check for sufficient bytes left, because the
+      other case of the character may have more or fewer bytes.  */
+
+      else
+        {
+        unsigned int dc;
+        GETCHARINC(dc, eptr);
+        ecode += length;
+
+        /* If we have Unicode property support, we can use it to test the other
+        case of the character, if there is one. */
+
+        if (fc != dc)
+          {
+#ifdef SUPPORT_UCP
+          if (dc != UCD_OTHERCASE(fc))
+#endif
+            RRETURN(MATCH_NOMATCH);
+          }
+        }
+      }
+    else
+#endif   /* SUPPORT_UTF */
+
+    /* Not UTF mode */
+      {
+      if (TABLE_GET(ecode[1], md->lcc, ecode[1])
+          != TABLE_GET(*eptr, md->lcc, *eptr)) RRETURN(MATCH_NOMATCH);
+      eptr++;
+      ecode += 2;
+      }
+    break;
+
+    /* Match a single character repeatedly. */
+
+    case OP_EXACT:
+    case OP_EXACTI:
+    min = max = GET2(ecode, 1);
+    ecode += 1 + IMM2_SIZE;
+    goto REPEATCHAR;
+
+    case OP_POSUPTO:
+    case OP_POSUPTOI:
+    possessive = TRUE;
+    /* Fall through */
+
+    case OP_UPTO:
+    case OP_UPTOI:
+    case OP_MINUPTO:
+    case OP_MINUPTOI:
+    min = 0;
+    max = GET2(ecode, 1);
+    minimize = *ecode == OP_MINUPTO || *ecode == OP_MINUPTOI;
+    ecode += 1 + IMM2_SIZE;
+    goto REPEATCHAR;
+
+    case OP_POSSTAR:
+    case OP_POSSTARI:
+    possessive = TRUE;
+    min = 0;
+    max = INT_MAX;
+    ecode++;
+    goto REPEATCHAR;
+
+    case OP_POSPLUS:
+    case OP_POSPLUSI:
+    possessive = TRUE;
+    min = 1;
+    max = INT_MAX;
+    ecode++;
+    goto REPEATCHAR;
+
+    case OP_POSQUERY:
+    case OP_POSQUERYI:
+    possessive = TRUE;
+    min = 0;
+    max = 1;
+    ecode++;
+    goto REPEATCHAR;
+
+    case OP_STAR:
+    case OP_STARI:
+    case OP_MINSTAR:
+    case OP_MINSTARI:
+    case OP_PLUS:
+    case OP_PLUSI:
+    case OP_MINPLUS:
+    case OP_MINPLUSI:
+    case OP_QUERY:
+    case OP_QUERYI:
+    case OP_MINQUERY:
+    case OP_MINQUERYI:
+    c = *ecode++ - ((op < OP_STARI)? OP_STAR : OP_STARI);
+    minimize = (c & 1) != 0;
+    min = rep_min[c];                 /* Pick up values from tables; */
+    max = rep_max[c];                 /* zero for max => infinity */
+    if (max == 0) max = INT_MAX;
+
+    /* Common code for all repeated single-character matches. */
+
+    REPEATCHAR:
+#ifdef SUPPORT_UTF
+    if (utf)
+      {
+      length = 1;
+      charptr = ecode;
+      GETCHARLEN(fc, ecode, length);
+      ecode += length;
+
+      /* Handle multibyte character matching specially here. There is
+      support for caseless matching if UCP support is present. */
+
+      if (length > 1)
+        {
+#ifdef SUPPORT_UCP
+        unsigned int othercase;
+        if (op >= OP_STARI &&     /* Caseless */
+            (othercase = UCD_OTHERCASE(fc)) != fc)
+          oclength = PRIV(ord2utf)(othercase, occhars);
+        else oclength = 0;
+#endif  /* SUPPORT_UCP */
+
+        for (i = 1; i <= min; i++)
+          {
+          if (eptr <= md->end_subject - length &&
+            memcmp(eptr, charptr, IN_UCHARS(length)) == 0) eptr += length;
+#ifdef SUPPORT_UCP
+          else if (oclength > 0 &&
+                   eptr <= md->end_subject - oclength &&
+                   memcmp(eptr, occhars, IN_UCHARS(oclength)) == 0) eptr += oclength;
+#endif  /* SUPPORT_UCP */
+          else
+            {
+            CHECK_PARTIAL();
+            RRETURN(MATCH_NOMATCH);
+            }
+          }
+
+        if (min == max) continue;
+
+        if (minimize)
+          {
+          for (fi = min;; fi++)
+            {
+            RMATCH(eptr, ecode, offset_top, md, eptrb, RM22);
+            if (rrc != MATCH_NOMATCH) RRETURN(rrc);
+            if (fi >= max) RRETURN(MATCH_NOMATCH);
+            if (eptr <= md->end_subject - length &&
+              memcmp(eptr, charptr, IN_UCHARS(length)) == 0) eptr += length;
+#ifdef SUPPORT_UCP
+            else if (oclength > 0 &&
+                     eptr <= md->end_subject - oclength &&
+                     memcmp(eptr, occhars, IN_UCHARS(oclength)) == 0) eptr += oclength;
+#endif  /* SUPPORT_UCP */
+            else
+              {
+              CHECK_PARTIAL();
+              RRETURN(MATCH_NOMATCH);
+              }
+            }
+          /* Control never gets here */
+          }
+
+        else  /* Maximize */
+          {
+          pp = eptr;
+          for (i = min; i < max; i++)
+            {
+            if (eptr <= md->end_subject - length &&
+                memcmp(eptr, charptr, IN_UCHARS(length)) == 0) eptr += length;
+#ifdef SUPPORT_UCP
+            else if (oclength > 0 &&
+                     eptr <= md->end_subject - oclength &&
+                     memcmp(eptr, occhars, IN_UCHARS(oclength)) == 0) eptr += oclength;
+#endif  /* SUPPORT_UCP */
+            else
+              {
+              CHECK_PARTIAL();
+              break;
+              }
+            }
+
+          if (possessive) continue;
+
+          for(;;)
+            {
+            RMATCH(eptr, ecode, offset_top, md, eptrb, RM23);
+            if (rrc != MATCH_NOMATCH) RRETURN(rrc);
+            if (eptr == pp) { RRETURN(MATCH_NOMATCH); }
+#ifdef SUPPORT_UCP
+            eptr--;
+            BACKCHAR(eptr);
+#else   /* without SUPPORT_UCP */
+            eptr -= length;
+#endif  /* SUPPORT_UCP */
+            }
+          }
+        /* Control never gets here */
+        }
+
+      /* If the length of a UTF-8 character is 1, we fall through here, and
+      obey the code as for non-UTF-8 characters below, though in this case the
+      value of fc will always be < 128. */
+      }
+    else
+#endif  /* SUPPORT_UTF */
+      /* When not in UTF-8 mode, load a single-byte character. */
+      fc = *ecode++;
+
+    /* The value of fc at this point is always one character, though we may
+    or may not be in UTF mode. The code is duplicated for the caseless and
+    caseful cases, for speed, since matching characters is likely to be quite
+    common. First, ensure the minimum number of matches are present. If min =
+    max, continue at the same level without recursing. Otherwise, if
+    minimizing, keep trying the rest of the expression and advancing one
+    matching character if failing, up to the maximum. Alternatively, if
+    maximizing, find the maximum number of characters and work backwards. */
+
+    DPRINTF(("matching %c{%d,%d} against subject %.*s\n", fc, min, max,
+      max, (char *)eptr));
+
+    if (op >= OP_STARI)  /* Caseless */
+      {
+#ifdef COMPILE_PCRE8
+      /* fc must be < 128 if UTF is enabled. */
+      foc = md->fcc[fc];
+#else
+#ifdef SUPPORT_UTF
+#ifdef SUPPORT_UCP
+      if (utf && fc > 127)
+        foc = UCD_OTHERCASE(fc);
+#else
+      if (utf && fc > 127)
+        foc = fc;
+#endif /* SUPPORT_UCP */
+      else
+#endif /* SUPPORT_UTF */
+        foc = TABLE_GET(fc, md->fcc, fc);
+#endif /* COMPILE_PCRE8 */
+
+      for (i = 1; i <= min; i++)
+        {
+        if (eptr >= md->end_subject)
+          {
+          SCHECK_PARTIAL();
+          RRETURN(MATCH_NOMATCH);
+          }
+        if (fc != *eptr && foc != *eptr) RRETURN(MATCH_NOMATCH);
+        eptr++;
+        }
+      if (min == max) continue;
+      if (minimize)
+        {
+        for (fi = min;; fi++)
+          {
+          RMATCH(eptr, ecode, offset_top, md, eptrb, RM24);
+          if (rrc != MATCH_NOMATCH) RRETURN(rrc);
+          if (fi >= max) RRETURN(MATCH_NOMATCH);
+          if (eptr >= md->end_subject)
+            {
+            SCHECK_PARTIAL();
+            RRETURN(MATCH_NOMATCH);
+            }
+          if (fc != *eptr && foc != *eptr) RRETURN(MATCH_NOMATCH);
+          eptr++;
+          }
+        /* Control never gets here */
+        }
+      else  /* Maximize */
+        {
+        pp = eptr;
+        for (i = min; i < max; i++)
+          {
+          if (eptr >= md->end_subject)
+            {
+            SCHECK_PARTIAL();
+            break;
+            }
+          if (fc != *eptr && foc != *eptr) break;
+          eptr++;
+          }
+
+        if (possessive) continue;
+
+        while (eptr >= pp)
+          {
+          RMATCH(eptr, ecode, offset_top, md, eptrb, RM25);
+          eptr--;
+          if (rrc != MATCH_NOMATCH) RRETURN(rrc);
+          }
+        RRETURN(MATCH_NOMATCH);
+        }
+      /* Control never gets here */
+      }
+
+    /* Caseful comparisons (includes all multi-byte characters) */
+
+    else
+      {
+      for (i = 1; i <= min; i++)
+        {
+        if (eptr >= md->end_subject)
+          {
+          SCHECK_PARTIAL();
+          RRETURN(MATCH_NOMATCH);
+          }
+        if (fc != *eptr++) RRETURN(MATCH_NOMATCH);
+        }
+
+      if (min == max) continue;
+
+      if (minimize)
+        {
+        for (fi = min;; fi++)
+          {
+          RMATCH(eptr, ecode, offset_top, md, eptrb, RM26);
+          if (rrc != MATCH_NOMATCH) RRETURN(rrc);
+          if (fi >= max) RRETURN(MATCH_NOMATCH);
+          if (eptr >= md->end_subject)
+            {
+            SCHECK_PARTIAL();
+            RRETURN(MATCH_NOMATCH);
+            }
+          if (fc != *eptr++) RRETURN(MATCH_NOMATCH);
+          }
+        /* Control never gets here */
+        }
+      else  /* Maximize */
+        {
+        pp = eptr;
+        for (i = min; i < max; i++)
+          {
+          if (eptr >= md->end_subject)
+            {
+            SCHECK_PARTIAL();
+            break;
+            }
+          if (fc != *eptr) break;
+          eptr++;
+          }
+        if (possessive) continue;
+
+        while (eptr >= pp)
+          {
+          RMATCH(eptr, ecode, offset_top, md, eptrb, RM27);
+          eptr--;
+          if (rrc != MATCH_NOMATCH) RRETURN(rrc);
+          }
+        RRETURN(MATCH_NOMATCH);
+        }
+      }
+    /* Control never gets here */
+
+    /* Match a negated single one-byte character. The character we are
+    checking can be multibyte. */
+
+    case OP_NOT:
+    case OP_NOTI:
+    if (eptr >= md->end_subject)
+      {
+      SCHECK_PARTIAL();
+      RRETURN(MATCH_NOMATCH);
+      }
+#ifdef SUPPORT_UTF
+    if (utf)
+      {
+      register unsigned int ch, och;
+
+      ecode++;
+      GETCHARINC(ch, ecode);
+      GETCHARINC(c, eptr);
+
+      if (op == OP_NOT)
+        {
+        if (ch == c) RRETURN(MATCH_NOMATCH);
+        }
+      else
+        {
+#ifdef SUPPORT_UCP
+        if (ch > 127)
+          och = UCD_OTHERCASE(ch);
+#else
+        if (ch > 127)
+          och = ch;
+#endif /* SUPPORT_UCP */
+        else
+          och = TABLE_GET(ch, md->fcc, ch);
+        if (ch == c || och == c) RRETURN(MATCH_NOMATCH);
+        }
+      }
+    else
+#endif
+      {
+      register unsigned int ch = ecode[1];
+      c = *eptr++;
+      if (ch == c || (op == OP_NOTI && TABLE_GET(ch, md->fcc, ch) == c))
+        RRETURN(MATCH_NOMATCH);
+      ecode += 2;
+      }
+    break;
+
+    /* Match a negated single one-byte character repeatedly. This is almost a
+    repeat of the code for a repeated single character, but I haven't found a
+    nice way of commoning these up that doesn't require a test of the
+    positive/negative option for each character match. Maybe that wouldn't add
+    very much to the time taken, but character matching *is* what this is all
+    about... */
+
+    case OP_NOTEXACT:
+    case OP_NOTEXACTI:
+    min = max = GET2(ecode, 1);
+    ecode += 1 + IMM2_SIZE;
+    goto REPEATNOTCHAR;
+
+    case OP_NOTUPTO:
+    case OP_NOTUPTOI:
+    case OP_NOTMINUPTO:
+    case OP_NOTMINUPTOI:
+    min = 0;
+    max = GET2(ecode, 1);
+    minimize = *ecode == OP_NOTMINUPTO || *ecode == OP_NOTMINUPTOI;
+    ecode += 1 + IMM2_SIZE;
+    goto REPEATNOTCHAR;
+
+    case OP_NOTPOSSTAR:
+    case OP_NOTPOSSTARI:
+    possessive = TRUE;
+    min = 0;
+    max = INT_MAX;
+    ecode++;
+    goto REPEATNOTCHAR;
+
+    case OP_NOTPOSPLUS:
+    case OP_NOTPOSPLUSI:
+    possessive = TRUE;
+    min = 1;
+    max = INT_MAX;
+    ecode++;
+    goto REPEATNOTCHAR;
+
+    case OP_NOTPOSQUERY:
+    case OP_NOTPOSQUERYI:
+    possessive = TRUE;
+    min = 0;
+    max = 1;
+    ecode++;
+    goto REPEATNOTCHAR;
+
+    case OP_NOTPOSUPTO:
+    case OP_NOTPOSUPTOI:
+    possessive = TRUE;
+    min = 0;
+    max = GET2(ecode, 1);
+    ecode += 1 + IMM2_SIZE;
+    goto REPEATNOTCHAR;
+
+    case OP_NOTSTAR:
+    case OP_NOTSTARI:
+    case OP_NOTMINSTAR:
+    case OP_NOTMINSTARI:
+    case OP_NOTPLUS:
+    case OP_NOTPLUSI:
+    case OP_NOTMINPLUS:
+    case OP_NOTMINPLUSI:
+    case OP_NOTQUERY:
+    case OP_NOTQUERYI:
+    case OP_NOTMINQUERY:
+    case OP_NOTMINQUERYI:
+    c = *ecode++ - ((op >= OP_NOTSTARI)? OP_NOTSTARI: OP_NOTSTAR);
+    minimize = (c & 1) != 0;
+    min = rep_min[c];                 /* Pick up values from tables; */
+    max = rep_max[c];                 /* zero for max => infinity */
+    if (max == 0) max = INT_MAX;
+
+    /* Common code for all repeated single-byte matches. */
+
+    REPEATNOTCHAR:
+    GETCHARINCTEST(fc, ecode);
+
+    /* The code is duplicated for the caseless and caseful cases, for speed,
+    since matching characters is likely to be quite common. First, ensure the
+    minimum number of matches are present. If min = max, continue at the same
+    level without recursing. Otherwise, if minimizing, keep trying the rest of
+    the expression and advancing one matching character if failing, up to the
+    maximum. Alternatively, if maximizing, find the maximum number of
+    characters and work backwards. */
+
+    DPRINTF(("negative matching %c{%d,%d} against subject %.*s\n", fc, min, max,
+      max, (char *)eptr));
+
+    if (op >= OP_NOTSTARI)     /* Caseless */
+      {
+#ifdef SUPPORT_UTF
+#ifdef SUPPORT_UCP
+      if (utf && fc > 127)
+        foc = UCD_OTHERCASE(fc);
+#else
+      if (utf && fc > 127)
+        foc = fc;
+#endif /* SUPPORT_UCP */
+      else
+#endif /* SUPPORT_UTF */
+        foc = TABLE_GET(fc, md->fcc, fc);
+
+#ifdef SUPPORT_UTF
+      if (utf)
+        {
+        register unsigned int d;
+        for (i = 1; i <= min; i++)
+          {
+          if (eptr >= md->end_subject)
+            {
+            SCHECK_PARTIAL();
+            RRETURN(MATCH_NOMATCH);
+            }
+          GETCHARINC(d, eptr);
+          if (fc == d || (unsigned int)foc == d) RRETURN(MATCH_NOMATCH);
+          }
+        }
+      else
+#endif
+      /* Not UTF mode */
+        {
+        for (i = 1; i <= min; i++)
+          {
+          if (eptr >= md->end_subject)
+            {
+            SCHECK_PARTIAL();
+            RRETURN(MATCH_NOMATCH);
+            }
+          if (fc == *eptr || foc == *eptr) RRETURN(MATCH_NOMATCH);
+          eptr++;
+          }
+        }
+
+      if (min == max) continue;
+
+      if (minimize)
+        {
+#ifdef SUPPORT_UTF
+        if (utf)
+          {
+          register unsigned int d;
+          for (fi = min;; fi++)
+            {
+            RMATCH(eptr, ecode, offset_top, md, eptrb, RM28);
+            if (rrc != MATCH_NOMATCH) RRETURN(rrc);
+            if (fi >= max) RRETURN(MATCH_NOMATCH);
+            if (eptr >= md->end_subject)
+              {
+              SCHECK_PARTIAL();
+              RRETURN(MATCH_NOMATCH);
+              }
+            GETCHARINC(d, eptr);
+            if (fc == d || (unsigned int)foc == d) RRETURN(MATCH_NOMATCH);
+            }
+          }
+        else
+#endif
+        /* Not UTF mode */
+          {
+          for (fi = min;; fi++)
+            {
+            RMATCH(eptr, ecode, offset_top, md, eptrb, RM29);
+            if (rrc != MATCH_NOMATCH) RRETURN(rrc);
+            if (fi >= max) RRETURN(MATCH_NOMATCH);
+            if (eptr >= md->end_subject)
+              {
+              SCHECK_PARTIAL();
+              RRETURN(MATCH_NOMATCH);
+              }
+            if (fc == *eptr || foc == *eptr) RRETURN(MATCH_NOMATCH);
+            eptr++;
+            }
+          }
+        /* Control never gets here */
+        }
+
+      /* Maximize case */
+
+      else
+        {
+        pp = eptr;
+
+#ifdef SUPPORT_UTF
+        if (utf)
+          {
+          register unsigned int d;
+          for (i = min; i < max; i++)
+            {
+            int len = 1;
+            if (eptr >= md->end_subject)
+              {
+              SCHECK_PARTIAL();
+              break;
+              }
+            GETCHARLEN(d, eptr, len);
+            if (fc == d || (unsigned int)foc == d) break;
+            eptr += len;
+            }
+          if (possessive) continue;
+          for(;;)
+            {
+            RMATCH(eptr, ecode, offset_top, md, eptrb, RM30);
+            if (rrc != MATCH_NOMATCH) RRETURN(rrc);
+            if (eptr-- == pp) break;        /* Stop if tried at original pos */
+            BACKCHAR(eptr);
+            }
+          }
+        else
+#endif
+        /* Not UTF mode */
+          {
+          for (i = min; i < max; i++)
+            {
+            if (eptr >= md->end_subject)
+              {
+              SCHECK_PARTIAL();
+              break;
+              }
+            if (fc == *eptr || foc == *eptr) break;
+            eptr++;
+            }
+          if (possessive) continue;
+          while (eptr >= pp)
+            {
+            RMATCH(eptr, ecode, offset_top, md, eptrb, RM31);
+            if (rrc != MATCH_NOMATCH) RRETURN(rrc);
+            eptr--;
+            }
+          }
+
+        RRETURN(MATCH_NOMATCH);
+        }
+      /* Control never gets here */
+      }
+
+    /* Caseful comparisons */
+
+    else
+      {
+#ifdef SUPPORT_UTF
+      if (utf)
+        {
+        register unsigned int d;
+        for (i = 1; i <= min; i++)
+          {
+          if (eptr >= md->end_subject)
+            {
+            SCHECK_PARTIAL();
+            RRETURN(MATCH_NOMATCH);
+            }
+          GETCHARINC(d, eptr);
+          if (fc == d) RRETURN(MATCH_NOMATCH);
+          }
+        }
+      else
+#endif
+      /* Not UTF mode */
+        {
+        for (i = 1; i <= min; i++)
+          {
+          if (eptr >= md->end_subject)
+            {
+            SCHECK_PARTIAL();
+            RRETURN(MATCH_NOMATCH);
+            }
+          if (fc == *eptr++) RRETURN(MATCH_NOMATCH);
+          }
+        }
+
+      if (min == max) continue;
+
+      if (minimize)
+        {
+#ifdef SUPPORT_UTF
+        if (utf)
+          {
+          register unsigned int d;
+          for (fi = min;; fi++)
+            {
+            RMATCH(eptr, ecode, offset_top, md, eptrb, RM32);
+            if (rrc != MATCH_NOMATCH) RRETURN(rrc);
+            if (fi >= max) RRETURN(MATCH_NOMATCH);
+            if (eptr >= md->end_subject)
+              {
+              SCHECK_PARTIAL();
+              RRETURN(MATCH_NOMATCH);
+              }
+            GETCHARINC(d, eptr);
+            if (fc == d) RRETURN(MATCH_NOMATCH);
+            }
+          }
+        else
+#endif
+        /* Not UTF mode */
+          {
+          for (fi = min;; fi++)
+            {
+            RMATCH(eptr, ecode, offset_top, md, eptrb, RM33);
+            if (rrc != MATCH_NOMATCH) RRETURN(rrc);
+            if (fi >= max) RRETURN(MATCH_NOMATCH);
+            if (eptr >= md->end_subject)
+              {
+              SCHECK_PARTIAL();
+              RRETURN(MATCH_NOMATCH);
+              }
+            if (fc == *eptr++) RRETURN(MATCH_NOMATCH);
+            }
+          }
+        /* Control never gets here */
+        }
+
+      /* Maximize case */
+
+      else
+        {
+        pp = eptr;
+
+#ifdef SUPPORT_UTF
+        if (utf)
+          {
+          register unsigned int d;
+          for (i = min; i < max; i++)
+            {
+            int len = 1;
+            if (eptr >= md->end_subject)
+              {
+              SCHECK_PARTIAL();
+              break;
+              }
+            GETCHARLEN(d, eptr, len);
+            if (fc == d) break;
+            eptr += len;
+            }
+          if (possessive) continue;
+          for(;;)
+            {
+            RMATCH(eptr, ecode, offset_top, md, eptrb, RM34);
+            if (rrc != MATCH_NOMATCH) RRETURN(rrc);
+            if (eptr-- == pp) break;        /* Stop if tried at original pos */
+            BACKCHAR(eptr);
+            }
+          }
+        else
+#endif
+        /* Not UTF mode */
+          {
+          for (i = min; i < max; i++)
+            {
+            if (eptr >= md->end_subject)
+              {
+              SCHECK_PARTIAL();
+              break;
+              }
+            if (fc == *eptr) break;
+            eptr++;
+            }
+          if (possessive) continue;
+          while (eptr >= pp)
+            {
+            RMATCH(eptr, ecode, offset_top, md, eptrb, RM35);
+            if (rrc != MATCH_NOMATCH) RRETURN(rrc);
+            eptr--;
+            }
+          }
+
+        RRETURN(MATCH_NOMATCH);
+        }
+      }
+    /* Control never gets here */
+
+    /* Match a single character type repeatedly; several different opcodes
+    share code. This is very similar to the code for single characters, but we
+    repeat it in the interests of efficiency. */
+
+    case OP_TYPEEXACT:
+    min = max = GET2(ecode, 1);
+    minimize = TRUE;
+    ecode += 1 + IMM2_SIZE;
+    goto REPEATTYPE;
+
+    case OP_TYPEUPTO:
+    case OP_TYPEMINUPTO:
+    min = 0;
+    max = GET2(ecode, 1);
+    minimize = *ecode == OP_TYPEMINUPTO;
+    ecode += 1 + IMM2_SIZE;
+    goto REPEATTYPE;
+
+    case OP_TYPEPOSSTAR:
+    possessive = TRUE;
+    min = 0;
+    max = INT_MAX;
+    ecode++;
+    goto REPEATTYPE;
+
+    case OP_TYPEPOSPLUS:
+    possessive = TRUE;
+    min = 1;
+    max = INT_MAX;
+    ecode++;
+    goto REPEATTYPE;
+
+    case OP_TYPEPOSQUERY:
+    possessive = TRUE;
+    min = 0;
+    max = 1;
+    ecode++;
+    goto REPEATTYPE;
+
+    case OP_TYPEPOSUPTO:
+    possessive = TRUE;
+    min = 0;
+    max = GET2(ecode, 1);
+    ecode += 1 + IMM2_SIZE;
+    goto REPEATTYPE;
+
+    case OP_TYPESTAR:
+    case OP_TYPEMINSTAR:
+    case OP_TYPEPLUS:
+    case OP_TYPEMINPLUS:
+    case OP_TYPEQUERY:
+    case OP_TYPEMINQUERY:
+    c = *ecode++ - OP_TYPESTAR;
+    minimize = (c & 1) != 0;
+    min = rep_min[c];                 /* Pick up values from tables; */
+    max = rep_max[c];                 /* zero for max => infinity */
+    if (max == 0) max = INT_MAX;
+
+    /* Common code for all repeated single character type matches. Note that
+    in UTF-8 mode, '.' matches a character of any length, but for the other
+    character types, the valid characters are all one-byte long. */
+
+    REPEATTYPE:
+    ctype = *ecode++;      /* Code for the character type */
+
+#ifdef SUPPORT_UCP
+    if (ctype == OP_PROP || ctype == OP_NOTPROP)
+      {
+      prop_fail_result = ctype == OP_NOTPROP;
+      prop_type = *ecode++;
+      prop_value = *ecode++;
+      }
+    else prop_type = -1;
+#endif
+
+    /* First, ensure the minimum number of matches are present. Use inline
+    code for maximizing the speed, and do the type test once at the start
+    (i.e. keep it out of the loop). Separate the UTF-8 code completely as that
+    is tidier. Also separate the UCP code, which can be the same for both UTF-8
+    and single-bytes. */
+
+    if (min > 0)
+      {
+#ifdef SUPPORT_UCP
+      if (prop_type >= 0)
+        {
+        switch(prop_type)
+          {
+          case PT_ANY:
+          if (prop_fail_result) RRETURN(MATCH_NOMATCH);
+          for (i = 1; i <= min; i++)
+            {
+            if (eptr >= md->end_subject)
+              {
+              SCHECK_PARTIAL();
+              RRETURN(MATCH_NOMATCH);
+              }
+            GETCHARINCTEST(c, eptr);
+            }
+          break;
+
+          case PT_LAMP:
+          for (i = 1; i <= min; i++)
+            {
+            int chartype;
+            if (eptr >= md->end_subject)
+              {
+              SCHECK_PARTIAL();
+              RRETURN(MATCH_NOMATCH);
+              }
+            GETCHARINCTEST(c, eptr);
+            chartype = UCD_CHARTYPE(c);
+            if ((chartype == ucp_Lu ||
+                 chartype == ucp_Ll ||
+                 chartype == ucp_Lt) == prop_fail_result)
+              RRETURN(MATCH_NOMATCH);
+            }
+          break;
+
+          case PT_GC:
+          for (i = 1; i <= min; i++)
+            {
+            if (eptr >= md->end_subject)
+              {
+              SCHECK_PARTIAL();
+              RRETURN(MATCH_NOMATCH);
+              }
+            GETCHARINCTEST(c, eptr);
+            if ((UCD_CATEGORY(c) == prop_value) == prop_fail_result)
+              RRETURN(MATCH_NOMATCH);
+            }
+          break;
+
+          case PT_PC:
+          for (i = 1; i <= min; i++)
+            {
+            if (eptr >= md->end_subject)
+              {
+              SCHECK_PARTIAL();
+              RRETURN(MATCH_NOMATCH);
+              }
+            GETCHARINCTEST(c, eptr);
+            if ((UCD_CHARTYPE(c) == prop_value) == prop_fail_result)
+              RRETURN(MATCH_NOMATCH);
+            }
+          break;
+
+          case PT_SC:
+          for (i = 1; i <= min; i++)
+            {
+            if (eptr >= md->end_subject)
+              {
+              SCHECK_PARTIAL();
+              RRETURN(MATCH_NOMATCH);
+              }
+            GETCHARINCTEST(c, eptr);
+            if ((UCD_SCRIPT(c) == prop_value) == prop_fail_result)
+              RRETURN(MATCH_NOMATCH);
+            }
+          break;
+
+          case PT_ALNUM:
+          for (i = 1; i <= min; i++)
+            {
+            int category;
+            if (eptr >= md->end_subject)
+              {
+              SCHECK_PARTIAL();
+              RRETURN(MATCH_NOMATCH);
+              }
+            GETCHARINCTEST(c, eptr);
+            category = UCD_CATEGORY(c);
+            if ((category == ucp_L || category == ucp_N) == prop_fail_result)
+              RRETURN(MATCH_NOMATCH);
+            }
+          break;
+
+          case PT_SPACE:    /* Perl space */
+          for (i = 1; i <= min; i++)
+            {
+            if (eptr >= md->end_subject)
+              {
+              SCHECK_PARTIAL();
+              RRETURN(MATCH_NOMATCH);
+              }
+            GETCHARINCTEST(c, eptr);
+            if ((UCD_CATEGORY(c) == ucp_Z || c == CHAR_HT || c == CHAR_NL ||
+                 c == CHAR_FF || c == CHAR_CR)
+                   == prop_fail_result)
+              RRETURN(MATCH_NOMATCH);
+            }
+          break;
+
+          case PT_PXSPACE:  /* POSIX space */
+          for (i = 1; i <= min; i++)
+            {
+            if (eptr >= md->end_subject)
+              {
+              SCHECK_PARTIAL();
+              RRETURN(MATCH_NOMATCH);
+              }
+            GETCHARINCTEST(c, eptr);
+            if ((UCD_CATEGORY(c) == ucp_Z || c == CHAR_HT || c == CHAR_NL ||
+                 c == CHAR_VT || c == CHAR_FF || c == CHAR_CR)
+                   == prop_fail_result)
+              RRETURN(MATCH_NOMATCH);
+            }
+          break;
+
+          case PT_WORD:
+          for (i = 1; i <= min; i++)
+            {
+            int category;
+            if (eptr >= md->end_subject)
+              {
+              SCHECK_PARTIAL();
+              RRETURN(MATCH_NOMATCH);
+              }
+            GETCHARINCTEST(c, eptr);
+            category = UCD_CATEGORY(c);
+            if ((category == ucp_L || category == ucp_N || c == CHAR_UNDERSCORE)
+                   == prop_fail_result)
+              RRETURN(MATCH_NOMATCH);
+            }
+          break;
+
+          /* This should not occur */
+
+          default:
+          RRETURN(PCRE_ERROR_INTERNAL);
+          }
+        }
+
+      /* Match extended Unicode sequences. We will get here only if the
+      support is in the binary; otherwise a compile-time error occurs. */
+
+      else if (ctype == OP_EXTUNI)
+        {
+        for (i = 1; i <= min; i++)
+          {
+          if (eptr >= md->end_subject)
+            {
+            SCHECK_PARTIAL();
+            RRETURN(MATCH_NOMATCH);
+            }
+          GETCHARINCTEST(c, eptr);
+          if (UCD_CATEGORY(c) == ucp_M) RRETURN(MATCH_NOMATCH);
+          while (eptr < md->end_subject)
+            {
+            int len = 1;
+            if (!utf) c = *eptr; else { GETCHARLEN(c, eptr, len); }
+            if (UCD_CATEGORY(c) != ucp_M) break;
+            eptr += len;
+            }
+          CHECK_PARTIAL();
+          }
+        }
+
+      else
+#endif     /* SUPPORT_UCP */
+
+/* Handle all other cases when the coding is UTF-8 */
+
+#ifdef SUPPORT_UTF
+      if (utf) switch(ctype)
+        {
+        case OP_ANY:
+        for (i = 1; i <= min; i++)
+          {
+          if (eptr >= md->end_subject)
+            {
+            SCHECK_PARTIAL();
+            RRETURN(MATCH_NOMATCH);
+            }
+          if (IS_NEWLINE(eptr)) RRETURN(MATCH_NOMATCH);
+          if (md->partial != 0 &&
+              eptr + 1 >= md->end_subject &&
+              NLBLOCK->nltype == NLTYPE_FIXED &&
+              NLBLOCK->nllen == 2 &&
+              *eptr == NLBLOCK->nl[0])
+            {
+            md->hitend = TRUE;
+            if (md->partial > 1) RRETURN(PCRE_ERROR_PARTIAL);
+            }
+          eptr++;
+          ACROSSCHAR(eptr < md->end_subject, *eptr, eptr++);
+          }
+        break;
+
+        case OP_ALLANY:
+        for (i = 1; i <= min; i++)
+          {
+          if (eptr >= md->end_subject)
+            {
+            SCHECK_PARTIAL();
+            RRETURN(MATCH_NOMATCH);
+            }
+          eptr++;
+          ACROSSCHAR(eptr < md->end_subject, *eptr, eptr++);
+          }
+        break;
+
+        case OP_ANYBYTE:
+        if (eptr > md->end_subject - min) RRETURN(MATCH_NOMATCH);
+        eptr += min;
+        break;
+
+        case OP_ANYNL:
+        for (i = 1; i <= min; i++)
+          {
+          if (eptr >= md->end_subject)
+            {
+            SCHECK_PARTIAL();
+            RRETURN(MATCH_NOMATCH);
+            }
+          GETCHARINC(c, eptr);
+          switch(c)
+            {
+            default: RRETURN(MATCH_NOMATCH);
+
+            case 0x000d:
+            if (eptr < md->end_subject && *eptr == 0x0a) eptr++;
+            break;
+
+            case 0x000a:
+            break;
+
+            case 0x000b:
+            case 0x000c:
+            case 0x0085:
+            case 0x2028:
+            case 0x2029:
+            if (md->bsr_anycrlf) RRETURN(MATCH_NOMATCH);
+            break;
+            }
+          }
+        break;
+
+        case OP_NOT_HSPACE:
+        for (i = 1; i <= min; i++)
+          {
+          if (eptr >= md->end_subject)
+            {
+            SCHECK_PARTIAL();
+            RRETURN(MATCH_NOMATCH);
+            }
+          GETCHARINC(c, eptr);
+          switch(c)
+            {
+            default: break;
+            case 0x09:      /* HT */
+            case 0x20:      /* SPACE */
+            case 0xa0:      /* NBSP */
+            case 0x1680:    /* OGHAM SPACE MARK */
+            case 0x180e:    /* MONGOLIAN VOWEL SEPARATOR */
+            case 0x2000:    /* EN QUAD */
+            case 0x2001:    /* EM QUAD */
+            case 0x2002:    /* EN SPACE */
+            case 0x2003:    /* EM SPACE */
+            case 0x2004:    /* THREE-PER-EM SPACE */
+            case 0x2005:    /* FOUR-PER-EM SPACE */
+            case 0x2006:    /* SIX-PER-EM SPACE */
+            case 0x2007:    /* FIGURE SPACE */
+            case 0x2008:    /* PUNCTUATION SPACE */
+            case 0x2009:    /* THIN SPACE */
+            case 0x200A:    /* HAIR SPACE */
+            case 0x202f:    /* NARROW NO-BREAK SPACE */
+            case 0x205f:    /* MEDIUM MATHEMATICAL SPACE */
+            case 0x3000:    /* IDEOGRAPHIC SPACE */
+            RRETURN(MATCH_NOMATCH);
+            }
+          }
+        break;
+
+        case OP_HSPACE:
+        for (i = 1; i <= min; i++)
+          {
+          if (eptr >= md->end_subject)
+            {
+            SCHECK_PARTIAL();
+            RRETURN(MATCH_NOMATCH);
+            }
+          GETCHARINC(c, eptr);
+          switch(c)
+            {
+            default: RRETURN(MATCH_NOMATCH);
+            case 0x09:      /* HT */
+            case 0x20:      /* SPACE */
+            case 0xa0:      /* NBSP */
+            case 0x1680:    /* OGHAM SPACE MARK */
+            case 0x180e:    /* MONGOLIAN VOWEL SEPARATOR */
+            case 0x2000:    /* EN QUAD */
+            case 0x2001:    /* EM QUAD */
+            case 0x2002:    /* EN SPACE */
+            case 0x2003:    /* EM SPACE */
+            case 0x2004:    /* THREE-PER-EM SPACE */
+            case 0x2005:    /* FOUR-PER-EM SPACE */
+            case 0x2006:    /* SIX-PER-EM SPACE */
+            case 0x2007:    /* FIGURE SPACE */
+            case 0x2008:    /* PUNCTUATION SPACE */
+            case 0x2009:    /* THIN SPACE */
+            case 0x200A:    /* HAIR SPACE */
+            case 0x202f:    /* NARROW NO-BREAK SPACE */
+            case 0x205f:    /* MEDIUM MATHEMATICAL SPACE */
+            case 0x3000:    /* IDEOGRAPHIC SPACE */
+            break;
+            }
+          }
+        break;
+
+        case OP_NOT_VSPACE:
+        for (i = 1; i <= min; i++)
+          {
+          if (eptr >= md->end_subject)
+            {
+            SCHECK_PARTIAL();
+            RRETURN(MATCH_NOMATCH);
+            }
+          GETCHARINC(c, eptr);
+          switch(c)
+            {
+            default: break;
+            case 0x0a:      /* LF */
+            case 0x0b:      /* VT */
+            case 0x0c:      /* FF */
+            case 0x0d:      /* CR */
+            case 0x85:      /* NEL */
+            case 0x2028:    /* LINE SEPARATOR */
+            case 0x2029:    /* PARAGRAPH SEPARATOR */
+            RRETURN(MATCH_NOMATCH);
+            }
+          }
+        break;
+
+        case OP_VSPACE:
+        for (i = 1; i <= min; i++)
+          {
+          if (eptr >= md->end_subject)
+            {
+            SCHECK_PARTIAL();
+            RRETURN(MATCH_NOMATCH);
+            }
+          GETCHARINC(c, eptr);
+          switch(c)
+            {
+            default: RRETURN(MATCH_NOMATCH);
+            case 0x0a:      /* LF */
+            case 0x0b:      /* VT */
+            case 0x0c:      /* FF */
+            case 0x0d:      /* CR */
+            case 0x85:      /* NEL */
+            case 0x2028:    /* LINE SEPARATOR */
+            case 0x2029:    /* PARAGRAPH SEPARATOR */
+            break;
+            }
+          }
+        break;
+
+        case OP_NOT_DIGIT:
+        for (i = 1; i <= min; i++)
+          {
+          if (eptr >= md->end_subject)
+            {
+            SCHECK_PARTIAL();
+            RRETURN(MATCH_NOMATCH);
+            }
+          GETCHARINC(c, eptr);
+          if (c < 128 && (md->ctypes[c] & ctype_digit) != 0)
+            RRETURN(MATCH_NOMATCH);
+          }
+        break;
+
+        case OP_DIGIT:
+        for (i = 1; i <= min; i++)
+          {
+          if (eptr >= md->end_subject)
+            {
+            SCHECK_PARTIAL();
+            RRETURN(MATCH_NOMATCH);
+            }
+          if (*eptr >= 128 || (md->ctypes[*eptr] & ctype_digit) == 0)
+            RRETURN(MATCH_NOMATCH);
+          eptr++;
+          /* No need to skip more bytes - we know it's a 1-byte character */
+          }
+        break;
+
+        case OP_NOT_WHITESPACE:
+        for (i = 1; i <= min; i++)
+          {
+          if (eptr >= md->end_subject)
+            {
+            SCHECK_PARTIAL();
+            RRETURN(MATCH_NOMATCH);
+            }
+          if (*eptr < 128 && (md->ctypes[*eptr] & ctype_space) != 0)
+            RRETURN(MATCH_NOMATCH);
+          eptr++;
+          ACROSSCHAR(eptr < md->end_subject, *eptr, eptr++);
+          }
+        break;
+
+        case OP_WHITESPACE:
+        for (i = 1; i <= min; i++)
+          {
+          if (eptr >= md->end_subject)
+            {
+            SCHECK_PARTIAL();
+            RRETURN(MATCH_NOMATCH);
+            }
+          if (*eptr >= 128 || (md->ctypes[*eptr] & ctype_space) == 0)
+            RRETURN(MATCH_NOMATCH);
+          eptr++;
+          /* No need to skip more bytes - we know it's a 1-byte character */
+          }
+        break;
+
+        case OP_NOT_WORDCHAR:
+        for (i = 1; i <= min; i++)
+          {
+          if (eptr >= md->end_subject)
+            {
+            SCHECK_PARTIAL();
+            RRETURN(MATCH_NOMATCH);
+            }
+          if (*eptr < 128 && (md->ctypes[*eptr] & ctype_word) != 0)
+            RRETURN(MATCH_NOMATCH);
+          eptr++;
+          ACROSSCHAR(eptr < md->end_subject, *eptr, eptr++);
+          }
+        break;
+
+        case OP_WORDCHAR:
+        for (i = 1; i <= min; i++)
+          {
+          if (eptr >= md->end_subject)
+            {
+            SCHECK_PARTIAL();
+            RRETURN(MATCH_NOMATCH);
+            }
+          if (*eptr >= 128 || (md->ctypes[*eptr] & ctype_word) == 0)
+            RRETURN(MATCH_NOMATCH);
+          eptr++;
+          /* No need to skip more bytes - we know it's a 1-byte character */
+          }
+        break;
+
+        default:
+        RRETURN(PCRE_ERROR_INTERNAL);
+        }  /* End switch(ctype) */
+
+      else
+#endif     /* SUPPORT_UTF */
+
+      /* Code for the non-UTF-8 case for minimum matching of operators other
+      than OP_PROP and OP_NOTPROP. */
+
+      switch(ctype)
+        {
+        case OP_ANY:
+        for (i = 1; i <= min; i++)
+          {
+          if (eptr >= md->end_subject)
+            {
+            SCHECK_PARTIAL();
+            RRETURN(MATCH_NOMATCH);
+            }
+          if (IS_NEWLINE(eptr)) RRETURN(MATCH_NOMATCH);
+          if (md->partial != 0 &&
+              eptr + 1 >= md->end_subject &&
+              NLBLOCK->nltype == NLTYPE_FIXED &&
+              NLBLOCK->nllen == 2 &&
+              *eptr == NLBLOCK->nl[0])
+            {
+            md->hitend = TRUE;
+            if (md->partial > 1) RRETURN(PCRE_ERROR_PARTIAL);
+            }
+          eptr++;
+          }
+        break;
+
+        case OP_ALLANY:
+        if (eptr > md->end_subject - min)
+          {
+          SCHECK_PARTIAL();
+          RRETURN(MATCH_NOMATCH);
+          }
+        eptr += min;
+        break;
+
+        case OP_ANYBYTE:
+        if (eptr > md->end_subject - min)
+          {
+          SCHECK_PARTIAL();
+          RRETURN(MATCH_NOMATCH);
+          }
+        eptr += min;
+        break;
+
+        case OP_ANYNL:
+        for (i = 1; i <= min; i++)
+          {
+          if (eptr >= md->end_subject)
+            {
+            SCHECK_PARTIAL();
+            RRETURN(MATCH_NOMATCH);
+            }
+          switch(*eptr++)
+            {
+            default: RRETURN(MATCH_NOMATCH);
+
+            case 0x000d:
+            if (eptr < md->end_subject && *eptr == 0x0a) eptr++;
+            break;
+
+            case 0x000a:
+            break;
+
+            case 0x000b:
+            case 0x000c:
+            case 0x0085:
+#ifdef COMPILE_PCRE16
+            case 0x2028:
+            case 0x2029:
+#endif
+            if (md->bsr_anycrlf) RRETURN(MATCH_NOMATCH);
+            break;
+            }
+          }
+        break;
+
+        case OP_NOT_HSPACE:
+        for (i = 1; i <= min; i++)
+          {
+          if (eptr >= md->end_subject)
+            {
+            SCHECK_PARTIAL();
+            RRETURN(MATCH_NOMATCH);
+            }
+          switch(*eptr++)
+            {
+            default: break;
+            case 0x09:      /* HT */
+            case 0x20:      /* SPACE */
+            case 0xa0:      /* NBSP */
+#ifdef COMPILE_PCRE16
+            case 0x1680:    /* OGHAM SPACE MARK */
+            case 0x180e:    /* MONGOLIAN VOWEL SEPARATOR */
+            case 0x2000:    /* EN QUAD */
+            case 0x2001:    /* EM QUAD */
+            case 0x2002:    /* EN SPACE */
+            case 0x2003:    /* EM SPACE */
+            case 0x2004:    /* THREE-PER-EM SPACE */
+            case 0x2005:    /* FOUR-PER-EM SPACE */
+            case 0x2006:    /* SIX-PER-EM SPACE */
+            case 0x2007:    /* FIGURE SPACE */
+            case 0x2008:    /* PUNCTUATION SPACE */
+            case 0x2009:    /* THIN SPACE */
+            case 0x200A:    /* HAIR SPACE */
+            case 0x202f:    /* NARROW NO-BREAK SPACE */
+            case 0x205f:    /* MEDIUM MATHEMATICAL SPACE */
+            case 0x3000:    /* IDEOGRAPHIC SPACE */
+#endif
+            RRETURN(MATCH_NOMATCH);
+            }
+          }
+        break;
+
+        case OP_HSPACE:
+        for (i = 1; i <= min; i++)
+          {
+          if (eptr >= md->end_subject)
+            {
+            SCHECK_PARTIAL();
+            RRETURN(MATCH_NOMATCH);
+            }
+          switch(*eptr++)
+            {
+            default: RRETURN(MATCH_NOMATCH);
+            case 0x09:      /* HT */
+            case 0x20:      /* SPACE */
+            case 0xa0:      /* NBSP */
+#ifdef COMPILE_PCRE16
+            case 0x1680:    /* OGHAM SPACE MARK */
+            case 0x180e:    /* MONGOLIAN VOWEL SEPARATOR */
+            case 0x2000:    /* EN QUAD */
+            case 0x2001:    /* EM QUAD */
+            case 0x2002:    /* EN SPACE */
+            case 0x2003:    /* EM SPACE */
+            case 0x2004:    /* THREE-PER-EM SPACE */
+            case 0x2005:    /* FOUR-PER-EM SPACE */
+            case 0x2006:    /* SIX-PER-EM SPACE */
+            case 0x2007:    /* FIGURE SPACE */
+            case 0x2008:    /* PUNCTUATION SPACE */
+            case 0x2009:    /* THIN SPACE */
+            case 0x200A:    /* HAIR SPACE */
+            case 0x202f:    /* NARROW NO-BREAK SPACE */
+            case 0x205f:    /* MEDIUM MATHEMATICAL SPACE */
+            case 0x3000:    /* IDEOGRAPHIC SPACE */
+#endif
+            break;
+            }
+          }
+        break;
+
+        case OP_NOT_VSPACE:
+        for (i = 1; i <= min; i++)
+          {
+          if (eptr >= md->end_subject)
+            {
+            SCHECK_PARTIAL();
+            RRETURN(MATCH_NOMATCH);
+            }
+          switch(*eptr++)
+            {
+            default: break;
+            case 0x0a:      /* LF */
+            case 0x0b:      /* VT */
+            case 0x0c:      /* FF */
+            case 0x0d:      /* CR */
+            case 0x85:      /* NEL */
+#ifdef COMPILE_PCRE16
+            case 0x2028:    /* LINE SEPARATOR */
+            case 0x2029:    /* PARAGRAPH SEPARATOR */
+#endif
+            RRETURN(MATCH_NOMATCH);
+            }
+          }
+        break;
+
+        case OP_VSPACE:
+        for (i = 1; i <= min; i++)
+          {
+          if (eptr >= md->end_subject)
+            {
+            SCHECK_PARTIAL();
+            RRETURN(MATCH_NOMATCH);
+            }
+          switch(*eptr++)
+            {
+            default: RRETURN(MATCH_NOMATCH);
+            case 0x0a:      /* LF */
+            case 0x0b:      /* VT */
+            case 0x0c:      /* FF */
+            case 0x0d:      /* CR */
+            case 0x85:      /* NEL */
+#ifdef COMPILE_PCRE16
+            case 0x2028:    /* LINE SEPARATOR */
+            case 0x2029:    /* PARAGRAPH SEPARATOR */
+#endif
+            break;
+            }
+          }
+        break;
+
+        case OP_NOT_DIGIT:
+        for (i = 1; i <= min; i++)
+          {
+          if (eptr >= md->end_subject)
+            {
+            SCHECK_PARTIAL();
+            RRETURN(MATCH_NOMATCH);
+            }
+          if (MAX_255(*eptr) && (md->ctypes[*eptr] & ctype_digit) != 0)
+            RRETURN(MATCH_NOMATCH);
+          eptr++;
+          }
+        break;
+
+        case OP_DIGIT:
+        for (i = 1; i <= min; i++)
+          {
+          if (eptr >= md->end_subject)
+            {
+            SCHECK_PARTIAL();
+            RRETURN(MATCH_NOMATCH);
+            }
+          if (!MAX_255(*eptr) || (md->ctypes[*eptr] & ctype_digit) == 0)
+            RRETURN(MATCH_NOMATCH);
+          eptr++;
+          }
+        break;
+
+        case OP_NOT_WHITESPACE:
+        for (i = 1; i <= min; i++)
+          {
+          if (eptr >= md->end_subject)
+            {
+            SCHECK_PARTIAL();
+            RRETURN(MATCH_NOMATCH);
+            }
+          if (MAX_255(*eptr) && (md->ctypes[*eptr] & ctype_space) != 0)
+            RRETURN(MATCH_NOMATCH);
+          eptr++;
+          }
+        break;
+
+        case OP_WHITESPACE:
+        for (i = 1; i <= min; i++)
+          {
+          if (eptr >= md->end_subject)
+            {
+            SCHECK_PARTIAL();
+            RRETURN(MATCH_NOMATCH);
+            }
+          if (!MAX_255(*eptr) || (md->ctypes[*eptr] & ctype_space) == 0)
+            RRETURN(MATCH_NOMATCH);
+          eptr++;
+          }
+        break;
+
+        case OP_NOT_WORDCHAR:
+        for (i = 1; i <= min; i++)
+          {
+          if (eptr >= md->end_subject)
+            {
+            SCHECK_PARTIAL();
+            RRETURN(MATCH_NOMATCH);
+            }
+          if (MAX_255(*eptr) && (md->ctypes[*eptr] & ctype_word) != 0)
+            RRETURN(MATCH_NOMATCH);
+          eptr++;
+          }
+        break;
+
+        case OP_WORDCHAR:
+        for (i = 1; i <= min; i++)
+          {
+          if (eptr >= md->end_subject)
+            {
+            SCHECK_PARTIAL();
+            RRETURN(MATCH_NOMATCH);
+            }
+          if (!MAX_255(*eptr) || (md->ctypes[*eptr] & ctype_word) == 0)
+            RRETURN(MATCH_NOMATCH);
+          eptr++;
+          }
+        break;
+
+        default:
+        RRETURN(PCRE_ERROR_INTERNAL);
+        }
+      }
+
+    /* If min = max, continue at the same level without recursing */
+
+    if (min == max) continue;
+
+    /* If minimizing, we have to test the rest of the pattern before each
+    subsequent match. Again, separate the UTF-8 case for speed, and also
+    separate the UCP cases. */
+
+    if (minimize)
+      {
+#ifdef SUPPORT_UCP
+      if (prop_type >= 0)
+        {
+        switch(prop_type)
+          {
+          case PT_ANY:
+          for (fi = min;; fi++)
+            {
+            RMATCH(eptr, ecode, offset_top, md, eptrb, RM36);
+            if (rrc != MATCH_NOMATCH) RRETURN(rrc);
+            if (fi >= max) RRETURN(MATCH_NOMATCH);
+            if (eptr >= md->end_subject)
+              {
+              SCHECK_PARTIAL();
+              RRETURN(MATCH_NOMATCH);
+              }
+            GETCHARINCTEST(c, eptr);
+            if (prop_fail_result) RRETURN(MATCH_NOMATCH);
+            }
+          /* Control never gets here */
+
+          case PT_LAMP:
+          for (fi = min;; fi++)
+            {
+            int chartype;
+            RMATCH(eptr, ecode, offset_top, md, eptrb, RM37);
+            if (rrc != MATCH_NOMATCH) RRETURN(rrc);
+            if (fi >= max) RRETURN(MATCH_NOMATCH);
+            if (eptr >= md->end_subject)
+              {
+              SCHECK_PARTIAL();
+              RRETURN(MATCH_NOMATCH);
+              }
+            GETCHARINCTEST(c, eptr);
+            chartype = UCD_CHARTYPE(c);
+            if ((chartype == ucp_Lu ||
+                 chartype == ucp_Ll ||
+                 chartype == ucp_Lt) == prop_fail_result)
+              RRETURN(MATCH_NOMATCH);
+            }
+          /* Control never gets here */
+
+          case PT_GC:
+          for (fi = min;; fi++)
+            {
+            RMATCH(eptr, ecode, offset_top, md, eptrb, RM38);
+            if (rrc != MATCH_NOMATCH) RRETURN(rrc);
+            if (fi >= max) RRETURN(MATCH_NOMATCH);
+            if (eptr >= md->end_subject)
+              {
+              SCHECK_PARTIAL();
+              RRETURN(MATCH_NOMATCH);
+              }
+            GETCHARINCTEST(c, eptr);
+            if ((UCD_CATEGORY(c) == prop_value) == prop_fail_result)
+              RRETURN(MATCH_NOMATCH);
+            }
+          /* Control never gets here */
+
+          case PT_PC:
+          for (fi = min;; fi++)
+            {
+            RMATCH(eptr, ecode, offset_top, md, eptrb, RM39);
+            if (rrc != MATCH_NOMATCH) RRETURN(rrc);
+            if (fi >= max) RRETURN(MATCH_NOMATCH);
+            if (eptr >= md->end_subject)
+              {
+              SCHECK_PARTIAL();
+              RRETURN(MATCH_NOMATCH);
+              }
+            GETCHARINCTEST(c, eptr);
+            if ((UCD_CHARTYPE(c) == prop_value) == prop_fail_result)
+              RRETURN(MATCH_NOMATCH);
+            }
+          /* Control never gets here */
+
+          case PT_SC:
+          for (fi = min;; fi++)
+            {
+            RMATCH(eptr, ecode, offset_top, md, eptrb, RM40);
+            if (rrc != MATCH_NOMATCH) RRETURN(rrc);
+            if (fi >= max) RRETURN(MATCH_NOMATCH);
+            if (eptr >= md->end_subject)
+              {
+              SCHECK_PARTIAL();
+              RRETURN(MATCH_NOMATCH);
+              }
+            GETCHARINCTEST(c, eptr);
+            if ((UCD_SCRIPT(c) == prop_value) == prop_fail_result)
+              RRETURN(MATCH_NOMATCH);
+            }
+          /* Control never gets here */
+
+          case PT_ALNUM:
+          for (fi = min;; fi++)
+            {
+            int category;
+            RMATCH(eptr, ecode, offset_top, md, eptrb, RM59);
+            if (rrc != MATCH_NOMATCH) RRETURN(rrc);
+            if (fi >= max) RRETURN(MATCH_NOMATCH);
+            if (eptr >= md->end_subject)
+              {
+              SCHECK_PARTIAL();
+              RRETURN(MATCH_NOMATCH);
+              }
+            GETCHARINCTEST(c, eptr);
+            category = UCD_CATEGORY(c);
+            if ((category == ucp_L || category == ucp_N) == prop_fail_result)
+              RRETURN(MATCH_NOMATCH);
+            }
+          /* Control never gets here */
+
+          case PT_SPACE:    /* Perl space */
+          for (fi = min;; fi++)
+            {
+            RMATCH(eptr, ecode, offset_top, md, eptrb, RM60);
+            if (rrc != MATCH_NOMATCH) RRETURN(rrc);
+            if (fi >= max) RRETURN(MATCH_NOMATCH);
+            if (eptr >= md->end_subject)
+              {
+              SCHECK_PARTIAL();
+              RRETURN(MATCH_NOMATCH);
+              }
+            GETCHARINCTEST(c, eptr);
+            if ((UCD_CATEGORY(c) == ucp_Z || c == CHAR_HT || c == CHAR_NL ||
+                 c == CHAR_FF || c == CHAR_CR)
+                   == prop_fail_result)
+              RRETURN(MATCH_NOMATCH);
+            }
+          /* Control never gets here */
+
+          case PT_PXSPACE:  /* POSIX space */
+          for (fi = min;; fi++)
+            {
+            RMATCH(eptr, ecode, offset_top, md, eptrb, RM61);
+            if (rrc != MATCH_NOMATCH) RRETURN(rrc);
+            if (fi >= max) RRETURN(MATCH_NOMATCH);
+            if (eptr >= md->end_subject)
+              {
+              SCHECK_PARTIAL();
+              RRETURN(MATCH_NOMATCH);
+              }
+            GETCHARINCTEST(c, eptr);
+            if ((UCD_CATEGORY(c) == ucp_Z || c == CHAR_HT || c == CHAR_NL ||
+                 c == CHAR_VT || c == CHAR_FF || c == CHAR_CR)
+                   == prop_fail_result)
+              RRETURN(MATCH_NOMATCH);
+            }
+          /* Control never gets here */
+
+          case PT_WORD:
+          for (fi = min;; fi++)
+            {
+            int category;
+            RMATCH(eptr, ecode, offset_top, md, eptrb, RM62);
+            if (rrc != MATCH_NOMATCH) RRETURN(rrc);
+            if (fi >= max) RRETURN(MATCH_NOMATCH);
+            if (eptr >= md->end_subject)
+              {
+              SCHECK_PARTIAL();
+              RRETURN(MATCH_NOMATCH);
+              }
+            GETCHARINCTEST(c, eptr);
+            category = UCD_CATEGORY(c);
+            if ((category == ucp_L ||
+                 category == ucp_N ||
+                 c == CHAR_UNDERSCORE)
+                   == prop_fail_result)
+              RRETURN(MATCH_NOMATCH);
+            }
+          /* Control never gets here */
+
+          /* This should never occur */
+
+          default:
+          RRETURN(PCRE_ERROR_INTERNAL);
+          }
+        }
+
+      /* Match extended Unicode sequences. We will get here only if the
+      support is in the binary; otherwise a compile-time error occurs. */
+
+      else if (ctype == OP_EXTUNI)
+        {
+        for (fi = min;; fi++)
+          {
+          RMATCH(eptr, ecode, offset_top, md, eptrb, RM41);
+          if (rrc != MATCH_NOMATCH) RRETURN(rrc);
+          if (fi >= max) RRETURN(MATCH_NOMATCH);
+          if (eptr >= md->end_subject)
+            {
+            SCHECK_PARTIAL();
+            RRETURN(MATCH_NOMATCH);
+            }
+          GETCHARINCTEST(c, eptr);
+          if (UCD_CATEGORY(c) == ucp_M) RRETURN(MATCH_NOMATCH);
+          while (eptr < md->end_subject)
+            {
+            int len = 1;
+            if (!utf) c = *eptr; else { GETCHARLEN(c, eptr, len); }
+            if (UCD_CATEGORY(c) != ucp_M) break;
+            eptr += len;
+            }
+          CHECK_PARTIAL();
+          }
+        }
+      else
+#endif     /* SUPPORT_UCP */
+
+#ifdef SUPPORT_UTF
+      if (utf)
+        {
+        for (fi = min;; fi++)
+          {
+          RMATCH(eptr, ecode, offset_top, md, eptrb, RM42);
+          if (rrc != MATCH_NOMATCH) RRETURN(rrc);
+          if (fi >= max) RRETURN(MATCH_NOMATCH);
+          if (eptr >= md->end_subject)
+            {
+            SCHECK_PARTIAL();
+            RRETURN(MATCH_NOMATCH);
+            }
+          if (ctype == OP_ANY && IS_NEWLINE(eptr))
+            RRETURN(MATCH_NOMATCH);
+          GETCHARINC(c, eptr);
+          switch(ctype)
+            {
+            case OP_ANY:               /* This is the non-NL case */
+            if (md->partial != 0 &&    /* Take care with CRLF partial */
+                eptr >= md->end_subject &&
+                NLBLOCK->nltype == NLTYPE_FIXED &&
+                NLBLOCK->nllen == 2 &&
+                c == NLBLOCK->nl[0])
+              {
+              md->hitend = TRUE;
+              if (md->partial > 1) RRETURN(PCRE_ERROR_PARTIAL);
+              }
+            break;
+
+            case OP_ALLANY:
+            case OP_ANYBYTE:
+            break;
+
+            case OP_ANYNL:
+            switch(c)
+              {
+              default: RRETURN(MATCH_NOMATCH);
+              case 0x000d:
+              if (eptr < md->end_subject && *eptr == 0x0a) eptr++;
+              break;
+              case 0x000a:
+              break;
+
+              case 0x000b:
+              case 0x000c:
+              case 0x0085:
+              case 0x2028:
+              case 0x2029:
+              if (md->bsr_anycrlf) RRETURN(MATCH_NOMATCH);
+              break;
+              }
+            break;
+
+            case OP_NOT_HSPACE:
+            switch(c)
+              {
+              default: break;
+              case 0x09:      /* HT */
+              case 0x20:      /* SPACE */
+              case 0xa0:      /* NBSP */
+              case 0x1680:    /* OGHAM SPACE MARK */
+              case 0x180e:    /* MONGOLIAN VOWEL SEPARATOR */
+              case 0x2000:    /* EN QUAD */
+              case 0x2001:    /* EM QUAD */
+              case 0x2002:    /* EN SPACE */
+              case 0x2003:    /* EM SPACE */
+              case 0x2004:    /* THREE-PER-EM SPACE */
+              case 0x2005:    /* FOUR-PER-EM SPACE */
+              case 0x2006:    /* SIX-PER-EM SPACE */
+              case 0x2007:    /* FIGURE SPACE */
+              case 0x2008:    /* PUNCTUATION SPACE */
+              case 0x2009:    /* THIN SPACE */
+              case 0x200A:    /* HAIR SPACE */
+              case 0x202f:    /* NARROW NO-BREAK SPACE */
+              case 0x205f:    /* MEDIUM MATHEMATICAL SPACE */
+              case 0x3000:    /* IDEOGRAPHIC SPACE */
+              RRETURN(MATCH_NOMATCH);
+              }
+            break;
+
+            case OP_HSPACE:
+            switch(c)
+              {
+              default: RRETURN(MATCH_NOMATCH);
+              case 0x09:      /* HT */
+              case 0x20:      /* SPACE */
+              case 0xa0:      /* NBSP */
+              case 0x1680:    /* OGHAM SPACE MARK */
+              case 0x180e:    /* MONGOLIAN VOWEL SEPARATOR */
+              case 0x2000:    /* EN QUAD */
+              case 0x2001:    /* EM QUAD */
+              case 0x2002:    /* EN SPACE */
+              case 0x2003:    /* EM SPACE */
+              case 0x2004:    /* THREE-PER-EM SPACE */
+              case 0x2005:    /* FOUR-PER-EM SPACE */
+              case 0x2006:    /* SIX-PER-EM SPACE */
+              case 0x2007:    /* FIGURE SPACE */
+              case 0x2008:    /* PUNCTUATION SPACE */
+              case 0x2009:    /* THIN SPACE */
+              case 0x200A:    /* HAIR SPACE */
+              case 0x202f:    /* NARROW NO-BREAK SPACE */
+              case 0x205f:    /* MEDIUM MATHEMATICAL SPACE */
+              case 0x3000:    /* IDEOGRAPHIC SPACE */
+              break;
+              }
+            break;
+
+            case OP_NOT_VSPACE:
+            switch(c)
+              {
+              default: break;
+              case 0x0a:      /* LF */
+              case 0x0b:      /* VT */
+              case 0x0c:      /* FF */
+              case 0x0d:      /* CR */
+              case 0x85:      /* NEL */
+              case 0x2028:    /* LINE SEPARATOR */
+              case 0x2029:    /* PARAGRAPH SEPARATOR */
+              RRETURN(MATCH_NOMATCH);
+              }
+            break;
+
+            case OP_VSPACE:
+            switch(c)
+              {
+              default: RRETURN(MATCH_NOMATCH);
+              case 0x0a:      /* LF */
+              case 0x0b:      /* VT */
+              case 0x0c:      /* FF */
+              case 0x0d:      /* CR */
+              case 0x85:      /* NEL */
+              case 0x2028:    /* LINE SEPARATOR */
+              case 0x2029:    /* PARAGRAPH SEPARATOR */
+              break;
+              }
+            break;
+
+            case OP_NOT_DIGIT:
+            if (c < 256 && (md->ctypes[c] & ctype_digit) != 0)
+              RRETURN(MATCH_NOMATCH);
+            break;
+
+            case OP_DIGIT:
+            if (c >= 256 || (md->ctypes[c] & ctype_digit) == 0)
+              RRETURN(MATCH_NOMATCH);
+            break;
+
+            case OP_NOT_WHITESPACE:
+            if (c < 256 && (md->ctypes[c] & ctype_space) != 0)
+              RRETURN(MATCH_NOMATCH);
+            break;
+
+            case OP_WHITESPACE:
+            if (c >= 256 || (md->ctypes[c] & ctype_space) == 0)
+              RRETURN(MATCH_NOMATCH);
+            break;
+
+            case OP_NOT_WORDCHAR:
+            if (c < 256 && (md->ctypes[c] & ctype_word) != 0)
+              RRETURN(MATCH_NOMATCH);
+            break;
+
+            case OP_WORDCHAR:
+            if (c >= 256 || (md->ctypes[c] & ctype_word) == 0)
+              RRETURN(MATCH_NOMATCH);
+            break;
+
+            default:
+            RRETURN(PCRE_ERROR_INTERNAL);
+            }
+          }
+        }
+      else
+#endif
+      /* Not UTF mode */
+        {
+        for (fi = min;; fi++)
+          {
+          RMATCH(eptr, ecode, offset_top, md, eptrb, RM43);
+          if (rrc != MATCH_NOMATCH) RRETURN(rrc);
+          if (fi >= max) RRETURN(MATCH_NOMATCH);
+          if (eptr >= md->end_subject)
+            {
+            SCHECK_PARTIAL();
+            RRETURN(MATCH_NOMATCH);
+            }
+          if (ctype == OP_ANY && IS_NEWLINE(eptr))
+            RRETURN(MATCH_NOMATCH);
+          c = *eptr++;
+          switch(ctype)
+            {
+            case OP_ANY:               /* This is the non-NL case */
+            if (md->partial != 0 &&    /* Take care with CRLF partial */
+                eptr >= md->end_subject &&
+                NLBLOCK->nltype == NLTYPE_FIXED &&
+                NLBLOCK->nllen == 2 &&
+                c == NLBLOCK->nl[0])
+              {
+              md->hitend = TRUE;
+              if (md->partial > 1) RRETURN(PCRE_ERROR_PARTIAL);
+              }
+            break;
+
+            case OP_ALLANY:
+            case OP_ANYBYTE:
+            break;
+
+            case OP_ANYNL:
+            switch(c)
+              {
+              default: RRETURN(MATCH_NOMATCH);
+              case 0x000d:
+              if (eptr < md->end_subject && *eptr == 0x0a) eptr++;
+              break;
+
+              case 0x000a:
+              break;
+
+              case 0x000b:
+              case 0x000c:
+              case 0x0085:
+#ifdef COMPILE_PCRE16
+              case 0x2028:
+              case 0x2029:
+#endif
+              if (md->bsr_anycrlf) RRETURN(MATCH_NOMATCH);
+              break;
+              }
+            break;
+
+            case OP_NOT_HSPACE:
+            switch(c)
+              {
+              default: break;
+              case 0x09:      /* HT */
+              case 0x20:      /* SPACE */
+              case 0xa0:      /* NBSP */
+#ifdef COMPILE_PCRE16
+              case 0x1680:    /* OGHAM SPACE MARK */
+              case 0x180e:    /* MONGOLIAN VOWEL SEPARATOR */
+              case 0x2000:    /* EN QUAD */
+              case 0x2001:    /* EM QUAD */
+              case 0x2002:    /* EN SPACE */
+              case 0x2003:    /* EM SPACE */
+              case 0x2004:    /* THREE-PER-EM SPACE */
+              case 0x2005:    /* FOUR-PER-EM SPACE */
+              case 0x2006:    /* SIX-PER-EM SPACE */
+              case 0x2007:    /* FIGURE SPACE */
+              case 0x2008:    /* PUNCTUATION SPACE */
+              case 0x2009:    /* THIN SPACE */
+              case 0x200A:    /* HAIR SPACE */
+              case 0x202f:    /* NARROW NO-BREAK SPACE */
+              case 0x205f:    /* MEDIUM MATHEMATICAL SPACE */
+              case 0x3000:    /* IDEOGRAPHIC SPACE */
+#endif
+              RRETURN(MATCH_NOMATCH);
+              }
+            break;
+
+            case OP_HSPACE:
+            switch(c)
+              {
+              default: RRETURN(MATCH_NOMATCH);
+              case 0x09:      /* HT */
+              case 0x20:      /* SPACE */
+              case 0xa0:      /* NBSP */
+#ifdef COMPILE_PCRE16
+              case 0x1680:    /* OGHAM SPACE MARK */
+              case 0x180e:    /* MONGOLIAN VOWEL SEPARATOR */
+              case 0x2000:    /* EN QUAD */
+              case 0x2001:    /* EM QUAD */
+              case 0x2002:    /* EN SPACE */
+              case 0x2003:    /* EM SPACE */
+              case 0x2004:    /* THREE-PER-EM SPACE */
+              case 0x2005:    /* FOUR-PER-EM SPACE */
+              case 0x2006:    /* SIX-PER-EM SPACE */
+              case 0x2007:    /* FIGURE SPACE */
+              case 0x2008:    /* PUNCTUATION SPACE */
+              case 0x2009:    /* THIN SPACE */
+              case 0x200A:    /* HAIR SPACE */
+              case 0x202f:    /* NARROW NO-BREAK SPACE */
+              case 0x205f:    /* MEDIUM MATHEMATICAL SPACE */
+              case 0x3000:    /* IDEOGRAPHIC SPACE */
+#endif
+              break;
+              }
+            break;
+
+            case OP_NOT_VSPACE:
+            switch(c)
+              {
+              default: break;
+              case 0x0a:      /* LF */
+              case 0x0b:      /* VT */
+              case 0x0c:      /* FF */
+              case 0x0d:      /* CR */
+              case 0x85:      /* NEL */
+#ifdef COMPILE_PCRE16
+              case 0x2028:    /* LINE SEPARATOR */
+              case 0x2029:    /* PARAGRAPH SEPARATOR */
+#endif
+              RRETURN(MATCH_NOMATCH);
+              }
+            break;
+
+            case OP_VSPACE:
+            switch(c)
+              {
+              default: RRETURN(MATCH_NOMATCH);
+              case 0x0a:      /* LF */
+              case 0x0b:      /* VT */
+              case 0x0c:      /* FF */
+              case 0x0d:      /* CR */
+              case 0x85:      /* NEL */
+#ifdef COMPILE_PCRE16
+              case 0x2028:    /* LINE SEPARATOR */
+              case 0x2029:    /* PARAGRAPH SEPARATOR */
+#endif
+              break;
+              }
+            break;
+
+            case OP_NOT_DIGIT:
+            if (MAX_255(c) && (md->ctypes[c] & ctype_digit) != 0) RRETURN(MATCH_NOMATCH);
+            break;
+
+            case OP_DIGIT:
+            if (!MAX_255(c) || (md->ctypes[c] & ctype_digit) == 0) RRETURN(MATCH_NOMATCH);
+            break;
+
+            case OP_NOT_WHITESPACE:
+            if (MAX_255(c) && (md->ctypes[c] & ctype_space) != 0) RRETURN(MATCH_NOMATCH);
+            break;
+
+            case OP_WHITESPACE:
+            if (!MAX_255(c) || (md->ctypes[c] & ctype_space) == 0) RRETURN(MATCH_NOMATCH);
+            break;
+
+            case OP_NOT_WORDCHAR:
+            if (MAX_255(c) && (md->ctypes[c] & ctype_word) != 0) RRETURN(MATCH_NOMATCH);
+            break;
+
+            case OP_WORDCHAR:
+            if (!MAX_255(c) || (md->ctypes[c] & ctype_word) == 0) RRETURN(MATCH_NOMATCH);
+            break;
+
+            default:
+            RRETURN(PCRE_ERROR_INTERNAL);
+            }
+          }
+        }
+      /* Control never gets here */
+      }
+
+    /* If maximizing, it is worth using inline code for speed, doing the type
+    test once at the start (i.e. keep it out of the loop). Again, keep the
+    UTF-8 and UCP stuff separate. */
+
+    else
+      {
+      pp = eptr;  /* Remember where we started */
+
+#ifdef SUPPORT_UCP
+      if (prop_type >= 0)
+        {
+        switch(prop_type)
+          {
+          case PT_ANY:
+          for (i = min; i < max; i++)
+            {
+            int len = 1;
+            if (eptr >= md->end_subject)
+              {
+              SCHECK_PARTIAL();
+              break;
+              }
+            GETCHARLENTEST(c, eptr, len);
+            if (prop_fail_result) break;
+            eptr+= len;
+            }
+          break;
+
+          case PT_LAMP:
+          for (i = min; i < max; i++)
+            {
+            int chartype;
+            int len = 1;
+            if (eptr >= md->end_subject)
+              {
+              SCHECK_PARTIAL();
+              break;
+              }
+            GETCHARLENTEST(c, eptr, len);
+            chartype = UCD_CHARTYPE(c);
+            if ((chartype == ucp_Lu ||
+                 chartype == ucp_Ll ||
+                 chartype == ucp_Lt) == prop_fail_result)
+              break;
+            eptr+= len;
+            }
+          break;
+
+          case PT_GC:
+          for (i = min; i < max; i++)
+            {
+            int len = 1;
+            if (eptr >= md->end_subject)
+              {
+              SCHECK_PARTIAL();
+              break;
+              }
+            GETCHARLENTEST(c, eptr, len);
+            if ((UCD_CATEGORY(c) == prop_value) == prop_fail_result) break;
+            eptr+= len;
+            }
+          break;
+
+          case PT_PC:
+          for (i = min; i < max; i++)
+            {
+            int len = 1;
+            if (eptr >= md->end_subject)
+              {
+              SCHECK_PARTIAL();
+              break;
+              }
+            GETCHARLENTEST(c, eptr, len);
+            if ((UCD_CHARTYPE(c) == prop_value) == prop_fail_result) break;
+            eptr+= len;
+            }
+          break;
+
+          case PT_SC:
+          for (i = min; i < max; i++)
+            {
+            int len = 1;
+            if (eptr >= md->end_subject)
+              {
+              SCHECK_PARTIAL();
+              break;
+              }
+            GETCHARLENTEST(c, eptr, len);
+            if ((UCD_SCRIPT(c) == prop_value) == prop_fail_result) break;
+            eptr+= len;
+            }
+          break;
+
+          case PT_ALNUM:
+          for (i = min; i < max; i++)
+            {
+            int category;
+            int len = 1;
+            if (eptr >= md->end_subject)
+              {
+              SCHECK_PARTIAL();
+              break;
+              }
+            GETCHARLENTEST(c, eptr, len);
+            category = UCD_CATEGORY(c);
+            if ((category == ucp_L || category == ucp_N) == prop_fail_result)
+              break;
+            eptr+= len;
+            }
+          break;
+
+          case PT_SPACE:    /* Perl space */
+          for (i = min; i < max; i++)
+            {
+            int len = 1;
+            if (eptr >= md->end_subject)
+              {
+              SCHECK_PARTIAL();
+              break;
+              }
+            GETCHARLENTEST(c, eptr, len);
+            if ((UCD_CATEGORY(c) == ucp_Z || c == CHAR_HT || c == CHAR_NL ||
+                 c == CHAR_FF || c == CHAR_CR)
+                 == prop_fail_result)
+              break;
+            eptr+= len;
+            }
+          break;
+
+          case PT_PXSPACE:  /* POSIX space */
+          for (i = min; i < max; i++)
+            {
+            int len = 1;
+            if (eptr >= md->end_subject)
+              {
+              SCHECK_PARTIAL();
+              break;
+              }
+            GETCHARLENTEST(c, eptr, len);
+            if ((UCD_CATEGORY(c) == ucp_Z || c == CHAR_HT || c == CHAR_NL ||
+                 c == CHAR_VT || c == CHAR_FF || c == CHAR_CR)
+                 == prop_fail_result)
+              break;
+            eptr+= len;
+            }
+          break;
+
+          case PT_WORD:
+          for (i = min; i < max; i++)
+            {
+            int category;
+            int len = 1;
+            if (eptr >= md->end_subject)
+              {
+              SCHECK_PARTIAL();
+              break;
+              }
+            GETCHARLENTEST(c, eptr, len);
+            category = UCD_CATEGORY(c);
+            if ((category == ucp_L || category == ucp_N ||
+                 c == CHAR_UNDERSCORE) == prop_fail_result)
+              break;
+            eptr+= len;
+            }
+          break;
+
+          default:
+          RRETURN(PCRE_ERROR_INTERNAL);
+          }
+
+        /* eptr is now past the end of the maximum run */
+
+        if (possessive) continue;
+        for(;;)
+          {
+          RMATCH(eptr, ecode, offset_top, md, eptrb, RM44);
+          if (rrc != MATCH_NOMATCH) RRETURN(rrc);
+          if (eptr-- == pp) break;        /* Stop if tried at original pos */
+          if (utf) BACKCHAR(eptr);
+          }
+        }
+
+      /* Match extended Unicode sequences. We will get here only if the
+      support is in the binary; otherwise a compile-time error occurs. */
+
+      else if (ctype == OP_EXTUNI)
+        {
+        for (i = min; i < max; i++)
+          {
+          int len = 1;
+          if (eptr >= md->end_subject)
+            {
+            SCHECK_PARTIAL();
+            break;
+            }
+          if (!utf) c = *eptr; else { GETCHARLEN(c, eptr, len); }
+          if (UCD_CATEGORY(c) == ucp_M) break;
+          eptr += len;
+          while (eptr < md->end_subject)
+            {
+            len = 1;
+            if (!utf) c = *eptr; else { GETCHARLEN(c, eptr, len); }
+            if (UCD_CATEGORY(c) != ucp_M) break;
+            eptr += len;
+            }
+          CHECK_PARTIAL();
+          }
+
+        /* eptr is now past the end of the maximum run */
+
+        if (possessive) continue;
+
+        for(;;)
+          {
+          RMATCH(eptr, ecode, offset_top, md, eptrb, RM45);
+          if (rrc != MATCH_NOMATCH) RRETURN(rrc);
+          if (eptr-- == pp) break;        /* Stop if tried at original pos */
+          for (;;)                        /* Move back over one extended */
+            {
+            if (!utf) c = *eptr; else
+              {
+              BACKCHAR(eptr);
+              GETCHAR(c, eptr);
+              }
+            if (UCD_CATEGORY(c) != ucp_M) break;
+            eptr--;
+            }
+          }
+        }
+
+      else
+#endif   /* SUPPORT_UCP */
+
+#ifdef SUPPORT_UTF
+      if (utf)
+        {
+        switch(ctype)
+          {
+          case OP_ANY:
+          if (max < INT_MAX)
+            {
+            for (i = min; i < max; i++)
+              {
+              if (eptr >= md->end_subject)
+                {
+                SCHECK_PARTIAL();
+                break;
+                }
+              if (IS_NEWLINE(eptr)) break;
+              if (md->partial != 0 &&    /* Take care with CRLF partial */
+                  eptr + 1 >= md->end_subject &&
+                  NLBLOCK->nltype == NLTYPE_FIXED &&
+                  NLBLOCK->nllen == 2 &&
+                  *eptr == NLBLOCK->nl[0])
+                {
+                md->hitend = TRUE;
+                if (md->partial > 1) RRETURN(PCRE_ERROR_PARTIAL);
+                }
+              eptr++;
+              ACROSSCHAR(eptr < md->end_subject, *eptr, eptr++);
+              }
+            }
+
+          /* Handle unlimited UTF-8 repeat */
+
+          else
+            {
+            for (i = min; i < max; i++)
+              {
+              if (eptr >= md->end_subject)
+                {
+                SCHECK_PARTIAL();
+                break;
+                }
+              if (IS_NEWLINE(eptr)) break;
+              if (md->partial != 0 &&    /* Take care with CRLF partial */
+                  eptr + 1 >= md->end_subject &&
+                  NLBLOCK->nltype == NLTYPE_FIXED &&
+                  NLBLOCK->nllen == 2 &&
+                  *eptr == NLBLOCK->nl[0])
+                {
+                md->hitend = TRUE;
+                if (md->partial > 1) RRETURN(PCRE_ERROR_PARTIAL);
+                }
+              eptr++;
+              ACROSSCHAR(eptr < md->end_subject, *eptr, eptr++);
+              }
+            }
+          break;
+
+          case OP_ALLANY:
+          if (max < INT_MAX)
+            {
+            for (i = min; i < max; i++)
+              {
+              if (eptr >= md->end_subject)
+                {
+                SCHECK_PARTIAL();
+                break;
+                }
+              eptr++;
+              ACROSSCHAR(eptr < md->end_subject, *eptr, eptr++);
+              }
+            }
+          else
+            {
+            eptr = md->end_subject;   /* Unlimited UTF-8 repeat */
+            SCHECK_PARTIAL();
+            }
+          break;
+
+          /* The byte case is the same as non-UTF8 */
+
+          case OP_ANYBYTE:
+          c = max - min;
+          if (c > (unsigned int)(md->end_subject - eptr))
+            {
+            eptr = md->end_subject;
+            SCHECK_PARTIAL();
+            }
+          else eptr += c;
+          break;
+
+          case OP_ANYNL:
+          for (i = min; i < max; i++)
+            {
+            int len = 1;
+            if (eptr >= md->end_subject)
+              {
+              SCHECK_PARTIAL();
+              break;
+              }
+            GETCHARLEN(c, eptr, len);
+            if (c == 0x000d)
+              {
+              if (++eptr >= md->end_subject) break;
+              if (*eptr == 0x000a) eptr++;
+              }
+            else
+              {
+              if (c != 0x000a &&
+                  (md->bsr_anycrlf ||
+                   (c != 0x000b && c != 0x000c &&
+                    c != 0x0085 && c != 0x2028 && c != 0x2029)))
+                break;
+              eptr += len;
+              }
+            }
+          break;
+
+          case OP_NOT_HSPACE:
+          case OP_HSPACE:
+          for (i = min; i < max; i++)
+            {
+            BOOL gotspace;
+            int len = 1;
+            if (eptr >= md->end_subject)
+              {
+              SCHECK_PARTIAL();
+              break;
+              }
+            GETCHARLEN(c, eptr, len);
+            switch(c)
+              {
+              default: gotspace = FALSE; break;
+              case 0x09:      /* HT */
+              case 0x20:      /* SPACE */
+              case 0xa0:      /* NBSP */
+              case 0x1680:    /* OGHAM SPACE MARK */
+              case 0x180e:    /* MONGOLIAN VOWEL SEPARATOR */
+              case 0x2000:    /* EN QUAD */
+              case 0x2001:    /* EM QUAD */
+              case 0x2002:    /* EN SPACE */
+              case 0x2003:    /* EM SPACE */
+              case 0x2004:    /* THREE-PER-EM SPACE */
+              case 0x2005:    /* FOUR-PER-EM SPACE */
+              case 0x2006:    /* SIX-PER-EM SPACE */
+              case 0x2007:    /* FIGURE SPACE */
+              case 0x2008:    /* PUNCTUATION SPACE */
+              case 0x2009:    /* THIN SPACE */
+              case 0x200A:    /* HAIR SPACE */
+              case 0x202f:    /* NARROW NO-BREAK SPACE */
+              case 0x205f:    /* MEDIUM MATHEMATICAL SPACE */
+              case 0x3000:    /* IDEOGRAPHIC SPACE */
+              gotspace = TRUE;
+              break;
+              }
+            if (gotspace == (ctype == OP_NOT_HSPACE)) break;
+            eptr += len;
+            }
+          break;
+
+          case OP_NOT_VSPACE:
+          case OP_VSPACE:
+          for (i = min; i < max; i++)
+            {
+            BOOL gotspace;
+            int len = 1;
+            if (eptr >= md->end_subject)
+              {
+              SCHECK_PARTIAL();
+              break;
+              }
+            GETCHARLEN(c, eptr, len);
+            switch(c)
+              {
+              default: gotspace = FALSE; break;
+              case 0x0a:      /* LF */
+              case 0x0b:      /* VT */
+              case 0x0c:      /* FF */
+              case 0x0d:      /* CR */
+              case 0x85:      /* NEL */
+              case 0x2028:    /* LINE SEPARATOR */
+              case 0x2029:    /* PARAGRAPH SEPARATOR */
+              gotspace = TRUE;
+              break;
+              }
+            if (gotspace == (ctype == OP_NOT_VSPACE)) break;
+            eptr += len;
+            }
+          break;
+
+          case OP_NOT_DIGIT:
+          for (i = min; i < max; i++)
+            {
+            int len = 1;
+            if (eptr >= md->end_subject)
+              {
+              SCHECK_PARTIAL();
+              break;
+              }
+            GETCHARLEN(c, eptr, len);
+            if (c < 256 && (md->ctypes[c] & ctype_digit) != 0) break;
+            eptr+= len;
+            }
+          break;
+
+          case OP_DIGIT:
+          for (i = min; i < max; i++)
+            {
+            int len = 1;
+            if (eptr >= md->end_subject)
+              {
+              SCHECK_PARTIAL();
+              break;
+              }
+            GETCHARLEN(c, eptr, len);
+            if (c >= 256 ||(md->ctypes[c] & ctype_digit) == 0) break;
+            eptr+= len;
+            }
+          break;
+
+          case OP_NOT_WHITESPACE:
+          for (i = min; i < max; i++)
+            {
+            int len = 1;
+            if (eptr >= md->end_subject)
+              {
+              SCHECK_PARTIAL();
+              break;
+              }
+            GETCHARLEN(c, eptr, len);
+            if (c < 256 && (md->ctypes[c] & ctype_space) != 0) break;
+            eptr+= len;
+            }
+          break;
+
+          case OP_WHITESPACE:
+          for (i = min; i < max; i++)
+            {
+            int len = 1;
+            if (eptr >= md->end_subject)
+              {
+              SCHECK_PARTIAL();
+              break;
+              }
+            GETCHARLEN(c, eptr, len);
+            if (c >= 256 ||(md->ctypes[c] & ctype_space) == 0) break;
+            eptr+= len;
+            }
+          break;
+
+          case OP_NOT_WORDCHAR:
+          for (i = min; i < max; i++)
+            {
+            int len = 1;
+            if (eptr >= md->end_subject)
+              {
+              SCHECK_PARTIAL();
+              break;
+              }
+            GETCHARLEN(c, eptr, len);
+            if (c < 256 && (md->ctypes[c] & ctype_word) != 0) break;
+            eptr+= len;
+            }
+          break;
+
+          case OP_WORDCHAR:
+          for (i = min; i < max; i++)
+            {
+            int len = 1;
+            if (eptr >= md->end_subject)
+              {
+              SCHECK_PARTIAL();
+              break;
+              }
+            GETCHARLEN(c, eptr, len);
+            if (c >= 256 || (md->ctypes[c] & ctype_word) == 0) break;
+            eptr+= len;
+            }
+          break;
+
+          default:
+          RRETURN(PCRE_ERROR_INTERNAL);
+          }
+
+        /* eptr is now past the end of the maximum run. If possessive, we are
+        done (no backing up). Otherwise, match at this position; anything other
+        than no match is immediately returned. For nomatch, back up one
+        character, unless we are matching \R and the last thing matched was
+        \r\n, in which case, back up two bytes. */
+
+        if (possessive) continue;
+        for(;;)
+          {
+          RMATCH(eptr, ecode, offset_top, md, eptrb, RM46);
+          if (rrc != MATCH_NOMATCH) RRETURN(rrc);
+          if (eptr-- == pp) break;        /* Stop if tried at original pos */
+          BACKCHAR(eptr);
+          if (ctype == OP_ANYNL && eptr > pp  && *eptr == '\n' &&
+              eptr[-1] == '\r') eptr--;
+          }
+        }
+      else
+#endif  /* SUPPORT_UTF */
+      /* Not UTF mode */
+        {
+        switch(ctype)
+          {
+          case OP_ANY:
+          for (i = min; i < max; i++)
+            {
+            if (eptr >= md->end_subject)
+              {
+              SCHECK_PARTIAL();
+              break;
+              }
+            if (IS_NEWLINE(eptr)) break;
+            if (md->partial != 0 &&    /* Take care with CRLF partial */
+                eptr + 1 >= md->end_subject &&
+                NLBLOCK->nltype == NLTYPE_FIXED &&
+                NLBLOCK->nllen == 2 &&
+                *eptr == NLBLOCK->nl[0])
+              {
+              md->hitend = TRUE;
+              if (md->partial > 1) RRETURN(PCRE_ERROR_PARTIAL);
+              }
+            eptr++;
+            }
+          break;
+
+          case OP_ALLANY:
+          case OP_ANYBYTE:
+          c = max - min;
+          if (c > (unsigned int)(md->end_subject - eptr))
+            {
+            eptr = md->end_subject;
+            SCHECK_PARTIAL();
+            }
+          else eptr += c;
+          break;
+
+          case OP_ANYNL:
+          for (i = min; i < max; i++)
+            {
+            if (eptr >= md->end_subject)
+              {
+              SCHECK_PARTIAL();
+              break;
+              }
+            c = *eptr;
+            if (c == 0x000d)
+              {
+              if (++eptr >= md->end_subject) break;
+              if (*eptr == 0x000a) eptr++;
+              }
+            else
+              {
+              if (c != 0x000a && (md->bsr_anycrlf ||
+                (c != 0x000b && c != 0x000c && c != 0x0085
+#ifdef COMPILE_PCRE16
+                && c != 0x2028 && c != 0x2029
+#endif
+                ))) break;
+              eptr++;
+              }
+            }
+          break;
+
+          case OP_NOT_HSPACE:
+          for (i = min; i < max; i++)
+            {
+            if (eptr >= md->end_subject)
+              {
+              SCHECK_PARTIAL();
+              break;
+              }
+            c = *eptr;
+            if (c == 0x09 || c == 0x20 || c == 0xa0
+#ifdef COMPILE_PCRE16
+              || c == 0x1680 || c == 0x180e || (c >= 0x2000 && c <= 0x200A)
+              || c == 0x202f || c == 0x205f || c == 0x3000
+#endif
+              ) break;
+            eptr++;
+            }
+          break;
+
+          case OP_HSPACE:
+          for (i = min; i < max; i++)
+            {
+            if (eptr >= md->end_subject)
+              {
+              SCHECK_PARTIAL();
+              break;
+              }
+            c = *eptr;
+            if (c != 0x09 && c != 0x20 && c != 0xa0
+#ifdef COMPILE_PCRE16
+              && c != 0x1680 && c != 0x180e && (c < 0x2000 || c > 0x200A)
+              && c != 0x202f && c != 0x205f && c != 0x3000
+#endif
+              ) break;
+            eptr++;
+            }
+          break;
+
+          case OP_NOT_VSPACE:
+          for (i = min; i < max; i++)
+            {
+            if (eptr >= md->end_subject)
+              {
+              SCHECK_PARTIAL();
+              break;
+              }
+            c = *eptr;
+            if (c == 0x0a || c == 0x0b || c == 0x0c || c == 0x0d || c == 0x85
+#ifdef COMPILE_PCRE16
+              || c == 0x2028 || c == 0x2029
+#endif
+              ) break;
+            eptr++;
+            }
+          break;
+
+          case OP_VSPACE:
+          for (i = min; i < max; i++)
+            {
+            if (eptr >= md->end_subject)
+              {
+              SCHECK_PARTIAL();
+              break;
+              }
+            c = *eptr;
+            if (c != 0x0a && c != 0x0b && c != 0x0c && c != 0x0d && c != 0x85
+#ifdef COMPILE_PCRE16
+              && c != 0x2028 && c != 0x2029
+#endif
+              ) break;
+            eptr++;
+            }
+          break;
+
+          case OP_NOT_DIGIT:
+          for (i = min; i < max; i++)
+            {
+            if (eptr >= md->end_subject)
+              {
+              SCHECK_PARTIAL();
+              break;
+              }
+            if (MAX_255(*eptr) && (md->ctypes[*eptr] & ctype_digit) != 0) break;
+            eptr++;
+            }
+          break;
+
+          case OP_DIGIT:
+          for (i = min; i < max; i++)
+            {
+            if (eptr >= md->end_subject)
+              {
+              SCHECK_PARTIAL();
+              break;
+              }
+            if (!MAX_255(*eptr) || (md->ctypes[*eptr] & ctype_digit) == 0) break;
+            eptr++;
+            }
+          break;
+
+          case OP_NOT_WHITESPACE:
+          for (i = min; i < max; i++)
+            {
+            if (eptr >= md->end_subject)
+              {
+              SCHECK_PARTIAL();
+              break;
+              }
+            if (MAX_255(*eptr) && (md->ctypes[*eptr] & ctype_space) != 0) break;
+            eptr++;
+            }
+          break;
+
+          case OP_WHITESPACE:
+          for (i = min; i < max; i++)
+            {
+            if (eptr >= md->end_subject)
+              {
+              SCHECK_PARTIAL();
+              break;
+              }
+            if (!MAX_255(*eptr) || (md->ctypes[*eptr] & ctype_space) == 0) break;
+            eptr++;
+            }
+          break;
+
+          case OP_NOT_WORDCHAR:
+          for (i = min; i < max; i++)
+            {
+            if (eptr >= md->end_subject)
+              {
+              SCHECK_PARTIAL();
+              break;
+              }
+            if (MAX_255(*eptr) && (md->ctypes[*eptr] & ctype_word) != 0) break;
+            eptr++;
+            }
+          break;
+
+          case OP_WORDCHAR:
+          for (i = min; i < max; i++)
+            {
+            if (eptr >= md->end_subject)
+              {
+              SCHECK_PARTIAL();
+              break;
+              }
+            if (!MAX_255(*eptr) || (md->ctypes[*eptr] & ctype_word) == 0) break;
+            eptr++;
+            }
+          break;
+
+          default:
+          RRETURN(PCRE_ERROR_INTERNAL);
+          }
+
+        /* eptr is now past the end of the maximum run. If possessive, we are
+        done (no backing up). Otherwise, match at this position; anything other
+        than no match is immediately returned. For nomatch, back up one
+        character (byte), unless we are matching \R and the last thing matched
+        was \r\n, in which case, back up two bytes. */
+
+        if (possessive) continue;
+        while (eptr >= pp)
+          {
+          RMATCH(eptr, ecode, offset_top, md, eptrb, RM47);
+          if (rrc != MATCH_NOMATCH) RRETURN(rrc);
+          eptr--;
+          if (ctype == OP_ANYNL && eptr > pp  && *eptr == '\n' &&
+              eptr[-1] == '\r') eptr--;
+          }
+        }
+
+      /* Get here if we can't make it match with any permitted repetitions */
+
+      RRETURN(MATCH_NOMATCH);
+      }
+    /* Control never gets here */
+
+    /* There's been some horrible disaster. Arrival here can only mean there is
+    something seriously wrong in the code above or the OP_xxx definitions. */
+
+    default:
+    DPRINTF(("Unknown opcode %d\n", *ecode));
+    RRETURN(PCRE_ERROR_UNKNOWN_OPCODE);
+    }
+
+  /* Do not stick any code in here without much thought; it is assumed
+  that "continue" in the code above comes out to here to repeat the main
+  loop. */
+
+  }             /* End of main loop */
+/* Control never reaches here */
+
+
+/* When compiling to use the heap rather than the stack for recursive calls to
+match(), the RRETURN() macro jumps here. The number that is saved in
+frame->Xwhere indicates which label we actually want to return to. */
+
+#ifdef NO_RECURSE
+#define LBL(val) case val: goto L_RM##val;
+HEAP_RETURN:
+switch (frame->Xwhere)
+  {
+  LBL( 1) LBL( 2) LBL( 3) LBL( 4) LBL( 5) LBL( 6) LBL( 7) LBL( 8)
+  LBL( 9) LBL(10) LBL(11) LBL(12) LBL(13) LBL(14) LBL(15) LBL(17)
+  LBL(19) LBL(24) LBL(25) LBL(26) LBL(27) LBL(29) LBL(31) LBL(33)
+  LBL(35) LBL(43) LBL(47) LBL(48) LBL(49) LBL(50) LBL(51) LBL(52)
+  LBL(53) LBL(54) LBL(55) LBL(56) LBL(57) LBL(58) LBL(63) LBL(64)
+  LBL(65) LBL(66)
+#if defined SUPPORT_UTF || !defined COMPILE_PCRE8
+  LBL(21)
+#endif
+#ifdef SUPPORT_UTF
+  LBL(16) LBL(18) LBL(20)
+  LBL(22) LBL(23) LBL(28) LBL(30)
+  LBL(32) LBL(34) LBL(42) LBL(46)
+#ifdef SUPPORT_UCP
+  LBL(36) LBL(37) LBL(38) LBL(39) LBL(40) LBL(41) LBL(44) LBL(45)
+  LBL(59) LBL(60) LBL(61) LBL(62)
+#endif  /* SUPPORT_UCP */
+#endif  /* SUPPORT_UTF */
+  default:
+  DPRINTF(("jump error in pcre match: label %d non-existent\n", frame->Xwhere));
+
+printf("+++jump error in pcre match: label %d non-existent\n", frame->Xwhere);
+
+  return PCRE_ERROR_INTERNAL;
+  }
+#undef LBL
+#endif  /* NO_RECURSE */
+}
+
+
+/***************************************************************************
+****************************************************************************
+                   RECURSION IN THE match() FUNCTION
+
+Undefine all the macros that were defined above to handle this. */
+
+#ifdef NO_RECURSE
+#undef eptr
+#undef ecode
+#undef mstart
+#undef offset_top
+#undef eptrb
+#undef flags
+
+#undef callpat
+#undef charptr
+#undef data
+#undef next
+#undef pp
+#undef prev
+#undef saved_eptr
+
+#undef new_recursive
+
+#undef cur_is_word
+#undef condition
+#undef prev_is_word
+
+#undef ctype
+#undef length
+#undef max
+#undef min
+#undef number
+#undef offset
+#undef op
+#undef save_capture_last
+#undef save_offset1
+#undef save_offset2
+#undef save_offset3
+#undef stacksave
+
+#undef newptrb
+
+#endif
+
+/* These two are defined as macros in both cases */
+
+#undef fc
+#undef fi
+
+/***************************************************************************
+***************************************************************************/
+
+
+#ifdef NO_RECURSE
+/*************************************************
+*          Release allocated heap frames         *
+*************************************************/
+
+/* This function releases all the allocated frames. The base frame is on the
+machine stack, and so must not be freed.
+
+Argument: the address of the base frame
+Returns:  nothing
+*/
+
+static void
+release_match_heapframes (heapframe *frame_base)
+{
+heapframe *nextframe = frame_base->Xnextframe;
+while (nextframe != NULL)
+  {
+  heapframe *oldframe = nextframe;
+  nextframe = nextframe->Xnextframe;
+  (PUBL(stack_free))(oldframe);
+  }
+}
+#endif
+
+
+/*************************************************
+*         Execute a Regular Expression           *
+*************************************************/
+
+/* This function applies a compiled re to a subject string and picks out
+portions of the string if it matches. Two elements in the vector are set for
+each substring: the offsets to the start and end of the substring.
+
+Arguments:
+  argument_re     points to the compiled expression
+  extra_data      points to extra data or is NULL
+  subject         points to the subject string
+  length          length of subject string (may contain binary zeros)
+  start_offset    where to start in the subject string
+  options         option bits
+  offsets         points to a vector of ints to be filled in with offsets
+  offsetcount     the number of elements in the vector
+
+Returns:          > 0 => success; value is the number of elements filled in
+                  = 0 => success, but offsets is not big enough
+                   -1 => failed to match
+                 < -1 => some kind of unexpected problem
+*/
+
+#ifdef COMPILE_PCRE8
+PCRE_EXP_DEFN int PCRE_CALL_CONVENTION
+pcre_exec(const pcre *argument_re, const pcre_extra *extra_data,
+  PCRE_SPTR subject, int length, int start_offset, int options, int *offsets,
+  int offsetcount)
+#else
+PCRE_EXP_DEFN int PCRE_CALL_CONVENTION
+pcre16_exec(const pcre16 *argument_re, const pcre16_extra *extra_data,
+  PCRE_SPTR16 subject, int length, int start_offset, int options, int *offsets,
+  int offsetcount)
+#endif
+{
+int rc, ocount, arg_offset_max;
+int newline;
+BOOL using_temporary_offsets = FALSE;
+BOOL anchored;
+BOOL startline;
+BOOL firstline;
+BOOL utf;
+BOOL has_first_char = FALSE;
+BOOL has_req_char = FALSE;
+pcre_uchar first_char = 0;
+pcre_uchar first_char2 = 0;
+pcre_uchar req_char = 0;
+pcre_uchar req_char2 = 0;
+match_data match_block;
+match_data *md = &match_block;
+const pcre_uint8 *tables;
+const pcre_uint8 *start_bits = NULL;
+PCRE_PUCHAR start_match = (PCRE_PUCHAR)subject + start_offset;
+PCRE_PUCHAR end_subject;
+PCRE_PUCHAR start_partial = NULL;
+PCRE_PUCHAR req_char_ptr = start_match - 1;
+
+const pcre_study_data *study;
+const REAL_PCRE *re = (const REAL_PCRE *)argument_re;
+
+#ifdef NO_RECURSE
+heapframe frame_zero;
+frame_zero.Xprevframe = NULL;            /* Marks the top level */
+frame_zero.Xnextframe = NULL;            /* None are allocated yet */
+md->match_frames_base = &frame_zero;
+#endif
+
+/* Check for the special magic call that measures the size of the stack used
+per recursive call of match(). Without the funny casting for sizeof, a Windows
+compiler gave this error: "unary minus operator applied to unsigned type,
+result still unsigned". Hopefully the cast fixes that. */
+
+if (re == NULL && extra_data == NULL && subject == NULL && length == -999 &&
+    start_offset == -999)
+#ifdef NO_RECURSE
+  return -((int)sizeof(heapframe));
+#else
+  return match(NULL, NULL, NULL, 0, NULL, NULL, 0);
+#endif
+
+/* Plausibility checks */
+
+if ((options & ~PUBLIC_EXEC_OPTIONS) != 0) return PCRE_ERROR_BADOPTION;
+if (re == NULL || subject == NULL || (offsets == NULL && offsetcount > 0))
+  return PCRE_ERROR_NULL;
+if (offsetcount < 0) return PCRE_ERROR_BADCOUNT;
+if (start_offset < 0 || start_offset > length) return PCRE_ERROR_BADOFFSET;
+
+/* Check that the first field in the block is the magic number. If it is not,
+return with PCRE_ERROR_BADMAGIC. However, if the magic number is equal to
+REVERSED_MAGIC_NUMBER we return with PCRE_ERROR_BADENDIANNESS, which
+means that the pattern is likely compiled with different endianness. */
+
+if (re->magic_number != MAGIC_NUMBER)
+  return re->magic_number == REVERSED_MAGIC_NUMBER?
+    PCRE_ERROR_BADENDIANNESS:PCRE_ERROR_BADMAGIC;
+if ((re->flags & PCRE_MODE) == 0) return PCRE_ERROR_BADMODE;
+
+/* These two settings are used in the code for checking a UTF-8 string that
+follows immediately afterwards. Other values in the md block are used only
+during "normal" pcre_exec() processing, not when the JIT support is in use,
+so they are set up later. */
+
+/* PCRE_UTF16 has the same value as PCRE_UTF8. */
+utf = md->utf = (re->options & PCRE_UTF8) != 0;
+md->partial = ((options & PCRE_PARTIAL_HARD) != 0)? 2 :
+              ((options & PCRE_PARTIAL_SOFT) != 0)? 1 : 0;
+
+/* Check a UTF-8 string if required. Pass back the character offset and error
+code for an invalid string if a results vector is available. */
+
+#ifdef SUPPORT_UTF
+if (utf && (options & PCRE_NO_UTF8_CHECK) == 0)
+  {
+  int erroroffset;
+  int errorcode = PRIV(valid_utf)((PCRE_PUCHAR)subject, length, &erroroffset);
+  if (errorcode != 0)
+    {
+    if (offsetcount >= 2)
+      {
+      offsets[0] = erroroffset;
+      offsets[1] = errorcode;
+      }
+#ifdef COMPILE_PCRE16
+    return (errorcode <= PCRE_UTF16_ERR1 && md->partial > 1)?
+      PCRE_ERROR_SHORTUTF16 : PCRE_ERROR_BADUTF16;
+#else
+    return (errorcode <= PCRE_UTF8_ERR5 && md->partial > 1)?
+      PCRE_ERROR_SHORTUTF8 : PCRE_ERROR_BADUTF8;
+#endif
+    }
+
+  /* Check that a start_offset points to the start of a UTF character. */
+  if (start_offset > 0 && start_offset < length &&
+      NOT_FIRSTCHAR(((PCRE_PUCHAR)subject)[start_offset]))
+    return PCRE_ERROR_BADUTF8_OFFSET;
+  }
+#endif
+
+/* If the pattern was successfully studied with JIT support, run the JIT
+executable instead of the rest of this function. Most options must be set at
+compile time for the JIT code to be usable. Fallback to the normal code path if
+an unsupported flag is set. */
+
+#ifdef SUPPORT_JIT
+if (extra_data != NULL
+    && (extra_data->flags & (PCRE_EXTRA_EXECUTABLE_JIT |
+                             PCRE_EXTRA_TABLES)) == PCRE_EXTRA_EXECUTABLE_JIT
+    && extra_data->executable_jit != NULL
+    && (options & ~(PCRE_NO_UTF8_CHECK | PCRE_NOTBOL | PCRE_NOTEOL |
+                    PCRE_NOTEMPTY | PCRE_NOTEMPTY_ATSTART |
+                    PCRE_PARTIAL_SOFT | PCRE_PARTIAL_HARD)) == 0)
+  {
+  rc = PRIV(jit_exec)(re, extra_data, (const pcre_uchar *)subject, length,
+       start_offset, options, offsets, offsetcount);
+
+  /* PCRE_ERROR_NULL means that the selected normal or partial matching
+  mode is not compiled. In this case we simply fallback to interpreter. */
+
+  if (rc != PCRE_ERROR_NULL) return rc;
+  }
+#endif
+
+/* Carry on with non-JIT matching. This information is for finding all the
+numbers associated with a given name, for condition testing. */
+
+md->name_table = (pcre_uchar *)re + re->name_table_offset;
+md->name_count = re->name_count;
+md->name_entry_size = re->name_entry_size;
+
+/* Fish out the optional data from the extra_data structure, first setting
+the default values. */
+
+study = NULL;
+md->match_limit = MATCH_LIMIT;
+md->match_limit_recursion = MATCH_LIMIT_RECURSION;
+md->callout_data = NULL;
+
+/* The table pointer is always in native byte order. */
+
+tables = re->tables;
+
+if (extra_data != NULL)
+  {
+  register unsigned int flags = extra_data->flags;
+  if ((flags & PCRE_EXTRA_STUDY_DATA) != 0)
+    study = (const pcre_study_data *)extra_data->study_data;
+  if ((flags & PCRE_EXTRA_MATCH_LIMIT) != 0)
+    md->match_limit = extra_data->match_limit;
+  if ((flags & PCRE_EXTRA_MATCH_LIMIT_RECURSION) != 0)
+    md->match_limit_recursion = extra_data->match_limit_recursion;
+  if ((flags & PCRE_EXTRA_CALLOUT_DATA) != 0)
+    md->callout_data = extra_data->callout_data;
+  if ((flags & PCRE_EXTRA_TABLES) != 0) tables = extra_data->tables;
+  }
+
+/* If the exec call supplied NULL for tables, use the inbuilt ones. This
+is a feature that makes it possible to save compiled regex and re-use them
+in other programs later. */
+
+if (tables == NULL) tables = PRIV(default_tables);
+
+/* Set up other data */
+
+anchored = ((re->options | options) & PCRE_ANCHORED) != 0;
+startline = (re->flags & PCRE_STARTLINE) != 0;
+firstline = (re->options & PCRE_FIRSTLINE) != 0;
+
+/* The code starts after the real_pcre block and the capture name table. */
+
+md->start_code = (const pcre_uchar *)re + re->name_table_offset +
+  re->name_count * re->name_entry_size;
+
+md->start_subject = (PCRE_PUCHAR)subject;
+md->start_offset = start_offset;
+md->end_subject = md->start_subject + length;
+end_subject = md->end_subject;
+
+md->endonly = (re->options & PCRE_DOLLAR_ENDONLY) != 0;
+md->use_ucp = (re->options & PCRE_UCP) != 0;
+md->jscript_compat = (re->options & PCRE_JAVASCRIPT_COMPAT) != 0;
+md->ignore_skip_arg = FALSE;
+
+/* Some options are unpacked into BOOL variables in the hope that testing
+them will be faster than individual option bits. */
+
+md->notbol = (options & PCRE_NOTBOL) != 0;
+md->noteol = (options & PCRE_NOTEOL) != 0;
+md->notempty = (options & PCRE_NOTEMPTY) != 0;
+md->notempty_atstart = (options & PCRE_NOTEMPTY_ATSTART) != 0;
+
+md->hitend = FALSE;
+md->mark = md->nomatch_mark = NULL;     /* In case never set */
+
+md->recursive = NULL;                   /* No recursion at top level */
+md->hasthen = (re->flags & PCRE_HASTHEN) != 0;
+
+md->lcc = tables + lcc_offset;
+md->fcc = tables + fcc_offset;
+md->ctypes = tables + ctypes_offset;
+
+/* Handle different \R options. */
+
+switch (options & (PCRE_BSR_ANYCRLF|PCRE_BSR_UNICODE))
+  {
+  case 0:
+  if ((re->options & (PCRE_BSR_ANYCRLF|PCRE_BSR_UNICODE)) != 0)
+    md->bsr_anycrlf = (re->options & PCRE_BSR_ANYCRLF) != 0;
+  else
+#ifdef BSR_ANYCRLF
+  md->bsr_anycrlf = TRUE;
+#else
+  md->bsr_anycrlf = FALSE;
+#endif
+  break;
+
+  case PCRE_BSR_ANYCRLF:
+  md->bsr_anycrlf = TRUE;
+  break;
+
+  case PCRE_BSR_UNICODE:
+  md->bsr_anycrlf = FALSE;
+  break;
+
+  default: return PCRE_ERROR_BADNEWLINE;
+  }
+
+/* Handle different types of newline. The three bits give eight cases. If
+nothing is set at run time, whatever was used at compile time applies. */
+
+switch ((((options & PCRE_NEWLINE_BITS) == 0)? re->options :
+        (pcre_uint32)options) & PCRE_NEWLINE_BITS)
+  {
+  case 0: newline = NEWLINE; break;   /* Compile-time default */
+  case PCRE_NEWLINE_CR: newline = CHAR_CR; break;
+  case PCRE_NEWLINE_LF: newline = CHAR_NL; break;
+  case PCRE_NEWLINE_CR+
+       PCRE_NEWLINE_LF: newline = (CHAR_CR << 8) | CHAR_NL; break;
+  case PCRE_NEWLINE_ANY: newline = -1; break;
+  case PCRE_NEWLINE_ANYCRLF: newline = -2; break;
+  default: return PCRE_ERROR_BADNEWLINE;
+  }
+
+if (newline == -2)
+  {
+  md->nltype = NLTYPE_ANYCRLF;
+  }
+else if (newline < 0)
+  {
+  md->nltype = NLTYPE_ANY;
+  }
+else
+  {
+  md->nltype = NLTYPE_FIXED;
+  if (newline > 255)
+    {
+    md->nllen = 2;
+    md->nl[0] = (newline >> 8) & 255;
+    md->nl[1] = newline & 255;
+    }
+  else
+    {
+    md->nllen = 1;
+    md->nl[0] = newline;
+    }
+  }
+
+/* Partial matching was originally supported only for a restricted set of
+regexes; from release 8.00 there are no restrictions, but the bits are still
+defined (though never set). So there's no harm in leaving this code. */
+
+if (md->partial && (re->flags & PCRE_NOPARTIAL) != 0)
+  return PCRE_ERROR_BADPARTIAL;
+
+/* If the expression has got more back references than the offsets supplied can
+hold, we get a temporary chunk of working store to use during the matching.
+Otherwise, we can use the vector supplied, rounding down its size to a multiple
+of 3. */
+
+ocount = offsetcount - (offsetcount % 3);
+arg_offset_max = (2*ocount)/3;
+
+if (re->top_backref > 0 && re->top_backref >= ocount/3)
+  {
+  ocount = re->top_backref * 3 + 3;
+  md->offset_vector = (int *)(PUBL(malloc))(ocount * sizeof(int));
+  if (md->offset_vector == NULL) return PCRE_ERROR_NOMEMORY;
+  using_temporary_offsets = TRUE;
+  DPRINTF(("Got memory to hold back references\n"));
+  }
+else md->offset_vector = offsets;
+
+md->offset_end = ocount;
+md->offset_max = (2*ocount)/3;
+md->offset_overflow = FALSE;
+md->capture_last = -1;
+
+/* Reset the working variable associated with each extraction. These should
+never be used unless previously set, but they get saved and restored, and so we
+initialize them to avoid reading uninitialized locations. Also, unset the
+offsets for the matched string. This is really just for tidiness with callouts,
+in case they inspect these fields. */
+
+if (md->offset_vector != NULL)
+  {
+  register int *iptr = md->offset_vector + ocount;
+  register int *iend = iptr - re->top_bracket;
+  if (iend < md->offset_vector + 2) iend = md->offset_vector + 2;
+  while (--iptr >= iend) *iptr = -1;
+  md->offset_vector[0] = md->offset_vector[1] = -1;
+  }
+
+/* Set up the first character to match, if available. The first_char value is
+never set for an anchored regular expression, but the anchoring may be forced
+at run time, so we have to test for anchoring. The first char may be unset for
+an unanchored pattern, of course. If there's no first char and the pattern was
+studied, there may be a bitmap of possible first characters. */
+
+if (!anchored)
+  {
+  if ((re->flags & PCRE_FIRSTSET) != 0)
+    {
+    has_first_char = TRUE;
+    first_char = first_char2 = (pcre_uchar)(re->first_char);
+    if ((re->flags & PCRE_FCH_CASELESS) != 0)
+      {
+      first_char2 = TABLE_GET(first_char, md->fcc, first_char);
+#if defined SUPPORT_UCP && !(defined COMPILE_PCRE8)
+      if (utf && first_char > 127)
+        first_char2 = UCD_OTHERCASE(first_char);
+#endif
+      }
+    }
+  else
+    if (!startline && study != NULL &&
+      (study->flags & PCRE_STUDY_MAPPED) != 0)
+        start_bits = study->start_bits;
+  }
+
+/* For anchored or unanchored matches, there may be a "last known required
+character" set. */
+
+if ((re->flags & PCRE_REQCHSET) != 0)
+  {
+  has_req_char = TRUE;
+  req_char = req_char2 = (pcre_uchar)(re->req_char);
+  if ((re->flags & PCRE_RCH_CASELESS) != 0)
+    {
+    req_char2 = TABLE_GET(req_char, md->fcc, req_char);
+#if defined SUPPORT_UCP && !(defined COMPILE_PCRE8)
+    if (utf && req_char > 127)
+      req_char2 = UCD_OTHERCASE(req_char);
+#endif
+    }
+  }
+
+
+/* ==========================================================================*/
+
+/* Loop for handling unanchored repeated matching attempts; for anchored regexs
+the loop runs just once. */
+
+for(;;)
+  {
+  PCRE_PUCHAR save_end_subject = end_subject;
+  PCRE_PUCHAR new_start_match;
+
+  /* If firstline is TRUE, the start of the match is constrained to the first
+  line of a multiline string. That is, the match must be before or at the first
+  newline. Implement this by temporarily adjusting end_subject so that we stop
+  scanning at a newline. If the match fails at the newline, later code breaks
+  this loop. */
+
+  if (firstline)
+    {
+    PCRE_PUCHAR t = start_match;
+#ifdef SUPPORT_UTF
+    if (utf)
+      {
+      while (t < md->end_subject && !IS_NEWLINE(t))
+        {
+        t++;
+        ACROSSCHAR(t < end_subject, *t, t++);
+        }
+      }
+    else
+#endif
+    while (t < md->end_subject && !IS_NEWLINE(t)) t++;
+    end_subject = t;
+    }
+
+  /* There are some optimizations that avoid running the match if a known
+  starting point is not found, or if a known later character is not present.
+  However, there is an option that disables these, for testing and for ensuring
+  that all callouts do actually occur. The option can be set in the regex by
+  (*NO_START_OPT) or passed in match-time options. */
+
+  if (((options | re->options) & PCRE_NO_START_OPTIMIZE) == 0)
+    {
+    /* Advance to a unique first char if there is one. */
+
+    if (has_first_char)
+      {
+      if (first_char != first_char2)
+        while (start_match < end_subject &&
+            *start_match != first_char && *start_match != first_char2)
+          start_match++;
+      else
+        while (start_match < end_subject && *start_match != first_char)
+          start_match++;
+      }
+
+    /* Or to just after a linebreak for a multiline match */
+
+    else if (startline)
+      {
+      if (start_match > md->start_subject + start_offset)
+        {
+#ifdef SUPPORT_UTF
+        if (utf)
+          {
+          while (start_match < end_subject && !WAS_NEWLINE(start_match))
+            {
+            start_match++;
+            ACROSSCHAR(start_match < end_subject, *start_match,
+              start_match++);
+            }
+          }
+        else
+#endif
+        while (start_match < end_subject && !WAS_NEWLINE(start_match))
+          start_match++;
+
+        /* If we have just passed a CR and the newline option is ANY or ANYCRLF,
+        and we are now at a LF, advance the match position by one more character.
+        */
+
+        if (start_match[-1] == CHAR_CR &&
+             (md->nltype == NLTYPE_ANY || md->nltype == NLTYPE_ANYCRLF) &&
+             start_match < end_subject &&
+             *start_match == CHAR_NL)
+          start_match++;
+        }
+      }
+
+    /* Or to a non-unique first byte after study */
+
+    else if (start_bits != NULL)
+      {
+      while (start_match < end_subject)
+        {
+        register unsigned int c = *start_match;
+#ifndef COMPILE_PCRE8
+        if (c > 255) c = 255;
+#endif
+        if ((start_bits[c/8] & (1 << (c&7))) == 0)
+          {
+          start_match++;
+#if defined SUPPORT_UTF && defined COMPILE_PCRE8
+          /* In non 8-bit mode, the iteration will stop for
+          characters > 255 at the beginning or not stop at all. */
+          if (utf)
+            ACROSSCHAR(start_match < end_subject, *start_match,
+              start_match++);
+#endif
+          }
+        else break;
+        }
+      }
+    }   /* Starting optimizations */
+
+  /* Restore fudged end_subject */
+
+  end_subject = save_end_subject;
+
+  /* The following two optimizations are disabled for partial matching or if
+  disabling is explicitly requested. */
+
+  if (((options | re->options) & PCRE_NO_START_OPTIMIZE) == 0 && !md->partial)
+    {
+    /* If the pattern was studied, a minimum subject length may be set. This is
+    a lower bound; no actual string of that length may actually match the
+    pattern. Although the value is, strictly, in characters, we treat it as
+    bytes to avoid spending too much time in this optimization. */
+
+    if (study != NULL && (study->flags & PCRE_STUDY_MINLEN) != 0 &&
+        (pcre_uint32)(end_subject - start_match) < study->minlength)
+      {
+      rc = MATCH_NOMATCH;
+      break;
+      }
+
+    /* If req_char is set, we know that that character must appear in the
+    subject for the match to succeed. If the first character is set, req_char
+    must be later in the subject; otherwise the test starts at the match point.
+    This optimization can save a huge amount of backtracking in patterns with
+    nested unlimited repeats that aren't going to match. Writing separate code
+    for cased/caseless versions makes it go faster, as does using an
+    autoincrement and backing off on a match.
+
+    HOWEVER: when the subject string is very, very long, searching to its end
+    can take a long time, and give bad performance on quite ordinary patterns.
+    This showed up when somebody was matching something like /^\d+C/ on a
+    32-megabyte string... so we don't do this when the string is sufficiently
+    long. */
+
+    if (has_req_char && end_subject - start_match < REQ_BYTE_MAX)
+      {
+      register PCRE_PUCHAR p = start_match + (has_first_char? 1:0);
+
+      /* We don't need to repeat the search if we haven't yet reached the
+      place we found it at last time. */
+
+      if (p > req_char_ptr)
+        {
+        if (req_char != req_char2)
+          {
+          while (p < end_subject)
+            {
+            register int pp = *p++;
+            if (pp == req_char || pp == req_char2) { p--; break; }
+            }
+          }
+        else
+          {
+          while (p < end_subject)
+            {
+            if (*p++ == req_char) { p--; break; }
+            }
+          }
+
+        /* If we can't find the required character, break the matching loop,
+        forcing a match failure. */
+
+        if (p >= end_subject)
+          {
+          rc = MATCH_NOMATCH;
+          break;
+          }
+
+        /* If we have found the required character, save the point where we
+        found it, so that we don't search again next time round the loop if
+        the start hasn't passed this character yet. */
+
+        req_char_ptr = p;
+        }
+      }
+    }
+
+#ifdef PCRE_DEBUG  /* Sigh. Some compilers never learn. */
+  printf(">>>> Match against: ");
+  pchars(start_match, end_subject - start_match, TRUE, md);
+  printf("\n");
+#endif
+
+  /* OK, we can now run the match. If "hitend" is set afterwards, remember the
+  first starting point for which a partial match was found. */
+
+  md->start_match_ptr = start_match;
+  md->start_used_ptr = start_match;
+  md->match_call_count = 0;
+  md->match_function_type = 0;
+  md->end_offset_top = 0;
+  rc = match(start_match, md->start_code, start_match, 2, md, NULL, 0);
+  if (md->hitend && start_partial == NULL) start_partial = md->start_used_ptr;
+
+  switch(rc)
+    {
+    /* If MATCH_SKIP_ARG reaches this level it means that a MARK that matched
+    the SKIP's arg was not found. In this circumstance, Perl ignores the SKIP
+    entirely. The only way we can do that is to re-do the match at the same
+    point, with a flag to force SKIP with an argument to be ignored. Just
+    treating this case as NOMATCH does not work because it does not check other
+    alternatives in patterns such as A(*SKIP:A)B|AC when the subject is AC. */
+
+    case MATCH_SKIP_ARG:
+    new_start_match = start_match;
+    md->ignore_skip_arg = TRUE;
+    break;
+
+    /* SKIP passes back the next starting point explicitly, but if it is the
+    same as the match we have just done, treat it as NOMATCH. */
+
+    case MATCH_SKIP:
+    if (md->start_match_ptr != start_match)
+      {
+      new_start_match = md->start_match_ptr;
+      break;
+      }
+    /* Fall through */
+
+    /* NOMATCH and PRUNE advance by one character. THEN at this level acts
+    exactly like PRUNE. Unset the ignore SKIP-with-argument flag. */
+
+    case MATCH_NOMATCH:
+    case MATCH_PRUNE:
+    case MATCH_THEN:
+    md->ignore_skip_arg = FALSE;
+    new_start_match = start_match + 1;
+#ifdef SUPPORT_UTF
+    if (utf)
+      ACROSSCHAR(new_start_match < end_subject, *new_start_match,
+        new_start_match++);
+#endif
+    break;
+
+    /* COMMIT disables the bumpalong, but otherwise behaves as NOMATCH. */
+
+    case MATCH_COMMIT:
+    rc = MATCH_NOMATCH;
+    goto ENDLOOP;
+
+    /* Any other return is either a match, or some kind of error. */
+
+    default:
+    goto ENDLOOP;
+    }
+
+  /* Control reaches here for the various types of "no match at this point"
+  result. Reset the code to MATCH_NOMATCH for subsequent checking. */
+
+  rc = MATCH_NOMATCH;
+
+  /* If PCRE_FIRSTLINE is set, the match must happen before or at the first
+  newline in the subject (though it may continue over the newline). Therefore,
+  if we have just failed to match, starting at a newline, do not continue. */
+
+  if (firstline && IS_NEWLINE(start_match)) break;
+
+  /* Advance to new matching position */
+
+  start_match = new_start_match;
+
+  /* Break the loop if the pattern is anchored or if we have passed the end of
+  the subject. */
+
+  if (anchored || start_match > end_subject) break;
+
+  /* If we have just passed a CR and we are now at a LF, and the pattern does
+  not contain any explicit matches for \r or \n, and the newline option is CRLF
+  or ANY or ANYCRLF, advance the match position by one more character. In
+  normal matching start_match will aways be greater than the first position at
+  this stage, but a failed *SKIP can cause a return at the same point, which is
+  why the first test exists. */
+
+  if (start_match > (PCRE_PUCHAR)subject + start_offset &&
+      start_match[-1] == CHAR_CR &&
+      start_match < end_subject &&
+      *start_match == CHAR_NL &&
+      (re->flags & PCRE_HASCRORLF) == 0 &&
+        (md->nltype == NLTYPE_ANY ||
+         md->nltype == NLTYPE_ANYCRLF ||
+         md->nllen == 2))
+    start_match++;
+
+  md->mark = NULL;   /* Reset for start of next match attempt */
+  }                  /* End of for(;;) "bumpalong" loop */
+
+/* ==========================================================================*/
+
+/* We reach here when rc is not MATCH_NOMATCH, or if one of the stopping
+conditions is true:
+
+(1) The pattern is anchored or the match was failed by (*COMMIT);
+
+(2) We are past the end of the subject;
+
+(3) PCRE_FIRSTLINE is set and we have failed to match at a newline, because
+    this option requests that a match occur at or before the first newline in
+    the subject.
+
+When we have a match and the offset vector is big enough to deal with any
+backreferences, captured substring offsets will already be set up. In the case
+where we had to get some local store to hold offsets for backreference
+processing, copy those that we can. In this case there need not be overflow if
+certain parts of the pattern were not used, even though there are more
+capturing parentheses than vector slots. */
+
+ENDLOOP:
+
+if (rc == MATCH_MATCH || rc == MATCH_ACCEPT)
+  {
+  if (using_temporary_offsets)
+    {
+    if (arg_offset_max >= 4)
+      {
+      memcpy(offsets + 2, md->offset_vector + 2,
+        (arg_offset_max - 2) * sizeof(int));
+      DPRINTF(("Copied offsets from temporary memory\n"));
+      }
+    if (md->end_offset_top > arg_offset_max) md->offset_overflow = TRUE;
+    DPRINTF(("Freeing temporary memory\n"));
+    (PUBL(free))(md->offset_vector);
+    }
+
+  /* Set the return code to the number of captured strings, or 0 if there were
+  too many to fit into the vector. */
+
+  rc = (md->offset_overflow && md->end_offset_top >= arg_offset_max)?
+    0 : md->end_offset_top/2;
+
+  /* If there is space in the offset vector, set any unused pairs at the end of
+  the pattern to -1 for backwards compatibility. It is documented that this
+  happens. In earlier versions, the whole set of potential capturing offsets
+  was set to -1 each time round the loop, but this is handled differently now.
+  "Gaps" are set to -1 dynamically instead (this fixes a bug). Thus, it is only
+  those at the end that need unsetting here. We can't just unset them all at
+  the start of the whole thing because they may get set in one branch that is
+  not the final matching branch. */
+
+  if (md->end_offset_top/2 <= re->top_bracket && offsets != NULL)
+    {
+    register int *iptr, *iend;
+    int resetcount = 2 + re->top_bracket * 2;
+    if (resetcount > offsetcount) resetcount = offsetcount;
+    iptr = offsets + md->end_offset_top;
+    iend = offsets + resetcount;
+    while (iptr < iend) *iptr++ = -1;
+    }
+
+  /* If there is space, set up the whole thing as substring 0. The value of
+  md->start_match_ptr might be modified if \K was encountered on the success
+  matching path. */
+
+  if (offsetcount < 2) rc = 0; else
+    {
+    offsets[0] = (int)(md->start_match_ptr - md->start_subject);
+    offsets[1] = (int)(md->end_match_ptr - md->start_subject);
+    }
+
+  /* Return MARK data if requested */
+
+  if (extra_data != NULL && (extra_data->flags & PCRE_EXTRA_MARK) != 0)
+    *(extra_data->mark) = (pcre_uchar *)md->mark;
+  DPRINTF((">>>> returning %d\n", rc));
+#ifdef NO_RECURSE
+  release_match_heapframes(&frame_zero);
+#endif
+  return rc;
+  }
+
+/* Control gets here if there has been an error, or if the overall match
+attempt has failed at all permitted starting positions. */
+
+if (using_temporary_offsets)
+  {
+  DPRINTF(("Freeing temporary memory\n"));
+  (PUBL(free))(md->offset_vector);
+  }
+
+/* For anything other than nomatch or partial match, just return the code. */
+
+if (rc != MATCH_NOMATCH && rc != PCRE_ERROR_PARTIAL)
+  {
+  DPRINTF((">>>> error: returning %d\n", rc));
+#ifdef NO_RECURSE
+  release_match_heapframes(&frame_zero);
+#endif
+  return rc;
+  }
+
+/* Handle partial matches - disable any mark data */
+
+if (start_partial != NULL)
+  {
+  DPRINTF((">>>> returning PCRE_ERROR_PARTIAL\n"));
+  md->mark = NULL;
+  if (offsetcount > 1)
+    {
+    offsets[0] = (int)(start_partial - (PCRE_PUCHAR)subject);
+    offsets[1] = (int)(end_subject - (PCRE_PUCHAR)subject);
+    }
+  rc = PCRE_ERROR_PARTIAL;
+  }
+
+/* This is the classic nomatch case */
+
+else
+  {
+  DPRINTF((">>>> returning PCRE_ERROR_NOMATCH\n"));
+  rc = PCRE_ERROR_NOMATCH;
+  }
+
+/* Return the MARK data if it has been requested. */
+
+if (extra_data != NULL && (extra_data->flags & PCRE_EXTRA_MARK) != 0)
+  *(extra_data->mark) = (pcre_uchar *)md->nomatch_mark;
+#ifdef NO_RECURSE
+  release_match_heapframes(&frame_zero);
+#endif
+return rc;
+}
+
+/* End of pcre_exec.c */
diff --git a/ext/pcre/pcrelib/pcre_fullinfo.c b/ext/pcre/pcrelib/pcre_fullinfo.c
new file mode 100644
index 0000000..2fe785a
--- /dev/null
+++ b/ext/pcre/pcrelib/pcre_fullinfo.c
@@ -0,0 +1,204 @@
+/*************************************************
+*      Perl-Compatible Regular Expressions       *
+*************************************************/
+
+/* PCRE is a library of functions to support regular expressions whose syntax
+and semantics are as close as possible to those of the Perl 5 language.
+
+                       Written by Philip Hazel
+           Copyright (c) 1997-2012 University of Cambridge
+
+-----------------------------------------------------------------------------
+Redistribution and use in source and binary forms, with or without
+modification, are permitted provided that the following conditions are met:
+
+    * Redistributions of source code must retain the above copyright notice,
+      this list of conditions and the following disclaimer.
+
+    * Redistributions in binary form must reproduce the above copyright
+      notice, this list of conditions and the following disclaimer in the
+      documentation and/or other materials provided with the distribution.
+
+    * Neither the name of the University of Cambridge nor the names of its
+      contributors may be used to endorse or promote products derived from
+      this software without specific prior written permission.
+
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+POSSIBILITY OF SUCH DAMAGE.
+-----------------------------------------------------------------------------
+*/
+
+
+/* This module contains the external function pcre_fullinfo(), which returns
+information about a compiled pattern. */
+
+
+#include "config.h"
+
+#include "pcre_internal.h"
+
+
+/*************************************************
+*        Return info about compiled pattern      *
+*************************************************/
+
+/* This is a newer "info" function which has an extensible interface so
+that additional items can be added compatibly.
+
+Arguments:
+  argument_re      points to compiled code
+  extra_data       points extra data, or NULL
+  what             what information is required
+  where            where to put the information
+
+Returns:           0 if data returned, negative on error
+*/
+
+#ifdef COMPILE_PCRE8
+PCRE_EXP_DEFN int PCRE_CALL_CONVENTION
+pcre_fullinfo(const pcre *argument_re, const pcre_extra *extra_data,
+  int what, void *where)
+#else
+PCRE_EXP_DEFN int PCRE_CALL_CONVENTION
+pcre16_fullinfo(const pcre16 *argument_re, const pcre16_extra *extra_data,
+  int what, void *where)
+#endif
+{
+const REAL_PCRE *re = (const REAL_PCRE *)argument_re;
+const pcre_study_data *study = NULL;
+
+if (re == NULL || where == NULL) return PCRE_ERROR_NULL;
+
+if (extra_data != NULL && (extra_data->flags & PCRE_EXTRA_STUDY_DATA) != 0)
+  study = (const pcre_study_data *)extra_data->study_data;
+
+/* Check that the first field in the block is the magic number. If it is not,
+return with PCRE_ERROR_BADMAGIC. However, if the magic number is equal to
+REVERSED_MAGIC_NUMBER we return with PCRE_ERROR_BADENDIANNESS, which
+means that the pattern is likely compiled with different endianness. */
+
+if (re->magic_number != MAGIC_NUMBER)
+  return re->magic_number == REVERSED_MAGIC_NUMBER?
+    PCRE_ERROR_BADENDIANNESS:PCRE_ERROR_BADMAGIC;
+
+/* Check that this pattern was compiled in the correct bit mode */
+
+if ((re->flags & PCRE_MODE) == 0) return PCRE_ERROR_BADMODE;
+
+switch (what)
+  {
+  case PCRE_INFO_OPTIONS:
+  *((unsigned long int *)where) = re->options & PUBLIC_COMPILE_OPTIONS;
+  break;
+
+  case PCRE_INFO_SIZE:
+  *((size_t *)where) = re->size;
+  break;
+
+  case PCRE_INFO_STUDYSIZE:
+  *((size_t *)where) = (study == NULL)? 0 : study->size;
+  break;
+
+  case PCRE_INFO_JITSIZE:
+#ifdef SUPPORT_JIT
+  *((size_t *)where) =
+      (extra_data != NULL &&
+      (extra_data->flags & PCRE_EXTRA_EXECUTABLE_JIT) != 0 &&
+      extra_data->executable_jit != NULL)?
+    PRIV(jit_get_size)(extra_data->executable_jit) : 0;
+#else
+  *((size_t *)where) = 0;
+#endif
+  break;
+
+  case PCRE_INFO_CAPTURECOUNT:
+  *((int *)where) = re->top_bracket;
+  break;
+
+  case PCRE_INFO_BACKREFMAX:
+  *((int *)where) = re->top_backref;
+  break;
+
+  case PCRE_INFO_FIRSTBYTE:
+  *((int *)where) =
+    ((re->flags & PCRE_FIRSTSET) != 0)? re->first_char :
+    ((re->flags & PCRE_STARTLINE) != 0)? -1 : -2;
+  break;
+
+  /* Make sure we pass back the pointer to the bit vector in the external
+  block, not the internal copy (with flipped integer fields). */
+
+  case PCRE_INFO_FIRSTTABLE:
+  *((const pcre_uint8 **)where) =
+    (study != NULL && (study->flags & PCRE_STUDY_MAPPED) != 0)?
+      ((const pcre_study_data *)extra_data->study_data)->start_bits : NULL;
+  break;
+
+  case PCRE_INFO_MINLENGTH:
+  *((int *)where) =
+    (study != NULL && (study->flags & PCRE_STUDY_MINLEN) != 0)?
+      (int)(study->minlength) : -1;
+  break;
+
+  case PCRE_INFO_JIT:
+  *((int *)where) = extra_data != NULL &&
+                    (extra_data->flags & PCRE_EXTRA_EXECUTABLE_JIT) != 0 &&
+                    extra_data->executable_jit != NULL;
+  break;
+
+  case PCRE_INFO_LASTLITERAL:
+  *((int *)where) =
+    ((re->flags & PCRE_REQCHSET) != 0)? re->req_char : -1;
+  break;
+
+  case PCRE_INFO_NAMEENTRYSIZE:
+  *((int *)where) = re->name_entry_size;
+  break;
+
+  case PCRE_INFO_NAMECOUNT:
+  *((int *)where) = re->name_count;
+  break;
+
+  case PCRE_INFO_NAMETABLE:
+  *((const pcre_uchar **)where) = (const pcre_uchar *)re + re->name_table_offset;
+  break;
+
+  case PCRE_INFO_DEFAULT_TABLES:
+  *((const pcre_uint8 **)where) = (const pcre_uint8 *)(PRIV(default_tables));
+  break;
+
+  /* From release 8.00 this will always return TRUE because NOPARTIAL is
+  no longer ever set (the restrictions have been removed). */
+
+  case PCRE_INFO_OKPARTIAL:
+  *((int *)where) = (re->flags & PCRE_NOPARTIAL) == 0;
+  break;
+
+  case PCRE_INFO_JCHANGED:
+  *((int *)where) = (re->flags & PCRE_JCHANGED) != 0;
+  break;
+
+  case PCRE_INFO_HASCRORLF:
+  *((int *)where) = (re->flags & PCRE_HASCRORLF) != 0;
+  break;
+
+  case PCRE_INFO_MAXLOOKBEHIND:
+  *((int *)where) = re->max_lookbehind;
+  break;
+
+  default: return PCRE_ERROR_BADOPTION;
+  }
+
+return 0;
+}
+
+/* End of pcre_fullinfo.c */
diff --git a/ext/pcre/pcrelib/pcre_get.c b/ext/pcre/pcrelib/pcre_get.c
new file mode 100644
index 0000000..61147ef
--- /dev/null
+++ b/ext/pcre/pcrelib/pcre_get.c
@@ -0,0 +1,585 @@
+/*************************************************
+*      Perl-Compatible Regular Expressions       *
+*************************************************/
+
+/* PCRE is a library of functions to support regular expressions whose syntax
+and semantics are as close as possible to those of the Perl 5 language.
+
+                       Written by Philip Hazel
+           Copyright (c) 1997-2012 University of Cambridge
+
+-----------------------------------------------------------------------------
+Redistribution and use in source and binary forms, with or without
+modification, are permitted provided that the following conditions are met:
+
+    * Redistributions of source code must retain the above copyright notice,
+      this list of conditions and the following disclaimer.
+
+    * Redistributions in binary form must reproduce the above copyright
+      notice, this list of conditions and the following disclaimer in the
+      documentation and/or other materials provided with the distribution.
+
+    * Neither the name of the University of Cambridge nor the names of its
+      contributors may be used to endorse or promote products derived from
+      this software without specific prior written permission.
+
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+POSSIBILITY OF SUCH DAMAGE.
+-----------------------------------------------------------------------------
+*/
+
+
+/* This module contains some convenience functions for extracting substrings
+from the subject string after a regex match has succeeded. The original idea
+for these functions came from Scott Wimer. */
+
+
+#include "config.h"
+
+#include "pcre_internal.h"
+
+
+/*************************************************
+*           Find number for named string         *
+*************************************************/
+
+/* This function is used by the get_first_set() function below, as well
+as being generally available. It assumes that names are unique.
+
+Arguments:
+  code        the compiled regex
+  stringname  the name whose number is required
+
+Returns:      the number of the named parentheses, or a negative number
+                (PCRE_ERROR_NOSUBSTRING) if not found
+*/
+
+#ifdef COMPILE_PCRE8
+PCRE_EXP_DEFN int PCRE_CALL_CONVENTION
+pcre_get_stringnumber(const pcre *code, const char *stringname)
+#else
+PCRE_EXP_DEFN int PCRE_CALL_CONVENTION
+pcre16_get_stringnumber(const pcre16 *code, PCRE_SPTR16 stringname)
+#endif
+{
+int rc;
+int entrysize;
+int top, bot;
+pcre_uchar *nametable;
+
+#ifdef COMPILE_PCRE8
+if ((rc = pcre_fullinfo(code, NULL, PCRE_INFO_NAMECOUNT, &top)) != 0)
+  return rc;
+if (top <= 0) return PCRE_ERROR_NOSUBSTRING;
+
+if ((rc = pcre_fullinfo(code, NULL, PCRE_INFO_NAMEENTRYSIZE, &entrysize)) != 0)
+  return rc;
+if ((rc = pcre_fullinfo(code, NULL, PCRE_INFO_NAMETABLE, &nametable)) != 0)
+  return rc;
+#endif
+#ifdef COMPILE_PCRE16
+if ((rc = pcre16_fullinfo(code, NULL, PCRE_INFO_NAMECOUNT, &top)) != 0)
+  return rc;
+if (top <= 0) return PCRE_ERROR_NOSUBSTRING;
+
+if ((rc = pcre16_fullinfo(code, NULL, PCRE_INFO_NAMEENTRYSIZE, &entrysize)) != 0)
+  return rc;
+if ((rc = pcre16_fullinfo(code, NULL, PCRE_INFO_NAMETABLE, &nametable)) != 0)
+  return rc;
+#endif
+
+bot = 0;
+while (top > bot)
+  {
+  int mid = (top + bot) / 2;
+  pcre_uchar *entry = nametable + entrysize*mid;
+  int c = STRCMP_UC_UC((pcre_uchar *)stringname,
+    (pcre_uchar *)(entry + IMM2_SIZE));
+  if (c == 0) return GET2(entry, 0);
+  if (c > 0) bot = mid + 1; else top = mid;
+  }
+
+return PCRE_ERROR_NOSUBSTRING;
+}
+
+
+
+/*************************************************
+*     Find (multiple) entries for named string   *
+*************************************************/
+
+/* This is used by the get_first_set() function below, as well as being
+generally available. It is used when duplicated names are permitted.
+
+Arguments:
+  code        the compiled regex
+  stringname  the name whose entries required
+  firstptr    where to put the pointer to the first entry
+  lastptr     where to put the pointer to the last entry
+
+Returns:      the length of each entry, or a negative number
+                (PCRE_ERROR_NOSUBSTRING) if not found
+*/
+
+#ifdef COMPILE_PCRE8
+PCRE_EXP_DEFN int PCRE_CALL_CONVENTION
+pcre_get_stringtable_entries(const pcre *code, const char *stringname,
+  char **firstptr, char **lastptr)
+#else
+PCRE_EXP_DEFN int PCRE_CALL_CONVENTION
+pcre16_get_stringtable_entries(const pcre16 *code, PCRE_SPTR16 stringname,
+  PCRE_UCHAR16 **firstptr, PCRE_UCHAR16 **lastptr)
+#endif
+{
+int rc;
+int entrysize;
+int top, bot;
+pcre_uchar *nametable, *lastentry;
+
+#ifdef COMPILE_PCRE8
+if ((rc = pcre_fullinfo(code, NULL, PCRE_INFO_NAMECOUNT, &top)) != 0)
+  return rc;
+if (top <= 0) return PCRE_ERROR_NOSUBSTRING;
+
+if ((rc = pcre_fullinfo(code, NULL, PCRE_INFO_NAMEENTRYSIZE, &entrysize)) != 0)
+  return rc;
+if ((rc = pcre_fullinfo(code, NULL, PCRE_INFO_NAMETABLE, &nametable)) != 0)
+  return rc;
+#endif
+#ifdef COMPILE_PCRE16
+if ((rc = pcre16_fullinfo(code, NULL, PCRE_INFO_NAMECOUNT, &top)) != 0)
+  return rc;
+if (top <= 0) return PCRE_ERROR_NOSUBSTRING;
+
+if ((rc = pcre16_fullinfo(code, NULL, PCRE_INFO_NAMEENTRYSIZE, &entrysize)) != 0)
+  return rc;
+if ((rc = pcre16_fullinfo(code, NULL, PCRE_INFO_NAMETABLE, &nametable)) != 0)
+  return rc;
+#endif
+
+lastentry = nametable + entrysize * (top - 1);
+bot = 0;
+while (top > bot)
+  {
+  int mid = (top + bot) / 2;
+  pcre_uchar *entry = nametable + entrysize*mid;
+  int c = STRCMP_UC_UC((pcre_uchar *)stringname,
+    (pcre_uchar *)(entry + IMM2_SIZE));
+  if (c == 0)
+    {
+    pcre_uchar *first = entry;
+    pcre_uchar *last = entry;
+    while (first > nametable)
+      {
+      if (STRCMP_UC_UC((pcre_uchar *)stringname,
+        (pcre_uchar *)(first - entrysize + IMM2_SIZE)) != 0) break;
+      first -= entrysize;
+      }
+    while (last < lastentry)
+      {
+      if (STRCMP_UC_UC((pcre_uchar *)stringname,
+        (pcre_uchar *)(last + entrysize + IMM2_SIZE)) != 0) break;
+      last += entrysize;
+      }
+#ifdef COMPILE_PCRE8
+    *firstptr = (char *)first;
+    *lastptr = (char *)last;
+#else
+    *firstptr = (PCRE_UCHAR16 *)first;
+    *lastptr = (PCRE_UCHAR16 *)last;
+#endif
+    return entrysize;
+    }
+  if (c > 0) bot = mid + 1; else top = mid;
+  }
+
+return PCRE_ERROR_NOSUBSTRING;
+}
+
+
+
+/*************************************************
+*    Find first set of multiple named strings    *
+*************************************************/
+
+/* This function allows for duplicate names in the table of named substrings.
+It returns the number of the first one that was set in a pattern match.
+
+Arguments:
+  code         the compiled regex
+  stringname   the name of the capturing substring
+  ovector      the vector of matched substrings
+
+Returns:       the number of the first that is set,
+               or the number of the last one if none are set,
+               or a negative number on error
+*/
+
+#ifdef COMPILE_PCRE8
+static int
+get_first_set(const pcre *code, const char *stringname, int *ovector)
+#else
+static int
+get_first_set(const pcre16 *code, PCRE_SPTR16 stringname, int *ovector)
+#endif
+{
+const REAL_PCRE *re = (const REAL_PCRE *)code;
+int entrysize;
+pcre_uchar *entry;
+#ifdef COMPILE_PCRE8
+char *first, *last;
+#else
+PCRE_UCHAR16 *first, *last;
+#endif
+
+#ifdef COMPILE_PCRE8
+if ((re->options & PCRE_DUPNAMES) == 0 && (re->flags & PCRE_JCHANGED) == 0)
+  return pcre_get_stringnumber(code, stringname);
+entrysize = pcre_get_stringtable_entries(code, stringname, &first, &last);
+#else
+if ((re->options & PCRE_DUPNAMES) == 0 && (re->flags & PCRE_JCHANGED) == 0)
+  return pcre16_get_stringnumber(code, stringname);
+entrysize = pcre16_get_stringtable_entries(code, stringname, &first, &last);
+#endif
+if (entrysize <= 0) return entrysize;
+for (entry = (pcre_uchar *)first; entry <= (pcre_uchar *)last; entry += entrysize)
+  {
+  int n = GET2(entry, 0);
+  if (ovector[n*2] >= 0) return n;
+  }
+return GET2(entry, 0);
+}
+
+
+
+
+/*************************************************
+*      Copy captured string to given buffer      *
+*************************************************/
+
+/* This function copies a single captured substring into a given buffer.
+Note that we use memcpy() rather than strncpy() in case there are binary zeros
+in the string.
+
+Arguments:
+  subject        the subject string that was matched
+  ovector        pointer to the offsets table
+  stringcount    the number of substrings that were captured
+                   (i.e. the yield of the pcre_exec call, unless
+                   that was zero, in which case it should be 1/3
+                   of the offset table size)
+  stringnumber   the number of the required substring
+  buffer         where to put the substring
+  size           the size of the buffer
+
+Returns:         if successful:
+                   the length of the copied string, not including the zero
+                   that is put on the end; can be zero
+                 if not successful:
+                   PCRE_ERROR_NOMEMORY (-6) buffer too small
+                   PCRE_ERROR_NOSUBSTRING (-7) no such captured substring
+*/
+
+#ifdef COMPILE_PCRE8
+PCRE_EXP_DEFN int PCRE_CALL_CONVENTION
+pcre_copy_substring(const char *subject, int *ovector, int stringcount,
+  int stringnumber, char *buffer, int size)
+#else
+PCRE_EXP_DEFN int PCRE_CALL_CONVENTION
+pcre16_copy_substring(PCRE_SPTR16 subject, int *ovector, int stringcount,
+  int stringnumber, PCRE_UCHAR16 *buffer, int size)
+#endif
+{
+int yield;
+if (stringnumber < 0 || stringnumber >= stringcount)
+  return PCRE_ERROR_NOSUBSTRING;
+stringnumber *= 2;
+yield = ovector[stringnumber+1] - ovector[stringnumber];
+if (size < yield + 1) return PCRE_ERROR_NOMEMORY;
+memcpy(buffer, subject + ovector[stringnumber], IN_UCHARS(yield));
+buffer[yield] = 0;
+return yield;
+}
+
+
+
+/*************************************************
+*   Copy named captured string to given buffer   *
+*************************************************/
+
+/* This function copies a single captured substring into a given buffer,
+identifying it by name. If the regex permits duplicate names, the first
+substring that is set is chosen.
+
+Arguments:
+  code           the compiled regex
+  subject        the subject string that was matched
+  ovector        pointer to the offsets table
+  stringcount    the number of substrings that were captured
+                   (i.e. the yield of the pcre_exec call, unless
+                   that was zero, in which case it should be 1/3
+                   of the offset table size)
+  stringname     the name of the required substring
+  buffer         where to put the substring
+  size           the size of the buffer
+
+Returns:         if successful:
+                   the length of the copied string, not including the zero
+                   that is put on the end; can be zero
+                 if not successful:
+                   PCRE_ERROR_NOMEMORY (-6) buffer too small
+                   PCRE_ERROR_NOSUBSTRING (-7) no such captured substring
+*/
+
+#ifdef COMPILE_PCRE8
+PCRE_EXP_DEFN int PCRE_CALL_CONVENTION
+pcre_copy_named_substring(const pcre *code, const char *subject,
+  int *ovector, int stringcount, const char *stringname,
+  char *buffer, int size)
+#else
+PCRE_EXP_DEFN int PCRE_CALL_CONVENTION
+pcre16_copy_named_substring(const pcre16 *code, PCRE_SPTR16 subject,
+  int *ovector, int stringcount, PCRE_SPTR16 stringname,
+  PCRE_UCHAR16 *buffer, int size)
+#endif
+{
+int n = get_first_set(code, stringname, ovector);
+if (n <= 0) return n;
+#ifdef COMPILE_PCRE8
+return pcre_copy_substring(subject, ovector, stringcount, n, buffer, size);
+#else
+return pcre16_copy_substring(subject, ovector, stringcount, n, buffer, size);
+#endif
+}
+
+
+
+/*************************************************
+*      Copy all captured strings to new store    *
+*************************************************/
+
+/* This function gets one chunk of store and builds a list of pointers and all
+of the captured substrings in it. A NULL pointer is put on the end of the list.
+
+Arguments:
+  subject        the subject string that was matched
+  ovector        pointer to the offsets table
+  stringcount    the number of substrings that were captured
+                   (i.e. the yield of the pcre_exec call, unless
+                   that was zero, in which case it should be 1/3
+                   of the offset table size)
+  listptr        set to point to the list of pointers
+
+Returns:         if successful: 0
+                 if not successful:
+                   PCRE_ERROR_NOMEMORY (-6) failed to get store
+*/
+
+#ifdef COMPILE_PCRE8
+PCRE_EXP_DEFN int PCRE_CALL_CONVENTION
+pcre_get_substring_list(const char *subject, int *ovector, int stringcount,
+  const char ***listptr)
+#else
+PCRE_EXP_DEFN int PCRE_CALL_CONVENTION
+pcre16_get_substring_list(PCRE_SPTR16 subject, int *ovector, int stringcount,
+  PCRE_SPTR16 **listptr)
+#endif
+{
+int i;
+int size = sizeof(pcre_uchar *);
+int double_count = stringcount * 2;
+pcre_uchar **stringlist;
+pcre_uchar *p;
+
+for (i = 0; i < double_count; i += 2)
+  size += sizeof(pcre_uchar *) + IN_UCHARS(ovector[i+1] - ovector[i] + 1);
+
+stringlist = (pcre_uchar **)(PUBL(malloc))(size);
+if (stringlist == NULL) return PCRE_ERROR_NOMEMORY;
+
+#ifdef COMPILE_PCRE8
+*listptr = (const char **)stringlist;
+#else
+*listptr = (PCRE_SPTR16 *)stringlist;
+#endif
+p = (pcre_uchar *)(stringlist + stringcount + 1);
+
+for (i = 0; i < double_count; i += 2)
+  {
+  int len = ovector[i+1] - ovector[i];
+  memcpy(p, subject + ovector[i], IN_UCHARS(len));
+  *stringlist++ = p;
+  p += len;
+  *p++ = 0;
+  }
+
+*stringlist = NULL;
+return 0;
+}
+
+
+
+/*************************************************
+*   Free store obtained by get_substring_list    *
+*************************************************/
+
+/* This function exists for the benefit of people calling PCRE from non-C
+programs that can call its functions, but not free() or (PUBL(free))()
+directly.
+
+Argument:   the result of a previous pcre_get_substring_list()
+Returns:    nothing
+*/
+
+#ifdef COMPILE_PCRE8
+PCRE_EXP_DEFN void PCRE_CALL_CONVENTION
+pcre_free_substring_list(const char **pointer)
+#else
+PCRE_EXP_DEFN void PCRE_CALL_CONVENTION
+pcre16_free_substring_list(PCRE_SPTR16 *pointer)
+#endif
+{
+(PUBL(free))((void *)pointer);
+}
+
+
+
+/*************************************************
+*      Copy captured string to new store         *
+*************************************************/
+
+/* This function copies a single captured substring into a piece of new
+store
+
+Arguments:
+  subject        the subject string that was matched
+  ovector        pointer to the offsets table
+  stringcount    the number of substrings that were captured
+                   (i.e. the yield of the pcre_exec call, unless
+                   that was zero, in which case it should be 1/3
+                   of the offset table size)
+  stringnumber   the number of the required substring
+  stringptr      where to put a pointer to the substring
+
+Returns:         if successful:
+                   the length of the string, not including the zero that
+                   is put on the end; can be zero
+                 if not successful:
+                   PCRE_ERROR_NOMEMORY (-6) failed to get store
+                   PCRE_ERROR_NOSUBSTRING (-7) substring not present
+*/
+
+#ifdef COMPILE_PCRE8
+PCRE_EXP_DEFN int PCRE_CALL_CONVENTION
+pcre_get_substring(const char *subject, int *ovector, int stringcount,
+  int stringnumber, const char **stringptr)
+#else
+PCRE_EXP_DEFN int PCRE_CALL_CONVENTION
+pcre16_get_substring(PCRE_SPTR16 subject, int *ovector, int stringcount,
+  int stringnumber, PCRE_SPTR16 *stringptr)
+#endif
+{
+int yield;
+pcre_uchar *substring;
+if (stringnumber < 0 || stringnumber >= stringcount)
+  return PCRE_ERROR_NOSUBSTRING;
+stringnumber *= 2;
+yield = ovector[stringnumber+1] - ovector[stringnumber];
+substring = (pcre_uchar *)(PUBL(malloc))(IN_UCHARS(yield + 1));
+if (substring == NULL) return PCRE_ERROR_NOMEMORY;
+memcpy(substring, subject + ovector[stringnumber], IN_UCHARS(yield));
+substring[yield] = 0;
+#ifdef COMPILE_PCRE8
+*stringptr = (const char *)substring;
+#else
+*stringptr = (PCRE_SPTR16)substring;
+#endif
+return yield;
+}
+
+
+
+/*************************************************
+*   Copy named captured string to new store      *
+*************************************************/
+
+/* This function copies a single captured substring, identified by name, into
+new store. If the regex permits duplicate names, the first substring that is
+set is chosen.
+
+Arguments:
+  code           the compiled regex
+  subject        the subject string that was matched
+  ovector        pointer to the offsets table
+  stringcount    the number of substrings that were captured
+                   (i.e. the yield of the pcre_exec call, unless
+                   that was zero, in which case it should be 1/3
+                   of the offset table size)
+  stringname     the name of the required substring
+  stringptr      where to put the pointer
+
+Returns:         if successful:
+                   the length of the copied string, not including the zero
+                   that is put on the end; can be zero
+                 if not successful:
+                   PCRE_ERROR_NOMEMORY (-6) couldn't get memory
+                   PCRE_ERROR_NOSUBSTRING (-7) no such captured substring
+*/
+
+#ifdef COMPILE_PCRE8
+PCRE_EXP_DEFN int PCRE_CALL_CONVENTION
+pcre_get_named_substring(const pcre *code, const char *subject,
+  int *ovector, int stringcount, const char *stringname,
+  const char **stringptr)
+#else
+PCRE_EXP_DEFN int PCRE_CALL_CONVENTION
+pcre16_get_named_substring(const pcre16 *code, PCRE_SPTR16 subject,
+  int *ovector, int stringcount, PCRE_SPTR16 stringname,
+  PCRE_SPTR16 *stringptr)
+#endif
+{
+int n = get_first_set(code, stringname, ovector);
+if (n <= 0) return n;
+#ifdef COMPILE_PCRE8
+return pcre_get_substring(subject, ovector, stringcount, n, stringptr);
+#else
+return pcre16_get_substring(subject, ovector, stringcount, n, stringptr);
+#endif
+}
+
+
+
+
+/*************************************************
+*       Free store obtained by get_substring     *
+*************************************************/
+
+/* This function exists for the benefit of people calling PCRE from non-C
+programs that can call its functions, but not free() or (PUBL(free))()
+directly.
+
+Argument:   the result of a previous pcre_get_substring()
+Returns:    nothing
+*/
+
+#ifdef COMPILE_PCRE8
+PCRE_EXP_DEFN void PCRE_CALL_CONVENTION
+pcre_free_substring(const char *pointer)
+#else
+PCRE_EXP_DEFN void PCRE_CALL_CONVENTION
+pcre16_free_substring(PCRE_SPTR16 pointer)
+#endif
+{
+(PUBL(free))((void *)pointer);
+}
+
+/* End of pcre_get.c */
diff --git a/ext/pcre/pcrelib/pcre_globals.c b/ext/pcre/pcrelib/pcre_globals.c
new file mode 100644
index 0000000..3dde1f6
--- /dev/null
+++ b/ext/pcre/pcrelib/pcre_globals.c
@@ -0,0 +1,82 @@
+/*************************************************
+*      Perl-Compatible Regular Expressions       *
+*************************************************/
+
+/* PCRE is a library of functions to support regular expressions whose syntax
+and semantics are as close as possible to those of the Perl 5 language.
+
+                       Written by Philip Hazel
+           Copyright (c) 1997-2012 University of Cambridge
+
+-----------------------------------------------------------------------------
+Redistribution and use in source and binary forms, with or without
+modification, are permitted provided that the following conditions are met:
+
+    * Redistributions of source code must retain the above copyright notice,
+      this list of conditions and the following disclaimer.
+
+    * Redistributions in binary form must reproduce the above copyright
+      notice, this list of conditions and the following disclaimer in the
+      documentation and/or other materials provided with the distribution.
+
+    * Neither the name of the University of Cambridge nor the names of its
+      contributors may be used to endorse or promote products derived from
+      this software without specific prior written permission.
+
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+POSSIBILITY OF SUCH DAMAGE.
+-----------------------------------------------------------------------------
+*/
+
+
+/* This module contains global variables that are exported by the PCRE library.
+PCRE is thread-clean and doesn't use any global variables in the normal sense.
+However, it calls memory allocation and freeing functions via the four
+indirections below, and it can optionally do callouts, using the fifth
+indirection. These values can be changed by the caller, but are shared between
+all threads.
+
+For MS Visual Studio and Symbian OS, there are problems in initializing these
+variables to non-local functions. In these cases, therefore, an indirection via
+a local function is used.
+
+Also, when compiling for Virtual Pascal, things are done differently, and
+global variables are not used. */
+
+#include "config.h"
+
+#include "pcre_internal.h"
+
+#if defined _MSC_VER || defined  __SYMBIAN32__
+static void* LocalPcreMalloc(size_t aSize)
+  {
+  return malloc(aSize);
+  }
+static void LocalPcreFree(void* aPtr)
+  {
+  free(aPtr);
+  }
+PCRE_EXP_DATA_DEFN void *(*PUBL(malloc))(size_t) = LocalPcreMalloc;
+PCRE_EXP_DATA_DEFN void  (*PUBL(free))(void *) = LocalPcreFree;
+PCRE_EXP_DATA_DEFN void *(*PUBL(stack_malloc))(size_t) = LocalPcreMalloc;
+PCRE_EXP_DATA_DEFN void  (*PUBL(stack_free))(void *) = LocalPcreFree;
+PCRE_EXP_DATA_DEFN int   (*PUBL(callout))(PUBL(callout_block) *) = NULL;
+
+#elif !defined VPCOMPAT
+PCRE_EXP_DATA_DEFN void *(*PUBL(malloc))(size_t) = malloc;
+PCRE_EXP_DATA_DEFN void  (*PUBL(free))(void *) = free;
+PCRE_EXP_DATA_DEFN void *(*PUBL(stack_malloc))(size_t) = malloc;
+PCRE_EXP_DATA_DEFN void  (*PUBL(stack_free))(void *) = free;
+PCRE_EXP_DATA_DEFN int   (*PUBL(callout))(PUBL(callout_block) *) = NULL;
+#endif
+
+/* End of pcre_globals.c */
diff --git a/ext/pcre/pcrelib/pcre_internal.h b/ext/pcre/pcrelib/pcre_internal.h
new file mode 100644
index 0000000..ed16269
--- /dev/null
+++ b/ext/pcre/pcrelib/pcre_internal.h
@@ -0,0 +1,2348 @@
+/*************************************************
+*      Perl-Compatible Regular Expressions       *
+*************************************************/
+
+
+/* PCRE is a library of functions to support regular expressions whose syntax
+and semantics are as close as possible to those of the Perl 5 language.
+
+                       Written by Philip Hazel
+           Copyright (c) 1997-2012 University of Cambridge
+
+-----------------------------------------------------------------------------
+Redistribution and use in source and binary forms, with or without
+modification, are permitted provided that the following conditions are met:
+
+    * Redistributions of source code must retain the above copyright notice,
+      this list of conditions and the following disclaimer.
+
+    * Redistributions in binary form must reproduce the above copyright
+      notice, this list of conditions and the following disclaimer in the
+      documentation and/or other materials provided with the distribution.
+
+    * Neither the name of the University of Cambridge nor the names of its
+      contributors may be used to endorse or promote products derived from
+      this software without specific prior written permission.
+
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+POSSIBILITY OF SUCH DAMAGE.
+-----------------------------------------------------------------------------
+*/
+
+/* This header contains definitions that are shared between the different
+modules, but which are not relevant to the exported API. This includes some
+functions whose names all begin with "_pcre_" or "_pcre16_" depending on
+the PRIV macro. */
+
+#ifndef PCRE_INTERNAL_H
+#define PCRE_INTERNAL_H
+
+/* Define PCRE_DEBUG to get debugging output on stdout. */
+
+#if 0
+#define PCRE_DEBUG
+#endif
+
+/* PCRE is compiled as an 8 bit library if it is not requested otherwise. */
+#ifndef COMPILE_PCRE16
+#define COMPILE_PCRE8
+#endif
+
+/* If SUPPORT_UCP is defined, SUPPORT_UTF must also be defined. The
+"configure" script ensures this, but not everybody uses "configure". */
+
+#if defined SUPPORT_UCP && !(defined SUPPORT_UTF)
+#define SUPPORT_UTF 1
+#endif
+
+/* We define SUPPORT_UTF if SUPPORT_UTF8 is enabled for compatibility
+reasons with existing code. */
+
+#if defined SUPPORT_UTF8 && !(defined SUPPORT_UTF)
+#define SUPPORT_UTF 1
+#endif
+
+/* Fixme: SUPPORT_UTF8 should be eventually disappear from the code.
+Until then we define it if SUPPORT_UTF is defined. */
+
+#if defined SUPPORT_UTF && !(defined SUPPORT_UTF8)
+#define SUPPORT_UTF8 1
+#endif
+
+/* We do not support both EBCDIC and UTF-8/16 at the same time. The "configure"
+script prevents both being selected, but not everybody uses "configure". */
+
+#if defined EBCDIC && defined SUPPORT_UTF
+#error The use of both EBCDIC and SUPPORT_UTF8/16 is not supported.
+#endif
+
+/* Use a macro for debugging printing, 'cause that eliminates the use of #ifdef
+inline, and there are *still* stupid compilers about that don't like indented
+pre-processor statements, or at least there were when I first wrote this. After
+all, it had only been about 10 years then...
+
+It turns out that the Mac Debugging.h header also defines the macro DPRINTF, so
+be absolutely sure we get our version. */
+
+#undef DPRINTF
+#ifdef PCRE_DEBUG
+#define DPRINTF(p) printf p
+#else
+#define DPRINTF(p) /* Nothing */
+#endif
+
+
+/* Standard C headers plus the external interface definition. The only time
+setjmp and stdarg are used is when NO_RECURSE is set. */
+
+#include <ctype.h>
+#include <limits.h>
+#include <stddef.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+
+/* When compiling a DLL for Windows, the exported symbols have to be declared
+using some MS magic. I found some useful information on this web page:
+http://msdn2.microsoft.com/en-us/library/y4h7bcy6(VS.80).aspx. According to the
+information there, using __declspec(dllexport) without "extern" we have a
+definition; with "extern" we have a declaration. The settings here override the
+setting in pcre.h (which is included below); it defines only PCRE_EXP_DECL,
+which is all that is needed for applications (they just import the symbols). We
+use:
+
+  PCRE_EXP_DECL       for declarations
+  PCRE_EXP_DEFN       for definitions of exported functions
+  PCRE_EXP_DATA_DEFN  for definitions of exported variables
+
+The reason for the two DEFN macros is that in non-Windows environments, one
+does not want to have "extern" before variable definitions because it leads to
+compiler warnings. So we distinguish between functions and variables. In
+Windows, the two should always be the same.
+
+The reason for wrapping this in #ifndef PCRE_EXP_DECL is so that pcretest,
+which is an application, but needs to import this file in order to "peek" at
+internals, can #include pcre.h first to get an application's-eye view.
+
+In principle, people compiling for non-Windows, non-Unix-like (i.e. uncommon,
+special-purpose environments) might want to stick other stuff in front of
+exported symbols. That's why, in the non-Windows case, we set PCRE_EXP_DEFN and
+PCRE_EXP_DATA_DEFN only if they are not already set. */
+
+#ifndef PCRE_EXP_DECL
+#  ifdef _WIN32
+#    ifndef PCRE_STATIC
+#      define PCRE_EXP_DECL       extern __declspec(dllexport)
+#      define PCRE_EXP_DEFN       __declspec(dllexport)
+#      define PCRE_EXP_DATA_DEFN  __declspec(dllexport)
+#    else
+#      define PCRE_EXP_DECL       extern
+#      define PCRE_EXP_DEFN
+#      define PCRE_EXP_DATA_DEFN
+#    endif
+#  else
+#    ifdef __cplusplus
+#      define PCRE_EXP_DECL       extern "C"
+#    else
+#      define PCRE_EXP_DECL       extern
+#    endif
+#    ifndef PCRE_EXP_DEFN
+#      define PCRE_EXP_DEFN       PCRE_EXP_DECL
+#    endif
+#    ifndef PCRE_EXP_DATA_DEFN
+#      define PCRE_EXP_DATA_DEFN
+#    endif
+#  endif
+#endif
+
+/* When compiling with the MSVC compiler, it is sometimes necessary to include
+a "calling convention" before exported function names. (This is secondhand
+information; I know nothing about MSVC myself). For example, something like
+
+  void __cdecl function(....)
+
+might be needed. In order so make this easy, all the exported functions have
+PCRE_CALL_CONVENTION just before their names. It is rarely needed; if not
+set, we ensure here that it has no effect. */
+
+#ifndef PCRE_CALL_CONVENTION
+#define PCRE_CALL_CONVENTION
+#endif
+
+/* We need to have types that specify unsigned 8, 16 and 32-bit integers. We
+cannot determine these outside the compilation (e.g. by running a program as
+part of "configure") because PCRE is often cross-compiled for use on other
+systems. Instead we make use of the maximum sizes that are available at
+preprocessor time in standard C environments. */
+
+typedef unsigned char pcre_uint8;
+
+#if USHRT_MAX == 65535
+  typedef unsigned short pcre_uint16;
+  typedef short pcre_int16;
+#elif UINT_MAX == 65535
+  typedef unsigned int pcre_uint16;
+  typedef int pcre_int16;
+#else
+  #error Cannot determine a type for 16-bit unsigned integers
+#endif
+
+#if UINT_MAX == 4294967295
+  typedef unsigned int pcre_uint32;
+  typedef int pcre_int32;
+#elif ULONG_MAX == 4294967295
+  typedef unsigned long int pcre_uint32;
+  typedef long int pcre_int32;
+#else
+  #error Cannot determine a type for 32-bit unsigned integers
+#endif
+
+/* When checking for integer overflow in pcre_compile(), we need to handle
+large integers. If a 64-bit integer type is available, we can use that.
+Otherwise we have to cast to double, which of course requires floating point
+arithmetic. Handle this by defining a macro for the appropriate type. If
+stdint.h is available, include it; it may define INT64_MAX. Systems that do not
+have stdint.h (e.g. Solaris) may have inttypes.h. The macro int64_t may be set
+by "configure". */
+
+#ifdef PHP_WIN32
+#include "win32/php_stdint.h"
+#elif HAVE_STDINT_H
+#include <stdint.h>
+#elif HAVE_INTTYPES_H
+#include <inttypes.h>
+#endif
+
+#if defined INT64_MAX || defined int64_t
+#define INT64_OR_DOUBLE int64_t
+#else
+#define INT64_OR_DOUBLE double
+#endif
+
+/* All character handling must be done as unsigned characters. Otherwise there
+are problems with top-bit-set characters and functions such as isspace().
+However, we leave the interface to the outside world as char * or short *,
+because that should make things easier for callers. This character type is
+called pcre_uchar.
+
+The IN_UCHARS macro multiply its argument with the byte size of the current
+pcre_uchar type. Useful for memcpy and such operations, whose require the
+byte size of their input/output buffers.
+
+The MAX_255 macro checks whether its pcre_uchar input is less than 256.
+
+The TABLE_GET macro is designed for accessing elements of tables whose contain
+exactly 256 items. When the character is able to contain more than 256
+items, some check is needed before accessing these tables.
+*/
+
+#ifdef COMPILE_PCRE8
+
+typedef unsigned char pcre_uchar;
+#define IN_UCHARS(x) (x)
+#define MAX_255(c) 1
+#define TABLE_GET(c, table, default) ((table)[c])
+
+#else
+
+#ifdef COMPILE_PCRE16
+#if USHRT_MAX != 65535
+/* This is a warning message. Change PCRE_UCHAR16 to a 16 bit data type in
+pcre.h(.in) and disable (comment out) this message. */
+#error Warning: PCRE_UCHAR16 is not a 16 bit data type.
+#endif
+
+typedef pcre_uint16 pcre_uchar;
+#define IN_UCHARS(x) ((x) << 1)
+#define MAX_255(c) ((c) <= 255u)
+#define TABLE_GET(c, table, default) (MAX_255(c)? ((table)[c]):(default))
+
+#else
+#error Unsupported compiling mode
+#endif /* COMPILE_PCRE16 */
+
+#endif /* COMPILE_PCRE8 */
+
+/* This is an unsigned int value that no character can ever have. UTF-8
+characters only go up to 0x7fffffff (though Unicode doesn't go beyond
+0x0010ffff). */
+
+#define NOTACHAR 0xffffffff
+
+/* PCRE is able to support several different kinds of newline (CR, LF, CRLF,
+"any" and "anycrlf" at present). The following macros are used to package up
+testing for newlines. NLBLOCK, PSSTART, and PSEND are defined in the various
+modules to indicate in which datablock the parameters exist, and what the
+start/end of string field names are. */
+
+#define NLTYPE_FIXED    0     /* Newline is a fixed length string */
+#define NLTYPE_ANY      1     /* Newline is any Unicode line ending */
+#define NLTYPE_ANYCRLF  2     /* Newline is CR, LF, or CRLF */
+
+/* This macro checks for a newline at the given position */
+
+#define IS_NEWLINE(p) \
+  ((NLBLOCK->nltype != NLTYPE_FIXED)? \
+    ((p) < NLBLOCK->PSEND && \
+     PRIV(is_newline)((p), NLBLOCK->nltype, NLBLOCK->PSEND, \
+       &(NLBLOCK->nllen), utf)) \
+    : \
+    ((p) <= NLBLOCK->PSEND - NLBLOCK->nllen && \
+     (p)[0] == NLBLOCK->nl[0] && \
+     (NLBLOCK->nllen == 1 || (p)[1] == NLBLOCK->nl[1]) \
+    ) \
+  )
+
+/* This macro checks for a newline immediately preceding the given position */
+
+#define WAS_NEWLINE(p) \
+  ((NLBLOCK->nltype != NLTYPE_FIXED)? \
+    ((p) > NLBLOCK->PSSTART && \
+     PRIV(was_newline)((p), NLBLOCK->nltype, NLBLOCK->PSSTART, \
+       &(NLBLOCK->nllen), utf)) \
+    : \
+    ((p) >= NLBLOCK->PSSTART + NLBLOCK->nllen && \
+     (p)[-NLBLOCK->nllen] == NLBLOCK->nl[0] && \
+     (NLBLOCK->nllen == 1 || (p)[-NLBLOCK->nllen+1] == NLBLOCK->nl[1]) \
+    ) \
+  )
+
+/* When PCRE is compiled as a C++ library, the subject pointer can be replaced
+with a custom type. This makes it possible, for example, to allow pcre_exec()
+to process subject strings that are discontinuous by using a smart pointer
+class. It must always be possible to inspect all of the subject string in
+pcre_exec() because of the way it backtracks. Two macros are required in the
+normal case, for sign-unspecified and unsigned char pointers. The former is
+used for the external interface and appears in pcre.h, which is why its name
+must begin with PCRE_. */
+
+#ifdef CUSTOM_SUBJECT_PTR
+#define PCRE_PUCHAR CUSTOM_SUBJECT_PTR
+#else
+#define PCRE_PUCHAR const pcre_uchar *
+#endif
+
+/* Include the public PCRE header and the definitions of UCP character property
+values. */
+
+#include "pcre.h"
+#include "ucp.h"
+
+/* When compiling for use with the Virtual Pascal compiler, these functions
+need to have their names changed. PCRE must be compiled with the -DVPCOMPAT
+option on the command line. */
+
+#ifdef VPCOMPAT
+#define strlen(s)        _strlen(s)
+#define strncmp(s1,s2,m) _strncmp(s1,s2,m)
+#define memcmp(s,c,n)    _memcmp(s,c,n)
+#define memcpy(d,s,n)    _memcpy(d,s,n)
+#define memmove(d,s,n)   _memmove(d,s,n)
+#define memset(s,c,n)    _memset(s,c,n)
+#else  /* VPCOMPAT */
+
+/* To cope with SunOS4 and other systems that lack memmove() but have bcopy(),
+define a macro for memmove() if HAVE_MEMMOVE is false, provided that HAVE_BCOPY
+is set. Otherwise, include an emulating function for those systems that have
+neither (there some non-Unix environments where this is the case). */
+
+#ifndef HAVE_MEMMOVE
+#undef  memmove        /* some systems may have a macro */
+#ifdef HAVE_BCOPY
+#define memmove(a, b, c) bcopy(b, a, c)
+#else  /* HAVE_BCOPY */
+static void *
+pcre_memmove(void *d, const void *s, size_t n)
+{
+size_t i;
+unsigned char *dest = (unsigned char *)d;
+const unsigned char *src = (const unsigned char *)s;
+if (dest > src)
+  {
+  dest += n;
+  src += n;
+  for (i = 0; i < n; ++i) *(--dest) = *(--src);
+  return (void *)dest;
+  }
+else
+  {
+  for (i = 0; i < n; ++i) *dest++ = *src++;
+  return (void *)(dest - n);
+  }
+}
+#define memmove(a, b, c) pcre_memmove(a, b, c)
+#endif   /* not HAVE_BCOPY */
+#endif   /* not HAVE_MEMMOVE */
+#endif   /* not VPCOMPAT */
+
+
+/* PCRE keeps offsets in its compiled code as 2-byte quantities (always stored
+in big-endian order) by default. These are used, for example, to link from the
+start of a subpattern to its alternatives and its end. The use of 2 bytes per
+offset limits the size of the compiled regex to around 64K, which is big enough
+for almost everybody. However, I received a request for an even bigger limit.
+For this reason, and also to make the code easier to maintain, the storing and
+loading of offsets from the byte string is now handled by the macros that are
+defined here.
+
+The macros are controlled by the value of LINK_SIZE. This defaults to 2 in
+the config.h file, but can be overridden by using -D on the command line. This
+is automated on Unix systems via the "configure" command. */
+
+#ifdef COMPILE_PCRE8
+
+#if LINK_SIZE == 2
+
+#define PUT(a,n,d)   \
+  (a[n] = (d) >> 8), \
+  (a[(n)+1] = (d) & 255)
+
+#define GET(a,n) \
+  (((a)[n] << 8) | (a)[(n)+1])
+
+#define MAX_PATTERN_SIZE (1 << 16)
+
+
+#elif LINK_SIZE == 3
+
+#define PUT(a,n,d)       \
+  (a[n] = (d) >> 16),    \
+  (a[(n)+1] = (d) >> 8), \
+  (a[(n)+2] = (d) & 255)
+
+#define GET(a,n) \
+  (((a)[n] << 16) | ((a)[(n)+1] << 8) | (a)[(n)+2])
+
+#define MAX_PATTERN_SIZE (1 << 24)
+
+
+#elif LINK_SIZE == 4
+
+#define PUT(a,n,d)        \
+  (a[n] = (d) >> 24),     \
+  (a[(n)+1] = (d) >> 16), \
+  (a[(n)+2] = (d) >> 8),  \
+  (a[(n)+3] = (d) & 255)
+
+#define GET(a,n) \
+  (((a)[n] << 24) | ((a)[(n)+1] << 16) | ((a)[(n)+2] << 8) | (a)[(n)+3])
+
+/* Keep it positive */
+#define MAX_PATTERN_SIZE (1 << 30)
+
+#else
+#error LINK_SIZE must be either 2, 3, or 4
+#endif
+
+#else /* COMPILE_PCRE8 */
+
+#ifdef COMPILE_PCRE16
+
+#if LINK_SIZE == 2
+
+#undef LINK_SIZE
+#define LINK_SIZE 1
+
+#define PUT(a,n,d)   \
+  (a[n] = (d))
+
+#define GET(a,n) \
+  (a[n])
+
+#define MAX_PATTERN_SIZE (1 << 16)
+
+#elif LINK_SIZE == 3 || LINK_SIZE == 4
+
+#undef LINK_SIZE
+#define LINK_SIZE 2
+
+#define PUT(a,n,d)   \
+  (a[n] = (d) >> 16), \
+  (a[(n)+1] = (d) & 65535)
+
+#define GET(a,n) \
+  (((a)[n] << 16) | (a)[(n)+1])
+
+/* Keep it positive */
+#define MAX_PATTERN_SIZE (1 << 30)
+
+#else
+#error LINK_SIZE must be either 2, 3, or 4
+#endif
+
+#else
+#error Unsupported compiling mode
+#endif /* COMPILE_PCRE16 */
+
+#endif /* COMPILE_PCRE8 */
+
+/* Convenience macro defined in terms of the others */
+
+#define PUTINC(a,n,d)   PUT(a,n,d), a += LINK_SIZE
+
+
+/* PCRE uses some other 2-byte quantities that do not change when the size of
+offsets changes. There are used for repeat counts and for other things such as
+capturing parenthesis numbers in back references. */
+
+#ifdef COMPILE_PCRE8
+
+#define IMM2_SIZE 2
+
+#define PUT2(a,n,d)   \
+  a[n] = (d) >> 8; \
+  a[(n)+1] = (d) & 255
+
+#define GET2(a,n) \
+  (((a)[n] << 8) | (a)[(n)+1])
+
+#else /* COMPILE_PCRE8 */
+
+#ifdef COMPILE_PCRE16
+
+#define IMM2_SIZE 1
+
+#define PUT2(a,n,d)   \
+   a[n] = d
+
+#define GET2(a,n) \
+   a[n]
+
+#else
+#error Unsupported compiling mode
+#endif /* COMPILE_PCRE16 */
+
+#endif /* COMPILE_PCRE8 */
+
+#define PUT2INC(a,n,d)  PUT2(a,n,d), a += IMM2_SIZE
+
+/* The maximum length of a MARK name is currently one data unit; it may be
+changed in future to be a fixed number of bytes or to depend on LINK_SIZE. */
+
+#define MAX_MARK ((1 << (sizeof(pcre_uchar)*8)) - 1)
+
+/* When UTF encoding is being used, a character is no longer just a single
+character. The macros for character handling generate simple sequences when
+used in character-mode, and more complicated ones for UTF characters.
+GETCHARLENTEST and other macros are not used when UTF is not supported,
+so they are not defined. To make sure they can never even appear when
+UTF support is omitted, we don't even define them. */
+
+#ifndef SUPPORT_UTF
+
+/* #define MAX_VALUE_FOR_SINGLE_CHAR */
+/* #define HAS_EXTRALEN(c) */
+/* #define GET_EXTRALEN(c) */
+/* #define NOT_FIRSTCHAR(c) */
+#define GETCHAR(c, eptr) c = *eptr;
+#define GETCHARTEST(c, eptr) c = *eptr;
+#define GETCHARINC(c, eptr) c = *eptr++;
+#define GETCHARINCTEST(c, eptr) c = *eptr++;
+#define GETCHARLEN(c, eptr, len) c = *eptr;
+/* #define GETCHARLENTEST(c, eptr, len) */
+/* #define BACKCHAR(eptr) */
+/* #define FORWARDCHAR(eptr) */
+/* #define ACROSSCHAR(condition, eptr, action) */
+
+#else   /* SUPPORT_UTF */
+
+#ifdef COMPILE_PCRE8
+
+/* These macros were originally written in the form of loops that used data
+from the tables whose names start with PRIV(utf8_table). They were rewritten by
+a user so as not to use loops, because in some environments this gives a
+significant performance advantage, and it seems never to do any harm. */
+
+/* Tells the biggest code point which can be encoded as a single character. */
+
+#define MAX_VALUE_FOR_SINGLE_CHAR 127
+
+/* Tests whether the code point needs extra characters to decode. */
+
+#define HAS_EXTRALEN(c) ((c) >= 0xc0)
+
+/* Returns with the additional number of characters if IS_MULTICHAR(c) is TRUE.
+Otherwise it has an undefined behaviour. */
+
+#define GET_EXTRALEN(c) (PRIV(utf8_table4)[(c) & 0x3f])
+
+/* Returns TRUE, if the given character is not the first character
+of a UTF sequence. */
+
+#define NOT_FIRSTCHAR(c) (((c) & 0xc0) == 0x80)
+
+/* Base macro to pick up the remaining bytes of a UTF-8 character, not
+advancing the pointer. */
+
+#define GETUTF8(c, eptr) \
+    { \
+    if ((c & 0x20) == 0) \
+      c = ((c & 0x1f) << 6) | (eptr[1] & 0x3f); \
+    else if ((c & 0x10) == 0) \
+      c = ((c & 0x0f) << 12) | ((eptr[1] & 0x3f) << 6) | (eptr[2] & 0x3f); \
+    else if ((c & 0x08) == 0) \
+      c = ((c & 0x07) << 18) | ((eptr[1] & 0x3f) << 12) | \
+      ((eptr[2] & 0x3f) << 6) | (eptr[3] & 0x3f); \
+    else if ((c & 0x04) == 0) \
+      c = ((c & 0x03) << 24) | ((eptr[1] & 0x3f) << 18) | \
+          ((eptr[2] & 0x3f) << 12) | ((eptr[3] & 0x3f) << 6) | \
+          (eptr[4] & 0x3f); \
+    else \
+      c = ((c & 0x01) << 30) | ((eptr[1] & 0x3f) << 24) | \
+          ((eptr[2] & 0x3f) << 18) | ((eptr[3] & 0x3f) << 12) | \
+          ((eptr[4] & 0x3f) << 6) | (eptr[5] & 0x3f); \
+    }
+
+/* Get the next UTF-8 character, not advancing the pointer. This is called when
+we know we are in UTF-8 mode. */
+
+#define GETCHAR(c, eptr) \
+  c = *eptr; \
+  if (c >= 0xc0) GETUTF8(c, eptr);
+
+/* Get the next UTF-8 character, testing for UTF-8 mode, and not advancing the
+pointer. */
+
+#define GETCHARTEST(c, eptr) \
+  c = *eptr; \
+  if (utf && c >= 0xc0) GETUTF8(c, eptr);
+
+/* Base macro to pick up the remaining bytes of a UTF-8 character, advancing
+the pointer. */
+
+#define GETUTF8INC(c, eptr) \
+    { \
+    if ((c & 0x20) == 0) \
+      c = ((c & 0x1f) << 6) | (*eptr++ & 0x3f); \
+    else if ((c & 0x10) == 0) \
+      { \
+      c = ((c & 0x0f) << 12) | ((*eptr & 0x3f) << 6) | (eptr[1] & 0x3f); \
+      eptr += 2; \
+      } \
+    else if ((c & 0x08) == 0) \
+      { \
+      c = ((c & 0x07) << 18) | ((*eptr & 0x3f) << 12) | \
+          ((eptr[1] & 0x3f) << 6) | (eptr[2] & 0x3f); \
+      eptr += 3; \
+      } \
+    else if ((c & 0x04) == 0) \
+      { \
+      c = ((c & 0x03) << 24) | ((*eptr & 0x3f) << 18) | \
+          ((eptr[1] & 0x3f) << 12) | ((eptr[2] & 0x3f) << 6) | \
+          (eptr[3] & 0x3f); \
+      eptr += 4; \
+      } \
+    else \
+      { \
+      c = ((c & 0x01) << 30) | ((*eptr & 0x3f) << 24) | \
+          ((eptr[1] & 0x3f) << 18) | ((eptr[2] & 0x3f) << 12) | \
+          ((eptr[3] & 0x3f) << 6) | (eptr[4] & 0x3f); \
+      eptr += 5; \
+      } \
+    }
+
+/* Get the next UTF-8 character, advancing the pointer. This is called when we
+know we are in UTF-8 mode. */
+
+#define GETCHARINC(c, eptr) \
+  c = *eptr++; \
+  if (c >= 0xc0) GETUTF8INC(c, eptr);
+
+/* Get the next character, testing for UTF-8 mode, and advancing the pointer.
+This is called when we don't know if we are in UTF-8 mode. */
+
+#define GETCHARINCTEST(c, eptr) \
+  c = *eptr++; \
+  if (utf && c >= 0xc0) GETUTF8INC(c, eptr);
+
+/* Base macro to pick up the remaining bytes of a UTF-8 character, not
+advancing the pointer, incrementing the length. */
+
+#define GETUTF8LEN(c, eptr, len) \
+    { \
+    if ((c & 0x20) == 0) \
+      { \
+      c = ((c & 0x1f) << 6) | (eptr[1] & 0x3f); \
+      len++; \
+      } \
+    else if ((c & 0x10)  == 0) \
+      { \
+      c = ((c & 0x0f) << 12) | ((eptr[1] & 0x3f) << 6) | (eptr[2] & 0x3f); \
+      len += 2; \
+      } \
+    else if ((c & 0x08)  == 0) \
+      {\
+      c = ((c & 0x07) << 18) | ((eptr[1] & 0x3f) << 12) | \
+          ((eptr[2] & 0x3f) << 6) | (eptr[3] & 0x3f); \
+      len += 3; \
+      } \
+    else if ((c & 0x04)  == 0) \
+      { \
+      c = ((c & 0x03) << 24) | ((eptr[1] & 0x3f) << 18) | \
+          ((eptr[2] & 0x3f) << 12) | ((eptr[3] & 0x3f) << 6) | \
+          (eptr[4] & 0x3f); \
+      len += 4; \
+      } \
+    else \
+      {\
+      c = ((c & 0x01) << 30) | ((eptr[1] & 0x3f) << 24) | \
+          ((eptr[2] & 0x3f) << 18) | ((eptr[3] & 0x3f) << 12) | \
+          ((eptr[4] & 0x3f) << 6) | (eptr[5] & 0x3f); \
+      len += 5; \
+      } \
+    }
+
+/* Get the next UTF-8 character, not advancing the pointer, incrementing length
+if there are extra bytes. This is called when we know we are in UTF-8 mode. */
+
+#define GETCHARLEN(c, eptr, len) \
+  c = *eptr; \
+  if (c >= 0xc0) GETUTF8LEN(c, eptr, len);
+
+/* Get the next UTF-8 character, testing for UTF-8 mode, not advancing the
+pointer, incrementing length if there are extra bytes. This is called when we
+do not know if we are in UTF-8 mode. */
+
+#define GETCHARLENTEST(c, eptr, len) \
+  c = *eptr; \
+  if (utf && c >= 0xc0) GETUTF8LEN(c, eptr, len);
+
+/* If the pointer is not at the start of a character, move it back until
+it is. This is called only in UTF-8 mode - we don't put a test within the macro
+because almost all calls are already within a block of UTF-8 only code. */
+
+#define BACKCHAR(eptr) while((*eptr & 0xc0) == 0x80) eptr--
+
+/* Same as above, just in the other direction. */
+#define FORWARDCHAR(eptr) while((*eptr & 0xc0) == 0x80) eptr++
+
+/* Same as above, but it allows a fully customizable form. */
+#define ACROSSCHAR(condition, eptr, action) \
+  while((condition) && ((eptr) & 0xc0) == 0x80) action
+
+#else /* COMPILE_PCRE8 */
+
+#ifdef COMPILE_PCRE16
+
+/* Tells the biggest code point which can be encoded as a single character. */
+
+#define MAX_VALUE_FOR_SINGLE_CHAR 65535
+
+/* Tests whether the code point needs extra characters to decode. */
+
+#define HAS_EXTRALEN(c) (((c) & 0xfc00) == 0xd800)
+
+/* Returns with the additional number of characters if IS_MULTICHAR(c) is TRUE.
+Otherwise it has an undefined behaviour. */
+
+#define GET_EXTRALEN(c) 1
+
+/* Returns TRUE, if the given character is not the first character
+of a UTF sequence. */
+
+#define NOT_FIRSTCHAR(c) (((c) & 0xfc00) == 0xdc00)
+
+/* Base macro to pick up the low surrogate of a UTF-16 character, not
+advancing the pointer. */
+
+#define GETUTF16(c, eptr) \
+   { c = (((c & 0x3ff) << 10) | (eptr[1] & 0x3ff)) + 0x10000; }
+
+/* Get the next UTF-16 character, not advancing the pointer. This is called when
+we know we are in UTF-16 mode. */
+
+#define GETCHAR(c, eptr) \
+  c = *eptr; \
+  if ((c & 0xfc00) == 0xd800) GETUTF16(c, eptr);
+
+/* Get the next UTF-16 character, testing for UTF-16 mode, and not advancing the
+pointer. */
+
+#define GETCHARTEST(c, eptr) \
+  c = *eptr; \
+  if (utf && (c & 0xfc00) == 0xd800) GETUTF16(c, eptr);
+
+/* Base macro to pick up the low surrogate of a UTF-16 character, advancing
+the pointer. */
+
+#define GETUTF16INC(c, eptr) \
+   { c = (((c & 0x3ff) << 10) | (*eptr++ & 0x3ff)) + 0x10000; }
+
+/* Get the next UTF-16 character, advancing the pointer. This is called when we
+know we are in UTF-16 mode. */
+
+#define GETCHARINC(c, eptr) \
+  c = *eptr++; \
+  if ((c & 0xfc00) == 0xd800) GETUTF16INC(c, eptr);
+
+/* Get the next character, testing for UTF-16 mode, and advancing the pointer.
+This is called when we don't know if we are in UTF-16 mode. */
+
+#define GETCHARINCTEST(c, eptr) \
+  c = *eptr++; \
+  if (utf && (c & 0xfc00) == 0xd800) GETUTF16INC(c, eptr);
+
+/* Base macro to pick up the low surrogate of a UTF-16 character, not
+advancing the pointer, incrementing the length. */
+
+#define GETUTF16LEN(c, eptr, len) \
+   { c = (((c & 0x3ff) << 10) | (eptr[1] & 0x3ff)) + 0x10000; len++; }
+
+/* Get the next UTF-16 character, not advancing the pointer, incrementing
+length if there is a low surrogate. This is called when we know we are in
+UTF-16 mode. */
+
+#define GETCHARLEN(c, eptr, len) \
+  c = *eptr; \
+  if ((c & 0xfc00) == 0xd800) GETUTF16LEN(c, eptr, len);
+
+/* Get the next UTF-816character, testing for UTF-16 mode, not advancing the
+pointer, incrementing length if there is a low surrogate. This is called when
+we do not know if we are in UTF-16 mode. */
+
+#define GETCHARLENTEST(c, eptr, len) \
+  c = *eptr; \
+  if (utf && (c & 0xfc00) == 0xd800) GETUTF16LEN(c, eptr, len);
+
+/* If the pointer is not at the start of a character, move it back until
+it is. This is called only in UTF-16 mode - we don't put a test within the
+macro because almost all calls are already within a block of UTF-16 only
+code. */
+
+#define BACKCHAR(eptr) if ((*eptr & 0xfc00) == 0xdc00) eptr--
+
+/* Same as above, just in the other direction. */
+#define FORWARDCHAR(eptr) if ((*eptr & 0xfc00) == 0xdc00) eptr++
+
+/* Same as above, but it allows a fully customizable form. */
+#define ACROSSCHAR(condition, eptr, action) \
+  if ((condition) && ((eptr) & 0xfc00) == 0xdc00) action
+
+#endif
+
+#endif /* COMPILE_PCRE8 */
+
+#endif  /* SUPPORT_UTF */
+
+
+/* In case there is no definition of offsetof() provided - though any proper
+Standard C system should have one. */
+
+#ifndef offsetof
+#define offsetof(p_type,field) ((size_t)&(((p_type *)0)->field))
+#endif
+
+
+/* Private flags containing information about the compiled regex. They used to
+live at the top end of the options word, but that got almost full, so now they
+are in a 16-bit flags word. From release 8.00, PCRE_NOPARTIAL is unused, as
+the restrictions on partial matching have been lifted. It remains for backwards
+compatibility. */
+
+#ifdef COMPILE_PCRE8
+#define PCRE_MODE          0x0001  /* compiled in 8 bit mode */
+#endif
+#ifdef COMPILE_PCRE16
+#define PCRE_MODE          0x0002  /* compiled in 16 bit mode */
+#endif
+#define PCRE_FIRSTSET      0x0010  /* first_char is set */
+#define PCRE_FCH_CASELESS  0x0020  /* caseless first char */
+#define PCRE_REQCHSET      0x0040  /* req_byte is set */
+#define PCRE_RCH_CASELESS  0x0080  /* caseless requested char */
+#define PCRE_STARTLINE     0x0100  /* start after \n for multiline */
+#define PCRE_NOPARTIAL     0x0200  /* can't use partial with this regex */
+#define PCRE_JCHANGED      0x0400  /* j option used in regex */
+#define PCRE_HASCRORLF     0x0800  /* explicit \r or \n in pattern */
+#define PCRE_HASTHEN       0x1000  /* pattern contains (*THEN) */
+
+/* Flags for the "extra" block produced by pcre_study(). */
+
+#define PCRE_STUDY_MAPPED  0x0001  /* a map of starting chars exists */
+#define PCRE_STUDY_MINLEN  0x0002  /* a minimum length field exists */
+
+/* Masks for identifying the public options that are permitted at compile
+time, run time, or study time, respectively. */
+
+#define PCRE_NEWLINE_BITS (PCRE_NEWLINE_CR|PCRE_NEWLINE_LF|PCRE_NEWLINE_ANY| \
+                           PCRE_NEWLINE_ANYCRLF)
+
+#define PUBLIC_COMPILE_OPTIONS \
+  (PCRE_CASELESS|PCRE_EXTENDED|PCRE_ANCHORED|PCRE_MULTILINE| \
+   PCRE_DOTALL|PCRE_DOLLAR_ENDONLY|PCRE_EXTRA|PCRE_UNGREEDY|PCRE_UTF8| \
+   PCRE_NO_AUTO_CAPTURE|PCRE_NO_UTF8_CHECK|PCRE_AUTO_CALLOUT|PCRE_FIRSTLINE| \
+   PCRE_DUPNAMES|PCRE_NEWLINE_BITS|PCRE_BSR_ANYCRLF|PCRE_BSR_UNICODE| \
+   PCRE_JAVASCRIPT_COMPAT|PCRE_UCP|PCRE_NO_START_OPTIMIZE)
+
+#define PUBLIC_EXEC_OPTIONS \
+  (PCRE_ANCHORED|PCRE_NOTBOL|PCRE_NOTEOL|PCRE_NOTEMPTY|PCRE_NOTEMPTY_ATSTART| \
+   PCRE_NO_UTF8_CHECK|PCRE_PARTIAL_HARD|PCRE_PARTIAL_SOFT|PCRE_NEWLINE_BITS| \
+   PCRE_BSR_ANYCRLF|PCRE_BSR_UNICODE|PCRE_NO_START_OPTIMIZE)
+
+#define PUBLIC_DFA_EXEC_OPTIONS \
+  (PCRE_ANCHORED|PCRE_NOTBOL|PCRE_NOTEOL|PCRE_NOTEMPTY|PCRE_NOTEMPTY_ATSTART| \
+   PCRE_NO_UTF8_CHECK|PCRE_PARTIAL_HARD|PCRE_PARTIAL_SOFT|PCRE_DFA_SHORTEST| \
+   PCRE_DFA_RESTART|PCRE_NEWLINE_BITS|PCRE_BSR_ANYCRLF|PCRE_BSR_UNICODE| \
+   PCRE_NO_START_OPTIMIZE)
+
+#define PUBLIC_STUDY_OPTIONS \
+   (PCRE_STUDY_JIT_COMPILE|PCRE_STUDY_JIT_PARTIAL_SOFT_COMPILE| \
+    PCRE_STUDY_JIT_PARTIAL_HARD_COMPILE)
+
+/* Magic number to provide a small check against being handed junk. */
+
+#define MAGIC_NUMBER  0x50435245UL   /* 'PCRE' */
+
+/* This variable is used to detect a loaded regular expression
+in different endianness. */
+
+#define REVERSED_MAGIC_NUMBER  0x45524350UL   /* 'ERCP' */
+
+/* Negative values for the firstchar and reqchar variables */
+
+#define REQ_UNSET (-2)
+#define REQ_NONE  (-1)
+
+/* The maximum remaining length of subject we are prepared to search for a
+req_byte match. */
+
+#define REQ_BYTE_MAX 1000
+
+/* Miscellaneous definitions. The #ifndef is to pacify compiler warnings in
+environments where these macros are defined elsewhere. Unfortunately, there
+is no way to do the same for the typedef. */
+
+typedef int BOOL;
+
+#ifndef FALSE
+#define FALSE   0
+#define TRUE    1
+#endif
+
+/* If PCRE is to support UTF-8 on EBCDIC platforms, we cannot use normal
+character constants like '*' because the compiler would emit their EBCDIC code,
+which is different from their ASCII/UTF-8 code. Instead we define macros for
+the characters so that they always use the ASCII/UTF-8 code when UTF-8 support
+is enabled. When UTF-8 support is not enabled, the definitions use character
+literals. Both character and string versions of each character are needed, and
+there are some longer strings as well.
+
+This means that, on EBCDIC platforms, the PCRE library can handle either
+EBCDIC, or UTF-8, but not both. To support both in the same compiled library
+would need different lookups depending on whether PCRE_UTF8 was set or not.
+This would make it impossible to use characters in switch/case statements,
+which would reduce performance. For a theoretical use (which nobody has asked
+for) in a minority area (EBCDIC platforms), this is not sensible. Any
+application that did need both could compile two versions of the library, using
+macros to give the functions distinct names. */
+
+#ifndef SUPPORT_UTF
+
+/* UTF-8 support is not enabled; use the platform-dependent character literals
+so that PCRE works on both ASCII and EBCDIC platforms, in non-UTF-mode only. */
+
+#define CHAR_HT                     '\t'
+#define CHAR_VT                     '\v'
+#define CHAR_FF                     '\f'
+#define CHAR_CR                     '\r'
+#define CHAR_NL                     '\n'
+#define CHAR_BS                     '\b'
+#define CHAR_BEL                    '\a'
+#ifdef EBCDIC
+#define CHAR_ESC                    '\047'
+#define CHAR_DEL                    '\007'
+#else
+#define CHAR_ESC                    '\033'
+#define CHAR_DEL                    '\177'
+#endif
+
+#define CHAR_SPACE                  ' '
+#define CHAR_EXCLAMATION_MARK       '!'
+#define CHAR_QUOTATION_MARK         '"'
+#define CHAR_NUMBER_SIGN            '#'
+#define CHAR_DOLLAR_SIGN            '$'
+#define CHAR_PERCENT_SIGN           '%'
+#define CHAR_AMPERSAND              '&'
+#define CHAR_APOSTROPHE             '\''
+#define CHAR_LEFT_PARENTHESIS       '('
+#define CHAR_RIGHT_PARENTHESIS      ')'
+#define CHAR_ASTERISK               '*'
+#define CHAR_PLUS                   '+'
+#define CHAR_COMMA                  ','
+#define CHAR_MINUS                  '-'
+#define CHAR_DOT                    '.'
+#define CHAR_SLASH                  '/'
+#define CHAR_0                      '0'
+#define CHAR_1                      '1'
+#define CHAR_2                      '2'
+#define CHAR_3                      '3'
+#define CHAR_4                      '4'
+#define CHAR_5                      '5'
+#define CHAR_6                      '6'
+#define CHAR_7                      '7'
+#define CHAR_8                      '8'
+#define CHAR_9                      '9'
+#define CHAR_COLON                  ':'
+#define CHAR_SEMICOLON              ';'
+#define CHAR_LESS_THAN_SIGN         '<'
+#define CHAR_EQUALS_SIGN            '='
+#define CHAR_GREATER_THAN_SIGN      '>'
+#define CHAR_QUESTION_MARK          '?'
+#define CHAR_COMMERCIAL_AT          '@'
+#define CHAR_A                      'A'
+#define CHAR_B                      'B'
+#define CHAR_C                      'C'
+#define CHAR_D                      'D'
+#define CHAR_E                      'E'
+#define CHAR_F                      'F'
+#define CHAR_G                      'G'
+#define CHAR_H                      'H'
+#define CHAR_I                      'I'
+#define CHAR_J                      'J'
+#define CHAR_K                      'K'
+#define CHAR_L                      'L'
+#define CHAR_M                      'M'
+#define CHAR_N                      'N'
+#define CHAR_O                      'O'
+#define CHAR_P                      'P'
+#define CHAR_Q                      'Q'
+#define CHAR_R                      'R'
+#define CHAR_S                      'S'
+#define CHAR_T                      'T'
+#define CHAR_U                      'U'
+#define CHAR_V                      'V'
+#define CHAR_W                      'W'
+#define CHAR_X                      'X'
+#define CHAR_Y                      'Y'
+#define CHAR_Z                      'Z'
+#define CHAR_LEFT_SQUARE_BRACKET    '['
+#define CHAR_BACKSLASH              '\\'
+#define CHAR_RIGHT_SQUARE_BRACKET   ']'
+#define CHAR_CIRCUMFLEX_ACCENT      '^'
+#define CHAR_UNDERSCORE             '_'
+#define CHAR_GRAVE_ACCENT           '`'
+#define CHAR_a                      'a'
+#define CHAR_b                      'b'
+#define CHAR_c                      'c'
+#define CHAR_d                      'd'
+#define CHAR_e                      'e'
+#define CHAR_f                      'f'
+#define CHAR_g                      'g'
+#define CHAR_h                      'h'
+#define CHAR_i                      'i'
+#define CHAR_j                      'j'
+#define CHAR_k                      'k'
+#define CHAR_l                      'l'
+#define CHAR_m                      'm'
+#define CHAR_n                      'n'
+#define CHAR_o                      'o'
+#define CHAR_p                      'p'
+#define CHAR_q                      'q'
+#define CHAR_r                      'r'
+#define CHAR_s                      's'
+#define CHAR_t                      't'
+#define CHAR_u                      'u'
+#define CHAR_v                      'v'
+#define CHAR_w                      'w'
+#define CHAR_x                      'x'
+#define CHAR_y                      'y'
+#define CHAR_z                      'z'
+#define CHAR_LEFT_CURLY_BRACKET     '{'
+#define CHAR_VERTICAL_LINE          '|'
+#define CHAR_RIGHT_CURLY_BRACKET    '}'
+#define CHAR_TILDE                  '~'
+
+#define STR_HT                      "\t"
+#define STR_VT                      "\v"
+#define STR_FF                      "\f"
+#define STR_CR                      "\r"
+#define STR_NL                      "\n"
+#define STR_BS                      "\b"
+#define STR_BEL                     "\a"
+#ifdef EBCDIC
+#define STR_ESC                     "\047"
+#define STR_DEL                     "\007"
+#else
+#define STR_ESC                     "\033"
+#define STR_DEL                     "\177"
+#endif
+
+#define STR_SPACE                   " "
+#define STR_EXCLAMATION_MARK        "!"
+#define STR_QUOTATION_MARK          "\""
+#define STR_NUMBER_SIGN             "#"
+#define STR_DOLLAR_SIGN             "$"
+#define STR_PERCENT_SIGN            "%"
+#define STR_AMPERSAND               "&"
+#define STR_APOSTROPHE              "'"
+#define STR_LEFT_PARENTHESIS        "("
+#define STR_RIGHT_PARENTHESIS       ")"
+#define STR_ASTERISK                "*"
+#define STR_PLUS                    "+"
+#define STR_COMMA                   ","
+#define STR_MINUS                   "-"
+#define STR_DOT                     "."
+#define STR_SLASH                   "/"
+#define STR_0                       "0"
+#define STR_1                       "1"
+#define STR_2                       "2"
+#define STR_3                       "3"
+#define STR_4                       "4"
+#define STR_5                       "5"
+#define STR_6                       "6"
+#define STR_7                       "7"
+#define STR_8                       "8"
+#define STR_9                       "9"
+#define STR_COLON                   ":"
+#define STR_SEMICOLON               ";"
+#define STR_LESS_THAN_SIGN          "<"
+#define STR_EQUALS_SIGN             "="
+#define STR_GREATER_THAN_SIGN       ">"
+#define STR_QUESTION_MARK           "?"
+#define STR_COMMERCIAL_AT           "@"
+#define STR_A                       "A"
+#define STR_B                       "B"
+#define STR_C                       "C"
+#define STR_D                       "D"
+#define STR_E                       "E"
+#define STR_F                       "F"
+#define STR_G                       "G"
+#define STR_H                       "H"
+#define STR_I                       "I"
+#define STR_J                       "J"
+#define STR_K                       "K"
+#define STR_L                       "L"
+#define STR_M                       "M"
+#define STR_N                       "N"
+#define STR_O                       "O"
+#define STR_P                       "P"
+#define STR_Q                       "Q"
+#define STR_R                       "R"
+#define STR_S                       "S"
+#define STR_T                       "T"
+#define STR_U                       "U"
+#define STR_V                       "V"
+#define STR_W                       "W"
+#define STR_X                       "X"
+#define STR_Y                       "Y"
+#define STR_Z                       "Z"
+#define STR_LEFT_SQUARE_BRACKET     "["
+#define STR_BACKSLASH               "\\"
+#define STR_RIGHT_SQUARE_BRACKET    "]"
+#define STR_CIRCUMFLEX_ACCENT       "^"
+#define STR_UNDERSCORE              "_"
+#define STR_GRAVE_ACCENT            "`"
+#define STR_a                       "a"
+#define STR_b                       "b"
+#define STR_c                       "c"
+#define STR_d                       "d"
+#define STR_e                       "e"
+#define STR_f                       "f"
+#define STR_g                       "g"
+#define STR_h                       "h"
+#define STR_i                       "i"
+#define STR_j                       "j"
+#define STR_k                       "k"
+#define STR_l                       "l"
+#define STR_m                       "m"
+#define STR_n                       "n"
+#define STR_o                       "o"
+#define STR_p                       "p"
+#define STR_q                       "q"
+#define STR_r                       "r"
+#define STR_s                       "s"
+#define STR_t                       "t"
+#define STR_u                       "u"
+#define STR_v                       "v"
+#define STR_w                       "w"
+#define STR_x                       "x"
+#define STR_y                       "y"
+#define STR_z                       "z"
+#define STR_LEFT_CURLY_BRACKET      "{"
+#define STR_VERTICAL_LINE           "|"
+#define STR_RIGHT_CURLY_BRACKET     "}"
+#define STR_TILDE                   "~"
+
+#define STRING_ACCEPT0              "ACCEPT\0"
+#define STRING_COMMIT0              "COMMIT\0"
+#define STRING_F0                   "F\0"
+#define STRING_FAIL0                "FAIL\0"
+#define STRING_MARK0                "MARK\0"
+#define STRING_PRUNE0               "PRUNE\0"
+#define STRING_SKIP0                "SKIP\0"
+#define STRING_THEN                 "THEN"
+
+#define STRING_alpha0               "alpha\0"
+#define STRING_lower0               "lower\0"
+#define STRING_upper0               "upper\0"
+#define STRING_alnum0               "alnum\0"
+#define STRING_ascii0               "ascii\0"
+#define STRING_blank0               "blank\0"
+#define STRING_cntrl0               "cntrl\0"
+#define STRING_digit0               "digit\0"
+#define STRING_graph0               "graph\0"
+#define STRING_print0               "print\0"
+#define STRING_punct0               "punct\0"
+#define STRING_space0               "space\0"
+#define STRING_word0                "word\0"
+#define STRING_xdigit               "xdigit"
+
+#define STRING_DEFINE               "DEFINE"
+
+#define STRING_CR_RIGHTPAR             "CR)"
+#define STRING_LF_RIGHTPAR             "LF)"
+#define STRING_CRLF_RIGHTPAR           "CRLF)"
+#define STRING_ANY_RIGHTPAR            "ANY)"
+#define STRING_ANYCRLF_RIGHTPAR        "ANYCRLF)"
+#define STRING_BSR_ANYCRLF_RIGHTPAR    "BSR_ANYCRLF)"
+#define STRING_BSR_UNICODE_RIGHTPAR    "BSR_UNICODE)"
+#ifdef COMPILE_PCRE8
+#define STRING_UTF_RIGHTPAR            "UTF8)"
+#endif
+#ifdef COMPILE_PCRE16
+#define STRING_UTF_RIGHTPAR            "UTF16)"
+#endif
+#define STRING_UCP_RIGHTPAR            "UCP)"
+#define STRING_NO_START_OPT_RIGHTPAR   "NO_START_OPT)"
+
+#else  /* SUPPORT_UTF */
+
+/* UTF-8 support is enabled; always use UTF-8 (=ASCII) character codes. This
+works in both modes non-EBCDIC platforms, and on EBCDIC platforms in UTF-8 mode
+only. */
+
+#define CHAR_HT                     '\011'
+#define CHAR_VT                     '\013'
+#define CHAR_FF                     '\014'
+#define CHAR_CR                     '\015'
+#define CHAR_NL                     '\012'
+#define CHAR_BS                     '\010'
+#define CHAR_BEL                    '\007'
+#define CHAR_ESC                    '\033'
+#define CHAR_DEL                    '\177'
+
+#define CHAR_SPACE                  '\040'
+#define CHAR_EXCLAMATION_MARK       '\041'
+#define CHAR_QUOTATION_MARK         '\042'
+#define CHAR_NUMBER_SIGN            '\043'
+#define CHAR_DOLLAR_SIGN            '\044'
+#define CHAR_PERCENT_SIGN           '\045'
+#define CHAR_AMPERSAND              '\046'
+#define CHAR_APOSTROPHE             '\047'
+#define CHAR_LEFT_PARENTHESIS       '\050'
+#define CHAR_RIGHT_PARENTHESIS      '\051'
+#define CHAR_ASTERISK               '\052'
+#define CHAR_PLUS                   '\053'
+#define CHAR_COMMA                  '\054'
+#define CHAR_MINUS                  '\055'
+#define CHAR_DOT                    '\056'
+#define CHAR_SLASH                  '\057'
+#define CHAR_0                      '\060'
+#define CHAR_1                      '\061'
+#define CHAR_2                      '\062'
+#define CHAR_3                      '\063'
+#define CHAR_4                      '\064'
+#define CHAR_5                      '\065'
+#define CHAR_6                      '\066'
+#define CHAR_7                      '\067'
+#define CHAR_8                      '\070'
+#define CHAR_9                      '\071'
+#define CHAR_COLON                  '\072'
+#define CHAR_SEMICOLON              '\073'
+#define CHAR_LESS_THAN_SIGN         '\074'
+#define CHAR_EQUALS_SIGN            '\075'
+#define CHAR_GREATER_THAN_SIGN      '\076'
+#define CHAR_QUESTION_MARK          '\077'
+#define CHAR_COMMERCIAL_AT          '\100'
+#define CHAR_A                      '\101'
+#define CHAR_B                      '\102'
+#define CHAR_C                      '\103'
+#define CHAR_D                      '\104'
+#define CHAR_E                      '\105'
+#define CHAR_F                      '\106'
+#define CHAR_G                      '\107'
+#define CHAR_H                      '\110'
+#define CHAR_I                      '\111'
+#define CHAR_J                      '\112'
+#define CHAR_K                      '\113'
+#define CHAR_L                      '\114'
+#define CHAR_M                      '\115'
+#define CHAR_N                      '\116'
+#define CHAR_O                      '\117'
+#define CHAR_P                      '\120'
+#define CHAR_Q                      '\121'
+#define CHAR_R                      '\122'
+#define CHAR_S                      '\123'
+#define CHAR_T                      '\124'
+#define CHAR_U                      '\125'
+#define CHAR_V                      '\126'
+#define CHAR_W                      '\127'
+#define CHAR_X                      '\130'
+#define CHAR_Y                      '\131'
+#define CHAR_Z                      '\132'
+#define CHAR_LEFT_SQUARE_BRACKET    '\133'
+#define CHAR_BACKSLASH              '\134'
+#define CHAR_RIGHT_SQUARE_BRACKET   '\135'
+#define CHAR_CIRCUMFLEX_ACCENT      '\136'
+#define CHAR_UNDERSCORE             '\137'
+#define CHAR_GRAVE_ACCENT           '\140'
+#define CHAR_a                      '\141'
+#define CHAR_b                      '\142'
+#define CHAR_c                      '\143'
+#define CHAR_d                      '\144'
+#define CHAR_e                      '\145'
+#define CHAR_f                      '\146'
+#define CHAR_g                      '\147'
+#define CHAR_h                      '\150'
+#define CHAR_i                      '\151'
+#define CHAR_j                      '\152'
+#define CHAR_k                      '\153'
+#define CHAR_l                      '\154'
+#define CHAR_m                      '\155'
+#define CHAR_n                      '\156'
+#define CHAR_o                      '\157'
+#define CHAR_p                      '\160'
+#define CHAR_q                      '\161'
+#define CHAR_r                      '\162'
+#define CHAR_s                      '\163'
+#define CHAR_t                      '\164'
+#define CHAR_u                      '\165'
+#define CHAR_v                      '\166'
+#define CHAR_w                      '\167'
+#define CHAR_x                      '\170'
+#define CHAR_y                      '\171'
+#define CHAR_z                      '\172'
+#define CHAR_LEFT_CURLY_BRACKET     '\173'
+#define CHAR_VERTICAL_LINE          '\174'
+#define CHAR_RIGHT_CURLY_BRACKET    '\175'
+#define CHAR_TILDE                  '\176'
+
+#define STR_HT                      "\011"
+#define STR_VT                      "\013"
+#define STR_FF                      "\014"
+#define STR_CR                      "\015"
+#define STR_NL                      "\012"
+#define STR_BS                      "\010"
+#define STR_BEL                     "\007"
+#define STR_ESC                     "\033"
+#define STR_DEL                     "\177"
+
+#define STR_SPACE                   "\040"
+#define STR_EXCLAMATION_MARK        "\041"
+#define STR_QUOTATION_MARK          "\042"
+#define STR_NUMBER_SIGN             "\043"
+#define STR_DOLLAR_SIGN             "\044"
+#define STR_PERCENT_SIGN            "\045"
+#define STR_AMPERSAND               "\046"
+#define STR_APOSTROPHE              "\047"
+#define STR_LEFT_PARENTHESIS        "\050"
+#define STR_RIGHT_PARENTHESIS       "\051"
+#define STR_ASTERISK                "\052"
+#define STR_PLUS                    "\053"
+#define STR_COMMA                   "\054"
+#define STR_MINUS                   "\055"
+#define STR_DOT                     "\056"
+#define STR_SLASH                   "\057"
+#define STR_0                       "\060"
+#define STR_1                       "\061"
+#define STR_2                       "\062"
+#define STR_3                       "\063"
+#define STR_4                       "\064"
+#define STR_5                       "\065"
+#define STR_6                       "\066"
+#define STR_7                       "\067"
+#define STR_8                       "\070"
+#define STR_9                       "\071"
+#define STR_COLON                   "\072"
+#define STR_SEMICOLON               "\073"
+#define STR_LESS_THAN_SIGN          "\074"
+#define STR_EQUALS_SIGN             "\075"
+#define STR_GREATER_THAN_SIGN       "\076"
+#define STR_QUESTION_MARK           "\077"
+#define STR_COMMERCIAL_AT           "\100"
+#define STR_A                       "\101"
+#define STR_B                       "\102"
+#define STR_C                       "\103"
+#define STR_D                       "\104"
+#define STR_E                       "\105"
+#define STR_F                       "\106"
+#define STR_G                       "\107"
+#define STR_H                       "\110"
+#define STR_I                       "\111"
+#define STR_J                       "\112"
+#define STR_K                       "\113"
+#define STR_L                       "\114"
+#define STR_M                       "\115"
+#define STR_N                       "\116"
+#define STR_O                       "\117"
+#define STR_P                       "\120"
+#define STR_Q                       "\121"
+#define STR_R                       "\122"
+#define STR_S                       "\123"
+#define STR_T                       "\124"
+#define STR_U                       "\125"
+#define STR_V                       "\126"
+#define STR_W                       "\127"
+#define STR_X                       "\130"
+#define STR_Y                       "\131"
+#define STR_Z                       "\132"
+#define STR_LEFT_SQUARE_BRACKET     "\133"
+#define STR_BACKSLASH               "\134"
+#define STR_RIGHT_SQUARE_BRACKET    "\135"
+#define STR_CIRCUMFLEX_ACCENT       "\136"
+#define STR_UNDERSCORE              "\137"
+#define STR_GRAVE_ACCENT            "\140"
+#define STR_a                       "\141"
+#define STR_b                       "\142"
+#define STR_c                       "\143"
+#define STR_d                       "\144"
+#define STR_e                       "\145"
+#define STR_f                       "\146"
+#define STR_g                       "\147"
+#define STR_h                       "\150"
+#define STR_i                       "\151"
+#define STR_j                       "\152"
+#define STR_k                       "\153"
+#define STR_l                       "\154"
+#define STR_m                       "\155"
+#define STR_n                       "\156"
+#define STR_o                       "\157"
+#define STR_p                       "\160"
+#define STR_q                       "\161"
+#define STR_r                       "\162"
+#define STR_s                       "\163"
+#define STR_t                       "\164"
+#define STR_u                       "\165"
+#define STR_v                       "\166"
+#define STR_w                       "\167"
+#define STR_x                       "\170"
+#define STR_y                       "\171"
+#define STR_z                       "\172"
+#define STR_LEFT_CURLY_BRACKET      "\173"
+#define STR_VERTICAL_LINE           "\174"
+#define STR_RIGHT_CURLY_BRACKET     "\175"
+#define STR_TILDE                   "\176"
+
+#define STRING_ACCEPT0              STR_A STR_C STR_C STR_E STR_P STR_T "\0"
+#define STRING_COMMIT0              STR_C STR_O STR_M STR_M STR_I STR_T "\0"
+#define STRING_F0                   STR_F "\0"
+#define STRING_FAIL0                STR_F STR_A STR_I STR_L "\0"
+#define STRING_MARK0                STR_M STR_A STR_R STR_K "\0"
+#define STRING_PRUNE0               STR_P STR_R STR_U STR_N STR_E "\0"
+#define STRING_SKIP0                STR_S STR_K STR_I STR_P "\0"
+#define STRING_THEN                 STR_T STR_H STR_E STR_N
+
+#define STRING_alpha0               STR_a STR_l STR_p STR_h STR_a "\0"
+#define STRING_lower0               STR_l STR_o STR_w STR_e STR_r "\0"
+#define STRING_upper0               STR_u STR_p STR_p STR_e STR_r "\0"
+#define STRING_alnum0               STR_a STR_l STR_n STR_u STR_m "\0"
+#define STRING_ascii0               STR_a STR_s STR_c STR_i STR_i "\0"
+#define STRING_blank0               STR_b STR_l STR_a STR_n STR_k "\0"
+#define STRING_cntrl0               STR_c STR_n STR_t STR_r STR_l "\0"
+#define STRING_digit0               STR_d STR_i STR_g STR_i STR_t "\0"
+#define STRING_graph0               STR_g STR_r STR_a STR_p STR_h "\0"
+#define STRING_print0               STR_p STR_r STR_i STR_n STR_t "\0"
+#define STRING_punct0               STR_p STR_u STR_n STR_c STR_t "\0"
+#define STRING_space0               STR_s STR_p STR_a STR_c STR_e "\0"
+#define STRING_word0                STR_w STR_o STR_r STR_d       "\0"
+#define STRING_xdigit               STR_x STR_d STR_i STR_g STR_i STR_t
+
+#define STRING_DEFINE               STR_D STR_E STR_F STR_I STR_N STR_E
+
+#define STRING_CR_RIGHTPAR             STR_C STR_R STR_RIGHT_PARENTHESIS
+#define STRING_LF_RIGHTPAR             STR_L STR_F STR_RIGHT_PARENTHESIS
+#define STRING_CRLF_RIGHTPAR           STR_C STR_R STR_L STR_F STR_RIGHT_PARENTHESIS
+#define STRING_ANY_RIGHTPAR            STR_A STR_N STR_Y STR_RIGHT_PARENTHESIS
+#define STRING_ANYCRLF_RIGHTPAR        STR_A STR_N STR_Y STR_C STR_R STR_L STR_F STR_RIGHT_PARENTHESIS
+#define STRING_BSR_ANYCRLF_RIGHTPAR    STR_B STR_S STR_R STR_UNDERSCORE STR_A STR_N STR_Y STR_C STR_R STR_L STR_F STR_RIGHT_PARENTHESIS
+#define STRING_BSR_UNICODE_RIGHTPAR    STR_B STR_S STR_R STR_UNDERSCORE STR_U STR_N STR_I STR_C STR_O STR_D STR_E STR_RIGHT_PARENTHESIS
+#ifdef COMPILE_PCRE8
+#define STRING_UTF_RIGHTPAR            STR_U STR_T STR_F STR_8 STR_RIGHT_PARENTHESIS
+#endif
+#ifdef COMPILE_PCRE16
+#define STRING_UTF_RIGHTPAR            STR_U STR_T STR_F STR_1 STR_6 STR_RIGHT_PARENTHESIS
+#endif
+#define STRING_UCP_RIGHTPAR            STR_U STR_C STR_P STR_RIGHT_PARENTHESIS
+#define STRING_NO_START_OPT_RIGHTPAR   STR_N STR_O STR_UNDERSCORE STR_S STR_T STR_A STR_R STR_T STR_UNDERSCORE STR_O STR_P STR_T STR_RIGHT_PARENTHESIS
+
+#endif  /* SUPPORT_UTF */
+
+/* Escape items that are just an encoding of a particular data value. */
+
+#ifndef ESC_e
+#define ESC_e CHAR_ESC
+#endif
+
+#ifndef ESC_f
+#define ESC_f CHAR_FF
+#endif
+
+#ifndef ESC_n
+#define ESC_n CHAR_NL
+#endif
+
+#ifndef ESC_r
+#define ESC_r CHAR_CR
+#endif
+
+/* We can't officially use ESC_t because it is a POSIX reserved identifier
+(presumably because of all the others like size_t). */
+
+#ifndef ESC_tee
+#define ESC_tee CHAR_HT
+#endif
+
+/* Codes for different types of Unicode property */
+
+#define PT_ANY        0    /* Any property - matches all chars */
+#define PT_LAMP       1    /* L& - the union of Lu, Ll, Lt */
+#define PT_GC         2    /* Specified general characteristic (e.g. L) */
+#define PT_PC         3    /* Specified particular characteristic (e.g. Lu) */
+#define PT_SC         4    /* Script (e.g. Han) */
+#define PT_ALNUM      5    /* Alphanumeric - the union of L and N */
+#define PT_SPACE      6    /* Perl space - Z plus 9,10,12,13 */
+#define PT_PXSPACE    7    /* POSIX space - Z plus 9,10,11,12,13 */
+#define PT_WORD       8    /* Word - L plus N plus underscore */
+
+/* Flag bits and data types for the extended class (OP_XCLASS) for classes that
+contain characters with values greater than 255. */
+
+#define XCL_NOT    0x01    /* Flag: this is a negative class */
+#define XCL_MAP    0x02    /* Flag: a 32-byte map is present */
+
+#define XCL_END       0    /* Marks end of individual items */
+#define XCL_SINGLE    1    /* Single item (one multibyte char) follows */
+#define XCL_RANGE     2    /* A range (two multibyte chars) follows */
+#define XCL_PROP      3    /* Unicode property (2-byte property code follows) */
+#define XCL_NOTPROP   4    /* Unicode inverted property (ditto) */
+
+/* These are escaped items that aren't just an encoding of a particular data
+value such as \n. They must have non-zero values, as check_escape() returns
+their negation. Also, they must appear in the same order as in the opcode
+definitions below, up to ESC_z. There's a dummy for OP_ALLANY because it
+corresponds to "." in DOTALL mode rather than an escape sequence. It is also
+used for [^] in JavaScript compatibility mode, and for \C in non-utf mode. In
+non-DOTALL mode, "." behaves like \N.
+
+The special values ESC_DU, ESC_du, etc. are used instead of ESC_D, ESC_d, etc.
+when PCRE_UCP is set, when replacement of \d etc by \p sequences is required.
+They must be contiguous, and remain in order so that the replacements can be
+looked up from a table.
+
+The final escape must be ESC_REF as subsequent values are used for
+backreferences (\1, \2, \3, etc). There are two tests in the code for an escape
+greater than ESC_b and less than ESC_Z to detect the types that may be
+repeated. These are the types that consume characters. If any new escapes are
+put in between that don't consume a character, that code will have to change.
+*/
+
+enum { ESC_A = 1, ESC_G, ESC_K, ESC_B, ESC_b, ESC_D, ESC_d, ESC_S, ESC_s,
+       ESC_W, ESC_w, ESC_N, ESC_dum, ESC_C, ESC_P, ESC_p, ESC_R, ESC_H,
+       ESC_h, ESC_V, ESC_v, ESC_X, ESC_Z, ESC_z,
+       ESC_E, ESC_Q, ESC_g, ESC_k,
+       ESC_DU, ESC_du, ESC_SU, ESC_su, ESC_WU, ESC_wu,
+       ESC_REF };
+
+/* Opcode table: Starting from 1 (i.e. after OP_END), the values up to
+OP_EOD must correspond in order to the list of escapes immediately above.
+
+*** NOTE NOTE NOTE *** Whenever this list is updated, the two macro definitions
+that follow must also be updated to match. There are also tables called
+"coptable" and "poptable" in pcre_dfa_exec.c that must be updated. */
+
+enum {
+  OP_END,            /* 0 End of pattern */
+
+  /* Values corresponding to backslashed metacharacters */
+
+  OP_SOD,            /* 1 Start of data: \A */
+  OP_SOM,            /* 2 Start of match (subject + offset): \G */
+  OP_SET_SOM,        /* 3 Set start of match (\K) */
+  OP_NOT_WORD_BOUNDARY,  /*  4 \B */
+  OP_WORD_BOUNDARY,      /*  5 \b */
+  OP_NOT_DIGIT,          /*  6 \D */
+  OP_DIGIT,              /*  7 \d */
+  OP_NOT_WHITESPACE,     /*  8 \S */
+  OP_WHITESPACE,         /*  9 \s */
+  OP_NOT_WORDCHAR,       /* 10 \W */
+  OP_WORDCHAR,           /* 11 \w */
+
+  OP_ANY,            /* 12 Match any character except newline */
+  OP_ALLANY,         /* 13 Match any character */
+  OP_ANYBYTE,        /* 14 Match any byte (\C); different to OP_ANY for UTF-8 */
+  OP_NOTPROP,        /* 15 \P (not Unicode property) */
+  OP_PROP,           /* 16 \p (Unicode property) */
+  OP_ANYNL,          /* 17 \R (any newline sequence) */
+  OP_NOT_HSPACE,     /* 18 \H (not horizontal whitespace) */
+  OP_HSPACE,         /* 19 \h (horizontal whitespace) */
+  OP_NOT_VSPACE,     /* 20 \V (not vertical whitespace) */
+  OP_VSPACE,         /* 21 \v (vertical whitespace) */
+  OP_EXTUNI,         /* 22 \X (extended Unicode sequence */
+  OP_EODN,           /* 23 End of data or \n at end of data: \Z. */
+  OP_EOD,            /* 24 End of data: \z */
+
+  OP_CIRC,           /* 25 Start of line - not multiline */
+  OP_CIRCM,          /* 26 Start of line - multiline */
+  OP_DOLL,           /* 27 End of line - not multiline */
+  OP_DOLLM,          /* 28 End of line - multiline */
+  OP_CHAR,           /* 29 Match one character, casefully */
+  OP_CHARI,          /* 30 Match one character, caselessly */
+  OP_NOT,            /* 31 Match one character, not the given one, casefully */
+  OP_NOTI,           /* 32 Match one character, not the given one, caselessly */
+
+  /* The following sets of 13 opcodes must always be kept in step because
+  the offset from the first one is used to generate the others. */
+
+  /**** Single characters, caseful, must precede the caseless ones ****/
+
+  OP_STAR,           /* 33 The maximizing and minimizing versions of */
+  OP_MINSTAR,        /* 34 these six opcodes must come in pairs, with */
+  OP_PLUS,           /* 35 the minimizing one second. */
+  OP_MINPLUS,        /* 36 */
+  OP_QUERY,          /* 37 */
+  OP_MINQUERY,       /* 38 */
+
+  OP_UPTO,           /* 39 From 0 to n matches of one character, caseful*/
+  OP_MINUPTO,        /* 40 */
+  OP_EXACT,          /* 41 Exactly n matches */
+
+  OP_POSSTAR,        /* 42 Possessified star, caseful */
+  OP_POSPLUS,        /* 43 Possessified plus, caseful */
+  OP_POSQUERY,       /* 44 Posesssified query, caseful */
+  OP_POSUPTO,        /* 45 Possessified upto, caseful */
+
+  /**** Single characters, caseless, must follow the caseful ones */
+
+  OP_STARI,          /* 46 */
+  OP_MINSTARI,       /* 47 */
+  OP_PLUSI,          /* 48 */
+  OP_MINPLUSI,       /* 49 */
+  OP_QUERYI,         /* 50 */
+  OP_MINQUERYI,      /* 51 */
+
+  OP_UPTOI,          /* 52 From 0 to n matches of one character, caseless */
+  OP_MINUPTOI,       /* 53 */
+  OP_EXACTI,         /* 54 */
+
+  OP_POSSTARI,       /* 55 Possessified star, caseless */
+  OP_POSPLUSI,       /* 56 Possessified plus, caseless */
+  OP_POSQUERYI,      /* 57 Posesssified query, caseless */
+  OP_POSUPTOI,       /* 58 Possessified upto, caseless */
+
+  /**** The negated ones must follow the non-negated ones, and match them ****/
+  /**** Negated single character, caseful; must precede the caseless ones ****/
+
+  OP_NOTSTAR,        /* 59 The maximizing and minimizing versions of */
+  OP_NOTMINSTAR,     /* 60 these six opcodes must come in pairs, with */
+  OP_NOTPLUS,        /* 61 the minimizing one second. They must be in */
+  OP_NOTMINPLUS,     /* 62 exactly the same order as those above. */
+  OP_NOTQUERY,       /* 63 */
+  OP_NOTMINQUERY,    /* 64 */
+
+  OP_NOTUPTO,        /* 65 From 0 to n matches, caseful */
+  OP_NOTMINUPTO,     /* 66 */
+  OP_NOTEXACT,       /* 67 Exactly n matches */
+
+  OP_NOTPOSSTAR,     /* 68 Possessified versions, caseful */
+  OP_NOTPOSPLUS,     /* 69 */
+  OP_NOTPOSQUERY,    /* 70 */
+  OP_NOTPOSUPTO,     /* 71 */
+
+  /**** Negated single character, caseless; must follow the caseful ones ****/
+
+  OP_NOTSTARI,       /* 72 */
+  OP_NOTMINSTARI,    /* 73 */
+  OP_NOTPLUSI,       /* 74 */
+  OP_NOTMINPLUSI,    /* 75 */
+  OP_NOTQUERYI,      /* 76 */
+  OP_NOTMINQUERYI,   /* 77 */
+
+  OP_NOTUPTOI,       /* 78 From 0 to n matches, caseless */
+  OP_NOTMINUPTOI,    /* 79 */
+  OP_NOTEXACTI,      /* 80 Exactly n matches */
+
+  OP_NOTPOSSTARI,    /* 81 Possessified versions, caseless */
+  OP_NOTPOSPLUSI,    /* 82 */
+  OP_NOTPOSQUERYI,   /* 83 */
+  OP_NOTPOSUPTOI,    /* 84 */
+
+  /**** Character types ****/
+
+  OP_TYPESTAR,       /* 85 The maximizing and minimizing versions of */
+  OP_TYPEMINSTAR,    /* 86 these six opcodes must come in pairs, with */
+  OP_TYPEPLUS,       /* 87 the minimizing one second. These codes must */
+  OP_TYPEMINPLUS,    /* 88 be in exactly the same order as those above. */
+  OP_TYPEQUERY,      /* 89 */
+  OP_TYPEMINQUERY,   /* 90 */
+
+  OP_TYPEUPTO,       /* 91 From 0 to n matches */
+  OP_TYPEMINUPTO,    /* 92 */
+  OP_TYPEEXACT,      /* 93 Exactly n matches */
+
+  OP_TYPEPOSSTAR,    /* 94 Possessified versions */
+  OP_TYPEPOSPLUS,    /* 95 */
+  OP_TYPEPOSQUERY,   /* 96 */
+  OP_TYPEPOSUPTO,    /* 97 */
+
+  /* These are used for character classes and back references; only the
+  first six are the same as the sets above. */
+
+  OP_CRSTAR,         /* 98 The maximizing and minimizing versions of */
+  OP_CRMINSTAR,      /* 99 all these opcodes must come in pairs, with */
+  OP_CRPLUS,         /* 100 the minimizing one second. These codes must */
+  OP_CRMINPLUS,      /* 101 be in exactly the same order as those above. */
+  OP_CRQUERY,        /* 102 */
+  OP_CRMINQUERY,     /* 103 */
+
+  OP_CRRANGE,        /* 104 These are different to the three sets above. */
+  OP_CRMINRANGE,     /* 105 */
+
+  /* End of quantifier opcodes */
+
+  OP_CLASS,          /* 106 Match a character class, chars < 256 only */
+  OP_NCLASS,         /* 107 Same, but the bitmap was created from a negative
+                              class - the difference is relevant only when a
+                              character > 255 is encountered. */
+  OP_XCLASS,         /* 108 Extended class for handling > 255 chars within the
+                              class. This does both positive and negative. */
+  OP_REF,            /* 109 Match a back reference, casefully */
+  OP_REFI,           /* 110 Match a back reference, caselessly */
+  OP_RECURSE,        /* 111 Match a numbered subpattern (possibly recursive) */
+  OP_CALLOUT,        /* 112 Call out to external function if provided */
+
+  OP_ALT,            /* 113 Start of alternation */
+  OP_KET,            /* 114 End of group that doesn't have an unbounded repeat */
+  OP_KETRMAX,        /* 115 These two must remain together and in this */
+  OP_KETRMIN,        /* 116 order. They are for groups the repeat for ever. */
+  OP_KETRPOS,        /* 117 Possessive unlimited repeat. */
+
+  /* The assertions must come before BRA, CBRA, ONCE, and COND, and the four
+  asserts must remain in order. */
+
+  OP_REVERSE,        /* 118 Move pointer back - used in lookbehind assertions */
+  OP_ASSERT,         /* 119 Positive lookahead */
+  OP_ASSERT_NOT,     /* 120 Negative lookahead */
+  OP_ASSERTBACK,     /* 121 Positive lookbehind */
+  OP_ASSERTBACK_NOT, /* 122 Negative lookbehind */
+
+  /* ONCE, ONCE_NC, BRA, BRAPOS, CBRA, CBRAPOS, and COND must come immediately
+  after the assertions, with ONCE first, as there's a test for >= ONCE for a
+  subpattern that isn't an assertion. The POS versions must immediately follow
+  the non-POS versions in each case. */
+
+  OP_ONCE,           /* 123 Atomic group, contains captures */
+  OP_ONCE_NC,        /* 124 Atomic group containing no captures */
+  OP_BRA,            /* 125 Start of non-capturing bracket */
+  OP_BRAPOS,         /* 126 Ditto, with unlimited, possessive repeat */
+  OP_CBRA,           /* 127 Start of capturing bracket */
+  OP_CBRAPOS,        /* 128 Ditto, with unlimited, possessive repeat */
+  OP_COND,           /* 129 Conditional group */
+
+  /* These five must follow the previous five, in the same order. There's a
+  check for >= SBRA to distinguish the two sets. */
+
+  OP_SBRA,           /* 130 Start of non-capturing bracket, check empty  */
+  OP_SBRAPOS,        /* 131 Ditto, with unlimited, possessive repeat */
+  OP_SCBRA,          /* 132 Start of capturing bracket, check empty */
+  OP_SCBRAPOS,       /* 133 Ditto, with unlimited, possessive repeat */
+  OP_SCOND,          /* 134 Conditional group, check empty */
+
+  /* The next two pairs must (respectively) be kept together. */
+
+  OP_CREF,           /* 135 Used to hold a capture number as condition */
+  OP_NCREF,          /* 136 Same, but generated by a name reference*/
+  OP_RREF,           /* 137 Used to hold a recursion number as condition */
+  OP_NRREF,          /* 138 Same, but generated by a name reference*/
+  OP_DEF,            /* 139 The DEFINE condition */
+
+  OP_BRAZERO,        /* 140 These two must remain together and in this */
+  OP_BRAMINZERO,     /* 141 order. */
+  OP_BRAPOSZERO,     /* 142 */
+
+  /* These are backtracking control verbs */
+
+  OP_MARK,           /* 143 always has an argument */
+  OP_PRUNE,          /* 144 */
+  OP_PRUNE_ARG,      /* 145 same, but with argument */
+  OP_SKIP,           /* 146 */
+  OP_SKIP_ARG,       /* 147 same, but with argument */
+  OP_THEN,           /* 148 */
+  OP_THEN_ARG,       /* 149 same, but with argument */
+  OP_COMMIT,         /* 150 */
+
+  /* These are forced failure and success verbs */
+
+  OP_FAIL,           /* 151 */
+  OP_ACCEPT,         /* 152 */
+  OP_ASSERT_ACCEPT,  /* 153 Used inside assertions */
+  OP_CLOSE,          /* 154 Used before OP_ACCEPT to close open captures */
+
+  /* This is used to skip a subpattern with a {0} quantifier */
+
+  OP_SKIPZERO,       /* 155 */
+
+  /* This is not an opcode, but is used to check that tables indexed by opcode
+  are the correct length, in order to catch updating errors - there have been
+  some in the past. */
+
+  OP_TABLE_LENGTH
+};
+
+/* *** NOTE NOTE NOTE *** Whenever the list above is updated, the two macro
+definitions that follow must also be updated to match. There are also tables
+called "coptable" and "poptable" in pcre_dfa_exec.c that must be updated. */
+
+
+/* This macro defines textual names for all the opcodes. These are used only
+for debugging, and some of them are only partial names. The macro is referenced
+only in pcre_printint.c, which fills out the full names in many cases (and in
+some cases doesn't actually use these names at all). */
+
+#define OP_NAME_LIST \
+  "End", "\\A", "\\G", "\\K", "\\B", "\\b", "\\D", "\\d",         \
+  "\\S", "\\s", "\\W", "\\w", "Any", "AllAny", "Anybyte",         \
+  "notprop", "prop", "\\R", "\\H", "\\h", "\\V", "\\v",           \
+  "extuni",  "\\Z", "\\z",                                        \
+  "^", "^", "$", "$", "char", "chari", "not", "noti",             \
+  "*", "*?", "+", "+?", "?", "??",                                \
+  "{", "{", "{",                                                  \
+  "*+","++", "?+", "{",                                           \
+  "*", "*?", "+", "+?", "?", "??",                                \
+  "{", "{", "{",                                                  \
+  "*+","++", "?+", "{",                                           \
+  "*", "*?", "+", "+?", "?", "??",                                \
+  "{", "{", "{",                                                  \
+  "*+","++", "?+", "{",                                           \
+  "*", "*?", "+", "+?", "?", "??",                                \
+  "{", "{", "{",                                                  \
+  "*+","++", "?+", "{",                                           \
+  "*", "*?", "+", "+?", "?", "??", "{", "{", "{",                 \
+  "*+","++", "?+", "{",                                           \
+  "*", "*?", "+", "+?", "?", "??", "{", "{",                      \
+  "class", "nclass", "xclass", "Ref", "Refi",                     \
+  "Recurse", "Callout",                                           \
+  "Alt", "Ket", "KetRmax", "KetRmin", "KetRpos",                  \
+  "Reverse", "Assert", "Assert not", "AssertB", "AssertB not",    \
+  "Once", "Once_NC",                                              \
+  "Bra", "BraPos", "CBra", "CBraPos",                             \
+  "Cond",                                                         \
+  "SBra", "SBraPos", "SCBra", "SCBraPos",                         \
+  "SCond",                                                        \
+  "Cond ref", "Cond nref", "Cond rec", "Cond nrec", "Cond def",   \
+  "Brazero", "Braminzero", "Braposzero",                          \
+  "*MARK", "*PRUNE", "*PRUNE", "*SKIP", "*SKIP",                  \
+  "*THEN", "*THEN", "*COMMIT", "*FAIL",                           \
+  "*ACCEPT", "*ASSERT_ACCEPT",                                    \
+  "Close", "Skip zero"
+
+
+/* This macro defines the length of fixed length operations in the compiled
+regex. The lengths are used when searching for specific things, and also in the
+debugging printing of a compiled regex. We use a macro so that it can be
+defined close to the definitions of the opcodes themselves.
+
+As things have been extended, some of these are no longer fixed lenths, but are
+minima instead. For example, the length of a single-character repeat may vary
+in UTF-8 mode. The code that uses this table must know about such things. */
+
+#define OP_LENGTHS \
+  1,                             /* End                                    */ \
+  1, 1, 1, 1, 1,                 /* \A, \G, \K, \B, \b                     */ \
+  1, 1, 1, 1, 1, 1,              /* \D, \d, \S, \s, \W, \w                 */ \
+  1, 1, 1,                       /* Any, AllAny, Anybyte                   */ \
+  3, 3,                          /* \P, \p                                 */ \
+  1, 1, 1, 1, 1,                 /* \R, \H, \h, \V, \v                     */ \
+  1,                             /* \X                                     */ \
+  1, 1, 1, 1, 1, 1,              /* \Z, \z, ^, ^M, $, $M                   */ \
+  2,                             /* Char  - the minimum length             */ \
+  2,                             /* Chari  - the minimum length            */ \
+  2,                             /* not                                    */ \
+  2,                             /* noti                                   */ \
+  /* Positive single-char repeats                             ** These are */ \
+  2, 2, 2, 2, 2, 2,              /* *, *?, +, +?, ?, ??       ** minima in */ \
+  2+IMM2_SIZE, 2+IMM2_SIZE,      /* upto, minupto             ** mode      */ \
+  2+IMM2_SIZE,                   /* exact                                  */ \
+  2, 2, 2, 2+IMM2_SIZE,          /* *+, ++, ?+, upto+                      */ \
+  2, 2, 2, 2, 2, 2,              /* *I, *?I, +I, +?I, ?I, ??I ** UTF-8     */ \
+  2+IMM2_SIZE, 2+IMM2_SIZE,      /* upto I, minupto I                      */ \
+  2+IMM2_SIZE,                   /* exact I                                */ \
+  2, 2, 2, 2+IMM2_SIZE,          /* *+I, ++I, ?+I, upto+I                  */ \
+  /* Negative single-char repeats - only for chars < 256                   */ \
+  2, 2, 2, 2, 2, 2,              /* NOT *, *?, +, +?, ?, ??                */ \
+  2+IMM2_SIZE, 2+IMM2_SIZE,      /* NOT upto, minupto                      */ \
+  2+IMM2_SIZE,                   /* NOT exact                              */ \
+  2, 2, 2, 2+IMM2_SIZE,          /* Possessive NOT *, +, ?, upto           */ \
+  2, 2, 2, 2, 2, 2,              /* NOT *I, *?I, +I, +?I, ?I, ??I          */ \
+  2+IMM2_SIZE, 2+IMM2_SIZE,      /* NOT upto I, minupto I                  */ \
+  2+IMM2_SIZE,                   /* NOT exact I                            */ \
+  2, 2, 2, 2+IMM2_SIZE,          /* Possessive NOT *I, +I, ?I, upto I      */ \
+  /* Positive type repeats                                                 */ \
+  2, 2, 2, 2, 2, 2,              /* Type *, *?, +, +?, ?, ??               */ \
+  2+IMM2_SIZE, 2+IMM2_SIZE,      /* Type upto, minupto                     */ \
+  2+IMM2_SIZE,                   /* Type exact                             */ \
+  2, 2, 2, 2+IMM2_SIZE,          /* Possessive *+, ++, ?+, upto+           */ \
+  /* Character class & ref repeats                                         */ \
+  1, 1, 1, 1, 1, 1,              /* *, *?, +, +?, ?, ??                    */ \
+  1+2*IMM2_SIZE, 1+2*IMM2_SIZE,  /* CRRANGE, CRMINRANGE                    */ \
+  1+(32/sizeof(pcre_uchar)),     /* CLASS                                  */ \
+  1+(32/sizeof(pcre_uchar)),     /* NCLASS                                 */ \
+  0,                             /* XCLASS - variable length               */ \
+  1+IMM2_SIZE,                   /* REF                                    */ \
+  1+IMM2_SIZE,                   /* REFI                                   */ \
+  1+LINK_SIZE,                   /* RECURSE                                */ \
+  2+2*LINK_SIZE,                 /* CALLOUT                                */ \
+  1+LINK_SIZE,                   /* Alt                                    */ \
+  1+LINK_SIZE,                   /* Ket                                    */ \
+  1+LINK_SIZE,                   /* KetRmax                                */ \
+  1+LINK_SIZE,                   /* KetRmin                                */ \
+  1+LINK_SIZE,                   /* KetRpos                                */ \
+  1+LINK_SIZE,                   /* Reverse                                */ \
+  1+LINK_SIZE,                   /* Assert                                 */ \
+  1+LINK_SIZE,                   /* Assert not                             */ \
+  1+LINK_SIZE,                   /* Assert behind                          */ \
+  1+LINK_SIZE,                   /* Assert behind not                      */ \
+  1+LINK_SIZE,                   /* ONCE                                   */ \
+  1+LINK_SIZE,                   /* ONCE_NC                                */ \
+  1+LINK_SIZE,                   /* BRA                                    */ \
+  1+LINK_SIZE,                   /* BRAPOS                                 */ \
+  1+LINK_SIZE+IMM2_SIZE,         /* CBRA                                   */ \
+  1+LINK_SIZE+IMM2_SIZE,         /* CBRAPOS                                */ \
+  1+LINK_SIZE,                   /* COND                                   */ \
+  1+LINK_SIZE,                   /* SBRA                                   */ \
+  1+LINK_SIZE,                   /* SBRAPOS                                */ \
+  1+LINK_SIZE+IMM2_SIZE,         /* SCBRA                                  */ \
+  1+LINK_SIZE+IMM2_SIZE,         /* SCBRAPOS                               */ \
+  1+LINK_SIZE,                   /* SCOND                                  */ \
+  1+IMM2_SIZE, 1+IMM2_SIZE,      /* CREF, NCREF                            */ \
+  1+IMM2_SIZE, 1+IMM2_SIZE,      /* RREF, NRREF                            */ \
+  1,                             /* DEF                                    */ \
+  1, 1, 1,                       /* BRAZERO, BRAMINZERO, BRAPOSZERO        */ \
+  3, 1, 3,                       /* MARK, PRUNE, PRUNE_ARG                 */ \
+  1, 3,                          /* SKIP, SKIP_ARG                         */ \
+  1, 3,                          /* THEN, THEN_ARG                         */ \
+  1, 1, 1, 1,                    /* COMMIT, FAIL, ACCEPT, ASSERT_ACCEPT    */ \
+  1+IMM2_SIZE, 1                 /* CLOSE, SKIPZERO                        */
+
+/* A magic value for OP_RREF and OP_NRREF to indicate the "any recursion"
+condition. */
+
+#define RREF_ANY  0xffff
+
+/* Compile time error code numbers. They are given names so that they can more
+easily be tracked. When a new number is added, the table called eint in
+pcreposix.c must be updated. */
+
+enum { ERR0,  ERR1,  ERR2,  ERR3,  ERR4,  ERR5,  ERR6,  ERR7,  ERR8,  ERR9,
+       ERR10, ERR11, ERR12, ERR13, ERR14, ERR15, ERR16, ERR17, ERR18, ERR19,
+       ERR20, ERR21, ERR22, ERR23, ERR24, ERR25, ERR26, ERR27, ERR28, ERR29,
+       ERR30, ERR31, ERR32, ERR33, ERR34, ERR35, ERR36, ERR37, ERR38, ERR39,
+       ERR40, ERR41, ERR42, ERR43, ERR44, ERR45, ERR46, ERR47, ERR48, ERR49,
+       ERR50, ERR51, ERR52, ERR53, ERR54, ERR55, ERR56, ERR57, ERR58, ERR59,
+       ERR60, ERR61, ERR62, ERR63, ERR64, ERR65, ERR66, ERR67, ERR68, ERR69,
+       ERR70, ERR71, ERR72, ERR73, ERR74, ERR75, ERR76, ERRCOUNT };
+
+/* JIT compiling modes. The function list is indexed by them. */
+enum { JIT_COMPILE, JIT_PARTIAL_SOFT_COMPILE, JIT_PARTIAL_HARD_COMPILE,
+       JIT_NUMBER_OF_COMPILE_MODES };
+
+/* The real format of the start of the pcre block; the index of names and the
+code vector run on as long as necessary after the end. We store an explicit
+offset to the name table so that if a regex is compiled on one host, saved, and
+then run on another where the size of pointers is different, all might still
+be well. For the case of compiled-on-4 and run-on-8, we include an extra
+pointer that is always NULL. For future-proofing, a few dummy fields were
+originally included - even though you can never get this planning right - but
+there is only one left now.
+
+NOTE NOTE NOTE:
+Because people can now save and re-use compiled patterns, any additions to this
+structure should be made at the end, and something earlier (e.g. a new
+flag in the options or one of the dummy fields) should indicate that the new
+fields are present. Currently PCRE always sets the dummy fields to zero.
+NOTE NOTE NOTE
+*/
+
+#ifdef COMPILE_PCRE8
+#define REAL_PCRE real_pcre
+#else
+#define REAL_PCRE real_pcre16
+#endif
+
+typedef struct REAL_PCRE {
+  pcre_uint32 magic_number;
+  pcre_uint32 size;               /* Total that was malloced */
+  pcre_uint32 options;            /* Public options */
+  pcre_uint16 flags;              /* Private flags */
+  pcre_uint16 max_lookbehind;     /* Longest lookbehind (characters) */
+  pcre_uint16 top_bracket;        /* Highest numbered group */
+  pcre_uint16 top_backref;        /* Highest numbered back reference */
+  pcre_uint16 first_char;         /* Starting character */
+  pcre_uint16 req_char;           /* This character must be seen */
+  pcre_uint16 name_table_offset;  /* Offset to name table that follows */
+  pcre_uint16 name_entry_size;    /* Size of any name items */
+  pcre_uint16 name_count;         /* Number of name items */
+  pcre_uint16 ref_count;          /* Reference count */
+  const pcre_uint8 *tables;       /* Pointer to tables or NULL for std */
+  const pcre_uint8 *nullpad;      /* NULL padding */
+} REAL_PCRE;
+
+/* The format of the block used to store data from pcre_study(). The same
+remark (see NOTE above) about extending this structure applies. */
+
+typedef struct pcre_study_data {
+  pcre_uint32 size;               /* Total that was malloced */
+  pcre_uint32 flags;              /* Private flags */
+  pcre_uint8 start_bits[32];      /* Starting char bits */
+  pcre_uint32 minlength;          /* Minimum subject length */
+} pcre_study_data;
+
+/* Structure for building a chain of open capturing subpatterns during
+compiling, so that instructions to close them can be compiled when (*ACCEPT) is
+encountered. This is also used to identify subpatterns that contain recursive
+back references to themselves, so that they can be made atomic. */
+
+typedef struct open_capitem {
+  struct open_capitem *next;    /* Chain link */
+  pcre_uint16 number;           /* Capture number */
+  pcre_uint16 flag;             /* Set TRUE if recursive back ref */
+} open_capitem;
+
+/* Structure for passing "static" information around between the functions
+doing the compiling, so that they are thread-safe. */
+
+typedef struct compile_data {
+  const pcre_uint8 *lcc;            /* Points to lower casing table */
+  const pcre_uint8 *fcc;            /* Points to case-flipping table */
+  const pcre_uint8 *cbits;          /* Points to character type table */
+  const pcre_uint8 *ctypes;         /* Points to table of type maps */
+  const pcre_uchar *start_workspace;/* The start of working space */
+  const pcre_uchar *start_code;     /* The start of the compiled code */
+  const pcre_uchar *start_pattern;  /* The start of the pattern */
+  const pcre_uchar *end_pattern;    /* The end of the pattern */
+  open_capitem *open_caps;          /* Chain of open capture items */
+  pcre_uchar *hwm;                  /* High watermark of workspace */
+  pcre_uchar *name_table;           /* The name/number table */
+  int  names_found;                 /* Number of entries so far */
+  int  name_entry_size;             /* Size of each entry */
+  int  workspace_size;              /* Size of workspace */
+  int  bracount;                    /* Count of capturing parens as we compile */
+  int  final_bracount;              /* Saved value after first pass */
+  int  max_lookbehind;              /* Maximum lookbehind (characters) */
+  int  top_backref;                 /* Maximum back reference */
+  unsigned int backref_map;         /* Bitmap of low back refs */
+  int  assert_depth;                /* Depth of nested assertions */
+  int  external_options;            /* External (initial) options */
+  int  external_flags;              /* External flag bits to be set */
+  int  req_varyopt;                 /* "After variable item" flag for reqbyte */
+  BOOL had_accept;                  /* (*ACCEPT) encountered */
+  BOOL check_lookbehind;            /* Lookbehinds need later checking */
+  int  nltype;                      /* Newline type */
+  int  nllen;                       /* Newline string length */
+  pcre_uchar nl[4];                 /* Newline string when fixed length */
+} compile_data;
+
+/* Structure for maintaining a chain of pointers to the currently incomplete
+branches, for testing for left recursion while compiling. */
+
+typedef struct branch_chain {
+  struct branch_chain *outer;
+  pcre_uchar *current_branch;
+} branch_chain;
+
+/* Structure for items in a linked list that represents an explicit recursive
+call within the pattern; used by pcre_exec(). */
+
+typedef struct recursion_info {
+  struct recursion_info *prevrec; /* Previous recursion record (or NULL) */
+  int group_num;                  /* Number of group that was called */
+  int *offset_save;               /* Pointer to start of saved offsets */
+  int saved_max;                  /* Number of saved offsets */
+  PCRE_PUCHAR subject_position;   /* Position at start of recursion */
+} recursion_info;
+
+/* A similar structure for pcre_dfa_exec(). */
+
+typedef struct dfa_recursion_info {
+  struct dfa_recursion_info *prevrec;
+  int group_num;
+  PCRE_PUCHAR subject_position;
+} dfa_recursion_info;
+
+/* Structure for building a chain of data for holding the values of the subject
+pointer at the start of each subpattern, so as to detect when an empty string
+has been matched by a subpattern - to break infinite loops; used by
+pcre_exec(). */
+
+typedef struct eptrblock {
+  struct eptrblock *epb_prev;
+  PCRE_PUCHAR epb_saved_eptr;
+} eptrblock;
+
+
+/* Structure for passing "static" information around between the functions
+doing traditional NFA matching, so that they are thread-safe. */
+
+typedef struct match_data {
+  unsigned long int match_call_count;      /* As it says */
+  unsigned long int match_limit;           /* As it says */
+  unsigned long int match_limit_recursion; /* As it says */
+  int   *offset_vector;           /* Offset vector */
+  int    offset_end;              /* One past the end */
+  int    offset_max;              /* The maximum usable for return data */
+  int    nltype;                  /* Newline type */
+  int    nllen;                   /* Newline string length */
+  int    name_count;              /* Number of names in name table */
+  int    name_entry_size;         /* Size of entry in names table */
+  pcre_uchar *name_table;         /* Table of names */
+  pcre_uchar nl[4];               /* Newline string when fixed */
+  const  pcre_uint8 *lcc;         /* Points to lower casing table */
+  const  pcre_uint8 *fcc;         /* Points to case-flipping table */
+  const  pcre_uint8 *ctypes;      /* Points to table of type maps */
+  BOOL   offset_overflow;         /* Set if too many extractions */
+  BOOL   notbol;                  /* NOTBOL flag */
+  BOOL   noteol;                  /* NOTEOL flag */
+  BOOL   utf;                     /* UTF-8 / UTF-16 flag */
+  BOOL   jscript_compat;          /* JAVASCRIPT_COMPAT flag */
+  BOOL   use_ucp;                 /* PCRE_UCP flag */
+  BOOL   endonly;                 /* Dollar not before final \n */
+  BOOL   notempty;                /* Empty string match not wanted */
+  BOOL   notempty_atstart;        /* Empty string match at start not wanted */
+  BOOL   hitend;                  /* Hit the end of the subject at some point */
+  BOOL   bsr_anycrlf;             /* \R is just any CRLF, not full Unicode */
+  BOOL   hasthen;                 /* Pattern contains (*THEN) */
+  BOOL   ignore_skip_arg;         /* For re-run when SKIP name not found */
+  const  pcre_uchar *start_code;  /* For use when recursing */
+  PCRE_PUCHAR start_subject;      /* Start of the subject string */
+  PCRE_PUCHAR end_subject;        /* End of the subject string */
+  PCRE_PUCHAR start_match_ptr;    /* Start of matched string */
+  PCRE_PUCHAR end_match_ptr;      /* Subject position at end match */
+  PCRE_PUCHAR start_used_ptr;     /* Earliest consulted character */
+  int    partial;                 /* PARTIAL options */
+  int    end_offset_top;          /* Highwater mark at end of match */
+  int    capture_last;            /* Most recent capture number */
+  int    start_offset;            /* The start offset value */
+  int    match_function_type;     /* Set for certain special calls of MATCH() */
+  eptrblock *eptrchain;           /* Chain of eptrblocks for tail recursions */
+  int    eptrn;                   /* Next free eptrblock */
+  recursion_info *recursive;      /* Linked list of recursion data */
+  void  *callout_data;            /* To pass back to callouts */
+  const  pcre_uchar *mark;        /* Mark pointer to pass back on success */
+  const  pcre_uchar *nomatch_mark;/* Mark pointer to pass back on failure */
+  const  pcre_uchar *once_target; /* Where to back up to for atomic groups */
+#ifdef NO_RECURSE
+  void  *match_frames_base;       /* For remembering malloc'd frames */
+#endif
+} match_data;
+
+/* A similar structure is used for the same purpose by the DFA matching
+functions. */
+
+typedef struct dfa_match_data {
+  const pcre_uchar *start_code;     /* Start of the compiled pattern */
+  const pcre_uchar *start_subject ; /* Start of the subject string */
+  const pcre_uchar *end_subject;    /* End of subject string */
+  const pcre_uchar *start_used_ptr; /* Earliest consulted character */
+  const pcre_uint8 *tables;         /* Character tables */
+  int   start_offset;               /* The start offset value */
+  int   moptions;                   /* Match options */
+  int   poptions;                   /* Pattern options */
+  int   nltype;                     /* Newline type */
+  int   nllen;                      /* Newline string length */
+  pcre_uchar nl[4];                 /* Newline string when fixed */
+  void *callout_data;               /* To pass back to callouts */
+  dfa_recursion_info *recursive;    /* Linked list of recursion data */
+} dfa_match_data;
+
+/* Bit definitions for entries in the pcre_ctypes table. */
+
+#define ctype_space   0x01
+#define ctype_letter  0x02
+#define ctype_digit   0x04
+#define ctype_xdigit  0x08
+#define ctype_word    0x10   /* alphanumeric or '_' */
+#define ctype_meta    0x80   /* regexp meta char or zero (end pattern) */
+
+/* Offsets for the bitmap tables in pcre_cbits. Each table contains a set
+of bits for a class map. Some classes are built by combining these tables. */
+
+#define cbit_space     0      /* [:space:] or \s */
+#define cbit_xdigit   32      /* [:xdigit:] */
+#define cbit_digit    64      /* [:digit:] or \d */
+#define cbit_upper    96      /* [:upper:] */
+#define cbit_lower   128      /* [:lower:] */
+#define cbit_word    160      /* [:word:] or \w */
+#define cbit_graph   192      /* [:graph:] */
+#define cbit_print   224      /* [:print:] */
+#define cbit_punct   256      /* [:punct:] */
+#define cbit_cntrl   288      /* [:cntrl:] */
+#define cbit_length  320      /* Length of the cbits table */
+
+/* Offsets of the various tables from the base tables pointer, and
+total length. */
+
+#define lcc_offset      0
+#define fcc_offset    256
+#define cbits_offset  512
+#define ctypes_offset (cbits_offset + cbit_length)
+#define tables_length (ctypes_offset + 256)
+
+/* Internal function and data prefixes. */
+
+#ifdef COMPILE_PCRE8
+#ifndef PUBL
+#define PUBL(name) pcre_##name
+#endif
+#ifndef PRIV
+#define PRIV(name) _pcre_##name
+#endif
+#else /* COMPILE_PCRE8 */
+#ifdef COMPILE_PCRE16
+#ifndef PUBL
+#define PUBL(name) pcre16_##name
+#endif
+#ifndef PRIV
+#define PRIV(name) _pcre16_##name
+#endif
+#else
+#error Unsupported compiling mode
+#endif /* COMPILE_PCRE16 */
+#endif /* COMPILE_PCRE8 */
+
+/* Layout of the UCP type table that translates property names into types and
+codes. Each entry used to point directly to a name, but to reduce the number of
+relocations in shared libraries, it now has an offset into a single string
+instead. */
+
+typedef struct {
+  pcre_uint16 name_offset;
+  pcre_uint16 type;
+  pcre_uint16 value;
+} ucp_type_table;
+
+
+/* Internal shared data tables. These are tables that are used by more than one
+of the exported public functions. They have to be "external" in the C sense,
+but are not part of the PCRE public API. The data for these tables is in the
+pcre_tables.c module. */
+
+#ifdef COMPILE_PCRE8
+
+extern const int            PRIV(utf8_table1)[];
+extern const int            PRIV(utf8_table1_size);
+extern const int            PRIV(utf8_table2)[];
+extern const int            PRIV(utf8_table3)[];
+extern const pcre_uint8     PRIV(utf8_table4)[];
+
+#endif /* COMPILE_PCRE8 */
+
+extern const char           PRIV(utt_names)[];
+extern const ucp_type_table PRIV(utt)[];
+extern const int            PRIV(utt_size);
+
+extern const pcre_uint8     PRIV(default_tables)[];
+
+extern const pcre_uint8     PRIV(OP_lengths)[];
+
+
+/* Internal shared functions. These are functions that are used by more than
+one of the exported public functions. They have to be "external" in the C
+sense, but are not part of the PCRE public API. */
+
+/* String comparison functions. */
+#ifdef COMPILE_PCRE8
+
+#define STRCMP_UC_UC(str1, str2) \
+  strcmp((char *)(str1), (char *)(str2))
+#define STRCMP_UC_C8(str1, str2) \
+  strcmp((char *)(str1), (str2))
+#define STRNCMP_UC_UC(str1, str2, num) \
+  strncmp((char *)(str1), (char *)(str2), (num))
+#define STRNCMP_UC_C8(str1, str2, num) \
+  strncmp((char *)(str1), (str2), (num))
+#define STRLEN_UC(str) strlen((const char *)str)
+
+#else
+
+extern int               PRIV(strcmp_uc_uc)(const pcre_uchar *,
+                           const pcre_uchar *);
+extern int               PRIV(strcmp_uc_c8)(const pcre_uchar *,
+                           const char *);
+extern int               PRIV(strncmp_uc_uc)(const pcre_uchar *,
+                           const pcre_uchar *, unsigned int num);
+extern int               PRIV(strncmp_uc_c8)(const pcre_uchar *,
+                           const char *, unsigned int num);
+extern unsigned int      PRIV(strlen_uc)(const pcre_uchar *str);
+
+#define STRCMP_UC_UC(str1, str2) \
+  PRIV(strcmp_uc_uc)((str1), (str2))
+#define STRCMP_UC_C8(str1, str2) \
+  PRIV(strcmp_uc_c8)((str1), (str2))
+#define STRNCMP_UC_UC(str1, str2, num) \
+  PRIV(strncmp_uc_uc)((str1), (str2), (num))
+#define STRNCMP_UC_C8(str1, str2, num) \
+  PRIV(strncmp_uc_c8)((str1), (str2), (num))
+#define STRLEN_UC(str) PRIV(strlen_uc)(str)
+
+#endif /* COMPILE_PCRE8 */
+
+extern const pcre_uchar *PRIV(find_bracket)(const pcre_uchar *, BOOL, int);
+extern BOOL              PRIV(is_newline)(PCRE_PUCHAR, int, PCRE_PUCHAR,
+                           int *, BOOL);
+extern int               PRIV(ord2utf)(pcre_uint32, pcre_uchar *);
+extern int               PRIV(valid_utf)(PCRE_PUCHAR, int, int *);
+extern BOOL              PRIV(was_newline)(PCRE_PUCHAR, int, PCRE_PUCHAR,
+                           int *, BOOL);
+extern BOOL              PRIV(xclass)(int, const pcre_uchar *, BOOL);
+
+#ifdef SUPPORT_JIT
+extern void              PRIV(jit_compile)(const REAL_PCRE *,
+                           PUBL(extra) *, int);
+extern int               PRIV(jit_exec)(const REAL_PCRE *, const PUBL(extra) *,
+                           const pcre_uchar *, int, int, int, int *, int);
+extern void              PRIV(jit_free)(void *);
+extern int               PRIV(jit_get_size)(void *);
+extern const char*       PRIV(jit_get_target)(void);
+#endif
+
+/* Unicode character database (UCD) */
+
+typedef struct {
+  pcre_uint8 script;
+  pcre_uint8 chartype;
+  pcre_int32 other_case;
+} ucd_record;
+
+extern const ucd_record  PRIV(ucd_records)[];
+extern const pcre_uint8  PRIV(ucd_stage1)[];
+extern const pcre_uint16 PRIV(ucd_stage2)[];
+extern const int         PRIV(ucp_gentype)[];
+#ifdef SUPPORT_JIT
+extern const int         PRIV(ucp_typerange)[];
+#endif
+
+#ifdef SUPPORT_UCP
+/* UCD access macros */
+
+#define UCD_BLOCK_SIZE 128
+#define GET_UCD(ch) (PRIV(ucd_records) + \
+        PRIV(ucd_stage2)[PRIV(ucd_stage1)[(ch) / UCD_BLOCK_SIZE] * \
+        UCD_BLOCK_SIZE + (ch) % UCD_BLOCK_SIZE])
+
+#define UCD_CHARTYPE(ch)  GET_UCD(ch)->chartype
+#define UCD_SCRIPT(ch)    GET_UCD(ch)->script
+#define UCD_CATEGORY(ch)  PRIV(ucp_gentype)[UCD_CHARTYPE(ch)]
+#define UCD_OTHERCASE(ch) (ch + GET_UCD(ch)->other_case)
+
+#endif /* SUPPORT_UCP */
+
+#endif
+
+/* End of pcre_internal.h */
diff --git a/ext/pcre/pcrelib/pcre_maketables.c b/ext/pcre/pcrelib/pcre_maketables.c
new file mode 100644
index 0000000..5c73b75
--- /dev/null
+++ b/ext/pcre/pcrelib/pcre_maketables.c
@@ -0,0 +1,146 @@
+/*************************************************
+*      Perl-Compatible Regular Expressions       *
+*************************************************/
+
+/* PCRE is a library of functions to support regular expressions whose syntax
+and semantics are as close as possible to those of the Perl 5 language.
+
+                       Written by Philip Hazel
+           Copyright (c) 1997-2012 University of Cambridge
+
+-----------------------------------------------------------------------------
+Redistribution and use in source and binary forms, with or without
+modification, are permitted provided that the following conditions are met:
+
+    * Redistributions of source code must retain the above copyright notice,
+      this list of conditions and the following disclaimer.
+
+    * Redistributions in binary form must reproduce the above copyright
+      notice, this list of conditions and the following disclaimer in the
+      documentation and/or other materials provided with the distribution.
+
+    * Neither the name of the University of Cambridge nor the names of its
+      contributors may be used to endorse or promote products derived from
+      this software without specific prior written permission.
+
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+POSSIBILITY OF SUCH DAMAGE.
+-----------------------------------------------------------------------------
+*/
+
+
+/* This module contains the external function pcre_maketables(), which builds
+character tables for PCRE in the current locale. The file is compiled on its
+own as part of the PCRE library. However, it is also included in the
+compilation of dftables.c, in which case the macro DFTABLES is defined. */
+
+
+#ifndef DFTABLES
+#  include "config.h"
+#  include "pcre_internal.h"
+#endif
+
+
+/*************************************************
+*           Create PCRE character tables         *
+*************************************************/
+
+/* This function builds a set of character tables for use by PCRE and returns
+a pointer to them. They are build using the ctype functions, and consequently
+their contents will depend upon the current locale setting. When compiled as
+part of the library, the store is obtained via PUBL(malloc)(), but when
+compiled inside dftables, use malloc().
+
+Arguments:   none
+Returns:     pointer to the contiguous block of data
+*/
+
+#ifdef COMPILE_PCRE8
+const unsigned char *
+pcre_maketables(void)
+#else
+const unsigned char *
+pcre16_maketables(void)
+#endif
+{
+unsigned char *yield, *p;
+int i;
+
+#ifndef DFTABLES
+yield = (unsigned char*)(PUBL(malloc))(tables_length);
+#else
+yield = (unsigned char*)malloc(tables_length);
+#endif
+
+if (yield == NULL) return NULL;
+p = yield;
+
+/* First comes the lower casing table */
+
+for (i = 0; i < 256; i++) *p++ = tolower(i);
+
+/* Next the case-flipping table */
+
+for (i = 0; i < 256; i++) *p++ = islower(i)? toupper(i) : tolower(i);
+
+/* Then the character class tables. Don't try to be clever and save effort on
+exclusive ones - in some locales things may be different. Note that the table
+for "space" includes everything "isspace" gives, including VT in the default
+locale. This makes it work for the POSIX class [:space:]. Note also that it is
+possible for a character to be alnum or alpha without being lower or upper,
+such as "male and female ordinals" (\xAA and \xBA) in the fr_FR locale (at
+least under Debian Linux's locales as of 12/2005). So we must test for alnum
+specially. */
+
+memset(p, 0, cbit_length);
+for (i = 0; i < 256; i++)
+  {
+  if (isdigit(i)) p[cbit_digit  + i/8] |= 1 << (i&7);
+  if (isupper(i)) p[cbit_upper  + i/8] |= 1 << (i&7);
+  if (islower(i)) p[cbit_lower  + i/8] |= 1 << (i&7);
+  if (isalnum(i)) p[cbit_word   + i/8] |= 1 << (i&7);
+  if (i == '_')   p[cbit_word   + i/8] |= 1 << (i&7);
+  if (isspace(i)) p[cbit_space  + i/8] |= 1 << (i&7);
+  if (isxdigit(i))p[cbit_xdigit + i/8] |= 1 << (i&7);
+  if (isgraph(i)) p[cbit_graph  + i/8] |= 1 << (i&7);
+  if (isprint(i)) p[cbit_print  + i/8] |= 1 << (i&7);
+  if (ispunct(i)) p[cbit_punct  + i/8] |= 1 << (i&7);
+  if (iscntrl(i)) p[cbit_cntrl  + i/8] |= 1 << (i&7);
+  }
+p += cbit_length;
+
+/* Finally, the character type table. In this, we exclude VT from the white
+space chars, because Perl doesn't recognize it as such for \s and for comments
+within regexes. */
+
+for (i = 0; i < 256; i++)
+  {
+  int x = 0;
+  if (i != 0x0b && isspace(i)) x += ctype_space;
+  if (isalpha(i)) x += ctype_letter;
+  if (isdigit(i)) x += ctype_digit;
+  if (isxdigit(i)) x += ctype_xdigit;
+  if (isalnum(i) || i == '_') x += ctype_word;
+
+  /* Note: strchr includes the terminating zero in the characters it considers.
+  In this instance, that is ok because we want binary zero to be flagged as a
+  meta-character, which in this sense is any character that terminates a run
+  of data characters. */
+
+  if (strchr("\\*+?{^.$|()[", i) != 0) x += ctype_meta;
+  *p++ = x;
+  }
+
+return yield;
+}
+
+/* End of pcre_maketables.c */
diff --git a/ext/pcre/pcrelib/pcre_newline.c b/ext/pcre/pcrelib/pcre_newline.c
new file mode 100644
index 0000000..ddd7708
--- /dev/null
+++ b/ext/pcre/pcrelib/pcre_newline.c
@@ -0,0 +1,182 @@
+/*************************************************
+*      Perl-Compatible Regular Expressions       *
+*************************************************/
+
+/* PCRE is a library of functions to support regular expressions whose syntax
+and semantics are as close as possible to those of the Perl 5 language.
+
+                       Written by Philip Hazel
+           Copyright (c) 1997-2012 University of Cambridge
+
+-----------------------------------------------------------------------------
+Redistribution and use in source and binary forms, with or without
+modification, are permitted provided that the following conditions are met:
+
+    * Redistributions of source code must retain the above copyright notice,
+      this list of conditions and the following disclaimer.
+
+    * Redistributions in binary form must reproduce the above copyright
+      notice, this list of conditions and the following disclaimer in the
+      documentation and/or other materials provided with the distribution.
+
+    * Neither the name of the University of Cambridge nor the names of its
+      contributors may be used to endorse or promote products derived from
+      this software without specific prior written permission.
+
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+POSSIBILITY OF SUCH DAMAGE.
+-----------------------------------------------------------------------------
+*/
+
+
+/* This module contains internal functions for testing newlines when more than
+one kind of newline is to be recognized. When a newline is found, its length is
+returned. In principle, we could implement several newline "types", each
+referring to a different set of newline characters. At present, PCRE supports
+only NLTYPE_FIXED, which gets handled without these functions, NLTYPE_ANYCRLF,
+and NLTYPE_ANY. The full list of Unicode newline characters is taken from
+http://unicode.org/unicode/reports/tr18/. */
+
+
+#include "config.h"
+
+#include "pcre_internal.h"
+
+
+
+/*************************************************
+*      Check for newline at given position       *
+*************************************************/
+
+/* It is guaranteed that the initial value of ptr is less than the end of the
+string that is being processed.
+
+Arguments:
+  ptr          pointer to possible newline
+  type         the newline type
+  endptr       pointer to the end of the string
+  lenptr       where to return the length
+  utf          TRUE if in utf mode
+
+Returns:       TRUE or FALSE
+*/
+
+BOOL
+PRIV(is_newline)(PCRE_PUCHAR ptr, int type, PCRE_PUCHAR endptr, int *lenptr,
+  BOOL utf)
+{
+int c;
+(void)utf;
+#ifdef SUPPORT_UTF
+if (utf)
+  {
+  GETCHAR(c, ptr);
+  }
+else
+#endif  /* SUPPORT_UTF */
+  c = *ptr;
+
+if (type == NLTYPE_ANYCRLF) switch(c)
+  {
+  case 0x000a: *lenptr = 1; return TRUE;             /* LF */
+  case 0x000d: *lenptr = (ptr < endptr - 1 && ptr[1] == 0x0a)? 2 : 1;
+               return TRUE;                          /* CR */
+  default: return FALSE;
+  }
+
+/* NLTYPE_ANY */
+
+else switch(c)
+  {
+  case 0x000a:                                       /* LF */
+  case 0x000b:                                       /* VT */
+  case 0x000c: *lenptr = 1; return TRUE;             /* FF */
+  case 0x000d: *lenptr = (ptr < endptr - 1 && ptr[1] == 0x0a)? 2 : 1;
+               return TRUE;                          /* CR */
+#ifdef COMPILE_PCRE8
+  case 0x0085: *lenptr = utf? 2 : 1; return TRUE;    /* NEL */
+  case 0x2028:                                       /* LS */
+  case 0x2029: *lenptr = 3; return TRUE;             /* PS */
+#else
+  case 0x0085:                                       /* NEL */
+  case 0x2028:                                       /* LS */
+  case 0x2029: *lenptr = 1; return TRUE;             /* PS */
+#endif /* COMPILE_PCRE8 */
+  default: return FALSE;
+  }
+}
+
+
+
+/*************************************************
+*     Check for newline at previous position     *
+*************************************************/
+
+/* It is guaranteed that the initial value of ptr is greater than the start of
+the string that is being processed.
+
+Arguments:
+  ptr          pointer to possible newline
+  type         the newline type
+  startptr     pointer to the start of the string
+  lenptr       where to return the length
+  utf          TRUE if in utf mode
+
+Returns:       TRUE or FALSE
+*/
+
+BOOL
+PRIV(was_newline)(PCRE_PUCHAR ptr, int type, PCRE_PUCHAR startptr, int *lenptr,
+  BOOL utf)
+{
+int c;
+(void)utf;
+ptr--;
+#ifdef SUPPORT_UTF
+if (utf)
+  {
+  BACKCHAR(ptr);
+  GETCHAR(c, ptr);
+  }
+else
+#endif  /* SUPPORT_UTF */
+  c = *ptr;
+
+if (type == NLTYPE_ANYCRLF) switch(c)
+  {
+  case 0x000a: *lenptr = (ptr > startptr && ptr[-1] == 0x0d)? 2 : 1;
+               return TRUE;                         /* LF */
+  case 0x000d: *lenptr = 1; return TRUE;            /* CR */
+  default: return FALSE;
+  }
+
+else switch(c)
+  {
+  case 0x000a: *lenptr = (ptr > startptr && ptr[-1] == 0x0d)? 2 : 1;
+               return TRUE;                         /* LF */
+  case 0x000b:                                      /* VT */
+  case 0x000c:                                      /* FF */
+  case 0x000d: *lenptr = 1; return TRUE;            /* CR */
+#ifdef COMPILE_PCRE8
+  case 0x0085: *lenptr = utf? 2 : 1; return TRUE;   /* NEL */
+  case 0x2028:                                      /* LS */
+  case 0x2029: *lenptr = 3; return TRUE;            /* PS */
+#else
+  case 0x0085:                                       /* NEL */
+  case 0x2028:                                       /* LS */
+  case 0x2029: *lenptr = 1; return TRUE;             /* PS */
+#endif /* COMPILE_PCRE8 */
+  default: return FALSE;
+  }
+}
+
+/* End of pcre_newline.c */
diff --git a/ext/pcre/pcrelib/pcre_ord2utf8.c b/ext/pcre/pcrelib/pcre_ord2utf8.c
new file mode 100644
index 0000000..917d943
--- /dev/null
+++ b/ext/pcre/pcrelib/pcre_ord2utf8.c
@@ -0,0 +1,95 @@
+/*************************************************
+*      Perl-Compatible Regular Expressions       *
+*************************************************/
+
+/* PCRE is a library of functions to support regular expressions whose syntax
+and semantics are as close as possible to those of the Perl 5 language.
+
+                       Written by Philip Hazel
+           Copyright (c) 1997-2012 University of Cambridge
+
+-----------------------------------------------------------------------------
+Redistribution and use in source and binary forms, with or without
+modification, are permitted provided that the following conditions are met:
+
+    * Redistributions of source code must retain the above copyright notice,
+      this list of conditions and the following disclaimer.
+
+    * Redistributions in binary form must reproduce the above copyright
+      notice, this list of conditions and the following disclaimer in the
+      documentation and/or other materials provided with the distribution.
+
+    * Neither the name of the University of Cambridge nor the names of its
+      contributors may be used to endorse or promote products derived from
+      this software without specific prior written permission.
+
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+POSSIBILITY OF SUCH DAMAGE.
+-----------------------------------------------------------------------------
+*/
+
+
+/* This file contains a private PCRE function that converts an ordinal
+character value into a UTF8 string. */
+
+#include "config.h"
+
+#include "pcre_internal.h"
+
+
+/*************************************************
+*       Convert character value to UTF-8         *
+*************************************************/
+
+/* This function takes an integer value in the range 0 - 0x10ffff
+and encodes it as a UTF-8 character in 1 to 6 pcre_uchars.
+
+Arguments:
+  cvalue     the character value
+  buffer     pointer to buffer for result - at least 6 pcre_uchars long
+
+Returns:     number of characters placed in the buffer
+*/
+
+int
+PRIV(ord2utf)(pcre_uint32 cvalue, pcre_uchar *buffer)
+{
+#ifdef SUPPORT_UTF
+
+register int i, j;
+
+/* Checking invalid cvalue character, encoded as invalid UTF-16 character.
+Should never happen in practice. */
+if ((cvalue & 0xf800) == 0xd800 || cvalue >= 0x110000)
+  cvalue = 0xfffe;
+
+for (i = 0; i < PRIV(utf8_table1_size); i++)
+  if ((int)cvalue <= PRIV(utf8_table1)[i]) break;
+buffer += i;
+for (j = i; j > 0; j--)
+ {
+ *buffer-- = 0x80 | (cvalue & 0x3f);
+ cvalue >>= 6;
+ }
+*buffer = PRIV(utf8_table2)[i] | cvalue;
+return i + 1;
+
+#else
+
+(void)(cvalue);  /* Keep compiler happy; this function won't ever be */
+(void)(buffer);  /* called when SUPPORT_UTF is not defined. */
+return 0;
+
+#endif
+}
+
+/* End of pcre_ord2utf8.c */
diff --git a/ext/pcre/pcrelib/pcre_printint.src b/ext/pcre/pcrelib/pcre_printint.src
new file mode 100644
index 0000000..c7d8629
--- /dev/null
+++ b/ext/pcre/pcrelib/pcre_printint.src
@@ -0,0 +1,572 @@
+/*************************************************
+*      Perl-Compatible Regular Expressions       *
+*************************************************/
+
+/* PCRE is a library of functions to support regular expressions whose syntax
+and semantics are as close as possible to those of the Perl 5 language.
+
+                       Written by Philip Hazel
+           Copyright (c) 1997-2010 University of Cambridge
+
+-----------------------------------------------------------------------------
+Redistribution and use in source and binary forms, with or without
+modification, are permitted provided that the following conditions are met:
+
+    * Redistributions of source code must retain the above copyright notice,
+      this list of conditions and the following disclaimer.
+
+    * Redistributions in binary form must reproduce the above copyright
+      notice, this list of conditions and the following disclaimer in the
+      documentation and/or other materials provided with the distribution.
+
+    * Neither the name of the University of Cambridge nor the names of its
+      contributors may be used to endorse or promote products derived from
+      this software without specific prior written permission.
+
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+POSSIBILITY OF SUCH DAMAGE.
+-----------------------------------------------------------------------------
+*/
+
+
+/* This module contains a PCRE private debugging function for printing out the
+internal form of a compiled regular expression, along with some supporting
+local functions. This source file is used in two places:
+
+(1) It is #included by pcre_compile.c when it is compiled in debugging mode
+(PCRE_DEBUG defined in pcre_internal.h). It is not included in production
+compiles.
+
+(2) It is always #included by pcretest.c, which can be asked to print out a
+compiled regex for debugging purposes. */
+
+
+/* Macro that decides whether a character should be output as a literal or in
+hexadecimal. We don't use isprint() because that can vary from system to system
+(even without the use of locales) and we want the output always to be the same,
+for testing purposes. This macro is used in pcretest as well as in this file. */
+
+#ifdef EBCDIC
+#define PRINTABLE(c) ((c) >= 64 && (c) < 255)
+#else
+#define PRINTABLE(c) ((c) >= 32 && (c) < 127)
+#endif
+
+/* The table of operator names. */
+
+static const char *OP_names[] = { OP_NAME_LIST };
+
+
+
+/*************************************************
+*       Print single- or multi-byte character    *
+*************************************************/
+
+static int
+print_char(FILE *f, uschar *ptr, BOOL utf8)
+{
+int c = *ptr;
+
+#ifndef SUPPORT_UTF8
+utf8 = utf8;  /* Avoid compiler warning */
+if (PRINTABLE(c)) fprintf(f, "%c", c); else fprintf(f, "\\x%02x", c);
+return 0;
+
+#else
+if (!utf8 || (c & 0xc0) != 0xc0)
+  {
+  if (PRINTABLE(c)) fprintf(f, "%c", c); else fprintf(f, "\\x%02x", c);
+  return 0;
+  }
+else
+  {
+  int i;
+  int a = _pcre_utf8_table4[c & 0x3f];  /* Number of additional bytes */
+  int s = 6*a;
+  c = (c & _pcre_utf8_table3[a]) << s;
+  for (i = 1; i <= a; i++)
+    {
+    /* This is a check for malformed UTF-8; it should only occur if the sanity
+    check has been turned off. Rather than swallow random bytes, just stop if
+    we hit a bad one. Print it with \X instead of \x as an indication. */
+
+    if ((ptr[i] & 0xc0) != 0x80)
+      {
+      fprintf(f, "\\X{%x}", c);
+      return i - 1;
+      }
+
+    /* The byte is OK */
+
+    s -= 6;
+    c |= (ptr[i] & 0x3f) << s;
+    }
+  if (c < 128) fprintf(f, "\\x%02x", c); else fprintf(f, "\\x{%x}", c);
+  return a;
+  }
+#endif
+}
+
+
+
+/*************************************************
+*          Find Unicode property name            *
+*************************************************/
+
+static const char *
+get_ucpname(int ptype, int pvalue)
+{
+#ifdef SUPPORT_UCP
+int i;
+for (i = _pcre_utt_size - 1; i >= 0; i--)
+  {
+  if (ptype == _pcre_utt[i].type && pvalue == _pcre_utt[i].value) break;
+  }
+return (i >= 0)? _pcre_utt_names + _pcre_utt[i].name_offset : "??";
+#else
+/* It gets harder and harder to shut off unwanted compiler warnings. */
+ptype = ptype * pvalue;
+return (ptype == pvalue)? "??" : "??";
+#endif
+}
+
+
+
+/*************************************************
+*         Print compiled regex                   *
+*************************************************/
+
+/* Make this function work for a regex with integers either byte order.
+However, we assume that what we are passed is a compiled regex. The
+print_lengths flag controls whether offsets and lengths of items are printed.
+They can be turned off from pcretest so that automatic tests on bytecode can be
+written that do not depend on the value of LINK_SIZE. */
+
+static void
+pcre_printint(pcre *external_re, FILE *f, BOOL print_lengths)
+{
+real_pcre *re = (real_pcre *)external_re;
+uschar *codestart, *code;
+BOOL utf8;
+
+unsigned int options = re->options;
+int offset = re->name_table_offset;
+int count = re->name_count;
+int size = re->name_entry_size;
+
+if (re->magic_number != MAGIC_NUMBER)
+  {
+  offset = ((offset << 8) & 0xff00) | ((offset >> 8) & 0xff);
+  count = ((count << 8) & 0xff00) | ((count >> 8) & 0xff);
+  size = ((size << 8) & 0xff00) | ((size >> 8) & 0xff);
+  options = ((options << 24) & 0xff000000) |
+            ((options <<  8) & 0x00ff0000) |
+            ((options >>  8) & 0x0000ff00) |
+            ((options >> 24) & 0x000000ff);
+  }
+
+code = codestart = (uschar *)re + offset + count * size;
+utf8 = (options & PCRE_UTF8) != 0;
+
+for(;;)
+  {
+  uschar *ccode;
+  int c;
+  int extra = 0;
+
+  if (print_lengths)
+    fprintf(f, "%3d ", (int)(code - codestart));
+  else
+    fprintf(f, "    ");
+
+  switch(*code)
+    {
+/* ========================================================================== */
+      /* These cases are never obeyed. This is a fudge that causes a compile-
+      time error if the vectors OP_names or _pcre_OP_lengths, which are indexed
+      by opcode, are not the correct length. It seems to be the only way to do
+      such a check at compile time, as the sizeof() operator does not work in
+      the C preprocessor. We do this while compiling pcretest, because that
+      #includes pcre_tables.c, which holds _pcre_OP_lengths. We can't do this
+      when building pcre_compile.c with PCRE_DEBUG set, because it doesn't then
+      know the size of _pcre_OP_lengths. */
+
+#ifdef COMPILING_PCRETEST
+      case OP_TABLE_LENGTH:
+      case OP_TABLE_LENGTH +
+        ((sizeof(OP_names)/sizeof(const char *) == OP_TABLE_LENGTH) &&
+        (sizeof(_pcre_OP_lengths) == OP_TABLE_LENGTH)):
+      break;
+#endif
+/* ========================================================================== */
+
+    case OP_END:
+    fprintf(f, "    %s\n", OP_names[*code]);
+    fprintf(f, "------------------------------------------------------------------\n");
+    return;
+
+    case OP_OPT:
+    fprintf(f, " %.2x %s", code[1], OP_names[*code]);
+    break;
+
+    case OP_CHAR:
+    fprintf(f, "    ");
+    do
+      {
+      code++;
+      code += 1 + print_char(f, code, utf8);
+      }
+    while (*code == OP_CHAR);
+    fprintf(f, "\n");
+    continue;
+
+    case OP_CHARNC:
+    fprintf(f, " NC ");
+    do
+      {
+      code++;
+      code += 1 + print_char(f, code, utf8);
+      }
+    while (*code == OP_CHARNC);
+    fprintf(f, "\n");
+    continue;
+
+    case OP_CBRA:
+    case OP_SCBRA:
+    if (print_lengths) fprintf(f, "%3d ", GET(code, 1));
+      else fprintf(f, "    ");
+    fprintf(f, "%s %d", OP_names[*code], GET2(code, 1+LINK_SIZE));
+    break;
+
+    case OP_BRA:
+    case OP_SBRA:
+    case OP_KETRMAX:
+    case OP_KETRMIN:
+    case OP_ALT:
+    case OP_KET:
+    case OP_ASSERT:
+    case OP_ASSERT_NOT:
+    case OP_ASSERTBACK:
+    case OP_ASSERTBACK_NOT:
+    case OP_ONCE:
+    case OP_COND:
+    case OP_SCOND:
+    case OP_REVERSE:
+    if (print_lengths) fprintf(f, "%3d ", GET(code, 1));
+      else fprintf(f, "    ");
+    fprintf(f, "%s", OP_names[*code]);
+    break;
+
+    case OP_CLOSE:
+    fprintf(f, "    %s %d", OP_names[*code], GET2(code, 1));
+    break;
+
+    case OP_CREF:
+    case OP_NCREF:
+    fprintf(f, "%3d %s", GET2(code,1), OP_names[*code]);
+    break;
+
+    case OP_RREF:
+    c = GET2(code, 1);
+    if (c == RREF_ANY)
+      fprintf(f, "    Cond recurse any");
+    else
+      fprintf(f, "    Cond recurse %d", c);
+    break;
+
+    case OP_NRREF:
+    c = GET2(code, 1);
+    if (c == RREF_ANY)
+      fprintf(f, "    Cond nrecurse any");
+    else
+      fprintf(f, "    Cond nrecurse %d", c);
+    break;
+
+    case OP_DEF:
+    fprintf(f, "    Cond def");
+    break;
+
+    case OP_STAR:
+    case OP_MINSTAR:
+    case OP_POSSTAR:
+    case OP_PLUS:
+    case OP_MINPLUS:
+    case OP_POSPLUS:
+    case OP_QUERY:
+    case OP_MINQUERY:
+    case OP_POSQUERY:
+    case OP_TYPESTAR:
+    case OP_TYPEMINSTAR:
+    case OP_TYPEPOSSTAR:
+    case OP_TYPEPLUS:
+    case OP_TYPEMINPLUS:
+    case OP_TYPEPOSPLUS:
+    case OP_TYPEQUERY:
+    case OP_TYPEMINQUERY:
+    case OP_TYPEPOSQUERY:
+    fprintf(f, "    ");
+    if (*code >= OP_TYPESTAR)
+      {
+      fprintf(f, "%s", OP_names[code[1]]);
+      if (code[1] == OP_PROP || code[1] == OP_NOTPROP)
+        {
+        fprintf(f, " %s ", get_ucpname(code[2], code[3]));
+        extra = 2;
+        }
+      }
+    else extra = print_char(f, code+1, utf8);
+    fprintf(f, "%s", OP_names[*code]);
+    break;
+
+    case OP_EXACT:
+    case OP_UPTO:
+    case OP_MINUPTO:
+    case OP_POSUPTO:
+    fprintf(f, "    ");
+    extra = print_char(f, code+3, utf8);
+    fprintf(f, "{");
+    if (*code != OP_EXACT) fprintf(f, "0,");
+    fprintf(f, "%d}", GET2(code,1));
+    if (*code == OP_MINUPTO) fprintf(f, "?");
+      else if (*code == OP_POSUPTO) fprintf(f, "+");
+    break;
+
+    case OP_TYPEEXACT:
+    case OP_TYPEUPTO:
+    case OP_TYPEMINUPTO:
+    case OP_TYPEPOSUPTO:
+    fprintf(f, "    %s", OP_names[code[3]]);
+    if (code[3] == OP_PROP || code[3] == OP_NOTPROP)
+      {
+      fprintf(f, " %s ", get_ucpname(code[4], code[5]));
+      extra = 2;
+      }
+    fprintf(f, "{");
+    if (*code != OP_TYPEEXACT) fprintf(f, "0,");
+    fprintf(f, "%d}", GET2(code,1));
+    if (*code == OP_TYPEMINUPTO) fprintf(f, "?");
+      else if (*code == OP_TYPEPOSUPTO) fprintf(f, "+");
+    break;
+
+    case OP_NOT:
+    c = code[1];
+    if (PRINTABLE(c)) fprintf(f, "    [^%c]", c);
+      else fprintf(f, "    [^\\x%02x]", c);
+    break;
+
+    case OP_NOTSTAR:
+    case OP_NOTMINSTAR:
+    case OP_NOTPOSSTAR:
+    case OP_NOTPLUS:
+    case OP_NOTMINPLUS:
+    case OP_NOTPOSPLUS:
+    case OP_NOTQUERY:
+    case OP_NOTMINQUERY:
+    case OP_NOTPOSQUERY:
+    c = code[1];
+    if (PRINTABLE(c)) fprintf(f, "    [^%c]", c);
+      else fprintf(f, "    [^\\x%02x]", c);
+    fprintf(f, "%s", OP_names[*code]);
+    break;
+
+    case OP_NOTEXACT:
+    case OP_NOTUPTO:
+    case OP_NOTMINUPTO:
+    case OP_NOTPOSUPTO:
+    c = code[3];
+    if (PRINTABLE(c)) fprintf(f, "    [^%c]{", c);
+      else fprintf(f, "    [^\\x%02x]{", c);
+    if (*code != OP_NOTEXACT) fprintf(f, "0,");
+    fprintf(f, "%d}", GET2(code,1));
+    if (*code == OP_NOTMINUPTO) fprintf(f, "?");
+      else if (*code == OP_NOTPOSUPTO) fprintf(f, "+");
+    break;
+
+    case OP_RECURSE:
+    if (print_lengths) fprintf(f, "%3d ", GET(code, 1));
+      else fprintf(f, "    ");
+    fprintf(f, "%s", OP_names[*code]);
+    break;
+
+    case OP_REF:
+    fprintf(f, "    \\%d", GET2(code,1));
+    ccode = code + _pcre_OP_lengths[*code];
+    goto CLASS_REF_REPEAT;
+
+    case OP_CALLOUT:
+    fprintf(f, "    %s %d %d %d", OP_names[*code], code[1], GET(code,2),
+      GET(code, 2 + LINK_SIZE));
+    break;
+
+    case OP_PROP:
+    case OP_NOTPROP:
+    fprintf(f, "    %s %s", OP_names[*code], get_ucpname(code[1], code[2]));
+    break;
+
+    /* OP_XCLASS can only occur in UTF-8 mode. However, there's no harm in
+    having this code always here, and it makes it less messy without all those
+    #ifdefs. */
+
+    case OP_CLASS:
+    case OP_NCLASS:
+    case OP_XCLASS:
+      {
+      int i, min, max;
+      BOOL printmap;
+
+      fprintf(f, "    [");
+
+      if (*code == OP_XCLASS)
+        {
+        extra = GET(code, 1);
+        ccode = code + LINK_SIZE + 1;
+        printmap = (*ccode & XCL_MAP) != 0;
+        if ((*ccode++ & XCL_NOT) != 0) fprintf(f, "^");
+        }
+      else
+        {
+        printmap = TRUE;
+        ccode = code + 1;
+        }
+
+      /* Print a bit map */
+
+      if (printmap)
+        {
+        for (i = 0; i < 256; i++)
+          {
+          if ((ccode[i/8] & (1 << (i&7))) != 0)
+            {
+            int j;
+            for (j = i+1; j < 256; j++)
+              if ((ccode[j/8] & (1 << (j&7))) == 0) break;
+            if (i == '-' || i == ']') fprintf(f, "\\");
+            if (PRINTABLE(i)) fprintf(f, "%c", i);
+              else fprintf(f, "\\x%02x", i);
+            if (--j > i)
+              {
+              if (j != i + 1) fprintf(f, "-");
+              if (j == '-' || j == ']') fprintf(f, "\\");
+              if (PRINTABLE(j)) fprintf(f, "%c", j);
+                else fprintf(f, "\\x%02x", j);
+              }
+            i = j;
+            }
+          }
+        ccode += 32;
+        }
+
+      /* For an XCLASS there is always some additional data */
+
+      if (*code == OP_XCLASS)
+        {
+        int ch;
+        while ((ch = *ccode++) != XCL_END)
+          {
+          if (ch == XCL_PROP)
+            {
+            int ptype = *ccode++;
+            int pvalue = *ccode++;
+            fprintf(f, "\\p{%s}", get_ucpname(ptype, pvalue));
+            }
+          else if (ch == XCL_NOTPROP)
+            {
+            int ptype = *ccode++;
+            int pvalue = *ccode++;
+            fprintf(f, "\\P{%s}", get_ucpname(ptype, pvalue));
+            }
+          else
+            {
+            ccode += 1 + print_char(f, ccode, TRUE);
+            if (ch == XCL_RANGE)
+              {
+              fprintf(f, "-");
+              ccode += 1 + print_char(f, ccode, TRUE);
+              }
+            }
+          }
+        }
+
+      /* Indicate a non-UTF8 class which was created by negation */
+
+      fprintf(f, "]%s", (*code == OP_NCLASS)? " (neg)" : "");
+
+      /* Handle repeats after a class or a back reference */
+
+      CLASS_REF_REPEAT:
+      switch(*ccode)
+        {
+        case OP_CRSTAR:
+        case OP_CRMINSTAR:
+        case OP_CRPLUS:
+        case OP_CRMINPLUS:
+        case OP_CRQUERY:
+        case OP_CRMINQUERY:
+        fprintf(f, "%s", OP_names[*ccode]);
+        extra += _pcre_OP_lengths[*ccode];
+        break;
+
+        case OP_CRRANGE:
+        case OP_CRMINRANGE:
+        min = GET2(ccode,1);
+        max = GET2(ccode,3);
+        if (max == 0) fprintf(f, "{%d,}", min);
+        else fprintf(f, "{%d,%d}", min, max);
+        if (*ccode == OP_CRMINRANGE) fprintf(f, "?");
+        extra += _pcre_OP_lengths[*ccode];
+        break;
+
+        /* Do nothing if it's not a repeat; this code stops picky compilers
+        warning about the lack of a default code path. */
+
+        default:
+        break;
+        }
+      }
+    break;
+
+    case OP_MARK:
+    case OP_PRUNE_ARG:
+    case OP_SKIP_ARG:
+    fprintf(f, "    %s %s", OP_names[*code], code + 2);
+    extra += code[1];
+    break;
+
+    case OP_THEN:
+    if (print_lengths)
+      fprintf(f, "    %s %d", OP_names[*code], GET(code, 1));
+    else
+      fprintf(f, "    %s", OP_names[*code]);
+    break;
+
+    case OP_THEN_ARG:
+    if (print_lengths)
+      fprintf(f, "    %s %d %s", OP_names[*code], GET(code, 1),
+        code + 2 + LINK_SIZE);
+    else
+      fprintf(f, "    %s %s", OP_names[*code], code + 2 + LINK_SIZE);
+    extra += code[1+LINK_SIZE];
+    break;
+
+    /* Anything else is just an item with no data*/
+
+    default:
+    fprintf(f, "    %s", OP_names[*code]);
+    break;
+    }
+
+  code += _pcre_OP_lengths[*code] + extra;
+  fprintf(f, "\n");
+  }
+}
+
+/* End of pcre_printint.src */
diff --git a/ext/pcre/pcrelib/pcre_refcount.c b/ext/pcre/pcrelib/pcre_refcount.c
new file mode 100644
index 0000000..ec16713
--- /dev/null
+++ b/ext/pcre/pcrelib/pcre_refcount.c
@@ -0,0 +1,87 @@
+/*************************************************
+*      Perl-Compatible Regular Expressions       *
+*************************************************/
+
+/* PCRE is a library of functions to support regular expressions whose syntax
+and semantics are as close as possible to those of the Perl 5 language.
+
+                       Written by Philip Hazel
+           Copyright (c) 1997-2012 University of Cambridge
+
+-----------------------------------------------------------------------------
+Redistribution and use in source and binary forms, with or without
+modification, are permitted provided that the following conditions are met:
+
+    * Redistributions of source code must retain the above copyright notice,
+      this list of conditions and the following disclaimer.
+
+    * Redistributions in binary form must reproduce the above copyright
+      notice, this list of conditions and the following disclaimer in the
+      documentation and/or other materials provided with the distribution.
+
+    * Neither the name of the University of Cambridge nor the names of its
+      contributors may be used to endorse or promote products derived from
+      this software without specific prior written permission.
+
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+POSSIBILITY OF SUCH DAMAGE.
+-----------------------------------------------------------------------------
+*/
+
+
+/* This module contains the external function pcre_refcount(), which is an
+auxiliary function that can be used to maintain a reference count in a compiled
+pattern data block. This might be helpful in applications where the block is
+shared by different users. */
+
+
+#include "config.h"
+
+#include "pcre_internal.h"
+
+
+/*************************************************
+*           Maintain reference count             *
+*************************************************/
+
+/* The reference count is a 16-bit field, initialized to zero. It is not
+possible to transfer a non-zero count from one host to a different host that
+has a different byte order - though I can't see why anyone in their right mind
+would ever want to do that!
+
+Arguments:
+  argument_re   points to compiled code
+  adjust        value to add to the count
+
+Returns:        the (possibly updated) count value (a non-negative number), or
+                a negative error number
+*/
+
+#ifdef COMPILE_PCRE8
+PCRE_EXP_DEFN int PCRE_CALL_CONVENTION
+pcre_refcount(pcre *argument_re, int adjust)
+#else
+PCRE_EXP_DEFN int PCRE_CALL_CONVENTION
+pcre16_refcount(pcre16 *argument_re, int adjust)
+#endif
+{
+REAL_PCRE *re = (REAL_PCRE *)argument_re;
+if (re == NULL) return PCRE_ERROR_NULL;
+if (re->magic_number != MAGIC_NUMBER) return PCRE_ERROR_BADMAGIC;
+if ((re->flags & PCRE_MODE) == 0) return PCRE_ERROR_BADMODE;
+re->ref_count = (-adjust > re->ref_count)? 0 :
+                (adjust + re->ref_count > 65535)? 65535 :
+                re->ref_count + adjust;
+return re->ref_count;
+}
+
+/* End of pcre_refcount.c */
diff --git a/ext/pcre/pcrelib/pcre_study.c b/ext/pcre/pcrelib/pcre_study.c
new file mode 100644
index 0000000..9d893d5
--- /dev/null
+++ b/ext/pcre/pcrelib/pcre_study.c
@@ -0,0 +1,1532 @@
+/*************************************************
+*      Perl-Compatible Regular Expressions       *
+*************************************************/
+
+/* PCRE is a library of functions to support regular expressions whose syntax
+and semantics are as close as possible to those of the Perl 5 language.
+
+                       Written by Philip Hazel
+           Copyright (c) 1997-2012 University of Cambridge
+
+-----------------------------------------------------------------------------
+Redistribution and use in source and binary forms, with or without
+modification, are permitted provided that the following conditions are met:
+
+    * Redistributions of source code must retain the above copyright notice,
+      this list of conditions and the following disclaimer.
+
+    * Redistributions in binary form must reproduce the above copyright
+      notice, this list of conditions and the following disclaimer in the
+      documentation and/or other materials provided with the distribution.
+
+    * Neither the name of the University of Cambridge nor the names of its
+      contributors may be used to endorse or promote products derived from
+      this software without specific prior written permission.
+
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+POSSIBILITY OF SUCH DAMAGE.
+-----------------------------------------------------------------------------
+*/
+
+
+/* This module contains the external function pcre_study(), along with local
+supporting functions. */
+
+
+#include "config.h"
+
+#include "pcre_internal.h"
+
+#define SET_BIT(c) start_bits[c/8] |= (1 << (c&7))
+
+/* Returns from set_start_bits() */
+
+enum { SSB_FAIL, SSB_DONE, SSB_CONTINUE, SSB_UNKNOWN };
+
+
+
+/*************************************************
+*   Find the minimum subject length for a group  *
+*************************************************/
+
+/* Scan a parenthesized group and compute the minimum length of subject that
+is needed to match it. This is a lower bound; it does not mean there is a
+string of that length that matches. In UTF8 mode, the result is in characters
+rather than bytes.
+
+Arguments:
+  code            pointer to start of group (the bracket)
+  startcode       pointer to start of the whole pattern
+  options         the compiling options
+  int             RECURSE depth
+
+Returns:   the minimum length
+           -1 if \C in UTF-8 mode or (*ACCEPT) was encountered
+           -2 internal error (missing capturing bracket)
+           -3 internal error (opcode not listed)
+*/
+
+static int
+find_minlength(const pcre_uchar *code, const pcre_uchar *startcode, int options,
+  int recurse_depth)
+{
+int length = -1;
+/* PCRE_UTF16 has the same value as PCRE_UTF8. */
+BOOL utf = (options & PCRE_UTF8) != 0;
+BOOL had_recurse = FALSE;
+register int branchlength = 0;
+register pcre_uchar *cc = (pcre_uchar *)code + 1 + LINK_SIZE;
+
+if (*code == OP_CBRA || *code == OP_SCBRA ||
+    *code == OP_CBRAPOS || *code == OP_SCBRAPOS) cc += IMM2_SIZE;
+
+/* Scan along the opcodes for this branch. If we get to the end of the
+branch, check the length against that of the other branches. */
+
+for (;;)
+  {
+  int d, min;
+  pcre_uchar *cs, *ce;
+  register int op = *cc;
+
+  switch (op)
+    {
+    case OP_COND:
+    case OP_SCOND:
+
+    /* If there is only one branch in a condition, the implied branch has zero
+    length, so we don't add anything. This covers the DEFINE "condition"
+    automatically. */
+
+    cs = cc + GET(cc, 1);
+    if (*cs != OP_ALT)
+      {
+      cc = cs + 1 + LINK_SIZE;
+      break;
+      }
+
+    /* Otherwise we can fall through and treat it the same as any other
+    subpattern. */
+
+    case OP_CBRA:
+    case OP_SCBRA:
+    case OP_BRA:
+    case OP_SBRA:
+    case OP_CBRAPOS:
+    case OP_SCBRAPOS:
+    case OP_BRAPOS:
+    case OP_SBRAPOS:
+    case OP_ONCE:
+    case OP_ONCE_NC:
+    d = find_minlength(cc, startcode, options, recurse_depth);
+    if (d < 0) return d;
+    branchlength += d;
+    do cc += GET(cc, 1); while (*cc == OP_ALT);
+    cc += 1 + LINK_SIZE;
+    break;
+
+    /* ACCEPT makes things far too complicated; we have to give up. */
+
+    case OP_ACCEPT:
+    case OP_ASSERT_ACCEPT:
+    return -1;
+
+    /* Reached end of a branch; if it's a ket it is the end of a nested
+    call. If it's ALT it is an alternation in a nested call. If it is END it's
+    the end of the outer call. All can be handled by the same code. If an
+    ACCEPT was previously encountered, use the length that was in force at that
+    time, and pass back the shortest ACCEPT length. */
+
+    case OP_ALT:
+    case OP_KET:
+    case OP_KETRMAX:
+    case OP_KETRMIN:
+    case OP_KETRPOS:
+    case OP_END:
+    if (length < 0 || (!had_recurse && branchlength < length))
+      length = branchlength;
+    if (op != OP_ALT) return length;
+    cc += 1 + LINK_SIZE;
+    branchlength = 0;
+    had_recurse = FALSE;
+    break;
+
+    /* Skip over assertive subpatterns */
+
+    case OP_ASSERT:
+    case OP_ASSERT_NOT:
+    case OP_ASSERTBACK:
+    case OP_ASSERTBACK_NOT:
+    do cc += GET(cc, 1); while (*cc == OP_ALT);
+    /* Fall through */
+
+    /* Skip over things that don't match chars */
+
+    case OP_REVERSE:
+    case OP_CREF:
+    case OP_NCREF:
+    case OP_RREF:
+    case OP_NRREF:
+    case OP_DEF:
+    case OP_CALLOUT:
+    case OP_SOD:
+    case OP_SOM:
+    case OP_EOD:
+    case OP_EODN:
+    case OP_CIRC:
+    case OP_CIRCM:
+    case OP_DOLL:
+    case OP_DOLLM:
+    case OP_NOT_WORD_BOUNDARY:
+    case OP_WORD_BOUNDARY:
+    cc += PRIV(OP_lengths)[*cc];
+    break;
+
+    /* Skip over a subpattern that has a {0} or {0,x} quantifier */
+
+    case OP_BRAZERO:
+    case OP_BRAMINZERO:
+    case OP_BRAPOSZERO:
+    case OP_SKIPZERO:
+    cc += PRIV(OP_lengths)[*cc];
+    do cc += GET(cc, 1); while (*cc == OP_ALT);
+    cc += 1 + LINK_SIZE;
+    break;
+
+    /* Handle literal characters and + repetitions */
+
+    case OP_CHAR:
+    case OP_CHARI:
+    case OP_NOT:
+    case OP_NOTI:
+    case OP_PLUS:
+    case OP_PLUSI:
+    case OP_MINPLUS:
+    case OP_MINPLUSI:
+    case OP_POSPLUS:
+    case OP_POSPLUSI:
+    case OP_NOTPLUS:
+    case OP_NOTPLUSI:
+    case OP_NOTMINPLUS:
+    case OP_NOTMINPLUSI:
+    case OP_NOTPOSPLUS:
+    case OP_NOTPOSPLUSI:
+    branchlength++;
+    cc += 2;
+#ifdef SUPPORT_UTF
+    if (utf && HAS_EXTRALEN(cc[-1])) cc += GET_EXTRALEN(cc[-1]);
+#endif
+    break;
+
+    case OP_TYPEPLUS:
+    case OP_TYPEMINPLUS:
+    case OP_TYPEPOSPLUS:
+    branchlength++;
+    cc += (cc[1] == OP_PROP || cc[1] == OP_NOTPROP)? 4 : 2;
+    break;
+
+    /* Handle exact repetitions. The count is already in characters, but we
+    need to skip over a multibyte character in UTF8 mode.  */
+
+    case OP_EXACT:
+    case OP_EXACTI:
+    case OP_NOTEXACT:
+    case OP_NOTEXACTI:
+    branchlength += GET2(cc,1);
+    cc += 2 + IMM2_SIZE;
+#ifdef SUPPORT_UTF
+    if (utf && HAS_EXTRALEN(cc[-1])) cc += GET_EXTRALEN(cc[-1]);
+#endif
+    break;
+
+    case OP_TYPEEXACT:
+    branchlength += GET2(cc,1);
+    cc += 2 + IMM2_SIZE + ((cc[1 + IMM2_SIZE] == OP_PROP
+      || cc[1 + IMM2_SIZE] == OP_NOTPROP)? 2 : 0);
+    break;
+
+    /* Handle single-char non-literal matchers */
+
+    case OP_PROP:
+    case OP_NOTPROP:
+    cc += 2;
+    /* Fall through */
+
+    case OP_NOT_DIGIT:
+    case OP_DIGIT:
+    case OP_NOT_WHITESPACE:
+    case OP_WHITESPACE:
+    case OP_NOT_WORDCHAR:
+    case OP_WORDCHAR:
+    case OP_ANY:
+    case OP_ALLANY:
+    case OP_EXTUNI:
+    case OP_HSPACE:
+    case OP_NOT_HSPACE:
+    case OP_VSPACE:
+    case OP_NOT_VSPACE:
+    branchlength++;
+    cc++;
+    break;
+
+    /* "Any newline" might match two characters, but it also might match just
+    one. */
+
+    case OP_ANYNL:
+    branchlength += 1;
+    cc++;
+    break;
+
+    /* The single-byte matcher means we can't proceed in UTF-8 mode. (In
+    non-UTF-8 mode \C will actually be turned into OP_ALLANY, so won't ever
+    appear, but leave the code, just in case.) */
+
+    case OP_ANYBYTE:
+#ifdef SUPPORT_UTF
+    if (utf) return -1;
+#endif
+    branchlength++;
+    cc++;
+    break;
+
+    /* For repeated character types, we have to test for \p and \P, which have
+    an extra two bytes of parameters. */
+
+    case OP_TYPESTAR:
+    case OP_TYPEMINSTAR:
+    case OP_TYPEQUERY:
+    case OP_TYPEMINQUERY:
+    case OP_TYPEPOSSTAR:
+    case OP_TYPEPOSQUERY:
+    if (cc[1] == OP_PROP || cc[1] == OP_NOTPROP) cc += 2;
+    cc += PRIV(OP_lengths)[op];
+    break;
+
+    case OP_TYPEUPTO:
+    case OP_TYPEMINUPTO:
+    case OP_TYPEPOSUPTO:
+    if (cc[1 + IMM2_SIZE] == OP_PROP
+      || cc[1 + IMM2_SIZE] == OP_NOTPROP) cc += 2;
+    cc += PRIV(OP_lengths)[op];
+    break;
+
+    /* Check a class for variable quantification */
+
+#if defined SUPPORT_UTF || !defined COMPILE_PCRE8
+    case OP_XCLASS:
+    cc += GET(cc, 1) - PRIV(OP_lengths)[OP_CLASS];
+    /* Fall through */
+#endif
+
+    case OP_CLASS:
+    case OP_NCLASS:
+    cc += PRIV(OP_lengths)[OP_CLASS];
+
+    switch (*cc)
+      {
+      case OP_CRPLUS:
+      case OP_CRMINPLUS:
+      branchlength++;
+      /* Fall through */
+
+      case OP_CRSTAR:
+      case OP_CRMINSTAR:
+      case OP_CRQUERY:
+      case OP_CRMINQUERY:
+      cc++;
+      break;
+
+      case OP_CRRANGE:
+      case OP_CRMINRANGE:
+      branchlength += GET2(cc,1);
+      cc += 1 + 2 * IMM2_SIZE;
+      break;
+
+      default:
+      branchlength++;
+      break;
+      }
+    break;
+
+    /* Backreferences and subroutine calls are treated in the same way: we find
+    the minimum length for the subpattern. A recursion, however, causes an
+    a flag to be set that causes the length of this branch to be ignored. The
+    logic is that a recursion can only make sense if there is another
+    alternation that stops the recursing. That will provide the minimum length
+    (when no recursion happens). A backreference within the group that it is
+    referencing behaves in the same way.
+
+    If PCRE_JAVASCRIPT_COMPAT is set, a backreference to an unset bracket
+    matches an empty string (by default it causes a matching failure), so in
+    that case we must set the minimum length to zero. */
+
+    case OP_REF:
+    case OP_REFI:
+    if ((options & PCRE_JAVASCRIPT_COMPAT) == 0)
+      {
+      ce = cs = (pcre_uchar *)PRIV(find_bracket)(startcode, utf, GET2(cc, 1));
+      if (cs == NULL) return -2;
+      do ce += GET(ce, 1); while (*ce == OP_ALT);
+      if (cc > cs && cc < ce)
+        {
+        d = 0;
+        had_recurse = TRUE;
+        }
+      else
+        {
+        d = find_minlength(cs, startcode, options, recurse_depth);
+        }
+      }
+    else d = 0;
+    cc += 1 + IMM2_SIZE;
+
+    /* Handle repeated back references */
+
+    switch (*cc)
+      {
+      case OP_CRSTAR:
+      case OP_CRMINSTAR:
+      case OP_CRQUERY:
+      case OP_CRMINQUERY:
+      min = 0;
+      cc++;
+      break;
+
+      case OP_CRPLUS:
+      case OP_CRMINPLUS:
+      min = 1;
+      cc++;
+      break;
+
+      case OP_CRRANGE:
+      case OP_CRMINRANGE:
+      min = GET2(cc, 1);
+      cc += 1 + 2 * IMM2_SIZE;
+      break;
+
+      default:
+      min = 1;
+      break;
+      }
+
+    branchlength += min * d;
+    break;
+
+    /* We can easily detect direct recursion, but not mutual recursion. This is
+    caught by a recursion depth count. */
+
+    case OP_RECURSE:
+    cs = ce = (pcre_uchar *)startcode + GET(cc, 1);
+    do ce += GET(ce, 1); while (*ce == OP_ALT);
+    if ((cc > cs && cc < ce) || recurse_depth > 10)
+      had_recurse = TRUE;
+    else
+      {
+      branchlength += find_minlength(cs, startcode, options, recurse_depth + 1);
+      }
+    cc += 1 + LINK_SIZE;
+    break;
+
+    /* Anything else does not or need not match a character. We can get the
+    item's length from the table, but for those that can match zero occurrences
+    of a character, we must take special action for UTF-8 characters. As it
+    happens, the "NOT" versions of these opcodes are used at present only for
+    ASCII characters, so they could be omitted from this list. However, in
+    future that may change, so we include them here so as not to leave a
+    gotcha for a future maintainer. */
+
+    case OP_UPTO:
+    case OP_UPTOI:
+    case OP_NOTUPTO:
+    case OP_NOTUPTOI:
+    case OP_MINUPTO:
+    case OP_MINUPTOI:
+    case OP_NOTMINUPTO:
+    case OP_NOTMINUPTOI:
+    case OP_POSUPTO:
+    case OP_POSUPTOI:
+    case OP_NOTPOSUPTO:
+    case OP_NOTPOSUPTOI:
+
+    case OP_STAR:
+    case OP_STARI:
+    case OP_NOTSTAR:
+    case OP_NOTSTARI:
+    case OP_MINSTAR:
+    case OP_MINSTARI:
+    case OP_NOTMINSTAR:
+    case OP_NOTMINSTARI:
+    case OP_POSSTAR:
+    case OP_POSSTARI:
+    case OP_NOTPOSSTAR:
+    case OP_NOTPOSSTARI:
+
+    case OP_QUERY:
+    case OP_QUERYI:
+    case OP_NOTQUERY:
+    case OP_NOTQUERYI:
+    case OP_MINQUERY:
+    case OP_MINQUERYI:
+    case OP_NOTMINQUERY:
+    case OP_NOTMINQUERYI:
+    case OP_POSQUERY:
+    case OP_POSQUERYI:
+    case OP_NOTPOSQUERY:
+    case OP_NOTPOSQUERYI:
+
+    cc += PRIV(OP_lengths)[op];
+#ifdef SUPPORT_UTF
+    if (utf && HAS_EXTRALEN(cc[-1])) cc += GET_EXTRALEN(cc[-1]);
+#endif
+    break;
+
+    /* Skip these, but we need to add in the name length. */
+
+    case OP_MARK:
+    case OP_PRUNE_ARG:
+    case OP_SKIP_ARG:
+    case OP_THEN_ARG:
+    cc += PRIV(OP_lengths)[op] + cc[1];
+    break;
+
+    /* The remaining opcodes are just skipped over. */
+
+    case OP_CLOSE:
+    case OP_COMMIT:
+    case OP_FAIL:
+    case OP_PRUNE:
+    case OP_SET_SOM:
+    case OP_SKIP:
+    case OP_THEN:
+    cc += PRIV(OP_lengths)[op];
+    break;
+
+    /* This should not occur: we list all opcodes explicitly so that when
+    new ones get added they are properly considered. */
+
+    default:
+    return -3;
+    }
+  }
+/* Control never gets here */
+}
+
+
+
+/*************************************************
+*      Set a bit and maybe its alternate case    *
+*************************************************/
+
+/* Given a character, set its first byte's bit in the table, and also the
+corresponding bit for the other version of a letter if we are caseless. In
+UTF-8 mode, for characters greater than 127, we can only do the caseless thing
+when Unicode property support is available.
+
+Arguments:
+  start_bits    points to the bit map
+  p             points to the character
+  caseless      the caseless flag
+  cd            the block with char table pointers
+  utf           TRUE for UTF-8 / UTF-16 mode
+
+Returns:        pointer after the character
+*/
+
+static const pcre_uchar *
+set_table_bit(pcre_uint8 *start_bits, const pcre_uchar *p, BOOL caseless,
+  compile_data *cd, BOOL utf)
+{
+unsigned int c = *p;
+
+#ifdef COMPILE_PCRE8
+SET_BIT(c);
+
+#ifdef SUPPORT_UTF
+if (utf && c > 127)
+  {
+  GETCHARINC(c, p);
+#ifdef SUPPORT_UCP
+  if (caseless)
+    {
+    pcre_uchar buff[6];
+    c = UCD_OTHERCASE(c);
+    (void)PRIV(ord2utf)(c, buff);
+    SET_BIT(buff[0]);
+    }
+#endif
+  return p;
+  }
+#endif
+
+/* Not UTF-8 mode, or character is less than 127. */
+
+if (caseless && (cd->ctypes[c] & ctype_letter) != 0) SET_BIT(cd->fcc[c]);
+return p + 1;
+#endif
+
+#ifdef COMPILE_PCRE16
+if (c > 0xff)
+  {
+  c = 0xff;
+  caseless = FALSE;
+  }
+SET_BIT(c);
+
+#ifdef SUPPORT_UTF
+if (utf && c > 127)
+  {
+  GETCHARINC(c, p);
+#ifdef SUPPORT_UCP
+  if (caseless)
+    {
+    c = UCD_OTHERCASE(c);
+    if (c > 0xff)
+      c = 0xff;
+    SET_BIT(c);
+    }
+#endif
+  return p;
+  }
+#endif
+
+if (caseless && (cd->ctypes[c] & ctype_letter) != 0) SET_BIT(cd->fcc[c]);
+return p + 1;
+#endif
+}
+
+
+
+/*************************************************
+*     Set bits for a positive character type     *
+*************************************************/
+
+/* This function sets starting bits for a character type. In UTF-8 mode, we can
+only do a direct setting for bytes less than 128, as otherwise there can be
+confusion with bytes in the middle of UTF-8 characters. In a "traditional"
+environment, the tables will only recognize ASCII characters anyway, but in at
+least one Windows environment, some higher bytes bits were set in the tables.
+So we deal with that case by considering the UTF-8 encoding.
+
+Arguments:
+  start_bits     the starting bitmap
+  cbit type      the type of character wanted
+  table_limit    32 for non-UTF-8; 16 for UTF-8
+  cd             the block with char table pointers
+
+Returns:         nothing
+*/
+
+static void
+set_type_bits(pcre_uint8 *start_bits, int cbit_type, int table_limit,
+  compile_data *cd)
+{
+register int c;
+for (c = 0; c < table_limit; c++) start_bits[c] |= cd->cbits[c+cbit_type];
+#if defined SUPPORT_UTF && defined COMPILE_PCRE8
+if (table_limit == 32) return;
+for (c = 128; c < 256; c++)
+  {
+  if ((cd->cbits[c/8] & (1 << (c&7))) != 0)
+    {
+    pcre_uchar buff[6];
+    (void)PRIV(ord2utf)(c, buff);
+    SET_BIT(buff[0]);
+    }
+  }
+#endif
+}
+
+
+/*************************************************
+*     Set bits for a negative character type     *
+*************************************************/
+
+/* This function sets starting bits for a negative character type such as \D.
+In UTF-8 mode, we can only do a direct setting for bytes less than 128, as
+otherwise there can be confusion with bytes in the middle of UTF-8 characters.
+Unlike in the positive case, where we can set appropriate starting bits for
+specific high-valued UTF-8 characters, in this case we have to set the bits for
+all high-valued characters. The lowest is 0xc2, but we overkill by starting at
+0xc0 (192) for simplicity.
+
+Arguments:
+  start_bits     the starting bitmap
+  cbit type      the type of character wanted
+  table_limit    32 for non-UTF-8; 16 for UTF-8
+  cd             the block with char table pointers
+
+Returns:         nothing
+*/
+
+static void
+set_nottype_bits(pcre_uint8 *start_bits, int cbit_type, int table_limit,
+  compile_data *cd)
+{
+register int c;
+for (c = 0; c < table_limit; c++) start_bits[c] |= ~cd->cbits[c+cbit_type];
+#if defined SUPPORT_UTF && defined COMPILE_PCRE8
+if (table_limit != 32) for (c = 24; c < 32; c++) start_bits[c] = 0xff;
+#endif
+}
+
+
+
+/*************************************************
+*          Create bitmap of starting bytes       *
+*************************************************/
+
+/* This function scans a compiled unanchored expression recursively and
+attempts to build a bitmap of the set of possible starting bytes. As time goes
+by, we may be able to get more clever at doing this. The SSB_CONTINUE return is
+useful for parenthesized groups in patterns such as (a*)b where the group
+provides some optional starting bytes but scanning must continue at the outer
+level to find at least one mandatory byte. At the outermost level, this
+function fails unless the result is SSB_DONE.
+
+Arguments:
+  code         points to an expression
+  start_bits   points to a 32-byte table, initialized to 0
+  utf          TRUE if in UTF-8 / UTF-16 mode
+  cd           the block with char table pointers
+
+Returns:       SSB_FAIL     => Failed to find any starting bytes
+               SSB_DONE     => Found mandatory starting bytes
+               SSB_CONTINUE => Found optional starting bytes
+               SSB_UNKNOWN  => Hit an unrecognized opcode
+*/
+
+static int
+set_start_bits(const pcre_uchar *code, pcre_uint8 *start_bits, BOOL utf,
+  compile_data *cd)
+{
+register int c;
+int yield = SSB_DONE;
+#if defined SUPPORT_UTF && defined COMPILE_PCRE8
+int table_limit = utf? 16:32;
+#else
+int table_limit = 32;
+#endif
+
+#if 0
+/* ========================================================================= */
+/* The following comment and code was inserted in January 1999. In May 2006,
+when it was observed to cause compiler warnings about unused values, I took it
+out again. If anybody is still using OS/2, they will have to put it back
+manually. */
+
+/* This next statement and the later reference to dummy are here in order to
+trick the optimizer of the IBM C compiler for OS/2 into generating correct
+code. Apparently IBM isn't going to fix the problem, and we would rather not
+disable optimization (in this module it actually makes a big difference, and
+the pcre module can use all the optimization it can get). */
+
+volatile int dummy;
+/* ========================================================================= */
+#endif
+
+do
+  {
+  BOOL try_next = TRUE;
+  const pcre_uchar *tcode = code + 1 + LINK_SIZE;
+
+  if (*code == OP_CBRA || *code == OP_SCBRA ||
+      *code == OP_CBRAPOS || *code == OP_SCBRAPOS) tcode += IMM2_SIZE;
+
+  while (try_next)    /* Loop for items in this branch */
+    {
+    int rc;
+
+    switch(*tcode)
+      {
+      /* If we reach something we don't understand, it means a new opcode has
+      been created that hasn't been added to this code. Hopefully this problem
+      will be discovered during testing. */
+
+      default:
+      return SSB_UNKNOWN;
+
+      /* Fail for a valid opcode that implies no starting bits. */
+
+      case OP_ACCEPT:
+      case OP_ASSERT_ACCEPT:
+      case OP_ALLANY:
+      case OP_ANY:
+      case OP_ANYBYTE:
+      case OP_CIRC:
+      case OP_CIRCM:
+      case OP_CLOSE:
+      case OP_COMMIT:
+      case OP_COND:
+      case OP_CREF:
+      case OP_DEF:
+      case OP_DOLL:
+      case OP_DOLLM:
+      case OP_END:
+      case OP_EOD:
+      case OP_EODN:
+      case OP_EXTUNI:
+      case OP_FAIL:
+      case OP_MARK:
+      case OP_NCREF:
+      case OP_NOT:
+      case OP_NOTEXACT:
+      case OP_NOTEXACTI:
+      case OP_NOTI:
+      case OP_NOTMINPLUS:
+      case OP_NOTMINPLUSI:
+      case OP_NOTMINQUERY:
+      case OP_NOTMINQUERYI:
+      case OP_NOTMINSTAR:
+      case OP_NOTMINSTARI:
+      case OP_NOTMINUPTO:
+      case OP_NOTMINUPTOI:
+      case OP_NOTPLUS:
+      case OP_NOTPLUSI:
+      case OP_NOTPOSPLUS:
+      case OP_NOTPOSPLUSI:
+      case OP_NOTPOSQUERY:
+      case OP_NOTPOSQUERYI:
+      case OP_NOTPOSSTAR:
+      case OP_NOTPOSSTARI:
+      case OP_NOTPOSUPTO:
+      case OP_NOTPOSUPTOI:
+      case OP_NOTPROP:
+      case OP_NOTQUERY:
+      case OP_NOTQUERYI:
+      case OP_NOTSTAR:
+      case OP_NOTSTARI:
+      case OP_NOTUPTO:
+      case OP_NOTUPTOI:
+      case OP_NOT_HSPACE:
+      case OP_NOT_VSPACE:
+      case OP_NRREF:
+      case OP_PROP:
+      case OP_PRUNE:
+      case OP_PRUNE_ARG:
+      case OP_RECURSE:
+      case OP_REF:
+      case OP_REFI:
+      case OP_REVERSE:
+      case OP_RREF:
+      case OP_SCOND:
+      case OP_SET_SOM:
+      case OP_SKIP:
+      case OP_SKIP_ARG:
+      case OP_SOD:
+      case OP_SOM:
+      case OP_THEN:
+      case OP_THEN_ARG:
+#if defined SUPPORT_UTF || !defined COMPILE_PCRE8
+      case OP_XCLASS:
+#endif
+      return SSB_FAIL;
+
+      /* We can ignore word boundary tests. */
+
+      case OP_WORD_BOUNDARY:
+      case OP_NOT_WORD_BOUNDARY:
+      tcode++;
+      break;
+
+      /* If we hit a bracket or a positive lookahead assertion, recurse to set
+      bits from within the subpattern. If it can't find anything, we have to
+      give up. If it finds some mandatory character(s), we are done for this
+      branch. Otherwise, carry on scanning after the subpattern. */
+
+      case OP_BRA:
+      case OP_SBRA:
+      case OP_CBRA:
+      case OP_SCBRA:
+      case OP_BRAPOS:
+      case OP_SBRAPOS:
+      case OP_CBRAPOS:
+      case OP_SCBRAPOS:
+      case OP_ONCE:
+      case OP_ONCE_NC:
+      case OP_ASSERT:
+      rc = set_start_bits(tcode, start_bits, utf, cd);
+      if (rc == SSB_FAIL || rc == SSB_UNKNOWN) return rc;
+      if (rc == SSB_DONE) try_next = FALSE; else
+        {
+        do tcode += GET(tcode, 1); while (*tcode == OP_ALT);
+        tcode += 1 + LINK_SIZE;
+        }
+      break;
+
+      /* If we hit ALT or KET, it means we haven't found anything mandatory in
+      this branch, though we might have found something optional. For ALT, we
+      continue with the next alternative, but we have to arrange that the final
+      result from subpattern is SSB_CONTINUE rather than SSB_DONE. For KET,
+      return SSB_CONTINUE: if this is the top level, that indicates failure,
+      but after a nested subpattern, it causes scanning to continue. */
+
+      case OP_ALT:
+      yield = SSB_CONTINUE;
+      try_next = FALSE;
+      break;
+
+      case OP_KET:
+      case OP_KETRMAX:
+      case OP_KETRMIN:
+      case OP_KETRPOS:
+      return SSB_CONTINUE;
+
+      /* Skip over callout */
+
+      case OP_CALLOUT:
+      tcode += 2 + 2*LINK_SIZE;
+      break;
+
+      /* Skip over lookbehind and negative lookahead assertions */
+
+      case OP_ASSERT_NOT:
+      case OP_ASSERTBACK:
+      case OP_ASSERTBACK_NOT:
+      do tcode += GET(tcode, 1); while (*tcode == OP_ALT);
+      tcode += 1 + LINK_SIZE;
+      break;
+
+      /* BRAZERO does the bracket, but carries on. */
+
+      case OP_BRAZERO:
+      case OP_BRAMINZERO:
+      case OP_BRAPOSZERO:
+      rc = set_start_bits(++tcode, start_bits, utf, cd);
+      if (rc == SSB_FAIL || rc == SSB_UNKNOWN) return rc;
+/* =========================================================================
+      See the comment at the head of this function concerning the next line,
+      which was an old fudge for the benefit of OS/2.
+      dummy = 1;
+  ========================================================================= */
+      do tcode += GET(tcode,1); while (*tcode == OP_ALT);
+      tcode += 1 + LINK_SIZE;
+      break;
+
+      /* SKIPZERO skips the bracket. */
+
+      case OP_SKIPZERO:
+      tcode++;
+      do tcode += GET(tcode,1); while (*tcode == OP_ALT);
+      tcode += 1 + LINK_SIZE;
+      break;
+
+      /* Single-char * or ? sets the bit and tries the next item */
+
+      case OP_STAR:
+      case OP_MINSTAR:
+      case OP_POSSTAR:
+      case OP_QUERY:
+      case OP_MINQUERY:
+      case OP_POSQUERY:
+      tcode = set_table_bit(start_bits, tcode + 1, FALSE, cd, utf);
+      break;
+
+      case OP_STARI:
+      case OP_MINSTARI:
+      case OP_POSSTARI:
+      case OP_QUERYI:
+      case OP_MINQUERYI:
+      case OP_POSQUERYI:
+      tcode = set_table_bit(start_bits, tcode + 1, TRUE, cd, utf);
+      break;
+
+      /* Single-char upto sets the bit and tries the next */
+
+      case OP_UPTO:
+      case OP_MINUPTO:
+      case OP_POSUPTO:
+      tcode = set_table_bit(start_bits, tcode + 1 + IMM2_SIZE, FALSE, cd, utf);
+      break;
+
+      case OP_UPTOI:
+      case OP_MINUPTOI:
+      case OP_POSUPTOI:
+      tcode = set_table_bit(start_bits, tcode + 1 + IMM2_SIZE, TRUE, cd, utf);
+      break;
+
+      /* At least one single char sets the bit and stops */
+
+      case OP_EXACT:
+      tcode += IMM2_SIZE;
+      /* Fall through */
+      case OP_CHAR:
+      case OP_PLUS:
+      case OP_MINPLUS:
+      case OP_POSPLUS:
+      (void)set_table_bit(start_bits, tcode + 1, FALSE, cd, utf);
+      try_next = FALSE;
+      break;
+
+      case OP_EXACTI:
+      tcode += IMM2_SIZE;
+      /* Fall through */
+      case OP_CHARI:
+      case OP_PLUSI:
+      case OP_MINPLUSI:
+      case OP_POSPLUSI:
+      (void)set_table_bit(start_bits, tcode + 1, TRUE, cd, utf);
+      try_next = FALSE;
+      break;
+
+      /* Special spacing and line-terminating items. These recognize specific
+      lists of characters. The difference between VSPACE and ANYNL is that the
+      latter can match the two-character CRLF sequence, but that is not
+      relevant for finding the first character, so their code here is
+      identical. */
+
+      case OP_HSPACE:
+      SET_BIT(0x09);
+      SET_BIT(0x20);
+#ifdef SUPPORT_UTF
+      if (utf)
+        {
+#ifdef COMPILE_PCRE8
+        SET_BIT(0xC2);  /* For U+00A0 */
+        SET_BIT(0xE1);  /* For U+1680, U+180E */
+        SET_BIT(0xE2);  /* For U+2000 - U+200A, U+202F, U+205F */
+        SET_BIT(0xE3);  /* For U+3000 */
+#endif
+#ifdef COMPILE_PCRE16
+        SET_BIT(0xA0);
+        SET_BIT(0xFF);  /* For characters > 255 */
+#endif
+        }
+      else
+#endif /* SUPPORT_UTF */
+        {
+        SET_BIT(0xA0);
+#ifdef COMPILE_PCRE16
+        SET_BIT(0xFF);  /* For characters > 255 */
+#endif
+        }
+      try_next = FALSE;
+      break;
+
+      case OP_ANYNL:
+      case OP_VSPACE:
+      SET_BIT(0x0A);
+      SET_BIT(0x0B);
+      SET_BIT(0x0C);
+      SET_BIT(0x0D);
+#ifdef SUPPORT_UTF
+      if (utf)
+        {
+#ifdef COMPILE_PCRE8
+        SET_BIT(0xC2);  /* For U+0085 */
+        SET_BIT(0xE2);  /* For U+2028, U+2029 */
+#endif
+#ifdef COMPILE_PCRE16
+        SET_BIT(0x85);
+        SET_BIT(0xFF);  /* For characters > 255 */
+#endif
+        }
+      else
+#endif /* SUPPORT_UTF */
+        {
+        SET_BIT(0x85);
+#ifdef COMPILE_PCRE16
+        SET_BIT(0xFF);  /* For characters > 255 */
+#endif
+        }
+      try_next = FALSE;
+      break;
+
+      /* Single character types set the bits and stop. Note that if PCRE_UCP
+      is set, we do not see these op codes because \d etc are converted to
+      properties. Therefore, these apply in the case when only characters less
+      than 256 are recognized to match the types. */
+
+      case OP_NOT_DIGIT:
+      set_nottype_bits(start_bits, cbit_digit, table_limit, cd);
+      try_next = FALSE;
+      break;
+
+      case OP_DIGIT:
+      set_type_bits(start_bits, cbit_digit, table_limit, cd);
+      try_next = FALSE;
+      break;
+
+      /* The cbit_space table has vertical tab as whitespace; we have to
+      ensure it is set as not whitespace. */
+
+      case OP_NOT_WHITESPACE:
+      set_nottype_bits(start_bits, cbit_space, table_limit, cd);
+      start_bits[1] |= 0x08;
+      try_next = FALSE;
+      break;
+
+      /* The cbit_space table has vertical tab as whitespace; we have to
+      not set it from the table. */
+
+      case OP_WHITESPACE:
+      c = start_bits[1];    /* Save in case it was already set */
+      set_type_bits(start_bits, cbit_space, table_limit, cd);
+      start_bits[1] = (start_bits[1] & ~0x08) | c;
+      try_next = FALSE;
+      break;
+
+      case OP_NOT_WORDCHAR:
+      set_nottype_bits(start_bits, cbit_word, table_limit, cd);
+      try_next = FALSE;
+      break;
+
+      case OP_WORDCHAR:
+      set_type_bits(start_bits, cbit_word, table_limit, cd);
+      try_next = FALSE;
+      break;
+
+      /* One or more character type fudges the pointer and restarts, knowing
+      it will hit a single character type and stop there. */
+
+      case OP_TYPEPLUS:
+      case OP_TYPEMINPLUS:
+      case OP_TYPEPOSPLUS:
+      tcode++;
+      break;
+
+      case OP_TYPEEXACT:
+      tcode += 1 + IMM2_SIZE;
+      break;
+
+      /* Zero or more repeats of character types set the bits and then
+      try again. */
+
+      case OP_TYPEUPTO:
+      case OP_TYPEMINUPTO:
+      case OP_TYPEPOSUPTO:
+      tcode += IMM2_SIZE;  /* Fall through */
+
+      case OP_TYPESTAR:
+      case OP_TYPEMINSTAR:
+      case OP_TYPEPOSSTAR:
+      case OP_TYPEQUERY:
+      case OP_TYPEMINQUERY:
+      case OP_TYPEPOSQUERY:
+      switch(tcode[1])
+        {
+        default:
+        case OP_ANY:
+        case OP_ALLANY:
+        return SSB_FAIL;
+
+        case OP_HSPACE:
+        SET_BIT(0x09);
+        SET_BIT(0x20);
+#ifdef SUPPORT_UTF
+        if (utf)
+          {
+#ifdef COMPILE_PCRE8
+          SET_BIT(0xC2);  /* For U+00A0 */
+          SET_BIT(0xE1);  /* For U+1680, U+180E */
+          SET_BIT(0xE2);  /* For U+2000 - U+200A, U+202F, U+205F */
+          SET_BIT(0xE3);  /* For U+3000 */
+#endif
+#ifdef COMPILE_PCRE16
+          SET_BIT(0xA0);
+          SET_BIT(0xFF);  /* For characters > 255 */
+#endif
+          }
+        else
+#endif /* SUPPORT_UTF */
+          SET_BIT(0xA0);
+        break;
+
+        case OP_ANYNL:
+        case OP_VSPACE:
+        SET_BIT(0x0A);
+        SET_BIT(0x0B);
+        SET_BIT(0x0C);
+        SET_BIT(0x0D);
+#ifdef SUPPORT_UTF
+        if (utf)
+          {
+#ifdef COMPILE_PCRE8
+          SET_BIT(0xC2);  /* For U+0085 */
+          SET_BIT(0xE2);  /* For U+2028, U+2029 */
+#endif
+#ifdef COMPILE_PCRE16
+          SET_BIT(0x85);
+          SET_BIT(0xFF);  /* For characters > 255 */
+#endif
+          }
+        else
+#endif /* SUPPORT_UTF */
+          SET_BIT(0x85);
+        break;
+
+        case OP_NOT_DIGIT:
+        set_nottype_bits(start_bits, cbit_digit, table_limit, cd);
+        break;
+
+        case OP_DIGIT:
+        set_type_bits(start_bits, cbit_digit, table_limit, cd);
+        break;
+
+        /* The cbit_space table has vertical tab as whitespace; we have to
+        ensure it gets set as not whitespace. */
+
+        case OP_NOT_WHITESPACE:
+        set_nottype_bits(start_bits, cbit_space, table_limit, cd);
+        start_bits[1] |= 0x08;
+        break;
+
+        /* The cbit_space table has vertical tab as whitespace; we have to
+        avoid setting it. */
+
+        case OP_WHITESPACE:
+        c = start_bits[1];    /* Save in case it was already set */
+        set_type_bits(start_bits, cbit_space, table_limit, cd);
+        start_bits[1] = (start_bits[1] & ~0x08) | c;
+        break;
+
+        case OP_NOT_WORDCHAR:
+        set_nottype_bits(start_bits, cbit_word, table_limit, cd);
+        break;
+
+        case OP_WORDCHAR:
+        set_type_bits(start_bits, cbit_word, table_limit, cd);
+        break;
+        }
+
+      tcode += 2;
+      break;
+
+      /* Character class where all the information is in a bit map: set the
+      bits and either carry on or not, according to the repeat count. If it was
+      a negative class, and we are operating with UTF-8 characters, any byte
+      with a value >= 0xc4 is a potentially valid starter because it starts a
+      character with a value > 255. */
+
+      case OP_NCLASS:
+#if defined SUPPORT_UTF && defined COMPILE_PCRE8
+      if (utf)
+        {
+        start_bits[24] |= 0xf0;              /* Bits for 0xc4 - 0xc8 */
+        memset(start_bits+25, 0xff, 7);      /* Bits for 0xc9 - 0xff */
+        }
+#endif
+#ifdef COMPILE_PCRE16
+      SET_BIT(0xFF);                         /* For characters > 255 */
+#endif
+      /* Fall through */
+
+      case OP_CLASS:
+        {
+        pcre_uint8 *map;
+        tcode++;
+        map = (pcre_uint8 *)tcode;
+
+        /* In UTF-8 mode, the bits in a bit map correspond to character
+        values, not to byte values. However, the bit map we are constructing is
+        for byte values. So we have to do a conversion for characters whose
+        value is > 127. In fact, there are only two possible starting bytes for
+        characters in the range 128 - 255. */
+
+#if defined SUPPORT_UTF && defined COMPILE_PCRE8
+        if (utf)
+          {
+          for (c = 0; c < 16; c++) start_bits[c] |= map[c];
+          for (c = 128; c < 256; c++)
+            {
+            if ((map[c/8] && (1 << (c&7))) != 0)
+              {
+              int d = (c >> 6) | 0xc0;            /* Set bit for this starter */
+              start_bits[d/8] |= (1 << (d&7));    /* and then skip on to the */
+              c = (c & 0xc0) + 0x40 - 1;          /* next relevant character. */
+              }
+            }
+          }
+        else
+#endif
+          {
+          /* In non-UTF-8 mode, the two bit maps are completely compatible. */
+          for (c = 0; c < 32; c++) start_bits[c] |= map[c];
+          }
+
+        /* Advance past the bit map, and act on what follows. For a zero
+        minimum repeat, continue; otherwise stop processing. */
+
+        tcode += 32 / sizeof(pcre_uchar);
+        switch (*tcode)
+          {
+          case OP_CRSTAR:
+          case OP_CRMINSTAR:
+          case OP_CRQUERY:
+          case OP_CRMINQUERY:
+          tcode++;
+          break;
+
+          case OP_CRRANGE:
+          case OP_CRMINRANGE:
+          if (GET2(tcode, 1) == 0) tcode += 1 + 2 * IMM2_SIZE;
+            else try_next = FALSE;
+          break;
+
+          default:
+          try_next = FALSE;
+          break;
+          }
+        }
+      break; /* End of bitmap class handling */
+
+      }      /* End of switch */
+    }        /* End of try_next loop */
+
+  code += GET(code, 1);   /* Advance to next branch */
+  }
+while (*code == OP_ALT);
+return yield;
+}
+
+
+
+
+
+/*************************************************
+*          Study a compiled expression           *
+*************************************************/
+
+/* This function is handed a compiled expression that it must study to produce
+information that will speed up the matching. It returns a pcre[16]_extra block
+which then gets handed back to pcre_exec().
+
+Arguments:
+  re        points to the compiled expression
+  options   contains option bits
+  errorptr  points to where to place error messages;
+            set NULL unless error
+
+Returns:    pointer to a pcre[16]_extra block, with study_data filled in and
+              the appropriate flags set;
+            NULL on error or if no optimization possible
+*/
+
+#ifdef COMPILE_PCRE8
+PCRE_EXP_DEFN pcre_extra * PCRE_CALL_CONVENTION
+pcre_study(const pcre *external_re, int options, const char **errorptr)
+#else
+PCRE_EXP_DEFN pcre16_extra * PCRE_CALL_CONVENTION
+pcre16_study(const pcre16 *external_re, int options, const char **errorptr)
+#endif
+{
+int min;
+BOOL bits_set = FALSE;
+pcre_uint8 start_bits[32];
+PUBL(extra) *extra = NULL;
+pcre_study_data *study;
+const pcre_uint8 *tables;
+pcre_uchar *code;
+compile_data compile_block;
+const REAL_PCRE *re = (const REAL_PCRE *)external_re;
+
+*errorptr = NULL;
+
+if (re == NULL || re->magic_number != MAGIC_NUMBER)
+  {
+  *errorptr = "argument is not a compiled regular expression";
+  return NULL;
+  }
+
+if ((re->flags & PCRE_MODE) == 0)
+  {
+#ifdef COMPILE_PCRE8
+  *errorptr = "argument is compiled in 16 bit mode";
+#else
+  *errorptr = "argument is compiled in 8 bit mode";
+#endif
+  return NULL;
+  }
+
+if ((options & ~PUBLIC_STUDY_OPTIONS) != 0)
+  {
+  *errorptr = "unknown or incorrect option bit(s) set";
+  return NULL;
+  }
+
+code = (pcre_uchar *)re + re->name_table_offset +
+  (re->name_count * re->name_entry_size);
+
+/* For an anchored pattern, or an unanchored pattern that has a first char, or
+a multiline pattern that matches only at "line starts", there is no point in
+seeking a list of starting bytes. */
+
+if ((re->options & PCRE_ANCHORED) == 0 &&
+    (re->flags & (PCRE_FIRSTSET|PCRE_STARTLINE)) == 0)
+  {
+  int rc;
+
+  /* Set the character tables in the block that is passed around */
+
+  tables = re->tables;
+
+#ifdef COMPILE_PCRE8
+  if (tables == NULL)
+    (void)pcre_fullinfo(external_re, NULL, PCRE_INFO_DEFAULT_TABLES,
+    (void *)(&tables));
+#else
+  if (tables == NULL)
+    (void)pcre16_fullinfo(external_re, NULL, PCRE_INFO_DEFAULT_TABLES,
+    (void *)(&tables));
+#endif
+
+  compile_block.lcc = tables + lcc_offset;
+  compile_block.fcc = tables + fcc_offset;
+  compile_block.cbits = tables + cbits_offset;
+  compile_block.ctypes = tables + ctypes_offset;
+
+  /* See if we can find a fixed set of initial characters for the pattern. */
+
+  memset(start_bits, 0, 32 * sizeof(pcre_uint8));
+  rc = set_start_bits(code, start_bits, (re->options & PCRE_UTF8) != 0,
+    &compile_block);
+  bits_set = rc == SSB_DONE;
+  if (rc == SSB_UNKNOWN)
+    {
+    *errorptr = "internal error: opcode not recognized";
+    return NULL;
+    }
+  }
+
+/* Find the minimum length of subject string. */
+
+switch(min = find_minlength(code, code, re->options, 0))
+  {
+  case -2: *errorptr = "internal error: missing capturing bracket"; return NULL;
+  case -3: *errorptr = "internal error: opcode not recognized"; return NULL;
+  default: break;
+  }
+
+/* If a set of starting bytes has been identified, or if the minimum length is
+greater than zero, or if JIT optimization has been requested, get a
+pcre[16]_extra block and a pcre_study_data block. The study data is put in the
+latter, which is pointed to by the former, which may also get additional data
+set later by the calling program. At the moment, the size of pcre_study_data
+is fixed. We nevertheless save it in a field for returning via the
+pcre_fullinfo() function so that if it becomes variable in the future,
+we don't have to change that code. */
+
+if (bits_set || min > 0
+#ifdef SUPPORT_JIT
+    || (options & (PCRE_STUDY_JIT_COMPILE | PCRE_STUDY_JIT_PARTIAL_SOFT_COMPILE
+                 | PCRE_STUDY_JIT_PARTIAL_HARD_COMPILE)) != 0
+#endif
+  )
+  {
+  extra = (PUBL(extra) *)(PUBL(malloc))
+    (sizeof(PUBL(extra)) + sizeof(pcre_study_data));
+  if (extra == NULL)
+    {
+    *errorptr = "failed to get memory";
+    return NULL;
+    }
+
+  study = (pcre_study_data *)((char *)extra + sizeof(PUBL(extra)));
+  extra->flags = PCRE_EXTRA_STUDY_DATA;
+  extra->study_data = study;
+
+  study->size = sizeof(pcre_study_data);
+  study->flags = 0;
+
+  /* Set the start bits always, to avoid unset memory errors if the
+  study data is written to a file, but set the flag only if any of the bits
+  are set, to save time looking when none are. */
+
+  if (bits_set)
+    {
+    study->flags |= PCRE_STUDY_MAPPED;
+    memcpy(study->start_bits, start_bits, sizeof(start_bits));
+    }
+  else memset(study->start_bits, 0, 32 * sizeof(pcre_uint8));
+
+#ifdef PCRE_DEBUG
+  if (bits_set)
+    {
+    pcre_uint8 *ptr = start_bits;
+    int i;
+
+    printf("Start bits:\n");
+    for (i = 0; i < 32; i++)
+      printf("%3d: %02x%s", i * 8, *ptr++, ((i + 1) & 0x7) != 0? " " : "\n");
+    }
+#endif
+
+  /* Always set the minlength value in the block, because the JIT compiler
+  makes use of it. However, don't set the bit unless the length is greater than
+  zero - the interpretive pcre_exec() and pcre_dfa_exec() needn't waste time
+  checking the zero case. */
+
+  if (min > 0)
+    {
+    study->flags |= PCRE_STUDY_MINLEN;
+    study->minlength = min;
+    }
+  else study->minlength = 0;
+
+  /* If JIT support was compiled and requested, attempt the JIT compilation.
+  If no starting bytes were found, and the minimum length is zero, and JIT
+  compilation fails, abandon the extra block and return NULL. */
+
+#ifdef SUPPORT_JIT
+  extra->executable_jit = NULL;
+  if ((options & PCRE_STUDY_JIT_COMPILE) != 0)
+    PRIV(jit_compile)(re, extra, JIT_COMPILE);
+  if ((options & PCRE_STUDY_JIT_PARTIAL_SOFT_COMPILE) != 0)
+    PRIV(jit_compile)(re, extra, JIT_PARTIAL_SOFT_COMPILE);
+  if ((options & PCRE_STUDY_JIT_PARTIAL_HARD_COMPILE) != 0)
+    PRIV(jit_compile)(re, extra, JIT_PARTIAL_HARD_COMPILE);
+
+  if (study->flags == 0 && (extra->flags & PCRE_EXTRA_EXECUTABLE_JIT) == 0)
+    {
+#ifdef COMPILE_PCRE8
+    pcre_free_study(extra);
+#endif
+#ifdef COMPILE_PCRE16
+    pcre16_free_study(extra);
+#endif
+    extra = NULL;
+    }
+#endif
+  }
+
+return extra;
+}
+
+
+/*************************************************
+*          Free the study data                   *
+*************************************************/
+
+/* This function frees the memory that was obtained by pcre_study().
+
+Argument:   a pointer to the pcre[16]_extra block
+Returns:    nothing
+*/
+
+#ifdef COMPILE_PCRE8
+PCRE_EXP_DEFN void
+pcre_free_study(pcre_extra *extra)
+#else
+PCRE_EXP_DEFN void
+pcre16_free_study(pcre16_extra *extra)
+#endif
+{
+if (extra == NULL)
+  return;
+#ifdef SUPPORT_JIT
+if ((extra->flags & PCRE_EXTRA_EXECUTABLE_JIT) != 0 &&
+     extra->executable_jit != NULL)
+  PRIV(jit_free)(extra->executable_jit);
+#endif
+PUBL(free)(extra);
+}
+
+/* End of pcre_study.c */
diff --git a/ext/pcre/pcrelib/pcre_tables.c b/ext/pcre/pcrelib/pcre_tables.c
new file mode 100644
index 0000000..2f605f5
--- /dev/null
+++ b/ext/pcre/pcrelib/pcre_tables.c
@@ -0,0 +1,587 @@
+/*************************************************
+*      Perl-Compatible Regular Expressions       *
+*************************************************/
+
+/* PCRE is a library of functions to support regular expressions whose syntax
+and semantics are as close as possible to those of the Perl 5 language.
+
+                       Written by Philip Hazel
+           Copyright (c) 1997-2012 University of Cambridge
+
+-----------------------------------------------------------------------------
+Redistribution and use in source and binary forms, with or without
+modification, are permitted provided that the following conditions are met:
+
+    * Redistributions of source code must retain the above copyright notice,
+      this list of conditions and the following disclaimer.
+
+    * Redistributions in binary form must reproduce the above copyright
+      notice, this list of conditions and the following disclaimer in the
+      documentation and/or other materials provided with the distribution.
+
+    * Neither the name of the University of Cambridge nor the names of its
+      contributors may be used to endorse or promote products derived from
+      this software without specific prior written permission.
+
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+POSSIBILITY OF SUCH DAMAGE.
+-----------------------------------------------------------------------------
+*/
+
+#ifndef PCRE_INCLUDED
+
+/* This module contains some fixed tables that are used by more than one of the
+PCRE code modules. The tables are also #included by the pcretest program, which
+uses macros to change their names from _pcre_xxx to xxxx, thereby avoiding name
+clashes with the library. */
+
+
+#include "config.h"
+
+#include "pcre_internal.h"
+
+#endif /* PCRE_INCLUDED */
+
+/* Table of sizes for the fixed-length opcodes. It's defined in a macro so that
+the definition is next to the definition of the opcodes in pcre_internal.h. */
+
+const pcre_uint8 PRIV(OP_lengths)[] = { OP_LENGTHS };
+
+
+
+/*************************************************
+*           Tables for UTF-8 support             *
+*************************************************/
+
+/* These are the breakpoints for different numbers of bytes in a UTF-8
+character. */
+
+#if (defined SUPPORT_UTF && defined COMPILE_PCRE8) \
+  || (defined PCRE_INCLUDED && defined SUPPORT_PCRE16)
+
+/* These tables are also required by pcretest in 16 bit mode. */
+
+const int PRIV(utf8_table1)[] =
+  { 0x7f, 0x7ff, 0xffff, 0x1fffff, 0x3ffffff, 0x7fffffff};
+
+const int PRIV(utf8_table1_size) = sizeof(PRIV(utf8_table1)) / sizeof(int);
+
+/* These are the indicator bits and the mask for the data bits to set in the
+first byte of a character, indexed by the number of additional bytes. */
+
+const int PRIV(utf8_table2)[] = { 0,    0xc0, 0xe0, 0xf0, 0xf8, 0xfc};
+const int PRIV(utf8_table3)[] = { 0xff, 0x1f, 0x0f, 0x07, 0x03, 0x01};
+
+/* Table of the number of extra bytes, indexed by the first byte masked with
+0x3f. The highest number for a valid UTF-8 first byte is in fact 0x3d. */
+
+const pcre_uint8 PRIV(utf8_table4)[] = {
+  1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
+  1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
+  2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,
+  3,3,3,3,3,3,3,3,4,4,4,4,5,5,5,5 };
+
+#endif /* (SUPPORT_UTF && COMPILE_PCRE8) || (PCRE_INCLUDED && SUPPORT_PCRE16)*/
+
+#ifdef SUPPORT_UTF
+
+/* Table to translate from particular type value to the general value. */
+
+const int PRIV(ucp_gentype)[] = {
+  ucp_C, ucp_C, ucp_C, ucp_C, ucp_C,  /* Cc, Cf, Cn, Co, Cs */
+  ucp_L, ucp_L, ucp_L, ucp_L, ucp_L,  /* Ll, Lu, Lm, Lo, Lt */
+  ucp_M, ucp_M, ucp_M,                /* Mc, Me, Mn */
+  ucp_N, ucp_N, ucp_N,                /* Nd, Nl, No */
+  ucp_P, ucp_P, ucp_P, ucp_P, ucp_P,  /* Pc, Pd, Pe, Pf, Pi */
+  ucp_P, ucp_P,                       /* Ps, Po */
+  ucp_S, ucp_S, ucp_S, ucp_S,         /* Sc, Sk, Sm, So */
+  ucp_Z, ucp_Z, ucp_Z                 /* Zl, Zp, Zs */
+};
+
+#ifdef SUPPORT_JIT
+/* This table reverses PRIV(ucp_gentype). We can save the cost
+of a memory load. */
+
+const int PRIV(ucp_typerange)[] = {
+  ucp_Cc, ucp_Cs,
+  ucp_Ll, ucp_Lu,
+  ucp_Mc, ucp_Mn,
+  ucp_Nd, ucp_No,
+  ucp_Pc, ucp_Ps,
+  ucp_Sc, ucp_So,
+  ucp_Zl, ucp_Zs,
+};
+#endif /* SUPPORT_JIT */
+
+/* The pcre_utt[] table below translates Unicode property names into type and
+code values. It is searched by binary chop, so must be in collating sequence of
+name. Originally, the table contained pointers to the name strings in the first
+field of each entry. However, that leads to a large number of relocations when
+a shared library is dynamically loaded. A significant reduction is made by
+putting all the names into a single, large string and then using offsets in the
+table itself. Maintenance is more error-prone, but frequent changes to this
+data are unlikely.
+
+July 2008: There is now a script called maint/GenerateUtt.py that can be used
+to generate this data automatically instead of maintaining it by hand.
+
+The script was updated in March 2009 to generate a new EBCDIC-compliant
+version. Like all other character and string literals that are compared against
+the regular expression pattern, we must use STR_ macros instead of literal
+strings to make sure that UTF-8 support works on EBCDIC platforms. */
+
+#define STRING_Any0 STR_A STR_n STR_y "\0"
+#define STRING_Arabic0 STR_A STR_r STR_a STR_b STR_i STR_c "\0"
+#define STRING_Armenian0 STR_A STR_r STR_m STR_e STR_n STR_i STR_a STR_n "\0"
+#define STRING_Avestan0 STR_A STR_v STR_e STR_s STR_t STR_a STR_n "\0"
+#define STRING_Balinese0 STR_B STR_a STR_l STR_i STR_n STR_e STR_s STR_e "\0"
+#define STRING_Bamum0 STR_B STR_a STR_m STR_u STR_m "\0"
+#define STRING_Batak0 STR_B STR_a STR_t STR_a STR_k "\0"
+#define STRING_Bengali0 STR_B STR_e STR_n STR_g STR_a STR_l STR_i "\0"
+#define STRING_Bopomofo0 STR_B STR_o STR_p STR_o STR_m STR_o STR_f STR_o "\0"
+#define STRING_Brahmi0 STR_B STR_r STR_a STR_h STR_m STR_i "\0"
+#define STRING_Braille0 STR_B STR_r STR_a STR_i STR_l STR_l STR_e "\0"
+#define STRING_Buginese0 STR_B STR_u STR_g STR_i STR_n STR_e STR_s STR_e "\0"
+#define STRING_Buhid0 STR_B STR_u STR_h STR_i STR_d "\0"
+#define STRING_C0 STR_C "\0"
+#define STRING_Canadian_Aboriginal0 STR_C STR_a STR_n STR_a STR_d STR_i STR_a STR_n STR_UNDERSCORE STR_A STR_b STR_o STR_r STR_i STR_g STR_i STR_n STR_a STR_l "\0"
+#define STRING_Carian0 STR_C STR_a STR_r STR_i STR_a STR_n "\0"
+#define STRING_Cc0 STR_C STR_c "\0"
+#define STRING_Cf0 STR_C STR_f "\0"
+#define STRING_Chakma0 STR_C STR_h STR_a STR_k STR_m STR_a "\0"
+#define STRING_Cham0 STR_C STR_h STR_a STR_m "\0"
+#define STRING_Cherokee0 STR_C STR_h STR_e STR_r STR_o STR_k STR_e STR_e "\0"
+#define STRING_Cn0 STR_C STR_n "\0"
+#define STRING_Co0 STR_C STR_o "\0"
+#define STRING_Common0 STR_C STR_o STR_m STR_m STR_o STR_n "\0"
+#define STRING_Coptic0 STR_C STR_o STR_p STR_t STR_i STR_c "\0"
+#define STRING_Cs0 STR_C STR_s "\0"
+#define STRING_Cuneiform0 STR_C STR_u STR_n STR_e STR_i STR_f STR_o STR_r STR_m "\0"
+#define STRING_Cypriot0 STR_C STR_y STR_p STR_r STR_i STR_o STR_t "\0"
+#define STRING_Cyrillic0 STR_C STR_y STR_r STR_i STR_l STR_l STR_i STR_c "\0"
+#define STRING_Deseret0 STR_D STR_e STR_s STR_e STR_r STR_e STR_t "\0"
+#define STRING_Devanagari0 STR_D STR_e STR_v STR_a STR_n STR_a STR_g STR_a STR_r STR_i "\0"
+#define STRING_Egyptian_Hieroglyphs0 STR_E STR_g STR_y STR_p STR_t STR_i STR_a STR_n STR_UNDERSCORE STR_H STR_i STR_e STR_r STR_o STR_g STR_l STR_y STR_p STR_h STR_s "\0"
+#define STRING_Ethiopic0 STR_E STR_t STR_h STR_i STR_o STR_p STR_i STR_c "\0"
+#define STRING_Georgian0 STR_G STR_e STR_o STR_r STR_g STR_i STR_a STR_n "\0"
+#define STRING_Glagolitic0 STR_G STR_l STR_a STR_g STR_o STR_l STR_i STR_t STR_i STR_c "\0"
+#define STRING_Gothic0 STR_G STR_o STR_t STR_h STR_i STR_c "\0"
+#define STRING_Greek0 STR_G STR_r STR_e STR_e STR_k "\0"
+#define STRING_Gujarati0 STR_G STR_u STR_j STR_a STR_r STR_a STR_t STR_i "\0"
+#define STRING_Gurmukhi0 STR_G STR_u STR_r STR_m STR_u STR_k STR_h STR_i "\0"
+#define STRING_Han0 STR_H STR_a STR_n "\0"
+#define STRING_Hangul0 STR_H STR_a STR_n STR_g STR_u STR_l "\0"
+#define STRING_Hanunoo0 STR_H STR_a STR_n STR_u STR_n STR_o STR_o "\0"
+#define STRING_Hebrew0 STR_H STR_e STR_b STR_r STR_e STR_w "\0"
+#define STRING_Hiragana0 STR_H STR_i STR_r STR_a STR_g STR_a STR_n STR_a "\0"
+#define STRING_Imperial_Aramaic0 STR_I STR_m STR_p STR_e STR_r STR_i STR_a STR_l STR_UNDERSCORE STR_A STR_r STR_a STR_m STR_a STR_i STR_c "\0"
+#define STRING_Inherited0 STR_I STR_n STR_h STR_e STR_r STR_i STR_t STR_e STR_d "\0"
+#define STRING_Inscriptional_Pahlavi0 STR_I STR_n STR_s STR_c STR_r STR_i STR_p STR_t STR_i STR_o STR_n STR_a STR_l STR_UNDERSCORE STR_P STR_a STR_h STR_l STR_a STR_v STR_i "\0"
+#define STRING_Inscriptional_Parthian0 STR_I STR_n STR_s STR_c STR_r STR_i STR_p STR_t STR_i STR_o STR_n STR_a STR_l STR_UNDERSCORE STR_P STR_a STR_r STR_t STR_h STR_i STR_a STR_n "\0"
+#define STRING_Javanese0 STR_J STR_a STR_v STR_a STR_n STR_e STR_s STR_e "\0"
+#define STRING_Kaithi0 STR_K STR_a STR_i STR_t STR_h STR_i "\0"
+#define STRING_Kannada0 STR_K STR_a STR_n STR_n STR_a STR_d STR_a "\0"
+#define STRING_Katakana0 STR_K STR_a STR_t STR_a STR_k STR_a STR_n STR_a "\0"
+#define STRING_Kayah_Li0 STR_K STR_a STR_y STR_a STR_h STR_UNDERSCORE STR_L STR_i "\0"
+#define STRING_Kharoshthi0 STR_K STR_h STR_a STR_r STR_o STR_s STR_h STR_t STR_h STR_i "\0"
+#define STRING_Khmer0 STR_K STR_h STR_m STR_e STR_r "\0"
+#define STRING_L0 STR_L "\0"
+#define STRING_L_AMPERSAND0 STR_L STR_AMPERSAND "\0"
+#define STRING_Lao0 STR_L STR_a STR_o "\0"
+#define STRING_Latin0 STR_L STR_a STR_t STR_i STR_n "\0"
+#define STRING_Lepcha0 STR_L STR_e STR_p STR_c STR_h STR_a "\0"
+#define STRING_Limbu0 STR_L STR_i STR_m STR_b STR_u "\0"
+#define STRING_Linear_B0 STR_L STR_i STR_n STR_e STR_a STR_r STR_UNDERSCORE STR_B "\0"
+#define STRING_Lisu0 STR_L STR_i STR_s STR_u "\0"
+#define STRING_Ll0 STR_L STR_l "\0"
+#define STRING_Lm0 STR_L STR_m "\0"
+#define STRING_Lo0 STR_L STR_o "\0"
+#define STRING_Lt0 STR_L STR_t "\0"
+#define STRING_Lu0 STR_L STR_u "\0"
+#define STRING_Lycian0 STR_L STR_y STR_c STR_i STR_a STR_n "\0"
+#define STRING_Lydian0 STR_L STR_y STR_d STR_i STR_a STR_n "\0"
+#define STRING_M0 STR_M "\0"
+#define STRING_Malayalam0 STR_M STR_a STR_l STR_a STR_y STR_a STR_l STR_a STR_m "\0"
+#define STRING_Mandaic0 STR_M STR_a STR_n STR_d STR_a STR_i STR_c "\0"
+#define STRING_Mc0 STR_M STR_c "\0"
+#define STRING_Me0 STR_M STR_e "\0"
+#define STRING_Meetei_Mayek0 STR_M STR_e STR_e STR_t STR_e STR_i STR_UNDERSCORE STR_M STR_a STR_y STR_e STR_k "\0"
+#define STRING_Meroitic_Cursive0 STR_M STR_e STR_r STR_o STR_i STR_t STR_i STR_c STR_UNDERSCORE STR_C STR_u STR_r STR_s STR_i STR_v STR_e "\0"
+#define STRING_Meroitic_Hieroglyphs0 STR_M STR_e STR_r STR_o STR_i STR_t STR_i STR_c STR_UNDERSCORE STR_H STR_i STR_e STR_r STR_o STR_g STR_l STR_y STR_p STR_h STR_s "\0"
+#define STRING_Miao0 STR_M STR_i STR_a STR_o "\0"
+#define STRING_Mn0 STR_M STR_n "\0"
+#define STRING_Mongolian0 STR_M STR_o STR_n STR_g STR_o STR_l STR_i STR_a STR_n "\0"
+#define STRING_Myanmar0 STR_M STR_y STR_a STR_n STR_m STR_a STR_r "\0"
+#define STRING_N0 STR_N "\0"
+#define STRING_Nd0 STR_N STR_d "\0"
+#define STRING_New_Tai_Lue0 STR_N STR_e STR_w STR_UNDERSCORE STR_T STR_a STR_i STR_UNDERSCORE STR_L STR_u STR_e "\0"
+#define STRING_Nko0 STR_N STR_k STR_o "\0"
+#define STRING_Nl0 STR_N STR_l "\0"
+#define STRING_No0 STR_N STR_o "\0"
+#define STRING_Ogham0 STR_O STR_g STR_h STR_a STR_m "\0"
+#define STRING_Ol_Chiki0 STR_O STR_l STR_UNDERSCORE STR_C STR_h STR_i STR_k STR_i "\0"
+#define STRING_Old_Italic0 STR_O STR_l STR_d STR_UNDERSCORE STR_I STR_t STR_a STR_l STR_i STR_c "\0"
+#define STRING_Old_Persian0 STR_O STR_l STR_d STR_UNDERSCORE STR_P STR_e STR_r STR_s STR_i STR_a STR_n "\0"
+#define STRING_Old_South_Arabian0 STR_O STR_l STR_d STR_UNDERSCORE STR_S STR_o STR_u STR_t STR_h STR_UNDERSCORE STR_A STR_r STR_a STR_b STR_i STR_a STR_n "\0"
+#define STRING_Old_Turkic0 STR_O STR_l STR_d STR_UNDERSCORE STR_T STR_u STR_r STR_k STR_i STR_c "\0"
+#define STRING_Oriya0 STR_O STR_r STR_i STR_y STR_a "\0"
+#define STRING_Osmanya0 STR_O STR_s STR_m STR_a STR_n STR_y STR_a "\0"
+#define STRING_P0 STR_P "\0"
+#define STRING_Pc0 STR_P STR_c "\0"
+#define STRING_Pd0 STR_P STR_d "\0"
+#define STRING_Pe0 STR_P STR_e "\0"
+#define STRING_Pf0 STR_P STR_f "\0"
+#define STRING_Phags_Pa0 STR_P STR_h STR_a STR_g STR_s STR_UNDERSCORE STR_P STR_a "\0"
+#define STRING_Phoenician0 STR_P STR_h STR_o STR_e STR_n STR_i STR_c STR_i STR_a STR_n "\0"
+#define STRING_Pi0 STR_P STR_i "\0"
+#define STRING_Po0 STR_P STR_o "\0"
+#define STRING_Ps0 STR_P STR_s "\0"
+#define STRING_Rejang0 STR_R STR_e STR_j STR_a STR_n STR_g "\0"
+#define STRING_Runic0 STR_R STR_u STR_n STR_i STR_c "\0"
+#define STRING_S0 STR_S "\0"
+#define STRING_Samaritan0 STR_S STR_a STR_m STR_a STR_r STR_i STR_t STR_a STR_n "\0"
+#define STRING_Saurashtra0 STR_S STR_a STR_u STR_r STR_a STR_s STR_h STR_t STR_r STR_a "\0"
+#define STRING_Sc0 STR_S STR_c "\0"
+#define STRING_Sharada0 STR_S STR_h STR_a STR_r STR_a STR_d STR_a "\0"
+#define STRING_Shavian0 STR_S STR_h STR_a STR_v STR_i STR_a STR_n "\0"
+#define STRING_Sinhala0 STR_S STR_i STR_n STR_h STR_a STR_l STR_a "\0"
+#define STRING_Sk0 STR_S STR_k "\0"
+#define STRING_Sm0 STR_S STR_m "\0"
+#define STRING_So0 STR_S STR_o "\0"
+#define STRING_Sora_Sompeng0 STR_S STR_o STR_r STR_a STR_UNDERSCORE STR_S STR_o STR_m STR_p STR_e STR_n STR_g "\0"
+#define STRING_Sundanese0 STR_S STR_u STR_n STR_d STR_a STR_n STR_e STR_s STR_e "\0"
+#define STRING_Syloti_Nagri0 STR_S STR_y STR_l STR_o STR_t STR_i STR_UNDERSCORE STR_N STR_a STR_g STR_r STR_i "\0"
+#define STRING_Syriac0 STR_S STR_y STR_r STR_i STR_a STR_c "\0"
+#define STRING_Tagalog0 STR_T STR_a STR_g STR_a STR_l STR_o STR_g "\0"
+#define STRING_Tagbanwa0 STR_T STR_a STR_g STR_b STR_a STR_n STR_w STR_a "\0"
+#define STRING_Tai_Le0 STR_T STR_a STR_i STR_UNDERSCORE STR_L STR_e "\0"
+#define STRING_Tai_Tham0 STR_T STR_a STR_i STR_UNDERSCORE STR_T STR_h STR_a STR_m "\0"
+#define STRING_Tai_Viet0 STR_T STR_a STR_i STR_UNDERSCORE STR_V STR_i STR_e STR_t "\0"
+#define STRING_Takri0 STR_T STR_a STR_k STR_r STR_i "\0"
+#define STRING_Tamil0 STR_T STR_a STR_m STR_i STR_l "\0"
+#define STRING_Telugu0 STR_T STR_e STR_l STR_u STR_g STR_u "\0"
+#define STRING_Thaana0 STR_T STR_h STR_a STR_a STR_n STR_a "\0"
+#define STRING_Thai0 STR_T STR_h STR_a STR_i "\0"
+#define STRING_Tibetan0 STR_T STR_i STR_b STR_e STR_t STR_a STR_n "\0"
+#define STRING_Tifinagh0 STR_T STR_i STR_f STR_i STR_n STR_a STR_g STR_h "\0"
+#define STRING_Ugaritic0 STR_U STR_g STR_a STR_r STR_i STR_t STR_i STR_c "\0"
+#define STRING_Vai0 STR_V STR_a STR_i "\0"
+#define STRING_Xan0 STR_X STR_a STR_n "\0"
+#define STRING_Xps0 STR_X STR_p STR_s "\0"
+#define STRING_Xsp0 STR_X STR_s STR_p "\0"
+#define STRING_Xwd0 STR_X STR_w STR_d "\0"
+#define STRING_Yi0 STR_Y STR_i "\0"
+#define STRING_Z0 STR_Z "\0"
+#define STRING_Zl0 STR_Z STR_l "\0"
+#define STRING_Zp0 STR_Z STR_p "\0"
+#define STRING_Zs0 STR_Z STR_s "\0"
+
+const char PRIV(utt_names)[] =
+  STRING_Any0
+  STRING_Arabic0
+  STRING_Armenian0
+  STRING_Avestan0
+  STRING_Balinese0
+  STRING_Bamum0
+  STRING_Batak0
+  STRING_Bengali0
+  STRING_Bopomofo0
+  STRING_Brahmi0
+  STRING_Braille0
+  STRING_Buginese0
+  STRING_Buhid0
+  STRING_C0
+  STRING_Canadian_Aboriginal0
+  STRING_Carian0
+  STRING_Cc0
+  STRING_Cf0
+  STRING_Chakma0
+  STRING_Cham0
+  STRING_Cherokee0
+  STRING_Cn0
+  STRING_Co0
+  STRING_Common0
+  STRING_Coptic0
+  STRING_Cs0
+  STRING_Cuneiform0
+  STRING_Cypriot0
+  STRING_Cyrillic0
+  STRING_Deseret0
+  STRING_Devanagari0
+  STRING_Egyptian_Hieroglyphs0
+  STRING_Ethiopic0
+  STRING_Georgian0
+  STRING_Glagolitic0
+  STRING_Gothic0
+  STRING_Greek0
+  STRING_Gujarati0
+  STRING_Gurmukhi0
+  STRING_Han0
+  STRING_Hangul0
+  STRING_Hanunoo0
+  STRING_Hebrew0
+  STRING_Hiragana0
+  STRING_Imperial_Aramaic0
+  STRING_Inherited0
+  STRING_Inscriptional_Pahlavi0
+  STRING_Inscriptional_Parthian0
+  STRING_Javanese0
+  STRING_Kaithi0
+  STRING_Kannada0
+  STRING_Katakana0
+  STRING_Kayah_Li0
+  STRING_Kharoshthi0
+  STRING_Khmer0
+  STRING_L0
+  STRING_L_AMPERSAND0
+  STRING_Lao0
+  STRING_Latin0
+  STRING_Lepcha0
+  STRING_Limbu0
+  STRING_Linear_B0
+  STRING_Lisu0
+  STRING_Ll0
+  STRING_Lm0
+  STRING_Lo0
+  STRING_Lt0
+  STRING_Lu0
+  STRING_Lycian0
+  STRING_Lydian0
+  STRING_M0
+  STRING_Malayalam0
+  STRING_Mandaic0
+  STRING_Mc0
+  STRING_Me0
+  STRING_Meetei_Mayek0
+  STRING_Meroitic_Cursive0
+  STRING_Meroitic_Hieroglyphs0
+  STRING_Miao0
+  STRING_Mn0
+  STRING_Mongolian0
+  STRING_Myanmar0
+  STRING_N0
+  STRING_Nd0
+  STRING_New_Tai_Lue0
+  STRING_Nko0
+  STRING_Nl0
+  STRING_No0
+  STRING_Ogham0
+  STRING_Ol_Chiki0
+  STRING_Old_Italic0
+  STRING_Old_Persian0
+  STRING_Old_South_Arabian0
+  STRING_Old_Turkic0
+  STRING_Oriya0
+  STRING_Osmanya0
+  STRING_P0
+  STRING_Pc0
+  STRING_Pd0
+  STRING_Pe0
+  STRING_Pf0
+  STRING_Phags_Pa0
+  STRING_Phoenician0
+  STRING_Pi0
+  STRING_Po0
+  STRING_Ps0
+  STRING_Rejang0
+  STRING_Runic0
+  STRING_S0
+  STRING_Samaritan0
+  STRING_Saurashtra0
+  STRING_Sc0
+  STRING_Sharada0
+  STRING_Shavian0
+  STRING_Sinhala0
+  STRING_Sk0
+  STRING_Sm0
+  STRING_So0
+  STRING_Sora_Sompeng0
+  STRING_Sundanese0
+  STRING_Syloti_Nagri0
+  STRING_Syriac0
+  STRING_Tagalog0
+  STRING_Tagbanwa0
+  STRING_Tai_Le0
+  STRING_Tai_Tham0
+  STRING_Tai_Viet0
+  STRING_Takri0
+  STRING_Tamil0
+  STRING_Telugu0
+  STRING_Thaana0
+  STRING_Thai0
+  STRING_Tibetan0
+  STRING_Tifinagh0
+  STRING_Ugaritic0
+  STRING_Vai0
+  STRING_Xan0
+  STRING_Xps0
+  STRING_Xsp0
+  STRING_Xwd0
+  STRING_Yi0
+  STRING_Z0
+  STRING_Zl0
+  STRING_Zp0
+  STRING_Zs0;
+
+const ucp_type_table PRIV(utt)[] = {
+  {   0, PT_ANY, 0 },
+  {   4, PT_SC, ucp_Arabic },
+  {  11, PT_SC, ucp_Armenian },
+  {  20, PT_SC, ucp_Avestan },
+  {  28, PT_SC, ucp_Balinese },
+  {  37, PT_SC, ucp_Bamum },
+  {  43, PT_SC, ucp_Batak },
+  {  49, PT_SC, ucp_Bengali },
+  {  57, PT_SC, ucp_Bopomofo },
+  {  66, PT_SC, ucp_Brahmi },
+  {  73, PT_SC, ucp_Braille },
+  {  81, PT_SC, ucp_Buginese },
+  {  90, PT_SC, ucp_Buhid },
+  {  96, PT_GC, ucp_C },
+  {  98, PT_SC, ucp_Canadian_Aboriginal },
+  { 118, PT_SC, ucp_Carian },
+  { 125, PT_PC, ucp_Cc },
+  { 128, PT_PC, ucp_Cf },
+  { 131, PT_SC, ucp_Chakma },
+  { 138, PT_SC, ucp_Cham },
+  { 143, PT_SC, ucp_Cherokee },
+  { 152, PT_PC, ucp_Cn },
+  { 155, PT_PC, ucp_Co },
+  { 158, PT_SC, ucp_Common },
+  { 165, PT_SC, ucp_Coptic },
+  { 172, PT_PC, ucp_Cs },
+  { 175, PT_SC, ucp_Cuneiform },
+  { 185, PT_SC, ucp_Cypriot },
+  { 193, PT_SC, ucp_Cyrillic },
+  { 202, PT_SC, ucp_Deseret },
+  { 210, PT_SC, ucp_Devanagari },
+  { 221, PT_SC, ucp_Egyptian_Hieroglyphs },
+  { 242, PT_SC, ucp_Ethiopic },
+  { 251, PT_SC, ucp_Georgian },
+  { 260, PT_SC, ucp_Glagolitic },
+  { 271, PT_SC, ucp_Gothic },
+  { 278, PT_SC, ucp_Greek },
+  { 284, PT_SC, ucp_Gujarati },
+  { 293, PT_SC, ucp_Gurmukhi },
+  { 302, PT_SC, ucp_Han },
+  { 306, PT_SC, ucp_Hangul },
+  { 313, PT_SC, ucp_Hanunoo },
+  { 321, PT_SC, ucp_Hebrew },
+  { 328, PT_SC, ucp_Hiragana },
+  { 337, PT_SC, ucp_Imperial_Aramaic },
+  { 354, PT_SC, ucp_Inherited },
+  { 364, PT_SC, ucp_Inscriptional_Pahlavi },
+  { 386, PT_SC, ucp_Inscriptional_Parthian },
+  { 409, PT_SC, ucp_Javanese },
+  { 418, PT_SC, ucp_Kaithi },
+  { 425, PT_SC, ucp_Kannada },
+  { 433, PT_SC, ucp_Katakana },
+  { 442, PT_SC, ucp_Kayah_Li },
+  { 451, PT_SC, ucp_Kharoshthi },
+  { 462, PT_SC, ucp_Khmer },
+  { 468, PT_GC, ucp_L },
+  { 470, PT_LAMP, 0 },
+  { 473, PT_SC, ucp_Lao },
+  { 477, PT_SC, ucp_Latin },
+  { 483, PT_SC, ucp_Lepcha },
+  { 490, PT_SC, ucp_Limbu },
+  { 496, PT_SC, ucp_Linear_B },
+  { 505, PT_SC, ucp_Lisu },
+  { 510, PT_PC, ucp_Ll },
+  { 513, PT_PC, ucp_Lm },
+  { 516, PT_PC, ucp_Lo },
+  { 519, PT_PC, ucp_Lt },
+  { 522, PT_PC, ucp_Lu },
+  { 525, PT_SC, ucp_Lycian },
+  { 532, PT_SC, ucp_Lydian },
+  { 539, PT_GC, ucp_M },
+  { 541, PT_SC, ucp_Malayalam },
+  { 551, PT_SC, ucp_Mandaic },
+  { 559, PT_PC, ucp_Mc },
+  { 562, PT_PC, ucp_Me },
+  { 565, PT_SC, ucp_Meetei_Mayek },
+  { 578, PT_SC, ucp_Meroitic_Cursive },
+  { 595, PT_SC, ucp_Meroitic_Hieroglyphs },
+  { 616, PT_SC, ucp_Miao },
+  { 621, PT_PC, ucp_Mn },
+  { 624, PT_SC, ucp_Mongolian },
+  { 634, PT_SC, ucp_Myanmar },
+  { 642, PT_GC, ucp_N },
+  { 644, PT_PC, ucp_Nd },
+  { 647, PT_SC, ucp_New_Tai_Lue },
+  { 659, PT_SC, ucp_Nko },
+  { 663, PT_PC, ucp_Nl },
+  { 666, PT_PC, ucp_No },
+  { 669, PT_SC, ucp_Ogham },
+  { 675, PT_SC, ucp_Ol_Chiki },
+  { 684, PT_SC, ucp_Old_Italic },
+  { 695, PT_SC, ucp_Old_Persian },
+  { 707, PT_SC, ucp_Old_South_Arabian },
+  { 725, PT_SC, ucp_Old_Turkic },
+  { 736, PT_SC, ucp_Oriya },
+  { 742, PT_SC, ucp_Osmanya },
+  { 750, PT_GC, ucp_P },
+  { 752, PT_PC, ucp_Pc },
+  { 755, PT_PC, ucp_Pd },
+  { 758, PT_PC, ucp_Pe },
+  { 761, PT_PC, ucp_Pf },
+  { 764, PT_SC, ucp_Phags_Pa },
+  { 773, PT_SC, ucp_Phoenician },
+  { 784, PT_PC, ucp_Pi },
+  { 787, PT_PC, ucp_Po },
+  { 790, PT_PC, ucp_Ps },
+  { 793, PT_SC, ucp_Rejang },
+  { 800, PT_SC, ucp_Runic },
+  { 806, PT_GC, ucp_S },
+  { 808, PT_SC, ucp_Samaritan },
+  { 818, PT_SC, ucp_Saurashtra },
+  { 829, PT_PC, ucp_Sc },
+  { 832, PT_SC, ucp_Sharada },
+  { 840, PT_SC, ucp_Shavian },
+  { 848, PT_SC, ucp_Sinhala },
+  { 856, PT_PC, ucp_Sk },
+  { 859, PT_PC, ucp_Sm },
+  { 862, PT_PC, ucp_So },
+  { 865, PT_SC, ucp_Sora_Sompeng },
+  { 878, PT_SC, ucp_Sundanese },
+  { 888, PT_SC, ucp_Syloti_Nagri },
+  { 901, PT_SC, ucp_Syriac },
+  { 908, PT_SC, ucp_Tagalog },
+  { 916, PT_SC, ucp_Tagbanwa },
+  { 925, PT_SC, ucp_Tai_Le },
+  { 932, PT_SC, ucp_Tai_Tham },
+  { 941, PT_SC, ucp_Tai_Viet },
+  { 950, PT_SC, ucp_Takri },
+  { 956, PT_SC, ucp_Tamil },
+  { 962, PT_SC, ucp_Telugu },
+  { 969, PT_SC, ucp_Thaana },
+  { 976, PT_SC, ucp_Thai },
+  { 981, PT_SC, ucp_Tibetan },
+  { 989, PT_SC, ucp_Tifinagh },
+  { 998, PT_SC, ucp_Ugaritic },
+  { 1007, PT_SC, ucp_Vai },
+  { 1011, PT_ALNUM, 0 },
+  { 1015, PT_PXSPACE, 0 },
+  { 1019, PT_SPACE, 0 },
+  { 1023, PT_WORD, 0 },
+  { 1027, PT_SC, ucp_Yi },
+  { 1030, PT_GC, ucp_Z },
+  { 1032, PT_PC, ucp_Zl },
+  { 1035, PT_PC, ucp_Zp },
+  { 1038, PT_PC, ucp_Zs }
+};
+
+const int PRIV(utt_size) = sizeof(PRIV(utt)) / sizeof(ucp_type_table);
+
+#endif /* SUPPORT_UTF */
+
+/* End of pcre_tables.c */
diff --git a/ext/pcre/pcrelib/pcre_ucd.c b/ext/pcre/pcrelib/pcre_ucd.c
new file mode 100644
index 0000000..39b5918
--- /dev/null
+++ b/ext/pcre/pcrelib/pcre_ucd.c
@@ -0,0 +1,3096 @@
+#include "config.h"
+
+#include "pcre_internal.h"
+
+/* Unicode character database. */
+/* This file was autogenerated by the MultiStage2.py script. */
+/* Total size: 62904 bytes, block size: 128. */
+
+/* The tables herein are needed only when UCP support is built */
+/* into PCRE. This module should not be referenced otherwise, so */
+/* it should not matter whether it is compiled or not. However */
+/* a comment was received about space saving - maybe the guy linked */
+/* all the modules rather than using a library - so we include a */
+/* condition to cut out the tables when not needed. But don't leave */
+/* a totally empty module because some compilers barf at that. */
+/* Instead, just supply small dummy tables. */
+
+#ifndef SUPPORT_UCP
+const ucd_record PRIV(ucd_records)[] = {{0,0,0 }};
+const pcre_uint8 PRIV(ucd_stage1)[] = {0};
+const pcre_uint16 PRIV(ucd_stage2)[] = {0};
+#else
+
+/* When recompiling tables with a new Unicode version,
+please check types in the structure definition from pcre_internal.h:
+typedef struct {
+pcre_uint8 property_0;
+pcre_uint8 property_1;
+pcre_int32 property_2;
+} ucd_record; */
+
+
+const ucd_record PRIV(ucd_records)[] = { /* 4536 bytes, record size 8 */
+  {     9,      0,      0, }, /*   0 */
+  {     9,     29,      0, }, /*   1 */
+  {     9,     21,      0, }, /*   2 */
+  {     9,     23,      0, }, /*   3 */
+  {     9,     22,      0, }, /*   4 */
+  {     9,     18,      0, }, /*   5 */
+  {     9,     25,      0, }, /*   6 */
+  {     9,     17,      0, }, /*   7 */
+  {     9,     13,      0, }, /*   8 */
+  {    33,      9,     32, }, /*   9 */
+  {     9,     24,      0, }, /*  10 */
+  {     9,     16,      0, }, /*  11 */
+  {    33,      5,    -32, }, /*  12 */
+  {     9,     26,      0, }, /*  13 */
+  {    33,      7,      0, }, /*  14 */
+  {     9,     20,      0, }, /*  15 */
+  {     9,      1,      0, }, /*  16 */
+  {     9,     15,      0, }, /*  17 */
+  {     9,      5,    743, }, /*  18 */
+  {     9,     19,      0, }, /*  19 */
+  {    33,      5,      0, }, /*  20 */
+  {    33,      5,    121, }, /*  21 */
+  {    33,      9,      1, }, /*  22 */
+  {    33,      5,     -1, }, /*  23 */
+  {    33,      9,   -199, }, /*  24 */
+  {    33,      5,   -232, }, /*  25 */
+  {    33,      9,   -121, }, /*  26 */
+  {    33,      5,   -300, }, /*  27 */
+  {    33,      5,    195, }, /*  28 */
+  {    33,      9,    210, }, /*  29 */
+  {    33,      9,    206, }, /*  30 */
+  {    33,      9,    205, }, /*  31 */
+  {    33,      9,     79, }, /*  32 */
+  {    33,      9,    202, }, /*  33 */
+  {    33,      9,    203, }, /*  34 */
+  {    33,      9,    207, }, /*  35 */
+  {    33,      5,     97, }, /*  36 */
+  {    33,      9,    211, }, /*  37 */
+  {    33,      9,    209, }, /*  38 */
+  {    33,      5,    163, }, /*  39 */
+  {    33,      9,    213, }, /*  40 */
+  {    33,      5,    130, }, /*  41 */
+  {    33,      9,    214, }, /*  42 */
+  {    33,      9,    218, }, /*  43 */
+  {    33,      9,    217, }, /*  44 */
+  {    33,      9,    219, }, /*  45 */
+  {    33,      5,     56, }, /*  46 */
+  {    33,      9,      2, }, /*  47 */
+  {    33,      8,     -1, }, /*  48 */
+  {    33,      5,     -2, }, /*  49 */
+  {    33,      5,    -79, }, /*  50 */
+  {    33,      9,    -97, }, /*  51 */
+  {    33,      9,    -56, }, /*  52 */
+  {    33,      9,   -130, }, /*  53 */
+  {    33,      9,  10795, }, /*  54 */
+  {    33,      9,   -163, }, /*  55 */
+  {    33,      9,  10792, }, /*  56 */
+  {    33,      5,  10815, }, /*  57 */
+  {    33,      9,   -195, }, /*  58 */
+  {    33,      9,     69, }, /*  59 */
+  {    33,      9,     71, }, /*  60 */
+  {    33,      5,  10783, }, /*  61 */
+  {    33,      5,  10780, }, /*  62 */
+  {    33,      5,  10782, }, /*  63 */
+  {    33,      5,   -210, }, /*  64 */
+  {    33,      5,   -206, }, /*  65 */
+  {    33,      5,   -205, }, /*  66 */
+  {    33,      5,   -202, }, /*  67 */
+  {    33,      5,   -203, }, /*  68 */
+  {    33,      5,   -207, }, /*  69 */
+  {    33,      5,  42280, }, /*  70 */
+  {    33,      5,  42308, }, /*  71 */
+  {    33,      5,   -209, }, /*  72 */
+  {    33,      5,   -211, }, /*  73 */
+  {    33,      5,  10743, }, /*  74 */
+  {    33,      5,  10749, }, /*  75 */
+  {    33,      5,   -213, }, /*  76 */
+  {    33,      5,   -214, }, /*  77 */
+  {    33,      5,  10727, }, /*  78 */
+  {    33,      5,   -218, }, /*  79 */
+  {    33,      5,    -69, }, /*  80 */
+  {    33,      5,   -217, }, /*  81 */
+  {    33,      5,    -71, }, /*  82 */
+  {    33,      5,   -219, }, /*  83 */
+  {    33,      6,      0, }, /*  84 */
+  {     9,      6,      0, }, /*  85 */
+  {     3,     24,      0, }, /*  86 */
+  {    27,     12,      0, }, /*  87 */
+  {    27,     12,     84, }, /*  88 */
+  {    19,      9,      1, }, /*  89 */
+  {    19,      5,     -1, }, /*  90 */
+  {    19,     24,      0, }, /*  91 */
+  {     9,      2,      0, }, /*  92 */
+  {    19,      6,      0, }, /*  93 */
+  {    19,      5,    130, }, /*  94 */
+  {    19,      9,     38, }, /*  95 */
+  {    19,      9,     37, }, /*  96 */
+  {    19,      9,     64, }, /*  97 */
+  {    19,      9,     63, }, /*  98 */
+  {    19,      5,      0, }, /*  99 */
+  {    19,      9,     32, }, /* 100 */
+  {    19,      5,    -38, }, /* 101 */
+  {    19,      5,    -37, }, /* 102 */
+  {    19,      5,    -32, }, /* 103 */
+  {    19,      5,    -31, }, /* 104 */
+  {    19,      5,    -64, }, /* 105 */
+  {    19,      5,    -63, }, /* 106 */
+  {    19,      9,      8, }, /* 107 */
+  {    19,      5,    -62, }, /* 108 */
+  {    19,      5,    -57, }, /* 109 */
+  {    19,      9,      0, }, /* 110 */
+  {    19,      5,    -47, }, /* 111 */
+  {    19,      5,    -54, }, /* 112 */
+  {    19,      5,     -8, }, /* 113 */
+  {    10,      9,      1, }, /* 114 */
+  {    10,      5,     -1, }, /* 115 */
+  {    19,      5,    -86, }, /* 116 */
+  {    19,      5,    -80, }, /* 117 */
+  {    19,      5,      7, }, /* 118 */
+  {    19,      9,    -60, }, /* 119 */
+  {    19,      5,    -96, }, /* 120 */
+  {    19,     25,      0, }, /* 121 */
+  {    19,      9,     -7, }, /* 122 */
+  {    19,      9,   -130, }, /* 123 */
+  {    12,      9,     80, }, /* 124 */
+  {    12,      9,     32, }, /* 125 */
+  {    12,      5,    -32, }, /* 126 */
+  {    12,      5,    -80, }, /* 127 */
+  {    12,      9,      1, }, /* 128 */
+  {    12,      5,     -1, }, /* 129 */
+  {    12,     26,      0, }, /* 130 */
+  {    12,     12,      0, }, /* 131 */
+  {    12,     11,      0, }, /* 132 */
+  {    12,      9,     15, }, /* 133 */
+  {    12,      5,    -15, }, /* 134 */
+  {     1,      9,     48, }, /* 135 */
+  {     1,      6,      0, }, /* 136 */
+  {     1,     21,      0, }, /* 137 */
+  {     1,      5,    -48, }, /* 138 */
+  {     1,      5,      0, }, /* 139 */
+  {     1,     17,      0, }, /* 140 */
+  {     1,     23,      0, }, /* 141 */
+  {    25,     12,      0, }, /* 142 */
+  {    25,     17,      0, }, /* 143 */
+  {    25,     21,      0, }, /* 144 */
+  {    25,      7,      0, }, /* 145 */
+  {     0,      1,      0, }, /* 146 */
+  {     0,     25,      0, }, /* 147 */
+  {     0,     21,      0, }, /* 148 */
+  {     0,     23,      0, }, /* 149 */
+  {     0,     26,      0, }, /* 150 */
+  {     0,     12,      0, }, /* 151 */
+  {     0,      7,      0, }, /* 152 */
+  {     0,      6,      0, }, /* 153 */
+  {     0,     13,      0, }, /* 154 */
+  {    49,     21,      0, }, /* 155 */
+  {    49,      1,      0, }, /* 156 */
+  {    49,      7,      0, }, /* 157 */
+  {    49,     12,      0, }, /* 158 */
+  {    55,      7,      0, }, /* 159 */
+  {    55,     12,      0, }, /* 160 */
+  {    63,     13,      0, }, /* 161 */
+  {    63,      7,      0, }, /* 162 */
+  {    63,     12,      0, }, /* 163 */
+  {    63,      6,      0, }, /* 164 */
+  {    63,     26,      0, }, /* 165 */
+  {    63,     21,      0, }, /* 166 */
+  {    89,      7,      0, }, /* 167 */
+  {    89,     12,      0, }, /* 168 */
+  {    89,      6,      0, }, /* 169 */
+  {    89,     21,      0, }, /* 170 */
+  {    94,      7,      0, }, /* 171 */
+  {    94,     12,      0, }, /* 172 */
+  {    94,     21,      0, }, /* 173 */
+  {    14,     12,      0, }, /* 174 */
+  {    14,     10,      0, }, /* 175 */
+  {    14,      7,      0, }, /* 176 */
+  {    14,     13,      0, }, /* 177 */
+  {    14,     21,      0, }, /* 178 */
+  {    14,      6,      0, }, /* 179 */
+  {     2,     12,      0, }, /* 180 */
+  {     2,     10,      0, }, /* 181 */
+  {     2,      7,      0, }, /* 182 */
+  {     2,     13,      0, }, /* 183 */
+  {     2,     23,      0, }, /* 184 */
+  {     2,     15,      0, }, /* 185 */
+  {     2,     26,      0, }, /* 186 */
+  {    21,     12,      0, }, /* 187 */
+  {    21,     10,      0, }, /* 188 */
+  {    21,      7,      0, }, /* 189 */
+  {    21,     13,      0, }, /* 190 */
+  {    20,     12,      0, }, /* 191 */
+  {    20,     10,      0, }, /* 192 */
+  {    20,      7,      0, }, /* 193 */
+  {    20,     13,      0, }, /* 194 */
+  {    20,     21,      0, }, /* 195 */
+  {    20,     23,      0, }, /* 196 */
+  {    43,     12,      0, }, /* 197 */
+  {    43,     10,      0, }, /* 198 */
+  {    43,      7,      0, }, /* 199 */
+  {    43,     13,      0, }, /* 200 */
+  {    43,     26,      0, }, /* 201 */
+  {    43,     15,      0, }, /* 202 */
+  {    53,     12,      0, }, /* 203 */
+  {    53,      7,      0, }, /* 204 */
+  {    53,     10,      0, }, /* 205 */
+  {    53,     13,      0, }, /* 206 */
+  {    53,     15,      0, }, /* 207 */
+  {    53,     26,      0, }, /* 208 */
+  {    53,     23,      0, }, /* 209 */
+  {    54,     10,      0, }, /* 210 */
+  {    54,      7,      0, }, /* 211 */
+  {    54,     12,      0, }, /* 212 */
+  {    54,     13,      0, }, /* 213 */
+  {    54,     15,      0, }, /* 214 */
+  {    54,     26,      0, }, /* 215 */
+  {    28,     10,      0, }, /* 216 */
+  {    28,      7,      0, }, /* 217 */
+  {    28,     12,      0, }, /* 218 */
+  {    28,     13,      0, }, /* 219 */
+  {    36,     10,      0, }, /* 220 */
+  {    36,      7,      0, }, /* 221 */
+  {    36,     12,      0, }, /* 222 */
+  {    36,     13,      0, }, /* 223 */
+  {    36,     15,      0, }, /* 224 */
+  {    36,     26,      0, }, /* 225 */
+  {    47,     10,      0, }, /* 226 */
+  {    47,      7,      0, }, /* 227 */
+  {    47,     12,      0, }, /* 228 */
+  {    47,     21,      0, }, /* 229 */
+  {    56,      7,      0, }, /* 230 */
+  {    56,     12,      0, }, /* 231 */
+  {    56,      6,      0, }, /* 232 */
+  {    56,     21,      0, }, /* 233 */
+  {    56,     13,      0, }, /* 234 */
+  {    32,      7,      0, }, /* 235 */
+  {    32,     12,      0, }, /* 236 */
+  {    32,      6,      0, }, /* 237 */
+  {    32,     13,      0, }, /* 238 */
+  {    57,      7,      0, }, /* 239 */
+  {    57,     26,      0, }, /* 240 */
+  {    57,     21,      0, }, /* 241 */
+  {    57,     12,      0, }, /* 242 */
+  {    57,     13,      0, }, /* 243 */
+  {    57,     15,      0, }, /* 244 */
+  {    57,     22,      0, }, /* 245 */
+  {    57,     18,      0, }, /* 246 */
+  {    57,     10,      0, }, /* 247 */
+  {    38,      7,      0, }, /* 248 */
+  {    38,     10,      0, }, /* 249 */
+  {    38,     12,      0, }, /* 250 */
+  {    38,     13,      0, }, /* 251 */
+  {    38,     21,      0, }, /* 252 */
+  {    38,     26,      0, }, /* 253 */
+  {    16,      9,   7264, }, /* 254 */
+  {    16,      7,      0, }, /* 255 */
+  {    16,      6,      0, }, /* 256 */
+  {    23,      7,      0, }, /* 257 */
+  {    15,      7,      0, }, /* 258 */
+  {    15,     12,      0, }, /* 259 */
+  {    15,     21,      0, }, /* 260 */
+  {    15,     15,      0, }, /* 261 */
+  {    15,     26,      0, }, /* 262 */
+  {     8,      7,      0, }, /* 263 */
+  {     7,     17,      0, }, /* 264 */
+  {     7,      7,      0, }, /* 265 */
+  {     7,     21,      0, }, /* 266 */
+  {    40,     29,      0, }, /* 267 */
+  {    40,      7,      0, }, /* 268 */
+  {    40,     22,      0, }, /* 269 */
+  {    40,     18,      0, }, /* 270 */
+  {    45,      7,      0, }, /* 271 */
+  {    45,     14,      0, }, /* 272 */
+  {    50,      7,      0, }, /* 273 */
+  {    50,     12,      0, }, /* 274 */
+  {    24,      7,      0, }, /* 275 */
+  {    24,     12,      0, }, /* 276 */
+  {     6,      7,      0, }, /* 277 */
+  {     6,     12,      0, }, /* 278 */
+  {    51,      7,      0, }, /* 279 */
+  {    51,     12,      0, }, /* 280 */
+  {    31,      7,      0, }, /* 281 */
+  {    31,     12,      0, }, /* 282 */
+  {    31,     10,      0, }, /* 283 */
+  {    31,     21,      0, }, /* 284 */
+  {    31,      6,      0, }, /* 285 */
+  {    31,     23,      0, }, /* 286 */
+  {    31,     13,      0, }, /* 287 */
+  {    31,     15,      0, }, /* 288 */
+  {    37,     21,      0, }, /* 289 */
+  {    37,     17,      0, }, /* 290 */
+  {    37,     12,      0, }, /* 291 */
+  {    37,     29,      0, }, /* 292 */
+  {    37,     13,      0, }, /* 293 */
+  {    37,      7,      0, }, /* 294 */
+  {    37,      6,      0, }, /* 295 */
+  {    34,      7,      0, }, /* 296 */
+  {    34,     12,      0, }, /* 297 */
+  {    34,     10,      0, }, /* 298 */
+  {    34,     26,      0, }, /* 299 */
+  {    34,     21,      0, }, /* 300 */
+  {    34,     13,      0, }, /* 301 */
+  {    52,      7,      0, }, /* 302 */
+  {    39,      7,      0, }, /* 303 */
+  {    39,     10,      0, }, /* 304 */
+  {    39,     13,      0, }, /* 305 */
+  {    39,     15,      0, }, /* 306 */
+  {    39,     26,      0, }, /* 307 */
+  {    31,     26,      0, }, /* 308 */
+  {     5,      7,      0, }, /* 309 */
+  {     5,     12,      0, }, /* 310 */
+  {     5,     10,      0, }, /* 311 */
+  {     5,     21,      0, }, /* 312 */
+  {    90,      7,      0, }, /* 313 */
+  {    90,     10,      0, }, /* 314 */
+  {    90,     12,      0, }, /* 315 */
+  {    90,     13,      0, }, /* 316 */
+  {    90,     21,      0, }, /* 317 */
+  {    90,      6,      0, }, /* 318 */
+  {    61,     12,      0, }, /* 319 */
+  {    61,     10,      0, }, /* 320 */
+  {    61,      7,      0, }, /* 321 */
+  {    61,     13,      0, }, /* 322 */
+  {    61,     21,      0, }, /* 323 */
+  {    61,     26,      0, }, /* 324 */
+  {    75,     12,      0, }, /* 325 */
+  {    75,     10,      0, }, /* 326 */
+  {    75,      7,      0, }, /* 327 */
+  {    75,     13,      0, }, /* 328 */
+  {    92,      7,      0, }, /* 329 */
+  {    92,     12,      0, }, /* 330 */
+  {    92,     10,      0, }, /* 331 */
+  {    92,     21,      0, }, /* 332 */
+  {    69,      7,      0, }, /* 333 */
+  {    69,     10,      0, }, /* 334 */
+  {    69,     12,      0, }, /* 335 */
+  {    69,     21,      0, }, /* 336 */
+  {    69,     13,      0, }, /* 337 */
+  {    72,     13,      0, }, /* 338 */
+  {    72,      7,      0, }, /* 339 */
+  {    72,      6,      0, }, /* 340 */
+  {    72,     21,      0, }, /* 341 */
+  {    75,     21,      0, }, /* 342 */
+  {     9,     10,      0, }, /* 343 */
+  {     9,      7,      0, }, /* 344 */
+  {    12,      5,      0, }, /* 345 */
+  {    12,      6,      0, }, /* 346 */
+  {    33,      5,  35332, }, /* 347 */
+  {    33,      5,   3814, }, /* 348 */
+  {    33,      5,    -59, }, /* 349 */
+  {    33,      9,  -7615, }, /* 350 */
+  {    19,      5,      8, }, /* 351 */
+  {    19,      9,     -8, }, /* 352 */
+  {    19,      5,     74, }, /* 353 */
+  {    19,      5,     86, }, /* 354 */
+  {    19,      5,    100, }, /* 355 */
+  {    19,      5,    128, }, /* 356 */
+  {    19,      5,    112, }, /* 357 */
+  {    19,      5,    126, }, /* 358 */
+  {    19,      8,     -8, }, /* 359 */
+  {    19,      5,      9, }, /* 360 */
+  {    19,      9,    -74, }, /* 361 */
+  {    19,      8,     -9, }, /* 362 */
+  {    19,      5,  -7205, }, /* 363 */
+  {    19,      9,    -86, }, /* 364 */
+  {    19,      9,   -100, }, /* 365 */
+  {    19,      9,   -112, }, /* 366 */
+  {    19,      9,   -128, }, /* 367 */
+  {    19,      9,   -126, }, /* 368 */
+  {    27,      1,      0, }, /* 369 */
+  {     9,     27,      0, }, /* 370 */
+  {     9,     28,      0, }, /* 371 */
+  {    27,     11,      0, }, /* 372 */
+  {     9,      9,      0, }, /* 373 */
+  {     9,      5,      0, }, /* 374 */
+  {    19,      9,  -7517, }, /* 375 */
+  {    33,      9,  -8383, }, /* 376 */
+  {    33,      9,  -8262, }, /* 377 */
+  {    33,      9,     28, }, /* 378 */
+  {    33,      5,    -28, }, /* 379 */
+  {    33,     14,     16, }, /* 380 */
+  {    33,     14,    -16, }, /* 381 */
+  {    33,     14,      0, }, /* 382 */
+  {     9,     26,     26, }, /* 383 */
+  {     9,     26,    -26, }, /* 384 */
+  {     4,     26,      0, }, /* 385 */
+  {    17,      9,     48, }, /* 386 */
+  {    17,      5,    -48, }, /* 387 */
+  {    33,      9, -10743, }, /* 388 */
+  {    33,      9,  -3814, }, /* 389 */
+  {    33,      9, -10727, }, /* 390 */
+  {    33,      5, -10795, }, /* 391 */
+  {    33,      5, -10792, }, /* 392 */
+  {    33,      9, -10780, }, /* 393 */
+  {    33,      9, -10749, }, /* 394 */
+  {    33,      9, -10783, }, /* 395 */
+  {    33,      9, -10782, }, /* 396 */
+  {    33,      9, -10815, }, /* 397 */
+  {    10,      5,      0, }, /* 398 */
+  {    10,     26,      0, }, /* 399 */
+  {    10,     12,      0, }, /* 400 */
+  {    10,     21,      0, }, /* 401 */
+  {    10,     15,      0, }, /* 402 */
+  {    16,      5,  -7264, }, /* 403 */
+  {    58,      7,      0, }, /* 404 */
+  {    58,      6,      0, }, /* 405 */
+  {    58,     21,      0, }, /* 406 */
+  {    58,     12,      0, }, /* 407 */
+  {    22,     26,      0, }, /* 408 */
+  {    22,      6,      0, }, /* 409 */
+  {    22,     14,      0, }, /* 410 */
+  {    23,     10,      0, }, /* 411 */
+  {    26,      7,      0, }, /* 412 */
+  {    26,      6,      0, }, /* 413 */
+  {    29,      7,      0, }, /* 414 */
+  {    29,      6,      0, }, /* 415 */
+  {     3,      7,      0, }, /* 416 */
+  {    23,     26,      0, }, /* 417 */
+  {    29,     26,      0, }, /* 418 */
+  {    22,      7,      0, }, /* 419 */
+  {    60,      7,      0, }, /* 420 */
+  {    60,      6,      0, }, /* 421 */
+  {    60,     26,      0, }, /* 422 */
+  {    85,      7,      0, }, /* 423 */
+  {    85,      6,      0, }, /* 424 */
+  {    85,     21,      0, }, /* 425 */
+  {    76,      7,      0, }, /* 426 */
+  {    76,      6,      0, }, /* 427 */
+  {    76,     21,      0, }, /* 428 */
+  {    76,     13,      0, }, /* 429 */
+  {    12,      7,      0, }, /* 430 */
+  {    12,     21,      0, }, /* 431 */
+  {    78,      7,      0, }, /* 432 */
+  {    78,     14,      0, }, /* 433 */
+  {    78,     12,      0, }, /* 434 */
+  {    78,     21,      0, }, /* 435 */
+  {    33,      9, -35332, }, /* 436 */
+  {    33,      9, -42280, }, /* 437 */
+  {    33,      9, -42308, }, /* 438 */
+  {    48,      7,      0, }, /* 439 */
+  {    48,     12,      0, }, /* 440 */
+  {    48,     10,      0, }, /* 441 */
+  {    48,     26,      0, }, /* 442 */
+  {    64,      7,      0, }, /* 443 */
+  {    64,     21,      0, }, /* 444 */
+  {    74,     10,      0, }, /* 445 */
+  {    74,      7,      0, }, /* 446 */
+  {    74,     12,      0, }, /* 447 */
+  {    74,     21,      0, }, /* 448 */
+  {    74,     13,      0, }, /* 449 */
+  {    68,     13,      0, }, /* 450 */
+  {    68,      7,      0, }, /* 451 */
+  {    68,     12,      0, }, /* 452 */
+  {    68,     21,      0, }, /* 453 */
+  {    73,      7,      0, }, /* 454 */
+  {    73,     12,      0, }, /* 455 */
+  {    73,     10,      0, }, /* 456 */
+  {    73,     21,      0, }, /* 457 */
+  {    83,     12,      0, }, /* 458 */
+  {    83,     10,      0, }, /* 459 */
+  {    83,      7,      0, }, /* 460 */
+  {    83,     21,      0, }, /* 461 */
+  {    83,      6,      0, }, /* 462 */
+  {    83,     13,      0, }, /* 463 */
+  {    67,      7,      0, }, /* 464 */
+  {    67,     12,      0, }, /* 465 */
+  {    67,     10,      0, }, /* 466 */
+  {    67,     13,      0, }, /* 467 */
+  {    67,     21,      0, }, /* 468 */
+  {    38,      6,      0, }, /* 469 */
+  {    91,      7,      0, }, /* 470 */
+  {    91,     12,      0, }, /* 471 */
+  {    91,      6,      0, }, /* 472 */
+  {    91,     21,      0, }, /* 473 */
+  {    86,      7,      0, }, /* 474 */
+  {    86,     10,      0, }, /* 475 */
+  {    86,     12,      0, }, /* 476 */
+  {    86,     21,      0, }, /* 477 */
+  {    86,      6,      0, }, /* 478 */
+  {    86,     13,      0, }, /* 479 */
+  {     9,      4,      0, }, /* 480 */
+  {     9,      3,      0, }, /* 481 */
+  {    25,     25,      0, }, /* 482 */
+  {     0,     24,      0, }, /* 483 */
+  {    35,      7,      0, }, /* 484 */
+  {    19,     14,      0, }, /* 485 */
+  {    19,     15,      0, }, /* 486 */
+  {    19,     26,      0, }, /* 487 */
+  {    70,      7,      0, }, /* 488 */
+  {    66,      7,      0, }, /* 489 */
+  {    41,      7,      0, }, /* 490 */
+  {    41,     15,      0, }, /* 491 */
+  {    18,      7,      0, }, /* 492 */
+  {    18,     14,      0, }, /* 493 */
+  {    59,      7,      0, }, /* 494 */
+  {    59,     21,      0, }, /* 495 */
+  {    42,      7,      0, }, /* 496 */
+  {    42,     21,      0, }, /* 497 */
+  {    42,     14,      0, }, /* 498 */
+  {    13,      9,     40, }, /* 499 */
+  {    13,      5,    -40, }, /* 500 */
+  {    46,      7,      0, }, /* 501 */
+  {    44,      7,      0, }, /* 502 */
+  {    44,     13,      0, }, /* 503 */
+  {    11,      7,      0, }, /* 504 */
+  {    80,      7,      0, }, /* 505 */
+  {    80,     21,      0, }, /* 506 */
+  {    80,     15,      0, }, /* 507 */
+  {    65,      7,      0, }, /* 508 */
+  {    65,     15,      0, }, /* 509 */
+  {    65,     21,      0, }, /* 510 */
+  {    71,      7,      0, }, /* 511 */
+  {    71,     21,      0, }, /* 512 */
+  {    97,      7,      0, }, /* 513 */
+  {    96,      7,      0, }, /* 514 */
+  {    30,      7,      0, }, /* 515 */
+  {    30,     12,      0, }, /* 516 */
+  {    30,     15,      0, }, /* 517 */
+  {    30,     21,      0, }, /* 518 */
+  {    87,      7,      0, }, /* 519 */
+  {    87,     15,      0, }, /* 520 */
+  {    87,     21,      0, }, /* 521 */
+  {    77,      7,      0, }, /* 522 */
+  {    77,     21,      0, }, /* 523 */
+  {    82,      7,      0, }, /* 524 */
+  {    82,     15,      0, }, /* 525 */
+  {    81,      7,      0, }, /* 526 */
+  {    81,     15,      0, }, /* 527 */
+  {    88,      7,      0, }, /* 528 */
+  {     0,     15,      0, }, /* 529 */
+  {    93,     10,      0, }, /* 530 */
+  {    93,     12,      0, }, /* 531 */
+  {    93,      7,      0, }, /* 532 */
+  {    93,     21,      0, }, /* 533 */
+  {    93,     15,      0, }, /* 534 */
+  {    93,     13,      0, }, /* 535 */
+  {    84,     12,      0, }, /* 536 */
+  {    84,     10,      0, }, /* 537 */
+  {    84,      7,      0, }, /* 538 */
+  {    84,     21,      0, }, /* 539 */
+  {    84,      1,      0, }, /* 540 */
+  {   100,      7,      0, }, /* 541 */
+  {   100,     13,      0, }, /* 542 */
+  {    95,     12,      0, }, /* 543 */
+  {    95,      7,      0, }, /* 544 */
+  {    95,     10,      0, }, /* 545 */
+  {    95,     13,      0, }, /* 546 */
+  {    95,     21,      0, }, /* 547 */
+  {    99,     12,      0, }, /* 548 */
+  {    99,     10,      0, }, /* 549 */
+  {    99,      7,      0, }, /* 550 */
+  {    99,     21,      0, }, /* 551 */
+  {    99,     13,      0, }, /* 552 */
+  {   101,      7,      0, }, /* 553 */
+  {   101,     12,      0, }, /* 554 */
+  {   101,     10,      0, }, /* 555 */
+  {   101,     13,      0, }, /* 556 */
+  {    62,      7,      0, }, /* 557 */
+  {    62,     14,      0, }, /* 558 */
+  {    62,     21,      0, }, /* 559 */
+  {    79,      7,      0, }, /* 560 */
+  {    98,      7,      0, }, /* 561 */
+  {    98,     10,      0, }, /* 562 */
+  {    98,     12,      0, }, /* 563 */
+  {    98,      6,      0, }, /* 564 */
+  {    19,     12,      0, }, /* 565 */
+  {    26,     26,      0, }, /* 566 */
+};
+
+const pcre_uint8 PRIV(ucd_stage1)[] = { /* 8704 bytes */
+  0,  1,  2,  3,  4,  5,  6,  7,  8,  9, 10, 11, 12, 13, 14, 15, /* U+0000 */
+ 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, /* U+0800 */
+ 32, 33, 34, 34, 35, 36, 37, 38, 39, 40, 40, 40, 41, 42, 43, 44, /* U+1000 */
+ 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, /* U+1800 */
+ 61, 62, 63, 64, 65, 65, 66, 67, 68, 69, 70, 71, 72, 70, 73, 74, /* U+2000 */
+ 75, 75, 65, 76, 65, 65, 77, 78, 79, 80, 81, 82, 83, 84, 85, 86, /* U+2800 */
+ 87, 88, 89, 90, 91, 92, 93, 70, 94, 94, 94, 94, 94, 94, 94, 94, /* U+3000 */
+ 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, /* U+3800 */
+ 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, /* U+4000 */
+ 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 95, 94, 94, 94, 94, /* U+4800 */
+ 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, /* U+5000 */
+ 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, /* U+5800 */
+ 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, /* U+6000 */
+ 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, /* U+6800 */
+ 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, /* U+7000 */
+ 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, /* U+7800 */
+ 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, /* U+8000 */
+ 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, /* U+8800 */
+ 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, /* U+9000 */
+ 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 96, /* U+9800 */
+ 97, 98, 98, 98, 98, 98, 98, 98, 98, 99,100,100,101,102,103,104, /* U+A000 */
+105,106,107,108,109,110,111,112, 34, 34, 34, 34, 34, 34, 34, 34, /* U+A800 */
+ 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, /* U+B000 */
+ 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, /* U+B800 */
+ 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, /* U+C000 */
+ 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, /* U+C800 */
+ 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34,113, /* U+D000 */
+114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, /* U+D800 */
+115,115,115,115,115,115,115,115,115,115,115,115,115,115,115,115, /* U+E000 */
+115,115,115,115,115,115,115,115,115,115,115,115,115,115,115,115, /* U+E800 */
+115,115,115,115,115,115,115,115,115,115,115,115,115,115,115,115, /* U+F000 */
+115,115, 94, 94,116,117,118,119,120,120,121,122,123,124,125,126, /* U+F800 */
+127,128,129,130, 78,131,132,133,134,135, 78, 78, 78, 78, 78, 78, /* U+10000 */
+136, 78,137,138,139, 78,140, 78,141, 78, 78, 78,142, 78, 78, 78, /* U+10800 */
+143,144,145,146, 78, 78, 78, 78, 78, 78, 78, 78, 78,147, 78, 78, /* U+11000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+11800 */
+148,148,148,148,148,148,149, 78,150, 78, 78, 78, 78, 78, 78, 78, /* U+12000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+12800 */
+151,151,151,151,151,151,151,151,152, 78, 78, 78, 78, 78, 78, 78, /* U+13000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+13800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+14000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+14800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+15000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+15800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+16000 */
+153,153,153,153,154, 78, 78, 78, 78, 78, 78, 78, 78, 78,155,156, /* U+16800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+17000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+17800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+18000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+18800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+19000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+19800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+1A000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+1A800 */
+157, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+1B000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+1B800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+1C000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+1C800 */
+ 70,158,159,160,161, 78,162, 78,163,164,165,166,167,168,169,170, /* U+1D000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+1D800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+1E000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78,171,172, 78, 78, /* U+1E800 */
+173,174,175,176,177, 78,178,179,180,181,182,183,184,185,186, 78, /* U+1F000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+1F800 */
+ 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, /* U+20000 */
+ 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, /* U+20800 */
+ 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, /* U+21000 */
+ 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, /* U+21800 */
+ 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, /* U+22000 */
+ 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, /* U+22800 */
+ 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, /* U+23000 */
+ 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, /* U+23800 */
+ 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, /* U+24000 */
+ 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, /* U+24800 */
+ 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, /* U+25000 */
+ 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, /* U+25800 */
+ 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, /* U+26000 */
+ 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, /* U+26800 */
+ 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, /* U+27000 */
+ 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, /* U+27800 */
+ 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, /* U+28000 */
+ 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, /* U+28800 */
+ 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, /* U+29000 */
+ 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, /* U+29800 */
+ 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94,187, 94, 94, /* U+2A000 */
+ 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, /* U+2A800 */
+ 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94, 94,188, 94, /* U+2B000 */
+189, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+2B800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+2C000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+2C800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+2D000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+2D800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+2E000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+2E800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+2F000 */
+ 94, 94, 94, 94,189, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+2F800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+30000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+30800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+31000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+31800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+32000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+32800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+33000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+33800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+34000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+34800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+35000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+35800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+36000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+36800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+37000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+37800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+38000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+38800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+39000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+39800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+3A000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+3A800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+3B000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+3B800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+3C000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+3C800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+3D000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+3D800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+3E000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+3E800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+3F000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+3F800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+40000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+40800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+41000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+41800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+42000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+42800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+43000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+43800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+44000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+44800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+45000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+45800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+46000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+46800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+47000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+47800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+48000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+48800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+49000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+49800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+4A000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+4A800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+4B000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+4B800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+4C000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+4C800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+4D000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+4D800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+4E000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+4E800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+4F000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+4F800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+50000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+50800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+51000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+51800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+52000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+52800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+53000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+53800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+54000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+54800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+55000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+55800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+56000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+56800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+57000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+57800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+58000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+58800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+59000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+59800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+5A000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+5A800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+5B000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+5B800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+5C000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+5C800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+5D000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+5D800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+5E000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+5E800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+5F000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+5F800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+60000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+60800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+61000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+61800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+62000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+62800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+63000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+63800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+64000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+64800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+65000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+65800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+66000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+66800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+67000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+67800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+68000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+68800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+69000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+69800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+6A000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+6A800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+6B000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+6B800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+6C000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+6C800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+6D000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+6D800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+6E000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+6E800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+6F000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+6F800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+70000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+70800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+71000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+71800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+72000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+72800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+73000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+73800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+74000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+74800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+75000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+75800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+76000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+76800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+77000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+77800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+78000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+78800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+79000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+79800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+7A000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+7A800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+7B000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+7B800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+7C000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+7C800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+7D000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+7D800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+7E000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+7E800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+7F000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+7F800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+80000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+80800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+81000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+81800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+82000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+82800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+83000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+83800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+84000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+84800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+85000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+85800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+86000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+86800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+87000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+87800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+88000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+88800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+89000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+89800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+8A000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+8A800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+8B000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+8B800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+8C000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+8C800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+8D000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+8D800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+8E000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+8E800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+8F000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+8F800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+90000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+90800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+91000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+91800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+92000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+92800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+93000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+93800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+94000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+94800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+95000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+95800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+96000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+96800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+97000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+97800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+98000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+98800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+99000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+99800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+9A000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+9A800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+9B000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+9B800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+9C000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+9C800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+9D000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+9D800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+9E000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+9E800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+9F000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+9F800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+A0000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+A0800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+A1000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+A1800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+A2000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+A2800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+A3000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+A3800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+A4000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+A4800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+A5000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+A5800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+A6000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+A6800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+A7000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+A7800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+A8000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+A8800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+A9000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+A9800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+AA000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+AA800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+AB000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+AB800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+AC000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+AC800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+AD000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+AD800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+AE000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+AE800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+AF000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+AF800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+B0000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+B0800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+B1000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+B1800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+B2000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+B2800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+B3000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+B3800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+B4000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+B4800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+B5000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+B5800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+B6000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+B6800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+B7000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+B7800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+B8000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+B8800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+B9000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+B9800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+BA000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+BA800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+BB000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+BB800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+BC000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+BC800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+BD000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+BD800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+BE000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+BE800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+BF000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+BF800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+C0000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+C0800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+C1000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+C1800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+C2000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+C2800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+C3000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+C3800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+C4000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+C4800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+C5000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+C5800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+C6000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+C6800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+C7000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+C7800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+C8000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+C8800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+C9000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+C9800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+CA000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+CA800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+CB000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+CB800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+CC000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+CC800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+CD000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+CD800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+CE000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+CE800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+CF000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+CF800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+D0000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+D0800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+D1000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+D1800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+D2000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+D2800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+D3000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+D3800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+D4000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+D4800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+D5000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+D5800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+D6000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+D6800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+D7000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+D7800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+D8000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+D8800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+D9000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+D9800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+DA000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+DA800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+DB000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+DB800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+DC000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+DC800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+DD000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+DD800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+DE000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+DE800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+DF000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+DF800 */
+190, 78,191,192, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+E0000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+E0800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+E1000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+E1800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+E2000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+E2800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+E3000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+E3800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+E4000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+E4800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+E5000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+E5800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+E6000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+E6800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+E7000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+E7800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+E8000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+E8800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+E9000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+E9800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+EA000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+EA800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+EB000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+EB800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+EC000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+EC800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+ED000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+ED800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+EE000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+EE800 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+EF000 */
+ 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, 78, /* U+EF800 */
+115,115,115,115,115,115,115,115,115,115,115,115,115,115,115,115, /* U+F0000 */
+115,115,115,115,115,115,115,115,115,115,115,115,115,115,115,115, /* U+F0800 */
+115,115,115,115,115,115,115,115,115,115,115,115,115,115,115,115, /* U+F1000 */
+115,115,115,115,115,115,115,115,115,115,115,115,115,115,115,115, /* U+F1800 */
+115,115,115,115,115,115,115,115,115,115,115,115,115,115,115,115, /* U+F2000 */
+115,115,115,115,115,115,115,115,115,115,115,115,115,115,115,115, /* U+F2800 */
+115,115,115,115,115,115,115,115,115,115,115,115,115,115,115,115, /* U+F3000 */
+115,115,115,115,115,115,115,115,115,115,115,115,115,115,115,115, /* U+F3800 */
+115,115,115,115,115,115,115,115,115,115,115,115,115,115,115,115, /* U+F4000 */
+115,115,115,115,115,115,115,115,115,115,115,115,115,115,115,115, /* U+F4800 */
+115,115,115,115,115,115,115,115,115,115,115,115,115,115,115,115, /* U+F5000 */
+115,115,115,115,115,115,115,115,115,115,115,115,115,115,115,115, /* U+F5800 */
+115,115,115,115,115,115,115,115,115,115,115,115,115,115,115,115, /* U+F6000 */
+115,115,115,115,115,115,115,115,115,115,115,115,115,115,115,115, /* U+F6800 */
+115,115,115,115,115,115,115,115,115,115,115,115,115,115,115,115, /* U+F7000 */
+115,115,115,115,115,115,115,115,115,115,115,115,115,115,115,115, /* U+F7800 */
+115,115,115,115,115,115,115,115,115,115,115,115,115,115,115,115, /* U+F8000 */
+115,115,115,115,115,115,115,115,115,115,115,115,115,115,115,115, /* U+F8800 */
+115,115,115,115,115,115,115,115,115,115,115,115,115,115,115,115, /* U+F9000 */
+115,115,115,115,115,115,115,115,115,115,115,115,115,115,115,115, /* U+F9800 */
+115,115,115,115,115,115,115,115,115,115,115,115,115,115,115,115, /* U+FA000 */
+115,115,115,115,115,115,115,115,115,115,115,115,115,115,115,115, /* U+FA800 */
+115,115,115,115,115,115,115,115,115,115,115,115,115,115,115,115, /* U+FB000 */
+115,115,115,115,115,115,115,115,115,115,115,115,115,115,115,115, /* U+FB800 */
+115,115,115,115,115,115,115,115,115,115,115,115,115,115,115,115, /* U+FC000 */
+115,115,115,115,115,115,115,115,115,115,115,115,115,115,115,115, /* U+FC800 */
+115,115,115,115,115,115,115,115,115,115,115,115,115,115,115,115, /* U+FD000 */
+115,115,115,115,115,115,115,115,115,115,115,115,115,115,115,115, /* U+FD800 */
+115,115,115,115,115,115,115,115,115,115,115,115,115,115,115,115, /* U+FE000 */
+115,115,115,115,115,115,115,115,115,115,115,115,115,115,115,115, /* U+FE800 */
+115,115,115,115,115,115,115,115,115,115,115,115,115,115,115,115, /* U+FF000 */
+115,115,115,115,115,115,115,115,115,115,115,115,115,115,115,193, /* U+FF800 */
+115,115,115,115,115,115,115,115,115,115,115,115,115,115,115,115, /* U+100000 */
+115,115,115,115,115,115,115,115,115,115,115,115,115,115,115,115, /* U+100800 */
+115,115,115,115,115,115,115,115,115,115,115,115,115,115,115,115, /* U+101000 */
+115,115,115,115,115,115,115,115,115,115,115,115,115,115,115,115, /* U+101800 */
+115,115,115,115,115,115,115,115,115,115,115,115,115,115,115,115, /* U+102000 */
+115,115,115,115,115,115,115,115,115,115,115,115,115,115,115,115, /* U+102800 */
+115,115,115,115,115,115,115,115,115,115,115,115,115,115,115,115, /* U+103000 */
+115,115,115,115,115,115,115,115,115,115,115,115,115,115,115,115, /* U+103800 */
+115,115,115,115,115,115,115,115,115,115,115,115,115,115,115,115, /* U+104000 */
+115,115,115,115,115,115,115,115,115,115,115,115,115,115,115,115, /* U+104800 */
+115,115,115,115,115,115,115,115,115,115,115,115,115,115,115,115, /* U+105000 */
+115,115,115,115,115,115,115,115,115,115,115,115,115,115,115,115, /* U+105800 */
+115,115,115,115,115,115,115,115,115,115,115,115,115,115,115,115, /* U+106000 */
+115,115,115,115,115,115,115,115,115,115,115,115,115,115,115,115, /* U+106800 */
+115,115,115,115,115,115,115,115,115,115,115,115,115,115,115,115, /* U+107000 */
+115,115,115,115,115,115,115,115,115,115,115,115,115,115,115,115, /* U+107800 */
+115,115,115,115,115,115,115,115,115,115,115,115,115,115,115,115, /* U+108000 */
+115,115,115,115,115,115,115,115,115,115,115,115,115,115,115,115, /* U+108800 */
+115,115,115,115,115,115,115,115,115,115,115,115,115,115,115,115, /* U+109000 */
+115,115,115,115,115,115,115,115,115,115,115,115,115,115,115,115, /* U+109800 */
+115,115,115,115,115,115,115,115,115,115,115,115,115,115,115,115, /* U+10A000 */
+115,115,115,115,115,115,115,115,115,115,115,115,115,115,115,115, /* U+10A800 */
+115,115,115,115,115,115,115,115,115,115,115,115,115,115,115,115, /* U+10B000 */
+115,115,115,115,115,115,115,115,115,115,115,115,115,115,115,115, /* U+10B800 */
+115,115,115,115,115,115,115,115,115,115,115,115,115,115,115,115, /* U+10C000 */
+115,115,115,115,115,115,115,115,115,115,115,115,115,115,115,115, /* U+10C800 */
+115,115,115,115,115,115,115,115,115,115,115,115,115,115,115,115, /* U+10D000 */
+115,115,115,115,115,115,115,115,115,115,115,115,115,115,115,115, /* U+10D800 */
+115,115,115,115,115,115,115,115,115,115,115,115,115,115,115,115, /* U+10E000 */
+115,115,115,115,115,115,115,115,115,115,115,115,115,115,115,115, /* U+10E800 */
+115,115,115,115,115,115,115,115,115,115,115,115,115,115,115,115, /* U+10F000 */
+115,115,115,115,115,115,115,115,115,115,115,115,115,115,115,193, /* U+10F800 */
+};
+
+const pcre_uint16 PRIV(ucd_stage2)[] = { /* 49664 bytes, block = 128 */
+/* block 0 */
+  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,
+  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,
+  1,  2,  2,  2,  3,  2,  2,  2,  4,  5,  2,  6,  2,  7,  2,  2,
+  8,  8,  8,  8,  8,  8,  8,  8,  8,  8,  2,  2,  6,  6,  6,  2,
+  2,  9,  9,  9,  9,  9,  9,  9,  9,  9,  9,  9,  9,  9,  9,  9,
+  9,  9,  9,  9,  9,  9,  9,  9,  9,  9,  9,  4,  2,  5, 10, 11,
+ 10, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12,
+ 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12,  4,  6,  5,  6,  0,
+
+/* block 1 */
+  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,
+  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,
+  1,  2,  3,  3,  3,  3, 13,  2, 10, 13, 14, 15,  6, 16, 13, 10,
+ 13,  6, 17, 17, 10, 18,  2,  2, 10, 17, 14, 19, 17, 17, 17,  2,
+  9,  9,  9,  9,  9,  9,  9,  9,  9,  9,  9,  9,  9,  9,  9,  9,
+  9,  9,  9,  9,  9,  9,  9,  6,  9,  9,  9,  9,  9,  9,  9, 20,
+ 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12,
+ 12, 12, 12, 12, 12, 12, 12,  6, 12, 12, 12, 12, 12, 12, 12, 21,
+
+/* block 2 */
+ 22, 23, 22, 23, 22, 23, 22, 23, 22, 23, 22, 23, 22, 23, 22, 23,
+ 22, 23, 22, 23, 22, 23, 22, 23, 22, 23, 22, 23, 22, 23, 22, 23,
+ 22, 23, 22, 23, 22, 23, 22, 23, 22, 23, 22, 23, 22, 23, 22, 23,
+ 24, 25, 22, 23, 22, 23, 22, 23, 20, 22, 23, 22, 23, 22, 23, 22,
+ 23, 22, 23, 22, 23, 22, 23, 22, 23, 20, 22, 23, 22, 23, 22, 23,
+ 22, 23, 22, 23, 22, 23, 22, 23, 22, 23, 22, 23, 22, 23, 22, 23,
+ 22, 23, 22, 23, 22, 23, 22, 23, 22, 23, 22, 23, 22, 23, 22, 23,
+ 22, 23, 22, 23, 22, 23, 22, 23, 26, 22, 23, 22, 23, 22, 23, 27,
+
+/* block 3 */
+ 28, 29, 22, 23, 22, 23, 30, 22, 23, 31, 31, 22, 23, 20, 32, 33,
+ 34, 22, 23, 31, 35, 36, 37, 38, 22, 23, 39, 20, 37, 40, 41, 42,
+ 22, 23, 22, 23, 22, 23, 43, 22, 23, 43, 20, 20, 22, 23, 43, 22,
+ 23, 44, 44, 22, 23, 22, 23, 45, 22, 23, 20, 14, 22, 23, 20, 46,
+ 14, 14, 14, 14, 47, 48, 49, 47, 48, 49, 47, 48, 49, 22, 23, 22,
+ 23, 22, 23, 22, 23, 22, 23, 22, 23, 22, 23, 22, 23, 50, 22, 23,
+ 22, 23, 22, 23, 22, 23, 22, 23, 22, 23, 22, 23, 22, 23, 22, 23,
+ 20, 47, 48, 49, 22, 23, 51, 52, 22, 23, 22, 23, 22, 23, 22, 23,
+
+/* block 4 */
+ 22, 23, 22, 23, 22, 23, 22, 23, 22, 23, 22, 23, 22, 23, 22, 23,
+ 22, 23, 22, 23, 22, 23, 22, 23, 22, 23, 22, 23, 22, 23, 22, 23,
+ 53, 20, 22, 23, 22, 23, 22, 23, 22, 23, 22, 23, 22, 23, 22, 23,
+ 22, 23, 22, 23, 20, 20, 20, 20, 20, 20, 54, 22, 23, 55, 56, 57,
+ 57, 22, 23, 58, 59, 60, 22, 23, 22, 23, 22, 23, 22, 23, 22, 23,
+ 61, 62, 63, 64, 65, 20, 66, 66, 20, 67, 20, 68, 20, 20, 20, 20,
+ 66, 20, 20, 69, 20, 70, 71, 20, 72, 73, 20, 74, 20, 20, 20, 73,
+ 20, 75, 76, 20, 20, 77, 20, 20, 20, 20, 20, 20, 20, 78, 20, 20,
+
+/* block 5 */
+ 79, 20, 20, 79, 20, 20, 20, 20, 79, 80, 81, 81, 82, 20, 20, 20,
+ 20, 20, 83, 20, 14, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20,
+ 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20,
+ 84, 84, 84, 84, 84, 84, 84, 84, 84, 85, 85, 85, 85, 85, 85, 85,
+ 85, 85, 10, 10, 10, 10, 85, 85, 85, 85, 85, 85, 85, 85, 85, 85,
+ 85, 85, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10,
+ 84, 84, 84, 84, 84, 10, 10, 10, 10, 10, 86, 86, 85, 10, 85, 10,
+ 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10,
+
+/* block 6 */
+ 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87,
+ 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87,
+ 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87,
+ 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87,
+ 87, 87, 87, 87, 87, 88, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87,
+ 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87,
+ 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87,
+ 89, 90, 89, 90, 85, 91, 89, 90, 92, 92, 93, 94, 94, 94,  2, 92,
+
+/* block 7 */
+ 92, 92, 92, 92, 91, 10, 95,  2, 96, 96, 96, 92, 97, 92, 98, 98,
+ 99,100,100,100,100,100,100,100,100,100,100,100,100,100,100,100,
+100,100, 92,100,100,100,100,100,100,100,100,100,101,102,102,102,
+ 99,103,103,103,103,103,103,103,103,103,103,103,103,103,103,103,
+103,103,104,103,103,103,103,103,103,103,103,103,105,106,106,107,
+108,109,110,110,110,111,112,113, 89, 90, 89, 90, 89, 90, 89, 90,
+ 89, 90,114,115,114,115,114,115,114,115,114,115,114,115,114,115,
+116,117,118, 99,119,120,121, 89, 90,122, 89, 90, 99,123,123,123,
+
+/* block 8 */
+124,124,124,124,124,124,124,124,124,124,124,124,124,124,124,124,
+125,125,125,125,125,125,125,125,125,125,125,125,125,125,125,125,
+125,125,125,125,125,125,125,125,125,125,125,125,125,125,125,125,
+126,126,126,126,126,126,126,126,126,126,126,126,126,126,126,126,
+126,126,126,126,126,126,126,126,126,126,126,126,126,126,126,126,
+127,127,127,127,127,127,127,127,127,127,127,127,127,127,127,127,
+128,129,128,129,128,129,128,129,128,129,128,129,128,129,128,129,
+128,129,128,129,128,129,128,129,128,129,128,129,128,129,128,129,
+
+/* block 9 */
+128,129,130,131,131, 87, 87,131,132,132,128,129,128,129,128,129,
+128,129,128,129,128,129,128,129,128,129,128,129,128,129,128,129,
+128,129,128,129,128,129,128,129,128,129,128,129,128,129,128,129,
+128,129,128,129,128,129,128,129,128,129,128,129,128,129,128,129,
+133,128,129,128,129,128,129,128,129,128,129,128,129,128,129,134,
+128,129,128,129,128,129,128,129,128,129,128,129,128,129,128,129,
+128,129,128,129,128,129,128,129,128,129,128,129,128,129,128,129,
+128,129,128,129,128,129,128,129,128,129,128,129,128,129,128,129,
+
+/* block 10 */
+128,129,128,129,128,129,128,129,128,129,128,129,128,129,128,129,
+128,129,128,129,128,129,128,129,128,129,128,129,128,129,128,129,
+128,129,128,129,128,129,128,129, 92, 92, 92, 92, 92, 92, 92, 92,
+ 92,135,135,135,135,135,135,135,135,135,135,135,135,135,135,135,
+135,135,135,135,135,135,135,135,135,135,135,135,135,135,135,135,
+135,135,135,135,135,135,135, 92, 92,136,137,137,137,137,137,137,
+ 92,138,138,138,138,138,138,138,138,138,138,138,138,138,138,138,
+138,138,138,138,138,138,138,138,138,138,138,138,138,138,138,138,
+
+/* block 11 */
+138,138,138,138,138,138,138,139, 92,  2,140, 92, 92, 92, 92,141,
+ 92,142,142,142,142,142,142,142,142,142,142,142,142,142,142,142,
+142,142,142,142,142,142,142,142,142,142,142,142,142,142,142,142,
+142,142,142,142,142,142,142,142,142,142,142,142,142,142,143,142,
+144,142,142,144,142,142,144,142, 92, 92, 92, 92, 92, 92, 92, 92,
+145,145,145,145,145,145,145,145,145,145,145,145,145,145,145,145,
+145,145,145,145,145,145,145,145,145,145,145, 92, 92, 92, 92, 92,
+145,145,145,144,144, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+
+/* block 12 */
+146,146,146,146,146, 92,147,147,147,148,148,149,  2,148,150,150,
+151,151,151,151,151,151,151,151,151,151,151,  2, 92, 92,148,  2,
+152,152,152,152,152,152,152,152,152,152,152,152,152,152,152,152,
+152,152,152,152,152,152,152,152,152,152,152,152,152,152,152,152,
+ 85,152,152,152,152,152,152,152,152,152,152, 87, 87, 87, 87, 87,
+ 87, 87, 87, 87, 87, 87,151,151,151,151,151,151,151,151,151, 87,
+  8,  8,  8,  8,  8,  8,  8,  8,  8,  8,148,148,148,148,152,152,
+ 87,152,152,152,152,152,152,152,152,152,152,152,152,152,152,152,
+
+/* block 13 */
+152,152,152,152,152,152,152,152,152,152,152,152,152,152,152,152,
+152,152,152,152,152,152,152,152,152,152,152,152,152,152,152,152,
+152,152,152,152,152,152,152,152,152,152,152,152,152,152,152,152,
+152,152,152,152,152,152,152,152,152,152,152,152,152,152,152,152,
+152,152,152,152,152,152,152,152,152,152,152,152,152,152,152,152,
+152,152,152,152,148,152,151,151,151,151,151,151,151, 16,150,151,
+151,151,151,151,151,153,153,151,151,150,151,151,151,151,152,152,
+154,154,154,154,154,154,154,154,154,154,152,152,152,150,150,152,
+
+/* block 14 */
+155,155,155,155,155,155,155,155,155,155,155,155,155,155, 92,156,
+157,158,157,157,157,157,157,157,157,157,157,157,157,157,157,157,
+157,157,157,157,157,157,157,157,157,157,157,157,157,157,157,157,
+158,158,158,158,158,158,158,158,158,158,158,158,158,158,158,158,
+158,158,158,158,158,158,158,158,158,158,158, 92, 92,157,157,157,
+152,152,152,152,152,152,152,152,152,152,152,152,152,152,152,152,
+152,152,152,152,152,152,152,152,152,152,152,152,152,152,152,152,
+152,152,152,152,152,152,152,152,152,152,152,152,152,152,152,152,
+
+/* block 15 */
+159,159,159,159,159,159,159,159,159,159,159,159,159,159,159,159,
+159,159,159,159,159,159,159,159,159,159,159,159,159,159,159,159,
+159,159,159,159,159,159,160,160,160,160,160,160,160,160,160,160,
+160,159, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+161,161,161,161,161,161,161,161,161,161,162,162,162,162,162,162,
+162,162,162,162,162,162,162,162,162,162,162,162,162,162,162,162,
+162,162,162,162,162,162,162,162,162,162,162,163,163,163,163,163,
+163,163,163,163,164,164,165,166,166,166,164, 92, 92, 92, 92, 92,
+
+/* block 16 */
+167,167,167,167,167,167,167,167,167,167,167,167,167,167,167,167,
+167,167,167,167,167,167,168,168,168,168,169,168,168,168,168,168,
+168,168,168,168,169,168,168,168,169,168,168,168,168,168, 92, 92,
+170,170,170,170,170,170,170,170,170,170,170,170,170,170,170, 92,
+171,171,171,171,171,171,171,171,171,171,171,171,171,171,171,171,
+171,171,171,171,171,171,171,171,171,172,172,172, 92, 92,173, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+
+/* block 17 */
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+152, 92,152,152,152,152,152,152,152,152,152,152,152, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92,151,151,151,151,151,151,151,151,151,151,151,151,
+151,151,151,151,151,151,151,151,151,151,151,151,151,151,151, 92,
+
+/* block 18 */
+174,174,174,175,176,176,176,176,176,176,176,176,176,176,176,176,
+176,176,176,176,176,176,176,176,176,176,176,176,176,176,176,176,
+176,176,176,176,176,176,176,176,176,176,176,176,176,176,176,176,
+176,176,176,176,176,176,176,176,176,176,174,175,174,176,175,175,
+175,174,174,174,174,174,174,174,174,175,175,175,175,174,175,175,
+176, 87, 87,174,174,174,174,174,176,176,176,176,176,176,176,176,
+176,176,174,174,  2,  2,177,177,177,177,177,177,177,177,177,177,
+178,179,176,176,176,176,176,176, 92,176,176,176,176,176,176,176,
+
+/* block 19 */
+ 92,180,181,181, 92,182,182,182,182,182,182,182,182, 92, 92,182,
+182, 92, 92,182,182,182,182,182,182,182,182,182,182,182,182,182,
+182,182,182,182,182,182,182,182,182, 92,182,182,182,182,182,182,
+182, 92,182, 92, 92, 92,182,182,182,182, 92, 92,180,182,181,181,
+181,180,180,180,180, 92, 92,181,181, 92, 92,181,181,180,182, 92,
+ 92, 92, 92, 92, 92, 92, 92,181, 92, 92, 92, 92,182,182, 92,182,
+182,182,180,180, 92, 92,183,183,183,183,183,183,183,183,183,183,
+182,182,184,184,185,185,185,185,185,185,186,184, 92, 92, 92, 92,
+
+/* block 20 */
+ 92,187,187,188, 92,189,189,189,189,189,189, 92, 92, 92, 92,189,
+189, 92, 92,189,189,189,189,189,189,189,189,189,189,189,189,189,
+189,189,189,189,189,189,189,189,189, 92,189,189,189,189,189,189,
+189, 92,189,189, 92,189,189, 92,189,189, 92, 92,187, 92,188,188,
+188,187,187, 92, 92, 92, 92,187,187, 92, 92,187,187,187, 92, 92,
+ 92,187, 92, 92, 92, 92, 92, 92, 92,189,189,189,189, 92,189, 92,
+ 92, 92, 92, 92, 92, 92,190,190,190,190,190,190,190,190,190,190,
+187,187,189,189,189,187, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+
+/* block 21 */
+ 92,191,191,192, 92,193,193,193,193,193,193,193,193,193, 92,193,
+193,193, 92,193,193,193,193,193,193,193,193,193,193,193,193,193,
+193,193,193,193,193,193,193,193,193, 92,193,193,193,193,193,193,
+193, 92,193,193, 92,193,193,193,193,193, 92, 92,191,193,192,192,
+192,191,191,191,191,191, 92,191,191,192, 92,192,192,191, 92, 92,
+193, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+193,193,191,191, 92, 92,194,194,194,194,194,194,194,194,194,194,
+195,196, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+
+/* block 22 */
+ 92,197,198,198, 92,199,199,199,199,199,199,199,199, 92, 92,199,
+199, 92, 92,199,199,199,199,199,199,199,199,199,199,199,199,199,
+199,199,199,199,199,199,199,199,199, 92,199,199,199,199,199,199,
+199, 92,199,199, 92,199,199,199,199,199, 92, 92,197,199,198,197,
+198,197,197,197,197, 92, 92,198,198, 92, 92,198,198,197, 92, 92,
+ 92, 92, 92, 92, 92, 92,197,198, 92, 92, 92, 92,199,199, 92,199,
+199,199,197,197, 92, 92,200,200,200,200,200,200,200,200,200,200,
+201,199,202,202,202,202,202,202, 92, 92, 92, 92, 92, 92, 92, 92,
+
+/* block 23 */
+ 92, 92,203,204, 92,204,204,204,204,204,204, 92, 92, 92,204,204,
+204, 92,204,204,204,204, 92, 92, 92,204,204, 92,204, 92,204,204,
+ 92, 92, 92,204,204, 92, 92, 92,204,204,204, 92, 92, 92,204,204,
+204,204,204,204,204,204,204,204,204,204, 92, 92, 92, 92,205,205,
+203,205,205, 92, 92, 92,205,205,205, 92,205,205,205,203, 92, 92,
+204, 92, 92, 92, 92, 92, 92,205, 92, 92, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92,206,206,206,206,206,206,206,206,206,206,
+207,207,207,208,208,208,208,208,208,209,208, 92, 92, 92, 92, 92,
+
+/* block 24 */
+ 92,210,210,210, 92,211,211,211,211,211,211,211,211, 92,211,211,
+211, 92,211,211,211,211,211,211,211,211,211,211,211,211,211,211,
+211,211,211,211,211,211,211,211,211, 92,211,211,211,211,211,211,
+211,211,211,211, 92,211,211,211,211,211, 92, 92, 92,211,212,212,
+212,210,210,210,210, 92,212,212,212, 92,212,212,212,212, 92, 92,
+ 92, 92, 92, 92, 92,212,212, 92,211,211, 92, 92, 92, 92, 92, 92,
+211,211,212,212, 92, 92,213,213,213,213,213,213,213,213,213,213,
+ 92, 92, 92, 92, 92, 92, 92, 92,214,214,214,214,214,214,214,215,
+
+/* block 25 */
+ 92, 92,216,216, 92,217,217,217,217,217,217,217,217, 92,217,217,
+217, 92,217,217,217,217,217,217,217,217,217,217,217,217,217,217,
+217,217,217,217,217,217,217,217,217, 92,217,217,217,217,217,217,
+217,217,217,217, 92,217,217,217,217,217, 92, 92,218,217,216,218,
+216,216,216,216,216, 92,218,216,216, 92,216,216,218,218, 92, 92,
+ 92, 92, 92, 92, 92,216,216, 92, 92, 92, 92, 92, 92, 92,217, 92,
+217,217,218,218, 92, 92,219,219,219,219,219,219,219,219,219,219,
+ 92,217,217, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+
+/* block 26 */
+ 92, 92,220,220, 92,221,221,221,221,221,221,221,221, 92,221,221,
+221, 92,221,221,221,221,221,221,221,221,221,221,221,221,221,221,
+221,221,221,221,221,221,221,221,221,221,221,221,221,221,221,221,
+221,221,221,221,221,221,221,221,221,221,221, 92, 92,221,220,220,
+220,222,222,222,222, 92,220,220,220, 92,220,220,220,222,221, 92,
+ 92, 92, 92, 92, 92, 92, 92,220, 92, 92, 92, 92, 92, 92, 92, 92,
+221,221,222,222, 92, 92,223,223,223,223,223,223,223,223,223,223,
+224,224,224,224,224,224, 92, 92, 92,225,221,221,221,221,221,221,
+
+/* block 27 */
+ 92, 92,226,226, 92,227,227,227,227,227,227,227,227,227,227,227,
+227,227,227,227,227,227,227, 92, 92, 92,227,227,227,227,227,227,
+227,227,227,227,227,227,227,227,227,227,227,227,227,227,227,227,
+227,227, 92,227,227,227,227,227,227,227,227,227, 92,227, 92, 92,
+227,227,227,227,227,227,227, 92, 92, 92,228, 92, 92, 92, 92,226,
+226,226,228,228,228, 92,228, 92,226,226,226,226,226,226,226,226,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 92, 92,226,226,229, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+
+/* block 28 */
+ 92,230,230,230,230,230,230,230,230,230,230,230,230,230,230,230,
+230,230,230,230,230,230,230,230,230,230,230,230,230,230,230,230,
+230,230,230,230,230,230,230,230,230,230,230,230,230,230,230,230,
+230,231,230,230,231,231,231,231,231,231,231, 92, 92, 92, 92,  3,
+230,230,230,230,230,230,232,231,231,231,231,231,231,231,231,233,
+234,234,234,234,234,234,234,234,234,234,233,233, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+
+/* block 29 */
+ 92,235,235, 92,235, 92, 92,235,235, 92,235, 92, 92,235, 92, 92,
+ 92, 92, 92, 92,235,235,235,235, 92,235,235,235,235,235,235,235,
+ 92,235,235,235, 92,235, 92,235, 92, 92,235,235, 92,235,235,235,
+235,236,235,235,236,236,236,236,236,236, 92,236,236,235, 92, 92,
+235,235,235,235,235, 92,237, 92,236,236,236,236,236,236, 92, 92,
+238,238,238,238,238,238,238,238,238,238, 92, 92,235,235,235,235,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+
+/* block 30 */
+239,240,240,240,241,241,241,241,241,241,241,241,241,241,241,241,
+241,241,241,240,241,240,240,240,242,242,240,240,240,240,240,240,
+243,243,243,243,243,243,243,243,243,243,244,244,244,244,244,244,
+244,244,244,244,240,242,240,242,240,242,245,246,245,246,247,247,
+239,239,239,239,239,239,239,239, 92,239,239,239,239,239,239,239,
+239,239,239,239,239,239,239,239,239,239,239,239,239,239,239,239,
+239,239,239,239,239,239,239,239,239,239,239,239,239, 92, 92, 92,
+ 92,242,242,242,242,242,242,242,242,242,242,242,242,242,242,247,
+
+/* block 31 */
+242,242,242,242,242,241,242,242,239,239,239,239,239,242,242,242,
+242,242,242,242,242,242,242,242, 92,242,242,242,242,242,242,242,
+242,242,242,242,242,242,242,242,242,242,242,242,242,242,242,242,
+242,242,242,242,242,242,242,242,242,242,242,242,242, 92,240,240,
+240,240,240,240,240,240,242,240,240,240,240,240,240, 92,240,240,
+241,241,241,241,241, 13, 13, 13, 13,241,241, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+
+/* block 32 */
+248,248,248,248,248,248,248,248,248,248,248,248,248,248,248,248,
+248,248,248,248,248,248,248,248,248,248,248,248,248,248,248,248,
+248,248,248,248,248,248,248,248,248,248,248,249,249,250,250,250,
+250,249,250,250,250,250,250,250,249,250,250,249,249,250,250,248,
+251,251,251,251,251,251,251,251,251,251,252,252,252,252,252,252,
+248,248,248,248,248,248,249,249,250,250,248,248,248,248,250,250,
+250,248,249,249,249,248,248,249,249,249,249,249,249,249,248,248,
+248,250,250,250,250,248,248,248,248,248,248,248,248,248,248,248,
+
+/* block 33 */
+248,248,250,249,249,250,250,249,249,249,249,249,249,250,248,249,
+251,251,251,251,251,251,251,251,251,251,249,249,249,250,253,253,
+254,254,254,254,254,254,254,254,254,254,254,254,254,254,254,254,
+254,254,254,254,254,254,254,254,254,254,254,254,254,254,254,254,
+254,254,254,254,254,254, 92,254, 92, 92, 92, 92, 92,254, 92, 92,
+255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,
+255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,
+255,255,255,255,255,255,255,255,255,255,255,  2,256,255,255,255,
+
+/* block 34 */
+257,257,257,257,257,257,257,257,257,257,257,257,257,257,257,257,
+257,257,257,257,257,257,257,257,257,257,257,257,257,257,257,257,
+257,257,257,257,257,257,257,257,257,257,257,257,257,257,257,257,
+257,257,257,257,257,257,257,257,257,257,257,257,257,257,257,257,
+257,257,257,257,257,257,257,257,257,257,257,257,257,257,257,257,
+257,257,257,257,257,257,257,257,257,257,257,257,257,257,257,257,
+257,257,257,257,257,257,257,257,257,257,257,257,257,257,257,257,
+257,257,257,257,257,257,257,257,257,257,257,257,257,257,257,257,
+
+/* block 35 */
+258,258,258,258,258,258,258,258,258,258,258,258,258,258,258,258,
+258,258,258,258,258,258,258,258,258,258,258,258,258,258,258,258,
+258,258,258,258,258,258,258,258,258,258,258,258,258,258,258,258,
+258,258,258,258,258,258,258,258,258,258,258,258,258,258,258,258,
+258,258,258,258,258,258,258,258,258, 92,258,258,258,258, 92, 92,
+258,258,258,258,258,258,258, 92,258, 92,258,258,258,258, 92, 92,
+258,258,258,258,258,258,258,258,258,258,258,258,258,258,258,258,
+258,258,258,258,258,258,258,258,258,258,258,258,258,258,258,258,
+
+/* block 36 */
+258,258,258,258,258,258,258,258,258, 92,258,258,258,258, 92, 92,
+258,258,258,258,258,258,258,258,258,258,258,258,258,258,258,258,
+258,258,258,258,258,258,258,258,258,258,258,258,258,258,258,258,
+258, 92,258,258,258,258, 92, 92,258,258,258,258,258,258,258, 92,
+258, 92,258,258,258,258, 92, 92,258,258,258,258,258,258,258,258,
+258,258,258,258,258,258,258, 92,258,258,258,258,258,258,258,258,
+258,258,258,258,258,258,258,258,258,258,258,258,258,258,258,258,
+258,258,258,258,258,258,258,258,258,258,258,258,258,258,258,258,
+
+/* block 37 */
+258,258,258,258,258,258,258,258,258,258,258,258,258,258,258,258,
+258, 92,258,258,258,258, 92, 92,258,258,258,258,258,258,258,258,
+258,258,258,258,258,258,258,258,258,258,258,258,258,258,258,258,
+258,258,258,258,258,258,258,258,258,258,258,258,258,258,258,258,
+258,258,258,258,258,258,258,258,258,258,258,258,258,258,258,258,
+258,258,258,258,258,258,258,258,258,258,258, 92, 92,259,259,259,
+260,260,260,260,260,260,260,260,260,261,261,261,261,261,261,261,
+261,261,261,261,261,261,261,261,261,261,261,261,261, 92, 92, 92,
+
+/* block 38 */
+258,258,258,258,258,258,258,258,258,258,258,258,258,258,258,258,
+262,262,262,262,262,262,262,262,262,262, 92, 92, 92, 92, 92, 92,
+263,263,263,263,263,263,263,263,263,263,263,263,263,263,263,263,
+263,263,263,263,263,263,263,263,263,263,263,263,263,263,263,263,
+263,263,263,263,263,263,263,263,263,263,263,263,263,263,263,263,
+263,263,263,263,263,263,263,263,263,263,263,263,263,263,263,263,
+263,263,263,263,263,263,263,263,263,263,263,263,263,263,263,263,
+263,263,263,263,263, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+
+/* block 39 */
+264,265,265,265,265,265,265,265,265,265,265,265,265,265,265,265,
+265,265,265,265,265,265,265,265,265,265,265,265,265,265,265,265,
+265,265,265,265,265,265,265,265,265,265,265,265,265,265,265,265,
+265,265,265,265,265,265,265,265,265,265,265,265,265,265,265,265,
+265,265,265,265,265,265,265,265,265,265,265,265,265,265,265,265,
+265,265,265,265,265,265,265,265,265,265,265,265,265,265,265,265,
+265,265,265,265,265,265,265,265,265,265,265,265,265,265,265,265,
+265,265,265,265,265,265,265,265,265,265,265,265,265,265,265,265,
+
+/* block 40 */
+265,265,265,265,265,265,265,265,265,265,265,265,265,265,265,265,
+265,265,265,265,265,265,265,265,265,265,265,265,265,265,265,265,
+265,265,265,265,265,265,265,265,265,265,265,265,265,265,265,265,
+265,265,265,265,265,265,265,265,265,265,265,265,265,265,265,265,
+265,265,265,265,265,265,265,265,265,265,265,265,265,265,265,265,
+265,265,265,265,265,265,265,265,265,265,265,265,265,265,265,265,
+265,265,265,265,265,265,265,265,265,265,265,265,265,265,265,265,
+265,265,265,265,265,265,265,265,265,265,265,265,265,265,265,265,
+
+/* block 41 */
+265,265,265,265,265,265,265,265,265,265,265,265,265,265,265,265,
+265,265,265,265,265,265,265,265,265,265,265,265,265,265,265,265,
+265,265,265,265,265,265,265,265,265,265,265,265,265,265,265,265,
+265,265,265,265,265,265,265,265,265,265,265,265,265,265,265,265,
+265,265,265,265,265,265,265,265,265,265,265,265,265,265,265,265,
+265,265,265,265,265,265,265,265,265,265,265,265,265,265,265,265,
+265,265,265,265,265,265,265,265,265,265,265,265,265,266,266,265,
+265,265,265,265,265,265,265,265,265,265,265,265,265,265,265,265,
+
+/* block 42 */
+267,268,268,268,268,268,268,268,268,268,268,268,268,268,268,268,
+268,268,268,268,268,268,268,268,268,268,268,269,270, 92, 92, 92,
+271,271,271,271,271,271,271,271,271,271,271,271,271,271,271,271,
+271,271,271,271,271,271,271,271,271,271,271,271,271,271,271,271,
+271,271,271,271,271,271,271,271,271,271,271,271,271,271,271,271,
+271,271,271,271,271,271,271,271,271,271,271,271,271,271,271,271,
+271,271,271,271,271,271,271,271,271,271,271,  2,  2,  2,272,272,
+272, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+
+/* block 43 */
+273,273,273,273,273,273,273,273,273,273,273,273,273, 92,273,273,
+273,273,274,274,274, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+275,275,275,275,275,275,275,275,275,275,275,275,275,275,275,275,
+275,275,276,276,276,  2,  2, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+277,277,277,277,277,277,277,277,277,277,277,277,277,277,277,277,
+277,277,278,278, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+279,279,279,279,279,279,279,279,279,279,279,279,279, 92,279,279,
+279, 92,280,280, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+
+/* block 44 */
+281,281,281,281,281,281,281,281,281,281,281,281,281,281,281,281,
+281,281,281,281,281,281,281,281,281,281,281,281,281,281,281,281,
+281,281,281,281,281,281,281,281,281,281,281,281,281,281,281,281,
+281,281,281,281,282,282,283,282,282,282,282,282,282,282,283,283,
+283,283,283,283,283,283,282,283,283,282,282,282,282,282,282,282,
+282,282,282,282,284,284,284,285,284,284,284,286,281,282, 92, 92,
+287,287,287,287,287,287,287,287,287,287, 92, 92, 92, 92, 92, 92,
+288,288,288,288,288,288,288,288,288,288, 92, 92, 92, 92, 92, 92,
+
+/* block 45 */
+289,289,  2,  2,289,  2,290,289,289,289,289,291,291,291,292, 92,
+293,293,293,293,293,293,293,293,293,293, 92, 92, 92, 92, 92, 92,
+294,294,294,294,294,294,294,294,294,294,294,294,294,294,294,294,
+294,294,294,294,294,294,294,294,294,294,294,294,294,294,294,294,
+294,294,294,295,294,294,294,294,294,294,294,294,294,294,294,294,
+294,294,294,294,294,294,294,294,294,294,294,294,294,294,294,294,
+294,294,294,294,294,294,294,294,294,294,294,294,294,294,294,294,
+294,294,294,294,294,294,294,294, 92, 92, 92, 92, 92, 92, 92, 92,
+
+/* block 46 */
+294,294,294,294,294,294,294,294,294,294,294,294,294,294,294,294,
+294,294,294,294,294,294,294,294,294,294,294,294,294,294,294,294,
+294,294,294,294,294,294,294,294,294,291,294, 92, 92, 92, 92, 92,
+265,265,265,265,265,265,265,265,265,265,265,265,265,265,265,265,
+265,265,265,265,265,265,265,265,265,265,265,265,265,265,265,265,
+265,265,265,265,265,265,265,265,265,265,265,265,265,265,265,265,
+265,265,265,265,265,265,265,265,265,265,265,265,265,265,265,265,
+265,265,265,265,265,265, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+
+/* block 47 */
+296,296,296,296,296,296,296,296,296,296,296,296,296,296,296,296,
+296,296,296,296,296,296,296,296,296,296,296,296,296, 92, 92, 92,
+297,297,297,298,298,298,298,297,297,298,298,298, 92, 92, 92, 92,
+298,298,297,298,298,298,298,298,298,297,297,297, 92, 92, 92, 92,
+299, 92, 92, 92,300,300,301,301,301,301,301,301,301,301,301,301,
+302,302,302,302,302,302,302,302,302,302,302,302,302,302,302,302,
+302,302,302,302,302,302,302,302,302,302,302,302,302,302, 92, 92,
+302,302,302,302,302, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+
+/* block 48 */
+303,303,303,303,303,303,303,303,303,303,303,303,303,303,303,303,
+303,303,303,303,303,303,303,303,303,303,303,303,303,303,303,303,
+303,303,303,303,303,303,303,303,303,303,303,303, 92, 92, 92, 92,
+304,304,304,304,304,304,304,304,304,304,304,304,304,304,304,304,
+304,303,303,303,303,303,303,303,304,304, 92, 92, 92, 92, 92, 92,
+305,305,305,305,305,305,305,305,305,305,306, 92, 92, 92,307,307,
+308,308,308,308,308,308,308,308,308,308,308,308,308,308,308,308,
+308,308,308,308,308,308,308,308,308,308,308,308,308,308,308,308,
+
+/* block 49 */
+309,309,309,309,309,309,309,309,309,309,309,309,309,309,309,309,
+309,309,309,309,309,309,309,310,310,311,311,311, 92, 92,312,312,
+313,313,313,313,313,313,313,313,313,313,313,313,313,313,313,313,
+313,313,313,313,313,313,313,313,313,313,313,313,313,313,313,313,
+313,313,313,313,313,313,313,313,313,313,313,313,313,313,313,313,
+313,313,313,313,313,314,315,314,315,315,315,315,315,315,315, 92,
+315,314,315,314,314,315,315,315,315,315,315,315,315,314,314,314,
+314,314,314,315,315,315,315,315,315,315,315,315,315, 92, 92,315,
+
+/* block 50 */
+316,316,316,316,316,316,316,316,316,316, 92, 92, 92, 92, 92, 92,
+316,316,316,316,316,316,316,316,316,316, 92, 92, 92, 92, 92, 92,
+317,317,317,317,317,317,317,318,317,317,317,317,317,317, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+
+/* block 51 */
+319,319,319,319,320,321,321,321,321,321,321,321,321,321,321,321,
+321,321,321,321,321,321,321,321,321,321,321,321,321,321,321,321,
+321,321,321,321,321,321,321,321,321,321,321,321,321,321,321,321,
+321,321,321,321,319,320,319,319,319,319,319,320,319,320,320,320,
+320,320,319,320,320,321,321,321,321,321,321,321, 92, 92, 92, 92,
+322,322,322,322,322,322,322,322,322,322,323,323,323,323,323,323,
+323,324,324,324,324,324,324,324,324,324,324,319,319,319,319,319,
+319,319,319,319,324,324,324,324,324,324,324,324,324, 92, 92, 92,
+
+/* block 52 */
+325,325,326,327,327,327,327,327,327,327,327,327,327,327,327,327,
+327,327,327,327,327,327,327,327,327,327,327,327,327,327,327,327,
+327,326,325,325,325,325,326,326,325,325,326,325,326,326,327,327,
+328,328,328,328,328,328,328,328,328,328,327,327,327,327,327,327,
+329,329,329,329,329,329,329,329,329,329,329,329,329,329,329,329,
+329,329,329,329,329,329,329,329,329,329,329,329,329,329,329,329,
+329,329,329,329,329,329,330,331,330,330,331,331,331,330,331,330,
+330,330,331,331, 92, 92, 92, 92, 92, 92, 92, 92,332,332,332,332,
+
+/* block 53 */
+333,333,333,333,333,333,333,333,333,333,333,333,333,333,333,333,
+333,333,333,333,333,333,333,333,333,333,333,333,333,333,333,333,
+333,333,333,333,334,334,334,334,334,334,334,334,335,335,335,335,
+335,335,335,335,334,334,335,335, 92, 92, 92,336,336,336,336,336,
+337,337,337,337,337,337,337,337,337,337, 92, 92, 92,333,333,333,
+338,338,338,338,338,338,338,338,338,338,339,339,339,339,339,339,
+339,339,339,339,339,339,339,339,339,339,339,339,339,339,339,339,
+339,339,339,339,339,339,339,339,340,340,340,340,340,340,341,341,
+
+/* block 54 */
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+342,342,342,342,342,342,342,342, 92, 92, 92, 92, 92, 92, 92, 92,
+ 87, 87, 87,  2, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87,
+ 87,343, 87, 87, 87, 87, 87, 87, 87,344,344,344,344, 87,344,344,
+344,344,343,343, 87,344,344, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+
+/* block 55 */
+ 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20,
+ 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20,
+ 20, 20, 20, 20, 20, 20, 99, 99, 99, 99, 99,345, 84, 84, 84, 84,
+ 84, 84, 84, 84, 84, 84, 84, 84, 84, 84, 84, 84, 84, 84, 84, 84,
+ 84, 84, 84, 84, 84, 84, 84, 84, 84, 84, 84, 84, 84, 84, 84, 84,
+ 84, 84, 84, 84, 84, 84, 84, 84, 84, 84, 84, 84, 84, 93, 93, 93,
+ 93, 93, 84, 84, 84, 84, 93, 93, 93, 93, 93, 20, 20, 20, 20, 20,
+ 20, 20, 20, 20, 20, 20, 20, 20,346,347, 20, 20, 20,348, 20, 20,
+
+/* block 56 */
+ 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20,
+ 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 84, 84, 84, 84, 84,
+ 84, 84, 84, 84, 84, 84, 84, 84, 84, 84, 84, 84, 84, 84, 84, 84,
+ 84, 84, 84, 84, 84, 84, 84, 84, 84, 84, 84, 84, 84, 84, 84, 93,
+ 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87,
+ 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87,
+ 87, 87, 87, 87, 87, 87, 87, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 87, 87, 87, 87,
+
+/* block 57 */
+ 22, 23, 22, 23, 22, 23, 22, 23, 22, 23, 22, 23, 22, 23, 22, 23,
+ 22, 23, 22, 23, 22, 23, 22, 23, 22, 23, 22, 23, 22, 23, 22, 23,
+ 22, 23, 22, 23, 22, 23, 22, 23, 22, 23, 22, 23, 22, 23, 22, 23,
+ 22, 23, 22, 23, 22, 23, 22, 23, 22, 23, 22, 23, 22, 23, 22, 23,
+ 22, 23, 22, 23, 22, 23, 22, 23, 22, 23, 22, 23, 22, 23, 22, 23,
+ 22, 23, 22, 23, 22, 23, 22, 23, 22, 23, 22, 23, 22, 23, 22, 23,
+ 22, 23, 22, 23, 22, 23, 22, 23, 22, 23, 22, 23, 22, 23, 22, 23,
+ 22, 23, 22, 23, 22, 23, 22, 23, 22, 23, 22, 23, 22, 23, 22, 23,
+
+/* block 58 */
+ 22, 23, 22, 23, 22, 23, 22, 23, 22, 23, 22, 23, 22, 23, 22, 23,
+ 22, 23, 22, 23, 22, 23, 20, 20, 20, 20, 20,349, 20, 20,350, 20,
+ 22, 23, 22, 23, 22, 23, 22, 23, 22, 23, 22, 23, 22, 23, 22, 23,
+ 22, 23, 22, 23, 22, 23, 22, 23, 22, 23, 22, 23, 22, 23, 22, 23,
+ 22, 23, 22, 23, 22, 23, 22, 23, 22, 23, 22, 23, 22, 23, 22, 23,
+ 22, 23, 22, 23, 22, 23, 22, 23, 22, 23, 22, 23, 22, 23, 22, 23,
+ 22, 23, 22, 23, 22, 23, 22, 23, 22, 23, 22, 23, 22, 23, 22, 23,
+ 22, 23, 22, 23, 22, 23, 22, 23, 22, 23, 22, 23, 22, 23, 22, 23,
+
+/* block 59 */
+351,351,351,351,351,351,351,351,352,352,352,352,352,352,352,352,
+351,351,351,351,351,351, 92, 92,352,352,352,352,352,352, 92, 92,
+351,351,351,351,351,351,351,351,352,352,352,352,352,352,352,352,
+351,351,351,351,351,351,351,351,352,352,352,352,352,352,352,352,
+351,351,351,351,351,351, 92, 92,352,352,352,352,352,352, 92, 92,
+ 99,351, 99,351, 99,351, 99,351, 92,352, 92,352, 92,352, 92,352,
+351,351,351,351,351,351,351,351,352,352,352,352,352,352,352,352,
+353,353,354,354,354,354,355,355,356,356,357,357,358,358, 92, 92,
+
+/* block 60 */
+351,351,351,351,351,351,351,351,359,359,359,359,359,359,359,359,
+351,351,351,351,351,351,351,351,359,359,359,359,359,359,359,359,
+351,351,351,351,351,351,351,351,359,359,359,359,359,359,359,359,
+351,351, 99,360, 99, 92, 99, 99,352,352,361,361,362, 91,363, 91,
+ 91, 91, 99,360, 99, 92, 99, 99,364,364,364,364,362, 91, 91, 91,
+351,351, 99, 99, 92, 92, 99, 99,352,352,365,365, 92, 91, 91, 91,
+351,351, 99, 99, 99,118, 99, 99,352,352,366,366,122, 91, 91, 91,
+ 92, 92, 99,360, 99, 92, 99, 99,367,367,368,368,362, 91, 91, 92,
+
+/* block 61 */
+  1,  1,  1,  1,  1,  1,  1,  1,  1,  1,  1, 16,369,369, 16, 16,
+  7,  7,  7,  7,  7,  7,  2,  2, 15, 19,  4, 15, 15, 19,  4, 15,
+  2,  2,  2,  2,  2,  2,  2,  2,370,371, 16, 16, 16, 16, 16,  1,
+  2,  2,  2,  2,  2,  2,  2,  2,  2, 15, 19,  2,  2,  2,  2, 11,
+ 11,  2,  2,  2,  6,  4,  5,  2,  2,  2,  2,  2,  2,  2,  2,  2,
+  2,  2,  6,  2, 11,  2,  2,  2,  2,  2,  2,  2,  2,  2,  2,  1,
+ 16, 16, 16, 16, 16, 92, 92, 92, 92, 92, 16, 16, 16, 16, 16, 16,
+ 17, 84, 92, 92, 17, 17, 17, 17, 17, 17,  6,  6,  6,  4,  5, 84,
+
+/* block 62 */
+ 17, 17, 17, 17, 17, 17, 17, 17, 17, 17,  6,  6,  6,  4,  5, 92,
+ 84, 84, 84, 84, 84, 84, 84, 84, 84, 84, 84, 84, 84, 92, 92, 92,
+  3,  3,  3,  3,  3,  3,  3,  3,  3,  3,  3,  3,  3,  3,  3,  3,
+  3,  3,  3,  3,  3,  3,  3,  3,  3,  3, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87,372,372,372,
+372, 87,372,372,372, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87,
+ 87, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+
+/* block 63 */
+ 13, 13,373, 13, 13, 13, 13,373, 13, 13,374,373,373,373,374,374,
+373,373,373,374, 13,373, 13, 13,  6,373,373,373,373,373, 13, 13,
+ 13, 13, 13, 13,373, 13,375, 13,373, 13,376,377,373,373, 13,374,
+373,373,378,373,374,344,344,344,344,374, 13, 13,374,374,373,373,
+  6,  6,  6,  6,  6,373,374,374,374,374, 13,  6, 13, 13,379, 13,
+ 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17,
+380,380,380,380,380,380,380,380,380,380,380,380,380,380,380,380,
+381,381,381,381,381,381,381,381,381,381,381,381,381,381,381,381,
+
+/* block 64 */
+382,382,382, 22, 23,382,382,382,382, 17, 92, 92, 92, 92, 92, 92,
+  6,  6,  6,  6,  6, 13, 13, 13, 13, 13,  6,  6, 13, 13, 13, 13,
+  6, 13, 13,  6, 13, 13,  6, 13, 13, 13, 13, 13, 13, 13,  6, 13,
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,  6,  6,
+ 13, 13,  6, 13,  6, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+ 13, 13, 13, 13,  6,  6,  6,  6,  6,  6,  6,  6,  6,  6,  6,  6,
+
+/* block 65 */
+  6,  6,  6,  6,  6,  6,  6,  6,  6,  6,  6,  6,  6,  6,  6,  6,
+  6,  6,  6,  6,  6,  6,  6,  6,  6,  6,  6,  6,  6,  6,  6,  6,
+  6,  6,  6,  6,  6,  6,  6,  6,  6,  6,  6,  6,  6,  6,  6,  6,
+  6,  6,  6,  6,  6,  6,  6,  6,  6,  6,  6,  6,  6,  6,  6,  6,
+  6,  6,  6,  6,  6,  6,  6,  6,  6,  6,  6,  6,  6,  6,  6,  6,
+  6,  6,  6,  6,  6,  6,  6,  6,  6,  6,  6,  6,  6,  6,  6,  6,
+  6,  6,  6,  6,  6,  6,  6,  6,  6,  6,  6,  6,  6,  6,  6,  6,
+  6,  6,  6,  6,  6,  6,  6,  6,  6,  6,  6,  6,  6,  6,  6,  6,
+
+/* block 66 */
+ 13, 13, 13, 13, 13, 13, 13, 13,  6,  6,  6,  6, 13, 13, 13, 13,
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+  6,  6, 13, 13, 13, 13, 13, 13, 13,  4,  5, 13, 13, 13, 13, 13,
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,  6, 13, 13, 13,
+
+/* block 67 */
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,  6,  6,  6,  6,  6,
+  6,  6,  6,  6,  6,  6,  6,  6,  6,  6,  6,  6,  6,  6,  6,  6,
+  6,  6,  6,  6, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,  6,  6,  6,  6,
+  6,  6, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+ 13, 13, 13, 13, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+
+/* block 68 */
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+ 13, 13, 13, 13, 13, 13, 13, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17,
+ 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17,
+
+/* block 69 */
+ 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17,
+ 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 13, 13, 13, 13,
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+ 13, 13, 13, 13, 13, 13,383,383,383,383,383,383,383,383,383,383,
+383,383,383,383,383,383,383,383,383,383,383,383,383,383,383,383,
+384,384,384,384,384,384,384,384,384,384,384,384,384,384,384,384,
+384,384,384,384,384,384,384,384,384,384, 17, 17, 17, 17, 17, 17,
+ 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17,
+
+/* block 70 */
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+
+/* block 71 */
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+ 13, 13, 13, 13, 13, 13, 13,  6, 13, 13, 13, 13, 13, 13, 13, 13,
+ 13,  6, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+ 13, 13, 13, 13, 13, 13, 13, 13,  6,  6,  6,  6,  6,  6,  6,  6,
+
+/* block 72 */
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,  6,
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+
+/* block 73 */
+ 92, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+ 13, 13, 13, 13, 13, 13, 13, 13,  4,  5,  4,  5,  4,  5,  4,  5,
+  4,  5,  4,  5,  4,  5, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17,
+
+/* block 74 */
+ 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17,
+ 17, 17, 17, 17, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+  6,  6,  6,  6,  6,  4,  5,  6,  6,  6,  6,  6,  6,  6,  6,  6,
+  6,  6,  6,  6,  6,  6,  6,  6,  6,  6,  6,  6,  6,  6,  6,  6,
+  6,  6,  6,  6,  6,  6,  4,  5,  4,  5,  4,  5,  4,  5,  4,  5,
+  6,  6,  6,  6,  6,  6,  6,  6,  6,  6,  6,  6,  6,  6,  6,  6,
+
+/* block 75 */
+385,385,385,385,385,385,385,385,385,385,385,385,385,385,385,385,
+385,385,385,385,385,385,385,385,385,385,385,385,385,385,385,385,
+385,385,385,385,385,385,385,385,385,385,385,385,385,385,385,385,
+385,385,385,385,385,385,385,385,385,385,385,385,385,385,385,385,
+385,385,385,385,385,385,385,385,385,385,385,385,385,385,385,385,
+385,385,385,385,385,385,385,385,385,385,385,385,385,385,385,385,
+385,385,385,385,385,385,385,385,385,385,385,385,385,385,385,385,
+385,385,385,385,385,385,385,385,385,385,385,385,385,385,385,385,
+
+/* block 76 */
+  6,  6,  6,  4,  5,  4,  5,  4,  5,  4,  5,  4,  5,  4,  5,  4,
+  5,  4,  5,  4,  5,  4,  5,  4,  5,  6,  6,  6,  6,  6,  6,  6,
+  6,  6,  6,  6,  6,  6,  6,  6,  6,  6,  6,  6,  6,  6,  6,  6,
+  6,  6,  6,  6,  6,  6,  6,  6,  6,  6,  6,  6,  6,  6,  6,  6,
+  6,  6,  6,  6,  6,  6,  6,  6,  6,  6,  6,  6,  6,  6,  6,  6,
+  6,  6,  6,  6,  6,  6,  6,  6,  4,  5,  4,  5,  6,  6,  6,  6,
+  6,  6,  6,  6,  6,  6,  6,  6,  6,  6,  6,  6,  6,  6,  6,  6,
+  6,  6,  6,  6,  6,  6,  6,  6,  6,  6,  6,  6,  4,  5,  6,  6,
+
+/* block 77 */
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+  6,  6,  6,  6,  6,  6,  6,  6,  6,  6,  6,  6,  6,  6,  6,  6,
+  6,  6,  6,  6,  6, 13, 13,  6,  6,  6,  6,  6,  6, 92, 92, 92,
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+
+/* block 78 */
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+
+/* block 79 */
+386,386,386,386,386,386,386,386,386,386,386,386,386,386,386,386,
+386,386,386,386,386,386,386,386,386,386,386,386,386,386,386,386,
+386,386,386,386,386,386,386,386,386,386,386,386,386,386,386, 92,
+387,387,387,387,387,387,387,387,387,387,387,387,387,387,387,387,
+387,387,387,387,387,387,387,387,387,387,387,387,387,387,387,387,
+387,387,387,387,387,387,387,387,387,387,387,387,387,387,387, 92,
+ 22, 23,388,389,390,391,392, 22, 23, 22, 23, 22, 23,393,394,395,
+396, 20, 22, 23, 20, 22, 23, 20, 20, 20, 20, 20, 84, 84,397,397,
+
+/* block 80 */
+114,115,114,115,114,115,114,115,114,115,114,115,114,115,114,115,
+114,115,114,115,114,115,114,115,114,115,114,115,114,115,114,115,
+114,115,114,115,114,115,114,115,114,115,114,115,114,115,114,115,
+114,115,114,115,114,115,114,115,114,115,114,115,114,115,114,115,
+114,115,114,115,114,115,114,115,114,115,114,115,114,115,114,115,
+114,115,114,115,114,115,114,115,114,115,114,115,114,115,114,115,
+114,115,114,115,398,399,399,399,399,399,399,114,115,114,115,400,
+400,400,114,115, 92, 92, 92, 92, 92,401,401,401,401,402,401,401,
+
+/* block 81 */
+403,403,403,403,403,403,403,403,403,403,403,403,403,403,403,403,
+403,403,403,403,403,403,403,403,403,403,403,403,403,403,403,403,
+403,403,403,403,403,403, 92,403, 92, 92, 92, 92, 92,403, 92, 92,
+404,404,404,404,404,404,404,404,404,404,404,404,404,404,404,404,
+404,404,404,404,404,404,404,404,404,404,404,404,404,404,404,404,
+404,404,404,404,404,404,404,404,404,404,404,404,404,404,404,404,
+404,404,404,404,404,404,404,404, 92, 92, 92, 92, 92, 92, 92,405,
+406, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,407,
+
+/* block 82 */
+258,258,258,258,258,258,258,258,258,258,258,258,258,258,258,258,
+258,258,258,258,258,258,258, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+258,258,258,258,258,258,258, 92,258,258,258,258,258,258,258, 92,
+258,258,258,258,258,258,258, 92,258,258,258,258,258,258,258, 92,
+258,258,258,258,258,258,258, 92,258,258,258,258,258,258,258, 92,
+258,258,258,258,258,258,258, 92,258,258,258,258,258,258,258, 92,
+131,131,131,131,131,131,131,131,131,131,131,131,131,131,131,131,
+131,131,131,131,131,131,131,131,131,131,131,131,131,131,131,131,
+
+/* block 83 */
+  2,  2, 15, 19, 15, 19,  2,  2,  2, 15, 19,  2, 15, 19,  2,  2,
+  2,  2,  2,  2,  2,  2,  2,  7,  2,  2,  7,  2, 15, 19,  2,  2,
+ 15, 19,  4,  5,  4,  5,  4,  5,  4,  5,  2,  2,  2,  2,  2, 85,
+  2,  2,  2,  2,  2,  2,  2,  2,  2,  2,  7,  7, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+
+/* block 84 */
+408,408,408,408,408,408,408,408,408,408,408,408,408,408,408,408,
+408,408,408,408,408,408,408,408,408,408, 92,408,408,408,408,408,
+408,408,408,408,408,408,408,408,408,408,408,408,408,408,408,408,
+408,408,408,408,408,408,408,408,408,408,408,408,408,408,408,408,
+408,408,408,408,408,408,408,408,408,408,408,408,408,408,408,408,
+408,408,408,408,408,408,408,408,408,408,408,408,408,408,408,408,
+408,408,408,408,408,408,408,408,408,408,408,408,408,408,408,408,
+408,408,408,408, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+
+/* block 85 */
+408,408,408,408,408,408,408,408,408,408,408,408,408,408,408,408,
+408,408,408,408,408,408,408,408,408,408,408,408,408,408,408,408,
+408,408,408,408,408,408,408,408,408,408,408,408,408,408,408,408,
+408,408,408,408,408,408,408,408,408,408,408,408,408,408,408,408,
+408,408,408,408,408,408,408,408,408,408,408,408,408,408,408,408,
+408,408,408,408,408,408,408,408,408,408,408,408,408,408,408,408,
+408,408,408,408,408,408,408,408,408,408,408,408,408,408,408,408,
+408,408,408,408,408,408,408,408,408,408,408,408,408,408,408,408,
+
+/* block 86 */
+408,408,408,408,408,408,408,408,408,408,408,408,408,408,408,408,
+408,408,408,408,408,408,408,408,408,408,408,408,408,408,408,408,
+408,408,408,408,408,408,408,408,408,408,408,408,408,408,408,408,
+408,408,408,408,408,408,408,408,408,408,408,408,408,408,408,408,
+408,408,408,408,408,408,408,408,408,408,408,408,408,408,408,408,
+408,408,408,408,408,408, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 92, 92, 92, 92,
+
+/* block 87 */
+  1,  2,  2,  2, 13,409,344,410,  4,  5,  4,  5,  4,  5,  4,  5,
+  4,  5, 13, 13,  4,  5,  4,  5,  4,  5,  4,  5,  7,  4,  5,  5,
+ 13,410,410,410,410,410,410,410,410,410, 87, 87, 87, 87,411,411,
+  7, 85, 85, 85, 85, 85, 13, 13,410,410,410,409,344,  2, 13, 13,
+ 92,412,412,412,412,412,412,412,412,412,412,412,412,412,412,412,
+412,412,412,412,412,412,412,412,412,412,412,412,412,412,412,412,
+412,412,412,412,412,412,412,412,412,412,412,412,412,412,412,412,
+412,412,412,412,412,412,412,412,412,412,412,412,412,412,412,412,
+
+/* block 88 */
+412,412,412,412,412,412,412,412,412,412,412,412,412,412,412,412,
+412,412,412,412,412,412,412, 92, 92, 87, 87, 10, 10,413,413,412,
+  7,414,414,414,414,414,414,414,414,414,414,414,414,414,414,414,
+414,414,414,414,414,414,414,414,414,414,414,414,414,414,414,414,
+414,414,414,414,414,414,414,414,414,414,414,414,414,414,414,414,
+414,414,414,414,414,414,414,414,414,414,414,414,414,414,414,414,
+414,414,414,414,414,414,414,414,414,414,414,414,414,414,414,414,
+414,414,414,414,414,414,414,414,414,414,414,  2, 85,415,415,414,
+
+/* block 89 */
+ 92, 92, 92, 92, 92,416,416,416,416,416,416,416,416,416,416,416,
+416,416,416,416,416,416,416,416,416,416,416,416,416,416,416,416,
+416,416,416,416,416,416,416,416,416,416,416,416,416,416, 92, 92,
+ 92,257,257,257,257,257,257,257,257,257,257,257,257,257,257,257,
+257,257,257,257,257,257,257,257,257,257,257,257,257,257,257,257,
+257,257,257,257,257,257,257,257,257,257,257,257,257,257,257,257,
+257,257,257,257,257,257,257,257,257,257,257,257,257,257,257,257,
+257,257,257,257,257,257,257,257,257,257,257,257,257,257,257,257,
+
+/* block 90 */
+257,257,257,257,257,257,257,257,257,257,257,257,257,257,257, 92,
+ 13, 13, 17, 17, 17, 17, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+416,416,416,416,416,416,416,416,416,416,416,416,416,416,416,416,
+416,416,416,416,416,416,416,416,416,416,416, 92, 92, 92, 92, 92,
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+ 13, 13, 13, 13, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+414,414,414,414,414,414,414,414,414,414,414,414,414,414,414,414,
+
+/* block 91 */
+417,417,417,417,417,417,417,417,417,417,417,417,417,417,417,417,
+417,417,417,417,417,417,417,417,417,417,417,417,417,417,417, 92,
+ 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 13, 13, 13, 13, 13, 13,
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+ 13, 13, 13, 13, 13, 13, 13, 13, 17, 17, 17, 17, 17, 17, 17, 17,
+ 13, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17,
+417,417,417,417,417,417,417,417,417,417,417,417,417,417,417,417,
+417,417,417,417,417,417,417,417,417,417,417,417,417,417,417, 13,
+
+/* block 92 */
+ 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 13, 13, 13, 13, 13, 13,
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+ 13, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17,
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+418,418,418,418,418,418,418,418,418,418,418,418,418,418,418,418,
+418,418,418,418,418,418,418,418,418,418,418,418,418,418,418,418,
+418,418,418,418,418,418,418,418,418,418,418,418,418,418,418, 92,
+
+/* block 93 */
+418,418,418,418,418,418,418,418,418,418,418,418,418,418,418,418,
+418,418,418,418,418,418,418,418,418,418,418,418,418,418,418,418,
+418,418,418,418,418,418,418,418,418,418,418,418,418,418,418,418,
+418,418,418,418,418,418,418,418,418,418,418,418,418,418,418,418,
+418,418,418,418,418,418,418,418,418,418,418,418,418,418,418,418,
+418,418,418,418,418,418,418,418, 13, 13, 13, 13, 13, 13, 13, 13,
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+
+/* block 94 */
+419,419,419,419,419,419,419,419,419,419,419,419,419,419,419,419,
+419,419,419,419,419,419,419,419,419,419,419,419,419,419,419,419,
+419,419,419,419,419,419,419,419,419,419,419,419,419,419,419,419,
+419,419,419,419,419,419,419,419,419,419,419,419,419,419,419,419,
+419,419,419,419,419,419,419,419,419,419,419,419,419,419,419,419,
+419,419,419,419,419,419,419,419,419,419,419,419,419,419,419,419,
+419,419,419,419,419,419,419,419,419,419,419,419,419,419,419,419,
+419,419,419,419,419,419,419,419,419,419,419,419,419,419,419,419,
+
+/* block 95 */
+419,419,419,419,419,419,419,419,419,419,419,419,419,419,419,419,
+419,419,419,419,419,419,419,419,419,419,419,419,419,419,419,419,
+419,419,419,419,419,419,419,419,419,419,419,419,419,419,419,419,
+419,419,419,419,419,419, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+
+/* block 96 */
+419,419,419,419,419,419,419,419,419,419,419,419,419,419,419,419,
+419,419,419,419,419,419,419,419,419,419,419,419,419,419,419,419,
+419,419,419,419,419,419,419,419,419,419,419,419,419,419,419,419,
+419,419,419,419,419,419,419,419,419,419,419,419,419,419,419,419,
+419,419,419,419,419,419,419,419,419,419,419,419,419, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+
+/* block 97 */
+420,420,420,420,420,420,420,420,420,420,420,420,420,420,420,420,
+420,420,420,420,420,421,420,420,420,420,420,420,420,420,420,420,
+420,420,420,420,420,420,420,420,420,420,420,420,420,420,420,420,
+420,420,420,420,420,420,420,420,420,420,420,420,420,420,420,420,
+420,420,420,420,420,420,420,420,420,420,420,420,420,420,420,420,
+420,420,420,420,420,420,420,420,420,420,420,420,420,420,420,420,
+420,420,420,420,420,420,420,420,420,420,420,420,420,420,420,420,
+420,420,420,420,420,420,420,420,420,420,420,420,420,420,420,420,
+
+/* block 98 */
+420,420,420,420,420,420,420,420,420,420,420,420,420,420,420,420,
+420,420,420,420,420,420,420,420,420,420,420,420,420,420,420,420,
+420,420,420,420,420,420,420,420,420,420,420,420,420,420,420,420,
+420,420,420,420,420,420,420,420,420,420,420,420,420,420,420,420,
+420,420,420,420,420,420,420,420,420,420,420,420,420,420,420,420,
+420,420,420,420,420,420,420,420,420,420,420,420,420,420,420,420,
+420,420,420,420,420,420,420,420,420,420,420,420,420,420,420,420,
+420,420,420,420,420,420,420,420,420,420,420,420,420,420,420,420,
+
+/* block 99 */
+420,420,420,420,420,420,420,420,420,420,420,420,420, 92, 92, 92,
+422,422,422,422,422,422,422,422,422,422,422,422,422,422,422,422,
+422,422,422,422,422,422,422,422,422,422,422,422,422,422,422,422,
+422,422,422,422,422,422,422,422,422,422,422,422,422,422,422,422,
+422,422,422,422,422,422,422, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+423,423,423,423,423,423,423,423,423,423,423,423,423,423,423,423,
+423,423,423,423,423,423,423,423,423,423,423,423,423,423,423,423,
+423,423,423,423,423,423,423,423,424,424,424,424,424,424,425,425,
+
+/* block 100 */
+426,426,426,426,426,426,426,426,426,426,426,426,426,426,426,426,
+426,426,426,426,426,426,426,426,426,426,426,426,426,426,426,426,
+426,426,426,426,426,426,426,426,426,426,426,426,426,426,426,426,
+426,426,426,426,426,426,426,426,426,426,426,426,426,426,426,426,
+426,426,426,426,426,426,426,426,426,426,426,426,426,426,426,426,
+426,426,426,426,426,426,426,426,426,426,426,426,426,426,426,426,
+426,426,426,426,426,426,426,426,426,426,426,426,426,426,426,426,
+426,426,426,426,426,426,426,426,426,426,426,426,426,426,426,426,
+
+/* block 101 */
+426,426,426,426,426,426,426,426,426,426,426,426,427,428,428,428,
+426,426,426,426,426,426,426,426,426,426,426,426,426,426,426,426,
+429,429,429,429,429,429,429,429,429,429,426,426, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+128,129,128,129,128,129,128,129,128,129,128,129,128,129,128,129,
+128,129,128,129,128,129,128,129,128,129,128,129,128,129,128,129,
+128,129,128,129,128,129,128,129,128,129,128,129,128,129,430,131,
+132,132,132,431,131,131,131,131,131,131,131,131,131,131,431,346,
+
+/* block 102 */
+128,129,128,129,128,129,128,129,128,129,128,129,128,129,128,129,
+128,129,128,129,128,129,128,129, 92, 92, 92, 92, 92, 92, 92,131,
+432,432,432,432,432,432,432,432,432,432,432,432,432,432,432,432,
+432,432,432,432,432,432,432,432,432,432,432,432,432,432,432,432,
+432,432,432,432,432,432,432,432,432,432,432,432,432,432,432,432,
+432,432,432,432,432,432,432,432,432,432,432,432,432,432,432,432,
+432,432,432,432,432,432,433,433,433,433,433,433,433,433,433,433,
+434,434,435,435,435,435,435,435, 92, 92, 92, 92, 92, 92, 92, 92,
+
+/* block 103 */
+ 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10,
+ 10, 10, 10, 10, 10, 10, 10, 85, 85, 85, 85, 85, 85, 85, 85, 85,
+ 10, 10, 22, 23, 22, 23, 22, 23, 22, 23, 22, 23, 22, 23, 22, 23,
+ 20, 20, 22, 23, 22, 23, 22, 23, 22, 23, 22, 23, 22, 23, 22, 23,
+ 22, 23, 22, 23, 22, 23, 22, 23, 22, 23, 22, 23, 22, 23, 22, 23,
+ 22, 23, 22, 23, 22, 23, 22, 23, 22, 23, 22, 23, 22, 23, 22, 23,
+ 22, 23, 22, 23, 22, 23, 22, 23, 22, 23, 22, 23, 22, 23, 22, 23,
+ 84, 20, 20, 20, 20, 20, 20, 20, 20, 22, 23, 22, 23,436, 22, 23,
+
+/* block 104 */
+ 22, 23, 22, 23, 22, 23, 22, 23, 85, 10, 10, 22, 23,437, 20, 92,
+ 22, 23, 22, 23, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 22, 23, 22, 23, 22, 23, 22, 23, 22, 23,438, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 84, 84, 20, 14, 14, 14, 14, 14,
+
+/* block 105 */
+439,439,440,439,439,439,440,439,439,439,439,440,439,439,439,439,
+439,439,439,439,439,439,439,439,439,439,439,439,439,439,439,439,
+439,439,439,441,441,440,440,441,442,442,442,442, 92, 92, 92, 92,
+ 17, 17, 17, 17, 17, 17, 13, 13,  3, 13, 92, 92, 92, 92, 92, 92,
+443,443,443,443,443,443,443,443,443,443,443,443,443,443,443,443,
+443,443,443,443,443,443,443,443,443,443,443,443,443,443,443,443,
+443,443,443,443,443,443,443,443,443,443,443,443,443,443,443,443,
+443,443,443,443,444,444,444,444, 92, 92, 92, 92, 92, 92, 92, 92,
+
+/* block 106 */
+445,445,446,446,446,446,446,446,446,446,446,446,446,446,446,446,
+446,446,446,446,446,446,446,446,446,446,446,446,446,446,446,446,
+446,446,446,446,446,446,446,446,446,446,446,446,446,446,446,446,
+446,446,446,446,445,445,445,445,445,445,445,445,445,445,445,445,
+445,445,445,445,447, 92, 92, 92, 92, 92, 92, 92, 92, 92,448,448,
+449,449,449,449,449,449,449,449,449,449, 92, 92, 92, 92, 92, 92,
+174,174,174,174,174,174,174,174,174,174,174,174,174,174,174,174,
+174,174,176,176,176,176,176,176,178,178,178,176, 92, 92, 92, 92,
+
+/* block 107 */
+450,450,450,450,450,450,450,450,450,450,451,451,451,451,451,451,
+451,451,451,451,451,451,451,451,451,451,451,451,451,451,451,451,
+451,451,451,451,451,451,452,452,452,452,452,452,452,452,453,453,
+454,454,454,454,454,454,454,454,454,454,454,454,454,454,454,454,
+454,454,454,454,454,454,454,455,455,455,455,455,455,455,455,455,
+455,455,456,456, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,457,
+257,257,257,257,257,257,257,257,257,257,257,257,257,257,257,257,
+257,257,257,257,257,257,257,257,257,257,257,257,257, 92, 92, 92,
+
+/* block 108 */
+458,458,458,459,460,460,460,460,460,460,460,460,460,460,460,460,
+460,460,460,460,460,460,460,460,460,460,460,460,460,460,460,460,
+460,460,460,460,460,460,460,460,460,460,460,460,460,460,460,460,
+460,460,460,458,459,459,458,458,458,458,459,459,458,459,459,459,
+459,461,461,461,461,461,461,461,461,461,461,461,461,461, 92,462,
+463,463,463,463,463,463,463,463,463,463, 92, 92, 92, 92,461,461,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+
+/* block 109 */
+464,464,464,464,464,464,464,464,464,464,464,464,464,464,464,464,
+464,464,464,464,464,464,464,464,464,464,464,464,464,464,464,464,
+464,464,464,464,464,464,464,464,464,465,465,465,465,465,465,466,
+466,465,465,466,466,465,465, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+464,464,464,465,464,464,464,464,464,464,464,464,465,466, 92, 92,
+467,467,467,467,467,467,467,467,467,467, 92, 92,468,468,468,468,
+248,248,248,248,248,248,248,248,248,248,248,248,248,248,248,248,
+469,248,248,248,248,248,248,253,253,253,248,249, 92, 92, 92, 92,
+
+/* block 110 */
+470,470,470,470,470,470,470,470,470,470,470,470,470,470,470,470,
+470,470,470,470,470,470,470,470,470,470,470,470,470,470,470,470,
+470,470,470,470,470,470,470,470,470,470,470,470,470,470,470,470,
+471,470,471,471,471,470,470,471,471,470,470,470,470,470,471,471,
+470,471,470, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,470,470,472,473,473,
+474,474,474,474,474,474,474,474,474,474,474,475,476,476,475,475,
+477,477,474,478,478,475,476, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+
+/* block 111 */
+ 92,258,258,258,258,258,258, 92, 92,258,258,258,258,258,258, 92,
+ 92,258,258,258,258,258,258, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+258,258,258,258,258,258,258, 92,258,258,258,258,258,258,258, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+
+/* block 112 */
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+474,474,474,474,474,474,474,474,474,474,474,474,474,474,474,474,
+474,474,474,474,474,474,474,474,474,474,474,474,474,474,474,474,
+474,474,474,475,475,476,475,475,476,475,475,477,475,476, 92, 92,
+479,479,479,479,479,479,479,479,479,479, 92, 92, 92, 92, 92, 92,
+
+/* block 113 */
+257,257,257,257,257,257,257,257,257,257,257,257,257,257,257,257,
+257,257,257,257,257,257,257,257,257,257,257,257,257,257,257,257,
+257,257,257,257, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+257,257,257,257,257,257,257,257,257,257,257,257,257,257,257,257,
+257,257,257,257,257,257,257, 92, 92, 92, 92,257,257,257,257,257,
+257,257,257,257,257,257,257,257,257,257,257,257,257,257,257,257,
+257,257,257,257,257,257,257,257,257,257,257,257,257,257,257,257,
+257,257,257,257,257,257,257,257,257,257,257,257, 92, 92, 92, 92,
+
+/* block 114 */
+480,480,480,480,480,480,480,480,480,480,480,480,480,480,480,480,
+480,480,480,480,480,480,480,480,480,480,480,480,480,480,480,480,
+480,480,480,480,480,480,480,480,480,480,480,480,480,480,480,480,
+480,480,480,480,480,480,480,480,480,480,480,480,480,480,480,480,
+480,480,480,480,480,480,480,480,480,480,480,480,480,480,480,480,
+480,480,480,480,480,480,480,480,480,480,480,480,480,480,480,480,
+480,480,480,480,480,480,480,480,480,480,480,480,480,480,480,480,
+480,480,480,480,480,480,480,480,480,480,480,480,480,480,480,480,
+
+/* block 115 */
+481,481,481,481,481,481,481,481,481,481,481,481,481,481,481,481,
+481,481,481,481,481,481,481,481,481,481,481,481,481,481,481,481,
+481,481,481,481,481,481,481,481,481,481,481,481,481,481,481,481,
+481,481,481,481,481,481,481,481,481,481,481,481,481,481,481,481,
+481,481,481,481,481,481,481,481,481,481,481,481,481,481,481,481,
+481,481,481,481,481,481,481,481,481,481,481,481,481,481,481,481,
+481,481,481,481,481,481,481,481,481,481,481,481,481,481,481,481,
+481,481,481,481,481,481,481,481,481,481,481,481,481,481,481,481,
+
+/* block 116 */
+419,419,419,419,419,419,419,419,419,419,419,419,419,419,419,419,
+419,419,419,419,419,419,419,419,419,419,419,419,419,419,419,419,
+419,419,419,419,419,419,419,419,419,419,419,419,419,419,419,419,
+419,419,419,419,419,419,419,419,419,419,419,419,419,419,419,419,
+419,419,419,419,419,419,419,419,419,419,419,419,419,419,419,419,
+419,419,419,419,419,419,419,419,419,419,419,419,419,419,419,419,
+419,419,419,419,419,419,419,419,419,419,419,419,419,419, 92, 92,
+419,419,419,419,419,419,419,419,419,419,419,419,419,419,419,419,
+
+/* block 117 */
+419,419,419,419,419,419,419,419,419,419,419,419,419,419,419,419,
+419,419,419,419,419,419,419,419,419,419,419,419,419,419,419,419,
+419,419,419,419,419,419,419,419,419,419,419,419,419,419,419,419,
+419,419,419,419,419,419,419,419,419,419,419,419,419,419,419,419,
+419,419,419,419,419,419,419,419,419,419,419,419,419,419,419,419,
+419,419,419,419,419,419,419,419,419,419, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+
+/* block 118 */
+ 20, 20, 20, 20, 20, 20, 20, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92,139,139,139,139,139, 92, 92, 92, 92, 92,145,142,145,
+145,145,145,145,145,145,145,145,145,482,145,145,145,145,145,145,
+145,145,145,145,145,145,145, 92,145,145,145,145,145, 92,145, 92,
+145,145, 92,145,145, 92,145,145,145,145,145,145,145,145,145,145,
+152,152,152,152,152,152,152,152,152,152,152,152,152,152,152,152,
+152,152,152,152,152,152,152,152,152,152,152,152,152,152,152,152,
+152,152,152,152,152,152,152,152,152,152,152,152,152,152,152,152,
+
+/* block 119 */
+152,152,152,152,152,152,152,152,152,152,152,152,152,152,152,152,
+152,152,152,152,152,152,152,152,152,152,152,152,152,152,152,152,
+152,152,152,152,152,152,152,152,152,152,152,152,152,152,152,152,
+152,152,483,483,483,483,483,483,483,483,483,483,483,483,483,483,
+483,483, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92,152,152,152,152,152,152,152,152,152,152,152,152,152,
+152,152,152,152,152,152,152,152,152,152,152,152,152,152,152,152,
+152,152,152,152,152,152,152,152,152,152,152,152,152,152,152,152,
+
+/* block 120 */
+152,152,152,152,152,152,152,152,152,152,152,152,152,152,152,152,
+152,152,152,152,152,152,152,152,152,152,152,152,152,152,152,152,
+152,152,152,152,152,152,152,152,152,152,152,152,152,152,152,152,
+152,152,152,152,152,152,152,152,152,152,152,152,152,152,152,152,
+152,152,152,152,152,152,152,152,152,152,152,152,152,152,152,152,
+152,152,152,152,152,152,152,152,152,152,152,152,152,152,152,152,
+152,152,152,152,152,152,152,152,152,152,152,152,152,152,152,152,
+152,152,152,152,152,152,152,152,152,152,152,152,152,152,152,152,
+
+/* block 121 */
+152,152,152,152,152,152,152,152,152,152,152,152,152,152,152,152,
+152,152,152,152,152,152,152,152,152,152,152,152,152,152,152,152,
+152,152,152,152,152,152,152,152,152,152,152,152,152,152,152,152,
+152,152,152,152,152,152,152,152,152,152,152,152,152,152,  4,  5,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+152,152,152,152,152,152,152,152,152,152,152,152,152,152,152,152,
+152,152,152,152,152,152,152,152,152,152,152,152,152,152,152,152,
+152,152,152,152,152,152,152,152,152,152,152,152,152,152,152,152,
+
+/* block 122 */
+152,152,152,152,152,152,152,152,152,152,152,152,152,152,152,152,
+ 92, 92,152,152,152,152,152,152,152,152,152,152,152,152,152,152,
+152,152,152,152,152,152,152,152,152,152,152,152,152,152,152,152,
+152,152,152,152,152,152,152,152,152,152,152,152,152,152,152,152,
+152,152,152,152,152,152,152,152, 92, 92, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+152,152,152,152,152,152,152,152,152,152,152,152,149, 13, 92, 92,
+
+/* block 123 */
+ 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87,
+  2,  2,  2,  2,  2,  2,  2,  4,  5,  2, 92, 92, 92, 92, 92, 92,
+ 87, 87, 87, 87, 87, 87, 87, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+  2,  7,  7, 11, 11,  4,  5,  4,  5,  4,  5,  4,  5,  4,  5,  4,
+  5,  4,  5,  4,  5,  2,  2,  4,  5,  2,  2,  2,  2, 11, 11, 11,
+  2,  2,  2, 92,  2,  2,  2,  2,  7,  4,  5,  4,  5,  4,  5,  2,
+  2,  2,  6,  7,  6,  6,  6, 92,  2,  3,  2,  2, 92, 92, 92, 92,
+152,152,152,152,152, 92,152,152,152,152,152,152,152,152,152,152,
+
+/* block 124 */
+152,152,152,152,152,152,152,152,152,152,152,152,152,152,152,152,
+152,152,152,152,152,152,152,152,152,152,152,152,152,152,152,152,
+152,152,152,152,152,152,152,152,152,152,152,152,152,152,152,152,
+152,152,152,152,152,152,152,152,152,152,152,152,152,152,152,152,
+152,152,152,152,152,152,152,152,152,152,152,152,152,152,152,152,
+152,152,152,152,152,152,152,152,152,152,152,152,152,152,152,152,
+152,152,152,152,152,152,152,152,152,152,152,152,152,152,152,152,
+152,152,152,152,152,152,152,152,152,152,152,152,152, 92, 92, 16,
+
+/* block 125 */
+ 92,  2,  2,  2,  3,  2,  2,  2,  4,  5,  2,  6,  2,  7,  2,  2,
+  8,  8,  8,  8,  8,  8,  8,  8,  8,  8,  2,  2,  6,  6,  6,  2,
+  2,  9,  9,  9,  9,  9,  9,  9,  9,  9,  9,  9,  9,  9,  9,  9,
+  9,  9,  9,  9,  9,  9,  9,  9,  9,  9,  9,  4,  2,  5, 10, 11,
+ 10, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12,
+ 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12,  4,  6,  5,  6,  4,
+  5,  2,  4,  5,  2,  2,414,414,414,414,414,414,414,414,414,414,
+ 85,414,414,414,414,414,414,414,414,414,414,414,414,414,414,414,
+
+/* block 126 */
+414,414,414,414,414,414,414,414,414,414,414,414,414,414,414,414,
+414,414,414,414,414,414,414,414,414,414,414,414,414,414, 85, 85,
+257,257,257,257,257,257,257,257,257,257,257,257,257,257,257,257,
+257,257,257,257,257,257,257,257,257,257,257,257,257,257,257, 92,
+ 92, 92,257,257,257,257,257,257, 92, 92,257,257,257,257,257,257,
+ 92, 92,257,257,257,257,257,257, 92, 92,257,257,257, 92, 92, 92,
+  3,  3,  6, 10, 13,  3,  3, 92, 13,  6,  6,  6,  6, 13, 13, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 16, 16, 16, 13, 13, 92, 92,
+
+/* block 127 */
+484,484,484,484,484,484,484,484,484,484,484,484, 92,484,484,484,
+484,484,484,484,484,484,484,484,484,484,484,484,484,484,484,484,
+484,484,484,484,484,484,484, 92,484,484,484,484,484,484,484,484,
+484,484,484,484,484,484,484,484,484,484,484, 92,484,484, 92,484,
+484,484,484,484,484,484,484,484,484,484,484,484,484,484, 92, 92,
+484,484,484,484,484,484,484,484,484,484,484,484,484,484, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+
+/* block 128 */
+484,484,484,484,484,484,484,484,484,484,484,484,484,484,484,484,
+484,484,484,484,484,484,484,484,484,484,484,484,484,484,484,484,
+484,484,484,484,484,484,484,484,484,484,484,484,484,484,484,484,
+484,484,484,484,484,484,484,484,484,484,484,484,484,484,484,484,
+484,484,484,484,484,484,484,484,484,484,484,484,484,484,484,484,
+484,484,484,484,484,484,484,484,484,484,484,484,484,484,484,484,
+484,484,484,484,484,484,484,484,484,484,484,484,484,484,484,484,
+484,484,484,484,484,484,484,484,484,484,484, 92, 92, 92, 92, 92,
+
+/* block 129 */
+  2,  2,  2, 92, 92, 92, 92, 17, 17, 17, 17, 17, 17, 17, 17, 17,
+ 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17,
+ 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17,
+ 17, 17, 17, 17, 92, 92, 92, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+485,485,485,485,485,485,485,485,485,485,485,485,485,485,485,485,
+485,485,485,485,485,485,485,485,485,485,485,485,485,485,485,485,
+485,485,485,485,485,485,485,485,485,485,485,485,485,485,485,485,
+485,485,485,485,485,486,486,486,486,487,487,487,487,487,487,487,
+
+/* block 130 */
+487,487,487,487,487,487,487,487,487,487,486, 92, 92, 92, 92, 92,
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 87, 92, 92,
+
+/* block 131 */
+488,488,488,488,488,488,488,488,488,488,488,488,488,488,488,488,
+488,488,488,488,488,488,488,488,488,488,488,488,488, 92, 92, 92,
+489,489,489,489,489,489,489,489,489,489,489,489,489,489,489,489,
+489,489,489,489,489,489,489,489,489,489,489,489,489,489,489,489,
+489,489,489,489,489,489,489,489,489,489,489,489,489,489,489,489,
+489, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+
+/* block 132 */
+490,490,490,490,490,490,490,490,490,490,490,490,490,490,490,490,
+490,490,490,490,490,490,490,490,490,490,490,490,490,490,490, 92,
+491,491,491,491, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+492,492,492,492,492,492,492,492,492,492,492,492,492,492,492,492,
+492,493,492,492,492,492,492,492,492,492,493, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+
+/* block 133 */
+494,494,494,494,494,494,494,494,494,494,494,494,494,494,494,494,
+494,494,494,494,494,494,494,494,494,494,494,494,494,494, 92,495,
+496,496,496,496,496,496,496,496,496,496,496,496,496,496,496,496,
+496,496,496,496,496,496,496,496,496,496,496,496,496,496,496,496,
+496,496,496,496, 92, 92, 92, 92,496,496,496,496,496,496,496,496,
+497,498,498,498,498,498, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+
+/* block 134 */
+499,499,499,499,499,499,499,499,499,499,499,499,499,499,499,499,
+499,499,499,499,499,499,499,499,499,499,499,499,499,499,499,499,
+499,499,499,499,499,499,499,499,500,500,500,500,500,500,500,500,
+500,500,500,500,500,500,500,500,500,500,500,500,500,500,500,500,
+500,500,500,500,500,500,500,500,500,500,500,500,500,500,500,500,
+501,501,501,501,501,501,501,501,501,501,501,501,501,501,501,501,
+501,501,501,501,501,501,501,501,501,501,501,501,501,501,501,501,
+501,501,501,501,501,501,501,501,501,501,501,501,501,501,501,501,
+
+/* block 135 */
+502,502,502,502,502,502,502,502,502,502,502,502,502,502,502,502,
+502,502,502,502,502,502,502,502,502,502,502,502,502,502, 92, 92,
+503,503,503,503,503,503,503,503,503,503, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+
+/* block 136 */
+504,504,504,504,504,504, 92, 92,504, 92,504,504,504,504,504,504,
+504,504,504,504,504,504,504,504,504,504,504,504,504,504,504,504,
+504,504,504,504,504,504,504,504,504,504,504,504,504,504,504,504,
+504,504,504,504,504,504, 92,504,504, 92, 92, 92,504, 92, 92,504,
+505,505,505,505,505,505,505,505,505,505,505,505,505,505,505,505,
+505,505,505,505,505,505, 92,506,507,507,507,507,507,507,507,507,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+
+/* block 137 */
+508,508,508,508,508,508,508,508,508,508,508,508,508,508,508,508,
+508,508,508,508,508,508,509,509,509,509,509,509, 92, 92, 92,510,
+511,511,511,511,511,511,511,511,511,511,511,511,511,511,511,511,
+511,511,511,511,511,511,511,511,511,511, 92, 92, 92, 92, 92,512,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+
+/* block 138 */
+513,513,513,513,513,513,513,513,513,513,513,513,513,513,513,513,
+513,513,513,513,513,513,513,513,513,513,513,513,513,513,513,513,
+514,514,514,514,514,514,514,514,514,514,514,514,514,514,514,514,
+514,514,514,514,514,514,514,514, 92, 92, 92, 92, 92, 92,514,514,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+
+/* block 139 */
+515,516,516,516, 92,516,516, 92, 92, 92, 92, 92,516,516,516,516,
+515,515,515,515, 92,515,515,515, 92,515,515,515,515,515,515,515,
+515,515,515,515,515,515,515,515,515,515,515,515,515,515,515,515,
+515,515,515,515, 92, 92, 92, 92,516,516,516, 92, 92, 92, 92,516,
+517,517,517,517,517,517,517,517, 92, 92, 92, 92, 92, 92, 92, 92,
+518,518,518,518,518,518,518,518,518, 92, 92, 92, 92, 92, 92, 92,
+519,519,519,519,519,519,519,519,519,519,519,519,519,519,519,519,
+519,519,519,519,519,519,519,519,519,519,519,519,519,520,520,521,
+
+/* block 140 */
+522,522,522,522,522,522,522,522,522,522,522,522,522,522,522,522,
+522,522,522,522,522,522,522,522,522,522,522,522,522,522,522,522,
+522,522,522,522,522,522,522,522,522,522,522,522,522,522,522,522,
+522,522,522,522,522,522, 92, 92, 92,523,523,523,523,523,523,523,
+524,524,524,524,524,524,524,524,524,524,524,524,524,524,524,524,
+524,524,524,524,524,524, 92, 92,525,525,525,525,525,525,525,525,
+526,526,526,526,526,526,526,526,526,526,526,526,526,526,526,526,
+526,526,526, 92, 92, 92, 92, 92,527,527,527,527,527,527,527,527,
+
+/* block 141 */
+528,528,528,528,528,528,528,528,528,528,528,528,528,528,528,528,
+528,528,528,528,528,528,528,528,528,528,528,528,528,528,528,528,
+528,528,528,528,528,528,528,528,528,528,528,528,528,528,528,528,
+528,528,528,528,528,528,528,528,528,528,528,528,528,528,528,528,
+528,528,528,528,528,528,528,528,528, 92, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+
+/* block 142 */
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+529,529,529,529,529,529,529,529,529,529,529,529,529,529,529,529,
+529,529,529,529,529,529,529,529,529,529,529,529,529,529,529, 92,
+
+/* block 143 */
+530,531,530,532,532,532,532,532,532,532,532,532,532,532,532,532,
+532,532,532,532,532,532,532,532,532,532,532,532,532,532,532,532,
+532,532,532,532,532,532,532,532,532,532,532,532,532,532,532,532,
+532,532,532,532,532,532,532,532,531,531,531,531,531,531,531,531,
+531,531,531,531,531,531,531,533,533,533,533,533,533,533, 92, 92,
+ 92, 92,534,534,534,534,534,534,534,534,534,534,534,534,534,534,
+534,534,534,534,534,534,535,535,535,535,535,535,535,535,535,535,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+
+/* block 144 */
+536,536,537,538,538,538,538,538,538,538,538,538,538,538,538,538,
+538,538,538,538,538,538,538,538,538,538,538,538,538,538,538,538,
+538,538,538,538,538,538,538,538,538,538,538,538,538,538,538,538,
+537,537,537,536,536,536,536,537,537,536,536,539,539,540,539,539,
+539,539, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+541,541,541,541,541,541,541,541,541,541,541,541,541,541,541,541,
+541,541,541,541,541,541,541,541,541, 92, 92, 92, 92, 92, 92, 92,
+542,542,542,542,542,542,542,542,542,542, 92, 92, 92, 92, 92, 92,
+
+/* block 145 */
+543,543,543,544,544,544,544,544,544,544,544,544,544,544,544,544,
+544,544,544,544,544,544,544,544,544,544,544,544,544,544,544,544,
+544,544,544,544,544,544,544,543,543,543,543,543,545,543,543,543,
+543,543,543,543,543, 92,546,546,546,546,546,546,546,546,546,546,
+547,547,547,547, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+
+/* block 146 */
+548,548,549,550,550,550,550,550,550,550,550,550,550,550,550,550,
+550,550,550,550,550,550,550,550,550,550,550,550,550,550,550,550,
+550,550,550,550,550,550,550,550,550,550,550,550,550,550,550,550,
+550,550,550,549,549,549,548,548,548,548,548,548,548,548,548,549,
+549,550,550,550,550,551,551,551,551, 92, 92, 92, 92, 92, 92, 92,
+552,552,552,552,552,552,552,552,552,552, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+
+/* block 147 */
+553,553,553,553,553,553,553,553,553,553,553,553,553,553,553,553,
+553,553,553,553,553,553,553,553,553,553,553,553,553,553,553,553,
+553,553,553,553,553,553,553,553,553,553,553,554,555,554,555,555,
+554,554,554,554,554,554,555,554, 92, 92, 92, 92, 92, 92, 92, 92,
+556,556,556,556,556,556,556,556,556,556, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+
+/* block 148 */
+557,557,557,557,557,557,557,557,557,557,557,557,557,557,557,557,
+557,557,557,557,557,557,557,557,557,557,557,557,557,557,557,557,
+557,557,557,557,557,557,557,557,557,557,557,557,557,557,557,557,
+557,557,557,557,557,557,557,557,557,557,557,557,557,557,557,557,
+557,557,557,557,557,557,557,557,557,557,557,557,557,557,557,557,
+557,557,557,557,557,557,557,557,557,557,557,557,557,557,557,557,
+557,557,557,557,557,557,557,557,557,557,557,557,557,557,557,557,
+557,557,557,557,557,557,557,557,557,557,557,557,557,557,557,557,
+
+/* block 149 */
+557,557,557,557,557,557,557,557,557,557,557,557,557,557,557,557,
+557,557,557,557,557,557,557,557,557,557,557,557,557,557,557,557,
+557,557,557,557,557,557,557,557,557,557,557,557,557,557,557,557,
+557,557,557,557,557,557,557,557,557,557,557,557,557,557,557,557,
+557,557,557,557,557,557,557,557,557,557,557,557,557,557,557,557,
+557,557,557,557,557,557,557,557,557,557,557,557,557,557,557,557,
+557,557,557,557,557,557,557,557,557,557,557,557,557,557,557, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+
+/* block 150 */
+558,558,558,558,558,558,558,558,558,558,558,558,558,558,558,558,
+558,558,558,558,558,558,558,558,558,558,558,558,558,558,558,558,
+558,558,558,558,558,558,558,558,558,558,558,558,558,558,558,558,
+558,558,558,558,558,558,558,558,558,558,558,558,558,558,558,558,
+558,558,558,558,558,558,558,558,558,558,558,558,558,558,558,558,
+558,558,558,558,558,558,558,558,558,558,558,558,558,558,558,558,
+558,558,558, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+559,559,559,559, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+
+/* block 151 */
+560,560,560,560,560,560,560,560,560,560,560,560,560,560,560,560,
+560,560,560,560,560,560,560,560,560,560,560,560,560,560,560,560,
+560,560,560,560,560,560,560,560,560,560,560,560,560,560,560,560,
+560,560,560,560,560,560,560,560,560,560,560,560,560,560,560,560,
+560,560,560,560,560,560,560,560,560,560,560,560,560,560,560,560,
+560,560,560,560,560,560,560,560,560,560,560,560,560,560,560,560,
+560,560,560,560,560,560,560,560,560,560,560,560,560,560,560,560,
+560,560,560,560,560,560,560,560,560,560,560,560,560,560,560,560,
+
+/* block 152 */
+560,560,560,560,560,560,560,560,560,560,560,560,560,560,560,560,
+560,560,560,560,560,560,560,560,560,560,560,560,560,560,560,560,
+560,560,560,560,560,560,560,560,560,560,560,560,560,560,560, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+
+/* block 153 */
+432,432,432,432,432,432,432,432,432,432,432,432,432,432,432,432,
+432,432,432,432,432,432,432,432,432,432,432,432,432,432,432,432,
+432,432,432,432,432,432,432,432,432,432,432,432,432,432,432,432,
+432,432,432,432,432,432,432,432,432,432,432,432,432,432,432,432,
+432,432,432,432,432,432,432,432,432,432,432,432,432,432,432,432,
+432,432,432,432,432,432,432,432,432,432,432,432,432,432,432,432,
+432,432,432,432,432,432,432,432,432,432,432,432,432,432,432,432,
+432,432,432,432,432,432,432,432,432,432,432,432,432,432,432,432,
+
+/* block 154 */
+432,432,432,432,432,432,432,432,432,432,432,432,432,432,432,432,
+432,432,432,432,432,432,432,432,432,432,432,432,432,432,432,432,
+432,432,432,432,432,432,432,432,432,432,432,432,432,432,432,432,
+432,432,432,432,432,432,432,432,432, 92, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+
+/* block 155 */
+561,561,561,561,561,561,561,561,561,561,561,561,561,561,561,561,
+561,561,561,561,561,561,561,561,561,561,561,561,561,561,561,561,
+561,561,561,561,561,561,561,561,561,561,561,561,561,561,561,561,
+561,561,561,561,561,561,561,561,561,561,561,561,561,561,561,561,
+561,561,561,561,561, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+561,562,562,562,562,562,562,562,562,562,562,562,562,562,562,562,
+562,562,562,562,562,562,562,562,562,562,562,562,562,562,562,562,
+562,562,562,562,562,562,562,562,562,562,562,562,562,562,562, 92,
+
+/* block 156 */
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,563,
+563,563,563,564,564,564,564,564,564,564,564,564,564,564,564,564,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+
+/* block 157 */
+414,412, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+
+/* block 158 */
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+ 13, 13, 13, 13, 13, 13, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+
+/* block 159 */
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+ 13, 13, 13, 13, 13, 13, 13, 92, 92, 13, 13, 13, 13, 13, 13, 13,
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+ 13, 13, 13, 13, 13,343,343, 87, 87, 87, 13, 13, 13,343,343,343,
+343,343,343, 16, 16, 16, 16, 16, 16, 16, 16, 87, 87, 87, 87, 87,
+
+/* block 160 */
+ 87, 87, 87, 13, 13, 87, 87, 87, 87, 87, 87, 87, 13, 13, 13, 13,
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 87, 87, 87, 87, 13, 13,
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+
+/* block 161 */
+487,487,487,487,487,487,487,487,487,487,487,487,487,487,487,487,
+487,487,487,487,487,487,487,487,487,487,487,487,487,487,487,487,
+487,487,487,487,487,487,487,487,487,487,487,487,487,487,487,487,
+487,487,487,487,487,487,487,487,487,487,487,487,487,487,487,487,
+487,487,565,565,565,487, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+
+/* block 162 */
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+ 13, 13, 13, 13, 13, 13, 13, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17,
+ 17, 17, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+
+/* block 163 */
+373,373,373,373,373,373,373,373,373,373,373,373,373,373,373,373,
+373,373,373,373,373,373,373,373,373,373,374,374,374,374,374,374,
+374,374,374,374,374,374,374,374,374,374,374,374,374,374,374,374,
+374,374,374,374,373,373,373,373,373,373,373,373,373,373,373,373,
+373,373,373,373,373,373,373,373,373,373,373,373,373,373,374,374,
+374,374,374,374,374, 92,374,374,374,374,374,374,374,374,374,374,
+374,374,374,374,374,374,374,374,373,373,373,373,373,373,373,373,
+373,373,373,373,373,373,373,373,373,373,373,373,373,373,373,373,
+
+/* block 164 */
+373,373,374,374,374,374,374,374,374,374,374,374,374,374,374,374,
+374,374,374,374,374,374,374,374,374,374,374,374,373, 92,373,373,
+ 92, 92,373, 92, 92,373,373, 92, 92,373,373,373,373, 92,373,373,
+373,373,373,373,373,373,374,374,374,374, 92,374, 92,374,374,374,
+374,374,374,374, 92,374,374,374,374,374,374,374,374,374,374,374,
+373,373,373,373,373,373,373,373,373,373,373,373,373,373,373,373,
+373,373,373,373,373,373,373,373,373,373,374,374,374,374,374,374,
+374,374,374,374,374,374,374,374,374,374,374,374,374,374,374,374,
+
+/* block 165 */
+374,374,374,374,373,373, 92,373,373,373,373, 92, 92,373,373,373,
+373,373,373,373,373, 92,373,373,373,373,373,373,373, 92,374,374,
+374,374,374,374,374,374,374,374,374,374,374,374,374,374,374,374,
+374,374,374,374,374,374,374,374,373,373, 92,373,373,373,373, 92,
+373,373,373,373,373, 92,373, 92, 92, 92,373,373,373,373,373,373,
+373, 92,374,374,374,374,374,374,374,374,374,374,374,374,374,374,
+374,374,374,374,374,374,374,374,374,374,374,374,373,373,373,373,
+373,373,373,373,373,373,373,373,373,373,373,373,373,373,373,373,
+
+/* block 166 */
+373,373,373,373,373,373,374,374,374,374,374,374,374,374,374,374,
+374,374,374,374,374,374,374,374,374,374,374,374,374,374,374,374,
+373,373,373,373,373,373,373,373,373,373,373,373,373,373,373,373,
+373,373,373,373,373,373,373,373,373,373,374,374,374,374,374,374,
+374,374,374,374,374,374,374,374,374,374,374,374,374,374,374,374,
+374,374,374,374,373,373,373,373,373,373,373,373,373,373,373,373,
+373,373,373,373,373,373,373,373,373,373,373,373,373,373,374,374,
+374,374,374,374,374,374,374,374,374,374,374,374,374,374,374,374,
+
+/* block 167 */
+374,374,374,374,374,374,374,374,373,373,373,373,373,373,373,373,
+373,373,373,373,373,373,373,373,373,373,373,373,373,373,373,373,
+373,373,374,374,374,374,374,374,374,374,374,374,374,374,374,374,
+374,374,374,374,374,374,374,374,374,374,374,374,373,373,373,373,
+373,373,373,373,373,373,373,373,373,373,373,373,373,373,373,373,
+373,373,373,373,373,373,374,374,374,374,374,374,374,374,374,374,
+374,374,374,374,374,374,374,374,374,374,374,374,374,374,374,374,
+373,373,373,373,373,373,373,373,373,373,373,373,373,373,373,373,
+
+/* block 168 */
+373,373,373,373,373,373,373,373,373,373,374,374,374,374,374,374,
+374,374,374,374,374,374,374,374,374,374,374,374,374,374,374,374,
+374,374,374,374,374,374, 92, 92,373,373,373,373,373,373,373,373,
+373,373,373,373,373,373,373,373,373,373,373,373,373,373,373,373,
+373,  6,374,374,374,374,374,374,374,374,374,374,374,374,374,374,
+374,374,374,374,374,374,374,374,374,374,374,  6,374,374,374,374,
+374,374,373,373,373,373,373,373,373,373,373,373,373,373,373,373,
+373,373,373,373,373,373,373,373,373,373,373,  6,374,374,374,374,
+
+/* block 169 */
+374,374,374,374,374,374,374,374,374,374,374,374,374,374,374,374,
+374,374,374,374,374,  6,374,374,374,374,374,374,373,373,373,373,
+373,373,373,373,373,373,373,373,373,373,373,373,373,373,373,373,
+373,373,373,373,373,  6,374,374,374,374,374,374,374,374,374,374,
+374,374,374,374,374,374,374,374,374,374,374,374,374,374,374,  6,
+374,374,374,374,374,374,373,373,373,373,373,373,373,373,373,373,
+373,373,373,373,373,373,373,373,373,373,373,373,373,373,373,  6,
+374,374,374,374,374,374,374,374,374,374,374,374,374,374,374,374,
+
+/* block 170 */
+374,374,374,374,374,374,374,374,374,  6,374,374,374,374,374,374,
+373,373,373,373,373,373,373,373,373,373,373,373,373,373,373,373,
+373,373,373,373,373,373,373,373,373,  6,374,374,374,374,374,374,
+374,374,374,374,374,374,374,374,374,374,374,374,374,374,374,374,
+374,374,374,  6,374,374,374,374,374,374,373,374, 92, 92,  8,  8,
+  8,  8,  8,  8,  8,  8,  8,  8,  8,  8,  8,  8,  8,  8,  8,  8,
+  8,  8,  8,  8,  8,  8,  8,  8,  8,  8,  8,  8,  8,  8,  8,  8,
+  8,  8,  8,  8,  8,  8,  8,  8,  8,  8,  8,  8,  8,  8,  8,  8,
+
+/* block 171 */
+152,152,152,152, 92,152,152,152,152,152,152,152,152,152,152,152,
+152,152,152,152,152,152,152,152,152,152,152,152,152,152,152,152,
+ 92,152,152, 92,152, 92, 92,152, 92,152,152,152,152,152,152,152,
+152,152,152, 92,152,152,152,152, 92,152, 92,152, 92, 92, 92, 92,
+ 92, 92,152, 92, 92, 92, 92,152, 92,152, 92,152, 92,152,152,152,
+ 92,152,152, 92,152, 92, 92,152, 92,152, 92,152, 92,152, 92,152,
+ 92,152,152, 92,152, 92, 92,152,152,152,152, 92,152,152,152,152,
+152,152,152, 92,152,152,152,152, 92,152,152,152,152, 92,152, 92,
+
+/* block 172 */
+152,152,152,152,152,152,152,152,152,152, 92,152,152,152,152,152,
+152,152,152,152,152,152,152,152,152,152,152,152, 92, 92, 92, 92,
+ 92,152,152,152, 92,152,152,152,152,152, 92,152,152,152,152,152,
+152,152,152,152,152,152,152,152,152,152,152,152, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+147,147, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+
+/* block 173 */
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 92, 92, 92, 92,
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+
+/* block 174 */
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+ 13, 13, 13, 13, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 92,
+ 92, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 92,
+ 92, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+ 92, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+
+/* block 175 */
+ 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 17, 92, 92, 92, 92, 92,
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 92,
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 92, 92, 92, 92,
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+
+/* block 176 */
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+
+/* block 177 */
+566, 13, 13, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 92, 92, 92, 92, 92,
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 92, 92, 92, 92, 92, 92, 92,
+ 13, 13, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+
+/* block 178 */
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+ 13, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 13, 13, 13, 13, 13, 13, 92, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 92, 92, 92,
+
+/* block 179 */
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+ 13, 13, 13, 13, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+ 13, 13, 13, 13, 13, 92, 13, 13, 13, 13, 13, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+ 13, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+
+/* block 180 */
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 92,
+ 13, 92, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+
+/* block 181 */
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+ 13, 13, 13, 13, 13, 13, 13, 13, 92, 13, 13, 13, 13, 92, 92, 92,
+
+/* block 182 */
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 92, 92,
+ 13, 13, 13, 13, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+ 13, 13, 13, 13, 13, 13, 13, 13, 92, 92, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+
+/* block 183 */
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 13, 13, 13, 13, 13,
+
+/* block 184 */
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+ 13, 92, 92, 92, 92, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+
+/* block 185 */
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+ 13, 13, 13, 13, 13, 13, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+
+/* block 186 */
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+ 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
+ 13, 13, 13, 13, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+
+/* block 187 */
+419,419,419,419,419,419,419,419,419,419,419,419,419,419,419,419,
+419,419,419,419,419,419,419,419,419,419,419,419,419,419,419,419,
+419,419,419,419,419,419,419,419,419,419,419,419,419,419,419,419,
+419,419,419,419,419,419,419,419,419,419,419,419,419,419,419,419,
+419,419,419,419,419,419,419,419,419,419,419,419,419,419,419,419,
+419,419,419,419,419,419,419, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+
+/* block 188 */
+419,419,419,419,419,419,419,419,419,419,419,419,419,419,419,419,
+419,419,419,419,419,419,419,419,419,419,419,419,419,419,419,419,
+419,419,419,419,419,419,419,419,419,419,419,419,419,419,419,419,
+419,419,419,419,419, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+419,419,419,419,419,419,419,419,419,419,419,419,419,419,419,419,
+419,419,419,419,419,419,419,419,419,419,419,419,419,419,419,419,
+419,419,419,419,419,419,419,419,419,419,419,419,419,419,419,419,
+419,419,419,419,419,419,419,419,419,419,419,419,419,419,419,419,
+
+/* block 189 */
+419,419,419,419,419,419,419,419,419,419,419,419,419,419,419,419,
+419,419,419,419,419,419,419,419,419,419,419,419,419,419, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+
+/* block 190 */
+ 92, 16, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+ 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16,
+ 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16,
+ 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16,
+ 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16,
+ 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16,
+ 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16,
+
+/* block 191 */
+ 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87,
+ 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87,
+ 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87,
+ 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87,
+ 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87,
+ 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87,
+ 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87,
+ 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87,
+
+/* block 192 */
+ 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87,
+ 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87,
+ 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87,
+ 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87,
+ 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87,
+ 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87,
+ 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87, 87,
+ 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92, 92,
+
+/* block 193 */
+481,481,481,481,481,481,481,481,481,481,481,481,481,481,481,481,
+481,481,481,481,481,481,481,481,481,481,481,481,481,481,481,481,
+481,481,481,481,481,481,481,481,481,481,481,481,481,481,481,481,
+481,481,481,481,481,481,481,481,481,481,481,481,481,481,481,481,
+481,481,481,481,481,481,481,481,481,481,481,481,481,481,481,481,
+481,481,481,481,481,481,481,481,481,481,481,481,481,481,481,481,
+481,481,481,481,481,481,481,481,481,481,481,481,481,481,481,481,
+481,481,481,481,481,481,481,481,481,481,481,481,481,481, 92, 92,
+
+};
+
+#if UCD_BLOCK_SIZE != 128
+#error Please correct UCD_BLOCK_SIZE in pcre_internal.h
+#endif
+#endif  /* SUPPORT_UCP */
diff --git a/ext/pcre/pcrelib/pcre_valid_utf8.c b/ext/pcre/pcrelib/pcre_valid_utf8.c
new file mode 100644
index 0000000..f49832d
--- /dev/null
+++ b/ext/pcre/pcrelib/pcre_valid_utf8.c
@@ -0,0 +1,297 @@
+/*************************************************
+*      Perl-Compatible Regular Expressions       *
+*************************************************/
+
+/* PCRE is a library of functions to support regular expressions whose syntax
+and semantics are as close as possible to those of the Perl 5 language.
+
+                       Written by Philip Hazel
+           Copyright (c) 1997-2012 University of Cambridge
+
+-----------------------------------------------------------------------------
+Redistribution and use in source and binary forms, with or without
+modification, are permitted provided that the following conditions are met:
+
+    * Redistributions of source code must retain the above copyright notice,
+      this list of conditions and the following disclaimer.
+
+    * Redistributions in binary form must reproduce the above copyright
+      notice, this list of conditions and the following disclaimer in the
+      documentation and/or other materials provided with the distribution.
+
+    * Neither the name of the University of Cambridge nor the names of its
+      contributors may be used to endorse or promote products derived from
+      this software without specific prior written permission.
+
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+POSSIBILITY OF SUCH DAMAGE.
+-----------------------------------------------------------------------------
+*/
+
+
+/* This module contains an internal function for validating UTF-8 character
+strings. */
+
+
+#include "config.h"
+
+#include "pcre_internal.h"
+
+
+/*************************************************
+*         Validate a UTF-8 string                *
+*************************************************/
+
+/* This function is called (optionally) at the start of compile or match, to
+check that a supposed UTF-8 string is actually valid. The early check means
+that subsequent code can assume it is dealing with a valid string. The check
+can be turned off for maximum performance, but the consequences of supplying an
+invalid string are then undefined.
+
+Originally, this function checked according to RFC 2279, allowing for values in
+the range 0 to 0x7fffffff, up to 6 bytes long, but ensuring that they were in
+the canonical format. Once somebody had pointed out RFC 3629 to me (it
+obsoletes 2279), additional restrictions were applied. The values are now
+limited to be between 0 and 0x0010ffff, no more than 4 bytes long, and the
+subrange 0xd000 to 0xdfff is excluded. However, the format of 5-byte and 6-byte
+characters is still checked.
+
+From release 8.13 more information about the details of the error are passed
+back in the returned value:
+
+PCRE_UTF8_ERR0   No error
+PCRE_UTF8_ERR1   Missing 1 byte at the end of the string
+PCRE_UTF8_ERR2   Missing 2 bytes at the end of the string
+PCRE_UTF8_ERR3   Missing 3 bytes at the end of the string
+PCRE_UTF8_ERR4   Missing 4 bytes at the end of the string
+PCRE_UTF8_ERR5   Missing 5 bytes at the end of the string
+PCRE_UTF8_ERR6   2nd-byte's two top bits are not 0x80
+PCRE_UTF8_ERR7   3rd-byte's two top bits are not 0x80
+PCRE_UTF8_ERR8   4th-byte's two top bits are not 0x80
+PCRE_UTF8_ERR9   5th-byte's two top bits are not 0x80
+PCRE_UTF8_ERR10  6th-byte's two top bits are not 0x80
+PCRE_UTF8_ERR11  5-byte character is not permitted by RFC 3629
+PCRE_UTF8_ERR12  6-byte character is not permitted by RFC 3629
+PCRE_UTF8_ERR13  4-byte character with value > 0x10ffff is not permitted
+PCRE_UTF8_ERR14  3-byte character with value 0xd000-0xdfff is not permitted
+PCRE_UTF8_ERR15  Overlong 2-byte sequence
+PCRE_UTF8_ERR16  Overlong 3-byte sequence
+PCRE_UTF8_ERR17  Overlong 4-byte sequence
+PCRE_UTF8_ERR18  Overlong 5-byte sequence (won't ever occur)
+PCRE_UTF8_ERR19  Overlong 6-byte sequence (won't ever occur)
+PCRE_UTF8_ERR20  Isolated 0x80 byte (not within UTF-8 character)
+PCRE_UTF8_ERR21  Byte with the illegal value 0xfe or 0xff
+
+Arguments:
+  string       points to the string
+  length       length of string, or -1 if the string is zero-terminated
+  errp         pointer to an error position offset variable
+
+Returns:       = 0    if the string is a valid UTF-8 string
+               > 0    otherwise, setting the offset of the bad character
+*/
+
+int
+PRIV(valid_utf)(PCRE_PUCHAR string, int length, int *erroroffset)
+{
+#ifdef SUPPORT_UTF
+register PCRE_PUCHAR p;
+
+if (length < 0)
+  {
+  for (p = string; *p != 0; p++);
+  length = (int)(p - string);
+  }
+
+for (p = string; length-- > 0; p++)
+  {
+  register int ab, c, d;
+
+  c = *p;
+  if (c < 128) continue;                /* ASCII character */
+
+  if (c < 0xc0)                         /* Isolated 10xx xxxx byte */
+    {
+    *erroroffset = (int)(p - string);
+    return PCRE_UTF8_ERR20;
+    }
+
+  if (c >= 0xfe)                        /* Invalid 0xfe or 0xff bytes */
+    {
+    *erroroffset = (int)(p - string);
+    return PCRE_UTF8_ERR21;
+    }
+
+  ab = PRIV(utf8_table4)[c & 0x3f];     /* Number of additional bytes */
+  if (length < ab)
+    {
+    *erroroffset = (int)(p - string);          /* Missing bytes */
+    return ab - length;                 /* Codes ERR1 to ERR5 */
+    }
+  length -= ab;                         /* Length remaining */
+
+  /* Check top bits in the second byte */
+
+  if (((d = *(++p)) & 0xc0) != 0x80)
+    {
+    *erroroffset = (int)(p - string) - 1;
+    return PCRE_UTF8_ERR6;
+    }
+
+  /* For each length, check that the remaining bytes start with the 0x80 bit
+  set and not the 0x40 bit. Then check for an overlong sequence, and for the
+  excluded range 0xd800 to 0xdfff. */
+
+  switch (ab)
+    {
+    /* 2-byte character. No further bytes to check for 0x80. Check first byte
+    for for xx00 000x (overlong sequence). */
+
+    case 1: if ((c & 0x3e) == 0)
+      {
+      *erroroffset = (int)(p - string) - 1;
+      return PCRE_UTF8_ERR15;
+      }
+    break;
+
+    /* 3-byte character. Check third byte for 0x80. Then check first 2 bytes
+      for 1110 0000, xx0x xxxx (overlong sequence) or
+          1110 1101, 1010 xxxx (0xd800 - 0xdfff) */
+
+    case 2:
+    if ((*(++p) & 0xc0) != 0x80)     /* Third byte */
+      {
+      *erroroffset = (int)(p - string) - 2;
+      return PCRE_UTF8_ERR7;
+      }
+    if (c == 0xe0 && (d & 0x20) == 0)
+      {
+      *erroroffset = (int)(p - string) - 2;
+      return PCRE_UTF8_ERR16;
+      }
+    if (c == 0xed && d >= 0xa0)
+      {
+      *erroroffset = (int)(p - string) - 2;
+      return PCRE_UTF8_ERR14;
+      }
+    break;
+
+    /* 4-byte character. Check 3rd and 4th bytes for 0x80. Then check first 2
+       bytes for for 1111 0000, xx00 xxxx (overlong sequence), then check for a
+       character greater than 0x0010ffff (f4 8f bf bf) */
+
+    case 3:
+    if ((*(++p) & 0xc0) != 0x80)     /* Third byte */
+      {
+      *erroroffset = (int)(p - string) - 2;
+      return PCRE_UTF8_ERR7;
+      }
+    if ((*(++p) & 0xc0) != 0x80)     /* Fourth byte */
+      {
+      *erroroffset = (int)(p - string) - 3;
+      return PCRE_UTF8_ERR8;
+      }
+    if (c == 0xf0 && (d & 0x30) == 0)
+      {
+      *erroroffset = (int)(p - string) - 3;
+      return PCRE_UTF8_ERR17;
+      }
+    if (c > 0xf4 || (c == 0xf4 && d > 0x8f))
+      {
+      *erroroffset = (int)(p - string) - 3;
+      return PCRE_UTF8_ERR13;
+      }
+    break;
+
+    /* 5-byte and 6-byte characters are not allowed by RFC 3629, and will be
+    rejected by the length test below. However, we do the appropriate tests
+    here so that overlong sequences get diagnosed, and also in case there is
+    ever an option for handling these larger code points. */
+
+    /* 5-byte character. Check 3rd, 4th, and 5th bytes for 0x80. Then check for
+    1111 1000, xx00 0xxx */
+
+    case 4:
+    if ((*(++p) & 0xc0) != 0x80)     /* Third byte */
+      {
+      *erroroffset = (int)(p - string) - 2;
+      return PCRE_UTF8_ERR7;
+      }
+    if ((*(++p) & 0xc0) != 0x80)     /* Fourth byte */
+      {
+      *erroroffset = (int)(p - string) - 3;
+      return PCRE_UTF8_ERR8;
+      }
+    if ((*(++p) & 0xc0) != 0x80)     /* Fifth byte */
+      {
+      *erroroffset = (int)(p - string) - 4;
+      return PCRE_UTF8_ERR9;
+      }
+    if (c == 0xf8 && (d & 0x38) == 0)
+      {
+      *erroroffset = (int)(p - string) - 4;
+      return PCRE_UTF8_ERR18;
+      }
+    break;
+
+    /* 6-byte character. Check 3rd-6th bytes for 0x80. Then check for
+    1111 1100, xx00 00xx. */
+
+    case 5:
+    if ((*(++p) & 0xc0) != 0x80)     /* Third byte */
+      {
+      *erroroffset = (int)(p - string) - 2;
+      return PCRE_UTF8_ERR7;
+      }
+    if ((*(++p) & 0xc0) != 0x80)     /* Fourth byte */
+      {
+      *erroroffset = (int)(p - string) - 3;
+      return PCRE_UTF8_ERR8;
+      }
+    if ((*(++p) & 0xc0) != 0x80)     /* Fifth byte */
+      {
+      *erroroffset = (int)(p - string) - 4;
+      return PCRE_UTF8_ERR9;
+      }
+    if ((*(++p) & 0xc0) != 0x80)     /* Sixth byte */
+      {
+      *erroroffset = (int)(p - string) - 5;
+      return PCRE_UTF8_ERR10;
+      }
+    if (c == 0xfc && (d & 0x3c) == 0)
+      {
+      *erroroffset = (int)(p - string) - 5;
+      return PCRE_UTF8_ERR19;
+      }
+    break;
+    }
+
+  /* Character is valid under RFC 2279, but 4-byte and 5-byte characters are
+  excluded by RFC 3629. The pointer p is currently at the last byte of the
+  character. */
+
+  if (ab > 3)
+    {
+    *erroroffset = (int)(p - string) - ab;
+    return (ab == 4)? PCRE_UTF8_ERR11 : PCRE_UTF8_ERR12;
+    }
+  }
+
+#else  /* SUPPORT_UTF */
+(void)(string);  /* Keep picky compilers happy */
+(void)(length);
+#endif
+
+return PCRE_UTF8_ERR0;   /* This indicates success */
+}
+
+/* End of pcre_valid_utf8.c */
diff --git a/ext/pcre/pcrelib/pcre_version.c b/ext/pcre/pcrelib/pcre_version.c
new file mode 100644
index 0000000..3dd60a5
--- /dev/null
+++ b/ext/pcre/pcrelib/pcre_version.c
@@ -0,0 +1,93 @@
+/*************************************************
+*      Perl-Compatible Regular Expressions       *
+*************************************************/
+
+/* PCRE is a library of functions to support regular expressions whose syntax
+and semantics are as close as possible to those of the Perl 5 language.
+
+                       Written by Philip Hazel
+           Copyright (c) 1997-2012 University of Cambridge
+
+-----------------------------------------------------------------------------
+Redistribution and use in source and binary forms, with or without
+modification, are permitted provided that the following conditions are met:
+
+    * Redistributions of source code must retain the above copyright notice,
+      this list of conditions and the following disclaimer.
+
+    * Redistributions in binary form must reproduce the above copyright
+      notice, this list of conditions and the following disclaimer in the
+      documentation and/or other materials provided with the distribution.
+
+    * Neither the name of the University of Cambridge nor the names of its
+      contributors may be used to endorse or promote products derived from
+      this software without specific prior written permission.
+
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+POSSIBILITY OF SUCH DAMAGE.
+-----------------------------------------------------------------------------
+*/
+
+
+/* This module contains the external function pcre_version(), which returns a
+string that identifies the PCRE version that is in use. */
+
+
+#include "config.h"
+
+#include "pcre_internal.h"
+
+
+/*************************************************
+*          Return version string                 *
+*************************************************/
+
+/* These macros are the standard way of turning unquoted text into C strings.
+They allow macros like PCRE_MAJOR to be defined without quotes, which is
+convenient for user programs that want to test its value. */
+
+#define STRING(a)  # a
+#define XSTRING(s) STRING(s)
+
+/* A problem turned up with PCRE_PRERELEASE, which is defined empty for
+production releases. Originally, it was used naively in this code:
+
+  return XSTRING(PCRE_MAJOR)
+         "." XSTRING(PCRE_MINOR)
+             XSTRING(PCRE_PRERELEASE)
+         " " XSTRING(PCRE_DATE);
+
+However, when PCRE_PRERELEASE is empty, this leads to an attempted expansion of
+STRING(). The C standard states: "If (before argument substitution) any
+argument consists of no preprocessing tokens, the behavior is undefined." It
+turns out the gcc treats this case as a single empty string - which is what we
+really want - but Visual C grumbles about the lack of an argument for the
+macro. Unfortunately, both are within their rights. To cope with both ways of
+handling this, I had resort to some messy hackery that does a test at run time.
+I could find no way of detecting that a macro is defined as an empty string at
+pre-processor time. This hack uses a standard trick for avoiding calling
+the STRING macro with an empty argument when doing the test. */
+
+#ifdef COMPILE_PCRE8
+PCRE_EXP_DEFN const char * PCRE_CALL_CONVENTION
+pcre_version(void)
+#else
+PCRE_EXP_DEFN const char * PCRE_CALL_CONVENTION
+pcre16_version(void)
+#endif
+{
+return (XSTRING(Z PCRE_PRERELEASE)[1] == 0)?
+  XSTRING(PCRE_MAJOR.PCRE_MINOR PCRE_DATE) :
+  XSTRING(PCRE_MAJOR.PCRE_MINOR) XSTRING(PCRE_PRERELEASE PCRE_DATE);
+}
+
+/* End of pcre_version.c */
diff --git a/ext/pcre/pcrelib/pcre_xclass.c b/ext/pcre/pcrelib/pcre_xclass.c
new file mode 100644
index 0000000..446f85d
--- /dev/null
+++ b/ext/pcre/pcrelib/pcre_xclass.c
@@ -0,0 +1,196 @@
+/*************************************************
+*      Perl-Compatible Regular Expressions       *
+*************************************************/
+
+/* PCRE is a library of functions to support regular expressions whose syntax
+and semantics are as close as possible to those of the Perl 5 language.
+
+                       Written by Philip Hazel
+           Copyright (c) 1997-2012 University of Cambridge
+
+-----------------------------------------------------------------------------
+Redistribution and use in source and binary forms, with or without
+modification, are permitted provided that the following conditions are met:
+
+    * Redistributions of source code must retain the above copyright notice,
+      this list of conditions and the following disclaimer.
+
+    * Redistributions in binary form must reproduce the above copyright
+      notice, this list of conditions and the following disclaimer in the
+      documentation and/or other materials provided with the distribution.
+
+    * Neither the name of the University of Cambridge nor the names of its
+      contributors may be used to endorse or promote products derived from
+      this software without specific prior written permission.
+
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+POSSIBILITY OF SUCH DAMAGE.
+-----------------------------------------------------------------------------
+*/
+
+
+/* This module contains an internal function that is used to match an extended
+class. It is used by both pcre_exec() and pcre_def_exec(). */
+
+
+#include "config.h"
+
+#include "pcre_internal.h"
+
+
+/*************************************************
+*       Match character against an XCLASS        *
+*************************************************/
+
+/* This function is called to match a character against an extended class that
+might contain values > 255 and/or Unicode properties.
+
+Arguments:
+  c           the character
+  data        points to the flag byte of the XCLASS data
+
+Returns:      TRUE if character matches, else FALSE
+*/
+
+BOOL
+PRIV(xclass)(int c, const pcre_uchar *data, BOOL utf)
+{
+int t;
+BOOL negated = (*data & XCL_NOT) != 0;
+
+(void)utf;
+#ifdef COMPILE_PCRE8
+/* In 8 bit mode, this must always be TRUE. Help the compiler to know that. */
+utf = TRUE;
+#endif
+
+/* Character values < 256 are matched against a bitmap, if one is present. If
+not, we still carry on, because there may be ranges that start below 256 in the
+additional data. */
+
+if (c < 256)
+  {
+  if ((*data & XCL_MAP) != 0 &&
+    (((pcre_uint8 *)(data + 1))[c/8] & (1 << (c&7))) != 0)
+    return !negated; /* char found */
+  }
+
+/* First skip the bit map if present. Then match against the list of Unicode
+properties or large chars or ranges that end with a large char. We won't ever
+encounter XCL_PROP or XCL_NOTPROP when UCP support is not compiled. */
+
+if ((*data++ & XCL_MAP) != 0) data += 32 / sizeof(pcre_uchar);
+
+while ((t = *data++) != XCL_END)
+  {
+  int x, y;
+  if (t == XCL_SINGLE)
+    {
+#ifdef SUPPORT_UTF
+    if (utf)
+      {
+      GETCHARINC(x, data); /* macro generates multiple statements */
+      }
+    else
+#endif
+      x = *data++;
+    if (c == x) return !negated;
+    }
+  else if (t == XCL_RANGE)
+    {
+#ifdef SUPPORT_UTF
+    if (utf)
+      {
+      GETCHARINC(x, data); /* macro generates multiple statements */
+      GETCHARINC(y, data); /* macro generates multiple statements */
+      }
+    else
+#endif
+      {
+      x = *data++;
+      y = *data++;
+      }
+    if (c >= x && c <= y) return !negated;
+    }
+
+#ifdef SUPPORT_UCP
+  else  /* XCL_PROP & XCL_NOTPROP */
+    {
+    const ucd_record *prop = GET_UCD(c);
+
+    switch(*data)
+      {
+      case PT_ANY:
+      if (t == XCL_PROP) return !negated;
+      break;
+
+      case PT_LAMP:
+      if ((prop->chartype == ucp_Lu || prop->chartype == ucp_Ll ||
+           prop->chartype == ucp_Lt) == (t == XCL_PROP)) return !negated;
+      break;
+
+      case PT_GC:
+      if ((data[1] == PRIV(ucp_gentype)[prop->chartype]) == (t == XCL_PROP))
+        return !negated;
+      break;
+
+      case PT_PC:
+      if ((data[1] == prop->chartype) == (t == XCL_PROP)) return !negated;
+      break;
+
+      case PT_SC:
+      if ((data[1] == prop->script) == (t == XCL_PROP)) return !negated;
+      break;
+
+      case PT_ALNUM:
+      if ((PRIV(ucp_gentype)[prop->chartype] == ucp_L ||
+           PRIV(ucp_gentype)[prop->chartype] == ucp_N) == (t == XCL_PROP))
+        return !negated;
+      break;
+
+      case PT_SPACE:    /* Perl space */
+      if ((PRIV(ucp_gentype)[prop->chartype] == ucp_Z ||
+           c == CHAR_HT || c == CHAR_NL || c == CHAR_FF || c == CHAR_CR)
+             == (t == XCL_PROP))
+        return !negated;
+      break;
+
+      case PT_PXSPACE:  /* POSIX space */
+      if ((PRIV(ucp_gentype)[prop->chartype] == ucp_Z ||
+           c == CHAR_HT || c == CHAR_NL || c == CHAR_VT ||
+           c == CHAR_FF || c == CHAR_CR) == (t == XCL_PROP))
+        return !negated;
+      break;
+
+      case PT_WORD:
+      if ((PRIV(ucp_gentype)[prop->chartype] == ucp_L ||
+           PRIV(ucp_gentype)[prop->chartype] == ucp_N || c == CHAR_UNDERSCORE)
+             == (t == XCL_PROP))
+        return !negated;
+      break;
+
+      /* This should never occur, but compilers may mutter if there is no
+      default. */
+
+      default:
+      return FALSE;
+      }
+
+    data += 2;
+    }
+#endif  /* SUPPORT_UCP */
+  }
+
+return negated;   /* char did not match */
+}
+
+/* End of pcre_xclass.c */
diff --git a/ext/pcre/pcrelib/pcredemo.c b/ext/pcre/pcrelib/pcredemo.c
new file mode 100644
index 0000000..946aba4
--- /dev/null
+++ b/ext/pcre/pcrelib/pcredemo.c
@@ -0,0 +1,406 @@
+/*************************************************
+*           PCRE DEMONSTRATION PROGRAM           *
+*************************************************/
+
+/* This is a demonstration program to illustrate the most straightforward ways
+of calling the PCRE regular expression library from a C program. See the
+pcresample documentation for a short discussion ("man pcresample" if you have
+the PCRE man pages installed).
+
+In Unix-like environments, if PCRE is installed in your standard system
+libraries, you should be able to compile this program using this command:
+
+gcc -Wall pcredemo.c -lpcre -o pcredemo
+
+If PCRE is not installed in a standard place, it is likely to be installed with
+support for the pkg-config mechanism. If you have pkg-config, you can compile
+this program using this command:
+
+gcc -Wall pcredemo.c `pkg-config --cflags --libs libpcre` -o pcredemo
+
+If you do not have pkg-config, you may have to use this:
+
+gcc -Wall pcredemo.c -I/usr/local/include -L/usr/local/lib \
+  -R/usr/local/lib -lpcre -o pcredemo
+
+Replace "/usr/local/include" and "/usr/local/lib" with wherever the include and
+library files for PCRE are installed on your system. Only some operating
+systems (e.g. Solaris) use the -R option.
+
+Building under Windows:
+
+If you want to statically link this program against a non-dll .a file, you must
+define PCRE_STATIC before including pcre.h, otherwise the pcre_malloc() and
+pcre_free() exported functions will be declared __declspec(dllimport), with
+unwanted results. So in this environment, uncomment the following line. */
+
+/* #define PCRE_STATIC */
+
+#include <stdio.h>
+#include <string.h>
+#include <pcre.h>
+
+#define OVECCOUNT 30    /* should be a multiple of 3 */
+
+
+int main(int argc, char **argv)
+{
+pcre *re;
+const char *error;
+char *pattern;
+char *subject;
+unsigned char *name_table;
+unsigned int option_bits;
+int erroffset;
+int find_all;
+int crlf_is_newline;
+int namecount;
+int name_entry_size;
+int ovector[OVECCOUNT];
+int subject_length;
+int rc, i;
+int utf8;
+
+
+/**************************************************************************
+* First, sort out the command line. There is only one possible option at  *
+* the moment, "-g" to request repeated matching to find all occurrences,  *
+* like Perl's /g option. We set the variable find_all to a non-zero value *
+* if the -g option is present. Apart from that, there must be exactly two *
+* arguments.                                                              *
+**************************************************************************/
+
+find_all = 0;
+for (i = 1; i < argc; i++)
+  {
+  if (strcmp(argv[i], "-g") == 0) find_all = 1;
+    else break;
+  }
+
+/* After the options, we require exactly two arguments, which are the pattern,
+and the subject string. */
+
+if (argc - i != 2)
+  {
+  printf("Two arguments required: a regex and a subject string\n");
+  return 1;
+  }
+
+pattern = argv[i];
+subject = argv[i+1];
+subject_length = (int)strlen(subject);
+
+
+/*************************************************************************
+* Now we are going to compile the regular expression pattern, and handle *
+* and errors that are detected.                                          *
+*************************************************************************/
+
+re = pcre_compile(
+  pattern,              /* the pattern */
+  0,                    /* default options */
+  &error,               /* for error message */
+  &erroffset,           /* for error offset */
+  NULL);                /* use default character tables */
+
+/* Compilation failed: print the error message and exit */
+
+if (re == NULL)
+  {
+  printf("PCRE compilation failed at offset %d: %s\n", erroffset, error);
+  return 1;
+  }
+
+
+/*************************************************************************
+* If the compilation succeeded, we call PCRE again, in order to do a     *
+* pattern match against the subject string. This does just ONE match. If *
+* further matching is needed, it will be done below.                     *
+*************************************************************************/
+
+rc = pcre_exec(
+  re,                   /* the compiled pattern */
+  NULL,                 /* no extra data - we didn't study the pattern */
+  subject,              /* the subject string */
+  subject_length,       /* the length of the subject */
+  0,                    /* start at offset 0 in the subject */
+  0,                    /* default options */
+  ovector,              /* output vector for substring information */
+  OVECCOUNT);           /* number of elements in the output vector */
+
+/* Matching failed: handle error cases */
+
+if (rc < 0)
+  {
+  switch(rc)
+    {
+    case PCRE_ERROR_NOMATCH: printf("No match\n"); break;
+    /*
+    Handle other special cases if you like
+    */
+    default: printf("Matching error %d\n", rc); break;
+    }
+  pcre_free(re);     /* Release memory used for the compiled pattern */
+  return 1;
+  }
+
+/* Match succeded */
+
+printf("\nMatch succeeded at offset %d\n", ovector[0]);
+
+
+/*************************************************************************
+* We have found the first match within the subject string. If the output *
+* vector wasn't big enough, say so. Then output any substrings that were *
+* captured.                                                              *
+*************************************************************************/
+
+/* The output vector wasn't big enough */
+
+if (rc == 0)
+  {
+  rc = OVECCOUNT/3;
+  printf("ovector only has room for %d captured substrings\n", rc - 1);
+  }
+
+/* Show substrings stored in the output vector by number. Obviously, in a real
+application you might want to do things other than print them. */
+
+for (i = 0; i < rc; i++)
+  {
+  char *substring_start = subject + ovector[2*i];
+  int substring_length = ovector[2*i+1] - ovector[2*i];
+  printf("%2d: %.*s\n", i, substring_length, substring_start);
+  }
+
+
+/**************************************************************************
+* That concludes the basic part of this demonstration program. We have    *
+* compiled a pattern, and performed a single match. The code that follows *
+* shows first how to access named substrings, and then how to code for    *
+* repeated matches on the same subject.                                   *
+**************************************************************************/
+
+/* See if there are any named substrings, and if so, show them by name. First
+we have to extract the count of named parentheses from the pattern. */
+
+(void)pcre_fullinfo(
+  re,                   /* the compiled pattern */
+  NULL,                 /* no extra data - we didn't study the pattern */
+  PCRE_INFO_NAMECOUNT,  /* number of named substrings */
+  &namecount);          /* where to put the answer */
+
+if (namecount <= 0) printf("No named substrings\n"); else
+  {
+  unsigned char *tabptr;
+  printf("Named substrings\n");
+
+  /* Before we can access the substrings, we must extract the table for
+  translating names to numbers, and the size of each entry in the table. */
+
+  (void)pcre_fullinfo(
+    re,                       /* the compiled pattern */
+    NULL,                     /* no extra data - we didn't study the pattern */
+    PCRE_INFO_NAMETABLE,      /* address of the table */
+    &name_table);             /* where to put the answer */
+
+  (void)pcre_fullinfo(
+    re,                       /* the compiled pattern */
+    NULL,                     /* no extra data - we didn't study the pattern */
+    PCRE_INFO_NAMEENTRYSIZE,  /* size of each entry in the table */
+    &name_entry_size);        /* where to put the answer */
+
+  /* Now we can scan the table and, for each entry, print the number, the name,
+  and the substring itself. */
+
+  tabptr = name_table;
+  for (i = 0; i < namecount; i++)
+    {
+    int n = (tabptr[0] << 8) | tabptr[1];
+    printf("(%d) %*s: %.*s\n", n, name_entry_size - 3, tabptr + 2,
+      ovector[2*n+1] - ovector[2*n], subject + ovector[2*n]);
+    tabptr += name_entry_size;
+    }
+  }
+
+
+/*************************************************************************
+* If the "-g" option was given on the command line, we want to continue  *
+* to search for additional matches in the subject string, in a similar   *
+* way to the /g option in Perl. This turns out to be trickier than you   *
+* might think because of the possibility of matching an empty string.    *
+* What happens is as follows:                                            *
+*                                                                        *
+* If the previous match was NOT for an empty string, we can just start   *
+* the next match at the end of the previous one.                         *
+*                                                                        *
+* If the previous match WAS for an empty string, we can't do that, as it *
+* would lead to an infinite loop. Instead, a special call of pcre_exec() *
+* is made with the PCRE_NOTEMPTY_ATSTART and PCRE_ANCHORED flags set.    *
+* The first of these tells PCRE that an empty string at the start of the *
+* subject is not a valid match; other possibilities must be tried. The   *
+* second flag restricts PCRE to one match attempt at the initial string  *
+* position. If this match succeeds, an alternative to the empty string   *
+* match has been found, and we can print it and proceed round the loop,  *
+* advancing by the length of whatever was found. If this match does not  *
+* succeed, we still stay in the loop, advancing by just one character.   *
+* In UTF-8 mode, which can be set by (*UTF8) in the pattern, this may be *
+* more than one byte.                                                    *
+*                                                                        *
+* However, there is a complication concerned with newlines. When the     *
+* newline convention is such that CRLF is a valid newline, we must       *
+* advance by two characters rather than one. The newline convention can  *
+* be set in the regex by (*CR), etc.; if not, we must find the default.  *
+*************************************************************************/
+
+if (!find_all)     /* Check for -g */
+  {
+  pcre_free(re);   /* Release the memory used for the compiled pattern */
+  return 0;        /* Finish unless -g was given */
+  }
+
+/* Before running the loop, check for UTF-8 and whether CRLF is a valid newline
+sequence. First, find the options with which the regex was compiled; extract
+the UTF-8 state, and mask off all but the newline options. */
+
+(void)pcre_fullinfo(re, NULL, PCRE_INFO_OPTIONS, &option_bits);
+utf8 = option_bits & PCRE_UTF8;
+option_bits &= PCRE_NEWLINE_CR|PCRE_NEWLINE_LF|PCRE_NEWLINE_CRLF|
+               PCRE_NEWLINE_ANY|PCRE_NEWLINE_ANYCRLF;
+
+/* If no newline options were set, find the default newline convention from the
+build configuration. */
+
+if (option_bits == 0)
+  {
+  int d;
+  (void)pcre_config(PCRE_CONFIG_NEWLINE, &d);
+  /* Note that these values are always the ASCII ones, even in
+  EBCDIC environments. CR = 13, NL = 10. */
+  option_bits = (d == 13)? PCRE_NEWLINE_CR :
+          (d == 10)? PCRE_NEWLINE_LF :
+          (d == (13<<8 | 10))? PCRE_NEWLINE_CRLF :
+          (d == -2)? PCRE_NEWLINE_ANYCRLF :
+          (d == -1)? PCRE_NEWLINE_ANY : 0;
+  }
+
+/* See if CRLF is a valid newline sequence. */
+
+crlf_is_newline =
+     option_bits == PCRE_NEWLINE_ANY ||
+     option_bits == PCRE_NEWLINE_CRLF ||
+     option_bits == PCRE_NEWLINE_ANYCRLF;
+
+/* Loop for second and subsequent matches */
+
+for (;;)
+  {
+  int options = 0;                 /* Normally no options */
+  int start_offset = ovector[1];   /* Start at end of previous match */
+
+  /* If the previous match was for an empty string, we are finished if we are
+  at the end of the subject. Otherwise, arrange to run another match at the
+  same point to see if a non-empty match can be found. */
+
+  if (ovector[0] == ovector[1])
+    {
+    if (ovector[0] == subject_length) break;
+    options = PCRE_NOTEMPTY_ATSTART | PCRE_ANCHORED;
+    }
+
+  /* Run the next matching operation */
+
+  rc = pcre_exec(
+    re,                   /* the compiled pattern */
+    NULL,                 /* no extra data - we didn't study the pattern */
+    subject,              /* the subject string */
+    subject_length,       /* the length of the subject */
+    start_offset,         /* starting offset in the subject */
+    options,              /* options */
+    ovector,              /* output vector for substring information */
+    OVECCOUNT);           /* number of elements in the output vector */
+
+  /* This time, a result of NOMATCH isn't an error. If the value in "options"
+  is zero, it just means we have found all possible matches, so the loop ends.
+  Otherwise, it means we have failed to find a non-empty-string match at a
+  point where there was a previous empty-string match. In this case, we do what
+  Perl does: advance the matching position by one character, and continue. We
+  do this by setting the "end of previous match" offset, because that is picked
+  up at the top of the loop as the point at which to start again.
+
+  There are two complications: (a) When CRLF is a valid newline sequence, and
+  the current position is just before it, advance by an extra byte. (b)
+  Otherwise we must ensure that we skip an entire UTF-8 character if we are in
+  UTF-8 mode. */
+
+  if (rc == PCRE_ERROR_NOMATCH)
+    {
+    if (options == 0) break;                    /* All matches found */
+    ovector[1] = start_offset + 1;              /* Advance one byte */
+    if (crlf_is_newline &&                      /* If CRLF is newline & */
+        start_offset < subject_length - 1 &&    /* we are at CRLF, */
+        subject[start_offset] == '\r' &&
+        subject[start_offset + 1] == '\n')
+      ovector[1] += 1;                          /* Advance by one more. */
+    else if (utf8)                              /* Otherwise, ensure we */
+      {                                         /* advance a whole UTF-8 */
+      while (ovector[1] < subject_length)       /* character. */
+        {
+        if ((subject[ovector[1]] & 0xc0) != 0x80) break;
+        ovector[1] += 1;
+        }
+      }
+    continue;    /* Go round the loop again */
+    }
+
+  /* Other matching errors are not recoverable. */
+
+  if (rc < 0)
+    {
+    printf("Matching error %d\n", rc);
+    pcre_free(re);    /* Release memory used for the compiled pattern */
+    return 1;
+    }
+
+  /* Match succeded */
+
+  printf("\nMatch succeeded again at offset %d\n", ovector[0]);
+
+  /* The match succeeded, but the output vector wasn't big enough. */
+
+  if (rc == 0)
+    {
+    rc = OVECCOUNT/3;
+    printf("ovector only has room for %d captured substrings\n", rc - 1);
+    }
+
+  /* As before, show substrings stored in the output vector by number, and then
+  also any named substrings. */
+
+  for (i = 0; i < rc; i++)
+    {
+    char *substring_start = subject + ovector[2*i];
+    int substring_length = ovector[2*i+1] - ovector[2*i];
+    printf("%2d: %.*s\n", i, substring_length, substring_start);
+    }
+
+  if (namecount <= 0) printf("No named substrings\n"); else
+    {
+    unsigned char *tabptr = name_table;
+    printf("Named substrings\n");
+    for (i = 0; i < namecount; i++)
+      {
+      int n = (tabptr[0] << 8) | tabptr[1];
+      printf("(%d) %*s: %.*s\n", n, name_entry_size - 3, tabptr + 2,
+        ovector[2*n+1] - ovector[2*n], subject + ovector[2*n]);
+      tabptr += name_entry_size;
+      }
+    }
+  }      /* End of loop to find second and subsequent matches */
+
+printf("\n");
+pcre_free(re);       /* Release memory used for the compiled pattern */
+return 0;
+}
+
+/* End of pcredemo.c */
diff --git a/ext/pcre/pcrelib/pcreposix.c b/ext/pcre/pcrelib/pcreposix.c
new file mode 100644
index 0000000..d45a15f
--- /dev/null
+++ b/ext/pcre/pcrelib/pcreposix.c
@@ -0,0 +1,414 @@
+/*************************************************
+*      Perl-Compatible Regular Expressions       *
+*************************************************/
+
+/* PCRE is a library of functions to support regular expressions whose syntax
+and semantics are as close as possible to those of the Perl 5 language.
+
+                       Written by Philip Hazel
+           Copyright (c) 1997-2012 University of Cambridge
+
+-----------------------------------------------------------------------------
+Redistribution and use in source and binary forms, with or without
+modification, are permitted provided that the following conditions are met:
+
+    * Redistributions of source code must retain the above copyright notice,
+      this list of conditions and the following disclaimer.
+
+    * Redistributions in binary form must reproduce the above copyright
+      notice, this list of conditions and the following disclaimer in the
+      documentation and/or other materials provided with the distribution.
+
+    * Neither the name of the University of Cambridge nor the names of its
+      contributors may be used to endorse or promote products derived from
+      this software without specific prior written permission.
+
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+POSSIBILITY OF SUCH DAMAGE.
+-----------------------------------------------------------------------------
+*/
+
+
+/* This module is a wrapper that provides a POSIX API to the underlying PCRE
+functions. */
+
+
+#include "config.h"
+
+
+/* Ensure that the PCREPOSIX_EXP_xxx macros are set appropriately for
+compiling these functions. This must come before including pcreposix.h, where
+they are set for an application (using these functions) if they have not
+previously been set. */
+
+#if defined(_WIN32) && !defined(PCRE_STATIC)
+#  define PCREPOSIX_EXP_DECL extern __declspec(dllexport)
+#  define PCREPOSIX_EXP_DEFN __declspec(dllexport)
+#endif
+
+/* We include pcre.h before pcre_internal.h so that the PCRE library functions
+are declared as "import" for Windows by defining PCRE_EXP_DECL as "import".
+This is needed even though pcre_internal.h itself includes pcre.h, because it
+does so after it has set PCRE_EXP_DECL to "export" if it is not already set. */
+
+#include "pcre.h"
+#include "pcre_internal.h"
+#include "pcreposix.h"
+
+
+/* Table to translate PCRE compile time error codes into POSIX error codes. */
+
+static const int eint[] = {
+  0,           /* no error */
+  REG_EESCAPE, /* \ at end of pattern */
+  REG_EESCAPE, /* \c at end of pattern */
+  REG_EESCAPE, /* unrecognized character follows \ */
+  REG_BADBR,   /* numbers out of order in {} quantifier */
+  /* 5 */
+  REG_BADBR,   /* number too big in {} quantifier */
+  REG_EBRACK,  /* missing terminating ] for character class */
+  REG_ECTYPE,  /* invalid escape sequence in character class */
+  REG_ERANGE,  /* range out of order in character class */
+  REG_BADRPT,  /* nothing to repeat */
+  /* 10 */
+  REG_BADRPT,  /* operand of unlimited repeat could match the empty string */
+  REG_ASSERT,  /* internal error: unexpected repeat */
+  REG_BADPAT,  /* unrecognized character after (? */
+  REG_BADPAT,  /* POSIX named classes are supported only within a class */
+  REG_EPAREN,  /* missing ) */
+  /* 15 */
+  REG_ESUBREG, /* reference to non-existent subpattern */
+  REG_INVARG,  /* erroffset passed as NULL */
+  REG_INVARG,  /* unknown option bit(s) set */
+  REG_EPAREN,  /* missing ) after comment */
+  REG_ESIZE,   /* parentheses nested too deeply */
+  /* 20 */
+  REG_ESIZE,   /* regular expression too large */
+  REG_ESPACE,  /* failed to get memory */
+  REG_EPAREN,  /* unmatched parentheses */
+  REG_ASSERT,  /* internal error: code overflow */
+  REG_BADPAT,  /* unrecognized character after (?< */
+  /* 25 */
+  REG_BADPAT,  /* lookbehind assertion is not fixed length */
+  REG_BADPAT,  /* malformed number or name after (?( */
+  REG_BADPAT,  /* conditional group contains more than two branches */
+  REG_BADPAT,  /* assertion expected after (?( */
+  REG_BADPAT,  /* (?R or (?[+-]digits must be followed by ) */
+  /* 30 */
+  REG_ECTYPE,  /* unknown POSIX class name */
+  REG_BADPAT,  /* POSIX collating elements are not supported */
+  REG_INVARG,  /* this version of PCRE is not compiled with PCRE_UTF8 support */
+  REG_BADPAT,  /* spare error */
+  REG_BADPAT,  /* character value in \x{...} sequence is too large */
+  /* 35 */
+  REG_BADPAT,  /* invalid condition (?(0) */
+  REG_BADPAT,  /* \C not allowed in lookbehind assertion */
+  REG_EESCAPE, /* PCRE does not support \L, \l, \N, \U, or \u */
+  REG_BADPAT,  /* number after (?C is > 255 */
+  REG_BADPAT,  /* closing ) for (?C expected */
+  /* 40 */
+  REG_BADPAT,  /* recursive call could loop indefinitely */
+  REG_BADPAT,  /* unrecognized character after (?P */
+  REG_BADPAT,  /* syntax error in subpattern name (missing terminator) */
+  REG_BADPAT,  /* two named subpatterns have the same name */
+  REG_BADPAT,  /* invalid UTF-8 string */
+  /* 45 */
+  REG_BADPAT,  /* support for \P, \p, and \X has not been compiled */
+  REG_BADPAT,  /* malformed \P or \p sequence */
+  REG_BADPAT,  /* unknown property name after \P or \p */
+  REG_BADPAT,  /* subpattern name is too long (maximum 32 characters) */
+  REG_BADPAT,  /* too many named subpatterns (maximum 10,000) */
+  /* 50 */
+  REG_BADPAT,  /* repeated subpattern is too long */
+  REG_BADPAT,  /* octal value is greater than \377 (not in UTF-8 mode) */
+  REG_BADPAT,  /* internal error: overran compiling workspace */
+  REG_BADPAT,  /* internal error: previously-checked referenced subpattern not found */
+  REG_BADPAT,  /* DEFINE group contains more than one branch */
+  /* 55 */
+  REG_BADPAT,  /* repeating a DEFINE group is not allowed */
+  REG_INVARG,  /* inconsistent NEWLINE options */
+  REG_BADPAT,  /* \g is not followed followed by an (optionally braced) non-zero number */
+  REG_BADPAT,  /* a numbered reference must not be zero */
+  REG_BADPAT,  /* an argument is not allowed for (*ACCEPT), (*FAIL), or (*COMMIT) */
+  /* 60 */
+  REG_BADPAT,  /* (*VERB) not recognized */
+  REG_BADPAT,  /* number is too big */
+  REG_BADPAT,  /* subpattern name expected */
+  REG_BADPAT,  /* digit expected after (?+ */
+  REG_BADPAT,  /* ] is an invalid data character in JavaScript compatibility mode */
+  /* 65 */
+  REG_BADPAT,  /* different names for subpatterns of the same number are not allowed */
+  REG_BADPAT,  /* (*MARK) must have an argument */
+  REG_INVARG,  /* this version of PCRE is not compiled with PCRE_UCP support */
+  REG_BADPAT,  /* \c must be followed by an ASCII character */
+  REG_BADPAT,  /* \k is not followed by a braced, angle-bracketed, or quoted name */
+  /* 70 */
+  REG_BADPAT,  /* internal error: unknown opcode in find_fixedlength() */
+  REG_BADPAT,  /* \N is not supported in a class */
+  REG_BADPAT,  /* too many forward references */
+  REG_BADPAT,  /* disallowed UTF-8/16 code point (>= 0xd800 && <= 0xdfff) */
+  REG_BADPAT,  /* invalid UTF-16 string (should not occur) */
+  /* 75 */
+  REG_BADPAT,  /* overlong MARK name */
+  REG_BADPAT   /* character value in \u.... sequence is too large */
+};
+
+/* Table of texts corresponding to POSIX error codes */
+
+static const char *const pstring[] = {
+  "",                                /* Dummy for value 0 */
+  "internal error",                  /* REG_ASSERT */
+  "invalid repeat counts in {}",     /* BADBR      */
+  "pattern error",                   /* BADPAT     */
+  "? * + invalid",                   /* BADRPT     */
+  "unbalanced {}",                   /* EBRACE     */
+  "unbalanced []",                   /* EBRACK     */
+  "collation error - not relevant",  /* ECOLLATE   */
+  "bad class",                       /* ECTYPE     */
+  "bad escape sequence",             /* EESCAPE    */
+  "empty expression",                /* EMPTY      */
+  "unbalanced ()",                   /* EPAREN     */
+  "bad range inside []",             /* ERANGE     */
+  "expression too big",              /* ESIZE      */
+  "failed to get memory",            /* ESPACE     */
+  "bad back reference",              /* ESUBREG    */
+  "bad argument",                    /* INVARG     */
+  "match failed"                     /* NOMATCH    */
+};
+
+
+
+
+/*************************************************
+*          Translate error code to string        *
+*************************************************/
+
+PCREPOSIX_EXP_DEFN size_t PCRE_CALL_CONVENTION
+regerror(int errcode, const regex_t *preg, char *errbuf, size_t errbuf_size)
+{
+const char *message, *addmessage;
+size_t length, addlength;
+
+message = (errcode >= (int)(sizeof(pstring)/sizeof(char *)))?
+  "unknown error code" : pstring[errcode];
+length = strlen(message) + 1;
+
+addmessage = " at offset ";
+addlength = (preg != NULL && (int)preg->re_erroffset != -1)?
+  strlen(addmessage) + 6 : 0;
+
+if (errbuf_size > 0)
+  {
+  if (addlength > 0 && errbuf_size >= length + addlength)
+    sprintf(errbuf, "%s%s%-6d", message, addmessage, (int)preg->re_erroffset);
+  else
+    {
+    strncpy(errbuf, message, errbuf_size - 1);
+    errbuf[errbuf_size-1] = 0;
+    }
+  }
+
+return length + addlength;
+}
+
+
+
+
+/*************************************************
+*           Free store held by a regex           *
+*************************************************/
+
+PCREPOSIX_EXP_DEFN void PCRE_CALL_CONVENTION
+regfree(regex_t *preg)
+{
+(PUBL(free))(preg->re_pcre);
+}
+
+
+
+
+/*************************************************
+*            Compile a regular expression        *
+*************************************************/
+
+/*
+Arguments:
+  preg        points to a structure for recording the compiled expression
+  pattern     the pattern to compile
+  cflags      compilation flags
+
+Returns:      0 on success
+              various non-zero codes on failure
+*/
+
+PCREPOSIX_EXP_DEFN int PCRE_CALL_CONVENTION
+regcomp(regex_t *preg, const char *pattern, int cflags)
+{
+const char *errorptr;
+int erroffset;
+int errorcode;
+int options = 0;
+
+if ((cflags & REG_ICASE) != 0)    options |= PCRE_CASELESS;
+if ((cflags & REG_NEWLINE) != 0)  options |= PCRE_MULTILINE;
+if ((cflags & REG_DOTALL) != 0)   options |= PCRE_DOTALL;
+if ((cflags & REG_NOSUB) != 0)    options |= PCRE_NO_AUTO_CAPTURE;
+if ((cflags & REG_UTF8) != 0)     options |= PCRE_UTF8;
+if ((cflags & REG_UCP) != 0)      options |= PCRE_UCP;
+if ((cflags & REG_UNGREEDY) != 0) options |= PCRE_UNGREEDY;
+
+preg->re_pcre = pcre_compile2(pattern, options, &errorcode, &errorptr,
+  &erroffset, NULL);
+preg->re_erroffset = erroffset;
+
+/* Safety: if the error code is too big for the translation vector (which
+should not happen, but we all make mistakes), return REG_BADPAT. */
+
+if (preg->re_pcre == NULL)
+  {
+  return (errorcode < (int)(sizeof(eint)/sizeof(const int)))?
+    eint[errorcode] : REG_BADPAT;
+  }
+
+(void)pcre_fullinfo((const pcre *)preg->re_pcre, NULL, PCRE_INFO_CAPTURECOUNT,
+  &(preg->re_nsub));
+return 0;
+}
+
+
+
+
+/*************************************************
+*              Match a regular expression        *
+*************************************************/
+
+/* Unfortunately, PCRE requires 3 ints of working space for each captured
+substring, so we have to get and release working store instead of just using
+the POSIX structures as was done in earlier releases when PCRE needed only 2
+ints. However, if the number of possible capturing brackets is small, use a
+block of store on the stack, to reduce the use of malloc/free. The threshold is
+in a macro that can be changed at configure time.
+
+If REG_NOSUB was specified at compile time, the PCRE_NO_AUTO_CAPTURE flag will
+be set. When this is the case, the nmatch and pmatch arguments are ignored, and
+the only result is yes/no/error. */
+
+PCREPOSIX_EXP_DEFN int PCRE_CALL_CONVENTION
+regexec(const regex_t *preg, const char *string, size_t nmatch,
+  regmatch_t pmatch[], int eflags)
+{
+int rc, so, eo;
+int options = 0;
+int *ovector = NULL;
+int small_ovector[POSIX_MALLOC_THRESHOLD * 3];
+BOOL allocated_ovector = FALSE;
+BOOL nosub =
+  (((const pcre *)preg->re_pcre)->options & PCRE_NO_AUTO_CAPTURE) != 0;
+
+if ((eflags & REG_NOTBOL) != 0) options |= PCRE_NOTBOL;
+if ((eflags & REG_NOTEOL) != 0) options |= PCRE_NOTEOL;
+if ((eflags & REG_NOTEMPTY) != 0) options |= PCRE_NOTEMPTY;
+
+((regex_t *)preg)->re_erroffset = (size_t)(-1);  /* Only has meaning after compile */
+
+/* When no string data is being returned, or no vector has been passed in which
+to put it, ensure that nmatch is zero. Otherwise, ensure the vector for holding
+the return data is large enough. */
+
+if (nosub || pmatch == NULL) nmatch = 0;
+
+else if (nmatch > 0)
+  {
+  if (nmatch <= POSIX_MALLOC_THRESHOLD)
+    {
+    ovector = &(small_ovector[0]);
+    }
+  else
+    {
+    if (nmatch > INT_MAX/(sizeof(int) * 3)) return REG_ESPACE;
+    ovector = (int *)malloc(sizeof(int) * nmatch * 3);
+    if (ovector == NULL) return REG_ESPACE;
+    allocated_ovector = TRUE;
+    }
+  }
+
+/* REG_STARTEND is a BSD extension, to allow for non-NUL-terminated strings.
+The man page from OS X says "REG_STARTEND affects only the location of the
+string, not how it is matched". That is why the "so" value is used to bump the
+start location rather than being passed as a PCRE "starting offset". */
+
+if ((eflags & REG_STARTEND) != 0)
+  {
+  so = pmatch[0].rm_so;
+  eo = pmatch[0].rm_eo;
+  }
+else
+  {
+  so = 0;
+  eo = (int)strlen(string);
+  }
+
+rc = pcre_exec((const pcre *)preg->re_pcre, NULL, string + so, (eo - so),
+  0, options, ovector, (int)(nmatch * 3));
+
+if (rc == 0) rc = (int)nmatch;    /* All captured slots were filled in */
+
+/* Successful match */
+
+if (rc >= 0)
+  {
+  size_t i;
+  if (!nosub)
+    {
+    for (i = 0; i < (size_t)rc; i++)
+      {
+      pmatch[i].rm_so = ovector[i*2];
+      pmatch[i].rm_eo = ovector[i*2+1];
+      }
+    if (allocated_ovector) free(ovector);
+    for (; i < nmatch; i++) pmatch[i].rm_so = pmatch[i].rm_eo = -1;
+    }
+  return 0;
+  }
+
+/* Unsuccessful match */
+
+if (allocated_ovector) free(ovector);
+switch(rc)
+  {
+/* ========================================================================== */
+  /* These cases are never obeyed. This is a fudge that causes a compile-time
+  error if the vector eint, which is indexed by compile-time error number, is
+  not the correct length. It seems to be the only way to do such a check at
+  compile time, as the sizeof() operator does not work in the C preprocessor.
+  As all the PCRE_ERROR_xxx values are negative, we can use 0 and 1. */
+
+  case 0:
+  case (sizeof(eint)/sizeof(int) == ERRCOUNT):
+  return REG_ASSERT;
+/* ========================================================================== */
+
+  case PCRE_ERROR_NOMATCH: return REG_NOMATCH;
+  case PCRE_ERROR_NULL: return REG_INVARG;
+  case PCRE_ERROR_BADOPTION: return REG_INVARG;
+  case PCRE_ERROR_BADMAGIC: return REG_INVARG;
+  case PCRE_ERROR_UNKNOWN_NODE: return REG_ASSERT;
+  case PCRE_ERROR_NOMEMORY: return REG_ESPACE;
+  case PCRE_ERROR_MATCHLIMIT: return REG_ESPACE;
+  case PCRE_ERROR_BADUTF8: return REG_INVARG;
+  case PCRE_ERROR_BADUTF8_OFFSET: return REG_INVARG;
+  case PCRE_ERROR_BADMODE: return REG_INVARG;
+  default: return REG_ASSERT;
+  }
+}
+
+/* End of pcreposix.c */
diff --git a/ext/pcre/pcrelib/pcreposix.h b/ext/pcre/pcrelib/pcreposix.h
new file mode 100644
index 0000000..c77c0b0
--- /dev/null
+++ b/ext/pcre/pcrelib/pcreposix.h
@@ -0,0 +1,146 @@
+/*************************************************
+*       Perl-Compatible Regular Expressions      *
+*************************************************/
+
+#ifndef _PCREPOSIX_H
+#define _PCREPOSIX_H
+
+/* This is the header for the POSIX wrapper interface to the PCRE Perl-
+Compatible Regular Expression library. It defines the things POSIX says should
+be there. I hope.
+
+            Copyright (c) 1997-2012 University of Cambridge
+
+-----------------------------------------------------------------------------
+Redistribution and use in source and binary forms, with or without
+modification, are permitted provided that the following conditions are met:
+
+    * Redistributions of source code must retain the above copyright notice,
+      this list of conditions and the following disclaimer.
+
+    * Redistributions in binary form must reproduce the above copyright
+      notice, this list of conditions and the following disclaimer in the
+      documentation and/or other materials provided with the distribution.
+
+    * Neither the name of the University of Cambridge nor the names of its
+      contributors may be used to endorse or promote products derived from
+      this software without specific prior written permission.
+
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+POSSIBILITY OF SUCH DAMAGE.
+-----------------------------------------------------------------------------
+*/
+
+/* Have to include stdlib.h in order to ensure that size_t is defined. */
+
+#include <stdlib.h>
+
+/* Allow for C++ users */
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+/* Options, mostly defined by POSIX, but with some extras. */
+
+#define REG_ICASE     0x0001   /* Maps to PCRE_CASELESS */
+#define REG_NEWLINE   0x0002   /* Maps to PCRE_MULTILINE */
+#define REG_NOTBOL    0x0004   /* Maps to PCRE_NOTBOL */
+#define REG_NOTEOL    0x0008   /* Maps to PCRE_NOTEOL */
+#define REG_DOTALL    0x0010   /* NOT defined by POSIX; maps to PCRE_DOTALL */
+#define REG_NOSUB     0x0020   /* Maps to PCRE_NO_AUTO_CAPTURE */
+#define REG_UTF8      0x0040   /* NOT defined by POSIX; maps to PCRE_UTF8 */
+#define REG_STARTEND  0x0080   /* BSD feature: pass subject string by so,eo */
+#define REG_NOTEMPTY  0x0100   /* NOT defined by POSIX; maps to PCRE_NOTEMPTY */
+#define REG_UNGREEDY  0x0200   /* NOT defined by POSIX; maps to PCRE_UNGREEDY */
+#define REG_UCP       0x0400   /* NOT defined by POSIX; maps to PCRE_UCP */
+
+/* This is not used by PCRE, but by defining it we make it easier
+to slot PCRE into existing programs that make POSIX calls. */
+
+#define REG_EXTENDED  0
+
+/* Error values. Not all these are relevant or used by the wrapper. */
+
+enum {
+  REG_ASSERT = 1,  /* internal error ? */
+  REG_BADBR,       /* invalid repeat counts in {} */
+  REG_BADPAT,      /* pattern error */
+  REG_BADRPT,      /* ? * + invalid */
+  REG_EBRACE,      /* unbalanced {} */
+  REG_EBRACK,      /* unbalanced [] */
+  REG_ECOLLATE,    /* collation error - not relevant */
+  REG_ECTYPE,      /* bad class */
+  REG_EESCAPE,     /* bad escape sequence */
+  REG_EMPTY,       /* empty expression */
+  REG_EPAREN,      /* unbalanced () */
+  REG_ERANGE,      /* bad range inside [] */
+  REG_ESIZE,       /* expression too big */
+  REG_ESPACE,      /* failed to get memory */
+  REG_ESUBREG,     /* bad back reference */
+  REG_INVARG,      /* bad argument */
+  REG_NOMATCH      /* match failed */
+};
+
+
+/* The structure representing a compiled regular expression. */
+
+typedef struct {
+  void *re_pcre;
+  size_t re_nsub;
+  size_t re_erroffset;
+} regex_t;
+
+/* The structure in which a captured offset is returned. */
+
+typedef int regoff_t;
+
+typedef struct {
+  regoff_t rm_so;
+  regoff_t rm_eo;
+} regmatch_t;
+
+/* When an application links to a PCRE DLL in Windows, the symbols that are
+imported have to be identified as such. When building PCRE, the appropriate
+export settings are needed, and are set in pcreposix.c before including this
+file. */
+
+#if defined(_WIN32) && !defined(PCRE_STATIC) && !defined(PCREPOSIX_EXP_DECL)
+#  define PCREPOSIX_EXP_DECL  extern __declspec(dllimport)
+#  define PCREPOSIX_EXP_DEFN  __declspec(dllimport)
+#endif
+
+/* By default, we use the standard "extern" declarations. */
+
+#ifndef PCREPOSIX_EXP_DECL
+#  ifdef __cplusplus
+#    define PCREPOSIX_EXP_DECL  extern "C"
+#    define PCREPOSIX_EXP_DEFN  extern "C"
+#  else
+#    define PCREPOSIX_EXP_DECL  extern
+#    define PCREPOSIX_EXP_DEFN  extern
+#  endif
+#endif
+
+/* The functions */
+
+PCREPOSIX_EXP_DECL int regcomp(regex_t *, const char *, int);
+PCREPOSIX_EXP_DECL int regexec(const regex_t *, const char *, size_t,
+                     regmatch_t *, int);
+PCREPOSIX_EXP_DECL size_t regerror(int, const regex_t *, char *, size_t);
+PCREPOSIX_EXP_DECL void regfree(regex_t *);
+
+#ifdef __cplusplus
+}   /* extern "C" */
+#endif
+
+#endif /* End of pcreposix.h */
diff --git a/ext/pcre/pcrelib/testdata/grepinput b/ext/pcre/pcrelib/testdata/grepinput
new file mode 100644
index 0000000..0f00edd
--- /dev/null
+++ b/ext/pcre/pcrelib/testdata/grepinput
@@ -0,0 +1,611 @@
+This is a file of miscellaneous text that is used as test data for checking
+that the pcregrep command is working correctly. The file must be more than 24K
+long so that it needs more than a single read() call to process it. New
+features should be added at the end, because some of the tests involve the
+output of line numbers, and we don't want these to change.
+
+PATTERN at the start of a line.
+In the middle of a line, PATTERN appears.
+
+This pattern is in lower case.
+
+Here follows a whole lot of stuff that makes the file over 24K long.
+
+-------------------------------------------------------------------------------
+The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the
+lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox
+jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick
+brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog.
+
+The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the
+lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox
+jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick
+brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog.
+
+The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the
+lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox
+jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick
+brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog.
+
+The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the
+lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox
+jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick
+brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog.
+
+The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the
+lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox
+jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick
+brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog.
+
+The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the
+lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox
+jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick
+brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog.
+
+The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the
+lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox
+jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick
+brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog.
+
+The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the
+lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox
+jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick
+brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog.
+
+The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the
+lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox
+jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick
+brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog.
+
+The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the
+lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox
+jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick
+brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog.
+
+The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the
+lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox
+jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick
+brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog.
+
+The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the
+lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox
+jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick
+brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog.
+
+The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the
+lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox
+jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick
+brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog.
+
+The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the
+lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox
+jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick
+brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog.
+
+The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the
+lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox
+jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick
+brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog.
+
+The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the
+lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox
+jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick
+brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog.
+
+The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the
+lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox
+jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick
+brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog.
+
+The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the
+lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox
+jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick
+brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog.
+
+The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the
+lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox
+jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick
+brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog.
+
+The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the
+lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox
+jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick
+brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog.
+
+The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the
+lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox
+jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick
+brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog.
+
+The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the
+lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox
+jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick
+brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog.
+
+The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the
+lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox
+jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick
+brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog.
+
+The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the
+lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox
+jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick
+brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog.
+
+The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the
+lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox
+jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick
+brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog.
+
+The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the
+lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox
+jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick
+brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog.
+
+The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the
+lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox
+jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick
+brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog.
+
+The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the
+lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox
+jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick
+brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog.
+
+The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the
+lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox
+jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick
+brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog.
+
+The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the
+lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox
+jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick
+brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog.
+
+The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the
+lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox
+jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick
+brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog.
+
+The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the
+lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox
+jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick
+brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog.
+
+The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the
+lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox
+jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick
+brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog.
+
+The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the
+lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox
+jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick
+brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog.
+
+The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the
+lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox
+jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick
+brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog.
+
+The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the
+lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox
+jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick
+brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog.
+
+The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the
+lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox
+jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick
+brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog.
+
+The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the
+lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox
+jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick
+brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog.
+
+The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the
+lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox
+jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick
+brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog.
+
+The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the
+lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox
+jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick
+brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog.
+
+The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the
+lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox
+jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick
+brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog.
+
+The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the
+lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox
+jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick
+brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog.
+
+The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the
+lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox
+jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick
+brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog.
+
+The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the
+lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox
+jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick
+brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog.
+
+The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the
+lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox
+jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick
+brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog.
+
+The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the
+lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox
+jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick
+brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog.
+
+The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the
+lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox
+jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick
+brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog.
+
+The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the
+lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox
+jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick
+brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog.
+
+The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the
+lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox
+jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick
+brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog.
+
+The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the
+lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox
+jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick
+brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog.
+
+The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the
+lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox
+jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick
+brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog.
+
+The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the
+lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox
+jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick
+brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog.
+
+The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the
+lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox
+jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick
+brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog.
+
+The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the
+lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox
+jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick
+brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog.
+
+The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the
+lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox
+jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick
+brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog.
+
+The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the
+lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox
+jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick
+brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog.
+
+The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the
+lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox
+jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick
+brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog.
+
+The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the
+lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox
+jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick
+brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog.
+
+The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the
+lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox
+jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick
+brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog.
+
+The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the
+lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox
+jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick
+brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog.
+
+The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the
+lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox
+jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick
+brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog.
+
+The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the
+lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox
+jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick
+brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog.
+
+The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the
+lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox
+jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick
+brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog.
+
+The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the
+lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox
+jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick
+brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog.
+
+The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the
+lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox
+jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick
+brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog.
+
+The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the
+lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox
+jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick
+brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog.
+
+The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the
+lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox
+jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick
+brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog.
+
+The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the
+lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox
+jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick
+brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog.
+
+The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the
+lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox
+jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick
+brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog.
+
+The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the
+lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox
+jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick
+brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog.
+
+The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the
+lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox
+jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick
+brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog.
+
+The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the
+lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox
+jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick
+brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog.
+
+The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the
+lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox
+jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick
+brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog.
+
+The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the
+lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox
+jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick
+brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog.
+
+The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the
+lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox
+jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick
+brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog.
+
+The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the
+lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox
+jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick
+brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog.
+
+The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the
+lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox
+jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick
+brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog.
+
+The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the
+lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox
+jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick
+brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog.
+
+The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the
+lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox
+jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick
+brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog.
+
+The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the
+lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox
+jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick
+brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog.
+
+The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the
+lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox
+jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick
+brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog.
+
+The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the
+lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox
+jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick
+brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog.
+
+The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the
+lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox
+jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick
+brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog.
+
+The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the
+lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox
+jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick
+brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog.
+
+The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the
+lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox
+jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick
+brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog.
+
+The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the
+lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox
+jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick
+brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog.
+
+The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the
+lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox
+jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick
+brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog.
+
+The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the
+lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox
+jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick
+brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog.
+
+The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the
+lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox
+jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick
+brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog.
+
+The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the
+lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox
+jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick
+brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog.
+
+The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the
+lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox
+jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick
+brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog.
+
+The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the
+lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox
+jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick
+brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog.
+
+The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the
+lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox
+jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick
+brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog.
+
+The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the
+lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox
+jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick
+brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog.
+
+The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the
+lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox
+jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick
+brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog.
+
+The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the
+lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox
+jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick
+brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog.
+
+The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the
+lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox
+jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick
+brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog.
+
+The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the
+lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox
+jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick
+brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog.
+
+The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the
+lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox
+jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick
+brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog.
+
+The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the
+lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox
+jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick
+brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog.
+
+The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the
+lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox
+jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick
+brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog.
+
+The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the
+lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox
+jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick
+brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog.
+
+The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the
+lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox
+jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick
+brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog.
+
+The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the
+lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox
+jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick
+brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog.
+
+The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the
+lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox
+jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick
+brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog.
+
+The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the
+lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox
+jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick
+brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog.
+
+The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the
+lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox
+jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick
+brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog.
+
+The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the
+lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox
+jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick
+brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog.
+
+The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the
+lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox
+jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick
+brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog.
+
+The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the
+lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox
+jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick
+brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog.
+
+The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the
+lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox
+jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick
+brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog.
+
+The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the
+lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox
+jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick
+brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog.
+
+The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the
+lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox
+jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick
+brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog.
+
+The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the
+lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox
+jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick
+brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog.
+-------------------------------------------------------------------------------
+
+aaaaa0
+aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+bbbbbb
+cccccccccccccccccccccccccccccccccccccccccc
+aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+eeeee
+aaaaa2
+ffffffffff
+
+This is a line before the binary zero.
+This line contains a binary zero here >
+This is a line after the binary zero.
+
+ABOVE the elephant 
+ABOVE
+ABOVE theatre
+AB.VE
+AB.VE the turtle
+
+010203040506
+
+PUT NEW DATA ABOVE THIS LINE.
+=============================
+
+Check up on PATTERN near the end.
+This is the last line of this file.
diff --git a/ext/pcre/pcrelib/testdata/grepinput8 b/ext/pcre/pcrelib/testdata/grepinput8
new file mode 100644
index 0000000..7163aa6
--- /dev/null
+++ b/ext/pcre/pcrelib/testdata/grepinput8
@@ -0,0 +1,11 @@
+X one
+X twoX threeX four
X five
+X six
+X seven…X eight
X nine
X ten
+
+Before 111
+Before 222
Before 333…Match
+After 111
+After 222
After 333
+And so on and so on
+And so on and so on
diff --git a/ext/pcre/pcrelib/testdata/grepinputx b/ext/pcre/pcrelib/testdata/grepinputx
new file mode 100644
index 0000000..730cc8a
--- /dev/null
+++ b/ext/pcre/pcrelib/testdata/grepinputx
@@ -0,0 +1,43 @@
+This is a second file of input for the pcregrep tests.
+
+Here is the pattern again.
+
+Pattern
+That time it was on a line by itself.
+
+To pat or not to pat, that is the question.
+
+complete pair
+of lines
+
+That was a complete pair
+of lines all by themselves.
+
+complete pair
+of lines
+
+And there they were again, to check line numbers.
+
+one
+two
+three
+four
+five
+six
+seven
+eight
+nine
+ten
+eleven
+twelve
+thirteen
+fourteen
+fifteen
+sixteen
+seventeen
+eighteen
+nineteen
+twenty
+
+This line contains pattern not on a line by itself.
+This is the last line of this file.
diff --git a/ext/pcre/pcrelib/testdata/greplist b/ext/pcre/pcrelib/testdata/greplist
new file mode 100644
index 0000000..1434ae9
--- /dev/null
+++ b/ext/pcre/pcrelib/testdata/greplist
@@ -0,0 +1,7 @@
+This is a file of patterns for testing the -f option. Don't include any blank
+lines because they will match everything! This is no longer true, so have one.
+
+pattern
+line by itself
+
+End of the list of patterns.
diff --git a/ext/pcre/pcrelib/testdata/grepoutput b/ext/pcre/pcrelib/testdata/grepoutput
new file mode 100644
index 0000000..e9072bc
--- /dev/null
+++ b/ext/pcre/pcrelib/testdata/grepoutput
@@ -0,0 +1,670 @@
+---------------------------- Test 1 ------------------------------
+PATTERN at the start of a line.
+In the middle of a line, PATTERN appears.
+Check up on PATTERN near the end.
+RC=0
+---------------------------- Test 2 ------------------------------
+PATTERN at the start of a line.
+RC=0
+---------------------------- Test 3 ------------------------------
+7:PATTERN at the start of a line.
+8:In the middle of a line, PATTERN appears.
+10:This pattern is in lower case.
+610:Check up on PATTERN near the end.
+RC=0
+---------------------------- Test 4 ------------------------------
+4
+RC=0
+---------------------------- Test 5 ------------------------------
+./testdata/grepinput:7:PATTERN at the start of a line.
+./testdata/grepinput:8:In the middle of a line, PATTERN appears.
+./testdata/grepinput:10:This pattern is in lower case.
+./testdata/grepinput:610:Check up on PATTERN near the end.
+./testdata/grepinputx:3:Here is the pattern again.
+./testdata/grepinputx:5:Pattern
+./testdata/grepinputx:42:This line contains pattern not on a line by itself.
+RC=0
+---------------------------- Test 6 ------------------------------
+7:PATTERN at the start of a line.
+8:In the middle of a line, PATTERN appears.
+10:This pattern is in lower case.
+610:Check up on PATTERN near the end.
+3:Here is the pattern again.
+5:Pattern
+42:This line contains pattern not on a line by itself.
+RC=0
+---------------------------- Test 7 ------------------------------
+./testdata/grepinput
+./testdata/grepinputx
+RC=0
+---------------------------- Test 8 ------------------------------
+./testdata/grepinput
+RC=0
+---------------------------- Test 9 ------------------------------
+RC=0
+---------------------------- Test 10 -----------------------------
+RC=1
+---------------------------- Test 11 -----------------------------
+1:This is a second file of input for the pcregrep tests.
+2:
+4:
+5:Pattern
+6:That time it was on a line by itself.
+7:
+8:To pat or not to pat, that is the question.
+9:
+10:complete pair
+11:of lines
+12:
+13:That was a complete pair
+14:of lines all by themselves.
+15:
+16:complete pair
+17:of lines
+18:
+19:And there they were again, to check line numbers.
+20:
+21:one
+22:two
+23:three
+24:four
+25:five
+26:six
+27:seven
+28:eight
+29:nine
+30:ten
+31:eleven
+32:twelve
+33:thirteen
+34:fourteen
+35:fifteen
+36:sixteen
+37:seventeen
+38:eighteen
+39:nineteen
+40:twenty
+41:
+43:This is the last line of this file.
+RC=0
+---------------------------- Test 12 -----------------------------
+Pattern
+RC=0
+---------------------------- Test 13 -----------------------------
+Here is the pattern again.
+That time it was on a line by itself.
+This line contains pattern not on a line by itself.
+RC=0
+---------------------------- Test 14 -----------------------------
+./testdata/grepinputx:To pat or not to pat, that is the question.
+RC=0
+---------------------------- Test 15 -----------------------------
+pcregrep: Error in command-line regex at offset 4: nothing to repeat
+RC=2
+---------------------------- Test 16 -----------------------------
+pcregrep: Failed to open ./testdata/nonexistfile: No such file or directory
+RC=2
+---------------------------- Test 17 -----------------------------
+features should be added at the end, because some of the tests involve the
+output of line numbers, and we don't want these to change.
+RC=0
+---------------------------- Test 18 -----------------------------
+4:features should be added at the end, because some of the tests involve the
+output of line numbers, and we don't want these to change.
+583:brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog.
+-------------------------------------------------------------------------------
+RC=0
+---------------------------- Test 19 -----------------------------
+Pattern
+RC=0
+---------------------------- Test 20 -----------------------------
+10:complete pair
+of lines
+16:complete pair
+of lines
+RC=0
+---------------------------- Test 21 -----------------------------
+24:four
+25-five
+26-six
+27-seven
+--
+34:fourteen
+35-fifteen
+36-sixteen
+37-seventeen
+RC=0
+---------------------------- Test 22 -----------------------------
+21-one
+22-two
+23-three
+24:four
+--
+31-eleven
+32-twelve
+33-thirteen
+34:fourteen
+RC=0
+---------------------------- Test 23 -----------------------------
+one
+two
+three
+four
+five
+six
+seven
+--
+eleven
+twelve
+thirteen
+fourteen
+fifteen
+sixteen
+seventeen
+RC=0
+---------------------------- Test 24 -----------------------------
+four
+five
+six
+seven
+eight
+nine
+ten
+eleven
+twelve
+thirteen
+fourteen
+fifteen
+sixteen
+seventeen
+eighteen
+nineteen
+twenty
+
+This line contains pattern not on a line by itself.
+This is the last line of this file.
+RC=0
+---------------------------- Test 25 -----------------------------
+15-
+16-complete pair
+17-of lines
+18-
+19-And there they were again, to check line numbers.
+20-
+21-one
+22-two
+23-three
+24:four
+25-five
+26-six
+27-seven
+28-eight
+29-nine
+30-ten
+31-eleven
+32-twelve
+33-thirteen
+34:fourteen
+RC=0
+---------------------------- Test 26 -----------------------------
+
+complete pair
+of lines
+
+And there they were again, to check line numbers.
+
+one
+two
+three
+four
+five
+six
+seven
+eight
+nine
+ten
+eleven
+twelve
+thirteen
+fourteen
+fifteen
+sixteen
+seventeen
+eighteen
+nineteen
+twenty
+
+This line contains pattern not on a line by itself.
+This is the last line of this file.
+RC=0
+---------------------------- Test 27 -----------------------------
+four
+five
+six
+seven
+eight
+nine
+ten
+eleven
+twelve
+thirteen
+fourteen
+fifteen
+sixteen
+seventeen
+eighteen
+nineteen
+twenty
+
+This line contains pattern not on a line by itself.
+This is the last line of this file.
+RC=0
+---------------------------- Test 28 -----------------------------
+14-of lines all by themselves.
+15-
+16-complete pair
+17-of lines
+18-
+19-And there they were again, to check line numbers.
+20-
+21-one
+22-two
+23-three
+24:four
+25-five
+26-six
+27-seven
+28-eight
+29-nine
+30-ten
+31-eleven
+32-twelve
+33-thirteen
+34:fourteen
+RC=0
+---------------------------- Test 29 -----------------------------
+of lines all by themselves.
+
+complete pair
+of lines
+
+And there they were again, to check line numbers.
+
+one
+two
+three
+four
+five
+six
+seven
+eight
+nine
+ten
+eleven
+twelve
+thirteen
+fourteen
+fifteen
+sixteen
+seventeen
+eighteen
+nineteen
+twenty
+
+This line contains pattern not on a line by itself.
+This is the last line of this file.
+RC=0
+---------------------------- Test 30 -----------------------------
+./testdata/grepinput-4-features should be added at the end, because some of the tests involve the
+./testdata/grepinput-5-output of line numbers, and we don't want these to change.
+./testdata/grepinput-6-
+./testdata/grepinput:7:PATTERN at the start of a line.
+./testdata/grepinput:8:In the middle of a line, PATTERN appears.
+./testdata/grepinput-9-
+./testdata/grepinput:10:This pattern is in lower case.
+--
+./testdata/grepinput-607-PUT NEW DATA ABOVE THIS LINE.
+./testdata/grepinput-608-=============================
+./testdata/grepinput-609-
+./testdata/grepinput:610:Check up on PATTERN near the end.
+--
+./testdata/grepinputx-1-This is a second file of input for the pcregrep tests.
+./testdata/grepinputx-2-
+./testdata/grepinputx:3:Here is the pattern again.
+./testdata/grepinputx-4-
+./testdata/grepinputx:5:Pattern
+--
+./testdata/grepinputx-39-nineteen
+./testdata/grepinputx-40-twenty
+./testdata/grepinputx-41-
+./testdata/grepinputx:42:This line contains pattern not on a line by itself.
+RC=0
+---------------------------- Test 31 -----------------------------
+./testdata/grepinput:7:PATTERN at the start of a line.
+./testdata/grepinput:8:In the middle of a line, PATTERN appears.
+./testdata/grepinput-9-
+./testdata/grepinput:10:This pattern is in lower case.
+./testdata/grepinput-11-
+./testdata/grepinput-12-Here follows a whole lot of stuff that makes the file over 24K long.
+./testdata/grepinput-13-
+--
+./testdata/grepinput:610:Check up on PATTERN near the end.
+./testdata/grepinput-611-This is the last line of this file.
+--
+./testdata/grepinputx:3:Here is the pattern again.
+./testdata/grepinputx-4-
+./testdata/grepinputx:5:Pattern
+./testdata/grepinputx-6-That time it was on a line by itself.
+./testdata/grepinputx-7-
+./testdata/grepinputx-8-To pat or not to pat, that is the question.
+--
+./testdata/grepinputx:42:This line contains pattern not on a line by itself.
+./testdata/grepinputx-43-This is the last line of this file.
+RC=0
+---------------------------- Test 32 -----------------------------
+./testdata/grepinputx
+RC=0
+---------------------------- Test 33 -----------------------------
+pcregrep: Failed to open ./testdata/grepnonexist: No such file or directory
+RC=2
+---------------------------- Test 34 -----------------------------
+RC=2
+---------------------------- Test 35 -----------------------------
+./testdata/grepinputx
+RC=0
+---------------------------- Test 36 -----------------------------
+./testdata/grepinput3
+./testdata/grepinput8
+./testdata/grepinputx
+RC=0
+---------------------------- Test 37 -----------------------------
+aaaaa0
+aaaaa2
+010203040506
+RC=0
+======== STDERR ========
+pcregrep: pcre_exec() gave error -8 while matching this text:
+
+aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+
+pcregrep: pcre_exec() gave error -8 while matching this text:
+
+aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+
+pcregrep: Error -8, -21 or -27 means that a resource limit was exceeded.
+pcregrep: Check your regex for nested unlimited loops.
+---------------------------- Test 38 ------------------------------
+This line contains a binary zero here >
+RC=0
+---------------------------- Test 39 ------------------------------
+This is a line before the binary zero.
+This line contains a binary zero here >
+RC=0
+---------------------------- Test 40 ------------------------------
+This line contains a binary zero here >
+This is a line after the binary zero.
+RC=0
+---------------------------- Test 41 ------------------------------
+before the binary zero
+after the binary zero
+RC=0
+---------------------------- Test 42 ------------------------------
+./testdata/grepinput:595:before the binary zero
+./testdata/grepinput:597:after the binary zero
+RC=0
+---------------------------- Test 43 ------------------------------
+595:before
+595:zero
+596:zero
+597:after
+597:zero
+RC=0
+---------------------------- Test 44 ------------------------------
+595:before
+595:zero
+596:zero
+597:zero
+RC=0
+---------------------------- Test 45 ------------------------------
+10:pattern
+595:binary
+596:binary
+597:binary
+RC=0
+---------------------------- Test 46 ------------------------------
+pcregrep: Error in 2nd command-line regex at offset 9: missing )
+RC=2
+---------------------------- Test 47 ------------------------------
+AB.VE
+RC=0
+---------------------------- Test 48 ------------------------------
+ABOVE the elephant 
+AB.VE
+AB.VE the turtle
+RC=0
+---------------------------- Test 49 ------------------------------
+ABOVE the elephant 
+AB.VE
+AB.VE the turtle
+PUT NEW DATA ABOVE THIS LINE.
+RC=0
+---------------------------- Test 50 ------------------------------
+RC=1
+---------------------------- Test 51 ------------------------------
+over the lazy dog.
+This time it jumps and jumps and jumps.
+RC=0
+---------------------------- Test 52 ------------------------------
+fox jumps
+This time it jumps and jumps and jumps.
+RC=0
+---------------------------- Test 53 ------------------------------
+36972,6
+36990,4
+37024,4
+37066,5
+37083,4
+RC=0
+---------------------------- Test 54 ------------------------------
+595:15,6
+595:33,4
+596:28,4
+597:15,5
+597:32,4
+RC=0
+---------------------------- Test 55 -----------------------------
+Here is the pattern again.
+That time it was on a line by itself.
+This line contains pattern not on a line by itself.
+RC=0
+---------------------------- Test 56 -----------------------------
+./testdata/grepinput:456
+./testdata/grepinput3:0
+./testdata/grepinput8:0
+./testdata/grepinputv:1
+./testdata/grepinputx:0
+RC=0
+---------------------------- Test 57 -----------------------------
+./testdata/grepinput:456
+./testdata/grepinputv:1
+RC=0
+---------------------------- Test 58 -----------------------------
+PATTERN at the start of a line.
+In the middle of a line, PATTERN appears.
+Check up on PATTERN near the end.
+RC=0
+---------------------------- Test 59 -----------------------------
+PATTERN at the start of a line.
+In the middle of a line, PATTERN appears.
+Check up on PATTERN near the end.
+RC=0
+---------------------------- Test 60 -----------------------------
+PATTERN at the start of a line.
+In the middle of a line, PATTERN appears.
+Check up on PATTERN near the end.
+RC=0
+---------------------------- Test 61 -----------------------------
+PATTERN at the start of a line.
+In the middle of a line, PATTERN appears.
+Check up on PATTERN near the end.
+RC=0
+---------------------------- Test 62 -----------------------------
+pcregrep: pcre_exec() gave error -8 while matching text that starts:
+
+This is a file of miscellaneous text that is used as test data for checking
+that the pcregrep command is working correctly. The file must be more than 24K
+long so that it needs more than a single read
+
+pcregrep: Error -8, -21 or -27 means that a resource limit was exceeded.
+pcregrep: Check your regex for nested unlimited loops.
+RC=1
+---------------------------- Test 63 -----------------------------
+pcregrep: pcre_exec() gave error -21 while matching text that starts:
+
+This is a file of miscellaneous text that is used as test data for checking
+that the pcregrep command is working correctly. The file must be more than 24K
+long so that it needs more than a single read
+
+pcregrep: Error -8, -21 or -27 means that a resource limit was exceeded.
+pcregrep: Check your regex for nested unlimited loops.
+RC=1
+---------------------------- Test 64 ------------------------------
+appears
+RC=0
+---------------------------- Test 65 ------------------------------
+pear
+RC=0
+---------------------------- Test 66 ------------------------------
+RC=0
+---------------------------- Test 67 ------------------------------
+RC=0
+---------------------------- Test 68 ------------------------------
+pear
+RC=0
+---------------------------- Test 69 -----------------------------
+1:This is a second file of input for the pcregrep tests.
+2:
+4:
+5:Pattern
+6:That time it was on a line by itself.
+7:
+8:To pat or not to pat, that is the question.
+9:
+10:complete pair
+11:of lines
+12:
+13:That was a complete pair
+14:of lines all by themselves.
+15:
+16:complete pair
+17:of lines
+18:
+19:And there they were again, to check line numbers.
+20:
+21:one
+22:two
+23:three
+24:four
+25:five
+26:six
+27:seven
+28:eight
+29:nine
+30:ten
+31:eleven
+32:twelve
+33:thirteen
+34:fourteen
+35:fifteen
+36:sixteen
+37:seventeen
+38:eighteen
+39:nineteen
+40:twenty
+41:
+43:This is the last line of this file.
+RC=0
+---------------------------- Test 70 -----------------------------
+triple:	t1_txt	s1_tag	s_txt	p_tag	p_txt	o_tag	o_txt
+
+triple:	t3_txt	s2_tag	s_txt	p_tag	p_txt	o_tag	o_txt
+
+triple:	t4_txt	s1_tag	s_txt	p_tag	p_txt	o_tag	o_txt
+
+triple:	t6_txt	s2_tag	s_txt	p_tag	p_txt	o_tag	o_txt
+
+RC=0
+---------------------------- Test 71 -----------------------------
+01
+RC=0
+---------------------------- Test 72 -----------------------------
+010203040506
+RC=0
+---------------------------- Test 73 -----------------------------
+01
+RC=0
+---------------------------- Test 74 -----------------------------
+01
+02
+RC=0
+---------------------------- Test 75 -----------------------------
+010203040506
+RC=0
+---------------------------- Test 76 -----------------------------
+01
+02
+RC=0
+---------------------------- Test 77 -----------------------------
+01
+03
+RC=0
+---------------------------- Test 78 -----------------------------
+010203040506
+RC=0
+---------------------------- Test 79 -----------------------------
+01
+03
+RC=0
+---------------------------- Test 80 -----------------------------
+01
+RC=0
+---------------------------- Test 81 -----------------------------
+010203040506
+RC=0
+---------------------------- Test 82 -----------------------------
+01
+RC=0
+---------------------------- Test 83 -----------------------------
+pcregrep: line 4 of file ./testdata/grepinput3 is too long for the internal buffer
+pcregrep: check the --buffer-size option
+RC=2
+---------------------------- Test 84 -----------------------------
+testdata/grepinputv:fox jumps
+testdata/grepinputx:complete pair
+testdata/grepinputx:That was a complete pair
+testdata/grepinputx:complete pair
+RC=0
+---------------------------- Test 85 -----------------------------
+./testdata/grepinput3:Lorem ipsum dolor sit amet, consectetur adipisicing elit, sed do eiusmod tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam, quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo consequat. Duis aute irure dolor in reprehenderit in voluptate velit esse cillum dolore eu fugiat nulla pariatur. Excepteur sint occaecat cupidatat non proident, sunt in culpa qui officia deserunt mollit anim id est laborum.
+RC=0
+---------------------------- Test 86 -----------------------------
+Binary file ./testdata/grepbinary matches
+RC=0
+---------------------------- Test 87 -----------------------------
+RC=1
+---------------------------- Test 88 -----------------------------
+Binary file ./testdata/grepbinary matches
+RC=0
+---------------------------- Test 89 -----------------------------
+RC=1
+---------------------------- Test 90 -----------------------------
+RC=1
+---------------------------- Test 91 -----------------------------
+The quick brown f
+RC=0
+---------------------------- Test 92 -----------------------------
+The quick brown f
+RC=0
+---------------------------- Test 93 -----------------------------
+The quick brown f
+RC=0
diff --git a/ext/pcre/pcrelib/testdata/grepoutput8 b/ext/pcre/pcrelib/testdata/grepoutput8
new file mode 100644
index 0000000..385266b
--- /dev/null
+++ b/ext/pcre/pcrelib/testdata/grepoutput8
@@ -0,0 +1,12 @@
+---------------------------- Test U1 ------------------------------
+1:X one
+2:X two3:X three4:X four
5:X five
+6:X six
+7:X seven…8:X eight
9:X nine
10:X ten
+RC=0
+---------------------------- Test U2 ------------------------------
+12-Before 111
+13-Before 222
14-Before 333…15:Match
+16-After 111
+17-After 222
18-After 333
+RC=0
diff --git a/ext/pcre/pcrelib/testdata/grepoutputN b/ext/pcre/pcrelib/testdata/grepoutputN
new file mode 100644
index 0000000..6760314
--- /dev/null
+++ b/ext/pcre/pcrelib/testdata/grepoutputN
@@ -0,0 +1,16 @@
+---------------------------- Test N1 ------------------------------
+1:abc
2:def
---------------------------- Test N2 ------------------------------
+1:abc
def
+2:ghi
+jkl---------------------------- Test N3 ------------------------------
+2:def
3:
+ghi
+jkl---------------------------- Test N4 ------------------------------
+2:ghi
+jkl---------------------------- Test N5 ------------------------------
+1:abc
2:def
+3:ghi
+4:jkl---------------------------- Test N6 ------------------------------
+1:abc
2:def
+3:ghi
+4:jkl
\ No newline at end of file
diff --git a/ext/pcre/pcrelib/testdata/testinput1 b/ext/pcre/pcrelib/testdata/testinput1
new file mode 100644
index 0000000..1ec7689
--- /dev/null
+++ b/ext/pcre/pcrelib/testdata/testinput1
@@ -0,0 +1,5265 @@
+/-- This set of tests is for features that are compatible with all versions of
+    Perl >= 5.10, in non-UTF-8 mode. It should run clean for both the 8-bit and
+    16-bit PCRE libraries. --/
+
+/the quick brown fox/
+    the quick brown fox
+    The quick brown FOX
+    What do you know about the quick brown fox?
+    What do you know about THE QUICK BROWN FOX?
+
+/The quick brown fox/i
+    the quick brown fox
+    The quick brown FOX
+    What do you know about the quick brown fox?
+    What do you know about THE QUICK BROWN FOX?
+
+/abcd\t\n\r\f\a\e\071\x3b\$\\\?caxyz/
+    abcd\t\n\r\f\a\e9;\$\\?caxyz
+
+/a*abc?xyz+pqr{3}ab{2,}xy{4,5}pq{0,6}AB{0,}zz/
+    abxyzpqrrrabbxyyyypqAzz
+    abxyzpqrrrabbxyyyypqAzz
+    aabxyzpqrrrabbxyyyypqAzz
+    aaabxyzpqrrrabbxyyyypqAzz
+    aaaabxyzpqrrrabbxyyyypqAzz
+    abcxyzpqrrrabbxyyyypqAzz
+    aabcxyzpqrrrabbxyyyypqAzz
+    aaabcxyzpqrrrabbxyyyypAzz
+    aaabcxyzpqrrrabbxyyyypqAzz
+    aaabcxyzpqrrrabbxyyyypqqAzz
+    aaabcxyzpqrrrabbxyyyypqqqAzz
+    aaabcxyzpqrrrabbxyyyypqqqqAzz
+    aaabcxyzpqrrrabbxyyyypqqqqqAzz
+    aaabcxyzpqrrrabbxyyyypqqqqqqAzz
+    aaaabcxyzpqrrrabbxyyyypqAzz
+    abxyzzpqrrrabbxyyyypqAzz
+    aabxyzzzpqrrrabbxyyyypqAzz
+    aaabxyzzzzpqrrrabbxyyyypqAzz
+    aaaabxyzzzzpqrrrabbxyyyypqAzz
+    abcxyzzpqrrrabbxyyyypqAzz
+    aabcxyzzzpqrrrabbxyyyypqAzz
+    aaabcxyzzzzpqrrrabbxyyyypqAzz
+    aaaabcxyzzzzpqrrrabbxyyyypqAzz
+    aaaabcxyzzzzpqrrrabbbxyyyypqAzz
+    aaaabcxyzzzzpqrrrabbbxyyyyypqAzz
+    aaabcxyzpqrrrabbxyyyypABzz
+    aaabcxyzpqrrrabbxyyyypABBzz
+    >>>aaabxyzpqrrrabbxyyyypqAzz
+    >aaaabxyzpqrrrabbxyyyypqAzz
+    >>>>abcxyzpqrrrabbxyyyypqAzz
+    *** Failers
+    abxyzpqrrabbxyyyypqAzz
+    abxyzpqrrrrabbxyyyypqAzz
+    abxyzpqrrrabxyyyypqAzz
+    aaaabcxyzzzzpqrrrabbbxyyyyyypqAzz
+    aaaabcxyzzzzpqrrrabbbxyyypqAzz
+    aaabcxyzpqrrrabbxyyyypqqqqqqqAzz
+
+/^(abc){1,2}zz/
+    abczz
+    abcabczz
+    *** Failers
+    zz
+    abcabcabczz
+    >>abczz
+
+/^(b+?|a){1,2}?c/
+    bc
+    bbc
+    bbbc
+    bac
+    bbac
+    aac
+    abbbbbbbbbbbc
+    bbbbbbbbbbbac
+    *** Failers
+    aaac
+    abbbbbbbbbbbac
+
+/^(b+|a){1,2}c/
+    bc
+    bbc
+    bbbc
+    bac
+    bbac
+    aac
+    abbbbbbbbbbbc
+    bbbbbbbbbbbac
+    *** Failers
+    aaac
+    abbbbbbbbbbbac
+
+/^(b+|a){1,2}?bc/
+    bbc
+
+/^(b*|ba){1,2}?bc/
+    babc
+    bbabc
+    bababc
+    *** Failers
+    bababbc
+    babababc
+
+/^(ba|b*){1,2}?bc/
+    babc
+    bbabc
+    bababc
+    *** Failers
+    bababbc
+    babababc
+
+/^\ca\cA\c[\c{\c:/
+    \x01\x01\e;z
+
+/^[ab\]cde]/
+    athing
+    bthing
+    ]thing
+    cthing
+    dthing
+    ething
+    *** Failers
+    fthing
+    [thing
+    \\thing
+
+/^[]cde]/
+    ]thing
+    cthing
+    dthing
+    ething
+    *** Failers
+    athing
+    fthing
+
+/^[^ab\]cde]/
+    fthing
+    [thing
+    \\thing
+    *** Failers
+    athing
+    bthing
+    ]thing
+    cthing
+    dthing
+    ething
+
+/^[^]cde]/
+    athing
+    fthing
+    *** Failers
+    ]thing
+    cthing
+    dthing
+    ething
+
+/^\�/
+    �
+
+/^ÿ/
+    ÿ
+
+/^[0-9]+$/
+    0
+    1
+    2
+    3
+    4
+    5
+    6
+    7
+    8
+    9
+    10
+    100
+    *** Failers
+    abc
+
+/^.*nter/
+    enter
+    inter
+    uponter
+
+/^xxx[0-9]+$/
+    xxx0
+    xxx1234
+    *** Failers
+    xxx
+
+/^.+[0-9][0-9][0-9]$/
+    x123
+    xx123
+    123456
+    *** Failers
+    123
+    x1234
+
+/^.+?[0-9][0-9][0-9]$/
+    x123
+    xx123
+    123456
+    *** Failers
+    123
+    x1234
+
+/^([^!]+)!(.+)=apquxz\.ixr\.zzz\.ac\.uk$/
+    abc!pqr=apquxz.ixr.zzz.ac.uk
+    *** Failers
+    !pqr=apquxz.ixr.zzz.ac.uk
+    abc!=apquxz.ixr.zzz.ac.uk
+    abc!pqr=apquxz:ixr.zzz.ac.uk
+    abc!pqr=apquxz.ixr.zzz.ac.ukk
+
+/:/
+    Well, we need a colon: somewhere
+    *** Fail if we don't
+
+/([\da-f:]+)$/i
+    0abc
+    abc
+    fed
+    E
+    ::
+    5f03:12C0::932e
+    fed def
+    Any old stuff
+    *** Failers
+    0zzz
+    gzzz
+    fed\x20
+    Any old rubbish
+
+/^.*\.(\d{1,3})\.(\d{1,3})\.(\d{1,3})$/
+    .1.2.3
+    A.12.123.0
+    *** Failers
+    .1.2.3333
+    1.2.3
+    1234.2.3
+
+/^(\d+)\s+IN\s+SOA\s+(\S+)\s+(\S+)\s*\(\s*$/
+    1 IN SOA non-sp1 non-sp2(
+    1    IN    SOA    non-sp1    non-sp2   (
+    *** Failers
+    1IN SOA non-sp1 non-sp2(
+
+/^[a-zA-Z\d][a-zA-Z\d\-]*(\.[a-zA-Z\d][a-zA-z\d\-]*)*\.$/
+    a.
+    Z.
+    2.
+    ab-c.pq-r.
+    sxk.zzz.ac.uk.
+    x-.y-.
+    *** Failers
+    -abc.peq.
+
+/^\*\.[a-z]([a-z\-\d]*[a-z\d]+)?(\.[a-z]([a-z\-\d]*[a-z\d]+)?)*$/
+    *.a
+    *.b0-a
+    *.c3-b.c
+    *.c-a.b-c
+    *** Failers
+    *.0
+    *.a-
+    *.a-b.c-
+    *.c-a.0-c
+
+/^(?=ab(de))(abd)(e)/
+    abde
+
+/^(?!(ab)de|x)(abd)(f)/
+    abdf
+
+/^(?=(ab(cd)))(ab)/
+    abcd
+
+/^[\da-f](\.[\da-f])*$/i
+    a.b.c.d
+    A.B.C.D
+    a.b.c.1.2.3.C
+
+/^\".*\"\s*(;.*)?$/
+    \"1234\"
+    \"abcd\" ;
+    \"\" ; rhubarb
+    *** Failers
+    \"1234\" : things
+
+/^$/
+    \
+    *** Failers
+
+/   ^    a   (?# begins with a)  b\sc (?# then b c) $ (?# then end)/x
+    ab c
+    *** Failers
+    abc
+    ab cde
+
+/(?x)   ^    a   (?# begins with a)  b\sc (?# then b c) $ (?# then end)/
+    ab c
+    *** Failers
+    abc
+    ab cde
+
+/^   a\ b[c ]d       $/x
+    a bcd
+    a b d
+    *** Failers
+    abcd
+    ab d
+
+/^(a(b(c)))(d(e(f)))(h(i(j)))(k(l(m)))$/
+    abcdefhijklm
+
+/^(?:a(b(c)))(?:d(e(f)))(?:h(i(j)))(?:k(l(m)))$/
+    abcdefhijklm
+
+/^[\w][\W][\s][\S][\d][\D][\b][\n][\c]][\022]/
+    a+ Z0+\x08\n\x1d\x12
+
+/^[.^$|()*+?{,}]+/
+    .^\$(*+)|{?,?}
+
+/^a*\w/
+    z
+    az
+    aaaz
+    a
+    aa
+    aaaa
+    a+
+    aa+
+
+/^a*?\w/
+    z
+    az
+    aaaz
+    a
+    aa
+    aaaa
+    a+
+    aa+
+
+/^a+\w/
+    az
+    aaaz
+    aa
+    aaaa
+    aa+
+
+/^a+?\w/
+    az
+    aaaz
+    aa
+    aaaa
+    aa+
+
+/^\d{8}\w{2,}/
+    1234567890
+    12345678ab
+    12345678__
+    *** Failers
+    1234567
+
+/^[aeiou\d]{4,5}$/
+    uoie
+    1234
+    12345
+    aaaaa
+    *** Failers
+    123456
+
+/^[aeiou\d]{4,5}?/
+    uoie
+    1234
+    12345
+    aaaaa
+    123456
+
+/\A(abc|def)=(\1){2,3}\Z/
+    abc=abcabc
+    def=defdefdef
+    *** Failers
+    abc=defdef
+
+/^(a)(b)(c)(d)(e)(f)(g)(h)(i)(j)(k)\11*(\3\4)\1(?#)2$/
+    abcdefghijkcda2
+    abcdefghijkkkkcda2
+
+/(cat(a(ract|tonic)|erpillar)) \1()2(3)/
+    cataract cataract23
+    catatonic catatonic23
+    caterpillar caterpillar23
+
+
+/^From +([^ ]+) +[a-zA-Z][a-zA-Z][a-zA-Z] +[a-zA-Z][a-zA-Z][a-zA-Z] +[0-9]?[0-9] +[0-9][0-9]:[0-9][0-9]/
+    From abcd  Mon Sep 01 12:33:02 1997
+
+/^From\s+\S+\s+([a-zA-Z]{3}\s+){2}\d{1,2}\s+\d\d:\d\d/
+    From abcd  Mon Sep 01 12:33:02 1997
+    From abcd  Mon Sep  1 12:33:02 1997
+    *** Failers
+    From abcd  Sep 01 12:33:02 1997
+
+/^12.34/s
+    12\n34
+    12\r34
+
+/\w+(?=\t)/
+    the quick brown\t fox
+
+/foo(?!bar)(.*)/
+    foobar is foolish see?
+
+/(?:(?!foo)...|^.{0,2})bar(.*)/
+    foobar crowbar etc
+    barrel
+    2barrel
+    A barrel
+
+/^(\D*)(?=\d)(?!123)/
+    abc456
+    *** Failers
+    abc123
+
+/^1234(?# test newlines
+  inside)/
+    1234
+
+/^1234 #comment in extended re
+  /x
+    1234
+
+/#rhubarb
+  abcd/x
+    abcd
+
+/^abcd#rhubarb/x
+    abcd
+
+/^(a)\1{2,3}(.)/
+    aaab
+    aaaab
+    aaaaab
+    aaaaaab
+
+/(?!^)abc/
+    the abc
+    *** Failers
+    abc
+
+/(?=^)abc/
+    abc
+    *** Failers
+    the abc
+
+/^[ab]{1,3}(ab*|b)/
+    aabbbbb
+
+/^[ab]{1,3}?(ab*|b)/
+    aabbbbb
+
+/^[ab]{1,3}?(ab*?|b)/
+    aabbbbb
+
+/^[ab]{1,3}(ab*?|b)/
+    aabbbbb
+
+/  (?: [\040\t] |  \(
+(?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  |  \( (?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  )* \)  )*
+\)  )*                          # optional leading comment
+(?:    (?:
+[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+    # some number of atom characters...
+(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom
+|
+" (?:                      # opening quote...
+[^\\\x80-\xff\n\015"]                #   Anything except backslash and quote
+|                     #    or
+\\ [^\x80-\xff]           #   Escaped something (something != CR)
+)* "  # closing quote
+)                    # initial word
+(?:  (?: [\040\t] |  \(
+(?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  |  \( (?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  )* \)  )*
+\)  )*  \.  (?: [\040\t] |  \(
+(?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  |  \( (?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  )* \)  )*
+\)  )*   (?:
+[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+    # some number of atom characters...
+(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom
+|
+" (?:                      # opening quote...
+[^\\\x80-\xff\n\015"]                #   Anything except backslash and quote
+|                     #    or
+\\ [^\x80-\xff]           #   Escaped something (something != CR)
+)* "  # closing quote
+)  )* # further okay, if led by a period
+(?: [\040\t] |  \(
+(?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  |  \( (?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  )* \)  )*
+\)  )*  @  (?: [\040\t] |  \(
+(?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  |  \( (?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  )* \)  )*
+\)  )*    (?:
+[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+    # some number of atom characters...
+(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom
+|   \[                         # [
+(?: [^\\\x80-\xff\n\015\[\]] |  \\ [^\x80-\xff]  )*    #    stuff
+\]                        #           ]
+)                           # initial subdomain
+(?:                                  #
+(?: [\040\t] |  \(
+(?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  |  \( (?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  )* \)  )*
+\)  )*  \.                        # if led by a period...
+(?: [\040\t] |  \(
+(?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  |  \( (?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  )* \)  )*
+\)  )*   (?:
+[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+    # some number of atom characters...
+(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom
+|   \[                         # [
+(?: [^\\\x80-\xff\n\015\[\]] |  \\ [^\x80-\xff]  )*    #    stuff
+\]                        #           ]
+)                     #   ...further okay
+)*
+# address
+|                     #  or
+(?:
+[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+    # some number of atom characters...
+(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom
+|
+" (?:                      # opening quote...
+[^\\\x80-\xff\n\015"]                #   Anything except backslash and quote
+|                     #    or
+\\ [^\x80-\xff]           #   Escaped something (something != CR)
+)* "  # closing quote
+)             # one word, optionally followed by....
+(?:
+[^()<>@,;:".\\\[\]\x80-\xff\000-\010\012-\037]  |  # atom and space parts, or...
+\(
+(?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  |  \( (?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  )* \)  )*
+\)       |  # comments, or...
+
+" (?:                      # opening quote...
+[^\\\x80-\xff\n\015"]                #   Anything except backslash and quote
+|                     #    or
+\\ [^\x80-\xff]           #   Escaped something (something != CR)
+)* "  # closing quote
+# quoted strings
+)*
+<  (?: [\040\t] |  \(
+(?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  |  \( (?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  )* \)  )*
+\)  )*                     # leading <
+(?:  @  (?: [\040\t] |  \(
+(?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  |  \( (?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  )* \)  )*
+\)  )*    (?:
+[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+    # some number of atom characters...
+(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom
+|   \[                         # [
+(?: [^\\\x80-\xff\n\015\[\]] |  \\ [^\x80-\xff]  )*    #    stuff
+\]                        #           ]
+)                           # initial subdomain
+(?:                                  #
+(?: [\040\t] |  \(
+(?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  |  \( (?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  )* \)  )*
+\)  )*  \.                        # if led by a period...
+(?: [\040\t] |  \(
+(?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  |  \( (?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  )* \)  )*
+\)  )*   (?:
+[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+    # some number of atom characters...
+(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom
+|   \[                         # [
+(?: [^\\\x80-\xff\n\015\[\]] |  \\ [^\x80-\xff]  )*    #    stuff
+\]                        #           ]
+)                     #   ...further okay
+)*
+
+(?:  (?: [\040\t] |  \(
+(?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  |  \( (?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  )* \)  )*
+\)  )*  ,  (?: [\040\t] |  \(
+(?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  |  \( (?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  )* \)  )*
+\)  )*  @  (?: [\040\t] |  \(
+(?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  |  \( (?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  )* \)  )*
+\)  )*    (?:
+[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+    # some number of atom characters...
+(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom
+|   \[                         # [
+(?: [^\\\x80-\xff\n\015\[\]] |  \\ [^\x80-\xff]  )*    #    stuff
+\]                        #           ]
+)                           # initial subdomain
+(?:                                  #
+(?: [\040\t] |  \(
+(?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  |  \( (?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  )* \)  )*
+\)  )*  \.                        # if led by a period...
+(?: [\040\t] |  \(
+(?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  |  \( (?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  )* \)  )*
+\)  )*   (?:
+[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+    # some number of atom characters...
+(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom
+|   \[                         # [
+(?: [^\\\x80-\xff\n\015\[\]] |  \\ [^\x80-\xff]  )*    #    stuff
+\]                        #           ]
+)                     #   ...further okay
+)*
+)* # further okay, if led by comma
+:                                # closing colon
+(?: [\040\t] |  \(
+(?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  |  \( (?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  )* \)  )*
+\)  )*  )? #       optional route
+(?:
+[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+    # some number of atom characters...
+(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom
+|
+" (?:                      # opening quote...
+[^\\\x80-\xff\n\015"]                #   Anything except backslash and quote
+|                     #    or
+\\ [^\x80-\xff]           #   Escaped something (something != CR)
+)* "  # closing quote
+)                    # initial word
+(?:  (?: [\040\t] |  \(
+(?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  |  \( (?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  )* \)  )*
+\)  )*  \.  (?: [\040\t] |  \(
+(?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  |  \( (?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  )* \)  )*
+\)  )*   (?:
+[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+    # some number of atom characters...
+(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom
+|
+" (?:                      # opening quote...
+[^\\\x80-\xff\n\015"]                #   Anything except backslash and quote
+|                     #    or
+\\ [^\x80-\xff]           #   Escaped something (something != CR)
+)* "  # closing quote
+)  )* # further okay, if led by a period
+(?: [\040\t] |  \(
+(?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  |  \( (?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  )* \)  )*
+\)  )*  @  (?: [\040\t] |  \(
+(?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  |  \( (?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  )* \)  )*
+\)  )*    (?:
+[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+    # some number of atom characters...
+(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom
+|   \[                         # [
+(?: [^\\\x80-\xff\n\015\[\]] |  \\ [^\x80-\xff]  )*    #    stuff
+\]                        #           ]
+)                           # initial subdomain
+(?:                                  #
+(?: [\040\t] |  \(
+(?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  |  \( (?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  )* \)  )*
+\)  )*  \.                        # if led by a period...
+(?: [\040\t] |  \(
+(?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  |  \( (?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  )* \)  )*
+\)  )*   (?:
+[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+    # some number of atom characters...
+(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom
+|   \[                         # [
+(?: [^\\\x80-\xff\n\015\[\]] |  \\ [^\x80-\xff]  )*    #    stuff
+\]                        #           ]
+)                     #   ...further okay
+)*
+#       address spec
+(?: [\040\t] |  \(
+(?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  |  \( (?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  )* \)  )*
+\)  )*  > #                  trailing >
+# name and address
+)  (?: [\040\t] |  \(
+(?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  |  \( (?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  )* \)  )*
+\)  )*                       # optional trailing comment
+/x
+    Alan Other <user\@dom.ain>
+    <user\@dom.ain>
+    user\@dom.ain
+    \"A. Other\" <user.1234\@dom.ain> (a comment)
+    A. Other <user.1234\@dom.ain> (a comment)
+    \"/s=user/ou=host/o=place/prmd=uu.yy/admd= /c=gb/\"\@x400-re.lay
+    A missing angle <user\@some.where
+    *** Failers
+    The quick brown fox
+
+/[\040\t]*                    # Nab whitespace.
+(?:
+\(                              #  (
+[^\\\x80-\xff\n\015()] *                             #     normal*
+(?:                                 #       (
+(?:  \\ [^\x80-\xff]  |
+\(                            #  (
+[^\\\x80-\xff\n\015()] *                            #     normal*
+(?:  \\ [^\x80-\xff]   [^\\\x80-\xff\n\015()] * )*        #     (special normal*)*
+\)                           #                       )
+)    #         special
+[^\\\x80-\xff\n\015()] *                         #         normal*
+)*                                  #            )*
+\)                             #                )
+[\040\t]* )*    # If comment found, allow more spaces.
+# optional leading comment
+(?:
+(?:
+[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+    # some number of atom characters...
+(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom
+# Atom
+|                       #  or
+"                                     # "
+[^\\\x80-\xff\n\015"] *                            #   normal
+(?:  \\ [^\x80-\xff]  [^\\\x80-\xff\n\015"] * )*        #   ( special normal* )*
+"                                     #        "
+# Quoted string
+)
+[\040\t]*                    # Nab whitespace.
+(?:
+\(                              #  (
+[^\\\x80-\xff\n\015()] *                             #     normal*
+(?:                                 #       (
+(?:  \\ [^\x80-\xff]  |
+\(                            #  (
+[^\\\x80-\xff\n\015()] *                            #     normal*
+(?:  \\ [^\x80-\xff]   [^\\\x80-\xff\n\015()] * )*        #     (special normal*)*
+\)                           #                       )
+)    #         special
+[^\\\x80-\xff\n\015()] *                         #         normal*
+)*                                  #            )*
+\)                             #                )
+[\040\t]* )*    # If comment found, allow more spaces.
+(?:
+\.
+[\040\t]*                    # Nab whitespace.
+(?:
+\(                              #  (
+[^\\\x80-\xff\n\015()] *                             #     normal*
+(?:                                 #       (
+(?:  \\ [^\x80-\xff]  |
+\(                            #  (
+[^\\\x80-\xff\n\015()] *                            #     normal*
+(?:  \\ [^\x80-\xff]   [^\\\x80-\xff\n\015()] * )*        #     (special normal*)*
+\)                           #                       )
+)    #         special
+[^\\\x80-\xff\n\015()] *                         #         normal*
+)*                                  #            )*
+\)                             #                )
+[\040\t]* )*    # If comment found, allow more spaces.
+(?:
+[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+    # some number of atom characters...
+(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom
+# Atom
+|                       #  or
+"                                     # "
+[^\\\x80-\xff\n\015"] *                            #   normal
+(?:  \\ [^\x80-\xff]  [^\\\x80-\xff\n\015"] * )*        #   ( special normal* )*
+"                                     #        "
+# Quoted string
+)
+[\040\t]*                    # Nab whitespace.
+(?:
+\(                              #  (
+[^\\\x80-\xff\n\015()] *                             #     normal*
+(?:                                 #       (
+(?:  \\ [^\x80-\xff]  |
+\(                            #  (
+[^\\\x80-\xff\n\015()] *                            #     normal*
+(?:  \\ [^\x80-\xff]   [^\\\x80-\xff\n\015()] * )*        #     (special normal*)*
+\)                           #                       )
+)    #         special
+[^\\\x80-\xff\n\015()] *                         #         normal*
+)*                                  #            )*
+\)                             #                )
+[\040\t]* )*    # If comment found, allow more spaces.
+# additional words
+)*
+@
+[\040\t]*                    # Nab whitespace.
+(?:
+\(                              #  (
+[^\\\x80-\xff\n\015()] *                             #     normal*
+(?:                                 #       (
+(?:  \\ [^\x80-\xff]  |
+\(                            #  (
+[^\\\x80-\xff\n\015()] *                            #     normal*
+(?:  \\ [^\x80-\xff]   [^\\\x80-\xff\n\015()] * )*        #     (special normal*)*
+\)                           #                       )
+)    #         special
+[^\\\x80-\xff\n\015()] *                         #         normal*
+)*                                  #            )*
+\)                             #                )
+[\040\t]* )*    # If comment found, allow more spaces.
+(?:
+[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+    # some number of atom characters...
+(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom
+|
+\[                            # [
+(?: [^\\\x80-\xff\n\015\[\]] |  \\ [^\x80-\xff]  )*     #    stuff
+\]                           #           ]
+)
+[\040\t]*                    # Nab whitespace.
+(?:
+\(                              #  (
+[^\\\x80-\xff\n\015()] *                             #     normal*
+(?:                                 #       (
+(?:  \\ [^\x80-\xff]  |
+\(                            #  (
+[^\\\x80-\xff\n\015()] *                            #     normal*
+(?:  \\ [^\x80-\xff]   [^\\\x80-\xff\n\015()] * )*        #     (special normal*)*
+\)                           #                       )
+)    #         special
+[^\\\x80-\xff\n\015()] *                         #         normal*
+)*                                  #            )*
+\)                             #                )
+[\040\t]* )*    # If comment found, allow more spaces.
+# optional trailing comments
+(?:
+\.
+[\040\t]*                    # Nab whitespace.
+(?:
+\(                              #  (
+[^\\\x80-\xff\n\015()] *                             #     normal*
+(?:                                 #       (
+(?:  \\ [^\x80-\xff]  |
+\(                            #  (
+[^\\\x80-\xff\n\015()] *                            #     normal*
+(?:  \\ [^\x80-\xff]   [^\\\x80-\xff\n\015()] * )*        #     (special normal*)*
+\)                           #                       )
+)    #         special
+[^\\\x80-\xff\n\015()] *                         #         normal*
+)*                                  #            )*
+\)                             #                )
+[\040\t]* )*    # If comment found, allow more spaces.
+(?:
+[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+    # some number of atom characters...
+(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom
+|
+\[                            # [
+(?: [^\\\x80-\xff\n\015\[\]] |  \\ [^\x80-\xff]  )*     #    stuff
+\]                           #           ]
+)
+[\040\t]*                    # Nab whitespace.
+(?:
+\(                              #  (
+[^\\\x80-\xff\n\015()] *                             #     normal*
+(?:                                 #       (
+(?:  \\ [^\x80-\xff]  |
+\(                            #  (
+[^\\\x80-\xff\n\015()] *                            #     normal*
+(?:  \\ [^\x80-\xff]   [^\\\x80-\xff\n\015()] * )*        #     (special normal*)*
+\)                           #                       )
+)    #         special
+[^\\\x80-\xff\n\015()] *                         #         normal*
+)*                                  #            )*
+\)                             #                )
+[\040\t]* )*    # If comment found, allow more spaces.
+# optional trailing comments
+)*
+# address
+|                             #  or
+(?:
+[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+    # some number of atom characters...
+(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom
+# Atom
+|                       #  or
+"                                     # "
+[^\\\x80-\xff\n\015"] *                            #   normal
+(?:  \\ [^\x80-\xff]  [^\\\x80-\xff\n\015"] * )*        #   ( special normal* )*
+"                                     #        "
+# Quoted string
+)
+# leading word
+[^()<>@,;:".\\\[\]\x80-\xff\000-\010\012-\037] *               # "normal" atoms and or spaces
+(?:
+(?:
+\(                              #  (
+[^\\\x80-\xff\n\015()] *                             #     normal*
+(?:                                 #       (
+(?:  \\ [^\x80-\xff]  |
+\(                            #  (
+[^\\\x80-\xff\n\015()] *                            #     normal*
+(?:  \\ [^\x80-\xff]   [^\\\x80-\xff\n\015()] * )*        #     (special normal*)*
+\)                           #                       )
+)    #         special
+[^\\\x80-\xff\n\015()] *                         #         normal*
+)*                                  #            )*
+\)                             #                )
+|
+"                                     # "
+[^\\\x80-\xff\n\015"] *                            #   normal
+(?:  \\ [^\x80-\xff]  [^\\\x80-\xff\n\015"] * )*        #   ( special normal* )*
+"                                     #        "
+) # "special" comment or quoted string
+[^()<>@,;:".\\\[\]\x80-\xff\000-\010\012-\037] *            #  more "normal"
+)*
+<
+[\040\t]*                    # Nab whitespace.
+(?:
+\(                              #  (
+[^\\\x80-\xff\n\015()] *                             #     normal*
+(?:                                 #       (
+(?:  \\ [^\x80-\xff]  |
+\(                            #  (
+[^\\\x80-\xff\n\015()] *                            #     normal*
+(?:  \\ [^\x80-\xff]   [^\\\x80-\xff\n\015()] * )*        #     (special normal*)*
+\)                           #                       )
+)    #         special
+[^\\\x80-\xff\n\015()] *                         #         normal*
+)*                                  #            )*
+\)                             #                )
+[\040\t]* )*    # If comment found, allow more spaces.
+# <
+(?:
+@
+[\040\t]*                    # Nab whitespace.
+(?:
+\(                              #  (
+[^\\\x80-\xff\n\015()] *                             #     normal*
+(?:                                 #       (
+(?:  \\ [^\x80-\xff]  |
+\(                            #  (
+[^\\\x80-\xff\n\015()] *                            #     normal*
+(?:  \\ [^\x80-\xff]   [^\\\x80-\xff\n\015()] * )*        #     (special normal*)*
+\)                           #                       )
+)    #         special
+[^\\\x80-\xff\n\015()] *                         #         normal*
+)*                                  #            )*
+\)                             #                )
+[\040\t]* )*    # If comment found, allow more spaces.
+(?:
+[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+    # some number of atom characters...
+(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom
+|
+\[                            # [
+(?: [^\\\x80-\xff\n\015\[\]] |  \\ [^\x80-\xff]  )*     #    stuff
+\]                           #           ]
+)
+[\040\t]*                    # Nab whitespace.
+(?:
+\(                              #  (
+[^\\\x80-\xff\n\015()] *                             #     normal*
+(?:                                 #       (
+(?:  \\ [^\x80-\xff]  |
+\(                            #  (
+[^\\\x80-\xff\n\015()] *                            #     normal*
+(?:  \\ [^\x80-\xff]   [^\\\x80-\xff\n\015()] * )*        #     (special normal*)*
+\)                           #                       )
+)    #         special
+[^\\\x80-\xff\n\015()] *                         #         normal*
+)*                                  #            )*
+\)                             #                )
+[\040\t]* )*    # If comment found, allow more spaces.
+# optional trailing comments
+(?:
+\.
+[\040\t]*                    # Nab whitespace.
+(?:
+\(                              #  (
+[^\\\x80-\xff\n\015()] *                             #     normal*
+(?:                                 #       (
+(?:  \\ [^\x80-\xff]  |
+\(                            #  (
+[^\\\x80-\xff\n\015()] *                            #     normal*
+(?:  \\ [^\x80-\xff]   [^\\\x80-\xff\n\015()] * )*        #     (special normal*)*
+\)                           #                       )
+)    #         special
+[^\\\x80-\xff\n\015()] *                         #         normal*
+)*                                  #            )*
+\)                             #                )
+[\040\t]* )*    # If comment found, allow more spaces.
+(?:
+[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+    # some number of atom characters...
+(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom
+|
+\[                            # [
+(?: [^\\\x80-\xff\n\015\[\]] |  \\ [^\x80-\xff]  )*     #    stuff
+\]                           #           ]
+)
+[\040\t]*                    # Nab whitespace.
+(?:
+\(                              #  (
+[^\\\x80-\xff\n\015()] *                             #     normal*
+(?:                                 #       (
+(?:  \\ [^\x80-\xff]  |
+\(                            #  (
+[^\\\x80-\xff\n\015()] *                            #     normal*
+(?:  \\ [^\x80-\xff]   [^\\\x80-\xff\n\015()] * )*        #     (special normal*)*
+\)                           #                       )
+)    #         special
+[^\\\x80-\xff\n\015()] *                         #         normal*
+)*                                  #            )*
+\)                             #                )
+[\040\t]* )*    # If comment found, allow more spaces.
+# optional trailing comments
+)*
+(?: ,
+[\040\t]*                    # Nab whitespace.
+(?:
+\(                              #  (
+[^\\\x80-\xff\n\015()] *                             #     normal*
+(?:                                 #       (
+(?:  \\ [^\x80-\xff]  |
+\(                            #  (
+[^\\\x80-\xff\n\015()] *                            #     normal*
+(?:  \\ [^\x80-\xff]   [^\\\x80-\xff\n\015()] * )*        #     (special normal*)*
+\)                           #                       )
+)    #         special
+[^\\\x80-\xff\n\015()] *                         #         normal*
+)*                                  #            )*
+\)                             #                )
+[\040\t]* )*    # If comment found, allow more spaces.
+@
+[\040\t]*                    # Nab whitespace.
+(?:
+\(                              #  (
+[^\\\x80-\xff\n\015()] *                             #     normal*
+(?:                                 #       (
+(?:  \\ [^\x80-\xff]  |
+\(                            #  (
+[^\\\x80-\xff\n\015()] *                            #     normal*
+(?:  \\ [^\x80-\xff]   [^\\\x80-\xff\n\015()] * )*        #     (special normal*)*
+\)                           #                       )
+)    #         special
+[^\\\x80-\xff\n\015()] *                         #         normal*
+)*                                  #            )*
+\)                             #                )
+[\040\t]* )*    # If comment found, allow more spaces.
+(?:
+[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+    # some number of atom characters...
+(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom
+|
+\[                            # [
+(?: [^\\\x80-\xff\n\015\[\]] |  \\ [^\x80-\xff]  )*     #    stuff
+\]                           #           ]
+)
+[\040\t]*                    # Nab whitespace.
+(?:
+\(                              #  (
+[^\\\x80-\xff\n\015()] *                             #     normal*
+(?:                                 #       (
+(?:  \\ [^\x80-\xff]  |
+\(                            #  (
+[^\\\x80-\xff\n\015()] *                            #     normal*
+(?:  \\ [^\x80-\xff]   [^\\\x80-\xff\n\015()] * )*        #     (special normal*)*
+\)                           #                       )
+)    #         special
+[^\\\x80-\xff\n\015()] *                         #         normal*
+)*                                  #            )*
+\)                             #                )
+[\040\t]* )*    # If comment found, allow more spaces.
+# optional trailing comments
+(?:
+\.
+[\040\t]*                    # Nab whitespace.
+(?:
+\(                              #  (
+[^\\\x80-\xff\n\015()] *                             #     normal*
+(?:                                 #       (
+(?:  \\ [^\x80-\xff]  |
+\(                            #  (
+[^\\\x80-\xff\n\015()] *                            #     normal*
+(?:  \\ [^\x80-\xff]   [^\\\x80-\xff\n\015()] * )*        #     (special normal*)*
+\)                           #                       )
+)    #         special
+[^\\\x80-\xff\n\015()] *                         #         normal*
+)*                                  #            )*
+\)                             #                )
+[\040\t]* )*    # If comment found, allow more spaces.
+(?:
+[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+    # some number of atom characters...
+(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom
+|
+\[                            # [
+(?: [^\\\x80-\xff\n\015\[\]] |  \\ [^\x80-\xff]  )*     #    stuff
+\]                           #           ]
+)
+[\040\t]*                    # Nab whitespace.
+(?:
+\(                              #  (
+[^\\\x80-\xff\n\015()] *                             #     normal*
+(?:                                 #       (
+(?:  \\ [^\x80-\xff]  |
+\(                            #  (
+[^\\\x80-\xff\n\015()] *                            #     normal*
+(?:  \\ [^\x80-\xff]   [^\\\x80-\xff\n\015()] * )*        #     (special normal*)*
+\)                           #                       )
+)    #         special
+[^\\\x80-\xff\n\015()] *                         #         normal*
+)*                                  #            )*
+\)                             #                )
+[\040\t]* )*    # If comment found, allow more spaces.
+# optional trailing comments
+)*
+)*  # additional domains
+:
+[\040\t]*                    # Nab whitespace.
+(?:
+\(                              #  (
+[^\\\x80-\xff\n\015()] *                             #     normal*
+(?:                                 #       (
+(?:  \\ [^\x80-\xff]  |
+\(                            #  (
+[^\\\x80-\xff\n\015()] *                            #     normal*
+(?:  \\ [^\x80-\xff]   [^\\\x80-\xff\n\015()] * )*        #     (special normal*)*
+\)                           #                       )
+)    #         special
+[^\\\x80-\xff\n\015()] *                         #         normal*
+)*                                  #            )*
+\)                             #                )
+[\040\t]* )*    # If comment found, allow more spaces.
+# optional trailing comments
+)?     #       optional route
+(?:
+[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+    # some number of atom characters...
+(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom
+# Atom
+|                       #  or
+"                                     # "
+[^\\\x80-\xff\n\015"] *                            #   normal
+(?:  \\ [^\x80-\xff]  [^\\\x80-\xff\n\015"] * )*        #   ( special normal* )*
+"                                     #        "
+# Quoted string
+)
+[\040\t]*                    # Nab whitespace.
+(?:
+\(                              #  (
+[^\\\x80-\xff\n\015()] *                             #     normal*
+(?:                                 #       (
+(?:  \\ [^\x80-\xff]  |
+\(                            #  (
+[^\\\x80-\xff\n\015()] *                            #     normal*
+(?:  \\ [^\x80-\xff]   [^\\\x80-\xff\n\015()] * )*        #     (special normal*)*
+\)                           #                       )
+)    #         special
+[^\\\x80-\xff\n\015()] *                         #         normal*
+)*                                  #            )*
+\)                             #                )
+[\040\t]* )*    # If comment found, allow more spaces.
+(?:
+\.
+[\040\t]*                    # Nab whitespace.
+(?:
+\(                              #  (
+[^\\\x80-\xff\n\015()] *                             #     normal*
+(?:                                 #       (
+(?:  \\ [^\x80-\xff]  |
+\(                            #  (
+[^\\\x80-\xff\n\015()] *                            #     normal*
+(?:  \\ [^\x80-\xff]   [^\\\x80-\xff\n\015()] * )*        #     (special normal*)*
+\)                           #                       )
+)    #         special
+[^\\\x80-\xff\n\015()] *                         #         normal*
+)*                                  #            )*
+\)                             #                )
+[\040\t]* )*    # If comment found, allow more spaces.
+(?:
+[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+    # some number of atom characters...
+(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom
+# Atom
+|                       #  or
+"                                     # "
+[^\\\x80-\xff\n\015"] *                            #   normal
+(?:  \\ [^\x80-\xff]  [^\\\x80-\xff\n\015"] * )*        #   ( special normal* )*
+"                                     #        "
+# Quoted string
+)
+[\040\t]*                    # Nab whitespace.
+(?:
+\(                              #  (
+[^\\\x80-\xff\n\015()] *                             #     normal*
+(?:                                 #       (
+(?:  \\ [^\x80-\xff]  |
+\(                            #  (
+[^\\\x80-\xff\n\015()] *                            #     normal*
+(?:  \\ [^\x80-\xff]   [^\\\x80-\xff\n\015()] * )*        #     (special normal*)*
+\)                           #                       )
+)    #         special
+[^\\\x80-\xff\n\015()] *                         #         normal*
+)*                                  #            )*
+\)                             #                )
+[\040\t]* )*    # If comment found, allow more spaces.
+# additional words
+)*
+@
+[\040\t]*                    # Nab whitespace.
+(?:
+\(                              #  (
+[^\\\x80-\xff\n\015()] *                             #     normal*
+(?:                                 #       (
+(?:  \\ [^\x80-\xff]  |
+\(                            #  (
+[^\\\x80-\xff\n\015()] *                            #     normal*
+(?:  \\ [^\x80-\xff]   [^\\\x80-\xff\n\015()] * )*        #     (special normal*)*
+\)                           #                       )
+)    #         special
+[^\\\x80-\xff\n\015()] *                         #         normal*
+)*                                  #            )*
+\)                             #                )
+[\040\t]* )*    # If comment found, allow more spaces.
+(?:
+[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+    # some number of atom characters...
+(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom
+|
+\[                            # [
+(?: [^\\\x80-\xff\n\015\[\]] |  \\ [^\x80-\xff]  )*     #    stuff
+\]                           #           ]
+)
+[\040\t]*                    # Nab whitespace.
+(?:
+\(                              #  (
+[^\\\x80-\xff\n\015()] *                             #     normal*
+(?:                                 #       (
+(?:  \\ [^\x80-\xff]  |
+\(                            #  (
+[^\\\x80-\xff\n\015()] *                            #     normal*
+(?:  \\ [^\x80-\xff]   [^\\\x80-\xff\n\015()] * )*        #     (special normal*)*
+\)                           #                       )
+)    #         special
+[^\\\x80-\xff\n\015()] *                         #         normal*
+)*                                  #            )*
+\)                             #                )
+[\040\t]* )*    # If comment found, allow more spaces.
+# optional trailing comments
+(?:
+\.
+[\040\t]*                    # Nab whitespace.
+(?:
+\(                              #  (
+[^\\\x80-\xff\n\015()] *                             #     normal*
+(?:                                 #       (
+(?:  \\ [^\x80-\xff]  |
+\(                            #  (
+[^\\\x80-\xff\n\015()] *                            #     normal*
+(?:  \\ [^\x80-\xff]   [^\\\x80-\xff\n\015()] * )*        #     (special normal*)*
+\)                           #                       )
+)    #         special
+[^\\\x80-\xff\n\015()] *                         #         normal*
+)*                                  #            )*
+\)                             #                )
+[\040\t]* )*    # If comment found, allow more spaces.
+(?:
+[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+    # some number of atom characters...
+(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom
+|
+\[                            # [
+(?: [^\\\x80-\xff\n\015\[\]] |  \\ [^\x80-\xff]  )*     #    stuff
+\]                           #           ]
+)
+[\040\t]*                    # Nab whitespace.
+(?:
+\(                              #  (
+[^\\\x80-\xff\n\015()] *                             #     normal*
+(?:                                 #       (
+(?:  \\ [^\x80-\xff]  |
+\(                            #  (
+[^\\\x80-\xff\n\015()] *                            #     normal*
+(?:  \\ [^\x80-\xff]   [^\\\x80-\xff\n\015()] * )*        #     (special normal*)*
+\)                           #                       )
+)    #         special
+[^\\\x80-\xff\n\015()] *                         #         normal*
+)*                                  #            )*
+\)                             #                )
+[\040\t]* )*    # If comment found, allow more spaces.
+# optional trailing comments
+)*
+#       address spec
+>                    #                 >
+# name and address
+)
+/x
+    Alan Other <user\@dom.ain>
+    <user\@dom.ain>
+    user\@dom.ain
+    \"A. Other\" <user.1234\@dom.ain> (a comment)
+    A. Other <user.1234\@dom.ain> (a comment)
+    \"/s=user/ou=host/o=place/prmd=uu.yy/admd= /c=gb/\"\@x400-re.lay
+    A missing angle <user\@some.where
+    *** Failers
+    The quick brown fox
+
+/abc\0def\00pqr\000xyz\0000AB/
+    abc\0def\00pqr\000xyz\0000AB
+    abc456 abc\0def\00pqr\000xyz\0000ABCDE
+
+/abc\x0def\x00pqr\x000xyz\x0000AB/
+    abc\x0def\x00pqr\x000xyz\x0000AB
+    abc456 abc\x0def\x00pqr\x000xyz\x0000ABCDE
+
+/^[\000-\037]/
+    \0A
+    \01B
+    \037C
+
+/\0*/
+    \0\0\0\0
+
+/A\x0{2,3}Z/
+    The A\x0\x0Z
+    An A\0\x0\0Z
+    *** Failers
+    A\0Z
+    A\0\x0\0\x0Z
+
+/^(cow|)\1(bell)/
+    cowcowbell
+    bell
+    *** Failers
+    cowbell
+
+/^\s/
+    \040abc
+    \x0cabc
+    \nabc
+    \rabc
+    \tabc
+    *** Failers
+    abc
+
+/^a	b
+      c/x
+    abc
+
+/^(a|)\1*b/
+    ab
+    aaaab
+    b
+    *** Failers
+    acb
+
+/^(a|)\1+b/
+    aab
+    aaaab
+    b
+    *** Failers
+    ab
+
+/^(a|)\1?b/
+    ab
+    aab
+    b
+    *** Failers
+    acb
+
+/^(a|)\1{2}b/
+    aaab
+    b
+    *** Failers
+    ab
+    aab
+    aaaab
+
+/^(a|)\1{2,3}b/
+    aaab
+    aaaab
+    b
+    *** Failers
+    ab
+    aab
+    aaaaab
+
+/ab{1,3}bc/
+    abbbbc
+    abbbc
+    abbc
+    *** Failers
+    abc
+    abbbbbc
+
+/([^.]*)\.([^:]*):[T ]+(.*)/
+    track1.title:TBlah blah blah
+
+/([^.]*)\.([^:]*):[T ]+(.*)/i
+    track1.title:TBlah blah blah
+
+/([^.]*)\.([^:]*):[t ]+(.*)/i
+    track1.title:TBlah blah blah
+
+/^[W-c]+$/
+    WXY_^abc
+    *** Failers
+    wxy
+
+/^[W-c]+$/i
+    WXY_^abc
+    wxy_^ABC
+
+/^[\x3f-\x5F]+$/i
+    WXY_^abc
+    wxy_^ABC
+
+/^abc$/m
+    abc
+    qqq\nabc
+    abc\nzzz
+    qqq\nabc\nzzz
+
+/^abc$/
+    abc
+    *** Failers
+    qqq\nabc
+    abc\nzzz
+    qqq\nabc\nzzz
+
+/\Aabc\Z/m
+    abc
+    abc\n 
+    *** Failers
+    qqq\nabc
+    abc\nzzz
+    qqq\nabc\nzzz
+    
+/\A(.)*\Z/s
+    abc\ndef
+
+/\A(.)*\Z/m
+    *** Failers
+    abc\ndef
+
+/(?:b)|(?::+)/
+    b::c
+    c::b
+
+/[-az]+/
+    az-
+    *** Failers
+    b
+
+/[az-]+/
+    za-
+    *** Failers
+    b
+
+/[a\-z]+/
+    a-z
+    *** Failers
+    b
+
+/[a-z]+/
+    abcdxyz
+
+/[\d-]+/
+    12-34
+    *** Failers
+    aaa
+
+/[\d-z]+/
+    12-34z
+    *** Failers
+    aaa
+
+/\x5c/
+    \\
+
+/\x20Z/
+    the Zoo
+    *** Failers
+    Zulu
+
+/(abc)\1/i
+    abcabc
+    ABCabc
+    abcABC
+
+/ab{3cd/
+    ab{3cd
+
+/ab{3,cd/
+    ab{3,cd
+
+/ab{3,4a}cd/
+    ab{3,4a}cd
+
+/{4,5a}bc/
+    {4,5a}bc
+
+/abc$/
+    abc
+    abc\n
+    *** Failers
+    abc\ndef
+
+/(abc)\123/
+    abc\x53
+
+/(abc)\223/
+    abc\x93
+
+/(abc)\323/
+    abc\xd3
+
+/(abc)\100/
+    abc\x40
+    abc\100
+
+/(abc)\1000/
+    abc\x400
+    abc\x40\x30
+    abc\1000
+    abc\100\x30
+    abc\100\060
+    abc\100\60
+
+/abc\81/
+    abc\081
+    abc\0\x38\x31
+
+/abc\91/
+    abc\091
+    abc\0\x39\x31
+
+/(a)(b)(c)(d)(e)(f)(g)(h)(i)(j)(k)(l)\12\123/
+    abcdefghijkllS
+
+/(a)(b)(c)(d)(e)(f)(g)(h)(i)(j)(k)\12\123/
+    abcdefghijk\12S
+
+/ab\idef/
+    abidef
+
+/a{0}bc/
+    bc
+
+/(a|(bc)){0,0}?xyz/
+    xyz
+
+/abc[\10]de/
+    abc\010de
+
+/abc[\1]de/
+    abc\1de
+
+/(abc)[\1]de/
+    abc\1de
+
+/(?s)a.b/
+    a\nb
+
+/^([^a])([^\b])([^c]*)([^d]{3,4})/
+    baNOTccccd
+    baNOTcccd
+    baNOTccd
+    bacccd
+    *** Failers
+    anything
+    b\bc   
+    baccd
+
+/[^a]/
+    Abc
+  
+/[^a]/i
+    Abc 
+
+/[^a]+/
+    AAAaAbc
+  
+/[^a]+/i
+    AAAaAbc 
+
+/[^a]+/
+    bbb\nccc
+   
+/[^k]$/
+    abc
+    *** Failers
+    abk   
+   
+/[^k]{2,3}$/
+    abc
+    kbc
+    kabc 
+    *** Failers
+    abk
+    akb
+    akk 
+
+/^\d{8,}\@.+[^k]$/
+    12345678\@a.b.c.d
+    123456789\@x.y.z
+    *** Failers
+    12345678\@x.y.uk
+    1234567\@a.b.c.d       
+
+/(a)\1{8,}/
+    aaaaaaaaa
+    aaaaaaaaaa
+    *** Failers
+    aaaaaaa   
+
+/[^a]/
+    aaaabcd
+    aaAabcd 
+
+/[^a]/i
+    aaaabcd
+    aaAabcd 
+
+/[^az]/
+    aaaabcd
+    aaAabcd 
+
+/[^az]/i
+    aaaabcd
+    aaAabcd 
+
+/\000\001\002\003\004\005\006\007\010\011\012\013\014\015\016\017\020\021\022\023\024\025\026\027\030\031\032\033\034\035\036\037\040\041\042\043\044\045\046\047\050\051\052\053\054\055\056\057\060\061\062\063\064\065\066\067\070\071\072\073\074\075\076\077\100\101\102\103\104\105\106\107\110\111\112\113\114\115\116\117\120\121\122\123\124\125\126\127\130\131\132\133\134\135\136\137\140\141\142\143\144\145\146\147\150\151\152\153\154\155\156\157\160\161\162\163\164\165\166\167\170\171\172\173\174\175\176\177\200\201\202\203\204\205\206\207\210\211\212\213\214\215\216\217\220\221\222\223\224\225\226\227\230\231\232\233\234\235\236\237\240\241\242\243\244\245\246\247\250\251\252\253\254\255\256\257\260\261\262\263\264\265\266\267\270\271\272\273\274\275\276\277\300\301\302\303\304\305\306\307\310\311\312\313\314\315\316\317\320\321\322\323\324\325\326\327\330\331\332\333\334\335\336\337\340\341\342\343\344\345\346\347\350\351\352\353\354\355\356\357\360\361\362\363\364\365\366\367\370\371\372\373\374\375\376\377/
+ \000\001\002\003\004\005\006\007\010\011\012\013\014\015\016\017\020\021\022\023\024\025\026\027\030\031\032\033\034\035\036\037\040\041\042\043\044\045\046\047\050\051\052\053\054\055\056\057\060\061\062\063\064\065\066\067\070\071\072\073\074\075\076\077\100\101\102\103\104\105\106\107\110\111\112\113\114\115\116\117\120\121\122\123\124\125\126\127\130\131\132\133\134\135\136\137\140\141\142\143\144\145\146\147\150\151\152\153\154\155\156\157\160\161\162\163\164\165\166\167\170\171\172\173\174\175\176\177\200\201\202\203\204\205\206\207\210\211\212\213\214\215\216\217\220\221\222\223\224\225\226\227\230\231\232\233\234\235\236\237\240\241\242\243\244\245\246\247\250\251\252\253\254\255\256\257\260\261\262\263\264\265\266\267\270\271\272\273\274\275\276\277\300\301\302\303\304\305\306\307\310\311\312\313\314\315\316\317\320\321\322\323\324\325\326\327\330\331\332\333\334\335\336\337\340\341\342\343\344\345\346\347\350\351\352\353\354\355\356\357\360\361\362\363\364\365\366\367\370\371\372\373\374\375\376\377
+
+/P[^*]TAIRE[^*]{1,6}?LL/
+    xxxxxxxxxxxPSTAIREISLLxxxxxxxxx
+
+/P[^*]TAIRE[^*]{1,}?LL/
+    xxxxxxxxxxxPSTAIREISLLxxxxxxxxx
+
+/(\.\d\d[1-9]?)\d+/
+    1.230003938
+    1.875000282   
+    1.235  
+                  
+/(\.\d\d((?=0)|\d(?=\d)))/
+    1.230003938      
+    1.875000282
+    *** Failers 
+    1.235 
+    
+/a(?)b/
+    ab 
+ 
+/\b(foo)\s+(\w+)/i
+    Food is on the foo table
+    
+/foo(.*)bar/
+    The food is under the bar in the barn.
+    
+/foo(.*?)bar/  
+    The food is under the bar in the barn.
+
+/(.*)(\d*)/
+    I have 2 numbers: 53147
+    
+/(.*)(\d+)/
+    I have 2 numbers: 53147
+ 
+/(.*?)(\d*)/
+    I have 2 numbers: 53147
+
+/(.*?)(\d+)/
+    I have 2 numbers: 53147
+
+/(.*)(\d+)$/
+    I have 2 numbers: 53147
+
+/(.*?)(\d+)$/
+    I have 2 numbers: 53147
+
+/(.*)\b(\d+)$/
+    I have 2 numbers: 53147
+
+/(.*\D)(\d+)$/
+    I have 2 numbers: 53147
+
+/^\D*(?!123)/
+    ABC123
+     
+/^(\D*)(?=\d)(?!123)/
+    ABC445
+    *** Failers
+    ABC123
+    
+/^[W-]46]/
+    W46]789 
+    -46]789
+    *** Failers
+    Wall
+    Zebra
+    42
+    [abcd] 
+    ]abcd[
+       
+/^[W-\]46]/
+    W46]789 
+    Wall
+    Zebra
+    Xylophone  
+    42
+    [abcd] 
+    ]abcd[
+    \\backslash 
+    *** Failers
+    -46]789
+    well
+    
+/\d\d\/\d\d\/\d\d\d\d/
+    01/01/2000
+
+/word (?:[a-zA-Z0-9]+ ){0,10}otherword/
+  word cat dog elephant mussel cow horse canary baboon snake shark otherword
+  word cat dog elephant mussel cow horse canary baboon snake shark
+
+/word (?:[a-zA-Z0-9]+ ){0,300}otherword/
+  word cat dog elephant mussel cow horse canary baboon snake shark the quick brown fox and the lazy dog and several other words getting close to thirty by now I hope
+
+/^(a){0,0}/
+    bcd
+    abc
+    aab     
+
+/^(a){0,1}/
+    bcd
+    abc
+    aab  
+
+/^(a){0,2}/
+    bcd
+    abc
+    aab  
+
+/^(a){0,3}/
+    bcd
+    abc
+    aab
+    aaa   
+
+/^(a){0,}/
+    bcd
+    abc
+    aab
+    aaa
+    aaaaaaaa    
+
+/^(a){1,1}/
+    bcd
+    abc
+    aab  
+
+/^(a){1,2}/
+    bcd
+    abc
+    aab  
+
+/^(a){1,3}/
+    bcd
+    abc
+    aab
+    aaa   
+
+/^(a){1,}/
+    bcd
+    abc
+    aab
+    aaa
+    aaaaaaaa    
+
+/.*\.gif/
+    borfle\nbib.gif\nno
+
+/.{0,}\.gif/
+    borfle\nbib.gif\nno
+
+/.*\.gif/m
+    borfle\nbib.gif\nno
+
+/.*\.gif/s
+    borfle\nbib.gif\nno
+
+/.*\.gif/ms
+    borfle\nbib.gif\nno
+    
+/.*$/
+    borfle\nbib.gif\nno
+
+/.*$/m
+    borfle\nbib.gif\nno
+
+/.*$/s
+    borfle\nbib.gif\nno
+
+/.*$/ms
+    borfle\nbib.gif\nno
+    
+/.*$/
+    borfle\nbib.gif\nno\n
+
+/.*$/m
+    borfle\nbib.gif\nno\n
+
+/.*$/s
+    borfle\nbib.gif\nno\n
+
+/.*$/ms
+    borfle\nbib.gif\nno\n
+    
+/(.*X|^B)/
+    abcde\n1234Xyz
+    BarFoo 
+    *** Failers
+    abcde\nBar  
+
+/(.*X|^B)/m
+    abcde\n1234Xyz
+    BarFoo 
+    abcde\nBar  
+
+/(.*X|^B)/s
+    abcde\n1234Xyz
+    BarFoo 
+    *** Failers
+    abcde\nBar  
+
+/(.*X|^B)/ms
+    abcde\n1234Xyz
+    BarFoo 
+    abcde\nBar  
+
+/(?s)(.*X|^B)/
+    abcde\n1234Xyz
+    BarFoo 
+    *** Failers 
+    abcde\nBar  
+
+/(?s:.*X|^B)/
+    abcde\n1234Xyz
+    BarFoo 
+    *** Failers 
+    abcde\nBar  
+
+/^.*B/
+    **** Failers
+    abc\nB
+     
+/(?s)^.*B/
+    abc\nB
+
+/(?m)^.*B/
+    abc\nB
+     
+/(?ms)^.*B/
+    abc\nB
+
+/(?ms)^B/
+    abc\nB
+
+/(?s)B$/
+    B\n
+
+/^[0-9][0-9][0-9][0-9][0-9][0-9][0-9][0-9][0-9][0-9][0-9][0-9]/
+    123456654321
+  
+/^\d\d\d\d\d\d\d\d\d\d\d\d/
+    123456654321 
+
+/^[\d][\d][\d][\d][\d][\d][\d][\d][\d][\d][\d][\d]/
+    123456654321
+  
+/^[abc]{12}/
+    abcabcabcabc
+    
+/^[a-c]{12}/
+    abcabcabcabc
+    
+/^(a|b|c){12}/
+    abcabcabcabc 
+
+/^[abcdefghijklmnopqrstuvwxy0123456789]/
+    n
+    *** Failers 
+    z 
+
+/abcde{0,0}/
+    abcd
+    *** Failers
+    abce  
+
+/ab[cd]{0,0}e/
+    abe
+    *** Failers
+    abcde 
+    
+/ab(c){0,0}d/
+    abd
+    *** Failers
+    abcd   
+
+/a(b*)/
+    a
+    ab
+    abbbb
+    *** Failers
+    bbbbb    
+    
+/ab\d{0}e/
+    abe
+    *** Failers
+    ab1e   
+    
+/"([^\\"]+|\\.)*"/
+    the \"quick\" brown fox
+    \"the \\\"quick\\\" brown fox\" 
+
+/.*?/g+
+    abc
+  
+/\b/g+
+    abc 
+
+/\b/+g
+    abc 
+
+//g
+    abc
+
+/<tr([\w\W\s\d][^<>]{0,})><TD([\w\W\s\d][^<>]{0,})>([\d]{0,}\.)(.*)((<BR>([\w\W\s\d][^<>]{0,})|[\s]{0,}))<\/a><\/TD><TD([\w\W\s\d][^<>]{0,})>([\w\W\s\d][^<>]{0,})<\/TD><TD([\w\W\s\d][^<>]{0,})>([\w\W\s\d][^<>]{0,})<\/TD><\/TR>/is
+  <TR BGCOLOR='#DBE9E9'><TD align=left valign=top>43.<a href='joblist.cfm?JobID=94 6735&Keyword='>Word Processor<BR>(N-1286)</a></TD><TD align=left valign=top>Lega lstaff.com</TD><TD align=left valign=top>CA - Statewide</TD></TR>
+
+/a[^a]b/
+    acb
+    a\nb
+    
+/a.b/
+    acb
+    *** Failers 
+    a\nb   
+    
+/a[^a]b/s
+    acb
+    a\nb  
+    
+/a.b/s
+    acb
+    a\nb  
+
+/^(b+?|a){1,2}?c/
+    bac
+    bbac
+    bbbac
+    bbbbac
+    bbbbbac 
+
+/^(b+|a){1,2}?c/
+    bac
+    bbac
+    bbbac
+    bbbbac
+    bbbbbac 
+    
+/(?!\A)x/m
+    x\nb\n
+    a\bx\n  
+    
+/\x0{ab}/
+    \0{ab} 
+
+/(A|B)*?CD/
+    CD 
+    
+/(A|B)*CD/
+    CD 
+
+/(AB)*?\1/
+    ABABAB
+
+/(AB)*\1/
+    ABABAB
+    
+/(?<!bar)foo/
+    foo
+    catfood
+    arfootle
+    rfoosh
+    *** Failers
+    barfoo
+    towbarfoo
+
+/\w{3}(?<!bar)foo/
+    catfood
+    *** Failers
+    foo
+    barfoo
+    towbarfoo
+
+/(?<=(foo)a)bar/
+    fooabar
+    *** Failers
+    bar
+    foobbar
+      
+/\Aabc\z/m
+    abc
+    *** Failers
+    abc\n   
+    qqq\nabc
+    abc\nzzz
+    qqq\nabc\nzzz
+
+"(?>.*/)foo"
+    /this/is/a/very/long/line/in/deed/with/very/many/slashes/in/it/you/see/
+
+"(?>.*/)foo"
+    /this/is/a/very/long/line/in/deed/with/very/many/slashes/in/and/foo
+
+/(?>(\.\d\d[1-9]?))\d+/
+    1.230003938
+    1.875000282
+    *** Failers 
+    1.235 
+
+/^((?>\w+)|(?>\s+))*$/
+    now is the time for all good men to come to the aid of the party
+    *** Failers
+    this is not a line with only words and spaces!
+    
+/(\d+)(\w)/
+    12345a
+    12345+ 
+
+/((?>\d+))(\w)/
+    12345a
+    *** Failers
+    12345+ 
+
+/(?>a+)b/
+    aaab
+
+/((?>a+)b)/
+    aaab
+
+/(?>(a+))b/
+    aaab
+
+/(?>b)+/
+    aaabbbccc
+
+/(?>a+|b+|c+)*c/
+    aaabbbbccccd
+
+/((?>[^()]+)|\([^()]*\))+/
+    ((abc(ade)ufh()()x
+    
+/\(((?>[^()]+)|\([^()]+\))+\)/ 
+    (abc)
+    (abc(def)xyz)
+    *** Failers
+    ((()aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa   
+
+/a(?-i)b/i
+    ab
+    Ab
+    *** Failers 
+    aB
+    AB
+        
+/(a (?x)b c)d e/
+    a bcd e
+    *** Failers
+    a b cd e
+    abcd e   
+    a bcde 
+ 
+/(a b(?x)c d (?-x)e f)/
+    a bcde f
+    *** Failers
+    abcdef  
+
+/(a(?i)b)c/
+    abc
+    aBc
+    *** Failers
+    abC
+    aBC  
+    Abc
+    ABc
+    ABC
+    AbC
+    
+/a(?i:b)c/
+    abc
+    aBc
+    *** Failers 
+    ABC
+    abC
+    aBC
+    
+/a(?i:b)*c/
+    aBc
+    aBBc
+    *** Failers 
+    aBC
+    aBBC
+    
+/a(?=b(?i)c)\w\wd/
+    abcd
+    abCd
+    *** Failers
+    aBCd
+    abcD     
+    
+/(?s-i:more.*than).*million/i
+    more than million
+    more than MILLION
+    more \n than Million 
+    *** Failers
+    MORE THAN MILLION    
+    more \n than \n million 
+
+/(?:(?s-i)more.*than).*million/i
+    more than million
+    more than MILLION
+    more \n than Million 
+    *** Failers
+    MORE THAN MILLION    
+    more \n than \n million 
+    
+/(?>a(?i)b+)+c/ 
+    abc
+    aBbc
+    aBBc 
+    *** Failers
+    Abc
+    abAb    
+    abbC 
+    
+/(?=a(?i)b)\w\wc/
+    abc
+    aBc
+    *** Failers
+    Ab 
+    abC
+    aBC     
+    
+/(?<=a(?i)b)(\w\w)c/
+    abxxc
+    aBxxc
+    *** Failers
+    Abxxc
+    ABxxc
+    abxxC      
+
+/(?:(a)|b)(?(1)A|B)/
+    aA
+    bB
+    *** Failers
+    aB
+    bA    
+
+/^(a)?(?(1)a|b)+$/
+    aa
+    b
+    bb  
+    *** Failers
+    ab   
+
+/^(?(?=abc)\w{3}:|\d\d)$/
+    abc:
+    12
+    *** Failers
+    123
+    xyz    
+
+/^(?(?!abc)\d\d|\w{3}:)$/
+    abc:
+    12
+    *** Failers
+    123
+    xyz    
+    
+/(?(?<=foo)bar|cat)/
+    foobar
+    cat
+    fcat
+    focat   
+    *** Failers
+    foocat  
+
+/(?(?<!foo)cat|bar)/
+    foobar
+    cat
+    fcat
+    focat   
+    *** Failers
+    foocat  
+
+/( \( )? [^()]+ (?(1) \) |) /x
+    abcd
+    (abcd)
+    the quick (abcd) fox
+    (abcd   
+
+/( \( )? [^()]+ (?(1) \) ) /x
+    abcd
+    (abcd)
+    the quick (abcd) fox
+    (abcd   
+
+/^(?(2)a|(1)(2))+$/
+    12
+    12a
+    12aa
+    *** Failers
+    1234    
+
+/((?i)blah)\s+\1/
+    blah blah
+    BLAH BLAH
+    Blah Blah
+    blaH blaH
+    *** Failers
+    blah BLAH
+    Blah blah      
+    blaH blah 
+
+/((?i)blah)\s+(?i:\1)/
+    blah blah
+    BLAH BLAH
+    Blah Blah
+    blaH blaH
+    blah BLAH
+    Blah blah      
+    blaH blah 
+
+/(?>a*)*/
+    a
+    aa
+    aaaa
+    
+/(abc|)+/
+    abc
+    abcabc
+    abcabcabc
+    xyz      
+
+/([a]*)*/
+    a
+    aaaaa 
+ 
+/([ab]*)*/
+    a
+    b
+    ababab
+    aaaabcde
+    bbbb    
+ 
+/([^a]*)*/
+    b
+    bbbb
+    aaa   
+ 
+/([^ab]*)*/
+    cccc
+    abab  
+ 
+/([a]*?)*/
+    a
+    aaaa 
+ 
+/([ab]*?)*/
+    a
+    b
+    abab
+    baba   
+ 
+/([^a]*?)*/
+    b
+    bbbb
+    aaa   
+ 
+/([^ab]*?)*/
+    c
+    cccc
+    baba   
+ 
+/(?>a*)*/
+    a
+    aaabcde 
+ 
+/((?>a*))*/
+    aaaaa
+    aabbaa 
+ 
+/((?>a*?))*/
+    aaaaa
+    aabbaa 
+
+/(?(?=[^a-z]+[a-z])  \d{2}-[a-z]{3}-\d{2}  |  \d{2}-\d{2}-\d{2} ) /x
+    12-sep-98
+    12-09-98
+    *** Failers
+    sep-12-98
+        
+/(?<=(foo))bar\1/
+    foobarfoo
+    foobarfootling 
+    *** Failers
+    foobar
+    barfoo   
+
+/(?i:saturday|sunday)/
+    saturday
+    sunday
+    Saturday
+    Sunday
+    SATURDAY
+    SUNDAY
+    SunDay
+    
+/(a(?i)bc|BB)x/
+    abcx
+    aBCx
+    bbx
+    BBx
+    *** Failers
+    abcX
+    aBCX
+    bbX
+    BBX               
+
+/^([ab](?i)[cd]|[ef])/
+    ac
+    aC
+    bD
+    elephant
+    Europe 
+    frog
+    France
+    *** Failers
+    Africa     
+
+/^(ab|a(?i)[b-c](?m-i)d|x(?i)y|z)/
+    ab
+    aBd
+    xy
+    xY
+    zebra
+    Zambesi
+    *** Failers
+    aCD  
+    XY  
+
+/(?<=foo\n)^bar/m
+    foo\nbar
+    *** Failers
+    bar
+    baz\nbar   
+
+/(?<=(?<!foo)bar)baz/
+    barbaz
+    barbarbaz 
+    koobarbaz 
+    *** Failers
+    baz
+    foobarbaz 
+
+/The cases of aaaa and aaaaaa are missed out below because Perl does things/
+/differently. We know that odd, and maybe incorrect, things happen with/
+/recursive references in Perl, as far as 5.11.3 - see some stuff in test #2./
+
+/^(a\1?){4}$/
+    a
+    aa
+    aaa
+    aaaaa
+    aaaaaaa
+    aaaaaaaa
+    aaaaaaaaa
+    aaaaaaaaaa
+    aaaaaaaaaaa
+    aaaaaaaaaaaa
+    aaaaaaaaaaaaa
+    aaaaaaaaaaaaaa
+    aaaaaaaaaaaaaaa
+    aaaaaaaaaaaaaaaa               
+
+/^(a\1?)(a\1?)(a\2?)(a\3?)$/
+    a
+    aa
+    aaa
+    aaaa
+    aaaaa
+    aaaaaa
+    aaaaaaa
+    aaaaaaaa
+    aaaaaaaaa
+    aaaaaaaaaa
+    aaaaaaaaaaa
+    aaaaaaaaaaaa
+    aaaaaaaaaaaaa
+    aaaaaaaaaaaaaa
+    aaaaaaaaaaaaaaa
+    aaaaaaaaaaaaaaaa               
+
+/The following tests are taken from the Perl 5.005 test suite; some of them/
+/are compatible with 5.004, but I'd rather not have to sort them out./
+
+/abc/
+    abc
+    xabcy
+    ababc
+    *** Failers
+    xbc
+    axc
+    abx
+
+/ab*c/
+    abc
+
+/ab*bc/
+    abc
+    abbc
+    abbbbc
+
+/.{1}/
+    abbbbc
+
+/.{3,4}/
+    abbbbc
+
+/ab{0,}bc/
+    abbbbc
+
+/ab+bc/
+    abbc
+    *** Failers
+    abc
+    abq
+
+/ab{1,}bc/
+
+/ab+bc/
+    abbbbc
+
+/ab{1,}bc/
+    abbbbc
+
+/ab{1,3}bc/
+    abbbbc
+
+/ab{3,4}bc/
+    abbbbc
+
+/ab{4,5}bc/
+    *** Failers
+    abq
+    abbbbc
+
+/ab?bc/
+    abbc
+    abc
+
+/ab{0,1}bc/
+    abc
+
+/ab?bc/
+
+/ab?c/
+    abc
+
+/ab{0,1}c/
+    abc
+
+/^abc$/
+    abc
+    *** Failers
+    abbbbc
+    abcc
+
+/^abc/
+    abcc
+
+/^abc$/
+
+/abc$/
+    aabc
+    *** Failers
+    aabc
+    aabcd
+
+/^/
+    abc
+
+/$/
+    abc
+
+/a.c/
+    abc
+    axc
+
+/a.*c/
+    axyzc
+
+/a[bc]d/
+    abd
+    *** Failers
+    axyzd
+    abc
+
+/a[b-d]e/
+    ace
+
+/a[b-d]/
+    aac
+
+/a[-b]/
+    a-
+
+/a[b-]/
+    a-
+
+/a]/
+    a]
+
+/a[]]b/
+    a]b
+
+/a[^bc]d/
+    aed
+    *** Failers
+    abd
+    abd
+
+/a[^-b]c/
+    adc
+
+/a[^]b]c/
+    adc
+    *** Failers
+    a-c
+    a]c
+
+/\ba\b/
+    a-
+    -a
+    -a-
+
+/\by\b/
+    *** Failers
+    xy
+    yz
+    xyz
+
+/\Ba\B/
+    *** Failers
+    a-
+    -a
+    -a-
+
+/\By\b/
+    xy
+
+/\by\B/
+    yz
+
+/\By\B/
+    xyz
+
+/\w/
+    a
+
+/\W/
+    -
+    *** Failers
+    -
+    a
+
+/a\sb/
+    a b
+
+/a\Sb/
+    a-b
+    *** Failers
+    a-b
+    a b
+
+/\d/
+    1
+
+/\D/
+    -
+    *** Failers
+    -
+    1
+
+/[\w]/
+    a
+
+/[\W]/
+    -
+    *** Failers
+    -
+    a
+
+/a[\s]b/
+    a b
+
+/a[\S]b/
+    a-b
+    *** Failers
+    a-b
+    a b
+
+/[\d]/
+    1
+
+/[\D]/
+    -
+    *** Failers
+    -
+    1
+
+/ab|cd/
+    abc
+    abcd
+
+/()ef/
+    def
+
+/$b/
+
+/a\(b/
+    a(b
+
+/a\(*b/
+    ab
+    a((b
+
+/a\\b/
+    a\b
+
+/((a))/
+    abc
+
+/(a)b(c)/
+    abc
+
+/a+b+c/
+    aabbabc
+
+/a{1,}b{1,}c/
+    aabbabc
+
+/a.+?c/
+    abcabc
+
+/(a+|b)*/
+    ab
+
+/(a+|b){0,}/
+    ab
+
+/(a+|b)+/
+    ab
+
+/(a+|b){1,}/
+    ab
+
+/(a+|b)?/
+    ab
+
+/(a+|b){0,1}/
+    ab
+
+/[^ab]*/
+    cde
+
+/abc/
+    *** Failers
+    b
+    
+
+/a*/
+    
+
+/([abc])*d/
+    abbbcd
+
+/([abc])*bcd/
+    abcd
+
+/a|b|c|d|e/
+    e
+
+/(a|b|c|d|e)f/
+    ef
+
+/abcd*efg/
+    abcdefg
+
+/ab*/
+    xabyabbbz
+    xayabbbz
+
+/(ab|cd)e/
+    abcde
+
+/[abhgefdc]ij/
+    hij
+
+/^(ab|cd)e/
+
+/(abc|)ef/
+    abcdef
+
+/(a|b)c*d/
+    abcd
+
+/(ab|ab*)bc/
+    abc
+
+/a([bc]*)c*/
+    abc
+
+/a([bc]*)(c*d)/
+    abcd
+
+/a([bc]+)(c*d)/
+    abcd
+
+/a([bc]*)(c+d)/
+    abcd
+
+/a[bcd]*dcdcde/
+    adcdcde
+
+/a[bcd]+dcdcde/
+    *** Failers
+    abcde
+    adcdcde
+
+/(ab|a)b*c/
+    abc
+
+/((a)(b)c)(d)/
+    abcd
+
+/[a-zA-Z_][a-zA-Z0-9_]*/
+    alpha
+
+/^a(bc+|b[eh])g|.h$/
+    abh
+
+/(bc+d$|ef*g.|h?i(j|k))/
+    effgz
+    ij
+    reffgz
+    *** Failers
+    effg
+    bcdd
+
+/((((((((((a))))))))))/
+    a
+
+/((((((((((a))))))))))\10/
+    aa
+
+/(((((((((a)))))))))/
+    a
+
+/multiple words of text/
+    *** Failers
+    aa
+    uh-uh
+
+/multiple words/
+    multiple words, yeah
+
+/(.*)c(.*)/
+    abcde
+
+/\((.*), (.*)\)/
+    (a, b)
+
+/[k]/
+
+/abcd/
+    abcd
+
+/a(bc)d/
+    abcd
+
+/a[-]?c/
+    ac
+
+/(abc)\1/
+    abcabc
+
+/([a-c]*)\1/
+    abcabc
+
+/(a)|\1/
+    a
+    *** Failers
+    ab
+    x
+
+/(([a-c])b*?\2)*/
+    ababbbcbc
+
+/(([a-c])b*?\2){3}/
+    ababbbcbc
+
+/((\3|b)\2(a)x)+/
+    aaaxabaxbaaxbbax
+
+/((\3|b)\2(a)){2,}/
+    bbaababbabaaaaabbaaaabba
+
+/abc/i
+    ABC
+    XABCY
+    ABABC
+    *** Failers
+    aaxabxbaxbbx
+    XBC
+    AXC
+    ABX
+
+/ab*c/i
+    ABC
+
+/ab*bc/i
+    ABC
+    ABBC
+
+/ab*?bc/i
+    ABBBBC
+
+/ab{0,}?bc/i
+    ABBBBC
+
+/ab+?bc/i
+    ABBC
+
+/ab+bc/i
+    *** Failers
+    ABC
+    ABQ
+
+/ab{1,}bc/i
+
+/ab+bc/i
+    ABBBBC
+
+/ab{1,}?bc/i
+    ABBBBC
+
+/ab{1,3}?bc/i
+    ABBBBC
+
+/ab{3,4}?bc/i
+    ABBBBC
+
+/ab{4,5}?bc/i
+    *** Failers
+    ABQ
+    ABBBBC
+
+/ab??bc/i
+    ABBC
+    ABC
+
+/ab{0,1}?bc/i
+    ABC
+
+/ab??bc/i
+
+/ab??c/i
+    ABC
+
+/ab{0,1}?c/i
+    ABC
+
+/^abc$/i
+    ABC
+    *** Failers
+    ABBBBC
+    ABCC
+
+/^abc/i
+    ABCC
+
+/^abc$/i
+
+/abc$/i
+    AABC
+
+/^/i
+    ABC
+
+/$/i
+    ABC
+
+/a.c/i
+    ABC
+    AXC
+
+/a.*?c/i
+    AXYZC
+
+/a.*c/i
+    *** Failers
+    AABC
+    AXYZD
+
+/a[bc]d/i
+    ABD
+
+/a[b-d]e/i
+    ACE
+    *** Failers
+    ABC
+    ABD
+
+/a[b-d]/i
+    AAC
+
+/a[-b]/i
+    A-
+
+/a[b-]/i
+    A-
+
+/a]/i
+    A]
+
+/a[]]b/i
+    A]B
+
+/a[^bc]d/i
+    AED
+
+/a[^-b]c/i
+    ADC
+    *** Failers
+    ABD
+    A-C
+
+/a[^]b]c/i
+    ADC
+
+/ab|cd/i
+    ABC
+    ABCD
+
+/()ef/i
+    DEF
+
+/$b/i
+    *** Failers
+    A]C
+    B
+
+/a\(b/i
+    A(B
+
+/a\(*b/i
+    AB
+    A((B
+
+/a\\b/i
+    A\B
+
+/((a))/i
+    ABC
+
+/(a)b(c)/i
+    ABC
+
+/a+b+c/i
+    AABBABC
+
+/a{1,}b{1,}c/i
+    AABBABC
+
+/a.+?c/i
+    ABCABC
+
+/a.*?c/i
+    ABCABC
+
+/a.{0,5}?c/i
+    ABCABC
+
+/(a+|b)*/i
+    AB
+
+/(a+|b){0,}/i
+    AB
+
+/(a+|b)+/i
+    AB
+
+/(a+|b){1,}/i
+    AB
+
+/(a+|b)?/i
+    AB
+
+/(a+|b){0,1}/i
+    AB
+
+/(a+|b){0,1}?/i
+    AB
+
+/[^ab]*/i
+    CDE
+
+/abc/i
+
+/a*/i
+    
+
+/([abc])*d/i
+    ABBBCD
+
+/([abc])*bcd/i
+    ABCD
+
+/a|b|c|d|e/i
+    E
+
+/(a|b|c|d|e)f/i
+    EF
+
+/abcd*efg/i
+    ABCDEFG
+
+/ab*/i
+    XABYABBBZ
+    XAYABBBZ
+
+/(ab|cd)e/i
+    ABCDE
+
+/[abhgefdc]ij/i
+    HIJ
+
+/^(ab|cd)e/i
+    ABCDE
+
+/(abc|)ef/i
+    ABCDEF
+
+/(a|b)c*d/i
+    ABCD
+
+/(ab|ab*)bc/i
+    ABC
+
+/a([bc]*)c*/i
+    ABC
+
+/a([bc]*)(c*d)/i
+    ABCD
+
+/a([bc]+)(c*d)/i
+    ABCD
+
+/a([bc]*)(c+d)/i
+    ABCD
+
+/a[bcd]*dcdcde/i
+    ADCDCDE
+
+/a[bcd]+dcdcde/i
+
+/(ab|a)b*c/i
+    ABC
+
+/((a)(b)c)(d)/i
+    ABCD
+
+/[a-zA-Z_][a-zA-Z0-9_]*/i
+    ALPHA
+
+/^a(bc+|b[eh])g|.h$/i
+    ABH
+
+/(bc+d$|ef*g.|h?i(j|k))/i
+    EFFGZ
+    IJ
+    REFFGZ
+    *** Failers
+    ADCDCDE
+    EFFG
+    BCDD
+
+/((((((((((a))))))))))/i
+    A
+
+/((((((((((a))))))))))\10/i
+    AA
+
+/(((((((((a)))))))))/i
+    A
+
+/(?:(?:(?:(?:(?:(?:(?:(?:(?:(a))))))))))/i
+    A
+
+/(?:(?:(?:(?:(?:(?:(?:(?:(?:(a|b|c))))))))))/i
+    C
+
+/multiple words of text/i
+    *** Failers
+    AA
+    UH-UH
+
+/multiple words/i
+    MULTIPLE WORDS, YEAH
+
+/(.*)c(.*)/i
+    ABCDE
+
+/\((.*), (.*)\)/i
+    (A, B)
+
+/[k]/i
+
+/abcd/i
+    ABCD
+
+/a(bc)d/i
+    ABCD
+
+/a[-]?c/i
+    AC
+
+/(abc)\1/i
+    ABCABC
+
+/([a-c]*)\1/i
+    ABCABC
+
+/a(?!b)./
+    abad
+
+/a(?=d)./
+    abad
+
+/a(?=c|d)./
+    abad
+
+/a(?:b|c|d)(.)/
+    ace
+
+/a(?:b|c|d)*(.)/
+    ace
+
+/a(?:b|c|d)+?(.)/
+    ace
+    acdbcdbe
+
+/a(?:b|c|d)+(.)/
+    acdbcdbe
+
+/a(?:b|c|d){2}(.)/
+    acdbcdbe
+
+/a(?:b|c|d){4,5}(.)/
+    acdbcdbe
+
+/a(?:b|c|d){4,5}?(.)/
+    acdbcdbe
+
+/((foo)|(bar))*/
+    foobar
+
+/a(?:b|c|d){6,7}(.)/
+    acdbcdbe
+
+/a(?:b|c|d){6,7}?(.)/
+    acdbcdbe
+
+/a(?:b|c|d){5,6}(.)/
+    acdbcdbe
+
+/a(?:b|c|d){5,6}?(.)/
+    acdbcdbe
+
+/a(?:b|c|d){5,7}(.)/
+    acdbcdbe
+
+/a(?:b|c|d){5,7}?(.)/
+    acdbcdbe
+
+/a(?:b|(c|e){1,2}?|d)+?(.)/
+    ace
+
+/^(.+)?B/
+    AB
+
+/^([^a-z])|(\^)$/
+    .
+
+/^[<>]&/
+    <&OUT
+
+/^(a\1?){4}$/
+    aaaaaaaaaa
+    *** Failers
+    AB
+    aaaaaaaaa
+    aaaaaaaaaaa
+
+/^(a(?(1)\1)){4}$/
+    aaaaaaaaaa
+    *** Failers
+    aaaaaaaaa
+    aaaaaaaaaaa
+
+/(?:(f)(o)(o)|(b)(a)(r))*/
+    foobar
+
+/(?<=a)b/
+    ab
+    *** Failers
+    cb
+    b
+
+/(?<!c)b/
+    ab
+    b
+    b
+
+/(?:..)*a/
+    aba
+
+/(?:..)*?a/
+    aba
+
+/^(?:b|a(?=(.)))*\1/
+    abc
+
+/^(){3,5}/
+    abc
+
+/^(a+)*ax/
+    aax
+
+/^((a|b)+)*ax/
+    aax
+
+/^((a|bc)+)*ax/
+    aax
+
+/(a|x)*ab/
+    cab
+
+/(a)*ab/
+    cab
+
+/(?:(?i)a)b/
+    ab
+
+/((?i)a)b/
+    ab
+
+/(?:(?i)a)b/
+    Ab
+
+/((?i)a)b/
+    Ab
+
+/(?:(?i)a)b/
+    *** Failers
+    cb
+    aB
+
+/((?i)a)b/
+
+/(?i:a)b/
+    ab
+
+/((?i:a))b/
+    ab
+
+/(?i:a)b/
+    Ab
+
+/((?i:a))b/
+    Ab
+
+/(?i:a)b/
+    *** Failers
+    aB
+    aB
+
+/((?i:a))b/
+
+/(?:(?-i)a)b/i
+    ab
+
+/((?-i)a)b/i
+    ab
+
+/(?:(?-i)a)b/i
+    aB
+
+/((?-i)a)b/i
+    aB
+
+/(?:(?-i)a)b/i
+    *** Failers
+    aB
+    Ab
+
+/((?-i)a)b/i
+
+/(?:(?-i)a)b/i
+    aB
+
+/((?-i)a)b/i
+    aB
+
+/(?:(?-i)a)b/i
+    *** Failers
+    Ab
+    AB
+
+/((?-i)a)b/i
+
+/(?-i:a)b/i
+    ab
+
+/((?-i:a))b/i
+    ab
+
+/(?-i:a)b/i
+    aB
+
+/((?-i:a))b/i
+    aB
+
+/(?-i:a)b/i
+    *** Failers
+    AB
+    Ab
+
+/((?-i:a))b/i
+
+/(?-i:a)b/i
+    aB
+
+/((?-i:a))b/i
+    aB
+
+/(?-i:a)b/i
+    *** Failers
+    Ab
+    AB
+
+/((?-i:a))b/i
+
+/((?-i:a.))b/i
+    *** Failers
+    AB
+    a\nB
+
+/((?s-i:a.))b/i
+    a\nB
+
+/(?:c|d)(?:)(?:a(?:)(?:b)(?:b(?:))(?:b(?:)(?:b)))/
+    cabbbb
+
+/(?:c|d)(?:)(?:aaaaaaaa(?:)(?:bbbbbbbb)(?:bbbbbbbb(?:))(?:bbbbbbbb(?:)(?:bbbbbbbb)))/
+    caaaaaaaabbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbb
+
+/(ab)\d\1/i
+    Ab4ab
+    ab4Ab
+
+/foo\w*\d{4}baz/
+    foobar1234baz
+
+/x(~~)*(?:(?:F)?)?/
+    x~~
+
+/^a(?#xxx){3}c/
+    aaac
+
+/^a (?#xxx) (?#yyy) {3}c/x
+    aaac
+
+/(?<![cd])b/
+    *** Failers
+    B\nB
+    dbcb
+
+/(?<![cd])[ab]/
+    dbaacb
+
+/(?<!(c|d))b/
+
+/(?<!(c|d))[ab]/
+    dbaacb
+
+/(?<!cd)[ab]/
+    cdaccb
+
+/^(?:a?b?)*$/
+    \
+    a
+    ab
+    aaa   
+    *** Failers
+    dbcb
+    a--
+    aa-- 
+
+/((?s)^a(.))((?m)^b$)/
+    a\nb\nc\n
+
+/((?m)^b$)/
+    a\nb\nc\n
+
+/(?m)^b/
+    a\nb\n
+
+/(?m)^(b)/
+    a\nb\n
+
+/((?m)^b)/
+    a\nb\n
+
+/\n((?m)^b)/
+    a\nb\n
+
+/((?s).)c(?!.)/
+    a\nb\nc\n
+    a\nb\nc\n
+
+/((?s)b.)c(?!.)/
+    a\nb\nc\n
+    a\nb\nc\n
+
+/^b/
+
+/()^b/
+    *** Failers
+    a\nb\nc\n
+    a\nb\nc\n
+
+/((?m)^b)/
+    a\nb\nc\n
+
+/(x)?(?(1)a|b)/
+    *** Failers
+    a
+    a
+
+/(x)?(?(1)b|a)/
+    a
+
+/()?(?(1)b|a)/
+    a
+
+/()(?(1)b|a)/
+
+/()?(?(1)a|b)/
+    a
+
+/^(\()?blah(?(1)(\)))$/
+    (blah)
+    blah
+    *** Failers
+    a
+    blah)
+    (blah
+
+/^(\(+)?blah(?(1)(\)))$/
+    (blah)
+    blah
+    *** Failers
+    blah)
+    (blah
+
+/(?(?!a)a|b)/
+
+/(?(?!a)b|a)/
+    a
+
+/(?(?=a)b|a)/
+    *** Failers
+    a
+    a
+
+/(?(?=a)a|b)/
+    a
+
+/(?=(a+?))(\1ab)/
+    aaab
+
+/^(?=(a+?))\1ab/
+
+/(\w+:)+/
+    one:
+
+/$(?<=^(a))/
+    a
+
+/(?=(a+?))(\1ab)/
+    aaab
+
+/^(?=(a+?))\1ab/
+    *** Failers
+    aaab
+    aaab
+
+/([\w:]+::)?(\w+)$/
+    abcd
+    xy:z:::abcd
+
+/^[^bcd]*(c+)/
+    aexycd
+
+/(a*)b+/
+    caab
+
+/([\w:]+::)?(\w+)$/
+    abcd
+    xy:z:::abcd
+    *** Failers
+    abcd:
+    abcd:
+
+/^[^bcd]*(c+)/
+    aexycd
+
+/(>a+)ab/
+
+/(?>a+)b/
+    aaab
+
+/([[:]+)/
+    a:[b]:
+
+/([[=]+)/
+    a=[b]=
+
+/([[.]+)/
+    a.[b].
+
+/((?>a+)b)/
+    aaab
+
+/(?>(a+))b/
+    aaab
+
+/((?>[^()]+)|\([^()]*\))+/
+    ((abc(ade)ufh()()x
+
+/a\Z/
+    *** Failers
+    aaab
+    a\nb\n
+
+/b\Z/
+    a\nb\n
+
+/b\z/
+
+/b\Z/
+    a\nb
+
+/b\z/
+    a\nb
+    *** Failers
+    
+/^(?>(?(1)\.|())[^\W_](?>[a-z0-9-]*[^\W_])?)+$/
+    a
+    abc
+    a-b
+    0-9 
+    a.b
+    5.6.7  
+    the.quick.brown.fox
+    a100.b200.300c  
+    12-ab.1245 
+    *** Failers
+    \
+    .a
+    -a
+    a-
+    a.  
+    a_b 
+    a.-
+    a..  
+    ab..bc 
+    the.quick.brown.fox-
+    the.quick.brown.fox.
+    the.quick.brown.fox_
+    the.quick.brown.fox+       
+
+/(?>.*)(?<=(abcd|wxyz))/
+    alphabetabcd
+    endingwxyz
+    *** Failers
+    a rather long string that doesn't end with one of them
+
+/word (?>(?:(?!otherword)[a-zA-Z0-9]+ ){0,30})otherword/
+    word cat dog elephant mussel cow horse canary baboon snake shark otherword
+    word cat dog elephant mussel cow horse canary baboon snake shark
+  
+/word (?>[a-zA-Z0-9]+ ){0,30}otherword/
+    word cat dog elephant mussel cow horse canary baboon snake shark the quick brown fox and the lazy dog and several other words getting close to thirty by now I hope
+
+/(?<=\d{3}(?!999))foo/
+    999foo
+    123999foo 
+    *** Failers
+    123abcfoo
+    
+/(?<=(?!...999)\d{3})foo/
+    999foo
+    123999foo 
+    *** Failers
+    123abcfoo
+
+/(?<=\d{3}(?!999)...)foo/
+    123abcfoo
+    123456foo 
+    *** Failers
+    123999foo  
+    
+/(?<=\d{3}...)(?<!999)foo/
+    123abcfoo   
+    123456foo 
+    *** Failers
+    123999foo  
+
+/<a[\s]+href[\s]*=[\s]*          # find <a href=
+ ([\"\'])?                       # find single or double quote
+ (?(1) (.*?)\1 | ([^\s]+))       # if quote found, match up to next matching
+                                 # quote, otherwise match up to next space
+/isx
+    <a href=abcd xyz
+    <a href=\"abcd xyz pqr\" cats
+    <a href=\'abcd xyz pqr\' cats
+
+/<a\s+href\s*=\s*                # find <a href=
+ (["'])?                         # find single or double quote
+ (?(1) (.*?)\1 | (\S+))          # if quote found, match up to next matching
+                                 # quote, otherwise match up to next space
+/isx
+    <a href=abcd xyz
+    <a href=\"abcd xyz pqr\" cats
+    <a href       =       \'abcd xyz pqr\' cats
+
+/<a\s+href(?>\s*)=(?>\s*)        # find <a href=
+ (["'])?                         # find single or double quote
+ (?(1) (.*?)\1 | (\S+))          # if quote found, match up to next matching
+                                 # quote, otherwise match up to next space
+/isx
+    <a href=abcd xyz
+    <a href=\"abcd xyz pqr\" cats
+    <a href       =       \'abcd xyz pqr\' cats
+
+/((Z)+|A)*/
+    ZABCDEFG
+
+/(Z()|A)*/
+    ZABCDEFG
+
+/(Z(())|A)*/
+    ZABCDEFG
+
+/((?>Z)+|A)*/
+    ZABCDEFG
+
+/((?>)+|A)*/
+    ZABCDEFG
+
+/a*/g
+    abbab
+
+/^[a-\d]/
+    abcde
+    -things
+    0digit
+    *** Failers
+    bcdef    
+
+/^[\d-a]/
+    abcde
+    -things
+    0digit
+    *** Failers
+    bcdef    
+    
+/[[:space:]]+/
+    > \x09\x0a\x0c\x0d\x0b<
+     
+/[[:blank:]]+/
+    > \x09\x0a\x0c\x0d\x0b<
+     
+/[\s]+/
+    > \x09\x0a\x0c\x0d\x0b<
+     
+/\s+/
+    > \x09\x0a\x0c\x0d\x0b<
+     
+/ab/x
+    ab
+
+/(?!\A)x/m
+  a\nxb\n
+
+/(?!^)x/m
+  a\nxb\n
+
+/abc\Qabc\Eabc/
+    abcabcabc
+    
+/abc\Q(*+|\Eabc/
+    abc(*+|abc 
+
+/   abc\Q abc\Eabc/x
+    abc abcabc
+    *** Failers
+    abcabcabc  
+    
+/abc#comment
+    \Q#not comment
+    literal\E/x
+    abc#not comment\n    literal     
+
+/abc#comment
+    \Q#not comment
+    literal/x
+    abc#not comment\n    literal     
+
+/abc#comment
+    \Q#not comment
+    literal\E #more comment
+    /x
+    abc#not comment\n    literal     
+
+/abc#comment
+    \Q#not comment
+    literal\E #more comment/x
+    abc#not comment\n    literal     
+
+/\Qabc\$xyz\E/
+    abc\\\$xyz
+
+/\Qabc\E\$\Qxyz\E/
+    abc\$xyz
+
+/\Gabc/
+    abc
+    *** Failers
+    xyzabc  
+
+/\Gabc./g
+    abc1abc2xyzabc3
+
+/abc./g
+    abc1abc2xyzabc3 
+
+/a(?x: b c )d/
+    XabcdY
+    *** Failers 
+    Xa b c d Y 
+
+/((?x)x y z | a b c)/
+    XabcY
+    AxyzB 
+
+/(?i)AB(?-i)C/
+    XabCY
+    *** Failers
+    XabcY  
+
+/((?i)AB(?-i)C|D)E/
+    abCE
+    DE
+    *** Failers
+    abcE
+    abCe  
+    dE
+    De    
+
+/(.*)\d+\1/
+    abc123abc
+    abc123bc 
+
+/(.*)\d+\1/s
+    abc123abc
+    abc123bc 
+    
+/((.*))\d+\1/
+    abc123abc
+    abc123bc  
+
+/-- This tests for an IPv6 address in the form where it can have up to --/
+/-- eight components, one and only one of which is empty. This must be --/
+/-- an internal component. --/
+
+/^(?!:)                       # colon disallowed at start
+  (?:                         # start of item
+    (?: [0-9a-f]{1,4} |       # 1-4 hex digits or
+    (?(1)0 | () ) )           # if null previously matched, fail; else null
+    :                         # followed by colon
+  ){1,7}                      # end item; 1-7 of them required               
+  [0-9a-f]{1,4} $             # final hex number at end of string
+  (?(1)|.)                    # check that there was an empty component
+  /xi
+    a123::a123
+    a123:b342::abcd
+    a123:b342::324e:abcd
+    a123:ddde:b342::324e:abcd
+    a123:ddde:b342::324e:dcba:abcd
+    a123:ddde:9999:b342::324e:dcba:abcd
+    *** Failers
+    1:2:3:4:5:6:7:8
+    a123:bce:ddde:9999:b342::324e:dcba:abcd
+    a123::9999:b342::324e:dcba:abcd
+    abcde:2:3:4:5:6:7:8
+    ::1
+    abcd:fee0:123::   
+    :1
+    1:  
+
+/[z\Qa-d]\E]/
+    z
+    a
+    -
+    d
+    ] 
+    *** Failers
+    b     
+
+/[\z\C]/
+    z
+    C 
+    
+/\M/
+    M 
+    
+/(a+)*b/
+    aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa 
+    
+/(?i)reg(?:ul(?:[aä]|ae)r|ex)/
+    REGular
+    regulaer
+    Regex  
+    regulär 
+
+/Åæåä[à-ÿÀ-ß]+/
+    Åæåäà
+    Åæåäÿ
+    ÅæåäÀ
+    Åæåäß
+
+/(?<=Z)X./
+  \x84XAZXB
+
+/ab cd (?x) de fg/
+    ab cd defg
+
+/ab cd(?x) de fg/
+    ab cddefg
+    ** Failers 
+    abcddefg
+
+/(?<![^f]oo)(bar)/
+    foobarX 
+    ** Failers 
+    boobarX
+
+/(?<![^f])X/
+    offX
+    ** Failers
+    onyX  
+
+/(?<=[^f])X/
+    onyX
+    ** Failers
+    offX 
+
+/^/mg
+    a\nb\nc\n
+    \ 
+    
+/(?<=C\n)^/mg
+    A\nC\nC\n 
+
+/(?:(?(1)a|b)(X))+/
+    bXaX
+
+/(?:(?(1)\1a|b)(X|Y))+/
+    bXXaYYaY
+    bXYaXXaX  
+
+/()()()()()()()()()(?:(?(10)\10a|b)(X|Y))+/
+    bXXaYYaY
+
+/[[,abc,]+]/
+    abc]
+    a,b]
+    [a,b,c]  
+
+/(?-x: )/x
+    A\x20B
+    
+"(?x)(?-x: \s*#\s*)"
+    A # B
+    ** Failers
+    #  
+
+"(?x-is)(?:(?-ixs) \s*#\s*) include"
+    A #include
+    ** Failers
+    A#include  
+    A #Include
+
+/a*b*\w/
+    aaabbbb
+    aaaa
+    a
+
+/a*b?\w/
+    aaabbbb
+    aaaa
+    a
+
+/a*b{0,4}\w/
+    aaabbbb
+    aaaa
+    a
+
+/a*b{0,}\w/
+    aaabbbb
+    aaaa
+    a
+    
+/a*\d*\w/
+    0a
+    a 
+    
+/a*b *\w/x
+    a 
+
+/a*b#comment
+  *\w/x
+    a 
+
+/a* b *\w/x
+    a 
+
+/^\w+=.*(\\\n.*)*/
+    abc=xyz\\\npqr
+
+/(?=(\w+))\1:/
+    abcd:
+
+/^(?=(\w+))\1:/
+    abcd:
+
+/^\Eabc/
+    abc
+    
+/^[\Eabc]/
+    a
+    ** Failers 
+    E 
+    
+/^[a-\Ec]/
+    b
+    ** Failers
+    -
+    E    
+
+/^[a\E\E-\Ec]/
+    b
+    ** Failers
+    -
+    E    
+
+/^[\E\Qa\E-\Qz\E]+/
+    b
+    ** Failers
+    -  
+    
+/^[a\Q]bc\E]/
+    a
+    ]
+    c
+    
+/^[a-\Q\E]/
+    a
+    -     
+
+/^(a()*)*/
+    aaaa
+
+/^(?:a(?:(?:))*)*/
+    aaaa
+
+/^(a()+)+/
+    aaaa
+
+/^(?:a(?:(?:))+)+/
+    aaaa
+
+/(a){0,3}(?(1)b|(c|))*D/
+    abbD
+    ccccD
+    D  
+
+/(a|)*\d/
+  aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+  aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa4
+
+/(?>a|)*\d/
+  aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+  aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa4
+
+/(?:a|)*\d/
+  aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+  aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa4
+
+/\Z/g
+  abc\n
+  
+/^(?s)(?>.*)(?<!\n)/
+  abc
+  abc\n  
+
+/^(?![^\n]*\n\z)/
+  abc
+  abc\n 
+  
+/\z(?<!\n)/
+  abc
+  abc\n  
+
+/(.*(.)?)*/
+    abcd
+
+/( (A | (?(1)0|) )*   )/x
+    abcd
+
+/( ( (?(1)0|) )*   )/x
+    abcd
+
+/(  (?(1)0|)*   )/x
+    abcd
+
+/[[:abcd:xyz]]/
+    a]
+    :] 
+    
+/[abc[:x\]pqr]/
+    a
+    [
+    :
+    ]
+    p    
+
+/.*[op][xyz]/
+    fooabcfoo
+
+/(?(?=.*b)b|^)/
+   adc
+   abc 
+
+/(?(?=^.*b)b|^)/
+   adc
+   abc 
+
+/(?(?=.*b)b|^)*/
+   adc
+   abc 
+
+/(?(?=.*b)b|^)+/
+   adc
+   abc 
+
+/(?(?=b).*b|^d)/
+    abc
+
+/(?(?=.*b).*b|^d)/
+    abc
+
+/^%((?(?=[a])[^%])|b)*%$/
+    %ab%
+
+/(?i)a(?-i)b|c/
+    XabX
+    XAbX
+    CcC 
+    ** Failers
+    XABX   
+
+/[\x00-\xff\s]+/
+    \x0a\x0b\x0c\x0d
+
+/^\c/
+    ?
+
+/(abc)\1/i
+   abc
+
+/(abc)\1/
+   abc
+
+/[^a]*/i
+    12abc
+    12ABC
+
+/[^a]*+/i
+    12abc
+    12ABC
+
+/[^a]*?X/i
+    ** Failers
+    12abc
+    12ABC
+    
+/[^a]+?X/i   
+    ** Failers
+    12abc
+    12ABC
+
+/[^a]?X/i
+    12aXbcX
+    12AXBCX
+    BCX 
+
+/[^a]??X/i
+    12aXbcX
+    12AXBCX
+    BCX
+    
+/[^a]?+X/i
+    12aXbcX
+    12AXBCX
+    BCX 
+
+/[^a]{2,3}/i
+    abcdef
+    ABCDEF  
+
+/[^a]{2,3}?/i
+    abcdef
+    ABCDEF  
+
+/[^a]{2,3}+/i
+    abcdef
+    ABCDEF  
+
+/((a|)+)+Z/
+    Z
+
+/(a)b|(a)c/
+    ac
+
+/(?>(a))b|(a)c/
+    ac
+
+/(?=(a))ab|(a)c/
+    ac
+
+/((?>(a))b|(a)c)/
+    ac
+
+/((?>(a))b|(a)c)++/
+    ac
+
+/(?:(?>(a))b|(a)c)++/
+    ac
+
+/(?=(?>(a))b|(a)c)(..)/
+    ac
+
+/(?>(?>(a))b|(a)c)/
+    ac
+
+/(?:(?>([ab])))+a=/+
+    =ba=
+
+/(?>([ab]))+a=/+
+    =ba=
+
+/((?>(a+)b)+(aabab))/
+    aaaabaaabaabab
+
+/(?>a+|ab)+?c/
+    aabc
+
+/(?>a+|ab)+c/
+    aabc
+
+/(?:a+|ab)+c/
+    aabc
+
+/(?(?=(a))a)/
+    a
+
+/(?(?=(a))a)(b)/
+    ab
+
+/^(?:a|ab)++c/
+    aaaabc
+
+/^(?>a|ab)++c/
+    aaaabc
+
+/^(?:a|ab)+c/
+    aaaabc
+
+/(?=abc){3}abc/+
+    abcabcabc
+    ** Failers
+    xyz  
+    
+/(?=abc)+abc/+
+    abcabcabc
+    ** Failers
+    xyz  
+    
+/(?=abc)++abc/+
+    abcabcabc
+    ** Failers
+    xyz  
+    
+/(?=abc){0}xyz/
+    xyz 
+
+/(?=abc){1}xyz/
+    ** Failers
+    xyz 
+    
+/(?=(a))?./
+    ab
+    bc
+      
+/(?=(a))??./
+    ab
+    bc
+
+/^(?=(a)){0}b(?1)/
+    backgammon
+
+/^(?=(?1))?[az]([abc])d/
+    abd 
+    zcdxx 
+
+/^(?!a){0}\w+/
+    aaaaa
+
+/(?<=(abc))?xyz/
+    abcxyz
+    pqrxyz 
+
+/^[\g<a>]+/
+    ggg<<<aaa>>>
+    ** Failers
+    \\ga  
+    
+/^[\ga]+/
+    gggagagaxyz 
+    
+/^[:a[:digit:]]+/
+    aaaa444:::Z 
+
+/^[:a[:digit:]:b]+/
+    aaaa444:::bbbZ 
+
+/[:a]xxx[b:]/
+     :xxx:
+     
+/(?<=a{2})b/i
+    xaabc
+    ** Failers
+    xabc  
+
+/(?<!a{2})b/i
+    xabc
+    ** Failers
+    xaabc  
+
+/(?<=a\h)c/
+    xa c
+    
+/(?<=[^a]{2})b/
+    axxbc
+    aAAbc 
+    ** Failers
+    xaabc    
+
+/(?<=[^a]{2})b/i
+    axxbc  
+    ** Failers
+    aAAbc 
+    xaabc    
+
+/(?<=a\H)c/
+    abc
+
+/(?<=a\V)c/
+    abc
+    
+/(?<=a\v)c/
+    a\nc
+
+/(?(?=c)c|d)++Y/
+    XcccddYX
+
+/(?(?=c)c|d)*+Y/
+    XcccddYX
+
+/^(a{2,3}){2,}+a/
+    aaaaaaa
+    ** Failers
+    aaaaaa
+    aaaaaaaaa 
+
+/^(a{2,3})++a/
+    ** Failers
+    aaaaaa
+
+/^(a{2,3})*+a/
+    ** Failers
+    aaaaaa
+
+/ab\Cde/
+    abXde
+    
+/(?<=ab\Cde)X/
+    abZdeX
+
+/a[\CD]b/
+    aCb
+    aDb 
+
+/a[\C-X]b/
+    aJb
+
+/\H\h\V\v/
+    X X\x0a
+    X\x09X\x0b
+    ** Failers
+    \xa0 X\x0a   
+    
+/\H*\h+\V?\v{3,4}/ 
+    \x09\x20\xa0X\x0a\x0b\x0c\x0d\x0a
+    \x09\x20\xa0\x0a\x0b\x0c\x0d\x0a
+    \x09\x20\xa0\x0a\x0b\x0c
+    ** Failers 
+    \x09\x20\xa0\x0a\x0b
+     
+/\H{3,4}/
+    XY  ABCDE
+    XY  PQR ST 
+    
+/.\h{3,4}./
+    XY  AB    PQRS
+
+/\h*X\h?\H+Y\H?Z/
+    >XNNNYZ
+    >  X NYQZ
+    ** Failers
+    >XYZ   
+    >  X NY Z
+
+/\v*X\v?Y\v+Z\V*\x0a\V+\x0b\V{2,3}\x0c/
+    >XY\x0aZ\x0aA\x0bNN\x0c
+    >\x0a\x0dX\x0aY\x0a\x0bZZZ\x0aAAA\x0bNNN\x0c
+
+/(foo)\Kbar/
+    foobar
+   
+/(foo)(\Kbar|baz)/
+    foobar
+    foobaz 
+
+/(foo\Kbar)baz/
+    foobarbaz
+
+/abc\K|def\K/g+
+    Xabcdefghi
+
+/ab\Kc|de\Kf/g+
+    Xabcdefghi
+    
+/(?=C)/g+
+    ABCDECBA
+    
+/^abc\K/+
+    abcdef
+    ** Failers
+    defabcxyz   
+
+/^(a(b))\1\g1\g{1}\g-1\g{-1}\g{-02}Z/
+    ababababbbabZXXXX
+
+/(?<A>tom|bon)-\g{A}/
+    tom-tom
+    bon-bon 
+    
+/(^(a|b\g{-1}))/
+    bacxxx
+
+/(?|(abc)|(xyz))\1/
+    abcabc
+    xyzxyz 
+    ** Failers
+    abcxyz
+    xyzabc   
+    
+/(?|(abc)|(xyz))(?1)/
+    abcabc
+    xyzabc 
+    ** Failers 
+    xyzxyz 
+ 
+/^X(?5)(a)(?|(b)|(q))(c)(d)(Y)/
+    XYabcdY
+
+/^X(?7)(a)(?|(b|(r)(s))|(q))(c)(d)(Y)/
+    XYabcdY
+
+/^X(?7)(a)(?|(b|(?|(r)|(t))(s))|(q))(c)(d)(Y)/
+    XYabcdY
+
+/(?'abc'\w+):\k<abc>{2}/
+    a:aaxyz
+    ab:ababxyz
+    ** Failers
+    a:axyz
+    ab:abxyz
+
+/(?'abc'\w+):\g{abc}{2}/
+    a:aaxyz
+    ab:ababxyz
+    ** Failers
+    a:axyz
+    ab:abxyz
+
+/^(?<ab>a)? (?(<ab>)b|c) (?('ab')d|e)/x
+    abd
+    ce
+
+/^(a.)\g-1Z/
+    aXaXZ
+
+/^(a.)\g{-1}Z/
+    aXaXZ
+
+/^(?(DEFINE) (?<A> a) (?<B> b) )  (?&A) (?&B) /x
+    abcd
+
+/(?<NAME>(?&NAME_PAT))\s+(?<ADDR>(?&ADDRESS_PAT))
+  (?(DEFINE)
+  (?<NAME_PAT>[a-z]+)
+  (?<ADDRESS_PAT>\d+)
+  )/x
+    metcalfe 33
+
+/(?(DEFINE)(?<byte>2[0-4]\d|25[0-5]|1\d\d|[1-9]?\d))\b(?&byte)(\.(?&byte)){3}/
+    1.2.3.4
+    131.111.10.206
+    10.0.0.0
+    ** Failers
+    10.6
+    455.3.4.5
+
+/\b(?&byte)(\.(?&byte)){3}(?(DEFINE)(?<byte>2[0-4]\d|25[0-5]|1\d\d|[1-9]?\d))/
+    1.2.3.4
+    131.111.10.206
+    10.0.0.0
+    ** Failers
+    10.6
+    455.3.4.5
+
+/^(\w++|\s++)*$/
+    now is the time for all good men to come to the aid of the party
+    *** Failers
+    this is not a line with only words and spaces!
+
+/(\d++)(\w)/
+    12345a
+    *** Failers
+    12345+
+
+/a++b/
+    aaab
+
+/(a++b)/
+    aaab
+
+/(a++)b/
+    aaab
+
+/([^()]++|\([^()]*\))+/
+    ((abc(ade)ufh()()x
+
+/\(([^()]++|\([^()]+\))+\)/
+    (abc)
+    (abc(def)xyz)
+    *** Failers
+    ((()aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+
+/^([^()]|\((?1)*\))*$/
+    abc
+    a(b)c
+    a(b(c))d
+    *** Failers)
+    a(b(c)d
+
+/^>abc>([^()]|\((?1)*\))*<xyz<$/
+   >abc>123<xyz<
+   >abc>1(2)3<xyz<
+   >abc>(1(2)3)<xyz<
+
+/^(?:((.)(?1)\2|)|((.)(?3)\4|.))$/i
+    1221
+    Satanoscillatemymetallicsonatas
+    AmanaplanacanalPanama
+    AblewasIereIsawElba
+    *** Failers
+    Thequickbrownfox
+
+/^(\d+|\((?1)([+*-])(?1)\)|-(?1))$/
+    12
+    (((2+2)*-3)-7)
+    -12
+    *** Failers
+    ((2+2)*-3)-7)
+
+/^(x(y|(?1){2})z)/
+    xyz
+    xxyzxyzz
+    *** Failers
+    xxyzz
+    xxyzxyzxyzz
+
+/((< (?: (?(R) \d++  | [^<>]*+) | (?2)) * >))/x
+    <>
+    <abcd>
+    <abc <123> hij>
+    <abc <def> hij>
+    <abc<>def>
+    <abc<>
+    *** Failers
+    <abc
+
+/^a+(*FAIL)/
+    aaaaaa
+    
+/a+b?c+(*FAIL)/
+    aaabccc
+
+/a+b?(*PRUNE)c+(*FAIL)/
+    aaabccc
+
+/a+b?(*COMMIT)c+(*FAIL)/
+    aaabccc
+    
+/a+b?(*SKIP)c+(*FAIL)/
+    aaabcccaaabccc
+
+/^(?:aaa(*THEN)\w{6}|bbb(*THEN)\w{5}|ccc(*THEN)\w{4}|\w{3})/
+    aaaxxxxxx
+    aaa++++++ 
+    bbbxxxxx
+    bbb+++++ 
+    cccxxxx
+    ccc++++ 
+    dddddddd   
+
+/^(aaa(*THEN)\w{6}|bbb(*THEN)\w{5}|ccc(*THEN)\w{4}|\w{3})/
+    aaaxxxxxx
+    aaa++++++ 
+    bbbxxxxx
+    bbb+++++ 
+    cccxxxx
+    ccc++++ 
+    dddddddd   
+
+/a+b?(*THEN)c+(*FAIL)/
+    aaabccc
+
+/(A (A|B(*ACCEPT)|C) D)(E)/x
+    AB
+    ABX
+    AADE
+    ACDE
+    ** Failers
+    AD 
+        
+/^\W*+(?:((.)\W*+(?1)\W*+\2|)|((.)\W*+(?3)\W*+\4|\W*+.\W*+))\W*+$/i
+    1221
+    Satan, oscillate my metallic sonatas!
+    A man, a plan, a canal: Panama!
+    Able was I ere I saw Elba.
+    *** Failers
+    The quick brown fox
+
+/^((.)(?1)\2|.)$/
+    a
+    aba
+    aabaa  
+    abcdcba 
+    pqaabaaqp  
+    ablewasiereisawelba
+    rhubarb
+    the quick brown fox  
+
+/(a)(?<=b(?1))/
+    baz
+    ** Failers
+    caz  
+    
+/(?<=b(?1))(a)/
+    zbaaz
+    ** Failers
+    aaa  
+    
+/(?<X>a)(?<=b(?&X))/
+    baz
+
+/^(?|(abc)|(def))\1/
+    abcabc
+    defdef 
+    ** Failers
+    abcdef
+    defabc   
+    
+/^(?|(abc)|(def))(?1)/
+    abcabc
+    defabc
+    ** Failers
+    defdef
+    abcdef    
+
+/(?:a(?<quote> (?<apostrophe>')|(?<realquote>")) |b(?<quote> (?<apostrophe>')|(?<realquote>")) ) (?('quote')[a-z]+|[0-9]+)/xJ
+    a\"aaaaa
+    b\"aaaaa 
+    ** Failers 
+    b\"11111
+
+/(?:(?1)|B)(A(*F)|C)/
+    ABCD
+    CCD
+    ** Failers
+    CAD   
+
+/^(?:(?1)|B)(A(*F)|C)/
+    CCD
+    BCD 
+    ** Failers
+    ABCD
+    CAD
+    BAD    
+
+/(?:(?1)|B)(A(*ACCEPT)XX|C)D/
+    AAD
+    ACD
+    BAD
+    BCD
+    BAX  
+    ** Failers
+    ACX
+    ABC   
+
+/(?(DEFINE)(A))B(?1)C/
+    BAC
+
+/(?(DEFINE)((A)\2))B(?1)C/
+    BAAC
+
+/(?<pn> \( ( [^()]++ | (?&pn) )* \) )/x
+    (ab(cd)ef)
+
+/^(?!a(*SKIP)b)/
+    ac
+    
+/^(?=a(*SKIP)b|ac)/
+    ** Failers
+    ac
+    
+/^(?=a(*THEN)b|ac)/
+    ac
+    
+/^(?=a(*PRUNE)b)/
+    ab  
+    ** Failers 
+    ac
+
+/^(?=a(*ACCEPT)b)/
+    ac
+
+/^(?(?!a(*SKIP)b))/
+    ac
+
+/(?>a\Kb)/
+    ab
+
+/((?>a\Kb))/
+    ab
+
+/(a\Kb)/
+    ab
+    
+/^a\Kcz|ac/
+    ac
+    
+/(?>a\Kbz|ab)/
+    ab 
+
+/^(?&t)(?(DEFINE)(?<t>a\Kb))$/
+    ab
+
+/^([^()]|\((?1)*\))*$/
+    a(b)c
+    a(b(c)d)e 
+
+/(?P<L1>(?P<L2>0)(?P>L1)|(?P>L2))/
+    0
+    00
+    0000  
+
+/(?P<L1>(?P<L2>0)|(?P>L2)(?P>L1))/
+    0
+    00
+    0000  
+
+/--- This one does fail, as expected, in Perl. It needs the complex item at the
+     end of the pattern. A single letter instead of (B|D) makes it not fail,
+     which I think is a Perl bug. --- /
+
+/A(*COMMIT)(B|D)/
+    ACABX
+
+/--- Check the use of names for failure ---/
+
+/^(A(*PRUNE:A)B|C(*PRUNE:B)D)/K
+    ** Failers
+    AC
+    CB    
+    
+/--- Force no study, otherwise mark is not seen. The studied version is in
+     test 2 because it isn't Perl-compatible. ---/
+
+/(*MARK:A)(*SKIP:B)(C|X)/KSS
+    C
+    D
+     
+/^(A(*THEN:A)B|C(*THEN:B)D)/K
+    ** Failers
+    CB    
+
+/^(?:A(*THEN:A)B|C(*THEN:B)D)/K
+    CB    
+    
+/^(?>A(*THEN:A)B|C(*THEN:B)D)/K
+    CB    
+    
+/--- This should succeed, as the skip causes bump to offset 1 (the mark). Note
+that we have to have something complicated such as (B|Z) at the end because,
+for Perl, a simple character somehow causes an unwanted optimization to mess
+with the handling of backtracking verbs. ---/
+
+/A(*MARK:A)A+(*SKIP:A)(B|Z) | AC/xK
+    AAAC
+    
+/--- Test skipping over a non-matching mark. ---/
+
+/A(*MARK:A)A+(*MARK:B)(*SKIP:A)(B|Z) | AC/xK
+    AAAC
+    
+/--- Check shorthand for MARK ---/
+
+/A(*:A)A+(*SKIP:A)(B|Z) | AC/xK
+    AAAC
+
+/--- Don't loop! Force no study, otherwise mark is not seen. ---/
+
+/(*:A)A+(*SKIP:A)(B|Z)/KSS
+    AAAC
+
+/--- This should succeed, as a non-existent skip name disables the skip ---/ 
+
+/A(*MARK:A)A+(*SKIP:B)(B|Z) | AC/xK
+    AAAC
+
+/A(*MARK:A)A+(*SKIP:B)(B|Z) | AC(*:B)/xK
+    AAAC
+
+/--- COMMIT at the start of a pattern should act like an anchor. Again, 
+however, we need the complication for Perl. ---/
+
+/(*COMMIT)(A|P)(B|P)(C|P)/
+    ABCDEFG
+    ** Failers
+    DEFGABC  
+
+/--- COMMIT inside an atomic group can't stop backtracking over the group. ---/
+
+/(\w+)(?>b(*COMMIT))\w{2}/
+    abbb
+
+/(\w+)b(*COMMIT)\w{2}/
+    abbb
+
+/--- Check opening parens in comment when seeking forward reference. ---/ 
+
+/(?&t)(?#()(?(DEFINE)(?<t>a))/
+    bac
+
+/--- COMMIT should override THEN ---/
+
+/(?>(*COMMIT)(?>yes|no)(*THEN)(*F))?/
+  yes
+
+/(?>(*COMMIT)(yes|no)(*THEN)(*F))?/
+  yes
+
+/b?(*SKIP)c/
+    bc
+    abc
+   
+/(*SKIP)bc/
+    a
+
+/(*SKIP)b/
+    a 
+
+/(?P<abn>(?P=abn)xxx|)+/
+    xxx
+
+/(?i:([^b]))(?1)/
+    aa
+    aA     
+    ** Failers
+    ab
+    aB
+    Ba
+    ba
+
+/^(?&t)*+(?(DEFINE)(?<t>a))\w$/
+    aaaaaaX
+    ** Failers 
+    aaaaaa 
+
+/^(?&t)*(?(DEFINE)(?<t>a))\w$/
+    aaaaaaX
+    aaaaaa 
+
+/^(a)*+(\w)/
+    aaaaX
+    YZ 
+    ** Failers 
+    aaaa
+
+/^(?:a)*+(\w)/
+    aaaaX
+    YZ 
+    ** Failers 
+    aaaa
+
+/^(a)++(\w)/
+    aaaaX
+    ** Failers 
+    aaaa
+    YZ 
+
+/^(?:a)++(\w)/
+    aaaaX
+    ** Failers 
+    aaaa
+    YZ 
+
+/^(a)?+(\w)/
+    aaaaX
+    YZ 
+
+/^(?:a)?+(\w)/
+    aaaaX
+    YZ 
+
+/^(a){2,}+(\w)/
+    aaaaX
+    ** Failers
+    aaa
+    YZ 
+
+/^(?:a){2,}+(\w)/
+    aaaaX
+    ** Failers
+    aaa
+    YZ 
+
+/(a|)*(?1)b/
+    b
+    ab
+    aab  
+
+/(a)++(?1)b/
+    ** Failers
+    ab 
+    aab
+
+/(a)*+(?1)b/
+    ** Failers
+    ab
+    aab  
+
+/(?1)(?:(b)){0}/
+    b
+
+/(foo ( \( ((?:(?> [^()]+ )|(?2))*) \) ) )/x
+    foo(bar(baz)+baz(bop))
+
+/(A (A|B(*ACCEPT)|C) D)(E)/x
+    AB
+
+/\A.*?(?:a|b(*THEN)c)/
+    ba
+
+/\A.*?(?:a|bc)/
+    ba
+
+/\A.*?(a|b(*THEN)c)/
+    ba
+
+/\A.*?(a|bc)/
+    ba
+
+/\A.*?(?:a|b(*THEN)c)++/
+    ba
+
+/\A.*?(?:a|bc)++/
+    ba
+
+/\A.*?(a|b(*THEN)c)++/
+    ba
+
+/\A.*?(a|bc)++/
+    ba
+
+/\A.*?(?:a|b(*THEN)c|d)/
+    ba
+
+/\A.*?(?:a|bc|d)/
+    ba
+
+/(?:(b))++/
+    beetle
+
+/(?(?=(a(*ACCEPT)z))a)/
+    a
+
+/^(a)(?1)+ab/
+    aaaab
+    
+/^(a)(?1)++ab/
+    aaaab
+
+/^(?=a(*:M))aZ/K
+    aZbc
+
+/^(?!(*:M)b)aZ/K
+    aZbc
+
+/(?(DEFINE)(a))?b(?1)/
+    backgammon
+
+/^\N+/
+    abc\ndef
+    
+/^\N{1,}/
+    abc\ndef 
+
+/(?(R)a+|(?R)b)/
+    aaaabcde
+
+/(?(R)a+|((?R))b)/
+    aaaabcde
+
+/((?(R)a+|(?1)b))/
+    aaaabcde
+
+/((?(R1)a+|(?1)b))/
+    aaaabcde
+
+/a(*:any 
+name)/K
+    abc
+    
+/(?>(?&t)c|(?&t))(?(DEFINE)(?<t>a|b(*PRUNE)c))/
+    a
+    ba
+    bba 
+    
+/--- Checking revised (*THEN) handling ---/ 
+
+/--- Capture ---/
+
+/^.*? (a(*THEN)b) c/x
+    aabc
+
+/^.*? (a(*THEN)b|(*F)) c/x
+    aabc
+
+/^.*? ( (a(*THEN)b) | (*F) ) c/x
+    aabc
+
+/^.*? ( (a(*THEN)b) ) c/x
+    aabc
+
+/--- Non-capture ---/
+
+/^.*? (?:a(*THEN)b) c/x
+    aabc
+
+/^.*? (?:a(*THEN)b|(*F)) c/x
+    aabc
+
+/^.*? (?: (?:a(*THEN)b) | (*F) ) c/x
+    aabc
+
+/^.*? (?: (?:a(*THEN)b) ) c/x
+    aabc
+
+/--- Atomic ---/
+
+/^.*? (?>a(*THEN)b) c/x
+    aabc
+
+/^.*? (?>a(*THEN)b|(*F)) c/x
+    aabc
+
+/^.*? (?> (?>a(*THEN)b) | (*F) ) c/x
+    aabc
+
+/^.*? (?> (?>a(*THEN)b) ) c/x
+    aabc
+
+/--- Possessive capture ---/
+
+/^.*? (a(*THEN)b)++ c/x
+    aabc
+
+/^.*? (a(*THEN)b|(*F))++ c/x
+    aabc
+
+/^.*? ( (a(*THEN)b)++ | (*F) )++ c/x
+    aabc
+
+/^.*? ( (a(*THEN)b)++ )++ c/x
+    aabc
+
+/--- Possessive non-capture ---/
+
+/^.*? (?:a(*THEN)b)++ c/x
+    aabc
+
+/^.*? (?:a(*THEN)b|(*F))++ c/x
+    aabc
+
+/^.*? (?: (?:a(*THEN)b)++ | (*F) )++ c/x
+    aabc
+
+/^.*? (?: (?:a(*THEN)b)++ )++ c/x
+    aabc
+    
+/--- Condition assertion ---/
+
+/^(?(?=a(*THEN)b)ab|ac)/
+    ac
+ 
+/--- Condition ---/
+
+/^.*?(?(?=a)a|b(*THEN)c)/
+    ba
+
+/^.*?(?:(?(?=a)a|b(*THEN)c)|d)/
+    ba
+
+/^.*?(?(?=a)a(*THEN)b|c)/
+    ac
+
+/--- Assertion ---/
+
+/^.*(?=a(*THEN)b)/ 
+    aabc
+
+/------------------------------/
+
+/(?>a(*:m))/imsxSK 
+    a
+
+/(?>(a)(*:m))/imsxSK 
+    a
+
+/(?<=a(*ACCEPT)b)c/
+    xacd
+
+/(?<=(a(*ACCEPT)b))c/
+    xacd
+
+/(?<=(a(*COMMIT)b))c/
+    xabcd
+    ** Failers 
+    xacd
+    
+/(?<!a(*FAIL)b)c/
+    xcd
+    acd 
+
+/(?<=a(*:N)b)c/K
+    xabcd
+    
+/(?<=a(*PRUNE)b)c/
+    xabcd 
+
+/(?<=a(*SKIP)b)c/
+    xabcd 
+
+/(?<=a(*THEN)b)c/
+    xabcd 
+
+/(a)(?2){2}(.)/
+    abcd
+
+/(*MARK:A)(*PRUNE:B)(C|X)/KS
+    C
+    D 
+
+/(*MARK:A)(*PRUNE:B)(C|X)/KSS
+    C
+    D 
+
+/(*MARK:A)(*THEN:B)(C|X)/KS
+    C
+    D 
+
+/(*MARK:A)(*THEN:B)(C|X)/KSY
+    C
+    D 
+
+/(*MARK:A)(*THEN:B)(C|X)/KSS
+    C
+    D 
+
+/--- This should fail, as the skip causes a bump to offset 3 (the skip) ---/
+
+/A(*MARK:A)A+(*SKIP)(B|Z) | AC/xK
+    AAAC
+
+/--- Same --/
+
+/A(*MARK:A)A+(*MARK:B)(*SKIP:B)(B|Z) | AC/xK
+    AAAC
+
+/A(*:A)A+(*SKIP)(B|Z) | AC/xK
+    AAAC
+
+/--- This should fail, as a null name is the same as no name ---/
+
+/A(*MARK:A)A+(*SKIP:)(B|Z) | AC/xK
+    AAAC
+
+/--- A check on what happens after hitting a mark and them bumping along to
+something that does not even start. Perl reports tags after the failures here, 
+though it does not when the individual letters are made into something 
+more complicated. ---/
+
+/A(*:A)B|XX(*:B)Y/K
+    AABC
+    XXYZ 
+    ** Failers
+    XAQQ  
+    XAQQXZZ  
+    AXQQQ 
+    AXXQQQ 
+    
+/^(A(*THEN:A)B|C(*THEN:B)D)/K
+    AB
+    CD
+    ** Failers
+    AC
+    CB    
+    
+/^(A(*PRUNE:A)B|C(*PRUNE:B)D)/K
+    AB
+    CD
+    ** Failers
+    AC
+    CB    
+    
+/--- An empty name does not pass back an empty string. It is the same as if no
+name were given. ---/ 
+
+/^(A(*PRUNE:)B|C(*PRUNE:B)D)/K
+    AB
+    CD 
+
+/--- PRUNE goes to next bumpalong; COMMIT does not. ---/
+    
+/A(*PRUNE:A)B/K
+    ACAB
+
+/--- Mark names can be duplicated ---/
+
+/A(*:A)B|X(*:A)Y/K
+    AABC
+    XXYZ 
+    
+/b(*:m)f|a(*:n)w/K
+    aw 
+    ** Failers 
+    abc
+
+/b(*:m)f|aw/K
+    abaw
+    ** Failers 
+    abc
+    abax 
+
+/A(*MARK:A)A+(*SKIP:B)(B|Z) | AAC/xK
+    AAAC
+
+/a(*PRUNE:X)bc|qq/KY
+    ** Failers
+    axy
+
+/a(*THEN:X)bc|qq/KY
+    ** Failers
+    axy
+
+/(?=a(*MARK:A)b)..x/K
+    abxy
+    ** Failers
+    abpq  
+
+/(?=a(*MARK:A)b)..(*:Y)x/K
+    abxy
+    ** Failers
+    abpq  
+
+/(?=a(*PRUNE:A)b)..x/K
+    abxy
+    ** Failers
+    abpq  
+
+/(?=a(*PRUNE:A)b)..(*:Y)x/K
+    abxy
+    ** Failers
+    abpq  
+
+/(?=a(*THEN:A)b)..x/K
+    abxy
+    ** Failers
+    abpq  
+
+/(?=a(*THEN:A)b)..(*:Y)x/K
+    abxy
+    ** Failers
+    abpq  
+
+/(another)?(\1?)test/
+    hello world test
+
+/(another)?(\1+)test/
+    hello world test
+
+/(a(*COMMIT)b){0}a(?1)|aac/
+    aac
+
+/(?!a(*COMMIT)b)ac|cd/
+    ac
+
+/((?:a?)*)*c/
+  aac   
+
+/((?>a?)*)*c/
+  aac   
+
+/-- End of testinput1 --/
diff --git a/ext/pcre/pcrelib/testdata/testinput10 b/ext/pcre/pcrelib/testdata/testinput10
new file mode 100644
index 0000000..7856518
--- /dev/null
+++ b/ext/pcre/pcrelib/testdata/testinput10
@@ -0,0 +1,1029 @@
+/-- This set of tests check Unicode property support with the DFA matching 
+    functionality of pcre_dfa_exec(). The -dfa flag must be used with pcretest
+    when running it. --/
+
+/\pL\P{Nd}/8
+    AB
+    *** Failers
+    A0
+    00   
+
+/\X./8
+    AB
+    A\x{300}BC 
+    A\x{300}\x{301}\x{302}BC 
+    *** Failers
+    \x{300}  
+
+/\X\X/8
+    ABC
+    A\x{300}B\x{300}\x{301}C 
+    A\x{300}\x{301}\x{302}BC 
+    *** Failers
+    \x{300}  
+
+/^\pL+/8
+    abcd
+    a 
+    *** Failers 
+
+/^\PL+/8
+    1234
+    = 
+    *** Failers 
+    abcd 
+
+/^\X+/8
+    abcdA\x{300}\x{301}\x{302}
+    A\x{300}\x{301}\x{302}
+    A\x{300}\x{301}\x{302}A\x{300}\x{301}\x{302}
+    a 
+    *** Failers 
+    \x{300}\x{301}\x{302}
+
+/\X?abc/8
+    abc
+    A\x{300}abc
+    A\x{300}\x{301}\x{302}A\x{300}A\x{300}A\x{300}abcxyz
+    \x{300}abc  
+    *** Failers
+
+/^\X?abc/8
+    abc
+    A\x{300}abc
+    *** Failers
+    A\x{300}\x{301}\x{302}A\x{300}A\x{300}A\x{300}abcxyz
+    \x{300}abc  
+
+/\X*abc/8
+    abc
+    A\x{300}abc
+    A\x{300}\x{301}\x{302}A\x{300}A\x{300}A\x{300}abcxyz
+    \x{300}abc  
+    *** Failers
+
+/^\X*abc/8
+    abc
+    A\x{300}abc
+    A\x{300}\x{301}\x{302}A\x{300}A\x{300}A\x{300}abcxyz
+    *** Failers
+    \x{300}abc  
+
+/^\pL?=./8
+    A=b
+    =c 
+    *** Failers
+    1=2 
+    AAAA=b  
+
+/^\pL*=./8
+    AAAA=b
+    =c 
+    *** Failers
+    1=2  
+
+/^\X{2,3}X/8
+    A\x{300}\x{301}\x{302}A\x{300}\x{301}\x{302}X
+    A\x{300}\x{301}\x{302}A\x{300}\x{301}\x{302}A\x{300}\x{301}\x{302}X 
+    *** Failers
+    X
+    A\x{300}\x{301}\x{302}X
+    A\x{300}\x{301}\x{302}A\x{300}\x{301}\x{302}A\x{300}\x{301}\x{302}A\x{300}\x{301}\x{302}X
+
+/^\pC\pL\pM\pN\pP\pS\pZ</8
+    \x7f\x{c0}\x{30f}\x{660}\x{66c}\x{f01}\x{1680}<
+    \np\x{300}9!\$ < 
+    ** Failers 
+    ap\x{300}9!\$ < 
+  
+/^\PC/8
+    X
+    ** Failers 
+    \x7f
+  
+/^\PL/8
+    9
+    ** Failers 
+    \x{c0}
+  
+/^\PM/8
+    X
+    ** Failers 
+    \x{30f}
+  
+/^\PN/8
+    X
+    ** Failers 
+    \x{660}
+  
+/^\PP/8
+    X
+    ** Failers 
+    \x{66c}
+  
+/^\PS/8
+    X
+    ** Failers 
+    \x{f01}
+  
+/^\PZ/8
+    X
+    ** Failers 
+    \x{1680}
+    
+/^\p{Cc}/8
+    \x{017}
+    \x{09f} 
+    ** Failers
+    \x{0600} 
+  
+/^\p{Cf}/8
+    \x{601}
+    ** Failers
+    \x{09f} 
+  
+/^\p{Cn}/8
+    ** Failers
+    \x{09f} 
+  
+/^\p{Co}/8
+    \x{f8ff}
+    ** Failers
+    \x{09f} 
+  
+/^\p{Cs}/8
+    \?\x{dfff}
+    ** Failers
+    \x{09f} 
+  
+/^\p{Ll}/8
+    a
+    ** Failers 
+    Z
+    \x{e000}  
+  
+/^\p{Lm}/8
+    \x{2b0}
+    ** Failers
+    a 
+  
+/^\p{Lo}/8
+    \x{1bb}
+    ** Failers
+    a 
+    \x{2b0}
+  
+/^\p{Lt}/8
+    \x{1c5}
+    ** Failers
+    a 
+    \x{2b0}
+  
+/^\p{Lu}/8
+    A
+    ** Failers
+    \x{2b0}
+  
+/^\p{Mc}/8
+    \x{903}
+    ** Failers
+    X
+    \x{300}
+       
+/^\p{Me}/8
+    \x{488}
+    ** Failers
+    X
+    \x{903}
+    \x{300}
+  
+/^\p{Mn}/8
+    \x{300}
+    ** Failers
+    X
+    \x{903}
+  
+/^\p{Nd}+/8
+    0123456789\x{660}\x{661}\x{662}\x{663}\x{664}\x{665}\x{666}\x{667}\x{668}\x{669}\x{66a}
+    \x{6f0}\x{6f1}\x{6f2}\x{6f3}\x{6f4}\x{6f5}\x{6f6}\x{6f7}\x{6f8}\x{6f9}\x{6fa}
+    \x{966}\x{967}\x{968}\x{969}\x{96a}\x{96b}\x{96c}\x{96d}\x{96e}\x{96f}\x{970}
+    ** Failers
+    X
+  
+/^\p{Nl}/8
+    \x{16ee}
+    ** Failers
+    X
+    \x{966}
+  
+/^\p{No}/8
+    \x{b2}
+    \x{b3}
+    ** Failers
+    X
+    \x{16ee}
+  
+/^\p{Pc}/8
+    \x5f
+    \x{203f}
+    ** Failers
+    X
+    -
+    \x{58a}
+  
+/^\p{Pd}/8
+    -
+    \x{58a}
+    ** Failers
+    X
+    \x{203f}
+  
+/^\p{Pe}/8
+    )
+    ]
+    }
+    \x{f3b}
+    ** Failers
+    X
+    \x{203f}
+    (
+    [
+    {
+    \x{f3c}
+  
+/^\p{Pf}/8
+    \x{bb}
+    \x{2019}
+    ** Failers
+    X
+    \x{203f}
+  
+/^\p{Pi}/8
+    \x{ab}
+    \x{2018}
+    ** Failers
+    X
+    \x{203f}
+  
+/^\p{Po}/8
+    !
+    \x{37e}
+    ** Failers
+    X
+    \x{203f}
+  
+/^\p{Ps}/8
+    (
+    [
+    {
+    \x{f3c}
+    ** Failers
+    X
+    )
+    ]
+    }
+    \x{f3b}
+  
+/^\p{Sc}+/8
+    $\x{a2}\x{a3}\x{a4}\x{a5}\x{a6}
+    \x{9f2}
+    ** Failers
+    X
+    \x{2c2}
+  
+/^\p{Sk}/8
+    \x{2c2}
+    ** Failers
+    X
+    \x{9f2}
+  
+/^\p{Sm}+/8
+    +<|~\x{ac}\x{2044}
+    ** Failers
+    X
+    \x{9f2}
+  
+/^\p{So}/8
+    \x{a6}
+    \x{482} 
+    ** Failers
+    X
+    \x{9f2}
+  
+/^\p{Zl}/8
+    \x{2028}
+    ** Failers
+    X
+    \x{2029}
+  
+/^\p{Zp}/8
+    \x{2029}
+    ** Failers
+    X
+    \x{2028}
+  
+/^\p{Zs}/8
+    \ \
+    \x{a0}
+    \x{1680}
+    \x{180e}
+    \x{2000}
+    \x{2001}     
+    ** Failers
+    \x{2028}
+    \x{200d} 
+  
+/\p{Nd}+(..)/8
+      \x{660}\x{661}\x{662}ABC
+  
+/\p{Nd}+?(..)/8
+      \x{660}\x{661}\x{662}ABC
+  
+/\p{Nd}{2,}(..)/8
+      \x{660}\x{661}\x{662}ABC
+  
+/\p{Nd}{2,}?(..)/8
+      \x{660}\x{661}\x{662}ABC
+  
+/\p{Nd}*(..)/8
+      \x{660}\x{661}\x{662}ABC
+  
+/\p{Nd}*?(..)/8
+      \x{660}\x{661}\x{662}ABC
+  
+/\p{Nd}{2}(..)/8
+      \x{660}\x{661}\x{662}ABC
+  
+/\p{Nd}{2,3}(..)/8
+      \x{660}\x{661}\x{662}ABC
+  
+/\p{Nd}{2,3}?(..)/8
+      \x{660}\x{661}\x{662}ABC
+  
+/\p{Nd}?(..)/8
+      \x{660}\x{661}\x{662}ABC
+  
+/\p{Nd}??(..)/8
+      \x{660}\x{661}\x{662}ABC
+  
+/\p{Nd}*+(..)/8
+      \x{660}\x{661}\x{662}ABC
+  
+/\p{Nd}*+(...)/8
+      \x{660}\x{661}\x{662}ABC
+  
+/\p{Nd}*+(....)/8
+      ** Failers
+      \x{660}\x{661}\x{662}ABC
+  
+/\p{Lu}/8i
+    A
+    a\x{10a0}B 
+    ** Failers 
+    a
+    \x{1d00}  
+
+/\p{^Lu}/8i
+    1234
+    ** Failers
+    ABC 
+
+/\P{Lu}/8i
+    1234
+    ** Failers
+    ABC 
+
+/(?<=A\p{Nd})XYZ/8
+    A2XYZ
+    123A5XYZPQR
+    ABA\x{660}XYZpqr
+    ** Failers
+    AXYZ
+    XYZ     
+    
+/(?<!\pL)XYZ/8
+    1XYZ
+    AB=XYZ.. 
+    XYZ 
+    ** Failers
+    WXYZ 
+
+/[\p{Nd}]/8
+    1234
+
+/[\p{Nd}+-]+/8
+    1234
+    12-34
+    12+\x{661}-34  
+    ** Failers
+    abcd  
+
+/[\P{Nd}]+/8
+    abcd
+    ** Failers
+    1234
+
+/\D+/8
+    11111111111111111111111111111111111111111111111111111111111111111111111
+    aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+     
+/\P{Nd}+/8
+    11111111111111111111111111111111111111111111111111111111111111111111111
+    aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+
+/[\D]+/8
+    11111111111111111111111111111111111111111111111111111111111111111111111
+    aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+
+/[\P{Nd}]+/8
+    11111111111111111111111111111111111111111111111111111111111111111111111
+    aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+
+/[\D\P{Nd}]+/8
+    11111111111111111111111111111111111111111111111111111111111111111111111
+    aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+
+/\pL/8
+    a
+    A 
+
+/\pL/8i
+    a
+    A 
+    
+/\p{Lu}/8 
+    A
+    aZ
+    ** Failers
+    abc   
+
+/\p{Lu}/8i
+    A
+    aZ
+    ** Failers
+    abc   
+
+/\p{Ll}/8 
+    a
+    Az
+    ** Failers
+    ABC   
+
+/\p{Ll}/8i 
+    a
+    Az
+    ** Failers
+    ABC   
+
+/^\x{c0}$/8i
+    \x{c0}
+    \x{e0} 
+
+/^\x{e0}$/8i
+    \x{c0}
+    \x{e0} 
+
+/A\x{391}\x{10427}\x{ff3a}\x{1fb0}/8
+    A\x{391}\x{10427}\x{ff3a}\x{1fb0}
+    ** Failers
+    a\x{391}\x{10427}\x{ff3a}\x{1fb0}   
+    A\x{3b1}\x{10427}\x{ff3a}\x{1fb0}
+    A\x{391}\x{1044F}\x{ff3a}\x{1fb0}
+    A\x{391}\x{10427}\x{ff5a}\x{1fb0}
+    A\x{391}\x{10427}\x{ff3a}\x{1fb8}
+
+/A\x{391}\x{10427}\x{ff3a}\x{1fb0}/8i
+    A\x{391}\x{10427}\x{ff3a}\x{1fb0}
+    a\x{391}\x{10427}\x{ff3a}\x{1fb0}   
+    A\x{3b1}\x{10427}\x{ff3a}\x{1fb0}
+    A\x{391}\x{1044F}\x{ff3a}\x{1fb0}
+    A\x{391}\x{10427}\x{ff5a}\x{1fb0}
+    A\x{391}\x{10427}\x{ff3a}\x{1fb8}
+
+/\x{391}+/8i
+    \x{391}\x{3b1}\x{3b1}\x{3b1}\x{391}
+
+/\x{391}{3,5}(.)/8i
+    \x{391}\x{3b1}\x{3b1}\x{3b1}\x{391}X
+
+/\x{391}{3,5}?(.)/8i
+    \x{391}\x{3b1}\x{3b1}\x{3b1}\x{391}X
+
+/[\x{391}\x{ff3a}]/8i
+    \x{391}
+    \x{ff3a}
+    \x{3b1}
+    \x{ff5a}   
+    
+/[\x{c0}\x{391}]/8i
+    \x{c0}
+    \x{e0} 
+
+/[\x{105}-\x{109}]/8i
+    \x{104}
+    \x{105}
+    \x{109}  
+    ** Failers
+    \x{100}
+    \x{10a} 
+    
+/[z-\x{100}]/8i 
+    Z
+    z
+    \x{39c}
+    \x{178}
+    |
+    \x{80}
+    \x{ff}
+    \x{100}
+    \x{101} 
+    ** Failers
+    \x{102}
+    Y
+    y           
+
+/[z-\x{100}]/8i
+
+/^\X/8
+    A
+    A\x{300}BC 
+    A\x{300}\x{301}\x{302}BC 
+    *** Failers
+    \x{300}  
+
+/^[\X]/8
+    X123
+    *** Failers
+    AXYZ
+
+/^(\X*)C/8
+    A\x{300}\x{301}\x{302}BCA\x{300}\x{301} 
+    A\x{300}\x{301}\x{302}BCA\x{300}\x{301}C 
+
+/^(\X*?)C/8
+    A\x{300}\x{301}\x{302}BCA\x{300}\x{301} 
+    A\x{300}\x{301}\x{302}BCA\x{300}\x{301}C 
+
+/^(\X*)(.)/8
+    A\x{300}\x{301}\x{302}BCA\x{300}\x{301} 
+    A\x{300}\x{301}\x{302}BCA\x{300}\x{301}C 
+
+/^(\X*?)(.)/8
+    A\x{300}\x{301}\x{302}BCA\x{300}\x{301} 
+    A\x{300}\x{301}\x{302}BCA\x{300}\x{301}C 
+
+/^\X(.)/8
+    *** Failers
+    A\x{300}\x{301}\x{302}
+
+/^\X{2,3}(.)/8
+    A\x{300}\x{301}B\x{300}X
+    A\x{300}\x{301}B\x{300}C\x{300}\x{301}
+    A\x{300}\x{301}B\x{300}C\x{300}\x{301}X
+    A\x{300}\x{301}B\x{300}C\x{300}\x{301}DA\x{300}X
+    
+/^\X{2,3}?(.)/8
+    A\x{300}\x{301}B\x{300}X
+    A\x{300}\x{301}B\x{300}C\x{300}\x{301}
+    A\x{300}\x{301}B\x{300}C\x{300}\x{301}X
+    A\x{300}\x{301}B\x{300}C\x{300}\x{301}DA\x{300}X
+
+/^\pN{2,3}X/
+    12X
+    123X
+    *** Failers
+    X
+    1X
+    1234X     
+
+/\x{100}/i8
+    \x{100}   
+    \x{101} 
+    
+/^\p{Han}+/8
+    \x{2e81}\x{3007}\x{2f804}\x{31a0}
+    ** Failers
+    \x{2e7f}  
+
+/^\P{Katakana}+/8
+    \x{3105}
+    ** Failers
+    \x{30ff}  
+
+/^[\p{Arabic}]/8
+    \x{06e9}
+    \x{060b}
+    ** Failers
+    X\x{06e9}   
+
+/^[\P{Yi}]/8
+    \x{2f800}
+    ** Failers
+    \x{a014}
+    \x{a4c6}   
+
+/^\p{Any}X/8
+    AXYZ
+    \x{1234}XYZ 
+    ** Failers
+    X  
+    
+/^\P{Any}X/8
+    ** Failers
+    AX
+    
+/^\p{Any}?X/8
+    XYZ
+    AXYZ
+    \x{1234}XYZ 
+    ** Failers
+    ABXYZ   
+
+/^\P{Any}?X/8
+    XYZ
+    ** Failers
+    AXYZ
+    \x{1234}XYZ 
+    ABXYZ   
+
+/^\p{Any}+X/8
+    AXYZ
+    \x{1234}XYZ
+    A\x{1234}XYZ
+    ** Failers
+    XYZ
+
+/^\P{Any}+X/8
+    ** Failers
+    AXYZ
+    \x{1234}XYZ
+    A\x{1234}XYZ
+    XYZ
+
+/^\p{Any}*X/8
+    XYZ
+    AXYZ
+    \x{1234}XYZ
+    A\x{1234}XYZ
+    ** Failers
+
+/^\P{Any}*X/8
+    XYZ
+    ** Failers
+    AXYZ
+    \x{1234}XYZ
+    A\x{1234}XYZ
+
+/^[\p{Any}]X/8
+    AXYZ
+    \x{1234}XYZ 
+    ** Failers
+    X  
+    
+/^[\P{Any}]X/8
+    ** Failers
+    AX
+    
+/^[\p{Any}]?X/8
+    XYZ
+    AXYZ
+    \x{1234}XYZ 
+    ** Failers
+    ABXYZ   
+
+/^[\P{Any}]?X/8
+    XYZ
+    ** Failers
+    AXYZ
+    \x{1234}XYZ 
+    ABXYZ   
+
+/^[\p{Any}]+X/8
+    AXYZ
+    \x{1234}XYZ
+    A\x{1234}XYZ
+    ** Failers
+    XYZ
+
+/^[\P{Any}]+X/8
+    ** Failers
+    AXYZ
+    \x{1234}XYZ
+    A\x{1234}XYZ
+    XYZ
+
+/^[\p{Any}]*X/8
+    XYZ
+    AXYZ
+    \x{1234}XYZ
+    A\x{1234}XYZ
+    ** Failers
+
+/^[\P{Any}]*X/8
+    XYZ
+    ** Failers
+    AXYZ
+    \x{1234}XYZ
+    A\x{1234}XYZ
+
+/^\p{Any}{3,5}?/8
+    abcdefgh
+    \x{1234}\n\r\x{3456}xyz 
+
+/^\p{Any}{3,5}/8
+    abcdefgh
+    \x{1234}\n\r\x{3456}xyz 
+
+/^\P{Any}{3,5}?/8
+    ** Failers
+    abcdefgh
+    \x{1234}\n\r\x{3456}xyz 
+
+/^\p{L&}X/8
+     AXY
+     aXY
+     \x{1c5}XY
+     ** Failers
+     \x{1bb}XY
+     \x{2b0}XY
+     !XY      
+
+/^[\p{L&}]X/8
+     AXY
+     aXY
+     \x{1c5}XY
+     ** Failers
+     \x{1bb}XY
+     \x{2b0}XY
+     !XY      
+
+/^\p{L&}+X/8
+     AXY
+     aXY
+     AbcdeXyz 
+     \x{1c5}AbXY
+     abcDEXypqreXlmn 
+     ** Failers
+     \x{1bb}XY
+     \x{2b0}XY
+     !XY      
+
+/^[\p{L&}]+X/8
+     AXY
+     aXY
+     AbcdeXyz 
+     \x{1c5}AbXY
+     abcDEXypqreXlmn 
+     ** Failers
+     \x{1bb}XY
+     \x{2b0}XY
+     !XY      
+
+/^\p{L&}+?X/8
+     AXY
+     aXY
+     AbcdeXyz 
+     \x{1c5}AbXY
+     abcDEXypqreXlmn 
+     ** Failers
+     \x{1bb}XY
+     \x{2b0}XY
+     !XY      
+
+/^[\p{L&}]+?X/8
+     AXY
+     aXY
+     AbcdeXyz 
+     \x{1c5}AbXY
+     abcDEXypqreXlmn 
+     ** Failers
+     \x{1bb}XY
+     \x{2b0}XY
+     !XY      
+
+/^\P{L&}X/8
+     !XY
+     \x{1bb}XY
+     \x{2b0}XY
+     ** Failers
+     \x{1c5}XY
+     AXY      
+
+/^[\P{L&}]X/8
+     !XY
+     \x{1bb}XY
+     \x{2b0}XY
+     ** Failers
+     \x{1c5}XY
+     AXY      
+
+/^\x{023a}+?(\x{0130}+)/8i
+  \x{023a}\x{2c65}\x{0130}
+  
+/^\x{023a}+([^X])/8i
+  \x{023a}\x{2c65}X
+ 
+/\x{c0}+\x{116}+/8i
+    \x{c0}\x{e0}\x{116}\x{117}
+
+/[\x{c0}\x{116}]+/8i
+    \x{c0}\x{e0}\x{116}\x{117}
+
+/Check property support in non-UTF-8 mode/
+ 
+/\p{L}{4}/
+    123abcdefg
+    123abc\xc4\xc5zz
+
+/\p{Carian}\p{Cham}\p{Kayah_Li}\p{Lepcha}\p{Lycian}\p{Lydian}\p{Ol_Chiki}\p{Rejang}\p{Saurashtra}\p{Sundanese}\p{Vai}/8
+    \x{102A4}\x{AA52}\x{A91D}\x{1C46}\x{10283}\x{1092E}\x{1C6B}\x{A93B}\x{A8BF}\x{1BA0}\x{A50A}====
+
+/\x{a77d}\x{1d79}/8i
+    \x{a77d}\x{1d79}
+    \x{1d79}\x{a77d} 
+
+/\x{a77d}\x{1d79}/8
+    \x{a77d}\x{1d79}
+    ** Failers 
+    \x{1d79}\x{a77d} 
+
+/^\p{Xan}/8
+    ABCD
+    1234
+    \x{6ca}
+    \x{a6c}
+    \x{10a7}   
+    ** Failers
+    _ABC   
+
+/^\p{Xan}+/8
+    ABCD1234\x{6ca}\x{a6c}\x{10a7}_
+    ** Failers
+    _ABC   
+
+/^\p{Xan}*/8
+    ABCD1234\x{6ca}\x{a6c}\x{10a7}_
+    
+/^\p{Xan}{2,9}/8
+    ABCD1234\x{6ca}\x{a6c}\x{10a7}_
+    
+/^[\p{Xan}]/8
+    ABCD1234_
+    1234abcd_
+    \x{6ca}
+    \x{a6c}
+    \x{10a7}   
+    ** Failers
+    _ABC   
+ 
+/^[\p{Xan}]+/8
+    ABCD1234\x{6ca}\x{a6c}\x{10a7}_
+    ** Failers
+    _ABC   
+
+/^>\p{Xsp}/8
+    >\x{1680}\x{2028}\x{0b}
+    ** Failers
+    \x{0b} 
+
+/^>\p{Xsp}+/8
+    > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}\x{0b}
+
+/^>\p{Xsp}*/8
+    > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}\x{0b}
+    
+/^>\p{Xsp}{2,9}/8
+    > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}\x{0b}
+    
+/^>[\p{Xsp}]/8
+    >\x{2028}\x{0b}
+ 
+/^>[\p{Xsp}]+/8
+    > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}\x{0b}
+
+/^>\p{Xps}/8
+    >\x{1680}\x{2028}\x{0b}
+    >\x{a0} 
+    ** Failers
+    \x{0b} 
+
+/^>\p{Xps}+/8
+    > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}\x{0b}
+
+/^>\p{Xps}+?/8
+    >\x{1680}\x{2028}\x{0b}
+
+/^>\p{Xps}*/8
+    > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}\x{0b}
+    
+/^>\p{Xps}{2,9}/8
+    > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}\x{0b}
+    
+/^>\p{Xps}{2,9}?/8
+    > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}\x{0b}
+    
+/^>[\p{Xps}]/8
+    >\x{2028}\x{0b}
+ 
+/^>[\p{Xps}]+/8
+    > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}\x{0b}
+
+/^\p{Xwd}/8
+    ABCD
+    1234
+    \x{6ca}
+    \x{a6c}
+    \x{10a7}
+    _ABC    
+    ** Failers
+    [] 
+
+/^\p{Xwd}+/8
+    ABCD1234\x{6ca}\x{a6c}\x{10a7}_
+
+/^\p{Xwd}*/8
+    ABCD1234\x{6ca}\x{a6c}\x{10a7}_
+    
+/^\p{Xwd}{2,9}/8
+    A_12\x{6ca}\x{a6c}\x{10a7}
+    
+/^[\p{Xwd}]/8
+    ABCD1234_
+    1234abcd_
+    \x{6ca}
+    \x{a6c}
+    \x{10a7}   
+    _ABC 
+    ** Failers
+    []   
+ 
+/^[\p{Xwd}]+/8
+    ABCD1234\x{6ca}\x{a6c}\x{10a7}_
+
+/-- Unicode properties for \b abd \B --/
+
+/\b...\B/8W
+    abc_
+    \x{37e}abc\x{376} 
+    \x{37e}\x{376}\x{371}\x{393}\x{394} 
+    !\x{c0}++\x{c1}\x{c2} 
+    !\x{c0}+++++ 
+
+/-- Without PCRE_UCP, non-ASCII always fail, even if < 256  --/
+
+/\b...\B/8
+    abc_
+    ** Failers 
+    \x{37e}abc\x{376} 
+    \x{37e}\x{376}\x{371}\x{393}\x{394} 
+    !\x{c0}++\x{c1}\x{c2} 
+    !\x{c0}+++++ 
+
+/-- With PCRE_UCP, non-UTF8 chars that are < 256 still check properties  --/
+
+/\b...\B/W
+    abc_
+    !\x{c0}++\x{c1}\x{c2} 
+    !\x{c0}+++++ 
+    
+/-- Caseless single negated characters > 127 need UCP support --/
+
+/[^\x{100}]/8i
+    \x{100}\x{101}X
+
+/[^\x{100}]+/8i
+    \x{100}\x{101}XX
+
+/^\X/8
+    A\P
+    A\P\P 
+    A\x{300}\x{301}\P
+    A\x{300}\x{301}\P\P  
+    A\x{301}\P
+    A\x{301}\P\P  
+    
+/^\X{2,3}/8
+    A\P
+    A\P\P 
+    AA\P
+    AA\P\P  
+    A\x{300}\x{301}\P
+    A\x{300}\x{301}\P\P  
+    A\x{300}\x{301}A\x{300}\x{301}\P
+    A\x{300}\x{301}A\x{300}\x{301}\P\P  
+
+/^\X{2}/8
+    AA\P
+    AA\P\P  
+    A\x{300}\x{301}A\x{300}\x{301}\P
+    A\x{300}\x{301}A\x{300}\x{301}\P\P  
+    
+/^\X+/8
+    AA\P
+    AA\P\P  
+
+/^\X+?Z/8
+    AA\P
+    AA\P\P 
+
+/-- End of testinput10 --/ 
diff --git a/ext/pcre/pcrelib/testdata/testinput2 b/ext/pcre/pcrelib/testdata/testinput2
new file mode 100644
index 0000000..883d52e
--- /dev/null
+++ b/ext/pcre/pcrelib/testdata/testinput2
@@ -0,0 +1,3772 @@
+/-- This set of tests is not Perl-compatible. It checks on special features
+    of PCRE's API, error diagnostics, and the compiled code of some patterns.
+    It also checks the non-Perl syntax the PCRE supports (Python, .NET, 
+    Oniguruma). Finally, there are some tests where PCRE and Perl differ, 
+    either because PCRE can't be compatible, or there is a possible Perl 
+    bug.
+    
+    NOTE: This is a non-UTF set of tests. When UTF support is needed, use
+    test 5, and if Unicode Property Support is needed, use test 7. --/
+  
+/(a)b|/I
+
+/abc/I
+    abc
+    defabc
+    \Aabc
+    *** Failers
+    \Adefabc
+    ABC
+
+/^abc/I
+    abc
+    \Aabc
+    *** Failers
+    defabc
+    \Adefabc
+
+/a+bc/I
+
+/a*bc/I
+
+/a{3}bc/I
+
+/(abc|a+z)/I
+
+/^abc$/I
+    abc
+    *** Failers
+    def\nabc
+
+/ab\idef/X
+
+/(?X)ab\idef/X
+
+/x{5,4}/
+
+/z{65536}/
+
+/[abcd/
+
+/(?X)[\B]/
+
+/(?X)[\R]/
+
+/(?X)[\X]/
+
+/[\B]/BZ
+
+/[\R]/BZ
+
+/[\X]/BZ
+
+/[z-a]/
+
+/^*/
+
+/(abc/
+
+/(?# abc/
+
+/(?z)abc/
+
+/.*b/I
+
+/.*?b/I
+
+/cat|dog|elephant/I
+    this sentence eventually mentions a cat
+    this sentences rambles on and on for a while and then reaches elephant
+
+/cat|dog|elephant/IS
+    this sentence eventually mentions a cat
+    this sentences rambles on and on for a while and then reaches elephant
+
+/cat|dog|elephant/IiS
+    this sentence eventually mentions a CAT cat
+    this sentences rambles on and on for a while to elephant ElePhant
+
+/a|[bcd]/IS
+
+/(a|[^\dZ])/IS
+
+/(a|b)*[\s]/IS
+
+/(ab\2)/
+
+/{4,5}abc/
+
+/(a)(b)(c)\2/I
+    abcb
+    \O0abcb
+    \O3abcb
+    \O6abcb
+    \O9abcb
+    \O12abcb
+
+/(a)bc|(a)(b)\2/I
+    abc
+    \O0abc
+    \O3abc
+    \O6abc
+    aba
+    \O0aba
+    \O3aba
+    \O6aba
+    \O9aba
+    \O12aba
+
+/abc$/IE
+    abc
+    *** Failers
+    abc\n
+    abc\ndef
+
+/(a)(b)(c)(d)(e)\6/
+
+/the quick brown fox/I
+    the quick brown fox
+    this is a line with the quick brown fox
+
+/the quick brown fox/IA
+    the quick brown fox
+    *** Failers
+    this is a line with the quick brown fox
+
+/ab(?z)cd/
+
+/^abc|def/I
+    abcdef
+    abcdef\B
+
+/.*((abc)$|(def))/I
+    defabc
+    \Zdefabc
+
+/)/
+
+/a[]b/
+
+/[^aeiou ]{3,}/I
+    co-processors, and for
+
+/<.*>/I
+    abc<def>ghi<klm>nop
+
+/<.*?>/I
+    abc<def>ghi<klm>nop
+
+/<.*>/IU
+    abc<def>ghi<klm>nop
+
+/(?U)<.*>/I
+    abc<def>ghi<klm>nop
+
+/<.*?>/IU
+    abc<def>ghi<klm>nop
+
+/={3,}/IU
+    abc========def
+
+/(?U)={3,}?/I
+    abc========def
+
+/(?<!bar|cattle)foo/I
+    foo
+    catfoo
+    *** Failers
+    the barfoo
+    and cattlefoo
+
+/(?<=a+)b/
+
+/(?<=aaa|b{0,3})b/
+
+/(?<!(foo)a\1)bar/
+
+/(?i)abc/I
+
+/(a|(?m)a)/I
+
+/(?i)^1234/I
+
+/(^b|(?i)^d)/I
+
+/(?s).*/I
+
+/[abcd]/IS
+
+/(?i)[abcd]/IS
+
+/(?m)[xy]|(b|c)/IS
+
+/(^a|^b)/Im
+
+/(?i)(^a|^b)/Im
+
+/(a)(?(1)a|b|c)/
+
+/(?(?=a)a|b|c)/
+
+/(?(1a)/
+
+/(?(1a))/
+
+/(?(?i))/
+
+/(?(abc))/
+
+/(?(?<ab))/
+
+/((?s)blah)\s+\1/I
+
+/((?i)blah)\s+\1/I
+
+/((?i)b)/IDZS
+
+/(a*b|(?i:c*(?-i)d))/IS
+
+/a$/I
+    a
+    a\n
+    *** Failers
+    \Za
+    \Za\n
+
+/a$/Im
+    a
+    a\n
+    \Za\n
+    *** Failers
+    \Za
+
+/\Aabc/Im
+
+/^abc/Im
+
+/^((a+)(?U)([ab]+)(?-U)([bc]+)(\w*))/I
+  aaaaabbbbbcccccdef
+
+/(?<=foo)[ab]/IS
+
+/(?<!foo)(alpha|omega)/IS
+
+/(?!alphabet)[ab]/IS
+
+/(?<=foo\n)^bar/Im
+    foo\nbarbar
+    ***Failers
+    rhubarb
+    barbell
+    abc\nbarton
+
+/^(?<=foo\n)bar/Im
+    foo\nbarbar
+    ***Failers
+    rhubarb
+    barbell
+    abc\nbarton
+
+/(?>^abc)/Im
+    abc
+    def\nabc
+    *** Failers
+    defabc
+
+/(?<=ab(c+)d)ef/
+
+/(?<=ab(?<=c+)d)ef/
+
+/(?<=ab(c|de)f)g/
+
+/The next three are in testinput2 because they have variable length branches/
+
+/(?<=bullock|donkey)-cart/I
+    the bullock-cart
+    a donkey-cart race
+    *** Failers
+    cart
+    horse-and-cart
+
+/(?<=ab(?i)x|y|z)/I
+
+/(?>.*)(?<=(abcd)|(xyz))/I
+    alphabetabcd
+    endingxyz
+
+/(?<=ab(?i)x(?-i)y|(?i)z|b)ZZ/I
+    abxyZZ
+    abXyZZ
+    ZZZ
+    zZZ
+    bZZ
+    BZZ
+    *** Failers
+    ZZ
+    abXYZZ
+    zzz
+    bzz
+
+/(?<!(foo)a)bar/I
+    bar
+    foobbar
+    *** Failers
+    fooabar
+
+/This one is here because Perl 5.005_02 doesn't fail it/I
+
+/^(a)?(?(1)a|b)+$/I
+    *** Failers
+    a
+
+/This one is here because Perl behaves differently; see also the following/I
+
+/^(a\1?){4}$/I
+    aaaa
+    aaaaaa
+    
+/Perl does not fail these two for the final subjects. Neither did PCRE until/
+/release 8.01. The problem is in backtracking into a subpattern that contains/
+/a recursive reference to itself. PCRE has now made these into atomic patterns./
+
+/^(xa|=?\1a){2}$/
+    xa=xaa
+    ** Failers
+    xa=xaaa
+
+/^(xa|=?\1a)+$/
+    xa=xaa
+    ** Failers
+    xa=xaaa
+
+/These are syntax tests from Perl 5.005/I
+
+/a[b-a]/
+
+/a[]b/
+
+/a[/
+
+/*a/
+
+/(*)b/
+
+/abc)/
+
+/(abc/
+
+/a**/
+
+/)(/
+
+/\1/
+
+/\2/
+
+/(a)|\2/
+
+/a[b-a]/Ii
+
+/a[]b/Ii
+
+/a[/Ii
+
+/*a/Ii
+
+/(*)b/Ii
+
+/abc)/Ii
+
+/(abc/Ii
+
+/a**/Ii
+
+/)(/Ii
+
+/:(?:/
+
+/(?<%)b/
+
+/a(?{)b/
+
+/a(?{{})b/
+
+/a(?{}})b/
+
+/a(?{"{"})b/
+
+/a(?{"{"}})b/
+
+/(?(1?)a|b)/
+
+/[a[:xyz:/
+
+/(?<=x+)y/
+
+/a{37,17}/
+
+/abc/\
+
+/abc/\i
+
+/(a)bc(d)/I
+    abcd
+    abcd\C2
+    abcd\C5
+
+/(.{20})/I
+    abcdefghijklmnopqrstuvwxyz
+    abcdefghijklmnopqrstuvwxyz\C1
+    abcdefghijklmnopqrstuvwxyz\G1
+
+/(.{15})/I
+    abcdefghijklmnopqrstuvwxyz
+    abcdefghijklmnopqrstuvwxyz\C1\G1
+
+/(.{16})/I
+    abcdefghijklmnopqrstuvwxyz
+    abcdefghijklmnopqrstuvwxyz\C1\G1\L
+
+/^(a|(bc))de(f)/I
+    adef\G1\G2\G3\G4\L
+    bcdef\G1\G2\G3\G4\L
+    adefghijk\C0
+
+/^abc\00def/I
+    abc\00def\L\C0
+
+/word ((?:[a-zA-Z0-9]+ )((?:[a-zA-Z0-9]+ )((?:[a-zA-Z0-9]+ )((?:[a-zA-Z0-9]+
+)((?:[a-zA-Z0-9]+ )((?:[a-zA-Z0-9]+ )((?:[a-zA-Z0-9]+ )((?:[a-zA-Z0-9]+
+)?)?)?)?)?)?)?)?)?otherword/I
+
+/.*X/IDZ
+
+/.*X/IDZs
+
+/(.*X|^B)/IDZ
+
+/(.*X|^B)/IDZs
+
+/(?s)(.*X|^B)/IDZ
+
+/(?s:.*X|^B)/IDZ
+
+/\Biss\B/I+
+    Mississippi
+
+/iss/IG+
+    Mississippi
+
+/\Biss\B/IG+
+    Mississippi
+
+/\Biss\B/Ig+
+    Mississippi
+    *** Failers
+    Mississippi\A
+
+/(?<=[Ms])iss/Ig+
+    Mississippi
+
+/(?<=[Ms])iss/IG+
+    Mississippi
+
+/^iss/Ig+
+    ississippi
+
+/.*iss/Ig+
+    abciss\nxyzisspqr
+
+/.i./I+g
+    Mississippi
+    Mississippi\A
+    Missouri river
+    Missouri river\A
+
+/^.is/I+g
+    Mississippi
+
+/^ab\n/Ig+
+    ab\nab\ncd
+
+/^ab\n/Img+
+    ab\nab\ncd
+
+/abc/I
+
+/abc|bac/I
+
+/(abc|bac)/I
+
+/(abc|(c|dc))/I
+
+/(abc|(d|de)c)/I
+
+/a*/I
+
+/a+/I
+
+/(baa|a+)/I
+
+/a{0,3}/I
+
+/baa{3,}/I
+
+/"([^\\"]+|\\.)*"/I
+
+/(abc|ab[cd])/I
+
+/(a|.)/I
+
+/a|ba|\w/I
+
+/abc(?=pqr)/I
+
+/...(?<=abc)/I
+
+/abc(?!pqr)/I
+
+/ab./I
+
+/ab[xyz]/I
+
+/abc*/I
+
+/ab.c*/I
+
+/a.c*/I
+
+/.c*/I
+
+/ac*/I
+
+/(a.c*|b.c*)/I
+
+/a.c*|aba/I
+
+/.+a/I
+
+/(?=abcda)a.*/I
+
+/(?=a)a.*/I
+
+/a(b)*/I
+
+/a\d*/I
+
+/ab\d*/I
+
+/a(\d)*/I
+
+/abcde{0,0}/I
+
+/ab\d+/I
+
+/a(?(1)b)(.)/I
+
+/a(?(1)bag|big)(.)/I
+
+/a(?(1)bag|big)*(.)/I
+
+/a(?(1)bag|big)+(.)/I
+
+/a(?(1)b..|b..)(.)/I
+
+/ab\d{0}e/I
+
+/a?b?/I
+    a
+    b
+    ab
+    \
+    *** Failers
+    \N
+
+/|-/I
+    abcd
+    -abc
+    \Nab-c
+    *** Failers
+    \Nabc
+
+/^.?abcd/IS
+
+/\(             # ( at start
+  (?:           # Non-capturing bracket
+  (?>[^()]+)    # Either a sequence of non-brackets (no backtracking)
+  |             # Or
+  (?R)          # Recurse - i.e. nested bracketed string
+  )*            # Zero or more contents
+  \)            # Closing )
+  /Ix
+    (abcd)
+    (abcd)xyz
+    xyz(abcd)
+    (ab(xy)cd)pqr
+    (ab(xycd)pqr
+    () abc ()
+    12(abcde(fsh)xyz(foo(bar))lmno)89
+    *** Failers
+    abcd
+    abcd)
+    (abcd
+
+/\(  ( (?>[^()]+) | (?R) )* \) /Ixg
+    (ab(xy)cd)pqr
+    1(abcd)(x(y)z)pqr
+
+/\(  (?: (?>[^()]+) | (?R) ) \) /Ix
+    (abcd)
+    (ab(xy)cd)
+    (a(b(c)d)e)
+    ((ab))
+    *** Failers
+    ()
+
+/\(  (?: (?>[^()]+) | (?R) )? \) /Ix
+    ()
+    12(abcde(fsh)xyz(foo(bar))lmno)89
+
+/\(  ( (?>[^()]+) | (?R) )* \) /Ix
+    (ab(xy)cd)
+
+/\( ( ( (?>[^()]+) | (?R) )* ) \) /Ix
+    (ab(xy)cd)
+
+/\( (123)? ( ( (?>[^()]+) | (?R) )* ) \) /Ix
+    (ab(xy)cd)
+    (123ab(xy)cd)
+
+/\( ( (123)? ( (?>[^()]+) | (?R) )* ) \) /Ix
+    (ab(xy)cd)
+    (123ab(xy)cd)
+
+/\( (((((((((( ( (?>[^()]+) | (?R) )* )))))))))) \) /Ix
+    (ab(xy)cd)
+
+/\( ( ( (?>[^()<>]+) | ((?>[^()]+)) | (?R) )* ) \) /Ix
+    (abcd(xyz<p>qrs)123)
+
+/\( ( ( (?>[^()]+) | ((?R)) )* ) \) /Ix
+    (ab(cd)ef)
+    (ab(cd(ef)gh)ij)
+
+/^[[:alnum:]]/DZ
+
+/^[[:^alnum:]]/DZ
+
+/^[[:alpha:]]/DZ
+
+/^[[:^alpha:]]/DZ
+
+/[_[:alpha:]]/IS
+
+/^[[:ascii:]]/DZ
+
+/^[[:^ascii:]]/DZ
+
+/^[[:blank:]]/DZ
+
+/^[[:^blank:]]/DZ
+
+/[\n\x0b\x0c\x0d[:blank:]]/IS
+
+/^[[:cntrl:]]/DZ
+
+/^[[:digit:]]/DZ
+
+/^[[:graph:]]/DZ
+
+/^[[:lower:]]/DZ
+
+/^[[:print:]]/DZ
+
+/^[[:punct:]]/DZ
+
+/^[[:space:]]/DZ
+
+/^[[:upper:]]/DZ
+
+/^[[:xdigit:]]/DZ
+
+/^[[:word:]]/DZ
+
+/^[[:^cntrl:]]/DZ
+
+/^[12[:^digit:]]/DZ
+
+/^[[:^blank:]]/DZ
+
+/[01[:alpha:]%]/DZ
+
+/[[.ch.]]/I
+
+/[[=ch=]]/I
+
+/[[:rhubarb:]]/I
+
+/[[:upper:]]/Ii
+    A
+    a
+
+/[[:lower:]]/Ii
+    A
+    a
+
+/((?-i)[[:lower:]])[[:lower:]]/Ii
+    ab
+    aB
+    *** Failers
+    Ab
+    AB
+
+/[\200-\110]/I
+
+/^(?(0)f|b)oo/I
+
+/This one's here because of the large output vector needed/I
+
+/(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\w+)\s+(\270)/I
+    \O900 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 ABC ABC
+
+/This one's here because Perl does this differently and PCRE can't at present/I
+
+/(main(O)?)+/I
+    mainmain
+    mainOmain
+
+/These are all cases where Perl does it differently (nested captures)/I
+
+/^(a(b)?)+$/I
+    aba
+
+/^(aa(bb)?)+$/I
+    aabbaa
+
+/^(aa|aa(bb))+$/I
+    aabbaa
+
+/^(aa(bb)??)+$/I
+    aabbaa
+
+/^(?:aa(bb)?)+$/I
+    aabbaa
+
+/^(aa(b(b))?)+$/I
+    aabbaa
+
+/^(?:aa(b(b))?)+$/I
+    aabbaa
+
+/^(?:aa(b(?:b))?)+$/I
+    aabbaa
+
+/^(?:aa(bb(?:b))?)+$/I
+    aabbbaa
+
+/^(?:aa(b(?:bb))?)+$/I
+    aabbbaa
+
+/^(?:aa(?:b(b))?)+$/I
+    aabbaa
+
+/^(?:aa(?:b(bb))?)+$/I
+    aabbbaa
+
+/^(aa(b(bb))?)+$/I
+    aabbbaa
+
+/^(aa(bb(bb))?)+$/I
+    aabbbbaa
+
+/--------------------------------------------------------------------/I
+
+/#/IxDZ
+
+/a#/IxDZ
+
+/[\s]/DZ
+
+/[\S]/DZ
+
+/a(?i)b/DZ
+    ab
+    aB
+    *** Failers
+    AB
+
+/(a(?i)b)/DZ
+    ab
+    aB
+    *** Failers
+    AB
+
+/   (?i)abc/IxDZ
+
+/#this is a comment
+  (?i)abc/IxDZ
+
+/123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890/DZ
+
+/\Q123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890/DZ
+
+/\Q\E/DZ
+    \
+
+/\Q\Ex/DZ
+
+/ \Q\E/DZ
+
+/a\Q\E/DZ
+  abc
+  bca
+  bac
+
+/a\Q\Eb/DZ
+  abc
+
+/\Q\Eabc/DZ
+
+/x*+\w/DZ
+    *** Failers
+    xxxxx
+
+/x?+/DZ
+
+/x++/DZ
+
+/x{1,3}+/DZ
+
+/(x)*+/DZ
+
+/^(\w++|\s++)*$/I
+    now is the time for all good men to come to the aid of the party
+    *** Failers
+    this is not a line with only words and spaces!
+
+/(\d++)(\w)/I
+    12345a
+    *** Failers
+    12345+
+
+/a++b/I
+    aaab
+
+/(a++b)/I
+    aaab
+
+/(a++)b/I
+    aaab
+
+/([^()]++|\([^()]*\))+/I
+    ((abc(ade)ufh()()x
+
+/\(([^()]++|\([^()]+\))+\)/I
+    (abc)
+    (abc(def)xyz)
+    *** Failers
+    ((()aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+
+/(abc){1,3}+/DZ
+
+/a+?+/I
+
+/a{2,3}?+b/I
+
+/(?U)a+?+/I
+
+/a{2,3}?+b/IU
+
+/x(?U)a++b/DZ
+    xaaaab
+
+/(?U)xa++b/DZ
+    xaaaab
+
+/^((a+)(?U)([ab]+)(?-U)([bc]+)(\w*))/DZ
+
+/^x(?U)a+b/DZ
+
+/^x(?U)(a+)b/DZ
+
+/[.x.]/I
+
+/[=x=]/I
+
+/[:x:]/I
+
+/\l/I
+
+/\L/I
+
+/\N{name}/I
+
+/\u/I
+
+/\U/I
+
+/[/I
+
+/[a-/I
+
+/[[:space:]/I
+
+/[\s]/IDZ
+
+/[[:space:]]/IDZ
+
+/[[:space:]abcde]/IDZ
+
+/< (?: (?(R) \d++  | [^<>]*+) | (?R)) * >/Ix
+    <>
+    <abcd>
+    <abc <123> hij>
+    <abc <def> hij>
+    <abc<>def>
+    <abc<>
+    *** Failers
+    <abc
+
+|8J\$WE\<\.rX\+ix\[d1b\!H\#\?vV0vrK\:ZH1\=2M\>iV\;\?aPhFB\<\*vW\@QW\@sO9\}cfZA\-i\'w\%hKd6gt1UJP\,15_\#QY\$M\^Mss_U\/\]\&LK9\[5vQub\^w\[KDD\<EjmhUZ\?\.akp2dF\>qmj\;2\}YWFdYx\.Ap\]hjCPTP\(n28k\+3\;o\&WXqs\/gOXdr\$\:r\'do0\;b4c\(f_Gr\=\"\\4\)\[01T7ajQJvL\$W\~mL_sS\/4h\:x\*\[ZN\=KLs\&L5zX\/\/\>it\,o\:aU\(\;Z\>pW\&T7oP\'2K\^E\:x9\'c\[\%z\-\,64JQ5AeH_G\#KijUKghQw\^\\vea3a\?kka_G\$8\#\`\*kynsxzBLru\'\]k_\[7FrVx\}\^\=\$blx\>s\-N\%j\;D\*aZDnsw\:YKZ\%Q\.Kne9\#hP\?\+b3\(SOvL\,\^\;\&u5\@\?5C5Bhb\=m\-vEh_L15Jl\]U\)0RP6\{q\%L\^_z5E\'Dw6X\b|IDZ
+
+|\$\<\.X\+ix\[d1b\!H\#\?vV0vrK\:ZH1\=2M\>iV\;\?aPhFB\<\*vW\@QW\@sO9\}cfZA\-i\'w\%hKd6gt1UJP\,15_\#QY\$M\^Mss_U\/\]\&LK9\[5vQub\^w\[KDD\<EjmhUZ\?\.akp2dF\>qmj\;2\}YWFdYx\.Ap\]hjCPTP\(n28k\+3\;o\&WXqs\/gOXdr\$\:r\'do0\;b4c\(f_Gr\=\"\\4\)\[01T7ajQJvL\$W\~mL_sS\/4h\:x\*\[ZN\=KLs\&L5zX\/\/\>it\,o\:aU\(\;Z\>pW\&T7oP\'2K\^E\:x9\'c\[\%z\-\,64JQ5AeH_G\#KijUKghQw\^\\vea3a\?kka_G\$8\#\`\*kynsxzBLru\'\]k_\[7FrVx\}\^\=\$blx\>s\-N\%j\;D\*aZDnsw\:YKZ\%Q\.Kne9\#hP\?\+b3\(SOvL\,\^\;\&u5\@\?5C5Bhb\=m\-vEh_L15Jl\]U\)0RP6\{q\%L\^_z5E\'Dw6X\b|IDZ
+
+/(.*)\d+\1/I
+
+/(.*)\d+/I
+
+/(.*)\d+\1/Is
+
+/(.*)\d+/Is
+
+/(.*(xyz))\d+\2/I
+
+/((.*))\d+\1/I
+    abc123bc
+
+/a[b]/I
+
+/(?=a).*/I
+
+/(?=abc).xyz/IiI
+
+/(?=abc)(?i).xyz/I
+
+/(?=a)(?=b)/I
+
+/(?=.)a/I
+
+/((?=abcda)a)/I
+
+/((?=abcda)ab)/I
+
+/()a/I
+
+/(?(1)ab|ac)(.)/I
+
+/(?(1)abz|acz)(.)/I
+
+/(?(1)abz)(.)/I
+
+/(?(1)abz)(1)23/I
+
+/(a)+/I
+
+/(a){2,3}/I
+
+/(a)*/I
+
+/[a]/I
+
+/[ab]/I
+
+/[ab]/IS
+
+/[^a]/I
+
+/\d456/I
+
+/\d456/IS
+
+/a^b/I
+
+/^a/Im
+  abcde
+  xy\nabc
+  *** Failers
+  xyabc
+
+/c|abc/I
+
+/(?i)[ab]/IS
+
+/[ab](?i)cd/IS
+
+/abc(?C)def/I
+    abcdef
+    1234abcdef
+    *** Failers
+    abcxyz
+    abcxyzf
+
+/abc(?C)de(?C1)f/I
+    123abcdef
+
+/(?C1)\dabc(?C2)def/IS
+    1234abcdef
+    *** Failers
+    abcdef
+
+/(?C1)\dabc(?C2)def/ISS
+    1234abcdef
+    *** Failers
+    abcdef
+
+/(?C255)ab/I
+
+/(?C256)ab/I
+
+/(?Cab)xx/I
+
+/(?C12vr)x/I
+
+/abc(?C)def/I
+    *** Failers
+    \x83\x0\x61bcdef
+
+/(abc)(?C)de(?C1)f/I
+    123abcdef
+    123abcdef\C+
+    123abcdef\C-
+    *** Failers
+    123abcdef\C!1
+
+/(?C0)(abc(?C1))*/I
+    abcabcabc
+    abcabc\C!1!3
+    *** Failers
+    abcabcabc\C!1!3
+
+/(\d{3}(?C))*/I
+    123\C+
+    123456\C+
+    123456789\C+
+
+/((xyz)(?C)p|(?C1)xyzabc)/I
+    xyzabc\C+
+
+/(X)((xyz)(?C)p|(?C1)xyzabc)/I
+    Xxyzabc\C+
+
+/(?=(abc))(?C)abcdef/I
+    abcdef\C+
+
+/(?!(abc)(?C1)d)(?C2)abcxyz/I
+    abcxyz\C+
+
+/(?<=(abc)(?C))xyz/I
+   abcxyz\C+
+
+/a(b+)(c*)(?C1)/I
+    abbbbbccc\C*1
+
+/a(b+?)(c*?)(?C1)/I
+    abbbbbccc\C*1
+
+/(?C)abc/I
+
+/(?C)^abc/I
+
+/(?C)a|b/IS
+
+/(?R)/I
+
+/(a|(?R))/I
+
+/(ab|(bc|(de|(?R))))/I
+
+/x(ab|(bc|(de|(?R))))/I
+    xab
+    xbc
+    xde
+    xxab
+    xxxab
+    *** Failers
+    xyab
+
+/(ab|(bc|(de|(?1))))/I
+
+/x(ab|(bc|(de|(?1)x)x)x)/I
+
+/^([^()]|\((?1)*\))*$/I
+    abc
+    a(b)c
+    a(b(c))d
+    *** Failers)
+    a(b(c)d
+
+/^>abc>([^()]|\((?1)*\))*<xyz<$/I
+   >abc>123<xyz<
+   >abc>1(2)3<xyz<
+   >abc>(1(2)3)<xyz<
+
+/(a(?1)b)/DZ
+
+/(a(?1)+b)/DZ
+
+/^(\d+|\((?1)([+*-])(?1)\)|-(?1))$/I
+    12
+    (((2+2)*-3)-7)
+    -12
+    *** Failers
+    ((2+2)*-3)-7)
+
+/^(x(y|(?1){2})z)/I
+    xyz
+    xxyzxyzz
+    *** Failers
+    xxyzz
+    xxyzxyzxyzz
+
+/((< (?: (?(R) \d++  | [^<>]*+) | (?2)) * >))/Ix
+    <>
+    <abcd>
+    <abc <123> hij>
+    <abc <def> hij>
+    <abc<>def>
+    <abc<>
+    *** Failers
+    <abc
+
+/(?1)/I
+
+/((?2)(abc)/I
+
+/^(abc)def(?1)/I
+    abcdefabc
+
+/^(a|b|c)=(?1)+/I
+    a=a
+    a=b
+    a=bc
+
+/^(a|b|c)=((?1))+/I
+    a=a
+    a=b
+    a=bc
+
+/a(?P<name1>b|c)d(?P<longername2>e)/DZ
+    abde
+    acde
+
+/(?:a(?P<c>c(?P<d>d)))(?P<a>a)/DZ
+
+/(?P<a>a)...(?P=a)bbb(?P>a)d/DZ
+
+/^\W*(?:(?P<one>(?P<two>.)\W*(?P>one)\W*(?P=two)|)|(?P<three>(?P<four>.)\W*(?P>three)\W*(?P=four)|\W*.\W*))\W*$/Ii
+    1221
+    Satan, oscillate my metallic sonatas!
+    A man, a plan, a canal: Panama!
+    Able was I ere I saw Elba.
+    *** Failers
+    The quick brown fox
+
+/((?(R)a|b))\1(?1)?/I
+  bb
+  bbaa
+
+/(.*)a/Is
+
+/(.*)a\1/Is
+
+/(.*)a(b)\2/Is
+
+/((.*)a|(.*)b)z/Is
+
+/((.*)a|(.*)b)z\1/Is
+
+/((.*)a|(.*)b)z\2/Is
+
+/((.*)a|(.*)b)z\3/Is
+
+/((.*)a|^(.*)b)z\3/Is
+
+/(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)a/Is
+
+/(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)a\31/Is
+
+/(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)a\32/Is
+
+/(a)(bc)/INDZ
+  abc
+
+/(?P<one>a)(bc)/INDZ
+  abc
+
+/(a)(?P<named>bc)/INDZ
+
+/(a+)*zz/I
+  aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaazzbbbbbb\M
+  aaaaaaaaaaaaaz\M
+
+/(aaa(?C1)bbb|ab)/I
+   aaabbb
+   aaabbb\C*0
+   aaabbb\C*1
+   aaabbb\C*-1
+
+/ab(?P<one>cd)ef(?P<two>gh)/I
+    abcdefgh
+    abcdefgh\C1\Gtwo
+    abcdefgh\Cone\Ctwo
+    abcdefgh\Cthree
+
+/(?P<Tes>)(?P<Test>)/DZ
+
+/(?P<Test>)(?P<Tes>)/DZ
+
+/(?P<Z>zz)(?P<A>aa)/I
+    zzaa\CZ
+    zzaa\CA
+
+/(?P<x>eks)(?P<x>eccs)/I
+
+/(?P<abc>abc(?P<def>def)(?P<abc>xyz))/I
+
+"\[((?P<elem>\d+)(,(?P>elem))*)\]"I
+    [10,20,30,5,5,4,4,2,43,23,4234]
+    *** Failers
+    []
+
+"\[((?P<elem>\d+)(,(?P>elem))*)?\]"I
+    [10,20,30,5,5,4,4,2,43,23,4234]
+    []
+
+/(a(b(?2)c))?/DZ
+
+/(a(b(?2)c))*/DZ
+
+/(a(b(?2)c)){0,2}/DZ
+
+/[ab]{1}+/DZ
+
+/((w\/|-|with)*(free|immediate)*.*?shipping\s*[!.-]*)/Ii
+     Baby Bjorn Active Carrier - With free SHIPPING!!
+
+/((w\/|-|with)*(free|immediate)*.*?shipping\s*[!.-]*)/IiS
+     Baby Bjorn Active Carrier - With free SHIPPING!!
+
+/a*.*b/ISDZ
+
+/(a|b)*.?c/ISDZ
+
+/abc(?C255)de(?C)f/DZ
+
+/abcde/ICDZ
+  abcde
+  abcdfe
+
+/a*b/ICDZS
+  ab
+  aaaab
+  aaaacb
+
+/a*b/ICDZSS
+  ab
+  aaaab
+  aaaacb
+
+/a+b/ICDZ
+  ab
+  aaaab
+  aaaacb
+
+/(abc|def)x/ICDZS
+  abcx
+  defx
+  ** Failers 
+  abcdefzx
+
+/(abc|def)x/ICDZSS
+  abcx
+  defx
+  ** Failers 
+  abcdefzx
+
+/(ab|cd){3,4}/IC
+  ababab
+  abcdabcd
+  abcdcdcdcdcd
+
+/([ab]{,4}c|xy)/ICDZS
+    Note: that { does NOT introduce a quantifier
+
+/([ab]{,4}c|xy)/ICDZSS
+    Note: that { does NOT introduce a quantifier
+
+/([ab]{1,4}c|xy){4,5}?123/ICDZ
+    aacaacaacaacaac123
+
+/\b.*/I
+  ab cd\>1
+
+/\b.*/Is
+  ab cd\>1
+
+/(?!.bcd).*/I
+  Xbcd12345
+
+/abcde/I
+    ab\P
+    abc\P
+    abcd\P
+    abcde\P
+    the quick brown abc\P
+    ** Failers\P
+    the quick brown abxyz fox\P
+
+"^(0?[1-9]|[12][0-9]|3[01])/(0?[1-9]|1[012])/(20)?\d\d$"I
+    13/05/04\P
+    13/5/2004\P
+    02/05/09\P
+    1\P
+    1/2\P
+    1/2/0\P
+    1/2/04\P
+    0\P
+    02/\P
+    02/0\P
+    02/1\P
+    ** Failers\P
+    \P
+    123\P
+    33/4/04\P
+    3/13/04\P
+    0/1/2003\P
+    0/\P
+    02/0/\P
+    02/13\P
+
+/0{0,2}ABC/I
+
+/\d{3,}ABC/I
+
+/\d*ABC/I
+
+/[abc]+DE/I
+
+/[abc]?123/I
+    123\P
+    a\P
+    b\P
+    c\P
+    c12\P
+    c123\P
+
+/^(?:\d){3,5}X/I
+    1\P
+    123\P
+    123X
+    1234\P
+    1234X
+    12345\P
+    12345X
+    *** Failers
+    1X
+    123456\P
+
+/abc/IS>testsavedregex
+<testsavedregex
+    abc
+    ** Failers
+    bca
+
+/abc/ISS>testsavedregex
+<testsavedregex
+    abc
+    ** Failers
+    bca
+
+/abc/IFS>testsavedregex
+<testsavedregex
+    abc
+    ** Failers
+    bca
+
+/abc/IFSS>testsavedregex
+<testsavedregex
+    abc
+    ** Failers
+    bca
+
+/(a|b)/IS>testsavedregex
+<testsavedregex
+    abc
+    ** Failers
+    def
+
+/(a|b)/ISS>testsavedregex
+<testsavedregex
+    abc
+    ** Failers
+    def
+
+/(a|b)/ISF>testsavedregex
+<testsavedregex
+    abc
+    ** Failers
+    def
+
+/(a|b)/ISSF>testsavedregex
+<testsavedregex
+    abc
+    ** Failers
+    def
+
+~<(\w+)/?>(.)*</(\1)>~smgI
+    \J1024<!DOCTYPE seite SYSTEM "http://www.lco.lineas.de/xmlCms.dtd">\n<seite>\n<dokumenteninformation>\n<seitentitel>Partner der LCO</seitentitel>\n<sprache>de</sprache>\n<seitenbeschreibung>Partner der LINEAS Consulting\nGmbH</seitenbeschreibung>\n<schluesselworte>LINEAS Consulting GmbH Hamburg\nPartnerfirmen</schluesselworte>\n<revisit>30 days</revisit>\n<robots>index,follow</robots>\n<menueinformation>\n<aktiv>ja</aktiv>\n<menueposition>3</menueposition>\n<menuetext>Partner</menuetext>\n</menueinformation>\n<lastedited>\n<autor>LCO</autor>\n<firma>LINEAS Consulting</firma>\n<datum>15.10.2003</datum>\n</lastedited>\n</dokumenteninformation>\n<inhalt>\n\n<absatzueberschrift>Die Partnerfirmen der LINEAS Consulting\nGmbH</absatzueberschrift>\n\n<absatz><link ziel="http://www.ca.com/" zielfenster="_blank">\n<bild name="logo_ca.gif" rahmen="no"/></link> <link\nziel="http://www.ey.com/" zielfenster="_blank"><bild\nname="logo_euy.gif" rahmen="no"/></link>\n</absatz>\n\n<absatz><link ziel="http://www.cisco.de/" zielfenster="_blank">\n<bild name="logo_cisco.gif" rahmen="ja"/></link></absatz>\n\n<absatz><link ziel="http://www.atelion.de/"\nzielfenster="_blank"><bild\nname="logo_atelion.gif" rahmen="no"/></link>\n</absatz>\n\n<absatz><link ziel="http://www.line-information.de/"\nzielfenster="_blank">\n<bild name="logo_line_information.gif" rahmen="no"/></link>\n</absatz>\n\n<absatz><bild name="logo_aw.gif" rahmen="no"/></absatz>\n\n<absatz><link ziel="http://www.incognis.de/"\nzielfenster="_blank"><bild\nname="logo_incognis.gif" rahmen="no"/></link></absatz>\n\n<absatz><link ziel="http://www.addcraft.com/"\nzielfenster="_blank"><bild\nname="logo_addcraft.gif" rahmen="no"/></link></absatz>\n\n<absatz><link ziel="http://www.comendo.com/"\nzielfenster="_blank"><bild\nname="logo_comendo.gif" rahmen="no"/></link></absatz>\n\n</inhalt>\n</seite>
+
+/^a/IF
+
+/line\nbreak/I
+    this is a line\nbreak
+    line one\nthis is a line\nbreak in the second line
+
+/line\nbreak/If
+    this is a line\nbreak
+    ** Failers
+    line one\nthis is a line\nbreak in the second line
+
+/line\nbreak/Imf
+    this is a line\nbreak
+    ** Failers
+    line one\nthis is a line\nbreak in the second line
+
+/(?i)(?-i)AbCd/I
+    AbCd
+    ** Failers
+    abcd
+
+/a{11111111111111111111}/I
+
+/(){64294967295}/I
+
+/(){2,4294967295}/I
+
+"(?i:a)(?i:b)(?i:c)(?i:d)(?i:e)(?i:f)(?i:g)(?i:h)(?i:i)(?i:j)(k)(?i:l)A\1B"I
+    abcdefghijklAkB
+
+"(?P<n0>a)(?P<n1>b)(?P<n2>c)(?P<n3>d)(?P<n4>e)(?P<n5>f)(?P<n6>g)(?P<n7>h)(?P<n8>i)(?P<n9>j)(?P<n10>k)(?P<n11>l)A\11B"I
+    abcdefghijklAkB
+
+"(a)(b)(c)(d)(e)(f)(g)(h)(i)(j)(k)(l)A\11B"I
+    abcdefghijklAkB
+
+"(?P<name0>a)(?P<name1>a)(?P<name2>a)(?P<name3>a)(?P<name4>a)(?P<name5>a)(?P<name6>a)(?P<name7>a)(?P<name8>a)(?P<name9>a)(?P<name10>a)(?P<name11>a)(?P<name12>a)(?P<name13>a)(?P<name14>a)(?P<name15>a)(?P<name16>a)(?P<name17>a)(?P<name18>a)(?P<name19>a)(?P<name20>a)(?P<name21>a)(?P<name22>a)(?P<name23>a)(?P<name24>a)(?P<name25>a)(?P<name26>a)(?P<name27>a)(?P<name28>a)(?P<name29>a)(?P<name30>a)(?P<name31>a)(?P<name32>a)(?P<name33>a)(?P<name34>a)(?P<name35>a)(?P<name36>a)(?P<name37>a)(?P<name38>a)(?P<name39>a)(?P<name40>a)(?P<name41>a)(?P<name42>a)(?P<name43>a)(?P<name44>a)(?P<name45>a)(?P<name46>a)(?P<name47>a)(?P<name48>a)(?P<name49>a)(?P<name50>a)(?P<name51>a)(?P<name52>a)(?P<name53>a)(?P<name54>a)(?P<name55>a)(?P<name56>a)(?P<name57>a)(?P<name58>a)(?P<name59>a)(?P<name60>a)(?P<name61>a)(?P<name62>a)(?P<name63>a)(?P<name64>a)(?P<name65>a)(?P<name66>a)(?P<name67>a)(?P<name68>a)(?P<name69>a)(?P<name70>a)(?P<name71>a)(?P<name72>a)(?P<name73>a)(?P<name74>a)(?P<name75>a)(?P<name76>a)(?P<name77>a)(?P<name78>a)(?P<name79>a)(?P<name80>a)(?P<name81>a)(?P<name82>a)(?P<name83>a)(?P<name84>a)(?P<name85>a)(?P<name86>a)(?P<name87>a)(?P<name88>a)(?P<name89>a)(?P<name90>a)(?P<name91>a)(?P<name92>a)(?P<name93>a)(?P<name94>a)(?P<name95>a)(?P<name96>a)(?P<name97>a)(?P<name98>a)(?P<name99>a)(?P<name100>a)"I
+    aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+
+"(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)"I
+    aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+
+/[^()]*(?:\((?R)\)[^()]*)*/I
+    (this(and)that
+    (this(and)that)
+    (this(and)that)stuff
+
+/[^()]*(?:\((?>(?R))\)[^()]*)*/I
+    (this(and)that
+    (this(and)that)
+
+/[^()]*(?:\((?R)\))*[^()]*/I
+    (this(and)that
+    (this(and)that)
+
+/(?:\((?R)\))*[^()]*/I
+    (this(and)that
+    (this(and)that)
+    ((this))
+
+/(?:\((?R)\))|[^()]*/I
+    (this(and)that
+    (this(and)that)
+    (this)
+    ((this))
+
+/\x{0000ff}/I
+
+/^((?P<A>a1)|(?P<A>a2)b)/I
+
+/^((?P<A>a1)|(?P<A>a2)b)/IJ
+    a1b\CA
+    a2b\CA
+    ** Failers
+    a1b\CZ\CA
+
+/^(?P<A>a)(?P<A>b)/IJ
+    ab\CA
+
+/^(?P<A>a)(?P<A>b)|cd/IJ
+    ab\CA
+    cd\CA
+
+/^(?P<A>a)(?P<A>b)|cd(?P<A>ef)(?P<A>gh)/IJ
+    cdefgh\CA
+
+/^((?P<A>a1)|(?P<A>a2)b)/IJ
+    a1b\GA
+    a2b\GA
+    ** Failers
+    a1b\GZ\GA
+
+/^(?P<A>a)(?P<A>b)/IJ
+    ab\GA
+
+/^(?P<A>a)(?P<A>b)|cd/IJ
+    ab\GA
+    cd\GA
+
+/^(?P<A>a)(?P<A>b)|cd(?P<A>ef)(?P<A>gh)/IJ
+    cdefgh\GA
+
+/(?J)^((?P<A>a1)|(?P<A>a2)b)/I
+    a1b\CA
+    a2b\CA
+
+/^(?P<A>a) (?J:(?P<B>b)(?P<B>c)) (?P<A>d)/I
+
+/ In this next test, J is not set at the outer level; consequently it isn't
+set in the pattern's options; consequently pcre_get_named_substring() produces
+a random value. /Ix
+
+/^(?P<A>a) (?J:(?P<B>b)(?P<B>c)) (?P<C>d)/I
+    a bc d\CA\CB\CC
+
+/^(?P<A>a)?(?(A)a|b)/I
+    aabc
+    bc
+    ** Failers
+    abc
+
+/(?:(?(ZZ)a|b)(?P<ZZ>X))+/I
+    bXaX
+
+/(?:(?(2y)a|b)(X))+/I
+
+/(?:(?(ZA)a|b)(?P<ZZ>X))+/I
+
+/(?:(?(ZZ)a|b)(?(ZZ)a|b)(?P<ZZ>X))+/I
+    bbXaaX
+
+/(?:(?(ZZ)a|\(b\))\\(?P<ZZ>X))+/I
+    (b)\\Xa\\X
+
+/(?P<ABC/I
+
+/(?:(?(A)(?P=A)a|b)(?P<A>X|Y))+/I
+    bXXaYYaY
+    bXYaXXaX
+
+/()()()()()()()()()(?:(?(A)(?P=A)a|b)(?P<A>X|Y))+/I
+    bXXaYYaY
+
+/\s*,\s*/IS
+    \x0b,\x0b
+    \x0c,\x0d
+
+/^abc/Im
+    xyz\nabc
+    xyz\nabc\<lf>
+    xyz\r\nabc\<lf>
+    xyz\rabc\<cr>
+    xyz\r\nabc\<crlf>
+    ** Failers
+    xyz\nabc\<cr>
+    xyz\r\nabc\<cr>
+    xyz\nabc\<crlf>
+    xyz\rabc\<crlf>
+    xyz\rabc\<lf>
+
+/abc$/Im<lf>
+    xyzabc
+    xyzabc\n
+    xyzabc\npqr
+    xyzabc\r\<cr>
+    xyzabc\rpqr\<cr>
+    xyzabc\r\n\<crlf>
+    xyzabc\r\npqr\<crlf>
+    ** Failers
+    xyzabc\r
+    xyzabc\rpqr
+    xyzabc\r\n
+    xyzabc\r\npqr
+
+/^abc/Im<cr>
+    xyz\rabcdef
+    xyz\nabcdef\<lf>
+    ** Failers
+    xyz\nabcdef
+
+/^abc/Im<lf>
+    xyz\nabcdef
+    xyz\rabcdef\<cr>
+    ** Failers
+    xyz\rabcdef
+
+/^abc/Im<crlf>
+    xyz\r\nabcdef
+    xyz\rabcdef\<cr>
+    ** Failers
+    xyz\rabcdef
+
+/^abc/Im<bad>
+
+/abc/I
+    xyz\rabc\<bad>
+    abc
+
+/.*/I<lf>
+    abc\ndef
+    abc\rdef
+    abc\r\ndef
+    \<cr>abc\ndef
+    \<cr>abc\rdef
+    \<cr>abc\r\ndef
+    \<crlf>abc\ndef
+    \<crlf>abc\rdef
+    \<crlf>abc\r\ndef
+
+/\w+(.)(.)?def/Is
+    abc\ndef
+    abc\rdef
+    abc\r\ndef
+
++((?:\s|//.*\\n|/[*](?:\\n|.)*?[*]/)*)+I
+   /* this is a C style comment */\M
+
+/(?P<B>25[0-5]|2[0-4]\d|[01]?\d?\d)(?:\.(?P>B)){3}/I
+
+/()()()()()()()()()()()()()()()()()()()()
+ ()()()()()()()()()()()()()()()()()()()()
+ ()()()()()()()()()()()()()()()()()()()()
+ ()()()()()()()()()()()()()()()()()()()()
+ ()()()()()()()()()()()()()()()()()()()()
+ (.(.))/Ix
+    XY\O400
+
+/(a*b|(?i:c*(?-i)d))/IS
+
+/()[ab]xyz/IS
+
+/(|)[ab]xyz/IS
+
+/(|c)[ab]xyz/IS
+
+/(|c?)[ab]xyz/IS
+
+/(d?|c?)[ab]xyz/IS
+
+/(d?|c)[ab]xyz/IS
+
+/^a*b\d/DZ
+
+/^a*+b\d/DZ
+
+/^a*?b\d/DZ
+
+/^a+A\d/DZ
+    aaaA5
+    ** Failers
+    aaaa5
+
+/^a*A\d/IiDZ
+    aaaA5
+    aaaa5
+
+/(a*|b*)[cd]/IS
+
+/(a+|b*)[cd]/IS
+
+/(a*|b+)[cd]/IS
+
+/(a+|b+)[cd]/IS
+
+/((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((
+ ((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((
+ (((
+ a
+ ))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))
+ ))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))
+ )))
+/Ix
+  large nest
+
+/a*\d/BZ
+
+/a*\D/BZ
+
+/0*\d/BZ
+
+/0*\D/BZ
+
+/a*\s/BZ
+
+/a*\S/BZ
+
+/ *\s/BZ
+
+/ *\S/BZ
+
+/a*\w/BZ
+
+/a*\W/BZ
+
+/=*\w/BZ
+
+/=*\W/BZ
+
+/\d*a/BZ
+
+/\d*2/BZ
+
+/\d*\d/BZ
+
+/\d*\D/BZ
+
+/\d*\s/BZ
+
+/\d*\S/BZ
+
+/\d*\w/BZ
+
+/\d*\W/BZ
+
+/\D*a/BZ
+
+/\D*2/BZ
+
+/\D*\d/BZ
+
+/\D*\D/BZ
+
+/\D*\s/BZ
+
+/\D*\S/BZ
+
+/\D*\w/BZ
+
+/\D*\W/BZ
+
+/\s*a/BZ
+
+/\s*2/BZ
+
+/\s*\d/BZ
+
+/\s*\D/BZ
+
+/\s*\s/BZ
+
+/\s*\S/BZ
+
+/\s*\w/BZ
+
+/\s*\W/BZ
+
+/\S*a/BZ
+
+/\S*2/BZ
+
+/\S*\d/BZ
+
+/\S*\D/BZ
+
+/\S*\s/BZ
+
+/\S*\S/BZ
+
+/\S*\w/BZ
+
+/\S*\W/BZ
+
+/\w*a/BZ
+
+/\w*2/BZ
+
+/\w*\d/BZ
+
+/\w*\D/BZ
+
+/\w*\s/BZ
+
+/\w*\S/BZ
+
+/\w*\w/BZ
+
+/\w*\W/BZ
+
+/\W*a/BZ
+
+/\W*2/BZ
+
+/\W*\d/BZ
+
+/\W*\D/BZ
+
+/\W*\s/BZ
+
+/\W*\S/BZ
+
+/\W*\w/BZ
+
+/\W*\W/BZ
+
+/[^a]+a/BZ
+
+/[^a]+a/BZi
+
+/[^a]+A/BZi
+
+/[^a]+b/BZ
+
+/[^a]+\d/BZ
+
+/a*[^a]/BZ
+
+/(?P<abc>x)(?P<xyz>y)/I
+    xy\Cabc\Cxyz
+
+/(?<abc>x)(?'xyz'y)/I
+    xy\Cabc\Cxyz
+
+/(?<abc'x)(?'xyz'y)/I
+
+/(?<abc>x)(?'xyz>y)/I
+
+/(?P'abc'x)(?P<xyz>y)/I
+
+/^(?:(?(ZZ)a|b)(?<ZZ>X))+/
+    bXaX
+    bXbX
+    ** Failers
+    aXaX
+    aXbX
+
+/^(?P>abc)(?<abcd>xxx)/
+
+/^(?P>abc)(?<abc>x|y)/
+    xx
+    xy
+    yy
+    yx
+
+/^(?P>abc)(?P<abc>x|y)/
+    xx
+    xy
+    yy
+    yx
+
+/^((?(abc)a|b)(?<abc>x|y))+/
+    bxay
+    bxby
+    ** Failers
+    axby
+
+/^(((?P=abc)|X)(?<abc>x|y))+/
+    XxXxxx
+    XxXyyx
+    XxXyxx
+    ** Failers
+    x
+
+/^(?1)(abc)/
+    abcabc
+
+/^(?:(?:\1|X)(a|b))+/
+    Xaaa
+    Xaba
+
+/^[\E\Qa\E-\Qz\E]+/BZ
+
+/^[a\Q]bc\E]/BZ
+
+/^[a-\Q\E]/BZ
+
+/^(?P>abc)[()](?<abc>)/BZ
+
+/^((?(abc)y)[()](?P<abc>x))+/BZ
+    (xy)x
+
+/^(?P>abc)\Q()\E(?<abc>)/BZ
+
+/^(?P>abc)[a\Q(]\E(](?<abc>)/BZ
+
+/^(?P>abc) # this is (a comment)
+  (?<abc>)/BZx
+
+/^\W*(?:(?<one>(?<two>.)\W*(?&one)\W*\k<two>|)|(?<three>(?<four>.)\W*(?&three)\W*\k'four'|\W*.\W*))\W*$/Ii
+    1221
+    Satan, oscillate my metallic sonatas!
+    A man, a plan, a canal: Panama!
+    Able was I ere I saw Elba.
+    *** Failers
+    The quick brown fox
+
+/(?=(\w+))\1:/I
+    abcd:
+
+/(?=(?'abc'\w+))\k<abc>:/I
+    abcd:
+
+/(?'abc'a|b)(?<abc>d|e)\k<abc>{2}/J
+    adaa
+    ** Failers
+    addd
+    adbb
+
+/(?'abc'a|b)(?<abc>d|e)(?&abc){2}/J
+    bdaa
+    bdab
+    ** Failers
+    bddd
+
+/(?(<bc))/
+
+/(?(''))/
+
+/(?('R')stuff)/
+
+/((abc (?(R) (?(R1)1) (?(R2)2) X  |  (?1)  (?2)   (?R) ))) /x
+    abcabc1Xabc2XabcXabcabc
+
+/(?<A> (?'B' abc (?(R) (?(R&A)1) (?(R&B)2) X  |  (?1)  (?2)   (?R) ))) /x
+    abcabc1Xabc2XabcXabcabc
+
+/(?<A> (?'B' abc (?(R) (?(R&1)1) (?(R&B)2) X  |  (?1)  (?2)   (?R) ))) /x
+
+/(?<1> (?'B' abc (?(R) (?(R&1)1) (?(R&B)2) X  |  (?1)  (?2)   (?R) ))) /x
+    abcabc1Xabc2XabcXabcabc
+
+/^(?(DEFINE) abc | xyz ) /x
+
+/(?(DEFINE) abc) xyz/xI
+
+/(a|)*\d/
+  \O0aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+  \O0aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa4
+
+/^a.b/<lf>
+    a\rb
+    a\nb\<cr>
+    a\x85b\<anycrlf> 
+    ** Failers
+    a\nb
+    a\nb\<any>
+    a\rb\<cr>
+    a\rb\<any>
+    a\x85b\<any> 
+    a\rb\<anycrlf>
+
+/^abc./mgx<any>
+    abc1 \x0aabc2 \x0babc3xx \x0cabc4 \x0dabc5xx \x0d\x0aabc6 \x85abc7 JUNK
+
+/abc.$/mgx<any>
+    abc1\x0a abc2\x0b abc3\x0c abc4\x0d abc5\x0d\x0a abc6\x85 abc7 abc9
+
+/a/<cr><any>
+
+/a/<any><crlf>
+
+/^a\Rb/<bsr_unicode>
+    a\nb
+    a\rb
+    a\r\nb
+    a\x0bb
+    a\x0cb
+    a\x85b
+    ** Failers
+    a\n\rb
+
+/^a\R*b/<bsr_unicode>
+    ab
+    a\nb
+    a\rb
+    a\r\nb
+    a\x0bb
+    a\x0cb
+    a\x85b
+    a\n\rb
+    a\n\r\x85\x0cb
+
+/^a\R+b/<bsr_unicode>
+    a\nb
+    a\rb
+    a\r\nb
+    a\x0bb
+    a\x0cb
+    a\x85b
+    a\n\rb
+    a\n\r\x85\x0cb
+    ** Failers
+    ab
+
+/^a\R{1,3}b/<bsr_unicode>
+    a\nb
+    a\n\rb
+    a\n\r\x85b
+    a\r\n\r\nb
+    a\r\n\r\n\r\nb
+    a\n\r\n\rb
+    a\n\n\r\nb
+    ** Failers
+    a\n\n\n\rb
+    a\r
+
+/^a[\R]b/<bsr_unicode>
+    aRb
+    ** Failers
+    a\nb
+
+/(?&abc)X(?<abc>P)/I
+    abcPXP123
+
+/(?1)X(?<abc>P)/I
+    abcPXP123
+
+/(?:a(?&abc)b)*(?<abc>x)/
+    123axbaxbaxbx456
+    123axbaxbaxb456
+
+/(?:a(?&abc)b){1,5}(?<abc>x)/
+    123axbaxbaxbx456
+
+/(?:a(?&abc)b){2,5}(?<abc>x)/
+    123axbaxbaxbx456
+
+/(?:a(?&abc)b){2,}(?<abc>x)/
+    123axbaxbaxbx456
+
+/(abc)(?i:(?1))/
+   defabcabcxyz
+   DEFabcABCXYZ
+
+/(abc)(?:(?i)(?1))/
+   defabcabcxyz
+   DEFabcABCXYZ
+
+/^(a)\g-2/
+
+/^(a)\g/
+
+/^(a)\g{0}/
+
+/^(a)\g{3/
+
+/^(a)\g{4a}/
+
+/^a.b/<lf>
+    a\rb
+    *** Failers
+    a\nb
+
+/.+foo/
+    afoo
+    ** Failers
+    \r\nfoo
+    \nfoo
+
+/.+foo/<crlf>
+    afoo
+    \nfoo
+    ** Failers
+    \r\nfoo
+
+/.+foo/<any>
+    afoo
+    ** Failers
+    \nfoo
+    \r\nfoo
+
+/.+foo/s
+    afoo
+    \r\nfoo
+    \nfoo
+    
+/^$/mg<any>
+    abc\r\rxyz
+    abc\n\rxyz  
+    ** Failers 
+    abc\r\nxyz
+
+/(?m)^$/<any>g+
+    abc\r\n\r\n
+
+/(?m)^$|^\r\n/<any>g+ 
+    abc\r\n\r\n
+    
+/(?m)$/<any>g+ 
+    abc\r\n\r\n
+
+/abc.$/mgx<anycrlf>
+    abc1\x0a abc2\x0b abc3\x0c abc4\x0d abc5\x0d\x0a abc6\x85 abc9
+
+/^X/m
+    XABC
+    ** Failers 
+    XABC\B
+
+/(ab|c)(?-1)/BZ
+    abc
+
+/xy(?+1)(abc)/BZ
+    xyabcabc
+    ** Failers
+    xyabc  
+    
+/x(?-0)y/
+
+/x(?-1)y/
+
+/x(?+0)y/ 
+
+/x(?+1)y/
+
+/^(abc)?(?(-1)X|Y)/BZ
+    abcX
+    Y
+    ** Failers
+    abcY   
+    
+/^((?(+1)X|Y)(abc))+/BZ 
+    YabcXabc
+    YabcXabcXabc
+    ** Failers
+    XabcXabc  
+
+/(?(-1)a)/BZ
+
+/((?(-1)a))/BZ
+
+/((?(-2)a))/BZ
+
+/^(?(+1)X|Y)(.)/BZ
+    Y!
+
+/(?<A>tom|bon)-\k{A}/
+    tom-tom
+    bon-bon 
+    ** Failers
+    tom-bon  
+
+/\g{A/ 
+
+/(?|(abc)|(xyz))/BZ
+   >abc<
+   >xyz< 
+
+/(x)(?|(abc)|(xyz))(x)/BZ
+    xabcx
+    xxyzx 
+
+/(x)(?|(abc)(pqr)|(xyz))(x)/BZ
+    xabcpqrx
+    xxyzx 
+
+/\H++X/BZ
+    ** Failers
+    XXXX
+    
+/\H+\hY/BZ
+    XXXX Y 
+
+/\H+ Y/BZ
+
+/\h+A/BZ
+
+/\v*B/BZ
+
+/\V+\x0a/BZ
+
+/A+\h/BZ
+
+/ *\H/BZ
+
+/A*\v/BZ
+
+/\x0b*\V/BZ
+
+/\d+\h/BZ
+
+/\d*\v/BZ
+
+/S+\h\S+\v/BZ
+
+/\w{3,}\h\w+\v/BZ
+
+/\h+\d\h+\w\h+\S\h+\H/BZ
+
+/\v+\d\v+\w\v+\S\v+\V/BZ
+
+/\H+\h\H+\d/BZ
+
+/\V+\v\V+\w/BZ
+
+/\( (?: [^()]* | (?R) )* \)/x
+\J1024(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(00)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)
+
+/[\E]AAA/
+
+/[\Q\E]AAA/
+
+/[^\E]AAA/
+
+/[^\Q\E]AAA/
+
+/[\E^]AAA/
+
+/[\Q\E^]AAA/
+
+/A(*PRUNE)B(*SKIP)C(*THEN)D(*COMMIT)E(*F)F(*FAIL)G(?!)H(*ACCEPT)I/BZ
+
+/^a+(*FAIL)/C
+    aaaaaa
+    
+/a+b?c+(*FAIL)/C
+    aaabccc
+
+/a+b?(*PRUNE)c+(*FAIL)/C
+    aaabccc
+
+/a+b?(*COMMIT)c+(*FAIL)/C
+    aaabccc
+    
+/a+b?(*SKIP)c+(*FAIL)/C
+    aaabcccaaabccc
+
+/a+b?(*THEN)c+(*FAIL)/C
+    aaabccc
+    
+/a(*MARK)b/ 
+
+/(?i:A{1,}\6666666666)/
+
+/\g6666666666/
+
+/[\g6666666666]/BZ
+
+/(?1)\c[/
+
+/.+A/<crlf>
+    \r\nA
+    
+/\nA/<crlf>
+    \r\nA 
+
+/[\r\n]A/<crlf>
+    \r\nA 
+
+/(\r|\n)A/<crlf>
+    \r\nA 
+
+/a(*CR)b/
+
+/(*CR)a.b/
+    a\nb
+    ** Failers
+    a\rb  
+
+/(*CR)a.b/<lf>
+    a\nb
+    ** Failers
+    a\rb  
+
+/(*LF)a.b/<CRLF>
+    a\rb
+    ** Failers
+    a\nb  
+
+/(*CRLF)a.b/
+    a\rb
+    a\nb  
+    ** Failers
+    a\r\nb  
+
+/(*ANYCRLF)a.b/<CR>
+    ** Failers
+    a\rb
+    a\nb  
+    a\r\nb  
+
+/(*ANY)a.b/<cr>
+    ** Failers
+    a\rb
+    a\nb  
+    a\r\nb  
+    a\x85b 
+    
+/(*ANY).*/g
+    abc\r\ndef
+
+/(*ANYCRLF).*/g
+    abc\r\ndef
+
+/(*CRLF).*/g
+    abc\r\ndef
+
+/a\Rb/I<bsr_anycrlf>
+    a\rb
+    a\nb
+    a\r\nb
+    ** Failers
+    a\x85b
+    a\x0bb     
+
+/a\Rb/I<bsr_unicode>
+    a\rb
+    a\nb
+    a\r\nb
+    a\x85b
+    a\x0bb     
+    ** Failers 
+    a\x85b\<bsr_anycrlf>
+    a\x0bb\<bsr_anycrlf>
+    
+/a\R?b/I<bsr_anycrlf>
+    a\rb
+    a\nb
+    a\r\nb
+    ** Failers
+    a\x85b
+    a\x0bb     
+
+/a\R?b/I<bsr_unicode>
+    a\rb
+    a\nb
+    a\r\nb
+    a\x85b
+    a\x0bb     
+    ** Failers 
+    a\x85b\<bsr_anycrlf>
+    a\x0bb\<bsr_anycrlf>
+    
+/a\R{2,4}b/I<bsr_anycrlf>
+    a\r\n\nb
+    a\n\r\rb
+    a\r\n\r\n\r\n\r\nb
+    ** Failers
+    a\x85\85b
+    a\x0b\0bb     
+
+/a\R{2,4}b/I<bsr_unicode>
+    a\r\rb
+    a\n\n\nb
+    a\r\n\n\r\rb
+    a\x85\85b
+    a\x0b\0bb     
+    ** Failers 
+    a\r\r\r\r\rb 
+    a\x85\85b\<bsr_anycrlf>
+    a\x0b\0bb\<bsr_anycrlf>
+ 
+/(*BSR_ANYCRLF)a\Rb/I
+    a\nb
+    a\rb 
+
+/(*BSR_UNICODE)a\Rb/I
+    a\x85b
+
+/(*BSR_ANYCRLF)(*CRLF)a\Rb/I
+    a\nb
+    a\rb 
+
+/(*CRLF)(*BSR_UNICODE)a\Rb/I
+    a\x85b
+
+/(*CRLF)(*BSR_ANYCRLF)(*CR)ab/I
+
+/(?<a>)(?&)/
+
+/(?<abc>)(?&a)/
+
+/(?<a>)(?&aaaaaaaaaaaaaaaaaaaaaaa)/
+
+/(?+-a)/
+
+/(?-+a)/
+
+/(?(-1))/
+
+/(?(+10))/
+
+/(?(10))/
+
+/(?(+2))()()/
+
+/(?(2))()()/
+
+/\k''/
+
+/\k<>/
+
+/\k{}/
+
+/\k/
+
+/\kabc/
+
+/(?P=)/
+
+/(?P>)/
+
+/(?!\w)(?R)/
+
+/(?=\w)(?R)/
+
+/(?<!\w)(?R)/
+
+/(?<=\w)(?R)/
+
+/[[:foo:]]/
+
+/[[:1234:]]/
+
+/[[:f\oo:]]/
+
+/[[: :]]/
+
+/[[:...:]]/
+
+/[[:l\ower:]]/
+
+/[[:abc\:]]/
+
+/[abc[:x\]pqr:]]/
+
+/[[:a\dz:]]/
+
+/(^(a|b\g<-1'c))/
+
+/^(?+1)(?<a>x|y){0}z/
+    xzxx
+    yzyy 
+    ** Failers
+    xxz  
+
+/(\3)(\1)(a)/
+    cat
+
+/(\3)(\1)(a)/<JS>
+    cat
+    
+/TA]/
+    The ACTA] comes 
+
+/TA]/<JS>
+    The ACTA] comes 
+
+/(?2)[]a()b](abc)/
+    abcbabc
+
+/(?2)[^]a()b](abc)/
+    abcbabc
+
+/(?1)[]a()b](abc)/
+    abcbabc
+    ** Failers 
+    abcXabc
+
+/(?1)[^]a()b](abc)/
+    abcXabc
+    ** Failers 
+    abcbabc
+
+/(?2)[]a()b](abc)(xyz)/
+    xyzbabcxyz
+
+/(?&N)[]a(?<N>)](?<M>abc)/
+   abc<abc
+
+/(?&N)[]a(?<N>)](abc)/
+   abc<abc
+
+/a[]b/
+
+/a[^]b/
+
+/a[]b/<JS>
+    ** Failers
+    ab
+
+/a[]+b/<JS>
+    ** Failers
+    ab 
+
+/a[]*+b/<JS>
+    ** Failers
+    ab 
+
+/a[^]b/<JS>
+    aXb
+    a\nb 
+    ** Failers
+    ab  
+    
+/a[^]+b/<JS> 
+    aXb
+    a\nX\nXb 
+    ** Failers
+    ab  
+
+/a(?!)+b/
+
+/a(*FAIL)+b/
+
+/(abc|pqr|123){0}[xyz]/SI
+
+/(?(?=.*b)b|^)/CI
+   adc
+   abc 
+   
+/(?(?=b).*b|^d)/I
+
+/(?(?=.*b).*b|^d)/I
+
+/xyz/C
+  xyz 
+  abcxyz 
+  abcxyz\Y
+  ** Failers 
+  abc
+  abc\Y
+  abcxypqr  
+  abcxypqr\Y  
+  
+/(*NO_START_OPT)xyz/C
+  abcxyz 
+
+/xyz/CY
+  abcxyz 
+
+/^"((?(?=[a])[^"])|b)*"$/C
+    "ab"
+
+/^"((?(?=[a])[^"])|b)*"$/
+    "ab"
+
+/^X(?5)(a)(?|(b)|(q))(c)(d)Y/
+    XYabcdY
+
+/^X(?&N)(a)(?|(b)|(q))(c)(d)(?<N>Y)/
+    XYabcdY
+ 
+/Xa{2,4}b/
+    X\P
+    Xa\P
+    Xaa\P 
+    Xaaa\P
+    Xaaaa\P 
+    
+/Xa{2,4}?b/
+    X\P
+    Xa\P
+    Xaa\P 
+    Xaaa\P
+    Xaaaa\P 
+    
+/Xa{2,4}+b/
+    X\P
+    Xa\P
+    Xaa\P 
+    Xaaa\P
+    Xaaaa\P 
+    
+/X\d{2,4}b/
+    X\P
+    X3\P
+    X33\P 
+    X333\P
+    X3333\P 
+    
+/X\d{2,4}?b/
+    X\P
+    X3\P
+    X33\P 
+    X333\P
+    X3333\P 
+    
+/X\d{2,4}+b/
+    X\P
+    X3\P
+    X33\P 
+    X333\P
+    X3333\P 
+    
+/X\D{2,4}b/
+    X\P
+    Xa\P
+    Xaa\P 
+    Xaaa\P
+    Xaaaa\P 
+    
+/X\D{2,4}?b/
+    X\P
+    Xa\P
+    Xaa\P 
+    Xaaa\P
+    Xaaaa\P 
+    
+/X\D{2,4}+b/
+    X\P
+    Xa\P
+    Xaa\P 
+    Xaaa\P
+    Xaaaa\P 
+    
+/X[abc]{2,4}b/
+    X\P
+    Xa\P
+    Xaa\P 
+    Xaaa\P
+    Xaaaa\P 
+    
+/X[abc]{2,4}?b/
+    X\P
+    Xa\P
+    Xaa\P 
+    Xaaa\P
+    Xaaaa\P 
+    
+/X[abc]{2,4}+b/
+    X\P
+    Xa\P
+    Xaa\P 
+    Xaaa\P
+    Xaaaa\P 
+    
+/X[^a]{2,4}b/
+    X\P
+    Xz\P
+    Xzz\P 
+    Xzzz\P
+    Xzzzz\P 
+    
+/X[^a]{2,4}?b/
+    X\P
+    Xz\P
+    Xzz\P 
+    Xzzz\P
+    Xzzzz\P 
+    
+/X[^a]{2,4}+b/
+    X\P
+    Xz\P
+    Xzz\P 
+    Xzzz\P
+    Xzzzz\P 
+    
+/(Y)X\1{2,4}b/
+    YX\P
+    YXY\P
+    YXYY\P 
+    YXYYY\P
+    YXYYYY\P 
+    
+/(Y)X\1{2,4}?b/
+    YX\P
+    YXY\P
+    YXYY\P 
+    YXYYY\P
+    YXYYYY\P 
+    
+/(Y)X\1{2,4}+b/
+    YX\P
+    YXY\P
+    YXYY\P 
+    YXYYY\P
+    YXYYYY\P 
+    
+/\++\KZ|\d+X|9+Y/
+    ++++123999\P
+    ++++123999Y\P
+    ++++Z1234\P 
+
+/Z(*F)/
+    Z\P
+    ZA\P 
+    
+/Z(?!)/
+    Z\P 
+    ZA\P 
+
+/dog(sbody)?/
+    dogs\P
+    dogs\P\P 
+    
+/dog(sbody)??/
+    dogs\P
+    dogs\P\P 
+
+/dog|dogsbody/
+    dogs\P
+    dogs\P\P 
+ 
+/dogsbody|dog/
+    dogs\P
+    dogs\P\P 
+
+/\bthe cat\b/
+    the cat\P
+    the cat\P\P
+
+/abc/
+   abc\P
+   abc\P\P
+   
+/abc\K123/
+    xyzabc123pqr
+    xyzabc12\P
+    xyzabc12\P\P
+    
+/(?<=abc)123/
+    xyzabc123pqr 
+    xyzabc12\P
+    xyzabc12\P\P
+
+/\babc\b/
+    +++abc+++
+    +++ab\P
+    +++ab\P\P  
+
+/(?&word)(?&element)(?(DEFINE)(?<element><[^m][^>]>[^<])(?<word>\w*+))/BZ
+
+/(?&word)(?&element)(?(DEFINE)(?<element><[^\d][^>]>[^<])(?<word>\w*+))/BZ
+
+/(ab)(x(y)z(cd(*ACCEPT)))pq/BZ
+
+/abc\K/+
+    abcdef
+    abcdef\N\N
+    xyzabcdef\N\N
+    ** Failers
+    abcdef\N 
+    xyzabcdef\N
+    
+/^(?:(?=abc)|abc\K)/+
+    abcdef
+    abcdef\N\N 
+    ** Failers 
+    abcdef\N 
+
+/a?b?/+
+    xyz
+    xyzabc
+    xyzabc\N
+    xyzabc\N\N
+    xyz\N\N    
+    ** Failers 
+    xyz\N 
+
+/^a?b?/+
+    xyz
+    xyzabc
+    ** Failers 
+    xyzabc\N
+    xyzabc\N\N
+    xyz\N\N    
+    xyz\N 
+    
+/^(?<name>a|b\g<name>c)/
+    aaaa
+    bacxxx
+    bbaccxxx 
+    bbbacccxx
+
+/^(?<name>a|b\g'name'c)/
+    aaaa
+    bacxxx
+    bbaccxxx 
+    bbbacccxx
+
+/^(a|b\g<1>c)/
+    aaaa
+    bacxxx
+    bbaccxxx 
+    bbbacccxx
+
+/^(a|b\g'1'c)/
+    aaaa
+    bacxxx
+    bbaccxxx 
+    bbbacccxx
+
+/^(a|b\g'-1'c)/
+    aaaa
+    bacxxx
+    bbaccxxx 
+    bbbacccxx
+
+/(^(a|b\g<-1>c))/
+    aaaa
+    bacxxx
+    bbaccxxx 
+    bbbacccxx
+
+/(?-i:\g<name>)(?i:(?<name>a))/
+    XaaX
+    XAAX 
+
+/(?i:\g<name>)(?-i:(?<name>a))/
+    XaaX
+    ** Failers 
+    XAAX 
+
+/(?-i:\g<+1>)(?i:(a))/
+    XaaX
+    XAAX 
+
+/(?=(?<regex>(?#simplesyntax)\$(?<name>[a-zA-Z_\x{7f}-\x{ff}][a-zA-Z0-9_\x{7f}-\x{ff}]*)(?:\[(?<index>[a-zA-Z0-9_\x{7f}-\x{ff}]+|\$\g<name>)\]|->\g<name>(\(.*?\))?)?|(?#simple syntax withbraces)\$\{(?:\g<name>(?<indices>\[(?:\g<index>|'(?:\\.|[^'\\])*'|"(?:\g<regex>|\\.|[^"\\])*")\])?|\g<complex>|\$\{\g<complex>\})\}|(?#complexsyntax)\{(?<complex>\$(?<segment>\g<name>(\g<indices>*|\(.*?\))?)(?:->\g<segment>)*|\$\g<complex>|\$\{\g<complex>\})\}))\{/
+
+/(?<n>a|b|c)\g<n>*/
+   abc
+   accccbbb 
+
+/^X(?7)(a)(?|(b)|(q)(r)(s))(c)(d)(Y)/
+    XYabcdY
+
+/(?<=b(?1)|zzz)(a)/
+    xbaax
+    xzzzax 
+
+/(a)(?<=b\1)/
+
+/(a)(?<=b+(?1))/
+
+/(a+)(?<=b(?1))/
+
+/(a(?<=b(?1)))/
+
+/(?<=b(?1))xyz/
+
+/(?<=b(?1))xyz(b+)pqrstuvew/
+
+/(a|bc)\1/SI
+
+/(a|bc)\1{2,3}/SI
+
+/(a|bc)(?1)/SI
+
+/(a|b\1)(a|b\1)/SI
+
+/(a|b\1){2}/SI
+
+/(a|bbbb\1)(a|bbbb\1)/SI
+
+/(a|bbbb\1){2}/SI
+
+/^From +([^ ]+) +[a-zA-Z][a-zA-Z][a-zA-Z] +[a-zA-Z][a-zA-Z][a-zA-Z] +[0-9]?[0-9] +[0-9][0-9]:[0-9][0-9]/SI
+
+/<tr([\w\W\s\d][^<>]{0,})><TD([\w\W\s\d][^<>]{0,})>([\d]{0,}\.)(.*)((<BR>([\w\W\s\d][^<>]{0,})|[\s]{0,}))<\/a><\/TD><TD([\w\W\s\d][^<>]{0,})>([\w\W\s\d][^<>]{0,})<\/TD><TD([\w\W\s\d][^<>]{0,})>([\w\W\s\d][^<>]{0,})<\/TD><\/TR>/isIS
+
+"(?>.*/)foo"SI
+
+/(?(?=[^a-z]+[a-z])  \d{2}-[a-z]{3}-\d{2}  |  \d{2}-\d{2}-\d{2} ) /xSI
+
+/(?:(?:(?:(?:(?:(?:(?:(?:(?:(a|b|c))))))))))/iSI
+
+/(?:c|d)(?:)(?:aaaaaaaa(?:)(?:bbbbbbbb)(?:bbbbbbbb(?:))(?:bbbbbbbb(?:)(?:bbbbbbbb)))/SI
+
+/<a[\s]+href[\s]*=[\s]*          # find <a href=
+ ([\"\'])?                       # find single or double quote
+ (?(1) (.*?)\1 | ([^\s]+))       # if quote found, match up to next matching
+                                 # quote, otherwise match up to next space
+/isxSI
+
+/^(?!:)                       # colon disallowed at start
+  (?:                         # start of item
+    (?: [0-9a-f]{1,4} |       # 1-4 hex digits or
+    (?(1)0 | () ) )           # if null previously matched, fail; else null
+    :                         # followed by colon
+  ){1,7}                      # end item; 1-7 of them required               
+  [0-9a-f]{1,4} $             # final hex number at end of string
+  (?(1)|.)                    # check that there was an empty component
+  /xiIS
+
+/(?|(?<a>A)|(?<a>B))/I
+    AB\Ca
+    BA\Ca
+
+/(?|(?<a>A)|(?<b>B))/ 
+
+/(?:a(?<quote> (?<apostrophe>')|(?<realquote>")) |
+    b(?<quote> (?<apostrophe>')|(?<realquote>")) ) 
+    (?('quote')[a-z]+|[0-9]+)/JIx
+    a"aaaaa
+    b"aaaaa 
+    ** Failers 
+    b"11111
+    a"11111 
+    
+/^(?|(a)(b)(c)(?<D>d)|(?<D>e)) (?('D')X|Y)/JDZx
+    abcdX
+    eX
+    ** Failers
+    abcdY
+    ey     
+    
+/(?<A>a) (b)(c)  (?<A>d  (?(R&A)$ | (?4)) )/JDZx
+    abcdd
+    ** Failers
+    abcdde  
+
+/abcd*/
+    xxxxabcd\P
+    xxxxabcd\P\P
+
+/abcd*/i
+    xxxxabcd\P
+    xxxxabcd\P\P
+    XXXXABCD\P
+    XXXXABCD\P\P
+
+/abc\d*/
+    xxxxabc1\P
+    xxxxabc1\P\P
+
+/(a)bc\1*/
+    xxxxabca\P
+    xxxxabca\P\P
+
+/abc[de]*/
+    xxxxabcde\P
+    xxxxabcde\P\P
+
+/-- This is not in the Perl >= 5.10 test because Perl seems currently to be
+    broken and not behaving as specified in that it *does* bumpalong after
+    hitting (*COMMIT). --/
+
+/(?1)(A(*COMMIT)|B)D/
+    ABD
+    XABD
+    BAD
+    ABXABD  
+    ** Failers 
+    ABX 
+    BAXBAD  
+
+/(\3)(\1)(a)/<JS>
+    cat
+
+/(\3)(\1)(a)/SI<JS>
+    cat
+
+/(\3)(\1)(a)/SI
+    cat
+
+/i(?(DEFINE)(?<s>a))/SI
+    i
+    
+/()i(?(1)a)/SI 
+    ia
+
+/(?i)a(?-i)b|c/BZ
+    XabX
+    XAbX
+    CcC 
+    ** Failers
+    XABX   
+
+/(?i)a(?s)b|c/BZ
+
+/(?i)a(?s-i)b|c/BZ
+
+/^(ab(c\1)d|x){2}$/BZ
+    xabcxd
+    
+/^(?&t)*+(?(DEFINE)(?<t>.))$/BZ
+
+/^(?&t)*(?(DEFINE)(?<t>.))$/BZ
+
+/ -- The first four of these are not in the Perl >= 5.10 test because Perl 
+     documents that the use of \K in assertions is "not well defined". The
+     last is here because Perl gives the match as "b" rather than "ab". I
+     believe this to be a Perl bug. --/  
+      
+/(?=a\Kb)ab/
+    ab 
+
+/(?!a\Kb)ac/
+    ac 
+    
+/^abc(?<=b\Kc)d/
+    abcd
+
+/^abc(?<!b\Kq)d/
+    abcd
+
+/(?>a\Kb)z|(ab)/
+    ab 
+
+/----------------------/
+
+/(?P<L1>(?P<L2>0|)|(?P>L2)(?P>L1))/
+
+/abc(*MARK:)pqr/
+
+/abc(*:)pqr/
+
+/abc(*FAIL:123)xyz/
+
+/--- This should, and does, fail. In Perl, it does not, which I think is a 
+     bug because replacing the B in the pattern by (B|D) does make it fail. ---/
+
+/A(*COMMIT)B/+K
+    ACABX
+
+/--- These should be different, but in Perl 5.11 are not, which I think
+     is a bug in Perl. ---/
+
+/A(*THEN)B|A(*THEN)C/K
+    AC
+
+/A(*PRUNE)B|A(*PRUNE)C/K
+    AC
+    
+/--- This should fail; the SKIP advances by one, but when we get to AC, the
+     PRUNE kills it. Perl behaves differently. ---/ 
+    
+/A(*PRUNE:A)A+(*SKIP:A)(B|Z) | AC/xK
+    AAAC
+
+/--- Mark names can be duplicated. Perl doesn't give a mark for this one,
+though PCRE does. ---/
+
+/^A(*:A)B|^X(*:A)Y/K
+    ** Failers
+    XAQQ
+    
+/--- COMMIT at the start of a pattern should be the same as an anchor. Perl 
+optimizations defeat this. So does the PCRE optimization unless we disable it 
+with \Y. ---/
+
+/(*COMMIT)ABC/
+    ABCDEFG
+    ** Failers
+    DEFGABC\Y  
+    
+/^(ab (c+(*THEN)cd) | xyz)/x
+    abcccd  
+
+/^(ab (c+(*PRUNE)cd) | xyz)/x
+    abcccd  
+
+/^(ab (c+(*FAIL)cd) | xyz)/x
+    abcccd  
+    
+/--- Perl 5.11 gets some of these wrong ---/ 
+
+/(?>.(*ACCEPT))*?5/
+    abcde
+
+/(.(*ACCEPT))*?5/
+    abcde
+
+/(.(*ACCEPT))5/
+    abcde
+
+/(.(*ACCEPT))*5/
+    abcde
+
+/A\NB./BZ
+    ACBD
+    *** Failers
+    A\nB
+    ACB\n   
+
+/A\NB./sBZ
+    ACBD
+    ACB\n 
+    *** Failers
+    A\nB  
+  
+/A\NB/<crlf>
+    A\nB
+    A\rB
+    ** Failers
+    A\r\nB    
+
+/\R+b/BZ
+
+/\R+\n/BZ
+
+/\R+\d/BZ
+
+/\d*\R/BZ
+
+/\s*\R/BZ
+    \x20\x0a
+    \x20\x0d
+    \x20\x0d\x0a
+
+/\S*\R/BZ
+    a\x0a
+
+/X\h*\R/BZ
+    X\x20\x0a
+
+/X\H*\R/BZ
+    X\x0d\x0a
+
+/X\H+\R/BZ
+    X\x0d\x0a
+
+/X\H++\R/BZ
+    X\x0d\x0a
+
+/-- Perl treats this one differently, not failing the second string. I believe
+    that is a bug in Perl. --/
+
+/^((abc|abcx)(*THEN)y|abcd)/
+    abcd
+    *** Failers 
+    abcxy 
+
+/(?<=abc)def/
+    abc\P\P
+
+/abc$/
+    abc
+    abc\P
+    abc\P\P
+
+/abc$/m
+    abc
+    abc\n
+    abc\P\P
+    abc\n\P\P 
+    abc\P
+    abc\n\P
+
+/abc\z/
+    abc
+    abc\P
+    abc\P\P
+
+/abc\Z/
+    abc
+    abc\P
+    abc\P\P
+
+/abc\b/
+    abc
+    abc\P
+    abc\P\P
+
+/abc\B/
+    abc
+    abc\P
+    abc\P\P
+
+/.+/
+    abc\>0
+    abc\>1
+    abc\>2
+    abc\>3
+    abc\>4
+    abc\>-4 
+
+/^\cģ/
+
+/(?P<abn>(?P=abn)xxx)/BZ
+
+/(a\1z)/BZ
+
+/(?P<abn>(?P=abn)(?<badstufxxx)/BZ
+
+/(?P<abn>(?P=axn)xxx)/BZ
+
+/(?P<abn>(?P=axn)xxx)(?<axn>yy)/BZ
+
+/-- These tests are here because Perl gets the first one wrong. --/
+
+/(\R*)(.)/s
+    \r\n
+    \r\r\n\n\r 
+    \r\r\n\n\r\n 
+
+/(\R)*(.)/s
+    \r\n
+    \r\r\n\n\r 
+    \r\r\n\n\r\n 
+
+/((?>\r\n|\n|\x0b|\f|\r|\x85)*)(.)/s
+    \r\n
+    \r\r\n\n\r 
+    \r\r\n\n\r\n 
+
+/-- --/
+
+/^abc$/BZ
+
+/^abc$/BZm
+
+/^(a)*+(\w)/S
+    aaaaX
+    ** Failers 
+    aaaa
+
+/^(?:a)*+(\w)/S
+    aaaaX
+    ** Failers 
+    aaaa
+
+/(a)++1234/SDZ
+
+/([abc])++1234/SI
+
+/(?<=(abc)+)X/
+
+/(^ab)/I
+
+/(^ab)++/I
+
+/(^ab|^)+/I
+
+/(^ab|^)++/I
+
+/(?:^ab)/I
+
+/(?:^ab)++/I
+
+/(?:^ab|^)+/I
+
+/(?:^ab|^)++/I
+
+/(.*ab)/I
+
+/(.*ab)++/I
+
+/(.*ab|.*)+/I
+
+/(.*ab|.*)++/I
+
+/(?:.*ab)/I
+
+/(?:.*ab)++/I
+
+/(?:.*ab|.*)+/I
+
+/(?:.*ab|.*)++/I
+
+/(?=a)[bcd]/I
+
+/((?=a))[bcd]/I
+
+/((?=a))+[bcd]/I
+
+/((?=a))++[bcd]/I
+
+/(?=a+)[bcd]/iI
+
+/(?=a+?)[bcd]/iI
+
+/(?=a++)[bcd]/iI
+
+/(?=a{3})[bcd]/iI
+
+/(abc)\1+/S
+
+/-- Perl doesn't get these right IMO (the 3rd is PCRE-specific) --/
+
+/(?1)(?:(b(*ACCEPT))){0}/
+    b
+
+/(?1)(?:(b(*ACCEPT))){0}c/
+    bc
+    ** Failers 
+    b 
+
+/(?1)(?:((*ACCEPT))){0}c/
+    c
+    c\N 
+
+/^.*?(?(?=a)a|b(*THEN)c)/
+    ba
+
+/^.*?(?(?=a)a|bc)/
+    ba
+
+/^.*?(?(?=a)a(*THEN)b|c)/
+    ac
+
+/^.*?(?(?=a)a(*THEN)b)c/
+    ac
+
+/^.*?(a(*THEN)b)c/
+    aabc
+    
+/^.*? (?1) c (?(DEFINE)(a(*THEN)b))/x
+    aabc
+
+/^.*?(a(*THEN)b|z)c/
+    aabc
+
+/^.*?(z|a(*THEN)b)c/
+    aabc
+
+/-- --/
+
+/-- These studied versions are here because they are not Perl-compatible; the
+    studying means the mark is not seen. --/
+
+/(*MARK:A)(*SKIP:B)(C|X)/KS
+    C
+    D
+     
+/(*:A)A+(*SKIP:A)(B|Z)/KS
+    AAAC
+
+/-- --/
+
+"(?=a*(*ACCEPT)b)c"
+    c
+    c\N 
+    
+/(?1)c(?(DEFINE)((*ACCEPT)b))/
+    c
+    c\N  
+    
+/(?>(*ACCEPT)b)c/
+    c
+    c\N  
+
+/(?:(?>(a)))+a%/++
+    %aa%
+
+/(a)b|ac/++SS
+    ac\O3
+    
+/(a)(b)x|abc/++
+     abc\O6
+
+/(a)bc|(a)(b)\2/
+    \O3abc
+    \O4abc 
+
+/(?(DEFINE)(a(?2)|b)(b(?1)|a))(?:(?1)|(?2))/SI
+
+/(a(?2)|b)(b(?1)|a)(?:(?1)|(?2))/SI
+
+/(a(?2)|b)(b(?1)|a)(?1)(?2)/SI
+
+/(abc)(?1)/SI
+
+/^(?>a)++/
+    aa\M
+    aaaaaaaaa\M 
+    
+/(a)(?1)++/
+    aa\M
+    aaaaaaaaa\M  
+
+/(?:(foo)|(bar)|(baz))X/SS=
+    bazfooX
+    foobazbarX
+    barfooX
+    bazX
+    foobarbazX    
+    bazfooX\O0
+    bazfooX\O2
+    bazfooX\O4
+    bazfooX\O6
+    bazfooX\O8
+    bazfooX\O10
+
+/(?=abc){3}abc/BZ
+
+/(?=abc)+abc/BZ
+
+/(?=abc)++abc/BZ
+
+/(?=abc){0}xyz/BZ
+
+/(?=(a))?./BZ
+
+/(?=(a))??./BZ
+
+/^(?=(a)){0}b(?1)/BZ
+
+/(?(DEFINE)(a))?b(?1)/BZ
+
+/^(?=(?1))?[az]([abc])d/BZ
+
+/^(?!a){0}\w+/BZ
+
+/(?<=(abc))?xyz/BZ
+
+/[:a[:abc]b:]/BZ
+
+/((?2))((?1))/SS
+    abc
+
+/((?(R2)a+|(?1)b))/SS
+    aaaabcde
+
+/(?(R)a*(?1)|((?R))b)/SS
+    aaaabcde
+
+/(a+|(?R)b)/
+
+/^(a(*:A)(d|e(*:B))z|aeq)/C
+    adz
+    aez
+    aeqwerty
+
+/.(*F)/
+    \P\Pabc
+
+/\btype\b\W*?\btext\b\W*?\bjavascript\b/IS
+
+/\btype\b\W*?\btext\b\W*?\bjavascript\b|\burl\b\W*?\bshell:|<input\b.*?\btype\b\W*?\bimage\b|\bonkeyup\b\W*?\=/IS
+
+/a(*SKIP)c|b(*ACCEPT)|/+SI
+    a
+
+/a(*SKIP)c|b(*ACCEPT)cd(*ACCEPT)|x/SI
+    ax
+
+'a*(*ACCEPT)b'+
+    \N\N
+    abc\N\N
+    bbb\N\N 
+
+/(*ACCEPT)a/+I
+    bax
+
+/z(*ACCEPT)a/+I
+    baxzbx
+
+/a(?:.)*?a/ims                                                                  
+    \Mabbbbbbbbbbbbbbbbbbbbba
+    
+/a(?:.(*THEN))*?a/ims
+    \Mabbbbbbbbbbbbbbbbbbbbba
+
+/a(?:.(*THEN:ABC))*?a/ims
+    \Mabbbbbbbbbbbbbbbbbbbbba
+
+/-- These tests are in agreement with development Perl 5.015, which has fixed
+    some things, but they don't all work with 5.012, so they aren't in the
+    Perl-compatible tests. Those after the first come from Perl's own test
+    files. --/
+    
+/^((yes|no)(*THEN)(*F))?/
+  yes
+
+/(A (.*)   C? (*THEN)  | A D) (*FAIL)/x
+AbcdCBefgBhiBqz
+
+/(A (.*)   C? (*THEN)  | A D) z/x
+AbcdCBefgBhiBqz
+
+/(A (.*)   C? (*THEN)  | A D) \s* (*FAIL)/x
+AbcdCBefgBhiBqz
+
+/(A (.*)   C? (*THEN)  | A D) \s* z/x
+AbcdCBefgBhiBqz
+
+/(A (.*)   (?:C|) (*THEN)  | A D) (*FAIL)/x
+AbcdCBefgBhiBqz
+
+/(A (.*)   (?:C|) (*THEN)  | A D) z/x
+AbcdCBefgBhiBqz
+
+/(A (.*)   C{0,6} (*THEN)  | A D) (*FAIL)/x
+AbcdCBefgBhiBqz
+
+/(A (.*)   C{0,6} (*THEN)  | A D) z/x
+AbcdCBefgBhiBqz
+
+/(A (.*)   (CE){0,6} (*THEN)  | A D) (*FAIL)/x
+AbcdCEBefgBhiBqz
+
+/(A (.*)   (CE){0,6} (*THEN)  | A D) z/x
+AbcdCEBefgBhiBqz
+
+/(A (.*)   (CE*){0,6} (*THEN)  | A D) (*FAIL)/x
+AbcdCBefgBhiBqz
+
+/(A (.*)   (CE*){0,6} (*THEN)  | A D) z/x
+AbcdCBefgBhiBqz
+
+/-----------------------------------------------/  
+
+/^(?>a+)(?>(z+))\w/BZ
+    aaaazzzzb
+    ** Failers
+    aazz  
+
+/(.)(\1|a(?2))/
+    bab
+    
+/\1|(.)(?R)\1/
+    cbbbc
+    
+/(.)((?(1)c|a)|a(?2))/
+    baa  
+
+/(?P<abn>(?P=abn)xxx)/BZ
+
+/(a\1z)/BZ
+
+/^(?>a+)(?>b+)(?>c+)(?>d+)(?>e+)/
+     \Maabbccddee
+
+/^(?>(a+))(?>(b+))(?>(c+))(?>(d+))(?>(e+))/
+     \Maabbccddee
+
+/^(?>(a+))(?>b+)(?>(c+))(?>d+)(?>(e+))/
+     \Maabbccddee
+
+/^a\x41z/<JS>
+    aAz
+    *** Failers
+    ax41z
+
+/^a[m\x41]z/<JS>
+    aAz
+
+/^a\x1z/<JS>
+    ax1z
+
+/^a\u0041z/<JS>
+    aAz
+    *** Failers
+    au0041z
+
+/^a[m\u0041]z/<JS>
+    aAz
+
+/^a\u041z/<JS>
+    au041z
+    *** Failers
+    aAz
+
+/^a\U0041z/<JS>
+    aU0041z
+    *** Failers
+    aAz
+
+/(?(?=c)c|d)++Y/BZ
+
+/(?(?=c)c|d)*+Y/BZ
+
+/a[\NB]c/
+    aNc
+    
+/a[B-\Nc]/ 
+
+/(a)(?2){0,1999}?(b)/
+
+/(a)(?(DEFINE)(b))(?2){0,1999}?(?2)/
+
+/--- This test, with something more complicated than individual letters, causes
+different behaviour in Perl. Perhaps it disables some optimization; no tag is
+passed back for the failures, whereas in PCRE there is a tag. ---/
+    
+/(A|P)(*:A)(B|P) | (X|P)(X|P)(*:B)(Y|P)/xK
+    AABC
+    XXYZ 
+    ** Failers
+    XAQQ  
+    XAQQXZZ  
+    AXQQQ 
+    AXXQQQ 
+
+/-- Perl doesn't give marks for these, though it does if the alternatives are
+replaced by single letters. --/
+    
+/(b|q)(*:m)f|a(*:n)w/K
+    aw 
+    ** Failers 
+    abc
+
+/(q|b)(*:m)f|a(*:n)w/K
+    aw 
+    ** Failers 
+    abc
+
+/-- After a partial match, the behaviour is as for a failure. --/
+
+/^a(*:X)bcde/K
+   abc\P
+   
+/-- These are here because Perl doesn't return a mark, except for the first --/
+
+/(?=(*:x))(q|)/K+
+    abc
+
+/(?=(*:x))((*:y)q|)/K+
+    abc
+
+/(?=(*:x))(?:(*:y)q|)/K+
+    abc
+
+/(?=(*:x))(?>(*:y)q|)/K+
+    abc
+
+/(?=a(*:x))(?!a(*:y)c)/K+
+    ab
+
+/(?=a(*:x))(?=a(*:y)c|)/K+
+    ab
+
+/(..)\1/
+    ab\P
+    aba\P
+    abab\P
+
+/(..)\1/i
+    ab\P
+    abA\P
+    aBAb\P
+
+/(..)\1{2,}/
+    ab\P
+    aba\P
+    abab\P
+    ababa\P
+    ababab\P
+    ababab\P\P
+    abababa\P
+    abababa\P\P
+
+/(..)\1{2,}/i
+    ab\P
+    aBa\P
+    aBAb\P
+    AbaBA\P
+    abABAb\P
+    aBAbaB\P\P
+    abABabA\P
+    abaBABa\P\P
+
+/(..)\1{2,}?x/i
+    ab\P
+    abA\P
+    aBAb\P
+    abaBA\P
+    abAbaB\P
+    abaBabA\P
+    abAbABaBx\P
+
+/^(..)\1/
+    aba\P
+
+/^(..)\1{2,3}x/
+    aba\P
+    ababa\P
+    ababa\P\P
+    abababx
+    ababababx  
+
+/^(..)\1{2,3}?x/
+    aba\P
+    ababa\P
+    ababa\P\P
+    abababx
+    ababababx  
+    
+/^(..)(\1{2,3})ab/
+    abababab
+
+/^\R/
+    \r\P
+    \r\P\P
+    
+/^\R{2,3}x/
+    \r\P
+    \r\P\P
+    \r\r\P 
+    \r\r\P\P
+    \r\r\r\P  
+    \r\r\r\P\P
+    \r\rx
+    \r\r\rx    
+
+/^\R{2,3}?x/
+    \r\P
+    \r\P\P
+    \r\r\P 
+    \r\r\P\P
+    \r\r\r\P  
+    \r\r\r\P\P
+    \r\rx
+    \r\r\rx    
+    
+/^\R?x/
+    \r\P
+    \r\P\P 
+    x
+    \rx  
+
+/^\R+x/
+    \r\P
+    \r\P\P 
+    \r\n\P
+    \r\n\P\P  
+    \rx  
+
+/^a$/<CRLF>
+    a\r\P
+    a\r\P\P 
+
+/^a$/m<CRLF>
+    a\r\P
+    a\r\P\P 
+
+/^(a$|a\r)/<CRLF>
+    a\r\P
+    a\r\P\P 
+
+/^(a$|a\r)/m<CRLF>
+    a\r\P
+    a\r\P\P 
+
+/./<CRLF>
+    \r\P
+    \r\P\P 
+  
+/.{2,3}/<CRLF>
+    \r\P 
+    \r\P\P
+    \r\r\P
+    \r\r\P\P
+    \r\r\r\P
+    \r\r\r\P\P     
+
+/.{2,3}?/<CRLF>
+    \r\P 
+    \r\P\P
+    \r\r\P
+    \r\r\P\P
+    \r\r\r\P
+    \r\r\r\P\P     
+
+/-- These two are here because Perl does not match: it seems to allow the
+COMMIT to escape from the assertion. --/
+
+/(?=a(*COMMIT)b|ac)ac|ac/
+    ac
+
+/(?=a(*COMMIT)b|(ac)) ac | (a)c/x
+    ac
+
+"AB(C(D))(E(F))?(?(?=\2)(?=\4))"
+    ABCDGHI\O03
+    
+/-- This one is here because Perl does not confine the *COMMIT to the 
+assertion, and therefore fails the entire subroutine call. --/ 
+    
+/((?=a(*COMMIT)b)ab|ac){0}(?:(?1)|a(c))/
+    ac 
+
+/-- End of testinput2 --/
diff --git a/ext/pcre/pcrelib/testdata/testinput3 b/ext/pcre/pcrelib/testdata/testinput3
new file mode 100644
index 0000000..6fea2f5
--- /dev/null
+++ b/ext/pcre/pcrelib/testdata/testinput3
@@ -0,0 +1,95 @@
+/-- This set of tests checks local-specific features, using the fr_FR locale. 
+    It is not Perl-compatible. There is different version called wintestinput3
+  f  or use on Windows, where the locale is called "french". --/
+
+/^[\w]+/
+    *** Failers
+    École
+
+/^[\w]+/Lfr_FR
+    École
+
+/^[\w]+/
+    *** Failers
+    École
+
+/^[\W]+/
+    École
+
+/^[\W]+/Lfr_FR
+    *** Failers
+    École
+
+/[\b]/
+    \b
+    *** Failers
+    a
+
+/[\b]/Lfr_FR
+    \b
+    *** Failers
+    a
+
+/^\w+/
+    *** Failers
+    École
+
+/^\w+/Lfr_FR
+    École
+
+/(.+)\b(.+)/
+    École
+
+/(.+)\b(.+)/Lfr_FR
+    *** Failers
+    École
+
+/École/i
+    École
+    *** Failers
+    école
+
+/École/iLfr_FR
+    École
+    école
+
+/\w/IS
+
+/\w/ISLfr_FR
+
+/^[\xc8-\xc9]/iLfr_FR
+    École
+    école
+
+/^[\xc8-\xc9]/Lfr_FR
+    École
+    *** Failers 
+    école
+
+/\W+/Lfr_FR
+    >>>\xaa<<<
+    >>>\xba<<< 
+
+/[\W]+/Lfr_FR
+    >>>\xaa<<<
+    >>>\xba<<< 
+
+/[^[:alpha:]]+/Lfr_FR
+    >>>\xaa<<<
+    >>>\xba<<< 
+
+/\w+/Lfr_FR
+    >>>\xaa<<<
+    >>>\xba<<< 
+
+/[\w]+/Lfr_FR
+    >>>\xaa<<<
+    >>>\xba<<< 
+
+/[[:alpha:]]+/Lfr_FR
+    >>>\xaa<<<
+    >>>\xba<<< 
+    
+/[[:alpha:]][[:lower:]][[:upper:]]/DZLfr_FR 
+
+/-- End of testinput3 --/
diff --git a/ext/pcre/pcrelib/testdata/testinput4 b/ext/pcre/pcrelib/testdata/testinput4
new file mode 100644
index 0000000..c7bb370
--- /dev/null
+++ b/ext/pcre/pcrelib/testdata/testinput4
@@ -0,0 +1,624 @@
+/-- This set of tests is for UTF support, excluding Unicode properties. It is
+    compatible with all versions of Perl >= 5.10 and both the 8-bit and 16-bit
+    PCRE libraries. --/
+   
+/a.b/8
+    acb
+    a\x7fb
+    a\x{100}b 
+    *** Failers
+    a\nb  
+
+/a(.{3})b/8
+    a\x{4000}xyb 
+    a\x{4000}\x7fyb 
+    a\x{4000}\x{100}yb 
+    *** Failers
+    a\x{4000}b 
+    ac\ncb 
+
+/a(.*?)(.)/
+    a\xc0\x88b
+
+/a(.*?)(.)/8
+    a\x{100}b
+
+/a(.*)(.)/
+    a\xc0\x88b
+
+/a(.*)(.)/8
+    a\x{100}b
+
+/a(.)(.)/
+    a\xc0\x92bcd
+
+/a(.)(.)/8
+    a\x{240}bcd
+
+/a(.?)(.)/
+    a\xc0\x92bcd
+
+/a(.?)(.)/8
+    a\x{240}bcd
+
+/a(.??)(.)/
+    a\xc0\x92bcd
+
+/a(.??)(.)/8
+    a\x{240}bcd
+
+/a(.{3})b/8
+    a\x{1234}xyb 
+    a\x{1234}\x{4321}yb 
+    a\x{1234}\x{4321}\x{3412}b 
+    *** Failers
+    a\x{1234}b 
+    ac\ncb 
+
+/a(.{3,})b/8
+    a\x{1234}xyb 
+    a\x{1234}\x{4321}yb 
+    a\x{1234}\x{4321}\x{3412}b 
+    axxxxbcdefghijb 
+    a\x{1234}\x{4321}\x{3412}\x{3421}b 
+    *** Failers
+    a\x{1234}b 
+
+/a(.{3,}?)b/8
+    a\x{1234}xyb 
+    a\x{1234}\x{4321}yb 
+    a\x{1234}\x{4321}\x{3412}b 
+    axxxxbcdefghijb 
+    a\x{1234}\x{4321}\x{3412}\x{3421}b 
+    *** Failers
+    a\x{1234}b 
+
+/a(.{3,5})b/8
+    a\x{1234}xyb 
+    a\x{1234}\x{4321}yb 
+    a\x{1234}\x{4321}\x{3412}b 
+    axxxxbcdefghijb 
+    a\x{1234}\x{4321}\x{3412}\x{3421}b 
+    axbxxbcdefghijb 
+    axxxxxbcdefghijb 
+    *** Failers
+    a\x{1234}b 
+    axxxxxxbcdefghijb 
+
+/a(.{3,5}?)b/8
+    a\x{1234}xyb 
+    a\x{1234}\x{4321}yb 
+    a\x{1234}\x{4321}\x{3412}b 
+    axxxxbcdefghijb 
+    a\x{1234}\x{4321}\x{3412}\x{3421}b 
+    axbxxbcdefghijb 
+    axxxxxbcdefghijb 
+    *** Failers
+    a\x{1234}b 
+    axxxxxxbcdefghijb 
+
+/^[a\x{c0}]/8
+    *** Failers
+    \x{100}
+
+/(?<=aXb)cd/8
+    aXbcd
+
+/(?<=a\x{100}b)cd/8
+    a\x{100}bcd
+
+/(?<=a\x{100000}b)cd/8
+    a\x{100000}bcd
+    
+/(?:\x{100}){3}b/8
+    \x{100}\x{100}\x{100}b
+    *** Failers 
+    \x{100}\x{100}b
+
+/\x{ab}/8
+    \x{ab} 
+    \xc2\xab
+    *** Failers 
+    \x00{ab}
+
+/(?<=(.))X/8
+    WXYZ
+    \x{256}XYZ 
+    *** Failers
+    XYZ 
+
+/[^a]+/8g
+    bcd
+    \x{100}aY\x{256}Z 
+    
+/^[^a]{2}/8
+    \x{100}bc
+ 
+/^[^a]{2,}/8
+    \x{100}bcAa
+
+/^[^a]{2,}?/8
+    \x{100}bca
+
+/[^a]+/8ig
+    bcd
+    \x{100}aY\x{256}Z 
+    
+/^[^a]{2}/8i
+    \x{100}bc
+ 
+/^[^a]{2,}/8i
+    \x{100}bcAa
+
+/^[^a]{2,}?/8i
+    \x{100}bca
+
+/\x{100}{0,0}/8
+    abcd
+ 
+/\x{100}?/8
+    abcd
+    \x{100}\x{100} 
+
+/\x{100}{0,3}/8 
+    \x{100}\x{100} 
+    \x{100}\x{100}\x{100}\x{100} 
+    
+/\x{100}*/8
+    abce
+    \x{100}\x{100}\x{100}\x{100} 
+
+/\x{100}{1,1}/8
+    abcd\x{100}\x{100}\x{100}\x{100} 
+
+/\x{100}{1,3}/8
+    abcd\x{100}\x{100}\x{100}\x{100} 
+
+/\x{100}+/8
+    abcd\x{100}\x{100}\x{100}\x{100} 
+
+/\x{100}{3}/8
+    abcd\x{100}\x{100}\x{100}XX
+
+/\x{100}{3,5}/8
+    abcd\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}XX
+
+/\x{100}{3,}/8
+    abcd\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}XX
+
+/(?<=a\x{100}{2}b)X/8+
+    Xyyya\x{100}\x{100}bXzzz
+
+/\D*/8
+  aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+
+/\D*/8
+  \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}
+
+/\D/8
+    1X2
+    1\x{100}2 
+  
+/>\S/8
+    > >X Y
+    > >\x{100} Y
+  
+/\d/8
+    \x{100}3
+    
+/\s/8
+    \x{100} X
+    
+/\D+/8
+    12abcd34
+    *** Failers
+    1234  
+
+/\D{2,3}/8
+    12abcd34
+    12ab34
+    *** Failers  
+    1234
+    12a34  
+
+/\D{2,3}?/8
+    12abcd34
+    12ab34
+    *** Failers  
+    1234
+    12a34  
+
+/\d+/8
+    12abcd34
+    *** Failers
+
+/\d{2,3}/8
+    12abcd34
+    1234abcd
+    *** Failers  
+    1.4 
+
+/\d{2,3}?/8
+    12abcd34
+    1234abcd
+    *** Failers  
+    1.4 
+
+/\S+/8
+    12abcd34
+    *** Failers
+    \    \ 
+
+/\S{2,3}/8
+    12abcd34
+    1234abcd
+    *** Failers
+    \     \  
+
+/\S{2,3}?/8
+    12abcd34
+    1234abcd
+    *** Failers
+    \     \  
+
+/>\s+</8+
+    12>      <34
+    *** Failers
+
+/>\s{2,3}</8+
+    ab>  <cd
+    ab>   <ce
+    *** Failers
+    ab>    <cd 
+
+/>\s{2,3}?</8+
+    ab>  <cd
+    ab>   <ce
+    *** Failers
+    ab>    <cd 
+
+/\w+/8
+    12      34
+    *** Failers
+    +++=*! 
+
+/\w{2,3}/8
+    ab  cd
+    abcd ce
+    *** Failers
+    a.b.c
+
+/\w{2,3}?/8
+    ab  cd
+    abcd ce
+    *** Failers
+    a.b.c
+
+/\W+/8
+    12====34
+    *** Failers
+    abcd 
+
+/\W{2,3}/8
+    ab====cd
+    ab==cd
+    *** Failers
+    a.b.c
+
+/\W{2,3}?/8
+    ab====cd
+    ab==cd
+    *** Failers
+    a.b.c
+
+/[\x{100}]/8
+    \x{100}
+    Z\x{100}
+    \x{100}Z
+    *** Failers 
+
+/[Z\x{100}]/8
+    Z\x{100}
+    \x{100}
+    \x{100}Z
+    *** Failers 
+
+/[\x{100}\x{200}]/8
+   ab\x{100}cd
+   ab\x{200}cd
+   *** Failers  
+
+/[\x{100}-\x{200}]/8
+   ab\x{100}cd
+   ab\x{200}cd
+   ab\x{111}cd 
+   *** Failers  
+
+/[z-\x{200}]/8
+   ab\x{100}cd
+   ab\x{200}cd
+   ab\x{111}cd 
+   abzcd
+   ab|cd  
+   *** Failers  
+
+/[Q\x{100}\x{200}]/8
+   ab\x{100}cd
+   ab\x{200}cd
+   Q? 
+   *** Failers  
+
+/[Q\x{100}-\x{200}]/8
+   ab\x{100}cd
+   ab\x{200}cd
+   ab\x{111}cd 
+   Q? 
+   *** Failers  
+
+/[Qz-\x{200}]/8
+   ab\x{100}cd
+   ab\x{200}cd
+   ab\x{111}cd 
+   abzcd
+   ab|cd  
+   Q? 
+   *** Failers  
+
+/[\x{100}\x{200}]{1,3}/8
+   ab\x{100}cd
+   ab\x{200}cd
+   ab\x{200}\x{100}\x{200}\x{100}cd
+   *** Failers  
+
+/[\x{100}\x{200}]{1,3}?/8
+   ab\x{100}cd
+   ab\x{200}cd
+   ab\x{200}\x{100}\x{200}\x{100}cd
+   *** Failers  
+
+/[Q\x{100}\x{200}]{1,3}/8
+   ab\x{100}cd
+   ab\x{200}cd
+   ab\x{200}\x{100}\x{200}\x{100}cd
+   *** Failers  
+
+/[Q\x{100}\x{200}]{1,3}?/8
+   ab\x{100}cd
+   ab\x{200}cd
+   ab\x{200}\x{100}\x{200}\x{100}cd
+   *** Failers  
+
+/(?<=[\x{100}\x{200}])X/8
+    abc\x{200}X
+    abc\x{100}X 
+    *** Failers
+    X  
+
+/(?<=[Q\x{100}\x{200}])X/8
+    abc\x{200}X
+    abc\x{100}X 
+    abQX 
+    *** Failers
+    X  
+
+/(?<=[\x{100}\x{200}]{3})X/8
+    abc\x{100}\x{200}\x{100}X
+    *** Failers
+    abc\x{200}X
+    X  
+
+/[^\x{100}\x{200}]X/8
+    AX
+    \x{150}X
+    \x{500}X 
+    *** Failers
+    \x{100}X
+    \x{200}X   
+
+/[^Q\x{100}\x{200}]X/8
+    AX
+    \x{150}X
+    \x{500}X 
+    *** Failers
+    \x{100}X
+    \x{200}X   
+    QX 
+
+/[^\x{100}-\x{200}]X/8
+    AX
+    \x{500}X 
+    *** Failers
+    \x{100}X
+    \x{150}X
+    \x{200}X   
+
+/[z-\x{100}]/8i
+    z
+    Z 
+    \x{100}
+    *** Failers
+    \x{102}
+    y    
+
+/[\xFF]/
+    >\xff<
+
+/[\xff]/8
+    >\x{ff}<
+
+/[^\xFF]/
+    XYZ
+
+/[^\xff]/8
+    XYZ
+    \x{123} 
+
+/^[ac]*b/8
+  xb
+
+/^[ac\x{100}]*b/8
+  xb
+
+/^[^x]*b/8i
+  xb
+
+/^[^x]*b/8
+  xb
+  
+/^\d*b/8
+  xb 
+
+/(|a)/g8
+    catac
+    a\x{256}a 
+
+/^\x{85}$/8i
+    \x{85}
+
+/^ሴ/8
+    ሴ 
+
+/^\ሴ/8
+    ሴ 
+
+"(?s)(.{1,5})"8
+    abcdefg
+    ab
+
+/a*\x{100}*\w/8
+    a 
+
+/\S\S/8g
+    A\x{a3}BC
+    
+/\S{2}/8g
+    A\x{a3}BC
+    
+/\W\W/8g
+    +\x{a3}== 
+
+/\W{2}/8g
+    +\x{a3}== 
+
+/\S/8g
+    \x{442}\x{435}\x{441}\x{442}
+
+/[\S]/8g
+    \x{442}\x{435}\x{441}\x{442}
+
+/\D/8g
+    \x{442}\x{435}\x{441}\x{442}
+
+/[\D]/8g
+    \x{442}\x{435}\x{441}\x{442}
+
+/\W/8g
+    \x{2442}\x{2435}\x{2441}\x{2442}
+
+/[\W]/8g
+    \x{2442}\x{2435}\x{2441}\x{2442}
+    
+/[\S\s]*/8
+    abc\n\r\x{442}\x{435}\x{441}\x{442}xyz 
+
+/[\x{41f}\S]/8g
+    \x{442}\x{435}\x{441}\x{442}
+
+/.[^\S]./8g
+    abc def\x{442}\x{443}xyz\npqr
+
+/.[^\S\n]./8g
+    abc def\x{442}\x{443}xyz\npqr
+
+/[[:^alnum:]]/8g  
+    +\x{2442}
+    
+/[[:^alpha:]]/8g 
+    +\x{2442}
+    
+/[[:^ascii:]]/8g 
+    A\x{442}
+    
+/[[:^blank:]]/8g 
+    A\x{442}
+    
+/[[:^cntrl:]]/8g 
+    A\x{442}
+    
+/[[:^digit:]]/8g 
+    A\x{442}
+    
+/[[:^graph:]]/8g 
+    \x19\x{e01ff}
+    
+/[[:^lower:]]/8g 
+    A\x{422}
+    
+/[[:^print:]]/8g 
+    \x{19}\x{e01ff}
+    
+/[[:^punct:]]/8g 
+    A\x{442}
+    
+/[[:^space:]]/8g 
+    A\x{442}
+    
+/[[:^upper:]]/8g 
+    a\x{442}
+    
+/[[:^word:]]/8g  
+    +\x{2442}
+    
+/[[:^xdigit:]]/8g
+    M\x{442}
+
+/[^ABCDEFGHIJKLMNOPQRSTUVWXYZÀ�ÂÃÄÅÆÇÈÉÊËÌ�Î��ÑÒÓÔÕÖØÙÚÛÜ�ÞĀĂĄĆĈĊČĎ�ĒĔĖĘĚĜĞĠĢĤĦĨĪĬĮİIJĴĶĹĻĽĿ�ŃŅŇŊŌŎ�ŒŔŖŘŚŜŞŠŢŤŦŨŪŬŮŰŲŴŶŸŹŻŽ�ƂƄƆƇƉƊƋƎ��ƑƓƔƖƗƘƜ�ƟƠƢƤƦƧƩƬƮƯƱƲƳƵƷƸƼDŽLJNJ��ǑǓǕǗǙǛǞǠǢǤǦǨǪǬǮDZǴǶǷǸǺǼǾȀȂȄȆȈȊȌȎ�ȒȔȖȘȚȜȞȠȢȤȦȨȪȬȮȰȲȺȻȽȾ�ΆΈΉΊΌΎ�ΑΒΓΔΕΖΗΘΙΚΛΜ�ΞΟΠΡΣΤΥΦΧΨΩΪΫϒϓϔϘϚϜϞϠϢϤϦϨϪϬϮϴϷϹϺϽϾϿЀ�ЂЃЄЅІЇЈЉЊЋЌ�Ў��БВГДЕЖЗИЙКЛМ�ОПРСТУФХЦЧШЩЪЫЬЭЮЯѠѢѤѦѨѪѬѮѰѲѴѶѸѺѼѾҀҊҌҎ�ҒҔҖҘҚҜҞҠҢҤҦҨҪҬҮҰҲҴҶҸҺҼҾӀ�ӃӅӇӉӋ��ӒӔӖӘӚӜӞӠӢӤӦӨӪӬӮӰӲӴӶӸԀԂԄԆԈԊԌԎԱԲԳԴԵԶԷԸԹԺԻԼԽԾԿՀ�ՂՃՄՅՆՇՈՉՊՋՌ�Վ��ՑՒՓՔՕՖႠႡႢႣႤႥႦႧႨႩႪႫႬႭႮႯႰႱႲႳႴႵႶႷႸႹႺႻႼႽႾႿჀ�ჂჃჄჅḀḂḄḆḈḊḌḎ�ḒḔḖḘḚḜḞḠḢḤḦḨḪḬḮḰḲḴḶḸḺḼḾṀṂṄṆṈṊṌṎ�ṒṔṖṘṚṜṞṠṢṤṦṨṪṬṮṰṲṴṶṸṺṼṾẀẂẄẆẈẊẌẎ�ẒẔẠẢẤẦẨẪẬẮẰẲẴẶẸẺẼẾỀỂỄỆỈỊỌỎ�ỒỔỖỘỚỜỞỠỢỤỦỨỪỬỮỰỲỴỶỸἈἉἊἋἌ�Ἆ�ἘἙἚἛἜ�ἨἩἪἫἬἭἮἯἸἹἺἻἼἽἾἿὈὉὊὋὌ�ὙὛ�ὟὨὩὪὫὬὭὮὯᾸᾹᾺΆῈΈῊΉῘῙῚΊῨῩῪΎῬῸΌῺΏabcdefghijklmnopqrstuvwxyzªµºßàáâãäåæçèéêëìíîïðñòóôõöøùúûüýþÿ�ăąćĉċ��đēĕėęě�ğġģĥħĩīĭįıijĵķĸĺļľŀłńņňʼnŋ��őœŕŗřś�şšţťŧũūŭůűųŵŷźżžſƀƃƅƈƌ�ƒƕƙƚƛƞơƣƥƨƪƫƭưƴƶƹƺƽƾƿdžljnjǎ�ǒǔǖǘǚǜ�ǟǡǣǥǧǩǫǭǯǰdzǵǹǻǽǿ�ȃȅȇȉȋ��ȑȓȕȗșț�ȟȡȣȥȧȩȫȭȯȱȳȴȵȶȷȸȹȼȿɀ�ɑɒɓɔɕɖɗɘəɚɛɜ�ɞɟɠɡɢɣɤɥɦɧɨɩɪɫɬɭɮɯɰɱɲɳɴɵɶɷɸɹɺɻɼɽɾɿʀ�ʂʃʄʅʆʇʈʉʊʋʌ�ʎ��ʑʒʓʔʕʖʗʘʙʚʛʜ�ʞʟʠʡʢʣʤʥʦʧʨʩʪʫʬʭʮʯ�άέήίΰαβγδεζηθικλμνξοπ�ςστυφχψωϊϋό�ώ�ϑϕϖϗϙϛ�ϟϡϣϥϧϩϫϭϯϰϱϲϳϵϸϻϼабвгдежзийклмнопр�туфхцчшщъыь�ю��ёђѓєѕіїјљњћќ�ўџѡѣѥѧѩѫѭѯѱѳѵѷѹѻѽѿ�ҋ��ґғҕҗҙқ�ҟҡңҥҧҩҫҭүұҳҵҷҹһҽҿӂӄӆӈӊӌӎӑӓӕӗәӛ�ӟӡӣӥӧөӫӭӯӱӳӵӷӹ�ԃԅԇԉԋ��աբգդեզէըթժիլխծկհձղճմյնշոչպջռսվտր�ւփքօֆևᴀ�ᴂᴃᴄᴅᴆᴇᴈᴉᴊᴋᴌ�ᴎ��ᴑᴒᴓᴔᴕᴖᴗᴘᴙᴚᴛᴜ�ᴞᴟᴠᴡᴢᴣᴤᴥᴦᴧᴨᴩᴪᴫᵢᵣᵤᵥᵦᵧᵨᵩᵪᵫᵬᵭᵮᵯᵰᵱᵲᵳᵴᵵᵶᵷᵹᵺᵻᵼᵽᵾᵿᶀ�ᶂᶃᶄᶅᶆᶇᶈᶉᶊᶋᶌ�ᶎ��ᶑᶒᶓᶔᶕᶖᶗᶘᶙᶚ�ḃḅḇḉḋ��ḑḓḕḗḙḛ�ḟḡḣḥḧḩḫḭḯḱḳḵḷḹḻḽḿ�ṃṅṇṉṋ��ṑṓṕṗṙṛ�ṟṡṣṥṧṩṫṭṯṱṳṵṷṹṻṽṿ�ẃẅẇẉẋ��ẑẓẕẖẗẘẙẚẛạảấầẩẫậắằẳẵặẹẻẽế�ểễệỉị��ốồổỗộớ�ởỡợụủứừửữựỳỵỷỹἀ�ἂἃἄἅἆἇ�ἑἒἓἔἕἠἡἢἣἤἥἦἧἰἱἲἳἴἵἶἷὀ�ὂὃὄὅ�ὑὒὓὔὕὖὗὠὡὢὣὤὥὦὧὰάὲέὴήὶίὸόὺύὼώᾀ�ᾂᾃᾄᾅᾆᾇ�ᾑᾒᾓᾔᾕᾖᾗᾠᾡᾢᾣᾤᾥᾦᾧᾰᾱᾲᾳᾴᾶᾷιῂῃῄῆῇ�ῑῒΐῖῗῠῡῢΰῤῥῦῧῲῳῴῶῷ�ⲃⲅⲇⲉⲋ��ⲑⲓⲕⲗⲙⲛ�ⲟⲡⲣⲥⲧⲩⲫⲭⲯⲱⲳⲵⲷⲹⲻⲽⲿ�ⳃⳅⳇⳉⳋ��ⳑⳓⳕⳗⳙⳛ�ⳟⳡⳣⳤⴀ�ⴂⴃⴄⴅⴆⴇⴈⴉⴊⴋⴌ�ⴎ��ⴑⴒⴓⴔⴕⴖⴗⴘⴙⴚⴛⴜ�ⴞⴟⴠⴡⴢⴣⴤⴥff�flffifflſtstﬓﬔﬕﬖﬗ\d-_^]/8
+
+/^[^d]*?$/
+    abc
+
+/^[^d]*?$/8
+    abc
+
+/^[^d]*?$/i
+    abc
+
+/^[^d]*?$/8i
+    abc
+
+/(?i)[\xc3\xa9\xc3\xbd]|[\xc3\xa9\xc3\xbdA]/8
+
+/^[a\x{c0}]b/8
+    \x{c0}b
+    
+/^([a\x{c0}]*?)aa/8
+    a\x{c0}aaaa/ 
+
+/^([a\x{c0}]*?)aa/8
+    a\x{c0}aaaa/ 
+    a\x{c0}a\x{c0}aaa/ 
+
+/^([a\x{c0}]*)aa/8
+    a\x{c0}aaaa/ 
+    a\x{c0}a\x{c0}aaa/ 
+
+/^([a\x{c0}]*)a\x{c0}/8
+    a\x{c0}aaaa/ 
+    a\x{c0}a\x{c0}aaa/ 
+
+/A*/g8
+    AAB\x{123}BAA
+
+/(abc)\1/8i
+   abc
+
+/(abc)\1/8
+   abc
+
+/a(*:a\x{1234}b)/8K
+    abc
+
+/a(*:a£b)/8K 
+    abc
+
+/-- End of testinput4 --/
diff --git a/ext/pcre/pcrelib/testdata/testinput5 b/ext/pcre/pcrelib/testdata/testinput5
new file mode 100644
index 0000000..642749c
--- /dev/null
+++ b/ext/pcre/pcrelib/testdata/testinput5
@@ -0,0 +1,772 @@
+/-- This set of tests checks the API, internals, and non-Perl stuff for UTF
+    support, excluding Unicode properties. However, tests that give different
+    results in 8-bit and 16-bit modes are excluded (see tests 16 and 17). --/
+
+/\x{110000}/8DZ
+
+/\x{ffffffff}/8
+
+/\x{100000000}/8
+
+/\x{d800}/8
+
+/\x{dfff}/8
+
+/\x{d7ff}/8
+
+/\x{e000}/8
+
+/^\x{100}a\x{1234}/8
+    \x{100}a\x{1234}bcd
+
+/\x{0041}\x{2262}\x{0391}\x{002e}/DZ8
+    \x{0041}\x{2262}\x{0391}\x{002e}
+    
+/.{3,5}X/DZ8
+    \x{212ab}\x{212ab}\x{212ab}\x{861}X
+
+/.{3,5}?/DZ8
+    \x{212ab}\x{212ab}\x{212ab}\x{861}
+
+/(?<=\C)X/8
+    Should produce an error diagnostic
+    
+/^[ab]/8DZ
+    bar
+    *** Failers
+    c
+    \x{ff}
+    \x{100}  
+
+/^[^ab]/8DZ
+    c
+    \x{ff}
+    \x{100}  
+    *** Failers 
+    aaa
+  
+/\x{100}*(\d+|"(?1)")/8
+    1234
+    "1234" 
+    \x{100}1234
+    "\x{100}1234"  
+    \x{100}\x{100}12ab 
+    \x{100}\x{100}"12" 
+    *** Failers 
+    \x{100}\x{100}abcd
+
+/\x{100}*/8DZ
+
+/a\x{100}*/8DZ
+
+/ab\x{100}*/8DZ
+
+/\x{100}*A/8DZ
+    A
+
+/\x{100}*\d(?R)/8DZ
+
+/[Z\x{100}]/8DZ
+    Z\x{100}
+    \x{100}
+    \x{100}Z
+    *** Failers 
+
+/[\x{200}-\x{100}]/8
+
+/[Ä€-Ä„]/8
+    \x{100}
+    \x{104}
+    *** Failers
+    \x{105}
+    \x{ff}    
+
+/[z-\x{100}]/8DZ
+
+/[z\Qa-d]Ä€\E]/8DZ
+    \x{100}
+    Ā 
+
+/[\xFF]/DZ
+    >\xff<
+
+/[^\xFF]/DZ
+
+/[Ä-Ü]/8
+    Ö # Matches without Study
+    \x{d6}
+    
+/[Ä-Ü]/8S
+    Ö <-- Same with Study
+    \x{d6}
+    
+/[\x{c4}-\x{dc}]/8 
+    Ö # Matches without Study
+    \x{d6} 
+
+/[\x{c4}-\x{dc}]/8S
+    Ö <-- Same with Study
+    \x{d6} 
+
+/[^\x{100}]abc(xyz(?1))/8DZ
+
+/[ab\x{100}]abc(xyz(?1))/8DZ
+
+/(\x{100}(b(?2)c))?/DZ8
+
+/(\x{100}(b(?2)c)){0,2}/DZ8
+
+/(\x{100}(b(?1)c))?/DZ8
+
+/(\x{100}(b(?1)c)){0,2}/DZ8
+
+/\W/8
+    A.B
+    A\x{100}B 
+  
+/\w/8
+    \x{100}X   
+
+/^\ሴ/8DZ
+
+/\x{100}*\d/8DZ
+
+/\x{100}*\s/8DZ
+
+/\x{100}*\w/8DZ
+
+/\x{100}*\D/8DZ
+
+/\x{100}*\S/8DZ
+
+/\x{100}*\W/8DZ
+
+/()()()()()()()()()()
+ ()()()()()()()()()()
+ ()()()()()()()()()()
+ ()()()()()()()()()()
+ A (x) (?41) B/8x
+    AxxB     
+
+/^[\x{100}\E-\Q\E\x{150}]/BZ8
+
+/^[\QĀ\E-\Q�\E]/BZ8
+
+/^abc./mgx8<any>
+    abc1 \x0aabc2 \x0babc3xx \x0cabc4 \x0dabc5xx \x0d\x0aabc6 \x{0085}abc7 \x{2028}abc8 \x{2029}abc9 JUNK
+
+/abc.$/mgx8<any>
+    abc1\x0a abc2\x0b abc3\x0c abc4\x0d abc5\x0d\x0a abc6\x{0085} abc7\x{2028} abc8\x{2029} abc9
+
+/^a\Rb/8<bsr_unicode>
+    a\nb
+    a\rb
+    a\r\nb
+    a\x0bb
+    a\x0cb
+    a\x{85}b   
+    a\x{2028}b 
+    a\x{2029}b 
+    ** Failers
+    a\n\rb    
+
+/^a\R*b/8<bsr_unicode>
+    ab
+    a\nb
+    a\rb
+    a\r\nb
+    a\x0bb
+    a\x0c\x{2028}\x{2029}b
+    a\x{85}b   
+    a\n\rb    
+    a\n\r\x{85}\x0cb 
+
+/^a\R+b/8<bsr_unicode>
+    a\nb
+    a\rb
+    a\r\nb
+    a\x0bb
+    a\x0c\x{2028}\x{2029}b
+    a\x{85}b   
+    a\n\rb    
+    a\n\r\x{85}\x0cb 
+    ** Failers
+    ab  
+
+/^a\R{1,3}b/8<bsr_unicode>
+    a\nb
+    a\n\rb
+    a\n\r\x{85}b
+    a\r\n\r\nb 
+    a\r\n\r\n\r\nb 
+    a\n\r\n\rb
+    a\n\n\r\nb 
+    ** Failers
+    a\n\n\n\rb
+    a\r
+
+/\H\h\V\v/8
+    X X\x0a
+    X\x09X\x0b
+    ** Failers
+    \x{a0} X\x0a   
+    
+/\H*\h+\V?\v{3,4}/8 
+    \x09\x20\x{a0}X\x0a\x0b\x0c\x0d\x0a
+    \x09\x20\x{a0}\x0a\x0b\x0c\x0d\x0a
+    \x09\x20\x{a0}\x0a\x0b\x0c
+    ** Failers 
+    \x09\x20\x{a0}\x0a\x0b
+     
+/\H\h\V\v/8
+    \x{3001}\x{3000}\x{2030}\x{2028}
+    X\x{180e}X\x{85}
+    ** Failers
+    \x{2009} X\x0a   
+    
+/\H*\h+\V?\v{3,4}/8 
+    \x{1680}\x{180e}\x{2007}X\x{2028}\x{2029}\x0c\x0d\x0a
+    \x09\x{205f}\x{a0}\x0a\x{2029}\x0c\x{2028}\x0a
+    \x09\x20\x{202f}\x0a\x0b\x0c
+    ** Failers 
+    \x09\x{200a}\x{a0}\x{2028}\x0b
+     
+/[\h]/8BZ
+    >\x{1680}
+
+/[\h]{3,}/8BZ
+    >\x{1680}\x{180e}\x{2000}\x{2003}\x{200a}\x{202f}\x{205f}\x{3000}<
+
+/[\v]/8BZ
+
+/[\H]/8BZ
+
+/[\V]/8BZ
+
+/.*$/8<any>
+    \x{1ec5} 
+    
+/a\Rb/I8<bsr_anycrlf>
+    a\rb
+    a\nb
+    a\r\nb
+    ** Failers
+    a\x{85}b
+    a\x0bb     
+
+/a\Rb/I8<bsr_unicode>
+    a\rb
+    a\nb
+    a\r\nb
+    a\x{85}b
+    a\x0bb     
+    ** Failers 
+    a\x{85}b\<bsr_anycrlf>
+    a\x0bb\<bsr_anycrlf>
+    
+/a\R?b/I8<bsr_anycrlf>
+    a\rb
+    a\nb
+    a\r\nb
+    ** Failers
+    a\x{85}b
+    a\x0bb     
+
+/a\R?b/I8<bsr_unicode>
+    a\rb
+    a\nb
+    a\r\nb
+    a\x{85}b
+    a\x0bb     
+    ** Failers 
+    a\x{85}b\<bsr_anycrlf>
+    a\x0bb\<bsr_anycrlf>
+ 
+/.*a.*=.b.*/8<ANY>
+    QQQ\x{2029}ABCaXYZ=!bPQR
+    ** Failers
+    a\x{2029}b
+    \x61\xe2\x80\xa9\x62 
+
+/[[:a\x{100}b:]]/8
+
+/a[^]b/<JS>8
+    a\x{1234}b
+    a\nb 
+    ** Failers
+    ab  
+    
+/a[^]+b/<JS>8
+    aXb
+    a\nX\nX\x{1234}b 
+    ** Failers
+    ab  
+
+/(\x{de})\1/
+    \x{de}\x{de}
+
+/X/8f<any> 
+    A\x{1ec5}ABCXYZ
+
+/Xa{2,4}b/8
+    X\P
+    Xa\P
+    Xaa\P 
+    Xaaa\P
+    Xaaaa\P 
+    
+/Xa{2,4}?b/8
+    X\P
+    Xa\P
+    Xaa\P 
+    Xaaa\P
+    Xaaaa\P 
+    
+/Xa{2,4}+b/8
+    X\P
+    Xa\P
+    Xaa\P 
+    Xaaa\P
+    Xaaaa\P 
+    
+/X\x{123}{2,4}b/8
+    X\P
+    X\x{123}\P
+    X\x{123}\x{123}\P 
+    X\x{123}\x{123}\x{123}\P
+    X\x{123}\x{123}\x{123}\x{123}\P 
+    
+/X\x{123}{2,4}?b/8
+    X\P
+    X\x{123}\P
+    X\x{123}\x{123}\P 
+    X\x{123}\x{123}\x{123}\P
+    X\x{123}\x{123}\x{123}\x{123}\P 
+    
+/X\x{123}{2,4}+b/8
+    X\P
+    X\x{123}\P
+    X\x{123}\x{123}\P 
+    X\x{123}\x{123}\x{123}\P
+    X\x{123}\x{123}\x{123}\x{123}\P 
+    
+/X\x{123}{2,4}b/8
+    Xx\P
+    X\x{123}x\P
+    X\x{123}\x{123}x\P 
+    X\x{123}\x{123}\x{123}x\P
+    X\x{123}\x{123}\x{123}\x{123}x\P 
+    
+/X\x{123}{2,4}?b/8
+    Xx\P
+    X\x{123}x\P
+    X\x{123}\x{123}x\P 
+    X\x{123}\x{123}\x{123}x\P
+    X\x{123}\x{123}\x{123}\x{123}x\P 
+    
+/X\x{123}{2,4}+b/8
+    Xx\P
+    X\x{123}x\P
+    X\x{123}\x{123}x\P 
+    X\x{123}\x{123}\x{123}x\P
+    X\x{123}\x{123}\x{123}\x{123}x\P 
+    
+/X\d{2,4}b/8
+    X\P
+    X3\P
+    X33\P 
+    X333\P
+    X3333\P 
+    
+/X\d{2,4}?b/8
+    X\P
+    X3\P
+    X33\P 
+    X333\P
+    X3333\P 
+    
+/X\d{2,4}+b/8
+    X\P
+    X3\P
+    X33\P 
+    X333\P
+    X3333\P 
+
+/X\D{2,4}b/8
+    X\P
+    Xa\P
+    Xaa\P 
+    Xaaa\P
+    Xaaaa\P 
+    
+/X\D{2,4}?b/8
+    X\P
+    Xa\P
+    Xaa\P 
+    Xaaa\P
+    Xaaaa\P 
+    
+/X\D{2,4}+b/8
+    X\P
+    Xa\P
+    Xaa\P 
+    Xaaa\P
+    Xaaaa\P 
+
+/X\D{2,4}b/8
+    X\P
+    X\x{123}\P
+    X\x{123}\x{123}\P 
+    X\x{123}\x{123}\x{123}\P
+    X\x{123}\x{123}\x{123}\x{123}\P 
+    
+/X\D{2,4}?b/8
+    X\P
+    X\x{123}\P
+    X\x{123}\x{123}\P 
+    X\x{123}\x{123}\x{123}\P
+    X\x{123}\x{123}\x{123}\x{123}\P 
+    
+/X\D{2,4}+b/8
+    X\P
+    X\x{123}\P
+    X\x{123}\x{123}\P 
+    X\x{123}\x{123}\x{123}\P
+    X\x{123}\x{123}\x{123}\x{123}\P 
+
+/X[abc]{2,4}b/8
+    X\P
+    Xa\P
+    Xaa\P 
+    Xaaa\P
+    Xaaaa\P 
+    
+/X[abc]{2,4}?b/8
+    X\P
+    Xa\P
+    Xaa\P 
+    Xaaa\P
+    Xaaaa\P 
+    
+/X[abc]{2,4}+b/8
+    X\P
+    Xa\P
+    Xaa\P 
+    Xaaa\P
+    Xaaaa\P 
+
+/X[abc\x{123}]{2,4}b/8
+    X\P
+    X\x{123}\P
+    X\x{123}\x{123}\P 
+    X\x{123}\x{123}\x{123}\P
+    X\x{123}\x{123}\x{123}\x{123}\P 
+    
+/X[abc\x{123}]{2,4}?b/8
+    X\P
+    X\x{123}\P
+    X\x{123}\x{123}\P 
+    X\x{123}\x{123}\x{123}\P
+    X\x{123}\x{123}\x{123}\x{123}\P 
+    
+/X[abc\x{123}]{2,4}+b/8
+    X\P
+    X\x{123}\P
+    X\x{123}\x{123}\P 
+    X\x{123}\x{123}\x{123}\P
+    X\x{123}\x{123}\x{123}\x{123}\P 
+
+/X[^a]{2,4}b/8
+    X\P
+    Xz\P
+    Xzz\P 
+    Xzzz\P
+    Xzzzz\P 
+    
+/X[^a]{2,4}?b/8
+    X\P
+    Xz\P
+    Xzz\P 
+    Xzzz\P
+    Xzzzz\P 
+    
+/X[^a]{2,4}+b/8
+    X\P
+    Xz\P
+    Xzz\P 
+    Xzzz\P
+    Xzzzz\P 
+
+/X[^a]{2,4}b/8
+    X\P
+    X\x{123}\P
+    X\x{123}\x{123}\P 
+    X\x{123}\x{123}\x{123}\P
+    X\x{123}\x{123}\x{123}\x{123}\P 
+    
+/X[^a]{2,4}?b/8
+    X\P
+    X\x{123}\P
+    X\x{123}\x{123}\P 
+    X\x{123}\x{123}\x{123}\P
+    X\x{123}\x{123}\x{123}\x{123}\P 
+    
+/X[^a]{2,4}+b/8
+    X\P
+    X\x{123}\P
+    X\x{123}\x{123}\P 
+    X\x{123}\x{123}\x{123}\P
+    X\x{123}\x{123}\x{123}\x{123}\P 
+
+/(Y)X\1{2,4}b/8
+    YX\P
+    YXY\P
+    YXYY\P 
+    YXYYY\P
+    YXYYYY\P 
+    
+/(Y)X\1{2,4}?b/8
+    YX\P
+    YXY\P
+    YXYY\P 
+    YXYYY\P
+    YXYYYY\P 
+    
+/(Y)X\1{2,4}+b/8
+    YX\P
+    YXY\P
+    YXYY\P 
+    YXYYY\P
+    YXYYYY\P 
+
+/(\x{123})X\1{2,4}b/8
+    \x{123}X\P
+    \x{123}X\x{123}\P
+    \x{123}X\x{123}\x{123}\P 
+    \x{123}X\x{123}\x{123}\x{123}\P
+    \x{123}X\x{123}\x{123}\x{123}\x{123}\P 
+    
+/(\x{123})X\1{2,4}?b/8
+    \x{123}X\P
+    \x{123}X\x{123}\P
+    \x{123}X\x{123}\x{123}\P 
+    \x{123}X\x{123}\x{123}\x{123}\P
+    \x{123}X\x{123}\x{123}\x{123}\x{123}\P 
+    
+/(\x{123})X\1{2,4}+b/8
+    \x{123}X\P
+    \x{123}X\x{123}\P
+    \x{123}X\x{123}\x{123}\P 
+    \x{123}X\x{123}\x{123}\x{123}\P
+    \x{123}X\x{123}\x{123}\x{123}\x{123}\P 
+
+/\bthe cat\b/8
+    the cat\P
+    the cat\P\P
+
+/abcd*/8
+    xxxxabcd\P
+    xxxxabcd\P\P
+
+/abcd*/i8
+    xxxxabcd\P
+    xxxxabcd\P\P
+    XXXXABCD\P
+    XXXXABCD\P\P
+
+/abc\d*/8
+    xxxxabc1\P
+    xxxxabc1\P\P
+
+/(a)bc\1*/8
+    xxxxabca\P
+    xxxxabca\P\P
+
+/abc[de]*/8
+    xxxxabcde\P
+    xxxxabcde\P\P
+
+/X\W{3}X/8
+    \PX
+
+/\sxxx\s/8T1
+    AB\x{85}xxx\x{a0}XYZ
+    AB\x{a0}xxx\x{85}XYZ
+
+/\S \S/8T1
+    \x{a2} \x{84} 
+
+'A#хц'8x<any>BZ
+
+'A#хц
+  PQ'8x<any>BZ
+  
+/a+#Ñ…aa
+  z#XX?/8x<any>BZ 
+
+/a+#Ñ…aa
+  z#Ñ…?/8x<any>BZ 
+
+/\g{A}xxx#bXX(?'A'123)
(?'A'456)/8x<any>BZ
+
+/\g{A}xxx#bÑ…(?'A'123)
(?'A'456)/8x<any>BZ
+
+/^\cģ/8
+
+/(\R*)(.)/s8
+    \r\n
+    \r\r\n\n\r 
+    \r\r\n\n\r\n 
+
+/(\R)*(.)/s8
+    \r\n
+    \r\r\n\n\r 
+    \r\r\n\n\r\n 
+
+/[^\x{1234}]+/iS8I   
+
+/[^\x{1234}]+?/iS8I   
+
+/[^\x{1234}]++/iS8I   
+
+/[^\x{1234}]{2}/iS8I
+
+//<bsr_anycrlf><bsr_unicode>
+
+/f.*/
+    \P\Pfor
+
+/f.*/s
+    \P\Pfor
+
+/f.*/8
+    \P\Pfor
+
+/f.*/8s
+    \P\Pfor
+    
+/\x{d7ff}\x{e000}/8
+
+/\x{d800}/8
+
+/\x{dfff}/8 
+
+/\h+/8
+    \x{1681}\x{200b}\x{1680}\x{2000}\x{202f}\x{3000}
+    \x{3001}\x{2fff}\x{200a}\x{a0}\x{2000}
+
+/[\h\x{e000}]+/8BZ
+    \x{1681}\x{200b}\x{1680}\x{2000}\x{202f}\x{3000}
+    \x{3001}\x{2fff}\x{200a}\x{a0}\x{2000}
+
+/\H+/8
+    \x{1680}\x{180e}\x{167f}\x{1681}\x{180d}\x{180f}
+    \x{2000}\x{200a}\x{1fff}\x{200b}
+    \x{202f}\x{205f}\x{202e}\x{2030}\x{205e}\x{2060}
+    \x{a0}\x{3000}\x{9f}\x{a1}\x{2fff}\x{3001}
+
+/[\H\x{d7ff}]+/8BZ
+    \x{1680}\x{180e}\x{167f}\x{1681}\x{180d}\x{180f}
+    \x{2000}\x{200a}\x{1fff}\x{200b}
+    \x{202f}\x{205f}\x{202e}\x{2030}\x{205e}\x{2060}
+    \x{a0}\x{3000}\x{9f}\x{a1}\x{2fff}\x{3001}
+
+/\v+/8
+    \x{2027}\x{2030}\x{2028}\x{2029}
+    \x09\x0e\x{84}\x{86}\x{85}\x0a\x0b\x0c\x0d
+
+/[\v\x{e000}]+/8BZ
+    \x{2027}\x{2030}\x{2028}\x{2029}
+    \x09\x0e\x{84}\x{86}\x{85}\x0a\x0b\x0c\x0d
+
+/\V+/8
+    \x{2028}\x{2029}\x{2027}\x{2030}
+    \x{85}\x0a\x0b\x0c\x0d\x09\x0e\x{84}\x{86}
+
+/[\V\x{d7ff}]+/8BZ
+    \x{2028}\x{2029}\x{2027}\x{2030}
+    \x{85}\x0a\x0b\x0c\x0d\x09\x0e\x{84}\x{86}
+
+/\R+/8<bsr_unicode>
+    \x{2027}\x{2030}\x{2028}\x{2029}
+    \x09\x0e\x{84}\x{86}\x{85}\x0a\x0b\x0c\x0d
+
+/(..)\1/8
+    ab\P
+    aba\P
+    abab\P
+
+/(..)\1/8i
+    ab\P
+    abA\P
+    aBAb\P
+
+/(..)\1{2,}/8
+    ab\P
+    aba\P
+    abab\P
+    ababa\P
+    ababab\P
+    ababab\P\P
+    abababa\P
+    abababa\P\P
+
+/(..)\1{2,}/8i
+    ab\P
+    aBa\P
+    aBAb\P
+    AbaBA\P
+    abABAb\P
+    aBAbaB\P\P
+    abABabA\P
+    abaBABa\P\P
+
+/(..)\1{2,}?x/8i
+    ab\P
+    abA\P
+    aBAb\P
+    abaBA\P
+    abAbaB\P
+    abaBabA\P
+    abAbABaBx\P
+
+/./8<CRLF>
+    \r\P
+    \r\P\P 
+  
+/.{2,3}/8<CRLF>
+    \r\P 
+    \r\P\P
+    \r\r\P
+    \r\r\P\P
+    \r\r\r\P
+    \r\r\r\P\P     
+
+/.{2,3}?/8<CRLF>
+    \r\P 
+    \r\P\P
+    \r\r\P
+    \r\r\P\P
+    \r\r\r\P
+    \r\r\r\P\P     
+
+/[^\x{100}][^\x{1234}][^\x{ffff}][^\x{10000}][^\x{10ffff}]/8BZ
+
+/[^\x{100}][^\x{1234}][^\x{ffff}][^\x{10000}][^\x{10ffff}]/8BZi
+
+/[^\x{100}]*[^\x{10000}]+[^\x{10ffff}]??[^\x{8000}]{4,}[^\x{7fff}]{2,9}?[^\x{fffff}]{5,6}+/8BZ
+
+/[^\x{100}]*[^\x{10000}]+[^\x{10ffff}]??[^\x{8000}]{4,}[^\x{7fff}]{2,9}?[^\x{fffff}]{5,6}+/8BZi
+
+/(?<=\x{1234}\x{1234})\bxy/I8
+
+/(?<!^)ETA/8
+    ETA
+
+/\u0100/<JS>8BZ
+
+/[\u0100-\u0200]/<JS>8BZ
+
+/\ud800/<JS>8
+
+/-- End of testinput5 --/
diff --git a/ext/pcre/pcrelib/testdata/testinput6 b/ext/pcre/pcrelib/testdata/testinput6
new file mode 100644
index 0000000..7010a0d
--- /dev/null
+++ b/ext/pcre/pcrelib/testdata/testinput6
@@ -0,0 +1,818 @@
+/-- This set of tests is for Unicode property support. It is compatible with
+    Perl >= 5.10, but not 5.8 because it tests some extra properties that are
+    not in the earlier release. --/ 
+
+/^\pC\pL\pM\pN\pP\pS\pZ</8
+    \x7f\x{c0}\x{30f}\x{660}\x{66c}\x{f01}\x{1680}<
+    \np\x{300}9!\$ < 
+    ** Failers 
+    ap\x{300}9!\$ < 
+  
+/^\PC/8
+    X
+    ** Failers 
+    \x7f
+  
+/^\PL/8
+    9
+    ** Failers 
+    \x{c0}
+  
+/^\PM/8
+    X
+    ** Failers 
+    \x{30f}
+  
+/^\PN/8
+    X
+    ** Failers 
+    \x{660}
+  
+/^\PP/8
+    X
+    ** Failers 
+    \x{66c}
+  
+/^\PS/8
+    X
+    ** Failers 
+    \x{f01}
+  
+/^\PZ/8
+    X
+    ** Failers 
+    \x{1680}
+    
+/^\p{Cc}/8
+    \x{017}
+    \x{09f} 
+    ** Failers
+    \x{0600} 
+  
+/^\p{Cf}/8
+    \x{601}
+    ** Failers
+    \x{09f} 
+  
+/^\p{Cn}/8
+    \x{e0000}
+    ** Failers
+    \x{09f} 
+  
+/^\p{Co}/8
+    \x{f8ff}
+    ** Failers
+    \x{09f} 
+  
+/^\p{Ll}/8
+    a
+    ** Failers 
+    Z
+    \x{e000}  
+  
+/^\p{Lm}/8
+    \x{2b0}
+    ** Failers
+    a 
+  
+/^\p{Lo}/8
+    \x{1bb}
+    \x{3400}
+    \x{3401}
+    \x{4d00}
+    \x{4db4}
+    \x{4db5}     
+    ** Failers
+    a 
+    \x{2b0}
+    \x{4db6} 
+  
+/^\p{Lt}/8
+    \x{1c5}
+    ** Failers
+    a 
+    \x{2b0}
+  
+/^\p{Lu}/8
+    A
+    ** Failers
+    \x{2b0}
+  
+/^\p{Mc}/8
+    \x{903}
+    ** Failers
+    X
+    \x{300}
+       
+/^\p{Me}/8
+    \x{488}
+    ** Failers
+    X
+    \x{903}
+    \x{300}
+  
+/^\p{Mn}/8
+    \x{300}
+    ** Failers
+    X
+    \x{903}
+  
+/^\p{Nd}+/8
+    0123456789\x{660}\x{661}\x{662}\x{663}\x{664}\x{665}\x{666}\x{667}\x{668}\x{669}\x{66a}
+    \x{6f0}\x{6f1}\x{6f2}\x{6f3}\x{6f4}\x{6f5}\x{6f6}\x{6f7}\x{6f8}\x{6f9}\x{6fa}
+    \x{966}\x{967}\x{968}\x{969}\x{96a}\x{96b}\x{96c}\x{96d}\x{96e}\x{96f}\x{970}
+    ** Failers
+    X
+  
+/^\p{Nl}/8
+    \x{16ee}
+    ** Failers
+    X
+    \x{966}
+  
+/^\p{No}/8
+    \x{b2}
+    \x{b3}
+    ** Failers
+    X
+    \x{16ee}
+  
+/^\p{Pc}/8
+    \x5f
+    \x{203f}
+    ** Failers
+    X
+    -
+    \x{58a}
+  
+/^\p{Pd}/8
+    -
+    \x{58a}
+    ** Failers
+    X
+    \x{203f}
+  
+/^\p{Pe}/8
+    )
+    ]
+    }
+    \x{f3b}
+    ** Failers
+    X
+    \x{203f}
+    (
+    [
+    {
+    \x{f3c}
+  
+/^\p{Pf}/8
+    \x{bb}
+    \x{2019}
+    ** Failers
+    X
+    \x{203f}
+  
+/^\p{Pi}/8
+    \x{ab}
+    \x{2018}
+    ** Failers
+    X
+    \x{203f}
+  
+/^\p{Po}/8
+    !
+    \x{37e}
+    ** Failers
+    X
+    \x{203f}
+  
+/^\p{Ps}/8
+    (
+    [
+    {
+    \x{f3c}
+    ** Failers
+    X
+    )
+    ]
+    }
+    \x{f3b}
+  
+/^\p{Sk}/8
+    \x{2c2}
+    ** Failers
+    X
+    \x{9f2}
+  
+/^\p{Sm}+/8
+    +<|~\x{ac}\x{2044}
+    ** Failers
+    X
+    \x{9f2}
+  
+/^\p{So}/8
+    \x{a6}
+    \x{482} 
+    ** Failers
+    X
+    \x{9f2}
+  
+/^\p{Zl}/8
+    \x{2028}
+    ** Failers
+    X
+    \x{2029}
+  
+/^\p{Zp}/8
+    \x{2029}
+    ** Failers
+    X
+    \x{2028}
+  
+/\p{Nd}+(..)/8
+      \x{660}\x{661}\x{662}ABC
+  
+/\p{Nd}+?(..)/8
+      \x{660}\x{661}\x{662}ABC
+  
+/\p{Nd}{2,}(..)/8
+      \x{660}\x{661}\x{662}ABC
+  
+/\p{Nd}{2,}?(..)/8
+      \x{660}\x{661}\x{662}ABC
+  
+/\p{Nd}*(..)/8
+      \x{660}\x{661}\x{662}ABC
+  
+/\p{Nd}*?(..)/8
+      \x{660}\x{661}\x{662}ABC
+  
+/\p{Nd}{2}(..)/8
+      \x{660}\x{661}\x{662}ABC
+  
+/\p{Nd}{2,3}(..)/8
+      \x{660}\x{661}\x{662}ABC
+  
+/\p{Nd}{2,3}?(..)/8
+      \x{660}\x{661}\x{662}ABC
+  
+/\p{Nd}?(..)/8
+      \x{660}\x{661}\x{662}ABC
+  
+/\p{Nd}??(..)/8
+      \x{660}\x{661}\x{662}ABC
+  
+/\p{Nd}*+(..)/8
+      \x{660}\x{661}\x{662}ABC
+  
+/\p{Nd}*+(...)/8
+      \x{660}\x{661}\x{662}ABC
+  
+/\p{Nd}*+(....)/8
+      ** Failers
+      \x{660}\x{661}\x{662}ABC
+  
+/(?<=A\p{Nd})XYZ/8
+    A2XYZ
+    123A5XYZPQR
+    ABA\x{660}XYZpqr
+    ** Failers
+    AXYZ
+    XYZ     
+    
+/(?<!\pL)XYZ/8
+    1XYZ
+    AB=XYZ.. 
+    XYZ 
+    ** Failers
+    WXYZ 
+
+/[\P{Nd}]+/8
+    abcd
+    ** Failers
+    1234
+
+/\D+/8
+    11111111111111111111111111111111111111111111111111111111111111111111111
+    aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+     
+/\P{Nd}+/8
+    11111111111111111111111111111111111111111111111111111111111111111111111
+    aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+
+/[\D]+/8
+    11111111111111111111111111111111111111111111111111111111111111111111111
+    aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+
+/[\P{Nd}]+/8
+    11111111111111111111111111111111111111111111111111111111111111111111111
+    aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+
+/[\D\P{Nd}]+/8
+    11111111111111111111111111111111111111111111111111111111111111111111111
+    aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+
+/\pL/8
+    a
+    A 
+
+/\pL/8i
+    a
+    A 
+    
+/\p{Lu}/8 
+    A
+    aZ
+    ** Failers
+    abc   
+
+/\p{Lu}/8i
+    A
+    aZ
+    ** Failers
+    abc   
+
+/\p{Ll}/8 
+    a
+    Az
+    ** Failers
+    ABC   
+
+/A\x{391}\x{10427}\x{ff3a}\x{1fb0}/8
+    A\x{391}\x{10427}\x{ff3a}\x{1fb0}
+    ** Failers
+    a\x{391}\x{10427}\x{ff3a}\x{1fb0}   
+    A\x{3b1}\x{10427}\x{ff3a}\x{1fb0}
+    A\x{391}\x{1044F}\x{ff3a}\x{1fb0}
+    A\x{391}\x{10427}\x{ff5a}\x{1fb0}
+    A\x{391}\x{10427}\x{ff3a}\x{1fb8}
+
+/A\x{391}\x{10427}\x{ff3a}\x{1fb0}/8i
+    A\x{391}\x{10427}\x{ff3a}\x{1fb0}
+    a\x{391}\x{10427}\x{ff3a}\x{1fb0}   
+    A\x{3b1}\x{10427}\x{ff3a}\x{1fb0}
+    A\x{391}\x{1044F}\x{ff3a}\x{1fb0}
+    A\x{391}\x{10427}\x{ff5a}\x{1fb0}
+    A\x{391}\x{10427}\x{ff3a}\x{1fb8}
+
+/\x{391}+/8i
+    \x{391}\x{3b1}\x{3b1}\x{3b1}\x{391}
+
+/\x{391}{3,5}(.)/8i
+    \x{391}\x{3b1}\x{3b1}\x{3b1}\x{391}X
+
+/\x{391}{3,5}?(.)/8i
+    \x{391}\x{3b1}\x{3b1}\x{3b1}\x{391}X
+
+/[\x{391}\x{ff3a}]/8i
+    \x{391}
+    \x{ff3a}
+    \x{3b1}
+    \x{ff5a}   
+    
+/^[\X]/8
+    X123
+    *** Failers
+    AXYZ
+
+/^(\X*)C/8
+    A\x{300}\x{301}\x{302}BCA\x{300}\x{301} 
+    A\x{300}\x{301}\x{302}BCA\x{300}\x{301}C 
+
+/^(\X*?)C/8
+    A\x{300}\x{301}\x{302}BCA\x{300}\x{301} 
+    A\x{300}\x{301}\x{302}BCA\x{300}\x{301}C 
+
+/^(\X*)(.)/8
+    A\x{300}\x{301}\x{302}BCA\x{300}\x{301} 
+    A\x{300}\x{301}\x{302}BCA\x{300}\x{301}C 
+
+/^(\X*?)(.)/8
+    A\x{300}\x{301}\x{302}BCA\x{300}\x{301} 
+    A\x{300}\x{301}\x{302}BCA\x{300}\x{301}C 
+
+/^\X(.)/8
+    *** Failers
+    A\x{300}\x{301}\x{302}
+
+/^\X{2,3}(.)/8
+    A\x{300}\x{301}B\x{300}X
+    A\x{300}\x{301}B\x{300}C\x{300}\x{301}
+    A\x{300}\x{301}B\x{300}C\x{300}\x{301}X
+    A\x{300}\x{301}B\x{300}C\x{300}\x{301}DA\x{300}X
+    
+/^\X{2,3}?(.)/8
+    A\x{300}\x{301}B\x{300}X
+    A\x{300}\x{301}B\x{300}C\x{300}\x{301}
+    A\x{300}\x{301}B\x{300}C\x{300}\x{301}X
+    A\x{300}\x{301}B\x{300}C\x{300}\x{301}DA\x{300}X
+    
+/^\p{Han}+/8
+    \x{2e81}\x{3007}\x{2f804}\x{31a0}
+    ** Failers
+    \x{2e7f}  
+
+/^\P{Katakana}+/8
+    \x{3105}
+    ** Failers
+    \x{30ff}  
+
+/^[\p{Arabic}]/8
+    \x{06e9}
+    \x{060b}
+    ** Failers
+    X\x{06e9}   
+
+/^[\P{Yi}]/8
+    \x{2f800}
+    ** Failers
+    \x{a014}
+    \x{a4c6}   
+    
+/^\p{Any}X/8
+    AXYZ
+    \x{1234}XYZ 
+    ** Failers
+    X  
+    
+/^\P{Any}X/8
+    ** Failers
+    AX
+    
+/^\p{Any}?X/8
+    XYZ
+    AXYZ
+    \x{1234}XYZ 
+    ** Failers
+    ABXYZ   
+
+/^\P{Any}?X/8
+    XYZ
+    ** Failers
+    AXYZ
+    \x{1234}XYZ 
+    ABXYZ   
+
+/^\p{Any}+X/8
+    AXYZ
+    \x{1234}XYZ
+    A\x{1234}XYZ
+    ** Failers
+    XYZ
+
+/^\P{Any}+X/8
+    ** Failers
+    AXYZ
+    \x{1234}XYZ
+    A\x{1234}XYZ
+    XYZ
+
+/^\p{Any}*X/8
+    XYZ
+    AXYZ
+    \x{1234}XYZ
+    A\x{1234}XYZ
+    ** Failers
+
+/^\P{Any}*X/8
+    XYZ
+    ** Failers
+    AXYZ
+    \x{1234}XYZ
+    A\x{1234}XYZ
+
+/^[\p{Any}]X/8
+    AXYZ
+    \x{1234}XYZ 
+    ** Failers
+    X  
+    
+/^[\P{Any}]X/8
+    ** Failers
+    AX
+    
+/^[\p{Any}]?X/8
+    XYZ
+    AXYZ
+    \x{1234}XYZ 
+    ** Failers
+    ABXYZ   
+
+/^[\P{Any}]?X/8
+    XYZ
+    ** Failers
+    AXYZ
+    \x{1234}XYZ 
+    ABXYZ   
+
+/^[\p{Any}]+X/8
+    AXYZ
+    \x{1234}XYZ
+    A\x{1234}XYZ
+    ** Failers
+    XYZ
+
+/^[\P{Any}]+X/8
+    ** Failers
+    AXYZ
+    \x{1234}XYZ
+    A\x{1234}XYZ
+    XYZ
+
+/^[\p{Any}]*X/8
+    XYZ
+    AXYZ
+    \x{1234}XYZ
+    A\x{1234}XYZ
+    ** Failers
+
+/^[\P{Any}]*X/8
+    XYZ
+    ** Failers
+    AXYZ
+    \x{1234}XYZ
+    A\x{1234}XYZ
+
+/^\p{Any}{3,5}?/8
+    abcdefgh
+    \x{1234}\n\r\x{3456}xyz 
+
+/^\p{Any}{3,5}/8
+    abcdefgh
+    \x{1234}\n\r\x{3456}xyz 
+
+/^\P{Any}{3,5}?/8
+    ** Failers
+    abcdefgh
+    \x{1234}\n\r\x{3456}xyz 
+
+/^\p{L&}X/8
+     AXY
+     aXY
+     \x{1c5}XY
+     ** Failers
+     \x{1bb}XY
+     \x{2b0}XY
+     !XY      
+
+/^[\p{L&}]X/8
+     AXY
+     aXY
+     \x{1c5}XY
+     ** Failers
+     \x{1bb}XY
+     \x{2b0}XY
+     !XY      
+
+/^\p{L&}+X/8
+     AXY
+     aXY
+     AbcdeXyz 
+     \x{1c5}AbXY
+     abcDEXypqreXlmn 
+     ** Failers
+     \x{1bb}XY
+     \x{2b0}XY
+     !XY      
+
+/^[\p{L&}]+X/8
+     AXY
+     aXY
+     AbcdeXyz 
+     \x{1c5}AbXY
+     abcDEXypqreXlmn 
+     ** Failers
+     \x{1bb}XY
+     \x{2b0}XY
+     !XY      
+
+/^\p{L&}+?X/8
+     AXY
+     aXY
+     AbcdeXyz 
+     \x{1c5}AbXY
+     abcDEXypqreXlmn 
+     ** Failers
+     \x{1bb}XY
+     \x{2b0}XY
+     !XY      
+
+/^[\p{L&}]+?X/8
+     AXY
+     aXY
+     AbcdeXyz 
+     \x{1c5}AbXY
+     abcDEXypqreXlmn 
+     ** Failers
+     \x{1bb}XY
+     \x{2b0}XY
+     !XY      
+
+/^\P{L&}X/8
+     !XY
+     \x{1bb}XY
+     \x{2b0}XY
+     ** Failers
+     \x{1c5}XY
+     AXY      
+
+/^[\P{L&}]X/8
+     !XY
+     \x{1bb}XY
+     \x{2b0}XY
+     ** Failers
+     \x{1c5}XY
+     AXY      
+
+/^(\p{Z}[^\p{C}\p{Z}]+)*$/
+    \xa0!
+
+/^[\pL](abc)(?1)/
+    AabcabcYZ    
+
+/([\pL]=(abc))*X/
+    L=abcX
+
+/^\p{Balinese}\p{Cuneiform}\p{Nko}\p{Phags_Pa}\p{Phoenician}/8
+    \x{1b00}\x{12000}\x{7c0}\x{a840}\x{10900}
+
+/Check property support in non-UTF-8 mode/
+ 
+/\p{L}{4}/
+    123abcdefg
+    123abc\xc4\xc5zz
+
+/\X{1,3}\d/
+  \x8aBCD
+  
+/\X?\d/
+  \x8aBCD 
+
+/\P{L}?\d/
+  \x8aBCD 
+
+/[\PPP\x8a]{1,}\x80/
+    A\x80
+
+/^[\p{Arabic}]/8
+    \x{604}
+    \x{60e} 
+    \x{656} 
+    \x{657} 
+    \x{658} 
+    \x{659} 
+    \x{65a} 
+    \x{65b} 
+    \x{65c} 
+    \x{65d} 
+    \x{65e} 
+    \x{66a} 
+    \x{6e9} 
+    \x{6ef}
+    \x{6fa}  
+    ** Failers
+    \x{650}
+    \x{651}  
+    \x{652}  
+    \x{653}  
+    \x{654} 
+    \x{655} 
+    \x{65f}  
+    
+/^\p{Cyrillic}/8
+    \x{1d2b} 
+    
+/^\p{Common}/8
+    \x{589}
+    \x{60c}
+    \x{61f}  
+    \x{964}
+    \x{965}  
+
+/^\p{Inherited}/8
+    \x{64b}
+    \x{654}
+    \x{655}
+    \x{200c} 
+    ** Failers
+    \x{64a}
+    \x{656}     
+
+/^\p{Shavian}/8
+    \x{10450}
+    \x{1047f}
+    
+/^\p{Deseret}/8
+    \x{10400}
+    \x{1044f}
+    
+/^\p{Osmanya}/8
+    \x{10480}
+    \x{1049d}
+    \x{104a0}
+    \x{104a9}
+    ** Failers
+    \x{1049e}
+    \x{1049f}
+    \x{104aa}           
+
+/\p{Carian}\p{Cham}\p{Kayah_Li}\p{Lepcha}\p{Lycian}\p{Lydian}\p{Ol_Chiki}\p{Rejang}\p{Saurashtra}\p{Sundanese}\p{Vai}/8
+    \x{102A4}\x{AA52}\x{A91D}\x{1C46}\x{10283}\x{1092E}\x{1C6B}\x{A93B}\x{A8BF}\x{1BA0}\x{A50A}====
+
+/\x{a77d}\x{1d79}/8i
+    \x{a77d}\x{1d79}
+    \x{1d79}\x{a77d} 
+
+/\x{a77d}\x{1d79}/8
+    \x{a77d}\x{1d79}
+    ** Failers 
+    \x{1d79}\x{a77d} 
+
+/(A)\1/8i
+    AA
+    Aa
+    aa
+    aA
+
+/(\x{10a})\1/8i
+    \x{10a}\x{10a}
+    \x{10a}\x{10b}
+    \x{10b}\x{10b}
+    \x{10b}\x{10a}
+    
+/The next two tests are for property support in non-UTF-8 mode/
+
+/(?:\p{Lu}|\x20)+/
+    \x41\x20\x50\xC2\x54\xC9\x20\x54\x4F\x44\x41\x59
+
+/[\p{Lu}\x20]+/
+    \x41\x20\x50\xC2\x54\xC9\x20\x54\x4F\x44\x41\x59
+
+/\p{Avestan}\p{Bamum}\p{Egyptian_Hieroglyphs}\p{Imperial_Aramaic}\p{Inscriptional_Pahlavi}\p{Inscriptional_Parthian}\p{Javanese}\p{Kaithi}\p{Lisu}\p{Meetei_Mayek}\p{Old_South_Arabian}\p{Old_Turkic}\p{Samaritan}\p{Tai_Tham}\p{Tai_Viet}/8
+    \x{10b00}\x{a6ef}\x{13007}\x{10857}\x{10b78}\x{10b58}\x{a980}\x{110c1}\x{a4ff}\x{abc0}\x{10a7d}\x{10c48}\x{0800}\x{1aad}\x{aac0}
+
+/^\w+/8W
+    Az_\x{aa}\x{c0}\x{1c5}\x{2b0}\x{3b6}\x{1d7c9}\x{2fa1d}1\x{660}\x{bef}\x{16ee}
+
+/^[[:xdigit:]]*/8W
+    1a\x{660}\x{bef}\x{16ee}
+  
+/^\d+/8W
+    1\x{660}\x{bef}\x{16ee}
+  
+/^[[:digit:]]+/8W
+    1\x{660}\x{bef}\x{16ee}
+
+/^>\s+/8W
+    >\x{20}\x{a0}\x{1680}\x{2028}\x{2029}\x{202f}\x{9}\x{b} 
+  
+/^>\pZ+/8W
+    >\x{20}\x{a0}\x{1680}\x{2028}\x{2029}\x{202f}\x{9}\x{b} 
+  
+/^>[[:space:]]*/8W
+    >\x{20}\x{a0}\x{1680}\x{2028}\x{2029}\x{202f}\x{9}\x{b} 
+
+/^>[[:blank:]]*/8W
+    >\x{20}\x{a0}\x{1680}\x{180e}\x{2000}\x{202f}\x{9}\x{b}\x{2028} 
+
+/^[[:alpha:]]*/8W
+    Az\x{aa}\x{c0}\x{1c5}\x{2b0}\x{3b6}\x{1d7c9}\x{2fa1d}
+
+/^[[:alnum:]]*/8W
+    Az\x{aa}\x{c0}\x{1c5}\x{2b0}\x{3b6}\x{1d7c9}\x{2fa1d}1\x{660}\x{bef}\x{16ee}
+
+/^[[:cntrl:]]*/8W
+    \x{0}\x{09}\x{1f}\x{7f}\x{9f} 
+
+/^[[:graph:]]*/8W
+    A\x{a1}\x{a0}
+
+/^[[:print:]]*/8W
+    A z\x{a0}\x{a1}
+
+/^[[:punct:]]*/8W
+    .+\x{a1}\x{a0}
+
+/\p{Zs}*?\R/
+    ** Failers
+    a\xFCb   
+
+/\p{Zs}*\R/                                                                    
+    ** Failers 
+    a\xFCb   
+
+/â±¥/8i
+    â±¥
+    Ⱥx 
+    Ⱥ 
+
+/[â±¥]/8i
+    â±¥
+    Ⱥx 
+    Ⱥ 
+
+/Ⱥ/8i
+    Ⱥ
+    â±¥
+
+/-- End of testinput6 --/
diff --git a/ext/pcre/pcrelib/testdata/testinput7 b/ext/pcre/pcrelib/testdata/testinput7
new file mode 100644
index 0000000..6ef9230
--- /dev/null
+++ b/ext/pcre/pcrelib/testdata/testinput7
@@ -0,0 +1,625 @@
+/-- These tests for Unicode property support test PCRE's API and show some of
+    the compiled code. They are not Perl-compatible. --/
+
+/[\p{L}]/DZ
+
+/[\p{^L}]/DZ
+
+/[\P{L}]/DZ
+
+/[\P{^L}]/DZ
+
+/[abc\p{L}\x{0660}]/8DZ
+
+/[\p{Nd}]/8DZ
+    1234
+
+/[\p{Nd}+-]+/8DZ
+    1234
+    12-34
+    12+\x{661}-34  
+    ** Failers
+    abcd  
+
+/[\x{105}-\x{109}]/8iDZ
+    \x{104}
+    \x{105}
+    \x{109}  
+    ** Failers
+    \x{100}
+    \x{10a} 
+    
+/[z-\x{100}]/8iDZ 
+    Z
+    z
+    \x{39c}
+    \x{178}
+    |
+    \x{80}
+    \x{ff}
+    \x{100}
+    \x{101} 
+    ** Failers
+    \x{102}
+    Y
+    y           
+
+/[z-\x{100}]/8DZi
+
+/(?:[\PPa*]*){8,}/
+
+/[\P{Any}]/BZ
+
+/[\P{Any}\E]/BZ
+
+/(\P{Yi}+\277)/
+
+/(\P{Yi}+\277)?/
+
+/(?<=\P{Yi}{3}A)X/
+
+/\p{Yi}+(\P{Yi}+)(?1)/
+
+/(\P{Yi}{2}\277)?/
+
+/[\P{Yi}A]/
+
+/[\P{Yi}\P{Yi}\P{Yi}A]/
+
+/[^\P{Yi}A]/
+
+/[^\P{Yi}\P{Yi}\P{Yi}A]/
+
+/(\P{Yi}*\277)*/
+
+/(\P{Yi}*?\277)*/
+
+/(\p{Yi}*+\277)*/
+
+/(\P{Yi}?\277)*/
+
+/(\P{Yi}??\277)*/
+
+/(\p{Yi}?+\277)*/
+
+/(\P{Yi}{0,3}\277)*/
+
+/(\P{Yi}{0,3}?\277)*/
+
+/(\p{Yi}{0,3}+\277)*/
+
+/\p{Zl}{2,3}+/8BZ
+    \xe2\x80\xa8\xe2\x80\xa8
+    \x{2028}\x{2028}\x{2028}
+    
+/\p{Zl}/8BZ
+
+/\p{Lu}{3}+/8BZ
+
+/\pL{2}+/8BZ
+
+/\p{Cc}{2}+/8BZ
+
+/^\p{Cs}/8
+    \?\x{dfff}
+    ** Failers
+    \x{09f} 
+  
+/^\p{Sc}+/8
+    $\x{a2}\x{a3}\x{a4}\x{a5}\x{a6}
+    \x{9f2}
+    ** Failers
+    X
+    \x{2c2}
+  
+/^\p{Zs}/8
+    \ \
+    \x{a0}
+    \x{1680}
+    \x{180e}
+    \x{2000}
+    \x{2001}     
+    ** Failers
+    \x{2028}
+    \x{200d} 
+  
+/-- These four are here rather than in test 6 because Perl has problems with
+    the negative versions of the properties. --/
+      
+/\p{^Lu}/8i
+    1234
+    ** Failers
+    ABC 
+
+/\P{Lu}/8i
+    1234
+    ** Failers
+    ABC 
+
+/\p{Ll}/8i 
+    a
+    Az
+    ** Failers
+    ABC   
+
+/\p{Lu}/8i
+    A
+    a\x{10a0}B 
+    ** Failers 
+    a
+    \x{1d00}  
+
+/[\x{c0}\x{391}]/8i
+    \x{c0}
+    \x{e0} 
+
+/-- The next two are special cases where the lengths of the different cases of
+the same character differ. The first went wrong with heap frame storage; the
+second was broken in all cases. --/
+
+/^\x{023a}+?(\x{0130}+)/8i
+  \x{023a}\x{2c65}\x{0130}
+  
+/^\x{023a}+([^X])/8i
+  \x{023a}\x{2c65}X
+
+/\x{c0}+\x{116}+/8i
+    \x{c0}\x{e0}\x{116}\x{117}
+
+/[\x{c0}\x{116}]+/8i
+    \x{c0}\x{e0}\x{116}\x{117}
+
+/(\x{de})\1/8i
+    \x{de}\x{de}
+    \x{de}\x{fe}
+    \x{fe}\x{fe}
+    \x{fe}\x{de}
+
+/^\x{c0}$/8i
+    \x{c0}
+    \x{e0} 
+
+/^\x{e0}$/8i
+    \x{c0}
+    \x{e0} 
+
+/-- The next two should be Perl-compatible, but it fails to match \x{e0}. PCRE
+will match it only with UCP support, because without that it has no notion
+of case for anything other than the ASCII letters. --/ 
+
+/((?i)[\x{c0}])/8
+    \x{c0}
+    \x{e0} 
+
+/(?i:[\x{c0}])/8
+    \x{c0}
+    \x{e0} 
+
+/-- This should be Perl-compatible but Perl 5.11 gets \x{300} wrong. --/8
+    
+/^\X/8
+    A
+    A\x{300}BC 
+    A\x{300}\x{301}\x{302}BC 
+    *** Failers
+    \x{300}  
+    
+/-- These are PCRE's extra properties to help with Unicodizing \d etc. --/
+
+/^\p{Xan}/8
+    ABCD
+    1234
+    \x{6ca}
+    \x{a6c}
+    \x{10a7}   
+    ** Failers
+    _ABC   
+
+/^\p{Xan}+/8
+    ABCD1234\x{6ca}\x{a6c}\x{10a7}_
+    ** Failers
+    _ABC   
+
+/^\p{Xan}+?/8
+    \x{6ca}\x{a6c}\x{10a7}_
+
+/^\p{Xan}*/8
+    ABCD1234\x{6ca}\x{a6c}\x{10a7}_
+    
+/^\p{Xan}{2,9}/8
+    ABCD1234\x{6ca}\x{a6c}\x{10a7}_
+    
+/^\p{Xan}{2,9}?/8
+    \x{6ca}\x{a6c}\x{10a7}_
+    
+/^[\p{Xan}]/8
+    ABCD1234_
+    1234abcd_
+    \x{6ca}
+    \x{a6c}
+    \x{10a7}   
+    ** Failers
+    _ABC   
+ 
+/^[\p{Xan}]+/8
+    ABCD1234\x{6ca}\x{a6c}\x{10a7}_
+    ** Failers
+    _ABC   
+
+/^>\p{Xsp}/8
+    >\x{1680}\x{2028}\x{0b}
+    >\x{a0} 
+    ** Failers
+    \x{0b} 
+
+/^>\p{Xsp}+/8
+    > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}\x{0b}
+
+/^>\p{Xsp}+?/8
+    >\x{1680}\x{2028}\x{0b}
+
+/^>\p{Xsp}*/8
+    > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}\x{0b}
+    
+/^>\p{Xsp}{2,9}/8
+    > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}\x{0b}
+    
+/^>\p{Xsp}{2,9}?/8
+    > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}\x{0b}
+    
+/^>[\p{Xsp}]/8
+    >\x{2028}\x{0b}
+ 
+/^>[\p{Xsp}]+/8
+    > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}\x{0b}
+
+/^>\p{Xps}/8
+    >\x{1680}\x{2028}\x{0b}
+    >\x{a0} 
+    ** Failers
+    \x{0b} 
+
+/^>\p{Xps}+/8
+    > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}\x{0b}
+
+/^>\p{Xps}+?/8
+    >\x{1680}\x{2028}\x{0b}
+
+/^>\p{Xps}*/8
+    > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}\x{0b}
+    
+/^>\p{Xps}{2,9}/8
+    > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}\x{0b}
+    
+/^>\p{Xps}{2,9}?/8
+    > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}\x{0b}
+    
+/^>[\p{Xps}]/8
+    >\x{2028}\x{0b}
+ 
+/^>[\p{Xps}]+/8
+    > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}\x{0b}
+
+/^\p{Xwd}/8
+    ABCD
+    1234
+    \x{6ca}
+    \x{a6c}
+    \x{10a7}
+    _ABC    
+    ** Failers
+    [] 
+
+/^\p{Xwd}+/8
+    ABCD1234\x{6ca}\x{a6c}\x{10a7}_
+
+/^\p{Xwd}+?/8
+    \x{6ca}\x{a6c}\x{10a7}_
+
+/^\p{Xwd}*/8
+    ABCD1234\x{6ca}\x{a6c}\x{10a7}_
+    
+/^\p{Xwd}{2,9}/8
+    A_B12\x{6ca}\x{a6c}\x{10a7}
+    
+/^\p{Xwd}{2,9}?/8
+    \x{6ca}\x{a6c}\x{10a7}_
+    
+/^[\p{Xwd}]/8
+    ABCD1234_
+    1234abcd_
+    \x{6ca}
+    \x{a6c}
+    \x{10a7}   
+    _ABC 
+    ** Failers
+    []   
+ 
+/^[\p{Xwd}]+/8
+    ABCD1234\x{6ca}\x{a6c}\x{10a7}_
+
+/-- A check not in UTF-8 mode --/
+
+/^[\p{Xwd}]+/
+    ABCD1234_
+    
+/-- Some negative checks --/
+
+/^[\P{Xwd}]+/8
+    !.+\x{019}\x{35a}AB
+
+/^[\p{^Xwd}]+/8
+    !.+\x{019}\x{35a}AB
+
+/[\D]/WBZ8
+    1\x{3c8}2
+
+/[\d]/WBZ8
+    >\x{6f4}<
+
+/[\S]/WBZ8
+    \x{1680}\x{6f4}\x{1680}
+
+/[\s]/WBZ8
+    >\x{1680}<
+
+/[\W]/WBZ8
+    A\x{1712}B
+
+/[\w]/WBZ8
+    >\x{1723}<
+
+/\D/WBZ8
+    1\x{3c8}2
+
+/\d/WBZ8
+    >\x{6f4}<
+
+/\S/WBZ8
+    \x{1680}\x{6f4}\x{1680}
+
+/\s/WBZ8
+    >\x{1680}>
+
+/\W/WBZ8
+    A\x{1712}B
+
+/\w/WBZ8
+    >\x{1723}<
+
+/[[:alpha:]]/WBZ
+
+/[[:lower:]]/WBZ
+
+/[[:upper:]]/WBZ
+
+/[[:alnum:]]/WBZ
+
+/[[:ascii:]]/WBZ
+
+/[[:cntrl:]]/WBZ
+
+/[[:digit:]]/WBZ
+
+/[[:graph:]]/WBZ
+
+/[[:print:]]/WBZ
+
+/[[:punct:]]/WBZ
+
+/[[:space:]]/WBZ
+
+/[[:word:]]/WBZ
+
+/[[:xdigit:]]/WBZ
+
+/-- Unicode properties for \b abd \B --/
+
+/\b...\B/8W
+    abc_
+    \x{37e}abc\x{376} 
+    \x{37e}\x{376}\x{371}\x{393}\x{394} 
+    !\x{c0}++\x{c1}\x{c2} 
+    !\x{c0}+++++ 
+
+/-- Without PCRE_UCP, non-ASCII always fail, even if < 256  --/
+
+/\b...\B/8
+    abc_
+    ** Failers 
+    \x{37e}abc\x{376} 
+    \x{37e}\x{376}\x{371}\x{393}\x{394} 
+    !\x{c0}++\x{c1}\x{c2} 
+    !\x{c0}+++++ 
+
+/-- With PCRE_UCP, non-UTF8 chars that are < 256 still check properties  --/
+
+/\b...\B/W
+    abc_
+    !\x{c0}++\x{c1}\x{c2} 
+    !\x{c0}+++++ 
+
+/-- Some of these are silly, but they check various combinations --/
+
+/[[:^alpha:][:^cntrl:]]+/8WBZ
+    123
+    abc 
+
+/[[:^cntrl:][:^alpha:]]+/8WBZ
+    123
+    abc 
+
+/[[:alpha:]]+/8WBZ
+    abc
+
+/[[:^alpha:]\S]+/8WBZ
+    123
+    abc 
+
+/[^\d]+/8WBZ
+    abc123
+    abc\x{123}
+    \x{660}abc   
+
+/\p{Lu}+9\p{Lu}+B\p{Lu}+b/BZ
+
+/\p{^Lu}+9\p{^Lu}+B\p{^Lu}+b/BZ
+
+/\P{Lu}+9\P{Lu}+B\P{Lu}+b/BZ
+
+/\p{Han}+X\p{Greek}+\x{370}/BZ8
+
+/\p{Xan}+!\p{Xan}+A/BZ
+
+/\p{Xsp}+!\p{Xsp}\t/BZ
+
+/\p{Xps}+!\p{Xps}\t/BZ
+
+/\p{Xwd}+!\p{Xwd}_/BZ
+
+/A+\p{N}A+\dB+\p{N}*B+\d*/WBZ
+
+/-- These behaved oddly in Perl, so they are kept in this test --/
+
+/(\x{23a}\x{23a}\x{23a})?\1/8i
+    \x{23a}\x{23a}\x{23a}\x{2c65}\x{2c65}
+
+/(ȺȺȺ)?\1/8i
+    ȺȺȺⱥⱥ
+
+/(\x{23a}\x{23a}\x{23a})?\1/8i
+    \x{23a}\x{23a}\x{23a}\x{2c65}\x{2c65}\x{2c65}
+
+/(ȺȺȺ)?\1/8i
+    ȺȺȺⱥⱥⱥ
+
+/(\x{23a}\x{23a}\x{23a})\1/8i
+    \x{23a}\x{23a}\x{23a}\x{2c65}\x{2c65}
+
+/(ȺȺȺ)\1/8i
+    ȺȺȺⱥⱥ
+
+/(\x{23a}\x{23a}\x{23a})\1/8i
+    \x{23a}\x{23a}\x{23a}\x{2c65}\x{2c65}\x{2c65}
+
+/(ȺȺȺ)\1/8i
+    ȺȺȺⱥⱥⱥ
+
+/(\x{2c65}\x{2c65})\1/8i
+    \x{2c65}\x{2c65}\x{23a}\x{23a}
+    
+/(ⱥⱥ)\1/8i
+    ⱥⱥȺȺ 
+    
+/(\x{23a}\x{23a}\x{23a})\1Y/8i
+    X\x{23a}\x{23a}\x{23a}\x{2c65}\x{2c65}\x{2c65}YZ
+
+/(\x{2c65}\x{2c65})\1Y/8i
+    X\x{2c65}\x{2c65}\x{23a}\x{23a}YZ
+
+/-- --/ 
+
+/-- These scripts weren't yet in Perl when I added Unicode 6.0.0 to PCRE --/
+
+/^[\p{Batak}]/8
+    \x{1bc0}
+    \x{1bff}
+    ** Failers
+    \x{1bf4}
+    
+/^[\p{Brahmi}]/8
+    \x{11000}
+    \x{1106f}
+    ** Failers
+    \x{1104e}
+    
+/^[\p{Mandaic}]/8
+    \x{840}
+    \x{85e}
+    ** Failers
+    \x{85c}
+    \x{85d}    
+
+/-- --/ 
+
+/(\X*)(.)/s8
+    A\x{300}
+
+/^S(\X*)e(\X*)$/8
+    Ste�re�o
+    
+/^\X/8 
+    �re�o
+
+/^a\X41z/<JS>
+    aX41z
+    *** Failers
+    aAz
+
+/(?<=ab\Cde)X/8
+
+/\X/
+    a\P
+    a\P\P
+
+/\Xa/
+    aa\P
+    aa\P\P
+
+/\X{2}/
+    aa\P
+    aa\P\P
+
+/\X+a/
+    a\P
+    aa\P
+    aa\P\P
+
+/\X+?a/
+    a\P
+    ab\P
+    aa\P
+    aa\P\P
+    aba\P
+    
+/-- These Unicode 6.1.0 scripts are not known to Perl. --/ 
+
+/\p{Chakma}\d/8W
+    \x{11100}\x{1113c}
+
+/\p{Takri}\d/8W
+    \x{11680}\x{116c0}
+
+/^\X/8
+    A\P
+    A\P\P 
+    A\x{300}\x{301}\P
+    A\x{300}\x{301}\P\P  
+    A\x{301}\P
+    A\x{301}\P\P  
+    
+/^\X{2,3}/8
+    A\P
+    A\P\P 
+    AA\P
+    AA\P\P  
+    A\x{300}\x{301}\P
+    A\x{300}\x{301}\P\P  
+    A\x{300}\x{301}A\x{300}\x{301}\P
+    A\x{300}\x{301}A\x{300}\x{301}\P\P  
+
+/^\X{2}/8
+    AA\P
+    AA\P\P  
+    A\x{300}\x{301}A\x{300}\x{301}\P
+    A\x{300}\x{301}A\x{300}\x{301}\P\P  
+    
+/^\X+/8
+    AA\P
+    AA\P\P  
+
+/^\X+?Z/8
+    AA\P
+    AA\P\P 
+
+/-- End of testinput7 --/
diff --git a/ext/pcre/pcrelib/testdata/testinput8 b/ext/pcre/pcrelib/testdata/testinput8
new file mode 100644
index 0000000..e235445
--- /dev/null
+++ b/ext/pcre/pcrelib/testdata/testinput8
@@ -0,0 +1,4801 @@
+/-- This set of tests check the DFA matching functionality of pcre_dfa_exec().
+    The -dfa flag must be used with pcretest when running it. --/
+     
+/abc/
+    abc
+    
+/ab*c/
+    abc
+    abbbbc
+    ac
+    
+/ab+c/
+    abc
+    abbbbbbc
+    *** Failers 
+    ac
+    ab
+    
+/a*/
+    a
+    aaaaaaaaaaaaaaaaa
+    aaaaaaaaaaaaaaaaaaaaaaaaaaaaaa 
+    aaaaaaaaaaaaaaaaaaaaaaaaaaaaaa\F 
+    
+/(a|abcd|african)/
+    a
+    abcd
+    african
+    
+/^abc/
+    abcdef
+    *** Failers
+    xyzabc
+    xyz\nabc    
+    
+/^abc/m
+    abcdef
+    xyz\nabc    
+    *** Failers
+    xyzabc
+    
+/\Aabc/
+    abcdef
+    *** Failers
+    xyzabc
+    xyz\nabc    
+    
+/\Aabc/m
+    abcdef
+    *** Failers
+    xyzabc
+    xyz\nabc    
+    
+/\Gabc/
+    abcdef
+    xyzabc\>3
+    *** Failers
+    xyzabc    
+    xyzabc\>2 
+    
+/x\dy\Dz/
+    x9yzz
+    x0y+z
+    *** Failers
+    xyz
+    xxy0z     
+    
+/x\sy\Sz/
+    x yzz
+    x y+z
+    *** Failers
+    xyz
+    xxyyz
+    
+/x\wy\Wz/
+    xxy+z
+    *** Failers
+    xxy0z
+    x+y+z         
+    
+/x.y/
+    x+y
+    x-y
+    *** Failers
+    x\ny
+    
+/x.y/s
+    x+y
+    x-y
+    x\ny
+
+/(a.b(?s)c.d|x.y)p.q/
+    a+bc+dp+q
+    a+bc\ndp+q
+    x\nyp+q 
+    *** Failers 
+    a\nbc\ndp+q
+    a+bc\ndp\nq
+    x\nyp\nq 
+
+/a\d\z/
+    ba0
+    *** Failers
+    ba0\n
+    ba0\ncd   
+
+/a\d\z/m
+    ba0
+    *** Failers
+    ba0\n
+    ba0\ncd   
+
+/a\d\Z/
+    ba0
+    ba0\n
+    *** Failers
+    ba0\ncd   
+
+/a\d\Z/m
+    ba0
+    ba0\n
+    *** Failers
+    ba0\ncd   
+
+/a\d$/
+    ba0
+    ba0\n
+    *** Failers
+    ba0\ncd   
+
+/a\d$/m
+    ba0
+    ba0\n
+    ba0\ncd   
+    *** Failers
+
+/abc/i
+    abc
+    aBc
+    ABC
+    
+/[^a]/
+    abcd
+    
+/ab?\w/
+    abz
+    abbz
+    azz  
+
+/x{0,3}yz/
+    ayzq
+    axyzq
+    axxyz
+    axxxyzq
+    axxxxyzq
+    *** Failers
+    ax
+    axx     
+      
+/x{3}yz/
+    axxxyzq
+    axxxxyzq
+    *** Failers
+    ax
+    axx     
+    ayzq
+    axyzq
+    axxyz
+      
+/x{2,3}yz/
+    axxyz
+    axxxyzq
+    axxxxyzq
+    *** Failers
+    ax
+    axx     
+    ayzq
+    axyzq
+      
+/[^a]+/
+    bac
+    bcdefax
+    *** Failers
+    aaaaa   
+
+/[^a]*/
+    bac
+    bcdefax
+    *** Failers
+    aaaaa   
+    
+/[^a]{3,5}/
+    xyz
+    awxyza
+    abcdefa
+    abcdefghijk
+    *** Failers
+    axya
+    axa
+    aaaaa         
+
+/\d*/
+    1234b567
+    xyz
+    
+/\D*/
+    a1234b567
+    xyz
+     
+/\d+/
+    ab1234c56
+    *** Failers
+    xyz
+    
+/\D+/
+    ab123c56
+    *** Failers
+    789
+    
+/\d?A/
+    045ABC
+    ABC
+    *** Failers
+    XYZ
+    
+/\D?A/
+    ABC
+    BAC
+    9ABC             
+    *** Failers
+
+/a+/
+    aaaa
+
+/^.*xyz/
+    xyz
+    ggggggggxyz
+    
+/^.+xyz/
+    abcdxyz
+    axyz
+    *** Failers
+    xyz
+    
+/^.?xyz/
+    xyz
+    cxyz       
+
+/^\d{2,3}X/
+    12X
+    123X
+    *** Failers
+    X
+    1X
+    1234X     
+
+/^[abcd]\d/
+    a45
+    b93
+    c99z
+    d04
+    *** Failers
+    e45
+    abcd      
+    abcd1234
+    1234  
+
+/^[abcd]*\d/
+    a45
+    b93
+    c99z
+    d04
+    abcd1234
+    1234  
+    *** Failers
+    e45
+    abcd      
+
+/^[abcd]+\d/
+    a45
+    b93
+    c99z
+    d04
+    abcd1234
+    *** Failers
+    1234  
+    e45
+    abcd      
+
+/^a+X/
+    aX
+    aaX 
+
+/^[abcd]?\d/
+    a45
+    b93
+    c99z
+    d04
+    1234  
+    *** Failers
+    abcd1234
+    e45
+
+/^[abcd]{2,3}\d/
+    ab45
+    bcd93
+    *** Failers
+    1234 
+    a36 
+    abcd1234
+    ee45
+
+/^(abc)*\d/
+    abc45
+    abcabcabc45
+    42xyz 
+    *** Failers
+
+/^(abc)+\d/
+    abc45
+    abcabcabc45
+    *** Failers
+    42xyz 
+
+/^(abc)?\d/
+    abc45
+    42xyz 
+    *** Failers
+    abcabcabc45
+
+/^(abc){2,3}\d/
+    abcabc45
+    abcabcabc45
+    *** Failers
+    abcabcabcabc45
+    abc45
+    42xyz 
+
+/1(abc|xyz)2(?1)3/
+    1abc2abc3456
+    1abc2xyz3456 
+
+/^(a*\w|ab)=(a*\w|ab)/
+    ab=ab
+
+/^(a*\w|ab)=(?1)/
+    ab=ab
+
+/^([^()]|\((?1)*\))*$/
+    abc
+    a(b)c
+    a(b(c))d  
+    *** Failers)
+    a(b(c)d  
+
+/^>abc>([^()]|\((?1)*\))*<xyz<$/
+    >abc>123<xyz<
+    >abc>1(2)3<xyz<
+    >abc>(1(2)3)<xyz<
+
+/^(?>a*)\d/
+    aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa9876
+    *** Failers 
+    aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+
+/< (?: (?(R) \d++  | [^<>]*+) | (?R)) * >/x
+    <>
+    <abcd>
+    <abc <123> hij>
+    <abc <def> hij>
+    <abc<>def> 
+    <abc<>      
+    *** Failers
+    <abc
+
+/^(?(?=abc)\w{3}:|\d\d)$/        
+    abc:                          
+    12                             
+    *** Failers                     
+    123                       
+    xyz                        
+                                
+/^(?(?!abc)\d\d|\w{3}:)$/      
+    abc:                        
+    12         
+    *** Failers
+    123
+    xyz    
+
+/^(?=abc)\w{5}:$/        
+    abcde:                          
+    *** Failers                     
+    abc.. 
+    123                       
+    vwxyz                        
+                                
+/^(?!abc)\d\d$/      
+    12         
+    *** Failers
+    abcde:
+    abc..  
+    123
+    vwxyz    
+
+/(?<=abc|xy)123/
+    abc12345
+    wxy123z
+    *** Failers
+    123abc
+
+/(?<!abc|xy)123/
+    123abc
+    mno123456 
+    *** Failers
+    abc12345
+    wxy123z
+
+/abc(?C1)xyz/
+    abcxyz
+    123abcxyz999 
+
+/(ab|cd){3,4}/C
+  ababab
+  abcdabcd
+  abcdcdcdcdcd  
+
+/^abc/
+    abcdef
+    *** Failers
+    abcdef\B  
+
+/^(a*|xyz)/
+    bcd
+    aaabcd
+    xyz
+    xyz\N  
+    *** Failers
+    bcd\N   
+    
+/xyz$/
+    xyz
+    xyz\n
+    *** Failers
+    xyz\Z
+    xyz\n\Z    
+    
+/xyz$/m
+    xyz
+    xyz\n 
+    abcxyz\npqr 
+    abcxyz\npqr\Z 
+    xyz\n\Z    
+    *** Failers
+    xyz\Z
+
+/\Gabc/
+    abcdef
+    defabcxyz\>3 
+    *** Failers 
+    defabcxyz
+
+/^abcdef/
+    ab\P
+    abcde\P
+    abcdef\P
+    *** Failers
+    abx\P    
+
+/^a{2,4}\d+z/
+    a\P
+    aa\P
+    aa2\P 
+    aaa\P
+    aaa23\P 
+    aaaa12345\P
+    aa0z\P
+    aaaa4444444444444z\P 
+    *** Failers
+    az\P 
+    aaaaa\P 
+    a56\P 
+
+/^abcdef/
+   abc\P
+   def\R 
+   
+/(?<=foo)bar/
+   xyzfo\P 
+   foob\P\>2 
+   foobar...\R\P\>4 
+   xyzfo\P
+   foobar\>2  
+   *** Failers
+   xyzfo\P
+   obar\R   
+
+/(ab*(cd|ef))+X/
+    adfadadaklhlkalkajhlkjahdfasdfasdfladsfjkj\P\Z
+    lkjhlkjhlkjhlkjhabbbbbbcdaefabbbbbbbefa\P\B\Z
+    cdabbbbbbbb\P\R\B\Z
+    efabbbbbbbbbbbbbbbb\P\R\B\Z
+    bbbbbbbbbbbbcdXyasdfadf\P\R\B\Z    
+
+/(a|b)/SF>testsavedregex
+<testsavedregex
+    abc
+    ** Failers
+    def  
+    
+/the quick brown fox/
+    the quick brown fox
+    The quick brown FOX
+    What do you know about the quick brown fox?
+    What do you know about THE QUICK BROWN FOX?
+
+/The quick brown fox/i
+    the quick brown fox
+    The quick brown FOX
+    What do you know about the quick brown fox?
+    What do you know about THE QUICK BROWN FOX?
+
+/abcd\t\n\r\f\a\e\071\x3b\$\\\?caxyz/
+    abcd\t\n\r\f\a\e9;\$\\?caxyz
+
+/a*abc?xyz+pqr{3}ab{2,}xy{4,5}pq{0,6}AB{0,}zz/
+    abxyzpqrrrabbxyyyypqAzz
+    abxyzpqrrrabbxyyyypqAzz
+    aabxyzpqrrrabbxyyyypqAzz
+    aaabxyzpqrrrabbxyyyypqAzz
+    aaaabxyzpqrrrabbxyyyypqAzz
+    abcxyzpqrrrabbxyyyypqAzz
+    aabcxyzpqrrrabbxyyyypqAzz
+    aaabcxyzpqrrrabbxyyyypAzz
+    aaabcxyzpqrrrabbxyyyypqAzz
+    aaabcxyzpqrrrabbxyyyypqqAzz
+    aaabcxyzpqrrrabbxyyyypqqqAzz
+    aaabcxyzpqrrrabbxyyyypqqqqAzz
+    aaabcxyzpqrrrabbxyyyypqqqqqAzz
+    aaabcxyzpqrrrabbxyyyypqqqqqqAzz
+    aaaabcxyzpqrrrabbxyyyypqAzz
+    abxyzzpqrrrabbxyyyypqAzz
+    aabxyzzzpqrrrabbxyyyypqAzz
+    aaabxyzzzzpqrrrabbxyyyypqAzz
+    aaaabxyzzzzpqrrrabbxyyyypqAzz
+    abcxyzzpqrrrabbxyyyypqAzz
+    aabcxyzzzpqrrrabbxyyyypqAzz
+    aaabcxyzzzzpqrrrabbxyyyypqAzz
+    aaaabcxyzzzzpqrrrabbxyyyypqAzz
+    aaaabcxyzzzzpqrrrabbbxyyyypqAzz
+    aaaabcxyzzzzpqrrrabbbxyyyyypqAzz
+    aaabcxyzpqrrrabbxyyyypABzz
+    aaabcxyzpqrrrabbxyyyypABBzz
+    >>>aaabxyzpqrrrabbxyyyypqAzz
+    >aaaabxyzpqrrrabbxyyyypqAzz
+    >>>>abcxyzpqrrrabbxyyyypqAzz
+    *** Failers
+    abxyzpqrrabbxyyyypqAzz
+    abxyzpqrrrrabbxyyyypqAzz
+    abxyzpqrrrabxyyyypqAzz
+    aaaabcxyzzzzpqrrrabbbxyyyyyypqAzz
+    aaaabcxyzzzzpqrrrabbbxyyypqAzz
+    aaabcxyzpqrrrabbxyyyypqqqqqqqAzz
+
+/^(abc){1,2}zz/
+    abczz
+    abcabczz
+    *** Failers
+    zz
+    abcabcabczz
+    >>abczz
+
+/^(b+?|a){1,2}?c/
+    bc
+    bbc
+    bbbc
+    bac
+    bbac
+    aac
+    abbbbbbbbbbbc
+    bbbbbbbbbbbac
+    *** Failers
+    aaac
+    abbbbbbbbbbbac
+
+/^(b+|a){1,2}c/
+    bc
+    bbc
+    bbbc
+    bac
+    bbac
+    aac
+    abbbbbbbbbbbc
+    bbbbbbbbbbbac
+    *** Failers
+    aaac
+    abbbbbbbbbbbac
+
+/^(b+|a){1,2}?bc/
+    bbc
+
+/^(b*|ba){1,2}?bc/
+    babc
+    bbabc
+    bababc
+    *** Failers
+    bababbc
+    babababc
+
+/^(ba|b*){1,2}?bc/
+    babc
+    bbabc
+    bababc
+    *** Failers
+    bababbc
+    babababc
+
+/^\ca\cA\c[\c{\c:/
+    \x01\x01\e;z
+
+/^[ab\]cde]/
+    athing
+    bthing
+    ]thing
+    cthing
+    dthing
+    ething
+    *** Failers
+    fthing
+    [thing
+    \\thing
+
+/^[]cde]/
+    ]thing
+    cthing
+    dthing
+    ething
+    *** Failers
+    athing
+    fthing
+
+/^[^ab\]cde]/
+    fthing
+    [thing
+    \\thing
+    *** Failers
+    athing
+    bthing
+    ]thing
+    cthing
+    dthing
+    ething
+
+/^[^]cde]/
+    athing
+    fthing
+    *** Failers
+    ]thing
+    cthing
+    dthing
+    ething
+
+/^\�/
+    �
+
+/^ÿ/
+    ÿ
+
+/^[0-9]+$/
+    0
+    1
+    2
+    3
+    4
+    5
+    6
+    7
+    8
+    9
+    10
+    100
+    *** Failers
+    abc
+
+/^.*nter/
+    enter
+    inter
+    uponter
+
+/^xxx[0-9]+$/
+    xxx0
+    xxx1234
+    *** Failers
+    xxx
+
+/^.+[0-9][0-9][0-9]$/
+    x123
+    xx123
+    123456
+    *** Failers
+    123
+    x1234
+
+/^.+?[0-9][0-9][0-9]$/
+    x123
+    xx123
+    123456
+    *** Failers
+    123
+    x1234
+
+/^([^!]+)!(.+)=apquxz\.ixr\.zzz\.ac\.uk$/
+    abc!pqr=apquxz.ixr.zzz.ac.uk
+    *** Failers
+    !pqr=apquxz.ixr.zzz.ac.uk
+    abc!=apquxz.ixr.zzz.ac.uk
+    abc!pqr=apquxz:ixr.zzz.ac.uk
+    abc!pqr=apquxz.ixr.zzz.ac.ukk
+
+/:/
+    Well, we need a colon: somewhere
+    *** Fail if we don't
+
+/([\da-f:]+)$/i
+    0abc
+    abc
+    fed
+    E
+    ::
+    5f03:12C0::932e
+    fed def
+    Any old stuff
+    *** Failers
+    0zzz
+    gzzz
+    fed\x20
+    Any old rubbish
+
+/^.*\.(\d{1,3})\.(\d{1,3})\.(\d{1,3})$/
+    .1.2.3
+    A.12.123.0
+    *** Failers
+    .1.2.3333
+    1.2.3
+    1234.2.3
+
+/^(\d+)\s+IN\s+SOA\s+(\S+)\s+(\S+)\s*\(\s*$/
+    1 IN SOA non-sp1 non-sp2(
+    1    IN    SOA    non-sp1    non-sp2   (
+    *** Failers
+    1IN SOA non-sp1 non-sp2(
+
+/^[a-zA-Z\d][a-zA-Z\d\-]*(\.[a-zA-Z\d][a-zA-z\d\-]*)*\.$/
+    a.
+    Z.
+    2.
+    ab-c.pq-r.
+    sxk.zzz.ac.uk.
+    x-.y-.
+    *** Failers
+    -abc.peq.
+
+/^\*\.[a-z]([a-z\-\d]*[a-z\d]+)?(\.[a-z]([a-z\-\d]*[a-z\d]+)?)*$/
+    *.a
+    *.b0-a
+    *.c3-b.c
+    *.c-a.b-c
+    *** Failers
+    *.0
+    *.a-
+    *.a-b.c-
+    *.c-a.0-c
+
+/^(?=ab(de))(abd)(e)/
+    abde
+
+/^(?!(ab)de|x)(abd)(f)/
+    abdf
+
+/^(?=(ab(cd)))(ab)/
+    abcd
+
+/^[\da-f](\.[\da-f])*$/i
+    a.b.c.d
+    A.B.C.D
+    a.b.c.1.2.3.C
+
+/^\".*\"\s*(;.*)?$/
+    \"1234\"
+    \"abcd\" ;
+    \"\" ; rhubarb
+    *** Failers
+    \"1234\" : things
+
+/^$/
+    \
+    *** Failers
+
+/   ^    a   (?# begins with a)  b\sc (?# then b c) $ (?# then end)/x
+    ab c
+    *** Failers
+    abc
+    ab cde
+
+/(?x)   ^    a   (?# begins with a)  b\sc (?# then b c) $ (?# then end)/
+    ab c
+    *** Failers
+    abc
+    ab cde
+
+/^   a\ b[c ]d       $/x
+    a bcd
+    a b d
+    *** Failers
+    abcd
+    ab d
+
+/^(a(b(c)))(d(e(f)))(h(i(j)))(k(l(m)))$/
+    abcdefhijklm
+
+/^(?:a(b(c)))(?:d(e(f)))(?:h(i(j)))(?:k(l(m)))$/
+    abcdefhijklm
+
+/^[\w][\W][\s][\S][\d][\D][\b][\n][\c]][\022]/
+    a+ Z0+\x08\n\x1d\x12
+
+/^[.^$|()*+?{,}]+/
+    .^\$(*+)|{?,?}
+
+/^a*\w/
+    z
+    az
+    aaaz
+    a
+    aa
+    aaaa
+    a+
+    aa+
+
+/^a*?\w/
+    z
+    az
+    aaaz
+    a
+    aa
+    aaaa
+    a+
+    aa+
+
+/^a+\w/
+    az
+    aaaz
+    aa
+    aaaa
+    aa+
+
+/^a+?\w/
+    az
+    aaaz
+    aa
+    aaaa
+    aa+
+
+/^\d{8}\w{2,}/
+    1234567890
+    12345678ab
+    12345678__
+    *** Failers
+    1234567
+
+/^[aeiou\d]{4,5}$/
+    uoie
+    1234
+    12345
+    aaaaa
+    *** Failers
+    123456
+
+/^[aeiou\d]{4,5}?/
+    uoie
+    1234
+    12345
+    aaaaa
+    123456
+
+/^From +([^ ]+) +[a-zA-Z][a-zA-Z][a-zA-Z] +[a-zA-Z][a-zA-Z][a-zA-Z] +[0-9]?[0-9] +[0-9][0-9]:[0-9][0-9]/
+    From abcd  Mon Sep 01 12:33:02 1997
+
+/^From\s+\S+\s+([a-zA-Z]{3}\s+){2}\d{1,2}\s+\d\d:\d\d/
+    From abcd  Mon Sep 01 12:33:02 1997
+    From abcd  Mon Sep  1 12:33:02 1997
+    *** Failers
+    From abcd  Sep 01 12:33:02 1997
+
+/^12.34/s
+    12\n34
+    12\r34
+
+/\w+(?=\t)/
+    the quick brown\t fox
+
+/foo(?!bar)(.*)/
+    foobar is foolish see?
+
+/(?:(?!foo)...|^.{0,2})bar(.*)/
+    foobar crowbar etc
+    barrel
+    2barrel
+    A barrel
+
+/^(\D*)(?=\d)(?!123)/
+    abc456
+    *** Failers
+    abc123
+
+/^1234(?# test newlines
+  inside)/
+    1234
+
+/^1234 #comment in extended re
+  /x
+    1234
+
+/#rhubarb
+  abcd/x
+    abcd
+
+/^abcd#rhubarb/x
+    abcd
+
+/(?!^)abc/
+    the abc
+    *** Failers
+    abc
+
+/(?=^)abc/
+    abc
+    *** Failers
+    the abc
+
+/^[ab]{1,3}(ab*|b)/
+    aabbbbb
+
+/^[ab]{1,3}?(ab*|b)/
+    aabbbbb
+
+/^[ab]{1,3}?(ab*?|b)/
+    aabbbbb
+
+/^[ab]{1,3}(ab*?|b)/
+    aabbbbb
+
+/  (?: [\040\t] |  \(
+(?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  |  \( (?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  )* \)  )*
+\)  )*                          # optional leading comment
+(?:    (?:
+[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+    # some number of atom characters...
+(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom
+|
+" (?:                      # opening quote...
+[^\\\x80-\xff\n\015"]                #   Anything except backslash and quote
+|                     #    or
+\\ [^\x80-\xff]           #   Escaped something (something != CR)
+)* "  # closing quote
+)                    # initial word
+(?:  (?: [\040\t] |  \(
+(?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  |  \( (?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  )* \)  )*
+\)  )*  \.  (?: [\040\t] |  \(
+(?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  |  \( (?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  )* \)  )*
+\)  )*   (?:
+[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+    # some number of atom characters...
+(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom
+|
+" (?:                      # opening quote...
+[^\\\x80-\xff\n\015"]                #   Anything except backslash and quote
+|                     #    or
+\\ [^\x80-\xff]           #   Escaped something (something != CR)
+)* "  # closing quote
+)  )* # further okay, if led by a period
+(?: [\040\t] |  \(
+(?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  |  \( (?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  )* \)  )*
+\)  )*  @  (?: [\040\t] |  \(
+(?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  |  \( (?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  )* \)  )*
+\)  )*    (?:
+[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+    # some number of atom characters...
+(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom
+|   \[                         # [
+(?: [^\\\x80-\xff\n\015\[\]] |  \\ [^\x80-\xff]  )*    #    stuff
+\]                        #           ]
+)                           # initial subdomain
+(?:                                  #
+(?: [\040\t] |  \(
+(?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  |  \( (?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  )* \)  )*
+\)  )*  \.                        # if led by a period...
+(?: [\040\t] |  \(
+(?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  |  \( (?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  )* \)  )*
+\)  )*   (?:
+[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+    # some number of atom characters...
+(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom
+|   \[                         # [
+(?: [^\\\x80-\xff\n\015\[\]] |  \\ [^\x80-\xff]  )*    #    stuff
+\]                        #           ]
+)                     #   ...further okay
+)*
+# address
+|                     #  or
+(?:
+[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+    # some number of atom characters...
+(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom
+|
+" (?:                      # opening quote...
+[^\\\x80-\xff\n\015"]                #   Anything except backslash and quote
+|                     #    or
+\\ [^\x80-\xff]           #   Escaped something (something != CR)
+)* "  # closing quote
+)             # one word, optionally followed by....
+(?:
+[^()<>@,;:".\\\[\]\x80-\xff\000-\010\012-\037]  |  # atom and space parts, or...
+\(
+(?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  |  \( (?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  )* \)  )*
+\)       |  # comments, or...
+
+" (?:                      # opening quote...
+[^\\\x80-\xff\n\015"]                #   Anything except backslash and quote
+|                     #    or
+\\ [^\x80-\xff]           #   Escaped something (something != CR)
+)* "  # closing quote
+# quoted strings
+)*
+<  (?: [\040\t] |  \(
+(?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  |  \( (?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  )* \)  )*
+\)  )*                     # leading <
+(?:  @  (?: [\040\t] |  \(
+(?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  |  \( (?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  )* \)  )*
+\)  )*    (?:
+[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+    # some number of atom characters...
+(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom
+|   \[                         # [
+(?: [^\\\x80-\xff\n\015\[\]] |  \\ [^\x80-\xff]  )*    #    stuff
+\]                        #           ]
+)                           # initial subdomain
+(?:                                  #
+(?: [\040\t] |  \(
+(?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  |  \( (?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  )* \)  )*
+\)  )*  \.                        # if led by a period...
+(?: [\040\t] |  \(
+(?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  |  \( (?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  )* \)  )*
+\)  )*   (?:
+[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+    # some number of atom characters...
+(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom
+|   \[                         # [
+(?: [^\\\x80-\xff\n\015\[\]] |  \\ [^\x80-\xff]  )*    #    stuff
+\]                        #           ]
+)                     #   ...further okay
+)*
+
+(?:  (?: [\040\t] |  \(
+(?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  |  \( (?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  )* \)  )*
+\)  )*  ,  (?: [\040\t] |  \(
+(?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  |  \( (?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  )* \)  )*
+\)  )*  @  (?: [\040\t] |  \(
+(?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  |  \( (?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  )* \)  )*
+\)  )*    (?:
+[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+    # some number of atom characters...
+(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom
+|   \[                         # [
+(?: [^\\\x80-\xff\n\015\[\]] |  \\ [^\x80-\xff]  )*    #    stuff
+\]                        #           ]
+)                           # initial subdomain
+(?:                                  #
+(?: [\040\t] |  \(
+(?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  |  \( (?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  )* \)  )*
+\)  )*  \.                        # if led by a period...
+(?: [\040\t] |  \(
+(?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  |  \( (?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  )* \)  )*
+\)  )*   (?:
+[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+    # some number of atom characters...
+(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom
+|   \[                         # [
+(?: [^\\\x80-\xff\n\015\[\]] |  \\ [^\x80-\xff]  )*    #    stuff
+\]                        #           ]
+)                     #   ...further okay
+)*
+)* # further okay, if led by comma
+:                                # closing colon
+(?: [\040\t] |  \(
+(?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  |  \( (?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  )* \)  )*
+\)  )*  )? #       optional route
+(?:
+[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+    # some number of atom characters...
+(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom
+|
+" (?:                      # opening quote...
+[^\\\x80-\xff\n\015"]                #   Anything except backslash and quote
+|                     #    or
+\\ [^\x80-\xff]           #   Escaped something (something != CR)
+)* "  # closing quote
+)                    # initial word
+(?:  (?: [\040\t] |  \(
+(?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  |  \( (?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  )* \)  )*
+\)  )*  \.  (?: [\040\t] |  \(
+(?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  |  \( (?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  )* \)  )*
+\)  )*   (?:
+[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+    # some number of atom characters...
+(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom
+|
+" (?:                      # opening quote...
+[^\\\x80-\xff\n\015"]                #   Anything except backslash and quote
+|                     #    or
+\\ [^\x80-\xff]           #   Escaped something (something != CR)
+)* "  # closing quote
+)  )* # further okay, if led by a period
+(?: [\040\t] |  \(
+(?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  |  \( (?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  )* \)  )*
+\)  )*  @  (?: [\040\t] |  \(
+(?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  |  \( (?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  )* \)  )*
+\)  )*    (?:
+[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+    # some number of atom characters...
+(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom
+|   \[                         # [
+(?: [^\\\x80-\xff\n\015\[\]] |  \\ [^\x80-\xff]  )*    #    stuff
+\]                        #           ]
+)                           # initial subdomain
+(?:                                  #
+(?: [\040\t] |  \(
+(?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  |  \( (?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  )* \)  )*
+\)  )*  \.                        # if led by a period...
+(?: [\040\t] |  \(
+(?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  |  \( (?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  )* \)  )*
+\)  )*   (?:
+[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+    # some number of atom characters...
+(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom
+|   \[                         # [
+(?: [^\\\x80-\xff\n\015\[\]] |  \\ [^\x80-\xff]  )*    #    stuff
+\]                        #           ]
+)                     #   ...further okay
+)*
+#       address spec
+(?: [\040\t] |  \(
+(?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  |  \( (?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  )* \)  )*
+\)  )*  > #                  trailing >
+# name and address
+)  (?: [\040\t] |  \(
+(?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  |  \( (?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  )* \)  )*
+\)  )*                       # optional trailing comment
+/x
+    Alan Other <user\@dom.ain>
+    <user\@dom.ain>
+    user\@dom.ain
+    \"A. Other\" <user.1234\@dom.ain> (a comment)
+    A. Other <user.1234\@dom.ain> (a comment)
+    \"/s=user/ou=host/o=place/prmd=uu.yy/admd= /c=gb/\"\@x400-re.lay
+    A missing angle <user\@some.where
+    *** Failers
+    The quick brown fox
+
+/[\040\t]*                    # Nab whitespace.
+(?:
+\(                              #  (
+[^\\\x80-\xff\n\015()] *                             #     normal*
+(?:                                 #       (
+(?:  \\ [^\x80-\xff]  |
+\(                            #  (
+[^\\\x80-\xff\n\015()] *                            #     normal*
+(?:  \\ [^\x80-\xff]   [^\\\x80-\xff\n\015()] * )*        #     (special normal*)*
+\)                           #                       )
+)    #         special
+[^\\\x80-\xff\n\015()] *                         #         normal*
+)*                                  #            )*
+\)                             #                )
+[\040\t]* )*    # If comment found, allow more spaces.
+# optional leading comment
+(?:
+(?:
+[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+    # some number of atom characters...
+(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom
+# Atom
+|                       #  or
+"                                     # "
+[^\\\x80-\xff\n\015"] *                            #   normal
+(?:  \\ [^\x80-\xff]  [^\\\x80-\xff\n\015"] * )*        #   ( special normal* )*
+"                                     #        "
+# Quoted string
+)
+[\040\t]*                    # Nab whitespace.
+(?:
+\(                              #  (
+[^\\\x80-\xff\n\015()] *                             #     normal*
+(?:                                 #       (
+(?:  \\ [^\x80-\xff]  |
+\(                            #  (
+[^\\\x80-\xff\n\015()] *                            #     normal*
+(?:  \\ [^\x80-\xff]   [^\\\x80-\xff\n\015()] * )*        #     (special normal*)*
+\)                           #                       )
+)    #         special
+[^\\\x80-\xff\n\015()] *                         #         normal*
+)*                                  #            )*
+\)                             #                )
+[\040\t]* )*    # If comment found, allow more spaces.
+(?:
+\.
+[\040\t]*                    # Nab whitespace.
+(?:
+\(                              #  (
+[^\\\x80-\xff\n\015()] *                             #     normal*
+(?:                                 #       (
+(?:  \\ [^\x80-\xff]  |
+\(                            #  (
+[^\\\x80-\xff\n\015()] *                            #     normal*
+(?:  \\ [^\x80-\xff]   [^\\\x80-\xff\n\015()] * )*        #     (special normal*)*
+\)                           #                       )
+)    #         special
+[^\\\x80-\xff\n\015()] *                         #         normal*
+)*                                  #            )*
+\)                             #                )
+[\040\t]* )*    # If comment found, allow more spaces.
+(?:
+[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+    # some number of atom characters...
+(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom
+# Atom
+|                       #  or
+"                                     # "
+[^\\\x80-\xff\n\015"] *                            #   normal
+(?:  \\ [^\x80-\xff]  [^\\\x80-\xff\n\015"] * )*        #   ( special normal* )*
+"                                     #        "
+# Quoted string
+)
+[\040\t]*                    # Nab whitespace.
+(?:
+\(                              #  (
+[^\\\x80-\xff\n\015()] *                             #     normal*
+(?:                                 #       (
+(?:  \\ [^\x80-\xff]  |
+\(                            #  (
+[^\\\x80-\xff\n\015()] *                            #     normal*
+(?:  \\ [^\x80-\xff]   [^\\\x80-\xff\n\015()] * )*        #     (special normal*)*
+\)                           #                       )
+)    #         special
+[^\\\x80-\xff\n\015()] *                         #         normal*
+)*                                  #            )*
+\)                             #                )
+[\040\t]* )*    # If comment found, allow more spaces.
+# additional words
+)*
+@
+[\040\t]*                    # Nab whitespace.
+(?:
+\(                              #  (
+[^\\\x80-\xff\n\015()] *                             #     normal*
+(?:                                 #       (
+(?:  \\ [^\x80-\xff]  |
+\(                            #  (
+[^\\\x80-\xff\n\015()] *                            #     normal*
+(?:  \\ [^\x80-\xff]   [^\\\x80-\xff\n\015()] * )*        #     (special normal*)*
+\)                           #                       )
+)    #         special
+[^\\\x80-\xff\n\015()] *                         #         normal*
+)*                                  #            )*
+\)                             #                )
+[\040\t]* )*    # If comment found, allow more spaces.
+(?:
+[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+    # some number of atom characters...
+(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom
+|
+\[                            # [
+(?: [^\\\x80-\xff\n\015\[\]] |  \\ [^\x80-\xff]  )*     #    stuff
+\]                           #           ]
+)
+[\040\t]*                    # Nab whitespace.
+(?:
+\(                              #  (
+[^\\\x80-\xff\n\015()] *                             #     normal*
+(?:                                 #       (
+(?:  \\ [^\x80-\xff]  |
+\(                            #  (
+[^\\\x80-\xff\n\015()] *                            #     normal*
+(?:  \\ [^\x80-\xff]   [^\\\x80-\xff\n\015()] * )*        #     (special normal*)*
+\)                           #                       )
+)    #         special
+[^\\\x80-\xff\n\015()] *                         #         normal*
+)*                                  #            )*
+\)                             #                )
+[\040\t]* )*    # If comment found, allow more spaces.
+# optional trailing comments
+(?:
+\.
+[\040\t]*                    # Nab whitespace.
+(?:
+\(                              #  (
+[^\\\x80-\xff\n\015()] *                             #     normal*
+(?:                                 #       (
+(?:  \\ [^\x80-\xff]  |
+\(                            #  (
+[^\\\x80-\xff\n\015()] *                            #     normal*
+(?:  \\ [^\x80-\xff]   [^\\\x80-\xff\n\015()] * )*        #     (special normal*)*
+\)                           #                       )
+)    #         special
+[^\\\x80-\xff\n\015()] *                         #         normal*
+)*                                  #            )*
+\)                             #                )
+[\040\t]* )*    # If comment found, allow more spaces.
+(?:
+[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+    # some number of atom characters...
+(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom
+|
+\[                            # [
+(?: [^\\\x80-\xff\n\015\[\]] |  \\ [^\x80-\xff]  )*     #    stuff
+\]                           #           ]
+)
+[\040\t]*                    # Nab whitespace.
+(?:
+\(                              #  (
+[^\\\x80-\xff\n\015()] *                             #     normal*
+(?:                                 #       (
+(?:  \\ [^\x80-\xff]  |
+\(                            #  (
+[^\\\x80-\xff\n\015()] *                            #     normal*
+(?:  \\ [^\x80-\xff]   [^\\\x80-\xff\n\015()] * )*        #     (special normal*)*
+\)                           #                       )
+)    #         special
+[^\\\x80-\xff\n\015()] *                         #         normal*
+)*                                  #            )*
+\)                             #                )
+[\040\t]* )*    # If comment found, allow more spaces.
+# optional trailing comments
+)*
+# address
+|                             #  or
+(?:
+[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+    # some number of atom characters...
+(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom
+# Atom
+|                       #  or
+"                                     # "
+[^\\\x80-\xff\n\015"] *                            #   normal
+(?:  \\ [^\x80-\xff]  [^\\\x80-\xff\n\015"] * )*        #   ( special normal* )*
+"                                     #        "
+# Quoted string
+)
+# leading word
+[^()<>@,;:".\\\[\]\x80-\xff\000-\010\012-\037] *               # "normal" atoms and or spaces
+(?:
+(?:
+\(                              #  (
+[^\\\x80-\xff\n\015()] *                             #     normal*
+(?:                                 #       (
+(?:  \\ [^\x80-\xff]  |
+\(                            #  (
+[^\\\x80-\xff\n\015()] *                            #     normal*
+(?:  \\ [^\x80-\xff]   [^\\\x80-\xff\n\015()] * )*        #     (special normal*)*
+\)                           #                       )
+)    #         special
+[^\\\x80-\xff\n\015()] *                         #         normal*
+)*                                  #            )*
+\)                             #                )
+|
+"                                     # "
+[^\\\x80-\xff\n\015"] *                            #   normal
+(?:  \\ [^\x80-\xff]  [^\\\x80-\xff\n\015"] * )*        #   ( special normal* )*
+"                                     #        "
+) # "special" comment or quoted string
+[^()<>@,;:".\\\[\]\x80-\xff\000-\010\012-\037] *            #  more "normal"
+)*
+<
+[\040\t]*                    # Nab whitespace.
+(?:
+\(                              #  (
+[^\\\x80-\xff\n\015()] *                             #     normal*
+(?:                                 #       (
+(?:  \\ [^\x80-\xff]  |
+\(                            #  (
+[^\\\x80-\xff\n\015()] *                            #     normal*
+(?:  \\ [^\x80-\xff]   [^\\\x80-\xff\n\015()] * )*        #     (special normal*)*
+\)                           #                       )
+)    #         special
+[^\\\x80-\xff\n\015()] *                         #         normal*
+)*                                  #            )*
+\)                             #                )
+[\040\t]* )*    # If comment found, allow more spaces.
+# <
+(?:
+@
+[\040\t]*                    # Nab whitespace.
+(?:
+\(                              #  (
+[^\\\x80-\xff\n\015()] *                             #     normal*
+(?:                                 #       (
+(?:  \\ [^\x80-\xff]  |
+\(                            #  (
+[^\\\x80-\xff\n\015()] *                            #     normal*
+(?:  \\ [^\x80-\xff]   [^\\\x80-\xff\n\015()] * )*        #     (special normal*)*
+\)                           #                       )
+)    #         special
+[^\\\x80-\xff\n\015()] *                         #         normal*
+)*                                  #            )*
+\)                             #                )
+[\040\t]* )*    # If comment found, allow more spaces.
+(?:
+[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+    # some number of atom characters...
+(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom
+|
+\[                            # [
+(?: [^\\\x80-\xff\n\015\[\]] |  \\ [^\x80-\xff]  )*     #    stuff
+\]                           #           ]
+)
+[\040\t]*                    # Nab whitespace.
+(?:
+\(                              #  (
+[^\\\x80-\xff\n\015()] *                             #     normal*
+(?:                                 #       (
+(?:  \\ [^\x80-\xff]  |
+\(                            #  (
+[^\\\x80-\xff\n\015()] *                            #     normal*
+(?:  \\ [^\x80-\xff]   [^\\\x80-\xff\n\015()] * )*        #     (special normal*)*
+\)                           #                       )
+)    #         special
+[^\\\x80-\xff\n\015()] *                         #         normal*
+)*                                  #            )*
+\)                             #                )
+[\040\t]* )*    # If comment found, allow more spaces.
+# optional trailing comments
+(?:
+\.
+[\040\t]*                    # Nab whitespace.
+(?:
+\(                              #  (
+[^\\\x80-\xff\n\015()] *                             #     normal*
+(?:                                 #       (
+(?:  \\ [^\x80-\xff]  |
+\(                            #  (
+[^\\\x80-\xff\n\015()] *                            #     normal*
+(?:  \\ [^\x80-\xff]   [^\\\x80-\xff\n\015()] * )*        #     (special normal*)*
+\)                           #                       )
+)    #         special
+[^\\\x80-\xff\n\015()] *                         #         normal*
+)*                                  #            )*
+\)                             #                )
+[\040\t]* )*    # If comment found, allow more spaces.
+(?:
+[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+    # some number of atom characters...
+(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom
+|
+\[                            # [
+(?: [^\\\x80-\xff\n\015\[\]] |  \\ [^\x80-\xff]  )*     #    stuff
+\]                           #           ]
+)
+[\040\t]*                    # Nab whitespace.
+(?:
+\(                              #  (
+[^\\\x80-\xff\n\015()] *                             #     normal*
+(?:                                 #       (
+(?:  \\ [^\x80-\xff]  |
+\(                            #  (
+[^\\\x80-\xff\n\015()] *                            #     normal*
+(?:  \\ [^\x80-\xff]   [^\\\x80-\xff\n\015()] * )*        #     (special normal*)*
+\)                           #                       )
+)    #         special
+[^\\\x80-\xff\n\015()] *                         #         normal*
+)*                                  #            )*
+\)                             #                )
+[\040\t]* )*    # If comment found, allow more spaces.
+# optional trailing comments
+)*
+(?: ,
+[\040\t]*                    # Nab whitespace.
+(?:
+\(                              #  (
+[^\\\x80-\xff\n\015()] *                             #     normal*
+(?:                                 #       (
+(?:  \\ [^\x80-\xff]  |
+\(                            #  (
+[^\\\x80-\xff\n\015()] *                            #     normal*
+(?:  \\ [^\x80-\xff]   [^\\\x80-\xff\n\015()] * )*        #     (special normal*)*
+\)                           #                       )
+)    #         special
+[^\\\x80-\xff\n\015()] *                         #         normal*
+)*                                  #            )*
+\)                             #                )
+[\040\t]* )*    # If comment found, allow more spaces.
+@
+[\040\t]*                    # Nab whitespace.
+(?:
+\(                              #  (
+[^\\\x80-\xff\n\015()] *                             #     normal*
+(?:                                 #       (
+(?:  \\ [^\x80-\xff]  |
+\(                            #  (
+[^\\\x80-\xff\n\015()] *                            #     normal*
+(?:  \\ [^\x80-\xff]   [^\\\x80-\xff\n\015()] * )*        #     (special normal*)*
+\)                           #                       )
+)    #         special
+[^\\\x80-\xff\n\015()] *                         #         normal*
+)*                                  #            )*
+\)                             #                )
+[\040\t]* )*    # If comment found, allow more spaces.
+(?:
+[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+    # some number of atom characters...
+(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom
+|
+\[                            # [
+(?: [^\\\x80-\xff\n\015\[\]] |  \\ [^\x80-\xff]  )*     #    stuff
+\]                           #           ]
+)
+[\040\t]*                    # Nab whitespace.
+(?:
+\(                              #  (
+[^\\\x80-\xff\n\015()] *                             #     normal*
+(?:                                 #       (
+(?:  \\ [^\x80-\xff]  |
+\(                            #  (
+[^\\\x80-\xff\n\015()] *                            #     normal*
+(?:  \\ [^\x80-\xff]   [^\\\x80-\xff\n\015()] * )*        #     (special normal*)*
+\)                           #                       )
+)    #         special
+[^\\\x80-\xff\n\015()] *                         #         normal*
+)*                                  #            )*
+\)                             #                )
+[\040\t]* )*    # If comment found, allow more spaces.
+# optional trailing comments
+(?:
+\.
+[\040\t]*                    # Nab whitespace.
+(?:
+\(                              #  (
+[^\\\x80-\xff\n\015()] *                             #     normal*
+(?:                                 #       (
+(?:  \\ [^\x80-\xff]  |
+\(                            #  (
+[^\\\x80-\xff\n\015()] *                            #     normal*
+(?:  \\ [^\x80-\xff]   [^\\\x80-\xff\n\015()] * )*        #     (special normal*)*
+\)                           #                       )
+)    #         special
+[^\\\x80-\xff\n\015()] *                         #         normal*
+)*                                  #            )*
+\)                             #                )
+[\040\t]* )*    # If comment found, allow more spaces.
+(?:
+[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+    # some number of atom characters...
+(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom
+|
+\[                            # [
+(?: [^\\\x80-\xff\n\015\[\]] |  \\ [^\x80-\xff]  )*     #    stuff
+\]                           #           ]
+)
+[\040\t]*                    # Nab whitespace.
+(?:
+\(                              #  (
+[^\\\x80-\xff\n\015()] *                             #     normal*
+(?:                                 #       (
+(?:  \\ [^\x80-\xff]  |
+\(                            #  (
+[^\\\x80-\xff\n\015()] *                            #     normal*
+(?:  \\ [^\x80-\xff]   [^\\\x80-\xff\n\015()] * )*        #     (special normal*)*
+\)                           #                       )
+)    #         special
+[^\\\x80-\xff\n\015()] *                         #         normal*
+)*                                  #            )*
+\)                             #                )
+[\040\t]* )*    # If comment found, allow more spaces.
+# optional trailing comments
+)*
+)*  # additional domains
+:
+[\040\t]*                    # Nab whitespace.
+(?:
+\(                              #  (
+[^\\\x80-\xff\n\015()] *                             #     normal*
+(?:                                 #       (
+(?:  \\ [^\x80-\xff]  |
+\(                            #  (
+[^\\\x80-\xff\n\015()] *                            #     normal*
+(?:  \\ [^\x80-\xff]   [^\\\x80-\xff\n\015()] * )*        #     (special normal*)*
+\)                           #                       )
+)    #         special
+[^\\\x80-\xff\n\015()] *                         #         normal*
+)*                                  #            )*
+\)                             #                )
+[\040\t]* )*    # If comment found, allow more spaces.
+# optional trailing comments
+)?     #       optional route
+(?:
+[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+    # some number of atom characters...
+(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom
+# Atom
+|                       #  or
+"                                     # "
+[^\\\x80-\xff\n\015"] *                            #   normal
+(?:  \\ [^\x80-\xff]  [^\\\x80-\xff\n\015"] * )*        #   ( special normal* )*
+"                                     #        "
+# Quoted string
+)
+[\040\t]*                    # Nab whitespace.
+(?:
+\(                              #  (
+[^\\\x80-\xff\n\015()] *                             #     normal*
+(?:                                 #       (
+(?:  \\ [^\x80-\xff]  |
+\(                            #  (
+[^\\\x80-\xff\n\015()] *                            #     normal*
+(?:  \\ [^\x80-\xff]   [^\\\x80-\xff\n\015()] * )*        #     (special normal*)*
+\)                           #                       )
+)    #         special
+[^\\\x80-\xff\n\015()] *                         #         normal*
+)*                                  #            )*
+\)                             #                )
+[\040\t]* )*    # If comment found, allow more spaces.
+(?:
+\.
+[\040\t]*                    # Nab whitespace.
+(?:
+\(                              #  (
+[^\\\x80-\xff\n\015()] *                             #     normal*
+(?:                                 #       (
+(?:  \\ [^\x80-\xff]  |
+\(                            #  (
+[^\\\x80-\xff\n\015()] *                            #     normal*
+(?:  \\ [^\x80-\xff]   [^\\\x80-\xff\n\015()] * )*        #     (special normal*)*
+\)                           #                       )
+)    #         special
+[^\\\x80-\xff\n\015()] *                         #         normal*
+)*                                  #            )*
+\)                             #                )
+[\040\t]* )*    # If comment found, allow more spaces.
+(?:
+[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+    # some number of atom characters...
+(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom
+# Atom
+|                       #  or
+"                                     # "
+[^\\\x80-\xff\n\015"] *                            #   normal
+(?:  \\ [^\x80-\xff]  [^\\\x80-\xff\n\015"] * )*        #   ( special normal* )*
+"                                     #        "
+# Quoted string
+)
+[\040\t]*                    # Nab whitespace.
+(?:
+\(                              #  (
+[^\\\x80-\xff\n\015()] *                             #     normal*
+(?:                                 #       (
+(?:  \\ [^\x80-\xff]  |
+\(                            #  (
+[^\\\x80-\xff\n\015()] *                            #     normal*
+(?:  \\ [^\x80-\xff]   [^\\\x80-\xff\n\015()] * )*        #     (special normal*)*
+\)                           #                       )
+)    #         special
+[^\\\x80-\xff\n\015()] *                         #         normal*
+)*                                  #            )*
+\)                             #                )
+[\040\t]* )*    # If comment found, allow more spaces.
+# additional words
+)*
+@
+[\040\t]*                    # Nab whitespace.
+(?:
+\(                              #  (
+[^\\\x80-\xff\n\015()] *                             #     normal*
+(?:                                 #       (
+(?:  \\ [^\x80-\xff]  |
+\(                            #  (
+[^\\\x80-\xff\n\015()] *                            #     normal*
+(?:  \\ [^\x80-\xff]   [^\\\x80-\xff\n\015()] * )*        #     (special normal*)*
+\)                           #                       )
+)    #         special
+[^\\\x80-\xff\n\015()] *                         #         normal*
+)*                                  #            )*
+\)                             #                )
+[\040\t]* )*    # If comment found, allow more spaces.
+(?:
+[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+    # some number of atom characters...
+(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom
+|
+\[                            # [
+(?: [^\\\x80-\xff\n\015\[\]] |  \\ [^\x80-\xff]  )*     #    stuff
+\]                           #           ]
+)
+[\040\t]*                    # Nab whitespace.
+(?:
+\(                              #  (
+[^\\\x80-\xff\n\015()] *                             #     normal*
+(?:                                 #       (
+(?:  \\ [^\x80-\xff]  |
+\(                            #  (
+[^\\\x80-\xff\n\015()] *                            #     normal*
+(?:  \\ [^\x80-\xff]   [^\\\x80-\xff\n\015()] * )*        #     (special normal*)*
+\)                           #                       )
+)    #         special
+[^\\\x80-\xff\n\015()] *                         #         normal*
+)*                                  #            )*
+\)                             #                )
+[\040\t]* )*    # If comment found, allow more spaces.
+# optional trailing comments
+(?:
+\.
+[\040\t]*                    # Nab whitespace.
+(?:
+\(                              #  (
+[^\\\x80-\xff\n\015()] *                             #     normal*
+(?:                                 #       (
+(?:  \\ [^\x80-\xff]  |
+\(                            #  (
+[^\\\x80-\xff\n\015()] *                            #     normal*
+(?:  \\ [^\x80-\xff]   [^\\\x80-\xff\n\015()] * )*        #     (special normal*)*
+\)                           #                       )
+)    #         special
+[^\\\x80-\xff\n\015()] *                         #         normal*
+)*                                  #            )*
+\)                             #                )
+[\040\t]* )*    # If comment found, allow more spaces.
+(?:
+[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+    # some number of atom characters...
+(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom
+|
+\[                            # [
+(?: [^\\\x80-\xff\n\015\[\]] |  \\ [^\x80-\xff]  )*     #    stuff
+\]                           #           ]
+)
+[\040\t]*                    # Nab whitespace.
+(?:
+\(                              #  (
+[^\\\x80-\xff\n\015()] *                             #     normal*
+(?:                                 #       (
+(?:  \\ [^\x80-\xff]  |
+\(                            #  (
+[^\\\x80-\xff\n\015()] *                            #     normal*
+(?:  \\ [^\x80-\xff]   [^\\\x80-\xff\n\015()] * )*        #     (special normal*)*
+\)                           #                       )
+)    #         special
+[^\\\x80-\xff\n\015()] *                         #         normal*
+)*                                  #            )*
+\)                             #                )
+[\040\t]* )*    # If comment found, allow more spaces.
+# optional trailing comments
+)*
+#       address spec
+>                    #                 >
+# name and address
+)
+/x
+    Alan Other <user\@dom.ain>
+    <user\@dom.ain>
+    user\@dom.ain
+    \"A. Other\" <user.1234\@dom.ain> (a comment)
+    A. Other <user.1234\@dom.ain> (a comment)
+    \"/s=user/ou=host/o=place/prmd=uu.yy/admd= /c=gb/\"\@x400-re.lay
+    A missing angle <user\@some.where
+    *** Failers
+    The quick brown fox
+
+/abc\0def\00pqr\000xyz\0000AB/
+    abc\0def\00pqr\000xyz\0000AB
+    abc456 abc\0def\00pqr\000xyz\0000ABCDE
+
+/abc\x0def\x00pqr\x000xyz\x0000AB/
+    abc\x0def\x00pqr\x000xyz\x0000AB
+    abc456 abc\x0def\x00pqr\x000xyz\x0000ABCDE
+
+/^[\000-\037]/
+    \0A
+    \01B
+    \037C
+
+/\0*/
+    \0\0\0\0
+
+/A\x0{2,3}Z/
+    The A\x0\x0Z
+    An A\0\x0\0Z
+    *** Failers
+    A\0Z
+    A\0\x0\0\x0Z
+
+/^\s/
+    \040abc
+    \x0cabc
+    \nabc
+    \rabc
+    \tabc
+    *** Failers
+    abc
+
+/^a	b
+      c/x
+    abc
+
+/ab{1,3}bc/
+    abbbbc
+    abbbc
+    abbc
+    *** Failers
+    abc
+    abbbbbc
+
+/([^.]*)\.([^:]*):[T ]+(.*)/
+    track1.title:TBlah blah blah
+
+/([^.]*)\.([^:]*):[T ]+(.*)/i
+    track1.title:TBlah blah blah
+
+/([^.]*)\.([^:]*):[t ]+(.*)/i
+    track1.title:TBlah blah blah
+
+/^[W-c]+$/
+    WXY_^abc
+    *** Failers
+    wxy
+
+/^[W-c]+$/i
+    WXY_^abc
+    wxy_^ABC
+
+/^[\x3f-\x5F]+$/i
+    WXY_^abc
+    wxy_^ABC
+
+/^abc$/m
+    abc
+    qqq\nabc
+    abc\nzzz
+    qqq\nabc\nzzz
+
+/^abc$/
+    abc
+    *** Failers
+    qqq\nabc
+    abc\nzzz
+    qqq\nabc\nzzz
+
+/\Aabc\Z/m
+    abc
+    abc\n 
+    *** Failers
+    qqq\nabc
+    abc\nzzz
+    qqq\nabc\nzzz
+    
+/\A(.)*\Z/s
+    abc\ndef
+
+/\A(.)*\Z/m
+    *** Failers
+    abc\ndef
+
+/(?:b)|(?::+)/
+    b::c
+    c::b
+
+/[-az]+/
+    az-
+    *** Failers
+    b
+
+/[az-]+/
+    za-
+    *** Failers
+    b
+
+/[a\-z]+/
+    a-z
+    *** Failers
+    b
+
+/[a-z]+/
+    abcdxyz
+
+/[\d-]+/
+    12-34
+    *** Failers
+    aaa
+
+/[\d-z]+/
+    12-34z
+    *** Failers
+    aaa
+
+/\x5c/
+    \\
+
+/\x20Z/
+    the Zoo
+    *** Failers
+    Zulu
+
+/ab{3cd/
+    ab{3cd
+
+/ab{3,cd/
+    ab{3,cd
+
+/ab{3,4a}cd/
+    ab{3,4a}cd
+
+/{4,5a}bc/
+    {4,5a}bc
+
+/^a.b/<lf>
+    a\rb
+    *** Failers
+    a\nb
+
+/abc$/
+    abc
+    abc\n
+    *** Failers
+    abc\ndef
+
+/(abc)\123/
+    abc\x53
+
+/(abc)\223/
+    abc\x93
+
+/(abc)\323/
+    abc\xd3
+
+/(abc)\100/
+    abc\x40
+    abc\100
+
+/(abc)\1000/
+    abc\x400
+    abc\x40\x30
+    abc\1000
+    abc\100\x30
+    abc\100\060
+    abc\100\60
+
+/abc\81/
+    abc\081
+    abc\0\x38\x31
+
+/abc\91/
+    abc\091
+    abc\0\x39\x31
+
+/(a)(b)(c)(d)(e)(f)(g)(h)(i)(j)(k)\12\123/
+    abcdefghijk\12S
+
+/ab\idef/
+    abidef
+
+/a{0}bc/
+    bc
+
+/(a|(bc)){0,0}?xyz/
+    xyz
+
+/abc[\10]de/
+    abc\010de
+
+/abc[\1]de/
+    abc\1de
+
+/(abc)[\1]de/
+    abc\1de
+
+/(?s)a.b/
+    a\nb
+
+/^([^a])([^\b])([^c]*)([^d]{3,4})/
+    baNOTccccd
+    baNOTcccd
+    baNOTccd
+    bacccd
+    *** Failers
+    anything
+    b\bc   
+    baccd
+
+/[^a]/
+    Abc
+  
+/[^a]/i
+    Abc 
+
+/[^a]+/
+    AAAaAbc
+  
+/[^a]+/i
+    AAAaAbc 
+
+/[^a]+/
+    bbb\nccc
+   
+/[^k]$/
+    abc
+    *** Failers
+    abk   
+   
+/[^k]{2,3}$/
+    abc
+    kbc
+    kabc 
+    *** Failers
+    abk
+    akb
+    akk 
+
+/^\d{8,}\@.+[^k]$/
+    12345678\@a.b.c.d
+    123456789\@x.y.z
+    *** Failers
+    12345678\@x.y.uk
+    1234567\@a.b.c.d       
+
+/[^a]/
+    aaaabcd
+    aaAabcd 
+
+/[^a]/i
+    aaaabcd
+    aaAabcd 
+
+/[^az]/
+    aaaabcd
+    aaAabcd 
+
+/[^az]/i
+    aaaabcd
+    aaAabcd 
+
+/\000\001\002\003\004\005\006\007\010\011\012\013\014\015\016\017\020\021\022\023\024\025\026\027\030\031\032\033\034\035\036\037\040\041\042\043\044\045\046\047\050\051\052\053\054\055\056\057\060\061\062\063\064\065\066\067\070\071\072\073\074\075\076\077\100\101\102\103\104\105\106\107\110\111\112\113\114\115\116\117\120\121\122\123\124\125\126\127\130\131\132\133\134\135\136\137\140\141\142\143\144\145\146\147\150\151\152\153\154\155\156\157\160\161\162\163\164\165\166\167\170\171\172\173\174\175\176\177\200\201\202\203\204\205\206\207\210\211\212\213\214\215\216\217\220\221\222\223\224\225\226\227\230\231\232\233\234\235\236\237\240\241\242\243\244\245\246\247\250\251\252\253\254\255\256\257\260\261\262\263\264\265\266\267\270\271\272\273\274\275\276\277\300\301\302\303\304\305\306\307\310\311\312\313\314\315\316\317\320\321\322\323\324\325\326\327\330\331\332\333\334\335\336\337\340\341\342\343\344\345\346\347\350\351\352\353\354\355\356\357\360\361\362\363\364\365\366\367\370\371\372\373\374\375\376\377/
+ \000\001\002\003\004\005\006\007\010\011\012\013\014\015\016\017\020\021\022\023\024\025\026\027\030\031\032\033\034\035\036\037\040\041\042\043\044\045\046\047\050\051\052\053\054\055\056\057\060\061\062\063\064\065\066\067\070\071\072\073\074\075\076\077\100\101\102\103\104\105\106\107\110\111\112\113\114\115\116\117\120\121\122\123\124\125\126\127\130\131\132\133\134\135\136\137\140\141\142\143\144\145\146\147\150\151\152\153\154\155\156\157\160\161\162\163\164\165\166\167\170\171\172\173\174\175\176\177\200\201\202\203\204\205\206\207\210\211\212\213\214\215\216\217\220\221\222\223\224\225\226\227\230\231\232\233\234\235\236\237\240\241\242\243\244\245\246\247\250\251\252\253\254\255\256\257\260\261\262\263\264\265\266\267\270\271\272\273\274\275\276\277\300\301\302\303\304\305\306\307\310\311\312\313\314\315\316\317\320\321\322\323\324\325\326\327\330\331\332\333\334\335\336\337\340\341\342\343\344\345\346\347\350\351\352\353\354\355\356\357\360\361\362\363\364\365\366\367\370\371\372\373\374\375\376\377
+
+/P[^*]TAIRE[^*]{1,6}?LL/
+    xxxxxxxxxxxPSTAIREISLLxxxxxxxxx
+
+/P[^*]TAIRE[^*]{1,}?LL/
+    xxxxxxxxxxxPSTAIREISLLxxxxxxxxx
+
+/(\.\d\d[1-9]?)\d+/
+    1.230003938
+    1.875000282   
+    1.235  
+                  
+/(\.\d\d((?=0)|\d(?=\d)))/
+    1.230003938      
+    1.875000282
+    *** Failers 
+    1.235 
+    
+/a(?)b/
+    ab 
+ 
+/\b(foo)\s+(\w+)/i
+    Food is on the foo table
+    
+/foo(.*)bar/
+    The food is under the bar in the barn.
+    
+/foo(.*?)bar/  
+    The food is under the bar in the barn.
+
+/(.*)(\d*)/
+    I have 2 numbers: 53147
+    
+/(.*)(\d+)/
+    I have 2 numbers: 53147
+ 
+/(.*?)(\d*)/
+    I have 2 numbers: 53147
+
+/(.*?)(\d+)/
+    I have 2 numbers: 53147
+
+/(.*)(\d+)$/
+    I have 2 numbers: 53147
+
+/(.*?)(\d+)$/
+    I have 2 numbers: 53147
+
+/(.*)\b(\d+)$/
+    I have 2 numbers: 53147
+
+/(.*\D)(\d+)$/
+    I have 2 numbers: 53147
+
+/^\D*(?!123)/
+    ABC123
+     
+/^(\D*)(?=\d)(?!123)/
+    ABC445
+    *** Failers
+    ABC123
+    
+/^[W-]46]/
+    W46]789 
+    -46]789
+    *** Failers
+    Wall
+    Zebra
+    42
+    [abcd] 
+    ]abcd[
+       
+/^[W-\]46]/
+    W46]789 
+    Wall
+    Zebra
+    Xylophone  
+    42
+    [abcd] 
+    ]abcd[
+    \\backslash 
+    *** Failers
+    -46]789
+    well
+    
+/\d\d\/\d\d\/\d\d\d\d/
+    01/01/2000
+
+/word (?:[a-zA-Z0-9]+ ){0,10}otherword/
+  word cat dog elephant mussel cow horse canary baboon snake shark otherword
+  word cat dog elephant mussel cow horse canary baboon snake shark
+
+/word (?:[a-zA-Z0-9]+ ){0,300}otherword/
+  word cat dog elephant mussel cow horse canary baboon snake shark the quick brown fox and the lazy dog and several other words getting close to thirty by now I hope
+
+/^(a){0,0}/
+    bcd
+    abc
+    aab     
+
+/^(a){0,1}/
+    bcd
+    abc
+    aab  
+
+/^(a){0,2}/
+    bcd
+    abc
+    aab  
+
+/^(a){0,3}/
+    bcd
+    abc
+    aab
+    aaa   
+
+/^(a){0,}/
+    bcd
+    abc
+    aab
+    aaa
+    aaaaaaaa    
+
+/^(a){1,1}/
+    bcd
+    abc
+    aab  
+
+/^(a){1,2}/
+    bcd
+    abc
+    aab  
+
+/^(a){1,3}/
+    bcd
+    abc
+    aab
+    aaa   
+
+/^(a){1,}/
+    bcd
+    abc
+    aab
+    aaa
+    aaaaaaaa    
+
+/.*\.gif/
+    borfle\nbib.gif\nno
+
+/.{0,}\.gif/
+    borfle\nbib.gif\nno
+
+/.*\.gif/m
+    borfle\nbib.gif\nno
+
+/.*\.gif/s
+    borfle\nbib.gif\nno
+
+/.*\.gif/ms
+    borfle\nbib.gif\nno
+    
+/.*$/
+    borfle\nbib.gif\nno
+
+/.*$/m
+    borfle\nbib.gif\nno
+
+/.*$/s
+    borfle\nbib.gif\nno
+
+/.*$/ms
+    borfle\nbib.gif\nno
+    
+/.*$/
+    borfle\nbib.gif\nno\n
+
+/.*$/m
+    borfle\nbib.gif\nno\n
+
+/.*$/s
+    borfle\nbib.gif\nno\n
+
+/.*$/ms
+    borfle\nbib.gif\nno\n
+    
+/(.*X|^B)/
+    abcde\n1234Xyz
+    BarFoo 
+    *** Failers
+    abcde\nBar  
+
+/(.*X|^B)/m
+    abcde\n1234Xyz
+    BarFoo 
+    abcde\nBar  
+
+/(.*X|^B)/s
+    abcde\n1234Xyz
+    BarFoo 
+    *** Failers
+    abcde\nBar  
+
+/(.*X|^B)/ms
+    abcde\n1234Xyz
+    BarFoo 
+    abcde\nBar  
+
+/(?s)(.*X|^B)/
+    abcde\n1234Xyz
+    BarFoo 
+    *** Failers 
+    abcde\nBar  
+
+/(?s:.*X|^B)/
+    abcde\n1234Xyz
+    BarFoo 
+    *** Failers 
+    abcde\nBar  
+
+/^.*B/
+    **** Failers
+    abc\nB
+     
+/(?s)^.*B/
+    abc\nB
+
+/(?m)^.*B/
+    abc\nB
+     
+/(?ms)^.*B/
+    abc\nB
+
+/(?ms)^B/
+    abc\nB
+
+/(?s)B$/
+    B\n
+
+/^[0-9][0-9][0-9][0-9][0-9][0-9][0-9][0-9][0-9][0-9][0-9][0-9]/
+    123456654321
+  
+/^\d\d\d\d\d\d\d\d\d\d\d\d/
+    123456654321 
+
+/^[\d][\d][\d][\d][\d][\d][\d][\d][\d][\d][\d][\d]/
+    123456654321
+  
+/^[abc]{12}/
+    abcabcabcabc
+    
+/^[a-c]{12}/
+    abcabcabcabc
+    
+/^(a|b|c){12}/
+    abcabcabcabc 
+
+/^[abcdefghijklmnopqrstuvwxy0123456789]/
+    n
+    *** Failers 
+    z 
+
+/abcde{0,0}/
+    abcd
+    *** Failers
+    abce  
+
+/ab[cd]{0,0}e/
+    abe
+    *** Failers
+    abcde 
+    
+/ab(c){0,0}d/
+    abd
+    *** Failers
+    abcd   
+
+/a(b*)/
+    a
+    ab
+    abbbb
+    *** Failers
+    bbbbb    
+    
+/ab\d{0}e/
+    abe
+    *** Failers
+    ab1e   
+    
+/"([^\\"]+|\\.)*"/
+    the \"quick\" brown fox
+    \"the \\\"quick\\\" brown fox\" 
+
+/.*?/g+
+    abc
+  
+/\b/g+
+    abc 
+
+/\b/+g
+    abc 
+
+//g
+    abc
+
+/<tr([\w\W\s\d][^<>]{0,})><TD([\w\W\s\d][^<>]{0,})>([\d]{0,}\.)(.*)((<BR>([\w\W\s\d][^<>]{0,})|[\s]{0,}))<\/a><\/TD><TD([\w\W\s\d][^<>]{0,})>([\w\W\s\d][^<>]{0,})<\/TD><TD([\w\W\s\d][^<>]{0,})>([\w\W\s\d][^<>]{0,})<\/TD><\/TR>/is
+  <TR BGCOLOR='#DBE9E9'><TD align=left valign=top>43.<a href='joblist.cfm?JobID=94 6735&Keyword='>Word Processor<BR>(N-1286)</a></TD><TD align=left valign=top>Lega lstaff.com</TD><TD align=left valign=top>CA - Statewide</TD></TR>
+
+/a[^a]b/
+    acb
+    a\nb
+    
+/a.b/
+    acb
+    *** Failers 
+    a\nb   
+    
+/a[^a]b/s
+    acb
+    a\nb  
+    
+/a.b/s
+    acb
+    a\nb  
+
+/^(b+?|a){1,2}?c/
+    bac
+    bbac
+    bbbac
+    bbbbac
+    bbbbbac 
+
+/^(b+|a){1,2}?c/
+    bac
+    bbac
+    bbbac
+    bbbbac
+    bbbbbac 
+    
+/(?!\A)x/m
+    x\nb\n
+    a\bx\n  
+    
+/\x0{ab}/
+    \0{ab} 
+
+/(A|B)*?CD/
+    CD 
+    
+/(A|B)*CD/
+    CD 
+
+/(?<!bar)foo/
+    foo
+    catfood
+    arfootle
+    rfoosh
+    *** Failers
+    barfoo
+    towbarfoo
+
+/\w{3}(?<!bar)foo/
+    catfood
+    *** Failers
+    foo
+    barfoo
+    towbarfoo
+
+/(?<=(foo)a)bar/
+    fooabar
+    *** Failers
+    bar
+    foobbar
+      
+/\Aabc\z/m
+    abc
+    *** Failers
+    abc\n   
+    qqq\nabc
+    abc\nzzz
+    qqq\nabc\nzzz
+
+"(?>.*/)foo"
+    /this/is/a/very/long/line/in/deed/with/very/many/slashes/in/it/you/see/
+
+"(?>.*/)foo"
+    /this/is/a/very/long/line/in/deed/with/very/many/slashes/in/and/foo
+
+/(?>(\.\d\d[1-9]?))\d+/
+    1.230003938
+    1.875000282
+    *** Failers 
+    1.235 
+
+/^((?>\w+)|(?>\s+))*$/
+    now is the time for all good men to come to the aid of the party
+    *** Failers
+    this is not a line with only words and spaces!
+    
+/(\d+)(\w)/
+    12345a
+    12345+ 
+
+/((?>\d+))(\w)/
+    12345a
+    *** Failers
+    12345+ 
+
+/(?>a+)b/
+    aaab
+
+/((?>a+)b)/
+    aaab
+
+/(?>(a+))b/
+    aaab
+
+/(?>b)+/
+    aaabbbccc
+
+/(?>a+|b+|c+)*c/
+    aaabbbbccccd
+    
+/(a+|b+|c+)*c/
+    aaabbbbccccd
+
+/((?>[^()]+)|\([^()]*\))+/
+    ((abc(ade)ufh()()x
+    
+/\(((?>[^()]+)|\([^()]+\))+\)/ 
+    (abc)
+    (abc(def)xyz)
+    *** Failers
+    ((()aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa   
+
+/a(?-i)b/i
+    ab
+    Ab
+    *** Failers 
+    aB
+    AB
+        
+/(a (?x)b c)d e/
+    a bcd e
+    *** Failers
+    a b cd e
+    abcd e   
+    a bcde 
+ 
+/(a b(?x)c d (?-x)e f)/
+    a bcde f
+    *** Failers
+    abcdef  
+
+/(a(?i)b)c/
+    abc
+    aBc
+    *** Failers
+    abC
+    aBC  
+    Abc
+    ABc
+    ABC
+    AbC
+    
+/a(?i:b)c/
+    abc
+    aBc
+    *** Failers 
+    ABC
+    abC
+    aBC
+    
+/a(?i:b)*c/
+    aBc
+    aBBc
+    *** Failers 
+    aBC
+    aBBC
+    
+/a(?=b(?i)c)\w\wd/
+    abcd
+    abCd
+    *** Failers
+    aBCd
+    abcD     
+    
+/(?s-i:more.*than).*million/i
+    more than million
+    more than MILLION
+    more \n than Million 
+    *** Failers
+    MORE THAN MILLION    
+    more \n than \n million 
+
+/(?:(?s-i)more.*than).*million/i
+    more than million
+    more than MILLION
+    more \n than Million 
+    *** Failers
+    MORE THAN MILLION    
+    more \n than \n million 
+    
+/(?>a(?i)b+)+c/ 
+    abc
+    aBbc
+    aBBc 
+    *** Failers
+    Abc
+    abAb    
+    abbC 
+    
+/(?=a(?i)b)\w\wc/
+    abc
+    aBc
+    *** Failers
+    Ab 
+    abC
+    aBC     
+    
+/(?<=a(?i)b)(\w\w)c/
+    abxxc
+    aBxxc
+    *** Failers
+    Abxxc
+    ABxxc
+    abxxC      
+
+/^(?(?=abc)\w{3}:|\d\d)$/
+    abc:
+    12
+    *** Failers
+    123
+    xyz    
+
+/^(?(?!abc)\d\d|\w{3}:)$/
+    abc:
+    12
+    *** Failers
+    123
+    xyz    
+    
+/(?(?<=foo)bar|cat)/
+    foobar
+    cat
+    fcat
+    focat   
+    *** Failers
+    foocat  
+
+/(?(?<!foo)cat|bar)/
+    foobar
+    cat
+    fcat
+    focat   
+    *** Failers
+    foocat  
+
+/(?>a*)*/
+    a
+    aa
+    aaaa
+    
+/(abc|)+/
+    abc
+    abcabc
+    abcabcabc
+    xyz      
+
+/([a]*)*/
+    a
+    aaaaa 
+ 
+/([ab]*)*/
+    a
+    b
+    ababab
+    aaaabcde
+    bbbb    
+ 
+/([^a]*)*/
+    b
+    bbbb
+    aaa   
+ 
+/([^ab]*)*/
+    cccc
+    abab  
+ 
+/([a]*?)*/
+    a
+    aaaa 
+ 
+/([ab]*?)*/
+    a
+    b
+    abab
+    baba   
+ 
+/([^a]*?)*/
+    b
+    bbbb
+    aaa   
+ 
+/([^ab]*?)*/
+    c
+    cccc
+    baba   
+ 
+/(?>a*)*/
+    a
+    aaabcde 
+ 
+/((?>a*))*/
+    aaaaa
+    aabbaa 
+ 
+/((?>a*?))*/
+    aaaaa
+    aabbaa 
+
+/(?(?=[^a-z]+[a-z])  \d{2}-[a-z]{3}-\d{2}  |  \d{2}-\d{2}-\d{2} ) /x
+    12-sep-98
+    12-09-98
+    *** Failers
+    sep-12-98
+        
+/(?i:saturday|sunday)/
+    saturday
+    sunday
+    Saturday
+    Sunday
+    SATURDAY
+    SUNDAY
+    SunDay
+    
+/(a(?i)bc|BB)x/
+    abcx
+    aBCx
+    bbx
+    BBx
+    *** Failers
+    abcX
+    aBCX
+    bbX
+    BBX               
+
+/^([ab](?i)[cd]|[ef])/
+    ac
+    aC
+    bD
+    elephant
+    Europe 
+    frog
+    France
+    *** Failers
+    Africa     
+
+/^(ab|a(?i)[b-c](?m-i)d|x(?i)y|z)/
+    ab
+    aBd
+    xy
+    xY
+    zebra
+    Zambesi
+    *** Failers
+    aCD  
+    XY  
+
+/(?<=foo\n)^bar/m
+    foo\nbar
+    *** Failers
+    bar
+    baz\nbar   
+
+/(?<=(?<!foo)bar)baz/
+    barbaz
+    barbarbaz 
+    koobarbaz 
+    *** Failers
+    baz
+    foobarbaz 
+
+/The following tests are taken from the Perl 5.005 test suite; some of them/
+/are compatible with 5.004, but I'd rather not have to sort them out./
+
+/abc/
+    abc
+    xabcy
+    ababc
+    *** Failers
+    xbc
+    axc
+    abx
+
+/ab*c/
+    abc
+
+/ab*bc/
+    abc
+    abbc
+    abbbbc
+
+/.{1}/
+    abbbbc
+
+/.{3,4}/
+    abbbbc
+
+/ab{0,}bc/
+    abbbbc
+
+/ab+bc/
+    abbc
+    *** Failers
+    abc
+    abq
+
+/ab+bc/
+    abbbbc
+
+/ab{1,}bc/
+    abbbbc
+
+/ab{1,3}bc/
+    abbbbc
+
+/ab{3,4}bc/
+    abbbbc
+
+/ab{4,5}bc/
+    *** Failers
+    abq
+    abbbbc
+
+/ab?bc/
+    abbc
+    abc
+
+/ab{0,1}bc/
+    abc
+
+/ab?bc/
+
+/ab?c/
+    abc
+
+/ab{0,1}c/
+    abc
+
+/^abc$/
+    abc
+    *** Failers
+    abbbbc
+    abcc
+
+/^abc/
+    abcc
+
+/^abc$/
+
+/abc$/
+    aabc
+    *** Failers
+    aabc
+    aabcd
+
+/^/
+    abc
+
+/$/
+    abc
+
+/a.c/
+    abc
+    axc
+
+/a.*c/
+    axyzc
+
+/a[bc]d/
+    abd
+    *** Failers
+    axyzd
+    abc
+
+/a[b-d]e/
+    ace
+
+/a[b-d]/
+    aac
+
+/a[-b]/
+    a-
+
+/a[b-]/
+    a-
+
+/a]/
+    a]
+
+/a[]]b/
+    a]b
+
+/a[^bc]d/
+    aed
+    *** Failers
+    abd
+    abd
+
+/a[^-b]c/
+    adc
+
+/a[^]b]c/
+    adc
+    *** Failers
+    a-c
+    a]c
+
+/\ba\b/
+    a-
+    -a
+    -a-
+
+/\by\b/
+    *** Failers
+    xy
+    yz
+    xyz
+
+/\Ba\B/
+    *** Failers
+    a-
+    -a
+    -a-
+
+/\By\b/
+    xy
+
+/\by\B/
+    yz
+
+/\By\B/
+    xyz
+
+/\w/
+    a
+
+/\W/
+    -
+    *** Failers
+    -
+    a
+
+/a\sb/
+    a b
+
+/a\Sb/
+    a-b
+    *** Failers
+    a-b
+    a b
+
+/\d/
+    1
+
+/\D/
+    -
+    *** Failers
+    -
+    1
+
+/[\w]/
+    a
+
+/[\W]/
+    -
+    *** Failers
+    -
+    a
+
+/a[\s]b/
+    a b
+
+/a[\S]b/
+    a-b
+    *** Failers
+    a-b
+    a b
+
+/[\d]/
+    1
+
+/[\D]/
+    -
+    *** Failers
+    -
+    1
+
+/ab|cd/
+    abc
+    abcd
+
+/()ef/
+    def
+
+/$b/
+
+/a\(b/
+    a(b
+
+/a\(*b/
+    ab
+    a((b
+
+/a\\b/
+    a\b
+
+/((a))/
+    abc
+
+/(a)b(c)/
+    abc
+
+/a+b+c/
+    aabbabc
+
+/a{1,}b{1,}c/
+    aabbabc
+
+/a.+?c/
+    abcabc
+
+/(a+|b)*/
+    ab
+
+/(a+|b){0,}/
+    ab
+
+/(a+|b)+/
+    ab
+
+/(a+|b){1,}/
+    ab
+
+/(a+|b)?/
+    ab
+
+/(a+|b){0,1}/
+    ab
+
+/[^ab]*/
+    cde
+
+/abc/
+    *** Failers
+    b
+    
+
+/a*/
+    
+
+/([abc])*d/
+    abbbcd
+
+/([abc])*bcd/
+    abcd
+
+/a|b|c|d|e/
+    e
+
+/(a|b|c|d|e)f/
+    ef
+
+/abcd*efg/
+    abcdefg
+
+/ab*/
+    xabyabbbz
+    xayabbbz
+
+/(ab|cd)e/
+    abcde
+
+/[abhgefdc]ij/
+    hij
+
+/^(ab|cd)e/
+
+/(abc|)ef/
+    abcdef
+
+/(a|b)c*d/
+    abcd
+
+/(ab|ab*)bc/
+    abc
+
+/a([bc]*)c*/
+    abc
+
+/a([bc]*)(c*d)/
+    abcd
+
+/a([bc]+)(c*d)/
+    abcd
+
+/a([bc]*)(c+d)/
+    abcd
+
+/a[bcd]*dcdcde/
+    adcdcde
+
+/a[bcd]+dcdcde/
+    *** Failers
+    abcde
+    adcdcde
+
+/(ab|a)b*c/
+    abc
+
+/((a)(b)c)(d)/
+    abcd
+
+/[a-zA-Z_][a-zA-Z0-9_]*/
+    alpha
+
+/^a(bc+|b[eh])g|.h$/
+    abh
+
+/(bc+d$|ef*g.|h?i(j|k))/
+    effgz
+    ij
+    reffgz
+    *** Failers
+    effg
+    bcdd
+
+/((((((((((a))))))))))/
+    a
+
+/(((((((((a)))))))))/
+    a
+
+/multiple words of text/
+    *** Failers
+    aa
+    uh-uh
+
+/multiple words/
+    multiple words, yeah
+
+/(.*)c(.*)/
+    abcde
+
+/\((.*), (.*)\)/
+    (a, b)
+
+/[k]/
+
+/abcd/
+    abcd
+
+/a(bc)d/
+    abcd
+
+/a[-]?c/
+    ac
+
+/abc/i
+    ABC
+    XABCY
+    ABABC
+    *** Failers
+    aaxabxbaxbbx
+    XBC
+    AXC
+    ABX
+
+/ab*c/i
+    ABC
+
+/ab*bc/i
+    ABC
+    ABBC
+
+/ab*?bc/i
+    ABBBBC
+
+/ab{0,}?bc/i
+    ABBBBC
+
+/ab+?bc/i
+    ABBC
+
+/ab+bc/i
+    *** Failers
+    ABC
+    ABQ
+
+/ab{1,}bc/i
+
+/ab+bc/i
+    ABBBBC
+
+/ab{1,}?bc/i
+    ABBBBC
+
+/ab{1,3}?bc/i
+    ABBBBC
+
+/ab{3,4}?bc/i
+    ABBBBC
+
+/ab{4,5}?bc/i
+    *** Failers
+    ABQ
+    ABBBBC
+
+/ab??bc/i
+    ABBC
+    ABC
+
+/ab{0,1}?bc/i
+    ABC
+
+/ab??bc/i
+
+/ab??c/i
+    ABC
+
+/ab{0,1}?c/i
+    ABC
+
+/^abc$/i
+    ABC
+    *** Failers
+    ABBBBC
+    ABCC
+
+/^abc/i
+    ABCC
+
+/^abc$/i
+
+/abc$/i
+    AABC
+
+/^/i
+    ABC
+
+/$/i
+    ABC
+
+/a.c/i
+    ABC
+    AXC
+
+/a.*?c/i
+    AXYZC
+
+/a.*c/i
+    *** Failers
+    AABC
+    AXYZD
+
+/a[bc]d/i
+    ABD
+
+/a[b-d]e/i
+    ACE
+    *** Failers
+    ABC
+    ABD
+
+/a[b-d]/i
+    AAC
+
+/a[-b]/i
+    A-
+
+/a[b-]/i
+    A-
+
+/a]/i
+    A]
+
+/a[]]b/i
+    A]B
+
+/a[^bc]d/i
+    AED
+
+/a[^-b]c/i
+    ADC
+    *** Failers
+    ABD
+    A-C
+
+/a[^]b]c/i
+    ADC
+
+/ab|cd/i
+    ABC
+    ABCD
+
+/()ef/i
+    DEF
+
+/$b/i
+    *** Failers
+    A]C
+    B
+
+/a\(b/i
+    A(B
+
+/a\(*b/i
+    AB
+    A((B
+
+/a\\b/i
+    A\B
+
+/((a))/i
+    ABC
+
+/(a)b(c)/i
+    ABC
+
+/a+b+c/i
+    AABBABC
+
+/a{1,}b{1,}c/i
+    AABBABC
+
+/a.+?c/i
+    ABCABC
+
+/a.*?c/i
+    ABCABC
+
+/a.{0,5}?c/i
+    ABCABC
+
+/(a+|b)*/i
+    AB
+
+/(a+|b){0,}/i
+    AB
+
+/(a+|b)+/i
+    AB
+
+/(a+|b){1,}/i
+    AB
+
+/(a+|b)?/i
+    AB
+
+/(a+|b){0,1}/i
+    AB
+
+/(a+|b){0,1}?/i
+    AB
+
+/[^ab]*/i
+    CDE
+
+/abc/i
+
+/a*/i
+    
+
+/([abc])*d/i
+    ABBBCD
+
+/([abc])*bcd/i
+    ABCD
+
+/a|b|c|d|e/i
+    E
+
+/(a|b|c|d|e)f/i
+    EF
+
+/abcd*efg/i
+    ABCDEFG
+
+/ab*/i
+    XABYABBBZ
+    XAYABBBZ
+
+/(ab|cd)e/i
+    ABCDE
+
+/[abhgefdc]ij/i
+    HIJ
+
+/^(ab|cd)e/i
+    ABCDE
+
+/(abc|)ef/i
+    ABCDEF
+
+/(a|b)c*d/i
+    ABCD
+
+/(ab|ab*)bc/i
+    ABC
+
+/a([bc]*)c*/i
+    ABC
+
+/a([bc]*)(c*d)/i
+    ABCD
+
+/a([bc]+)(c*d)/i
+    ABCD
+
+/a([bc]*)(c+d)/i
+    ABCD
+
+/a[bcd]*dcdcde/i
+    ADCDCDE
+
+/a[bcd]+dcdcde/i
+
+/(ab|a)b*c/i
+    ABC
+
+/((a)(b)c)(d)/i
+    ABCD
+
+/[a-zA-Z_][a-zA-Z0-9_]*/i
+    ALPHA
+
+/^a(bc+|b[eh])g|.h$/i
+    ABH
+
+/(bc+d$|ef*g.|h?i(j|k))/i
+    EFFGZ
+    IJ
+    REFFGZ
+    *** Failers
+    ADCDCDE
+    EFFG
+    BCDD
+
+/((((((((((a))))))))))/i
+    A
+
+/(((((((((a)))))))))/i
+    A
+
+/(?:(?:(?:(?:(?:(?:(?:(?:(?:(a))))))))))/i
+    A
+
+/(?:(?:(?:(?:(?:(?:(?:(?:(?:(a|b|c))))))))))/i
+    C
+
+/multiple words of text/i
+    *** Failers
+    AA
+    UH-UH
+
+/multiple words/i
+    MULTIPLE WORDS, YEAH
+
+/(.*)c(.*)/i
+    ABCDE
+
+/\((.*), (.*)\)/i
+    (A, B)
+
+/[k]/i
+
+/abcd/i
+    ABCD
+
+/a(bc)d/i
+    ABCD
+
+/a[-]?c/i
+    AC
+
+/a(?!b)./
+    abad
+
+/a(?=d)./
+    abad
+
+/a(?=c|d)./
+    abad
+
+/a(?:b|c|d)(.)/
+    ace
+
+/a(?:b|c|d)*(.)/
+    ace
+
+/a(?:b|c|d)+?(.)/
+    ace
+    acdbcdbe
+
+/a(?:b|c|d)+(.)/
+    acdbcdbe
+
+/a(?:b|c|d){2}(.)/
+    acdbcdbe
+
+/a(?:b|c|d){4,5}(.)/
+    acdbcdbe
+
+/a(?:b|c|d){4,5}?(.)/
+    acdbcdbe
+
+/((foo)|(bar))*/
+    foobar
+
+/a(?:b|c|d){6,7}(.)/
+    acdbcdbe
+
+/a(?:b|c|d){6,7}?(.)/
+    acdbcdbe
+
+/a(?:b|c|d){5,6}(.)/
+    acdbcdbe
+
+/a(?:b|c|d){5,6}?(.)/
+    acdbcdbe
+
+/a(?:b|c|d){5,7}(.)/
+    acdbcdbe
+
+/a(?:b|c|d){5,7}?(.)/
+    acdbcdbe
+
+/a(?:b|(c|e){1,2}?|d)+?(.)/
+    ace
+
+/^(.+)?B/
+    AB
+
+/^([^a-z])|(\^)$/
+    .
+
+/^[<>]&/
+    <&OUT
+
+/(?:(f)(o)(o)|(b)(a)(r))*/
+    foobar
+
+/(?<=a)b/
+    ab
+    *** Failers
+    cb
+    b
+
+/(?<!c)b/
+    ab
+    b
+    b
+
+/(?:..)*a/
+    aba
+
+/(?:..)*?a/
+    aba
+
+/^(){3,5}/
+    abc
+
+/^(a+)*ax/
+    aax
+
+/^((a|b)+)*ax/
+    aax
+
+/^((a|bc)+)*ax/
+    aax
+
+/(a|x)*ab/
+    cab
+
+/(a)*ab/
+    cab
+
+/(?:(?i)a)b/
+    ab
+
+/((?i)a)b/
+    ab
+
+/(?:(?i)a)b/
+    Ab
+
+/((?i)a)b/
+    Ab
+
+/(?:(?i)a)b/
+    *** Failers
+    cb
+    aB
+
+/((?i)a)b/
+
+/(?i:a)b/
+    ab
+
+/((?i:a))b/
+    ab
+
+/(?i:a)b/
+    Ab
+
+/((?i:a))b/
+    Ab
+
+/(?i:a)b/
+    *** Failers
+    aB
+    aB
+
+/((?i:a))b/
+
+/(?:(?-i)a)b/i
+    ab
+
+/((?-i)a)b/i
+    ab
+
+/(?:(?-i)a)b/i
+    aB
+
+/((?-i)a)b/i
+    aB
+
+/(?:(?-i)a)b/i
+    *** Failers
+    aB
+    Ab
+
+/((?-i)a)b/i
+
+/(?:(?-i)a)b/i
+    aB
+
+/((?-i)a)b/i
+    aB
+
+/(?:(?-i)a)b/i
+    *** Failers
+    Ab
+    AB
+
+/((?-i)a)b/i
+
+/(?-i:a)b/i
+    ab
+
+/((?-i:a))b/i
+    ab
+
+/(?-i:a)b/i
+    aB
+
+/((?-i:a))b/i
+    aB
+
+/(?-i:a)b/i
+    *** Failers
+    AB
+    Ab
+
+/((?-i:a))b/i
+
+/(?-i:a)b/i
+    aB
+
+/((?-i:a))b/i
+    aB
+
+/(?-i:a)b/i
+    *** Failers
+    Ab
+    AB
+
+/((?-i:a))b/i
+
+/((?-i:a.))b/i
+    *** Failers
+    AB
+    a\nB
+
+/((?s-i:a.))b/i
+    a\nB
+
+/(?:c|d)(?:)(?:a(?:)(?:b)(?:b(?:))(?:b(?:)(?:b)))/
+    cabbbb
+
+/(?:c|d)(?:)(?:aaaaaaaa(?:)(?:bbbbbbbb)(?:bbbbbbbb(?:))(?:bbbbbbbb(?:)(?:bbbbbbbb)))/
+    caaaaaaaabbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbb
+
+/foo\w*\d{4}baz/
+    foobar1234baz
+
+/x(~~)*(?:(?:F)?)?/
+    x~~
+
+/^a(?#xxx){3}c/
+    aaac
+
+/^a (?#xxx) (?#yyy) {3}c/x
+    aaac
+
+/(?<![cd])b/
+    *** Failers
+    B\nB
+    dbcb
+
+/(?<![cd])[ab]/
+    dbaacb
+
+/(?<!(c|d))b/
+
+/(?<!(c|d))[ab]/
+    dbaacb
+
+/(?<!cd)[ab]/
+    cdaccb
+
+/^(?:a?b?)*$/
+    *** Failers
+    dbcb
+    a--
+
+/((?s)^a(.))((?m)^b$)/
+    a\nb\nc\n
+
+/((?m)^b$)/
+    a\nb\nc\n
+
+/(?m)^b/
+    a\nb\n
+
+/(?m)^(b)/
+    a\nb\n
+
+/((?m)^b)/
+    a\nb\n
+
+/\n((?m)^b)/
+    a\nb\n
+
+/((?s).)c(?!.)/
+    a\nb\nc\n
+    a\nb\nc\n
+
+/((?s)b.)c(?!.)/
+    a\nb\nc\n
+    a\nb\nc\n
+
+/^b/
+
+/()^b/
+    *** Failers
+    a\nb\nc\n
+    a\nb\nc\n
+
+/((?m)^b)/
+    a\nb\nc\n
+
+/(?(?!a)a|b)/
+
+/(?(?!a)b|a)/
+    a
+
+/(?(?=a)b|a)/
+    *** Failers
+    a
+    a
+
+/(?(?=a)a|b)/
+    a
+
+/(\w+:)+/
+    one:
+
+/$(?<=^(a))/
+    a
+
+/([\w:]+::)?(\w+)$/
+    abcd
+    xy:z:::abcd
+
+/^[^bcd]*(c+)/
+    aexycd
+
+/(a*)b+/
+    caab
+
+/([\w:]+::)?(\w+)$/
+    abcd
+    xy:z:::abcd
+    *** Failers
+    abcd:
+    abcd:
+
+/^[^bcd]*(c+)/
+    aexycd
+
+/(>a+)ab/
+
+/(?>a+)b/
+    aaab
+
+/([[:]+)/
+    a:[b]:
+
+/([[=]+)/
+    a=[b]=
+
+/([[.]+)/
+    a.[b].
+
+/((?>a+)b)/
+    aaab
+
+/(?>(a+))b/
+    aaab
+
+/((?>[^()]+)|\([^()]*\))+/
+    ((abc(ade)ufh()()x
+
+/a\Z/
+    *** Failers
+    aaab
+    a\nb\n
+
+/b\Z/
+    a\nb\n
+
+/b\z/
+
+/b\Z/
+    a\nb
+
+/b\z/
+    a\nb
+    *** Failers
+    
+/(?>.*)(?<=(abcd|wxyz))/
+    alphabetabcd
+    endingwxyz
+    *** Failers
+    a rather long string that doesn't end with one of them
+
+/word (?>(?:(?!otherword)[a-zA-Z0-9]+ ){0,30})otherword/
+    word cat dog elephant mussel cow horse canary baboon snake shark otherword
+    word cat dog elephant mussel cow horse canary baboon snake shark
+  
+/word (?>[a-zA-Z0-9]+ ){0,30}otherword/
+    word cat dog elephant mussel cow horse canary baboon snake shark the quick brown fox and the lazy dog and several other words getting close to thirty by now I hope
+
+/(?<=\d{3}(?!999))foo/
+    999foo
+    123999foo 
+    *** Failers
+    123abcfoo
+    
+/(?<=(?!...999)\d{3})foo/
+    999foo
+    123999foo 
+    *** Failers
+    123abcfoo
+
+/(?<=\d{3}(?!999)...)foo/
+    123abcfoo
+    123456foo 
+    *** Failers
+    123999foo  
+    
+/(?<=\d{3}...)(?<!999)foo/
+    123abcfoo   
+    123456foo 
+    *** Failers
+    123999foo  
+
+/((Z)+|A)*/
+    ZABCDEFG
+
+/(Z()|A)*/
+    ZABCDEFG
+
+/(Z(())|A)*/
+    ZABCDEFG
+
+/((?>Z)+|A)*/
+    ZABCDEFG
+
+/((?>)+|A)*/
+    ZABCDEFG
+
+/a*/g
+    abbab
+
+/^[a-\d]/
+    abcde
+    -things
+    0digit
+    *** Failers
+    bcdef    
+
+/^[\d-a]/
+    abcde
+    -things
+    0digit
+    *** Failers
+    bcdef    
+    
+/[[:space:]]+/
+    > \x09\x0a\x0c\x0d\x0b<
+     
+/[[:blank:]]+/
+    > \x09\x0a\x0c\x0d\x0b<
+     
+/[\s]+/
+    > \x09\x0a\x0c\x0d\x0b<
+     
+/\s+/
+    > \x09\x0a\x0c\x0d\x0b<
+     
+/ab/x
+    ab
+
+/(?!\A)x/m
+  a\nxb\n
+
+/(?!^)x/m
+  a\nxb\n
+
+/abc\Qabc\Eabc/
+    abcabcabc
+    
+/abc\Q(*+|\Eabc/
+    abc(*+|abc 
+
+/   abc\Q abc\Eabc/x
+    abc abcabc
+    *** Failers
+    abcabcabc  
+    
+/abc#comment
+    \Q#not comment
+    literal\E/x
+    abc#not comment\n    literal     
+
+/abc#comment
+    \Q#not comment
+    literal/x
+    abc#not comment\n    literal     
+
+/abc#comment
+    \Q#not comment
+    literal\E #more comment
+    /x
+    abc#not comment\n    literal     
+
+/abc#comment
+    \Q#not comment
+    literal\E #more comment/x
+    abc#not comment\n    literal     
+
+/\Qabc\$xyz\E/
+    abc\\\$xyz
+
+/\Qabc\E\$\Qxyz\E/
+    abc\$xyz
+
+/\Gabc/
+    abc
+    *** Failers
+    xyzabc  
+
+/\Gabc./g
+    abc1abc2xyzabc3
+
+/abc./g
+    abc1abc2xyzabc3 
+
+/a(?x: b c )d/
+    XabcdY
+    *** Failers 
+    Xa b c d Y 
+
+/((?x)x y z | a b c)/
+    XabcY
+    AxyzB 
+
+/(?i)AB(?-i)C/
+    XabCY
+    *** Failers
+    XabcY  
+
+/((?i)AB(?-i)C|D)E/
+    abCE
+    DE
+    *** Failers
+    abcE
+    abCe  
+    dE
+    De    
+
+/[z\Qa-d]\E]/
+    z
+    a
+    -
+    d
+    ] 
+    *** Failers
+    b     
+
+/[\z\C]/
+    z
+    C 
+    
+/\M/
+    M 
+    
+/(a+)*b/
+    aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa 
+    
+/(?i)reg(?:ul(?:[aä]|ae)r|ex)/
+    REGular
+    regulaer
+    Regex  
+    regulär 
+
+/Åæåä[à-ÿÀ-ß]+/
+    Åæåäà
+    Åæåäÿ
+    ÅæåäÀ
+    Åæåäß
+
+/(?<=Z)X./
+    \x84XAZXB
+
+/^(?(2)a|(1)(2))+$/
+    123a
+
+/(?<=a|bbbb)c/
+    ac
+    bbbbc
+
+/abc/SS>testsavedregex
+<testsavedregex
+    abc
+    *** Failers
+    bca
+    
+/abc/FSS>testsavedregex
+<testsavedregex
+    abc
+    *** Failers
+    bca
+
+/(a|b)/S>testsavedregex
+<testsavedregex
+    abc
+    *** Failers
+    def  
+    
+/(a|b)/SF>testsavedregex
+<testsavedregex
+    abc
+    *** Failers
+    def  
+    
+/line\nbreak/
+    this is a line\nbreak
+    line one\nthis is a line\nbreak in the second line 
+
+/line\nbreak/f
+    this is a line\nbreak
+    ** Failers 
+    line one\nthis is a line\nbreak in the second line 
+
+/line\nbreak/mf
+    this is a line\nbreak
+    ** Failers 
+    line one\nthis is a line\nbreak in the second line 
+
+/1234/
+    123\P
+    a4\P\R
+
+/1234/
+    123\P
+    4\P\R
+
+/^/mg
+    a\nb\nc\n
+    \ 
+    
+/(?<=C\n)^/mg
+    A\nC\nC\n 
+
+/(?s)A?B/
+    AB
+    aB  
+
+/(?s)A*B/
+    AB
+    aB  
+
+/(?m)A?B/
+    AB
+    aB  
+
+/(?m)A*B/
+    AB
+    aB  
+
+/Content-Type\x3A[^\r\n]{6,}/
+    Content-Type:xxxxxyyy 
+
+/Content-Type\x3A[^\r\n]{6,}z/
+    Content-Type:xxxxxyyyz
+
+/Content-Type\x3A[^a]{6,}/
+    Content-Type:xxxyyy 
+
+/Content-Type\x3A[^a]{6,}z/
+    Content-Type:xxxyyyz
+
+/^abc/m
+    xyz\nabc
+    xyz\nabc\<lf>
+    xyz\r\nabc\<lf>
+    xyz\rabc\<cr>
+    xyz\r\nabc\<crlf>
+    ** Failers 
+    xyz\nabc\<cr>
+    xyz\r\nabc\<cr>
+    xyz\nabc\<crlf>
+    xyz\rabc\<crlf>
+    xyz\rabc\<lf>
+    
+/abc$/m<lf>
+    xyzabc
+    xyzabc\n 
+    xyzabc\npqr 
+    xyzabc\r\<cr> 
+    xyzabc\rpqr\<cr> 
+    xyzabc\r\n\<crlf> 
+    xyzabc\r\npqr\<crlf> 
+    ** Failers
+    xyzabc\r 
+    xyzabc\rpqr 
+    xyzabc\r\n 
+    xyzabc\r\npqr 
+    
+/^abc/m<cr>
+    xyz\rabcdef
+    xyz\nabcdef\<lf>
+    ** Failers  
+    xyz\nabcdef
+       
+/^abc/m<lf>
+    xyz\nabcdef
+    xyz\rabcdef\<cr>
+    ** Failers  
+    xyz\rabcdef
+       
+/^abc/m<crlf>
+    xyz\r\nabcdef
+    xyz\rabcdef\<cr>
+    ** Failers  
+    xyz\rabcdef
+    
+/.*/<lf>
+    abc\ndef
+    abc\rdef
+    abc\r\ndef
+    \<cr>abc\ndef
+    \<cr>abc\rdef
+    \<cr>abc\r\ndef
+    \<crlf>abc\ndef
+    \<crlf>abc\rdef
+    \<crlf>abc\r\ndef
+
+/\w+(.)(.)?def/s
+    abc\ndef
+    abc\rdef
+    abc\r\ndef
+
+/^\w+=.*(\\\n.*)*/
+    abc=xyz\\\npqr
+
+/^(a()*)*/
+    aaaa
+
+/^(?:a(?:(?:))*)*/
+    aaaa
+
+/^(a()+)+/
+    aaaa
+
+/^(?:a(?:(?:))+)+/
+    aaaa
+
+/(a|)*\d/
+  aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+  aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa4
+
+/(?>a|)*\d/
+  aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+  aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa4
+
+/(?:a|)*\d/
+  aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+  aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa4
+
+/^a.b/<lf>
+    a\rb
+    a\nb\<cr> 
+    ** Failers
+    a\nb
+    a\nb\<any>
+    a\rb\<cr>   
+    a\rb\<any>   
+
+/^abc./mgx<any>
+    abc1 \x0aabc2 \x0babc3xx \x0cabc4 \x0dabc5xx \x0d\x0aabc6 \x85abc7 JUNK
+
+/abc.$/mgx<any>
+    abc1\x0a abc2\x0b abc3\x0c abc4\x0d abc5\x0d\x0a abc6\x85 abc9
+
+/^a\Rb/<bsr_unicode>
+    a\nb
+    a\rb
+    a\r\nb
+    a\x0bb
+    a\x0cb
+    a\x85b   
+    ** Failers
+    a\n\rb    
+
+/^a\R*b/<bsr_unicode>
+    ab
+    a\nb
+    a\rb
+    a\r\nb
+    a\x0bb
+    a\x0cb
+    a\x85b   
+    a\n\rb    
+    a\n\r\x85\x0cb 
+
+/^a\R+b/<bsr_unicode>
+    a\nb
+    a\rb
+    a\r\nb
+    a\x0bb
+    a\x0cb
+    a\x85b   
+    a\n\rb    
+    a\n\r\x85\x0cb 
+    ** Failers
+    ab  
+    
+/^a\R{1,3}b/<bsr_unicode>
+    a\nb
+    a\n\rb
+    a\n\r\x85b
+    a\r\n\r\nb 
+    a\r\n\r\n\r\nb 
+    a\n\r\n\rb
+    a\n\n\r\nb 
+    ** Failers
+    a\n\n\n\rb
+    a\r
+
+/^a[\R]b/<bsr_unicode>
+    aRb
+    ** Failers
+    a\nb  
+
+/.+foo/
+    afoo
+    ** Failers 
+    \r\nfoo 
+    \nfoo 
+
+/.+foo/<crlf>
+    afoo
+    \nfoo 
+    ** Failers 
+    \r\nfoo 
+
+/.+foo/<any>
+    afoo
+    ** Failers 
+    \nfoo 
+    \r\nfoo 
+
+/.+foo/s
+    afoo
+    \r\nfoo 
+    \nfoo 
+
+/^$/mg<any>
+    abc\r\rxyz
+    abc\n\rxyz  
+    ** Failers 
+    abc\r\nxyz
+
+/^X/m
+    XABC
+    ** Failers 
+    XABC\B
+
+/(?m)^$/<any>g+
+    abc\r\n\r\n
+
+/(?m)^$|^\r\n/<any>g+ 
+    abc\r\n\r\n
+    
+/(?m)$/<any>g+ 
+    abc\r\n\r\n
+
+/(?|(abc)|(xyz))/
+   >abc<
+   >xyz< 
+
+/(x)(?|(abc)|(xyz))(x)/
+    xabcx
+    xxyzx 
+
+/(x)(?|(abc)(pqr)|(xyz))(x)/
+    xabcpqrx
+    xxyzx 
+
+/(?|(abc)|(xyz))(?1)/
+    abcabc
+    xyzabc 
+    ** Failers 
+    xyzxyz 
+ 
+/\H\h\V\v/
+    X X\x0a
+    X\x09X\x0b
+    ** Failers
+    \xa0 X\x0a   
+    
+/\H*\h+\V?\v{3,4}/ 
+    \x09\x20\xa0X\x0a\x0b\x0c\x0d\x0a
+    \x09\x20\xa0\x0a\x0b\x0c\x0d\x0a
+    \x09\x20\xa0\x0a\x0b\x0c
+    ** Failers 
+    \x09\x20\xa0\x0a\x0b
+     
+/\H{3,4}/
+    XY  ABCDE
+    XY  PQR ST 
+    
+/.\h{3,4}./
+    XY  AB    PQRS
+
+/\h*X\h?\H+Y\H?Z/
+    >XNNNYZ
+    >  X NYQZ
+    ** Failers
+    >XYZ   
+    >  X NY Z
+
+/\v*X\v?Y\v+Z\V*\x0a\V+\x0b\V{2,3}\x0c/
+    >XY\x0aZ\x0aA\x0bNN\x0c
+    >\x0a\x0dX\x0aY\x0a\x0bZZZ\x0aAAA\x0bNNN\x0c
+
+/.+A/<crlf>
+    \r\nA
+    
+/\nA/<crlf>
+    \r\nA 
+
+/[\r\n]A/<crlf>
+    \r\nA 
+
+/(\r|\n)A/<crlf>
+    \r\nA 
+
+/a\Rb/I<bsr_anycrlf>
+    a\rb
+    a\nb
+    a\r\nb
+    ** Failers
+    a\x85b
+    a\x0bb     
+
+/a\Rb/I<bsr_unicode>
+    a\rb
+    a\nb
+    a\r\nb
+    a\x85b
+    a\x0bb     
+    ** Failers 
+    a\x85b\<bsr_anycrlf>
+    a\x0bb\<bsr_anycrlf>
+    
+/a\R?b/I<bsr_anycrlf>
+    a\rb
+    a\nb
+    a\r\nb
+    ** Failers
+    a\x85b
+    a\x0bb     
+
+/a\R?b/I<bsr_unicode>
+    a\rb
+    a\nb
+    a\r\nb
+    a\x85b
+    a\x0bb     
+    ** Failers 
+    a\x85b\<bsr_anycrlf>
+    a\x0bb\<bsr_anycrlf>
+    
+/a\R{2,4}b/I<bsr_anycrlf>
+    a\r\n\nb
+    a\n\r\rb
+    a\r\n\r\n\r\n\r\nb
+    ** Failers
+    a\x85\85b
+    a\x0b\0bb     
+
+/a\R{2,4}b/I<bsr_unicode>
+    a\r\rb
+    a\n\n\nb
+    a\r\n\n\r\rb
+    a\x85\85b
+    a\x0b\0bb     
+    ** Failers 
+    a\r\r\r\r\rb 
+    a\x85\85b\<bsr_anycrlf>
+    a\x0b\0bb\<bsr_anycrlf>
+    
+/a(?!)|\wbc/
+    abc 
+
+/a[]b/<JS>
+    ** Failers
+    ab
+
+/a[]+b/<JS>
+    ** Failers
+    ab 
+
+/a[]*+b/<JS>
+    ** Failers
+    ab 
+
+/a[^]b/<JS>
+    aXb
+    a\nb 
+    ** Failers
+    ab  
+    
+/a[^]+b/<JS> 
+    aXb
+    a\nX\nXb 
+    ** Failers
+    ab  
+
+/X$/E
+    X
+    ** Failers 
+    X\n 
+
+/X$/
+    X
+    X\n 
+
+/xyz/C
+  xyz 
+  abcxyz 
+  abcxyz\Y
+  ** Failers 
+  abc
+  abc\Y
+  abcxypqr  
+  abcxypqr\Y  
+
+/(*NO_START_OPT)xyz/C
+  abcxyz 
+  
+/(?C)ab/
+  ab
+  \C-ab
+  
+/ab/C
+  ab
+  \C-ab    
+
+/^"((?(?=[a])[^"])|b)*"$/C
+    "ab"
+    \C-"ab"
+
+/\d+X|9+Y/
+    ++++123999\P
+    ++++123999Y\P
+
+/Z(*F)/
+    Z\P
+    ZA\P 
+    
+/Z(?!)/
+    Z\P 
+    ZA\P 
+
+/dog(sbody)?/
+    dogs\P
+    dogs\P\P 
+    
+/dog(sbody)??/
+    dogs\P
+    dogs\P\P 
+
+/dog|dogsbody/
+    dogs\P
+    dogs\P\P 
+ 
+/dogsbody|dog/
+    dogs\P
+    dogs\P\P 
+
+/Z(*F)Q|ZXY/
+    Z\P
+    ZA\P 
+    X\P 
+
+/\bthe cat\b/
+    the cat\P
+    the cat\P\P
+
+/dog(sbody)?/
+    dogs\D\P
+    body\D\R
+
+/dog(sbody)?/
+    dogs\D\P\P
+    body\D\R
+
+/abc/
+   abc\P
+   abc\P\P
+
+/abc\K123/
+    xyzabc123pqr
+    
+/(?<=abc)123/
+    xyzabc123pqr 
+    xyzabc12\P
+    xyzabc12\P\P
+
+/\babc\b/
+    +++abc+++
+    +++ab\P
+    +++ab\P\P  
+
+/(?=C)/g+
+    ABCDECBA
+
+/(abc|def|xyz)/I
+    terhjk;abcdaadsfe
+    the quick xyz brown fox 
+    \Yterhjk;abcdaadsfe
+    \Ythe quick xyz brown fox 
+    ** Failers
+    thejk;adlfj aenjl;fda asdfasd ehj;kjxyasiupd
+    \Ythejk;adlfj aenjl;fda asdfasd ehj;kjxyasiupd
+
+/(abc|def|xyz)/SI
+    terhjk;abcdaadsfe
+    the quick xyz brown fox 
+    \Yterhjk;abcdaadsfe
+    \Ythe quick xyz brown fox 
+    ** Failers
+    thejk;adlfj aenjl;fda asdfasd ehj;kjxyasiupd
+    \Ythejk;adlfj aenjl;fda asdfasd ehj;kjxyasiupd
+
+/abcd*/+
+    xxxxabcd\P
+    xxxxabcd\P\P
+    dddxxx\R 
+    xxxxabcd\P\P
+    xxx\R 
+
+/abcd*/i
+    xxxxabcd\P
+    xxxxabcd\P\P
+    XXXXABCD\P
+    XXXXABCD\P\P
+
+/abc\d*/
+    xxxxabc1\P
+    xxxxabc1\P\P
+
+/abc[de]*/
+    xxxxabcde\P
+    xxxxabcde\P\P
+
+/(?:(?1)|B)(A(*F)|C)/
+    ABCD
+    CCD
+    ** Failers
+    CAD   
+
+/^(?:(?1)|B)(A(*F)|C)/
+    CCD
+    BCD 
+    ** Failers
+    ABCD
+    CAD
+    BAD    
+
+/^(?!a(*SKIP)b)/
+    ac
+    
+/^(?=a(*SKIP)b|ac)/
+    ** Failers
+    ac
+    
+/^(?=a(*THEN)b|ac)/
+    ac
+    
+/^(?=a(*PRUNE)b)/
+    ab  
+    ** Failers 
+    ac
+
+/^(?(?!a(*SKIP)b))/
+    ac
+
+/(?<=abc)def/
+    abc\P\P
+
+/abc$/
+    abc
+    abc\P
+    abc\P\P
+
+/abc$/m
+    abc
+    abc\n
+    abc\P\P
+    abc\n\P\P 
+    abc\P
+    abc\n\P
+
+/abc\z/
+    abc
+    abc\P
+    abc\P\P
+
+/abc\Z/
+    abc
+    abc\P
+    abc\P\P
+
+/abc\b/
+    abc
+    abc\P
+    abc\P\P
+
+/abc\B/
+    abc
+    abc\P
+    abc\P\P
+
+/.+/
+    abc\>0
+    abc\>1
+    abc\>2
+    abc\>3
+    abc\>4
+    abc\>-4 
+
+/^(?:a)++\w/
+     aaaab
+     ** Failers 
+     aaaa 
+     bbb 
+
+/^(?:aa|(?:a)++\w)/
+     aaaab
+     aaaa 
+     ** Failers 
+     bbb 
+
+/^(?:a)*+\w/
+     aaaab
+     bbb 
+     ** Failers 
+     aaaa 
+
+/^(a)++\w/
+     aaaab
+     ** Failers 
+     aaaa 
+     bbb 
+
+/^(a|)++\w/
+     aaaab
+     ** Failers 
+     aaaa 
+     bbb 
+
+/(?=abc){3}abc/+
+    abcabcabc
+    ** Failers
+    xyz  
+    
+/(?=abc)+abc/+
+    abcabcabc
+    ** Failers
+    xyz  
+    
+/(?=abc)++abc/+
+    abcabcabc
+    ** Failers
+    xyz  
+    
+/(?=abc){0}xyz/
+    xyz 
+
+/(?=abc){1}xyz/
+    ** Failers
+    xyz 
+    
+/(?=(a))?./
+    ab
+    bc
+      
+/(?=(a))??./
+    ab
+    bc
+
+/^(?=(a)){0}b(?1)/
+    backgammon
+
+/^(?=(?1))?[az]([abc])d/
+    abd 
+    zcdxx 
+
+/^(?!a){0}\w+/
+    aaaaa
+
+/(?<=(abc))?xyz/
+    abcxyz
+    pqrxyz 
+
+/((?2))((?1))/
+    abc
+
+/(?(R)a+|(?R)b)/
+    aaaabcde
+
+/(?(R)a+|((?R))b)/
+    aaaabcde
+
+/((?(R)a+|(?1)b))/
+    aaaabcde
+
+/((?(R2)a+|(?1)b))/
+    aaaabcde
+
+/(?(R)a*(?1)|((?R))b)/
+    aaaabcde
+
+/(a+)/
+    \O6aaaa
+    \O8aaaa
+
+/ab\Cde/
+    abXde
+    
+/(?<=ab\Cde)X/
+    abZdeX
+
+/^\R/
+    \r\P
+    \r\P\P
+    
+/^\R{2,3}x/
+    \r\P
+    \r\P\P
+    \r\r\P 
+    \r\r\P\P
+    \r\r\r\P  
+    \r\r\r\P\P
+    \r\rx
+    \r\r\rx    
+
+/^\R{2,3}?x/
+    \r\P
+    \r\P\P
+    \r\r\P 
+    \r\r\P\P
+    \r\r\r\P  
+    \r\r\r\P\P
+    \r\rx
+    \r\r\rx    
+    
+/^\R?x/
+    \r\P
+    \r\P\P 
+    x
+    \rx  
+
+/^\R+x/
+    \r\P
+    \r\P\P 
+    \r\n\P
+    \r\n\P\P  
+    \rx  
+
+/^a$/<CRLF>
+    a\r\P
+    a\r\P\P 
+
+/^a$/m<CRLF>
+    a\r\P
+    a\r\P\P 
+
+/^(a$|a\r)/<CRLF>
+    a\r\P
+    a\r\P\P 
+
+/^(a$|a\r)/m<CRLF>
+    a\r\P
+    a\r\P\P 
+
+/./<CRLF>
+    \r\P
+    \r\P\P 
+  
+/.{2,3}/<CRLF>
+    \r\P 
+    \r\P\P
+    \r\r\P
+    \r\r\P\P
+    \r\r\r\P
+    \r\r\r\P\P     
+
+/.{2,3}?/<CRLF>
+    \r\P 
+    \r\P\P
+    \r\r\P
+    \r\r\P\P
+    \r\r\r\P
+    \r\r\r\P\P     
+
+/-- Test simple validity check for restarts --/
+
+/abcdef/
+   abc\R
+
+/<H((?(?!<H|F>)(.)|(?R))++)*F>/
+    text <H more text <H texting more  hexA0-"\xA0"    hex above 7F-"\xBC" F> text xxxxx <H text F> text F> text2 <H text sample F> more text.
+
+/^(?>.{4})abc|^\w\w.xabcd/
+    xxxxabcd
+    xx\xa0xabcd 
+
+/^(.{4}){2}+abc|^\w\w.x\w\w\w\wabcd/
+    xxxxxxxxabcd
+    xx\xa0xxxxxabcd 
+
+/-- End of testinput8 --/
diff --git a/ext/pcre/pcrelib/testdata/testinput9 b/ext/pcre/pcrelib/testdata/testinput9
new file mode 100644
index 0000000..766c9c0
--- /dev/null
+++ b/ext/pcre/pcrelib/testdata/testinput9
@@ -0,0 +1,717 @@
+/-- This set of tests checks UTF-8 support with the DFA matching functionality
+    of pcre_dfa_exec(). The -dfa flag must be used with pcretest when running 
+    it. --/
+
+/\x{100}ab/8
+  \x{100}ab
+  
+/a\x{100}*b/8
+    ab
+    a\x{100}b  
+    a\x{100}\x{100}b  
+    
+/a\x{100}+b/8
+    a\x{100}b  
+    a\x{100}\x{100}b  
+    *** Failers 
+    ab
+     
+/\bX/8
+    Xoanon
+    +Xoanon
+    \x{300}Xoanon 
+    *** Failers 
+    YXoanon  
+    
+/\BX/8
+    YXoanon
+    *** Failers
+    Xoanon
+    +Xoanon    
+    \x{300}Xoanon 
+
+/X\b/8
+    X+oanon
+    ZX\x{300}oanon 
+    FAX 
+    *** Failers 
+    Xoanon  
+    
+/X\B/8
+    Xoanon  
+    *** Failers
+    X+oanon
+    ZX\x{300}oanon 
+    FAX 
+    
+/[^a]/8
+    abcd
+    a\x{100}   
+
+/^[abc\x{123}\x{400}-\x{402}]{2,3}\d/8
+    ab99
+    \x{123}\x{123}45
+    \x{400}\x{401}\x{402}6  
+    *** Failers
+    d99
+    \x{123}\x{122}4   
+    \x{400}\x{403}6  
+    \x{400}\x{401}\x{402}\x{402}6  
+
+/a.b/8
+    acb
+    a\x7fb
+    a\x{100}b 
+    *** Failers
+    a\nb  
+
+/a(.{3})b/8
+    a\x{4000}xyb 
+    a\x{4000}\x7fyb 
+    a\x{4000}\x{100}yb 
+    *** Failers
+    a\x{4000}b 
+    ac\ncb 
+
+/a(.*?)(.)/
+    a\xc0\x88b
+
+/a(.*?)(.)/8
+    a\x{100}b
+
+/a(.*)(.)/
+    a\xc0\x88b
+
+/a(.*)(.)/8
+    a\x{100}b
+
+/a(.)(.)/
+    a\xc0\x92bcd
+
+/a(.)(.)/8
+    a\x{240}bcd
+
+/a(.?)(.)/
+    a\xc0\x92bcd
+
+/a(.?)(.)/8
+    a\x{240}bcd
+
+/a(.??)(.)/
+    a\xc0\x92bcd
+
+/a(.??)(.)/8
+    a\x{240}bcd
+
+/a(.{3})b/8
+    a\x{1234}xyb 
+    a\x{1234}\x{4321}yb 
+    a\x{1234}\x{4321}\x{3412}b 
+    *** Failers
+    a\x{1234}b 
+    ac\ncb 
+
+/a(.{3,})b/8
+    a\x{1234}xyb 
+    a\x{1234}\x{4321}yb 
+    a\x{1234}\x{4321}\x{3412}b 
+    axxxxbcdefghijb 
+    a\x{1234}\x{4321}\x{3412}\x{3421}b 
+    *** Failers
+    a\x{1234}b 
+
+/a(.{3,}?)b/8
+    a\x{1234}xyb 
+    a\x{1234}\x{4321}yb 
+    a\x{1234}\x{4321}\x{3412}b 
+    axxxxbcdefghijb 
+    a\x{1234}\x{4321}\x{3412}\x{3421}b 
+    *** Failers
+    a\x{1234}b 
+
+/a(.{3,5})b/8
+    a\x{1234}xyb 
+    a\x{1234}\x{4321}yb 
+    a\x{1234}\x{4321}\x{3412}b 
+    axxxxbcdefghijb 
+    a\x{1234}\x{4321}\x{3412}\x{3421}b 
+    axbxxbcdefghijb 
+    axxxxxbcdefghijb 
+    *** Failers
+    a\x{1234}b 
+    axxxxxxbcdefghijb 
+
+/a(.{3,5}?)b/8
+    a\x{1234}xyb 
+    a\x{1234}\x{4321}yb 
+    a\x{1234}\x{4321}\x{3412}b 
+    axxxxbcdefghijb 
+    a\x{1234}\x{4321}\x{3412}\x{3421}b 
+    axbxxbcdefghijb 
+    axxxxxbcdefghijb 
+    *** Failers
+    a\x{1234}b 
+    axxxxxxbcdefghijb 
+
+/^[a\x{c0}]/8
+    *** Failers
+    \x{100}
+
+/(?<=aXb)cd/8
+    aXbcd
+
+/(?<=a\x{100}b)cd/8
+    a\x{100}bcd
+
+/(?<=a\x{100000}b)cd/8
+    a\x{100000}bcd
+    
+/(?:\x{100}){3}b/8
+    \x{100}\x{100}\x{100}b
+    *** Failers 
+    \x{100}\x{100}b
+
+/\x{ab}/8
+    \x{ab} 
+    \xc2\xab
+    *** Failers 
+    \x00{ab}
+
+/(?<=(.))X/8
+    WXYZ
+    \x{256}XYZ 
+    *** Failers
+    XYZ 
+
+/[^a]+/8g
+    bcd
+    \x{100}aY\x{256}Z 
+    
+/^[^a]{2}/8
+    \x{100}bc
+ 
+/^[^a]{2,}/8
+    \x{100}bcAa
+
+/^[^a]{2,}?/8
+    \x{100}bca
+
+/[^a]+/8ig
+    bcd
+    \x{100}aY\x{256}Z 
+    
+/^[^a]{2}/8i
+    \x{100}bc
+ 
+/^[^a]{2,}/8i
+    \x{100}bcAa
+
+/^[^a]{2,}?/8i
+    \x{100}bca
+
+/\x{100}{0,0}/8
+    abcd
+ 
+/\x{100}?/8
+    abcd
+    \x{100}\x{100} 
+
+/\x{100}{0,3}/8 
+    \x{100}\x{100} 
+    \x{100}\x{100}\x{100}\x{100} 
+    
+/\x{100}*/8
+    abce
+    \x{100}\x{100}\x{100}\x{100} 
+
+/\x{100}{1,1}/8
+    abcd\x{100}\x{100}\x{100}\x{100} 
+
+/\x{100}{1,3}/8
+    abcd\x{100}\x{100}\x{100}\x{100} 
+
+/\x{100}+/8
+    abcd\x{100}\x{100}\x{100}\x{100} 
+
+/\x{100}{3}/8
+    abcd\x{100}\x{100}\x{100}XX
+
+/\x{100}{3,5}/8
+    abcd\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}XX
+
+/\x{100}{3,}/8
+    abcd\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}XX
+
+/(?<=a\x{100}{2}b)X/8
+    Xyyya\x{100}\x{100}bXzzz
+
+/\D*/8
+  aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+
+/\D*/8
+  \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}
+
+/\D/8
+    1X2
+    1\x{100}2 
+  
+/>\S/8
+    > >X Y
+    > >\x{100} Y
+  
+/\d/8
+    \x{100}3
+    
+/\s/8
+    \x{100} X
+    
+/\D+/8
+    12abcd34
+    *** Failers
+    1234  
+
+/\D{2,3}/8
+    12abcd34
+    12ab34
+    *** Failers  
+    1234
+    12a34  
+
+/\D{2,3}?/8
+    12abcd34
+    12ab34
+    *** Failers  
+    1234
+    12a34  
+
+/\d+/8
+    12abcd34
+    *** Failers
+
+/\d{2,3}/8
+    12abcd34
+    1234abcd
+    *** Failers  
+    1.4 
+
+/\d{2,3}?/8
+    12abcd34
+    1234abcd
+    *** Failers  
+    1.4 
+
+/\S+/8
+    12abcd34
+    *** Failers
+    \    \ 
+
+/\S{2,3}/8
+    12abcd34
+    1234abcd
+    *** Failers
+    \     \  
+
+/\S{2,3}?/8
+    12abcd34
+    1234abcd
+    *** Failers
+    \     \  
+
+/>\s+</8
+    12>      <34
+    *** Failers
+
+/>\s{2,3}</8
+    ab>  <cd
+    ab>   <ce
+    *** Failers
+    ab>    <cd 
+
+/>\s{2,3}?</8
+    ab>  <cd
+    ab>   <ce
+    *** Failers
+    ab>    <cd 
+
+/\w+/8
+    12      34
+    *** Failers
+    +++=*! 
+
+/\w{2,3}/8
+    ab  cd
+    abcd ce
+    *** Failers
+    a.b.c
+
+/\w{2,3}?/8
+    ab  cd
+    abcd ce
+    *** Failers
+    a.b.c
+
+/\W+/8
+    12====34
+    *** Failers
+    abcd 
+
+/\W{2,3}/8
+    ab====cd
+    ab==cd
+    *** Failers
+    a.b.c
+
+/\W{2,3}?/8
+    ab====cd
+    ab==cd
+    *** Failers
+    a.b.c
+
+/[\x{100}]/8
+    \x{100}
+    Z\x{100}
+    \x{100}Z
+    *** Failers 
+
+/[Z\x{100}]/8
+    Z\x{100}
+    \x{100}
+    \x{100}Z
+    *** Failers 
+
+/[\x{100}\x{200}]/8
+   ab\x{100}cd
+   ab\x{200}cd
+   *** Failers  
+
+/[\x{100}-\x{200}]/8
+   ab\x{100}cd
+   ab\x{200}cd
+   ab\x{111}cd 
+   *** Failers  
+
+/[z-\x{200}]/8
+   ab\x{100}cd
+   ab\x{200}cd
+   ab\x{111}cd 
+   abzcd
+   ab|cd  
+   *** Failers  
+
+/[Q\x{100}\x{200}]/8
+   ab\x{100}cd
+   ab\x{200}cd
+   Q? 
+   *** Failers  
+
+/[Q\x{100}-\x{200}]/8
+   ab\x{100}cd
+   ab\x{200}cd
+   ab\x{111}cd 
+   Q? 
+   *** Failers  
+
+/[Qz-\x{200}]/8
+   ab\x{100}cd
+   ab\x{200}cd
+   ab\x{111}cd 
+   abzcd
+   ab|cd  
+   Q? 
+   *** Failers  
+
+/[\x{100}\x{200}]{1,3}/8
+   ab\x{100}cd
+   ab\x{200}cd
+   ab\x{200}\x{100}\x{200}\x{100}cd
+   *** Failers  
+
+/[\x{100}\x{200}]{1,3}?/8
+   ab\x{100}cd
+   ab\x{200}cd
+   ab\x{200}\x{100}\x{200}\x{100}cd
+   *** Failers  
+
+/[Q\x{100}\x{200}]{1,3}/8
+   ab\x{100}cd
+   ab\x{200}cd
+   ab\x{200}\x{100}\x{200}\x{100}cd
+   *** Failers  
+
+/[Q\x{100}\x{200}]{1,3}?/8
+   ab\x{100}cd
+   ab\x{200}cd
+   ab\x{200}\x{100}\x{200}\x{100}cd
+   *** Failers  
+
+/(?<=[\x{100}\x{200}])X/8
+    abc\x{200}X
+    abc\x{100}X 
+    *** Failers
+    X  
+
+/(?<=[Q\x{100}\x{200}])X/8
+    abc\x{200}X
+    abc\x{100}X 
+    abQX 
+    *** Failers
+    X  
+
+/(?<=[\x{100}\x{200}]{3})X/8
+    abc\x{100}\x{200}\x{100}X
+    *** Failers
+    abc\x{200}X
+    X  
+
+/[^\x{100}\x{200}]X/8
+    AX
+    \x{150}X
+    \x{500}X 
+    *** Failers
+    \x{100}X
+    \x{200}X   
+
+/[^Q\x{100}\x{200}]X/8
+    AX
+    \x{150}X
+    \x{500}X 
+    *** Failers
+    \x{100}X
+    \x{200}X   
+    QX 
+
+/[^\x{100}-\x{200}]X/8
+    AX
+    \x{500}X 
+    *** Failers
+    \x{100}X
+    \x{150}X
+    \x{200}X   
+
+/[z-\x{100}]/8i
+    z
+    Z 
+    \x{100}
+    *** Failers
+    \x{102}
+    y    
+
+/[\xFF]/
+    >\xff<
+
+/[\xff]/8
+    >\x{ff}<
+
+/[^\xFF]/
+    XYZ
+
+/[^\xff]/8
+    XYZ
+    \x{123} 
+
+/^[ac]*b/8
+  xb
+
+/^[ac\x{100}]*b/8
+  xb
+
+/^[^x]*b/8i
+  xb
+
+/^[^x]*b/8
+  xb
+  
+/^\d*b/8
+  xb 
+
+/(|a)/g8
+    catac
+    a\x{256}a 
+
+/^\x{85}$/8i
+    \x{85}
+
+/^abc./mgx8<any>
+    abc1 \x0aabc2 \x0babc3xx \x0cabc4 \x0dabc5xx \x0d\x0aabc6 \x{0085}abc7 \x{2028}abc8 \x{2029}abc9 JUNK
+
+/abc.$/mgx8<any>
+    abc1\x0a abc2\x0b abc3\x0c abc4\x0d abc5\x0d\x0a abc6\x{0085} abc7\x{2028} abc8\x{2029} abc9
+
+/^a\Rb/8<bsr_unicode>
+    a\nb
+    a\rb
+    a\r\nb
+    a\x0bb
+    a\x0cb
+    a\x{85}b   
+    a\x{2028}b 
+    a\x{2029}b 
+    ** Failers
+    a\n\rb    
+
+/^a\R*b/8<bsr_unicode>
+    ab
+    a\nb
+    a\rb
+    a\r\nb
+    a\x0bb
+    a\x0c\x{2028}\x{2029}b
+    a\x{85}b   
+    a\n\rb    
+    a\n\r\x{85}\x0cb 
+
+/^a\R+b/8<bsr_unicode>
+    a\nb
+    a\rb
+    a\r\nb
+    a\x0bb
+    a\x0c\x{2028}\x{2029}b
+    a\x{85}b   
+    a\n\rb    
+    a\n\r\x{85}\x0cb 
+    ** Failers
+    ab  
+
+/^a\R{1,3}b/8<bsr_unicode>
+    a\nb
+    a\n\rb
+    a\n\r\x{85}b
+    a\r\n\r\nb 
+    a\r\n\r\n\r\nb 
+    a\n\r\n\rb
+    a\n\n\r\nb 
+    ** Failers
+    a\n\n\n\rb
+    a\r
+
+/\h+\V?\v{3,4}/8 
+    \x09\x20\x{a0}X\x0a\x0b\x0c\x0d\x0a
+
+/\V?\v{3,4}/8 
+    \x20\x{a0}X\x0a\x0b\x0c\x0d\x0a
+
+/\h+\V?\v{3,4}/8
+    >\x09\x20\x{a0}X\x0a\x0a\x0a<
+
+/\V?\v{3,4}/8
+    >\x09\x20\x{a0}X\x0a\x0a\x0a<
+
+/\H\h\V\v/8
+    X X\x0a
+    X\x09X\x0b
+    ** Failers
+    \x{a0} X\x0a   
+    
+/\H*\h+\V?\v{3,4}/8 
+    \x09\x20\x{a0}X\x0a\x0b\x0c\x0d\x0a
+    \x09\x20\x{a0}\x0a\x0b\x0c\x0d\x0a
+    \x09\x20\x{a0}\x0a\x0b\x0c
+    ** Failers 
+    \x09\x20\x{a0}\x0a\x0b
+     
+/\H\h\V\v/8
+    \x{3001}\x{3000}\x{2030}\x{2028}
+    X\x{180e}X\x{85}
+    ** Failers
+    \x{2009} X\x0a   
+    
+/\H*\h+\V?\v{3,4}/8 
+    \x{1680}\x{180e}\x{2007}X\x{2028}\x{2029}\x0c\x0d\x0a
+    \x09\x{205f}\x{a0}\x0a\x{2029}\x0c\x{2028}\x0a
+    \x09\x20\x{202f}\x0a\x0b\x0c
+    ** Failers 
+    \x09\x{200a}\x{a0}\x{2028}\x0b
+     
+/a\Rb/I8<bsr_anycrlf>
+    a\rb
+    a\nb
+    a\r\nb
+    ** Failers
+    a\x{85}b
+    a\x0bb     
+
+/a\Rb/I8<bsr_unicode>
+    a\rb
+    a\nb
+    a\r\nb
+    a\x{85}b
+    a\x0bb     
+    ** Failers 
+    a\x{85}b\<bsr_anycrlf>
+    a\x0bb\<bsr_anycrlf>
+    
+/a\R?b/I8<bsr_anycrlf>
+    a\rb
+    a\nb
+    a\r\nb
+    ** Failers
+    a\x{85}b
+    a\x0bb     
+
+/a\R?b/I8<bsr_unicode>
+    a\rb
+    a\nb
+    a\r\nb
+    a\x{85}b
+    a\x0bb     
+    ** Failers 
+    a\x{85}b\<bsr_anycrlf>
+    a\x0bb\<bsr_anycrlf>
+ 
+/X/8f<any> 
+    A\x{1ec5}ABCXYZ
+
+/abcd*/8
+    xxxxabcd\P
+    xxxxabcd\P\P
+
+/abcd*/i8
+    xxxxabcd\P
+    xxxxabcd\P\P
+    XXXXABCD\P
+    XXXXABCD\P\P
+
+/abc\d*/8
+    xxxxabc1\P
+    xxxxabc1\P\P
+
+/abc[de]*/8
+    xxxxabcde\P
+    xxxxabcde\P\P
+
+/\bthe cat\b/8
+    the cat\P
+    the cat\P\P
+
+/ab\Cde/8
+    abXde
+
+/(?<=ab\Cde)X/8
+
+/./8<CRLF>
+    \r\P
+    \r\P\P 
+  
+/.{2,3}/8<CRLF>
+    \r\P 
+    \r\P\P
+    \r\r\P
+    \r\r\P\P
+    \r\r\r\P
+    \r\r\r\P\P     
+
+/.{2,3}?/8<CRLF>
+    \r\P 
+    \r\P\P
+    \r\r\P
+    \r\r\P\P
+    \r\r\r\P
+    \r\r\r\P\P     
+
+/[^\x{100}]/8
+    \x{100}\x{101}X
+
+/[^\x{100}]+/8
+    \x{100}\x{101}X
+
+/-- End of testinput9 --/ 
diff --git a/ext/pcre/pcrelib/testdata/testoutput1 b/ext/pcre/pcrelib/testdata/testoutput1
new file mode 100644
index 0000000..99c0ebb
--- /dev/null
+++ b/ext/pcre/pcrelib/testdata/testoutput1
@@ -0,0 +1,8736 @@
+/-- This set of tests is for features that are compatible with all versions of
+    Perl >= 5.10, in non-UTF-8 mode. It should run clean for both the 8-bit and
+    16-bit PCRE libraries. --/
+
+/the quick brown fox/
+    the quick brown fox
+ 0: the quick brown fox
+    The quick brown FOX
+No match
+    What do you know about the quick brown fox?
+ 0: the quick brown fox
+    What do you know about THE QUICK BROWN FOX?
+No match
+
+/The quick brown fox/i
+    the quick brown fox
+ 0: the quick brown fox
+    The quick brown FOX
+ 0: The quick brown FOX
+    What do you know about the quick brown fox?
+ 0: the quick brown fox
+    What do you know about THE QUICK BROWN FOX?
+ 0: THE QUICK BROWN FOX
+
+/abcd\t\n\r\f\a\e\071\x3b\$\\\?caxyz/
+    abcd\t\n\r\f\a\e9;\$\\?caxyz
+ 0: abcd\x09\x0a\x0d\x0c\x07\x1b9;$\?caxyz
+
+/a*abc?xyz+pqr{3}ab{2,}xy{4,5}pq{0,6}AB{0,}zz/
+    abxyzpqrrrabbxyyyypqAzz
+ 0: abxyzpqrrrabbxyyyypqAzz
+    abxyzpqrrrabbxyyyypqAzz
+ 0: abxyzpqrrrabbxyyyypqAzz
+    aabxyzpqrrrabbxyyyypqAzz
+ 0: aabxyzpqrrrabbxyyyypqAzz
+    aaabxyzpqrrrabbxyyyypqAzz
+ 0: aaabxyzpqrrrabbxyyyypqAzz
+    aaaabxyzpqrrrabbxyyyypqAzz
+ 0: aaaabxyzpqrrrabbxyyyypqAzz
+    abcxyzpqrrrabbxyyyypqAzz
+ 0: abcxyzpqrrrabbxyyyypqAzz
+    aabcxyzpqrrrabbxyyyypqAzz
+ 0: aabcxyzpqrrrabbxyyyypqAzz
+    aaabcxyzpqrrrabbxyyyypAzz
+ 0: aaabcxyzpqrrrabbxyyyypAzz
+    aaabcxyzpqrrrabbxyyyypqAzz
+ 0: aaabcxyzpqrrrabbxyyyypqAzz
+    aaabcxyzpqrrrabbxyyyypqqAzz
+ 0: aaabcxyzpqrrrabbxyyyypqqAzz
+    aaabcxyzpqrrrabbxyyyypqqqAzz
+ 0: aaabcxyzpqrrrabbxyyyypqqqAzz
+    aaabcxyzpqrrrabbxyyyypqqqqAzz
+ 0: aaabcxyzpqrrrabbxyyyypqqqqAzz
+    aaabcxyzpqrrrabbxyyyypqqqqqAzz
+ 0: aaabcxyzpqrrrabbxyyyypqqqqqAzz
+    aaabcxyzpqrrrabbxyyyypqqqqqqAzz
+ 0: aaabcxyzpqrrrabbxyyyypqqqqqqAzz
+    aaaabcxyzpqrrrabbxyyyypqAzz
+ 0: aaaabcxyzpqrrrabbxyyyypqAzz
+    abxyzzpqrrrabbxyyyypqAzz
+ 0: abxyzzpqrrrabbxyyyypqAzz
+    aabxyzzzpqrrrabbxyyyypqAzz
+ 0: aabxyzzzpqrrrabbxyyyypqAzz
+    aaabxyzzzzpqrrrabbxyyyypqAzz
+ 0: aaabxyzzzzpqrrrabbxyyyypqAzz
+    aaaabxyzzzzpqrrrabbxyyyypqAzz
+ 0: aaaabxyzzzzpqrrrabbxyyyypqAzz
+    abcxyzzpqrrrabbxyyyypqAzz
+ 0: abcxyzzpqrrrabbxyyyypqAzz
+    aabcxyzzzpqrrrabbxyyyypqAzz
+ 0: aabcxyzzzpqrrrabbxyyyypqAzz
+    aaabcxyzzzzpqrrrabbxyyyypqAzz
+ 0: aaabcxyzzzzpqrrrabbxyyyypqAzz
+    aaaabcxyzzzzpqrrrabbxyyyypqAzz
+ 0: aaaabcxyzzzzpqrrrabbxyyyypqAzz
+    aaaabcxyzzzzpqrrrabbbxyyyypqAzz
+ 0: aaaabcxyzzzzpqrrrabbbxyyyypqAzz
+    aaaabcxyzzzzpqrrrabbbxyyyyypqAzz
+ 0: aaaabcxyzzzzpqrrrabbbxyyyyypqAzz
+    aaabcxyzpqrrrabbxyyyypABzz
+ 0: aaabcxyzpqrrrabbxyyyypABzz
+    aaabcxyzpqrrrabbxyyyypABBzz
+ 0: aaabcxyzpqrrrabbxyyyypABBzz
+    >>>aaabxyzpqrrrabbxyyyypqAzz
+ 0: aaabxyzpqrrrabbxyyyypqAzz
+    >aaaabxyzpqrrrabbxyyyypqAzz
+ 0: aaaabxyzpqrrrabbxyyyypqAzz
+    >>>>abcxyzpqrrrabbxyyyypqAzz
+ 0: abcxyzpqrrrabbxyyyypqAzz
+    *** Failers
+No match
+    abxyzpqrrabbxyyyypqAzz
+No match
+    abxyzpqrrrrabbxyyyypqAzz
+No match
+    abxyzpqrrrabxyyyypqAzz
+No match
+    aaaabcxyzzzzpqrrrabbbxyyyyyypqAzz
+No match
+    aaaabcxyzzzzpqrrrabbbxyyypqAzz
+No match
+    aaabcxyzpqrrrabbxyyyypqqqqqqqAzz
+No match
+
+/^(abc){1,2}zz/
+    abczz
+ 0: abczz
+ 1: abc
+    abcabczz
+ 0: abcabczz
+ 1: abc
+    *** Failers
+No match
+    zz
+No match
+    abcabcabczz
+No match
+    >>abczz
+No match
+
+/^(b+?|a){1,2}?c/
+    bc
+ 0: bc
+ 1: b
+    bbc
+ 0: bbc
+ 1: b
+    bbbc
+ 0: bbbc
+ 1: bb
+    bac
+ 0: bac
+ 1: a
+    bbac
+ 0: bbac
+ 1: a
+    aac
+ 0: aac
+ 1: a
+    abbbbbbbbbbbc
+ 0: abbbbbbbbbbbc
+ 1: bbbbbbbbbbb
+    bbbbbbbbbbbac
+ 0: bbbbbbbbbbbac
+ 1: a
+    *** Failers
+No match
+    aaac
+No match
+    abbbbbbbbbbbac
+No match
+
+/^(b+|a){1,2}c/
+    bc
+ 0: bc
+ 1: b
+    bbc
+ 0: bbc
+ 1: bb
+    bbbc
+ 0: bbbc
+ 1: bbb
+    bac
+ 0: bac
+ 1: a
+    bbac
+ 0: bbac
+ 1: a
+    aac
+ 0: aac
+ 1: a
+    abbbbbbbbbbbc
+ 0: abbbbbbbbbbbc
+ 1: bbbbbbbbbbb
+    bbbbbbbbbbbac
+ 0: bbbbbbbbbbbac
+ 1: a
+    *** Failers
+No match
+    aaac
+No match
+    abbbbbbbbbbbac
+No match
+
+/^(b+|a){1,2}?bc/
+    bbc
+ 0: bbc
+ 1: b
+
+/^(b*|ba){1,2}?bc/
+    babc
+ 0: babc
+ 1: ba
+    bbabc
+ 0: bbabc
+ 1: ba
+    bababc
+ 0: bababc
+ 1: ba
+    *** Failers
+No match
+    bababbc
+No match
+    babababc
+No match
+
+/^(ba|b*){1,2}?bc/
+    babc
+ 0: babc
+ 1: ba
+    bbabc
+ 0: bbabc
+ 1: ba
+    bababc
+ 0: bababc
+ 1: ba
+    *** Failers
+No match
+    bababbc
+No match
+    babababc
+No match
+
+/^\ca\cA\c[\c{\c:/
+    \x01\x01\e;z
+ 0: \x01\x01\x1b;z
+
+/^[ab\]cde]/
+    athing
+ 0: a
+    bthing
+ 0: b
+    ]thing
+ 0: ]
+    cthing
+ 0: c
+    dthing
+ 0: d
+    ething
+ 0: e
+    *** Failers
+No match
+    fthing
+No match
+    [thing
+No match
+    \\thing
+No match
+
+/^[]cde]/
+    ]thing
+ 0: ]
+    cthing
+ 0: c
+    dthing
+ 0: d
+    ething
+ 0: e
+    *** Failers
+No match
+    athing
+No match
+    fthing
+No match
+
+/^[^ab\]cde]/
+    fthing
+ 0: f
+    [thing
+ 0: [
+    \\thing
+ 0: \
+    *** Failers
+ 0: *
+    athing
+No match
+    bthing
+No match
+    ]thing
+No match
+    cthing
+No match
+    dthing
+No match
+    ething
+No match
+
+/^[^]cde]/
+    athing
+ 0: a
+    fthing
+ 0: f
+    *** Failers
+ 0: *
+    ]thing
+No match
+    cthing
+No match
+    dthing
+No match
+    ething
+No match
+
+/^\�/
+    �
+ 0: \x81
+
+/^ÿ/
+    ÿ
+ 0: \xff
+
+/^[0-9]+$/
+    0
+ 0: 0
+    1
+ 0: 1
+    2
+ 0: 2
+    3
+ 0: 3
+    4
+ 0: 4
+    5
+ 0: 5
+    6
+ 0: 6
+    7
+ 0: 7
+    8
+ 0: 8
+    9
+ 0: 9
+    10
+ 0: 10
+    100
+ 0: 100
+    *** Failers
+No match
+    abc
+No match
+
+/^.*nter/
+    enter
+ 0: enter
+    inter
+ 0: inter
+    uponter
+ 0: uponter
+
+/^xxx[0-9]+$/
+    xxx0
+ 0: xxx0
+    xxx1234
+ 0: xxx1234
+    *** Failers
+No match
+    xxx
+No match
+
+/^.+[0-9][0-9][0-9]$/
+    x123
+ 0: x123
+    xx123
+ 0: xx123
+    123456
+ 0: 123456
+    *** Failers
+No match
+    123
+No match
+    x1234
+ 0: x1234
+
+/^.+?[0-9][0-9][0-9]$/
+    x123
+ 0: x123
+    xx123
+ 0: xx123
+    123456
+ 0: 123456
+    *** Failers
+No match
+    123
+No match
+    x1234
+ 0: x1234
+
+/^([^!]+)!(.+)=apquxz\.ixr\.zzz\.ac\.uk$/
+    abc!pqr=apquxz.ixr.zzz.ac.uk
+ 0: abc!pqr=apquxz.ixr.zzz.ac.uk
+ 1: abc
+ 2: pqr
+    *** Failers
+No match
+    !pqr=apquxz.ixr.zzz.ac.uk
+No match
+    abc!=apquxz.ixr.zzz.ac.uk
+No match
+    abc!pqr=apquxz:ixr.zzz.ac.uk
+No match
+    abc!pqr=apquxz.ixr.zzz.ac.ukk
+No match
+
+/:/
+    Well, we need a colon: somewhere
+ 0: :
+    *** Fail if we don't
+No match
+
+/([\da-f:]+)$/i
+    0abc
+ 0: 0abc
+ 1: 0abc
+    abc
+ 0: abc
+ 1: abc
+    fed
+ 0: fed
+ 1: fed
+    E
+ 0: E
+ 1: E
+    ::
+ 0: ::
+ 1: ::
+    5f03:12C0::932e
+ 0: 5f03:12C0::932e
+ 1: 5f03:12C0::932e
+    fed def
+ 0: def
+ 1: def
+    Any old stuff
+ 0: ff
+ 1: ff
+    *** Failers
+No match
+    0zzz
+No match
+    gzzz
+No match
+    fed\x20
+No match
+    Any old rubbish
+No match
+
+/^.*\.(\d{1,3})\.(\d{1,3})\.(\d{1,3})$/
+    .1.2.3
+ 0: .1.2.3
+ 1: 1
+ 2: 2
+ 3: 3
+    A.12.123.0
+ 0: A.12.123.0
+ 1: 12
+ 2: 123
+ 3: 0
+    *** Failers
+No match
+    .1.2.3333
+No match
+    1.2.3
+No match
+    1234.2.3
+No match
+
+/^(\d+)\s+IN\s+SOA\s+(\S+)\s+(\S+)\s*\(\s*$/
+    1 IN SOA non-sp1 non-sp2(
+ 0: 1 IN SOA non-sp1 non-sp2(
+ 1: 1
+ 2: non-sp1
+ 3: non-sp2
+    1    IN    SOA    non-sp1    non-sp2   (
+ 0: 1    IN    SOA    non-sp1    non-sp2   (
+ 1: 1
+ 2: non-sp1
+ 3: non-sp2
+    *** Failers
+No match
+    1IN SOA non-sp1 non-sp2(
+No match
+
+/^[a-zA-Z\d][a-zA-Z\d\-]*(\.[a-zA-Z\d][a-zA-z\d\-]*)*\.$/
+    a.
+ 0: a.
+    Z.
+ 0: Z.
+    2.
+ 0: 2.
+    ab-c.pq-r.
+ 0: ab-c.pq-r.
+ 1: .pq-r
+    sxk.zzz.ac.uk.
+ 0: sxk.zzz.ac.uk.
+ 1: .uk
+    x-.y-.
+ 0: x-.y-.
+ 1: .y-
+    *** Failers
+No match
+    -abc.peq.
+No match
+
+/^\*\.[a-z]([a-z\-\d]*[a-z\d]+)?(\.[a-z]([a-z\-\d]*[a-z\d]+)?)*$/
+    *.a
+ 0: *.a
+    *.b0-a
+ 0: *.b0-a
+ 1: 0-a
+    *.c3-b.c
+ 0: *.c3-b.c
+ 1: 3-b
+ 2: .c
+    *.c-a.b-c
+ 0: *.c-a.b-c
+ 1: -a
+ 2: .b-c
+ 3: -c
+    *** Failers
+No match
+    *.0
+No match
+    *.a-
+No match
+    *.a-b.c-
+No match
+    *.c-a.0-c
+No match
+
+/^(?=ab(de))(abd)(e)/
+    abde
+ 0: abde
+ 1: de
+ 2: abd
+ 3: e
+
+/^(?!(ab)de|x)(abd)(f)/
+    abdf
+ 0: abdf
+ 1: <unset>
+ 2: abd
+ 3: f
+
+/^(?=(ab(cd)))(ab)/
+    abcd
+ 0: ab
+ 1: abcd
+ 2: cd
+ 3: ab
+
+/^[\da-f](\.[\da-f])*$/i
+    a.b.c.d
+ 0: a.b.c.d
+ 1: .d
+    A.B.C.D
+ 0: A.B.C.D
+ 1: .D
+    a.b.c.1.2.3.C
+ 0: a.b.c.1.2.3.C
+ 1: .C
+
+/^\".*\"\s*(;.*)?$/
+    \"1234\"
+ 0: "1234"
+    \"abcd\" ;
+ 0: "abcd" ;
+ 1: ;
+    \"\" ; rhubarb
+ 0: "" ; rhubarb
+ 1: ; rhubarb
+    *** Failers
+No match
+    \"1234\" : things
+No match
+
+/^$/
+    \
+ 0: 
+    *** Failers
+No match
+
+/   ^    a   (?# begins with a)  b\sc (?# then b c) $ (?# then end)/x
+    ab c
+ 0: ab c
+    *** Failers
+No match
+    abc
+No match
+    ab cde
+No match
+
+/(?x)   ^    a   (?# begins with a)  b\sc (?# then b c) $ (?# then end)/
+    ab c
+ 0: ab c
+    *** Failers
+No match
+    abc
+No match
+    ab cde
+No match
+
+/^   a\ b[c ]d       $/x
+    a bcd
+ 0: a bcd
+    a b d
+ 0: a b d
+    *** Failers
+No match
+    abcd
+No match
+    ab d
+No match
+
+/^(a(b(c)))(d(e(f)))(h(i(j)))(k(l(m)))$/
+    abcdefhijklm
+ 0: abcdefhijklm
+ 1: abc
+ 2: bc
+ 3: c
+ 4: def
+ 5: ef
+ 6: f
+ 7: hij
+ 8: ij
+ 9: j
+10: klm
+11: lm
+12: m
+
+/^(?:a(b(c)))(?:d(e(f)))(?:h(i(j)))(?:k(l(m)))$/
+    abcdefhijklm
+ 0: abcdefhijklm
+ 1: bc
+ 2: c
+ 3: ef
+ 4: f
+ 5: ij
+ 6: j
+ 7: lm
+ 8: m
+
+/^[\w][\W][\s][\S][\d][\D][\b][\n][\c]][\022]/
+    a+ Z0+\x08\n\x1d\x12
+ 0: a+ Z0+\x08\x0a\x1d\x12
+
+/^[.^$|()*+?{,}]+/
+    .^\$(*+)|{?,?}
+ 0: .^$(*+)|{?,?}
+
+/^a*\w/
+    z
+ 0: z
+    az
+ 0: az
+    aaaz
+ 0: aaaz
+    a
+ 0: a
+    aa
+ 0: aa
+    aaaa
+ 0: aaaa
+    a+
+ 0: a
+    aa+
+ 0: aa
+
+/^a*?\w/
+    z
+ 0: z
+    az
+ 0: a
+    aaaz
+ 0: a
+    a
+ 0: a
+    aa
+ 0: a
+    aaaa
+ 0: a
+    a+
+ 0: a
+    aa+
+ 0: a
+
+/^a+\w/
+    az
+ 0: az
+    aaaz
+ 0: aaaz
+    aa
+ 0: aa
+    aaaa
+ 0: aaaa
+    aa+
+ 0: aa
+
+/^a+?\w/
+    az
+ 0: az
+    aaaz
+ 0: aa
+    aa
+ 0: aa
+    aaaa
+ 0: aa
+    aa+
+ 0: aa
+
+/^\d{8}\w{2,}/
+    1234567890
+ 0: 1234567890
+    12345678ab
+ 0: 12345678ab
+    12345678__
+ 0: 12345678__
+    *** Failers
+No match
+    1234567
+No match
+
+/^[aeiou\d]{4,5}$/
+    uoie
+ 0: uoie
+    1234
+ 0: 1234
+    12345
+ 0: 12345
+    aaaaa
+ 0: aaaaa
+    *** Failers
+No match
+    123456
+No match
+
+/^[aeiou\d]{4,5}?/
+    uoie
+ 0: uoie
+    1234
+ 0: 1234
+    12345
+ 0: 1234
+    aaaaa
+ 0: aaaa
+    123456
+ 0: 1234
+
+/\A(abc|def)=(\1){2,3}\Z/
+    abc=abcabc
+ 0: abc=abcabc
+ 1: abc
+ 2: abc
+    def=defdefdef
+ 0: def=defdefdef
+ 1: def
+ 2: def
+    *** Failers
+No match
+    abc=defdef
+No match
+
+/^(a)(b)(c)(d)(e)(f)(g)(h)(i)(j)(k)\11*(\3\4)\1(?#)2$/
+    abcdefghijkcda2
+ 0: abcdefghijkcda2
+ 1: a
+ 2: b
+ 3: c
+ 4: d
+ 5: e
+ 6: f
+ 7: g
+ 8: h
+ 9: i
+10: j
+11: k
+12: cd
+    abcdefghijkkkkcda2
+ 0: abcdefghijkkkkcda2
+ 1: a
+ 2: b
+ 3: c
+ 4: d
+ 5: e
+ 6: f
+ 7: g
+ 8: h
+ 9: i
+10: j
+11: k
+12: cd
+
+/(cat(a(ract|tonic)|erpillar)) \1()2(3)/
+    cataract cataract23
+ 0: cataract cataract23
+ 1: cataract
+ 2: aract
+ 3: ract
+ 4: 
+ 5: 3
+    catatonic catatonic23
+ 0: catatonic catatonic23
+ 1: catatonic
+ 2: atonic
+ 3: tonic
+ 4: 
+ 5: 3
+    caterpillar caterpillar23
+ 0: caterpillar caterpillar23
+ 1: caterpillar
+ 2: erpillar
+ 3: <unset>
+ 4: 
+ 5: 3
+
+
+/^From +([^ ]+) +[a-zA-Z][a-zA-Z][a-zA-Z] +[a-zA-Z][a-zA-Z][a-zA-Z] +[0-9]?[0-9] +[0-9][0-9]:[0-9][0-9]/
+    From abcd  Mon Sep 01 12:33:02 1997
+ 0: From abcd  Mon Sep 01 12:33
+ 1: abcd
+
+/^From\s+\S+\s+([a-zA-Z]{3}\s+){2}\d{1,2}\s+\d\d:\d\d/
+    From abcd  Mon Sep 01 12:33:02 1997
+ 0: From abcd  Mon Sep 01 12:33
+ 1: Sep 
+    From abcd  Mon Sep  1 12:33:02 1997
+ 0: From abcd  Mon Sep  1 12:33
+ 1: Sep  
+    *** Failers
+No match
+    From abcd  Sep 01 12:33:02 1997
+No match
+
+/^12.34/s
+    12\n34
+ 0: 12\x0a34
+    12\r34
+ 0: 12\x0d34
+
+/\w+(?=\t)/
+    the quick brown\t fox
+ 0: brown
+
+/foo(?!bar)(.*)/
+    foobar is foolish see?
+ 0: foolish see?
+ 1: lish see?
+
+/(?:(?!foo)...|^.{0,2})bar(.*)/
+    foobar crowbar etc
+ 0: rowbar etc
+ 1:  etc
+    barrel
+ 0: barrel
+ 1: rel
+    2barrel
+ 0: 2barrel
+ 1: rel
+    A barrel
+ 0: A barrel
+ 1: rel
+
+/^(\D*)(?=\d)(?!123)/
+    abc456
+ 0: abc
+ 1: abc
+    *** Failers
+No match
+    abc123
+No match
+
+/^1234(?# test newlines
+  inside)/
+    1234
+ 0: 1234
+
+/^1234 #comment in extended re
+  /x
+    1234
+ 0: 1234
+
+/#rhubarb
+  abcd/x
+    abcd
+ 0: abcd
+
+/^abcd#rhubarb/x
+    abcd
+ 0: abcd
+
+/^(a)\1{2,3}(.)/
+    aaab
+ 0: aaab
+ 1: a
+ 2: b
+    aaaab
+ 0: aaaab
+ 1: a
+ 2: b
+    aaaaab
+ 0: aaaaa
+ 1: a
+ 2: a
+    aaaaaab
+ 0: aaaaa
+ 1: a
+ 2: a
+
+/(?!^)abc/
+    the abc
+ 0: abc
+    *** Failers
+No match
+    abc
+No match
+
+/(?=^)abc/
+    abc
+ 0: abc
+    *** Failers
+No match
+    the abc
+No match
+
+/^[ab]{1,3}(ab*|b)/
+    aabbbbb
+ 0: aabb
+ 1: b
+
+/^[ab]{1,3}?(ab*|b)/
+    aabbbbb
+ 0: aabbbbb
+ 1: abbbbb
+
+/^[ab]{1,3}?(ab*?|b)/
+    aabbbbb
+ 0: aa
+ 1: a
+
+/^[ab]{1,3}(ab*?|b)/
+    aabbbbb
+ 0: aabb
+ 1: b
+
+/  (?: [\040\t] |  \(
+(?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  |  \( (?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  )* \)  )*
+\)  )*                          # optional leading comment
+(?:    (?:
+[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+    # some number of atom characters...
+(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom
+|
+" (?:                      # opening quote...
+[^\\\x80-\xff\n\015"]                #   Anything except backslash and quote
+|                     #    or
+\\ [^\x80-\xff]           #   Escaped something (something != CR)
+)* "  # closing quote
+)                    # initial word
+(?:  (?: [\040\t] |  \(
+(?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  |  \( (?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  )* \)  )*
+\)  )*  \.  (?: [\040\t] |  \(
+(?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  |  \( (?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  )* \)  )*
+\)  )*   (?:
+[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+    # some number of atom characters...
+(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom
+|
+" (?:                      # opening quote...
+[^\\\x80-\xff\n\015"]                #   Anything except backslash and quote
+|                     #    or
+\\ [^\x80-\xff]           #   Escaped something (something != CR)
+)* "  # closing quote
+)  )* # further okay, if led by a period
+(?: [\040\t] |  \(
+(?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  |  \( (?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  )* \)  )*
+\)  )*  @  (?: [\040\t] |  \(
+(?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  |  \( (?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  )* \)  )*
+\)  )*    (?:
+[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+    # some number of atom characters...
+(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom
+|   \[                         # [
+(?: [^\\\x80-\xff\n\015\[\]] |  \\ [^\x80-\xff]  )*    #    stuff
+\]                        #           ]
+)                           # initial subdomain
+(?:                                  #
+(?: [\040\t] |  \(
+(?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  |  \( (?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  )* \)  )*
+\)  )*  \.                        # if led by a period...
+(?: [\040\t] |  \(
+(?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  |  \( (?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  )* \)  )*
+\)  )*   (?:
+[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+    # some number of atom characters...
+(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom
+|   \[                         # [
+(?: [^\\\x80-\xff\n\015\[\]] |  \\ [^\x80-\xff]  )*    #    stuff
+\]                        #           ]
+)                     #   ...further okay
+)*
+# address
+|                     #  or
+(?:
+[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+    # some number of atom characters...
+(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom
+|
+" (?:                      # opening quote...
+[^\\\x80-\xff\n\015"]                #   Anything except backslash and quote
+|                     #    or
+\\ [^\x80-\xff]           #   Escaped something (something != CR)
+)* "  # closing quote
+)             # one word, optionally followed by....
+(?:
+[^()<>@,;:".\\\[\]\x80-\xff\000-\010\012-\037]  |  # atom and space parts, or...
+\(
+(?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  |  \( (?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  )* \)  )*
+\)       |  # comments, or...
+
+" (?:                      # opening quote...
+[^\\\x80-\xff\n\015"]                #   Anything except backslash and quote
+|                     #    or
+\\ [^\x80-\xff]           #   Escaped something (something != CR)
+)* "  # closing quote
+# quoted strings
+)*
+<  (?: [\040\t] |  \(
+(?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  |  \( (?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  )* \)  )*
+\)  )*                     # leading <
+(?:  @  (?: [\040\t] |  \(
+(?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  |  \( (?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  )* \)  )*
+\)  )*    (?:
+[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+    # some number of atom characters...
+(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom
+|   \[                         # [
+(?: [^\\\x80-\xff\n\015\[\]] |  \\ [^\x80-\xff]  )*    #    stuff
+\]                        #           ]
+)                           # initial subdomain
+(?:                                  #
+(?: [\040\t] |  \(
+(?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  |  \( (?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  )* \)  )*
+\)  )*  \.                        # if led by a period...
+(?: [\040\t] |  \(
+(?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  |  \( (?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  )* \)  )*
+\)  )*   (?:
+[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+    # some number of atom characters...
+(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom
+|   \[                         # [
+(?: [^\\\x80-\xff\n\015\[\]] |  \\ [^\x80-\xff]  )*    #    stuff
+\]                        #           ]
+)                     #   ...further okay
+)*
+
+(?:  (?: [\040\t] |  \(
+(?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  |  \( (?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  )* \)  )*
+\)  )*  ,  (?: [\040\t] |  \(
+(?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  |  \( (?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  )* \)  )*
+\)  )*  @  (?: [\040\t] |  \(
+(?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  |  \( (?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  )* \)  )*
+\)  )*    (?:
+[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+    # some number of atom characters...
+(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom
+|   \[                         # [
+(?: [^\\\x80-\xff\n\015\[\]] |  \\ [^\x80-\xff]  )*    #    stuff
+\]                        #           ]
+)                           # initial subdomain
+(?:                                  #
+(?: [\040\t] |  \(
+(?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  |  \( (?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  )* \)  )*
+\)  )*  \.                        # if led by a period...
+(?: [\040\t] |  \(
+(?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  |  \( (?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  )* \)  )*
+\)  )*   (?:
+[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+    # some number of atom characters...
+(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom
+|   \[                         # [
+(?: [^\\\x80-\xff\n\015\[\]] |  \\ [^\x80-\xff]  )*    #    stuff
+\]                        #           ]
+)                     #   ...further okay
+)*
+)* # further okay, if led by comma
+:                                # closing colon
+(?: [\040\t] |  \(
+(?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  |  \( (?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  )* \)  )*
+\)  )*  )? #       optional route
+(?:
+[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+    # some number of atom characters...
+(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom
+|
+" (?:                      # opening quote...
+[^\\\x80-\xff\n\015"]                #   Anything except backslash and quote
+|                     #    or
+\\ [^\x80-\xff]           #   Escaped something (something != CR)
+)* "  # closing quote
+)                    # initial word
+(?:  (?: [\040\t] |  \(
+(?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  |  \( (?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  )* \)  )*
+\)  )*  \.  (?: [\040\t] |  \(
+(?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  |  \( (?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  )* \)  )*
+\)  )*   (?:
+[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+    # some number of atom characters...
+(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom
+|
+" (?:                      # opening quote...
+[^\\\x80-\xff\n\015"]                #   Anything except backslash and quote
+|                     #    or
+\\ [^\x80-\xff]           #   Escaped something (something != CR)
+)* "  # closing quote
+)  )* # further okay, if led by a period
+(?: [\040\t] |  \(
+(?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  |  \( (?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  )* \)  )*
+\)  )*  @  (?: [\040\t] |  \(
+(?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  |  \( (?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  )* \)  )*
+\)  )*    (?:
+[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+    # some number of atom characters...
+(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom
+|   \[                         # [
+(?: [^\\\x80-\xff\n\015\[\]] |  \\ [^\x80-\xff]  )*    #    stuff
+\]                        #           ]
+)                           # initial subdomain
+(?:                                  #
+(?: [\040\t] |  \(
+(?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  |  \( (?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  )* \)  )*
+\)  )*  \.                        # if led by a period...
+(?: [\040\t] |  \(
+(?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  |  \( (?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  )* \)  )*
+\)  )*   (?:
+[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+    # some number of atom characters...
+(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom
+|   \[                         # [
+(?: [^\\\x80-\xff\n\015\[\]] |  \\ [^\x80-\xff]  )*    #    stuff
+\]                        #           ]
+)                     #   ...further okay
+)*
+#       address spec
+(?: [\040\t] |  \(
+(?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  |  \( (?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  )* \)  )*
+\)  )*  > #                  trailing >
+# name and address
+)  (?: [\040\t] |  \(
+(?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  |  \( (?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  )* \)  )*
+\)  )*                       # optional trailing comment
+/x
+    Alan Other <user\@dom.ain>
+ 0: Alan Other <user@dom.ain>
+    <user\@dom.ain>
+ 0: user@dom.ain
+    user\@dom.ain
+ 0: user@dom.ain
+    \"A. Other\" <user.1234\@dom.ain> (a comment)
+ 0: "A. Other" <user.1234@dom.ain> (a comment)
+    A. Other <user.1234\@dom.ain> (a comment)
+ 0:  Other <user.1234@dom.ain> (a comment)
+    \"/s=user/ou=host/o=place/prmd=uu.yy/admd= /c=gb/\"\@x400-re.lay
+ 0: "/s=user/ou=host/o=place/prmd=uu.yy/admd= /c=gb/"@x400-re.lay
+    A missing angle <user\@some.where
+ 0: user@some.where
+    *** Failers
+No match
+    The quick brown fox
+No match
+
+/[\040\t]*                    # Nab whitespace.
+(?:
+\(                              #  (
+[^\\\x80-\xff\n\015()] *                             #     normal*
+(?:                                 #       (
+(?:  \\ [^\x80-\xff]  |
+\(                            #  (
+[^\\\x80-\xff\n\015()] *                            #     normal*
+(?:  \\ [^\x80-\xff]   [^\\\x80-\xff\n\015()] * )*        #     (special normal*)*
+\)                           #                       )
+)    #         special
+[^\\\x80-\xff\n\015()] *                         #         normal*
+)*                                  #            )*
+\)                             #                )
+[\040\t]* )*    # If comment found, allow more spaces.
+# optional leading comment
+(?:
+(?:
+[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+    # some number of atom characters...
+(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom
+# Atom
+|                       #  or
+"                                     # "
+[^\\\x80-\xff\n\015"] *                            #   normal
+(?:  \\ [^\x80-\xff]  [^\\\x80-\xff\n\015"] * )*        #   ( special normal* )*
+"                                     #        "
+# Quoted string
+)
+[\040\t]*                    # Nab whitespace.
+(?:
+\(                              #  (
+[^\\\x80-\xff\n\015()] *                             #     normal*
+(?:                                 #       (
+(?:  \\ [^\x80-\xff]  |
+\(                            #  (
+[^\\\x80-\xff\n\015()] *                            #     normal*
+(?:  \\ [^\x80-\xff]   [^\\\x80-\xff\n\015()] * )*        #     (special normal*)*
+\)                           #                       )
+)    #         special
+[^\\\x80-\xff\n\015()] *                         #         normal*
+)*                                  #            )*
+\)                             #                )
+[\040\t]* )*    # If comment found, allow more spaces.
+(?:
+\.
+[\040\t]*                    # Nab whitespace.
+(?:
+\(                              #  (
+[^\\\x80-\xff\n\015()] *                             #     normal*
+(?:                                 #       (
+(?:  \\ [^\x80-\xff]  |
+\(                            #  (
+[^\\\x80-\xff\n\015()] *                            #     normal*
+(?:  \\ [^\x80-\xff]   [^\\\x80-\xff\n\015()] * )*        #     (special normal*)*
+\)                           #                       )
+)    #         special
+[^\\\x80-\xff\n\015()] *                         #         normal*
+)*                                  #            )*
+\)                             #                )
+[\040\t]* )*    # If comment found, allow more spaces.
+(?:
+[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+    # some number of atom characters...
+(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom
+# Atom
+|                       #  or
+"                                     # "
+[^\\\x80-\xff\n\015"] *                            #   normal
+(?:  \\ [^\x80-\xff]  [^\\\x80-\xff\n\015"] * )*        #   ( special normal* )*
+"                                     #        "
+# Quoted string
+)
+[\040\t]*                    # Nab whitespace.
+(?:
+\(                              #  (
+[^\\\x80-\xff\n\015()] *                             #     normal*
+(?:                                 #       (
+(?:  \\ [^\x80-\xff]  |
+\(                            #  (
+[^\\\x80-\xff\n\015()] *                            #     normal*
+(?:  \\ [^\x80-\xff]   [^\\\x80-\xff\n\015()] * )*        #     (special normal*)*
+\)                           #                       )
+)    #         special
+[^\\\x80-\xff\n\015()] *                         #         normal*
+)*                                  #            )*
+\)                             #                )
+[\040\t]* )*    # If comment found, allow more spaces.
+# additional words
+)*
+@
+[\040\t]*                    # Nab whitespace.
+(?:
+\(                              #  (
+[^\\\x80-\xff\n\015()] *                             #     normal*
+(?:                                 #       (
+(?:  \\ [^\x80-\xff]  |
+\(                            #  (
+[^\\\x80-\xff\n\015()] *                            #     normal*
+(?:  \\ [^\x80-\xff]   [^\\\x80-\xff\n\015()] * )*        #     (special normal*)*
+\)                           #                       )
+)    #         special
+[^\\\x80-\xff\n\015()] *                         #         normal*
+)*                                  #            )*
+\)                             #                )
+[\040\t]* )*    # If comment found, allow more spaces.
+(?:
+[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+    # some number of atom characters...
+(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom
+|
+\[                            # [
+(?: [^\\\x80-\xff\n\015\[\]] |  \\ [^\x80-\xff]  )*     #    stuff
+\]                           #           ]
+)
+[\040\t]*                    # Nab whitespace.
+(?:
+\(                              #  (
+[^\\\x80-\xff\n\015()] *                             #     normal*
+(?:                                 #       (
+(?:  \\ [^\x80-\xff]  |
+\(                            #  (
+[^\\\x80-\xff\n\015()] *                            #     normal*
+(?:  \\ [^\x80-\xff]   [^\\\x80-\xff\n\015()] * )*        #     (special normal*)*
+\)                           #                       )
+)    #         special
+[^\\\x80-\xff\n\015()] *                         #         normal*
+)*                                  #            )*
+\)                             #                )
+[\040\t]* )*    # If comment found, allow more spaces.
+# optional trailing comments
+(?:
+\.
+[\040\t]*                    # Nab whitespace.
+(?:
+\(                              #  (
+[^\\\x80-\xff\n\015()] *                             #     normal*
+(?:                                 #       (
+(?:  \\ [^\x80-\xff]  |
+\(                            #  (
+[^\\\x80-\xff\n\015()] *                            #     normal*
+(?:  \\ [^\x80-\xff]   [^\\\x80-\xff\n\015()] * )*        #     (special normal*)*
+\)                           #                       )
+)    #         special
+[^\\\x80-\xff\n\015()] *                         #         normal*
+)*                                  #            )*
+\)                             #                )
+[\040\t]* )*    # If comment found, allow more spaces.
+(?:
+[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+    # some number of atom characters...
+(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom
+|
+\[                            # [
+(?: [^\\\x80-\xff\n\015\[\]] |  \\ [^\x80-\xff]  )*     #    stuff
+\]                           #           ]
+)
+[\040\t]*                    # Nab whitespace.
+(?:
+\(                              #  (
+[^\\\x80-\xff\n\015()] *                             #     normal*
+(?:                                 #       (
+(?:  \\ [^\x80-\xff]  |
+\(                            #  (
+[^\\\x80-\xff\n\015()] *                            #     normal*
+(?:  \\ [^\x80-\xff]   [^\\\x80-\xff\n\015()] * )*        #     (special normal*)*
+\)                           #                       )
+)    #         special
+[^\\\x80-\xff\n\015()] *                         #         normal*
+)*                                  #            )*
+\)                             #                )
+[\040\t]* )*    # If comment found, allow more spaces.
+# optional trailing comments
+)*
+# address
+|                             #  or
+(?:
+[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+    # some number of atom characters...
+(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom
+# Atom
+|                       #  or
+"                                     # "
+[^\\\x80-\xff\n\015"] *                            #   normal
+(?:  \\ [^\x80-\xff]  [^\\\x80-\xff\n\015"] * )*        #   ( special normal* )*
+"                                     #        "
+# Quoted string
+)
+# leading word
+[^()<>@,;:".\\\[\]\x80-\xff\000-\010\012-\037] *               # "normal" atoms and or spaces
+(?:
+(?:
+\(                              #  (
+[^\\\x80-\xff\n\015()] *                             #     normal*
+(?:                                 #       (
+(?:  \\ [^\x80-\xff]  |
+\(                            #  (
+[^\\\x80-\xff\n\015()] *                            #     normal*
+(?:  \\ [^\x80-\xff]   [^\\\x80-\xff\n\015()] * )*        #     (special normal*)*
+\)                           #                       )
+)    #         special
+[^\\\x80-\xff\n\015()] *                         #         normal*
+)*                                  #            )*
+\)                             #                )
+|
+"                                     # "
+[^\\\x80-\xff\n\015"] *                            #   normal
+(?:  \\ [^\x80-\xff]  [^\\\x80-\xff\n\015"] * )*        #   ( special normal* )*
+"                                     #        "
+) # "special" comment or quoted string
+[^()<>@,;:".\\\[\]\x80-\xff\000-\010\012-\037] *            #  more "normal"
+)*
+<
+[\040\t]*                    # Nab whitespace.
+(?:
+\(                              #  (
+[^\\\x80-\xff\n\015()] *                             #     normal*
+(?:                                 #       (
+(?:  \\ [^\x80-\xff]  |
+\(                            #  (
+[^\\\x80-\xff\n\015()] *                            #     normal*
+(?:  \\ [^\x80-\xff]   [^\\\x80-\xff\n\015()] * )*        #     (special normal*)*
+\)                           #                       )
+)    #         special
+[^\\\x80-\xff\n\015()] *                         #         normal*
+)*                                  #            )*
+\)                             #                )
+[\040\t]* )*    # If comment found, allow more spaces.
+# <
+(?:
+@
+[\040\t]*                    # Nab whitespace.
+(?:
+\(                              #  (
+[^\\\x80-\xff\n\015()] *                             #     normal*
+(?:                                 #       (
+(?:  \\ [^\x80-\xff]  |
+\(                            #  (
+[^\\\x80-\xff\n\015()] *                            #     normal*
+(?:  \\ [^\x80-\xff]   [^\\\x80-\xff\n\015()] * )*        #     (special normal*)*
+\)                           #                       )
+)    #         special
+[^\\\x80-\xff\n\015()] *                         #         normal*
+)*                                  #            )*
+\)                             #                )
+[\040\t]* )*    # If comment found, allow more spaces.
+(?:
+[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+    # some number of atom characters...
+(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom
+|
+\[                            # [
+(?: [^\\\x80-\xff\n\015\[\]] |  \\ [^\x80-\xff]  )*     #    stuff
+\]                           #           ]
+)
+[\040\t]*                    # Nab whitespace.
+(?:
+\(                              #  (
+[^\\\x80-\xff\n\015()] *                             #     normal*
+(?:                                 #       (
+(?:  \\ [^\x80-\xff]  |
+\(                            #  (
+[^\\\x80-\xff\n\015()] *                            #     normal*
+(?:  \\ [^\x80-\xff]   [^\\\x80-\xff\n\015()] * )*        #     (special normal*)*
+\)                           #                       )
+)    #         special
+[^\\\x80-\xff\n\015()] *                         #         normal*
+)*                                  #            )*
+\)                             #                )
+[\040\t]* )*    # If comment found, allow more spaces.
+# optional trailing comments
+(?:
+\.
+[\040\t]*                    # Nab whitespace.
+(?:
+\(                              #  (
+[^\\\x80-\xff\n\015()] *                             #     normal*
+(?:                                 #       (
+(?:  \\ [^\x80-\xff]  |
+\(                            #  (
+[^\\\x80-\xff\n\015()] *                            #     normal*
+(?:  \\ [^\x80-\xff]   [^\\\x80-\xff\n\015()] * )*        #     (special normal*)*
+\)                           #                       )
+)    #         special
+[^\\\x80-\xff\n\015()] *                         #         normal*
+)*                                  #            )*
+\)                             #                )
+[\040\t]* )*    # If comment found, allow more spaces.
+(?:
+[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+    # some number of atom characters...
+(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom
+|
+\[                            # [
+(?: [^\\\x80-\xff\n\015\[\]] |  \\ [^\x80-\xff]  )*     #    stuff
+\]                           #           ]
+)
+[\040\t]*                    # Nab whitespace.
+(?:
+\(                              #  (
+[^\\\x80-\xff\n\015()] *                             #     normal*
+(?:                                 #       (
+(?:  \\ [^\x80-\xff]  |
+\(                            #  (
+[^\\\x80-\xff\n\015()] *                            #     normal*
+(?:  \\ [^\x80-\xff]   [^\\\x80-\xff\n\015()] * )*        #     (special normal*)*
+\)                           #                       )
+)    #         special
+[^\\\x80-\xff\n\015()] *                         #         normal*
+)*                                  #            )*
+\)                             #                )
+[\040\t]* )*    # If comment found, allow more spaces.
+# optional trailing comments
+)*
+(?: ,
+[\040\t]*                    # Nab whitespace.
+(?:
+\(                              #  (
+[^\\\x80-\xff\n\015()] *                             #     normal*
+(?:                                 #       (
+(?:  \\ [^\x80-\xff]  |
+\(                            #  (
+[^\\\x80-\xff\n\015()] *                            #     normal*
+(?:  \\ [^\x80-\xff]   [^\\\x80-\xff\n\015()] * )*        #     (special normal*)*
+\)                           #                       )
+)    #         special
+[^\\\x80-\xff\n\015()] *                         #         normal*
+)*                                  #            )*
+\)                             #                )
+[\040\t]* )*    # If comment found, allow more spaces.
+@
+[\040\t]*                    # Nab whitespace.
+(?:
+\(                              #  (
+[^\\\x80-\xff\n\015()] *                             #     normal*
+(?:                                 #       (
+(?:  \\ [^\x80-\xff]  |
+\(                            #  (
+[^\\\x80-\xff\n\015()] *                            #     normal*
+(?:  \\ [^\x80-\xff]   [^\\\x80-\xff\n\015()] * )*        #     (special normal*)*
+\)                           #                       )
+)    #         special
+[^\\\x80-\xff\n\015()] *                         #         normal*
+)*                                  #            )*
+\)                             #                )
+[\040\t]* )*    # If comment found, allow more spaces.
+(?:
+[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+    # some number of atom characters...
+(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom
+|
+\[                            # [
+(?: [^\\\x80-\xff\n\015\[\]] |  \\ [^\x80-\xff]  )*     #    stuff
+\]                           #           ]
+)
+[\040\t]*                    # Nab whitespace.
+(?:
+\(                              #  (
+[^\\\x80-\xff\n\015()] *                             #     normal*
+(?:                                 #       (
+(?:  \\ [^\x80-\xff]  |
+\(                            #  (
+[^\\\x80-\xff\n\015()] *                            #     normal*
+(?:  \\ [^\x80-\xff]   [^\\\x80-\xff\n\015()] * )*        #     (special normal*)*
+\)                           #                       )
+)    #         special
+[^\\\x80-\xff\n\015()] *                         #         normal*
+)*                                  #            )*
+\)                             #                )
+[\040\t]* )*    # If comment found, allow more spaces.
+# optional trailing comments
+(?:
+\.
+[\040\t]*                    # Nab whitespace.
+(?:
+\(                              #  (
+[^\\\x80-\xff\n\015()] *                             #     normal*
+(?:                                 #       (
+(?:  \\ [^\x80-\xff]  |
+\(                            #  (
+[^\\\x80-\xff\n\015()] *                            #     normal*
+(?:  \\ [^\x80-\xff]   [^\\\x80-\xff\n\015()] * )*        #     (special normal*)*
+\)                           #                       )
+)    #         special
+[^\\\x80-\xff\n\015()] *                         #         normal*
+)*                                  #            )*
+\)                             #                )
+[\040\t]* )*    # If comment found, allow more spaces.
+(?:
+[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+    # some number of atom characters...
+(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom
+|
+\[                            # [
+(?: [^\\\x80-\xff\n\015\[\]] |  \\ [^\x80-\xff]  )*     #    stuff
+\]                           #           ]
+)
+[\040\t]*                    # Nab whitespace.
+(?:
+\(                              #  (
+[^\\\x80-\xff\n\015()] *                             #     normal*
+(?:                                 #       (
+(?:  \\ [^\x80-\xff]  |
+\(                            #  (
+[^\\\x80-\xff\n\015()] *                            #     normal*
+(?:  \\ [^\x80-\xff]   [^\\\x80-\xff\n\015()] * )*        #     (special normal*)*
+\)                           #                       )
+)    #         special
+[^\\\x80-\xff\n\015()] *                         #         normal*
+)*                                  #            )*
+\)                             #                )
+[\040\t]* )*    # If comment found, allow more spaces.
+# optional trailing comments
+)*
+)*  # additional domains
+:
+[\040\t]*                    # Nab whitespace.
+(?:
+\(                              #  (
+[^\\\x80-\xff\n\015()] *                             #     normal*
+(?:                                 #       (
+(?:  \\ [^\x80-\xff]  |
+\(                            #  (
+[^\\\x80-\xff\n\015()] *                            #     normal*
+(?:  \\ [^\x80-\xff]   [^\\\x80-\xff\n\015()] * )*        #     (special normal*)*
+\)                           #                       )
+)    #         special
+[^\\\x80-\xff\n\015()] *                         #         normal*
+)*                                  #            )*
+\)                             #                )
+[\040\t]* )*    # If comment found, allow more spaces.
+# optional trailing comments
+)?     #       optional route
+(?:
+[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+    # some number of atom characters...
+(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom
+# Atom
+|                       #  or
+"                                     # "
+[^\\\x80-\xff\n\015"] *                            #   normal
+(?:  \\ [^\x80-\xff]  [^\\\x80-\xff\n\015"] * )*        #   ( special normal* )*
+"                                     #        "
+# Quoted string
+)
+[\040\t]*                    # Nab whitespace.
+(?:
+\(                              #  (
+[^\\\x80-\xff\n\015()] *                             #     normal*
+(?:                                 #       (
+(?:  \\ [^\x80-\xff]  |
+\(                            #  (
+[^\\\x80-\xff\n\015()] *                            #     normal*
+(?:  \\ [^\x80-\xff]   [^\\\x80-\xff\n\015()] * )*        #     (special normal*)*
+\)                           #                       )
+)    #         special
+[^\\\x80-\xff\n\015()] *                         #         normal*
+)*                                  #            )*
+\)                             #                )
+[\040\t]* )*    # If comment found, allow more spaces.
+(?:
+\.
+[\040\t]*                    # Nab whitespace.
+(?:
+\(                              #  (
+[^\\\x80-\xff\n\015()] *                             #     normal*
+(?:                                 #       (
+(?:  \\ [^\x80-\xff]  |
+\(                            #  (
+[^\\\x80-\xff\n\015()] *                            #     normal*
+(?:  \\ [^\x80-\xff]   [^\\\x80-\xff\n\015()] * )*        #     (special normal*)*
+\)                           #                       )
+)    #         special
+[^\\\x80-\xff\n\015()] *                         #         normal*
+)*                                  #            )*
+\)                             #                )
+[\040\t]* )*    # If comment found, allow more spaces.
+(?:
+[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+    # some number of atom characters...
+(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom
+# Atom
+|                       #  or
+"                                     # "
+[^\\\x80-\xff\n\015"] *                            #   normal
+(?:  \\ [^\x80-\xff]  [^\\\x80-\xff\n\015"] * )*        #   ( special normal* )*
+"                                     #        "
+# Quoted string
+)
+[\040\t]*                    # Nab whitespace.
+(?:
+\(                              #  (
+[^\\\x80-\xff\n\015()] *                             #     normal*
+(?:                                 #       (
+(?:  \\ [^\x80-\xff]  |
+\(                            #  (
+[^\\\x80-\xff\n\015()] *                            #     normal*
+(?:  \\ [^\x80-\xff]   [^\\\x80-\xff\n\015()] * )*        #     (special normal*)*
+\)                           #                       )
+)    #         special
+[^\\\x80-\xff\n\015()] *                         #         normal*
+)*                                  #            )*
+\)                             #                )
+[\040\t]* )*    # If comment found, allow more spaces.
+# additional words
+)*
+@
+[\040\t]*                    # Nab whitespace.
+(?:
+\(                              #  (
+[^\\\x80-\xff\n\015()] *                             #     normal*
+(?:                                 #       (
+(?:  \\ [^\x80-\xff]  |
+\(                            #  (
+[^\\\x80-\xff\n\015()] *                            #     normal*
+(?:  \\ [^\x80-\xff]   [^\\\x80-\xff\n\015()] * )*        #     (special normal*)*
+\)                           #                       )
+)    #         special
+[^\\\x80-\xff\n\015()] *                         #         normal*
+)*                                  #            )*
+\)                             #                )
+[\040\t]* )*    # If comment found, allow more spaces.
+(?:
+[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+    # some number of atom characters...
+(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom
+|
+\[                            # [
+(?: [^\\\x80-\xff\n\015\[\]] |  \\ [^\x80-\xff]  )*     #    stuff
+\]                           #           ]
+)
+[\040\t]*                    # Nab whitespace.
+(?:
+\(                              #  (
+[^\\\x80-\xff\n\015()] *                             #     normal*
+(?:                                 #       (
+(?:  \\ [^\x80-\xff]  |
+\(                            #  (
+[^\\\x80-\xff\n\015()] *                            #     normal*
+(?:  \\ [^\x80-\xff]   [^\\\x80-\xff\n\015()] * )*        #     (special normal*)*
+\)                           #                       )
+)    #         special
+[^\\\x80-\xff\n\015()] *                         #         normal*
+)*                                  #            )*
+\)                             #                )
+[\040\t]* )*    # If comment found, allow more spaces.
+# optional trailing comments
+(?:
+\.
+[\040\t]*                    # Nab whitespace.
+(?:
+\(                              #  (
+[^\\\x80-\xff\n\015()] *                             #     normal*
+(?:                                 #       (
+(?:  \\ [^\x80-\xff]  |
+\(                            #  (
+[^\\\x80-\xff\n\015()] *                            #     normal*
+(?:  \\ [^\x80-\xff]   [^\\\x80-\xff\n\015()] * )*        #     (special normal*)*
+\)                           #                       )
+)    #         special
+[^\\\x80-\xff\n\015()] *                         #         normal*
+)*                                  #            )*
+\)                             #                )
+[\040\t]* )*    # If comment found, allow more spaces.
+(?:
+[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+    # some number of atom characters...
+(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom
+|
+\[                            # [
+(?: [^\\\x80-\xff\n\015\[\]] |  \\ [^\x80-\xff]  )*     #    stuff
+\]                           #           ]
+)
+[\040\t]*                    # Nab whitespace.
+(?:
+\(                              #  (
+[^\\\x80-\xff\n\015()] *                             #     normal*
+(?:                                 #       (
+(?:  \\ [^\x80-\xff]  |
+\(                            #  (
+[^\\\x80-\xff\n\015()] *                            #     normal*
+(?:  \\ [^\x80-\xff]   [^\\\x80-\xff\n\015()] * )*        #     (special normal*)*
+\)                           #                       )
+)    #         special
+[^\\\x80-\xff\n\015()] *                         #         normal*
+)*                                  #            )*
+\)                             #                )
+[\040\t]* )*    # If comment found, allow more spaces.
+# optional trailing comments
+)*
+#       address spec
+>                    #                 >
+# name and address
+)
+/x
+    Alan Other <user\@dom.ain>
+ 0: Alan Other <user@dom.ain>
+    <user\@dom.ain>
+ 0: user@dom.ain
+    user\@dom.ain
+ 0: user@dom.ain
+    \"A. Other\" <user.1234\@dom.ain> (a comment)
+ 0: "A. Other" <user.1234@dom.ain>
+    A. Other <user.1234\@dom.ain> (a comment)
+ 0:  Other <user.1234@dom.ain>
+    \"/s=user/ou=host/o=place/prmd=uu.yy/admd= /c=gb/\"\@x400-re.lay
+ 0: "/s=user/ou=host/o=place/prmd=uu.yy/admd= /c=gb/"@x400-re.lay
+    A missing angle <user\@some.where
+ 0: user@some.where
+    *** Failers
+No match
+    The quick brown fox
+No match
+
+/abc\0def\00pqr\000xyz\0000AB/
+    abc\0def\00pqr\000xyz\0000AB
+ 0: abc\x00def\x00pqr\x00xyz\x000AB
+    abc456 abc\0def\00pqr\000xyz\0000ABCDE
+ 0: abc\x00def\x00pqr\x00xyz\x000AB
+
+/abc\x0def\x00pqr\x000xyz\x0000AB/
+    abc\x0def\x00pqr\x000xyz\x0000AB
+ 0: abc\x0def\x00pqr\x000xyz\x0000AB
+    abc456 abc\x0def\x00pqr\x000xyz\x0000ABCDE
+ 0: abc\x0def\x00pqr\x000xyz\x0000AB
+
+/^[\000-\037]/
+    \0A
+ 0: \x00
+    \01B
+ 0: \x01
+    \037C
+ 0: \x1f
+
+/\0*/
+    \0\0\0\0
+ 0: \x00\x00\x00\x00
+
+/A\x0{2,3}Z/
+    The A\x0\x0Z
+ 0: A\x00\x00Z
+    An A\0\x0\0Z
+ 0: A\x00\x00\x00Z
+    *** Failers
+No match
+    A\0Z
+No match
+    A\0\x0\0\x0Z
+No match
+
+/^(cow|)\1(bell)/
+    cowcowbell
+ 0: cowcowbell
+ 1: cow
+ 2: bell
+    bell
+ 0: bell
+ 1: 
+ 2: bell
+    *** Failers
+No match
+    cowbell
+No match
+
+/^\s/
+    \040abc
+ 0:  
+    \x0cabc
+ 0: \x0c
+    \nabc
+ 0: \x0a
+    \rabc
+ 0: \x0d
+    \tabc
+ 0: \x09
+    *** Failers
+No match
+    abc
+No match
+
+/^a	b
+      c/x
+    abc
+ 0: abc
+
+/^(a|)\1*b/
+    ab
+ 0: ab
+ 1: a
+    aaaab
+ 0: aaaab
+ 1: a
+    b
+ 0: b
+ 1: 
+    *** Failers
+No match
+    acb
+No match
+
+/^(a|)\1+b/
+    aab
+ 0: aab
+ 1: a
+    aaaab
+ 0: aaaab
+ 1: a
+    b
+ 0: b
+ 1: 
+    *** Failers
+No match
+    ab
+No match
+
+/^(a|)\1?b/
+    ab
+ 0: ab
+ 1: a
+    aab
+ 0: aab
+ 1: a
+    b
+ 0: b
+ 1: 
+    *** Failers
+No match
+    acb
+No match
+
+/^(a|)\1{2}b/
+    aaab
+ 0: aaab
+ 1: a
+    b
+ 0: b
+ 1: 
+    *** Failers
+No match
+    ab
+No match
+    aab
+No match
+    aaaab
+No match
+
+/^(a|)\1{2,3}b/
+    aaab
+ 0: aaab
+ 1: a
+    aaaab
+ 0: aaaab
+ 1: a
+    b
+ 0: b
+ 1: 
+    *** Failers
+No match
+    ab
+No match
+    aab
+No match
+    aaaaab
+No match
+
+/ab{1,3}bc/
+    abbbbc
+ 0: abbbbc
+    abbbc
+ 0: abbbc
+    abbc
+ 0: abbc
+    *** Failers
+No match
+    abc
+No match
+    abbbbbc
+No match
+
+/([^.]*)\.([^:]*):[T ]+(.*)/
+    track1.title:TBlah blah blah
+ 0: track1.title:TBlah blah blah
+ 1: track1
+ 2: title
+ 3: Blah blah blah
+
+/([^.]*)\.([^:]*):[T ]+(.*)/i
+    track1.title:TBlah blah blah
+ 0: track1.title:TBlah blah blah
+ 1: track1
+ 2: title
+ 3: Blah blah blah
+
+/([^.]*)\.([^:]*):[t ]+(.*)/i
+    track1.title:TBlah blah blah
+ 0: track1.title:TBlah blah blah
+ 1: track1
+ 2: title
+ 3: Blah blah blah
+
+/^[W-c]+$/
+    WXY_^abc
+ 0: WXY_^abc
+    *** Failers
+No match
+    wxy
+No match
+
+/^[W-c]+$/i
+    WXY_^abc
+ 0: WXY_^abc
+    wxy_^ABC
+ 0: wxy_^ABC
+
+/^[\x3f-\x5F]+$/i
+    WXY_^abc
+ 0: WXY_^abc
+    wxy_^ABC
+ 0: wxy_^ABC
+
+/^abc$/m
+    abc
+ 0: abc
+    qqq\nabc
+ 0: abc
+    abc\nzzz
+ 0: abc
+    qqq\nabc\nzzz
+ 0: abc
+
+/^abc$/
+    abc
+ 0: abc
+    *** Failers
+No match
+    qqq\nabc
+No match
+    abc\nzzz
+No match
+    qqq\nabc\nzzz
+No match
+
+/\Aabc\Z/m
+    abc
+ 0: abc
+    abc\n 
+ 0: abc
+    *** Failers
+No match
+    qqq\nabc
+No match
+    abc\nzzz
+No match
+    qqq\nabc\nzzz
+No match
+    
+/\A(.)*\Z/s
+    abc\ndef
+ 0: abc\x0adef
+ 1: f
+
+/\A(.)*\Z/m
+    *** Failers
+ 0: *** Failers
+ 1: s
+    abc\ndef
+No match
+
+/(?:b)|(?::+)/
+    b::c
+ 0: b
+    c::b
+ 0: ::
+
+/[-az]+/
+    az-
+ 0: az-
+    *** Failers
+ 0: a
+    b
+No match
+
+/[az-]+/
+    za-
+ 0: za-
+    *** Failers
+ 0: a
+    b
+No match
+
+/[a\-z]+/
+    a-z
+ 0: a-z
+    *** Failers
+ 0: a
+    b
+No match
+
+/[a-z]+/
+    abcdxyz
+ 0: abcdxyz
+
+/[\d-]+/
+    12-34
+ 0: 12-34
+    *** Failers
+No match
+    aaa
+No match
+
+/[\d-z]+/
+    12-34z
+ 0: 12-34z
+    *** Failers
+No match
+    aaa
+No match
+
+/\x5c/
+    \\
+ 0: \
+
+/\x20Z/
+    the Zoo
+ 0:  Z
+    *** Failers
+No match
+    Zulu
+No match
+
+/(abc)\1/i
+    abcabc
+ 0: abcabc
+ 1: abc
+    ABCabc
+ 0: ABCabc
+ 1: ABC
+    abcABC
+ 0: abcABC
+ 1: abc
+
+/ab{3cd/
+    ab{3cd
+ 0: ab{3cd
+
+/ab{3,cd/
+    ab{3,cd
+ 0: ab{3,cd
+
+/ab{3,4a}cd/
+    ab{3,4a}cd
+ 0: ab{3,4a}cd
+
+/{4,5a}bc/
+    {4,5a}bc
+ 0: {4,5a}bc
+
+/abc$/
+    abc
+ 0: abc
+    abc\n
+ 0: abc
+    *** Failers
+No match
+    abc\ndef
+No match
+
+/(abc)\123/
+    abc\x53
+ 0: abcS
+ 1: abc
+
+/(abc)\223/
+    abc\x93
+ 0: abc\x93
+ 1: abc
+
+/(abc)\323/
+    abc\xd3
+ 0: abc\xd3
+ 1: abc
+
+/(abc)\100/
+    abc\x40
+ 0: abc@
+ 1: abc
+    abc\100
+ 0: abc@
+ 1: abc
+
+/(abc)\1000/
+    abc\x400
+ 0: abc@0
+ 1: abc
+    abc\x40\x30
+ 0: abc@0
+ 1: abc
+    abc\1000
+ 0: abc@0
+ 1: abc
+    abc\100\x30
+ 0: abc@0
+ 1: abc
+    abc\100\060
+ 0: abc@0
+ 1: abc
+    abc\100\60
+ 0: abc@0
+ 1: abc
+
+/abc\81/
+    abc\081
+ 0: abc\x0081
+    abc\0\x38\x31
+ 0: abc\x0081
+
+/abc\91/
+    abc\091
+ 0: abc\x0091
+    abc\0\x39\x31
+ 0: abc\x0091
+
+/(a)(b)(c)(d)(e)(f)(g)(h)(i)(j)(k)(l)\12\123/
+    abcdefghijkllS
+ 0: abcdefghijkllS
+ 1: a
+ 2: b
+ 3: c
+ 4: d
+ 5: e
+ 6: f
+ 7: g
+ 8: h
+ 9: i
+10: j
+11: k
+12: l
+
+/(a)(b)(c)(d)(e)(f)(g)(h)(i)(j)(k)\12\123/
+    abcdefghijk\12S
+ 0: abcdefghijk\x0aS
+ 1: a
+ 2: b
+ 3: c
+ 4: d
+ 5: e
+ 6: f
+ 7: g
+ 8: h
+ 9: i
+10: j
+11: k
+
+/ab\idef/
+    abidef
+ 0: abidef
+
+/a{0}bc/
+    bc
+ 0: bc
+
+/(a|(bc)){0,0}?xyz/
+    xyz
+ 0: xyz
+
+/abc[\10]de/
+    abc\010de
+ 0: abc\x08de
+
+/abc[\1]de/
+    abc\1de
+ 0: abc\x01de
+
+/(abc)[\1]de/
+    abc\1de
+ 0: abc\x01de
+ 1: abc
+
+/(?s)a.b/
+    a\nb
+ 0: a\x0ab
+
+/^([^a])([^\b])([^c]*)([^d]{3,4})/
+    baNOTccccd
+ 0: baNOTcccc
+ 1: b
+ 2: a
+ 3: NOT
+ 4: cccc
+    baNOTcccd
+ 0: baNOTccc
+ 1: b
+ 2: a
+ 3: NOT
+ 4: ccc
+    baNOTccd
+ 0: baNOTcc
+ 1: b
+ 2: a
+ 3: NO
+ 4: Tcc
+    bacccd
+ 0: baccc
+ 1: b
+ 2: a
+ 3: 
+ 4: ccc
+    *** Failers
+ 0: *** Failers
+ 1: *
+ 2: *
+ 3: * Fail
+ 4: ers
+    anything
+No match
+    b\bc   
+No match
+    baccd
+No match
+
+/[^a]/
+    Abc
+ 0: A
+  
+/[^a]/i
+    Abc 
+ 0: b
+
+/[^a]+/
+    AAAaAbc
+ 0: AAA
+  
+/[^a]+/i
+    AAAaAbc 
+ 0: bc
+
+/[^a]+/
+    bbb\nccc
+ 0: bbb\x0accc
+   
+/[^k]$/
+    abc
+ 0: c
+    *** Failers
+ 0: s
+    abk   
+No match
+   
+/[^k]{2,3}$/
+    abc
+ 0: abc
+    kbc
+ 0: bc
+    kabc 
+ 0: abc
+    *** Failers
+ 0: ers
+    abk
+No match
+    akb
+No match
+    akk 
+No match
+
+/^\d{8,}\@.+[^k]$/
+    12345678\@a.b.c.d
+ 0: 12345678@a.b.c.d
+    123456789\@x.y.z
+ 0: 123456789@x.y.z
+    *** Failers
+No match
+    12345678\@x.y.uk
+No match
+    1234567\@a.b.c.d       
+No match
+
+/(a)\1{8,}/
+    aaaaaaaaa
+ 0: aaaaaaaaa
+ 1: a
+    aaaaaaaaaa
+ 0: aaaaaaaaaa
+ 1: a
+    *** Failers
+No match
+    aaaaaaa   
+No match
+
+/[^a]/
+    aaaabcd
+ 0: b
+    aaAabcd 
+ 0: A
+
+/[^a]/i
+    aaaabcd
+ 0: b
+    aaAabcd 
+ 0: b
+
+/[^az]/
+    aaaabcd
+ 0: b
+    aaAabcd 
+ 0: A
+
+/[^az]/i
+    aaaabcd
+ 0: b
+    aaAabcd 
+ 0: b
+
+/\000\001\002\003\004\005\006\007\010\011\012\013\014\015\016\017\020\021\022\023\024\025\026\027\030\031\032\033\034\035\036\037\040\041\042\043\044\045\046\047\050\051\052\053\054\055\056\057\060\061\062\063\064\065\066\067\070\071\072\073\074\075\076\077\100\101\102\103\104\105\106\107\110\111\112\113\114\115\116\117\120\121\122\123\124\125\126\127\130\131\132\133\134\135\136\137\140\141\142\143\144\145\146\147\150\151\152\153\154\155\156\157\160\161\162\163\164\165\166\167\170\171\172\173\174\175\176\177\200\201\202\203\204\205\206\207\210\211\212\213\214\215\216\217\220\221\222\223\224\225\226\227\230\231\232\233\234\235\236\237\240\241\242\243\244\245\246\247\250\251\252\253\254\255\256\257\260\261\262\263\264\265\266\267\270\271\272\273\274\275\276\277\300\301\302\303\304\305\306\307\310\311\312\313\314\315\316\317\320\321\322\323\324\325\326\327\330\331\332\333\334\335\336\337\340\341\342\343\344\345\346\347\350\351\352\353\354\355\356\357\360\361\362\363\364\365\366\367\370\371\372\373\374\375\376\377/
+ \000\001\002\003\004\005\006\007\010\011\012\013\014\015\016\017\020\021\022\023\024\025\026\027\030\031\032\033\034\035\036\037\040\041\042\043\044\045\046\047\050\051\052\053\054\055\056\057\060\061\062\063\064\065\066\067\070\071\072\073\074\075\076\077\100\101\102\103\104\105\106\107\110\111\112\113\114\115\116\117\120\121\122\123\124\125\126\127\130\131\132\133\134\135\136\137\140\141\142\143\144\145\146\147\150\151\152\153\154\155\156\157\160\161\162\163\164\165\166\167\170\171\172\173\174\175\176\177\200\201\202\203\204\205\206\207\210\211\212\213\214\215\216\217\220\221\222\223\224\225\226\227\230\231\232\233\234\235\236\237\240\241\242\243\244\245\246\247\250\251\252\253\254\255\256\257\260\261\262\263\264\265\266\267\270\271\272\273\274\275\276\277\300\301\302\303\304\305\306\307\310\311\312\313\314\315\316\317\320\321\322\323\324\325\326\327\330\331\332\333\334\335\336\337\340\341\342\343\344\345\346\347\350\351\352\353\354\355\356\357\360\361\362\363\364\365\366\367\370\371\372\373\374\375\376\377
+ 0: \x00\x01\x02\x03\x04\x05\x06\x07\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f\x10\x11\x12\x13\x14\x15\x16\x17\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f !"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\]^_`abcdefghijklmnopqrstuvwxyz{|}~\x7f\x80\x81\x82\x83\x84\x85\x86\x87\x88\x89\x8a\x8b\x8c\x8d\x8e\x8f\x90\x91\x92\x93\x94\x95\x96\x97\x98\x99\x9a\x9b\x9c\x9d\x9e\x9f\xa0\xa1\xa2\xa3\xa4\xa5\xa6\xa7\xa8\xa9\xaa\xab\xac\xad\xae\xaf\xb0\xb1\xb2\xb3\xb4\xb5\xb6\xb7\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf\xc0\xc1\xc2\xc3\xc4\xc5\xc6\xc7\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf\xd0\xd1\xd2\xd3\xd4\xd5\xd6\xd7\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7\xe8\xe9\xea\xeb\xec\xed\xee\xef\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff
+
+/P[^*]TAIRE[^*]{1,6}?LL/
+    xxxxxxxxxxxPSTAIREISLLxxxxxxxxx
+ 0: PSTAIREISLL
+
+/P[^*]TAIRE[^*]{1,}?LL/
+    xxxxxxxxxxxPSTAIREISLLxxxxxxxxx
+ 0: PSTAIREISLL
+
+/(\.\d\d[1-9]?)\d+/
+    1.230003938
+ 0: .230003938
+ 1: .23
+    1.875000282   
+ 0: .875000282
+ 1: .875
+    1.235  
+ 0: .235
+ 1: .23
+                  
+/(\.\d\d((?=0)|\d(?=\d)))/
+    1.230003938      
+ 0: .23
+ 1: .23
+ 2: 
+    1.875000282
+ 0: .875
+ 1: .875
+ 2: 5
+    *** Failers 
+No match
+    1.235 
+No match
+    
+/a(?)b/
+    ab 
+ 0: ab
+ 
+/\b(foo)\s+(\w+)/i
+    Food is on the foo table
+ 0: foo table
+ 1: foo
+ 2: table
+    
+/foo(.*)bar/
+    The food is under the bar in the barn.
+ 0: food is under the bar in the bar
+ 1: d is under the bar in the 
+    
+/foo(.*?)bar/  
+    The food is under the bar in the barn.
+ 0: food is under the bar
+ 1: d is under the 
+
+/(.*)(\d*)/
+    I have 2 numbers: 53147
+ 0: I have 2 numbers: 53147
+ 1: I have 2 numbers: 53147
+ 2: 
+    
+/(.*)(\d+)/
+    I have 2 numbers: 53147
+ 0: I have 2 numbers: 53147
+ 1: I have 2 numbers: 5314
+ 2: 7
+ 
+/(.*?)(\d*)/
+    I have 2 numbers: 53147
+ 0: 
+ 1: 
+ 2: 
+
+/(.*?)(\d+)/
+    I have 2 numbers: 53147
+ 0: I have 2
+ 1: I have 
+ 2: 2
+
+/(.*)(\d+)$/
+    I have 2 numbers: 53147
+ 0: I have 2 numbers: 53147
+ 1: I have 2 numbers: 5314
+ 2: 7
+
+/(.*?)(\d+)$/
+    I have 2 numbers: 53147
+ 0: I have 2 numbers: 53147
+ 1: I have 2 numbers: 
+ 2: 53147
+
+/(.*)\b(\d+)$/
+    I have 2 numbers: 53147
+ 0: I have 2 numbers: 53147
+ 1: I have 2 numbers: 
+ 2: 53147
+
+/(.*\D)(\d+)$/
+    I have 2 numbers: 53147
+ 0: I have 2 numbers: 53147
+ 1: I have 2 numbers: 
+ 2: 53147
+
+/^\D*(?!123)/
+    ABC123
+ 0: AB
+     
+/^(\D*)(?=\d)(?!123)/
+    ABC445
+ 0: ABC
+ 1: ABC
+    *** Failers
+No match
+    ABC123
+No match
+    
+/^[W-]46]/
+    W46]789 
+ 0: W46]
+    -46]789
+ 0: -46]
+    *** Failers
+No match
+    Wall
+No match
+    Zebra
+No match
+    42
+No match
+    [abcd] 
+No match
+    ]abcd[
+No match
+       
+/^[W-\]46]/
+    W46]789 
+ 0: W
+    Wall
+ 0: W
+    Zebra
+ 0: Z
+    Xylophone  
+ 0: X
+    42
+ 0: 4
+    [abcd] 
+ 0: [
+    ]abcd[
+ 0: ]
+    \\backslash 
+ 0: \
+    *** Failers
+No match
+    -46]789
+No match
+    well
+No match
+    
+/\d\d\/\d\d\/\d\d\d\d/
+    01/01/2000
+ 0: 01/01/2000
+
+/word (?:[a-zA-Z0-9]+ ){0,10}otherword/
+  word cat dog elephant mussel cow horse canary baboon snake shark otherword
+ 0: word cat dog elephant mussel cow horse canary baboon snake shark otherword
+  word cat dog elephant mussel cow horse canary baboon snake shark
+No match
+
+/word (?:[a-zA-Z0-9]+ ){0,300}otherword/
+  word cat dog elephant mussel cow horse canary baboon snake shark the quick brown fox and the lazy dog and several other words getting close to thirty by now I hope
+No match
+
+/^(a){0,0}/
+    bcd
+ 0: 
+    abc
+ 0: 
+    aab     
+ 0: 
+
+/^(a){0,1}/
+    bcd
+ 0: 
+    abc
+ 0: a
+ 1: a
+    aab  
+ 0: a
+ 1: a
+
+/^(a){0,2}/
+    bcd
+ 0: 
+    abc
+ 0: a
+ 1: a
+    aab  
+ 0: aa
+ 1: a
+
+/^(a){0,3}/
+    bcd
+ 0: 
+    abc
+ 0: a
+ 1: a
+    aab
+ 0: aa
+ 1: a
+    aaa   
+ 0: aaa
+ 1: a
+
+/^(a){0,}/
+    bcd
+ 0: 
+    abc
+ 0: a
+ 1: a
+    aab
+ 0: aa
+ 1: a
+    aaa
+ 0: aaa
+ 1: a
+    aaaaaaaa    
+ 0: aaaaaaaa
+ 1: a
+
+/^(a){1,1}/
+    bcd
+No match
+    abc
+ 0: a
+ 1: a
+    aab  
+ 0: a
+ 1: a
+
+/^(a){1,2}/
+    bcd
+No match
+    abc
+ 0: a
+ 1: a
+    aab  
+ 0: aa
+ 1: a
+
+/^(a){1,3}/
+    bcd
+No match
+    abc
+ 0: a
+ 1: a
+    aab
+ 0: aa
+ 1: a
+    aaa   
+ 0: aaa
+ 1: a
+
+/^(a){1,}/
+    bcd
+No match
+    abc
+ 0: a
+ 1: a
+    aab
+ 0: aa
+ 1: a
+    aaa
+ 0: aaa
+ 1: a
+    aaaaaaaa    
+ 0: aaaaaaaa
+ 1: a
+
+/.*\.gif/
+    borfle\nbib.gif\nno
+ 0: bib.gif
+
+/.{0,}\.gif/
+    borfle\nbib.gif\nno
+ 0: bib.gif
+
+/.*\.gif/m
+    borfle\nbib.gif\nno
+ 0: bib.gif
+
+/.*\.gif/s
+    borfle\nbib.gif\nno
+ 0: borfle\x0abib.gif
+
+/.*\.gif/ms
+    borfle\nbib.gif\nno
+ 0: borfle\x0abib.gif
+    
+/.*$/
+    borfle\nbib.gif\nno
+ 0: no
+
+/.*$/m
+    borfle\nbib.gif\nno
+ 0: borfle
+
+/.*$/s
+    borfle\nbib.gif\nno
+ 0: borfle\x0abib.gif\x0ano
+
+/.*$/ms
+    borfle\nbib.gif\nno
+ 0: borfle\x0abib.gif\x0ano
+    
+/.*$/
+    borfle\nbib.gif\nno\n
+ 0: no
+
+/.*$/m
+    borfle\nbib.gif\nno\n
+ 0: borfle
+
+/.*$/s
+    borfle\nbib.gif\nno\n
+ 0: borfle\x0abib.gif\x0ano\x0a
+
+/.*$/ms
+    borfle\nbib.gif\nno\n
+ 0: borfle\x0abib.gif\x0ano\x0a
+    
+/(.*X|^B)/
+    abcde\n1234Xyz
+ 0: 1234X
+ 1: 1234X
+    BarFoo 
+ 0: B
+ 1: B
+    *** Failers
+No match
+    abcde\nBar  
+No match
+
+/(.*X|^B)/m
+    abcde\n1234Xyz
+ 0: 1234X
+ 1: 1234X
+    BarFoo 
+ 0: B
+ 1: B
+    abcde\nBar  
+ 0: B
+ 1: B
+
+/(.*X|^B)/s
+    abcde\n1234Xyz
+ 0: abcde\x0a1234X
+ 1: abcde\x0a1234X
+    BarFoo 
+ 0: B
+ 1: B
+    *** Failers
+No match
+    abcde\nBar  
+No match
+
+/(.*X|^B)/ms
+    abcde\n1234Xyz
+ 0: abcde\x0a1234X
+ 1: abcde\x0a1234X
+    BarFoo 
+ 0: B
+ 1: B
+    abcde\nBar  
+ 0: B
+ 1: B
+
+/(?s)(.*X|^B)/
+    abcde\n1234Xyz
+ 0: abcde\x0a1234X
+ 1: abcde\x0a1234X
+    BarFoo 
+ 0: B
+ 1: B
+    *** Failers 
+No match
+    abcde\nBar  
+No match
+
+/(?s:.*X|^B)/
+    abcde\n1234Xyz
+ 0: abcde\x0a1234X
+    BarFoo 
+ 0: B
+    *** Failers 
+No match
+    abcde\nBar  
+No match
+
+/^.*B/
+    **** Failers
+No match
+    abc\nB
+No match
+     
+/(?s)^.*B/
+    abc\nB
+ 0: abc\x0aB
+
+/(?m)^.*B/
+    abc\nB
+ 0: B
+     
+/(?ms)^.*B/
+    abc\nB
+ 0: abc\x0aB
+
+/(?ms)^B/
+    abc\nB
+ 0: B
+
+/(?s)B$/
+    B\n
+ 0: B
+
+/^[0-9][0-9][0-9][0-9][0-9][0-9][0-9][0-9][0-9][0-9][0-9][0-9]/
+    123456654321
+ 0: 123456654321
+  
+/^\d\d\d\d\d\d\d\d\d\d\d\d/
+    123456654321 
+ 0: 123456654321
+
+/^[\d][\d][\d][\d][\d][\d][\d][\d][\d][\d][\d][\d]/
+    123456654321
+ 0: 123456654321
+  
+/^[abc]{12}/
+    abcabcabcabc
+ 0: abcabcabcabc
+    
+/^[a-c]{12}/
+    abcabcabcabc
+ 0: abcabcabcabc
+    
+/^(a|b|c){12}/
+    abcabcabcabc 
+ 0: abcabcabcabc
+ 1: c
+
+/^[abcdefghijklmnopqrstuvwxy0123456789]/
+    n
+ 0: n
+    *** Failers 
+No match
+    z 
+No match
+
+/abcde{0,0}/
+    abcd
+ 0: abcd
+    *** Failers
+No match
+    abce  
+No match
+
+/ab[cd]{0,0}e/
+    abe
+ 0: abe
+    *** Failers
+No match
+    abcde 
+No match
+    
+/ab(c){0,0}d/
+    abd
+ 0: abd
+    *** Failers
+No match
+    abcd   
+No match
+
+/a(b*)/
+    a
+ 0: a
+ 1: 
+    ab
+ 0: ab
+ 1: b
+    abbbb
+ 0: abbbb
+ 1: bbbb
+    *** Failers
+ 0: a
+ 1: 
+    bbbbb    
+No match
+    
+/ab\d{0}e/
+    abe
+ 0: abe
+    *** Failers
+No match
+    ab1e   
+No match
+    
+/"([^\\"]+|\\.)*"/
+    the \"quick\" brown fox
+ 0: "quick"
+ 1: quick
+    \"the \\\"quick\\\" brown fox\" 
+ 0: "the \"quick\" brown fox"
+ 1:  brown fox
+
+/.*?/g+
+    abc
+ 0: 
+ 0+ abc
+ 0: a
+ 0+ bc
+ 0: 
+ 0+ bc
+ 0: b
+ 0+ c
+ 0: 
+ 0+ c
+ 0: c
+ 0+ 
+ 0: 
+ 0+ 
+  
+/\b/g+
+    abc 
+ 0: 
+ 0+ abc
+ 0: 
+ 0+ 
+
+/\b/+g
+    abc 
+ 0: 
+ 0+ abc
+ 0: 
+ 0+ 
+
+//g
+    abc
+ 0: 
+ 0: 
+ 0: 
+ 0: 
+
+/<tr([\w\W\s\d][^<>]{0,})><TD([\w\W\s\d][^<>]{0,})>([\d]{0,}\.)(.*)((<BR>([\w\W\s\d][^<>]{0,})|[\s]{0,}))<\/a><\/TD><TD([\w\W\s\d][^<>]{0,})>([\w\W\s\d][^<>]{0,})<\/TD><TD([\w\W\s\d][^<>]{0,})>([\w\W\s\d][^<>]{0,})<\/TD><\/TR>/is
+  <TR BGCOLOR='#DBE9E9'><TD align=left valign=top>43.<a href='joblist.cfm?JobID=94 6735&Keyword='>Word Processor<BR>(N-1286)</a></TD><TD align=left valign=top>Lega lstaff.com</TD><TD align=left valign=top>CA - Statewide</TD></TR>
+ 0: <TR BGCOLOR='#DBE9E9'><TD align=left valign=top>43.<a href='joblist.cfm?JobID=94 6735&Keyword='>Word Processor<BR>(N-1286)</a></TD><TD align=left valign=top>Lega lstaff.com</TD><TD align=left valign=top>CA - Statewide</TD></TR>
+ 1:  BGCOLOR='#DBE9E9'
+ 2:  align=left valign=top
+ 3: 43.
+ 4: <a href='joblist.cfm?JobID=94 6735&Keyword='>Word Processor<BR>(N-1286)
+ 5: 
+ 6: 
+ 7: <unset>
+ 8:  align=left valign=top
+ 9: Lega lstaff.com
+10:  align=left valign=top
+11: CA - Statewide
+
+/a[^a]b/
+    acb
+ 0: acb
+    a\nb
+ 0: a\x0ab
+    
+/a.b/
+    acb
+ 0: acb
+    *** Failers 
+No match
+    a\nb   
+No match
+    
+/a[^a]b/s
+    acb
+ 0: acb
+    a\nb  
+ 0: a\x0ab
+    
+/a.b/s
+    acb
+ 0: acb
+    a\nb  
+ 0: a\x0ab
+
+/^(b+?|a){1,2}?c/
+    bac
+ 0: bac
+ 1: a
+    bbac
+ 0: bbac
+ 1: a
+    bbbac
+ 0: bbbac
+ 1: a
+    bbbbac
+ 0: bbbbac
+ 1: a
+    bbbbbac 
+ 0: bbbbbac
+ 1: a
+
+/^(b+|a){1,2}?c/
+    bac
+ 0: bac
+ 1: a
+    bbac
+ 0: bbac
+ 1: a
+    bbbac
+ 0: bbbac
+ 1: a
+    bbbbac
+ 0: bbbbac
+ 1: a
+    bbbbbac 
+ 0: bbbbbac
+ 1: a
+    
+/(?!\A)x/m
+    x\nb\n
+No match
+    a\bx\n  
+ 0: x
+    
+/\x0{ab}/
+    \0{ab} 
+ 0: \x00{ab}
+
+/(A|B)*?CD/
+    CD 
+ 0: CD
+    
+/(A|B)*CD/
+    CD 
+ 0: CD
+
+/(AB)*?\1/
+    ABABAB
+ 0: ABAB
+ 1: AB
+
+/(AB)*\1/
+    ABABAB
+ 0: ABABAB
+ 1: AB
+    
+/(?<!bar)foo/
+    foo
+ 0: foo
+    catfood
+ 0: foo
+    arfootle
+ 0: foo
+    rfoosh
+ 0: foo
+    *** Failers
+No match
+    barfoo
+No match
+    towbarfoo
+No match
+
+/\w{3}(?<!bar)foo/
+    catfood
+ 0: catfoo
+    *** Failers
+No match
+    foo
+No match
+    barfoo
+No match
+    towbarfoo
+No match
+
+/(?<=(foo)a)bar/
+    fooabar
+ 0: bar
+ 1: foo
+    *** Failers
+No match
+    bar
+No match
+    foobbar
+No match
+      
+/\Aabc\z/m
+    abc
+ 0: abc
+    *** Failers
+No match
+    abc\n   
+No match
+    qqq\nabc
+No match
+    abc\nzzz
+No match
+    qqq\nabc\nzzz
+No match
+
+"(?>.*/)foo"
+    /this/is/a/very/long/line/in/deed/with/very/many/slashes/in/it/you/see/
+No match
+
+"(?>.*/)foo"
+    /this/is/a/very/long/line/in/deed/with/very/many/slashes/in/and/foo
+ 0: /this/is/a/very/long/line/in/deed/with/very/many/slashes/in/and/foo
+
+/(?>(\.\d\d[1-9]?))\d+/
+    1.230003938
+ 0: .230003938
+ 1: .23
+    1.875000282
+ 0: .875000282
+ 1: .875
+    *** Failers 
+No match
+    1.235 
+No match
+
+/^((?>\w+)|(?>\s+))*$/
+    now is the time for all good men to come to the aid of the party
+ 0: now is the time for all good men to come to the aid of the party
+ 1: party
+    *** Failers
+No match
+    this is not a line with only words and spaces!
+No match
+    
+/(\d+)(\w)/
+    12345a
+ 0: 12345a
+ 1: 12345
+ 2: a
+    12345+ 
+ 0: 12345
+ 1: 1234
+ 2: 5
+
+/((?>\d+))(\w)/
+    12345a
+ 0: 12345a
+ 1: 12345
+ 2: a
+    *** Failers
+No match
+    12345+ 
+No match
+
+/(?>a+)b/
+    aaab
+ 0: aaab
+
+/((?>a+)b)/
+    aaab
+ 0: aaab
+ 1: aaab
+
+/(?>(a+))b/
+    aaab
+ 0: aaab
+ 1: aaa
+
+/(?>b)+/
+    aaabbbccc
+ 0: bbb
+
+/(?>a+|b+|c+)*c/
+    aaabbbbccccd
+ 0: aaabbbbc
+
+/((?>[^()]+)|\([^()]*\))+/
+    ((abc(ade)ufh()()x
+ 0: abc(ade)ufh()()x
+ 1: x
+    
+/\(((?>[^()]+)|\([^()]+\))+\)/ 
+    (abc)
+ 0: (abc)
+ 1: abc
+    (abc(def)xyz)
+ 0: (abc(def)xyz)
+ 1: xyz
+    *** Failers
+No match
+    ((()aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa   
+No match
+
+/a(?-i)b/i
+    ab
+ 0: ab
+    Ab
+ 0: Ab
+    *** Failers 
+No match
+    aB
+No match
+    AB
+No match
+        
+/(a (?x)b c)d e/
+    a bcd e
+ 0: a bcd e
+ 1: a bc
+    *** Failers
+No match
+    a b cd e
+No match
+    abcd e   
+No match
+    a bcde 
+No match
+ 
+/(a b(?x)c d (?-x)e f)/
+    a bcde f
+ 0: a bcde f
+ 1: a bcde f
+    *** Failers
+No match
+    abcdef  
+No match
+
+/(a(?i)b)c/
+    abc
+ 0: abc
+ 1: ab
+    aBc
+ 0: aBc
+ 1: aB
+    *** Failers
+No match
+    abC
+No match
+    aBC  
+No match
+    Abc
+No match
+    ABc
+No match
+    ABC
+No match
+    AbC
+No match
+    
+/a(?i:b)c/
+    abc
+ 0: abc
+    aBc
+ 0: aBc
+    *** Failers 
+No match
+    ABC
+No match
+    abC
+No match
+    aBC
+No match
+    
+/a(?i:b)*c/
+    aBc
+ 0: aBc
+    aBBc
+ 0: aBBc
+    *** Failers 
+No match
+    aBC
+No match
+    aBBC
+No match
+    
+/a(?=b(?i)c)\w\wd/
+    abcd
+ 0: abcd
+    abCd
+ 0: abCd
+    *** Failers
+No match
+    aBCd
+No match
+    abcD     
+No match
+    
+/(?s-i:more.*than).*million/i
+    more than million
+ 0: more than million
+    more than MILLION
+ 0: more than MILLION
+    more \n than Million 
+ 0: more \x0a than Million
+    *** Failers
+No match
+    MORE THAN MILLION    
+No match
+    more \n than \n million 
+No match
+
+/(?:(?s-i)more.*than).*million/i
+    more than million
+ 0: more than million
+    more than MILLION
+ 0: more than MILLION
+    more \n than Million 
+ 0: more \x0a than Million
+    *** Failers
+No match
+    MORE THAN MILLION    
+No match
+    more \n than \n million 
+No match
+    
+/(?>a(?i)b+)+c/ 
+    abc
+ 0: abc
+    aBbc
+ 0: aBbc
+    aBBc 
+ 0: aBBc
+    *** Failers
+No match
+    Abc
+No match
+    abAb    
+No match
+    abbC 
+No match
+    
+/(?=a(?i)b)\w\wc/
+    abc
+ 0: abc
+    aBc
+ 0: aBc
+    *** Failers
+No match
+    Ab 
+No match
+    abC
+No match
+    aBC     
+No match
+    
+/(?<=a(?i)b)(\w\w)c/
+    abxxc
+ 0: xxc
+ 1: xx
+    aBxxc
+ 0: xxc
+ 1: xx
+    *** Failers
+No match
+    Abxxc
+No match
+    ABxxc
+No match
+    abxxC      
+No match
+
+/(?:(a)|b)(?(1)A|B)/
+    aA
+ 0: aA
+ 1: a
+    bB
+ 0: bB
+    *** Failers
+No match
+    aB
+No match
+    bA    
+No match
+
+/^(a)?(?(1)a|b)+$/
+    aa
+ 0: aa
+ 1: a
+    b
+ 0: b
+    bb  
+ 0: bb
+    *** Failers
+No match
+    ab   
+No match
+
+/^(?(?=abc)\w{3}:|\d\d)$/
+    abc:
+ 0: abc:
+    12
+ 0: 12
+    *** Failers
+No match
+    123
+No match
+    xyz    
+No match
+
+/^(?(?!abc)\d\d|\w{3}:)$/
+    abc:
+ 0: abc:
+    12
+ 0: 12
+    *** Failers
+No match
+    123
+No match
+    xyz    
+No match
+    
+/(?(?<=foo)bar|cat)/
+    foobar
+ 0: bar
+    cat
+ 0: cat
+    fcat
+ 0: cat
+    focat   
+ 0: cat
+    *** Failers
+No match
+    foocat  
+No match
+
+/(?(?<!foo)cat|bar)/
+    foobar
+ 0: bar
+    cat
+ 0: cat
+    fcat
+ 0: cat
+    focat   
+ 0: cat
+    *** Failers
+No match
+    foocat  
+No match
+
+/( \( )? [^()]+ (?(1) \) |) /x
+    abcd
+ 0: abcd
+    (abcd)
+ 0: (abcd)
+ 1: (
+    the quick (abcd) fox
+ 0: the quick 
+    (abcd   
+ 0: abcd
+
+/( \( )? [^()]+ (?(1) \) ) /x
+    abcd
+ 0: abcd
+    (abcd)
+ 0: (abcd)
+ 1: (
+    the quick (abcd) fox
+ 0: the quick 
+    (abcd   
+ 0: abcd
+
+/^(?(2)a|(1)(2))+$/
+    12
+ 0: 12
+ 1: 1
+ 2: 2
+    12a
+ 0: 12a
+ 1: 1
+ 2: 2
+    12aa
+ 0: 12aa
+ 1: 1
+ 2: 2
+    *** Failers
+No match
+    1234    
+No match
+
+/((?i)blah)\s+\1/
+    blah blah
+ 0: blah blah
+ 1: blah
+    BLAH BLAH
+ 0: BLAH BLAH
+ 1: BLAH
+    Blah Blah
+ 0: Blah Blah
+ 1: Blah
+    blaH blaH
+ 0: blaH blaH
+ 1: blaH
+    *** Failers
+No match
+    blah BLAH
+No match
+    Blah blah      
+No match
+    blaH blah 
+No match
+
+/((?i)blah)\s+(?i:\1)/
+    blah blah
+ 0: blah blah
+ 1: blah
+    BLAH BLAH
+ 0: BLAH BLAH
+ 1: BLAH
+    Blah Blah
+ 0: Blah Blah
+ 1: Blah
+    blaH blaH
+ 0: blaH blaH
+ 1: blaH
+    blah BLAH
+ 0: blah BLAH
+ 1: blah
+    Blah blah      
+ 0: Blah blah
+ 1: Blah
+    blaH blah 
+ 0: blaH blah
+ 1: blaH
+
+/(?>a*)*/
+    a
+ 0: a
+    aa
+ 0: aa
+    aaaa
+ 0: aaaa
+    
+/(abc|)+/
+    abc
+ 0: abc
+ 1: 
+    abcabc
+ 0: abcabc
+ 1: 
+    abcabcabc
+ 0: abcabcabc
+ 1: 
+    xyz      
+ 0: 
+ 1: 
+
+/([a]*)*/
+    a
+ 0: a
+ 1: 
+    aaaaa 
+ 0: aaaaa
+ 1: 
+ 
+/([ab]*)*/
+    a
+ 0: a
+ 1: 
+    b
+ 0: b
+ 1: 
+    ababab
+ 0: ababab
+ 1: 
+    aaaabcde
+ 0: aaaab
+ 1: 
+    bbbb    
+ 0: bbbb
+ 1: 
+ 
+/([^a]*)*/
+    b
+ 0: b
+ 1: 
+    bbbb
+ 0: bbbb
+ 1: 
+    aaa   
+ 0: 
+ 1: 
+ 
+/([^ab]*)*/
+    cccc
+ 0: cccc
+ 1: 
+    abab  
+ 0: 
+ 1: 
+ 
+/([a]*?)*/
+    a
+ 0: 
+ 1: 
+    aaaa 
+ 0: 
+ 1: 
+ 
+/([ab]*?)*/
+    a
+ 0: 
+ 1: 
+    b
+ 0: 
+ 1: 
+    abab
+ 0: 
+ 1: 
+    baba   
+ 0: 
+ 1: 
+ 
+/([^a]*?)*/
+    b
+ 0: 
+ 1: 
+    bbbb
+ 0: 
+ 1: 
+    aaa   
+ 0: 
+ 1: 
+ 
+/([^ab]*?)*/
+    c
+ 0: 
+ 1: 
+    cccc
+ 0: 
+ 1: 
+    baba   
+ 0: 
+ 1: 
+ 
+/(?>a*)*/
+    a
+ 0: a
+    aaabcde 
+ 0: aaa
+ 
+/((?>a*))*/
+    aaaaa
+ 0: aaaaa
+ 1: 
+    aabbaa 
+ 0: aa
+ 1: 
+ 
+/((?>a*?))*/
+    aaaaa
+ 0: 
+ 1: 
+    aabbaa 
+ 0: 
+ 1: 
+
+/(?(?=[^a-z]+[a-z])  \d{2}-[a-z]{3}-\d{2}  |  \d{2}-\d{2}-\d{2} ) /x
+    12-sep-98
+ 0: 12-sep-98
+    12-09-98
+ 0: 12-09-98
+    *** Failers
+No match
+    sep-12-98
+No match
+        
+/(?<=(foo))bar\1/
+    foobarfoo
+ 0: barfoo
+ 1: foo
+    foobarfootling 
+ 0: barfoo
+ 1: foo
+    *** Failers
+No match
+    foobar
+No match
+    barfoo   
+No match
+
+/(?i:saturday|sunday)/
+    saturday
+ 0: saturday
+    sunday
+ 0: sunday
+    Saturday
+ 0: Saturday
+    Sunday
+ 0: Sunday
+    SATURDAY
+ 0: SATURDAY
+    SUNDAY
+ 0: SUNDAY
+    SunDay
+ 0: SunDay
+    
+/(a(?i)bc|BB)x/
+    abcx
+ 0: abcx
+ 1: abc
+    aBCx
+ 0: aBCx
+ 1: aBC
+    bbx
+ 0: bbx
+ 1: bb
+    BBx
+ 0: BBx
+ 1: BB
+    *** Failers
+No match
+    abcX
+No match
+    aBCX
+No match
+    bbX
+No match
+    BBX               
+No match
+
+/^([ab](?i)[cd]|[ef])/
+    ac
+ 0: ac
+ 1: ac
+    aC
+ 0: aC
+ 1: aC
+    bD
+ 0: bD
+ 1: bD
+    elephant
+ 0: e
+ 1: e
+    Europe 
+ 0: E
+ 1: E
+    frog
+ 0: f
+ 1: f
+    France
+ 0: F
+ 1: F
+    *** Failers
+No match
+    Africa     
+No match
+
+/^(ab|a(?i)[b-c](?m-i)d|x(?i)y|z)/
+    ab
+ 0: ab
+ 1: ab
+    aBd
+ 0: aBd
+ 1: aBd
+    xy
+ 0: xy
+ 1: xy
+    xY
+ 0: xY
+ 1: xY
+    zebra
+ 0: z
+ 1: z
+    Zambesi
+ 0: Z
+ 1: Z
+    *** Failers
+No match
+    aCD  
+No match
+    XY  
+No match
+
+/(?<=foo\n)^bar/m
+    foo\nbar
+ 0: bar
+    *** Failers
+No match
+    bar
+No match
+    baz\nbar   
+No match
+
+/(?<=(?<!foo)bar)baz/
+    barbaz
+ 0: baz
+    barbarbaz 
+ 0: baz
+    koobarbaz 
+ 0: baz
+    *** Failers
+No match
+    baz
+No match
+    foobarbaz 
+No match
+
+/The cases of aaaa and aaaaaa are missed out below because Perl does things/
+/differently. We know that odd, and maybe incorrect, things happen with/
+No match
+/recursive references in Perl, as far as 5.11.3 - see some stuff in test #2./
+No match
+
+/^(a\1?){4}$/
+    a
+No match
+    aa
+No match
+    aaa
+No match
+    aaaaa
+ 0: aaaaa
+ 1: a
+    aaaaaaa
+ 0: aaaaaaa
+ 1: a
+    aaaaaaaa
+No match
+    aaaaaaaaa
+No match
+    aaaaaaaaaa
+ 0: aaaaaaaaaa
+ 1: aaaa
+    aaaaaaaaaaa
+No match
+    aaaaaaaaaaaa
+No match
+    aaaaaaaaaaaaa
+No match
+    aaaaaaaaaaaaaa
+No match
+    aaaaaaaaaaaaaaa
+No match
+    aaaaaaaaaaaaaaaa               
+No match
+
+/^(a\1?)(a\1?)(a\2?)(a\3?)$/
+    a
+No match
+    aa
+No match
+    aaa
+No match
+    aaaa
+ 0: aaaa
+ 1: a
+ 2: a
+ 3: a
+ 4: a
+    aaaaa
+ 0: aaaaa
+ 1: a
+ 2: aa
+ 3: a
+ 4: a
+    aaaaaa
+ 0: aaaaaa
+ 1: a
+ 2: aa
+ 3: a
+ 4: aa
+    aaaaaaa
+ 0: aaaaaaa
+ 1: a
+ 2: aa
+ 3: aaa
+ 4: a
+    aaaaaaaa
+No match
+    aaaaaaaaa
+No match
+    aaaaaaaaaa
+ 0: aaaaaaaaaa
+ 1: a
+ 2: aa
+ 3: aaa
+ 4: aaaa
+    aaaaaaaaaaa
+No match
+    aaaaaaaaaaaa
+No match
+    aaaaaaaaaaaaa
+No match
+    aaaaaaaaaaaaaa
+No match
+    aaaaaaaaaaaaaaa
+No match
+    aaaaaaaaaaaaaaaa               
+No match
+
+/The following tests are taken from the Perl 5.005 test suite; some of them/
+/are compatible with 5.004, but I'd rather not have to sort them out./
+No match
+
+/abc/
+    abc
+ 0: abc
+    xabcy
+ 0: abc
+    ababc
+ 0: abc
+    *** Failers
+No match
+    xbc
+No match
+    axc
+No match
+    abx
+No match
+
+/ab*c/
+    abc
+ 0: abc
+
+/ab*bc/
+    abc
+ 0: abc
+    abbc
+ 0: abbc
+    abbbbc
+ 0: abbbbc
+
+/.{1}/
+    abbbbc
+ 0: a
+
+/.{3,4}/
+    abbbbc
+ 0: abbb
+
+/ab{0,}bc/
+    abbbbc
+ 0: abbbbc
+
+/ab+bc/
+    abbc
+ 0: abbc
+    *** Failers
+No match
+    abc
+No match
+    abq
+No match
+
+/ab{1,}bc/
+
+/ab+bc/
+    abbbbc
+ 0: abbbbc
+
+/ab{1,}bc/
+    abbbbc
+ 0: abbbbc
+
+/ab{1,3}bc/
+    abbbbc
+ 0: abbbbc
+
+/ab{3,4}bc/
+    abbbbc
+ 0: abbbbc
+
+/ab{4,5}bc/
+    *** Failers
+No match
+    abq
+No match
+    abbbbc
+No match
+
+/ab?bc/
+    abbc
+ 0: abbc
+    abc
+ 0: abc
+
+/ab{0,1}bc/
+    abc
+ 0: abc
+
+/ab?bc/
+
+/ab?c/
+    abc
+ 0: abc
+
+/ab{0,1}c/
+    abc
+ 0: abc
+
+/^abc$/
+    abc
+ 0: abc
+    *** Failers
+No match
+    abbbbc
+No match
+    abcc
+No match
+
+/^abc/
+    abcc
+ 0: abc
+
+/^abc$/
+
+/abc$/
+    aabc
+ 0: abc
+    *** Failers
+No match
+    aabc
+ 0: abc
+    aabcd
+No match
+
+/^/
+    abc
+ 0: 
+
+/$/
+    abc
+ 0: 
+
+/a.c/
+    abc
+ 0: abc
+    axc
+ 0: axc
+
+/a.*c/
+    axyzc
+ 0: axyzc
+
+/a[bc]d/
+    abd
+ 0: abd
+    *** Failers
+No match
+    axyzd
+No match
+    abc
+No match
+
+/a[b-d]e/
+    ace
+ 0: ace
+
+/a[b-d]/
+    aac
+ 0: ac
+
+/a[-b]/
+    a-
+ 0: a-
+
+/a[b-]/
+    a-
+ 0: a-
+
+/a]/
+    a]
+ 0: a]
+
+/a[]]b/
+    a]b
+ 0: a]b
+
+/a[^bc]d/
+    aed
+ 0: aed
+    *** Failers
+No match
+    abd
+No match
+    abd
+No match
+
+/a[^-b]c/
+    adc
+ 0: adc
+
+/a[^]b]c/
+    adc
+ 0: adc
+    *** Failers
+No match
+    a-c
+ 0: a-c
+    a]c
+No match
+
+/\ba\b/
+    a-
+ 0: a
+    -a
+ 0: a
+    -a-
+ 0: a
+
+/\by\b/
+    *** Failers
+No match
+    xy
+No match
+    yz
+No match
+    xyz
+No match
+
+/\Ba\B/
+    *** Failers
+ 0: a
+    a-
+No match
+    -a
+No match
+    -a-
+No match
+
+/\By\b/
+    xy
+ 0: y
+
+/\by\B/
+    yz
+ 0: y
+
+/\By\B/
+    xyz
+ 0: y
+
+/\w/
+    a
+ 0: a
+
+/\W/
+    -
+ 0: -
+    *** Failers
+ 0: *
+    -
+ 0: -
+    a
+No match
+
+/a\sb/
+    a b
+ 0: a b
+
+/a\Sb/
+    a-b
+ 0: a-b
+    *** Failers
+No match
+    a-b
+ 0: a-b
+    a b
+No match
+
+/\d/
+    1
+ 0: 1
+
+/\D/
+    -
+ 0: -
+    *** Failers
+ 0: *
+    -
+ 0: -
+    1
+No match
+
+/[\w]/
+    a
+ 0: a
+
+/[\W]/
+    -
+ 0: -
+    *** Failers
+ 0: *
+    -
+ 0: -
+    a
+No match
+
+/a[\s]b/
+    a b
+ 0: a b
+
+/a[\S]b/
+    a-b
+ 0: a-b
+    *** Failers
+No match
+    a-b
+ 0: a-b
+    a b
+No match
+
+/[\d]/
+    1
+ 0: 1
+
+/[\D]/
+    -
+ 0: -
+    *** Failers
+ 0: *
+    -
+ 0: -
+    1
+No match
+
+/ab|cd/
+    abc
+ 0: ab
+    abcd
+ 0: ab
+
+/()ef/
+    def
+ 0: ef
+ 1: 
+
+/$b/
+
+/a\(b/
+    a(b
+ 0: a(b
+
+/a\(*b/
+    ab
+ 0: ab
+    a((b
+ 0: a((b
+
+/a\\b/
+    a\b
+No match
+
+/((a))/
+    abc
+ 0: a
+ 1: a
+ 2: a
+
+/(a)b(c)/
+    abc
+ 0: abc
+ 1: a
+ 2: c
+
+/a+b+c/
+    aabbabc
+ 0: abc
+
+/a{1,}b{1,}c/
+    aabbabc
+ 0: abc
+
+/a.+?c/
+    abcabc
+ 0: abc
+
+/(a+|b)*/
+    ab
+ 0: ab
+ 1: b
+
+/(a+|b){0,}/
+    ab
+ 0: ab
+ 1: b
+
+/(a+|b)+/
+    ab
+ 0: ab
+ 1: b
+
+/(a+|b){1,}/
+    ab
+ 0: ab
+ 1: b
+
+/(a+|b)?/
+    ab
+ 0: a
+ 1: a
+
+/(a+|b){0,1}/
+    ab
+ 0: a
+ 1: a
+
+/[^ab]*/
+    cde
+ 0: cde
+
+/abc/
+    *** Failers
+No match
+    b
+No match
+    
+
+/a*/
+    
+
+/([abc])*d/
+    abbbcd
+ 0: abbbcd
+ 1: c
+
+/([abc])*bcd/
+    abcd
+ 0: abcd
+ 1: a
+
+/a|b|c|d|e/
+    e
+ 0: e
+
+/(a|b|c|d|e)f/
+    ef
+ 0: ef
+ 1: e
+
+/abcd*efg/
+    abcdefg
+ 0: abcdefg
+
+/ab*/
+    xabyabbbz
+ 0: ab
+    xayabbbz
+ 0: a
+
+/(ab|cd)e/
+    abcde
+ 0: cde
+ 1: cd
+
+/[abhgefdc]ij/
+    hij
+ 0: hij
+
+/^(ab|cd)e/
+
+/(abc|)ef/
+    abcdef
+ 0: ef
+ 1: 
+
+/(a|b)c*d/
+    abcd
+ 0: bcd
+ 1: b
+
+/(ab|ab*)bc/
+    abc
+ 0: abc
+ 1: a
+
+/a([bc]*)c*/
+    abc
+ 0: abc
+ 1: bc
+
+/a([bc]*)(c*d)/
+    abcd
+ 0: abcd
+ 1: bc
+ 2: d
+
+/a([bc]+)(c*d)/
+    abcd
+ 0: abcd
+ 1: bc
+ 2: d
+
+/a([bc]*)(c+d)/
+    abcd
+ 0: abcd
+ 1: b
+ 2: cd
+
+/a[bcd]*dcdcde/
+    adcdcde
+ 0: adcdcde
+
+/a[bcd]+dcdcde/
+    *** Failers
+No match
+    abcde
+No match
+    adcdcde
+No match
+
+/(ab|a)b*c/
+    abc
+ 0: abc
+ 1: ab
+
+/((a)(b)c)(d)/
+    abcd
+ 0: abcd
+ 1: abc
+ 2: a
+ 3: b
+ 4: d
+
+/[a-zA-Z_][a-zA-Z0-9_]*/
+    alpha
+ 0: alpha
+
+/^a(bc+|b[eh])g|.h$/
+    abh
+ 0: bh
+
+/(bc+d$|ef*g.|h?i(j|k))/
+    effgz
+ 0: effgz
+ 1: effgz
+    ij
+ 0: ij
+ 1: ij
+ 2: j
+    reffgz
+ 0: effgz
+ 1: effgz
+    *** Failers
+No match
+    effg
+No match
+    bcdd
+No match
+
+/((((((((((a))))))))))/
+    a
+ 0: a
+ 1: a
+ 2: a
+ 3: a
+ 4: a
+ 5: a
+ 6: a
+ 7: a
+ 8: a
+ 9: a
+10: a
+
+/((((((((((a))))))))))\10/
+    aa
+ 0: aa
+ 1: a
+ 2: a
+ 3: a
+ 4: a
+ 5: a
+ 6: a
+ 7: a
+ 8: a
+ 9: a
+10: a
+
+/(((((((((a)))))))))/
+    a
+ 0: a
+ 1: a
+ 2: a
+ 3: a
+ 4: a
+ 5: a
+ 6: a
+ 7: a
+ 8: a
+ 9: a
+
+/multiple words of text/
+    *** Failers
+No match
+    aa
+No match
+    uh-uh
+No match
+
+/multiple words/
+    multiple words, yeah
+ 0: multiple words
+
+/(.*)c(.*)/
+    abcde
+ 0: abcde
+ 1: ab
+ 2: de
+
+/\((.*), (.*)\)/
+    (a, b)
+ 0: (a, b)
+ 1: a
+ 2: b
+
+/[k]/
+
+/abcd/
+    abcd
+ 0: abcd
+
+/a(bc)d/
+    abcd
+ 0: abcd
+ 1: bc
+
+/a[-]?c/
+    ac
+ 0: ac
+
+/(abc)\1/
+    abcabc
+ 0: abcabc
+ 1: abc
+
+/([a-c]*)\1/
+    abcabc
+ 0: abcabc
+ 1: abc
+
+/(a)|\1/
+    a
+ 0: a
+ 1: a
+    *** Failers
+ 0: a
+ 1: a
+    ab
+ 0: a
+ 1: a
+    x
+No match
+
+/(([a-c])b*?\2)*/
+    ababbbcbc
+ 0: ababb
+ 1: bb
+ 2: b
+
+/(([a-c])b*?\2){3}/
+    ababbbcbc
+ 0: ababbbcbc
+ 1: cbc
+ 2: c
+
+/((\3|b)\2(a)x)+/
+    aaaxabaxbaaxbbax
+ 0: bbax
+ 1: bbax
+ 2: b
+ 3: a
+
+/((\3|b)\2(a)){2,}/
+    bbaababbabaaaaabbaaaabba
+ 0: bbaaaabba
+ 1: bba
+ 2: b
+ 3: a
+
+/abc/i
+    ABC
+ 0: ABC
+    XABCY
+ 0: ABC
+    ABABC
+ 0: ABC
+    *** Failers
+No match
+    aaxabxbaxbbx
+No match
+    XBC
+No match
+    AXC
+No match
+    ABX
+No match
+
+/ab*c/i
+    ABC
+ 0: ABC
+
+/ab*bc/i
+    ABC
+ 0: ABC
+    ABBC
+ 0: ABBC
+
+/ab*?bc/i
+    ABBBBC
+ 0: ABBBBC
+
+/ab{0,}?bc/i
+    ABBBBC
+ 0: ABBBBC
+
+/ab+?bc/i
+    ABBC
+ 0: ABBC
+
+/ab+bc/i
+    *** Failers
+No match
+    ABC
+No match
+    ABQ
+No match
+
+/ab{1,}bc/i
+
+/ab+bc/i
+    ABBBBC
+ 0: ABBBBC
+
+/ab{1,}?bc/i
+    ABBBBC
+ 0: ABBBBC
+
+/ab{1,3}?bc/i
+    ABBBBC
+ 0: ABBBBC
+
+/ab{3,4}?bc/i
+    ABBBBC
+ 0: ABBBBC
+
+/ab{4,5}?bc/i
+    *** Failers
+No match
+    ABQ
+No match
+    ABBBBC
+No match
+
+/ab??bc/i
+    ABBC
+ 0: ABBC
+    ABC
+ 0: ABC
+
+/ab{0,1}?bc/i
+    ABC
+ 0: ABC
+
+/ab??bc/i
+
+/ab??c/i
+    ABC
+ 0: ABC
+
+/ab{0,1}?c/i
+    ABC
+ 0: ABC
+
+/^abc$/i
+    ABC
+ 0: ABC
+    *** Failers
+No match
+    ABBBBC
+No match
+    ABCC
+No match
+
+/^abc/i
+    ABCC
+ 0: ABC
+
+/^abc$/i
+
+/abc$/i
+    AABC
+ 0: ABC
+
+/^/i
+    ABC
+ 0: 
+
+/$/i
+    ABC
+ 0: 
+
+/a.c/i
+    ABC
+ 0: ABC
+    AXC
+ 0: AXC
+
+/a.*?c/i
+    AXYZC
+ 0: AXYZC
+
+/a.*c/i
+    *** Failers
+No match
+    AABC
+ 0: AABC
+    AXYZD
+No match
+
+/a[bc]d/i
+    ABD
+ 0: ABD
+
+/a[b-d]e/i
+    ACE
+ 0: ACE
+    *** Failers
+No match
+    ABC
+No match
+    ABD
+No match
+
+/a[b-d]/i
+    AAC
+ 0: AC
+
+/a[-b]/i
+    A-
+ 0: A-
+
+/a[b-]/i
+    A-
+ 0: A-
+
+/a]/i
+    A]
+ 0: A]
+
+/a[]]b/i
+    A]B
+ 0: A]B
+
+/a[^bc]d/i
+    AED
+ 0: AED
+
+/a[^-b]c/i
+    ADC
+ 0: ADC
+    *** Failers
+No match
+    ABD
+No match
+    A-C
+No match
+
+/a[^]b]c/i
+    ADC
+ 0: ADC
+
+/ab|cd/i
+    ABC
+ 0: AB
+    ABCD
+ 0: AB
+
+/()ef/i
+    DEF
+ 0: EF
+ 1: 
+
+/$b/i
+    *** Failers
+No match
+    A]C
+No match
+    B
+No match
+
+/a\(b/i
+    A(B
+ 0: A(B
+
+/a\(*b/i
+    AB
+ 0: AB
+    A((B
+ 0: A((B
+
+/a\\b/i
+    A\B
+No match
+
+/((a))/i
+    ABC
+ 0: A
+ 1: A
+ 2: A
+
+/(a)b(c)/i
+    ABC
+ 0: ABC
+ 1: A
+ 2: C
+
+/a+b+c/i
+    AABBABC
+ 0: ABC
+
+/a{1,}b{1,}c/i
+    AABBABC
+ 0: ABC
+
+/a.+?c/i
+    ABCABC
+ 0: ABC
+
+/a.*?c/i
+    ABCABC
+ 0: ABC
+
+/a.{0,5}?c/i
+    ABCABC
+ 0: ABC
+
+/(a+|b)*/i
+    AB
+ 0: AB
+ 1: B
+
+/(a+|b){0,}/i
+    AB
+ 0: AB
+ 1: B
+
+/(a+|b)+/i
+    AB
+ 0: AB
+ 1: B
+
+/(a+|b){1,}/i
+    AB
+ 0: AB
+ 1: B
+
+/(a+|b)?/i
+    AB
+ 0: A
+ 1: A
+
+/(a+|b){0,1}/i
+    AB
+ 0: A
+ 1: A
+
+/(a+|b){0,1}?/i
+    AB
+ 0: 
+
+/[^ab]*/i
+    CDE
+ 0: CDE
+
+/abc/i
+
+/a*/i
+    
+
+/([abc])*d/i
+    ABBBCD
+ 0: ABBBCD
+ 1: C
+
+/([abc])*bcd/i
+    ABCD
+ 0: ABCD
+ 1: A
+
+/a|b|c|d|e/i
+    E
+ 0: E
+
+/(a|b|c|d|e)f/i
+    EF
+ 0: EF
+ 1: E
+
+/abcd*efg/i
+    ABCDEFG
+ 0: ABCDEFG
+
+/ab*/i
+    XABYABBBZ
+ 0: AB
+    XAYABBBZ
+ 0: A
+
+/(ab|cd)e/i
+    ABCDE
+ 0: CDE
+ 1: CD
+
+/[abhgefdc]ij/i
+    HIJ
+ 0: HIJ
+
+/^(ab|cd)e/i
+    ABCDE
+No match
+
+/(abc|)ef/i
+    ABCDEF
+ 0: EF
+ 1: 
+
+/(a|b)c*d/i
+    ABCD
+ 0: BCD
+ 1: B
+
+/(ab|ab*)bc/i
+    ABC
+ 0: ABC
+ 1: A
+
+/a([bc]*)c*/i
+    ABC
+ 0: ABC
+ 1: BC
+
+/a([bc]*)(c*d)/i
+    ABCD
+ 0: ABCD
+ 1: BC
+ 2: D
+
+/a([bc]+)(c*d)/i
+    ABCD
+ 0: ABCD
+ 1: BC
+ 2: D
+
+/a([bc]*)(c+d)/i
+    ABCD
+ 0: ABCD
+ 1: B
+ 2: CD
+
+/a[bcd]*dcdcde/i
+    ADCDCDE
+ 0: ADCDCDE
+
+/a[bcd]+dcdcde/i
+
+/(ab|a)b*c/i
+    ABC
+ 0: ABC
+ 1: AB
+
+/((a)(b)c)(d)/i
+    ABCD
+ 0: ABCD
+ 1: ABC
+ 2: A
+ 3: B
+ 4: D
+
+/[a-zA-Z_][a-zA-Z0-9_]*/i
+    ALPHA
+ 0: ALPHA
+
+/^a(bc+|b[eh])g|.h$/i
+    ABH
+ 0: BH
+
+/(bc+d$|ef*g.|h?i(j|k))/i
+    EFFGZ
+ 0: EFFGZ
+ 1: EFFGZ
+    IJ
+ 0: IJ
+ 1: IJ
+ 2: J
+    REFFGZ
+ 0: EFFGZ
+ 1: EFFGZ
+    *** Failers
+No match
+    ADCDCDE
+No match
+    EFFG
+No match
+    BCDD
+No match
+
+/((((((((((a))))))))))/i
+    A
+ 0: A
+ 1: A
+ 2: A
+ 3: A
+ 4: A
+ 5: A
+ 6: A
+ 7: A
+ 8: A
+ 9: A
+10: A
+
+/((((((((((a))))))))))\10/i
+    AA
+ 0: AA
+ 1: A
+ 2: A
+ 3: A
+ 4: A
+ 5: A
+ 6: A
+ 7: A
+ 8: A
+ 9: A
+10: A
+
+/(((((((((a)))))))))/i
+    A
+ 0: A
+ 1: A
+ 2: A
+ 3: A
+ 4: A
+ 5: A
+ 6: A
+ 7: A
+ 8: A
+ 9: A
+
+/(?:(?:(?:(?:(?:(?:(?:(?:(?:(a))))))))))/i
+    A
+ 0: A
+ 1: A
+
+/(?:(?:(?:(?:(?:(?:(?:(?:(?:(a|b|c))))))))))/i
+    C
+ 0: C
+ 1: C
+
+/multiple words of text/i
+    *** Failers
+No match
+    AA
+No match
+    UH-UH
+No match
+
+/multiple words/i
+    MULTIPLE WORDS, YEAH
+ 0: MULTIPLE WORDS
+
+/(.*)c(.*)/i
+    ABCDE
+ 0: ABCDE
+ 1: AB
+ 2: DE
+
+/\((.*), (.*)\)/i
+    (A, B)
+ 0: (A, B)
+ 1: A
+ 2: B
+
+/[k]/i
+
+/abcd/i
+    ABCD
+ 0: ABCD
+
+/a(bc)d/i
+    ABCD
+ 0: ABCD
+ 1: BC
+
+/a[-]?c/i
+    AC
+ 0: AC
+
+/(abc)\1/i
+    ABCABC
+ 0: ABCABC
+ 1: ABC
+
+/([a-c]*)\1/i
+    ABCABC
+ 0: ABCABC
+ 1: ABC
+
+/a(?!b)./
+    abad
+ 0: ad
+
+/a(?=d)./
+    abad
+ 0: ad
+
+/a(?=c|d)./
+    abad
+ 0: ad
+
+/a(?:b|c|d)(.)/
+    ace
+ 0: ace
+ 1: e
+
+/a(?:b|c|d)*(.)/
+    ace
+ 0: ace
+ 1: e
+
+/a(?:b|c|d)+?(.)/
+    ace
+ 0: ace
+ 1: e
+    acdbcdbe
+ 0: acd
+ 1: d
+
+/a(?:b|c|d)+(.)/
+    acdbcdbe
+ 0: acdbcdbe
+ 1: e
+
+/a(?:b|c|d){2}(.)/
+    acdbcdbe
+ 0: acdb
+ 1: b
+
+/a(?:b|c|d){4,5}(.)/
+    acdbcdbe
+ 0: acdbcdb
+ 1: b
+
+/a(?:b|c|d){4,5}?(.)/
+    acdbcdbe
+ 0: acdbcd
+ 1: d
+
+/((foo)|(bar))*/
+    foobar
+ 0: foobar
+ 1: bar
+ 2: foo
+ 3: bar
+
+/a(?:b|c|d){6,7}(.)/
+    acdbcdbe
+ 0: acdbcdbe
+ 1: e
+
+/a(?:b|c|d){6,7}?(.)/
+    acdbcdbe
+ 0: acdbcdbe
+ 1: e
+
+/a(?:b|c|d){5,6}(.)/
+    acdbcdbe
+ 0: acdbcdbe
+ 1: e
+
+/a(?:b|c|d){5,6}?(.)/
+    acdbcdbe
+ 0: acdbcdb
+ 1: b
+
+/a(?:b|c|d){5,7}(.)/
+    acdbcdbe
+ 0: acdbcdbe
+ 1: e
+
+/a(?:b|c|d){5,7}?(.)/
+    acdbcdbe
+ 0: acdbcdb
+ 1: b
+
+/a(?:b|(c|e){1,2}?|d)+?(.)/
+    ace
+ 0: ace
+ 1: c
+ 2: e
+
+/^(.+)?B/
+    AB
+ 0: AB
+ 1: A
+
+/^([^a-z])|(\^)$/
+    .
+ 0: .
+ 1: .
+
+/^[<>]&/
+    <&OUT
+ 0: <&
+
+/^(a\1?){4}$/
+    aaaaaaaaaa
+ 0: aaaaaaaaaa
+ 1: aaaa
+    *** Failers
+No match
+    AB
+No match
+    aaaaaaaaa
+No match
+    aaaaaaaaaaa
+No match
+
+/^(a(?(1)\1)){4}$/
+    aaaaaaaaaa
+ 0: aaaaaaaaaa
+ 1: aaaa
+    *** Failers
+No match
+    aaaaaaaaa
+No match
+    aaaaaaaaaaa
+No match
+
+/(?:(f)(o)(o)|(b)(a)(r))*/
+    foobar
+ 0: foobar
+ 1: f
+ 2: o
+ 3: o
+ 4: b
+ 5: a
+ 6: r
+
+/(?<=a)b/
+    ab
+ 0: b
+    *** Failers
+No match
+    cb
+No match
+    b
+No match
+
+/(?<!c)b/
+    ab
+ 0: b
+    b
+ 0: b
+    b
+ 0: b
+
+/(?:..)*a/
+    aba
+ 0: aba
+
+/(?:..)*?a/
+    aba
+ 0: a
+
+/^(?:b|a(?=(.)))*\1/
+    abc
+ 0: ab
+ 1: b
+
+/^(){3,5}/
+    abc
+ 0: 
+ 1: 
+
+/^(a+)*ax/
+    aax
+ 0: aax
+ 1: a
+
+/^((a|b)+)*ax/
+    aax
+ 0: aax
+ 1: a
+ 2: a
+
+/^((a|bc)+)*ax/
+    aax
+ 0: aax
+ 1: a
+ 2: a
+
+/(a|x)*ab/
+    cab
+ 0: ab
+
+/(a)*ab/
+    cab
+ 0: ab
+
+/(?:(?i)a)b/
+    ab
+ 0: ab
+
+/((?i)a)b/
+    ab
+ 0: ab
+ 1: a
+
+/(?:(?i)a)b/
+    Ab
+ 0: Ab
+
+/((?i)a)b/
+    Ab
+ 0: Ab
+ 1: A
+
+/(?:(?i)a)b/
+    *** Failers
+No match
+    cb
+No match
+    aB
+No match
+
+/((?i)a)b/
+
+/(?i:a)b/
+    ab
+ 0: ab
+
+/((?i:a))b/
+    ab
+ 0: ab
+ 1: a
+
+/(?i:a)b/
+    Ab
+ 0: Ab
+
+/((?i:a))b/
+    Ab
+ 0: Ab
+ 1: A
+
+/(?i:a)b/
+    *** Failers
+No match
+    aB
+No match
+    aB
+No match
+
+/((?i:a))b/
+
+/(?:(?-i)a)b/i
+    ab
+ 0: ab
+
+/((?-i)a)b/i
+    ab
+ 0: ab
+ 1: a
+
+/(?:(?-i)a)b/i
+    aB
+ 0: aB
+
+/((?-i)a)b/i
+    aB
+ 0: aB
+ 1: a
+
+/(?:(?-i)a)b/i
+    *** Failers
+No match
+    aB
+ 0: aB
+    Ab
+No match
+
+/((?-i)a)b/i
+
+/(?:(?-i)a)b/i
+    aB
+ 0: aB
+
+/((?-i)a)b/i
+    aB
+ 0: aB
+ 1: a
+
+/(?:(?-i)a)b/i
+    *** Failers
+No match
+    Ab
+No match
+    AB
+No match
+
+/((?-i)a)b/i
+
+/(?-i:a)b/i
+    ab
+ 0: ab
+
+/((?-i:a))b/i
+    ab
+ 0: ab
+ 1: a
+
+/(?-i:a)b/i
+    aB
+ 0: aB
+
+/((?-i:a))b/i
+    aB
+ 0: aB
+ 1: a
+
+/(?-i:a)b/i
+    *** Failers
+No match
+    AB
+No match
+    Ab
+No match
+
+/((?-i:a))b/i
+
+/(?-i:a)b/i
+    aB
+ 0: aB
+
+/((?-i:a))b/i
+    aB
+ 0: aB
+ 1: a
+
+/(?-i:a)b/i
+    *** Failers
+No match
+    Ab
+No match
+    AB
+No match
+
+/((?-i:a))b/i
+
+/((?-i:a.))b/i
+    *** Failers
+No match
+    AB
+No match
+    a\nB
+No match
+
+/((?s-i:a.))b/i
+    a\nB
+ 0: a\x0aB
+ 1: a\x0a
+
+/(?:c|d)(?:)(?:a(?:)(?:b)(?:b(?:))(?:b(?:)(?:b)))/
+    cabbbb
+ 0: cabbbb
+
+/(?:c|d)(?:)(?:aaaaaaaa(?:)(?:bbbbbbbb)(?:bbbbbbbb(?:))(?:bbbbbbbb(?:)(?:bbbbbbbb)))/
+    caaaaaaaabbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbb
+ 0: caaaaaaaabbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbb
+
+/(ab)\d\1/i
+    Ab4ab
+ 0: Ab4ab
+ 1: Ab
+    ab4Ab
+ 0: ab4Ab
+ 1: ab
+
+/foo\w*\d{4}baz/
+    foobar1234baz
+ 0: foobar1234baz
+
+/x(~~)*(?:(?:F)?)?/
+    x~~
+ 0: x~~
+ 1: ~~
+
+/^a(?#xxx){3}c/
+    aaac
+ 0: aaac
+
+/^a (?#xxx) (?#yyy) {3}c/x
+    aaac
+ 0: aaac
+
+/(?<![cd])b/
+    *** Failers
+No match
+    B\nB
+No match
+    dbcb
+No match
+
+/(?<![cd])[ab]/
+    dbaacb
+ 0: a
+
+/(?<!(c|d))b/
+
+/(?<!(c|d))[ab]/
+    dbaacb
+ 0: a
+
+/(?<!cd)[ab]/
+    cdaccb
+ 0: b
+
+/^(?:a?b?)*$/
+    \
+ 0: 
+    a
+ 0: a
+    ab
+ 0: ab
+    aaa   
+ 0: aaa
+    *** Failers
+No match
+    dbcb
+No match
+    a--
+No match
+    aa-- 
+No match
+
+/((?s)^a(.))((?m)^b$)/
+    a\nb\nc\n
+ 0: a\x0ab
+ 1: a\x0a
+ 2: \x0a
+ 3: b
+
+/((?m)^b$)/
+    a\nb\nc\n
+ 0: b
+ 1: b
+
+/(?m)^b/
+    a\nb\n
+ 0: b
+
+/(?m)^(b)/
+    a\nb\n
+ 0: b
+ 1: b
+
+/((?m)^b)/
+    a\nb\n
+ 0: b
+ 1: b
+
+/\n((?m)^b)/
+    a\nb\n
+ 0: \x0ab
+ 1: b
+
+/((?s).)c(?!.)/
+    a\nb\nc\n
+ 0: \x0ac
+ 1: \x0a
+    a\nb\nc\n
+ 0: \x0ac
+ 1: \x0a
+
+/((?s)b.)c(?!.)/
+    a\nb\nc\n
+ 0: b\x0ac
+ 1: b\x0a
+    a\nb\nc\n
+ 0: b\x0ac
+ 1: b\x0a
+
+/^b/
+
+/()^b/
+    *** Failers
+No match
+    a\nb\nc\n
+No match
+    a\nb\nc\n
+No match
+
+/((?m)^b)/
+    a\nb\nc\n
+ 0: b
+ 1: b
+
+/(x)?(?(1)a|b)/
+    *** Failers
+No match
+    a
+No match
+    a
+No match
+
+/(x)?(?(1)b|a)/
+    a
+ 0: a
+
+/()?(?(1)b|a)/
+    a
+ 0: a
+
+/()(?(1)b|a)/
+
+/()?(?(1)a|b)/
+    a
+ 0: a
+ 1: 
+
+/^(\()?blah(?(1)(\)))$/
+    (blah)
+ 0: (blah)
+ 1: (
+ 2: )
+    blah
+ 0: blah
+    *** Failers
+No match
+    a
+No match
+    blah)
+No match
+    (blah
+No match
+
+/^(\(+)?blah(?(1)(\)))$/
+    (blah)
+ 0: (blah)
+ 1: (
+ 2: )
+    blah
+ 0: blah
+    *** Failers
+No match
+    blah)
+No match
+    (blah
+No match
+
+/(?(?!a)a|b)/
+
+/(?(?!a)b|a)/
+    a
+ 0: a
+
+/(?(?=a)b|a)/
+    *** Failers
+No match
+    a
+No match
+    a
+No match
+
+/(?(?=a)a|b)/
+    a
+ 0: a
+
+/(?=(a+?))(\1ab)/
+    aaab
+ 0: aab
+ 1: a
+ 2: aab
+
+/^(?=(a+?))\1ab/
+
+/(\w+:)+/
+    one:
+ 0: one:
+ 1: one:
+
+/$(?<=^(a))/
+    a
+ 0: 
+ 1: a
+
+/(?=(a+?))(\1ab)/
+    aaab
+ 0: aab
+ 1: a
+ 2: aab
+
+/^(?=(a+?))\1ab/
+    *** Failers
+No match
+    aaab
+No match
+    aaab
+No match
+
+/([\w:]+::)?(\w+)$/
+    abcd
+ 0: abcd
+ 1: <unset>
+ 2: abcd
+    xy:z:::abcd
+ 0: xy:z:::abcd
+ 1: xy:z:::
+ 2: abcd
+
+/^[^bcd]*(c+)/
+    aexycd
+ 0: aexyc
+ 1: c
+
+/(a*)b+/
+    caab
+ 0: aab
+ 1: aa
+
+/([\w:]+::)?(\w+)$/
+    abcd
+ 0: abcd
+ 1: <unset>
+ 2: abcd
+    xy:z:::abcd
+ 0: xy:z:::abcd
+ 1: xy:z:::
+ 2: abcd
+    *** Failers
+ 0: Failers
+ 1: <unset>
+ 2: Failers
+    abcd:
+No match
+    abcd:
+No match
+
+/^[^bcd]*(c+)/
+    aexycd
+ 0: aexyc
+ 1: c
+
+/(>a+)ab/
+
+/(?>a+)b/
+    aaab
+ 0: aaab
+
+/([[:]+)/
+    a:[b]:
+ 0: :[
+ 1: :[
+
+/([[=]+)/
+    a=[b]=
+ 0: =[
+ 1: =[
+
+/([[.]+)/
+    a.[b].
+ 0: .[
+ 1: .[
+
+/((?>a+)b)/
+    aaab
+ 0: aaab
+ 1: aaab
+
+/(?>(a+))b/
+    aaab
+ 0: aaab
+ 1: aaa
+
+/((?>[^()]+)|\([^()]*\))+/
+    ((abc(ade)ufh()()x
+ 0: abc(ade)ufh()()x
+ 1: x
+
+/a\Z/
+    *** Failers
+No match
+    aaab
+No match
+    a\nb\n
+No match
+
+/b\Z/
+    a\nb\n
+ 0: b
+
+/b\z/
+
+/b\Z/
+    a\nb
+ 0: b
+
+/b\z/
+    a\nb
+ 0: b
+    *** Failers
+No match
+    
+/^(?>(?(1)\.|())[^\W_](?>[a-z0-9-]*[^\W_])?)+$/
+    a
+ 0: a
+ 1: 
+    abc
+ 0: abc
+ 1: 
+    a-b
+ 0: a-b
+ 1: 
+    0-9 
+ 0: 0-9
+ 1: 
+    a.b
+ 0: a.b
+ 1: 
+    5.6.7  
+ 0: 5.6.7
+ 1: 
+    the.quick.brown.fox
+ 0: the.quick.brown.fox
+ 1: 
+    a100.b200.300c  
+ 0: a100.b200.300c
+ 1: 
+    12-ab.1245 
+ 0: 12-ab.1245
+ 1: 
+    *** Failers
+No match
+    \
+No match
+    .a
+No match
+    -a
+No match
+    a-
+No match
+    a.  
+No match
+    a_b 
+No match
+    a.-
+No match
+    a..  
+No match
+    ab..bc 
+No match
+    the.quick.brown.fox-
+No match
+    the.quick.brown.fox.
+No match
+    the.quick.brown.fox_
+No match
+    the.quick.brown.fox+       
+No match
+
+/(?>.*)(?<=(abcd|wxyz))/
+    alphabetabcd
+ 0: alphabetabcd
+ 1: abcd
+    endingwxyz
+ 0: endingwxyz
+ 1: wxyz
+    *** Failers
+No match
+    a rather long string that doesn't end with one of them
+No match
+
+/word (?>(?:(?!otherword)[a-zA-Z0-9]+ ){0,30})otherword/
+    word cat dog elephant mussel cow horse canary baboon snake shark otherword
+ 0: word cat dog elephant mussel cow horse canary baboon snake shark otherword
+    word cat dog elephant mussel cow horse canary baboon snake shark
+No match
+  
+/word (?>[a-zA-Z0-9]+ ){0,30}otherword/
+    word cat dog elephant mussel cow horse canary baboon snake shark the quick brown fox and the lazy dog and several other words getting close to thirty by now I hope
+No match
+
+/(?<=\d{3}(?!999))foo/
+    999foo
+ 0: foo
+    123999foo 
+ 0: foo
+    *** Failers
+No match
+    123abcfoo
+No match
+    
+/(?<=(?!...999)\d{3})foo/
+    999foo
+ 0: foo
+    123999foo 
+ 0: foo
+    *** Failers
+No match
+    123abcfoo
+No match
+
+/(?<=\d{3}(?!999)...)foo/
+    123abcfoo
+ 0: foo
+    123456foo 
+ 0: foo
+    *** Failers
+No match
+    123999foo  
+No match
+    
+/(?<=\d{3}...)(?<!999)foo/
+    123abcfoo   
+ 0: foo
+    123456foo 
+ 0: foo
+    *** Failers
+No match
+    123999foo  
+No match
+
+/<a[\s]+href[\s]*=[\s]*          # find <a href=
+ ([\"\'])?                       # find single or double quote
+ (?(1) (.*?)\1 | ([^\s]+))       # if quote found, match up to next matching
+                                 # quote, otherwise match up to next space
+/isx
+    <a href=abcd xyz
+ 0: <a href=abcd
+ 1: <unset>
+ 2: <unset>
+ 3: abcd
+    <a href=\"abcd xyz pqr\" cats
+ 0: <a href="abcd xyz pqr"
+ 1: "
+ 2: abcd xyz pqr
+    <a href=\'abcd xyz pqr\' cats
+ 0: <a href='abcd xyz pqr'
+ 1: '
+ 2: abcd xyz pqr
+
+/<a\s+href\s*=\s*                # find <a href=
+ (["'])?                         # find single or double quote
+ (?(1) (.*?)\1 | (\S+))          # if quote found, match up to next matching
+                                 # quote, otherwise match up to next space
+/isx
+    <a href=abcd xyz
+ 0: <a href=abcd
+ 1: <unset>
+ 2: <unset>
+ 3: abcd
+    <a href=\"abcd xyz pqr\" cats
+ 0: <a href="abcd xyz pqr"
+ 1: "
+ 2: abcd xyz pqr
+    <a href       =       \'abcd xyz pqr\' cats
+ 0: <a href       =       'abcd xyz pqr'
+ 1: '
+ 2: abcd xyz pqr
+
+/<a\s+href(?>\s*)=(?>\s*)        # find <a href=
+ (["'])?                         # find single or double quote
+ (?(1) (.*?)\1 | (\S+))          # if quote found, match up to next matching
+                                 # quote, otherwise match up to next space
+/isx
+    <a href=abcd xyz
+ 0: <a href=abcd
+ 1: <unset>
+ 2: <unset>
+ 3: abcd
+    <a href=\"abcd xyz pqr\" cats
+ 0: <a href="abcd xyz pqr"
+ 1: "
+ 2: abcd xyz pqr
+    <a href       =       \'abcd xyz pqr\' cats
+ 0: <a href       =       'abcd xyz pqr'
+ 1: '
+ 2: abcd xyz pqr
+
+/((Z)+|A)*/
+    ZABCDEFG
+ 0: ZA
+ 1: A
+ 2: Z
+
+/(Z()|A)*/
+    ZABCDEFG
+ 0: ZA
+ 1: A
+ 2: 
+
+/(Z(())|A)*/
+    ZABCDEFG
+ 0: ZA
+ 1: A
+ 2: 
+ 3: 
+
+/((?>Z)+|A)*/
+    ZABCDEFG
+ 0: ZA
+ 1: A
+
+/((?>)+|A)*/
+    ZABCDEFG
+ 0: 
+ 1: 
+
+/a*/g
+    abbab
+ 0: a
+ 0: 
+ 0: 
+ 0: a
+ 0: 
+ 0: 
+
+/^[a-\d]/
+    abcde
+ 0: a
+    -things
+ 0: -
+    0digit
+ 0: 0
+    *** Failers
+No match
+    bcdef    
+No match
+
+/^[\d-a]/
+    abcde
+ 0: a
+    -things
+ 0: -
+    0digit
+ 0: 0
+    *** Failers
+No match
+    bcdef    
+No match
+    
+/[[:space:]]+/
+    > \x09\x0a\x0c\x0d\x0b<
+ 0:  \x09\x0a\x0c\x0d\x0b
+     
+/[[:blank:]]+/
+    > \x09\x0a\x0c\x0d\x0b<
+ 0:  \x09
+     
+/[\s]+/
+    > \x09\x0a\x0c\x0d\x0b<
+ 0:  \x09\x0a\x0c\x0d
+     
+/\s+/
+    > \x09\x0a\x0c\x0d\x0b<
+ 0:  \x09\x0a\x0c\x0d
+     
+/ab/x
+    ab
+No match
+
+/(?!\A)x/m
+  a\nxb\n
+ 0: x
+
+/(?!^)x/m
+  a\nxb\n
+No match
+
+/abc\Qabc\Eabc/
+    abcabcabc
+ 0: abcabcabc
+    
+/abc\Q(*+|\Eabc/
+    abc(*+|abc 
+ 0: abc(*+|abc
+
+/   abc\Q abc\Eabc/x
+    abc abcabc
+ 0: abc abcabc
+    *** Failers
+No match
+    abcabcabc  
+No match
+    
+/abc#comment
+    \Q#not comment
+    literal\E/x
+    abc#not comment\n    literal     
+ 0: abc#not comment\x0a    literal
+
+/abc#comment
+    \Q#not comment
+    literal/x
+    abc#not comment\n    literal     
+ 0: abc#not comment\x0a    literal
+
+/abc#comment
+    \Q#not comment
+    literal\E #more comment
+    /x
+    abc#not comment\n    literal     
+ 0: abc#not comment\x0a    literal
+
+/abc#comment
+    \Q#not comment
+    literal\E #more comment/x
+    abc#not comment\n    literal     
+ 0: abc#not comment\x0a    literal
+
+/\Qabc\$xyz\E/
+    abc\\\$xyz
+ 0: abc\$xyz
+
+/\Qabc\E\$\Qxyz\E/
+    abc\$xyz
+ 0: abc$xyz
+
+/\Gabc/
+    abc
+ 0: abc
+    *** Failers
+No match
+    xyzabc  
+No match
+
+/\Gabc./g
+    abc1abc2xyzabc3
+ 0: abc1
+ 0: abc2
+
+/abc./g
+    abc1abc2xyzabc3 
+ 0: abc1
+ 0: abc2
+ 0: abc3
+
+/a(?x: b c )d/
+    XabcdY
+ 0: abcd
+    *** Failers 
+No match
+    Xa b c d Y 
+No match
+
+/((?x)x y z | a b c)/
+    XabcY
+ 0: abc
+ 1: abc
+    AxyzB 
+ 0: xyz
+ 1: xyz
+
+/(?i)AB(?-i)C/
+    XabCY
+ 0: abC
+    *** Failers
+No match
+    XabcY  
+No match
+
+/((?i)AB(?-i)C|D)E/
+    abCE
+ 0: abCE
+ 1: abC
+    DE
+ 0: DE
+ 1: D
+    *** Failers
+No match
+    abcE
+No match
+    abCe  
+No match
+    dE
+No match
+    De    
+No match
+
+/(.*)\d+\1/
+    abc123abc
+ 0: abc123abc
+ 1: abc
+    abc123bc 
+ 0: bc123bc
+ 1: bc
+
+/(.*)\d+\1/s
+    abc123abc
+ 0: abc123abc
+ 1: abc
+    abc123bc 
+ 0: bc123bc
+ 1: bc
+    
+/((.*))\d+\1/
+    abc123abc
+ 0: abc123abc
+ 1: abc
+ 2: abc
+    abc123bc  
+ 0: bc123bc
+ 1: bc
+ 2: bc
+
+/-- This tests for an IPv6 address in the form where it can have up to --/
+/-- eight components, one and only one of which is empty. This must be --/
+No match
+/-- an internal component. --/
+No match
+
+/^(?!:)                       # colon disallowed at start
+  (?:                         # start of item
+    (?: [0-9a-f]{1,4} |       # 1-4 hex digits or
+    (?(1)0 | () ) )           # if null previously matched, fail; else null
+    :                         # followed by colon
+  ){1,7}                      # end item; 1-7 of them required               
+  [0-9a-f]{1,4} $             # final hex number at end of string
+  (?(1)|.)                    # check that there was an empty component
+  /xi
+    a123::a123
+ 0: a123::a123
+ 1: 
+    a123:b342::abcd
+ 0: a123:b342::abcd
+ 1: 
+    a123:b342::324e:abcd
+ 0: a123:b342::324e:abcd
+ 1: 
+    a123:ddde:b342::324e:abcd
+ 0: a123:ddde:b342::324e:abcd
+ 1: 
+    a123:ddde:b342::324e:dcba:abcd
+ 0: a123:ddde:b342::324e:dcba:abcd
+ 1: 
+    a123:ddde:9999:b342::324e:dcba:abcd
+ 0: a123:ddde:9999:b342::324e:dcba:abcd
+ 1: 
+    *** Failers
+No match
+    1:2:3:4:5:6:7:8
+No match
+    a123:bce:ddde:9999:b342::324e:dcba:abcd
+No match
+    a123::9999:b342::324e:dcba:abcd
+No match
+    abcde:2:3:4:5:6:7:8
+No match
+    ::1
+No match
+    abcd:fee0:123::   
+No match
+    :1
+No match
+    1:  
+No match
+
+/[z\Qa-d]\E]/
+    z
+ 0: z
+    a
+ 0: a
+    -
+ 0: -
+    d
+ 0: d
+    ] 
+ 0: ]
+    *** Failers
+ 0: a
+    b     
+No match
+
+/[\z\C]/
+    z
+ 0: z
+    C 
+ 0: C
+    
+/\M/
+    M 
+ 0: M
+    
+/(a+)*b/
+    aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa 
+No match
+    
+/(?i)reg(?:ul(?:[aä]|ae)r|ex)/
+    REGular
+ 0: REGular
+    regulaer
+ 0: regulaer
+    Regex  
+ 0: Regex
+    regulär 
+ 0: regul\xe4r
+
+/Åæåä[à-ÿÀ-ß]+/
+    Åæåäà
+ 0: \xc5\xe6\xe5\xe4\xe0
+    Åæåäÿ
+ 0: \xc5\xe6\xe5\xe4\xff
+    ÅæåäÀ
+ 0: \xc5\xe6\xe5\xe4\xc0
+    Åæåäß
+ 0: \xc5\xe6\xe5\xe4\xdf
+
+/(?<=Z)X./
+  \x84XAZXB
+ 0: XB
+
+/ab cd (?x) de fg/
+    ab cd defg
+ 0: ab cd defg
+
+/ab cd(?x) de fg/
+    ab cddefg
+ 0: ab cddefg
+    ** Failers 
+No match
+    abcddefg
+No match
+
+/(?<![^f]oo)(bar)/
+    foobarX 
+ 0: bar
+ 1: bar
+    ** Failers 
+No match
+    boobarX
+No match
+
+/(?<![^f])X/
+    offX
+ 0: X
+    ** Failers
+No match
+    onyX  
+No match
+
+/(?<=[^f])X/
+    onyX
+ 0: X
+    ** Failers
+No match
+    offX 
+No match
+
+/^/mg
+    a\nb\nc\n
+ 0: 
+ 0: 
+ 0: 
+    \ 
+ 0: 
+    
+/(?<=C\n)^/mg
+    A\nC\nC\n 
+ 0: 
+
+/(?:(?(1)a|b)(X))+/
+    bXaX
+ 0: bXaX
+ 1: X
+
+/(?:(?(1)\1a|b)(X|Y))+/
+    bXXaYYaY
+ 0: bXXaYYaY
+ 1: Y
+    bXYaXXaX  
+ 0: bX
+ 1: X
+
+/()()()()()()()()()(?:(?(10)\10a|b)(X|Y))+/
+    bXXaYYaY
+ 0: bX
+ 1: 
+ 2: 
+ 3: 
+ 4: 
+ 5: 
+ 6: 
+ 7: 
+ 8: 
+ 9: 
+10: X
+
+/[[,abc,]+]/
+    abc]
+ 0: abc]
+    a,b]
+ 0: a,b]
+    [a,b,c]  
+ 0: [a,b,c]
+
+/(?-x: )/x
+    A\x20B
+ 0:  
+    
+"(?x)(?-x: \s*#\s*)"
+    A # B
+ 0:  # 
+    ** Failers
+No match
+    #  
+No match
+
+"(?x-is)(?:(?-ixs) \s*#\s*) include"
+    A #include
+ 0:  #include
+    ** Failers
+No match
+    A#include  
+No match
+    A #Include
+No match
+
+/a*b*\w/
+    aaabbbb
+ 0: aaabbbb
+    aaaa
+ 0: aaaa
+    a
+ 0: a
+
+/a*b?\w/
+    aaabbbb
+ 0: aaabb
+    aaaa
+ 0: aaaa
+    a
+ 0: a
+
+/a*b{0,4}\w/
+    aaabbbb
+ 0: aaabbbb
+    aaaa
+ 0: aaaa
+    a
+ 0: a
+
+/a*b{0,}\w/
+    aaabbbb
+ 0: aaabbbb
+    aaaa
+ 0: aaaa
+    a
+ 0: a
+    
+/a*\d*\w/
+    0a
+ 0: 0a
+    a 
+ 0: a
+    
+/a*b *\w/x
+    a 
+ 0: a
+
+/a*b#comment
+  *\w/x
+    a 
+ 0: a
+
+/a* b *\w/x
+    a 
+ 0: a
+
+/^\w+=.*(\\\n.*)*/
+    abc=xyz\\\npqr
+ 0: abc=xyz\
+
+/(?=(\w+))\1:/
+    abcd:
+ 0: abcd:
+ 1: abcd
+
+/^(?=(\w+))\1:/
+    abcd:
+ 0: abcd:
+ 1: abcd
+
+/^\Eabc/
+    abc
+ 0: abc
+    
+/^[\Eabc]/
+    a
+ 0: a
+    ** Failers 
+No match
+    E 
+No match
+    
+/^[a-\Ec]/
+    b
+ 0: b
+    ** Failers
+No match
+    -
+No match
+    E    
+No match
+
+/^[a\E\E-\Ec]/
+    b
+ 0: b
+    ** Failers
+No match
+    -
+No match
+    E    
+No match
+
+/^[\E\Qa\E-\Qz\E]+/
+    b
+ 0: b
+    ** Failers
+No match
+    -  
+No match
+    
+/^[a\Q]bc\E]/
+    a
+ 0: a
+    ]
+ 0: ]
+    c
+ 0: c
+    
+/^[a-\Q\E]/
+    a
+ 0: a
+    -     
+ 0: -
+
+/^(a()*)*/
+    aaaa
+ 0: aaaa
+ 1: a
+ 2: 
+
+/^(?:a(?:(?:))*)*/
+    aaaa
+ 0: aaaa
+
+/^(a()+)+/
+    aaaa
+ 0: aaaa
+ 1: a
+ 2: 
+
+/^(?:a(?:(?:))+)+/
+    aaaa
+ 0: aaaa
+
+/(a){0,3}(?(1)b|(c|))*D/
+    abbD
+ 0: abbD
+ 1: a
+    ccccD
+ 0: ccccD
+ 1: <unset>
+ 2: 
+    D  
+ 0: D
+ 1: <unset>
+ 2: 
+
+/(a|)*\d/
+  aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+No match
+  aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa4
+ 0: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa4
+ 1: 
+
+/(?>a|)*\d/
+  aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+No match
+  aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa4
+ 0: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa4
+
+/(?:a|)*\d/
+  aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+No match
+  aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa4
+ 0: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa4
+
+/\Z/g
+  abc\n
+ 0: 
+ 0: 
+  
+/^(?s)(?>.*)(?<!\n)/
+  abc
+ 0: abc
+  abc\n  
+No match
+
+/^(?![^\n]*\n\z)/
+  abc
+ 0: 
+  abc\n 
+No match
+  
+/\z(?<!\n)/
+  abc
+ 0: 
+  abc\n  
+No match
+
+/(.*(.)?)*/
+    abcd
+ 0: abcd
+ 1: 
+
+/( (A | (?(1)0|) )*   )/x
+    abcd
+ 0: 
+ 1: 
+ 2: 
+
+/( ( (?(1)0|) )*   )/x
+    abcd
+ 0: 
+ 1: 
+ 2: 
+
+/(  (?(1)0|)*   )/x
+    abcd
+ 0: 
+ 1: 
+
+/[[:abcd:xyz]]/
+    a]
+ 0: a]
+    :] 
+ 0: :]
+    
+/[abc[:x\]pqr]/
+    a
+ 0: a
+    [
+ 0: [
+    :
+ 0: :
+    ]
+ 0: ]
+    p    
+ 0: p
+
+/.*[op][xyz]/
+    fooabcfoo
+No match
+
+/(?(?=.*b)b|^)/
+   adc
+ 0: 
+   abc 
+ 0: b
+
+/(?(?=^.*b)b|^)/
+   adc
+ 0: 
+   abc 
+No match
+
+/(?(?=.*b)b|^)*/
+   adc
+ 0: 
+   abc 
+ 0: 
+
+/(?(?=.*b)b|^)+/
+   adc
+ 0: 
+   abc 
+ 0: b
+
+/(?(?=b).*b|^d)/
+    abc
+ 0: b
+
+/(?(?=.*b).*b|^d)/
+    abc
+ 0: ab
+
+/^%((?(?=[a])[^%])|b)*%$/
+    %ab%
+ 0: %ab%
+ 1: 
+
+/(?i)a(?-i)b|c/
+    XabX
+ 0: ab
+    XAbX
+ 0: Ab
+    CcC 
+ 0: c
+    ** Failers
+No match
+    XABX   
+No match
+
+/[\x00-\xff\s]+/
+    \x0a\x0b\x0c\x0d
+ 0: \x0a\x0b\x0c\x0d
+
+/^\c/
+    ?
+ 0: ?
+
+/(abc)\1/i
+   abc
+No match
+
+/(abc)\1/
+   abc
+No match
+
+/[^a]*/i
+    12abc
+ 0: 12
+    12ABC
+ 0: 12
+
+/[^a]*+/i
+    12abc
+ 0: 12
+    12ABC
+ 0: 12
+
+/[^a]*?X/i
+    ** Failers
+No match
+    12abc
+No match
+    12ABC
+No match
+    
+/[^a]+?X/i   
+    ** Failers
+No match
+    12abc
+No match
+    12ABC
+No match
+
+/[^a]?X/i
+    12aXbcX
+ 0: X
+    12AXBCX
+ 0: X
+    BCX 
+ 0: CX
+
+/[^a]??X/i
+    12aXbcX
+ 0: X
+    12AXBCX
+ 0: X
+    BCX
+ 0: CX
+    
+/[^a]?+X/i
+    12aXbcX
+ 0: cX
+    12AXBCX
+ 0: CX
+    BCX 
+ 0: CX
+
+/[^a]{2,3}/i
+    abcdef
+ 0: bcd
+    ABCDEF  
+ 0: BCD
+
+/[^a]{2,3}?/i
+    abcdef
+ 0: bc
+    ABCDEF  
+ 0: BC
+
+/[^a]{2,3}+/i
+    abcdef
+ 0: bcd
+    ABCDEF  
+ 0: BCD
+
+/((a|)+)+Z/
+    Z
+ 0: Z
+ 1: 
+ 2: 
+
+/(a)b|(a)c/
+    ac
+ 0: ac
+ 1: <unset>
+ 2: a
+
+/(?>(a))b|(a)c/
+    ac
+ 0: ac
+ 1: <unset>
+ 2: a
+
+/(?=(a))ab|(a)c/
+    ac
+ 0: ac
+ 1: <unset>
+ 2: a
+
+/((?>(a))b|(a)c)/
+    ac
+ 0: ac
+ 1: ac
+ 2: <unset>
+ 3: a
+
+/((?>(a))b|(a)c)++/
+    ac
+ 0: ac
+ 1: ac
+ 2: <unset>
+ 3: a
+
+/(?:(?>(a))b|(a)c)++/
+    ac
+ 0: ac
+ 1: <unset>
+ 2: a
+
+/(?=(?>(a))b|(a)c)(..)/
+    ac
+ 0: ac
+ 1: <unset>
+ 2: a
+ 3: ac
+
+/(?>(?>(a))b|(a)c)/
+    ac
+ 0: ac
+ 1: <unset>
+ 2: a
+
+/(?:(?>([ab])))+a=/+
+    =ba=
+ 0: ba=
+ 0+ 
+ 1: b
+
+/(?>([ab]))+a=/+
+    =ba=
+ 0: ba=
+ 0+ 
+ 1: b
+
+/((?>(a+)b)+(aabab))/
+    aaaabaaabaabab
+ 0: aaaabaaabaabab
+ 1: aaaabaaabaabab
+ 2: aaa
+ 3: aabab
+
+/(?>a+|ab)+?c/
+    aabc
+No match
+
+/(?>a+|ab)+c/
+    aabc
+No match
+
+/(?:a+|ab)+c/
+    aabc
+ 0: aabc
+
+/(?(?=(a))a)/
+    a
+ 0: a
+ 1: a
+
+/(?(?=(a))a)(b)/
+    ab
+ 0: ab
+ 1: a
+ 2: b
+
+/^(?:a|ab)++c/
+    aaaabc
+No match
+
+/^(?>a|ab)++c/
+    aaaabc
+No match
+
+/^(?:a|ab)+c/
+    aaaabc
+ 0: aaaabc
+
+/(?=abc){3}abc/+
+    abcabcabc
+ 0: abc
+ 0+ abcabc
+    ** Failers
+No match
+    xyz  
+No match
+    
+/(?=abc)+abc/+
+    abcabcabc
+ 0: abc
+ 0+ abcabc
+    ** Failers
+No match
+    xyz  
+No match
+    
+/(?=abc)++abc/+
+    abcabcabc
+ 0: abc
+ 0+ abcabc
+    ** Failers
+No match
+    xyz  
+No match
+    
+/(?=abc){0}xyz/
+    xyz 
+ 0: xyz
+
+/(?=abc){1}xyz/
+    ** Failers
+No match
+    xyz 
+No match
+    
+/(?=(a))?./
+    ab
+ 0: a
+ 1: a
+    bc
+ 0: b
+      
+/(?=(a))??./
+    ab
+ 0: a
+    bc
+ 0: b
+
+/^(?=(a)){0}b(?1)/
+    backgammon
+ 0: ba
+
+/^(?=(?1))?[az]([abc])d/
+    abd 
+ 0: abd
+ 1: b
+    zcdxx 
+ 0: zcd
+ 1: c
+
+/^(?!a){0}\w+/
+    aaaaa
+ 0: aaaaa
+
+/(?<=(abc))?xyz/
+    abcxyz
+ 0: xyz
+ 1: abc
+    pqrxyz 
+ 0: xyz
+
+/^[\g<a>]+/
+    ggg<<<aaa>>>
+ 0: ggg<<<aaa>>>
+    ** Failers
+No match
+    \\ga  
+No match
+    
+/^[\ga]+/
+    gggagagaxyz 
+ 0: gggagaga
+    
+/^[:a[:digit:]]+/
+    aaaa444:::Z 
+ 0: aaaa444:::
+
+/^[:a[:digit:]:b]+/
+    aaaa444:::bbbZ 
+ 0: aaaa444:::bbb
+
+/[:a]xxx[b:]/
+     :xxx:
+ 0: :xxx:
+     
+/(?<=a{2})b/i
+    xaabc
+ 0: b
+    ** Failers
+No match
+    xabc  
+No match
+
+/(?<!a{2})b/i
+    xabc
+ 0: b
+    ** Failers
+No match
+    xaabc  
+No match
+
+/(?<=a\h)c/
+    xa c
+ 0: c
+    
+/(?<=[^a]{2})b/
+    axxbc
+ 0: b
+    aAAbc 
+ 0: b
+    ** Failers
+No match
+    xaabc    
+No match
+
+/(?<=[^a]{2})b/i
+    axxbc  
+ 0: b
+    ** Failers
+No match
+    aAAbc 
+No match
+    xaabc    
+No match
+
+/(?<=a\H)c/
+    abc
+ 0: c
+
+/(?<=a\V)c/
+    abc
+ 0: c
+    
+/(?<=a\v)c/
+    a\nc
+ 0: c
+
+/(?(?=c)c|d)++Y/
+    XcccddYX
+ 0: cccddY
+
+/(?(?=c)c|d)*+Y/
+    XcccddYX
+ 0: cccddY
+
+/^(a{2,3}){2,}+a/
+    aaaaaaa
+ 0: aaaaaaa
+ 1: aaa
+    ** Failers
+No match
+    aaaaaa
+No match
+    aaaaaaaaa 
+No match
+
+/^(a{2,3})++a/
+    ** Failers
+No match
+    aaaaaa
+No match
+
+/^(a{2,3})*+a/
+    ** Failers
+No match
+    aaaaaa
+No match
+
+/ab\Cde/
+    abXde
+ 0: abXde
+    
+/(?<=ab\Cde)X/
+    abZdeX
+ 0: X
+
+/a[\CD]b/
+    aCb
+ 0: aCb
+    aDb 
+ 0: aDb
+
+/a[\C-X]b/
+    aJb
+ 0: aJb
+
+/\H\h\V\v/
+    X X\x0a
+ 0: X X\x0a
+    X\x09X\x0b
+ 0: X\x09X\x0b
+    ** Failers
+No match
+    \xa0 X\x0a   
+No match
+    
+/\H*\h+\V?\v{3,4}/ 
+    \x09\x20\xa0X\x0a\x0b\x0c\x0d\x0a
+ 0: \x09 \xa0X\x0a\x0b\x0c\x0d
+    \x09\x20\xa0\x0a\x0b\x0c\x0d\x0a
+ 0: \x09 \xa0\x0a\x0b\x0c\x0d
+    \x09\x20\xa0\x0a\x0b\x0c
+ 0: \x09 \xa0\x0a\x0b\x0c
+    ** Failers 
+No match
+    \x09\x20\xa0\x0a\x0b
+No match
+     
+/\H{3,4}/
+    XY  ABCDE
+ 0: ABCD
+    XY  PQR ST 
+ 0: PQR
+    
+/.\h{3,4}./
+    XY  AB    PQRS
+ 0: B    P
+
+/\h*X\h?\H+Y\H?Z/
+    >XNNNYZ
+ 0: XNNNYZ
+    >  X NYQZ
+ 0:   X NYQZ
+    ** Failers
+No match
+    >XYZ   
+No match
+    >  X NY Z
+No match
+
+/\v*X\v?Y\v+Z\V*\x0a\V+\x0b\V{2,3}\x0c/
+    >XY\x0aZ\x0aA\x0bNN\x0c
+ 0: XY\x0aZ\x0aA\x0bNN\x0c
+    >\x0a\x0dX\x0aY\x0a\x0bZZZ\x0aAAA\x0bNNN\x0c
+ 0: \x0a\x0dX\x0aY\x0a\x0bZZZ\x0aAAA\x0bNNN\x0c
+
+/(foo)\Kbar/
+    foobar
+ 0: bar
+ 1: foo
+   
+/(foo)(\Kbar|baz)/
+    foobar
+ 0: bar
+ 1: foo
+ 2: bar
+    foobaz 
+ 0: foobaz
+ 1: foo
+ 2: baz
+
+/(foo\Kbar)baz/
+    foobarbaz
+ 0: barbaz
+ 1: foobar
+
+/abc\K|def\K/g+
+    Xabcdefghi
+ 0: 
+ 0+ defghi
+ 0: 
+ 0+ ghi
+
+/ab\Kc|de\Kf/g+
+    Xabcdefghi
+ 0: c
+ 0+ defghi
+ 0: f
+ 0+ ghi
+    
+/(?=C)/g+
+    ABCDECBA
+ 0: 
+ 0+ CDECBA
+ 0: 
+ 0+ CBA
+    
+/^abc\K/+
+    abcdef
+ 0: 
+ 0+ def
+    ** Failers
+No match
+    defabcxyz   
+No match
+
+/^(a(b))\1\g1\g{1}\g-1\g{-1}\g{-02}Z/
+    ababababbbabZXXXX
+ 0: ababababbbabZ
+ 1: ab
+ 2: b
+
+/(?<A>tom|bon)-\g{A}/
+    tom-tom
+ 0: tom-tom
+ 1: tom
+    bon-bon 
+ 0: bon-bon
+ 1: bon
+    
+/(^(a|b\g{-1}))/
+    bacxxx
+No match
+
+/(?|(abc)|(xyz))\1/
+    abcabc
+ 0: abcabc
+ 1: abc
+    xyzxyz 
+ 0: xyzxyz
+ 1: xyz
+    ** Failers
+No match
+    abcxyz
+No match
+    xyzabc   
+No match
+    
+/(?|(abc)|(xyz))(?1)/
+    abcabc
+ 0: abcabc
+ 1: abc
+    xyzabc 
+ 0: xyzabc
+ 1: xyz
+    ** Failers 
+No match
+    xyzxyz 
+No match
+ 
+/^X(?5)(a)(?|(b)|(q))(c)(d)(Y)/
+    XYabcdY
+ 0: XYabcdY
+ 1: a
+ 2: b
+ 3: c
+ 4: d
+ 5: Y
+
+/^X(?7)(a)(?|(b|(r)(s))|(q))(c)(d)(Y)/
+    XYabcdY
+ 0: XYabcdY
+ 1: a
+ 2: b
+ 3: <unset>
+ 4: <unset>
+ 5: c
+ 6: d
+ 7: Y
+
+/^X(?7)(a)(?|(b|(?|(r)|(t))(s))|(q))(c)(d)(Y)/
+    XYabcdY
+ 0: XYabcdY
+ 1: a
+ 2: b
+ 3: <unset>
+ 4: <unset>
+ 5: c
+ 6: d
+ 7: Y
+
+/(?'abc'\w+):\k<abc>{2}/
+    a:aaxyz
+ 0: a:aa
+ 1: a
+    ab:ababxyz
+ 0: ab:abab
+ 1: ab
+    ** Failers
+No match
+    a:axyz
+No match
+    ab:abxyz
+No match
+
+/(?'abc'\w+):\g{abc}{2}/
+    a:aaxyz
+ 0: a:aa
+ 1: a
+    ab:ababxyz
+ 0: ab:abab
+ 1: ab
+    ** Failers
+No match
+    a:axyz
+No match
+    ab:abxyz
+No match
+
+/^(?<ab>a)? (?(<ab>)b|c) (?('ab')d|e)/x
+    abd
+ 0: abd
+ 1: a
+    ce
+ 0: ce
+
+/^(a.)\g-1Z/
+    aXaXZ
+ 0: aXaXZ
+ 1: aX
+
+/^(a.)\g{-1}Z/
+    aXaXZ
+ 0: aXaXZ
+ 1: aX
+
+/^(?(DEFINE) (?<A> a) (?<B> b) )  (?&A) (?&B) /x
+    abcd
+ 0: ab
+
+/(?<NAME>(?&NAME_PAT))\s+(?<ADDR>(?&ADDRESS_PAT))
+  (?(DEFINE)
+  (?<NAME_PAT>[a-z]+)
+  (?<ADDRESS_PAT>\d+)
+  )/x
+    metcalfe 33
+ 0: metcalfe 33
+ 1: metcalfe
+ 2: 33
+
+/(?(DEFINE)(?<byte>2[0-4]\d|25[0-5]|1\d\d|[1-9]?\d))\b(?&byte)(\.(?&byte)){3}/
+    1.2.3.4
+ 0: 1.2.3.4
+ 1: <unset>
+ 2: .4
+    131.111.10.206
+ 0: 131.111.10.206
+ 1: <unset>
+ 2: .206
+    10.0.0.0
+ 0: 10.0.0.0
+ 1: <unset>
+ 2: .0
+    ** Failers
+No match
+    10.6
+No match
+    455.3.4.5
+No match
+
+/\b(?&byte)(\.(?&byte)){3}(?(DEFINE)(?<byte>2[0-4]\d|25[0-5]|1\d\d|[1-9]?\d))/
+    1.2.3.4
+ 0: 1.2.3.4
+ 1: .4
+    131.111.10.206
+ 0: 131.111.10.206
+ 1: .206
+    10.0.0.0
+ 0: 10.0.0.0
+ 1: .0
+    ** Failers
+No match
+    10.6
+No match
+    455.3.4.5
+No match
+
+/^(\w++|\s++)*$/
+    now is the time for all good men to come to the aid of the party
+ 0: now is the time for all good men to come to the aid of the party
+ 1: party
+    *** Failers
+No match
+    this is not a line with only words and spaces!
+No match
+
+/(\d++)(\w)/
+    12345a
+ 0: 12345a
+ 1: 12345
+ 2: a
+    *** Failers
+No match
+    12345+
+No match
+
+/a++b/
+    aaab
+ 0: aaab
+
+/(a++b)/
+    aaab
+ 0: aaab
+ 1: aaab
+
+/(a++)b/
+    aaab
+ 0: aaab
+ 1: aaa
+
+/([^()]++|\([^()]*\))+/
+    ((abc(ade)ufh()()x
+ 0: abc(ade)ufh()()x
+ 1: x
+
+/\(([^()]++|\([^()]+\))+\)/
+    (abc)
+ 0: (abc)
+ 1: abc
+    (abc(def)xyz)
+ 0: (abc(def)xyz)
+ 1: xyz
+    *** Failers
+No match
+    ((()aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+No match
+
+/^([^()]|\((?1)*\))*$/
+    abc
+ 0: abc
+ 1: c
+    a(b)c
+ 0: a(b)c
+ 1: c
+    a(b(c))d
+ 0: a(b(c))d
+ 1: d
+    *** Failers)
+No match
+    a(b(c)d
+No match
+
+/^>abc>([^()]|\((?1)*\))*<xyz<$/
+   >abc>123<xyz<
+ 0: >abc>123<xyz<
+ 1: 3
+   >abc>1(2)3<xyz<
+ 0: >abc>1(2)3<xyz<
+ 1: 3
+   >abc>(1(2)3)<xyz<
+ 0: >abc>(1(2)3)<xyz<
+ 1: (1(2)3)
+
+/^(?:((.)(?1)\2|)|((.)(?3)\4|.))$/i
+    1221
+ 0: 1221
+ 1: 1221
+ 2: 1
+    Satanoscillatemymetallicsonatas
+ 0: Satanoscillatemymetallicsonatas
+ 1: <unset>
+ 2: <unset>
+ 3: Satanoscillatemymetallicsonatas
+ 4: S
+    AmanaplanacanalPanama
+ 0: AmanaplanacanalPanama
+ 1: <unset>
+ 2: <unset>
+ 3: AmanaplanacanalPanama
+ 4: A
+    AblewasIereIsawElba
+ 0: AblewasIereIsawElba
+ 1: <unset>
+ 2: <unset>
+ 3: AblewasIereIsawElba
+ 4: A
+    *** Failers
+No match
+    Thequickbrownfox
+No match
+
+/^(\d+|\((?1)([+*-])(?1)\)|-(?1))$/
+    12
+ 0: 12
+ 1: 12
+    (((2+2)*-3)-7)
+ 0: (((2+2)*-3)-7)
+ 1: (((2+2)*-3)-7)
+ 2: -
+    -12
+ 0: -12
+ 1: -12
+    *** Failers
+No match
+    ((2+2)*-3)-7)
+No match
+
+/^(x(y|(?1){2})z)/
+    xyz
+ 0: xyz
+ 1: xyz
+ 2: y
+    xxyzxyzz
+ 0: xxyzxyzz
+ 1: xxyzxyzz
+ 2: xyzxyz
+    *** Failers
+No match
+    xxyzz
+No match
+    xxyzxyzxyzz
+No match
+
+/((< (?: (?(R) \d++  | [^<>]*+) | (?2)) * >))/x
+    <>
+ 0: <>
+ 1: <>
+ 2: <>
+    <abcd>
+ 0: <abcd>
+ 1: <abcd>
+ 2: <abcd>
+    <abc <123> hij>
+ 0: <abc <123> hij>
+ 1: <abc <123> hij>
+ 2: <abc <123> hij>
+    <abc <def> hij>
+ 0: <def>
+ 1: <def>
+ 2: <def>
+    <abc<>def>
+ 0: <abc<>def>
+ 1: <abc<>def>
+ 2: <abc<>def>
+    <abc<>
+ 0: <>
+ 1: <>
+ 2: <>
+    *** Failers
+No match
+    <abc
+No match
+
+/^a+(*FAIL)/
+    aaaaaa
+No match
+    
+/a+b?c+(*FAIL)/
+    aaabccc
+No match
+
+/a+b?(*PRUNE)c+(*FAIL)/
+    aaabccc
+No match
+
+/a+b?(*COMMIT)c+(*FAIL)/
+    aaabccc
+No match
+    
+/a+b?(*SKIP)c+(*FAIL)/
+    aaabcccaaabccc
+No match
+
+/^(?:aaa(*THEN)\w{6}|bbb(*THEN)\w{5}|ccc(*THEN)\w{4}|\w{3})/
+    aaaxxxxxx
+ 0: aaaxxxxxx
+    aaa++++++ 
+ 0: aaa
+    bbbxxxxx
+ 0: bbbxxxxx
+    bbb+++++ 
+ 0: bbb
+    cccxxxx
+ 0: cccxxxx
+    ccc++++ 
+ 0: ccc
+    dddddddd   
+ 0: ddd
+
+/^(aaa(*THEN)\w{6}|bbb(*THEN)\w{5}|ccc(*THEN)\w{4}|\w{3})/
+    aaaxxxxxx
+ 0: aaaxxxxxx
+ 1: aaaxxxxxx
+    aaa++++++ 
+ 0: aaa
+ 1: aaa
+    bbbxxxxx
+ 0: bbbxxxxx
+ 1: bbbxxxxx
+    bbb+++++ 
+ 0: bbb
+ 1: bbb
+    cccxxxx
+ 0: cccxxxx
+ 1: cccxxxx
+    ccc++++ 
+ 0: ccc
+ 1: ccc
+    dddddddd   
+ 0: ddd
+ 1: ddd
+
+/a+b?(*THEN)c+(*FAIL)/
+    aaabccc
+No match
+
+/(A (A|B(*ACCEPT)|C) D)(E)/x
+    AB
+ 0: AB
+ 1: AB
+ 2: B
+    ABX
+ 0: AB
+ 1: AB
+ 2: B
+    AADE
+ 0: AADE
+ 1: AAD
+ 2: A
+ 3: E
+    ACDE
+ 0: ACDE
+ 1: ACD
+ 2: C
+ 3: E
+    ** Failers
+No match
+    AD 
+No match
+        
+/^\W*+(?:((.)\W*+(?1)\W*+\2|)|((.)\W*+(?3)\W*+\4|\W*+.\W*+))\W*+$/i
+    1221
+ 0: 1221
+ 1: 1221
+ 2: 1
+    Satan, oscillate my metallic sonatas!
+ 0: Satan, oscillate my metallic sonatas!
+ 1: <unset>
+ 2: <unset>
+ 3: Satan, oscillate my metallic sonatas
+ 4: S
+    A man, a plan, a canal: Panama!
+ 0: A man, a plan, a canal: Panama!
+ 1: <unset>
+ 2: <unset>
+ 3: A man, a plan, a canal: Panama
+ 4: A
+    Able was I ere I saw Elba.
+ 0: Able was I ere I saw Elba.
+ 1: <unset>
+ 2: <unset>
+ 3: Able was I ere I saw Elba
+ 4: A
+    *** Failers
+No match
+    The quick brown fox
+No match
+
+/^((.)(?1)\2|.)$/
+    a
+ 0: a
+ 1: a
+    aba
+ 0: aba
+ 1: aba
+ 2: a
+    aabaa  
+ 0: aabaa
+ 1: aabaa
+ 2: a
+    abcdcba 
+ 0: abcdcba
+ 1: abcdcba
+ 2: a
+    pqaabaaqp  
+ 0: pqaabaaqp
+ 1: pqaabaaqp
+ 2: p
+    ablewasiereisawelba
+ 0: ablewasiereisawelba
+ 1: ablewasiereisawelba
+ 2: a
+    rhubarb
+No match
+    the quick brown fox  
+No match
+
+/(a)(?<=b(?1))/
+    baz
+ 0: a
+ 1: a
+    ** Failers
+No match
+    caz  
+No match
+    
+/(?<=b(?1))(a)/
+    zbaaz
+ 0: a
+ 1: a
+    ** Failers
+No match
+    aaa  
+No match
+    
+/(?<X>a)(?<=b(?&X))/
+    baz
+ 0: a
+ 1: a
+
+/^(?|(abc)|(def))\1/
+    abcabc
+ 0: abcabc
+ 1: abc
+    defdef 
+ 0: defdef
+ 1: def
+    ** Failers
+No match
+    abcdef
+No match
+    defabc   
+No match
+    
+/^(?|(abc)|(def))(?1)/
+    abcabc
+ 0: abcabc
+ 1: abc
+    defabc
+ 0: defabc
+ 1: def
+    ** Failers
+No match
+    defdef
+No match
+    abcdef    
+No match
+
+/(?:a(?<quote> (?<apostrophe>')|(?<realquote>")) |b(?<quote> (?<apostrophe>')|(?<realquote>")) ) (?('quote')[a-z]+|[0-9]+)/xJ
+    a\"aaaaa
+ 0: a"aaaaa
+ 1: "
+ 2: <unset>
+ 3: "
+    b\"aaaaa 
+ 0: b"aaaaa
+ 1: <unset>
+ 2: <unset>
+ 3: <unset>
+ 4: "
+ 5: <unset>
+ 6: "
+    ** Failers 
+No match
+    b\"11111
+No match
+
+/(?:(?1)|B)(A(*F)|C)/
+    ABCD
+ 0: BC
+ 1: C
+    CCD
+ 0: CC
+ 1: C
+    ** Failers
+No match
+    CAD   
+No match
+
+/^(?:(?1)|B)(A(*F)|C)/
+    CCD
+ 0: CC
+ 1: C
+    BCD 
+ 0: BC
+ 1: C
+    ** Failers
+No match
+    ABCD
+No match
+    CAD
+No match
+    BAD    
+No match
+
+/(?:(?1)|B)(A(*ACCEPT)XX|C)D/
+    AAD
+ 0: AA
+ 1: A
+    ACD
+ 0: ACD
+ 1: C
+    BAD
+ 0: BA
+ 1: A
+    BCD
+ 0: BCD
+ 1: C
+    BAX  
+ 0: BA
+ 1: A
+    ** Failers
+No match
+    ACX
+No match
+    ABC   
+No match
+
+/(?(DEFINE)(A))B(?1)C/
+    BAC
+ 0: BAC
+
+/(?(DEFINE)((A)\2))B(?1)C/
+    BAAC
+ 0: BAAC
+
+/(?<pn> \( ( [^()]++ | (?&pn) )* \) )/x
+    (ab(cd)ef)
+ 0: (ab(cd)ef)
+ 1: (ab(cd)ef)
+ 2: ef
+
+/^(?!a(*SKIP)b)/
+    ac
+ 0: 
+    
+/^(?=a(*SKIP)b|ac)/
+    ** Failers
+No match
+    ac
+No match
+    
+/^(?=a(*THEN)b|ac)/
+    ac
+ 0: 
+    
+/^(?=a(*PRUNE)b)/
+    ab  
+ 0: 
+    ** Failers 
+No match
+    ac
+No match
+
+/^(?=a(*ACCEPT)b)/
+    ac
+ 0: 
+
+/^(?(?!a(*SKIP)b))/
+    ac
+ 0: 
+
+/(?>a\Kb)/
+    ab
+ 0: b
+
+/((?>a\Kb))/
+    ab
+ 0: b
+ 1: ab
+
+/(a\Kb)/
+    ab
+ 0: b
+ 1: ab
+    
+/^a\Kcz|ac/
+    ac
+ 0: ac
+    
+/(?>a\Kbz|ab)/
+    ab 
+ 0: ab
+
+/^(?&t)(?(DEFINE)(?<t>a\Kb))$/
+    ab
+ 0: b
+
+/^([^()]|\((?1)*\))*$/
+    a(b)c
+ 0: a(b)c
+ 1: c
+    a(b(c)d)e 
+ 0: a(b(c)d)e
+ 1: e
+
+/(?P<L1>(?P<L2>0)(?P>L1)|(?P>L2))/
+    0
+ 0: 0
+ 1: 0
+    00
+ 0: 00
+ 1: 00
+ 2: 0
+    0000  
+ 0: 0000
+ 1: 0000
+ 2: 0
+
+/(?P<L1>(?P<L2>0)|(?P>L2)(?P>L1))/
+    0
+ 0: 0
+ 1: 0
+ 2: 0
+    00
+ 0: 0
+ 1: 0
+ 2: 0
+    0000  
+ 0: 0
+ 1: 0
+ 2: 0
+
+/--- This one does fail, as expected, in Perl. It needs the complex item at the
+     end of the pattern. A single letter instead of (B|D) makes it not fail,
+     which I think is a Perl bug. --- /
+
+/A(*COMMIT)(B|D)/
+    ACABX
+No match
+
+/--- Check the use of names for failure ---/
+
+/^(A(*PRUNE:A)B|C(*PRUNE:B)D)/K
+    ** Failers
+No match
+    AC
+No match, mark = A
+    CB    
+No match, mark = B
+    
+/--- Force no study, otherwise mark is not seen. The studied version is in
+     test 2 because it isn't Perl-compatible. ---/
+
+/(*MARK:A)(*SKIP:B)(C|X)/KSS
+    C
+ 0: C
+ 1: C
+MK: A
+    D
+No match, mark = A
+     
+/^(A(*THEN:A)B|C(*THEN:B)D)/K
+    ** Failers
+No match
+    CB    
+No match, mark = B
+
+/^(?:A(*THEN:A)B|C(*THEN:B)D)/K
+    CB    
+No match, mark = B
+    
+/^(?>A(*THEN:A)B|C(*THEN:B)D)/K
+    CB    
+No match, mark = B
+    
+/--- This should succeed, as the skip causes bump to offset 1 (the mark). Note
+that we have to have something complicated such as (B|Z) at the end because,
+for Perl, a simple character somehow causes an unwanted optimization to mess
+with the handling of backtracking verbs. ---/
+
+/A(*MARK:A)A+(*SKIP:A)(B|Z) | AC/xK
+    AAAC
+ 0: AC
+    
+/--- Test skipping over a non-matching mark. ---/
+
+/A(*MARK:A)A+(*MARK:B)(*SKIP:A)(B|Z) | AC/xK
+    AAAC
+ 0: AC
+    
+/--- Check shorthand for MARK ---/
+
+/A(*:A)A+(*SKIP:A)(B|Z) | AC/xK
+    AAAC
+ 0: AC
+
+/--- Don't loop! Force no study, otherwise mark is not seen. ---/
+
+/(*:A)A+(*SKIP:A)(B|Z)/KSS
+    AAAC
+No match, mark = A
+
+/--- This should succeed, as a non-existent skip name disables the skip ---/ 
+
+/A(*MARK:A)A+(*SKIP:B)(B|Z) | AC/xK
+    AAAC
+ 0: AC
+
+/A(*MARK:A)A+(*SKIP:B)(B|Z) | AC(*:B)/xK
+    AAAC
+ 0: AC
+MK: B
+
+/--- COMMIT at the start of a pattern should act like an anchor. Again, 
+however, we need the complication for Perl. ---/
+
+/(*COMMIT)(A|P)(B|P)(C|P)/
+    ABCDEFG
+ 0: ABC
+ 1: A
+ 2: B
+ 3: C
+    ** Failers
+No match
+    DEFGABC  
+No match
+
+/--- COMMIT inside an atomic group can't stop backtracking over the group. ---/
+
+/(\w+)(?>b(*COMMIT))\w{2}/
+    abbb
+ 0: abbb
+ 1: a
+
+/(\w+)b(*COMMIT)\w{2}/
+    abbb
+No match
+
+/--- Check opening parens in comment when seeking forward reference. ---/ 
+
+/(?&t)(?#()(?(DEFINE)(?<t>a))/
+    bac
+ 0: a
+
+/--- COMMIT should override THEN ---/
+
+/(?>(*COMMIT)(?>yes|no)(*THEN)(*F))?/
+  yes
+No match
+
+/(?>(*COMMIT)(yes|no)(*THEN)(*F))?/
+  yes
+No match
+
+/b?(*SKIP)c/
+    bc
+ 0: bc
+    abc
+ 0: bc
+   
+/(*SKIP)bc/
+    a
+No match
+
+/(*SKIP)b/
+    a 
+No match
+
+/(?P<abn>(?P=abn)xxx|)+/
+    xxx
+ 0: 
+ 1: 
+
+/(?i:([^b]))(?1)/
+    aa
+ 0: aa
+ 1: a
+    aA     
+ 0: aA
+ 1: a
+    ** Failers
+ 0: **
+ 1: *
+    ab
+No match
+    aB
+No match
+    Ba
+No match
+    ba
+No match
+
+/^(?&t)*+(?(DEFINE)(?<t>a))\w$/
+    aaaaaaX
+ 0: aaaaaaX
+    ** Failers 
+No match
+    aaaaaa 
+No match
+
+/^(?&t)*(?(DEFINE)(?<t>a))\w$/
+    aaaaaaX
+ 0: aaaaaaX
+    aaaaaa 
+ 0: aaaaaa
+
+/^(a)*+(\w)/
+    aaaaX
+ 0: aaaaX
+ 1: a
+ 2: X
+    YZ 
+ 0: Y
+ 1: <unset>
+ 2: Y
+    ** Failers 
+No match
+    aaaa
+No match
+
+/^(?:a)*+(\w)/
+    aaaaX
+ 0: aaaaX
+ 1: X
+    YZ 
+ 0: Y
+ 1: Y
+    ** Failers 
+No match
+    aaaa
+No match
+
+/^(a)++(\w)/
+    aaaaX
+ 0: aaaaX
+ 1: a
+ 2: X
+    ** Failers 
+No match
+    aaaa
+No match
+    YZ 
+No match
+
+/^(?:a)++(\w)/
+    aaaaX
+ 0: aaaaX
+ 1: X
+    ** Failers 
+No match
+    aaaa
+No match
+    YZ 
+No match
+
+/^(a)?+(\w)/
+    aaaaX
+ 0: aa
+ 1: a
+ 2: a
+    YZ 
+ 0: Y
+ 1: <unset>
+ 2: Y
+
+/^(?:a)?+(\w)/
+    aaaaX
+ 0: aa
+ 1: a
+    YZ 
+ 0: Y
+ 1: Y
+
+/^(a){2,}+(\w)/
+    aaaaX
+ 0: aaaaX
+ 1: a
+ 2: X
+    ** Failers
+No match
+    aaa
+No match
+    YZ 
+No match
+
+/^(?:a){2,}+(\w)/
+    aaaaX
+ 0: aaaaX
+ 1: X
+    ** Failers
+No match
+    aaa
+No match
+    YZ 
+No match
+
+/(a|)*(?1)b/
+    b
+ 0: b
+ 1: 
+    ab
+ 0: ab
+ 1: 
+    aab  
+ 0: aab
+ 1: 
+
+/(a)++(?1)b/
+    ** Failers
+No match
+    ab 
+No match
+    aab
+No match
+
+/(a)*+(?1)b/
+    ** Failers
+No match
+    ab
+No match
+    aab  
+No match
+
+/(?1)(?:(b)){0}/
+    b
+ 0: b
+
+/(foo ( \( ((?:(?> [^()]+ )|(?2))*) \) ) )/x
+    foo(bar(baz)+baz(bop))
+ 0: foo(bar(baz)+baz(bop))
+ 1: foo(bar(baz)+baz(bop))
+ 2: (bar(baz)+baz(bop))
+ 3: bar(baz)+baz(bop)
+
+/(A (A|B(*ACCEPT)|C) D)(E)/x
+    AB
+ 0: AB
+ 1: AB
+ 2: B
+
+/\A.*?(?:a|b(*THEN)c)/
+    ba
+ 0: ba
+
+/\A.*?(?:a|bc)/
+    ba
+ 0: ba
+
+/\A.*?(a|b(*THEN)c)/
+    ba
+ 0: ba
+ 1: a
+
+/\A.*?(a|bc)/
+    ba
+ 0: ba
+ 1: a
+
+/\A.*?(?:a|b(*THEN)c)++/
+    ba
+ 0: ba
+
+/\A.*?(?:a|bc)++/
+    ba
+ 0: ba
+
+/\A.*?(a|b(*THEN)c)++/
+    ba
+ 0: ba
+ 1: a
+
+/\A.*?(a|bc)++/
+    ba
+ 0: ba
+ 1: a
+
+/\A.*?(?:a|b(*THEN)c|d)/
+    ba
+ 0: ba
+
+/\A.*?(?:a|bc|d)/
+    ba
+ 0: ba
+
+/(?:(b))++/
+    beetle
+ 0: b
+ 1: b
+
+/(?(?=(a(*ACCEPT)z))a)/
+    a
+ 0: a
+ 1: a
+
+/^(a)(?1)+ab/
+    aaaab
+ 0: aaaab
+ 1: a
+    
+/^(a)(?1)++ab/
+    aaaab
+No match
+
+/^(?=a(*:M))aZ/K
+    aZbc
+ 0: aZ
+MK: M
+
+/^(?!(*:M)b)aZ/K
+    aZbc
+ 0: aZ
+
+/(?(DEFINE)(a))?b(?1)/
+    backgammon
+ 0: ba
+
+/^\N+/
+    abc\ndef
+ 0: abc
+    
+/^\N{1,}/
+    abc\ndef 
+ 0: abc
+
+/(?(R)a+|(?R)b)/
+    aaaabcde
+ 0: aaaab
+
+/(?(R)a+|((?R))b)/
+    aaaabcde
+ 0: aaaab
+ 1: aaaa
+
+/((?(R)a+|(?1)b))/
+    aaaabcde
+ 0: aaaab
+ 1: aaaab
+
+/((?(R1)a+|(?1)b))/
+    aaaabcde
+ 0: aaaab
+ 1: aaaab
+
+/a(*:any 
+name)/K
+    abc
+ 0: a
+MK: any \x0aname
+    
+/(?>(?&t)c|(?&t))(?(DEFINE)(?<t>a|b(*PRUNE)c))/
+    a
+ 0: a
+    ba
+ 0: a
+    bba 
+ 0: a
+    
+/--- Checking revised (*THEN) handling ---/ 
+
+/--- Capture ---/
+
+/^.*? (a(*THEN)b) c/x
+    aabc
+No match
+
+/^.*? (a(*THEN)b|(*F)) c/x
+    aabc
+ 0: aabc
+ 1: ab
+
+/^.*? ( (a(*THEN)b) | (*F) ) c/x
+    aabc
+ 0: aabc
+ 1: ab
+ 2: ab
+
+/^.*? ( (a(*THEN)b) ) c/x
+    aabc
+No match
+
+/--- Non-capture ---/
+
+/^.*? (?:a(*THEN)b) c/x
+    aabc
+No match
+
+/^.*? (?:a(*THEN)b|(*F)) c/x
+    aabc
+ 0: aabc
+
+/^.*? (?: (?:a(*THEN)b) | (*F) ) c/x
+    aabc
+ 0: aabc
+
+/^.*? (?: (?:a(*THEN)b) ) c/x
+    aabc
+No match
+
+/--- Atomic ---/
+
+/^.*? (?>a(*THEN)b) c/x
+    aabc
+No match
+
+/^.*? (?>a(*THEN)b|(*F)) c/x
+    aabc
+ 0: aabc
+
+/^.*? (?> (?>a(*THEN)b) | (*F) ) c/x
+    aabc
+ 0: aabc
+
+/^.*? (?> (?>a(*THEN)b) ) c/x
+    aabc
+No match
+
+/--- Possessive capture ---/
+
+/^.*? (a(*THEN)b)++ c/x
+    aabc
+No match
+
+/^.*? (a(*THEN)b|(*F))++ c/x
+    aabc
+ 0: aabc
+ 1: ab
+
+/^.*? ( (a(*THEN)b)++ | (*F) )++ c/x
+    aabc
+ 0: aabc
+ 1: ab
+ 2: ab
+
+/^.*? ( (a(*THEN)b)++ )++ c/x
+    aabc
+No match
+
+/--- Possessive non-capture ---/
+
+/^.*? (?:a(*THEN)b)++ c/x
+    aabc
+No match
+
+/^.*? (?:a(*THEN)b|(*F))++ c/x
+    aabc
+ 0: aabc
+
+/^.*? (?: (?:a(*THEN)b)++ | (*F) )++ c/x
+    aabc
+ 0: aabc
+
+/^.*? (?: (?:a(*THEN)b)++ )++ c/x
+    aabc
+No match
+    
+/--- Condition assertion ---/
+
+/^(?(?=a(*THEN)b)ab|ac)/
+    ac
+ 0: ac
+ 
+/--- Condition ---/
+
+/^.*?(?(?=a)a|b(*THEN)c)/
+    ba
+No match
+
+/^.*?(?:(?(?=a)a|b(*THEN)c)|d)/
+    ba
+ 0: ba
+
+/^.*?(?(?=a)a(*THEN)b|c)/
+    ac
+No match
+
+/--- Assertion ---/
+
+/^.*(?=a(*THEN)b)/ 
+    aabc
+ 0: a
+
+/------------------------------/
+
+/(?>a(*:m))/imsxSK 
+    a
+ 0: a
+MK: m
+
+/(?>(a)(*:m))/imsxSK 
+    a
+ 0: a
+ 1: a
+MK: m
+
+/(?<=a(*ACCEPT)b)c/
+    xacd
+ 0: c
+
+/(?<=(a(*ACCEPT)b))c/
+    xacd
+ 0: c
+ 1: a
+
+/(?<=(a(*COMMIT)b))c/
+    xabcd
+ 0: c
+ 1: ab
+    ** Failers 
+No match
+    xacd
+No match
+    
+/(?<!a(*FAIL)b)c/
+    xcd
+ 0: c
+    acd 
+ 0: c
+
+/(?<=a(*:N)b)c/K
+    xabcd
+ 0: c
+MK: N
+    
+/(?<=a(*PRUNE)b)c/
+    xabcd 
+ 0: c
+
+/(?<=a(*SKIP)b)c/
+    xabcd 
+ 0: c
+
+/(?<=a(*THEN)b)c/
+    xabcd 
+ 0: c
+
+/(a)(?2){2}(.)/
+    abcd
+ 0: abcd
+ 1: a
+ 2: d
+
+/(*MARK:A)(*PRUNE:B)(C|X)/KS
+    C
+ 0: C
+ 1: C
+MK: B
+    D 
+No match, mark = B
+
+/(*MARK:A)(*PRUNE:B)(C|X)/KSS
+    C
+ 0: C
+ 1: C
+MK: B
+    D 
+No match, mark = B
+
+/(*MARK:A)(*THEN:B)(C|X)/KS
+    C
+ 0: C
+ 1: C
+MK: B
+    D 
+No match, mark = B
+
+/(*MARK:A)(*THEN:B)(C|X)/KSY
+    C
+ 0: C
+ 1: C
+MK: B
+    D 
+No match, mark = B
+
+/(*MARK:A)(*THEN:B)(C|X)/KSS
+    C
+ 0: C
+ 1: C
+MK: B
+    D 
+No match, mark = B
+
+/--- This should fail, as the skip causes a bump to offset 3 (the skip) ---/
+
+/A(*MARK:A)A+(*SKIP)(B|Z) | AC/xK
+    AAAC
+No match, mark = A
+
+/--- Same --/
+
+/A(*MARK:A)A+(*MARK:B)(*SKIP:B)(B|Z) | AC/xK
+    AAAC
+No match, mark = B
+
+/A(*:A)A+(*SKIP)(B|Z) | AC/xK
+    AAAC
+No match, mark = A
+
+/--- This should fail, as a null name is the same as no name ---/
+
+/A(*MARK:A)A+(*SKIP:)(B|Z) | AC/xK
+    AAAC
+No match, mark = A
+
+/--- A check on what happens after hitting a mark and them bumping along to
+something that does not even start. Perl reports tags after the failures here, 
+though it does not when the individual letters are made into something 
+more complicated. ---/
+
+/A(*:A)B|XX(*:B)Y/K
+    AABC
+ 0: AB
+MK: A
+    XXYZ 
+ 0: XXY
+MK: B
+    ** Failers
+No match
+    XAQQ  
+No match, mark = A
+    XAQQXZZ  
+No match, mark = A
+    AXQQQ 
+No match, mark = A
+    AXXQQQ 
+No match, mark = B
+    
+/^(A(*THEN:A)B|C(*THEN:B)D)/K
+    AB
+ 0: AB
+ 1: AB
+MK: A
+    CD
+ 0: CD
+ 1: CD
+MK: B
+    ** Failers
+No match
+    AC
+No match, mark = A
+    CB    
+No match, mark = B
+    
+/^(A(*PRUNE:A)B|C(*PRUNE:B)D)/K
+    AB
+ 0: AB
+ 1: AB
+MK: A
+    CD
+ 0: CD
+ 1: CD
+MK: B
+    ** Failers
+No match
+    AC
+No match, mark = A
+    CB    
+No match, mark = B
+    
+/--- An empty name does not pass back an empty string. It is the same as if no
+name were given. ---/ 
+
+/^(A(*PRUNE:)B|C(*PRUNE:B)D)/K
+    AB
+ 0: AB
+ 1: AB
+    CD 
+ 0: CD
+ 1: CD
+MK: B
+
+/--- PRUNE goes to next bumpalong; COMMIT does not. ---/
+    
+/A(*PRUNE:A)B/K
+    ACAB
+ 0: AB
+MK: A
+
+/--- Mark names can be duplicated ---/
+
+/A(*:A)B|X(*:A)Y/K
+    AABC
+ 0: AB
+MK: A
+    XXYZ 
+ 0: XY
+MK: A
+    
+/b(*:m)f|a(*:n)w/K
+    aw 
+ 0: aw
+MK: n
+    ** Failers 
+No match, mark = n
+    abc
+No match, mark = m
+
+/b(*:m)f|aw/K
+    abaw
+ 0: aw
+    ** Failers 
+No match
+    abc
+No match, mark = m
+    abax 
+No match, mark = m
+
+/A(*MARK:A)A+(*SKIP:B)(B|Z) | AAC/xK
+    AAAC
+ 0: AAC
+
+/a(*PRUNE:X)bc|qq/KY
+    ** Failers
+No match, mark = X
+    axy
+No match, mark = X
+
+/a(*THEN:X)bc|qq/KY
+    ** Failers
+No match, mark = X
+    axy
+No match, mark = X
+
+/(?=a(*MARK:A)b)..x/K
+    abxy
+ 0: abx
+MK: A
+    ** Failers
+No match
+    abpq  
+No match
+
+/(?=a(*MARK:A)b)..(*:Y)x/K
+    abxy
+ 0: abx
+MK: Y
+    ** Failers
+No match
+    abpq  
+No match
+
+/(?=a(*PRUNE:A)b)..x/K
+    abxy
+ 0: abx
+MK: A
+    ** Failers
+No match
+    abpq  
+No match
+
+/(?=a(*PRUNE:A)b)..(*:Y)x/K
+    abxy
+ 0: abx
+MK: Y
+    ** Failers
+No match
+    abpq  
+No match
+
+/(?=a(*THEN:A)b)..x/K
+    abxy
+ 0: abx
+MK: A
+    ** Failers
+No match
+    abpq  
+No match
+
+/(?=a(*THEN:A)b)..(*:Y)x/K
+    abxy
+ 0: abx
+MK: Y
+    ** Failers
+No match
+    abpq  
+No match
+
+/(another)?(\1?)test/
+    hello world test
+ 0: test
+ 1: <unset>
+ 2: 
+
+/(another)?(\1+)test/
+    hello world test
+No match
+
+/(a(*COMMIT)b){0}a(?1)|aac/
+    aac
+ 0: aac
+
+/(?!a(*COMMIT)b)ac|cd/
+    ac
+ 0: ac
+
+/((?:a?)*)*c/
+  aac   
+ 0: aac
+ 1: 
+
+/((?>a?)*)*c/
+  aac   
+ 0: aac
+ 1: 
+
+/-- End of testinput1 --/
diff --git a/ext/pcre/pcrelib/testdata/testoutput10 b/ext/pcre/pcrelib/testdata/testoutput10
new file mode 100644
index 0000000..5009d5d
--- /dev/null
+++ b/ext/pcre/pcrelib/testdata/testoutput10
@@ -0,0 +1,2103 @@
+/-- This set of tests check Unicode property support with the DFA matching 
+    functionality of pcre_dfa_exec(). The -dfa flag must be used with pcretest
+    when running it. --/
+
+/\pL\P{Nd}/8
+    AB
+ 0: AB
+    *** Failers
+ 0: Fa
+    A0
+No match
+    00   
+No match
+
+/\X./8
+    AB
+ 0: AB
+    A\x{300}BC 
+ 0: A\x{300}B
+    A\x{300}\x{301}\x{302}BC 
+ 0: A\x{300}\x{301}\x{302}B
+    *** Failers
+ 0: **
+    \x{300}  
+No match
+
+/\X\X/8
+    ABC
+ 0: AB
+    A\x{300}B\x{300}\x{301}C 
+ 0: A\x{300}B\x{300}\x{301}
+    A\x{300}\x{301}\x{302}BC 
+ 0: A\x{300}\x{301}\x{302}B
+    *** Failers
+ 0: **
+    \x{300}  
+No match
+
+/^\pL+/8
+    abcd
+ 0: abcd
+ 1: abc
+ 2: ab
+ 3: a
+    a 
+ 0: a
+    *** Failers 
+No match
+
+/^\PL+/8
+    1234
+ 0: 1234
+ 1: 123
+ 2: 12
+ 3: 1
+    = 
+ 0: =
+    *** Failers 
+ 0: *** 
+ 1: ***
+ 2: **
+ 3: *
+    abcd 
+No match
+
+/^\X+/8
+    abcdA\x{300}\x{301}\x{302}
+ 0: abcdA\x{300}\x{301}\x{302}
+ 1: abcd
+ 2: abc
+ 3: ab
+ 4: a
+    A\x{300}\x{301}\x{302}
+ 0: A\x{300}\x{301}\x{302}
+    A\x{300}\x{301}\x{302}A\x{300}\x{301}\x{302}
+ 0: A\x{300}\x{301}\x{302}A\x{300}\x{301}\x{302}
+ 1: A\x{300}\x{301}\x{302}
+    a 
+ 0: a
+    *** Failers 
+ 0: *** Failers
+ 1: *** Failer
+ 2: *** Faile
+ 3: *** Fail
+ 4: *** Fai
+ 5: *** Fa
+ 6: *** F
+ 7: *** 
+ 8: ***
+ 9: **
+10: *
+    \x{300}\x{301}\x{302}
+No match
+
+/\X?abc/8
+    abc
+ 0: abc
+    A\x{300}abc
+ 0: A\x{300}abc
+    A\x{300}\x{301}\x{302}A\x{300}A\x{300}A\x{300}abcxyz
+ 0: A\x{300}abc
+    \x{300}abc  
+ 0: abc
+    *** Failers
+No match
+
+/^\X?abc/8
+    abc
+ 0: abc
+    A\x{300}abc
+ 0: A\x{300}abc
+    *** Failers
+No match
+    A\x{300}\x{301}\x{302}A\x{300}A\x{300}A\x{300}abcxyz
+No match
+    \x{300}abc  
+No match
+
+/\X*abc/8
+    abc
+ 0: abc
+    A\x{300}abc
+ 0: A\x{300}abc
+    A\x{300}\x{301}\x{302}A\x{300}A\x{300}A\x{300}abcxyz
+ 0: A\x{300}\x{301}\x{302}A\x{300}A\x{300}A\x{300}abc
+    \x{300}abc  
+ 0: abc
+    *** Failers
+No match
+
+/^\X*abc/8
+    abc
+ 0: abc
+    A\x{300}abc
+ 0: A\x{300}abc
+    A\x{300}\x{301}\x{302}A\x{300}A\x{300}A\x{300}abcxyz
+ 0: A\x{300}\x{301}\x{302}A\x{300}A\x{300}A\x{300}abc
+    *** Failers
+No match
+    \x{300}abc  
+No match
+
+/^\pL?=./8
+    A=b
+ 0: A=b
+    =c 
+ 0: =c
+    *** Failers
+No match
+    1=2 
+No match
+    AAAA=b  
+No match
+
+/^\pL*=./8
+    AAAA=b
+ 0: AAAA=b
+    =c 
+ 0: =c
+    *** Failers
+No match
+    1=2  
+No match
+
+/^\X{2,3}X/8
+    A\x{300}\x{301}\x{302}A\x{300}\x{301}\x{302}X
+ 0: A\x{300}\x{301}\x{302}A\x{300}\x{301}\x{302}X
+    A\x{300}\x{301}\x{302}A\x{300}\x{301}\x{302}A\x{300}\x{301}\x{302}X 
+ 0: A\x{300}\x{301}\x{302}A\x{300}\x{301}\x{302}A\x{300}\x{301}\x{302}X
+    *** Failers
+No match
+    X
+No match
+    A\x{300}\x{301}\x{302}X
+No match
+    A\x{300}\x{301}\x{302}A\x{300}\x{301}\x{302}A\x{300}\x{301}\x{302}A\x{300}\x{301}\x{302}X
+No match
+
+/^\pC\pL\pM\pN\pP\pS\pZ</8
+    \x7f\x{c0}\x{30f}\x{660}\x{66c}\x{f01}\x{1680}<
+ 0: \x{7f}\x{c0}\x{30f}\x{660}\x{66c}\x{f01}\x{1680}<
+    \np\x{300}9!\$ < 
+ 0: \x{0a}p\x{300}9!$ <
+    ** Failers 
+No match
+    ap\x{300}9!\$ < 
+No match
+  
+/^\PC/8
+    X
+ 0: X
+    ** Failers 
+ 0: *
+    \x7f
+No match
+  
+/^\PL/8
+    9
+ 0: 9
+    ** Failers 
+ 0: *
+    \x{c0}
+No match
+  
+/^\PM/8
+    X
+ 0: X
+    ** Failers 
+ 0: *
+    \x{30f}
+No match
+  
+/^\PN/8
+    X
+ 0: X
+    ** Failers 
+ 0: *
+    \x{660}
+No match
+  
+/^\PP/8
+    X
+ 0: X
+    ** Failers 
+No match
+    \x{66c}
+No match
+  
+/^\PS/8
+    X
+ 0: X
+    ** Failers 
+ 0: *
+    \x{f01}
+No match
+  
+/^\PZ/8
+    X
+ 0: X
+    ** Failers 
+ 0: *
+    \x{1680}
+No match
+    
+/^\p{Cc}/8
+    \x{017}
+ 0: \x{17}
+    \x{09f} 
+ 0: \x{9f}
+    ** Failers
+No match
+    \x{0600} 
+No match
+  
+/^\p{Cf}/8
+    \x{601}
+ 0: \x{601}
+    ** Failers
+No match
+    \x{09f} 
+No match
+  
+/^\p{Cn}/8
+    ** Failers
+No match
+    \x{09f} 
+No match
+  
+/^\p{Co}/8
+    \x{f8ff}
+ 0: \x{f8ff}
+    ** Failers
+No match
+    \x{09f} 
+No match
+  
+/^\p{Cs}/8
+    \?\x{dfff}
+ 0: \x{dfff}
+    ** Failers
+No match
+    \x{09f} 
+No match
+  
+/^\p{Ll}/8
+    a
+ 0: a
+    ** Failers 
+No match
+    Z
+No match
+    \x{e000}  
+No match
+  
+/^\p{Lm}/8
+    \x{2b0}
+ 0: \x{2b0}
+    ** Failers
+No match
+    a 
+No match
+  
+/^\p{Lo}/8
+    \x{1bb}
+ 0: \x{1bb}
+    ** Failers
+No match
+    a 
+No match
+    \x{2b0}
+No match
+  
+/^\p{Lt}/8
+    \x{1c5}
+ 0: \x{1c5}
+    ** Failers
+No match
+    a 
+No match
+    \x{2b0}
+No match
+  
+/^\p{Lu}/8
+    A
+ 0: A
+    ** Failers
+No match
+    \x{2b0}
+No match
+  
+/^\p{Mc}/8
+    \x{903}
+ 0: \x{903}
+    ** Failers
+No match
+    X
+No match
+    \x{300}
+No match
+       
+/^\p{Me}/8
+    \x{488}
+ 0: \x{488}
+    ** Failers
+No match
+    X
+No match
+    \x{903}
+No match
+    \x{300}
+No match
+  
+/^\p{Mn}/8
+    \x{300}
+ 0: \x{300}
+    ** Failers
+No match
+    X
+No match
+    \x{903}
+No match
+  
+/^\p{Nd}+/8
+    0123456789\x{660}\x{661}\x{662}\x{663}\x{664}\x{665}\x{666}\x{667}\x{668}\x{669}\x{66a}
+ 0: 0123456789\x{660}\x{661}\x{662}\x{663}\x{664}\x{665}\x{666}\x{667}\x{668}\x{669}
+ 1: 0123456789\x{660}\x{661}\x{662}\x{663}\x{664}\x{665}\x{666}\x{667}\x{668}
+ 2: 0123456789\x{660}\x{661}\x{662}\x{663}\x{664}\x{665}\x{666}\x{667}
+ 3: 0123456789\x{660}\x{661}\x{662}\x{663}\x{664}\x{665}\x{666}
+ 4: 0123456789\x{660}\x{661}\x{662}\x{663}\x{664}\x{665}
+ 5: 0123456789\x{660}\x{661}\x{662}\x{663}\x{664}
+ 6: 0123456789\x{660}\x{661}\x{662}\x{663}
+ 7: 0123456789\x{660}\x{661}\x{662}
+ 8: 0123456789\x{660}\x{661}
+ 9: 0123456789\x{660}
+10: 0123456789
+11: 012345678
+12: 01234567
+13: 0123456
+14: 012345
+15: 01234
+16: 0123
+17: 012
+18: 01
+19: 0
+    \x{6f0}\x{6f1}\x{6f2}\x{6f3}\x{6f4}\x{6f5}\x{6f6}\x{6f7}\x{6f8}\x{6f9}\x{6fa}
+ 0: \x{6f0}\x{6f1}\x{6f2}\x{6f3}\x{6f4}\x{6f5}\x{6f6}\x{6f7}\x{6f8}\x{6f9}
+ 1: \x{6f0}\x{6f1}\x{6f2}\x{6f3}\x{6f4}\x{6f5}\x{6f6}\x{6f7}\x{6f8}
+ 2: \x{6f0}\x{6f1}\x{6f2}\x{6f3}\x{6f4}\x{6f5}\x{6f6}\x{6f7}
+ 3: \x{6f0}\x{6f1}\x{6f2}\x{6f3}\x{6f4}\x{6f5}\x{6f6}
+ 4: \x{6f0}\x{6f1}\x{6f2}\x{6f3}\x{6f4}\x{6f5}
+ 5: \x{6f0}\x{6f1}\x{6f2}\x{6f3}\x{6f4}
+ 6: \x{6f0}\x{6f1}\x{6f2}\x{6f3}
+ 7: \x{6f0}\x{6f1}\x{6f2}
+ 8: \x{6f0}\x{6f1}
+ 9: \x{6f0}
+    \x{966}\x{967}\x{968}\x{969}\x{96a}\x{96b}\x{96c}\x{96d}\x{96e}\x{96f}\x{970}
+ 0: \x{966}\x{967}\x{968}\x{969}\x{96a}\x{96b}\x{96c}\x{96d}\x{96e}\x{96f}
+ 1: \x{966}\x{967}\x{968}\x{969}\x{96a}\x{96b}\x{96c}\x{96d}\x{96e}
+ 2: \x{966}\x{967}\x{968}\x{969}\x{96a}\x{96b}\x{96c}\x{96d}
+ 3: \x{966}\x{967}\x{968}\x{969}\x{96a}\x{96b}\x{96c}
+ 4: \x{966}\x{967}\x{968}\x{969}\x{96a}\x{96b}
+ 5: \x{966}\x{967}\x{968}\x{969}\x{96a}
+ 6: \x{966}\x{967}\x{968}\x{969}
+ 7: \x{966}\x{967}\x{968}
+ 8: \x{966}\x{967}
+ 9: \x{966}
+    ** Failers
+No match
+    X
+No match
+  
+/^\p{Nl}/8
+    \x{16ee}
+ 0: \x{16ee}
+    ** Failers
+No match
+    X
+No match
+    \x{966}
+No match
+  
+/^\p{No}/8
+    \x{b2}
+ 0: \x{b2}
+    \x{b3}
+ 0: \x{b3}
+    ** Failers
+No match
+    X
+No match
+    \x{16ee}
+No match
+  
+/^\p{Pc}/8
+    \x5f
+ 0: _
+    \x{203f}
+ 0: \x{203f}
+    ** Failers
+No match
+    X
+No match
+    -
+No match
+    \x{58a}
+No match
+  
+/^\p{Pd}/8
+    -
+ 0: -
+    \x{58a}
+ 0: \x{58a}
+    ** Failers
+No match
+    X
+No match
+    \x{203f}
+No match
+  
+/^\p{Pe}/8
+    )
+ 0: )
+    ]
+ 0: ]
+    }
+ 0: }
+    \x{f3b}
+ 0: \x{f3b}
+    ** Failers
+No match
+    X
+No match
+    \x{203f}
+No match
+    (
+No match
+    [
+No match
+    {
+No match
+    \x{f3c}
+No match
+  
+/^\p{Pf}/8
+    \x{bb}
+ 0: \x{bb}
+    \x{2019}
+ 0: \x{2019}
+    ** Failers
+No match
+    X
+No match
+    \x{203f}
+No match
+  
+/^\p{Pi}/8
+    \x{ab}
+ 0: \x{ab}
+    \x{2018}
+ 0: \x{2018}
+    ** Failers
+No match
+    X
+No match
+    \x{203f}
+No match
+  
+/^\p{Po}/8
+    !
+ 0: !
+    \x{37e}
+ 0: \x{37e}
+    ** Failers
+ 0: *
+    X
+No match
+    \x{203f}
+No match
+  
+/^\p{Ps}/8
+    (
+ 0: (
+    [
+ 0: [
+    {
+ 0: {
+    \x{f3c}
+ 0: \x{f3c}
+    ** Failers
+No match
+    X
+No match
+    )
+No match
+    ]
+No match
+    }
+No match
+    \x{f3b}
+No match
+  
+/^\p{Sc}+/8
+    $\x{a2}\x{a3}\x{a4}\x{a5}\x{a6}
+ 0: $\x{a2}\x{a3}\x{a4}\x{a5}
+ 1: $\x{a2}\x{a3}\x{a4}
+ 2: $\x{a2}\x{a3}
+ 3: $\x{a2}
+ 4: $
+    \x{9f2}
+ 0: \x{9f2}
+    ** Failers
+No match
+    X
+No match
+    \x{2c2}
+No match
+  
+/^\p{Sk}/8
+    \x{2c2}
+ 0: \x{2c2}
+    ** Failers
+No match
+    X
+No match
+    \x{9f2}
+No match
+  
+/^\p{Sm}+/8
+    +<|~\x{ac}\x{2044}
+ 0: +<|~\x{ac}\x{2044}
+ 1: +<|~\x{ac}
+ 2: +<|~
+ 3: +<|
+ 4: +<
+ 5: +
+    ** Failers
+No match
+    X
+No match
+    \x{9f2}
+No match
+  
+/^\p{So}/8
+    \x{a6}
+ 0: \x{a6}
+    \x{482} 
+ 0: \x{482}
+    ** Failers
+No match
+    X
+No match
+    \x{9f2}
+No match
+  
+/^\p{Zl}/8
+    \x{2028}
+ 0: \x{2028}
+    ** Failers
+No match
+    X
+No match
+    \x{2029}
+No match
+  
+/^\p{Zp}/8
+    \x{2029}
+ 0: \x{2029}
+    ** Failers
+No match
+    X
+No match
+    \x{2028}
+No match
+  
+/^\p{Zs}/8
+    \ \
+ 0:  
+    \x{a0}
+ 0: \x{a0}
+    \x{1680}
+ 0: \x{1680}
+    \x{180e}
+ 0: \x{180e}
+    \x{2000}
+ 0: \x{2000}
+    \x{2001}     
+ 0: \x{2001}
+    ** Failers
+No match
+    \x{2028}
+No match
+    \x{200d} 
+No match
+  
+/\p{Nd}+(..)/8
+      \x{660}\x{661}\x{662}ABC
+ 0: \x{660}\x{661}\x{662}AB
+ 1: \x{660}\x{661}\x{662}A
+ 2: \x{660}\x{661}\x{662}
+  
+/\p{Nd}+?(..)/8
+      \x{660}\x{661}\x{662}ABC
+ 0: \x{660}\x{661}\x{662}AB
+ 1: \x{660}\x{661}\x{662}A
+ 2: \x{660}\x{661}\x{662}
+  
+/\p{Nd}{2,}(..)/8
+      \x{660}\x{661}\x{662}ABC
+ 0: \x{660}\x{661}\x{662}AB
+ 1: \x{660}\x{661}\x{662}A
+  
+/\p{Nd}{2,}?(..)/8
+      \x{660}\x{661}\x{662}ABC
+ 0: \x{660}\x{661}\x{662}AB
+ 1: \x{660}\x{661}\x{662}A
+  
+/\p{Nd}*(..)/8
+      \x{660}\x{661}\x{662}ABC
+ 0: \x{660}\x{661}\x{662}AB
+ 1: \x{660}\x{661}\x{662}A
+ 2: \x{660}\x{661}\x{662}
+ 3: \x{660}\x{661}
+  
+/\p{Nd}*?(..)/8
+      \x{660}\x{661}\x{662}ABC
+ 0: \x{660}\x{661}\x{662}AB
+ 1: \x{660}\x{661}\x{662}A
+ 2: \x{660}\x{661}\x{662}
+ 3: \x{660}\x{661}
+  
+/\p{Nd}{2}(..)/8
+      \x{660}\x{661}\x{662}ABC
+ 0: \x{660}\x{661}\x{662}A
+  
+/\p{Nd}{2,3}(..)/8
+      \x{660}\x{661}\x{662}ABC
+ 0: \x{660}\x{661}\x{662}AB
+ 1: \x{660}\x{661}\x{662}A
+  
+/\p{Nd}{2,3}?(..)/8
+      \x{660}\x{661}\x{662}ABC
+ 0: \x{660}\x{661}\x{662}AB
+ 1: \x{660}\x{661}\x{662}A
+  
+/\p{Nd}?(..)/8
+      \x{660}\x{661}\x{662}ABC
+ 0: \x{660}\x{661}\x{662}
+ 1: \x{660}\x{661}
+  
+/\p{Nd}??(..)/8
+      \x{660}\x{661}\x{662}ABC
+ 0: \x{660}\x{661}\x{662}
+ 1: \x{660}\x{661}
+  
+/\p{Nd}*+(..)/8
+      \x{660}\x{661}\x{662}ABC
+ 0: \x{660}\x{661}\x{662}AB
+  
+/\p{Nd}*+(...)/8
+      \x{660}\x{661}\x{662}ABC
+ 0: \x{660}\x{661}\x{662}ABC
+  
+/\p{Nd}*+(....)/8
+      ** Failers
+ 0: ** F
+      \x{660}\x{661}\x{662}ABC
+No match
+  
+/\p{Lu}/8i
+    A
+ 0: A
+    a\x{10a0}B 
+ 0: \x{10a0}
+    ** Failers 
+ 0: F
+    a
+No match
+    \x{1d00}  
+No match
+
+/\p{^Lu}/8i
+    1234
+ 0: 1
+    ** Failers
+ 0: *
+    ABC 
+No match
+
+/\P{Lu}/8i
+    1234
+ 0: 1
+    ** Failers
+ 0: *
+    ABC 
+No match
+
+/(?<=A\p{Nd})XYZ/8
+    A2XYZ
+ 0: XYZ
+    123A5XYZPQR
+ 0: XYZ
+    ABA\x{660}XYZpqr
+ 0: XYZ
+    ** Failers
+No match
+    AXYZ
+No match
+    XYZ     
+No match
+    
+/(?<!\pL)XYZ/8
+    1XYZ
+ 0: XYZ
+    AB=XYZ.. 
+ 0: XYZ
+    XYZ 
+ 0: XYZ
+    ** Failers
+No match
+    WXYZ 
+No match
+
+/[\p{Nd}]/8
+    1234
+ 0: 1
+
+/[\p{Nd}+-]+/8
+    1234
+ 0: 1234
+ 1: 123
+ 2: 12
+ 3: 1
+    12-34
+ 0: 12-34
+ 1: 12-3
+ 2: 12-
+ 3: 12
+ 4: 1
+    12+\x{661}-34  
+ 0: 12+\x{661}-34
+ 1: 12+\x{661}-3
+ 2: 12+\x{661}-
+ 3: 12+\x{661}
+ 4: 12+
+ 5: 12
+ 6: 1
+    ** Failers
+No match
+    abcd  
+No match
+
+/[\P{Nd}]+/8
+    abcd
+ 0: abcd
+ 1: abc
+ 2: ab
+ 3: a
+    ** Failers
+ 0: ** Failers
+ 1: ** Failer
+ 2: ** Faile
+ 3: ** Fail
+ 4: ** Fai
+ 5: ** Fa
+ 6: ** F
+ 7: ** 
+ 8: **
+ 9: *
+    1234
+No match
+
+/\D+/8
+    11111111111111111111111111111111111111111111111111111111111111111111111
+No match
+    aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+Matched, but too many subsidiary matches
+ 0: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+ 1: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+ 2: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+ 3: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+ 4: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+ 5: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+ 6: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+ 7: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+ 8: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+ 9: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+10: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+11: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+12: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+13: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+14: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+15: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+16: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+17: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+18: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+19: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+20: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+21: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+     
+/\P{Nd}+/8
+    11111111111111111111111111111111111111111111111111111111111111111111111
+No match
+    aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+Matched, but too many subsidiary matches
+ 0: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+ 1: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+ 2: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+ 3: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+ 4: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+ 5: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+ 6: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+ 7: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+ 8: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+ 9: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+10: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+11: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+12: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+13: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+14: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+15: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+16: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+17: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+18: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+19: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+20: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+21: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+
+/[\D]+/8
+    11111111111111111111111111111111111111111111111111111111111111111111111
+No match
+    aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+Matched, but too many subsidiary matches
+ 0: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+ 1: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+ 2: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+ 3: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+ 4: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+ 5: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+ 6: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+ 7: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+ 8: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+ 9: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+10: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+11: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+12: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+13: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+14: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+15: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+16: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+17: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+18: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+19: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+20: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+21: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+
+/[\P{Nd}]+/8
+    11111111111111111111111111111111111111111111111111111111111111111111111
+No match
+    aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+Matched, but too many subsidiary matches
+ 0: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+ 1: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+ 2: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+ 3: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+ 4: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+ 5: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+ 6: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+ 7: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+ 8: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+ 9: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+10: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+11: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+12: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+13: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+14: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+15: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+16: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+17: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+18: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+19: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+20: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+21: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+
+/[\D\P{Nd}]+/8
+    11111111111111111111111111111111111111111111111111111111111111111111111
+No match
+    aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+Matched, but too many subsidiary matches
+ 0: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+ 1: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+ 2: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+ 3: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+ 4: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+ 5: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+ 6: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+ 7: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+ 8: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+ 9: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+10: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+11: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+12: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+13: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+14: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+15: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+16: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+17: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+18: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+19: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+20: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+21: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+
+/\pL/8
+    a
+ 0: a
+    A 
+ 0: A
+
+/\pL/8i
+    a
+ 0: a
+    A 
+ 0: A
+    
+/\p{Lu}/8 
+    A
+ 0: A
+    aZ
+ 0: Z
+    ** Failers
+ 0: F
+    abc   
+No match
+
+/\p{Lu}/8i
+    A
+ 0: A
+    aZ
+ 0: Z
+    ** Failers
+ 0: F
+    abc   
+No match
+
+/\p{Ll}/8 
+    a
+ 0: a
+    Az
+ 0: z
+    ** Failers
+ 0: a
+    ABC   
+No match
+
+/\p{Ll}/8i 
+    a
+ 0: a
+    Az
+ 0: z
+    ** Failers
+ 0: a
+    ABC   
+No match
+
+/^\x{c0}$/8i
+    \x{c0}
+ 0: \x{c0}
+    \x{e0} 
+ 0: \x{e0}
+
+/^\x{e0}$/8i
+    \x{c0}
+ 0: \x{c0}
+    \x{e0} 
+ 0: \x{e0}
+
+/A\x{391}\x{10427}\x{ff3a}\x{1fb0}/8
+    A\x{391}\x{10427}\x{ff3a}\x{1fb0}
+ 0: A\x{391}\x{10427}\x{ff3a}\x{1fb0}
+    ** Failers
+No match
+    a\x{391}\x{10427}\x{ff3a}\x{1fb0}   
+No match
+    A\x{3b1}\x{10427}\x{ff3a}\x{1fb0}
+No match
+    A\x{391}\x{1044F}\x{ff3a}\x{1fb0}
+No match
+    A\x{391}\x{10427}\x{ff5a}\x{1fb0}
+No match
+    A\x{391}\x{10427}\x{ff3a}\x{1fb8}
+No match
+
+/A\x{391}\x{10427}\x{ff3a}\x{1fb0}/8i
+    A\x{391}\x{10427}\x{ff3a}\x{1fb0}
+ 0: A\x{391}\x{10427}\x{ff3a}\x{1fb0}
+    a\x{391}\x{10427}\x{ff3a}\x{1fb0}   
+ 0: a\x{391}\x{10427}\x{ff3a}\x{1fb0}
+    A\x{3b1}\x{10427}\x{ff3a}\x{1fb0}
+ 0: A\x{3b1}\x{10427}\x{ff3a}\x{1fb0}
+    A\x{391}\x{1044F}\x{ff3a}\x{1fb0}
+ 0: A\x{391}\x{1044f}\x{ff3a}\x{1fb0}
+    A\x{391}\x{10427}\x{ff5a}\x{1fb0}
+ 0: A\x{391}\x{10427}\x{ff5a}\x{1fb0}
+    A\x{391}\x{10427}\x{ff3a}\x{1fb8}
+ 0: A\x{391}\x{10427}\x{ff3a}\x{1fb8}
+
+/\x{391}+/8i
+    \x{391}\x{3b1}\x{3b1}\x{3b1}\x{391}
+ 0: \x{391}\x{3b1}\x{3b1}\x{3b1}\x{391}
+ 1: \x{391}\x{3b1}\x{3b1}\x{3b1}
+ 2: \x{391}\x{3b1}\x{3b1}
+ 3: \x{391}\x{3b1}
+ 4: \x{391}
+
+/\x{391}{3,5}(.)/8i
+    \x{391}\x{3b1}\x{3b1}\x{3b1}\x{391}X
+ 0: \x{391}\x{3b1}\x{3b1}\x{3b1}\x{391}X
+ 1: \x{391}\x{3b1}\x{3b1}\x{3b1}\x{391}
+ 2: \x{391}\x{3b1}\x{3b1}\x{3b1}
+
+/\x{391}{3,5}?(.)/8i
+    \x{391}\x{3b1}\x{3b1}\x{3b1}\x{391}X
+ 0: \x{391}\x{3b1}\x{3b1}\x{3b1}\x{391}X
+ 1: \x{391}\x{3b1}\x{3b1}\x{3b1}\x{391}
+ 2: \x{391}\x{3b1}\x{3b1}\x{3b1}
+
+/[\x{391}\x{ff3a}]/8i
+    \x{391}
+ 0: \x{391}
+    \x{ff3a}
+ 0: \x{ff3a}
+    \x{3b1}
+ 0: \x{3b1}
+    \x{ff5a}   
+ 0: \x{ff5a}
+    
+/[\x{c0}\x{391}]/8i
+    \x{c0}
+ 0: \x{c0}
+    \x{e0} 
+ 0: \x{e0}
+
+/[\x{105}-\x{109}]/8i
+    \x{104}
+ 0: \x{104}
+    \x{105}
+ 0: \x{105}
+    \x{109}  
+ 0: \x{109}
+    ** Failers
+No match
+    \x{100}
+No match
+    \x{10a} 
+No match
+    
+/[z-\x{100}]/8i 
+    Z
+ 0: Z
+    z
+ 0: z
+    \x{39c}
+ 0: \x{39c}
+    \x{178}
+ 0: \x{178}
+    |
+ 0: |
+    \x{80}
+ 0: \x{80}
+    \x{ff}
+ 0: \x{ff}
+    \x{100}
+ 0: \x{100}
+    \x{101} 
+ 0: \x{101}
+    ** Failers
+No match
+    \x{102}
+No match
+    Y
+No match
+    y           
+No match
+
+/[z-\x{100}]/8i
+
+/^\X/8
+    A
+ 0: A
+    A\x{300}BC 
+ 0: A\x{300}
+    A\x{300}\x{301}\x{302}BC 
+ 0: A\x{300}\x{301}\x{302}
+    *** Failers
+ 0: *
+    \x{300}  
+No match
+
+/^[\X]/8
+    X123
+ 0: X
+    *** Failers
+No match
+    AXYZ
+No match
+
+/^(\X*)C/8
+    A\x{300}\x{301}\x{302}BCA\x{300}\x{301} 
+ 0: A\x{300}\x{301}\x{302}BC
+    A\x{300}\x{301}\x{302}BCA\x{300}\x{301}C 
+ 0: A\x{300}\x{301}\x{302}BCA\x{300}\x{301}C
+ 1: A\x{300}\x{301}\x{302}BC
+
+/^(\X*?)C/8
+    A\x{300}\x{301}\x{302}BCA\x{300}\x{301} 
+ 0: A\x{300}\x{301}\x{302}BC
+    A\x{300}\x{301}\x{302}BCA\x{300}\x{301}C 
+ 0: A\x{300}\x{301}\x{302}BCA\x{300}\x{301}C
+ 1: A\x{300}\x{301}\x{302}BC
+
+/^(\X*)(.)/8
+    A\x{300}\x{301}\x{302}BCA\x{300}\x{301} 
+ 0: A\x{300}\x{301}\x{302}BCA
+ 1: A\x{300}\x{301}\x{302}BC
+ 2: A\x{300}\x{301}\x{302}B
+ 3: A
+    A\x{300}\x{301}\x{302}BCA\x{300}\x{301}C 
+ 0: A\x{300}\x{301}\x{302}BCA\x{300}\x{301}C
+ 1: A\x{300}\x{301}\x{302}BCA
+ 2: A\x{300}\x{301}\x{302}BC
+ 3: A\x{300}\x{301}\x{302}B
+ 4: A
+
+/^(\X*?)(.)/8
+    A\x{300}\x{301}\x{302}BCA\x{300}\x{301} 
+ 0: A\x{300}\x{301}\x{302}BCA
+ 1: A\x{300}\x{301}\x{302}BC
+ 2: A\x{300}\x{301}\x{302}B
+ 3: A
+    A\x{300}\x{301}\x{302}BCA\x{300}\x{301}C 
+ 0: A\x{300}\x{301}\x{302}BCA\x{300}\x{301}C
+ 1: A\x{300}\x{301}\x{302}BCA
+ 2: A\x{300}\x{301}\x{302}BC
+ 3: A\x{300}\x{301}\x{302}B
+ 4: A
+
+/^\X(.)/8
+    *** Failers
+ 0: **
+    A\x{300}\x{301}\x{302}
+No match
+
+/^\X{2,3}(.)/8
+    A\x{300}\x{301}B\x{300}X
+ 0: A\x{300}\x{301}B\x{300}X
+    A\x{300}\x{301}B\x{300}C\x{300}\x{301}
+ 0: A\x{300}\x{301}B\x{300}C
+    A\x{300}\x{301}B\x{300}C\x{300}\x{301}X
+ 0: A\x{300}\x{301}B\x{300}C\x{300}\x{301}X
+ 1: A\x{300}\x{301}B\x{300}C
+    A\x{300}\x{301}B\x{300}C\x{300}\x{301}DA\x{300}X
+ 0: A\x{300}\x{301}B\x{300}C\x{300}\x{301}D
+ 1: A\x{300}\x{301}B\x{300}C
+    
+/^\X{2,3}?(.)/8
+    A\x{300}\x{301}B\x{300}X
+ 0: A\x{300}\x{301}B\x{300}X
+    A\x{300}\x{301}B\x{300}C\x{300}\x{301}
+ 0: A\x{300}\x{301}B\x{300}C
+    A\x{300}\x{301}B\x{300}C\x{300}\x{301}X
+ 0: A\x{300}\x{301}B\x{300}C\x{300}\x{301}X
+ 1: A\x{300}\x{301}B\x{300}C
+    A\x{300}\x{301}B\x{300}C\x{300}\x{301}DA\x{300}X
+ 0: A\x{300}\x{301}B\x{300}C\x{300}\x{301}D
+ 1: A\x{300}\x{301}B\x{300}C
+
+/^\pN{2,3}X/
+    12X
+ 0: 12X
+    123X
+ 0: 123X
+    *** Failers
+No match
+    X
+No match
+    1X
+No match
+    1234X     
+No match
+
+/\x{100}/i8
+    \x{100}   
+ 0: \x{100}
+    \x{101} 
+ 0: \x{101}
+    
+/^\p{Han}+/8
+    \x{2e81}\x{3007}\x{2f804}\x{31a0}
+ 0: \x{2e81}\x{3007}\x{2f804}
+ 1: \x{2e81}\x{3007}
+ 2: \x{2e81}
+    ** Failers
+No match
+    \x{2e7f}  
+No match
+
+/^\P{Katakana}+/8
+    \x{3105}
+ 0: \x{3105}
+    ** Failers
+ 0: ** Failers
+ 1: ** Failer
+ 2: ** Faile
+ 3: ** Fail
+ 4: ** Fai
+ 5: ** Fa
+ 6: ** F
+ 7: ** 
+ 8: **
+ 9: *
+    \x{30ff}  
+No match
+
+/^[\p{Arabic}]/8
+    \x{06e9}
+ 0: \x{6e9}
+    \x{060b}
+ 0: \x{60b}
+    ** Failers
+No match
+    X\x{06e9}   
+No match
+
+/^[\P{Yi}]/8
+    \x{2f800}
+ 0: \x{2f800}
+    ** Failers
+ 0: *
+    \x{a014}
+No match
+    \x{a4c6}   
+No match
+
+/^\p{Any}X/8
+    AXYZ
+ 0: AX
+    \x{1234}XYZ 
+ 0: \x{1234}X
+    ** Failers
+No match
+    X  
+No match
+    
+/^\P{Any}X/8
+    ** Failers
+No match
+    AX
+No match
+    
+/^\p{Any}?X/8
+    XYZ
+ 0: X
+    AXYZ
+ 0: AX
+    \x{1234}XYZ 
+ 0: \x{1234}X
+    ** Failers
+No match
+    ABXYZ   
+No match
+
+/^\P{Any}?X/8
+    XYZ
+ 0: X
+    ** Failers
+No match
+    AXYZ
+No match
+    \x{1234}XYZ 
+No match
+    ABXYZ   
+No match
+
+/^\p{Any}+X/8
+    AXYZ
+ 0: AX
+    \x{1234}XYZ
+ 0: \x{1234}X
+    A\x{1234}XYZ
+ 0: A\x{1234}X
+    ** Failers
+No match
+    XYZ
+No match
+
+/^\P{Any}+X/8
+    ** Failers
+No match
+    AXYZ
+No match
+    \x{1234}XYZ
+No match
+    A\x{1234}XYZ
+No match
+    XYZ
+No match
+
+/^\p{Any}*X/8
+    XYZ
+ 0: X
+    AXYZ
+ 0: AX
+    \x{1234}XYZ
+ 0: \x{1234}X
+    A\x{1234}XYZ
+ 0: A\x{1234}X
+    ** Failers
+No match
+
+/^\P{Any}*X/8
+    XYZ
+ 0: X
+    ** Failers
+No match
+    AXYZ
+No match
+    \x{1234}XYZ
+No match
+    A\x{1234}XYZ
+No match
+
+/^[\p{Any}]X/8
+    AXYZ
+ 0: AX
+    \x{1234}XYZ 
+ 0: \x{1234}X
+    ** Failers
+No match
+    X  
+No match
+    
+/^[\P{Any}]X/8
+    ** Failers
+No match
+    AX
+No match
+    
+/^[\p{Any}]?X/8
+    XYZ
+ 0: X
+    AXYZ
+ 0: AX
+    \x{1234}XYZ 
+ 0: \x{1234}X
+    ** Failers
+No match
+    ABXYZ   
+No match
+
+/^[\P{Any}]?X/8
+    XYZ
+ 0: X
+    ** Failers
+No match
+    AXYZ
+No match
+    \x{1234}XYZ 
+No match
+    ABXYZ   
+No match
+
+/^[\p{Any}]+X/8
+    AXYZ
+ 0: AX
+    \x{1234}XYZ
+ 0: \x{1234}X
+    A\x{1234}XYZ
+ 0: A\x{1234}X
+    ** Failers
+No match
+    XYZ
+No match
+
+/^[\P{Any}]+X/8
+    ** Failers
+No match
+    AXYZ
+No match
+    \x{1234}XYZ
+No match
+    A\x{1234}XYZ
+No match
+    XYZ
+No match
+
+/^[\p{Any}]*X/8
+    XYZ
+ 0: X
+    AXYZ
+ 0: AX
+    \x{1234}XYZ
+ 0: \x{1234}X
+    A\x{1234}XYZ
+ 0: A\x{1234}X
+    ** Failers
+No match
+
+/^[\P{Any}]*X/8
+    XYZ
+ 0: X
+    ** Failers
+No match
+    AXYZ
+No match
+    \x{1234}XYZ
+No match
+    A\x{1234}XYZ
+No match
+
+/^\p{Any}{3,5}?/8
+    abcdefgh
+ 0: abcde
+ 1: abcd
+ 2: abc
+    \x{1234}\n\r\x{3456}xyz 
+ 0: \x{1234}\x{0a}\x{0d}\x{3456}x
+ 1: \x{1234}\x{0a}\x{0d}\x{3456}
+ 2: \x{1234}\x{0a}\x{0d}
+
+/^\p{Any}{3,5}/8
+    abcdefgh
+ 0: abcde
+ 1: abcd
+ 2: abc
+    \x{1234}\n\r\x{3456}xyz 
+ 0: \x{1234}\x{0a}\x{0d}\x{3456}x
+ 1: \x{1234}\x{0a}\x{0d}\x{3456}
+ 2: \x{1234}\x{0a}\x{0d}
+
+/^\P{Any}{3,5}?/8
+    ** Failers
+No match
+    abcdefgh
+No match
+    \x{1234}\n\r\x{3456}xyz 
+No match
+
+/^\p{L&}X/8
+     AXY
+ 0: AX
+     aXY
+ 0: aX
+     \x{1c5}XY
+ 0: \x{1c5}X
+     ** Failers
+No match
+     \x{1bb}XY
+No match
+     \x{2b0}XY
+No match
+     !XY      
+No match
+
+/^[\p{L&}]X/8
+     AXY
+ 0: AX
+     aXY
+ 0: aX
+     \x{1c5}XY
+ 0: \x{1c5}X
+     ** Failers
+No match
+     \x{1bb}XY
+No match
+     \x{2b0}XY
+No match
+     !XY      
+No match
+
+/^\p{L&}+X/8
+     AXY
+ 0: AX
+     aXY
+ 0: aX
+     AbcdeXyz 
+ 0: AbcdeX
+     \x{1c5}AbXY
+ 0: \x{1c5}AbX
+     abcDEXypqreXlmn 
+ 0: abcDEXypqreX
+ 1: abcDEX
+     ** Failers
+No match
+     \x{1bb}XY
+No match
+     \x{2b0}XY
+No match
+     !XY      
+No match
+
+/^[\p{L&}]+X/8
+     AXY
+ 0: AX
+     aXY
+ 0: aX
+     AbcdeXyz 
+ 0: AbcdeX
+     \x{1c5}AbXY
+ 0: \x{1c5}AbX
+     abcDEXypqreXlmn 
+ 0: abcDEXypqreX
+ 1: abcDEX
+     ** Failers
+No match
+     \x{1bb}XY
+No match
+     \x{2b0}XY
+No match
+     !XY      
+No match
+
+/^\p{L&}+?X/8
+     AXY
+ 0: AX
+     aXY
+ 0: aX
+     AbcdeXyz 
+ 0: AbcdeX
+     \x{1c5}AbXY
+ 0: \x{1c5}AbX
+     abcDEXypqreXlmn 
+ 0: abcDEXypqreX
+ 1: abcDEX
+     ** Failers
+No match
+     \x{1bb}XY
+No match
+     \x{2b0}XY
+No match
+     !XY      
+No match
+
+/^[\p{L&}]+?X/8
+     AXY
+ 0: AX
+     aXY
+ 0: aX
+     AbcdeXyz 
+ 0: AbcdeX
+     \x{1c5}AbXY
+ 0: \x{1c5}AbX
+     abcDEXypqreXlmn 
+ 0: abcDEXypqreX
+ 1: abcDEX
+     ** Failers
+No match
+     \x{1bb}XY
+No match
+     \x{2b0}XY
+No match
+     !XY      
+No match
+
+/^\P{L&}X/8
+     !XY
+ 0: !X
+     \x{1bb}XY
+ 0: \x{1bb}X
+     \x{2b0}XY
+ 0: \x{2b0}X
+     ** Failers
+No match
+     \x{1c5}XY
+No match
+     AXY      
+No match
+
+/^[\P{L&}]X/8
+     !XY
+ 0: !X
+     \x{1bb}XY
+ 0: \x{1bb}X
+     \x{2b0}XY
+ 0: \x{2b0}X
+     ** Failers
+No match
+     \x{1c5}XY
+No match
+     AXY      
+No match
+
+/^\x{023a}+?(\x{0130}+)/8i
+  \x{023a}\x{2c65}\x{0130}
+ 0: \x{23a}\x{2c65}\x{130}
+  
+/^\x{023a}+([^X])/8i
+  \x{023a}\x{2c65}X
+ 0: \x{23a}\x{2c65}
+ 
+/\x{c0}+\x{116}+/8i
+    \x{c0}\x{e0}\x{116}\x{117}
+ 0: \x{c0}\x{e0}\x{116}\x{117}
+ 1: \x{c0}\x{e0}\x{116}
+
+/[\x{c0}\x{116}]+/8i
+    \x{c0}\x{e0}\x{116}\x{117}
+ 0: \x{c0}\x{e0}\x{116}\x{117}
+ 1: \x{c0}\x{e0}\x{116}
+ 2: \x{c0}\x{e0}
+ 3: \x{c0}
+
+/Check property support in non-UTF-8 mode/
+ 
+/\p{L}{4}/
+    123abcdefg
+ 0: abcd
+    123abc\xc4\xc5zz
+ 0: abc\xc4
+
+/\p{Carian}\p{Cham}\p{Kayah_Li}\p{Lepcha}\p{Lycian}\p{Lydian}\p{Ol_Chiki}\p{Rejang}\p{Saurashtra}\p{Sundanese}\p{Vai}/8
+    \x{102A4}\x{AA52}\x{A91D}\x{1C46}\x{10283}\x{1092E}\x{1C6B}\x{A93B}\x{A8BF}\x{1BA0}\x{A50A}====
+ 0: \x{102a4}\x{aa52}\x{a91d}\x{1c46}\x{10283}\x{1092e}\x{1c6b}\x{a93b}\x{a8bf}\x{1ba0}\x{a50a}
+
+/\x{a77d}\x{1d79}/8i
+    \x{a77d}\x{1d79}
+ 0: \x{a77d}\x{1d79}
+    \x{1d79}\x{a77d} 
+ 0: \x{1d79}\x{a77d}
+
+/\x{a77d}\x{1d79}/8
+    \x{a77d}\x{1d79}
+ 0: \x{a77d}\x{1d79}
+    ** Failers 
+No match
+    \x{1d79}\x{a77d} 
+No match
+
+/^\p{Xan}/8
+    ABCD
+ 0: A
+    1234
+ 0: 1
+    \x{6ca}
+ 0: \x{6ca}
+    \x{a6c}
+ 0: \x{a6c}
+    \x{10a7}   
+ 0: \x{10a7}
+    ** Failers
+No match
+    _ABC   
+No match
+
+/^\p{Xan}+/8
+    ABCD1234\x{6ca}\x{a6c}\x{10a7}_
+ 0: ABCD1234\x{6ca}\x{a6c}\x{10a7}
+ 1: ABCD1234\x{6ca}\x{a6c}
+ 2: ABCD1234\x{6ca}
+ 3: ABCD1234
+ 4: ABCD123
+ 5: ABCD12
+ 6: ABCD1
+ 7: ABCD
+ 8: ABC
+ 9: AB
+10: A
+    ** Failers
+No match
+    _ABC   
+No match
+
+/^\p{Xan}*/8
+    ABCD1234\x{6ca}\x{a6c}\x{10a7}_
+ 0: ABCD1234\x{6ca}\x{a6c}\x{10a7}
+ 1: ABCD1234\x{6ca}\x{a6c}
+ 2: ABCD1234\x{6ca}
+ 3: ABCD1234
+ 4: ABCD123
+ 5: ABCD12
+ 6: ABCD1
+ 7: ABCD
+ 8: ABC
+ 9: AB
+10: A
+11: 
+    
+/^\p{Xan}{2,9}/8
+    ABCD1234\x{6ca}\x{a6c}\x{10a7}_
+ 0: ABCD1234\x{6ca}
+ 1: ABCD1234
+ 2: ABCD123
+ 3: ABCD12
+ 4: ABCD1
+ 5: ABCD
+ 6: ABC
+ 7: AB
+    
+/^[\p{Xan}]/8
+    ABCD1234_
+ 0: A
+    1234abcd_
+ 0: 1
+    \x{6ca}
+ 0: \x{6ca}
+    \x{a6c}
+ 0: \x{a6c}
+    \x{10a7}   
+ 0: \x{10a7}
+    ** Failers
+No match
+    _ABC   
+No match
+ 
+/^[\p{Xan}]+/8
+    ABCD1234\x{6ca}\x{a6c}\x{10a7}_
+ 0: ABCD1234\x{6ca}\x{a6c}\x{10a7}
+ 1: ABCD1234\x{6ca}\x{a6c}
+ 2: ABCD1234\x{6ca}
+ 3: ABCD1234
+ 4: ABCD123
+ 5: ABCD12
+ 6: ABCD1
+ 7: ABCD
+ 8: ABC
+ 9: AB
+10: A
+    ** Failers
+No match
+    _ABC   
+No match
+
+/^>\p{Xsp}/8
+    >\x{1680}\x{2028}\x{0b}
+ 0: >\x{1680}
+    ** Failers
+No match
+    \x{0b} 
+No match
+
+/^>\p{Xsp}+/8
+    > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}\x{0b}
+ 0: > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}
+ 1: > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}
+ 2: > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}
+ 3: > \x{09}\x{0a}\x{0c}\x{0d}
+ 4: > \x{09}\x{0a}\x{0c}
+ 5: > \x{09}\x{0a}
+ 6: > \x{09}
+ 7: > 
+
+/^>\p{Xsp}*/8
+    > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}\x{0b}
+ 0: > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}
+ 1: > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}
+ 2: > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}
+ 3: > \x{09}\x{0a}\x{0c}\x{0d}
+ 4: > \x{09}\x{0a}\x{0c}
+ 5: > \x{09}\x{0a}
+ 6: > \x{09}
+ 7: > 
+ 8: >
+    
+/^>\p{Xsp}{2,9}/8
+    > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}\x{0b}
+ 0: > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}
+ 1: > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}
+ 2: > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}
+ 3: > \x{09}\x{0a}\x{0c}\x{0d}
+ 4: > \x{09}\x{0a}\x{0c}
+ 5: > \x{09}\x{0a}
+ 6: > \x{09}
+    
+/^>[\p{Xsp}]/8
+    >\x{2028}\x{0b}
+ 0: >\x{2028}
+ 
+/^>[\p{Xsp}]+/8
+    > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}\x{0b}
+ 0: > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}
+ 1: > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}
+ 2: > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}
+ 3: > \x{09}\x{0a}\x{0c}\x{0d}
+ 4: > \x{09}\x{0a}\x{0c}
+ 5: > \x{09}\x{0a}
+ 6: > \x{09}
+ 7: > 
+
+/^>\p{Xps}/8
+    >\x{1680}\x{2028}\x{0b}
+ 0: >\x{1680}
+    >\x{a0} 
+ 0: >\x{a0}
+    ** Failers
+No match
+    \x{0b} 
+No match
+
+/^>\p{Xps}+/8
+    > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}\x{0b}
+ 0: > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}\x{0b}
+ 1: > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}
+ 2: > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}
+ 3: > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}
+ 4: > \x{09}\x{0a}\x{0c}\x{0d}
+ 5: > \x{09}\x{0a}\x{0c}
+ 6: > \x{09}\x{0a}
+ 7: > \x{09}
+ 8: > 
+
+/^>\p{Xps}+?/8
+    >\x{1680}\x{2028}\x{0b}
+ 0: >\x{1680}\x{2028}\x{0b}
+ 1: >\x{1680}\x{2028}
+ 2: >\x{1680}
+
+/^>\p{Xps}*/8
+    > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}\x{0b}
+ 0: > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}\x{0b}
+ 1: > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}
+ 2: > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}
+ 3: > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}
+ 4: > \x{09}\x{0a}\x{0c}\x{0d}
+ 5: > \x{09}\x{0a}\x{0c}
+ 6: > \x{09}\x{0a}
+ 7: > \x{09}
+ 8: > 
+ 9: >
+    
+/^>\p{Xps}{2,9}/8
+    > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}\x{0b}
+ 0: > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}\x{0b}
+ 1: > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}
+ 2: > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}
+ 3: > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}
+ 4: > \x{09}\x{0a}\x{0c}\x{0d}
+ 5: > \x{09}\x{0a}\x{0c}
+ 6: > \x{09}\x{0a}
+ 7: > \x{09}
+    
+/^>\p{Xps}{2,9}?/8
+    > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}\x{0b}
+ 0: > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}\x{0b}
+ 1: > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}
+ 2: > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}
+ 3: > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}
+ 4: > \x{09}\x{0a}\x{0c}\x{0d}
+ 5: > \x{09}\x{0a}\x{0c}
+ 6: > \x{09}\x{0a}
+ 7: > \x{09}
+    
+/^>[\p{Xps}]/8
+    >\x{2028}\x{0b}
+ 0: >\x{2028}
+ 
+/^>[\p{Xps}]+/8
+    > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}\x{0b}
+ 0: > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}\x{0b}
+ 1: > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}
+ 2: > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}
+ 3: > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}
+ 4: > \x{09}\x{0a}\x{0c}\x{0d}
+ 5: > \x{09}\x{0a}\x{0c}
+ 6: > \x{09}\x{0a}
+ 7: > \x{09}
+ 8: > 
+
+/^\p{Xwd}/8
+    ABCD
+ 0: A
+    1234
+ 0: 1
+    \x{6ca}
+ 0: \x{6ca}
+    \x{a6c}
+ 0: \x{a6c}
+    \x{10a7}
+ 0: \x{10a7}
+    _ABC    
+ 0: _
+    ** Failers
+No match
+    [] 
+No match
+
+/^\p{Xwd}+/8
+    ABCD1234\x{6ca}\x{a6c}\x{10a7}_
+ 0: ABCD1234\x{6ca}\x{a6c}\x{10a7}_
+ 1: ABCD1234\x{6ca}\x{a6c}\x{10a7}
+ 2: ABCD1234\x{6ca}\x{a6c}
+ 3: ABCD1234\x{6ca}
+ 4: ABCD1234
+ 5: ABCD123
+ 6: ABCD12
+ 7: ABCD1
+ 8: ABCD
+ 9: ABC
+10: AB
+11: A
+
+/^\p{Xwd}*/8
+    ABCD1234\x{6ca}\x{a6c}\x{10a7}_
+ 0: ABCD1234\x{6ca}\x{a6c}\x{10a7}_
+ 1: ABCD1234\x{6ca}\x{a6c}\x{10a7}
+ 2: ABCD1234\x{6ca}\x{a6c}
+ 3: ABCD1234\x{6ca}
+ 4: ABCD1234
+ 5: ABCD123
+ 6: ABCD12
+ 7: ABCD1
+ 8: ABCD
+ 9: ABC
+10: AB
+11: A
+12: 
+    
+/^\p{Xwd}{2,9}/8
+    A_12\x{6ca}\x{a6c}\x{10a7}
+ 0: A_12\x{6ca}\x{a6c}\x{10a7}
+ 1: A_12\x{6ca}\x{a6c}
+ 2: A_12\x{6ca}
+ 3: A_12
+ 4: A_1
+ 5: A_
+    
+/^[\p{Xwd}]/8
+    ABCD1234_
+ 0: A
+    1234abcd_
+ 0: 1
+    \x{6ca}
+ 0: \x{6ca}
+    \x{a6c}
+ 0: \x{a6c}
+    \x{10a7}   
+ 0: \x{10a7}
+    _ABC 
+ 0: _
+    ** Failers
+No match
+    []   
+No match
+ 
+/^[\p{Xwd}]+/8
+    ABCD1234\x{6ca}\x{a6c}\x{10a7}_
+ 0: ABCD1234\x{6ca}\x{a6c}\x{10a7}_
+ 1: ABCD1234\x{6ca}\x{a6c}\x{10a7}
+ 2: ABCD1234\x{6ca}\x{a6c}
+ 3: ABCD1234\x{6ca}
+ 4: ABCD1234
+ 5: ABCD123
+ 6: ABCD12
+ 7: ABCD1
+ 8: ABCD
+ 9: ABC
+10: AB
+11: A
+
+/-- Unicode properties for \b abd \B --/
+
+/\b...\B/8W
+    abc_
+ 0: abc
+    \x{37e}abc\x{376} 
+ 0: abc
+    \x{37e}\x{376}\x{371}\x{393}\x{394} 
+ 0: \x{376}\x{371}\x{393}
+    !\x{c0}++\x{c1}\x{c2} 
+ 0: ++\x{c1}
+    !\x{c0}+++++ 
+ 0: \x{c0}++
+
+/-- Without PCRE_UCP, non-ASCII always fail, even if < 256  --/
+
+/\b...\B/8
+    abc_
+ 0: abc
+    ** Failers 
+ 0: Fai
+    \x{37e}abc\x{376} 
+No match
+    \x{37e}\x{376}\x{371}\x{393}\x{394} 
+No match
+    !\x{c0}++\x{c1}\x{c2} 
+No match
+    !\x{c0}+++++ 
+No match
+
+/-- With PCRE_UCP, non-UTF8 chars that are < 256 still check properties  --/
+
+/\b...\B/W
+    abc_
+ 0: abc
+    !\x{c0}++\x{c1}\x{c2} 
+ 0: ++\xc1
+    !\x{c0}+++++ 
+ 0: \xc0++
+    
+/-- Caseless single negated characters > 127 need UCP support --/
+
+/[^\x{100}]/8i
+    \x{100}\x{101}X
+ 0: X
+
+/[^\x{100}]+/8i
+    \x{100}\x{101}XX
+ 0: XX
+ 1: X
+
+/^\X/8
+    A\P
+ 0: A
+    A\P\P 
+Partial match: A
+    A\x{300}\x{301}\P
+ 0: A\x{300}\x{301}
+    A\x{300}\x{301}\P\P  
+Partial match: A\x{300}\x{301}
+    A\x{301}\P
+ 0: A\x{301}
+    A\x{301}\P\P  
+Partial match: A\x{301}
+    
+/^\X{2,3}/8
+    A\P
+Partial match: A
+    A\P\P 
+Partial match: A
+    AA\P
+ 0: AA
+    AA\P\P  
+Partial match: AA
+    A\x{300}\x{301}\P
+Partial match: A\x{300}\x{301}
+    A\x{300}\x{301}\P\P  
+Partial match: A\x{300}\x{301}
+    A\x{300}\x{301}A\x{300}\x{301}\P
+ 0: A\x{300}\x{301}A\x{300}\x{301}
+    A\x{300}\x{301}A\x{300}\x{301}\P\P  
+Partial match: A\x{300}\x{301}A\x{300}\x{301}
+
+/^\X{2}/8
+    AA\P
+ 0: AA
+    AA\P\P  
+Partial match: AA
+    A\x{300}\x{301}A\x{300}\x{301}\P
+ 0: A\x{300}\x{301}A\x{300}\x{301}
+    A\x{300}\x{301}A\x{300}\x{301}\P\P  
+Partial match: A\x{300}\x{301}A\x{300}\x{301}
+    
+/^\X+/8
+    AA\P
+ 0: AA
+ 1: A
+    AA\P\P  
+Partial match: AA
+
+/^\X+?Z/8
+    AA\P
+Partial match: AA
+    AA\P\P 
+Partial match: AA
+
+/-- End of testinput10 --/ 
diff --git a/ext/pcre/pcrelib/testdata/testoutput2 b/ext/pcre/pcrelib/testdata/testoutput2
new file mode 100644
index 0000000..77b108c
--- /dev/null
+++ b/ext/pcre/pcrelib/testdata/testoutput2
@@ -0,0 +1,12364 @@
+/-- This set of tests is not Perl-compatible. It checks on special features
+    of PCRE's API, error diagnostics, and the compiled code of some patterns.
+    It also checks the non-Perl syntax the PCRE supports (Python, .NET, 
+    Oniguruma). Finally, there are some tests where PCRE and Perl differ, 
+    either because PCRE can't be compatible, or there is a possible Perl 
+    bug.
+    
+    NOTE: This is a non-UTF set of tests. When UTF support is needed, use
+    test 5, and if Unicode Property Support is needed, use test 7. --/
+  
+/(a)b|/I
+Capturing subpattern count = 1
+No options
+No first char
+No need char
+
+/abc/I
+Capturing subpattern count = 0
+No options
+First char = 'a'
+Need char = 'c'
+    abc
+ 0: abc
+    defabc
+ 0: abc
+    \Aabc
+ 0: abc
+    *** Failers
+No match
+    \Adefabc
+No match
+    ABC
+No match
+
+/^abc/I
+Capturing subpattern count = 0
+Options: anchored
+No first char
+No need char
+    abc
+ 0: abc
+    \Aabc
+ 0: abc
+    *** Failers
+No match
+    defabc
+No match
+    \Adefabc
+No match
+
+/a+bc/I
+Capturing subpattern count = 0
+No options
+First char = 'a'
+Need char = 'c'
+
+/a*bc/I
+Capturing subpattern count = 0
+No options
+No first char
+Need char = 'c'
+
+/a{3}bc/I
+Capturing subpattern count = 0
+No options
+First char = 'a'
+Need char = 'c'
+
+/(abc|a+z)/I
+Capturing subpattern count = 1
+No options
+First char = 'a'
+No need char
+
+/^abc$/I
+Capturing subpattern count = 0
+Options: anchored
+No first char
+No need char
+    abc
+ 0: abc
+    *** Failers
+No match
+    def\nabc
+No match
+
+/ab\idef/X
+Failed: unrecognized character follows \ at offset 3
+
+/(?X)ab\idef/X
+Failed: unrecognized character follows \ at offset 7
+
+/x{5,4}/
+Failed: numbers out of order in {} quantifier at offset 5
+
+/z{65536}/
+Failed: number too big in {} quantifier at offset 7
+
+/[abcd/
+Failed: missing terminating ] for character class at offset 5
+
+/(?X)[\B]/
+Failed: invalid escape sequence in character class at offset 6
+
+/(?X)[\R]/
+Failed: invalid escape sequence in character class at offset 6
+
+/(?X)[\X]/
+Failed: invalid escape sequence in character class at offset 6
+
+/[\B]/BZ
+------------------------------------------------------------------
+        Bra
+        B
+        Ket
+        End
+------------------------------------------------------------------
+
+/[\R]/BZ
+------------------------------------------------------------------
+        Bra
+        R
+        Ket
+        End
+------------------------------------------------------------------
+
+/[\X]/BZ
+------------------------------------------------------------------
+        Bra
+        X
+        Ket
+        End
+------------------------------------------------------------------
+
+/[z-a]/
+Failed: range out of order in character class at offset 3
+
+/^*/
+Failed: nothing to repeat at offset 1
+
+/(abc/
+Failed: missing ) at offset 4
+
+/(?# abc/
+Failed: missing ) after comment at offset 7
+
+/(?z)abc/
+Failed: unrecognized character after (? or (?- at offset 2
+
+/.*b/I
+Capturing subpattern count = 0
+No options
+First char at start or follows newline
+Need char = 'b'
+
+/.*?b/I
+Capturing subpattern count = 0
+No options
+First char at start or follows newline
+Need char = 'b'
+
+/cat|dog|elephant/I
+Capturing subpattern count = 0
+No options
+No first char
+No need char
+    this sentence eventually mentions a cat
+ 0: cat
+    this sentences rambles on and on for a while and then reaches elephant
+ 0: elephant
+
+/cat|dog|elephant/IS
+Capturing subpattern count = 0
+No options
+No first char
+No need char
+Subject length lower bound = 3
+Starting byte set: c d e 
+    this sentence eventually mentions a cat
+ 0: cat
+    this sentences rambles on and on for a while and then reaches elephant
+ 0: elephant
+
+/cat|dog|elephant/IiS
+Capturing subpattern count = 0
+Options: caseless
+No first char
+No need char
+Subject length lower bound = 3
+Starting byte set: C D E c d e 
+    this sentence eventually mentions a CAT cat
+ 0: CAT
+    this sentences rambles on and on for a while to elephant ElePhant
+ 0: elephant
+
+/a|[bcd]/IS
+Capturing subpattern count = 0
+No options
+No first char
+No need char
+Subject length lower bound = 1
+Starting byte set: a b c d 
+
+/(a|[^\dZ])/IS
+Capturing subpattern count = 1
+No options
+No first char
+No need char
+Subject length lower bound = 1
+Starting byte set: \x00 \x01 \x02 \x03 \x04 \x05 \x06 \x07 \x08 \x09 \x0a 
+  \x0b \x0c \x0d \x0e \x0f \x10 \x11 \x12 \x13 \x14 \x15 \x16 \x17 \x18 \x19 
+  \x1a \x1b \x1c \x1d \x1e \x1f \x20 ! " # $ % & ' ( ) * + , - . / : ; < = > 
+  ? @ A B C D E F G H I J K L M N O P Q R S T U V W X Y [ \ ] ^ _ ` a b c d 
+  e f g h i j k l m n o p q r s t u v w x y z { | } ~ \x7f \x80 \x81 \x82 \x83 
+  \x84 \x85 \x86 \x87 \x88 \x89 \x8a \x8b \x8c \x8d \x8e \x8f \x90 \x91 \x92 
+  \x93 \x94 \x95 \x96 \x97 \x98 \x99 \x9a \x9b \x9c \x9d \x9e \x9f \xa0 \xa1 
+  \xa2 \xa3 \xa4 \xa5 \xa6 \xa7 \xa8 \xa9 \xaa \xab \xac \xad \xae \xaf \xb0 
+  \xb1 \xb2 \xb3 \xb4 \xb5 \xb6 \xb7 \xb8 \xb9 \xba \xbb \xbc \xbd \xbe \xbf 
+  \xc0 \xc1 \xc2 \xc3 \xc4 \xc5 \xc6 \xc7 \xc8 \xc9 \xca \xcb \xcc \xcd \xce 
+  \xcf \xd0 \xd1 \xd2 \xd3 \xd4 \xd5 \xd6 \xd7 \xd8 \xd9 \xda \xdb \xdc \xdd 
+  \xde \xdf \xe0 \xe1 \xe2 \xe3 \xe4 \xe5 \xe6 \xe7 \xe8 \xe9 \xea \xeb \xec 
+  \xed \xee \xef \xf0 \xf1 \xf2 \xf3 \xf4 \xf5 \xf6 \xf7 \xf8 \xf9 \xfa \xfb 
+  \xfc \xfd \xfe \xff 
+
+/(a|b)*[\s]/IS
+Capturing subpattern count = 1
+No options
+No first char
+No need char
+Subject length lower bound = 1
+Starting byte set: \x09 \x0a \x0c \x0d \x20 a b 
+
+/(ab\2)/
+Failed: reference to non-existent subpattern at offset 6
+
+/{4,5}abc/
+Failed: nothing to repeat at offset 4
+
+/(a)(b)(c)\2/I
+Capturing subpattern count = 3
+Max back reference = 2
+No options
+First char = 'a'
+Need char = 'c'
+    abcb
+ 0: abcb
+ 1: a
+ 2: b
+ 3: c
+    \O0abcb
+Matched, but too many substrings
+    \O3abcb
+Matched, but too many substrings
+ 0: abcb
+    \O6abcb
+Matched, but too many substrings
+ 0: abcb
+ 1: a
+    \O9abcb
+Matched, but too many substrings
+ 0: abcb
+ 1: a
+ 2: b
+    \O12abcb
+ 0: abcb
+ 1: a
+ 2: b
+ 3: c
+
+/(a)bc|(a)(b)\2/I
+Capturing subpattern count = 3
+Max back reference = 2
+No options
+First char = 'a'
+No need char
+    abc
+ 0: abc
+ 1: a
+    \O0abc
+Matched, but too many substrings
+    \O3abc
+Matched, but too many substrings
+ 0: abc
+    \O6abc
+ 0: abc
+ 1: a
+    aba
+ 0: aba
+ 1: <unset>
+ 2: a
+ 3: b
+    \O0aba
+Matched, but too many substrings
+    \O3aba
+Matched, but too many substrings
+ 0: aba
+    \O6aba
+Matched, but too many substrings
+ 0: aba
+ 1: <unset>
+    \O9aba
+Matched, but too many substrings
+ 0: aba
+ 1: <unset>
+ 2: a
+    \O12aba
+ 0: aba
+ 1: <unset>
+ 2: a
+ 3: b
+
+/abc$/IE
+Capturing subpattern count = 0
+Options: dollar_endonly
+First char = 'a'
+Need char = 'c'
+    abc
+ 0: abc
+    *** Failers
+No match
+    abc\n
+No match
+    abc\ndef
+No match
+
+/(a)(b)(c)(d)(e)\6/
+Failed: reference to non-existent subpattern at offset 17
+
+/the quick brown fox/I
+Capturing subpattern count = 0
+No options
+First char = 't'
+Need char = 'x'
+    the quick brown fox
+ 0: the quick brown fox
+    this is a line with the quick brown fox
+ 0: the quick brown fox
+
+/the quick brown fox/IA
+Capturing subpattern count = 0
+Options: anchored
+No first char
+No need char
+    the quick brown fox
+ 0: the quick brown fox
+    *** Failers
+No match
+    this is a line with the quick brown fox
+No match
+
+/ab(?z)cd/
+Failed: unrecognized character after (? or (?- at offset 4
+
+/^abc|def/I
+Capturing subpattern count = 0
+No options
+No first char
+No need char
+    abcdef
+ 0: abc
+    abcdef\B
+ 0: def
+
+/.*((abc)$|(def))/I
+Capturing subpattern count = 3
+No options
+First char at start or follows newline
+No need char
+    defabc
+ 0: defabc
+ 1: abc
+ 2: abc
+    \Zdefabc
+ 0: def
+ 1: def
+ 2: <unset>
+ 3: def
+
+/)/
+Failed: unmatched parentheses at offset 0
+
+/a[]b/
+Failed: missing terminating ] for character class at offset 4
+
+/[^aeiou ]{3,}/I
+Capturing subpattern count = 0
+No options
+No first char
+No need char
+    co-processors, and for
+ 0: -pr
+
+/<.*>/I
+Capturing subpattern count = 0
+No options
+First char = '<'
+Need char = '>'
+    abc<def>ghi<klm>nop
+ 0: <def>ghi<klm>
+
+/<.*?>/I
+Capturing subpattern count = 0
+No options
+First char = '<'
+Need char = '>'
+    abc<def>ghi<klm>nop
+ 0: <def>
+
+/<.*>/IU
+Capturing subpattern count = 0
+Options: ungreedy
+First char = '<'
+Need char = '>'
+    abc<def>ghi<klm>nop
+ 0: <def>
+
+/(?U)<.*>/I
+Capturing subpattern count = 0
+Options: ungreedy
+First char = '<'
+Need char = '>'
+    abc<def>ghi<klm>nop
+ 0: <def>
+
+/<.*?>/IU
+Capturing subpattern count = 0
+Options: ungreedy
+First char = '<'
+Need char = '>'
+    abc<def>ghi<klm>nop
+ 0: <def>ghi<klm>
+
+/={3,}/IU
+Capturing subpattern count = 0
+Options: ungreedy
+First char = '='
+Need char = '='
+    abc========def
+ 0: ===
+
+/(?U)={3,}?/I
+Capturing subpattern count = 0
+Options: ungreedy
+First char = '='
+Need char = '='
+    abc========def
+ 0: ========
+
+/(?<!bar|cattle)foo/I
+Capturing subpattern count = 0
+No options
+First char = 'f'
+Need char = 'o'
+Max lookbehind = 6
+    foo
+ 0: foo
+    catfoo
+ 0: foo
+    *** Failers
+No match
+    the barfoo
+No match
+    and cattlefoo
+No match
+
+/(?<=a+)b/
+Failed: lookbehind assertion is not fixed length at offset 6
+
+/(?<=aaa|b{0,3})b/
+Failed: lookbehind assertion is not fixed length at offset 14
+
+/(?<!(foo)a\1)bar/
+Failed: lookbehind assertion is not fixed length at offset 12
+
+/(?i)abc/I
+Capturing subpattern count = 0
+Options: caseless
+First char = 'a' (caseless)
+Need char = 'c' (caseless)
+
+/(a|(?m)a)/I
+Capturing subpattern count = 1
+No options
+First char = 'a'
+No need char
+
+/(?i)^1234/I
+Capturing subpattern count = 0
+Options: anchored caseless
+No first char
+No need char
+
+/(^b|(?i)^d)/I
+Capturing subpattern count = 1
+Options: anchored
+No first char
+No need char
+
+/(?s).*/I
+Capturing subpattern count = 0
+Options: anchored dotall
+No first char
+No need char
+
+/[abcd]/IS
+Capturing subpattern count = 0
+No options
+No first char
+No need char
+Subject length lower bound = 1
+Starting byte set: a b c d 
+
+/(?i)[abcd]/IS
+Capturing subpattern count = 0
+Options: caseless
+No first char
+No need char
+Subject length lower bound = 1
+Starting byte set: A B C D a b c d 
+
+/(?m)[xy]|(b|c)/IS
+Capturing subpattern count = 1
+Options: multiline
+No first char
+No need char
+Subject length lower bound = 1
+Starting byte set: b c x y 
+
+/(^a|^b)/Im
+Capturing subpattern count = 1
+Options: multiline
+First char at start or follows newline
+No need char
+
+/(?i)(^a|^b)/Im
+Capturing subpattern count = 1
+Options: caseless multiline
+First char at start or follows newline
+No need char
+
+/(a)(?(1)a|b|c)/
+Failed: conditional group contains more than two branches at offset 13
+
+/(?(?=a)a|b|c)/
+Failed: conditional group contains more than two branches at offset 12
+
+/(?(1a)/
+Failed: missing ) at offset 6
+
+/(?(1a))/
+Failed: reference to non-existent subpattern at offset 6
+
+/(?(?i))/
+Failed: assertion expected after (?( at offset 3
+
+/(?(abc))/
+Failed: reference to non-existent subpattern at offset 7
+
+/(?(?<ab))/
+Failed: syntax error in subpattern name (missing terminator) at offset 7
+
+/((?s)blah)\s+\1/I
+Capturing subpattern count = 1
+Max back reference = 1
+No options
+First char = 'b'
+Need char = 'h'
+
+/((?i)blah)\s+\1/I
+Capturing subpattern count = 1
+Max back reference = 1
+No options
+First char = 'b' (caseless)
+Need char = 'h' (caseless)
+
+/((?i)b)/IDZS
+------------------------------------------------------------------
+        Bra
+        CBra 1
+     /i b
+        Ket
+        Ket
+        End
+------------------------------------------------------------------
+Capturing subpattern count = 1
+No options
+First char = 'b' (caseless)
+No need char
+Subject length lower bound = 1
+No set of starting bytes
+
+/(a*b|(?i:c*(?-i)d))/IS
+Capturing subpattern count = 1
+No options
+No first char
+No need char
+Subject length lower bound = 1
+Starting byte set: C a b c d 
+
+/a$/I
+Capturing subpattern count = 0
+No options
+First char = 'a'
+No need char
+    a
+ 0: a
+    a\n
+ 0: a
+    *** Failers
+No match
+    \Za
+No match
+    \Za\n
+No match
+
+/a$/Im
+Capturing subpattern count = 0
+Options: multiline
+First char = 'a'
+No need char
+    a
+ 0: a
+    a\n
+ 0: a
+    \Za\n
+ 0: a
+    *** Failers
+No match
+    \Za
+No match
+
+/\Aabc/Im
+Capturing subpattern count = 0
+Options: anchored multiline
+No first char
+No need char
+
+/^abc/Im
+Capturing subpattern count = 0
+Options: multiline
+First char at start or follows newline
+Need char = 'c'
+
+/^((a+)(?U)([ab]+)(?-U)([bc]+)(\w*))/I
+Capturing subpattern count = 5
+Options: anchored
+No first char
+No need char
+  aaaaabbbbbcccccdef
+ 0: aaaaabbbbbcccccdef
+ 1: aaaaabbbbbcccccdef
+ 2: aaaaa
+ 3: b
+ 4: bbbbccccc
+ 5: def
+
+/(?<=foo)[ab]/IS
+Capturing subpattern count = 0
+No options
+No first char
+No need char
+Max lookbehind = 3
+Subject length lower bound = 1
+Starting byte set: a b 
+
+/(?<!foo)(alpha|omega)/IS
+Capturing subpattern count = 1
+No options
+No first char
+Need char = 'a'
+Max lookbehind = 3
+Subject length lower bound = 5
+Starting byte set: a o 
+
+/(?!alphabet)[ab]/IS
+Capturing subpattern count = 0
+No options
+No first char
+No need char
+Subject length lower bound = 1
+Starting byte set: a b 
+
+/(?<=foo\n)^bar/Im
+Capturing subpattern count = 0
+Contains explicit CR or LF match
+Options: multiline
+No first char
+Need char = 'r'
+Max lookbehind = 4
+    foo\nbarbar
+ 0: bar
+    ***Failers
+No match
+    rhubarb
+No match
+    barbell
+No match
+    abc\nbarton
+No match
+
+/^(?<=foo\n)bar/Im
+Capturing subpattern count = 0
+Contains explicit CR or LF match
+Options: multiline
+First char at start or follows newline
+Need char = 'r'
+Max lookbehind = 4
+    foo\nbarbar
+ 0: bar
+    ***Failers
+No match
+    rhubarb
+No match
+    barbell
+No match
+    abc\nbarton
+No match
+
+/(?>^abc)/Im
+Capturing subpattern count = 0
+Options: multiline
+First char at start or follows newline
+Need char = 'c'
+    abc
+ 0: abc
+    def\nabc
+ 0: abc
+    *** Failers
+No match
+    defabc
+No match
+
+/(?<=ab(c+)d)ef/
+Failed: lookbehind assertion is not fixed length at offset 11
+
+/(?<=ab(?<=c+)d)ef/
+Failed: lookbehind assertion is not fixed length at offset 12
+
+/(?<=ab(c|de)f)g/
+Failed: lookbehind assertion is not fixed length at offset 13
+
+/The next three are in testinput2 because they have variable length branches/
+
+/(?<=bullock|donkey)-cart/I
+Capturing subpattern count = 0
+No options
+First char = '-'
+Need char = 't'
+Max lookbehind = 7
+    the bullock-cart
+ 0: -cart
+    a donkey-cart race
+ 0: -cart
+    *** Failers
+No match
+    cart
+No match
+    horse-and-cart
+No match
+
+/(?<=ab(?i)x|y|z)/I
+Capturing subpattern count = 0
+No options
+No first char
+No need char
+Max lookbehind = 3
+
+/(?>.*)(?<=(abcd)|(xyz))/I
+Capturing subpattern count = 2
+No options
+First char at start or follows newline
+No need char
+Max lookbehind = 4
+    alphabetabcd
+ 0: alphabetabcd
+ 1: abcd
+    endingxyz
+ 0: endingxyz
+ 1: <unset>
+ 2: xyz
+
+/(?<=ab(?i)x(?-i)y|(?i)z|b)ZZ/I
+Capturing subpattern count = 0
+No options
+First char = 'Z'
+Need char = 'Z'
+Max lookbehind = 4
+    abxyZZ
+ 0: ZZ
+    abXyZZ
+ 0: ZZ
+    ZZZ
+ 0: ZZ
+    zZZ
+ 0: ZZ
+    bZZ
+ 0: ZZ
+    BZZ
+ 0: ZZ
+    *** Failers
+No match
+    ZZ
+No match
+    abXYZZ
+No match
+    zzz
+No match
+    bzz
+No match
+
+/(?<!(foo)a)bar/I
+Capturing subpattern count = 1
+No options
+First char = 'b'
+Need char = 'r'
+Max lookbehind = 4
+    bar
+ 0: bar
+    foobbar
+ 0: bar
+    *** Failers
+No match
+    fooabar
+No match
+
+/This one is here because Perl 5.005_02 doesn't fail it/I
+Capturing subpattern count = 0
+No options
+First char = 'T'
+Need char = 't'
+
+/^(a)?(?(1)a|b)+$/I
+Capturing subpattern count = 1
+Options: anchored
+No first char
+No need char
+    *** Failers
+No match
+    a
+No match
+
+/This one is here because Perl behaves differently; see also the following/I
+Capturing subpattern count = 0
+No options
+First char = 'T'
+Need char = 'g'
+
+/^(a\1?){4}$/I
+Capturing subpattern count = 1
+Max back reference = 1
+Options: anchored
+No first char
+No need char
+    aaaa
+No match
+    aaaaaa
+No match
+    
+/Perl does not fail these two for the final subjects. Neither did PCRE until/
+/release 8.01. The problem is in backtracking into a subpattern that contains/
+No match
+/a recursive reference to itself. PCRE has now made these into atomic patterns./
+No match
+
+/^(xa|=?\1a){2}$/
+    xa=xaa
+ 0: xa=xaa
+ 1: =xaa
+    ** Failers
+No match
+    xa=xaaa
+No match
+
+/^(xa|=?\1a)+$/
+    xa=xaa
+ 0: xa=xaa
+ 1: =xaa
+    ** Failers
+No match
+    xa=xaaa
+No match
+
+/These are syntax tests from Perl 5.005/I
+Capturing subpattern count = 0
+No options
+First char = 'T'
+Need char = '5'
+
+/a[b-a]/
+Failed: range out of order in character class at offset 4
+
+/a[]b/
+Failed: missing terminating ] for character class at offset 4
+
+/a[/
+Failed: missing terminating ] for character class at offset 2
+
+/*a/
+Failed: nothing to repeat at offset 0
+
+/(*)b/
+Failed: nothing to repeat at offset 1
+
+/abc)/
+Failed: unmatched parentheses at offset 3
+
+/(abc/
+Failed: missing ) at offset 4
+
+/a**/
+Failed: nothing to repeat at offset 2
+
+/)(/
+Failed: unmatched parentheses at offset 0
+
+/\1/
+Failed: reference to non-existent subpattern at offset 2
+
+/\2/
+Failed: reference to non-existent subpattern at offset 2
+
+/(a)|\2/
+Failed: reference to non-existent subpattern at offset 6
+
+/a[b-a]/Ii
+Failed: range out of order in character class at offset 4
+
+/a[]b/Ii
+Failed: missing terminating ] for character class at offset 4
+
+/a[/Ii
+Failed: missing terminating ] for character class at offset 2
+
+/*a/Ii
+Failed: nothing to repeat at offset 0
+
+/(*)b/Ii
+Failed: nothing to repeat at offset 1
+
+/abc)/Ii
+Failed: unmatched parentheses at offset 3
+
+/(abc/Ii
+Failed: missing ) at offset 4
+
+/a**/Ii
+Failed: nothing to repeat at offset 2
+
+/)(/Ii
+Failed: unmatched parentheses at offset 0
+
+/:(?:/
+Failed: missing ) at offset 4
+
+/(?<%)b/
+Failed: unrecognized character after (?< at offset 3
+
+/a(?{)b/
+Failed: unrecognized character after (? or (?- at offset 3
+
+/a(?{{})b/
+Failed: unrecognized character after (? or (?- at offset 3
+
+/a(?{}})b/
+Failed: unrecognized character after (? or (?- at offset 3
+
+/a(?{"{"})b/
+Failed: unrecognized character after (? or (?- at offset 3
+
+/a(?{"{"}})b/
+Failed: unrecognized character after (? or (?- at offset 3
+
+/(?(1?)a|b)/
+Failed: malformed number or name after (?( at offset 4
+
+/[a[:xyz:/
+Failed: missing terminating ] for character class at offset 8
+
+/(?<=x+)y/
+Failed: lookbehind assertion is not fixed length at offset 6
+
+/a{37,17}/
+Failed: numbers out of order in {} quantifier at offset 7
+
+/abc/\
+Failed: \ at end of pattern at offset 4
+
+/abc/\i
+Failed: \ at end of pattern at offset 4
+
+/(a)bc(d)/I
+Capturing subpattern count = 2
+No options
+First char = 'a'
+Need char = 'd'
+    abcd
+ 0: abcd
+ 1: a
+ 2: d
+    abcd\C2
+ 0: abcd
+ 1: a
+ 2: d
+ 2C d (1)
+    abcd\C5
+ 0: abcd
+ 1: a
+ 2: d
+copy substring 5 failed -7
+
+/(.{20})/I
+Capturing subpattern count = 1
+No options
+No first char
+No need char
+    abcdefghijklmnopqrstuvwxyz
+ 0: abcdefghijklmnopqrst
+ 1: abcdefghijklmnopqrst
+    abcdefghijklmnopqrstuvwxyz\C1
+ 0: abcdefghijklmnopqrst
+ 1: abcdefghijklmnopqrst
+ 1C abcdefghijklmnopqrst (20)
+    abcdefghijklmnopqrstuvwxyz\G1
+ 0: abcdefghijklmnopqrst
+ 1: abcdefghijklmnopqrst
+ 1G abcdefghijklmnopqrst (20)
+
+/(.{15})/I
+Capturing subpattern count = 1
+No options
+No first char
+No need char
+    abcdefghijklmnopqrstuvwxyz
+ 0: abcdefghijklmno
+ 1: abcdefghijklmno
+    abcdefghijklmnopqrstuvwxyz\C1\G1
+ 0: abcdefghijklmno
+ 1: abcdefghijklmno
+ 1C abcdefghijklmno (15)
+ 1G abcdefghijklmno (15)
+
+/(.{16})/I
+Capturing subpattern count = 1
+No options
+No first char
+No need char
+    abcdefghijklmnopqrstuvwxyz
+ 0: abcdefghijklmnop
+ 1: abcdefghijklmnop
+    abcdefghijklmnopqrstuvwxyz\C1\G1\L
+ 0: abcdefghijklmnop
+ 1: abcdefghijklmnop
+ 1C abcdefghijklmnop (16)
+ 1G abcdefghijklmnop (16)
+ 0L abcdefghijklmnop
+ 1L abcdefghijklmnop
+
+/^(a|(bc))de(f)/I
+Capturing subpattern count = 3
+Options: anchored
+No first char
+No need char
+    adef\G1\G2\G3\G4\L
+ 0: adef
+ 1: a
+ 2: <unset>
+ 3: f
+ 1G a (1)
+ 2G  (0)
+ 3G f (1)
+get substring 4 failed -7
+ 0L adef
+ 1L a
+ 2L 
+ 3L f
+    bcdef\G1\G2\G3\G4\L
+ 0: bcdef
+ 1: bc
+ 2: bc
+ 3: f
+ 1G bc (2)
+ 2G bc (2)
+ 3G f (1)
+get substring 4 failed -7
+ 0L bcdef
+ 1L bc
+ 2L bc
+ 3L f
+    adefghijk\C0
+ 0: adef
+ 1: a
+ 2: <unset>
+ 3: f
+ 0C adef (4)
+
+/^abc\00def/I
+Capturing subpattern count = 0
+Options: anchored
+No first char
+No need char
+    abc\00def\L\C0
+ 0: abc\x00def
+ 0C abc\x00def (7)
+ 0L abc
+
+/word ((?:[a-zA-Z0-9]+ )((?:[a-zA-Z0-9]+ )((?:[a-zA-Z0-9]+ )((?:[a-zA-Z0-9]+
+)((?:[a-zA-Z0-9]+ )((?:[a-zA-Z0-9]+ )((?:[a-zA-Z0-9]+ )((?:[a-zA-Z0-9]+
+)?)?)?)?)?)?)?)?)?otherword/I
+Capturing subpattern count = 8
+Contains explicit CR or LF match
+No options
+First char = 'w'
+Need char = 'd'
+
+/.*X/IDZ
+------------------------------------------------------------------
+        Bra
+        Any*
+        X
+        Ket
+        End
+------------------------------------------------------------------
+Capturing subpattern count = 0
+No options
+First char at start or follows newline
+Need char = 'X'
+
+/.*X/IDZs
+------------------------------------------------------------------
+        Bra
+        AllAny*
+        X
+        Ket
+        End
+------------------------------------------------------------------
+Capturing subpattern count = 0
+Options: anchored dotall
+No first char
+Need char = 'X'
+
+/(.*X|^B)/IDZ
+------------------------------------------------------------------
+        Bra
+        CBra 1
+        Any*
+        X
+        Alt
+        ^
+        B
+        Ket
+        Ket
+        End
+------------------------------------------------------------------
+Capturing subpattern count = 1
+No options
+First char at start or follows newline
+No need char
+
+/(.*X|^B)/IDZs
+------------------------------------------------------------------
+        Bra
+        CBra 1
+        AllAny*
+        X
+        Alt
+        ^
+        B
+        Ket
+        Ket
+        End
+------------------------------------------------------------------
+Capturing subpattern count = 1
+Options: anchored dotall
+No first char
+No need char
+
+/(?s)(.*X|^B)/IDZ
+------------------------------------------------------------------
+        Bra
+        CBra 1
+        AllAny*
+        X
+        Alt
+        ^
+        B
+        Ket
+        Ket
+        End
+------------------------------------------------------------------
+Capturing subpattern count = 1
+Options: anchored dotall
+No first char
+No need char
+
+/(?s:.*X|^B)/IDZ
+------------------------------------------------------------------
+        Bra
+        Bra
+        AllAny*
+        X
+        Alt
+        ^
+        B
+        Ket
+        Ket
+        End
+------------------------------------------------------------------
+Capturing subpattern count = 0
+Options: anchored
+No first char
+No need char
+
+/\Biss\B/I+
+Capturing subpattern count = 0
+No options
+First char = 'i'
+Need char = 's'
+Max lookbehind = 1
+    Mississippi
+ 0: iss
+ 0+ issippi
+
+/iss/IG+
+Capturing subpattern count = 0
+No options
+First char = 'i'
+Need char = 's'
+    Mississippi
+ 0: iss
+ 0+ issippi
+ 0: iss
+ 0+ ippi
+
+/\Biss\B/IG+
+Capturing subpattern count = 0
+No options
+First char = 'i'
+Need char = 's'
+Max lookbehind = 1
+    Mississippi
+ 0: iss
+ 0+ issippi
+
+/\Biss\B/Ig+
+Capturing subpattern count = 0
+No options
+First char = 'i'
+Need char = 's'
+Max lookbehind = 1
+    Mississippi
+ 0: iss
+ 0+ issippi
+ 0: iss
+ 0+ ippi
+    *** Failers
+No match
+    Mississippi\A
+No match
+
+/(?<=[Ms])iss/Ig+
+Capturing subpattern count = 0
+No options
+First char = 'i'
+Need char = 's'
+Max lookbehind = 1
+    Mississippi
+ 0: iss
+ 0+ issippi
+ 0: iss
+ 0+ ippi
+
+/(?<=[Ms])iss/IG+
+Capturing subpattern count = 0
+No options
+First char = 'i'
+Need char = 's'
+Max lookbehind = 1
+    Mississippi
+ 0: iss
+ 0+ issippi
+
+/^iss/Ig+
+Capturing subpattern count = 0
+Options: anchored
+No first char
+No need char
+    ississippi
+ 0: iss
+ 0+ issippi
+
+/.*iss/Ig+
+Capturing subpattern count = 0
+No options
+First char at start or follows newline
+Need char = 's'
+    abciss\nxyzisspqr
+ 0: abciss
+ 0+ \x0axyzisspqr
+ 0: xyziss
+ 0+ pqr
+
+/.i./I+g
+Capturing subpattern count = 0
+No options
+No first char
+Need char = 'i'
+    Mississippi
+ 0: Mis
+ 0+ sissippi
+ 0: sis
+ 0+ sippi
+ 0: sip
+ 0+ pi
+    Mississippi\A
+ 0: Mis
+ 0+ sissippi
+ 0: sis
+ 0+ sippi
+ 0: sip
+ 0+ pi
+    Missouri river
+ 0: Mis
+ 0+ souri river
+ 0: ri 
+ 0+ river
+ 0: riv
+ 0+ er
+    Missouri river\A
+ 0: Mis
+ 0+ souri river
+
+/^.is/I+g
+Capturing subpattern count = 0
+Options: anchored
+No first char
+No need char
+    Mississippi
+ 0: Mis
+ 0+ sissippi
+
+/^ab\n/Ig+
+Capturing subpattern count = 0
+Contains explicit CR or LF match
+Options: anchored
+No first char
+No need char
+    ab\nab\ncd
+ 0: ab\x0a
+ 0+ ab\x0acd
+
+/^ab\n/Img+
+Capturing subpattern count = 0
+Contains explicit CR or LF match
+Options: multiline
+First char at start or follows newline
+Need char = \x0a
+    ab\nab\ncd
+ 0: ab\x0a
+ 0+ ab\x0acd
+ 0: ab\x0a
+ 0+ cd
+
+/abc/I
+Capturing subpattern count = 0
+No options
+First char = 'a'
+Need char = 'c'
+
+/abc|bac/I
+Capturing subpattern count = 0
+No options
+No first char
+Need char = 'c'
+
+/(abc|bac)/I
+Capturing subpattern count = 1
+No options
+No first char
+Need char = 'c'
+
+/(abc|(c|dc))/I
+Capturing subpattern count = 2
+No options
+No first char
+Need char = 'c'
+
+/(abc|(d|de)c)/I
+Capturing subpattern count = 2
+No options
+No first char
+Need char = 'c'
+
+/a*/I
+Capturing subpattern count = 0
+No options
+No first char
+No need char
+
+/a+/I
+Capturing subpattern count = 0
+No options
+First char = 'a'
+No need char
+
+/(baa|a+)/I
+Capturing subpattern count = 1
+No options
+No first char
+Need char = 'a'
+
+/a{0,3}/I
+Capturing subpattern count = 0
+No options
+No first char
+No need char
+
+/baa{3,}/I
+Capturing subpattern count = 0
+No options
+First char = 'b'
+Need char = 'a'
+
+/"([^\\"]+|\\.)*"/I
+Capturing subpattern count = 1
+No options
+First char = '"'
+Need char = '"'
+
+/(abc|ab[cd])/I
+Capturing subpattern count = 1
+No options
+First char = 'a'
+No need char
+
+/(a|.)/I
+Capturing subpattern count = 1
+No options
+No first char
+No need char
+
+/a|ba|\w/I
+Capturing subpattern count = 0
+No options
+No first char
+No need char
+
+/abc(?=pqr)/I
+Capturing subpattern count = 0
+No options
+First char = 'a'
+Need char = 'r'
+
+/...(?<=abc)/I
+Capturing subpattern count = 0
+No options
+No first char
+No need char
+Max lookbehind = 3
+
+/abc(?!pqr)/I
+Capturing subpattern count = 0
+No options
+First char = 'a'
+Need char = 'c'
+
+/ab./I
+Capturing subpattern count = 0
+No options
+First char = 'a'
+Need char = 'b'
+
+/ab[xyz]/I
+Capturing subpattern count = 0
+No options
+First char = 'a'
+Need char = 'b'
+
+/abc*/I
+Capturing subpattern count = 0
+No options
+First char = 'a'
+Need char = 'b'
+
+/ab.c*/I
+Capturing subpattern count = 0
+No options
+First char = 'a'
+Need char = 'b'
+
+/a.c*/I
+Capturing subpattern count = 0
+No options
+First char = 'a'
+No need char
+
+/.c*/I
+Capturing subpattern count = 0
+No options
+No first char
+No need char
+
+/ac*/I
+Capturing subpattern count = 0
+No options
+First char = 'a'
+No need char
+
+/(a.c*|b.c*)/I
+Capturing subpattern count = 1
+No options
+No first char
+No need char
+
+/a.c*|aba/I
+Capturing subpattern count = 0
+No options
+First char = 'a'
+No need char
+
+/.+a/I
+Capturing subpattern count = 0
+No options
+No first char
+Need char = 'a'
+
+/(?=abcda)a.*/I
+Capturing subpattern count = 0
+No options
+First char = 'a'
+Need char = 'a'
+
+/(?=a)a.*/I
+Capturing subpattern count = 0
+No options
+First char = 'a'
+No need char
+
+/a(b)*/I
+Capturing subpattern count = 1
+No options
+First char = 'a'
+No need char
+
+/a\d*/I
+Capturing subpattern count = 0
+No options
+First char = 'a'
+No need char
+
+/ab\d*/I
+Capturing subpattern count = 0
+No options
+First char = 'a'
+Need char = 'b'
+
+/a(\d)*/I
+Capturing subpattern count = 1
+No options
+First char = 'a'
+No need char
+
+/abcde{0,0}/I
+Capturing subpattern count = 0
+No options
+First char = 'a'
+Need char = 'd'
+
+/ab\d+/I
+Capturing subpattern count = 0
+No options
+First char = 'a'
+Need char = 'b'
+
+/a(?(1)b)(.)/I
+Capturing subpattern count = 1
+No options
+First char = 'a'
+No need char
+
+/a(?(1)bag|big)(.)/I
+Capturing subpattern count = 1
+No options
+First char = 'a'
+Need char = 'g'
+
+/a(?(1)bag|big)*(.)/I
+Capturing subpattern count = 1
+No options
+First char = 'a'
+No need char
+
+/a(?(1)bag|big)+(.)/I
+Capturing subpattern count = 1
+No options
+First char = 'a'
+Need char = 'g'
+
+/a(?(1)b..|b..)(.)/I
+Capturing subpattern count = 1
+No options
+First char = 'a'
+Need char = 'b'
+
+/ab\d{0}e/I
+Capturing subpattern count = 0
+No options
+First char = 'a'
+Need char = 'e'
+
+/a?b?/I
+Capturing subpattern count = 0
+No options
+No first char
+No need char
+    a
+ 0: a
+    b
+ 0: b
+    ab
+ 0: ab
+    \
+ 0: 
+    *** Failers
+ 0: 
+    \N
+No match
+
+/|-/I
+Capturing subpattern count = 0
+No options
+No first char
+No need char
+    abcd
+ 0: 
+    -abc
+ 0: 
+    \Nab-c
+ 0: -
+    *** Failers
+ 0: 
+    \Nabc
+No match
+
+/^.?abcd/IS
+Capturing subpattern count = 0
+Options: anchored
+No first char
+Need char = 'd'
+Subject length lower bound = 4
+No set of starting bytes
+
+/\(             # ( at start
+  (?:           # Non-capturing bracket
+  (?>[^()]+)    # Either a sequence of non-brackets (no backtracking)
+  |             # Or
+  (?R)          # Recurse - i.e. nested bracketed string
+  )*            # Zero or more contents
+  \)            # Closing )
+  /Ix
+Capturing subpattern count = 0
+Options: extended
+First char = '('
+Need char = ')'
+    (abcd)
+ 0: (abcd)
+    (abcd)xyz
+ 0: (abcd)
+    xyz(abcd)
+ 0: (abcd)
+    (ab(xy)cd)pqr
+ 0: (ab(xy)cd)
+    (ab(xycd)pqr
+ 0: (xycd)
+    () abc ()
+ 0: ()
+    12(abcde(fsh)xyz(foo(bar))lmno)89
+ 0: (abcde(fsh)xyz(foo(bar))lmno)
+    *** Failers
+No match
+    abcd
+No match
+    abcd)
+No match
+    (abcd
+No match
+
+/\(  ( (?>[^()]+) | (?R) )* \) /Ixg
+Capturing subpattern count = 1
+Options: extended
+First char = '('
+Need char = ')'
+    (ab(xy)cd)pqr
+ 0: (ab(xy)cd)
+ 1: cd
+    1(abcd)(x(y)z)pqr
+ 0: (abcd)
+ 1: abcd
+ 0: (x(y)z)
+ 1: z
+
+/\(  (?: (?>[^()]+) | (?R) ) \) /Ix
+Capturing subpattern count = 0
+Options: extended
+First char = '('
+Need char = ')'
+    (abcd)
+ 0: (abcd)
+    (ab(xy)cd)
+ 0: (xy)
+    (a(b(c)d)e)
+ 0: (c)
+    ((ab))
+ 0: ((ab))
+    *** Failers
+No match
+    ()
+No match
+
+/\(  (?: (?>[^()]+) | (?R) )? \) /Ix
+Capturing subpattern count = 0
+Options: extended
+First char = '('
+Need char = ')'
+    ()
+ 0: ()
+    12(abcde(fsh)xyz(foo(bar))lmno)89
+ 0: (fsh)
+
+/\(  ( (?>[^()]+) | (?R) )* \) /Ix
+Capturing subpattern count = 1
+Options: extended
+First char = '('
+Need char = ')'
+    (ab(xy)cd)
+ 0: (ab(xy)cd)
+ 1: cd
+
+/\( ( ( (?>[^()]+) | (?R) )* ) \) /Ix
+Capturing subpattern count = 2
+Options: extended
+First char = '('
+Need char = ')'
+    (ab(xy)cd)
+ 0: (ab(xy)cd)
+ 1: ab(xy)cd
+ 2: cd
+
+/\( (123)? ( ( (?>[^()]+) | (?R) )* ) \) /Ix
+Capturing subpattern count = 3
+Options: extended
+First char = '('
+Need char = ')'
+    (ab(xy)cd)
+ 0: (ab(xy)cd)
+ 1: <unset>
+ 2: ab(xy)cd
+ 3: cd
+    (123ab(xy)cd)
+ 0: (123ab(xy)cd)
+ 1: 123
+ 2: ab(xy)cd
+ 3: cd
+
+/\( ( (123)? ( (?>[^()]+) | (?R) )* ) \) /Ix
+Capturing subpattern count = 3
+Options: extended
+First char = '('
+Need char = ')'
+    (ab(xy)cd)
+ 0: (ab(xy)cd)
+ 1: ab(xy)cd
+ 2: <unset>
+ 3: cd
+    (123ab(xy)cd)
+ 0: (123ab(xy)cd)
+ 1: 123ab(xy)cd
+ 2: 123
+ 3: cd
+
+/\( (((((((((( ( (?>[^()]+) | (?R) )* )))))))))) \) /Ix
+Capturing subpattern count = 11
+Options: extended
+First char = '('
+Need char = ')'
+    (ab(xy)cd)
+ 0: (ab(xy)cd)
+ 1: ab(xy)cd
+ 2: ab(xy)cd
+ 3: ab(xy)cd
+ 4: ab(xy)cd
+ 5: ab(xy)cd
+ 6: ab(xy)cd
+ 7: ab(xy)cd
+ 8: ab(xy)cd
+ 9: ab(xy)cd
+10: ab(xy)cd
+11: cd
+
+/\( ( ( (?>[^()<>]+) | ((?>[^()]+)) | (?R) )* ) \) /Ix
+Capturing subpattern count = 3
+Options: extended
+First char = '('
+Need char = ')'
+    (abcd(xyz<p>qrs)123)
+ 0: (abcd(xyz<p>qrs)123)
+ 1: abcd(xyz<p>qrs)123
+ 2: 123
+
+/\( ( ( (?>[^()]+) | ((?R)) )* ) \) /Ix
+Capturing subpattern count = 3
+Options: extended
+First char = '('
+Need char = ')'
+    (ab(cd)ef)
+ 0: (ab(cd)ef)
+ 1: ab(cd)ef
+ 2: ef
+ 3: (cd)
+    (ab(cd(ef)gh)ij)
+ 0: (ab(cd(ef)gh)ij)
+ 1: ab(cd(ef)gh)ij
+ 2: ij
+ 3: (cd(ef)gh)
+
+/^[[:alnum:]]/DZ
+------------------------------------------------------------------
+        Bra
+        ^
+        [0-9A-Za-z]
+        Ket
+        End
+------------------------------------------------------------------
+Capturing subpattern count = 0
+Options: anchored
+No first char
+No need char
+
+/^[[:^alnum:]]/DZ
+------------------------------------------------------------------
+        Bra
+        ^
+        [\x00-/:-@[-`{-\xff] (neg)
+        Ket
+        End
+------------------------------------------------------------------
+Capturing subpattern count = 0
+Options: anchored
+No first char
+No need char
+
+/^[[:alpha:]]/DZ
+------------------------------------------------------------------
+        Bra
+        ^
+        [A-Za-z]
+        Ket
+        End
+------------------------------------------------------------------
+Capturing subpattern count = 0
+Options: anchored
+No first char
+No need char
+
+/^[[:^alpha:]]/DZ
+------------------------------------------------------------------
+        Bra
+        ^
+        [\x00-@[-`{-\xff] (neg)
+        Ket
+        End
+------------------------------------------------------------------
+Capturing subpattern count = 0
+Options: anchored
+No first char
+No need char
+
+/[_[:alpha:]]/IS
+Capturing subpattern count = 0
+No options
+No first char
+No need char
+Subject length lower bound = 1
+Starting byte set: A B C D E F G H I J K L M N O P Q R S T U V W X Y Z 
+  _ a b c d e f g h i j k l m n o p q r s t u v w x y z 
+
+/^[[:ascii:]]/DZ
+------------------------------------------------------------------
+        Bra
+        ^
+        [\x00-\x7f]
+        Ket
+        End
+------------------------------------------------------------------
+Capturing subpattern count = 0
+Options: anchored
+No first char
+No need char
+
+/^[[:^ascii:]]/DZ
+------------------------------------------------------------------
+        Bra
+        ^
+        [\x80-\xff] (neg)
+        Ket
+        End
+------------------------------------------------------------------
+Capturing subpattern count = 0
+Options: anchored
+No first char
+No need char
+
+/^[[:blank:]]/DZ
+------------------------------------------------------------------
+        Bra
+        ^
+        [\x09 ]
+        Ket
+        End
+------------------------------------------------------------------
+Capturing subpattern count = 0
+Options: anchored
+No first char
+No need char
+
+/^[[:^blank:]]/DZ
+------------------------------------------------------------------
+        Bra
+        ^
+        [\x00-\x08\x0a-\x1f!-\xff] (neg)
+        Ket
+        End
+------------------------------------------------------------------
+Capturing subpattern count = 0
+Options: anchored
+No first char
+No need char
+
+/[\n\x0b\x0c\x0d[:blank:]]/IS
+Capturing subpattern count = 0
+Contains explicit CR or LF match
+No options
+No first char
+No need char
+Subject length lower bound = 1
+Starting byte set: \x09 \x0a \x0b \x0c \x0d \x20 
+
+/^[[:cntrl:]]/DZ
+------------------------------------------------------------------
+        Bra
+        ^
+        [\x00-\x1f\x7f]
+        Ket
+        End
+------------------------------------------------------------------
+Capturing subpattern count = 0
+Options: anchored
+No first char
+No need char
+
+/^[[:digit:]]/DZ
+------------------------------------------------------------------
+        Bra
+        ^
+        [0-9]
+        Ket
+        End
+------------------------------------------------------------------
+Capturing subpattern count = 0
+Options: anchored
+No first char
+No need char
+
+/^[[:graph:]]/DZ
+------------------------------------------------------------------
+        Bra
+        ^
+        [!-~]
+        Ket
+        End
+------------------------------------------------------------------
+Capturing subpattern count = 0
+Options: anchored
+No first char
+No need char
+
+/^[[:lower:]]/DZ
+------------------------------------------------------------------
+        Bra
+        ^
+        [a-z]
+        Ket
+        End
+------------------------------------------------------------------
+Capturing subpattern count = 0
+Options: anchored
+No first char
+No need char
+
+/^[[:print:]]/DZ
+------------------------------------------------------------------
+        Bra
+        ^
+        [ -~]
+        Ket
+        End
+------------------------------------------------------------------
+Capturing subpattern count = 0
+Options: anchored
+No first char
+No need char
+
+/^[[:punct:]]/DZ
+------------------------------------------------------------------
+        Bra
+        ^
+        [!-/:-@[-`{-~]
+        Ket
+        End
+------------------------------------------------------------------
+Capturing subpattern count = 0
+Options: anchored
+No first char
+No need char
+
+/^[[:space:]]/DZ
+------------------------------------------------------------------
+        Bra
+        ^
+        [\x09-\x0d ]
+        Ket
+        End
+------------------------------------------------------------------
+Capturing subpattern count = 0
+Options: anchored
+No first char
+No need char
+
+/^[[:upper:]]/DZ
+------------------------------------------------------------------
+        Bra
+        ^
+        [A-Z]
+        Ket
+        End
+------------------------------------------------------------------
+Capturing subpattern count = 0
+Options: anchored
+No first char
+No need char
+
+/^[[:xdigit:]]/DZ
+------------------------------------------------------------------
+        Bra
+        ^
+        [0-9A-Fa-f]
+        Ket
+        End
+------------------------------------------------------------------
+Capturing subpattern count = 0
+Options: anchored
+No first char
+No need char
+
+/^[[:word:]]/DZ
+------------------------------------------------------------------
+        Bra
+        ^
+        [0-9A-Z_a-z]
+        Ket
+        End
+------------------------------------------------------------------
+Capturing subpattern count = 0
+Options: anchored
+No first char
+No need char
+
+/^[[:^cntrl:]]/DZ
+------------------------------------------------------------------
+        Bra
+        ^
+        [ -~\x80-\xff] (neg)
+        Ket
+        End
+------------------------------------------------------------------
+Capturing subpattern count = 0
+Options: anchored
+No first char
+No need char
+
+/^[12[:^digit:]]/DZ
+------------------------------------------------------------------
+        Bra
+        ^
+        [\x00-/12:-\xff] (neg)
+        Ket
+        End
+------------------------------------------------------------------
+Capturing subpattern count = 0
+Options: anchored
+No first char
+No need char
+
+/^[[:^blank:]]/DZ
+------------------------------------------------------------------
+        Bra
+        ^
+        [\x00-\x08\x0a-\x1f!-\xff] (neg)
+        Ket
+        End
+------------------------------------------------------------------
+Capturing subpattern count = 0
+Options: anchored
+No first char
+No need char
+
+/[01[:alpha:]%]/DZ
+------------------------------------------------------------------
+        Bra
+        [%01A-Za-z]
+        Ket
+        End
+------------------------------------------------------------------
+Capturing subpattern count = 0
+No options
+No first char
+No need char
+
+/[[.ch.]]/I
+Failed: POSIX collating elements are not supported at offset 1
+
+/[[=ch=]]/I
+Failed: POSIX collating elements are not supported at offset 1
+
+/[[:rhubarb:]]/I
+Failed: unknown POSIX class name at offset 3
+
+/[[:upper:]]/Ii
+Capturing subpattern count = 0
+Options: caseless
+No first char
+No need char
+    A
+ 0: A
+    a
+ 0: a
+
+/[[:lower:]]/Ii
+Capturing subpattern count = 0
+Options: caseless
+No first char
+No need char
+    A
+ 0: A
+    a
+ 0: a
+
+/((?-i)[[:lower:]])[[:lower:]]/Ii
+Capturing subpattern count = 1
+Options: caseless
+No first char
+No need char
+    ab
+ 0: ab
+ 1: a
+    aB
+ 0: aB
+ 1: a
+    *** Failers
+ 0: ai
+ 1: a
+    Ab
+No match
+    AB
+No match
+
+/[\200-\110]/I
+Failed: range out of order in character class at offset 9
+
+/^(?(0)f|b)oo/I
+Failed: invalid condition (?(0) at offset 6
+
+/This one's here because of the large output vector needed/I
+Capturing subpattern count = 0
+No options
+First char = 'T'
+Need char = 'd'
+
+/(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\w+)\s+(\270)/I
+Capturing subpattern count = 271
+Max back reference = 270
+No options
+No first char
+No need char
+    \O900 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 ABC ABC
+ 0: 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 ABC ABC
+ 1: 1 
+ 2: 2 
+ 3: 3 
+ 4: 4 
+ 5: 5 
+ 6: 6 
+ 7: 7 
+ 8: 8 
+ 9: 9 
+10: 10 
+11: 11 
+12: 12 
+13: 13 
+14: 14 
+15: 15 
+16: 16 
+17: 17 
+18: 18 
+19: 19 
+20: 20 
+21: 21 
+22: 22 
+23: 23 
+24: 24 
+25: 25 
+26: 26 
+27: 27 
+28: 28 
+29: 29 
+30: 30 
+31: 31 
+32: 32 
+33: 33 
+34: 34 
+35: 35 
+36: 36 
+37: 37 
+38: 38 
+39: 39 
+40: 40 
+41: 41 
+42: 42 
+43: 43 
+44: 44 
+45: 45 
+46: 46 
+47: 47 
+48: 48 
+49: 49 
+50: 50 
+51: 51 
+52: 52 
+53: 53 
+54: 54 
+55: 55 
+56: 56 
+57: 57 
+58: 58 
+59: 59 
+60: 60 
+61: 61 
+62: 62 
+63: 63 
+64: 64 
+65: 65 
+66: 66 
+67: 67 
+68: 68 
+69: 69 
+70: 70 
+71: 71 
+72: 72 
+73: 73 
+74: 74 
+75: 75 
+76: 76 
+77: 77 
+78: 78 
+79: 79 
+80: 80 
+81: 81 
+82: 82 
+83: 83 
+84: 84 
+85: 85 
+86: 86 
+87: 87 
+88: 88 
+89: 89 
+90: 90 
+91: 91 
+92: 92 
+93: 93 
+94: 94 
+95: 95 
+96: 96 
+97: 97 
+98: 98 
+99: 99 
+100: 100 
+101: 101 
+102: 102 
+103: 103 
+104: 104 
+105: 105 
+106: 106 
+107: 107 
+108: 108 
+109: 109 
+110: 110 
+111: 111 
+112: 112 
+113: 113 
+114: 114 
+115: 115 
+116: 116 
+117: 117 
+118: 118 
+119: 119 
+120: 120 
+121: 121 
+122: 122 
+123: 123 
+124: 124 
+125: 125 
+126: 126 
+127: 127 
+128: 128 
+129: 129 
+130: 130 
+131: 131 
+132: 132 
+133: 133 
+134: 134 
+135: 135 
+136: 136 
+137: 137 
+138: 138 
+139: 139 
+140: 140 
+141: 141 
+142: 142 
+143: 143 
+144: 144 
+145: 145 
+146: 146 
+147: 147 
+148: 148 
+149: 149 
+150: 150 
+151: 151 
+152: 152 
+153: 153 
+154: 154 
+155: 155 
+156: 156 
+157: 157 
+158: 158 
+159: 159 
+160: 160 
+161: 161 
+162: 162 
+163: 163 
+164: 164 
+165: 165 
+166: 166 
+167: 167 
+168: 168 
+169: 169 
+170: 170 
+171: 171 
+172: 172 
+173: 173 
+174: 174 
+175: 175 
+176: 176 
+177: 177 
+178: 178 
+179: 179 
+180: 180 
+181: 181 
+182: 182 
+183: 183 
+184: 184 
+185: 185 
+186: 186 
+187: 187 
+188: 188 
+189: 189 
+190: 190 
+191: 191 
+192: 192 
+193: 193 
+194: 194 
+195: 195 
+196: 196 
+197: 197 
+198: 198 
+199: 199 
+200: 200 
+201: 201 
+202: 202 
+203: 203 
+204: 204 
+205: 205 
+206: 206 
+207: 207 
+208: 208 
+209: 209 
+210: 210 
+211: 211 
+212: 212 
+213: 213 
+214: 214 
+215: 215 
+216: 216 
+217: 217 
+218: 218 
+219: 219 
+220: 220 
+221: 221 
+222: 222 
+223: 223 
+224: 224 
+225: 225 
+226: 226 
+227: 227 
+228: 228 
+229: 229 
+230: 230 
+231: 231 
+232: 232 
+233: 233 
+234: 234 
+235: 235 
+236: 236 
+237: 237 
+238: 238 
+239: 239 
+240: 240 
+241: 241 
+242: 242 
+243: 243 
+244: 244 
+245: 245 
+246: 246 
+247: 247 
+248: 248 
+249: 249 
+250: 250 
+251: 251 
+252: 252 
+253: 253 
+254: 254 
+255: 255 
+256: 256 
+257: 257 
+258: 258 
+259: 259 
+260: 260 
+261: 261 
+262: 262 
+263: 263 
+264: 264 
+265: 265 
+266: 266 
+267: 267 
+268: 268 
+269: 269 
+270: ABC
+271: ABC
+
+/This one's here because Perl does this differently and PCRE can't at present/I
+Capturing subpattern count = 0
+No options
+First char = 'T'
+Need char = 't'
+
+/(main(O)?)+/I
+Capturing subpattern count = 2
+No options
+First char = 'm'
+Need char = 'n'
+    mainmain
+ 0: mainmain
+ 1: main
+    mainOmain
+ 0: mainOmain
+ 1: main
+ 2: O
+
+/These are all cases where Perl does it differently (nested captures)/I
+Capturing subpattern count = 1
+No options
+First char = 'T'
+Need char = 's'
+
+/^(a(b)?)+$/I
+Capturing subpattern count = 2
+Options: anchored
+No first char
+No need char
+    aba
+ 0: aba
+ 1: a
+ 2: b
+
+/^(aa(bb)?)+$/I
+Capturing subpattern count = 2
+Options: anchored
+No first char
+No need char
+    aabbaa
+ 0: aabbaa
+ 1: aa
+ 2: bb
+
+/^(aa|aa(bb))+$/I
+Capturing subpattern count = 2
+Options: anchored
+No first char
+No need char
+    aabbaa
+ 0: aabbaa
+ 1: aa
+ 2: bb
+
+/^(aa(bb)??)+$/I
+Capturing subpattern count = 2
+Options: anchored
+No first char
+No need char
+    aabbaa
+ 0: aabbaa
+ 1: aa
+ 2: bb
+
+/^(?:aa(bb)?)+$/I
+Capturing subpattern count = 1
+Options: anchored
+No first char
+No need char
+    aabbaa
+ 0: aabbaa
+ 1: bb
+
+/^(aa(b(b))?)+$/I
+Capturing subpattern count = 3
+Options: anchored
+No first char
+No need char
+    aabbaa
+ 0: aabbaa
+ 1: aa
+ 2: bb
+ 3: b
+
+/^(?:aa(b(b))?)+$/I
+Capturing subpattern count = 2
+Options: anchored
+No first char
+No need char
+    aabbaa
+ 0: aabbaa
+ 1: bb
+ 2: b
+
+/^(?:aa(b(?:b))?)+$/I
+Capturing subpattern count = 1
+Options: anchored
+No first char
+No need char
+    aabbaa
+ 0: aabbaa
+ 1: bb
+
+/^(?:aa(bb(?:b))?)+$/I
+Capturing subpattern count = 1
+Options: anchored
+No first char
+No need char
+    aabbbaa
+ 0: aabbbaa
+ 1: bbb
+
+/^(?:aa(b(?:bb))?)+$/I
+Capturing subpattern count = 1
+Options: anchored
+No first char
+No need char
+    aabbbaa
+ 0: aabbbaa
+ 1: bbb
+
+/^(?:aa(?:b(b))?)+$/I
+Capturing subpattern count = 1
+Options: anchored
+No first char
+No need char
+    aabbaa
+ 0: aabbaa
+ 1: b
+
+/^(?:aa(?:b(bb))?)+$/I
+Capturing subpattern count = 1
+Options: anchored
+No first char
+No need char
+    aabbbaa
+ 0: aabbbaa
+ 1: bb
+
+/^(aa(b(bb))?)+$/I
+Capturing subpattern count = 3
+Options: anchored
+No first char
+No need char
+    aabbbaa
+ 0: aabbbaa
+ 1: aa
+ 2: bbb
+ 3: bb
+
+/^(aa(bb(bb))?)+$/I
+Capturing subpattern count = 3
+Options: anchored
+No first char
+No need char
+    aabbbbaa
+ 0: aabbbbaa
+ 1: aa
+ 2: bbbb
+ 3: bb
+
+/--------------------------------------------------------------------/I
+Capturing subpattern count = 0
+No options
+First char = '-'
+Need char = '-'
+
+/#/IxDZ
+------------------------------------------------------------------
+        Bra
+        Ket
+        End
+------------------------------------------------------------------
+Capturing subpattern count = 0
+Options: extended
+No first char
+No need char
+
+/a#/IxDZ
+------------------------------------------------------------------
+        Bra
+        a
+        Ket
+        End
+------------------------------------------------------------------
+Capturing subpattern count = 0
+Options: extended
+First char = 'a'
+No need char
+
+/[\s]/DZ
+------------------------------------------------------------------
+        Bra
+        [\x09\x0a\x0c\x0d ]
+        Ket
+        End
+------------------------------------------------------------------
+Capturing subpattern count = 0
+No options
+No first char
+No need char
+
+/[\S]/DZ
+------------------------------------------------------------------
+        Bra
+        [\x00-\x08\x0b\x0e-\x1f!-\xff] (neg)
+        Ket
+        End
+------------------------------------------------------------------
+Capturing subpattern count = 0
+No options
+No first char
+No need char
+
+/a(?i)b/DZ
+------------------------------------------------------------------
+        Bra
+        a
+     /i b
+        Ket
+        End
+------------------------------------------------------------------
+Capturing subpattern count = 0
+No options
+First char = 'a'
+Need char = 'b' (caseless)
+    ab
+ 0: ab
+    aB
+ 0: aB
+    *** Failers
+No match
+    AB
+No match
+
+/(a(?i)b)/DZ
+------------------------------------------------------------------
+        Bra
+        CBra 1
+        a
+     /i b
+        Ket
+        Ket
+        End
+------------------------------------------------------------------
+Capturing subpattern count = 1
+No options
+First char = 'a'
+Need char = 'b' (caseless)
+    ab
+ 0: ab
+ 1: ab
+    aB
+ 0: aB
+ 1: aB
+    *** Failers
+No match
+    AB
+No match
+
+/   (?i)abc/IxDZ
+------------------------------------------------------------------
+        Bra
+     /i abc
+        Ket
+        End
+------------------------------------------------------------------
+Capturing subpattern count = 0
+Options: caseless extended
+First char = 'a' (caseless)
+Need char = 'c' (caseless)
+
+/#this is a comment
+  (?i)abc/IxDZ
+------------------------------------------------------------------
+        Bra
+     /i abc
+        Ket
+        End
+------------------------------------------------------------------
+Capturing subpattern count = 0
+Options: caseless extended
+First char = 'a' (caseless)
+Need char = 'c' (caseless)
+
+/123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890/DZ
+------------------------------------------------------------------
+        Bra
+        123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890
+        Ket
+        End
+------------------------------------------------------------------
+Capturing subpattern count = 0
+No options
+First char = '1'
+Need char = '0'
+
+/\Q123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890/DZ
+------------------------------------------------------------------
+        Bra
+        123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890
+        Ket
+        End
+------------------------------------------------------------------
+Capturing subpattern count = 0
+No options
+First char = '1'
+Need char = '0'
+
+/\Q\E/DZ
+------------------------------------------------------------------
+        Bra
+        Ket
+        End
+------------------------------------------------------------------
+Capturing subpattern count = 0
+No options
+No first char
+No need char
+    \
+ 0: 
+
+/\Q\Ex/DZ
+------------------------------------------------------------------
+        Bra
+        x
+        Ket
+        End
+------------------------------------------------------------------
+Capturing subpattern count = 0
+No options
+First char = 'x'
+No need char
+
+/ \Q\E/DZ
+------------------------------------------------------------------
+        Bra
+         
+        Ket
+        End
+------------------------------------------------------------------
+Capturing subpattern count = 0
+No options
+First char = ' '
+No need char
+
+/a\Q\E/DZ
+------------------------------------------------------------------
+        Bra
+        a
+        Ket
+        End
+------------------------------------------------------------------
+Capturing subpattern count = 0
+No options
+First char = 'a'
+No need char
+  abc
+ 0: a
+  bca
+ 0: a
+  bac
+ 0: a
+
+/a\Q\Eb/DZ
+------------------------------------------------------------------
+        Bra
+        ab
+        Ket
+        End
+------------------------------------------------------------------
+Capturing subpattern count = 0
+No options
+First char = 'a'
+Need char = 'b'
+  abc
+ 0: ab
+
+/\Q\Eabc/DZ
+------------------------------------------------------------------
+        Bra
+        abc
+        Ket
+        End
+------------------------------------------------------------------
+Capturing subpattern count = 0
+No options
+First char = 'a'
+Need char = 'c'
+
+/x*+\w/DZ
+------------------------------------------------------------------
+        Bra
+        x*+
+        \w
+        Ket
+        End
+------------------------------------------------------------------
+Capturing subpattern count = 0
+No options
+No first char
+No need char
+    *** Failers
+ 0: F
+    xxxxx
+No match
+
+/x?+/DZ
+------------------------------------------------------------------
+        Bra
+        x?+
+        Ket
+        End
+------------------------------------------------------------------
+Capturing subpattern count = 0
+No options
+No first char
+No need char
+
+/x++/DZ
+------------------------------------------------------------------
+        Bra
+        x++
+        Ket
+        End
+------------------------------------------------------------------
+Capturing subpattern count = 0
+No options
+First char = 'x'
+No need char
+
+/x{1,3}+/DZ
+------------------------------------------------------------------
+        Bra
+        Once
+        x
+        x{0,2}
+        Ket
+        Ket
+        End
+------------------------------------------------------------------
+Capturing subpattern count = 0
+No options
+First char = 'x'
+No need char
+
+/(x)*+/DZ
+------------------------------------------------------------------
+        Bra
+        Braposzero
+        CBraPos 1
+        x
+        KetRpos
+        Ket
+        End
+------------------------------------------------------------------
+Capturing subpattern count = 1
+No options
+No first char
+No need char
+
+/^(\w++|\s++)*$/I
+Capturing subpattern count = 1
+Options: anchored
+No first char
+No need char
+    now is the time for all good men to come to the aid of the party
+ 0: now is the time for all good men to come to the aid of the party
+ 1: party
+    *** Failers
+No match
+    this is not a line with only words and spaces!
+No match
+
+/(\d++)(\w)/I
+Capturing subpattern count = 2
+No options
+No first char
+No need char
+    12345a
+ 0: 12345a
+ 1: 12345
+ 2: a
+    *** Failers
+No match
+    12345+
+No match
+
+/a++b/I
+Capturing subpattern count = 0
+No options
+First char = 'a'
+Need char = 'b'
+    aaab
+ 0: aaab
+
+/(a++b)/I
+Capturing subpattern count = 1
+No options
+First char = 'a'
+Need char = 'b'
+    aaab
+ 0: aaab
+ 1: aaab
+
+/(a++)b/I
+Capturing subpattern count = 1
+No options
+First char = 'a'
+Need char = 'b'
+    aaab
+ 0: aaab
+ 1: aaa
+
+/([^()]++|\([^()]*\))+/I
+Capturing subpattern count = 1
+No options
+No first char
+No need char
+    ((abc(ade)ufh()()x
+ 0: abc(ade)ufh()()x
+ 1: x
+
+/\(([^()]++|\([^()]+\))+\)/I
+Capturing subpattern count = 1
+No options
+First char = '('
+Need char = ')'
+    (abc)
+ 0: (abc)
+ 1: abc
+    (abc(def)xyz)
+ 0: (abc(def)xyz)
+ 1: xyz
+    *** Failers
+No match
+    ((()aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+No match
+
+/(abc){1,3}+/DZ
+------------------------------------------------------------------
+        Bra
+        Once
+        CBra 1
+        abc
+        Ket
+        Brazero
+        Bra
+        CBra 1
+        abc
+        Ket
+        Brazero
+        CBra 1
+        abc
+        Ket
+        Ket
+        Ket
+        Ket
+        End
+------------------------------------------------------------------
+Capturing subpattern count = 1
+No options
+First char = 'a'
+Need char = 'c'
+
+/a+?+/I
+Failed: nothing to repeat at offset 3
+
+/a{2,3}?+b/I
+Failed: nothing to repeat at offset 7
+
+/(?U)a+?+/I
+Failed: nothing to repeat at offset 7
+
+/a{2,3}?+b/IU
+Failed: nothing to repeat at offset 7
+
+/x(?U)a++b/DZ
+------------------------------------------------------------------
+        Bra
+        x
+        a++
+        b
+        Ket
+        End
+------------------------------------------------------------------
+Capturing subpattern count = 0
+No options
+First char = 'x'
+Need char = 'b'
+    xaaaab
+ 0: xaaaab
+
+/(?U)xa++b/DZ
+------------------------------------------------------------------
+        Bra
+        x
+        a++
+        b
+        Ket
+        End
+------------------------------------------------------------------
+Capturing subpattern count = 0
+Options: ungreedy
+First char = 'x'
+Need char = 'b'
+    xaaaab
+ 0: xaaaab
+
+/^((a+)(?U)([ab]+)(?-U)([bc]+)(\w*))/DZ
+------------------------------------------------------------------
+        Bra
+        ^
+        CBra 1
+        CBra 2
+        a+
+        Ket
+        CBra 3
+        [ab]+?
+        Ket
+        CBra 4
+        [bc]+
+        Ket
+        CBra 5
+        \w*
+        Ket
+        Ket
+        Ket
+        End
+------------------------------------------------------------------
+Capturing subpattern count = 5
+Options: anchored
+No first char
+No need char
+
+/^x(?U)a+b/DZ
+------------------------------------------------------------------
+        Bra
+        ^
+        x
+        a++
+        b
+        Ket
+        End
+------------------------------------------------------------------
+Capturing subpattern count = 0
+Options: anchored
+No first char
+Need char = 'b'
+
+/^x(?U)(a+)b/DZ
+------------------------------------------------------------------
+        Bra
+        ^
+        x
+        CBra 1
+        a+?
+        Ket
+        b
+        Ket
+        End
+------------------------------------------------------------------
+Capturing subpattern count = 1
+Options: anchored
+No first char
+Need char = 'b'
+
+/[.x.]/I
+Failed: POSIX collating elements are not supported at offset 0
+
+/[=x=]/I
+Failed: POSIX collating elements are not supported at offset 0
+
+/[:x:]/I
+Failed: POSIX named classes are supported only within a class at offset 0
+
+/\l/I
+Failed: PCRE does not support \L, \l, \N{name}, \U, or \u at offset 1
+
+/\L/I
+Failed: PCRE does not support \L, \l, \N{name}, \U, or \u at offset 1
+
+/\N{name}/I
+Failed: PCRE does not support \L, \l, \N{name}, \U, or \u at offset 1
+
+/\u/I
+Failed: PCRE does not support \L, \l, \N{name}, \U, or \u at offset 1
+
+/\U/I
+Failed: PCRE does not support \L, \l, \N{name}, \U, or \u at offset 1
+
+/[/I
+Failed: missing terminating ] for character class at offset 1
+
+/[a-/I
+Failed: missing terminating ] for character class at offset 3
+
+/[[:space:]/I
+Failed: missing terminating ] for character class at offset 10
+
+/[\s]/IDZ
+------------------------------------------------------------------
+        Bra
+        [\x09\x0a\x0c\x0d ]
+        Ket
+        End
+------------------------------------------------------------------
+Capturing subpattern count = 0
+No options
+No first char
+No need char
+
+/[[:space:]]/IDZ
+------------------------------------------------------------------
+        Bra
+        [\x09-\x0d ]
+        Ket
+        End
+------------------------------------------------------------------
+Capturing subpattern count = 0
+No options
+No first char
+No need char
+
+/[[:space:]abcde]/IDZ
+------------------------------------------------------------------
+        Bra
+        [\x09-\x0d a-e]
+        Ket
+        End
+------------------------------------------------------------------
+Capturing subpattern count = 0
+No options
+No first char
+No need char
+
+/< (?: (?(R) \d++  | [^<>]*+) | (?R)) * >/Ix
+Capturing subpattern count = 0
+Options: extended
+First char = '<'
+Need char = '>'
+    <>
+ 0: <>
+    <abcd>
+ 0: <abcd>
+    <abc <123> hij>
+ 0: <abc <123> hij>
+    <abc <def> hij>
+ 0: <def>
+    <abc<>def>
+ 0: <abc<>def>
+    <abc<>
+ 0: <>
+    *** Failers
+No match
+    <abc
+No match
+
+|8J\$WE\<\.rX\+ix\[d1b\!H\#\?vV0vrK\:ZH1\=2M\>iV\;\?aPhFB\<\*vW\@QW\@sO9\}cfZA\-i\'w\%hKd6gt1UJP\,15_\#QY\$M\^Mss_U\/\]\&LK9\[5vQub\^w\[KDD\<EjmhUZ\?\.akp2dF\>qmj\;2\}YWFdYx\.Ap\]hjCPTP\(n28k\+3\;o\&WXqs\/gOXdr\$\:r\'do0\;b4c\(f_Gr\=\"\\4\)\[01T7ajQJvL\$W\~mL_sS\/4h\:x\*\[ZN\=KLs\&L5zX\/\/\>it\,o\:aU\(\;Z\>pW\&T7oP\'2K\^E\:x9\'c\[\%z\-\,64JQ5AeH_G\#KijUKghQw\^\\vea3a\?kka_G\$8\#\`\*kynsxzBLru\'\]k_\[7FrVx\}\^\=\$blx\>s\-N\%j\;D\*aZDnsw\:YKZ\%Q\.Kne9\#hP\?\+b3\(SOvL\,\^\;\&u5\@\?5C5Bhb\=m\-vEh_L15Jl\]U\)0RP6\{q\%L\^_z5E\'Dw6X\b|IDZ
+------------------------------------------------------------------
+        Bra
+        8J$WE<.rX+ix[d1b!H#?vV0vrK:ZH1=2M>iV;?aPhFB<*vW@QW@sO9}cfZA-i'w%hKd6gt1UJP,15_#QY$M^Mss_U/]&LK9[5vQub^w[KDD<EjmhUZ?.akp2dF>qmj;2}YWFdYx.Ap]hjCPTP(n28k+3;o&WXqs/gOXdr$:r'do0;b4c(f_Gr="\4)[01T7ajQJvL$W~mL_sS/4h:x*[ZN=KLs&L5zX//>it,o:aU(;Z>pW&T7oP'2K^E:x9'c[%z-,64JQ5AeH_G#KijUKghQw^\vea3a?kka_G$8#`*kynsxzBLru']k_[7FrVx}^=$blx>s-N%j;D*aZDnsw:YKZ%Q.Kne9#hP?+b3(SOvL,^;&u5@?5C5Bhb=m-vEh_L15Jl]U)0RP6{q%L^_z5E'Dw6X
+        \b
+        Ket
+        End
+------------------------------------------------------------------
+Capturing subpattern count = 0
+No options
+First char = '8'
+Need char = 'X'
+Max lookbehind = 1
+
+|\$\<\.X\+ix\[d1b\!H\#\?vV0vrK\:ZH1\=2M\>iV\;\?aPhFB\<\*vW\@QW\@sO9\}cfZA\-i\'w\%hKd6gt1UJP\,15_\#QY\$M\^Mss_U\/\]\&LK9\[5vQub\^w\[KDD\<EjmhUZ\?\.akp2dF\>qmj\;2\}YWFdYx\.Ap\]hjCPTP\(n28k\+3\;o\&WXqs\/gOXdr\$\:r\'do0\;b4c\(f_Gr\=\"\\4\)\[01T7ajQJvL\$W\~mL_sS\/4h\:x\*\[ZN\=KLs\&L5zX\/\/\>it\,o\:aU\(\;Z\>pW\&T7oP\'2K\^E\:x9\'c\[\%z\-\,64JQ5AeH_G\#KijUKghQw\^\\vea3a\?kka_G\$8\#\`\*kynsxzBLru\'\]k_\[7FrVx\}\^\=\$blx\>s\-N\%j\;D\*aZDnsw\:YKZ\%Q\.Kne9\#hP\?\+b3\(SOvL\,\^\;\&u5\@\?5C5Bhb\=m\-vEh_L15Jl\]U\)0RP6\{q\%L\^_z5E\'Dw6X\b|IDZ
+------------------------------------------------------------------
+        Bra
+        $<.X+ix[d1b!H#?vV0vrK:ZH1=2M>iV;?aPhFB<*vW@QW@sO9}cfZA-i'w%hKd6gt1UJP,15_#QY$M^Mss_U/]&LK9[5vQub^w[KDD<EjmhUZ?.akp2dF>qmj;2}YWFdYx.Ap]hjCPTP(n28k+3;o&WXqs/gOXdr$:r'do0;b4c(f_Gr="\4)[01T7ajQJvL$W~mL_sS/4h:x*[ZN=KLs&L5zX//>it,o:aU(;Z>pW&T7oP'2K^E:x9'c[%z-,64JQ5AeH_G#KijUKghQw^\vea3a?kka_G$8#`*kynsxzBLru']k_[7FrVx}^=$blx>s-N%j;D*aZDnsw:YKZ%Q.Kne9#hP?+b3(SOvL,^;&u5@?5C5Bhb=m-vEh_L15Jl]U)0RP6{q%L^_z5E'Dw6X
+        \b
+        Ket
+        End
+------------------------------------------------------------------
+Capturing subpattern count = 0
+No options
+First char = '$'
+Need char = 'X'
+Max lookbehind = 1
+
+/(.*)\d+\1/I
+Capturing subpattern count = 1
+Max back reference = 1
+No options
+No first char
+No need char
+
+/(.*)\d+/I
+Capturing subpattern count = 1
+No options
+First char at start or follows newline
+No need char
+
+/(.*)\d+\1/Is
+Capturing subpattern count = 1
+Max back reference = 1
+Options: dotall
+No first char
+No need char
+
+/(.*)\d+/Is
+Capturing subpattern count = 1
+Options: anchored dotall
+No first char
+No need char
+
+/(.*(xyz))\d+\2/I
+Capturing subpattern count = 2
+Max back reference = 2
+No options
+First char at start or follows newline
+Need char = 'z'
+
+/((.*))\d+\1/I
+Capturing subpattern count = 2
+Max back reference = 1
+No options
+No first char
+No need char
+    abc123bc
+ 0: bc123bc
+ 1: bc
+ 2: bc
+
+/a[b]/I
+Capturing subpattern count = 0
+No options
+First char = 'a'
+Need char = 'b'
+
+/(?=a).*/I
+Capturing subpattern count = 0
+No options
+First char = 'a'
+No need char
+
+/(?=abc).xyz/IiI
+Capturing subpattern count = 0
+Options: caseless
+First char = 'a' (caseless)
+Need char = 'z' (caseless)
+
+/(?=abc)(?i).xyz/I
+Capturing subpattern count = 0
+No options
+First char = 'a'
+Need char = 'z' (caseless)
+
+/(?=a)(?=b)/I
+Capturing subpattern count = 0
+No options
+First char = 'a'
+No need char
+
+/(?=.)a/I
+Capturing subpattern count = 0
+No options
+First char = 'a'
+No need char
+
+/((?=abcda)a)/I
+Capturing subpattern count = 1
+No options
+First char = 'a'
+Need char = 'a'
+
+/((?=abcda)ab)/I
+Capturing subpattern count = 1
+No options
+First char = 'a'
+Need char = 'b'
+
+/()a/I
+Capturing subpattern count = 1
+No options
+No first char
+Need char = 'a'
+
+/(?(1)ab|ac)(.)/I
+Capturing subpattern count = 1
+No options
+First char = 'a'
+No need char
+
+/(?(1)abz|acz)(.)/I
+Capturing subpattern count = 1
+No options
+First char = 'a'
+Need char = 'z'
+
+/(?(1)abz)(.)/I
+Capturing subpattern count = 1
+No options
+No first char
+No need char
+
+/(?(1)abz)(1)23/I
+Capturing subpattern count = 1
+No options
+No first char
+Need char = '3'
+
+/(a)+/I
+Capturing subpattern count = 1
+No options
+First char = 'a'
+No need char
+
+/(a){2,3}/I
+Capturing subpattern count = 1
+No options
+First char = 'a'
+Need char = 'a'
+
+/(a)*/I
+Capturing subpattern count = 1
+No options
+No first char
+No need char
+
+/[a]/I
+Capturing subpattern count = 0
+No options
+First char = 'a'
+No need char
+
+/[ab]/I
+Capturing subpattern count = 0
+No options
+No first char
+No need char
+
+/[ab]/IS
+Capturing subpattern count = 0
+No options
+No first char
+No need char
+Subject length lower bound = 1
+Starting byte set: a b 
+
+/[^a]/I
+Capturing subpattern count = 0
+No options
+No first char
+No need char
+
+/\d456/I
+Capturing subpattern count = 0
+No options
+No first char
+Need char = '6'
+
+/\d456/IS
+Capturing subpattern count = 0
+No options
+No first char
+Need char = '6'
+Subject length lower bound = 4
+Starting byte set: 0 1 2 3 4 5 6 7 8 9 
+
+/a^b/I
+Capturing subpattern count = 0
+No options
+First char = 'a'
+Need char = 'b'
+
+/^a/Im
+Capturing subpattern count = 0
+Options: multiline
+First char at start or follows newline
+Need char = 'a'
+  abcde
+ 0: a
+  xy\nabc
+ 0: a
+  *** Failers
+No match
+  xyabc
+No match
+
+/c|abc/I
+Capturing subpattern count = 0
+No options
+No first char
+Need char = 'c'
+
+/(?i)[ab]/IS
+Capturing subpattern count = 0
+Options: caseless
+No first char
+No need char
+Subject length lower bound = 1
+Starting byte set: A B a b 
+
+/[ab](?i)cd/IS
+Capturing subpattern count = 0
+No options
+No first char
+Need char = 'd' (caseless)
+Subject length lower bound = 3
+Starting byte set: a b 
+
+/abc(?C)def/I
+Capturing subpattern count = 0
+No options
+First char = 'a'
+Need char = 'f'
+    abcdef
+--->abcdef
+  0 ^  ^       d
+ 0: abcdef
+    1234abcdef
+--->1234abcdef
+  0     ^  ^       d
+ 0: abcdef
+    *** Failers
+No match
+    abcxyz
+No match
+    abcxyzf
+--->abcxyzf
+  0 ^  ^        d
+No match
+
+/abc(?C)de(?C1)f/I
+Capturing subpattern count = 0
+No options
+First char = 'a'
+Need char = 'f'
+    123abcdef
+--->123abcdef
+  0    ^  ^       d
+  1    ^    ^     f
+ 0: abcdef
+
+/(?C1)\dabc(?C2)def/IS
+Capturing subpattern count = 0
+No options
+No first char
+Need char = 'f'
+Subject length lower bound = 7
+Starting byte set: 0 1 2 3 4 5 6 7 8 9 
+    1234abcdef
+--->1234abcdef
+  1 ^              \d
+  1  ^             \d
+  1   ^            \d
+  1    ^           \d
+  2    ^   ^       d
+ 0: 4abcdef
+    *** Failers
+No match
+    abcdef
+No match
+
+/(?C1)\dabc(?C2)def/ISS
+Capturing subpattern count = 0
+No options
+No first char
+Need char = 'f'
+    1234abcdef
+--->1234abcdef
+  1 ^              \d
+  1  ^             \d
+  1   ^            \d
+  1    ^           \d
+  2    ^   ^       d
+ 0: 4abcdef
+    *** Failers
+No match
+    abcdef
+--->abcdef
+  1 ^          \d
+  1  ^         \d
+  1   ^        \d
+  1    ^       \d
+  1     ^      \d
+  1      ^     \d
+No match
+
+/(?C255)ab/I
+Capturing subpattern count = 0
+No options
+First char = 'a'
+Need char = 'b'
+
+/(?C256)ab/I
+Failed: number after (?C is > 255 at offset 6
+
+/(?Cab)xx/I
+Failed: closing ) for (?C expected at offset 3
+
+/(?C12vr)x/I
+Failed: closing ) for (?C expected at offset 5
+
+/abc(?C)def/I
+Capturing subpattern count = 0
+No options
+First char = 'a'
+Need char = 'f'
+    *** Failers
+No match
+    \x83\x0\x61bcdef
+--->\x83\x00abcdef
+  0         ^  ^       d
+ 0: abcdef
+
+/(abc)(?C)de(?C1)f/I
+Capturing subpattern count = 1
+No options
+First char = 'a'
+Need char = 'f'
+    123abcdef
+--->123abcdef
+  0    ^  ^       d
+  1    ^    ^     f
+ 0: abcdef
+ 1: abc
+    123abcdef\C+
+Callout 0: last capture = 1
+ 0: <unset>
+ 1: abc
+--->123abcdef
+       ^  ^       d
+Callout 1: last capture = 1
+ 0: <unset>
+ 1: abc
+--->123abcdef
+       ^    ^     f
+ 0: abcdef
+ 1: abc
+    123abcdef\C-
+ 0: abcdef
+ 1: abc
+    *** Failers
+No match
+    123abcdef\C!1
+--->123abcdef
+  0    ^  ^       d
+  1    ^    ^     f
+No match
+
+/(?C0)(abc(?C1))*/I
+Capturing subpattern count = 1
+No options
+No first char
+No need char
+    abcabcabc
+--->abcabcabc
+  0 ^             (abc(?C1))*
+  1 ^  ^          )
+  1 ^     ^       )
+  1 ^        ^    )
+ 0: abcabcabc
+ 1: abc
+    abcabc\C!1!3
+--->abcabc
+  0 ^          (abc(?C1))*
+  1 ^  ^       )
+  1 ^     ^    )
+ 0: abcabc
+ 1: abc
+    *** Failers
+--->*** Failers
+  0 ^               (abc(?C1))*
+ 0: 
+    abcabcabc\C!1!3
+--->abcabcabc
+  0 ^             (abc(?C1))*
+  1 ^  ^          )
+  1 ^     ^       )
+  1 ^        ^    )
+ 0: abcabc
+ 1: abc
+
+/(\d{3}(?C))*/I
+Capturing subpattern count = 1
+No options
+No first char
+No need char
+    123\C+
+Callout 0: last capture = -1
+ 0: <unset>
+--->123
+    ^  ^    )
+ 0: 123
+ 1: 123
+    123456\C+
+Callout 0: last capture = -1
+ 0: <unset>
+--->123456
+    ^  ^       )
+Callout 0: last capture = 1
+ 0: <unset>
+ 1: 123
+--->123456
+    ^     ^    )
+ 0: 123456
+ 1: 456
+    123456789\C+
+Callout 0: last capture = -1
+ 0: <unset>
+--->123456789
+    ^  ^          )
+Callout 0: last capture = 1
+ 0: <unset>
+ 1: 123
+--->123456789
+    ^     ^       )
+Callout 0: last capture = 1
+ 0: <unset>
+ 1: 456
+--->123456789
+    ^        ^    )
+ 0: 123456789
+ 1: 789
+
+/((xyz)(?C)p|(?C1)xyzabc)/I
+Capturing subpattern count = 2
+No options
+First char = 'x'
+No need char
+    xyzabc\C+
+Callout 0: last capture = 2
+ 0: <unset>
+ 1: <unset>
+ 2: xyz
+--->xyzabc
+    ^  ^       p
+Callout 1: last capture = -1
+ 0: <unset>
+--->xyzabc
+    ^          x
+ 0: xyzabc
+ 1: xyzabc
+
+/(X)((xyz)(?C)p|(?C1)xyzabc)/I
+Capturing subpattern count = 3
+No options
+First char = 'X'
+Need char = 'x'
+    Xxyzabc\C+
+Callout 0: last capture = 3
+ 0: <unset>
+ 1: X
+ 2: <unset>
+ 3: xyz
+--->Xxyzabc
+    ^   ^       p
+Callout 1: last capture = 1
+ 0: <unset>
+ 1: X
+--->Xxyzabc
+    ^^          x
+ 0: Xxyzabc
+ 1: X
+ 2: xyzabc
+
+/(?=(abc))(?C)abcdef/I
+Capturing subpattern count = 1
+No options
+First char = 'a'
+Need char = 'f'
+    abcdef\C+
+Callout 0: last capture = 1
+ 0: <unset>
+ 1: abc
+--->abcdef
+    ^          a
+ 0: abcdef
+ 1: abc
+
+/(?!(abc)(?C1)d)(?C2)abcxyz/I
+Capturing subpattern count = 1
+No options
+First char = 'a'
+Need char = 'z'
+    abcxyz\C+
+Callout 1: last capture = 1
+ 0: <unset>
+ 1: abc
+--->abcxyz
+    ^  ^       d
+Callout 2: last capture = -1
+ 0: <unset>
+--->abcxyz
+    ^          a
+ 0: abcxyz
+
+/(?<=(abc)(?C))xyz/I
+Capturing subpattern count = 1
+No options
+First char = 'x'
+Need char = 'z'
+Max lookbehind = 3
+   abcxyz\C+
+Callout 0: last capture = 1
+ 0: <unset>
+ 1: abc
+--->abcxyz
+       ^       )
+ 0: xyz
+ 1: abc
+
+/a(b+)(c*)(?C1)/I
+Capturing subpattern count = 2
+No options
+First char = 'a'
+Need char = 'b'
+    abbbbbccc\C*1
+--->abbbbbccc
+  1 ^        ^    
+Callout data = 1
+  1 ^       ^     
+Callout data = 1
+  1 ^      ^      
+Callout data = 1
+  1 ^     ^       
+Callout data = 1
+  1 ^    ^        
+Callout data = 1
+  1 ^   ^         
+Callout data = 1
+  1 ^  ^          
+Callout data = 1
+  1 ^ ^           
+Callout data = 1
+No match
+
+/a(b+?)(c*?)(?C1)/I
+Capturing subpattern count = 2
+No options
+First char = 'a'
+Need char = 'b'
+    abbbbbccc\C*1
+--->abbbbbccc
+  1 ^ ^           
+Callout data = 1
+  1 ^  ^          
+Callout data = 1
+  1 ^   ^         
+Callout data = 1
+  1 ^    ^        
+Callout data = 1
+  1 ^     ^       
+Callout data = 1
+  1 ^      ^      
+Callout data = 1
+  1 ^       ^     
+Callout data = 1
+  1 ^        ^    
+Callout data = 1
+No match
+
+/(?C)abc/I
+Capturing subpattern count = 0
+No options
+First char = 'a'
+Need char = 'c'
+
+/(?C)^abc/I
+Capturing subpattern count = 0
+Options: anchored
+No first char
+No need char
+
+/(?C)a|b/IS
+Capturing subpattern count = 0
+No options
+No first char
+No need char
+Subject length lower bound = 1
+Starting byte set: a b 
+
+/(?R)/I
+Failed: recursive call could loop indefinitely at offset 3
+
+/(a|(?R))/I
+Failed: recursive call could loop indefinitely at offset 6
+
+/(ab|(bc|(de|(?R))))/I
+Failed: recursive call could loop indefinitely at offset 15
+
+/x(ab|(bc|(de|(?R))))/I
+Capturing subpattern count = 3
+No options
+First char = 'x'
+No need char
+    xab
+ 0: xab
+ 1: ab
+    xbc
+ 0: xbc
+ 1: bc
+ 2: bc
+    xde
+ 0: xde
+ 1: de
+ 2: de
+ 3: de
+    xxab
+ 0: xxab
+ 1: xab
+ 2: xab
+ 3: xab
+    xxxab
+ 0: xxxab
+ 1: xxab
+ 2: xxab
+ 3: xxab
+    *** Failers
+No match
+    xyab
+No match
+
+/(ab|(bc|(de|(?1))))/I
+Failed: recursive call could loop indefinitely at offset 15
+
+/x(ab|(bc|(de|(?1)x)x)x)/I
+Failed: recursive call could loop indefinitely at offset 16
+
+/^([^()]|\((?1)*\))*$/I
+Capturing subpattern count = 1
+Options: anchored
+No first char
+No need char
+    abc
+ 0: abc
+ 1: c
+    a(b)c
+ 0: a(b)c
+ 1: c
+    a(b(c))d
+ 0: a(b(c))d
+ 1: d
+    *** Failers)
+No match
+    a(b(c)d
+No match
+
+/^>abc>([^()]|\((?1)*\))*<xyz<$/I
+Capturing subpattern count = 1
+Options: anchored
+No first char
+Need char = '<'
+   >abc>123<xyz<
+ 0: >abc>123<xyz<
+ 1: 3
+   >abc>1(2)3<xyz<
+ 0: >abc>1(2)3<xyz<
+ 1: 3
+   >abc>(1(2)3)<xyz<
+ 0: >abc>(1(2)3)<xyz<
+ 1: (1(2)3)
+
+/(a(?1)b)/DZ
+------------------------------------------------------------------
+        Bra
+        CBra 1
+        a
+        Recurse
+        b
+        Ket
+        Ket
+        End
+------------------------------------------------------------------
+Capturing subpattern count = 1
+No options
+First char = 'a'
+Need char = 'b'
+
+/(a(?1)+b)/DZ
+------------------------------------------------------------------
+        Bra
+        CBra 1
+        a
+        Once
+        Recurse
+        KetRmax
+        b
+        Ket
+        Ket
+        End
+------------------------------------------------------------------
+Capturing subpattern count = 1
+No options
+First char = 'a'
+Need char = 'b'
+
+/^(\d+|\((?1)([+*-])(?1)\)|-(?1))$/I
+Capturing subpattern count = 2
+Options: anchored
+No first char
+No need char
+    12
+ 0: 12
+ 1: 12
+    (((2+2)*-3)-7)
+ 0: (((2+2)*-3)-7)
+ 1: (((2+2)*-3)-7)
+ 2: -
+    -12
+ 0: -12
+ 1: -12
+    *** Failers
+No match
+    ((2+2)*-3)-7)
+No match
+
+/^(x(y|(?1){2})z)/I
+Capturing subpattern count = 2
+Options: anchored
+No first char
+No need char
+    xyz
+ 0: xyz
+ 1: xyz
+ 2: y
+    xxyzxyzz
+ 0: xxyzxyzz
+ 1: xxyzxyzz
+ 2: xyzxyz
+    *** Failers
+No match
+    xxyzz
+No match
+    xxyzxyzxyzz
+No match
+
+/((< (?: (?(R) \d++  | [^<>]*+) | (?2)) * >))/Ix
+Capturing subpattern count = 2
+Options: extended
+First char = '<'
+Need char = '>'
+    <>
+ 0: <>
+ 1: <>
+ 2: <>
+    <abcd>
+ 0: <abcd>
+ 1: <abcd>
+ 2: <abcd>
+    <abc <123> hij>
+ 0: <abc <123> hij>
+ 1: <abc <123> hij>
+ 2: <abc <123> hij>
+    <abc <def> hij>
+ 0: <def>
+ 1: <def>
+ 2: <def>
+    <abc<>def>
+ 0: <abc<>def>
+ 1: <abc<>def>
+ 2: <abc<>def>
+    <abc<>
+ 0: <>
+ 1: <>
+ 2: <>
+    *** Failers
+No match
+    <abc
+No match
+
+/(?1)/I
+Failed: reference to non-existent subpattern at offset 3
+
+/((?2)(abc)/I
+Failed: missing ) at offset 10
+
+/^(abc)def(?1)/I
+Capturing subpattern count = 1
+Options: anchored
+No first char
+No need char
+    abcdefabc
+ 0: abcdefabc
+ 1: abc
+
+/^(a|b|c)=(?1)+/I
+Capturing subpattern count = 1
+Options: anchored
+No first char
+No need char
+    a=a
+ 0: a=a
+ 1: a
+    a=b
+ 0: a=b
+ 1: a
+    a=bc
+ 0: a=bc
+ 1: a
+
+/^(a|b|c)=((?1))+/I
+Capturing subpattern count = 2
+Options: anchored
+No first char
+No need char
+    a=a
+ 0: a=a
+ 1: a
+ 2: a
+    a=b
+ 0: a=b
+ 1: a
+ 2: b
+    a=bc
+ 0: a=bc
+ 1: a
+ 2: c
+
+/a(?P<name1>b|c)d(?P<longername2>e)/DZ
+------------------------------------------------------------------
+        Bra
+        a
+        CBra 1
+        b
+        Alt
+        c
+        Ket
+        d
+        CBra 2
+        e
+        Ket
+        Ket
+        End
+------------------------------------------------------------------
+Capturing subpattern count = 2
+Named capturing subpatterns:
+  longername2   2
+  name1         1
+No options
+First char = 'a'
+Need char = 'e'
+    abde
+ 0: abde
+ 1: b
+ 2: e
+    acde
+ 0: acde
+ 1: c
+ 2: e
+
+/(?:a(?P<c>c(?P<d>d)))(?P<a>a)/DZ
+------------------------------------------------------------------
+        Bra
+        Bra
+        a
+        CBra 1
+        c
+        CBra 2
+        d
+        Ket
+        Ket
+        Ket
+        CBra 3
+        a
+        Ket
+        Ket
+        End
+------------------------------------------------------------------
+Capturing subpattern count = 3
+Named capturing subpatterns:
+  a   3
+  c   1
+  d   2
+No options
+First char = 'a'
+Need char = 'a'
+
+/(?P<a>a)...(?P=a)bbb(?P>a)d/DZ
+------------------------------------------------------------------
+        Bra
+        CBra 1
+        a
+        Ket
+        Any
+        Any
+        Any
+        \1
+        bbb
+        Recurse
+        d
+        Ket
+        End
+------------------------------------------------------------------
+Capturing subpattern count = 1
+Max back reference = 1
+Named capturing subpatterns:
+  a   1
+No options
+First char = 'a'
+Need char = 'd'
+
+/^\W*(?:(?P<one>(?P<two>.)\W*(?P>one)\W*(?P=two)|)|(?P<three>(?P<four>.)\W*(?P>three)\W*(?P=four)|\W*.\W*))\W*$/Ii
+Capturing subpattern count = 4
+Max back reference = 4
+Named capturing subpatterns:
+  four    4
+  one     1
+  three   3
+  two     2
+Options: anchored caseless
+No first char
+No need char
+    1221
+ 0: 1221
+ 1: 1221
+ 2: 1
+    Satan, oscillate my metallic sonatas!
+ 0: Satan, oscillate my metallic sonatas!
+ 1: <unset>
+ 2: <unset>
+ 3: Satan, oscillate my metallic sonatas
+ 4: S
+    A man, a plan, a canal: Panama!
+ 0: A man, a plan, a canal: Panama!
+ 1: <unset>
+ 2: <unset>
+ 3: A man, a plan, a canal: Panama
+ 4: A
+    Able was I ere I saw Elba.
+ 0: Able was I ere I saw Elba.
+ 1: <unset>
+ 2: <unset>
+ 3: Able was I ere I saw Elba
+ 4: A
+    *** Failers
+No match
+    The quick brown fox
+No match
+
+/((?(R)a|b))\1(?1)?/I
+Capturing subpattern count = 1
+Max back reference = 1
+No options
+No first char
+No need char
+  bb
+ 0: bb
+ 1: b
+  bbaa
+ 0: bba
+ 1: b
+
+/(.*)a/Is
+Capturing subpattern count = 1
+Options: anchored dotall
+No first char
+Need char = 'a'
+
+/(.*)a\1/Is
+Capturing subpattern count = 1
+Max back reference = 1
+Options: dotall
+No first char
+Need char = 'a'
+
+/(.*)a(b)\2/Is
+Capturing subpattern count = 2
+Max back reference = 2
+Options: anchored dotall
+No first char
+Need char = 'b'
+
+/((.*)a|(.*)b)z/Is
+Capturing subpattern count = 3
+Options: anchored dotall
+No first char
+Need char = 'z'
+
+/((.*)a|(.*)b)z\1/Is
+Capturing subpattern count = 3
+Max back reference = 1
+Options: dotall
+No first char
+Need char = 'z'
+
+/((.*)a|(.*)b)z\2/Is
+Capturing subpattern count = 3
+Max back reference = 2
+Options: dotall
+No first char
+Need char = 'z'
+
+/((.*)a|(.*)b)z\3/Is
+Capturing subpattern count = 3
+Max back reference = 3
+Options: dotall
+No first char
+Need char = 'z'
+
+/((.*)a|^(.*)b)z\3/Is
+Capturing subpattern count = 3
+Max back reference = 3
+Options: anchored dotall
+No first char
+Need char = 'z'
+
+/(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)a/Is
+Capturing subpattern count = 31
+Options: anchored dotall
+No first char
+No need char
+
+/(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)a\31/Is
+Capturing subpattern count = 31
+Max back reference = 31
+Options: dotall
+No first char
+No need char
+
+/(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)a\32/Is
+Capturing subpattern count = 32
+Max back reference = 32
+Options: dotall
+No first char
+No need char
+
+/(a)(bc)/INDZ
+------------------------------------------------------------------
+        Bra
+        Bra
+        a
+        Ket
+        Bra
+        bc
+        Ket
+        Ket
+        End
+------------------------------------------------------------------
+Capturing subpattern count = 0
+Options: no_auto_capture
+First char = 'a'
+Need char = 'c'
+  abc
+ 0: abc
+
+/(?P<one>a)(bc)/INDZ
+------------------------------------------------------------------
+        Bra
+        CBra 1
+        a
+        Ket
+        Bra
+        bc
+        Ket
+        Ket
+        End
+------------------------------------------------------------------
+Capturing subpattern count = 1
+Named capturing subpatterns:
+  one   1
+Options: no_auto_capture
+First char = 'a'
+Need char = 'c'
+  abc
+ 0: abc
+ 1: a
+
+/(a)(?P<named>bc)/INDZ
+------------------------------------------------------------------
+        Bra
+        Bra
+        a
+        Ket
+        CBra 1
+        bc
+        Ket
+        Ket
+        End
+------------------------------------------------------------------
+Capturing subpattern count = 1
+Named capturing subpatterns:
+  named   1
+Options: no_auto_capture
+First char = 'a'
+Need char = 'c'
+
+/(a+)*zz/I
+Capturing subpattern count = 1
+No options
+No first char
+Need char = 'z'
+  aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaazzbbbbbb\M
+Minimum match() limit = 8
+Minimum match() recursion limit = 6
+ 0: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaazz
+ 1: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+  aaaaaaaaaaaaaz\M
+Minimum match() limit = 32768
+Minimum match() recursion limit = 42
+No match
+
+/(aaa(?C1)bbb|ab)/I
+Capturing subpattern count = 1
+No options
+First char = 'a'
+Need char = 'b'
+   aaabbb
+--->aaabbb
+  1 ^  ^       b
+ 0: aaabbb
+ 1: aaabbb
+   aaabbb\C*0
+--->aaabbb
+  1 ^  ^       b
+ 0: aaabbb
+ 1: aaabbb
+   aaabbb\C*1
+--->aaabbb
+  1 ^  ^       b
+Callout data = 1
+ 0: ab
+ 1: ab
+   aaabbb\C*-1
+--->aaabbb
+  1 ^  ^       b
+Callout data = -1
+No match
+
+/ab(?P<one>cd)ef(?P<two>gh)/I
+Capturing subpattern count = 2
+Named capturing subpatterns:
+  one   1
+  two   2
+No options
+First char = 'a'
+Need char = 'h'
+    abcdefgh
+ 0: abcdefgh
+ 1: cd
+ 2: gh
+    abcdefgh\C1\Gtwo
+ 0: abcdefgh
+ 1: cd
+ 2: gh
+ 1C cd (2)
+  G gh (2) two
+    abcdefgh\Cone\Ctwo
+ 0: abcdefgh
+ 1: cd
+ 2: gh
+  C cd (2) one
+  C gh (2) two
+    abcdefgh\Cthree
+no parentheses with name "three"
+ 0: abcdefgh
+ 1: cd
+ 2: gh
+copy substring three failed -7
+
+/(?P<Tes>)(?P<Test>)/DZ
+------------------------------------------------------------------
+        Bra
+        CBra 1
+        Ket
+        CBra 2
+        Ket
+        Ket
+        End
+------------------------------------------------------------------
+Capturing subpattern count = 2
+Named capturing subpatterns:
+  Tes    1
+  Test   2
+No options
+No first char
+No need char
+
+/(?P<Test>)(?P<Tes>)/DZ
+------------------------------------------------------------------
+        Bra
+        CBra 1
+        Ket
+        CBra 2
+        Ket
+        Ket
+        End
+------------------------------------------------------------------
+Capturing subpattern count = 2
+Named capturing subpatterns:
+  Tes    2
+  Test   1
+No options
+No first char
+No need char
+
+/(?P<Z>zz)(?P<A>aa)/I
+Capturing subpattern count = 2
+Named capturing subpatterns:
+  A   2
+  Z   1
+No options
+First char = 'z'
+Need char = 'a'
+    zzaa\CZ
+ 0: zzaa
+ 1: zz
+ 2: aa
+  C zz (2) Z
+    zzaa\CA
+ 0: zzaa
+ 1: zz
+ 2: aa
+  C aa (2) A
+
+/(?P<x>eks)(?P<x>eccs)/I
+Failed: two named subpatterns have the same name at offset 15
+
+/(?P<abc>abc(?P<def>def)(?P<abc>xyz))/I
+Failed: two named subpatterns have the same name at offset 30
+
+"\[((?P<elem>\d+)(,(?P>elem))*)\]"I
+Capturing subpattern count = 3
+Named capturing subpatterns:
+  elem   2
+No options
+First char = '['
+Need char = ']'
+    [10,20,30,5,5,4,4,2,43,23,4234]
+ 0: [10,20,30,5,5,4,4,2,43,23,4234]
+ 1: 10,20,30,5,5,4,4,2,43,23,4234
+ 2: 10
+ 3: ,4234
+    *** Failers
+No match
+    []
+No match
+
+"\[((?P<elem>\d+)(,(?P>elem))*)?\]"I
+Capturing subpattern count = 3
+Named capturing subpatterns:
+  elem   2
+No options
+First char = '['
+Need char = ']'
+    [10,20,30,5,5,4,4,2,43,23,4234]
+ 0: [10,20,30,5,5,4,4,2,43,23,4234]
+ 1: 10,20,30,5,5,4,4,2,43,23,4234
+ 2: 10
+ 3: ,4234
+    []
+ 0: []
+
+/(a(b(?2)c))?/DZ
+------------------------------------------------------------------
+        Bra
+        Brazero
+        CBra 1
+        a
+        CBra 2
+        b
+        Recurse
+        c
+        Ket
+        Ket
+        Ket
+        End
+------------------------------------------------------------------
+Capturing subpattern count = 2
+No options
+No first char
+No need char
+
+/(a(b(?2)c))*/DZ
+------------------------------------------------------------------
+        Bra
+        Brazero
+        CBra 1
+        a
+        CBra 2
+        b
+        Recurse
+        c
+        Ket
+        KetRmax
+        Ket
+        End
+------------------------------------------------------------------
+Capturing subpattern count = 2
+No options
+No first char
+No need char
+
+/(a(b(?2)c)){0,2}/DZ
+------------------------------------------------------------------
+        Bra
+        Brazero
+        Bra
+        CBra 1
+        a
+        CBra 2
+        b
+        Recurse
+        c
+        Ket
+        Ket
+        Brazero
+        CBra 1
+        a
+        CBra 2
+        b
+        Recurse
+        c
+        Ket
+        Ket
+        Ket
+        Ket
+        End
+------------------------------------------------------------------
+Capturing subpattern count = 2
+No options
+No first char
+No need char
+
+/[ab]{1}+/DZ
+------------------------------------------------------------------
+        Bra
+        Once
+        [ab]{1,1}
+        Ket
+        Ket
+        End
+------------------------------------------------------------------
+Capturing subpattern count = 0
+No options
+No first char
+No need char
+
+/((w\/|-|with)*(free|immediate)*.*?shipping\s*[!.-]*)/Ii
+Capturing subpattern count = 3
+Options: caseless
+No first char
+Need char = 'g' (caseless)
+     Baby Bjorn Active Carrier - With free SHIPPING!!
+ 0: Baby Bjorn Active Carrier - With free SHIPPING!!
+ 1: Baby Bjorn Active Carrier - With free SHIPPING!!
+
+/((w\/|-|with)*(free|immediate)*.*?shipping\s*[!.-]*)/IiS
+Capturing subpattern count = 3
+Options: caseless
+No first char
+Need char = 'g' (caseless)
+Subject length lower bound = 8
+No set of starting bytes
+     Baby Bjorn Active Carrier - With free SHIPPING!!
+ 0: Baby Bjorn Active Carrier - With free SHIPPING!!
+ 1: Baby Bjorn Active Carrier - With free SHIPPING!!
+
+/a*.*b/ISDZ
+------------------------------------------------------------------
+        Bra
+        a*
+        Any*
+        b
+        Ket
+        End
+------------------------------------------------------------------
+Capturing subpattern count = 0
+No options
+No first char
+Need char = 'b'
+Subject length lower bound = 1
+No set of starting bytes
+
+/(a|b)*.?c/ISDZ
+------------------------------------------------------------------
+        Bra
+        Brazero
+        CBra 1
+        a
+        Alt
+        b
+        KetRmax
+        Any?
+        c
+        Ket
+        End
+------------------------------------------------------------------
+Capturing subpattern count = 1
+No options
+No first char
+Need char = 'c'
+Subject length lower bound = 1
+No set of starting bytes
+
+/abc(?C255)de(?C)f/DZ
+------------------------------------------------------------------
+        Bra
+        abc
+        Callout 255 10 1
+        de
+        Callout 0 16 1
+        f
+        Ket
+        End
+------------------------------------------------------------------
+Capturing subpattern count = 0
+No options
+First char = 'a'
+Need char = 'f'
+
+/abcde/ICDZ
+------------------------------------------------------------------
+        Bra
+        Callout 255 0 1
+        a
+        Callout 255 1 1
+        b
+        Callout 255 2 1
+        c
+        Callout 255 3 1
+        d
+        Callout 255 4 1
+        e
+        Callout 255 5 0
+        Ket
+        End
+------------------------------------------------------------------
+Capturing subpattern count = 0
+Options:
+First char = 'a'
+Need char = 'e'
+  abcde
+--->abcde
+ +0 ^         a
+ +1 ^^        b
+ +2 ^ ^       c
+ +3 ^  ^      d
+ +4 ^   ^     e
+ +5 ^    ^    
+ 0: abcde
+  abcdfe
+--->abcdfe
+ +0 ^          a
+ +1 ^^         b
+ +2 ^ ^        c
+ +3 ^  ^       d
+ +4 ^   ^      e
+No match
+
+/a*b/ICDZS
+------------------------------------------------------------------
+        Bra
+        Callout 255 0 2
+        a*+
+        Callout 255 2 1
+        b
+        Callout 255 3 0
+        Ket
+        End
+------------------------------------------------------------------
+Capturing subpattern count = 0
+Options:
+No first char
+Need char = 'b'
+Subject length lower bound = 1
+Starting byte set: a b 
+  ab
+--->ab
+ +0 ^      a*
+ +2 ^^     b
+ +3 ^ ^    
+ 0: ab
+  aaaab
+--->aaaab
+ +0 ^         a*
+ +2 ^   ^     b
+ +3 ^    ^    
+ 0: aaaab
+  aaaacb
+--->aaaacb
+ +0 ^          a*
+ +2 ^   ^      b
+ +0  ^         a*
+ +2  ^  ^      b
+ +0   ^        a*
+ +2   ^ ^      b
+ +0    ^       a*
+ +2    ^^      b
+ +0      ^     a*
+ +2      ^     b
+ +3      ^^    
+ 0: b
+
+/a*b/ICDZSS
+------------------------------------------------------------------
+        Bra
+        Callout 255 0 2
+        a*+
+        Callout 255 2 1
+        b
+        Callout 255 3 0
+        Ket
+        End
+------------------------------------------------------------------
+Capturing subpattern count = 0
+Options:
+No first char
+Need char = 'b'
+  ab
+--->ab
+ +0 ^      a*
+ +2 ^^     b
+ +3 ^ ^    
+ 0: ab
+  aaaab
+--->aaaab
+ +0 ^         a*
+ +2 ^   ^     b
+ +3 ^    ^    
+ 0: aaaab
+  aaaacb
+--->aaaacb
+ +0 ^          a*
+ +2 ^   ^      b
+ +0  ^         a*
+ +2  ^  ^      b
+ +0   ^        a*
+ +2   ^ ^      b
+ +0    ^       a*
+ +2    ^^      b
+ +0     ^      a*
+ +2     ^      b
+ +0      ^     a*
+ +2      ^     b
+ +3      ^^    
+ 0: b
+
+/a+b/ICDZ
+------------------------------------------------------------------
+        Bra
+        Callout 255 0 2
+        a++
+        Callout 255 2 1
+        b
+        Callout 255 3 0
+        Ket
+        End
+------------------------------------------------------------------
+Capturing subpattern count = 0
+Options:
+First char = 'a'
+Need char = 'b'
+  ab
+--->ab
+ +0 ^      a+
+ +2 ^^     b
+ +3 ^ ^    
+ 0: ab
+  aaaab
+--->aaaab
+ +0 ^         a+
+ +2 ^   ^     b
+ +3 ^    ^    
+ 0: aaaab
+  aaaacb
+--->aaaacb
+ +0 ^          a+
+ +2 ^   ^      b
+ +0  ^         a+
+ +2  ^  ^      b
+ +0   ^        a+
+ +2   ^ ^      b
+ +0    ^       a+
+ +2    ^^      b
+No match
+
+/(abc|def)x/ICDZS
+------------------------------------------------------------------
+        Bra
+        Callout 255 0 9
+        CBra 1
+        Callout 255 1 1
+        a
+        Callout 255 2 1
+        b
+        Callout 255 3 1
+        c
+        Callout 255 4 0
+        Alt
+        Callout 255 5 1
+        d
+        Callout 255 6 1
+        e
+        Callout 255 7 1
+        f
+        Callout 255 8 0
+        Ket
+        Callout 255 9 1
+        x
+        Callout 255 10 0
+        Ket
+        End
+------------------------------------------------------------------
+Capturing subpattern count = 1
+Options:
+No first char
+Need char = 'x'
+Subject length lower bound = 4
+Starting byte set: a d 
+  abcx
+--->abcx
+ +0 ^        (abc|def)
+ +1 ^        a
+ +2 ^^       b
+ +3 ^ ^      c
+ +4 ^  ^     |
+ +9 ^  ^     x
++10 ^   ^    
+ 0: abcx
+ 1: abc
+  defx
+--->defx
+ +0 ^        (abc|def)
+ +1 ^        a
+ +5 ^        d
+ +6 ^^       e
+ +7 ^ ^      f
+ +8 ^  ^     )
+ +9 ^  ^     x
++10 ^   ^    
+ 0: defx
+ 1: def
+  ** Failers 
+No match
+  abcdefzx
+--->abcdefzx
+ +0 ^            (abc|def)
+ +1 ^            a
+ +2 ^^           b
+ +3 ^ ^          c
+ +4 ^  ^         |
+ +9 ^  ^         x
+ +5 ^            d
+ +0    ^         (abc|def)
+ +1    ^         a
+ +5    ^         d
+ +6    ^^        e
+ +7    ^ ^       f
+ +8    ^  ^      )
+ +9    ^  ^      x
+No match
+
+/(abc|def)x/ICDZSS
+------------------------------------------------------------------
+        Bra
+        Callout 255 0 9
+        CBra 1
+        Callout 255 1 1
+        a
+        Callout 255 2 1
+        b
+        Callout 255 3 1
+        c
+        Callout 255 4 0
+        Alt
+        Callout 255 5 1
+        d
+        Callout 255 6 1
+        e
+        Callout 255 7 1
+        f
+        Callout 255 8 0
+        Ket
+        Callout 255 9 1
+        x
+        Callout 255 10 0
+        Ket
+        End
+------------------------------------------------------------------
+Capturing subpattern count = 1
+Options:
+No first char
+Need char = 'x'
+  abcx
+--->abcx
+ +0 ^        (abc|def)
+ +1 ^        a
+ +2 ^^       b
+ +3 ^ ^      c
+ +4 ^  ^     |
+ +9 ^  ^     x
++10 ^   ^    
+ 0: abcx
+ 1: abc
+  defx
+--->defx
+ +0 ^        (abc|def)
+ +1 ^        a
+ +5 ^        d
+ +6 ^^       e
+ +7 ^ ^      f
+ +8 ^  ^     )
+ +9 ^  ^     x
++10 ^   ^    
+ 0: defx
+ 1: def
+  ** Failers 
+No match
+  abcdefzx
+--->abcdefzx
+ +0 ^            (abc|def)
+ +1 ^            a
+ +2 ^^           b
+ +3 ^ ^          c
+ +4 ^  ^         |
+ +9 ^  ^         x
+ +5 ^            d
+ +0  ^           (abc|def)
+ +1  ^           a
+ +5  ^           d
+ +0   ^          (abc|def)
+ +1   ^          a
+ +5   ^          d
+ +0    ^         (abc|def)
+ +1    ^         a
+ +5    ^         d
+ +6    ^^        e
+ +7    ^ ^       f
+ +8    ^  ^      )
+ +9    ^  ^      x
+ +0     ^        (abc|def)
+ +1     ^        a
+ +5     ^        d
+ +0      ^       (abc|def)
+ +1      ^       a
+ +5      ^       d
+ +0       ^      (abc|def)
+ +1       ^      a
+ +5       ^      d
+ +0        ^     (abc|def)
+ +1        ^     a
+ +5        ^     d
+No match
+
+/(ab|cd){3,4}/IC
+Capturing subpattern count = 1
+Options:
+No first char
+No need char
+  ababab
+--->ababab
+ +0 ^          (ab|cd){3,4}
+ +1 ^          a
+ +2 ^^         b
+ +3 ^ ^        |
+ +1 ^ ^        a
+ +2 ^  ^       b
+ +3 ^   ^      |
+ +1 ^   ^      a
+ +2 ^    ^     b
+ +3 ^     ^    |
+ +1 ^     ^    a
+ +4 ^     ^    c
++12 ^     ^    
+ 0: ababab
+ 1: ab
+  abcdabcd
+--->abcdabcd
+ +0 ^            (ab|cd){3,4}
+ +1 ^            a
+ +2 ^^           b
+ +3 ^ ^          |
+ +1 ^ ^          a
+ +4 ^ ^          c
+ +5 ^  ^         d
+ +6 ^   ^        )
+ +1 ^   ^        a
+ +2 ^    ^       b
+ +3 ^     ^      |
+ +1 ^     ^      a
+ +4 ^     ^      c
+ +5 ^      ^     d
+ +6 ^       ^    )
++12 ^       ^    
+ 0: abcdabcd
+ 1: cd
+  abcdcdcdcdcd
+--->abcdcdcdcdcd
+ +0 ^                (ab|cd){3,4}
+ +1 ^                a
+ +2 ^^               b
+ +3 ^ ^              |
+ +1 ^ ^              a
+ +4 ^ ^              c
+ +5 ^  ^             d
+ +6 ^   ^            )
+ +1 ^   ^            a
+ +4 ^   ^            c
+ +5 ^    ^           d
+ +6 ^     ^          )
+ +1 ^     ^          a
+ +4 ^     ^          c
+ +5 ^      ^         d
+ +6 ^       ^        )
++12 ^       ^        
+ 0: abcdcdcd
+ 1: cd
+
+/([ab]{,4}c|xy)/ICDZS
+------------------------------------------------------------------
+        Bra
+        Callout 255 0 14
+        CBra 1
+        Callout 255 1 4
+        [ab]
+        Callout 255 5 1
+        {
+        Callout 255 6 1
+        ,
+        Callout 255 7 1
+        4
+        Callout 255 8 1
+        }
+        Callout 255 9 1
+        c
+        Callout 255 10 0
+        Alt
+        Callout 255 11 1
+        x
+        Callout 255 12 1
+        y
+        Callout 255 13 0
+        Ket
+        Callout 255 14 0
+        Ket
+        End
+------------------------------------------------------------------
+Capturing subpattern count = 1
+Options:
+No first char
+No need char
+Subject length lower bound = 2
+Starting byte set: a b x 
+    Note: that { does NOT introduce a quantifier
+--->Note: that { does NOT introduce a quantifier
+ +0         ^                                        ([ab]{,4}c|xy)
+ +1         ^                                        [ab]
+ +5         ^^                                       {
++11         ^                                        x
+ +0                                 ^                ([ab]{,4}c|xy)
+ +1                                 ^                [ab]
+ +5                                 ^^               {
++11                                 ^                x
+ +0                                     ^            ([ab]{,4}c|xy)
+ +1                                     ^            [ab]
+ +5                                     ^^           {
++11                                     ^            x
+No match
+
+/([ab]{,4}c|xy)/ICDZSS
+------------------------------------------------------------------
+        Bra
+        Callout 255 0 14
+        CBra 1
+        Callout 255 1 4
+        [ab]
+        Callout 255 5 1
+        {
+        Callout 255 6 1
+        ,
+        Callout 255 7 1
+        4
+        Callout 255 8 1
+        }
+        Callout 255 9 1
+        c
+        Callout 255 10 0
+        Alt
+        Callout 255 11 1
+        x
+        Callout 255 12 1
+        y
+        Callout 255 13 0
+        Ket
+        Callout 255 14 0
+        Ket
+        End
+------------------------------------------------------------------
+Capturing subpattern count = 1
+Options:
+No first char
+No need char
+    Note: that { does NOT introduce a quantifier
+--->Note: that { does NOT introduce a quantifier
+ +0 ^                                                ([ab]{,4}c|xy)
+ +1 ^                                                [ab]
++11 ^                                                x
+ +0  ^                                               ([ab]{,4}c|xy)
+ +1  ^                                               [ab]
++11  ^                                               x
+ +0   ^                                              ([ab]{,4}c|xy)
+ +1   ^                                              [ab]
++11   ^                                              x
+ +0    ^                                             ([ab]{,4}c|xy)
+ +1    ^                                             [ab]
++11    ^                                             x
+ +0     ^                                            ([ab]{,4}c|xy)
+ +1     ^                                            [ab]
++11     ^                                            x
+ +0      ^                                           ([ab]{,4}c|xy)
+ +1      ^                                           [ab]
++11      ^                                           x
+ +0       ^                                          ([ab]{,4}c|xy)
+ +1       ^                                          [ab]
++11       ^                                          x
+ +0        ^                                         ([ab]{,4}c|xy)
+ +1        ^                                         [ab]
++11        ^                                         x
+ +0         ^                                        ([ab]{,4}c|xy)
+ +1         ^                                        [ab]
+ +5         ^^                                       {
++11         ^                                        x
+ +0          ^                                       ([ab]{,4}c|xy)
+ +1          ^                                       [ab]
++11          ^                                       x
+ +0           ^                                      ([ab]{,4}c|xy)
+ +1           ^                                      [ab]
++11           ^                                      x
+ +0            ^                                     ([ab]{,4}c|xy)
+ +1            ^                                     [ab]
++11            ^                                     x
+ +0             ^                                    ([ab]{,4}c|xy)
+ +1             ^                                    [ab]
++11             ^                                    x
+ +0              ^                                   ([ab]{,4}c|xy)
+ +1              ^                                   [ab]
++11              ^                                   x
+ +0               ^                                  ([ab]{,4}c|xy)
+ +1               ^                                  [ab]
++11               ^                                  x
+ +0                ^                                 ([ab]{,4}c|xy)
+ +1                ^                                 [ab]
++11                ^                                 x
+ +0                 ^                                ([ab]{,4}c|xy)
+ +1                 ^                                [ab]
++11                 ^                                x
+ +0                  ^                               ([ab]{,4}c|xy)
+ +1                  ^                               [ab]
++11                  ^                               x
+ +0                   ^                              ([ab]{,4}c|xy)
+ +1                   ^                              [ab]
++11                   ^                              x
+ +0                    ^                             ([ab]{,4}c|xy)
+ +1                    ^                             [ab]
++11                    ^                             x
+ +0                     ^                            ([ab]{,4}c|xy)
+ +1                     ^                            [ab]
++11                     ^                            x
+ +0                      ^                           ([ab]{,4}c|xy)
+ +1                      ^                           [ab]
++11                      ^                           x
+ +0                       ^                          ([ab]{,4}c|xy)
+ +1                       ^                          [ab]
++11                       ^                          x
+ +0                        ^                         ([ab]{,4}c|xy)
+ +1                        ^                         [ab]
++11                        ^                         x
+ +0                         ^                        ([ab]{,4}c|xy)
+ +1                         ^                        [ab]
++11                         ^                        x
+ +0                          ^                       ([ab]{,4}c|xy)
+ +1                          ^                       [ab]
++11                          ^                       x
+ +0                           ^                      ([ab]{,4}c|xy)
+ +1                           ^                      [ab]
++11                           ^                      x
+ +0                            ^                     ([ab]{,4}c|xy)
+ +1                            ^                     [ab]
++11                            ^                     x
+ +0                             ^                    ([ab]{,4}c|xy)
+ +1                             ^                    [ab]
++11                             ^                    x
+ +0                              ^                   ([ab]{,4}c|xy)
+ +1                              ^                   [ab]
++11                              ^                   x
+ +0                               ^                  ([ab]{,4}c|xy)
+ +1                               ^                  [ab]
++11                               ^                  x
+ +0                                ^                 ([ab]{,4}c|xy)
+ +1                                ^                 [ab]
++11                                ^                 x
+ +0                                 ^                ([ab]{,4}c|xy)
+ +1                                 ^                [ab]
+ +5                                 ^^               {
++11                                 ^                x
+ +0                                  ^               ([ab]{,4}c|xy)
+ +1                                  ^               [ab]
++11                                  ^               x
+ +0                                   ^              ([ab]{,4}c|xy)
+ +1                                   ^              [ab]
++11                                   ^              x
+ +0                                    ^             ([ab]{,4}c|xy)
+ +1                                    ^             [ab]
++11                                    ^             x
+ +0                                     ^            ([ab]{,4}c|xy)
+ +1                                     ^            [ab]
+ +5                                     ^^           {
++11                                     ^            x
+ +0                                      ^           ([ab]{,4}c|xy)
+ +1                                      ^           [ab]
++11                                      ^           x
+ +0                                       ^          ([ab]{,4}c|xy)
+ +1                                       ^          [ab]
++11                                       ^          x
+ +0                                        ^         ([ab]{,4}c|xy)
+ +1                                        ^         [ab]
++11                                        ^         x
+ +0                                         ^        ([ab]{,4}c|xy)
+ +1                                         ^        [ab]
++11                                         ^        x
+ +0                                          ^       ([ab]{,4}c|xy)
+ +1                                          ^       [ab]
++11                                          ^       x
+ +0                                           ^      ([ab]{,4}c|xy)
+ +1                                           ^      [ab]
++11                                           ^      x
+ +0                                            ^     ([ab]{,4}c|xy)
+ +1                                            ^     [ab]
++11                                            ^     x
+ +0                                             ^    ([ab]{,4}c|xy)
+ +1                                             ^    [ab]
++11                                             ^    x
+No match
+
+/([ab]{1,4}c|xy){4,5}?123/ICDZ
+------------------------------------------------------------------
+        Bra
+        Callout 255 0 21
+        CBra 1
+        Callout 255 1 9
+        [ab]{1,4}
+        Callout 255 10 1
+        c
+        Callout 255 11 0
+        Alt
+        Callout 255 12 1
+        x
+        Callout 255 13 1
+        y
+        Callout 255 14 0
+        Ket
+        CBra 1
+        Callout 255 1 9
+        [ab]{1,4}
+        Callout 255 10 1
+        c
+        Callout 255 11 0
+        Alt
+        Callout 255 12 1
+        x
+        Callout 255 13 1
+        y
+        Callout 255 14 0
+        Ket
+        CBra 1
+        Callout 255 1 9
+        [ab]{1,4}
+        Callout 255 10 1
+        c
+        Callout 255 11 0
+        Alt
+        Callout 255 12 1
+        x
+        Callout 255 13 1
+        y
+        Callout 255 14 0
+        Ket
+        CBra 1
+        Callout 255 1 9
+        [ab]{1,4}
+        Callout 255 10 1
+        c
+        Callout 255 11 0
+        Alt
+        Callout 255 12 1
+        x
+        Callout 255 13 1
+        y
+        Callout 255 14 0
+        Ket
+        Braminzero
+        CBra 1
+        Callout 255 1 9
+        [ab]{1,4}
+        Callout 255 10 1
+        c
+        Callout 255 11 0
+        Alt
+        Callout 255 12 1
+        x
+        Callout 255 13 1
+        y
+        Callout 255 14 0
+        Ket
+        Callout 255 21 1
+        1
+        Callout 255 22 1
+        2
+        Callout 255 23 1
+        3
+        Callout 255 24 0
+        Ket
+        End
+------------------------------------------------------------------
+Capturing subpattern count = 1
+Options:
+No first char
+Need char = '3'
+    aacaacaacaacaac123
+--->aacaacaacaacaac123
+ +0 ^                      ([ab]{1,4}c|xy){4,5}?
+ +1 ^                      [ab]{1,4}
++10 ^ ^                    c
++11 ^  ^                   |
+ +1 ^  ^                   [ab]{1,4}
++10 ^    ^                 c
++11 ^     ^                |
+ +1 ^     ^                [ab]{1,4}
++10 ^       ^              c
++11 ^        ^             |
+ +1 ^        ^             [ab]{1,4}
++10 ^          ^           c
++11 ^           ^          |
++21 ^           ^          1
+ +1 ^           ^          [ab]{1,4}
++10 ^             ^        c
++11 ^              ^       |
++21 ^              ^       1
++22 ^               ^      2
++23 ^                ^     3
++24 ^                 ^    
+ 0: aacaacaacaacaac123
+ 1: aac
+
+/\b.*/I
+Capturing subpattern count = 0
+No options
+No first char
+No need char
+Max lookbehind = 1
+  ab cd\>1
+ 0:  cd
+
+/\b.*/Is
+Capturing subpattern count = 0
+Options: dotall
+No first char
+No need char
+Max lookbehind = 1
+  ab cd\>1
+ 0:  cd
+
+/(?!.bcd).*/I
+Capturing subpattern count = 0
+No options
+No first char
+No need char
+  Xbcd12345
+ 0: bcd12345
+
+/abcde/I
+Capturing subpattern count = 0
+No options
+First char = 'a'
+Need char = 'e'
+    ab\P
+Partial match: ab
+    abc\P
+Partial match: abc
+    abcd\P
+Partial match: abcd
+    abcde\P
+ 0: abcde
+    the quick brown abc\P
+Partial match: abc
+    ** Failers\P
+No match
+    the quick brown abxyz fox\P
+No match
+
+"^(0?[1-9]|[12][0-9]|3[01])/(0?[1-9]|1[012])/(20)?\d\d$"I
+Capturing subpattern count = 3
+Options: anchored
+No first char
+Need char = '/'
+    13/05/04\P
+ 0: 13/05/04
+ 1: 13
+ 2: 05
+    13/5/2004\P
+ 0: 13/5/2004
+ 1: 13
+ 2: 5
+ 3: 20
+    02/05/09\P
+ 0: 02/05/09
+ 1: 02
+ 2: 05
+    1\P
+Partial match: 1
+    1/2\P
+Partial match: 1/2
+    1/2/0\P
+Partial match: 1/2/0
+    1/2/04\P
+ 0: 1/2/04
+ 1: 1
+ 2: 2
+    0\P
+Partial match: 0
+    02/\P
+Partial match: 02/
+    02/0\P
+Partial match: 02/0
+    02/1\P
+Partial match: 02/1
+    ** Failers\P
+No match
+    \P
+No match
+    123\P
+No match
+    33/4/04\P
+No match
+    3/13/04\P
+No match
+    0/1/2003\P
+No match
+    0/\P
+No match
+    02/0/\P
+No match
+    02/13\P
+No match
+
+/0{0,2}ABC/I
+Capturing subpattern count = 0
+No options
+No first char
+Need char = 'C'
+
+/\d{3,}ABC/I
+Capturing subpattern count = 0
+No options
+No first char
+Need char = 'C'
+
+/\d*ABC/I
+Capturing subpattern count = 0
+No options
+No first char
+Need char = 'C'
+
+/[abc]+DE/I
+Capturing subpattern count = 0
+No options
+No first char
+Need char = 'E'
+
+/[abc]?123/I
+Capturing subpattern count = 0
+No options
+No first char
+Need char = '3'
+    123\P
+ 0: 123
+    a\P
+Partial match: a
+    b\P
+Partial match: b
+    c\P
+Partial match: c
+    c12\P
+Partial match: c12
+    c123\P
+ 0: c123
+
+/^(?:\d){3,5}X/I
+Capturing subpattern count = 0
+Options: anchored
+No first char
+Need char = 'X'
+    1\P
+Partial match: 1
+    123\P
+Partial match: 123
+    123X
+ 0: 123X
+    1234\P
+Partial match: 1234
+    1234X
+ 0: 1234X
+    12345\P
+Partial match: 12345
+    12345X
+ 0: 12345X
+    *** Failers
+No match
+    1X
+No match
+    123456\P
+No match
+
+/abc/IS>testsavedregex
+Capturing subpattern count = 0
+No options
+First char = 'a'
+Need char = 'c'
+Subject length lower bound = 3
+No set of starting bytes
+Compiled pattern written to testsavedregex
+Study data written to testsavedregex
+<testsavedregex
+Compiled pattern loaded from testsavedregex
+Study data loaded from testsavedregex
+    abc
+ 0: abc
+    ** Failers
+No match
+    bca
+No match
+
+/abc/ISS>testsavedregex
+Capturing subpattern count = 0
+No options
+First char = 'a'
+Need char = 'c'
+Compiled pattern written to testsavedregex
+<testsavedregex
+Compiled pattern loaded from testsavedregex
+No study data
+    abc
+ 0: abc
+    ** Failers
+No match
+    bca
+No match
+
+/abc/IFS>testsavedregex
+Capturing subpattern count = 0
+No options
+First char = 'a'
+Need char = 'c'
+Subject length lower bound = 3
+No set of starting bytes
+Compiled pattern written to testsavedregex
+Study data written to testsavedregex
+<testsavedregex
+Compiled pattern (byte-inverted) loaded from testsavedregex
+Study data loaded from testsavedregex
+    abc
+ 0: abc
+    ** Failers
+No match
+    bca
+No match
+
+/abc/IFSS>testsavedregex
+Capturing subpattern count = 0
+No options
+First char = 'a'
+Need char = 'c'
+Compiled pattern written to testsavedregex
+<testsavedregex
+Compiled pattern (byte-inverted) loaded from testsavedregex
+No study data
+    abc
+ 0: abc
+    ** Failers
+No match
+    bca
+No match
+
+/(a|b)/IS>testsavedregex
+Capturing subpattern count = 1
+No options
+No first char
+No need char
+Subject length lower bound = 1
+Starting byte set: a b 
+Compiled pattern written to testsavedregex
+Study data written to testsavedregex
+<testsavedregex
+Compiled pattern loaded from testsavedregex
+Study data loaded from testsavedregex
+    abc
+ 0: a
+ 1: a
+    ** Failers
+ 0: a
+ 1: a
+    def
+No match
+
+/(a|b)/ISS>testsavedregex
+Capturing subpattern count = 1
+No options
+No first char
+No need char
+Compiled pattern written to testsavedregex
+<testsavedregex
+Compiled pattern loaded from testsavedregex
+No study data
+    abc
+ 0: a
+ 1: a
+    ** Failers
+ 0: a
+ 1: a
+    def
+No match
+
+/(a|b)/ISF>testsavedregex
+Capturing subpattern count = 1
+No options
+No first char
+No need char
+Subject length lower bound = 1
+Starting byte set: a b 
+Compiled pattern written to testsavedregex
+Study data written to testsavedregex
+<testsavedregex
+Compiled pattern (byte-inverted) loaded from testsavedregex
+Study data loaded from testsavedregex
+    abc
+ 0: a
+ 1: a
+    ** Failers
+ 0: a
+ 1: a
+    def
+No match
+
+/(a|b)/ISSF>testsavedregex
+Capturing subpattern count = 1
+No options
+No first char
+No need char
+Compiled pattern written to testsavedregex
+<testsavedregex
+Compiled pattern (byte-inverted) loaded from testsavedregex
+No study data
+    abc
+ 0: a
+ 1: a
+    ** Failers
+ 0: a
+ 1: a
+    def
+No match
+
+~<(\w+)/?>(.)*</(\1)>~smgI
+Capturing subpattern count = 3
+Max back reference = 1
+Options: multiline dotall
+First char = '<'
+Need char = '>'
+    \J1024<!DOCTYPE seite SYSTEM "http://www.lco.lineas.de/xmlCms.dtd">\n<seite>\n<dokumenteninformation>\n<seitentitel>Partner der LCO</seitentitel>\n<sprache>de</sprache>\n<seitenbeschreibung>Partner der LINEAS Consulting\nGmbH</seitenbeschreibung>\n<schluesselworte>LINEAS Consulting GmbH Hamburg\nPartnerfirmen</schluesselworte>\n<revisit>30 days</revisit>\n<robots>index,follow</robots>\n<menueinformation>\n<aktiv>ja</aktiv>\n<menueposition>3</menueposition>\n<menuetext>Partner</menuetext>\n</menueinformation>\n<lastedited>\n<autor>LCO</autor>\n<firma>LINEAS Consulting</firma>\n<datum>15.10.2003</datum>\n</lastedited>\n</dokumenteninformation>\n<inhalt>\n\n<absatzueberschrift>Die Partnerfirmen der LINEAS Consulting\nGmbH</absatzueberschrift>\n\n<absatz><link ziel="http://www.ca.com/" zielfenster="_blank">\n<bild name="logo_ca.gif" rahmen="no"/></link> <link\nziel="http://www.ey.com/" zielfenster="_blank"><bild\nname="logo_euy.gif" rahmen="no"/></link>\n</absatz>\n\n<absatz><link ziel="http://www.cisco.de/" zielfenster="_blank">\n<bild name="logo_cisco.gif" rahmen="ja"/></link></absatz>\n\n<absatz><link ziel="http://www.atelion.de/"\nzielfenster="_blank"><bild\nname="logo_atelion.gif" rahmen="no"/></link>\n</absatz>\n\n<absatz><link ziel="http://www.line-information.de/"\nzielfenster="_blank">\n<bild name="logo_line_information.gif" rahmen="no"/></link>\n</absatz>\n\n<absatz><bild name="logo_aw.gif" rahmen="no"/></absatz>\n\n<absatz><link ziel="http://www.incognis.de/"\nzielfenster="_blank"><bild\nname="logo_incognis.gif" rahmen="no"/></link></absatz>\n\n<absatz><link ziel="http://www.addcraft.com/"\nzielfenster="_blank"><bild\nname="logo_addcraft.gif" rahmen="no"/></link></absatz>\n\n<absatz><link ziel="http://www.comendo.com/"\nzielfenster="_blank"><bild\nname="logo_comendo.gif" rahmen="no"/></link></absatz>\n\n</inhalt>\n</seite>
+ 0: <seite>\x0a<dokumenteninformation>\x0a<seitentitel>Partner der LCO</seitentitel>\x0a<sprache>de</sprache>\x0a<seitenbeschreibung>Partner der LINEAS Consulting\x0aGmbH</seitenbeschreibung>\x0a<schluesselworte>LINEAS Consulting GmbH Hamburg\x0aPartnerfirmen</schluesselworte>\x0a<revisit>30 days</revisit>\x0a<robots>index,follow</robots>\x0a<menueinformation>\x0a<aktiv>ja</aktiv>\x0a<menueposition>3</menueposition>\x0a<menuetext>Partner</menuetext>\x0a</menueinformation>\x0a<lastedited>\x0a<autor>LCO</autor>\x0a<firma>LINEAS Consulting</firma>\x0a<datum>15.10.2003</datum>\x0a</lastedited>\x0a</dokumenteninformation>\x0a<inhalt>\x0a\x0a<absatzueberschrift>Die Partnerfirmen der LINEAS Consulting\x0aGmbH</absatzueberschrift>\x0a\x0a<absatz><link ziel="http://www.ca.com/" zielfenster="_blank">\x0a<bild name="logo_ca.gif" rahmen="no"/></link> <link\x0aziel="http://www.ey.com/" zielfenster="_blank"><bild\x0aname="logo_euy.gif" rahmen="no"/></link>\x0a</absatz>\x0a\x0a<absatz><link ziel="http://www.cisco.de/" zielfenster="_blank">\x0a<bild name="logo_cisco.gif" rahmen="ja"/></link></absatz>\x0a\x0a<absatz><link ziel="http://www.atelion.de/"\x0azielfenster="_blank"><bild\x0aname="logo_atelion.gif" rahmen="no"/></link>\x0a</absatz>\x0a\x0a<absatz><link ziel="http://www.line-information.de/"\x0azielfenster="_blank">\x0a<bild name="logo_line_information.gif" rahmen="no"/></link>\x0a</absatz>\x0a\x0a<absatz><bild name="logo_aw.gif" rahmen="no"/></absatz>\x0a\x0a<absatz><link ziel="http://www.incognis.de/"\x0azielfenster="_blank"><bild\x0aname="logo_incognis.gif" rahmen="no"/></link></absatz>\x0a\x0a<absatz><link ziel="http://www.addcraft.com/"\x0azielfenster="_blank"><bild\x0aname="logo_addcraft.gif" rahmen="no"/></link></absatz>\x0a\x0a<absatz><link ziel="http://www.comendo.com/"\x0azielfenster="_blank"><bild\x0aname="logo_comendo.gif" rahmen="no"/></link></absatz>\x0a\x0a</inhalt>\x0a</seite>
+ 1: seite
+ 2: \x0a
+ 3: seite
+
+/^a/IF
+Capturing subpattern count = 0
+Options: anchored
+No first char
+No need char
+
+/line\nbreak/I
+Capturing subpattern count = 0
+Contains explicit CR or LF match
+No options
+First char = 'l'
+Need char = 'k'
+    this is a line\nbreak
+ 0: line\x0abreak
+    line one\nthis is a line\nbreak in the second line
+ 0: line\x0abreak
+
+/line\nbreak/If
+Capturing subpattern count = 0
+Contains explicit CR or LF match
+Options: firstline
+First char = 'l'
+Need char = 'k'
+    this is a line\nbreak
+ 0: line\x0abreak
+    ** Failers
+No match
+    line one\nthis is a line\nbreak in the second line
+No match
+
+/line\nbreak/Imf
+Capturing subpattern count = 0
+Contains explicit CR or LF match
+Options: multiline firstline
+First char = 'l'
+Need char = 'k'
+    this is a line\nbreak
+ 0: line\x0abreak
+    ** Failers
+No match
+    line one\nthis is a line\nbreak in the second line
+No match
+
+/(?i)(?-i)AbCd/I
+Capturing subpattern count = 0
+No options
+First char = 'A'
+Need char = 'd'
+    AbCd
+ 0: AbCd
+    ** Failers
+No match
+    abcd
+No match
+
+/a{11111111111111111111}/I
+Failed: number too big in {} quantifier at offset 22
+
+/(){64294967295}/I
+Failed: number too big in {} quantifier at offset 14
+
+/(){2,4294967295}/I
+Failed: number too big in {} quantifier at offset 15
+
+"(?i:a)(?i:b)(?i:c)(?i:d)(?i:e)(?i:f)(?i:g)(?i:h)(?i:i)(?i:j)(k)(?i:l)A\1B"I
+Capturing subpattern count = 1
+Max back reference = 1
+No options
+First char = 'a' (caseless)
+Need char = 'B'
+    abcdefghijklAkB
+ 0: abcdefghijklAkB
+ 1: k
+
+"(?P<n0>a)(?P<n1>b)(?P<n2>c)(?P<n3>d)(?P<n4>e)(?P<n5>f)(?P<n6>g)(?P<n7>h)(?P<n8>i)(?P<n9>j)(?P<n10>k)(?P<n11>l)A\11B"I
+Capturing subpattern count = 12
+Max back reference = 11
+Named capturing subpatterns:
+  n0    1
+  n1    2
+  n10  11
+  n11  12
+  n2    3
+  n3    4
+  n4    5
+  n5    6
+  n6    7
+  n7    8
+  n8    9
+  n9   10
+No options
+First char = 'a'
+Need char = 'B'
+    abcdefghijklAkB
+ 0: abcdefghijklAkB
+ 1: a
+ 2: b
+ 3: c
+ 4: d
+ 5: e
+ 6: f
+ 7: g
+ 8: h
+ 9: i
+10: j
+11: k
+12: l
+
+"(a)(b)(c)(d)(e)(f)(g)(h)(i)(j)(k)(l)A\11B"I
+Capturing subpattern count = 12
+Max back reference = 11
+No options
+First char = 'a'
+Need char = 'B'
+    abcdefghijklAkB
+ 0: abcdefghijklAkB
+ 1: a
+ 2: b
+ 3: c
+ 4: d
+ 5: e
+ 6: f
+ 7: g
+ 8: h
+ 9: i
+10: j
+11: k
+12: l
+
+"(?P<name0>a)(?P<name1>a)(?P<name2>a)(?P<name3>a)(?P<name4>a)(?P<name5>a)(?P<name6>a)(?P<name7>a)(?P<name8>a)(?P<name9>a)(?P<name10>a)(?P<name11>a)(?P<name12>a)(?P<name13>a)(?P<name14>a)(?P<name15>a)(?P<name16>a)(?P<name17>a)(?P<name18>a)(?P<name19>a)(?P<name20>a)(?P<name21>a)(?P<name22>a)(?P<name23>a)(?P<name24>a)(?P<name25>a)(?P<name26>a)(?P<name27>a)(?P<name28>a)(?P<name29>a)(?P<name30>a)(?P<name31>a)(?P<name32>a)(?P<name33>a)(?P<name34>a)(?P<name35>a)(?P<name36>a)(?P<name37>a)(?P<name38>a)(?P<name39>a)(?P<name40>a)(?P<name41>a)(?P<name42>a)(?P<name43>a)(?P<name44>a)(?P<name45>a)(?P<name46>a)(?P<name47>a)(?P<name48>a)(?P<name49>a)(?P<name50>a)(?P<name51>a)(?P<name52>a)(?P<name53>a)(?P<name54>a)(?P<name55>a)(?P<name56>a)(?P<name57>a)(?P<name58>a)(?P<name59>a)(?P<name60>a)(?P<name61>a)(?P<name62>a)(?P<name63>a)(?P<name64>a)(?P<name65>a)(?P<name66>a)(?P<name67>a)(?P<name68>a)(?P<name69>a)(?P<name70>a)(?P<name71>a)(?P<name72>a)(?P<name73>a)(?P<name74>a)(?P<name75>a)(?P<name76>a)(?P<name77>a)(?P<name78>a)(?P<name79>a)(?P<name80>a)(?P<name81>a)(?P<name82>a)(?P<name83>a)(?P<name84>a)(?P<name85>a)(?P<name86>a)(?P<name87>a)(?P<name88>a)(?P<name89>a)(?P<name90>a)(?P<name91>a)(?P<name92>a)(?P<name93>a)(?P<name94>a)(?P<name95>a)(?P<name96>a)(?P<name97>a)(?P<name98>a)(?P<name99>a)(?P<name100>a)"I
+Capturing subpattern count = 101
+Named capturing subpatterns:
+  name0     1
+  name1     2
+  name10   11
+  name100 101
+  name11   12
+  name12   13
+  name13   14
+  name14   15
+  name15   16
+  name16   17
+  name17   18
+  name18   19
+  name19   20
+  name2     3
+  name20   21
+  name21   22
+  name22   23
+  name23   24
+  name24   25
+  name25   26
+  name26   27
+  name27   28
+  name28   29
+  name29   30
+  name3     4
+  name30   31
+  name31   32
+  name32   33
+  name33   34
+  name34   35
+  name35   36
+  name36   37
+  name37   38
+  name38   39
+  name39   40
+  name4     5
+  name40   41
+  name41   42
+  name42   43
+  name43   44
+  name44   45
+  name45   46
+  name46   47
+  name47   48
+  name48   49
+  name49   50
+  name5     6
+  name50   51
+  name51   52
+  name52   53
+  name53   54
+  name54   55
+  name55   56
+  name56   57
+  name57   58
+  name58   59
+  name59   60
+  name6     7
+  name60   61
+  name61   62
+  name62   63
+  name63   64
+  name64   65
+  name65   66
+  name66   67
+  name67   68
+  name68   69
+  name69   70
+  name7     8
+  name70   71
+  name71   72
+  name72   73
+  name73   74
+  name74   75
+  name75   76
+  name76   77
+  name77   78
+  name78   79
+  name79   80
+  name8     9
+  name80   81
+  name81   82
+  name82   83
+  name83   84
+  name84   85
+  name85   86
+  name86   87
+  name87   88
+  name88   89
+  name89   90
+  name9    10
+  name90   91
+  name91   92
+  name92   93
+  name93   94
+  name94   95
+  name95   96
+  name96   97
+  name97   98
+  name98   99
+  name99  100
+No options
+First char = 'a'
+Need char = 'a'
+    aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+Matched, but too many substrings
+ 0: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+ 1: a
+ 2: a
+ 3: a
+ 4: a
+ 5: a
+ 6: a
+ 7: a
+ 8: a
+ 9: a
+10: a
+11: a
+12: a
+13: a
+14: a
+
+"(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)"I
+Capturing subpattern count = 101
+No options
+First char = 'a'
+Need char = 'a'
+    aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+Matched, but too many substrings
+ 0: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+ 1: a
+ 2: a
+ 3: a
+ 4: a
+ 5: a
+ 6: a
+ 7: a
+ 8: a
+ 9: a
+10: a
+11: a
+12: a
+13: a
+14: a
+
+/[^()]*(?:\((?R)\)[^()]*)*/I
+Capturing subpattern count = 0
+No options
+No first char
+No need char
+    (this(and)that
+ 0: 
+    (this(and)that)
+ 0: (this(and)that)
+    (this(and)that)stuff
+ 0: (this(and)that)stuff
+
+/[^()]*(?:\((?>(?R))\)[^()]*)*/I
+Capturing subpattern count = 0
+No options
+No first char
+No need char
+    (this(and)that
+ 0: 
+    (this(and)that)
+ 0: (this(and)that)
+
+/[^()]*(?:\((?R)\))*[^()]*/I
+Capturing subpattern count = 0
+No options
+No first char
+No need char
+    (this(and)that
+ 0: 
+    (this(and)that)
+ 0: (this(and)that)
+
+/(?:\((?R)\))*[^()]*/I
+Capturing subpattern count = 0
+No options
+No first char
+No need char
+    (this(and)that
+ 0: 
+    (this(and)that)
+ 0: 
+    ((this))
+ 0: ((this))
+
+/(?:\((?R)\))|[^()]*/I
+Capturing subpattern count = 0
+No options
+No first char
+No need char
+    (this(and)that
+ 0: 
+    (this(and)that)
+ 0: 
+    (this)
+ 0: (this)
+    ((this))
+ 0: ((this))
+
+/\x{0000ff}/I
+Capturing subpattern count = 0
+No options
+First char = \xff
+No need char
+
+/^((?P<A>a1)|(?P<A>a2)b)/I
+Failed: two named subpatterns have the same name at offset 17
+
+/^((?P<A>a1)|(?P<A>a2)b)/IJ
+Capturing subpattern count = 3
+Named capturing subpatterns:
+  A   2
+  A   3
+Options: anchored dupnames
+No first char
+No need char
+    a1b\CA
+ 0: a1
+ 1: a1
+ 2: a1
+  C a1 (2) A
+    a2b\CA
+ 0: a2b
+ 1: a2b
+ 2: <unset>
+ 3: a2
+  C a2 (2) A
+    ** Failers
+No match
+    a1b\CZ\CA
+no parentheses with name "Z"
+ 0: a1
+ 1: a1
+ 2: a1
+copy substring Z failed -7
+  C a1 (2) A
+
+/^(?P<A>a)(?P<A>b)/IJ
+Capturing subpattern count = 2
+Named capturing subpatterns:
+  A   1
+  A   2
+Options: anchored dupnames
+No first char
+No need char
+    ab\CA
+ 0: ab
+ 1: a
+ 2: b
+  C a (1) A
+
+/^(?P<A>a)(?P<A>b)|cd/IJ
+Capturing subpattern count = 2
+Named capturing subpatterns:
+  A   1
+  A   2
+Options: dupnames
+No first char
+No need char
+    ab\CA
+ 0: ab
+ 1: a
+ 2: b
+  C a (1) A
+    cd\CA
+ 0: cd
+copy substring A failed -7
+
+/^(?P<A>a)(?P<A>b)|cd(?P<A>ef)(?P<A>gh)/IJ
+Capturing subpattern count = 4
+Named capturing subpatterns:
+  A   1
+  A   2
+  A   3
+  A   4
+Options: dupnames
+No first char
+No need char
+    cdefgh\CA
+ 0: cdefgh
+ 1: <unset>
+ 2: <unset>
+ 3: ef
+ 4: gh
+  C ef (2) A
+
+/^((?P<A>a1)|(?P<A>a2)b)/IJ
+Capturing subpattern count = 3
+Named capturing subpatterns:
+  A   2
+  A   3
+Options: anchored dupnames
+No first char
+No need char
+    a1b\GA
+ 0: a1
+ 1: a1
+ 2: a1
+  G a1 (2) A
+    a2b\GA
+ 0: a2b
+ 1: a2b
+ 2: <unset>
+ 3: a2
+  G a2 (2) A
+    ** Failers
+No match
+    a1b\GZ\GA
+no parentheses with name "Z"
+ 0: a1
+ 1: a1
+ 2: a1
+get substring Z failed -7
+  G a1 (2) A
+
+/^(?P<A>a)(?P<A>b)/IJ
+Capturing subpattern count = 2
+Named capturing subpatterns:
+  A   1
+  A   2
+Options: anchored dupnames
+No first char
+No need char
+    ab\GA
+ 0: ab
+ 1: a
+ 2: b
+  G a (1) A
+
+/^(?P<A>a)(?P<A>b)|cd/IJ
+Capturing subpattern count = 2
+Named capturing subpatterns:
+  A   1
+  A   2
+Options: dupnames
+No first char
+No need char
+    ab\GA
+ 0: ab
+ 1: a
+ 2: b
+  G a (1) A
+    cd\GA
+ 0: cd
+get substring A failed -7
+
+/^(?P<A>a)(?P<A>b)|cd(?P<A>ef)(?P<A>gh)/IJ
+Capturing subpattern count = 4
+Named capturing subpatterns:
+  A   1
+  A   2
+  A   3
+  A   4
+Options: dupnames
+No first char
+No need char
+    cdefgh\GA
+ 0: cdefgh
+ 1: <unset>
+ 2: <unset>
+ 3: ef
+ 4: gh
+  G ef (2) A
+
+/(?J)^((?P<A>a1)|(?P<A>a2)b)/I
+Capturing subpattern count = 3
+Named capturing subpatterns:
+  A   2
+  A   3
+Options: anchored dupnames
+Duplicate name status changes
+No first char
+No need char
+    a1b\CA
+ 0: a1
+ 1: a1
+ 2: a1
+  C a1 (2) A
+    a2b\CA
+ 0: a2b
+ 1: a2b
+ 2: <unset>
+ 3: a2
+  C a2 (2) A
+
+/^(?P<A>a) (?J:(?P<B>b)(?P<B>c)) (?P<A>d)/I
+Failed: two named subpatterns have the same name at offset 37
+
+/ In this next test, J is not set at the outer level; consequently it isn't
+set in the pattern's options; consequently pcre_get_named_substring() produces
+a random value. /Ix
+Capturing subpattern count = 1
+Options: extended
+First char = 'I'
+Need char = 'e'
+
+/^(?P<A>a) (?J:(?P<B>b)(?P<B>c)) (?P<C>d)/I
+Capturing subpattern count = 4
+Named capturing subpatterns:
+  A   1
+  B   2
+  B   3
+  C   4
+Options: anchored
+Duplicate name status changes
+No first char
+No need char
+    a bc d\CA\CB\CC
+ 0: a bc d
+ 1: a
+ 2: b
+ 3: c
+ 4: d
+  C a (1) A
+  C b (1) B
+  C d (1) C
+
+/^(?P<A>a)?(?(A)a|b)/I
+Capturing subpattern count = 1
+Named capturing subpatterns:
+  A   1
+Options: anchored
+No first char
+No need char
+    aabc
+ 0: aa
+ 1: a
+    bc
+ 0: b
+    ** Failers
+No match
+    abc
+No match
+
+/(?:(?(ZZ)a|b)(?P<ZZ>X))+/I
+Capturing subpattern count = 1
+Named capturing subpatterns:
+  ZZ   1
+No options
+No first char
+Need char = 'X'
+    bXaX
+ 0: bXaX
+ 1: X
+
+/(?:(?(2y)a|b)(X))+/I
+Failed: reference to non-existent subpattern at offset 9
+
+/(?:(?(ZA)a|b)(?P<ZZ>X))+/I
+Failed: reference to non-existent subpattern at offset 9
+
+/(?:(?(ZZ)a|b)(?(ZZ)a|b)(?P<ZZ>X))+/I
+Capturing subpattern count = 1
+Named capturing subpatterns:
+  ZZ   1
+No options
+No first char
+Need char = 'X'
+    bbXaaX
+ 0: bbXaaX
+ 1: X
+
+/(?:(?(ZZ)a|\(b\))\\(?P<ZZ>X))+/I
+Capturing subpattern count = 1
+Named capturing subpatterns:
+  ZZ   1
+No options
+No first char
+Need char = 'X'
+    (b)\\Xa\\X
+ 0: (b)\Xa\X
+ 1: X
+
+/(?P<ABC/I
+Failed: syntax error in subpattern name (missing terminator) at offset 7
+
+/(?:(?(A)(?P=A)a|b)(?P<A>X|Y))+/I
+Capturing subpattern count = 1
+Max back reference = 1
+Named capturing subpatterns:
+  A   1
+No options
+No first char
+No need char
+    bXXaYYaY
+ 0: bXXaYYaY
+ 1: Y
+    bXYaXXaX
+ 0: bX
+ 1: X
+
+/()()()()()()()()()(?:(?(A)(?P=A)a|b)(?P<A>X|Y))+/I
+Capturing subpattern count = 10
+Max back reference = 10
+Named capturing subpatterns:
+  A  10
+No options
+No first char
+No need char
+    bXXaYYaY
+ 0: bXXaYYaY
+ 1: 
+ 2: 
+ 3: 
+ 4: 
+ 5: 
+ 6: 
+ 7: 
+ 8: 
+ 9: 
+10: Y
+
+/\s*,\s*/IS
+Capturing subpattern count = 0
+No options
+No first char
+Need char = ','
+Subject length lower bound = 1
+Starting byte set: \x09 \x0a \x0c \x0d \x20 , 
+    \x0b,\x0b
+ 0: ,
+    \x0c,\x0d
+ 0: \x0c,\x0d
+
+/^abc/Im
+Capturing subpattern count = 0
+Options: multiline
+First char at start or follows newline
+Need char = 'c'
+    xyz\nabc
+ 0: abc
+    xyz\nabc\<lf>
+ 0: abc
+    xyz\r\nabc\<lf>
+ 0: abc
+    xyz\rabc\<cr>
+ 0: abc
+    xyz\r\nabc\<crlf>
+ 0: abc
+    ** Failers
+No match
+    xyz\nabc\<cr>
+No match
+    xyz\r\nabc\<cr>
+No match
+    xyz\nabc\<crlf>
+No match
+    xyz\rabc\<crlf>
+No match
+    xyz\rabc\<lf>
+No match
+
+/abc$/Im<lf>
+Capturing subpattern count = 0
+Options: multiline
+Forced newline sequence: LF
+First char = 'a'
+Need char = 'c'
+    xyzabc
+ 0: abc
+    xyzabc\n
+ 0: abc
+    xyzabc\npqr
+ 0: abc
+    xyzabc\r\<cr>
+ 0: abc
+    xyzabc\rpqr\<cr>
+ 0: abc
+    xyzabc\r\n\<crlf>
+ 0: abc
+    xyzabc\r\npqr\<crlf>
+ 0: abc
+    ** Failers
+No match
+    xyzabc\r
+No match
+    xyzabc\rpqr
+No match
+    xyzabc\r\n
+No match
+    xyzabc\r\npqr
+No match
+
+/^abc/Im<cr>
+Capturing subpattern count = 0
+Options: multiline
+Forced newline sequence: CR
+First char at start or follows newline
+Need char = 'c'
+    xyz\rabcdef
+ 0: abc
+    xyz\nabcdef\<lf>
+ 0: abc
+    ** Failers
+No match
+    xyz\nabcdef
+No match
+
+/^abc/Im<lf>
+Capturing subpattern count = 0
+Options: multiline
+Forced newline sequence: LF
+First char at start or follows newline
+Need char = 'c'
+    xyz\nabcdef
+ 0: abc
+    xyz\rabcdef\<cr>
+ 0: abc
+    ** Failers
+No match
+    xyz\rabcdef
+No match
+
+/^abc/Im<crlf>
+Capturing subpattern count = 0
+Options: multiline
+Forced newline sequence: CRLF
+First char at start or follows newline
+Need char = 'c'
+    xyz\r\nabcdef
+ 0: abc
+    xyz\rabcdef\<cr>
+ 0: abc
+    ** Failers
+No match
+    xyz\rabcdef
+No match
+
+/^abc/Im<bad>
+Unknown newline type at: <bad>
+
+
+/abc/I
+Capturing subpattern count = 0
+No options
+First char = 'a'
+Need char = 'c'
+    xyz\rabc\<bad>
+Unknown newline type at: <bad>
+    abc
+ 0: abc
+
+/.*/I<lf>
+Capturing subpattern count = 0
+Options:
+Forced newline sequence: LF
+First char at start or follows newline
+No need char
+    abc\ndef
+ 0: abc
+    abc\rdef
+ 0: abc\x0ddef
+    abc\r\ndef
+ 0: abc\x0d
+    \<cr>abc\ndef
+ 0: abc\x0adef
+    \<cr>abc\rdef
+ 0: abc
+    \<cr>abc\r\ndef
+ 0: abc
+    \<crlf>abc\ndef
+ 0: abc\x0adef
+    \<crlf>abc\rdef
+ 0: abc\x0ddef
+    \<crlf>abc\r\ndef
+ 0: abc
+
+/\w+(.)(.)?def/Is
+Capturing subpattern count = 2
+Options: dotall
+No first char
+Need char = 'f'
+    abc\ndef
+ 0: abc\x0adef
+ 1: \x0a
+    abc\rdef
+ 0: abc\x0ddef
+ 1: \x0d
+    abc\r\ndef
+ 0: abc\x0d\x0adef
+ 1: \x0d
+ 2: \x0a
+
++((?:\s|//.*\\n|/[*](?:\\n|.)*?[*]/)*)+I
+Capturing subpattern count = 1
+No options
+No first char
+No need char
+   /* this is a C style comment */\M
+Minimum match() limit = 120
+Minimum match() recursion limit = 6
+ 0: /* this is a C style comment */
+ 1: /* this is a C style comment */
+
+/(?P<B>25[0-5]|2[0-4]\d|[01]?\d?\d)(?:\.(?P>B)){3}/I
+Capturing subpattern count = 1
+Named capturing subpatterns:
+  B   1
+No options
+No first char
+Need char = '.'
+
+/()()()()()()()()()()()()()()()()()()()()
+ ()()()()()()()()()()()()()()()()()()()()
+ ()()()()()()()()()()()()()()()()()()()()
+ ()()()()()()()()()()()()()()()()()()()()
+ ()()()()()()()()()()()()()()()()()()()()
+ (.(.))/Ix
+Capturing subpattern count = 102
+Options: extended
+No first char
+No need char
+    XY\O400
+ 0: XY
+ 1: 
+ 2: 
+ 3: 
+ 4: 
+ 5: 
+ 6: 
+ 7: 
+ 8: 
+ 9: 
+10: 
+11: 
+12: 
+13: 
+14: 
+15: 
+16: 
+17: 
+18: 
+19: 
+20: 
+21: 
+22: 
+23: 
+24: 
+25: 
+26: 
+27: 
+28: 
+29: 
+30: 
+31: 
+32: 
+33: 
+34: 
+35: 
+36: 
+37: 
+38: 
+39: 
+40: 
+41: 
+42: 
+43: 
+44: 
+45: 
+46: 
+47: 
+48: 
+49: 
+50: 
+51: 
+52: 
+53: 
+54: 
+55: 
+56: 
+57: 
+58: 
+59: 
+60: 
+61: 
+62: 
+63: 
+64: 
+65: 
+66: 
+67: 
+68: 
+69: 
+70: 
+71: 
+72: 
+73: 
+74: 
+75: 
+76: 
+77: 
+78: 
+79: 
+80: 
+81: 
+82: 
+83: 
+84: 
+85: 
+86: 
+87: 
+88: 
+89: 
+90: 
+91: 
+92: 
+93: 
+94: 
+95: 
+96: 
+97: 
+98: 
+99: 
+100: 
+101: XY
+102: Y
+
+/(a*b|(?i:c*(?-i)d))/IS
+Capturing subpattern count = 1
+No options
+No first char
+No need char
+Subject length lower bound = 1
+Starting byte set: C a b c d 
+
+/()[ab]xyz/IS
+Capturing subpattern count = 1
+No options
+No first char
+Need char = 'z'
+Subject length lower bound = 4
+Starting byte set: a b 
+
+/(|)[ab]xyz/IS
+Capturing subpattern count = 1
+No options
+No first char
+Need char = 'z'
+Subject length lower bound = 4
+Starting byte set: a b 
+
+/(|c)[ab]xyz/IS
+Capturing subpattern count = 1
+No options
+No first char
+Need char = 'z'
+Subject length lower bound = 4
+Starting byte set: a b c 
+
+/(|c?)[ab]xyz/IS
+Capturing subpattern count = 1
+No options
+No first char
+Need char = 'z'
+Subject length lower bound = 4
+Starting byte set: a b c 
+
+/(d?|c?)[ab]xyz/IS
+Capturing subpattern count = 1
+No options
+No first char
+Need char = 'z'
+Subject length lower bound = 4
+Starting byte set: a b c d 
+
+/(d?|c)[ab]xyz/IS
+Capturing subpattern count = 1
+No options
+No first char
+Need char = 'z'
+Subject length lower bound = 4
+Starting byte set: a b c d 
+
+/^a*b\d/DZ
+------------------------------------------------------------------
+        Bra
+        ^
+        a*+
+        b
+        \d
+        Ket
+        End
+------------------------------------------------------------------
+Capturing subpattern count = 0
+Options: anchored
+No first char
+Need char = 'b'
+
+/^a*+b\d/DZ
+------------------------------------------------------------------
+        Bra
+        ^
+        a*+
+        b
+        \d
+        Ket
+        End
+------------------------------------------------------------------
+Capturing subpattern count = 0
+Options: anchored
+No first char
+Need char = 'b'
+
+/^a*?b\d/DZ
+------------------------------------------------------------------
+        Bra
+        ^
+        a*+
+        b
+        \d
+        Ket
+        End
+------------------------------------------------------------------
+Capturing subpattern count = 0
+Options: anchored
+No first char
+Need char = 'b'
+
+/^a+A\d/DZ
+------------------------------------------------------------------
+        Bra
+        ^
+        a++
+        A
+        \d
+        Ket
+        End
+------------------------------------------------------------------
+Capturing subpattern count = 0
+Options: anchored
+No first char
+Need char = 'A'
+    aaaA5
+ 0: aaaA5
+    ** Failers
+No match
+    aaaa5
+No match
+
+/^a*A\d/IiDZ
+------------------------------------------------------------------
+        Bra
+        ^
+     /i a*
+     /i A
+        \d
+        Ket
+        End
+------------------------------------------------------------------
+Capturing subpattern count = 0
+Options: anchored caseless
+No first char
+Need char = 'A' (caseless)
+    aaaA5
+ 0: aaaA5
+    aaaa5
+ 0: aaaa5
+
+/(a*|b*)[cd]/IS
+Capturing subpattern count = 1
+No options
+No first char
+No need char
+Subject length lower bound = 1
+Starting byte set: a b c d 
+
+/(a+|b*)[cd]/IS
+Capturing subpattern count = 1
+No options
+No first char
+No need char
+Subject length lower bound = 1
+Starting byte set: a b c d 
+
+/(a*|b+)[cd]/IS
+Capturing subpattern count = 1
+No options
+No first char
+No need char
+Subject length lower bound = 1
+Starting byte set: a b c d 
+
+/(a+|b+)[cd]/IS
+Capturing subpattern count = 1
+No options
+No first char
+No need char
+Subject length lower bound = 2
+Starting byte set: a b 
+
+/((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((
+ ((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((
+ (((
+ a
+ ))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))
+ ))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))
+ )))
+/Ix
+Capturing subpattern count = 203
+Options: extended
+First char = 'a'
+No need char
+  large nest
+Matched, but too many substrings
+ 0: a
+ 1: a
+ 2: a
+ 3: a
+ 4: a
+ 5: a
+ 6: a
+ 7: a
+ 8: a
+ 9: a
+10: a
+11: a
+12: a
+13: a
+14: a
+
+/a*\d/BZ
+------------------------------------------------------------------
+        Bra
+        a*+
+        \d
+        Ket
+        End
+------------------------------------------------------------------
+
+/a*\D/BZ
+------------------------------------------------------------------
+        Bra
+        a*
+        \D
+        Ket
+        End
+------------------------------------------------------------------
+
+/0*\d/BZ
+------------------------------------------------------------------
+        Bra
+        0*
+        \d
+        Ket
+        End
+------------------------------------------------------------------
+
+/0*\D/BZ
+------------------------------------------------------------------
+        Bra
+        0*+
+        \D
+        Ket
+        End
+------------------------------------------------------------------
+
+/a*\s/BZ
+------------------------------------------------------------------
+        Bra
+        a*+
+        \s
+        Ket
+        End
+------------------------------------------------------------------
+
+/a*\S/BZ
+------------------------------------------------------------------
+        Bra
+        a*
+        \S
+        Ket
+        End
+------------------------------------------------------------------
+
+/ *\s/BZ
+------------------------------------------------------------------
+        Bra
+         *
+        \s
+        Ket
+        End
+------------------------------------------------------------------
+
+/ *\S/BZ
+------------------------------------------------------------------
+        Bra
+         *+
+        \S
+        Ket
+        End
+------------------------------------------------------------------
+
+/a*\w/BZ
+------------------------------------------------------------------
+        Bra
+        a*
+        \w
+        Ket
+        End
+------------------------------------------------------------------
+
+/a*\W/BZ
+------------------------------------------------------------------
+        Bra
+        a*+
+        \W
+        Ket
+        End
+------------------------------------------------------------------
+
+/=*\w/BZ
+------------------------------------------------------------------
+        Bra
+        =*+
+        \w
+        Ket
+        End
+------------------------------------------------------------------
+
+/=*\W/BZ
+------------------------------------------------------------------
+        Bra
+        =*
+        \W
+        Ket
+        End
+------------------------------------------------------------------
+
+/\d*a/BZ
+------------------------------------------------------------------
+        Bra
+        \d*+
+        a
+        Ket
+        End
+------------------------------------------------------------------
+
+/\d*2/BZ
+------------------------------------------------------------------
+        Bra
+        \d*
+        2
+        Ket
+        End
+------------------------------------------------------------------
+
+/\d*\d/BZ
+------------------------------------------------------------------
+        Bra
+        \d*
+        \d
+        Ket
+        End
+------------------------------------------------------------------
+
+/\d*\D/BZ
+------------------------------------------------------------------
+        Bra
+        \d*+
+        \D
+        Ket
+        End
+------------------------------------------------------------------
+
+/\d*\s/BZ
+------------------------------------------------------------------
+        Bra
+        \d*+
+        \s
+        Ket
+        End
+------------------------------------------------------------------
+
+/\d*\S/BZ
+------------------------------------------------------------------
+        Bra
+        \d*
+        \S
+        Ket
+        End
+------------------------------------------------------------------
+
+/\d*\w/BZ
+------------------------------------------------------------------
+        Bra
+        \d*
+        \w
+        Ket
+        End
+------------------------------------------------------------------
+
+/\d*\W/BZ
+------------------------------------------------------------------
+        Bra
+        \d*+
+        \W
+        Ket
+        End
+------------------------------------------------------------------
+
+/\D*a/BZ
+------------------------------------------------------------------
+        Bra
+        \D*
+        a
+        Ket
+        End
+------------------------------------------------------------------
+
+/\D*2/BZ
+------------------------------------------------------------------
+        Bra
+        \D*+
+        2
+        Ket
+        End
+------------------------------------------------------------------
+
+/\D*\d/BZ
+------------------------------------------------------------------
+        Bra
+        \D*+
+        \d
+        Ket
+        End
+------------------------------------------------------------------
+
+/\D*\D/BZ
+------------------------------------------------------------------
+        Bra
+        \D*
+        \D
+        Ket
+        End
+------------------------------------------------------------------
+
+/\D*\s/BZ
+------------------------------------------------------------------
+        Bra
+        \D*
+        \s
+        Ket
+        End
+------------------------------------------------------------------
+
+/\D*\S/BZ
+------------------------------------------------------------------
+        Bra
+        \D*
+        \S
+        Ket
+        End
+------------------------------------------------------------------
+
+/\D*\w/BZ
+------------------------------------------------------------------
+        Bra
+        \D*
+        \w
+        Ket
+        End
+------------------------------------------------------------------
+
+/\D*\W/BZ
+------------------------------------------------------------------
+        Bra
+        \D*
+        \W
+        Ket
+        End
+------------------------------------------------------------------
+
+/\s*a/BZ
+------------------------------------------------------------------
+        Bra
+        \s*+
+        a
+        Ket
+        End
+------------------------------------------------------------------
+
+/\s*2/BZ
+------------------------------------------------------------------
+        Bra
+        \s*+
+        2
+        Ket
+        End
+------------------------------------------------------------------
+
+/\s*\d/BZ
+------------------------------------------------------------------
+        Bra
+        \s*+
+        \d
+        Ket
+        End
+------------------------------------------------------------------
+
+/\s*\D/BZ
+------------------------------------------------------------------
+        Bra
+        \s*
+        \D
+        Ket
+        End
+------------------------------------------------------------------
+
+/\s*\s/BZ
+------------------------------------------------------------------
+        Bra
+        \s*
+        \s
+        Ket
+        End
+------------------------------------------------------------------
+
+/\s*\S/BZ
+------------------------------------------------------------------
+        Bra
+        \s*+
+        \S
+        Ket
+        End
+------------------------------------------------------------------
+
+/\s*\w/BZ
+------------------------------------------------------------------
+        Bra
+        \s*+
+        \w
+        Ket
+        End
+------------------------------------------------------------------
+
+/\s*\W/BZ
+------------------------------------------------------------------
+        Bra
+        \s*
+        \W
+        Ket
+        End
+------------------------------------------------------------------
+
+/\S*a/BZ
+------------------------------------------------------------------
+        Bra
+        \S*
+        a
+        Ket
+        End
+------------------------------------------------------------------
+
+/\S*2/BZ
+------------------------------------------------------------------
+        Bra
+        \S*
+        2
+        Ket
+        End
+------------------------------------------------------------------
+
+/\S*\d/BZ
+------------------------------------------------------------------
+        Bra
+        \S*
+        \d
+        Ket
+        End
+------------------------------------------------------------------
+
+/\S*\D/BZ
+------------------------------------------------------------------
+        Bra
+        \S*
+        \D
+        Ket
+        End
+------------------------------------------------------------------
+
+/\S*\s/BZ
+------------------------------------------------------------------
+        Bra
+        \S*+
+        \s
+        Ket
+        End
+------------------------------------------------------------------
+
+/\S*\S/BZ
+------------------------------------------------------------------
+        Bra
+        \S*
+        \S
+        Ket
+        End
+------------------------------------------------------------------
+
+/\S*\w/BZ
+------------------------------------------------------------------
+        Bra
+        \S*
+        \w
+        Ket
+        End
+------------------------------------------------------------------
+
+/\S*\W/BZ
+------------------------------------------------------------------
+        Bra
+        \S*
+        \W
+        Ket
+        End
+------------------------------------------------------------------
+
+/\w*a/BZ
+------------------------------------------------------------------
+        Bra
+        \w*
+        a
+        Ket
+        End
+------------------------------------------------------------------
+
+/\w*2/BZ
+------------------------------------------------------------------
+        Bra
+        \w*
+        2
+        Ket
+        End
+------------------------------------------------------------------
+
+/\w*\d/BZ
+------------------------------------------------------------------
+        Bra
+        \w*
+        \d
+        Ket
+        End
+------------------------------------------------------------------
+
+/\w*\D/BZ
+------------------------------------------------------------------
+        Bra
+        \w*
+        \D
+        Ket
+        End
+------------------------------------------------------------------
+
+/\w*\s/BZ
+------------------------------------------------------------------
+        Bra
+        \w*+
+        \s
+        Ket
+        End
+------------------------------------------------------------------
+
+/\w*\S/BZ
+------------------------------------------------------------------
+        Bra
+        \w*
+        \S
+        Ket
+        End
+------------------------------------------------------------------
+
+/\w*\w/BZ
+------------------------------------------------------------------
+        Bra
+        \w*
+        \w
+        Ket
+        End
+------------------------------------------------------------------
+
+/\w*\W/BZ
+------------------------------------------------------------------
+        Bra
+        \w*+
+        \W
+        Ket
+        End
+------------------------------------------------------------------
+
+/\W*a/BZ
+------------------------------------------------------------------
+        Bra
+        \W*+
+        a
+        Ket
+        End
+------------------------------------------------------------------
+
+/\W*2/BZ
+------------------------------------------------------------------
+        Bra
+        \W*+
+        2
+        Ket
+        End
+------------------------------------------------------------------
+
+/\W*\d/BZ
+------------------------------------------------------------------
+        Bra
+        \W*+
+        \d
+        Ket
+        End
+------------------------------------------------------------------
+
+/\W*\D/BZ
+------------------------------------------------------------------
+        Bra
+        \W*
+        \D
+        Ket
+        End
+------------------------------------------------------------------
+
+/\W*\s/BZ
+------------------------------------------------------------------
+        Bra
+        \W*
+        \s
+        Ket
+        End
+------------------------------------------------------------------
+
+/\W*\S/BZ
+------------------------------------------------------------------
+        Bra
+        \W*
+        \S
+        Ket
+        End
+------------------------------------------------------------------
+
+/\W*\w/BZ
+------------------------------------------------------------------
+        Bra
+        \W*+
+        \w
+        Ket
+        End
+------------------------------------------------------------------
+
+/\W*\W/BZ
+------------------------------------------------------------------
+        Bra
+        \W*
+        \W
+        Ket
+        End
+------------------------------------------------------------------
+
+/[^a]+a/BZ
+------------------------------------------------------------------
+        Bra
+        [^a]++
+        a
+        Ket
+        End
+------------------------------------------------------------------
+
+/[^a]+a/BZi
+------------------------------------------------------------------
+        Bra
+     /i [^a]++
+     /i a
+        Ket
+        End
+------------------------------------------------------------------
+
+/[^a]+A/BZi
+------------------------------------------------------------------
+        Bra
+     /i [^a]++
+     /i A
+        Ket
+        End
+------------------------------------------------------------------
+
+/[^a]+b/BZ
+------------------------------------------------------------------
+        Bra
+        [^a]+
+        b
+        Ket
+        End
+------------------------------------------------------------------
+
+/[^a]+\d/BZ
+------------------------------------------------------------------
+        Bra
+        [^a]+
+        \d
+        Ket
+        End
+------------------------------------------------------------------
+
+/a*[^a]/BZ
+------------------------------------------------------------------
+        Bra
+        a*
+        [^a]
+        Ket
+        End
+------------------------------------------------------------------
+
+/(?P<abc>x)(?P<xyz>y)/I
+Capturing subpattern count = 2
+Named capturing subpatterns:
+  abc   1
+  xyz   2
+No options
+First char = 'x'
+Need char = 'y'
+    xy\Cabc\Cxyz
+ 0: xy
+ 1: x
+ 2: y
+  C x (1) abc
+  C y (1) xyz
+
+/(?<abc>x)(?'xyz'y)/I
+Capturing subpattern count = 2
+Named capturing subpatterns:
+  abc   1
+  xyz   2
+No options
+First char = 'x'
+Need char = 'y'
+    xy\Cabc\Cxyz
+ 0: xy
+ 1: x
+ 2: y
+  C x (1) abc
+  C y (1) xyz
+
+/(?<abc'x)(?'xyz'y)/I
+Failed: syntax error in subpattern name (missing terminator) at offset 6
+
+/(?<abc>x)(?'xyz>y)/I
+Failed: syntax error in subpattern name (missing terminator) at offset 15
+
+/(?P'abc'x)(?P<xyz>y)/I
+Failed: unrecognized character after (?P at offset 3
+
+/^(?:(?(ZZ)a|b)(?<ZZ>X))+/
+    bXaX
+ 0: bXaX
+ 1: X
+    bXbX
+ 0: bX
+ 1: X
+    ** Failers
+No match
+    aXaX
+No match
+    aXbX
+No match
+
+/^(?P>abc)(?<abcd>xxx)/
+Failed: reference to non-existent subpattern at offset 8
+
+/^(?P>abc)(?<abc>x|y)/
+    xx
+ 0: xx
+ 1: x
+    xy
+ 0: xy
+ 1: y
+    yy
+ 0: yy
+ 1: y
+    yx
+ 0: yx
+ 1: x
+
+/^(?P>abc)(?P<abc>x|y)/
+    xx
+ 0: xx
+ 1: x
+    xy
+ 0: xy
+ 1: y
+    yy
+ 0: yy
+ 1: y
+    yx
+ 0: yx
+ 1: x
+
+/^((?(abc)a|b)(?<abc>x|y))+/
+    bxay
+ 0: bxay
+ 1: ay
+ 2: y
+    bxby
+ 0: bx
+ 1: bx
+ 2: x
+    ** Failers
+No match
+    axby
+No match
+
+/^(((?P=abc)|X)(?<abc>x|y))+/
+    XxXxxx
+ 0: XxXxxx
+ 1: xx
+ 2: x
+ 3: x
+    XxXyyx
+ 0: XxXyyx
+ 1: yx
+ 2: y
+ 3: x
+    XxXyxx
+ 0: XxXy
+ 1: Xy
+ 2: X
+ 3: y
+    ** Failers
+No match
+    x
+No match
+
+/^(?1)(abc)/
+    abcabc
+ 0: abcabc
+ 1: abc
+
+/^(?:(?:\1|X)(a|b))+/
+    Xaaa
+ 0: Xaaa
+ 1: a
+    Xaba
+ 0: Xa
+ 1: a
+
+/^[\E\Qa\E-\Qz\E]+/BZ
+------------------------------------------------------------------
+        Bra
+        ^
+        [a-z]+
+        Ket
+        End
+------------------------------------------------------------------
+
+/^[a\Q]bc\E]/BZ
+------------------------------------------------------------------
+        Bra
+        ^
+        [\]a-c]
+        Ket
+        End
+------------------------------------------------------------------
+
+/^[a-\Q\E]/BZ
+------------------------------------------------------------------
+        Bra
+        ^
+        [\-a]
+        Ket
+        End
+------------------------------------------------------------------
+
+/^(?P>abc)[()](?<abc>)/BZ
+------------------------------------------------------------------
+        Bra
+        ^
+        Recurse
+        [()]
+        CBra 1
+        Ket
+        Ket
+        End
+------------------------------------------------------------------
+
+/^((?(abc)y)[()](?P<abc>x))+/BZ
+------------------------------------------------------------------
+        Bra
+        ^
+        CBra 1
+        Cond
+      2 Cond nref
+        y
+        Ket
+        [()]
+        CBra 2
+        x
+        Ket
+        KetRmax
+        Ket
+        End
+------------------------------------------------------------------
+    (xy)x
+ 0: (xy)x
+ 1: y)x
+ 2: x
+
+/^(?P>abc)\Q()\E(?<abc>)/BZ
+------------------------------------------------------------------
+        Bra
+        ^
+        Recurse
+        ()
+        CBra 1
+        Ket
+        Ket
+        End
+------------------------------------------------------------------
+
+/^(?P>abc)[a\Q(]\E(](?<abc>)/BZ
+------------------------------------------------------------------
+        Bra
+        ^
+        Recurse
+        [(\]a]
+        CBra 1
+        Ket
+        Ket
+        End
+------------------------------------------------------------------
+
+/^(?P>abc) # this is (a comment)
+  (?<abc>)/BZx
+------------------------------------------------------------------
+        Bra
+        ^
+        Recurse
+        CBra 1
+        Ket
+        Ket
+        End
+------------------------------------------------------------------
+
+/^\W*(?:(?<one>(?<two>.)\W*(?&one)\W*\k<two>|)|(?<three>(?<four>.)\W*(?&three)\W*\k'four'|\W*.\W*))\W*$/Ii
+Capturing subpattern count = 4
+Max back reference = 4
+Named capturing subpatterns:
+  four    4
+  one     1
+  three   3
+  two     2
+Options: anchored caseless
+No first char
+No need char
+    1221
+ 0: 1221
+ 1: 1221
+ 2: 1
+    Satan, oscillate my metallic sonatas!
+ 0: Satan, oscillate my metallic sonatas!
+ 1: <unset>
+ 2: <unset>
+ 3: Satan, oscillate my metallic sonatas
+ 4: S
+    A man, a plan, a canal: Panama!
+ 0: A man, a plan, a canal: Panama!
+ 1: <unset>
+ 2: <unset>
+ 3: A man, a plan, a canal: Panama
+ 4: A
+    Able was I ere I saw Elba.
+ 0: Able was I ere I saw Elba.
+ 1: <unset>
+ 2: <unset>
+ 3: Able was I ere I saw Elba
+ 4: A
+    *** Failers
+No match
+    The quick brown fox
+No match
+
+/(?=(\w+))\1:/I
+Capturing subpattern count = 1
+Max back reference = 1
+No options
+No first char
+Need char = ':'
+    abcd:
+ 0: abcd:
+ 1: abcd
+
+/(?=(?'abc'\w+))\k<abc>:/I
+Capturing subpattern count = 1
+Max back reference = 1
+Named capturing subpatterns:
+  abc   1
+No options
+No first char
+Need char = ':'
+    abcd:
+ 0: abcd:
+ 1: abcd
+
+/(?'abc'a|b)(?<abc>d|e)\k<abc>{2}/J
+    adaa
+ 0: adaa
+ 1: a
+ 2: d
+    ** Failers
+No match
+    addd
+No match
+    adbb
+No match
+
+/(?'abc'a|b)(?<abc>d|e)(?&abc){2}/J
+    bdaa
+ 0: bdaa
+ 1: b
+ 2: d
+    bdab
+ 0: bdab
+ 1: b
+ 2: d
+    ** Failers
+No match
+    bddd
+No match
+
+/(?(<bc))/
+Failed: malformed number or name after (?( at offset 6
+
+/(?(''))/
+Failed: assertion expected after (?( at offset 4
+
+/(?('R')stuff)/
+Failed: reference to non-existent subpattern at offset 7
+
+/((abc (?(R) (?(R1)1) (?(R2)2) X  |  (?1)  (?2)   (?R) ))) /x
+    abcabc1Xabc2XabcXabcabc
+ 0: abcabc1Xabc2XabcX
+ 1: abcabc1Xabc2XabcX
+ 2: abcabc1Xabc2XabcX
+
+/(?<A> (?'B' abc (?(R) (?(R&A)1) (?(R&B)2) X  |  (?1)  (?2)   (?R) ))) /x
+    abcabc1Xabc2XabcXabcabc
+ 0: abcabc1Xabc2XabcX
+ 1: abcabc1Xabc2XabcX
+ 2: abcabc1Xabc2XabcX
+
+/(?<A> (?'B' abc (?(R) (?(R&1)1) (?(R&B)2) X  |  (?1)  (?2)   (?R) ))) /x
+Failed: reference to non-existent subpattern at offset 29
+
+/(?<1> (?'B' abc (?(R) (?(R&1)1) (?(R&B)2) X  |  (?1)  (?2)   (?R) ))) /x
+    abcabc1Xabc2XabcXabcabc
+ 0: abcabc1Xabc2XabcX
+ 1: abcabc1Xabc2XabcX
+ 2: abcabc1Xabc2XabcX
+
+/^(?(DEFINE) abc | xyz ) /x
+Failed: DEFINE group contains more than one branch at offset 22
+
+/(?(DEFINE) abc) xyz/xI
+Capturing subpattern count = 0
+Options: extended
+First char = 'x'
+Need char = 'z'
+
+/(a|)*\d/
+  \O0aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+No match
+  \O0aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa4
+Matched, but too many substrings
+
+/^a.b/<lf>
+    a\rb
+ 0: a\x0db
+    a\nb\<cr>
+ 0: a\x0ab
+    a\x85b\<anycrlf> 
+ 0: a\x85b
+    ** Failers
+No match
+    a\nb
+No match
+    a\nb\<any>
+No match
+    a\rb\<cr>
+No match
+    a\rb\<any>
+No match
+    a\x85b\<any> 
+No match
+    a\rb\<anycrlf>
+No match
+
+/^abc./mgx<any>
+    abc1 \x0aabc2 \x0babc3xx \x0cabc4 \x0dabc5xx \x0d\x0aabc6 \x85abc7 JUNK
+ 0: abc1
+ 0: abc2
+ 0: abc3
+ 0: abc4
+ 0: abc5
+ 0: abc6
+ 0: abc7
+
+/abc.$/mgx<any>
+    abc1\x0a abc2\x0b abc3\x0c abc4\x0d abc5\x0d\x0a abc6\x85 abc7 abc9
+ 0: abc1
+ 0: abc2
+ 0: abc3
+ 0: abc4
+ 0: abc5
+ 0: abc6
+ 0: abc9
+
+/a/<cr><any>
+
+/a/<any><crlf>
+Failed: inconsistent NEWLINE options at offset 0
+
+/^a\Rb/<bsr_unicode>
+    a\nb
+ 0: a\x0ab
+    a\rb
+ 0: a\x0db
+    a\r\nb
+ 0: a\x0d\x0ab
+    a\x0bb
+ 0: a\x0bb
+    a\x0cb
+ 0: a\x0cb
+    a\x85b
+ 0: a\x85b
+    ** Failers
+No match
+    a\n\rb
+No match
+
+/^a\R*b/<bsr_unicode>
+    ab
+ 0: ab
+    a\nb
+ 0: a\x0ab
+    a\rb
+ 0: a\x0db
+    a\r\nb
+ 0: a\x0d\x0ab
+    a\x0bb
+ 0: a\x0bb
+    a\x0cb
+ 0: a\x0cb
+    a\x85b
+ 0: a\x85b
+    a\n\rb
+ 0: a\x0a\x0db
+    a\n\r\x85\x0cb
+ 0: a\x0a\x0d\x85\x0cb
+
+/^a\R+b/<bsr_unicode>
+    a\nb
+ 0: a\x0ab
+    a\rb
+ 0: a\x0db
+    a\r\nb
+ 0: a\x0d\x0ab
+    a\x0bb
+ 0: a\x0bb
+    a\x0cb
+ 0: a\x0cb
+    a\x85b
+ 0: a\x85b
+    a\n\rb
+ 0: a\x0a\x0db
+    a\n\r\x85\x0cb
+ 0: a\x0a\x0d\x85\x0cb
+    ** Failers
+No match
+    ab
+No match
+
+/^a\R{1,3}b/<bsr_unicode>
+    a\nb
+ 0: a\x0ab
+    a\n\rb
+ 0: a\x0a\x0db
+    a\n\r\x85b
+ 0: a\x0a\x0d\x85b
+    a\r\n\r\nb
+ 0: a\x0d\x0a\x0d\x0ab
+    a\r\n\r\n\r\nb
+ 0: a\x0d\x0a\x0d\x0a\x0d\x0ab
+    a\n\r\n\rb
+ 0: a\x0a\x0d\x0a\x0db
+    a\n\n\r\nb
+ 0: a\x0a\x0a\x0d\x0ab
+    ** Failers
+No match
+    a\n\n\n\rb
+No match
+    a\r
+No match
+
+/^a[\R]b/<bsr_unicode>
+    aRb
+ 0: aRb
+    ** Failers
+No match
+    a\nb
+No match
+
+/(?&abc)X(?<abc>P)/I
+Capturing subpattern count = 1
+Named capturing subpatterns:
+  abc   1
+No options
+No first char
+Need char = 'P'
+    abcPXP123
+ 0: PXP
+ 1: P
+
+/(?1)X(?<abc>P)/I
+Capturing subpattern count = 1
+Named capturing subpatterns:
+  abc   1
+No options
+No first char
+Need char = 'P'
+    abcPXP123
+ 0: PXP
+ 1: P
+
+/(?:a(?&abc)b)*(?<abc>x)/
+    123axbaxbaxbx456
+ 0: axbaxbaxbx
+ 1: x
+    123axbaxbaxb456
+ 0: x
+ 1: x
+
+/(?:a(?&abc)b){1,5}(?<abc>x)/
+    123axbaxbaxbx456
+ 0: axbaxbaxbx
+ 1: x
+
+/(?:a(?&abc)b){2,5}(?<abc>x)/
+    123axbaxbaxbx456
+ 0: axbaxbaxbx
+ 1: x
+
+/(?:a(?&abc)b){2,}(?<abc>x)/
+    123axbaxbaxbx456
+ 0: axbaxbaxbx
+ 1: x
+
+/(abc)(?i:(?1))/
+   defabcabcxyz
+ 0: abcabc
+ 1: abc
+   DEFabcABCXYZ
+No match
+
+/(abc)(?:(?i)(?1))/
+   defabcabcxyz
+ 0: abcabc
+ 1: abc
+   DEFabcABCXYZ
+No match
+
+/^(a)\g-2/
+Failed: reference to non-existent subpattern at offset 7
+
+/^(a)\g/
+Failed: a numbered reference must not be zero at offset 5
+
+/^(a)\g{0}/
+Failed: a numbered reference must not be zero at offset 8
+
+/^(a)\g{3/
+Failed: \g is not followed by a braced, angle-bracketed, or quoted name/number or by a plain number at offset 8
+
+/^(a)\g{4a}/
+Failed: reference to non-existent subpattern at offset 9
+
+/^a.b/<lf>
+    a\rb
+ 0: a\x0db
+    *** Failers
+No match
+    a\nb
+No match
+
+/.+foo/
+    afoo
+ 0: afoo
+    ** Failers
+No match
+    \r\nfoo
+No match
+    \nfoo
+No match
+
+/.+foo/<crlf>
+    afoo
+ 0: afoo
+    \nfoo
+ 0: \x0afoo
+    ** Failers
+No match
+    \r\nfoo
+No match
+
+/.+foo/<any>
+    afoo
+ 0: afoo
+    ** Failers
+No match
+    \nfoo
+No match
+    \r\nfoo
+No match
+
+/.+foo/s
+    afoo
+ 0: afoo
+    \r\nfoo
+ 0: \x0d\x0afoo
+    \nfoo
+ 0: \x0afoo
+    
+/^$/mg<any>
+    abc\r\rxyz
+ 0: 
+    abc\n\rxyz  
+ 0: 
+    ** Failers 
+No match
+    abc\r\nxyz
+No match
+
+/(?m)^$/<any>g+
+    abc\r\n\r\n
+ 0: 
+ 0+ \x0d\x0a
+
+/(?m)^$|^\r\n/<any>g+ 
+    abc\r\n\r\n
+ 0: 
+ 0+ \x0d\x0a
+ 0: \x0d\x0a
+ 0+ 
+    
+/(?m)$/<any>g+ 
+    abc\r\n\r\n
+ 0: 
+ 0+ \x0d\x0a\x0d\x0a
+ 0: 
+ 0+ \x0d\x0a
+ 0: 
+ 0+ 
+
+/abc.$/mgx<anycrlf>
+    abc1\x0a abc2\x0b abc3\x0c abc4\x0d abc5\x0d\x0a abc6\x85 abc9
+ 0: abc1
+ 0: abc4
+ 0: abc5
+ 0: abc9
+
+/^X/m
+    XABC
+ 0: X
+    ** Failers 
+No match
+    XABC\B
+No match
+
+/(ab|c)(?-1)/BZ
+------------------------------------------------------------------
+        Bra
+        CBra 1
+        ab
+        Alt
+        c
+        Ket
+        Recurse
+        Ket
+        End
+------------------------------------------------------------------
+    abc
+ 0: abc
+ 1: ab
+
+/xy(?+1)(abc)/BZ
+------------------------------------------------------------------
+        Bra
+        xy
+        Recurse
+        CBra 1
+        abc
+        Ket
+        Ket
+        End
+------------------------------------------------------------------
+    xyabcabc
+ 0: xyabcabc
+ 1: abc
+    ** Failers
+No match
+    xyabc  
+No match
+    
+/x(?-0)y/
+Failed: a numbered reference must not be zero at offset 5
+
+/x(?-1)y/
+Failed: reference to non-existent subpattern at offset 5
+
+/x(?+0)y/ 
+Failed: a numbered reference must not be zero at offset 5
+
+/x(?+1)y/
+Failed: reference to non-existent subpattern at offset 5
+
+/^(abc)?(?(-1)X|Y)/BZ
+------------------------------------------------------------------
+        Bra
+        ^
+        Brazero
+        CBra 1
+        abc
+        Ket
+        Cond
+      1 Cond ref
+        X
+        Alt
+        Y
+        Ket
+        Ket
+        End
+------------------------------------------------------------------
+    abcX
+ 0: abcX
+ 1: abc
+    Y
+ 0: Y
+    ** Failers
+No match
+    abcY   
+No match
+    
+/^((?(+1)X|Y)(abc))+/BZ 
+------------------------------------------------------------------
+        Bra
+        ^
+        CBra 1
+        Cond
+      2 Cond ref
+        X
+        Alt
+        Y
+        Ket
+        CBra 2
+        abc
+        Ket
+        KetRmax
+        Ket
+        End
+------------------------------------------------------------------
+    YabcXabc
+ 0: YabcXabc
+ 1: Xabc
+ 2: abc
+    YabcXabcXabc
+ 0: YabcXabcXabc
+ 1: Xabc
+ 2: abc
+    ** Failers
+No match
+    XabcXabc  
+No match
+
+/(?(-1)a)/BZ
+Failed: reference to non-existent subpattern at offset 6
+
+/((?(-1)a))/BZ
+------------------------------------------------------------------
+        Bra
+        CBra 1
+        Cond
+      1 Cond ref
+        a
+        Ket
+        Ket
+        Ket
+        End
+------------------------------------------------------------------
+
+/((?(-2)a))/BZ
+Failed: reference to non-existent subpattern at offset 7
+
+/^(?(+1)X|Y)(.)/BZ
+------------------------------------------------------------------
+        Bra
+        ^
+        Cond
+      1 Cond ref
+        X
+        Alt
+        Y
+        Ket
+        CBra 1
+        Any
+        Ket
+        Ket
+        End
+------------------------------------------------------------------
+    Y!
+ 0: Y!
+ 1: !
+
+/(?<A>tom|bon)-\k{A}/
+    tom-tom
+ 0: tom-tom
+ 1: tom
+    bon-bon 
+ 0: bon-bon
+ 1: bon
+    ** Failers
+No match
+    tom-bon  
+No match
+
+/\g{A/ 
+Failed: syntax error in subpattern name (missing terminator) at offset 4
+
+/(?|(abc)|(xyz))/BZ
+------------------------------------------------------------------
+        Bra
+        Bra
+        CBra 1
+        abc
+        Ket
+        Alt
+        CBra 1
+        xyz
+        Ket
+        Ket
+        Ket
+        End
+------------------------------------------------------------------
+   >abc<
+ 0: abc
+ 1: abc
+   >xyz< 
+ 0: xyz
+ 1: xyz
+
+/(x)(?|(abc)|(xyz))(x)/BZ
+------------------------------------------------------------------
+        Bra
+        CBra 1
+        x
+        Ket
+        Bra
+        CBra 2
+        abc
+        Ket
+        Alt
+        CBra 2
+        xyz
+        Ket
+        Ket
+        CBra 3
+        x
+        Ket
+        Ket
+        End
+------------------------------------------------------------------
+    xabcx
+ 0: xabcx
+ 1: x
+ 2: abc
+ 3: x
+    xxyzx 
+ 0: xxyzx
+ 1: x
+ 2: xyz
+ 3: x
+
+/(x)(?|(abc)(pqr)|(xyz))(x)/BZ
+------------------------------------------------------------------
+        Bra
+        CBra 1
+        x
+        Ket
+        Bra
+        CBra 2
+        abc
+        Ket
+        CBra 3
+        pqr
+        Ket
+        Alt
+        CBra 2
+        xyz
+        Ket
+        Ket
+        CBra 4
+        x
+        Ket
+        Ket
+        End
+------------------------------------------------------------------
+    xabcpqrx
+ 0: xabcpqrx
+ 1: x
+ 2: abc
+ 3: pqr
+ 4: x
+    xxyzx 
+ 0: xxyzx
+ 1: x
+ 2: xyz
+ 3: <unset>
+ 4: x
+
+/\H++X/BZ
+------------------------------------------------------------------
+        Bra
+        \H++
+        X
+        Ket
+        End
+------------------------------------------------------------------
+    ** Failers
+No match
+    XXXX
+No match
+    
+/\H+\hY/BZ
+------------------------------------------------------------------
+        Bra
+        \H++
+        \h
+        Y
+        Ket
+        End
+------------------------------------------------------------------
+    XXXX Y 
+ 0: XXXX Y
+
+/\H+ Y/BZ
+------------------------------------------------------------------
+        Bra
+        \H++
+         Y
+        Ket
+        End
+------------------------------------------------------------------
+
+/\h+A/BZ
+------------------------------------------------------------------
+        Bra
+        \h++
+        A
+        Ket
+        End
+------------------------------------------------------------------
+
+/\v*B/BZ
+------------------------------------------------------------------
+        Bra
+        \v*+
+        B
+        Ket
+        End
+------------------------------------------------------------------
+
+/\V+\x0a/BZ
+------------------------------------------------------------------
+        Bra
+        \V++
+        \x0a
+        Ket
+        End
+------------------------------------------------------------------
+
+/A+\h/BZ
+------------------------------------------------------------------
+        Bra
+        A++
+        \h
+        Ket
+        End
+------------------------------------------------------------------
+
+/ *\H/BZ
+------------------------------------------------------------------
+        Bra
+         *+
+        \H
+        Ket
+        End
+------------------------------------------------------------------
+
+/A*\v/BZ
+------------------------------------------------------------------
+        Bra
+        A*+
+        \v
+        Ket
+        End
+------------------------------------------------------------------
+
+/\x0b*\V/BZ
+------------------------------------------------------------------
+        Bra
+        \x0b*+
+        \V
+        Ket
+        End
+------------------------------------------------------------------
+
+/\d+\h/BZ
+------------------------------------------------------------------
+        Bra
+        \d++
+        \h
+        Ket
+        End
+------------------------------------------------------------------
+
+/\d*\v/BZ
+------------------------------------------------------------------
+        Bra
+        \d*+
+        \v
+        Ket
+        End
+------------------------------------------------------------------
+
+/S+\h\S+\v/BZ
+------------------------------------------------------------------
+        Bra
+        S++
+        \h
+        \S++
+        \v
+        Ket
+        End
+------------------------------------------------------------------
+
+/\w{3,}\h\w+\v/BZ
+------------------------------------------------------------------
+        Bra
+        \w{3}
+        \w*+
+        \h
+        \w++
+        \v
+        Ket
+        End
+------------------------------------------------------------------
+
+/\h+\d\h+\w\h+\S\h+\H/BZ
+------------------------------------------------------------------
+        Bra
+        \h++
+        \d
+        \h++
+        \w
+        \h++
+        \S
+        \h++
+        \H
+        Ket
+        End
+------------------------------------------------------------------
+
+/\v+\d\v+\w\v+\S\v+\V/BZ
+------------------------------------------------------------------
+        Bra
+        \v++
+        \d
+        \v++
+        \w
+        \v+
+        \S
+        \v++
+        \V
+        Ket
+        End
+------------------------------------------------------------------
+
+/\H+\h\H+\d/BZ
+------------------------------------------------------------------
+        Bra
+        \H++
+        \h
+        \H+
+        \d
+        Ket
+        End
+------------------------------------------------------------------
+
+/\V+\v\V+\w/BZ
+------------------------------------------------------------------
+        Bra
+        \V++
+        \v
+        \V+
+        \w
+        Ket
+        End
+------------------------------------------------------------------
+
+/\( (?: [^()]* | (?R) )* \)/x
+\J1024(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(00)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)
+ 0: (0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(00)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)
+
+/[\E]AAA/
+Failed: missing terminating ] for character class at offset 7
+
+/[\Q\E]AAA/
+Failed: missing terminating ] for character class at offset 9
+
+/[^\E]AAA/
+Failed: missing terminating ] for character class at offset 8
+
+/[^\Q\E]AAA/
+Failed: missing terminating ] for character class at offset 10
+
+/[\E^]AAA/
+Failed: missing terminating ] for character class at offset 8
+
+/[\Q\E^]AAA/
+Failed: missing terminating ] for character class at offset 10
+
+/A(*PRUNE)B(*SKIP)C(*THEN)D(*COMMIT)E(*F)F(*FAIL)G(?!)H(*ACCEPT)I/BZ
+------------------------------------------------------------------
+        Bra
+        A
+        *PRUNE
+        B
+        *SKIP
+        C
+        *THEN
+        D
+        *COMMIT
+        E
+        *FAIL
+        F
+        *FAIL
+        G
+        *FAIL
+        H
+        *ACCEPT
+        I
+        Ket
+        End
+------------------------------------------------------------------
+
+/^a+(*FAIL)/C
+    aaaaaa
+--->aaaaaa
+ +0 ^          ^
+ +1 ^          a+
+ +3 ^     ^    (*FAIL)
+ +3 ^    ^     (*FAIL)
+ +3 ^   ^      (*FAIL)
+ +3 ^  ^       (*FAIL)
+ +3 ^ ^        (*FAIL)
+ +3 ^^         (*FAIL)
+No match
+    
+/a+b?c+(*FAIL)/C
+    aaabccc
+--->aaabccc
+ +0 ^           a+
+ +2 ^  ^        b?
+ +4 ^   ^       c+
+ +6 ^      ^    (*FAIL)
+ +6 ^     ^     (*FAIL)
+ +6 ^    ^      (*FAIL)
+ +4 ^  ^        c+
+ +2 ^ ^         b?
+ +4 ^ ^         c+
+ +2 ^^          b?
+ +4 ^^          c+
+ +0  ^          a+
+ +2  ^ ^        b?
+ +4  ^  ^       c+
+ +6  ^     ^    (*FAIL)
+ +6  ^    ^     (*FAIL)
+ +6  ^   ^      (*FAIL)
+ +4  ^ ^        c+
+ +2  ^^         b?
+ +4  ^^         c+
+ +0   ^         a+
+ +2   ^^        b?
+ +4   ^ ^       c+
+ +6   ^    ^    (*FAIL)
+ +6   ^   ^     (*FAIL)
+ +6   ^  ^      (*FAIL)
+ +4   ^^        c+
+No match
+
+/a+b?(*PRUNE)c+(*FAIL)/C
+    aaabccc
+--->aaabccc
+ +0 ^           a+
+ +2 ^  ^        b?
+ +4 ^   ^       (*PRUNE)
++12 ^   ^       c+
++14 ^      ^    (*FAIL)
++14 ^     ^     (*FAIL)
++14 ^    ^      (*FAIL)
+ +0  ^          a+
+ +2  ^ ^        b?
+ +4  ^  ^       (*PRUNE)
++12  ^  ^       c+
++14  ^     ^    (*FAIL)
++14  ^    ^     (*FAIL)
++14  ^   ^      (*FAIL)
+ +0   ^         a+
+ +2   ^^        b?
+ +4   ^ ^       (*PRUNE)
++12   ^ ^       c+
++14   ^    ^    (*FAIL)
++14   ^   ^     (*FAIL)
++14   ^  ^      (*FAIL)
+No match
+
+/a+b?(*COMMIT)c+(*FAIL)/C
+    aaabccc
+--->aaabccc
+ +0 ^           a+
+ +2 ^  ^        b?
+ +4 ^   ^       (*COMMIT)
++13 ^   ^       c+
++15 ^      ^    (*FAIL)
++15 ^     ^     (*FAIL)
++15 ^    ^      (*FAIL)
+No match
+    
+/a+b?(*SKIP)c+(*FAIL)/C
+    aaabcccaaabccc
+--->aaabcccaaabccc
+ +0 ^                  a+
+ +2 ^  ^               b?
+ +4 ^   ^              (*SKIP)
++11 ^   ^              c+
++13 ^      ^           (*FAIL)
++13 ^     ^            (*FAIL)
++13 ^    ^             (*FAIL)
+ +0        ^           a+
+ +2        ^  ^        b?
+ +4        ^   ^       (*SKIP)
++11        ^   ^       c+
++13        ^      ^    (*FAIL)
++13        ^     ^     (*FAIL)
++13        ^    ^      (*FAIL)
+No match
+
+/a+b?(*THEN)c+(*FAIL)/C
+    aaabccc
+--->aaabccc
+ +0 ^           a+
+ +2 ^  ^        b?
+ +4 ^   ^       (*THEN)
++11 ^   ^       c+
++13 ^      ^    (*FAIL)
++13 ^     ^     (*FAIL)
++13 ^    ^      (*FAIL)
+ +0  ^          a+
+ +2  ^ ^        b?
+ +4  ^  ^       (*THEN)
++11  ^  ^       c+
++13  ^     ^    (*FAIL)
++13  ^    ^     (*FAIL)
++13  ^   ^      (*FAIL)
+ +0   ^         a+
+ +2   ^^        b?
+ +4   ^ ^       (*THEN)
++11   ^ ^       c+
++13   ^    ^    (*FAIL)
++13   ^   ^     (*FAIL)
++13   ^  ^      (*FAIL)
+No match
+    
+/a(*MARK)b/ 
+Failed: (*MARK) must have an argument at offset 7
+
+/(?i:A{1,}\6666666666)/
+Failed: number is too big at offset 19
+
+/\g6666666666/
+Failed: number is too big at offset 11
+
+/[\g6666666666]/BZ
+------------------------------------------------------------------
+        Bra
+        [6g]
+        Ket
+        End
+------------------------------------------------------------------
+
+/(?1)\c[/
+Failed: reference to non-existent subpattern at offset 3
+
+/.+A/<crlf>
+    \r\nA
+No match
+    
+/\nA/<crlf>
+    \r\nA 
+ 0: \x0aA
+
+/[\r\n]A/<crlf>
+    \r\nA 
+ 0: \x0aA
+
+/(\r|\n)A/<crlf>
+    \r\nA 
+ 0: \x0aA
+ 1: \x0a
+
+/a(*CR)b/
+Failed: (*VERB) not recognized at offset 5
+
+/(*CR)a.b/
+    a\nb
+ 0: a\x0ab
+    ** Failers
+No match
+    a\rb  
+No match
+
+/(*CR)a.b/<lf>
+    a\nb
+ 0: a\x0ab
+    ** Failers
+No match
+    a\rb  
+No match
+
+/(*LF)a.b/<CRLF>
+    a\rb
+ 0: a\x0db
+    ** Failers
+No match
+    a\nb  
+No match
+
+/(*CRLF)a.b/
+    a\rb
+ 0: a\x0db
+    a\nb  
+ 0: a\x0ab
+    ** Failers
+No match
+    a\r\nb  
+No match
+
+/(*ANYCRLF)a.b/<CR>
+    ** Failers
+No match
+    a\rb
+No match
+    a\nb  
+No match
+    a\r\nb  
+No match
+
+/(*ANY)a.b/<cr>
+    ** Failers
+No match
+    a\rb
+No match
+    a\nb  
+No match
+    a\r\nb  
+No match
+    a\x85b 
+No match
+    
+/(*ANY).*/g
+    abc\r\ndef
+ 0: abc
+ 0: 
+ 0: def
+ 0: 
+
+/(*ANYCRLF).*/g
+    abc\r\ndef
+ 0: abc
+ 0: 
+ 0: def
+ 0: 
+
+/(*CRLF).*/g
+    abc\r\ndef
+ 0: abc
+ 0: 
+ 0: def
+ 0: 
+
+/a\Rb/I<bsr_anycrlf>
+Capturing subpattern count = 0
+Options: bsr_anycrlf
+First char = 'a'
+Need char = 'b'
+    a\rb
+ 0: a\x0db
+    a\nb
+ 0: a\x0ab
+    a\r\nb
+ 0: a\x0d\x0ab
+    ** Failers
+No match
+    a\x85b
+No match
+    a\x0bb     
+No match
+
+/a\Rb/I<bsr_unicode>
+Capturing subpattern count = 0
+Options: bsr_unicode
+First char = 'a'
+Need char = 'b'
+    a\rb
+ 0: a\x0db
+    a\nb
+ 0: a\x0ab
+    a\r\nb
+ 0: a\x0d\x0ab
+    a\x85b
+ 0: a\x85b
+    a\x0bb     
+ 0: a\x0bb
+    ** Failers 
+No match
+    a\x85b\<bsr_anycrlf>
+No match
+    a\x0bb\<bsr_anycrlf>
+No match
+    
+/a\R?b/I<bsr_anycrlf>
+Capturing subpattern count = 0
+Options: bsr_anycrlf
+First char = 'a'
+Need char = 'b'
+    a\rb
+ 0: a\x0db
+    a\nb
+ 0: a\x0ab
+    a\r\nb
+ 0: a\x0d\x0ab
+    ** Failers
+No match
+    a\x85b
+No match
+    a\x0bb     
+No match
+
+/a\R?b/I<bsr_unicode>
+Capturing subpattern count = 0
+Options: bsr_unicode
+First char = 'a'
+Need char = 'b'
+    a\rb
+ 0: a\x0db
+    a\nb
+ 0: a\x0ab
+    a\r\nb
+ 0: a\x0d\x0ab
+    a\x85b
+ 0: a\x85b
+    a\x0bb     
+ 0: a\x0bb
+    ** Failers 
+No match
+    a\x85b\<bsr_anycrlf>
+No match
+    a\x0bb\<bsr_anycrlf>
+No match
+    
+/a\R{2,4}b/I<bsr_anycrlf>
+Capturing subpattern count = 0
+Options: bsr_anycrlf
+First char = 'a'
+Need char = 'b'
+    a\r\n\nb
+ 0: a\x0d\x0a\x0ab
+    a\n\r\rb
+ 0: a\x0a\x0d\x0db
+    a\r\n\r\n\r\n\r\nb
+ 0: a\x0d\x0a\x0d\x0a\x0d\x0a\x0d\x0ab
+    ** Failers
+No match
+    a\x85\85b
+No match
+    a\x0b\0bb     
+No match
+
+/a\R{2,4}b/I<bsr_unicode>
+Capturing subpattern count = 0
+Options: bsr_unicode
+First char = 'a'
+Need char = 'b'
+    a\r\rb
+ 0: a\x0d\x0db
+    a\n\n\nb
+ 0: a\x0a\x0a\x0ab
+    a\r\n\n\r\rb
+ 0: a\x0d\x0a\x0a\x0d\x0db
+    a\x85\85b
+No match
+    a\x0b\0bb     
+No match
+    ** Failers 
+No match
+    a\r\r\r\r\rb 
+No match
+    a\x85\85b\<bsr_anycrlf>
+No match
+    a\x0b\0bb\<bsr_anycrlf>
+No match
+ 
+/(*BSR_ANYCRLF)a\Rb/I
+Capturing subpattern count = 0
+Options: bsr_anycrlf
+First char = 'a'
+Need char = 'b'
+    a\nb
+ 0: a\x0ab
+    a\rb 
+ 0: a\x0db
+
+/(*BSR_UNICODE)a\Rb/I
+Capturing subpattern count = 0
+Options: bsr_unicode
+First char = 'a'
+Need char = 'b'
+    a\x85b
+ 0: a\x85b
+
+/(*BSR_ANYCRLF)(*CRLF)a\Rb/I
+Capturing subpattern count = 0
+Options: bsr_anycrlf
+Forced newline sequence: CRLF
+First char = 'a'
+Need char = 'b'
+    a\nb
+ 0: a\x0ab
+    a\rb 
+ 0: a\x0db
+
+/(*CRLF)(*BSR_UNICODE)a\Rb/I
+Capturing subpattern count = 0
+Options: bsr_unicode
+Forced newline sequence: CRLF
+First char = 'a'
+Need char = 'b'
+    a\x85b
+ 0: a\x85b
+
+/(*CRLF)(*BSR_ANYCRLF)(*CR)ab/I
+Capturing subpattern count = 0
+Options: bsr_anycrlf
+Forced newline sequence: CR
+First char = 'a'
+Need char = 'b'
+
+/(?<a>)(?&)/
+Failed: subpattern name expected at offset 9
+
+/(?<abc>)(?&a)/
+Failed: reference to non-existent subpattern at offset 12
+
+/(?<a>)(?&aaaaaaaaaaaaaaaaaaaaaaa)/
+Failed: reference to non-existent subpattern at offset 32
+
+/(?+-a)/
+Failed: digit expected after (?+ at offset 3
+
+/(?-+a)/
+Failed: unrecognized character after (? or (?- at offset 3
+
+/(?(-1))/
+Failed: reference to non-existent subpattern at offset 6
+
+/(?(+10))/
+Failed: reference to non-existent subpattern at offset 7
+
+/(?(10))/
+Failed: reference to non-existent subpattern at offset 6
+
+/(?(+2))()()/
+
+/(?(2))()()/
+
+/\k''/
+Failed: subpattern name expected at offset 3
+
+/\k<>/
+Failed: subpattern name expected at offset 3
+
+/\k{}/
+Failed: subpattern name expected at offset 3
+
+/\k/
+Failed: \k is not followed by a braced, angle-bracketed, or quoted name at offset 2
+
+/\kabc/
+Failed: \k is not followed by a braced, angle-bracketed, or quoted name at offset 5
+
+/(?P=)/
+Failed: subpattern name expected at offset 4
+
+/(?P>)/
+Failed: subpattern name expected at offset 4
+
+/(?!\w)(?R)/
+Failed: recursive call could loop indefinitely at offset 9
+
+/(?=\w)(?R)/
+Failed: recursive call could loop indefinitely at offset 9
+
+/(?<!\w)(?R)/
+Failed: recursive call could loop indefinitely at offset 10
+
+/(?<=\w)(?R)/
+Failed: recursive call could loop indefinitely at offset 10
+
+/[[:foo:]]/
+Failed: unknown POSIX class name at offset 3
+
+/[[:1234:]]/
+Failed: unknown POSIX class name at offset 3
+
+/[[:f\oo:]]/
+Failed: unknown POSIX class name at offset 3
+
+/[[: :]]/
+Failed: unknown POSIX class name at offset 3
+
+/[[:...:]]/
+Failed: unknown POSIX class name at offset 3
+
+/[[:l\ower:]]/
+Failed: unknown POSIX class name at offset 3
+
+/[[:abc\:]]/
+Failed: unknown POSIX class name at offset 3
+
+/[abc[:x\]pqr:]]/
+Failed: unknown POSIX class name at offset 6
+
+/[[:a\dz:]]/
+Failed: unknown POSIX class name at offset 3
+
+/(^(a|b\g<-1'c))/
+Failed: \g is not followed by a braced, angle-bracketed, or quoted name/number or by a plain number at offset 15
+
+/^(?+1)(?<a>x|y){0}z/
+    xzxx
+ 0: xz
+    yzyy 
+ 0: yz
+    ** Failers
+No match
+    xxz  
+No match
+
+/(\3)(\1)(a)/
+    cat
+No match
+
+/(\3)(\1)(a)/<JS>
+    cat
+ 0: a
+ 1: 
+ 2: 
+ 3: a
+    
+/TA]/
+    The ACTA] comes 
+ 0: TA]
+
+/TA]/<JS>
+Failed: ] is an invalid data character in JavaScript compatibility mode at offset 2
+
+/(?2)[]a()b](abc)/
+Failed: reference to non-existent subpattern at offset 3
+
+/(?2)[^]a()b](abc)/
+Failed: reference to non-existent subpattern at offset 3
+
+/(?1)[]a()b](abc)/
+    abcbabc
+ 0: abcbabc
+ 1: abc
+    ** Failers 
+No match
+    abcXabc
+No match
+
+/(?1)[^]a()b](abc)/
+    abcXabc
+ 0: abcXabc
+ 1: abc
+    ** Failers 
+No match
+    abcbabc
+No match
+
+/(?2)[]a()b](abc)(xyz)/
+    xyzbabcxyz
+ 0: xyzbabcxyz
+ 1: abc
+ 2: xyz
+
+/(?&N)[]a(?<N>)](?<M>abc)/
+Failed: reference to non-existent subpattern at offset 4
+
+/(?&N)[]a(?<N>)](abc)/
+Failed: reference to non-existent subpattern at offset 4
+
+/a[]b/
+Failed: missing terminating ] for character class at offset 4
+
+/a[^]b/
+Failed: missing terminating ] for character class at offset 5
+
+/a[]b/<JS>
+    ** Failers
+No match
+    ab
+No match
+
+/a[]+b/<JS>
+    ** Failers
+No match
+    ab 
+No match
+
+/a[]*+b/<JS>
+    ** Failers
+No match
+    ab 
+No match
+
+/a[^]b/<JS>
+    aXb
+ 0: aXb
+    a\nb 
+ 0: a\x0ab
+    ** Failers
+No match
+    ab  
+No match
+    
+/a[^]+b/<JS> 
+    aXb
+ 0: aXb
+    a\nX\nXb 
+ 0: a\x0aX\x0aXb
+    ** Failers
+No match
+    ab  
+No match
+
+/a(?!)+b/
+Failed: nothing to repeat at offset 5
+
+/a(*FAIL)+b/
+Failed: nothing to repeat at offset 8
+
+/(abc|pqr|123){0}[xyz]/SI
+Capturing subpattern count = 1
+No options
+No first char
+No need char
+Subject length lower bound = 1
+Starting byte set: x y z 
+
+/(?(?=.*b)b|^)/CI
+Capturing subpattern count = 0
+Options:
+No first char
+No need char
+   adc
+--->adc
+ +0 ^       (?(?=.*b)b|^)
+ +2 ^       (?=.*b)
+ +5 ^       .*
+ +7 ^  ^    b
+ +7 ^ ^     b
+ +7 ^^      b
+ +7 ^       b
++12 ^       )
++13 ^       
+ 0: 
+   abc 
+--->abc
+ +0 ^       (?(?=.*b)b|^)
+ +2 ^       (?=.*b)
+ +5 ^       .*
+ +7 ^  ^    b
+ +7 ^ ^     b
+ +7 ^^      b
+ +8 ^ ^     )
+ +9 ^       b
+ +0  ^      (?(?=.*b)b|^)
+ +2  ^      (?=.*b)
+ +5  ^      .*
+ +7  ^ ^    b
+ +7  ^^     b
+ +7  ^      b
+ +8  ^^     )
+ +9  ^      b
++10  ^^     |
++13  ^^     
+ 0: b
+   
+/(?(?=b).*b|^d)/I
+Capturing subpattern count = 0
+No options
+No first char
+No need char
+
+/(?(?=.*b).*b|^d)/I
+Capturing subpattern count = 0
+No options
+First char at start or follows newline
+No need char
+
+/xyz/C
+  xyz 
+--->xyz
+ +0 ^       x
+ +1 ^^      y
+ +2 ^ ^     z
+ +3 ^  ^    
+ 0: xyz
+  abcxyz 
+--->abcxyz
+ +0    ^       x
+ +1    ^^      y
+ +2    ^ ^     z
+ +3    ^  ^    
+ 0: xyz
+  abcxyz\Y
+--->abcxyz
+ +0 ^          x
+ +0  ^         x
+ +0   ^        x
+ +0    ^       x
+ +1    ^^      y
+ +2    ^ ^     z
+ +3    ^  ^    
+ 0: xyz
+  ** Failers 
+No match
+  abc
+No match
+  abc\Y
+--->abc
+ +0 ^       x
+ +0  ^      x
+ +0   ^     x
+ +0    ^    x
+No match
+  abcxypqr  
+No match
+  abcxypqr\Y  
+--->abcxypqr
+ +0 ^            x
+ +0  ^           x
+ +0   ^          x
+ +0    ^         x
+ +1    ^^        y
+ +2    ^ ^       z
+ +0     ^        x
+ +0      ^       x
+ +0       ^      x
+ +0        ^     x
+ +0         ^    x
+No match
+  
+/(*NO_START_OPT)xyz/C
+  abcxyz 
+--->abcxyz
++15 ^          x
++15  ^         x
++15   ^        x
++15    ^       x
++16    ^^      y
++17    ^ ^     z
++18    ^  ^    
+ 0: xyz
+
+/xyz/CY
+  abcxyz 
+--->abcxyz
+ +0 ^          x
+ +0  ^         x
+ +0   ^        x
+ +0    ^       x
+ +1    ^^      y
+ +2    ^ ^     z
+ +3    ^  ^    
+ 0: xyz
+
+/^"((?(?=[a])[^"])|b)*"$/C
+    "ab"
+--->"ab"
+ +0 ^        ^
+ +1 ^        "
+ +2 ^^       ((?(?=[a])[^"])|b)*
+ +3 ^^       (?(?=[a])[^"])
+ +5 ^^       (?=[a])
+ +8 ^^       [a]
++11 ^ ^      )
++12 ^^       [^"]
++16 ^ ^      )
++17 ^ ^      |
+ +3 ^ ^      (?(?=[a])[^"])
+ +5 ^ ^      (?=[a])
+ +8 ^ ^      [a]
++21 ^ ^      "
++18 ^ ^      b
++19 ^  ^     )
+ +3 ^  ^     (?(?=[a])[^"])
+ +5 ^  ^     (?=[a])
+ +8 ^  ^     [a]
++21 ^  ^     "
++22 ^   ^    $
++23 ^   ^    
+ 0: "ab"
+ 1: 
+
+/^"((?(?=[a])[^"])|b)*"$/
+    "ab"
+ 0: "ab"
+ 1: 
+
+/^X(?5)(a)(?|(b)|(q))(c)(d)Y/
+Failed: reference to non-existent subpattern at offset 5
+
+/^X(?&N)(a)(?|(b)|(q))(c)(d)(?<N>Y)/
+    XYabcdY
+ 0: XYabcdY
+ 1: a
+ 2: b
+ 3: c
+ 4: d
+ 5: Y
+ 
+/Xa{2,4}b/
+    X\P
+Partial match: X
+    Xa\P
+Partial match: Xa
+    Xaa\P 
+Partial match: Xaa
+    Xaaa\P
+Partial match: Xaaa
+    Xaaaa\P 
+Partial match: Xaaaa
+    
+/Xa{2,4}?b/
+    X\P
+Partial match: X
+    Xa\P
+Partial match: Xa
+    Xaa\P 
+Partial match: Xaa
+    Xaaa\P
+Partial match: Xaaa
+    Xaaaa\P 
+Partial match: Xaaaa
+    
+/Xa{2,4}+b/
+    X\P
+Partial match: X
+    Xa\P
+Partial match: Xa
+    Xaa\P 
+Partial match: Xaa
+    Xaaa\P
+Partial match: Xaaa
+    Xaaaa\P 
+Partial match: Xaaaa
+    
+/X\d{2,4}b/
+    X\P
+Partial match: X
+    X3\P
+Partial match: X3
+    X33\P 
+Partial match: X33
+    X333\P
+Partial match: X333
+    X3333\P 
+Partial match: X3333
+    
+/X\d{2,4}?b/
+    X\P
+Partial match: X
+    X3\P
+Partial match: X3
+    X33\P 
+Partial match: X33
+    X333\P
+Partial match: X333
+    X3333\P 
+Partial match: X3333
+    
+/X\d{2,4}+b/
+    X\P
+Partial match: X
+    X3\P
+Partial match: X3
+    X33\P 
+Partial match: X33
+    X333\P
+Partial match: X333
+    X3333\P 
+Partial match: X3333
+    
+/X\D{2,4}b/
+    X\P
+Partial match: X
+    Xa\P
+Partial match: Xa
+    Xaa\P 
+Partial match: Xaa
+    Xaaa\P
+Partial match: Xaaa
+    Xaaaa\P 
+Partial match: Xaaaa
+    
+/X\D{2,4}?b/
+    X\P
+Partial match: X
+    Xa\P
+Partial match: Xa
+    Xaa\P 
+Partial match: Xaa
+    Xaaa\P
+Partial match: Xaaa
+    Xaaaa\P 
+Partial match: Xaaaa
+    
+/X\D{2,4}+b/
+    X\P
+Partial match: X
+    Xa\P
+Partial match: Xa
+    Xaa\P 
+Partial match: Xaa
+    Xaaa\P
+Partial match: Xaaa
+    Xaaaa\P 
+Partial match: Xaaaa
+    
+/X[abc]{2,4}b/
+    X\P
+Partial match: X
+    Xa\P
+Partial match: Xa
+    Xaa\P 
+Partial match: Xaa
+    Xaaa\P
+Partial match: Xaaa
+    Xaaaa\P 
+Partial match: Xaaaa
+    
+/X[abc]{2,4}?b/
+    X\P
+Partial match: X
+    Xa\P
+Partial match: Xa
+    Xaa\P 
+Partial match: Xaa
+    Xaaa\P
+Partial match: Xaaa
+    Xaaaa\P 
+Partial match: Xaaaa
+    
+/X[abc]{2,4}+b/
+    X\P
+Partial match: X
+    Xa\P
+Partial match: Xa
+    Xaa\P 
+Partial match: Xaa
+    Xaaa\P
+Partial match: Xaaa
+    Xaaaa\P 
+Partial match: Xaaaa
+    
+/X[^a]{2,4}b/
+    X\P
+Partial match: X
+    Xz\P
+Partial match: Xz
+    Xzz\P 
+Partial match: Xzz
+    Xzzz\P
+Partial match: Xzzz
+    Xzzzz\P 
+Partial match: Xzzzz
+    
+/X[^a]{2,4}?b/
+    X\P
+Partial match: X
+    Xz\P
+Partial match: Xz
+    Xzz\P 
+Partial match: Xzz
+    Xzzz\P
+Partial match: Xzzz
+    Xzzzz\P 
+Partial match: Xzzzz
+    
+/X[^a]{2,4}+b/
+    X\P
+Partial match: X
+    Xz\P
+Partial match: Xz
+    Xzz\P 
+Partial match: Xzz
+    Xzzz\P
+Partial match: Xzzz
+    Xzzzz\P 
+Partial match: Xzzzz
+    
+/(Y)X\1{2,4}b/
+    YX\P
+Partial match: YX
+    YXY\P
+Partial match: YXY
+    YXYY\P 
+Partial match: YXYY
+    YXYYY\P
+Partial match: YXYYY
+    YXYYYY\P 
+Partial match: YXYYYY
+    
+/(Y)X\1{2,4}?b/
+    YX\P
+Partial match: YX
+    YXY\P
+Partial match: YXY
+    YXYY\P 
+Partial match: YXYY
+    YXYYY\P
+Partial match: YXYYY
+    YXYYYY\P 
+Partial match: YXYYYY
+    
+/(Y)X\1{2,4}+b/
+    YX\P
+Partial match: YX
+    YXY\P
+Partial match: YXY
+    YXYY\P 
+Partial match: YXYY
+    YXYYY\P
+Partial match: YXYYY
+    YXYYYY\P 
+Partial match: YXYYYY
+    
+/\++\KZ|\d+X|9+Y/
+    ++++123999\P
+Partial match: 123999
+    ++++123999Y\P
+ 0: 999Y
+    ++++Z1234\P 
+ 0: Z
+
+/Z(*F)/
+    Z\P
+No match
+    ZA\P 
+No match
+    
+/Z(?!)/
+    Z\P 
+No match
+    ZA\P 
+No match
+
+/dog(sbody)?/
+    dogs\P
+ 0: dog
+    dogs\P\P 
+Partial match: dogs
+    
+/dog(sbody)??/
+    dogs\P
+ 0: dog
+    dogs\P\P 
+ 0: dog
+
+/dog|dogsbody/
+    dogs\P
+ 0: dog
+    dogs\P\P 
+ 0: dog
+ 
+/dogsbody|dog/
+    dogs\P
+ 0: dog
+    dogs\P\P 
+Partial match: dogs
+
+/\bthe cat\b/
+    the cat\P
+ 0: the cat
+    the cat\P\P
+Partial match: the cat
+
+/abc/
+   abc\P
+ 0: abc
+   abc\P\P
+ 0: abc
+   
+/abc\K123/
+    xyzabc123pqr
+ 0: 123
+    xyzabc12\P
+Partial match: abc12
+    xyzabc12\P\P
+Partial match: abc12
+    
+/(?<=abc)123/
+    xyzabc123pqr 
+ 0: 123
+    xyzabc12\P
+Partial match: abc12
+    xyzabc12\P\P
+Partial match: abc12
+
+/\babc\b/
+    +++abc+++
+ 0: abc
+    +++ab\P
+Partial match: +ab
+    +++ab\P\P  
+Partial match: +ab
+
+/(?&word)(?&element)(?(DEFINE)(?<element><[^m][^>]>[^<])(?<word>\w*+))/BZ
+------------------------------------------------------------------
+        Bra
+        Recurse
+        Recurse
+        Cond
+        Cond def
+        CBra 1
+        <
+        [^m]
+        [^>]
+        >
+        [^<]
+        Ket
+        CBra 2
+        \w*+
+        Ket
+        Ket
+        Ket
+        End
+------------------------------------------------------------------
+
+/(?&word)(?&element)(?(DEFINE)(?<element><[^\d][^>]>[^<])(?<word>\w*+))/BZ
+------------------------------------------------------------------
+        Bra
+        Recurse
+        Recurse
+        Cond
+        Cond def
+        CBra 1
+        <
+        [\x00-/:-\xff] (neg)
+        [^>]
+        >
+        [^<]
+        Ket
+        CBra 2
+        \w*+
+        Ket
+        Ket
+        Ket
+        End
+------------------------------------------------------------------
+
+/(ab)(x(y)z(cd(*ACCEPT)))pq/BZ
+------------------------------------------------------------------
+        Bra
+        CBra 1
+        ab
+        Ket
+        CBra 2
+        x
+        CBra 3
+        y
+        Ket
+        z
+        CBra 4
+        cd
+        Close 4
+        Close 2
+        *ACCEPT
+        Ket
+        Ket
+        pq
+        Ket
+        End
+------------------------------------------------------------------
+
+/abc\K/+
+    abcdef
+ 0: 
+ 0+ def
+    abcdef\N\N
+ 0: 
+ 0+ def
+    xyzabcdef\N\N
+ 0: 
+ 0+ def
+    ** Failers
+No match
+    abcdef\N 
+No match
+    xyzabcdef\N
+No match
+    
+/^(?:(?=abc)|abc\K)/+
+    abcdef
+ 0: 
+ 0+ abcdef
+    abcdef\N\N 
+ 0: 
+ 0+ def
+    ** Failers 
+No match
+    abcdef\N 
+No match
+
+/a?b?/+
+    xyz
+ 0: 
+ 0+ xyz
+    xyzabc
+ 0: 
+ 0+ xyzabc
+    xyzabc\N
+ 0: ab
+ 0+ c
+    xyzabc\N\N
+ 0: 
+ 0+ yzabc
+    xyz\N\N    
+ 0: 
+ 0+ yz
+    ** Failers 
+ 0: 
+ 0+ ** Failers
+    xyz\N 
+No match
+
+/^a?b?/+
+    xyz
+ 0: 
+ 0+ xyz
+    xyzabc
+ 0: 
+ 0+ xyzabc
+    ** Failers 
+ 0: 
+ 0+ ** Failers
+    xyzabc\N
+No match
+    xyzabc\N\N
+No match
+    xyz\N\N    
+No match
+    xyz\N 
+No match
+    
+/^(?<name>a|b\g<name>c)/
+    aaaa
+ 0: a
+ 1: a
+    bacxxx
+ 0: bac
+ 1: bac
+    bbaccxxx 
+ 0: bbacc
+ 1: bbacc
+    bbbacccxx
+ 0: bbbaccc
+ 1: bbbaccc
+
+/^(?<name>a|b\g'name'c)/
+    aaaa
+ 0: a
+ 1: a
+    bacxxx
+ 0: bac
+ 1: bac
+    bbaccxxx 
+ 0: bbacc
+ 1: bbacc
+    bbbacccxx
+ 0: bbbaccc
+ 1: bbbaccc
+
+/^(a|b\g<1>c)/
+    aaaa
+ 0: a
+ 1: a
+    bacxxx
+ 0: bac
+ 1: bac
+    bbaccxxx 
+ 0: bbacc
+ 1: bbacc
+    bbbacccxx
+ 0: bbbaccc
+ 1: bbbaccc
+
+/^(a|b\g'1'c)/
+    aaaa
+ 0: a
+ 1: a
+    bacxxx
+ 0: bac
+ 1: bac
+    bbaccxxx 
+ 0: bbacc
+ 1: bbacc
+    bbbacccxx
+ 0: bbbaccc
+ 1: bbbaccc
+
+/^(a|b\g'-1'c)/
+    aaaa
+ 0: a
+ 1: a
+    bacxxx
+ 0: bac
+ 1: bac
+    bbaccxxx 
+ 0: bbacc
+ 1: bbacc
+    bbbacccxx
+ 0: bbbaccc
+ 1: bbbaccc
+
+/(^(a|b\g<-1>c))/
+    aaaa
+ 0: a
+ 1: a
+ 2: a
+    bacxxx
+ 0: bac
+ 1: bac
+ 2: bac
+    bbaccxxx 
+ 0: bbacc
+ 1: bbacc
+ 2: bbacc
+    bbbacccxx
+ 0: bbbaccc
+ 1: bbbaccc
+ 2: bbbaccc
+
+/(?-i:\g<name>)(?i:(?<name>a))/
+    XaaX
+ 0: aa
+ 1: a
+    XAAX 
+ 0: AA
+ 1: A
+
+/(?i:\g<name>)(?-i:(?<name>a))/
+    XaaX
+ 0: aa
+ 1: a
+    ** Failers 
+No match
+    XAAX 
+No match
+
+/(?-i:\g<+1>)(?i:(a))/
+    XaaX
+ 0: aa
+ 1: a
+    XAAX 
+ 0: AA
+ 1: A
+
+/(?=(?<regex>(?#simplesyntax)\$(?<name>[a-zA-Z_\x{7f}-\x{ff}][a-zA-Z0-9_\x{7f}-\x{ff}]*)(?:\[(?<index>[a-zA-Z0-9_\x{7f}-\x{ff}]+|\$\g<name>)\]|->\g<name>(\(.*?\))?)?|(?#simple syntax withbraces)\$\{(?:\g<name>(?<indices>\[(?:\g<index>|'(?:\\.|[^'\\])*'|"(?:\g<regex>|\\.|[^"\\])*")\])?|\g<complex>|\$\{\g<complex>\})\}|(?#complexsyntax)\{(?<complex>\$(?<segment>\g<name>(\g<indices>*|\(.*?\))?)(?:->\g<segment>)*|\$\g<complex>|\$\{\g<complex>\})\}))\{/
+
+/(?<n>a|b|c)\g<n>*/
+   abc
+ 0: abc
+ 1: a
+   accccbbb 
+ 0: accccbbb
+ 1: a
+
+/^X(?7)(a)(?|(b)|(q)(r)(s))(c)(d)(Y)/
+    XYabcdY
+ 0: XYabcdY
+ 1: a
+ 2: b
+ 3: <unset>
+ 4: <unset>
+ 5: c
+ 6: d
+ 7: Y
+
+/(?<=b(?1)|zzz)(a)/
+    xbaax
+ 0: a
+ 1: a
+    xzzzax 
+ 0: a
+ 1: a
+
+/(a)(?<=b\1)/
+Failed: lookbehind assertion is not fixed length at offset 10
+
+/(a)(?<=b+(?1))/
+Failed: lookbehind assertion is not fixed length at offset 13
+
+/(a+)(?<=b(?1))/
+Failed: lookbehind assertion is not fixed length at offset 14
+
+/(a(?<=b(?1)))/
+Failed: lookbehind assertion is not fixed length at offset 13
+
+/(?<=b(?1))xyz/
+Failed: reference to non-existent subpattern at offset 8
+
+/(?<=b(?1))xyz(b+)pqrstuvew/
+Failed: lookbehind assertion is not fixed length at offset 26
+
+/(a|bc)\1/SI
+Capturing subpattern count = 1
+Max back reference = 1
+No options
+No first char
+No need char
+Subject length lower bound = 2
+Starting byte set: a b 
+
+/(a|bc)\1{2,3}/SI
+Capturing subpattern count = 1
+Max back reference = 1
+No options
+No first char
+No need char
+Subject length lower bound = 3
+Starting byte set: a b 
+
+/(a|bc)(?1)/SI
+Capturing subpattern count = 1
+No options
+No first char
+No need char
+Subject length lower bound = 2
+Starting byte set: a b 
+
+/(a|b\1)(a|b\1)/SI
+Capturing subpattern count = 2
+Max back reference = 1
+No options
+No first char
+No need char
+Subject length lower bound = 2
+Starting byte set: a b 
+
+/(a|b\1){2}/SI
+Capturing subpattern count = 1
+Max back reference = 1
+No options
+No first char
+No need char
+Subject length lower bound = 2
+Starting byte set: a b 
+
+/(a|bbbb\1)(a|bbbb\1)/SI
+Capturing subpattern count = 2
+Max back reference = 1
+No options
+No first char
+No need char
+Subject length lower bound = 2
+Starting byte set: a b 
+
+/(a|bbbb\1){2}/SI
+Capturing subpattern count = 1
+Max back reference = 1
+No options
+No first char
+No need char
+Subject length lower bound = 2
+Starting byte set: a b 
+
+/^From +([^ ]+) +[a-zA-Z][a-zA-Z][a-zA-Z] +[a-zA-Z][a-zA-Z][a-zA-Z] +[0-9]?[0-9] +[0-9][0-9]:[0-9][0-9]/SI
+Capturing subpattern count = 1
+Options: anchored
+No first char
+Need char = ':'
+Subject length lower bound = 22
+No set of starting bytes
+
+/<tr([\w\W\s\d][^<>]{0,})><TD([\w\W\s\d][^<>]{0,})>([\d]{0,}\.)(.*)((<BR>([\w\W\s\d][^<>]{0,})|[\s]{0,}))<\/a><\/TD><TD([\w\W\s\d][^<>]{0,})>([\w\W\s\d][^<>]{0,})<\/TD><TD([\w\W\s\d][^<>]{0,})>([\w\W\s\d][^<>]{0,})<\/TD><\/TR>/isIS
+Capturing subpattern count = 11
+Options: caseless dotall
+First char = '<'
+Need char = '>'
+Subject length lower bound = 47
+No set of starting bytes
+
+"(?>.*/)foo"SI
+Capturing subpattern count = 0
+No options
+First char at start or follows newline
+Need char = 'o'
+Subject length lower bound = 4
+No set of starting bytes
+
+/(?(?=[^a-z]+[a-z])  \d{2}-[a-z]{3}-\d{2}  |  \d{2}-\d{2}-\d{2} ) /xSI
+Capturing subpattern count = 0
+Options: extended
+No first char
+Need char = '-'
+Subject length lower bound = 8
+No set of starting bytes
+
+/(?:(?:(?:(?:(?:(?:(?:(?:(?:(a|b|c))))))))))/iSI
+Capturing subpattern count = 1
+Options: caseless
+No first char
+No need char
+Subject length lower bound = 1
+Starting byte set: A B C a b c 
+
+/(?:c|d)(?:)(?:aaaaaaaa(?:)(?:bbbbbbbb)(?:bbbbbbbb(?:))(?:bbbbbbbb(?:)(?:bbbbbbbb)))/SI
+Capturing subpattern count = 0
+No options
+No first char
+Need char = 'b'
+Subject length lower bound = 41
+Starting byte set: c d 
+
+/<a[\s]+href[\s]*=[\s]*          # find <a href=
+ ([\"\'])?                       # find single or double quote
+ (?(1) (.*?)\1 | ([^\s]+))       # if quote found, match up to next matching
+                                 # quote, otherwise match up to next space
+/isxSI
+Capturing subpattern count = 3
+Max back reference = 1
+Options: caseless extended dotall
+First char = '<'
+Need char = '='
+Subject length lower bound = 9
+No set of starting bytes
+
+/^(?!:)                       # colon disallowed at start
+  (?:                         # start of item
+    (?: [0-9a-f]{1,4} |       # 1-4 hex digits or
+    (?(1)0 | () ) )           # if null previously matched, fail; else null
+    :                         # followed by colon
+  ){1,7}                      # end item; 1-7 of them required               
+  [0-9a-f]{1,4} $             # final hex number at end of string
+  (?(1)|.)                    # check that there was an empty component
+  /xiIS
+Capturing subpattern count = 1
+Options: anchored caseless extended
+No first char
+Need char = ':'
+Subject length lower bound = 2
+No set of starting bytes
+
+/(?|(?<a>A)|(?<a>B))/I
+Capturing subpattern count = 1
+Named capturing subpatterns:
+  a   1
+  a   1
+No options
+No first char
+No need char
+    AB\Ca
+ 0: A
+ 1: A
+  C A (1) a
+    BA\Ca
+ 0: B
+ 1: B
+  C B (1) a
+
+/(?|(?<a>A)|(?<b>B))/ 
+Failed: different names for subpatterns of the same number are not allowed at offset 15
+
+/(?:a(?<quote> (?<apostrophe>')|(?<realquote>")) |
+    b(?<quote> (?<apostrophe>')|(?<realquote>")) ) 
+    (?('quote')[a-z]+|[0-9]+)/JIx
+Capturing subpattern count = 6
+Named capturing subpatterns:
+  apostrophe   2
+  apostrophe   5
+  quote        1
+  quote        4
+  realquote    3
+  realquote    6
+Options: extended dupnames
+No first char
+No need char
+    a"aaaaa
+ 0: a"aaaaa
+ 1: "
+ 2: <unset>
+ 3: "
+    b"aaaaa 
+ 0: b"aaaaa
+ 1: <unset>
+ 2: <unset>
+ 3: <unset>
+ 4: "
+ 5: <unset>
+ 6: "
+    ** Failers 
+No match
+    b"11111
+No match
+    a"11111 
+No match
+    
+/^(?|(a)(b)(c)(?<D>d)|(?<D>e)) (?('D')X|Y)/JDZx
+------------------------------------------------------------------
+        Bra
+        ^
+        Bra
+        CBra 1
+        a
+        Ket
+        CBra 2
+        b
+        Ket
+        CBra 3
+        c
+        Ket
+        CBra 4
+        d
+        Ket
+        Alt
+        CBra 1
+        e
+        Ket
+        Ket
+        Cond
+      4 Cond nref
+        X
+        Alt
+        Y
+        Ket
+        Ket
+        End
+------------------------------------------------------------------
+Capturing subpattern count = 4
+Named capturing subpatterns:
+  D   4
+  D   1
+Options: anchored extended dupnames
+No first char
+No need char
+    abcdX
+ 0: abcdX
+ 1: a
+ 2: b
+ 3: c
+ 4: d
+    eX
+ 0: eX
+ 1: e
+    ** Failers
+No match
+    abcdY
+No match
+    ey     
+No match
+    
+/(?<A>a) (b)(c)  (?<A>d  (?(R&A)$ | (?4)) )/JDZx
+------------------------------------------------------------------
+        Bra
+        CBra 1
+        a
+        Ket
+        CBra 2
+        b
+        Ket
+        CBra 3
+        c
+        Ket
+        CBra 4
+        d
+        Cond
+        Cond nrecurse 1
+        $
+        Alt
+        Recurse
+        Ket
+        Ket
+        Ket
+        End
+------------------------------------------------------------------
+Capturing subpattern count = 4
+Named capturing subpatterns:
+  A   1
+  A   4
+Options: extended dupnames
+First char = 'a'
+Need char = 'd'
+    abcdd
+ 0: abcdd
+ 1: a
+ 2: b
+ 3: c
+ 4: dd
+    ** Failers
+No match
+    abcdde  
+No match
+
+/abcd*/
+    xxxxabcd\P
+ 0: abcd
+    xxxxabcd\P\P
+Partial match: abcd
+
+/abcd*/i
+    xxxxabcd\P
+ 0: abcd
+    xxxxabcd\P\P
+Partial match: abcd
+    XXXXABCD\P
+ 0: ABCD
+    XXXXABCD\P\P
+Partial match: ABCD
+
+/abc\d*/
+    xxxxabc1\P
+ 0: abc1
+    xxxxabc1\P\P
+Partial match: abc1
+
+/(a)bc\1*/
+    xxxxabca\P
+ 0: abca
+ 1: a
+    xxxxabca\P\P
+Partial match: abca
+
+/abc[de]*/
+    xxxxabcde\P
+ 0: abcde
+    xxxxabcde\P\P
+Partial match: abcde
+
+/-- This is not in the Perl >= 5.10 test because Perl seems currently to be
+    broken and not behaving as specified in that it *does* bumpalong after
+    hitting (*COMMIT). --/
+
+/(?1)(A(*COMMIT)|B)D/
+    ABD
+ 0: ABD
+ 1: B
+    XABD
+ 0: ABD
+ 1: B
+    BAD
+ 0: BAD
+ 1: A
+    ABXABD  
+ 0: ABD
+ 1: B
+    ** Failers 
+No match
+    ABX 
+No match
+    BAXBAD  
+No match
+
+/(\3)(\1)(a)/<JS>
+    cat
+ 0: a
+ 1: 
+ 2: 
+ 3: a
+
+/(\3)(\1)(a)/SI<JS>
+Capturing subpattern count = 3
+Max back reference = 3
+Options:
+No first char
+Need char = 'a'
+Subject length lower bound = 1
+No set of starting bytes
+    cat
+ 0: a
+ 1: 
+ 2: 
+ 3: a
+
+/(\3)(\1)(a)/SI
+Capturing subpattern count = 3
+Max back reference = 3
+No options
+No first char
+Need char = 'a'
+Subject length lower bound = 3
+No set of starting bytes
+    cat
+No match
+
+/i(?(DEFINE)(?<s>a))/SI
+Capturing subpattern count = 1
+Named capturing subpatterns:
+  s   1
+No options
+First char = 'i'
+No need char
+Subject length lower bound = 1
+No set of starting bytes
+    i
+ 0: i
+    
+/()i(?(1)a)/SI 
+Capturing subpattern count = 1
+No options
+No first char
+Need char = 'i'
+Subject length lower bound = 1
+Starting byte set: i 
+    ia
+ 0: ia
+ 1: 
+
+/(?i)a(?-i)b|c/BZ
+------------------------------------------------------------------
+        Bra
+     /i a
+        b
+        Alt
+        c
+        Ket
+        End
+------------------------------------------------------------------
+    XabX
+ 0: ab
+    XAbX
+ 0: Ab
+    CcC 
+ 0: c
+    ** Failers
+No match
+    XABX   
+No match
+
+/(?i)a(?s)b|c/BZ
+------------------------------------------------------------------
+        Bra
+     /i ab
+        Alt
+     /i c
+        Ket
+        End
+------------------------------------------------------------------
+
+/(?i)a(?s-i)b|c/BZ
+------------------------------------------------------------------
+        Bra
+     /i a
+        b
+        Alt
+        c
+        Ket
+        End
+------------------------------------------------------------------
+
+/^(ab(c\1)d|x){2}$/BZ
+------------------------------------------------------------------
+        Bra
+        ^
+        Once
+        CBra 1
+        ab
+        CBra 2
+        c
+        \1
+        Ket
+        d
+        Alt
+        x
+        Ket
+        Ket
+        Once
+        CBra 1
+        ab
+        CBra 2
+        c
+        \1
+        Ket
+        d
+        Alt
+        x
+        Ket
+        Ket
+        $
+        Ket
+        End
+------------------------------------------------------------------
+    xabcxd
+ 0: xabcxd
+ 1: abcxd
+ 2: cx
+    
+/^(?&t)*+(?(DEFINE)(?<t>.))$/BZ
+------------------------------------------------------------------
+        Bra
+        ^
+        Braposzero
+        SBraPos
+        Recurse
+        KetRpos
+        Cond
+        Cond def
+        CBra 1
+        Any
+        Ket
+        Ket
+        $
+        Ket
+        End
+------------------------------------------------------------------
+
+/^(?&t)*(?(DEFINE)(?<t>.))$/BZ
+------------------------------------------------------------------
+        Bra
+        ^
+        Brazero
+        Once
+        Recurse
+        KetRmax
+        Cond
+        Cond def
+        CBra 1
+        Any
+        Ket
+        Ket
+        $
+        Ket
+        End
+------------------------------------------------------------------
+
+/ -- The first four of these are not in the Perl >= 5.10 test because Perl 
+     documents that the use of \K in assertions is "not well defined". The
+     last is here because Perl gives the match as "b" rather than "ab". I
+     believe this to be a Perl bug. --/  
+      
+/(?=a\Kb)ab/
+    ab 
+ 0: b
+
+/(?!a\Kb)ac/
+    ac 
+ 0: ac
+    
+/^abc(?<=b\Kc)d/
+    abcd
+ 0: cd
+
+/^abc(?<!b\Kq)d/
+    abcd
+ 0: abcd
+
+/(?>a\Kb)z|(ab)/
+    ab 
+ 0: ab
+ 1: ab
+
+/----------------------/
+
+/(?P<L1>(?P<L2>0|)|(?P>L2)(?P>L1))/
+Failed: recursive call could loop indefinitely at offset 31
+
+/abc(*MARK:)pqr/
+Failed: (*MARK) must have an argument at offset 10
+
+/abc(*:)pqr/
+Failed: (*MARK) must have an argument at offset 6
+
+/abc(*FAIL:123)xyz/
+Failed: an argument is not allowed for (*ACCEPT), (*FAIL), or (*COMMIT) at offset 13
+
+/--- This should, and does, fail. In Perl, it does not, which I think is a 
+     bug because replacing the B in the pattern by (B|D) does make it fail. ---/
+
+/A(*COMMIT)B/+K
+    ACABX
+No match
+
+/--- These should be different, but in Perl 5.11 are not, which I think
+     is a bug in Perl. ---/
+
+/A(*THEN)B|A(*THEN)C/K
+    AC
+ 0: AC
+
+/A(*PRUNE)B|A(*PRUNE)C/K
+    AC
+No match
+    
+/--- This should fail; the SKIP advances by one, but when we get to AC, the
+     PRUNE kills it. Perl behaves differently. ---/ 
+    
+/A(*PRUNE:A)A+(*SKIP:A)(B|Z) | AC/xK
+    AAAC
+No match, mark = A
+
+/--- Mark names can be duplicated. Perl doesn't give a mark for this one,
+though PCRE does. ---/
+
+/^A(*:A)B|^X(*:A)Y/K
+    ** Failers
+No match
+    XAQQ
+No match, mark = A
+    
+/--- COMMIT at the start of a pattern should be the same as an anchor. Perl 
+optimizations defeat this. So does the PCRE optimization unless we disable it 
+with \Y. ---/
+
+/(*COMMIT)ABC/
+    ABCDEFG
+ 0: ABC
+    ** Failers
+No match
+    DEFGABC\Y  
+No match
+    
+/^(ab (c+(*THEN)cd) | xyz)/x
+    abcccd  
+No match
+
+/^(ab (c+(*PRUNE)cd) | xyz)/x
+    abcccd  
+No match
+
+/^(ab (c+(*FAIL)cd) | xyz)/x
+    abcccd  
+No match
+    
+/--- Perl 5.11 gets some of these wrong ---/ 
+
+/(?>.(*ACCEPT))*?5/
+    abcde
+ 0: a
+
+/(.(*ACCEPT))*?5/
+    abcde
+ 0: a
+ 1: a
+
+/(.(*ACCEPT))5/
+    abcde
+ 0: a
+ 1: a
+
+/(.(*ACCEPT))*5/
+    abcde
+ 0: a
+ 1: a
+
+/A\NB./BZ
+------------------------------------------------------------------
+        Bra
+        A
+        Any
+        B
+        Any
+        Ket
+        End
+------------------------------------------------------------------
+    ACBD
+ 0: ACBD
+    *** Failers
+No match
+    A\nB
+No match
+    ACB\n   
+No match
+
+/A\NB./sBZ
+------------------------------------------------------------------
+        Bra
+        A
+        Any
+        B
+        AllAny
+        Ket
+        End
+------------------------------------------------------------------
+    ACBD
+ 0: ACBD
+    ACB\n 
+ 0: ACB\x0a
+    *** Failers
+No match
+    A\nB  
+No match
+  
+/A\NB/<crlf>
+    A\nB
+ 0: A\x0aB
+    A\rB
+ 0: A\x0dB
+    ** Failers
+No match
+    A\r\nB    
+No match
+
+/\R+b/BZ
+------------------------------------------------------------------
+        Bra
+        \R++
+        b
+        Ket
+        End
+------------------------------------------------------------------
+
+/\R+\n/BZ
+------------------------------------------------------------------
+        Bra
+        \R+
+        \x0a
+        Ket
+        End
+------------------------------------------------------------------
+
+/\R+\d/BZ
+------------------------------------------------------------------
+        Bra
+        \R++
+        \d
+        Ket
+        End
+------------------------------------------------------------------
+
+/\d*\R/BZ
+------------------------------------------------------------------
+        Bra
+        \d*+
+        \R
+        Ket
+        End
+------------------------------------------------------------------
+
+/\s*\R/BZ
+------------------------------------------------------------------
+        Bra
+        \s*
+        \R
+        Ket
+        End
+------------------------------------------------------------------
+    \x20\x0a
+ 0:  \x0a
+    \x20\x0d
+ 0:  \x0d
+    \x20\x0d\x0a
+ 0:  \x0d\x0a
+
+/\S*\R/BZ
+------------------------------------------------------------------
+        Bra
+        \S*+
+        \R
+        Ket
+        End
+------------------------------------------------------------------
+    a\x0a
+ 0: a\x0a
+
+/X\h*\R/BZ
+------------------------------------------------------------------
+        Bra
+        X
+        \h*+
+        \R
+        Ket
+        End
+------------------------------------------------------------------
+    X\x20\x0a
+ 0: X \x0a
+
+/X\H*\R/BZ
+------------------------------------------------------------------
+        Bra
+        X
+        \H*
+        \R
+        Ket
+        End
+------------------------------------------------------------------
+    X\x0d\x0a
+ 0: X\x0d\x0a
+
+/X\H+\R/BZ
+------------------------------------------------------------------
+        Bra
+        X
+        \H+
+        \R
+        Ket
+        End
+------------------------------------------------------------------
+    X\x0d\x0a
+ 0: X\x0d\x0a
+
+/X\H++\R/BZ
+------------------------------------------------------------------
+        Bra
+        X
+        \H++
+        \R
+        Ket
+        End
+------------------------------------------------------------------
+    X\x0d\x0a
+No match
+
+/-- Perl treats this one differently, not failing the second string. I believe
+    that is a bug in Perl. --/
+
+/^((abc|abcx)(*THEN)y|abcd)/
+    abcd
+ 0: abcd
+ 1: abcd
+    *** Failers 
+No match
+    abcxy 
+No match
+
+/(?<=abc)def/
+    abc\P\P
+Partial match: abc
+
+/abc$/
+    abc
+ 0: abc
+    abc\P
+ 0: abc
+    abc\P\P
+Partial match: abc
+
+/abc$/m
+    abc
+ 0: abc
+    abc\n
+ 0: abc
+    abc\P\P
+Partial match: abc
+    abc\n\P\P 
+ 0: abc
+    abc\P
+ 0: abc
+    abc\n\P
+ 0: abc
+
+/abc\z/
+    abc
+ 0: abc
+    abc\P
+ 0: abc
+    abc\P\P
+Partial match: abc
+
+/abc\Z/
+    abc
+ 0: abc
+    abc\P
+ 0: abc
+    abc\P\P
+Partial match: abc
+
+/abc\b/
+    abc
+ 0: abc
+    abc\P
+ 0: abc
+    abc\P\P
+Partial match: abc
+
+/abc\B/
+    abc
+No match
+    abc\P
+Partial match: abc
+    abc\P\P
+Partial match: abc
+
+/.+/
+    abc\>0
+ 0: abc
+    abc\>1
+ 0: bc
+    abc\>2
+ 0: c
+    abc\>3
+No match
+    abc\>4
+Error -24 (bad offset value)
+    abc\>-4 
+Error -24 (bad offset value)
+
+/^\cģ/
+Failed: \c must be followed by an ASCII character at offset 3
+
+/(?P<abn>(?P=abn)xxx)/BZ
+------------------------------------------------------------------
+        Bra
+        Once
+        CBra 1
+        \1
+        xxx
+        Ket
+        Ket
+        Ket
+        End
+------------------------------------------------------------------
+
+/(a\1z)/BZ
+------------------------------------------------------------------
+        Bra
+        Once
+        CBra 1
+        a
+        \1
+        z
+        Ket
+        Ket
+        Ket
+        End
+------------------------------------------------------------------
+
+/(?P<abn>(?P=abn)(?<badstufxxx)/BZ
+Failed: syntax error in subpattern name (missing terminator) at offset 29
+
+/(?P<abn>(?P=axn)xxx)/BZ
+Failed: reference to non-existent subpattern at offset 15
+
+/(?P<abn>(?P=axn)xxx)(?<axn>yy)/BZ
+------------------------------------------------------------------
+        Bra
+        CBra 1
+        \2
+        xxx
+        Ket
+        CBra 2
+        yy
+        Ket
+        Ket
+        End
+------------------------------------------------------------------
+
+/-- These tests are here because Perl gets the first one wrong. --/
+
+/(\R*)(.)/s
+    \r\n
+ 0: \x0d
+ 1: 
+ 2: \x0d
+    \r\r\n\n\r 
+ 0: \x0d\x0d\x0a\x0a\x0d
+ 1: \x0d\x0d\x0a\x0a
+ 2: \x0d
+    \r\r\n\n\r\n 
+ 0: \x0d\x0d\x0a\x0a\x0d
+ 1: \x0d\x0d\x0a\x0a
+ 2: \x0d
+
+/(\R)*(.)/s
+    \r\n
+ 0: \x0d
+ 1: <unset>
+ 2: \x0d
+    \r\r\n\n\r 
+ 0: \x0d\x0d\x0a\x0a\x0d
+ 1: \x0a
+ 2: \x0d
+    \r\r\n\n\r\n 
+ 0: \x0d\x0d\x0a\x0a\x0d
+ 1: \x0a
+ 2: \x0d
+
+/((?>\r\n|\n|\x0b|\f|\r|\x85)*)(.)/s
+    \r\n
+ 0: \x0d
+ 1: 
+ 2: \x0d
+    \r\r\n\n\r 
+ 0: \x0d\x0d\x0a\x0a\x0d
+ 1: \x0d\x0d\x0a\x0a
+ 2: \x0d
+    \r\r\n\n\r\n 
+ 0: \x0d\x0d\x0a\x0a\x0d
+ 1: \x0d\x0d\x0a\x0a
+ 2: \x0d
+
+/-- --/
+
+/^abc$/BZ
+------------------------------------------------------------------
+        Bra
+        ^
+        abc
+        $
+        Ket
+        End
+------------------------------------------------------------------
+
+/^abc$/BZm
+------------------------------------------------------------------
+        Bra
+     /m ^
+        abc
+     /m $
+        Ket
+        End
+------------------------------------------------------------------
+
+/^(a)*+(\w)/S
+    aaaaX
+ 0: aaaaX
+ 1: a
+ 2: X
+    ** Failers 
+No match
+    aaaa
+No match
+
+/^(?:a)*+(\w)/S
+    aaaaX
+ 0: aaaaX
+ 1: X
+    ** Failers 
+No match
+    aaaa
+No match
+
+/(a)++1234/SDZ
+------------------------------------------------------------------
+        Bra
+        CBraPos 1
+        a
+        KetRpos
+        1234
+        Ket
+        End
+------------------------------------------------------------------
+Capturing subpattern count = 1
+No options
+First char = 'a'
+Need char = '4'
+Subject length lower bound = 5
+No set of starting bytes
+
+/([abc])++1234/SI
+Capturing subpattern count = 1
+No options
+No first char
+Need char = '4'
+Subject length lower bound = 5
+Starting byte set: a b c 
+
+/(?<=(abc)+)X/
+Failed: lookbehind assertion is not fixed length at offset 10
+
+/(^ab)/I
+Capturing subpattern count = 1
+Options: anchored
+No first char
+No need char
+
+/(^ab)++/I
+Capturing subpattern count = 1
+Options: anchored
+No first char
+No need char
+
+/(^ab|^)+/I
+Capturing subpattern count = 1
+Options: anchored
+No first char
+No need char
+
+/(^ab|^)++/I
+Capturing subpattern count = 1
+Options: anchored
+No first char
+No need char
+
+/(?:^ab)/I
+Capturing subpattern count = 0
+Options: anchored
+No first char
+No need char
+
+/(?:^ab)++/I
+Capturing subpattern count = 0
+Options: anchored
+No first char
+No need char
+
+/(?:^ab|^)+/I
+Capturing subpattern count = 0
+Options: anchored
+No first char
+No need char
+
+/(?:^ab|^)++/I
+Capturing subpattern count = 0
+Options: anchored
+No first char
+No need char
+
+/(.*ab)/I
+Capturing subpattern count = 1
+No options
+First char at start or follows newline
+Need char = 'b'
+
+/(.*ab)++/I
+Capturing subpattern count = 1
+No options
+First char at start or follows newline
+Need char = 'b'
+
+/(.*ab|.*)+/I
+Capturing subpattern count = 1
+No options
+First char at start or follows newline
+No need char
+
+/(.*ab|.*)++/I
+Capturing subpattern count = 1
+No options
+First char at start or follows newline
+No need char
+
+/(?:.*ab)/I
+Capturing subpattern count = 0
+No options
+First char at start or follows newline
+Need char = 'b'
+
+/(?:.*ab)++/I
+Capturing subpattern count = 0
+No options
+First char at start or follows newline
+Need char = 'b'
+
+/(?:.*ab|.*)+/I
+Capturing subpattern count = 0
+No options
+First char at start or follows newline
+No need char
+
+/(?:.*ab|.*)++/I
+Capturing subpattern count = 0
+No options
+First char at start or follows newline
+No need char
+
+/(?=a)[bcd]/I
+Capturing subpattern count = 0
+No options
+First char = 'a'
+No need char
+
+/((?=a))[bcd]/I
+Capturing subpattern count = 1
+No options
+First char = 'a'
+No need char
+
+/((?=a))+[bcd]/I
+Capturing subpattern count = 1
+No options
+First char = 'a'
+No need char
+
+/((?=a))++[bcd]/I
+Capturing subpattern count = 1
+No options
+First char = 'a'
+No need char
+
+/(?=a+)[bcd]/iI
+Capturing subpattern count = 0
+Options: caseless
+First char = 'a' (caseless)
+No need char
+
+/(?=a+?)[bcd]/iI
+Capturing subpattern count = 0
+Options: caseless
+First char = 'a' (caseless)
+No need char
+
+/(?=a++)[bcd]/iI
+Capturing subpattern count = 0
+Options: caseless
+First char = 'a' (caseless)
+No need char
+
+/(?=a{3})[bcd]/iI
+Capturing subpattern count = 0
+Options: caseless
+First char = 'a' (caseless)
+Need char = 'a' (caseless)
+
+/(abc)\1+/S
+
+/-- Perl doesn't get these right IMO (the 3rd is PCRE-specific) --/
+
+/(?1)(?:(b(*ACCEPT))){0}/
+    b
+ 0: b
+
+/(?1)(?:(b(*ACCEPT))){0}c/
+    bc
+ 0: bc
+    ** Failers 
+No match
+    b 
+No match
+
+/(?1)(?:((*ACCEPT))){0}c/
+    c
+ 0: c
+    c\N 
+ 0: c
+
+/^.*?(?(?=a)a|b(*THEN)c)/
+    ba
+No match
+
+/^.*?(?(?=a)a|bc)/
+    ba
+ 0: ba
+
+/^.*?(?(?=a)a(*THEN)b|c)/
+    ac
+No match
+
+/^.*?(?(?=a)a(*THEN)b)c/
+    ac
+No match
+
+/^.*?(a(*THEN)b)c/
+    aabc
+No match
+    
+/^.*? (?1) c (?(DEFINE)(a(*THEN)b))/x
+    aabc
+ 0: aabc
+
+/^.*?(a(*THEN)b|z)c/
+    aabc
+ 0: aabc
+ 1: ab
+
+/^.*?(z|a(*THEN)b)c/
+    aabc
+ 0: aabc
+ 1: ab
+
+/-- --/
+
+/-- These studied versions are here because they are not Perl-compatible; the
+    studying means the mark is not seen. --/
+
+/(*MARK:A)(*SKIP:B)(C|X)/KS
+    C
+ 0: C
+ 1: C
+MK: A
+    D
+No match, mark = A
+     
+/(*:A)A+(*SKIP:A)(B|Z)/KS
+    AAAC
+No match, mark = A
+
+/-- --/
+
+"(?=a*(*ACCEPT)b)c"
+    c
+ 0: c
+    c\N 
+ 0: c
+    
+/(?1)c(?(DEFINE)((*ACCEPT)b))/
+    c
+ 0: c
+    c\N  
+ 0: c
+    
+/(?>(*ACCEPT)b)c/
+    c
+ 0: 
+    c\N  
+No match
+
+/(?:(?>(a)))+a%/++
+    %aa%
+ 0: aa%
+ 0+ 
+ 1: a
+ 1+ a%
+
+/(a)b|ac/++SS
+    ac\O3
+Matched, but too many substrings
+ 0: ac
+ 0+ 
+    
+/(a)(b)x|abc/++
+     abc\O6
+ 0: abc
+ 0+ 
+
+/(a)bc|(a)(b)\2/
+    \O3abc
+Matched, but too many substrings
+ 0: abc
+    \O4abc 
+Matched, but too many substrings
+ 0: abc
+
+/(?(DEFINE)(a(?2)|b)(b(?1)|a))(?:(?1)|(?2))/SI
+Capturing subpattern count = 2
+No options
+No first char
+No need char
+Subject length lower bound = 1
+No set of starting bytes
+
+/(a(?2)|b)(b(?1)|a)(?:(?1)|(?2))/SI
+Capturing subpattern count = 2
+No options
+No first char
+No need char
+Subject length lower bound = 3
+Starting byte set: a b 
+
+/(a(?2)|b)(b(?1)|a)(?1)(?2)/SI
+Capturing subpattern count = 2
+No options
+No first char
+No need char
+Subject length lower bound = 4
+Starting byte set: a b 
+
+/(abc)(?1)/SI
+Capturing subpattern count = 1
+No options
+First char = 'a'
+Need char = 'c'
+Subject length lower bound = 6
+No set of starting bytes
+
+/^(?>a)++/
+    aa\M
+Minimum match() limit = 5
+Minimum match() recursion limit = 2
+ 0: aa
+    aaaaaaaaa\M 
+Minimum match() limit = 12
+Minimum match() recursion limit = 2
+ 0: aaaaaaaaa
+    
+/(a)(?1)++/
+    aa\M
+Minimum match() limit = 7
+Minimum match() recursion limit = 4
+ 0: aa
+ 1: a
+    aaaaaaaaa\M  
+Minimum match() limit = 21
+Minimum match() recursion limit = 4
+ 0: aaaaaaaaa
+ 1: a
+
+/(?:(foo)|(bar)|(baz))X/SS=
+    bazfooX
+ 0: fooX
+ 1: foo
+ 2: <unset>
+ 3: <unset>
+    foobazbarX
+ 0: barX
+ 1: <unset>
+ 2: bar
+ 3: <unset>
+    barfooX
+ 0: fooX
+ 1: foo
+ 2: <unset>
+ 3: <unset>
+    bazX
+ 0: bazX
+ 1: <unset>
+ 2: <unset>
+ 3: baz
+    foobarbazX    
+ 0: bazX
+ 1: <unset>
+ 2: <unset>
+ 3: baz
+    bazfooX\O0
+Matched, but too many substrings
+    bazfooX\O2
+Matched, but too many substrings
+ 0: fooX
+    bazfooX\O4
+Matched, but too many substrings
+ 0: fooX
+ 1: <unset>
+    bazfooX\O6
+Matched, but too many substrings
+ 0: fooX
+ 1: foo
+ 2: <unset>
+    bazfooX\O8
+Matched, but too many substrings
+ 0: fooX
+ 1: foo
+ 2: <unset>
+ 3: <unset>
+    bazfooX\O10
+ 0: fooX
+ 1: foo
+ 2: <unset>
+ 3: <unset>
+
+/(?=abc){3}abc/BZ
+------------------------------------------------------------------
+        Bra
+        Assert
+        abc
+        Ket
+        abc
+        Ket
+        End
+------------------------------------------------------------------
+
+/(?=abc)+abc/BZ
+------------------------------------------------------------------
+        Bra
+        Assert
+        abc
+        Ket
+        abc
+        Ket
+        End
+------------------------------------------------------------------
+
+/(?=abc)++abc/BZ
+------------------------------------------------------------------
+        Bra
+        Assert
+        abc
+        Ket
+        abc
+        Ket
+        End
+------------------------------------------------------------------
+
+/(?=abc){0}xyz/BZ
+------------------------------------------------------------------
+        Bra
+        Skip zero
+        Assert
+        abc
+        Ket
+        xyz
+        Ket
+        End
+------------------------------------------------------------------
+
+/(?=(a))?./BZ
+------------------------------------------------------------------
+        Bra
+        Brazero
+        Assert
+        CBra 1
+        a
+        Ket
+        Ket
+        Any
+        Ket
+        End
+------------------------------------------------------------------
+
+/(?=(a))??./BZ
+------------------------------------------------------------------
+        Bra
+        Braminzero
+        Assert
+        CBra 1
+        a
+        Ket
+        Ket
+        Any
+        Ket
+        End
+------------------------------------------------------------------
+
+/^(?=(a)){0}b(?1)/BZ
+------------------------------------------------------------------
+        Bra
+        ^
+        Skip zero
+        Assert
+        CBra 1
+        a
+        Ket
+        Ket
+        b
+        Recurse
+        Ket
+        End
+------------------------------------------------------------------
+
+/(?(DEFINE)(a))?b(?1)/BZ
+------------------------------------------------------------------
+        Bra
+        Cond
+        Cond def
+        CBra 1
+        a
+        Ket
+        Ket
+        b
+        Recurse
+        Ket
+        End
+------------------------------------------------------------------
+
+/^(?=(?1))?[az]([abc])d/BZ
+------------------------------------------------------------------
+        Bra
+        ^
+        Brazero
+        Assert
+        Recurse
+        Ket
+        [az]
+        CBra 1
+        [a-c]
+        Ket
+        d
+        Ket
+        End
+------------------------------------------------------------------
+
+/^(?!a){0}\w+/BZ
+------------------------------------------------------------------
+        Bra
+        ^
+        Skip zero
+        Assert not
+        a
+        Ket
+        \w+
+        Ket
+        End
+------------------------------------------------------------------
+
+/(?<=(abc))?xyz/BZ
+------------------------------------------------------------------
+        Bra
+        Brazero
+        AssertB
+        Reverse
+        CBra 1
+        abc
+        Ket
+        Ket
+        xyz
+        Ket
+        End
+------------------------------------------------------------------
+
+/[:a[:abc]b:]/BZ
+------------------------------------------------------------------
+        Bra
+        [:[a-c]
+        b:]
+        Ket
+        End
+------------------------------------------------------------------
+
+/((?2))((?1))/SS
+    abc
+Error -26 (nested recursion at the same subject position)
+
+/((?(R2)a+|(?1)b))/SS
+    aaaabcde
+Error -26 (nested recursion at the same subject position)
+
+/(?(R)a*(?1)|((?R))b)/SS
+    aaaabcde
+Error -26 (nested recursion at the same subject position)
+
+/(a+|(?R)b)/
+Failed: recursive call could loop indefinitely at offset 7
+
+/^(a(*:A)(d|e(*:B))z|aeq)/C
+    adz
+--->adz
+ +0 ^       ^
+ +1 ^       (a(*:A)(d|e(*:B))z|aeq)
+ +2 ^       a
+ +3 ^^      (*:A)
+ +8 ^^      (d|e(*:B))
+Latest Mark: A
+ +9 ^^      d
++10 ^ ^     |
++18 ^ ^     z
++19 ^  ^    |
++24 ^  ^    
+ 0: adz
+ 1: adz
+ 2: d
+    aez
+--->aez
+ +0 ^       ^
+ +1 ^       (a(*:A)(d|e(*:B))z|aeq)
+ +2 ^       a
+ +3 ^^      (*:A)
+ +8 ^^      (d|e(*:B))
+Latest Mark: A
+ +9 ^^      d
++11 ^^      e
++12 ^ ^     (*:B)
++17 ^ ^     )
+Latest Mark: B
++18 ^ ^     z
++19 ^  ^    |
++24 ^  ^    
+ 0: aez
+ 1: aez
+ 2: e
+    aeqwerty
+--->aeqwerty
+ +0 ^            ^
+ +1 ^            (a(*:A)(d|e(*:B))z|aeq)
+ +2 ^            a
+ +3 ^^           (*:A)
+ +8 ^^           (d|e(*:B))
+Latest Mark: A
+ +9 ^^           d
++11 ^^           e
++12 ^ ^          (*:B)
++17 ^ ^          )
+Latest Mark: B
++18 ^ ^          z
++20 ^            a
++21 ^^           e
++22 ^ ^          q
++23 ^  ^         )
++24 ^  ^         
+ 0: aeq
+ 1: aeq
+
+/.(*F)/
+    \P\Pabc
+No match
+
+/\btype\b\W*?\btext\b\W*?\bjavascript\b/IS
+Capturing subpattern count = 0
+No options
+First char = 't'
+Need char = 't'
+Max lookbehind = 1
+Subject length lower bound = 18
+No set of starting bytes
+
+/\btype\b\W*?\btext\b\W*?\bjavascript\b|\burl\b\W*?\bshell:|<input\b.*?\btype\b\W*?\bimage\b|\bonkeyup\b\W*?\=/IS
+Capturing subpattern count = 0
+No options
+No first char
+No need char
+Max lookbehind = 1
+Subject length lower bound = 8
+Starting byte set: < o t u 
+
+/a(*SKIP)c|b(*ACCEPT)|/+SI
+Capturing subpattern count = 0
+No options
+No first char
+No need char
+Study returned NULL
+    a
+ 0: 
+ 0+ 
+
+/a(*SKIP)c|b(*ACCEPT)cd(*ACCEPT)|x/SI
+Capturing subpattern count = 0
+No options
+No first char
+No need char
+Subject length lower bound = -1
+Starting byte set: a b x 
+    ax
+ 0: x
+
+'a*(*ACCEPT)b'+
+    \N\N
+No match
+    abc\N\N
+ 0: a
+ 0+ bc
+    bbb\N\N 
+ 0: 
+ 0+ bb
+
+/(*ACCEPT)a/+I
+Capturing subpattern count = 0
+No options
+No first char
+No need char
+    bax
+ 0: 
+ 0+ bax
+
+/z(*ACCEPT)a/+I
+Capturing subpattern count = 0
+No options
+First char = 'z'
+No need char
+    baxzbx
+ 0: z
+ 0+ bx
+
+/a(?:.)*?a/ims                                                                  
+    \Mabbbbbbbbbbbbbbbbbbbbba
+Minimum match() limit = 65
+Minimum match() recursion limit = 2
+ 0: abbbbbbbbbbbbbbbbbbbbba
+    
+/a(?:.(*THEN))*?a/ims
+    \Mabbbbbbbbbbbbbbbbbbbbba
+Minimum match() limit = 86
+Minimum match() recursion limit = 45
+ 0: abbbbbbbbbbbbbbbbbbbbba
+
+/a(?:.(*THEN:ABC))*?a/ims
+    \Mabbbbbbbbbbbbbbbbbbbbba
+Minimum match() limit = 86
+Minimum match() recursion limit = 45
+ 0: abbbbbbbbbbbbbbbbbbbbba
+
+/-- These tests are in agreement with development Perl 5.015, which has fixed
+    some things, but they don't all work with 5.012, so they aren't in the
+    Perl-compatible tests. Those after the first come from Perl's own test
+    files. --/
+    
+/^((yes|no)(*THEN)(*F))?/
+  yes
+No match
+
+/(A (.*)   C? (*THEN)  | A D) (*FAIL)/x
+AbcdCBefgBhiBqz
+No match
+
+/(A (.*)   C? (*THEN)  | A D) z/x
+AbcdCBefgBhiBqz
+No match
+
+/(A (.*)   C? (*THEN)  | A D) \s* (*FAIL)/x
+AbcdCBefgBhiBqz
+No match
+
+/(A (.*)   C? (*THEN)  | A D) \s* z/x
+AbcdCBefgBhiBqz
+No match
+
+/(A (.*)   (?:C|) (*THEN)  | A D) (*FAIL)/x
+AbcdCBefgBhiBqz
+No match
+
+/(A (.*)   (?:C|) (*THEN)  | A D) z/x
+AbcdCBefgBhiBqz
+No match
+
+/(A (.*)   C{0,6} (*THEN)  | A D) (*FAIL)/x
+AbcdCBefgBhiBqz
+No match
+
+/(A (.*)   C{0,6} (*THEN)  | A D) z/x
+AbcdCBefgBhiBqz
+No match
+
+/(A (.*)   (CE){0,6} (*THEN)  | A D) (*FAIL)/x
+AbcdCEBefgBhiBqz
+No match
+
+/(A (.*)   (CE){0,6} (*THEN)  | A D) z/x
+AbcdCEBefgBhiBqz
+No match
+
+/(A (.*)   (CE*){0,6} (*THEN)  | A D) (*FAIL)/x
+AbcdCBefgBhiBqz
+No match
+
+/(A (.*)   (CE*){0,6} (*THEN)  | A D) z/x
+AbcdCBefgBhiBqz
+No match
+
+/-----------------------------------------------/  
+
+/^(?>a+)(?>(z+))\w/BZ
+------------------------------------------------------------------
+        Bra
+        ^
+        Once_NC
+        a+
+        Ket
+        Once
+        CBra 1
+        z+
+        Ket
+        Ket
+        \w
+        Ket
+        End
+------------------------------------------------------------------
+    aaaazzzzb
+ 0: aaaazzzzb
+ 1: zzzz
+    ** Failers
+No match
+    aazz  
+No match
+
+/(.)(\1|a(?2))/
+    bab
+ 0: bab
+ 1: b
+ 2: ab
+    
+/\1|(.)(?R)\1/
+    cbbbc
+ 0: cbbbc
+ 1: c
+    
+/(.)((?(1)c|a)|a(?2))/
+    baa  
+No match
+
+/(?P<abn>(?P=abn)xxx)/BZ
+------------------------------------------------------------------
+        Bra
+        Once
+        CBra 1
+        \1
+        xxx
+        Ket
+        Ket
+        Ket
+        End
+------------------------------------------------------------------
+
+/(a\1z)/BZ
+------------------------------------------------------------------
+        Bra
+        Once
+        CBra 1
+        a
+        \1
+        z
+        Ket
+        Ket
+        Ket
+        End
+------------------------------------------------------------------
+
+/^(?>a+)(?>b+)(?>c+)(?>d+)(?>e+)/
+     \Maabbccddee
+Minimum match() limit = 12
+Minimum match() recursion limit = 3
+ 0: aabbccddee
+
+/^(?>(a+))(?>(b+))(?>(c+))(?>(d+))(?>(e+))/
+     \Maabbccddee
+Minimum match() limit = 22
+Minimum match() recursion limit = 21
+ 0: aabbccddee
+ 1: aa
+ 2: bb
+ 3: cc
+ 4: dd
+ 5: ee
+
+/^(?>(a+))(?>b+)(?>(c+))(?>d+)(?>(e+))/
+     \Maabbccddee
+Minimum match() limit = 18
+Minimum match() recursion limit = 13
+ 0: aabbccddee
+ 1: aa
+ 2: cc
+ 3: ee
+
+/^a\x41z/<JS>
+    aAz
+ 0: aAz
+    *** Failers
+No match
+    ax41z
+No match
+
+/^a[m\x41]z/<JS>
+    aAz
+ 0: aAz
+
+/^a\x1z/<JS>
+    ax1z
+ 0: ax1z
+
+/^a\u0041z/<JS>
+    aAz
+ 0: aAz
+    *** Failers
+No match
+    au0041z
+No match
+
+/^a[m\u0041]z/<JS>
+    aAz
+ 0: aAz
+
+/^a\u041z/<JS>
+    au041z
+ 0: au041z
+    *** Failers
+No match
+    aAz
+No match
+
+/^a\U0041z/<JS>
+    aU0041z
+ 0: aU0041z
+    *** Failers
+No match
+    aAz
+No match
+
+/(?(?=c)c|d)++Y/BZ
+------------------------------------------------------------------
+        Bra
+        BraPos
+        Cond
+        Assert
+        c
+        Ket
+        c
+        Alt
+        d
+        Ket
+        KetRpos
+        Y
+        Ket
+        End
+------------------------------------------------------------------
+
+/(?(?=c)c|d)*+Y/BZ
+------------------------------------------------------------------
+        Bra
+        Braposzero
+        BraPos
+        Cond
+        Assert
+        c
+        Ket
+        c
+        Alt
+        d
+        Ket
+        KetRpos
+        Y
+        Ket
+        End
+------------------------------------------------------------------
+
+/a[\NB]c/
+Failed: \N is not supported in a class at offset 3
+
+/a[B-\Nc]/ 
+Failed: \N is not supported in a class at offset 5
+
+/(a)(?2){0,1999}?(b)/
+
+/(a)(?(DEFINE)(b))(?2){0,1999}?(?2)/
+
+/--- This test, with something more complicated than individual letters, causes
+different behaviour in Perl. Perhaps it disables some optimization; no tag is
+passed back for the failures, whereas in PCRE there is a tag. ---/
+    
+/(A|P)(*:A)(B|P) | (X|P)(X|P)(*:B)(Y|P)/xK
+    AABC
+ 0: AB
+ 1: A
+ 2: B
+MK: A
+    XXYZ 
+ 0: XXY
+ 1: <unset>
+ 2: <unset>
+ 3: X
+ 4: X
+ 5: Y
+MK: B
+    ** Failers
+No match
+    XAQQ  
+No match, mark = A
+    XAQQXZZ  
+No match, mark = A
+    AXQQQ 
+No match, mark = A
+    AXXQQQ 
+No match, mark = B
+
+/-- Perl doesn't give marks for these, though it does if the alternatives are
+replaced by single letters. --/
+    
+/(b|q)(*:m)f|a(*:n)w/K
+    aw 
+ 0: aw
+MK: n
+    ** Failers 
+No match, mark = n
+    abc
+No match, mark = m
+
+/(q|b)(*:m)f|a(*:n)w/K
+    aw 
+ 0: aw
+MK: n
+    ** Failers 
+No match, mark = n
+    abc
+No match, mark = m
+
+/-- After a partial match, the behaviour is as for a failure. --/
+
+/^a(*:X)bcde/K
+   abc\P
+Partial match, mark=X: abc
+   
+/-- These are here because Perl doesn't return a mark, except for the first --/
+
+/(?=(*:x))(q|)/K+
+    abc
+ 0: 
+ 0+ abc
+ 1: 
+MK: x
+
+/(?=(*:x))((*:y)q|)/K+
+    abc
+ 0: 
+ 0+ abc
+ 1: 
+MK: x
+
+/(?=(*:x))(?:(*:y)q|)/K+
+    abc
+ 0: 
+ 0+ abc
+MK: x
+
+/(?=(*:x))(?>(*:y)q|)/K+
+    abc
+ 0: 
+ 0+ abc
+MK: x
+
+/(?=a(*:x))(?!a(*:y)c)/K+
+    ab
+ 0: 
+ 0+ ab
+MK: x
+
+/(?=a(*:x))(?=a(*:y)c|)/K+
+    ab
+ 0: 
+ 0+ ab
+MK: x
+
+/(..)\1/
+    ab\P
+Partial match: ab
+    aba\P
+Partial match: aba
+    abab\P
+ 0: abab
+ 1: ab
+
+/(..)\1/i
+    ab\P
+Partial match: ab
+    abA\P
+Partial match: abA
+    aBAb\P
+ 0: aBAb
+ 1: aB
+
+/(..)\1{2,}/
+    ab\P
+Partial match: ab
+    aba\P
+Partial match: aba
+    abab\P
+Partial match: abab
+    ababa\P
+Partial match: ababa
+    ababab\P
+ 0: ababab
+ 1: ab
+    ababab\P\P
+Partial match: ababab
+    abababa\P
+ 0: ababab
+ 1: ab
+    abababa\P\P
+Partial match: abababa
+
+/(..)\1{2,}/i
+    ab\P
+Partial match: ab
+    aBa\P
+Partial match: aBa
+    aBAb\P
+Partial match: aBAb
+    AbaBA\P
+Partial match: AbaBA
+    abABAb\P
+ 0: abABAb
+ 1: ab
+    aBAbaB\P\P
+Partial match: aBAbaB
+    abABabA\P
+ 0: abABab
+ 1: ab
+    abaBABa\P\P
+Partial match: abaBABa
+
+/(..)\1{2,}?x/i
+    ab\P
+Partial match: ab
+    abA\P
+Partial match: abA
+    aBAb\P
+Partial match: aBAb
+    abaBA\P
+Partial match: abaBA
+    abAbaB\P
+Partial match: abAbaB
+    abaBabA\P
+Partial match: abaBabA
+    abAbABaBx\P
+ 0: abAbABaBx
+ 1: ab
+
+/^(..)\1/
+    aba\P
+Partial match: aba
+
+/^(..)\1{2,3}x/
+    aba\P
+Partial match: aba
+    ababa\P
+Partial match: ababa
+    ababa\P\P
+Partial match: ababa
+    abababx
+ 0: abababx
+ 1: ab
+    ababababx  
+ 0: ababababx
+ 1: ab
+
+/^(..)\1{2,3}?x/
+    aba\P
+Partial match: aba
+    ababa\P
+Partial match: ababa
+    ababa\P\P
+Partial match: ababa
+    abababx
+ 0: abababx
+ 1: ab
+    ababababx  
+ 0: ababababx
+ 1: ab
+    
+/^(..)(\1{2,3})ab/
+    abababab
+ 0: abababab
+ 1: ab
+ 2: abab
+
+/^\R/
+    \r\P
+ 0: \x0d
+    \r\P\P
+Partial match: \x0d
+    
+/^\R{2,3}x/
+    \r\P
+Partial match: \x0d
+    \r\P\P
+Partial match: \x0d
+    \r\r\P 
+Partial match: \x0d\x0d
+    \r\r\P\P
+Partial match: \x0d\x0d
+    \r\r\r\P  
+Partial match: \x0d\x0d\x0d
+    \r\r\r\P\P
+Partial match: \x0d\x0d\x0d
+    \r\rx
+ 0: \x0d\x0dx
+    \r\r\rx    
+ 0: \x0d\x0d\x0dx
+
+/^\R{2,3}?x/
+    \r\P
+Partial match: \x0d
+    \r\P\P
+Partial match: \x0d
+    \r\r\P 
+Partial match: \x0d\x0d
+    \r\r\P\P
+Partial match: \x0d\x0d
+    \r\r\r\P  
+Partial match: \x0d\x0d\x0d
+    \r\r\r\P\P
+Partial match: \x0d\x0d\x0d
+    \r\rx
+ 0: \x0d\x0dx
+    \r\r\rx    
+ 0: \x0d\x0d\x0dx
+    
+/^\R?x/
+    \r\P
+Partial match: \x0d
+    \r\P\P 
+Partial match: \x0d
+    x
+ 0: x
+    \rx  
+ 0: \x0dx
+
+/^\R+x/
+    \r\P
+Partial match: \x0d
+    \r\P\P 
+Partial match: \x0d
+    \r\n\P
+Partial match: \x0d\x0a
+    \r\n\P\P  
+Partial match: \x0d\x0a
+    \rx  
+ 0: \x0dx
+
+/^a$/<CRLF>
+    a\r\P
+Partial match: a\x0d
+    a\r\P\P 
+Partial match: a\x0d
+
+/^a$/m<CRLF>
+    a\r\P
+Partial match: a\x0d
+    a\r\P\P 
+Partial match: a\x0d
+
+/^(a$|a\r)/<CRLF>
+    a\r\P
+ 0: a\x0d
+ 1: a\x0d
+    a\r\P\P 
+Partial match: a\x0d
+
+/^(a$|a\r)/m<CRLF>
+    a\r\P
+ 0: a\x0d
+ 1: a\x0d
+    a\r\P\P 
+Partial match: a\x0d
+
+/./<CRLF>
+    \r\P
+ 0: \x0d
+    \r\P\P 
+Partial match: \x0d
+  
+/.{2,3}/<CRLF>
+    \r\P 
+Partial match: \x0d
+    \r\P\P
+Partial match: \x0d
+    \r\r\P
+ 0: \x0d\x0d
+    \r\r\P\P
+Partial match: \x0d\x0d
+    \r\r\r\P
+ 0: \x0d\x0d\x0d
+    \r\r\r\P\P     
+Partial match: \x0d\x0d\x0d
+
+/.{2,3}?/<CRLF>
+    \r\P 
+Partial match: \x0d
+    \r\P\P
+Partial match: \x0d
+    \r\r\P
+ 0: \x0d\x0d
+    \r\r\P\P
+Partial match: \x0d\x0d
+    \r\r\r\P
+ 0: \x0d\x0d
+    \r\r\r\P\P     
+ 0: \x0d\x0d
+
+/-- These two are here because Perl does not match: it seems to allow the
+COMMIT to escape from the assertion. --/
+
+/(?=a(*COMMIT)b|ac)ac|ac/
+    ac
+ 0: ac
+
+/(?=a(*COMMIT)b|(ac)) ac | (a)c/x
+    ac
+ 0: ac
+ 1: <unset>
+ 2: a
+
+"AB(C(D))(E(F))?(?(?=\2)(?=\4))"
+    ABCDGHI\O03
+Matched, but too many substrings
+ 0: ABCD
+    
+/-- This one is here because Perl does not confine the *COMMIT to the 
+assertion, and therefore fails the entire subroutine call. --/ 
+    
+/((?=a(*COMMIT)b)ab|ac){0}(?:(?1)|a(c))/
+    ac 
+ 0: ac
+
+/-- End of testinput2 --/
diff --git a/ext/pcre/pcrelib/testdata/testoutput3 b/ext/pcre/pcrelib/testdata/testoutput3
new file mode 100644
index 0000000..7b0a3e9
--- /dev/null
+++ b/ext/pcre/pcrelib/testdata/testoutput3
@@ -0,0 +1,169 @@
+/-- This set of tests checks local-specific features, using the fr_FR locale. 
+    It is not Perl-compatible. There is different version called wintestinput3
+  f  or use on Windows, where the locale is called "french". --/
+
+/^[\w]+/
+    *** Failers
+No match
+    École
+No match
+
+/^[\w]+/Lfr_FR
+    École
+ 0: École
+
+/^[\w]+/
+    *** Failers
+No match
+    École
+No match
+
+/^[\W]+/
+    École
+ 0: \xc9
+
+/^[\W]+/Lfr_FR
+    *** Failers
+ 0: *** 
+    École
+No match
+
+/[\b]/
+    \b
+ 0: \x08
+    *** Failers
+No match
+    a
+No match
+
+/[\b]/Lfr_FR
+    \b
+ 0: \x08
+    *** Failers
+No match
+    a
+No match
+
+/^\w+/
+    *** Failers
+No match
+    École
+No match
+
+/^\w+/Lfr_FR
+    École
+ 0: École
+
+/(.+)\b(.+)/
+    École
+ 0: \xc9cole
+ 1: \xc9
+ 2: cole
+
+/(.+)\b(.+)/Lfr_FR
+    *** Failers
+ 0: *** Failers
+ 1: *** 
+ 2: Failers
+    École
+No match
+
+/École/i
+    École
+ 0: \xc9cole
+    *** Failers
+No match
+    école
+No match
+
+/École/iLfr_FR
+    École
+ 0: École
+    école
+ 0: école
+
+/\w/IS
+Capturing subpattern count = 0
+No options
+No first char
+No need char
+Subject length lower bound = 1
+Starting byte set: 0 1 2 3 4 5 6 7 8 9 A B C D E F G H I J K L M N O P 
+  Q R S T U V W X Y Z _ a b c d e f g h i j k l m n o p q r s t u v w x y z 
+
+/\w/ISLfr_FR
+Capturing subpattern count = 0
+No options
+No first char
+No need char
+Subject length lower bound = 1
+Starting byte set: 0 1 2 3 4 5 6 7 8 9 A B C D E F G H I J K L M N O P 
+  Q R S T U V W X Y Z _ a b c d e f g h i j k l m n o p q r s t u v w x y z 
+  ª µ º À Á Â Ã Ä Å Æ Ç È É Ê Ë Ì Í Î Ï Ð Ñ Ò Ó Ô Õ Ö Ø Ù Ú Û Ü Ý Þ ß à á â 
+  ã ä å æ ç è é ê ë ì í î ï ð ñ ò ó ô õ ö ø ù ú û ü ý þ ÿ 
+
+/^[\xc8-\xc9]/iLfr_FR
+    École
+ 0: É
+    école
+ 0: é
+
+/^[\xc8-\xc9]/Lfr_FR
+    École
+ 0: É
+    *** Failers 
+No match
+    école
+No match
+
+/\W+/Lfr_FR
+    >>>\xaa<<<
+ 0: >>>
+    >>>\xba<<< 
+ 0: >>>
+
+/[\W]+/Lfr_FR
+    >>>\xaa<<<
+ 0: >>>
+    >>>\xba<<< 
+ 0: >>>
+
+/[^[:alpha:]]+/Lfr_FR
+    >>>\xaa<<<
+ 0: >>>
+    >>>\xba<<< 
+ 0: >>>
+
+/\w+/Lfr_FR
+    >>>\xaa<<<
+ 0: ª
+    >>>\xba<<< 
+ 0: º
+
+/[\w]+/Lfr_FR
+    >>>\xaa<<<
+ 0: ª
+    >>>\xba<<< 
+ 0: º
+
+/[[:alpha:]]+/Lfr_FR
+    >>>\xaa<<<
+ 0: ª
+    >>>\xba<<< 
+ 0: º
+    
+/[[:alpha:]][[:lower:]][[:upper:]]/DZLfr_FR 
+------------------------------------------------------------------
+        Bra
+        [A-Za-z\xaa\xb5\xba\xc0-\xd6\xd8-\xf6\xf8-\xff]
+        [a-z\xb5\xdf-\xf6\xf8-\xff]
+        [A-Z\xc0-\xd6\xd8-\xde]
+        Ket
+        End
+------------------------------------------------------------------
+Capturing subpattern count = 0
+No options
+No first char
+No need char
+
+/-- End of testinput3 --/
diff --git a/ext/pcre/pcrelib/testdata/testoutput4 b/ext/pcre/pcrelib/testdata/testoutput4
new file mode 100644
index 0000000..2082721
--- /dev/null
+++ b/ext/pcre/pcrelib/testdata/testoutput4
@@ -0,0 +1,1094 @@
+/-- This set of tests is for UTF support, excluding Unicode properties. It is
+    compatible with all versions of Perl >= 5.10 and both the 8-bit and 16-bit
+    PCRE libraries. --/
+   
+/a.b/8
+    acb
+ 0: acb
+    a\x7fb
+ 0: a\x{7f}b
+    a\x{100}b 
+ 0: a\x{100}b
+    *** Failers
+No match
+    a\nb  
+No match
+
+/a(.{3})b/8
+    a\x{4000}xyb 
+ 0: a\x{4000}xyb
+ 1: \x{4000}xy
+    a\x{4000}\x7fyb 
+ 0: a\x{4000}\x{7f}yb
+ 1: \x{4000}\x{7f}y
+    a\x{4000}\x{100}yb 
+ 0: a\x{4000}\x{100}yb
+ 1: \x{4000}\x{100}y
+    *** Failers
+No match
+    a\x{4000}b 
+No match
+    ac\ncb 
+No match
+
+/a(.*?)(.)/
+    a\xc0\x88b
+ 0: a\xc0
+ 1: 
+ 2: \xc0
+
+/a(.*?)(.)/8
+    a\x{100}b
+ 0: a\x{100}
+ 1: 
+ 2: \x{100}
+
+/a(.*)(.)/
+    a\xc0\x88b
+ 0: a\xc0\x88b
+ 1: \xc0\x88
+ 2: b
+
+/a(.*)(.)/8
+    a\x{100}b
+ 0: a\x{100}b
+ 1: \x{100}
+ 2: b
+
+/a(.)(.)/
+    a\xc0\x92bcd
+ 0: a\xc0\x92
+ 1: \xc0
+ 2: \x92
+
+/a(.)(.)/8
+    a\x{240}bcd
+ 0: a\x{240}b
+ 1: \x{240}
+ 2: b
+
+/a(.?)(.)/
+    a\xc0\x92bcd
+ 0: a\xc0\x92
+ 1: \xc0
+ 2: \x92
+
+/a(.?)(.)/8
+    a\x{240}bcd
+ 0: a\x{240}b
+ 1: \x{240}
+ 2: b
+
+/a(.??)(.)/
+    a\xc0\x92bcd
+ 0: a\xc0
+ 1: 
+ 2: \xc0
+
+/a(.??)(.)/8
+    a\x{240}bcd
+ 0: a\x{240}
+ 1: 
+ 2: \x{240}
+
+/a(.{3})b/8
+    a\x{1234}xyb 
+ 0: a\x{1234}xyb
+ 1: \x{1234}xy
+    a\x{1234}\x{4321}yb 
+ 0: a\x{1234}\x{4321}yb
+ 1: \x{1234}\x{4321}y
+    a\x{1234}\x{4321}\x{3412}b 
+ 0: a\x{1234}\x{4321}\x{3412}b
+ 1: \x{1234}\x{4321}\x{3412}
+    *** Failers
+No match
+    a\x{1234}b 
+No match
+    ac\ncb 
+No match
+
+/a(.{3,})b/8
+    a\x{1234}xyb 
+ 0: a\x{1234}xyb
+ 1: \x{1234}xy
+    a\x{1234}\x{4321}yb 
+ 0: a\x{1234}\x{4321}yb
+ 1: \x{1234}\x{4321}y
+    a\x{1234}\x{4321}\x{3412}b 
+ 0: a\x{1234}\x{4321}\x{3412}b
+ 1: \x{1234}\x{4321}\x{3412}
+    axxxxbcdefghijb 
+ 0: axxxxbcdefghijb
+ 1: xxxxbcdefghij
+    a\x{1234}\x{4321}\x{3412}\x{3421}b 
+ 0: a\x{1234}\x{4321}\x{3412}\x{3421}b
+ 1: \x{1234}\x{4321}\x{3412}\x{3421}
+    *** Failers
+No match
+    a\x{1234}b 
+No match
+
+/a(.{3,}?)b/8
+    a\x{1234}xyb 
+ 0: a\x{1234}xyb
+ 1: \x{1234}xy
+    a\x{1234}\x{4321}yb 
+ 0: a\x{1234}\x{4321}yb
+ 1: \x{1234}\x{4321}y
+    a\x{1234}\x{4321}\x{3412}b 
+ 0: a\x{1234}\x{4321}\x{3412}b
+ 1: \x{1234}\x{4321}\x{3412}
+    axxxxbcdefghijb 
+ 0: axxxxb
+ 1: xxxx
+    a\x{1234}\x{4321}\x{3412}\x{3421}b 
+ 0: a\x{1234}\x{4321}\x{3412}\x{3421}b
+ 1: \x{1234}\x{4321}\x{3412}\x{3421}
+    *** Failers
+No match
+    a\x{1234}b 
+No match
+
+/a(.{3,5})b/8
+    a\x{1234}xyb 
+ 0: a\x{1234}xyb
+ 1: \x{1234}xy
+    a\x{1234}\x{4321}yb 
+ 0: a\x{1234}\x{4321}yb
+ 1: \x{1234}\x{4321}y
+    a\x{1234}\x{4321}\x{3412}b 
+ 0: a\x{1234}\x{4321}\x{3412}b
+ 1: \x{1234}\x{4321}\x{3412}
+    axxxxbcdefghijb 
+ 0: axxxxb
+ 1: xxxx
+    a\x{1234}\x{4321}\x{3412}\x{3421}b 
+ 0: a\x{1234}\x{4321}\x{3412}\x{3421}b
+ 1: \x{1234}\x{4321}\x{3412}\x{3421}
+    axbxxbcdefghijb 
+ 0: axbxxb
+ 1: xbxx
+    axxxxxbcdefghijb 
+ 0: axxxxxb
+ 1: xxxxx
+    *** Failers
+No match
+    a\x{1234}b 
+No match
+    axxxxxxbcdefghijb 
+No match
+
+/a(.{3,5}?)b/8
+    a\x{1234}xyb 
+ 0: a\x{1234}xyb
+ 1: \x{1234}xy
+    a\x{1234}\x{4321}yb 
+ 0: a\x{1234}\x{4321}yb
+ 1: \x{1234}\x{4321}y
+    a\x{1234}\x{4321}\x{3412}b 
+ 0: a\x{1234}\x{4321}\x{3412}b
+ 1: \x{1234}\x{4321}\x{3412}
+    axxxxbcdefghijb 
+ 0: axxxxb
+ 1: xxxx
+    a\x{1234}\x{4321}\x{3412}\x{3421}b 
+ 0: a\x{1234}\x{4321}\x{3412}\x{3421}b
+ 1: \x{1234}\x{4321}\x{3412}\x{3421}
+    axbxxbcdefghijb 
+ 0: axbxxb
+ 1: xbxx
+    axxxxxbcdefghijb 
+ 0: axxxxxb
+ 1: xxxxx
+    *** Failers
+No match
+    a\x{1234}b 
+No match
+    axxxxxxbcdefghijb 
+No match
+
+/^[a\x{c0}]/8
+    *** Failers
+No match
+    \x{100}
+No match
+
+/(?<=aXb)cd/8
+    aXbcd
+ 0: cd
+
+/(?<=a\x{100}b)cd/8
+    a\x{100}bcd
+ 0: cd
+
+/(?<=a\x{100000}b)cd/8
+    a\x{100000}bcd
+ 0: cd
+    
+/(?:\x{100}){3}b/8
+    \x{100}\x{100}\x{100}b
+ 0: \x{100}\x{100}\x{100}b
+    *** Failers 
+No match
+    \x{100}\x{100}b
+No match
+
+/\x{ab}/8
+    \x{ab} 
+ 0: \x{ab}
+    \xc2\xab
+ 0: \x{ab}
+    *** Failers 
+No match
+    \x00{ab}
+No match
+
+/(?<=(.))X/8
+    WXYZ
+ 0: X
+ 1: W
+    \x{256}XYZ 
+ 0: X
+ 1: \x{256}
+    *** Failers
+No match
+    XYZ 
+No match
+
+/[^a]+/8g
+    bcd
+ 0: bcd
+    \x{100}aY\x{256}Z 
+ 0: \x{100}
+ 0: Y\x{256}Z
+    
+/^[^a]{2}/8
+    \x{100}bc
+ 0: \x{100}b
+ 
+/^[^a]{2,}/8
+    \x{100}bcAa
+ 0: \x{100}bcA
+
+/^[^a]{2,}?/8
+    \x{100}bca
+ 0: \x{100}b
+
+/[^a]+/8ig
+    bcd
+ 0: bcd
+    \x{100}aY\x{256}Z 
+ 0: \x{100}
+ 0: Y\x{256}Z
+    
+/^[^a]{2}/8i
+    \x{100}bc
+ 0: \x{100}b
+ 
+/^[^a]{2,}/8i
+    \x{100}bcAa
+ 0: \x{100}bc
+
+/^[^a]{2,}?/8i
+    \x{100}bca
+ 0: \x{100}b
+
+/\x{100}{0,0}/8
+    abcd
+ 0: 
+ 
+/\x{100}?/8
+    abcd
+ 0: 
+    \x{100}\x{100} 
+ 0: \x{100}
+
+/\x{100}{0,3}/8 
+    \x{100}\x{100} 
+ 0: \x{100}\x{100}
+    \x{100}\x{100}\x{100}\x{100} 
+ 0: \x{100}\x{100}\x{100}
+    
+/\x{100}*/8
+    abce
+ 0: 
+    \x{100}\x{100}\x{100}\x{100} 
+ 0: \x{100}\x{100}\x{100}\x{100}
+
+/\x{100}{1,1}/8
+    abcd\x{100}\x{100}\x{100}\x{100} 
+ 0: \x{100}
+
+/\x{100}{1,3}/8
+    abcd\x{100}\x{100}\x{100}\x{100} 
+ 0: \x{100}\x{100}\x{100}
+
+/\x{100}+/8
+    abcd\x{100}\x{100}\x{100}\x{100} 
+ 0: \x{100}\x{100}\x{100}\x{100}
+
+/\x{100}{3}/8
+    abcd\x{100}\x{100}\x{100}XX
+ 0: \x{100}\x{100}\x{100}
+
+/\x{100}{3,5}/8
+    abcd\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}XX
+ 0: \x{100}\x{100}\x{100}\x{100}\x{100}
+
+/\x{100}{3,}/8
+    abcd\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}XX
+ 0: \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}
+
+/(?<=a\x{100}{2}b)X/8+
+    Xyyya\x{100}\x{100}bXzzz
+ 0: X
+ 0+ zzz
+
+/\D*/8
+  aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+ 0: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+
+/\D*/8
+  \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}
+ 0: \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}
+
+/\D/8
+    1X2
+ 0: X
+    1\x{100}2 
+ 0: \x{100}
+  
+/>\S/8
+    > >X Y
+ 0: >X
+    > >\x{100} Y
+ 0: >\x{100}
+  
+/\d/8
+    \x{100}3
+ 0: 3
+    
+/\s/8
+    \x{100} X
+ 0:  
+    
+/\D+/8
+    12abcd34
+ 0: abcd
+    *** Failers
+ 0: *** Failers
+    1234  
+No match
+
+/\D{2,3}/8
+    12abcd34
+ 0: abc
+    12ab34
+ 0: ab
+    *** Failers  
+ 0: ***
+    1234
+No match
+    12a34  
+No match
+
+/\D{2,3}?/8
+    12abcd34
+ 0: ab
+    12ab34
+ 0: ab
+    *** Failers  
+ 0: **
+    1234
+No match
+    12a34  
+No match
+
+/\d+/8
+    12abcd34
+ 0: 12
+    *** Failers
+No match
+
+/\d{2,3}/8
+    12abcd34
+ 0: 12
+    1234abcd
+ 0: 123
+    *** Failers  
+No match
+    1.4 
+No match
+
+/\d{2,3}?/8
+    12abcd34
+ 0: 12
+    1234abcd
+ 0: 12
+    *** Failers  
+No match
+    1.4 
+No match
+
+/\S+/8
+    12abcd34
+ 0: 12abcd34
+    *** Failers
+ 0: ***
+    \    \ 
+No match
+
+/\S{2,3}/8
+    12abcd34
+ 0: 12a
+    1234abcd
+ 0: 123
+    *** Failers
+ 0: ***
+    \     \  
+No match
+
+/\S{2,3}?/8
+    12abcd34
+ 0: 12
+    1234abcd
+ 0: 12
+    *** Failers
+ 0: **
+    \     \  
+No match
+
+/>\s+</8+
+    12>      <34
+ 0: >      <
+ 0+ 34
+    *** Failers
+No match
+
+/>\s{2,3}</8+
+    ab>  <cd
+ 0: >  <
+ 0+ cd
+    ab>   <ce
+ 0: >   <
+ 0+ ce
+    *** Failers
+No match
+    ab>    <cd 
+No match
+
+/>\s{2,3}?</8+
+    ab>  <cd
+ 0: >  <
+ 0+ cd
+    ab>   <ce
+ 0: >   <
+ 0+ ce
+    *** Failers
+No match
+    ab>    <cd 
+No match
+
+/\w+/8
+    12      34
+ 0: 12
+    *** Failers
+ 0: Failers
+    +++=*! 
+No match
+
+/\w{2,3}/8
+    ab  cd
+ 0: ab
+    abcd ce
+ 0: abc
+    *** Failers
+ 0: Fai
+    a.b.c
+No match
+
+/\w{2,3}?/8
+    ab  cd
+ 0: ab
+    abcd ce
+ 0: ab
+    *** Failers
+ 0: Fa
+    a.b.c
+No match
+
+/\W+/8
+    12====34
+ 0: ====
+    *** Failers
+ 0: *** 
+    abcd 
+No match
+
+/\W{2,3}/8
+    ab====cd
+ 0: ===
+    ab==cd
+ 0: ==
+    *** Failers
+ 0: ***
+    a.b.c
+No match
+
+/\W{2,3}?/8
+    ab====cd
+ 0: ==
+    ab==cd
+ 0: ==
+    *** Failers
+ 0: **
+    a.b.c
+No match
+
+/[\x{100}]/8
+    \x{100}
+ 0: \x{100}
+    Z\x{100}
+ 0: \x{100}
+    \x{100}Z
+ 0: \x{100}
+    *** Failers 
+No match
+
+/[Z\x{100}]/8
+    Z\x{100}
+ 0: Z
+    \x{100}
+ 0: \x{100}
+    \x{100}Z
+ 0: \x{100}
+    *** Failers 
+No match
+
+/[\x{100}\x{200}]/8
+   ab\x{100}cd
+ 0: \x{100}
+   ab\x{200}cd
+ 0: \x{200}
+   *** Failers  
+No match
+
+/[\x{100}-\x{200}]/8
+   ab\x{100}cd
+ 0: \x{100}
+   ab\x{200}cd
+ 0: \x{200}
+   ab\x{111}cd 
+ 0: \x{111}
+   *** Failers  
+No match
+
+/[z-\x{200}]/8
+   ab\x{100}cd
+ 0: \x{100}
+   ab\x{200}cd
+ 0: \x{200}
+   ab\x{111}cd 
+ 0: \x{111}
+   abzcd
+ 0: z
+   ab|cd  
+ 0: |
+   *** Failers  
+No match
+
+/[Q\x{100}\x{200}]/8
+   ab\x{100}cd
+ 0: \x{100}
+   ab\x{200}cd
+ 0: \x{200}
+   Q? 
+ 0: Q
+   *** Failers  
+No match
+
+/[Q\x{100}-\x{200}]/8
+   ab\x{100}cd
+ 0: \x{100}
+   ab\x{200}cd
+ 0: \x{200}
+   ab\x{111}cd 
+ 0: \x{111}
+   Q? 
+ 0: Q
+   *** Failers  
+No match
+
+/[Qz-\x{200}]/8
+   ab\x{100}cd
+ 0: \x{100}
+   ab\x{200}cd
+ 0: \x{200}
+   ab\x{111}cd 
+ 0: \x{111}
+   abzcd
+ 0: z
+   ab|cd  
+ 0: |
+   Q? 
+ 0: Q
+   *** Failers  
+No match
+
+/[\x{100}\x{200}]{1,3}/8
+   ab\x{100}cd
+ 0: \x{100}
+   ab\x{200}cd
+ 0: \x{200}
+   ab\x{200}\x{100}\x{200}\x{100}cd
+ 0: \x{200}\x{100}\x{200}
+   *** Failers  
+No match
+
+/[\x{100}\x{200}]{1,3}?/8
+   ab\x{100}cd
+ 0: \x{100}
+   ab\x{200}cd
+ 0: \x{200}
+   ab\x{200}\x{100}\x{200}\x{100}cd
+ 0: \x{200}
+   *** Failers  
+No match
+
+/[Q\x{100}\x{200}]{1,3}/8
+   ab\x{100}cd
+ 0: \x{100}
+   ab\x{200}cd
+ 0: \x{200}
+   ab\x{200}\x{100}\x{200}\x{100}cd
+ 0: \x{200}\x{100}\x{200}
+   *** Failers  
+No match
+
+/[Q\x{100}\x{200}]{1,3}?/8
+   ab\x{100}cd
+ 0: \x{100}
+   ab\x{200}cd
+ 0: \x{200}
+   ab\x{200}\x{100}\x{200}\x{100}cd
+ 0: \x{200}
+   *** Failers  
+No match
+
+/(?<=[\x{100}\x{200}])X/8
+    abc\x{200}X
+ 0: X
+    abc\x{100}X 
+ 0: X
+    *** Failers
+No match
+    X  
+No match
+
+/(?<=[Q\x{100}\x{200}])X/8
+    abc\x{200}X
+ 0: X
+    abc\x{100}X 
+ 0: X
+    abQX 
+ 0: X
+    *** Failers
+No match
+    X  
+No match
+
+/(?<=[\x{100}\x{200}]{3})X/8
+    abc\x{100}\x{200}\x{100}X
+ 0: X
+    *** Failers
+No match
+    abc\x{200}X
+No match
+    X  
+No match
+
+/[^\x{100}\x{200}]X/8
+    AX
+ 0: AX
+    \x{150}X
+ 0: \x{150}X
+    \x{500}X 
+ 0: \x{500}X
+    *** Failers
+No match
+    \x{100}X
+No match
+    \x{200}X   
+No match
+
+/[^Q\x{100}\x{200}]X/8
+    AX
+ 0: AX
+    \x{150}X
+ 0: \x{150}X
+    \x{500}X 
+ 0: \x{500}X
+    *** Failers
+No match
+    \x{100}X
+No match
+    \x{200}X   
+No match
+    QX 
+No match
+
+/[^\x{100}-\x{200}]X/8
+    AX
+ 0: AX
+    \x{500}X 
+ 0: \x{500}X
+    *** Failers
+No match
+    \x{100}X
+No match
+    \x{150}X
+No match
+    \x{200}X   
+No match
+
+/[z-\x{100}]/8i
+    z
+ 0: z
+    Z 
+ 0: Z
+    \x{100}
+ 0: \x{100}
+    *** Failers
+No match
+    \x{102}
+No match
+    y    
+No match
+
+/[\xFF]/
+    >\xff<
+ 0: \xff
+
+/[\xff]/8
+    >\x{ff}<
+ 0: \x{ff}
+
+/[^\xFF]/
+    XYZ
+ 0: X
+
+/[^\xff]/8
+    XYZ
+ 0: X
+    \x{123} 
+ 0: \x{123}
+
+/^[ac]*b/8
+  xb
+No match
+
+/^[ac\x{100}]*b/8
+  xb
+No match
+
+/^[^x]*b/8i
+  xb
+No match
+
+/^[^x]*b/8
+  xb
+No match
+  
+/^\d*b/8
+  xb 
+No match
+
+/(|a)/g8
+    catac
+ 0: 
+ 1: 
+ 0: 
+ 1: 
+ 0: a
+ 1: a
+ 0: 
+ 1: 
+ 0: 
+ 1: 
+ 0: a
+ 1: a
+ 0: 
+ 1: 
+ 0: 
+ 1: 
+    a\x{256}a 
+ 0: 
+ 1: 
+ 0: a
+ 1: a
+ 0: 
+ 1: 
+ 0: 
+ 1: 
+ 0: a
+ 1: a
+ 0: 
+ 1: 
+
+/^\x{85}$/8i
+    \x{85}
+ 0: \x{85}
+
+/^ሴ/8
+    ሴ 
+ 0: \x{1234}
+
+/^\ሴ/8
+    ሴ 
+ 0: \x{1234}
+
+"(?s)(.{1,5})"8
+    abcdefg
+ 0: abcde
+ 1: abcde
+    ab
+ 0: ab
+ 1: ab
+
+/a*\x{100}*\w/8
+    a 
+ 0: a
+
+/\S\S/8g
+    A\x{a3}BC
+ 0: A\x{a3}
+ 0: BC
+    
+/\S{2}/8g
+    A\x{a3}BC
+ 0: A\x{a3}
+ 0: BC
+    
+/\W\W/8g
+    +\x{a3}== 
+ 0: +\x{a3}
+ 0: ==
+
+/\W{2}/8g
+    +\x{a3}== 
+ 0: +\x{a3}
+ 0: ==
+
+/\S/8g
+    \x{442}\x{435}\x{441}\x{442}
+ 0: \x{442}
+ 0: \x{435}
+ 0: \x{441}
+ 0: \x{442}
+
+/[\S]/8g
+    \x{442}\x{435}\x{441}\x{442}
+ 0: \x{442}
+ 0: \x{435}
+ 0: \x{441}
+ 0: \x{442}
+
+/\D/8g
+    \x{442}\x{435}\x{441}\x{442}
+ 0: \x{442}
+ 0: \x{435}
+ 0: \x{441}
+ 0: \x{442}
+
+/[\D]/8g
+    \x{442}\x{435}\x{441}\x{442}
+ 0: \x{442}
+ 0: \x{435}
+ 0: \x{441}
+ 0: \x{442}
+
+/\W/8g
+    \x{2442}\x{2435}\x{2441}\x{2442}
+ 0: \x{2442}
+ 0: \x{2435}
+ 0: \x{2441}
+ 0: \x{2442}
+
+/[\W]/8g
+    \x{2442}\x{2435}\x{2441}\x{2442}
+ 0: \x{2442}
+ 0: \x{2435}
+ 0: \x{2441}
+ 0: \x{2442}
+    
+/[\S\s]*/8
+    abc\n\r\x{442}\x{435}\x{441}\x{442}xyz 
+ 0: abc\x{0a}\x{0d}\x{442}\x{435}\x{441}\x{442}xyz
+
+/[\x{41f}\S]/8g
+    \x{442}\x{435}\x{441}\x{442}
+ 0: \x{442}
+ 0: \x{435}
+ 0: \x{441}
+ 0: \x{442}
+
+/.[^\S]./8g
+    abc def\x{442}\x{443}xyz\npqr
+ 0: c d
+ 0: z\x{0a}p
+
+/.[^\S\n]./8g
+    abc def\x{442}\x{443}xyz\npqr
+ 0: c d
+
+/[[:^alnum:]]/8g  
+    +\x{2442}
+ 0: +
+ 0: \x{2442}
+    
+/[[:^alpha:]]/8g 
+    +\x{2442}
+ 0: +
+ 0: \x{2442}
+    
+/[[:^ascii:]]/8g 
+    A\x{442}
+ 0: \x{442}
+    
+/[[:^blank:]]/8g 
+    A\x{442}
+ 0: A
+ 0: \x{442}
+    
+/[[:^cntrl:]]/8g 
+    A\x{442}
+ 0: A
+ 0: \x{442}
+    
+/[[:^digit:]]/8g 
+    A\x{442}
+ 0: A
+ 0: \x{442}
+    
+/[[:^graph:]]/8g 
+    \x19\x{e01ff}
+ 0: \x{19}
+ 0: \x{e01ff}
+    
+/[[:^lower:]]/8g 
+    A\x{422}
+ 0: A
+ 0: \x{422}
+    
+/[[:^print:]]/8g 
+    \x{19}\x{e01ff}
+ 0: \x{19}
+ 0: \x{e01ff}
+    
+/[[:^punct:]]/8g 
+    A\x{442}
+ 0: A
+ 0: \x{442}
+    
+/[[:^space:]]/8g 
+    A\x{442}
+ 0: A
+ 0: \x{442}
+    
+/[[:^upper:]]/8g 
+    a\x{442}
+ 0: a
+ 0: \x{442}
+    
+/[[:^word:]]/8g  
+    +\x{2442}
+ 0: +
+ 0: \x{2442}
+    
+/[[:^xdigit:]]/8g
+    M\x{442}
+ 0: M
+ 0: \x{442}
+
+/[^ABCDEFGHIJKLMNOPQRSTUVWXYZÀ�ÂÃÄÅÆÇÈÉÊËÌ�Î��ÑÒÓÔÕÖØÙÚÛÜ�ÞĀĂĄĆĈĊČĎ�ĒĔĖĘĚĜĞĠĢĤĦĨĪĬĮİIJĴĶĹĻĽĿ�ŃŅŇŊŌŎ�ŒŔŖŘŚŜŞŠŢŤŦŨŪŬŮŰŲŴŶŸŹŻŽ�ƂƄƆƇƉƊƋƎ��ƑƓƔƖƗƘƜ�ƟƠƢƤƦƧƩƬƮƯƱƲƳƵƷƸƼDŽLJNJ��ǑǓǕǗǙǛǞǠǢǤǦǨǪǬǮDZǴǶǷǸǺǼǾȀȂȄȆȈȊȌȎ�ȒȔȖȘȚȜȞȠȢȤȦȨȪȬȮȰȲȺȻȽȾ�ΆΈΉΊΌΎ�ΑΒΓΔΕΖΗΘΙΚΛΜ�ΞΟΠΡΣΤΥΦΧΨΩΪΫϒϓϔϘϚϜϞϠϢϤϦϨϪϬϮϴϷϹϺϽϾϿЀ�ЂЃЄЅІЇЈЉЊЋЌ�Ў��БВГДЕЖЗИЙКЛМ�ОПРСТУФХЦЧШЩЪЫЬЭЮЯѠѢѤѦѨѪѬѮѰѲѴѶѸѺѼѾҀҊҌҎ�ҒҔҖҘҚҜҞҠҢҤҦҨҪҬҮҰҲҴҶҸҺҼҾӀ�ӃӅӇӉӋ��ӒӔӖӘӚӜӞӠӢӤӦӨӪӬӮӰӲӴӶӸԀԂԄԆԈԊԌԎԱԲԳԴԵԶԷԸԹԺԻԼԽԾԿՀ�ՂՃՄՅՆՇՈՉՊՋՌ�Վ��ՑՒՓՔՕՖႠႡႢႣႤႥႦႧႨႩႪႫႬႭႮႯႰႱႲႳႴႵႶႷႸႹႺႻႼႽႾႿჀ�ჂჃჄჅḀḂḄḆḈḊḌḎ�ḒḔḖḘḚḜḞḠḢḤḦḨḪḬḮḰḲḴḶḸḺḼḾṀṂṄṆṈṊṌṎ�ṒṔṖṘṚṜṞṠṢṤṦṨṪṬṮṰṲṴṶṸṺṼṾẀẂẄẆẈẊẌẎ�ẒẔẠẢẤẦẨẪẬẮẰẲẴẶẸẺẼẾỀỂỄỆỈỊỌỎ�ỒỔỖỘỚỜỞỠỢỤỦỨỪỬỮỰỲỴỶỸἈἉἊἋἌ�Ἆ�ἘἙἚἛἜ�ἨἩἪἫἬἭἮἯἸἹἺἻἼἽἾἿὈὉὊὋὌ�ὙὛ�ὟὨὩὪὫὬὭὮὯᾸᾹᾺΆῈΈῊΉῘῙῚΊῨῩῪΎῬῸΌῺΏabcdefghijklmnopqrstuvwxyzªµºßàáâãäåæçèéêëìíîïðñòóôõöøùúûüýþÿ�ăąćĉċ��đēĕėęě�ğġģĥħĩīĭįıijĵķĸĺļľŀłńņňʼnŋ��őœŕŗřś�şšţťŧũūŭůűųŵŷźżžſƀƃƅƈƌ�ƒƕƙƚƛƞơƣƥƨƪƫƭưƴƶƹƺƽƾƿdžljnjǎ�ǒǔǖǘǚǜ�ǟǡǣǥǧǩǫǭǯǰdzǵǹǻǽǿ�ȃȅȇȉȋ��ȑȓȕȗșț�ȟȡȣȥȧȩȫȭȯȱȳȴȵȶȷȸȹȼȿɀ�ɑɒɓɔɕɖɗɘəɚɛɜ�ɞɟɠɡɢɣɤɥɦɧɨɩɪɫɬɭɮɯɰɱɲɳɴɵɶɷɸɹɺɻɼɽɾɿʀ�ʂʃʄʅʆʇʈʉʊʋʌ�ʎ��ʑʒʓʔʕʖʗʘʙʚʛʜ�ʞʟʠʡʢʣʤʥʦʧʨʩʪʫʬʭʮʯ�άέήίΰαβγδεζηθικλμνξοπ�ςστυφχψωϊϋό�ώ�ϑϕϖϗϙϛ�ϟϡϣϥϧϩϫϭϯϰϱϲϳϵϸϻϼабвгдежзийклмнопр�туфхцчшщъыь�ю��ёђѓєѕіїјљњћќ�ўџѡѣѥѧѩѫѭѯѱѳѵѷѹѻѽѿ�ҋ��ґғҕҗҙқ�ҟҡңҥҧҩҫҭүұҳҵҷҹһҽҿӂӄӆӈӊӌӎӑӓӕӗәӛ�ӟӡӣӥӧөӫӭӯӱӳӵӷӹ�ԃԅԇԉԋ��աբգդեզէըթժիլխծկհձղճմյնշոչպջռսվտր�ւփքօֆևᴀ�ᴂᴃᴄᴅᴆᴇᴈᴉᴊᴋᴌ�ᴎ��ᴑᴒᴓᴔᴕᴖᴗᴘᴙᴚᴛᴜ�ᴞᴟᴠᴡᴢᴣᴤᴥᴦᴧᴨᴩᴪᴫᵢᵣᵤᵥᵦᵧᵨᵩᵪᵫᵬᵭᵮᵯᵰᵱᵲᵳᵴᵵᵶᵷᵹᵺᵻᵼᵽᵾᵿᶀ�ᶂᶃᶄᶅᶆᶇᶈᶉᶊᶋᶌ�ᶎ��ᶑᶒᶓᶔᶕᶖᶗᶘᶙᶚ�ḃḅḇḉḋ��ḑḓḕḗḙḛ�ḟḡḣḥḧḩḫḭḯḱḳḵḷḹḻḽḿ�ṃṅṇṉṋ��ṑṓṕṗṙṛ�ṟṡṣṥṧṩṫṭṯṱṳṵṷṹṻṽṿ�ẃẅẇẉẋ��ẑẓẕẖẗẘẙẚẛạảấầẩẫậắằẳẵặẹẻẽế�ểễệỉị��ốồổỗộớ�ởỡợụủứừửữựỳỵỷỹἀ�ἂἃἄἅἆἇ�ἑἒἓἔἕἠἡἢἣἤἥἦἧἰἱἲἳἴἵἶἷὀ�ὂὃὄὅ�ὑὒὓὔὕὖὗὠὡὢὣὤὥὦὧὰάὲέὴήὶίὸόὺύὼώᾀ�ᾂᾃᾄᾅᾆᾇ�ᾑᾒᾓᾔᾕᾖᾗᾠᾡᾢᾣᾤᾥᾦᾧᾰᾱᾲᾳᾴᾶᾷιῂῃῄῆῇ�ῑῒΐῖῗῠῡῢΰῤῥῦῧῲῳῴῶῷ�ⲃⲅⲇⲉⲋ��ⲑⲓⲕⲗⲙⲛ�ⲟⲡⲣⲥⲧⲩⲫⲭⲯⲱⲳⲵⲷⲹⲻⲽⲿ�ⳃⳅⳇⳉⳋ��ⳑⳓⳕⳗⳙⳛ�ⳟⳡⳣⳤⴀ�ⴂⴃⴄⴅⴆⴇⴈⴉⴊⴋⴌ�ⴎ��ⴑⴒⴓⴔⴕⴖⴗⴘⴙⴚⴛⴜ�ⴞⴟⴠⴡⴢⴣⴤⴥff�flffifflſtstﬓﬔﬕﬖﬗ\d-_^]/8
+
+/^[^d]*?$/
+    abc
+ 0: abc
+
+/^[^d]*?$/8
+    abc
+ 0: abc
+
+/^[^d]*?$/i
+    abc
+ 0: abc
+
+/^[^d]*?$/8i
+    abc
+ 0: abc
+
+/(?i)[\xc3\xa9\xc3\xbd]|[\xc3\xa9\xc3\xbdA]/8
+
+/^[a\x{c0}]b/8
+    \x{c0}b
+ 0: \x{c0}b
+    
+/^([a\x{c0}]*?)aa/8
+    a\x{c0}aaaa/ 
+ 0: a\x{c0}aa
+ 1: a\x{c0}
+
+/^([a\x{c0}]*?)aa/8
+    a\x{c0}aaaa/ 
+ 0: a\x{c0}aa
+ 1: a\x{c0}
+    a\x{c0}a\x{c0}aaa/ 
+ 0: a\x{c0}a\x{c0}aa
+ 1: a\x{c0}a\x{c0}
+
+/^([a\x{c0}]*)aa/8
+    a\x{c0}aaaa/ 
+ 0: a\x{c0}aaaa
+ 1: a\x{c0}aa
+    a\x{c0}a\x{c0}aaa/ 
+ 0: a\x{c0}a\x{c0}aaa
+ 1: a\x{c0}a\x{c0}a
+
+/^([a\x{c0}]*)a\x{c0}/8
+    a\x{c0}aaaa/ 
+ 0: a\x{c0}
+ 1: 
+    a\x{c0}a\x{c0}aaa/ 
+ 0: a\x{c0}a\x{c0}
+ 1: a\x{c0}
+
+/A*/g8
+    AAB\x{123}BAA
+ 0: AA
+ 0: 
+ 0: 
+ 0: 
+ 0: AA
+ 0: 
+
+/(abc)\1/8i
+   abc
+No match
+
+/(abc)\1/8
+   abc
+No match
+
+/a(*:a\x{1234}b)/8K
+    abc
+ 0: a
+MK: a\x{1234}b
+
+/a(*:a£b)/8K 
+    abc
+ 0: a
+MK: a\x{a3}b
+
+/-- End of testinput4 --/
diff --git a/ext/pcre/pcrelib/testdata/testoutput5 b/ext/pcre/pcrelib/testdata/testoutput5
new file mode 100644
index 0000000..c4f9a0c
--- /dev/null
+++ b/ext/pcre/pcrelib/testdata/testoutput5
@@ -0,0 +1,1849 @@
+/-- This set of tests checks the API, internals, and non-Perl stuff for UTF
+    support, excluding Unicode properties. However, tests that give different
+    results in 8-bit and 16-bit modes are excluded (see tests 16 and 17). --/
+
+/\x{110000}/8DZ
+Failed: character value in \x{...} sequence is too large at offset 9
+
+/\x{ffffffff}/8
+Failed: character value in \x{...} sequence is too large at offset 11
+
+/\x{100000000}/8
+Failed: character value in \x{...} sequence is too large at offset 12
+
+/\x{d800}/8
+Failed: disallowed Unicode code point (>= 0xd800 && <= 0xdfff) at offset 7
+
+/\x{dfff}/8
+Failed: disallowed Unicode code point (>= 0xd800 && <= 0xdfff) at offset 7
+
+/\x{d7ff}/8
+
+/\x{e000}/8
+
+/^\x{100}a\x{1234}/8
+    \x{100}a\x{1234}bcd
+ 0: \x{100}a\x{1234}
+
+/\x{0041}\x{2262}\x{0391}\x{002e}/DZ8
+------------------------------------------------------------------
+        Bra
+        A\x{2262}\x{391}.
+        Ket
+        End
+------------------------------------------------------------------
+Capturing subpattern count = 0
+Options: utf
+First char = 'A'
+Need char = '.'
+    \x{0041}\x{2262}\x{0391}\x{002e}
+ 0: A\x{2262}\x{391}.
+    
+/.{3,5}X/DZ8
+------------------------------------------------------------------
+        Bra
+        Any{3}
+        Any{0,2}
+        X
+        Ket
+        End
+------------------------------------------------------------------
+Capturing subpattern count = 0
+Options: utf
+No first char
+Need char = 'X'
+    \x{212ab}\x{212ab}\x{212ab}\x{861}X
+ 0: \x{212ab}\x{212ab}\x{212ab}\x{861}X
+
+/.{3,5}?/DZ8
+------------------------------------------------------------------
+        Bra
+        Any{3}
+        Any{0,2}?
+        Ket
+        End
+------------------------------------------------------------------
+Capturing subpattern count = 0
+Options: utf
+No first char
+No need char
+    \x{212ab}\x{212ab}\x{212ab}\x{861}
+ 0: \x{212ab}\x{212ab}\x{212ab}
+
+/(?<=\C)X/8
+Failed: \C not allowed in lookbehind assertion at offset 6
+
+/^[ab]/8DZ
+------------------------------------------------------------------
+        Bra
+        ^
+        [ab]
+        Ket
+        End
+------------------------------------------------------------------
+Capturing subpattern count = 0
+Options: anchored utf
+No first char
+No need char
+    bar
+ 0: b
+    *** Failers
+No match
+    c
+No match
+    \x{ff}
+No match
+    \x{100}  
+No match
+
+/^[^ab]/8DZ
+------------------------------------------------------------------
+        Bra
+        ^
+        [\x00-`c-\xff] (neg)
+        Ket
+        End
+------------------------------------------------------------------
+Capturing subpattern count = 0
+Options: anchored utf
+No first char
+No need char
+    c
+ 0: c
+    \x{ff}
+ 0: \x{ff}
+    \x{100}  
+ 0: \x{100}
+    *** Failers 
+ 0: *
+    aaa
+No match
+  
+/\x{100}*(\d+|"(?1)")/8
+    1234
+ 0: 1234
+ 1: 1234
+    "1234" 
+ 0: "1234"
+ 1: "1234"
+    \x{100}1234
+ 0: \x{100}1234
+ 1: 1234
+    "\x{100}1234"  
+ 0: \x{100}1234
+ 1: 1234
+    \x{100}\x{100}12ab 
+ 0: \x{100}\x{100}12
+ 1: 12
+    \x{100}\x{100}"12" 
+ 0: \x{100}\x{100}"12"
+ 1: "12"
+    *** Failers 
+No match
+    \x{100}\x{100}abcd
+No match
+
+/\x{100}*/8DZ
+------------------------------------------------------------------
+        Bra
+        \x{100}*
+        Ket
+        End
+------------------------------------------------------------------
+Capturing subpattern count = 0
+Options: utf
+No first char
+No need char
+
+/a\x{100}*/8DZ
+------------------------------------------------------------------
+        Bra
+        a
+        \x{100}*
+        Ket
+        End
+------------------------------------------------------------------
+Capturing subpattern count = 0
+Options: utf
+First char = 'a'
+No need char
+
+/ab\x{100}*/8DZ
+------------------------------------------------------------------
+        Bra
+        ab
+        \x{100}*
+        Ket
+        End
+------------------------------------------------------------------
+Capturing subpattern count = 0
+Options: utf
+First char = 'a'
+Need char = 'b'
+
+/\x{100}*A/8DZ
+------------------------------------------------------------------
+        Bra
+        \x{100}*+
+        A
+        Ket
+        End
+------------------------------------------------------------------
+Capturing subpattern count = 0
+Options: utf
+No first char
+Need char = 'A'
+    A
+ 0: A
+
+/\x{100}*\d(?R)/8DZ
+------------------------------------------------------------------
+        Bra
+        \x{100}*+
+        \d
+        Recurse
+        Ket
+        End
+------------------------------------------------------------------
+Capturing subpattern count = 0
+Options: utf
+No first char
+No need char
+
+/[Z\x{100}]/8DZ
+------------------------------------------------------------------
+        Bra
+        [Z\x{100}]
+        Ket
+        End
+------------------------------------------------------------------
+Capturing subpattern count = 0
+Options: utf
+No first char
+No need char
+    Z\x{100}
+ 0: Z
+    \x{100}
+ 0: \x{100}
+    \x{100}Z
+ 0: \x{100}
+    *** Failers 
+No match
+
+/[\x{200}-\x{100}]/8
+Failed: range out of order in character class at offset 15
+
+/[Ä€-Ä„]/8
+    \x{100}
+ 0: \x{100}
+    \x{104}
+ 0: \x{104}
+    *** Failers
+No match
+    \x{105}
+No match
+    \x{ff}    
+No match
+
+/[z-\x{100}]/8DZ
+------------------------------------------------------------------
+        Bra
+        [z-\x{100}]
+        Ket
+        End
+------------------------------------------------------------------
+Capturing subpattern count = 0
+Options: utf
+No first char
+No need char
+
+/[z\Qa-d]Ä€\E]/8DZ
+------------------------------------------------------------------
+        Bra
+        [\-\]adz\x{100}]
+        Ket
+        End
+------------------------------------------------------------------
+Capturing subpattern count = 0
+Options: utf
+No first char
+No need char
+    \x{100}
+ 0: \x{100}
+    Ā 
+ 0: \x{100}
+
+/[\xFF]/DZ
+------------------------------------------------------------------
+        Bra
+        \xff
+        Ket
+        End
+------------------------------------------------------------------
+Capturing subpattern count = 0
+No options
+First char = \xff
+No need char
+    >\xff<
+ 0: \xff
+
+/[^\xFF]/DZ
+------------------------------------------------------------------
+        Bra
+        [^\xff]
+        Ket
+        End
+------------------------------------------------------------------
+Capturing subpattern count = 0
+No options
+No first char
+No need char
+
+/[Ä-Ü]/8
+    Ö # Matches without Study
+ 0: \x{d6}
+    \x{d6}
+ 0: \x{d6}
+    
+/[Ä-Ü]/8S
+    Ö <-- Same with Study
+ 0: \x{d6}
+    \x{d6}
+ 0: \x{d6}
+    
+/[\x{c4}-\x{dc}]/8 
+    Ö # Matches without Study
+ 0: \x{d6}
+    \x{d6} 
+ 0: \x{d6}
+
+/[\x{c4}-\x{dc}]/8S
+    Ö <-- Same with Study
+ 0: \x{d6}
+    \x{d6} 
+ 0: \x{d6}
+
+/[^\x{100}]abc(xyz(?1))/8DZ
+------------------------------------------------------------------
+        Bra
+        [^\x{100}]
+        abc
+        CBra 1
+        xyz
+        Recurse
+        Ket
+        Ket
+        End
+------------------------------------------------------------------
+Capturing subpattern count = 1
+Options: utf
+No first char
+Need char = 'z'
+
+/[ab\x{100}]abc(xyz(?1))/8DZ
+------------------------------------------------------------------
+        Bra
+        [ab\x{100}]
+        abc
+        CBra 1
+        xyz
+        Recurse
+        Ket
+        Ket
+        End
+------------------------------------------------------------------
+Capturing subpattern count = 1
+Options: utf
+No first char
+Need char = 'z'
+
+/(\x{100}(b(?2)c))?/DZ8
+------------------------------------------------------------------
+        Bra
+        Brazero
+        CBra 1
+        \x{100}
+        CBra 2
+        b
+        Recurse
+        c
+        Ket
+        Ket
+        Ket
+        End
+------------------------------------------------------------------
+Capturing subpattern count = 2
+Options: utf
+No first char
+No need char
+
+/(\x{100}(b(?2)c)){0,2}/DZ8
+------------------------------------------------------------------
+        Bra
+        Brazero
+        Bra
+        CBra 1
+        \x{100}
+        CBra 2
+        b
+        Recurse
+        c
+        Ket
+        Ket
+        Brazero
+        CBra 1
+        \x{100}
+        CBra 2
+        b
+        Recurse
+        c
+        Ket
+        Ket
+        Ket
+        Ket
+        End
+------------------------------------------------------------------
+Capturing subpattern count = 2
+Options: utf
+No first char
+No need char
+
+/(\x{100}(b(?1)c))?/DZ8
+------------------------------------------------------------------
+        Bra
+        Brazero
+        CBra 1
+        \x{100}
+        CBra 2
+        b
+        Recurse
+        c
+        Ket
+        Ket
+        Ket
+        End
+------------------------------------------------------------------
+Capturing subpattern count = 2
+Options: utf
+No first char
+No need char
+
+/(\x{100}(b(?1)c)){0,2}/DZ8
+------------------------------------------------------------------
+        Bra
+        Brazero
+        Bra
+        CBra 1
+        \x{100}
+        CBra 2
+        b
+        Recurse
+        c
+        Ket
+        Ket
+        Brazero
+        CBra 1
+        \x{100}
+        CBra 2
+        b
+        Recurse
+        c
+        Ket
+        Ket
+        Ket
+        Ket
+        End
+------------------------------------------------------------------
+Capturing subpattern count = 2
+Options: utf
+No first char
+No need char
+
+/\W/8
+    A.B
+ 0: .
+    A\x{100}B 
+ 0: \x{100}
+  
+/\w/8
+    \x{100}X   
+ 0: X
+
+/^\ሴ/8DZ
+------------------------------------------------------------------
+        Bra
+        ^
+        \x{1234}
+        Ket
+        End
+------------------------------------------------------------------
+Capturing subpattern count = 0
+Options: anchored utf
+No first char
+No need char
+
+/\x{100}*\d/8DZ
+------------------------------------------------------------------
+        Bra
+        \x{100}*+
+        \d
+        Ket
+        End
+------------------------------------------------------------------
+Capturing subpattern count = 0
+Options: utf
+No first char
+No need char
+
+/\x{100}*\s/8DZ
+------------------------------------------------------------------
+        Bra
+        \x{100}*+
+        \s
+        Ket
+        End
+------------------------------------------------------------------
+Capturing subpattern count = 0
+Options: utf
+No first char
+No need char
+
+/\x{100}*\w/8DZ
+------------------------------------------------------------------
+        Bra
+        \x{100}*+
+        \w
+        Ket
+        End
+------------------------------------------------------------------
+Capturing subpattern count = 0
+Options: utf
+No first char
+No need char
+
+/\x{100}*\D/8DZ
+------------------------------------------------------------------
+        Bra
+        \x{100}*
+        \D
+        Ket
+        End
+------------------------------------------------------------------
+Capturing subpattern count = 0
+Options: utf
+No first char
+No need char
+
+/\x{100}*\S/8DZ
+------------------------------------------------------------------
+        Bra
+        \x{100}*
+        \S
+        Ket
+        End
+------------------------------------------------------------------
+Capturing subpattern count = 0
+Options: utf
+No first char
+No need char
+
+/\x{100}*\W/8DZ
+------------------------------------------------------------------
+        Bra
+        \x{100}*
+        \W
+        Ket
+        End
+------------------------------------------------------------------
+Capturing subpattern count = 0
+Options: utf
+No first char
+No need char
+
+/()()()()()()()()()()
+ ()()()()()()()()()()
+ ()()()()()()()()()()
+ ()()()()()()()()()()
+ A (x) (?41) B/8x
+    AxxB     
+Matched, but too many substrings
+ 0: AxxB
+ 1: 
+ 2: 
+ 3: 
+ 4: 
+ 5: 
+ 6: 
+ 7: 
+ 8: 
+ 9: 
+10: 
+11: 
+12: 
+13: 
+14: 
+
+/^[\x{100}\E-\Q\E\x{150}]/BZ8
+------------------------------------------------------------------
+        Bra
+        ^
+        [\x{100}-\x{150}]
+        Ket
+        End
+------------------------------------------------------------------
+
+/^[\QĀ\E-\Q�\E]/BZ8
+------------------------------------------------------------------
+        Bra
+        ^
+        [\x{100}-\x{150}]
+        Ket
+        End
+------------------------------------------------------------------
+
+/^abc./mgx8<any>
+    abc1 \x0aabc2 \x0babc3xx \x0cabc4 \x0dabc5xx \x0d\x0aabc6 \x{0085}abc7 \x{2028}abc8 \x{2029}abc9 JUNK
+ 0: abc1
+ 0: abc2
+ 0: abc3
+ 0: abc4
+ 0: abc5
+ 0: abc6
+ 0: abc7
+ 0: abc8
+ 0: abc9
+
+/abc.$/mgx8<any>
+    abc1\x0a abc2\x0b abc3\x0c abc4\x0d abc5\x0d\x0a abc6\x{0085} abc7\x{2028} abc8\x{2029} abc9
+ 0: abc1
+ 0: abc2
+ 0: abc3
+ 0: abc4
+ 0: abc5
+ 0: abc6
+ 0: abc7
+ 0: abc8
+ 0: abc9
+
+/^a\Rb/8<bsr_unicode>
+    a\nb
+ 0: a\x{0a}b
+    a\rb
+ 0: a\x{0d}b
+    a\r\nb
+ 0: a\x{0d}\x{0a}b
+    a\x0bb
+ 0: a\x{0b}b
+    a\x0cb
+ 0: a\x{0c}b
+    a\x{85}b   
+ 0: a\x{85}b
+    a\x{2028}b 
+ 0: a\x{2028}b
+    a\x{2029}b 
+ 0: a\x{2029}b
+    ** Failers
+No match
+    a\n\rb    
+No match
+
+/^a\R*b/8<bsr_unicode>
+    ab
+ 0: ab
+    a\nb
+ 0: a\x{0a}b
+    a\rb
+ 0: a\x{0d}b
+    a\r\nb
+ 0: a\x{0d}\x{0a}b
+    a\x0bb
+ 0: a\x{0b}b
+    a\x0c\x{2028}\x{2029}b
+ 0: a\x{0c}\x{2028}\x{2029}b
+    a\x{85}b   
+ 0: a\x{85}b
+    a\n\rb    
+ 0: a\x{0a}\x{0d}b
+    a\n\r\x{85}\x0cb 
+ 0: a\x{0a}\x{0d}\x{85}\x{0c}b
+
+/^a\R+b/8<bsr_unicode>
+    a\nb
+ 0: a\x{0a}b
+    a\rb
+ 0: a\x{0d}b
+    a\r\nb
+ 0: a\x{0d}\x{0a}b
+    a\x0bb
+ 0: a\x{0b}b
+    a\x0c\x{2028}\x{2029}b
+ 0: a\x{0c}\x{2028}\x{2029}b
+    a\x{85}b   
+ 0: a\x{85}b
+    a\n\rb    
+ 0: a\x{0a}\x{0d}b
+    a\n\r\x{85}\x0cb 
+ 0: a\x{0a}\x{0d}\x{85}\x{0c}b
+    ** Failers
+No match
+    ab  
+No match
+
+/^a\R{1,3}b/8<bsr_unicode>
+    a\nb
+ 0: a\x{0a}b
+    a\n\rb
+ 0: a\x{0a}\x{0d}b
+    a\n\r\x{85}b
+ 0: a\x{0a}\x{0d}\x{85}b
+    a\r\n\r\nb 
+ 0: a\x{0d}\x{0a}\x{0d}\x{0a}b
+    a\r\n\r\n\r\nb 
+ 0: a\x{0d}\x{0a}\x{0d}\x{0a}\x{0d}\x{0a}b
+    a\n\r\n\rb
+ 0: a\x{0a}\x{0d}\x{0a}\x{0d}b
+    a\n\n\r\nb 
+ 0: a\x{0a}\x{0a}\x{0d}\x{0a}b
+    ** Failers
+No match
+    a\n\n\n\rb
+No match
+    a\r
+No match
+
+/\H\h\V\v/8
+    X X\x0a
+ 0: X X\x{0a}
+    X\x09X\x0b
+ 0: X\x{09}X\x{0b}
+    ** Failers
+No match
+    \x{a0} X\x0a   
+No match
+    
+/\H*\h+\V?\v{3,4}/8 
+    \x09\x20\x{a0}X\x0a\x0b\x0c\x0d\x0a
+ 0: \x{09} \x{a0}X\x{0a}\x{0b}\x{0c}\x{0d}
+    \x09\x20\x{a0}\x0a\x0b\x0c\x0d\x0a
+ 0: \x{09} \x{a0}\x{0a}\x{0b}\x{0c}\x{0d}
+    \x09\x20\x{a0}\x0a\x0b\x0c
+ 0: \x{09} \x{a0}\x{0a}\x{0b}\x{0c}
+    ** Failers 
+No match
+    \x09\x20\x{a0}\x0a\x0b
+No match
+     
+/\H\h\V\v/8
+    \x{3001}\x{3000}\x{2030}\x{2028}
+ 0: \x{3001}\x{3000}\x{2030}\x{2028}
+    X\x{180e}X\x{85}
+ 0: X\x{180e}X\x{85}
+    ** Failers
+No match
+    \x{2009} X\x0a   
+No match
+    
+/\H*\h+\V?\v{3,4}/8 
+    \x{1680}\x{180e}\x{2007}X\x{2028}\x{2029}\x0c\x0d\x0a
+ 0: \x{1680}\x{180e}\x{2007}X\x{2028}\x{2029}\x{0c}\x{0d}
+    \x09\x{205f}\x{a0}\x0a\x{2029}\x0c\x{2028}\x0a
+ 0: \x{09}\x{205f}\x{a0}\x{0a}\x{2029}\x{0c}\x{2028}
+    \x09\x20\x{202f}\x0a\x0b\x0c
+ 0: \x{09} \x{202f}\x{0a}\x{0b}\x{0c}
+    ** Failers 
+No match
+    \x09\x{200a}\x{a0}\x{2028}\x0b
+No match
+     
+/[\h]/8BZ
+------------------------------------------------------------------
+        Bra
+        [\x09 \xa0\x{1680}\x{180e}\x{2000}-\x{200a}\x{202f}\x{205f}\x{3000}]
+        Ket
+        End
+------------------------------------------------------------------
+    >\x{1680}
+ 0: \x{1680}
+
+/[\h]{3,}/8BZ
+------------------------------------------------------------------
+        Bra
+        [\x09 \xa0\x{1680}\x{180e}\x{2000}-\x{200a}\x{202f}\x{205f}\x{3000}]{3,}
+        Ket
+        End
+------------------------------------------------------------------
+    >\x{1680}\x{180e}\x{2000}\x{2003}\x{200a}\x{202f}\x{205f}\x{3000}<
+ 0: \x{1680}\x{180e}\x{2000}\x{2003}\x{200a}\x{202f}\x{205f}\x{3000}
+
+/[\v]/8BZ
+------------------------------------------------------------------
+        Bra
+        [\x0a-\x0d\x85\x{2028}-\x{2029}]
+        Ket
+        End
+------------------------------------------------------------------
+
+/[\H]/8BZ
+------------------------------------------------------------------
+        Bra
+        [\x00-\x08\x0a-\x1f!-\x9f\xa1-\xff\x{100}-\x{167f}\x{1681}-\x{180d}\x{180f}-\x{1fff}\x{200b}-\x{202e}\x{2030}-\x{205e}\x{2060}-\x{2fff}\x{3001}-\x{10ffff}]
+        Ket
+        End
+------------------------------------------------------------------
+
+/[\V]/8BZ
+------------------------------------------------------------------
+        Bra
+        [\x00-\x09\x0e-\x84\x86-\xff\x{100}-\x{2027}\x{202a}-\x{10ffff}]
+        Ket
+        End
+------------------------------------------------------------------
+
+/.*$/8<any>
+    \x{1ec5} 
+ 0: \x{1ec5}
+    
+/a\Rb/I8<bsr_anycrlf>
+Capturing subpattern count = 0
+Options: bsr_anycrlf utf
+First char = 'a'
+Need char = 'b'
+    a\rb
+ 0: a\x{0d}b
+    a\nb
+ 0: a\x{0a}b
+    a\r\nb
+ 0: a\x{0d}\x{0a}b
+    ** Failers
+No match
+    a\x{85}b
+No match
+    a\x0bb     
+No match
+
+/a\Rb/I8<bsr_unicode>
+Capturing subpattern count = 0
+Options: bsr_unicode utf
+First char = 'a'
+Need char = 'b'
+    a\rb
+ 0: a\x{0d}b
+    a\nb
+ 0: a\x{0a}b
+    a\r\nb
+ 0: a\x{0d}\x{0a}b
+    a\x{85}b
+ 0: a\x{85}b
+    a\x0bb     
+ 0: a\x{0b}b
+    ** Failers 
+No match
+    a\x{85}b\<bsr_anycrlf>
+No match
+    a\x0bb\<bsr_anycrlf>
+No match
+    
+/a\R?b/I8<bsr_anycrlf>
+Capturing subpattern count = 0
+Options: bsr_anycrlf utf
+First char = 'a'
+Need char = 'b'
+    a\rb
+ 0: a\x{0d}b
+    a\nb
+ 0: a\x{0a}b
+    a\r\nb
+ 0: a\x{0d}\x{0a}b
+    ** Failers
+No match
+    a\x{85}b
+No match
+    a\x0bb     
+No match
+
+/a\R?b/I8<bsr_unicode>
+Capturing subpattern count = 0
+Options: bsr_unicode utf
+First char = 'a'
+Need char = 'b'
+    a\rb
+ 0: a\x{0d}b
+    a\nb
+ 0: a\x{0a}b
+    a\r\nb
+ 0: a\x{0d}\x{0a}b
+    a\x{85}b
+ 0: a\x{85}b
+    a\x0bb     
+ 0: a\x{0b}b
+    ** Failers 
+No match
+    a\x{85}b\<bsr_anycrlf>
+No match
+    a\x0bb\<bsr_anycrlf>
+No match
+ 
+/.*a.*=.b.*/8<ANY>
+    QQQ\x{2029}ABCaXYZ=!bPQR
+ 0: ABCaXYZ=!bPQR
+    ** Failers
+No match
+    a\x{2029}b
+No match
+    \x61\xe2\x80\xa9\x62 
+No match
+
+/[[:a\x{100}b:]]/8
+Failed: unknown POSIX class name at offset 3
+
+/a[^]b/<JS>8
+    a\x{1234}b
+ 0: a\x{1234}b
+    a\nb 
+ 0: a\x{0a}b
+    ** Failers
+No match
+    ab  
+No match
+    
+/a[^]+b/<JS>8
+    aXb
+ 0: aXb
+    a\nX\nX\x{1234}b 
+ 0: a\x{0a}X\x{0a}X\x{1234}b
+    ** Failers
+No match
+    ab  
+No match
+
+/(\x{de})\1/
+    \x{de}\x{de}
+ 0: \xde\xde
+ 1: \xde
+
+/X/8f<any> 
+    A\x{1ec5}ABCXYZ
+ 0: X
+
+/Xa{2,4}b/8
+    X\P
+Partial match: X
+    Xa\P
+Partial match: Xa
+    Xaa\P 
+Partial match: Xaa
+    Xaaa\P
+Partial match: Xaaa
+    Xaaaa\P 
+Partial match: Xaaaa
+    
+/Xa{2,4}?b/8
+    X\P
+Partial match: X
+    Xa\P
+Partial match: Xa
+    Xaa\P 
+Partial match: Xaa
+    Xaaa\P
+Partial match: Xaaa
+    Xaaaa\P 
+Partial match: Xaaaa
+    
+/Xa{2,4}+b/8
+    X\P
+Partial match: X
+    Xa\P
+Partial match: Xa
+    Xaa\P 
+Partial match: Xaa
+    Xaaa\P
+Partial match: Xaaa
+    Xaaaa\P 
+Partial match: Xaaaa
+    
+/X\x{123}{2,4}b/8
+    X\P
+Partial match: X
+    X\x{123}\P
+Partial match: X\x{123}
+    X\x{123}\x{123}\P 
+Partial match: X\x{123}\x{123}
+    X\x{123}\x{123}\x{123}\P
+Partial match: X\x{123}\x{123}\x{123}
+    X\x{123}\x{123}\x{123}\x{123}\P 
+Partial match: X\x{123}\x{123}\x{123}\x{123}
+    
+/X\x{123}{2,4}?b/8
+    X\P
+Partial match: X
+    X\x{123}\P
+Partial match: X\x{123}
+    X\x{123}\x{123}\P 
+Partial match: X\x{123}\x{123}
+    X\x{123}\x{123}\x{123}\P
+Partial match: X\x{123}\x{123}\x{123}
+    X\x{123}\x{123}\x{123}\x{123}\P 
+Partial match: X\x{123}\x{123}\x{123}\x{123}
+    
+/X\x{123}{2,4}+b/8
+    X\P
+Partial match: X
+    X\x{123}\P
+Partial match: X\x{123}
+    X\x{123}\x{123}\P 
+Partial match: X\x{123}\x{123}
+    X\x{123}\x{123}\x{123}\P
+Partial match: X\x{123}\x{123}\x{123}
+    X\x{123}\x{123}\x{123}\x{123}\P 
+Partial match: X\x{123}\x{123}\x{123}\x{123}
+    
+/X\x{123}{2,4}b/8
+    Xx\P
+No match
+    X\x{123}x\P
+No match
+    X\x{123}\x{123}x\P 
+No match
+    X\x{123}\x{123}\x{123}x\P
+No match
+    X\x{123}\x{123}\x{123}\x{123}x\P 
+No match
+    
+/X\x{123}{2,4}?b/8
+    Xx\P
+No match
+    X\x{123}x\P
+No match
+    X\x{123}\x{123}x\P 
+No match
+    X\x{123}\x{123}\x{123}x\P
+No match
+    X\x{123}\x{123}\x{123}\x{123}x\P 
+No match
+    
+/X\x{123}{2,4}+b/8
+    Xx\P
+No match
+    X\x{123}x\P
+No match
+    X\x{123}\x{123}x\P 
+No match
+    X\x{123}\x{123}\x{123}x\P
+No match
+    X\x{123}\x{123}\x{123}\x{123}x\P 
+No match
+    
+/X\d{2,4}b/8
+    X\P
+Partial match: X
+    X3\P
+Partial match: X3
+    X33\P 
+Partial match: X33
+    X333\P
+Partial match: X333
+    X3333\P 
+Partial match: X3333
+    
+/X\d{2,4}?b/8
+    X\P
+Partial match: X
+    X3\P
+Partial match: X3
+    X33\P 
+Partial match: X33
+    X333\P
+Partial match: X333
+    X3333\P 
+Partial match: X3333
+    
+/X\d{2,4}+b/8
+    X\P
+Partial match: X
+    X3\P
+Partial match: X3
+    X33\P 
+Partial match: X33
+    X333\P
+Partial match: X333
+    X3333\P 
+Partial match: X3333
+
+/X\D{2,4}b/8
+    X\P
+Partial match: X
+    Xa\P
+Partial match: Xa
+    Xaa\P 
+Partial match: Xaa
+    Xaaa\P
+Partial match: Xaaa
+    Xaaaa\P 
+Partial match: Xaaaa
+    
+/X\D{2,4}?b/8
+    X\P
+Partial match: X
+    Xa\P
+Partial match: Xa
+    Xaa\P 
+Partial match: Xaa
+    Xaaa\P
+Partial match: Xaaa
+    Xaaaa\P 
+Partial match: Xaaaa
+    
+/X\D{2,4}+b/8
+    X\P
+Partial match: X
+    Xa\P
+Partial match: Xa
+    Xaa\P 
+Partial match: Xaa
+    Xaaa\P
+Partial match: Xaaa
+    Xaaaa\P 
+Partial match: Xaaaa
+
+/X\D{2,4}b/8
+    X\P
+Partial match: X
+    X\x{123}\P
+Partial match: X\x{123}
+    X\x{123}\x{123}\P 
+Partial match: X\x{123}\x{123}
+    X\x{123}\x{123}\x{123}\P
+Partial match: X\x{123}\x{123}\x{123}
+    X\x{123}\x{123}\x{123}\x{123}\P 
+Partial match: X\x{123}\x{123}\x{123}\x{123}
+    
+/X\D{2,4}?b/8
+    X\P
+Partial match: X
+    X\x{123}\P
+Partial match: X\x{123}
+    X\x{123}\x{123}\P 
+Partial match: X\x{123}\x{123}
+    X\x{123}\x{123}\x{123}\P
+Partial match: X\x{123}\x{123}\x{123}
+    X\x{123}\x{123}\x{123}\x{123}\P 
+Partial match: X\x{123}\x{123}\x{123}\x{123}
+    
+/X\D{2,4}+b/8
+    X\P
+Partial match: X
+    X\x{123}\P
+Partial match: X\x{123}
+    X\x{123}\x{123}\P 
+Partial match: X\x{123}\x{123}
+    X\x{123}\x{123}\x{123}\P
+Partial match: X\x{123}\x{123}\x{123}
+    X\x{123}\x{123}\x{123}\x{123}\P 
+Partial match: X\x{123}\x{123}\x{123}\x{123}
+
+/X[abc]{2,4}b/8
+    X\P
+Partial match: X
+    Xa\P
+Partial match: Xa
+    Xaa\P 
+Partial match: Xaa
+    Xaaa\P
+Partial match: Xaaa
+    Xaaaa\P 
+Partial match: Xaaaa
+    
+/X[abc]{2,4}?b/8
+    X\P
+Partial match: X
+    Xa\P
+Partial match: Xa
+    Xaa\P 
+Partial match: Xaa
+    Xaaa\P
+Partial match: Xaaa
+    Xaaaa\P 
+Partial match: Xaaaa
+    
+/X[abc]{2,4}+b/8
+    X\P
+Partial match: X
+    Xa\P
+Partial match: Xa
+    Xaa\P 
+Partial match: Xaa
+    Xaaa\P
+Partial match: Xaaa
+    Xaaaa\P 
+Partial match: Xaaaa
+
+/X[abc\x{123}]{2,4}b/8
+    X\P
+Partial match: X
+    X\x{123}\P
+Partial match: X\x{123}
+    X\x{123}\x{123}\P 
+Partial match: X\x{123}\x{123}
+    X\x{123}\x{123}\x{123}\P
+Partial match: X\x{123}\x{123}\x{123}
+    X\x{123}\x{123}\x{123}\x{123}\P 
+Partial match: X\x{123}\x{123}\x{123}\x{123}
+    
+/X[abc\x{123}]{2,4}?b/8
+    X\P
+Partial match: X
+    X\x{123}\P
+Partial match: X\x{123}
+    X\x{123}\x{123}\P 
+Partial match: X\x{123}\x{123}
+    X\x{123}\x{123}\x{123}\P
+Partial match: X\x{123}\x{123}\x{123}
+    X\x{123}\x{123}\x{123}\x{123}\P 
+Partial match: X\x{123}\x{123}\x{123}\x{123}
+    
+/X[abc\x{123}]{2,4}+b/8
+    X\P
+Partial match: X
+    X\x{123}\P
+Partial match: X\x{123}
+    X\x{123}\x{123}\P 
+Partial match: X\x{123}\x{123}
+    X\x{123}\x{123}\x{123}\P
+Partial match: X\x{123}\x{123}\x{123}
+    X\x{123}\x{123}\x{123}\x{123}\P 
+Partial match: X\x{123}\x{123}\x{123}\x{123}
+
+/X[^a]{2,4}b/8
+    X\P
+Partial match: X
+    Xz\P
+Partial match: Xz
+    Xzz\P 
+Partial match: Xzz
+    Xzzz\P
+Partial match: Xzzz
+    Xzzzz\P 
+Partial match: Xzzzz
+    
+/X[^a]{2,4}?b/8
+    X\P
+Partial match: X
+    Xz\P
+Partial match: Xz
+    Xzz\P 
+Partial match: Xzz
+    Xzzz\P
+Partial match: Xzzz
+    Xzzzz\P 
+Partial match: Xzzzz
+    
+/X[^a]{2,4}+b/8
+    X\P
+Partial match: X
+    Xz\P
+Partial match: Xz
+    Xzz\P 
+Partial match: Xzz
+    Xzzz\P
+Partial match: Xzzz
+    Xzzzz\P 
+Partial match: Xzzzz
+
+/X[^a]{2,4}b/8
+    X\P
+Partial match: X
+    X\x{123}\P
+Partial match: X\x{123}
+    X\x{123}\x{123}\P 
+Partial match: X\x{123}\x{123}
+    X\x{123}\x{123}\x{123}\P
+Partial match: X\x{123}\x{123}\x{123}
+    X\x{123}\x{123}\x{123}\x{123}\P 
+Partial match: X\x{123}\x{123}\x{123}\x{123}
+    
+/X[^a]{2,4}?b/8
+    X\P
+Partial match: X
+    X\x{123}\P
+Partial match: X\x{123}
+    X\x{123}\x{123}\P 
+Partial match: X\x{123}\x{123}
+    X\x{123}\x{123}\x{123}\P
+Partial match: X\x{123}\x{123}\x{123}
+    X\x{123}\x{123}\x{123}\x{123}\P 
+Partial match: X\x{123}\x{123}\x{123}\x{123}
+    
+/X[^a]{2,4}+b/8
+    X\P
+Partial match: X
+    X\x{123}\P
+Partial match: X\x{123}
+    X\x{123}\x{123}\P 
+Partial match: X\x{123}\x{123}
+    X\x{123}\x{123}\x{123}\P
+Partial match: X\x{123}\x{123}\x{123}
+    X\x{123}\x{123}\x{123}\x{123}\P 
+Partial match: X\x{123}\x{123}\x{123}\x{123}
+
+/(Y)X\1{2,4}b/8
+    YX\P
+Partial match: YX
+    YXY\P
+Partial match: YXY
+    YXYY\P 
+Partial match: YXYY
+    YXYYY\P
+Partial match: YXYYY
+    YXYYYY\P 
+Partial match: YXYYYY
+    
+/(Y)X\1{2,4}?b/8
+    YX\P
+Partial match: YX
+    YXY\P
+Partial match: YXY
+    YXYY\P 
+Partial match: YXYY
+    YXYYY\P
+Partial match: YXYYY
+    YXYYYY\P 
+Partial match: YXYYYY
+    
+/(Y)X\1{2,4}+b/8
+    YX\P
+Partial match: YX
+    YXY\P
+Partial match: YXY
+    YXYY\P 
+Partial match: YXYY
+    YXYYY\P
+Partial match: YXYYY
+    YXYYYY\P 
+Partial match: YXYYYY
+
+/(\x{123})X\1{2,4}b/8
+    \x{123}X\P
+Partial match: \x{123}X
+    \x{123}X\x{123}\P
+Partial match: \x{123}X\x{123}
+    \x{123}X\x{123}\x{123}\P 
+Partial match: \x{123}X\x{123}\x{123}
+    \x{123}X\x{123}\x{123}\x{123}\P
+Partial match: \x{123}X\x{123}\x{123}\x{123}
+    \x{123}X\x{123}\x{123}\x{123}\x{123}\P 
+Partial match: \x{123}X\x{123}\x{123}\x{123}\x{123}
+    
+/(\x{123})X\1{2,4}?b/8
+    \x{123}X\P
+Partial match: \x{123}X
+    \x{123}X\x{123}\P
+Partial match: \x{123}X\x{123}
+    \x{123}X\x{123}\x{123}\P 
+Partial match: \x{123}X\x{123}\x{123}
+    \x{123}X\x{123}\x{123}\x{123}\P
+Partial match: \x{123}X\x{123}\x{123}\x{123}
+    \x{123}X\x{123}\x{123}\x{123}\x{123}\P 
+Partial match: \x{123}X\x{123}\x{123}\x{123}\x{123}
+    
+/(\x{123})X\1{2,4}+b/8
+    \x{123}X\P
+Partial match: \x{123}X
+    \x{123}X\x{123}\P
+Partial match: \x{123}X\x{123}
+    \x{123}X\x{123}\x{123}\P 
+Partial match: \x{123}X\x{123}\x{123}
+    \x{123}X\x{123}\x{123}\x{123}\P
+Partial match: \x{123}X\x{123}\x{123}\x{123}
+    \x{123}X\x{123}\x{123}\x{123}\x{123}\P 
+Partial match: \x{123}X\x{123}\x{123}\x{123}\x{123}
+
+/\bthe cat\b/8
+    the cat\P
+ 0: the cat
+    the cat\P\P
+Partial match: the cat
+
+/abcd*/8
+    xxxxabcd\P
+ 0: abcd
+    xxxxabcd\P\P
+Partial match: abcd
+
+/abcd*/i8
+    xxxxabcd\P
+ 0: abcd
+    xxxxabcd\P\P
+Partial match: abcd
+    XXXXABCD\P
+ 0: ABCD
+    XXXXABCD\P\P
+Partial match: ABCD
+
+/abc\d*/8
+    xxxxabc1\P
+ 0: abc1
+    xxxxabc1\P\P
+Partial match: abc1
+
+/(a)bc\1*/8
+    xxxxabca\P
+ 0: abca
+ 1: a
+    xxxxabca\P\P
+Partial match: abca
+
+/abc[de]*/8
+    xxxxabcde\P
+ 0: abcde
+    xxxxabcde\P\P
+Partial match: abcde
+
+/X\W{3}X/8
+    \PX
+Partial match: X
+
+/\sxxx\s/8T1
+    AB\x{85}xxx\x{a0}XYZ
+ 0: \x{85}xxx\x{a0}
+    AB\x{a0}xxx\x{85}XYZ
+ 0: \x{a0}xxx\x{85}
+
+/\S \S/8T1
+    \x{a2} \x{84} 
+ 0: \x{a2} \x{84}
+
+'A#хц'8x<any>BZ
+------------------------------------------------------------------
+        Bra
+        A
+        Ket
+        End
+------------------------------------------------------------------
+
+'A#хц
+  PQ'8x<any>BZ
+------------------------------------------------------------------
+        Bra
+        APQ
+        Ket
+        End
+------------------------------------------------------------------
+  
+/a+#Ñ…aa
+  z#XX?/8x<any>BZ 
+------------------------------------------------------------------
+        Bra
+        a++
+        z
+        Ket
+        End
+------------------------------------------------------------------
+
+/a+#Ñ…aa
+  z#Ñ…?/8x<any>BZ 
+------------------------------------------------------------------
+        Bra
+        a++
+        z
+        Ket
+        End
+------------------------------------------------------------------
+
+/\g{A}xxx#bXX(?'A'123)
(?'A'456)/8x<any>BZ
+------------------------------------------------------------------
+        Bra
+        \1
+        xxx
+        CBra 1
+        456
+        Ket
+        Ket
+        End
+------------------------------------------------------------------
+
+/\g{A}xxx#bÑ…(?'A'123)
(?'A'456)/8x<any>BZ
+------------------------------------------------------------------
+        Bra
+        \1
+        xxx
+        CBra 1
+        456
+        Ket
+        Ket
+        End
+------------------------------------------------------------------
+
+/^\cģ/8
+Failed: \c must be followed by an ASCII character at offset 3
+
+/(\R*)(.)/s8
+    \r\n
+ 0: \x{0d}
+ 1: 
+ 2: \x{0d}
+    \r\r\n\n\r 
+ 0: \x{0d}\x{0d}\x{0a}\x{0a}\x{0d}
+ 1: \x{0d}\x{0d}\x{0a}\x{0a}
+ 2: \x{0d}
+    \r\r\n\n\r\n 
+ 0: \x{0d}\x{0d}\x{0a}\x{0a}\x{0d}
+ 1: \x{0d}\x{0d}\x{0a}\x{0a}
+ 2: \x{0d}
+
+/(\R)*(.)/s8
+    \r\n
+ 0: \x{0d}
+ 1: <unset>
+ 2: \x{0d}
+    \r\r\n\n\r 
+ 0: \x{0d}\x{0d}\x{0a}\x{0a}\x{0d}
+ 1: \x{0a}
+ 2: \x{0d}
+    \r\r\n\n\r\n 
+ 0: \x{0d}\x{0d}\x{0a}\x{0a}\x{0d}
+ 1: \x{0a}
+ 2: \x{0d}
+
+/[^\x{1234}]+/iS8I   
+Capturing subpattern count = 0
+Options: caseless utf
+No first char
+No need char
+Subject length lower bound = 1
+No set of starting bytes
+
+/[^\x{1234}]+?/iS8I   
+Capturing subpattern count = 0
+Options: caseless utf
+No first char
+No need char
+Subject length lower bound = 1
+No set of starting bytes
+
+/[^\x{1234}]++/iS8I   
+Capturing subpattern count = 0
+Options: caseless utf
+No first char
+No need char
+Subject length lower bound = 1
+No set of starting bytes
+
+/[^\x{1234}]{2}/iS8I
+Capturing subpattern count = 0
+Options: caseless utf
+No first char
+No need char
+Subject length lower bound = 2
+No set of starting bytes
+
+//<bsr_anycrlf><bsr_unicode>
+Failed: inconsistent NEWLINE options at offset 0
+
+/f.*/
+    \P\Pfor
+Partial match: for
+
+/f.*/s
+    \P\Pfor
+Partial match: for
+
+/f.*/8
+    \P\Pfor
+Partial match: for
+
+/f.*/8s
+    \P\Pfor
+Partial match: for
+    
+/\x{d7ff}\x{e000}/8
+
+/\x{d800}/8
+Failed: disallowed Unicode code point (>= 0xd800 && <= 0xdfff) at offset 7
+
+/\x{dfff}/8 
+Failed: disallowed Unicode code point (>= 0xd800 && <= 0xdfff) at offset 7
+
+/\h+/8
+    \x{1681}\x{200b}\x{1680}\x{2000}\x{202f}\x{3000}
+ 0: \x{1680}\x{2000}\x{202f}\x{3000}
+    \x{3001}\x{2fff}\x{200a}\x{a0}\x{2000}
+ 0: \x{200a}\x{a0}\x{2000}
+
+/[\h\x{e000}]+/8BZ
+------------------------------------------------------------------
+        Bra
+        [\x09 \xa0\x{1680}\x{180e}\x{2000}-\x{200a}\x{202f}\x{205f}\x{3000}\x{e000}]+
+        Ket
+        End
+------------------------------------------------------------------
+    \x{1681}\x{200b}\x{1680}\x{2000}\x{202f}\x{3000}
+ 0: \x{1680}\x{2000}\x{202f}\x{3000}
+    \x{3001}\x{2fff}\x{200a}\x{a0}\x{2000}
+ 0: \x{200a}\x{a0}\x{2000}
+
+/\H+/8
+    \x{1680}\x{180e}\x{167f}\x{1681}\x{180d}\x{180f}
+ 0: \x{167f}\x{1681}\x{180d}\x{180f}
+    \x{2000}\x{200a}\x{1fff}\x{200b}
+ 0: \x{1fff}\x{200b}
+    \x{202f}\x{205f}\x{202e}\x{2030}\x{205e}\x{2060}
+ 0: \x{202e}\x{2030}\x{205e}\x{2060}
+    \x{a0}\x{3000}\x{9f}\x{a1}\x{2fff}\x{3001}
+ 0: \x{9f}\x{a1}\x{2fff}\x{3001}
+
+/[\H\x{d7ff}]+/8BZ
+------------------------------------------------------------------
+        Bra
+        [\x00-\x08\x0a-\x1f!-\x9f\xa1-\xff\x{100}-\x{167f}\x{1681}-\x{180d}\x{180f}-\x{1fff}\x{200b}-\x{202e}\x{2030}-\x{205e}\x{2060}-\x{2fff}\x{3001}-\x{10ffff}\x{d7ff}]+
+        Ket
+        End
+------------------------------------------------------------------
+    \x{1680}\x{180e}\x{167f}\x{1681}\x{180d}\x{180f}
+ 0: \x{167f}\x{1681}\x{180d}\x{180f}
+    \x{2000}\x{200a}\x{1fff}\x{200b}
+ 0: \x{1fff}\x{200b}
+    \x{202f}\x{205f}\x{202e}\x{2030}\x{205e}\x{2060}
+ 0: \x{202e}\x{2030}\x{205e}\x{2060}
+    \x{a0}\x{3000}\x{9f}\x{a1}\x{2fff}\x{3001}
+ 0: \x{9f}\x{a1}\x{2fff}\x{3001}
+
+/\v+/8
+    \x{2027}\x{2030}\x{2028}\x{2029}
+ 0: \x{2028}\x{2029}
+    \x09\x0e\x{84}\x{86}\x{85}\x0a\x0b\x0c\x0d
+ 0: \x{85}\x{0a}\x{0b}\x{0c}\x{0d}
+
+/[\v\x{e000}]+/8BZ
+------------------------------------------------------------------
+        Bra
+        [\x0a-\x0d\x85\x{2028}-\x{2029}\x{e000}]+
+        Ket
+        End
+------------------------------------------------------------------
+    \x{2027}\x{2030}\x{2028}\x{2029}
+ 0: \x{2028}\x{2029}
+    \x09\x0e\x{84}\x{86}\x{85}\x0a\x0b\x0c\x0d
+ 0: \x{85}\x{0a}\x{0b}\x{0c}\x{0d}
+
+/\V+/8
+    \x{2028}\x{2029}\x{2027}\x{2030}
+ 0: \x{2027}\x{2030}
+    \x{85}\x0a\x0b\x0c\x0d\x09\x0e\x{84}\x{86}
+ 0: \x{09}\x{0e}\x{84}\x{86}
+
+/[\V\x{d7ff}]+/8BZ
+------------------------------------------------------------------
+        Bra
+        [\x00-\x09\x0e-\x84\x86-\xff\x{100}-\x{2027}\x{202a}-\x{10ffff}\x{d7ff}]+
+        Ket
+        End
+------------------------------------------------------------------
+    \x{2028}\x{2029}\x{2027}\x{2030}
+ 0: \x{2027}\x{2030}
+    \x{85}\x0a\x0b\x0c\x0d\x09\x0e\x{84}\x{86}
+ 0: \x{09}\x{0e}\x{84}\x{86}
+
+/\R+/8<bsr_unicode>
+    \x{2027}\x{2030}\x{2028}\x{2029}
+ 0: \x{2028}\x{2029}
+    \x09\x0e\x{84}\x{86}\x{85}\x0a\x0b\x0c\x0d
+ 0: \x{85}\x{0a}\x{0b}\x{0c}\x{0d}
+
+/(..)\1/8
+    ab\P
+Partial match: ab
+    aba\P
+Partial match: aba
+    abab\P
+ 0: abab
+ 1: ab
+
+/(..)\1/8i
+    ab\P
+Partial match: ab
+    abA\P
+Partial match: abA
+    aBAb\P
+ 0: aBAb
+ 1: aB
+
+/(..)\1{2,}/8
+    ab\P
+Partial match: ab
+    aba\P
+Partial match: aba
+    abab\P
+Partial match: abab
+    ababa\P
+Partial match: ababa
+    ababab\P
+ 0: ababab
+ 1: ab
+    ababab\P\P
+Partial match: ababab
+    abababa\P
+ 0: ababab
+ 1: ab
+    abababa\P\P
+Partial match: abababa
+
+/(..)\1{2,}/8i
+    ab\P
+Partial match: ab
+    aBa\P
+Partial match: aBa
+    aBAb\P
+Partial match: aBAb
+    AbaBA\P
+Partial match: AbaBA
+    abABAb\P
+ 0: abABAb
+ 1: ab
+    aBAbaB\P\P
+Partial match: aBAbaB
+    abABabA\P
+ 0: abABab
+ 1: ab
+    abaBABa\P\P
+Partial match: abaBABa
+
+/(..)\1{2,}?x/8i
+    ab\P
+Partial match: ab
+    abA\P
+Partial match: abA
+    aBAb\P
+Partial match: aBAb
+    abaBA\P
+Partial match: abaBA
+    abAbaB\P
+Partial match: abAbaB
+    abaBabA\P
+Partial match: abaBabA
+    abAbABaBx\P
+ 0: abAbABaBx
+ 1: ab
+
+/./8<CRLF>
+    \r\P
+ 0: \x{0d}
+    \r\P\P 
+Partial match: \x{0d}
+  
+/.{2,3}/8<CRLF>
+    \r\P 
+Partial match: \x{0d}
+    \r\P\P
+Partial match: \x{0d}
+    \r\r\P
+ 0: \x{0d}\x{0d}
+    \r\r\P\P
+Partial match: \x{0d}\x{0d}
+    \r\r\r\P
+ 0: \x{0d}\x{0d}\x{0d}
+    \r\r\r\P\P     
+Partial match: \x{0d}\x{0d}\x{0d}
+
+/.{2,3}?/8<CRLF>
+    \r\P 
+Partial match: \x{0d}
+    \r\P\P
+Partial match: \x{0d}
+    \r\r\P
+ 0: \x{0d}\x{0d}
+    \r\r\P\P
+Partial match: \x{0d}\x{0d}
+    \r\r\r\P
+ 0: \x{0d}\x{0d}
+    \r\r\r\P\P     
+ 0: \x{0d}\x{0d}
+
+/[^\x{100}][^\x{1234}][^\x{ffff}][^\x{10000}][^\x{10ffff}]/8BZ
+------------------------------------------------------------------
+        Bra
+        [^\x{100}]
+        [^\x{1234}]
+        [^\x{ffff}]
+        [^\x{10000}]
+        [^\x{10ffff}]
+        Ket
+        End
+------------------------------------------------------------------
+
+/[^\x{100}][^\x{1234}][^\x{ffff}][^\x{10000}][^\x{10ffff}]/8BZi
+------------------------------------------------------------------
+        Bra
+     /i [^\x{100}]
+     /i [^\x{1234}]
+     /i [^\x{ffff}]
+     /i [^\x{10000}]
+     /i [^\x{10ffff}]
+        Ket
+        End
+------------------------------------------------------------------
+
+/[^\x{100}]*[^\x{10000}]+[^\x{10ffff}]??[^\x{8000}]{4,}[^\x{7fff}]{2,9}?[^\x{fffff}]{5,6}+/8BZ
+------------------------------------------------------------------
+        Bra
+        [^\x{100}]*
+        [^\x{10000}]+
+        [^\x{10ffff}]??
+        [^\x{8000}]{4}
+        [^\x{8000}]*
+        [^\x{7fff}]{2}
+        [^\x{7fff}]{0,7}?
+        [^\x{fffff}]{5}
+        [^\x{fffff}]?+
+        Ket
+        End
+------------------------------------------------------------------
+
+/[^\x{100}]*[^\x{10000}]+[^\x{10ffff}]??[^\x{8000}]{4,}[^\x{7fff}]{2,9}?[^\x{fffff}]{5,6}+/8BZi
+------------------------------------------------------------------
+        Bra
+     /i [^\x{100}]*
+     /i [^\x{10000}]+
+     /i [^\x{10ffff}]??
+     /i [^\x{8000}]{4}
+     /i [^\x{8000}]*
+     /i [^\x{7fff}]{2}
+     /i [^\x{7fff}]{0,7}?
+        Once
+     /i [^\x{fffff}]{5}
+     /i [^\x{fffff}]?
+        Ket
+        Ket
+        End
+------------------------------------------------------------------
+
+/(?<=\x{1234}\x{1234})\bxy/I8
+Capturing subpattern count = 0
+Options: utf
+First char = 'x'
+Need char = 'y'
+Max lookbehind = 2
+
+/(?<!^)ETA/8
+    ETA
+No match
+
+/\u0100/<JS>8BZ
+------------------------------------------------------------------
+        Bra
+        \x{100}
+        Ket
+        End
+------------------------------------------------------------------
+
+/[\u0100-\u0200]/<JS>8BZ
+------------------------------------------------------------------
+        Bra
+        [\x{100}-\x{200}]
+        Ket
+        End
+------------------------------------------------------------------
+
+/\ud800/<JS>8
+Failed: disallowed Unicode code point (>= 0xd800 && <= 0xdfff) at offset 5
+
+/-- End of testinput5 --/
diff --git a/ext/pcre/pcrelib/testdata/testoutput6 b/ext/pcre/pcrelib/testdata/testoutput6
new file mode 100644
index 0000000..e88fc09
--- /dev/null
+++ b/ext/pcre/pcrelib/testdata/testoutput6
@@ -0,0 +1,1376 @@
+/-- This set of tests is for Unicode property support. It is compatible with
+    Perl >= 5.10, but not 5.8 because it tests some extra properties that are
+    not in the earlier release. --/ 
+
+/^\pC\pL\pM\pN\pP\pS\pZ</8
+    \x7f\x{c0}\x{30f}\x{660}\x{66c}\x{f01}\x{1680}<
+ 0: \x{7f}\x{c0}\x{30f}\x{660}\x{66c}\x{f01}\x{1680}<
+    \np\x{300}9!\$ < 
+ 0: \x{0a}p\x{300}9!$ <
+    ** Failers 
+No match
+    ap\x{300}9!\$ < 
+No match
+  
+/^\PC/8
+    X
+ 0: X
+    ** Failers 
+ 0: *
+    \x7f
+No match
+  
+/^\PL/8
+    9
+ 0: 9
+    ** Failers 
+ 0: *
+    \x{c0}
+No match
+  
+/^\PM/8
+    X
+ 0: X
+    ** Failers 
+ 0: *
+    \x{30f}
+No match
+  
+/^\PN/8
+    X
+ 0: X
+    ** Failers 
+ 0: *
+    \x{660}
+No match
+  
+/^\PP/8
+    X
+ 0: X
+    ** Failers 
+No match
+    \x{66c}
+No match
+  
+/^\PS/8
+    X
+ 0: X
+    ** Failers 
+ 0: *
+    \x{f01}
+No match
+  
+/^\PZ/8
+    X
+ 0: X
+    ** Failers 
+ 0: *
+    \x{1680}
+No match
+    
+/^\p{Cc}/8
+    \x{017}
+ 0: \x{17}
+    \x{09f} 
+ 0: \x{9f}
+    ** Failers
+No match
+    \x{0600} 
+No match
+  
+/^\p{Cf}/8
+    \x{601}
+ 0: \x{601}
+    ** Failers
+No match
+    \x{09f} 
+No match
+  
+/^\p{Cn}/8
+    \x{e0000}
+ 0: \x{e0000}
+    ** Failers
+No match
+    \x{09f} 
+No match
+  
+/^\p{Co}/8
+    \x{f8ff}
+ 0: \x{f8ff}
+    ** Failers
+No match
+    \x{09f} 
+No match
+  
+/^\p{Ll}/8
+    a
+ 0: a
+    ** Failers 
+No match
+    Z
+No match
+    \x{e000}  
+No match
+  
+/^\p{Lm}/8
+    \x{2b0}
+ 0: \x{2b0}
+    ** Failers
+No match
+    a 
+No match
+  
+/^\p{Lo}/8
+    \x{1bb}
+ 0: \x{1bb}
+    \x{3400}
+ 0: \x{3400}
+    \x{3401}
+ 0: \x{3401}
+    \x{4d00}
+ 0: \x{4d00}
+    \x{4db4}
+ 0: \x{4db4}
+    \x{4db5}     
+ 0: \x{4db5}
+    ** Failers
+No match
+    a 
+No match
+    \x{2b0}
+No match
+    \x{4db6} 
+No match
+  
+/^\p{Lt}/8
+    \x{1c5}
+ 0: \x{1c5}
+    ** Failers
+No match
+    a 
+No match
+    \x{2b0}
+No match
+  
+/^\p{Lu}/8
+    A
+ 0: A
+    ** Failers
+No match
+    \x{2b0}
+No match
+  
+/^\p{Mc}/8
+    \x{903}
+ 0: \x{903}
+    ** Failers
+No match
+    X
+No match
+    \x{300}
+No match
+       
+/^\p{Me}/8
+    \x{488}
+ 0: \x{488}
+    ** Failers
+No match
+    X
+No match
+    \x{903}
+No match
+    \x{300}
+No match
+  
+/^\p{Mn}/8
+    \x{300}
+ 0: \x{300}
+    ** Failers
+No match
+    X
+No match
+    \x{903}
+No match
+  
+/^\p{Nd}+/8
+    0123456789\x{660}\x{661}\x{662}\x{663}\x{664}\x{665}\x{666}\x{667}\x{668}\x{669}\x{66a}
+ 0: 0123456789\x{660}\x{661}\x{662}\x{663}\x{664}\x{665}\x{666}\x{667}\x{668}\x{669}
+    \x{6f0}\x{6f1}\x{6f2}\x{6f3}\x{6f4}\x{6f5}\x{6f6}\x{6f7}\x{6f8}\x{6f9}\x{6fa}
+ 0: \x{6f0}\x{6f1}\x{6f2}\x{6f3}\x{6f4}\x{6f5}\x{6f6}\x{6f7}\x{6f8}\x{6f9}
+    \x{966}\x{967}\x{968}\x{969}\x{96a}\x{96b}\x{96c}\x{96d}\x{96e}\x{96f}\x{970}
+ 0: \x{966}\x{967}\x{968}\x{969}\x{96a}\x{96b}\x{96c}\x{96d}\x{96e}\x{96f}
+    ** Failers
+No match
+    X
+No match
+  
+/^\p{Nl}/8
+    \x{16ee}
+ 0: \x{16ee}
+    ** Failers
+No match
+    X
+No match
+    \x{966}
+No match
+  
+/^\p{No}/8
+    \x{b2}
+ 0: \x{b2}
+    \x{b3}
+ 0: \x{b3}
+    ** Failers
+No match
+    X
+No match
+    \x{16ee}
+No match
+  
+/^\p{Pc}/8
+    \x5f
+ 0: _
+    \x{203f}
+ 0: \x{203f}
+    ** Failers
+No match
+    X
+No match
+    -
+No match
+    \x{58a}
+No match
+  
+/^\p{Pd}/8
+    -
+ 0: -
+    \x{58a}
+ 0: \x{58a}
+    ** Failers
+No match
+    X
+No match
+    \x{203f}
+No match
+  
+/^\p{Pe}/8
+    )
+ 0: )
+    ]
+ 0: ]
+    }
+ 0: }
+    \x{f3b}
+ 0: \x{f3b}
+    ** Failers
+No match
+    X
+No match
+    \x{203f}
+No match
+    (
+No match
+    [
+No match
+    {
+No match
+    \x{f3c}
+No match
+  
+/^\p{Pf}/8
+    \x{bb}
+ 0: \x{bb}
+    \x{2019}
+ 0: \x{2019}
+    ** Failers
+No match
+    X
+No match
+    \x{203f}
+No match
+  
+/^\p{Pi}/8
+    \x{ab}
+ 0: \x{ab}
+    \x{2018}
+ 0: \x{2018}
+    ** Failers
+No match
+    X
+No match
+    \x{203f}
+No match
+  
+/^\p{Po}/8
+    !
+ 0: !
+    \x{37e}
+ 0: \x{37e}
+    ** Failers
+ 0: *
+    X
+No match
+    \x{203f}
+No match
+  
+/^\p{Ps}/8
+    (
+ 0: (
+    [
+ 0: [
+    {
+ 0: {
+    \x{f3c}
+ 0: \x{f3c}
+    ** Failers
+No match
+    X
+No match
+    )
+No match
+    ]
+No match
+    }
+No match
+    \x{f3b}
+No match
+  
+/^\p{Sk}/8
+    \x{2c2}
+ 0: \x{2c2}
+    ** Failers
+No match
+    X
+No match
+    \x{9f2}
+No match
+  
+/^\p{Sm}+/8
+    +<|~\x{ac}\x{2044}
+ 0: +<|~\x{ac}\x{2044}
+    ** Failers
+No match
+    X
+No match
+    \x{9f2}
+No match
+  
+/^\p{So}/8
+    \x{a6}
+ 0: \x{a6}
+    \x{482} 
+ 0: \x{482}
+    ** Failers
+No match
+    X
+No match
+    \x{9f2}
+No match
+  
+/^\p{Zl}/8
+    \x{2028}
+ 0: \x{2028}
+    ** Failers
+No match
+    X
+No match
+    \x{2029}
+No match
+  
+/^\p{Zp}/8
+    \x{2029}
+ 0: \x{2029}
+    ** Failers
+No match
+    X
+No match
+    \x{2028}
+No match
+  
+/\p{Nd}+(..)/8
+      \x{660}\x{661}\x{662}ABC
+ 0: \x{660}\x{661}\x{662}AB
+ 1: AB
+  
+/\p{Nd}+?(..)/8
+      \x{660}\x{661}\x{662}ABC
+ 0: \x{660}\x{661}\x{662}
+ 1: \x{661}\x{662}
+  
+/\p{Nd}{2,}(..)/8
+      \x{660}\x{661}\x{662}ABC
+ 0: \x{660}\x{661}\x{662}AB
+ 1: AB
+  
+/\p{Nd}{2,}?(..)/8
+      \x{660}\x{661}\x{662}ABC
+ 0: \x{660}\x{661}\x{662}A
+ 1: \x{662}A
+  
+/\p{Nd}*(..)/8
+      \x{660}\x{661}\x{662}ABC
+ 0: \x{660}\x{661}\x{662}AB
+ 1: AB
+  
+/\p{Nd}*?(..)/8
+      \x{660}\x{661}\x{662}ABC
+ 0: \x{660}\x{661}
+ 1: \x{660}\x{661}
+  
+/\p{Nd}{2}(..)/8
+      \x{660}\x{661}\x{662}ABC
+ 0: \x{660}\x{661}\x{662}A
+ 1: \x{662}A
+  
+/\p{Nd}{2,3}(..)/8
+      \x{660}\x{661}\x{662}ABC
+ 0: \x{660}\x{661}\x{662}AB
+ 1: AB
+  
+/\p{Nd}{2,3}?(..)/8
+      \x{660}\x{661}\x{662}ABC
+ 0: \x{660}\x{661}\x{662}A
+ 1: \x{662}A
+  
+/\p{Nd}?(..)/8
+      \x{660}\x{661}\x{662}ABC
+ 0: \x{660}\x{661}\x{662}
+ 1: \x{661}\x{662}
+  
+/\p{Nd}??(..)/8
+      \x{660}\x{661}\x{662}ABC
+ 0: \x{660}\x{661}
+ 1: \x{660}\x{661}
+  
+/\p{Nd}*+(..)/8
+      \x{660}\x{661}\x{662}ABC
+ 0: \x{660}\x{661}\x{662}AB
+ 1: AB
+  
+/\p{Nd}*+(...)/8
+      \x{660}\x{661}\x{662}ABC
+ 0: \x{660}\x{661}\x{662}ABC
+ 1: ABC
+  
+/\p{Nd}*+(....)/8
+      ** Failers
+ 0: ** F
+ 1: ** F
+      \x{660}\x{661}\x{662}ABC
+No match
+  
+/(?<=A\p{Nd})XYZ/8
+    A2XYZ
+ 0: XYZ
+    123A5XYZPQR
+ 0: XYZ
+    ABA\x{660}XYZpqr
+ 0: XYZ
+    ** Failers
+No match
+    AXYZ
+No match
+    XYZ     
+No match
+    
+/(?<!\pL)XYZ/8
+    1XYZ
+ 0: XYZ
+    AB=XYZ.. 
+ 0: XYZ
+    XYZ 
+ 0: XYZ
+    ** Failers
+No match
+    WXYZ 
+No match
+
+/[\P{Nd}]+/8
+    abcd
+ 0: abcd
+    ** Failers
+ 0: ** Failers
+    1234
+No match
+
+/\D+/8
+    11111111111111111111111111111111111111111111111111111111111111111111111
+No match
+    aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+ 0: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+     
+/\P{Nd}+/8
+    11111111111111111111111111111111111111111111111111111111111111111111111
+No match
+    aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+ 0: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+
+/[\D]+/8
+    11111111111111111111111111111111111111111111111111111111111111111111111
+No match
+    aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+ 0: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+
+/[\P{Nd}]+/8
+    11111111111111111111111111111111111111111111111111111111111111111111111
+No match
+    aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+ 0: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+
+/[\D\P{Nd}]+/8
+    11111111111111111111111111111111111111111111111111111111111111111111111
+No match
+    aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+ 0: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+
+/\pL/8
+    a
+ 0: a
+    A 
+ 0: A
+
+/\pL/8i
+    a
+ 0: a
+    A 
+ 0: A
+    
+/\p{Lu}/8 
+    A
+ 0: A
+    aZ
+ 0: Z
+    ** Failers
+ 0: F
+    abc   
+No match
+
+/\p{Lu}/8i
+    A
+ 0: A
+    aZ
+ 0: Z
+    ** Failers
+ 0: F
+    abc   
+No match
+
+/\p{Ll}/8 
+    a
+ 0: a
+    Az
+ 0: z
+    ** Failers
+ 0: a
+    ABC   
+No match
+
+/A\x{391}\x{10427}\x{ff3a}\x{1fb0}/8
+    A\x{391}\x{10427}\x{ff3a}\x{1fb0}
+ 0: A\x{391}\x{10427}\x{ff3a}\x{1fb0}
+    ** Failers
+No match
+    a\x{391}\x{10427}\x{ff3a}\x{1fb0}   
+No match
+    A\x{3b1}\x{10427}\x{ff3a}\x{1fb0}
+No match
+    A\x{391}\x{1044F}\x{ff3a}\x{1fb0}
+No match
+    A\x{391}\x{10427}\x{ff5a}\x{1fb0}
+No match
+    A\x{391}\x{10427}\x{ff3a}\x{1fb8}
+No match
+
+/A\x{391}\x{10427}\x{ff3a}\x{1fb0}/8i
+    A\x{391}\x{10427}\x{ff3a}\x{1fb0}
+ 0: A\x{391}\x{10427}\x{ff3a}\x{1fb0}
+    a\x{391}\x{10427}\x{ff3a}\x{1fb0}   
+ 0: a\x{391}\x{10427}\x{ff3a}\x{1fb0}
+    A\x{3b1}\x{10427}\x{ff3a}\x{1fb0}
+ 0: A\x{3b1}\x{10427}\x{ff3a}\x{1fb0}
+    A\x{391}\x{1044F}\x{ff3a}\x{1fb0}
+ 0: A\x{391}\x{1044f}\x{ff3a}\x{1fb0}
+    A\x{391}\x{10427}\x{ff5a}\x{1fb0}
+ 0: A\x{391}\x{10427}\x{ff5a}\x{1fb0}
+    A\x{391}\x{10427}\x{ff3a}\x{1fb8}
+ 0: A\x{391}\x{10427}\x{ff3a}\x{1fb8}
+
+/\x{391}+/8i
+    \x{391}\x{3b1}\x{3b1}\x{3b1}\x{391}
+ 0: \x{391}\x{3b1}\x{3b1}\x{3b1}\x{391}
+
+/\x{391}{3,5}(.)/8i
+    \x{391}\x{3b1}\x{3b1}\x{3b1}\x{391}X
+ 0: \x{391}\x{3b1}\x{3b1}\x{3b1}\x{391}X
+ 1: X
+
+/\x{391}{3,5}?(.)/8i
+    \x{391}\x{3b1}\x{3b1}\x{3b1}\x{391}X
+ 0: \x{391}\x{3b1}\x{3b1}\x{3b1}
+ 1: \x{3b1}
+
+/[\x{391}\x{ff3a}]/8i
+    \x{391}
+ 0: \x{391}
+    \x{ff3a}
+ 0: \x{ff3a}
+    \x{3b1}
+ 0: \x{3b1}
+    \x{ff5a}   
+ 0: \x{ff5a}
+    
+/^[\X]/8
+    X123
+ 0: X
+    *** Failers
+No match
+    AXYZ
+No match
+
+/^(\X*)C/8
+    A\x{300}\x{301}\x{302}BCA\x{300}\x{301} 
+ 0: A\x{300}\x{301}\x{302}BC
+ 1: A\x{300}\x{301}\x{302}B
+    A\x{300}\x{301}\x{302}BCA\x{300}\x{301}C 
+ 0: A\x{300}\x{301}\x{302}BCA\x{300}\x{301}C
+ 1: A\x{300}\x{301}\x{302}BCA\x{300}\x{301}
+
+/^(\X*?)C/8
+    A\x{300}\x{301}\x{302}BCA\x{300}\x{301} 
+ 0: A\x{300}\x{301}\x{302}BC
+ 1: A\x{300}\x{301}\x{302}B
+    A\x{300}\x{301}\x{302}BCA\x{300}\x{301}C 
+ 0: A\x{300}\x{301}\x{302}BC
+ 1: A\x{300}\x{301}\x{302}B
+
+/^(\X*)(.)/8
+    A\x{300}\x{301}\x{302}BCA\x{300}\x{301} 
+ 0: A\x{300}\x{301}\x{302}BCA
+ 1: A\x{300}\x{301}\x{302}BC
+ 2: A
+    A\x{300}\x{301}\x{302}BCA\x{300}\x{301}C 
+ 0: A\x{300}\x{301}\x{302}BCA\x{300}\x{301}C
+ 1: A\x{300}\x{301}\x{302}BCA\x{300}\x{301}
+ 2: C
+
+/^(\X*?)(.)/8
+    A\x{300}\x{301}\x{302}BCA\x{300}\x{301} 
+ 0: A
+ 1: 
+ 2: A
+    A\x{300}\x{301}\x{302}BCA\x{300}\x{301}C 
+ 0: A
+ 1: 
+ 2: A
+
+/^\X(.)/8
+    *** Failers
+ 0: **
+ 1: *
+    A\x{300}\x{301}\x{302}
+No match
+
+/^\X{2,3}(.)/8
+    A\x{300}\x{301}B\x{300}X
+ 0: A\x{300}\x{301}B\x{300}X
+ 1: X
+    A\x{300}\x{301}B\x{300}C\x{300}\x{301}
+ 0: A\x{300}\x{301}B\x{300}C
+ 1: C
+    A\x{300}\x{301}B\x{300}C\x{300}\x{301}X
+ 0: A\x{300}\x{301}B\x{300}C\x{300}\x{301}X
+ 1: X
+    A\x{300}\x{301}B\x{300}C\x{300}\x{301}DA\x{300}X
+ 0: A\x{300}\x{301}B\x{300}C\x{300}\x{301}D
+ 1: D
+    
+/^\X{2,3}?(.)/8
+    A\x{300}\x{301}B\x{300}X
+ 0: A\x{300}\x{301}B\x{300}X
+ 1: X
+    A\x{300}\x{301}B\x{300}C\x{300}\x{301}
+ 0: A\x{300}\x{301}B\x{300}C
+ 1: C
+    A\x{300}\x{301}B\x{300}C\x{300}\x{301}X
+ 0: A\x{300}\x{301}B\x{300}C
+ 1: C
+    A\x{300}\x{301}B\x{300}C\x{300}\x{301}DA\x{300}X
+ 0: A\x{300}\x{301}B\x{300}C
+ 1: C
+    
+/^\p{Han}+/8
+    \x{2e81}\x{3007}\x{2f804}\x{31a0}
+ 0: \x{2e81}\x{3007}\x{2f804}
+    ** Failers
+No match
+    \x{2e7f}  
+No match
+
+/^\P{Katakana}+/8
+    \x{3105}
+ 0: \x{3105}
+    ** Failers
+ 0: ** Failers
+    \x{30ff}  
+No match
+
+/^[\p{Arabic}]/8
+    \x{06e9}
+ 0: \x{6e9}
+    \x{060b}
+ 0: \x{60b}
+    ** Failers
+No match
+    X\x{06e9}   
+No match
+
+/^[\P{Yi}]/8
+    \x{2f800}
+ 0: \x{2f800}
+    ** Failers
+ 0: *
+    \x{a014}
+No match
+    \x{a4c6}   
+No match
+    
+/^\p{Any}X/8
+    AXYZ
+ 0: AX
+    \x{1234}XYZ 
+ 0: \x{1234}X
+    ** Failers
+No match
+    X  
+No match
+    
+/^\P{Any}X/8
+    ** Failers
+No match
+    AX
+No match
+    
+/^\p{Any}?X/8
+    XYZ
+ 0: X
+    AXYZ
+ 0: AX
+    \x{1234}XYZ 
+ 0: \x{1234}X
+    ** Failers
+No match
+    ABXYZ   
+No match
+
+/^\P{Any}?X/8
+    XYZ
+ 0: X
+    ** Failers
+No match
+    AXYZ
+No match
+    \x{1234}XYZ 
+No match
+    ABXYZ   
+No match
+
+/^\p{Any}+X/8
+    AXYZ
+ 0: AX
+    \x{1234}XYZ
+ 0: \x{1234}X
+    A\x{1234}XYZ
+ 0: A\x{1234}X
+    ** Failers
+No match
+    XYZ
+No match
+
+/^\P{Any}+X/8
+    ** Failers
+No match
+    AXYZ
+No match
+    \x{1234}XYZ
+No match
+    A\x{1234}XYZ
+No match
+    XYZ
+No match
+
+/^\p{Any}*X/8
+    XYZ
+ 0: X
+    AXYZ
+ 0: AX
+    \x{1234}XYZ
+ 0: \x{1234}X
+    A\x{1234}XYZ
+ 0: A\x{1234}X
+    ** Failers
+No match
+
+/^\P{Any}*X/8
+    XYZ
+ 0: X
+    ** Failers
+No match
+    AXYZ
+No match
+    \x{1234}XYZ
+No match
+    A\x{1234}XYZ
+No match
+
+/^[\p{Any}]X/8
+    AXYZ
+ 0: AX
+    \x{1234}XYZ 
+ 0: \x{1234}X
+    ** Failers
+No match
+    X  
+No match
+    
+/^[\P{Any}]X/8
+    ** Failers
+No match
+    AX
+No match
+    
+/^[\p{Any}]?X/8
+    XYZ
+ 0: X
+    AXYZ
+ 0: AX
+    \x{1234}XYZ 
+ 0: \x{1234}X
+    ** Failers
+No match
+    ABXYZ   
+No match
+
+/^[\P{Any}]?X/8
+    XYZ
+ 0: X
+    ** Failers
+No match
+    AXYZ
+No match
+    \x{1234}XYZ 
+No match
+    ABXYZ   
+No match
+
+/^[\p{Any}]+X/8
+    AXYZ
+ 0: AX
+    \x{1234}XYZ
+ 0: \x{1234}X
+    A\x{1234}XYZ
+ 0: A\x{1234}X
+    ** Failers
+No match
+    XYZ
+No match
+
+/^[\P{Any}]+X/8
+    ** Failers
+No match
+    AXYZ
+No match
+    \x{1234}XYZ
+No match
+    A\x{1234}XYZ
+No match
+    XYZ
+No match
+
+/^[\p{Any}]*X/8
+    XYZ
+ 0: X
+    AXYZ
+ 0: AX
+    \x{1234}XYZ
+ 0: \x{1234}X
+    A\x{1234}XYZ
+ 0: A\x{1234}X
+    ** Failers
+No match
+
+/^[\P{Any}]*X/8
+    XYZ
+ 0: X
+    ** Failers
+No match
+    AXYZ
+No match
+    \x{1234}XYZ
+No match
+    A\x{1234}XYZ
+No match
+
+/^\p{Any}{3,5}?/8
+    abcdefgh
+ 0: abc
+    \x{1234}\n\r\x{3456}xyz 
+ 0: \x{1234}\x{0a}\x{0d}
+
+/^\p{Any}{3,5}/8
+    abcdefgh
+ 0: abcde
+    \x{1234}\n\r\x{3456}xyz 
+ 0: \x{1234}\x{0a}\x{0d}\x{3456}x
+
+/^\P{Any}{3,5}?/8
+    ** Failers
+No match
+    abcdefgh
+No match
+    \x{1234}\n\r\x{3456}xyz 
+No match
+
+/^\p{L&}X/8
+     AXY
+ 0: AX
+     aXY
+ 0: aX
+     \x{1c5}XY
+ 0: \x{1c5}X
+     ** Failers
+No match
+     \x{1bb}XY
+No match
+     \x{2b0}XY
+No match
+     !XY      
+No match
+
+/^[\p{L&}]X/8
+     AXY
+ 0: AX
+     aXY
+ 0: aX
+     \x{1c5}XY
+ 0: \x{1c5}X
+     ** Failers
+No match
+     \x{1bb}XY
+No match
+     \x{2b0}XY
+No match
+     !XY      
+No match
+
+/^\p{L&}+X/8
+     AXY
+ 0: AX
+     aXY
+ 0: aX
+     AbcdeXyz 
+ 0: AbcdeX
+     \x{1c5}AbXY
+ 0: \x{1c5}AbX
+     abcDEXypqreXlmn 
+ 0: abcDEXypqreX
+     ** Failers
+No match
+     \x{1bb}XY
+No match
+     \x{2b0}XY
+No match
+     !XY      
+No match
+
+/^[\p{L&}]+X/8
+     AXY
+ 0: AX
+     aXY
+ 0: aX
+     AbcdeXyz 
+ 0: AbcdeX
+     \x{1c5}AbXY
+ 0: \x{1c5}AbX
+     abcDEXypqreXlmn 
+ 0: abcDEXypqreX
+     ** Failers
+No match
+     \x{1bb}XY
+No match
+     \x{2b0}XY
+No match
+     !XY      
+No match
+
+/^\p{L&}+?X/8
+     AXY
+ 0: AX
+     aXY
+ 0: aX
+     AbcdeXyz 
+ 0: AbcdeX
+     \x{1c5}AbXY
+ 0: \x{1c5}AbX
+     abcDEXypqreXlmn 
+ 0: abcDEX
+     ** Failers
+No match
+     \x{1bb}XY
+No match
+     \x{2b0}XY
+No match
+     !XY      
+No match
+
+/^[\p{L&}]+?X/8
+     AXY
+ 0: AX
+     aXY
+ 0: aX
+     AbcdeXyz 
+ 0: AbcdeX
+     \x{1c5}AbXY
+ 0: \x{1c5}AbX
+     abcDEXypqreXlmn 
+ 0: abcDEX
+     ** Failers
+No match
+     \x{1bb}XY
+No match
+     \x{2b0}XY
+No match
+     !XY      
+No match
+
+/^\P{L&}X/8
+     !XY
+ 0: !X
+     \x{1bb}XY
+ 0: \x{1bb}X
+     \x{2b0}XY
+ 0: \x{2b0}X
+     ** Failers
+No match
+     \x{1c5}XY
+No match
+     AXY      
+No match
+
+/^[\P{L&}]X/8
+     !XY
+ 0: !X
+     \x{1bb}XY
+ 0: \x{1bb}X
+     \x{2b0}XY
+ 0: \x{2b0}X
+     ** Failers
+No match
+     \x{1c5}XY
+No match
+     AXY      
+No match
+
+/^(\p{Z}[^\p{C}\p{Z}]+)*$/
+    \xa0!
+ 0: \xa0!
+ 1: \xa0!
+
+/^[\pL](abc)(?1)/
+    AabcabcYZ    
+ 0: Aabcabc
+ 1: abc
+
+/([\pL]=(abc))*X/
+    L=abcX
+ 0: L=abcX
+ 1: L=abc
+ 2: abc
+
+/^\p{Balinese}\p{Cuneiform}\p{Nko}\p{Phags_Pa}\p{Phoenician}/8
+    \x{1b00}\x{12000}\x{7c0}\x{a840}\x{10900}
+ 0: \x{1b00}\x{12000}\x{7c0}\x{a840}\x{10900}
+
+/Check property support in non-UTF-8 mode/
+ 
+/\p{L}{4}/
+    123abcdefg
+ 0: abcd
+    123abc\xc4\xc5zz
+ 0: abc\xc4
+
+/\X{1,3}\d/
+  \x8aBCD
+No match
+  
+/\X?\d/
+  \x8aBCD 
+No match
+
+/\P{L}?\d/
+  \x8aBCD 
+No match
+
+/[\PPP\x8a]{1,}\x80/
+    A\x80
+ 0: A\x80
+
+/^[\p{Arabic}]/8
+    \x{604}
+ 0: \x{604}
+    \x{60e} 
+ 0: \x{60e}
+    \x{656} 
+ 0: \x{656}
+    \x{657} 
+ 0: \x{657}
+    \x{658} 
+ 0: \x{658}
+    \x{659} 
+ 0: \x{659}
+    \x{65a} 
+ 0: \x{65a}
+    \x{65b} 
+ 0: \x{65b}
+    \x{65c} 
+ 0: \x{65c}
+    \x{65d} 
+ 0: \x{65d}
+    \x{65e} 
+ 0: \x{65e}
+    \x{66a} 
+ 0: \x{66a}
+    \x{6e9} 
+ 0: \x{6e9}
+    \x{6ef}
+ 0: \x{6ef}
+    \x{6fa}  
+ 0: \x{6fa}
+    ** Failers
+No match
+    \x{650}
+No match
+    \x{651}  
+No match
+    \x{652}  
+No match
+    \x{653}  
+No match
+    \x{654} 
+No match
+    \x{655} 
+No match
+    \x{65f}  
+No match
+    
+/^\p{Cyrillic}/8
+    \x{1d2b} 
+ 0: \x{1d2b}
+    
+/^\p{Common}/8
+    \x{589}
+ 0: \x{589}
+    \x{60c}
+ 0: \x{60c}
+    \x{61f}  
+ 0: \x{61f}
+    \x{964}
+ 0: \x{964}
+    \x{965}  
+ 0: \x{965}
+
+/^\p{Inherited}/8
+    \x{64b}
+ 0: \x{64b}
+    \x{654}
+ 0: \x{654}
+    \x{655}
+ 0: \x{655}
+    \x{200c} 
+ 0: \x{200c}
+    ** Failers
+No match
+    \x{64a}
+No match
+    \x{656}     
+No match
+
+/^\p{Shavian}/8
+    \x{10450}
+ 0: \x{10450}
+    \x{1047f}
+ 0: \x{1047f}
+    
+/^\p{Deseret}/8
+    \x{10400}
+ 0: \x{10400}
+    \x{1044f}
+ 0: \x{1044f}
+    
+/^\p{Osmanya}/8
+    \x{10480}
+ 0: \x{10480}
+    \x{1049d}
+ 0: \x{1049d}
+    \x{104a0}
+ 0: \x{104a0}
+    \x{104a9}
+ 0: \x{104a9}
+    ** Failers
+No match
+    \x{1049e}
+No match
+    \x{1049f}
+No match
+    \x{104aa}           
+No match
+
+/\p{Carian}\p{Cham}\p{Kayah_Li}\p{Lepcha}\p{Lycian}\p{Lydian}\p{Ol_Chiki}\p{Rejang}\p{Saurashtra}\p{Sundanese}\p{Vai}/8
+    \x{102A4}\x{AA52}\x{A91D}\x{1C46}\x{10283}\x{1092E}\x{1C6B}\x{A93B}\x{A8BF}\x{1BA0}\x{A50A}====
+ 0: \x{102a4}\x{aa52}\x{a91d}\x{1c46}\x{10283}\x{1092e}\x{1c6b}\x{a93b}\x{a8bf}\x{1ba0}\x{a50a}
+
+/\x{a77d}\x{1d79}/8i
+    \x{a77d}\x{1d79}
+ 0: \x{a77d}\x{1d79}
+    \x{1d79}\x{a77d} 
+ 0: \x{1d79}\x{a77d}
+
+/\x{a77d}\x{1d79}/8
+    \x{a77d}\x{1d79}
+ 0: \x{a77d}\x{1d79}
+    ** Failers 
+No match
+    \x{1d79}\x{a77d} 
+No match
+
+/(A)\1/8i
+    AA
+ 0: AA
+ 1: A
+    Aa
+ 0: Aa
+ 1: A
+    aa
+ 0: aa
+ 1: a
+    aA
+ 0: aA
+ 1: a
+
+/(\x{10a})\1/8i
+    \x{10a}\x{10a}
+ 0: \x{10a}\x{10a}
+ 1: \x{10a}
+    \x{10a}\x{10b}
+ 0: \x{10a}\x{10b}
+ 1: \x{10a}
+    \x{10b}\x{10b}
+ 0: \x{10b}\x{10b}
+ 1: \x{10b}
+    \x{10b}\x{10a}
+ 0: \x{10b}\x{10a}
+ 1: \x{10b}
+    
+/The next two tests are for property support in non-UTF-8 mode/
+
+/(?:\p{Lu}|\x20)+/
+    \x41\x20\x50\xC2\x54\xC9\x20\x54\x4F\x44\x41\x59
+ 0: A P\xc2T\xc9 TODAY
+
+/[\p{Lu}\x20]+/
+    \x41\x20\x50\xC2\x54\xC9\x20\x54\x4F\x44\x41\x59
+ 0: A P\xc2T\xc9 TODAY
+
+/\p{Avestan}\p{Bamum}\p{Egyptian_Hieroglyphs}\p{Imperial_Aramaic}\p{Inscriptional_Pahlavi}\p{Inscriptional_Parthian}\p{Javanese}\p{Kaithi}\p{Lisu}\p{Meetei_Mayek}\p{Old_South_Arabian}\p{Old_Turkic}\p{Samaritan}\p{Tai_Tham}\p{Tai_Viet}/8
+    \x{10b00}\x{a6ef}\x{13007}\x{10857}\x{10b78}\x{10b58}\x{a980}\x{110c1}\x{a4ff}\x{abc0}\x{10a7d}\x{10c48}\x{0800}\x{1aad}\x{aac0}
+ 0: \x{10b00}\x{a6ef}\x{13007}\x{10857}\x{10b78}\x{10b58}\x{a980}\x{110c1}\x{a4ff}\x{abc0}\x{10a7d}\x{10c48}\x{800}\x{1aad}\x{aac0}
+
+/^\w+/8W
+    Az_\x{aa}\x{c0}\x{1c5}\x{2b0}\x{3b6}\x{1d7c9}\x{2fa1d}1\x{660}\x{bef}\x{16ee}
+ 0: Az_\x{aa}\x{c0}\x{1c5}\x{2b0}\x{3b6}\x{1d7c9}\x{2fa1d}1\x{660}\x{bef}\x{16ee}
+
+/^[[:xdigit:]]*/8W
+    1a\x{660}\x{bef}\x{16ee}
+ 0: 1a
+  
+/^\d+/8W
+    1\x{660}\x{bef}\x{16ee}
+ 0: 1\x{660}\x{bef}
+  
+/^[[:digit:]]+/8W
+    1\x{660}\x{bef}\x{16ee}
+ 0: 1\x{660}\x{bef}
+
+/^>\s+/8W
+    >\x{20}\x{a0}\x{1680}\x{2028}\x{2029}\x{202f}\x{9}\x{b} 
+ 0: > \x{a0}\x{1680}\x{2028}\x{2029}\x{202f}\x{09}
+  
+/^>\pZ+/8W
+    >\x{20}\x{a0}\x{1680}\x{2028}\x{2029}\x{202f}\x{9}\x{b} 
+ 0: > \x{a0}\x{1680}\x{2028}\x{2029}\x{202f}
+  
+/^>[[:space:]]*/8W
+    >\x{20}\x{a0}\x{1680}\x{2028}\x{2029}\x{202f}\x{9}\x{b} 
+ 0: > \x{a0}\x{1680}\x{2028}\x{2029}\x{202f}\x{09}\x{0b}
+
+/^>[[:blank:]]*/8W
+    >\x{20}\x{a0}\x{1680}\x{180e}\x{2000}\x{202f}\x{9}\x{b}\x{2028} 
+ 0: > \x{a0}\x{1680}\x{180e}\x{2000}\x{202f}\x{09}
+
+/^[[:alpha:]]*/8W
+    Az\x{aa}\x{c0}\x{1c5}\x{2b0}\x{3b6}\x{1d7c9}\x{2fa1d}
+ 0: Az\x{aa}\x{c0}\x{1c5}\x{2b0}\x{3b6}\x{1d7c9}\x{2fa1d}
+
+/^[[:alnum:]]*/8W
+    Az\x{aa}\x{c0}\x{1c5}\x{2b0}\x{3b6}\x{1d7c9}\x{2fa1d}1\x{660}\x{bef}\x{16ee}
+ 0: Az\x{aa}\x{c0}\x{1c5}\x{2b0}\x{3b6}\x{1d7c9}\x{2fa1d}1\x{660}\x{bef}\x{16ee}
+
+/^[[:cntrl:]]*/8W
+    \x{0}\x{09}\x{1f}\x{7f}\x{9f} 
+ 0: \x{00}\x{09}\x{1f}\x{7f}
+
+/^[[:graph:]]*/8W
+    A\x{a1}\x{a0}
+ 0: A
+
+/^[[:print:]]*/8W
+    A z\x{a0}\x{a1}
+ 0: A z
+
+/^[[:punct:]]*/8W
+    .+\x{a1}\x{a0}
+ 0: .+
+
+/\p{Zs}*?\R/
+    ** Failers
+No match
+    a\xFCb   
+No match
+
+/\p{Zs}*\R/                                                                    
+    ** Failers 
+No match
+    a\xFCb   
+No match
+
+/â±¥/8i
+    â±¥
+ 0: \x{2c65}
+    Ⱥx 
+ 0: \x{23a}
+    Ⱥ 
+ 0: \x{23a}
+
+/[â±¥]/8i
+    â±¥
+ 0: \x{2c65}
+    Ⱥx 
+ 0: \x{23a}
+    Ⱥ 
+ 0: \x{23a}
+
+/Ⱥ/8i
+    Ⱥ
+ 0: \x{23a}
+    â±¥
+ 0: \x{2c65}
+
+/-- End of testinput6 --/
diff --git a/ext/pcre/pcrelib/testdata/testoutput7 b/ext/pcre/pcrelib/testdata/testoutput7
new file mode 100644
index 0000000..ccfdad9
--- /dev/null
+++ b/ext/pcre/pcrelib/testdata/testoutput7
@@ -0,0 +1,1316 @@
+/-- These tests for Unicode property support test PCRE's API and show some of
+    the compiled code. They are not Perl-compatible. --/
+
+/[\p{L}]/DZ
+------------------------------------------------------------------
+        Bra
+        [\p{L}]
+        Ket
+        End
+------------------------------------------------------------------
+Capturing subpattern count = 0
+No options
+No first char
+No need char
+
+/[\p{^L}]/DZ
+------------------------------------------------------------------
+        Bra
+        [\P{L}]
+        Ket
+        End
+------------------------------------------------------------------
+Capturing subpattern count = 0
+No options
+No first char
+No need char
+
+/[\P{L}]/DZ
+------------------------------------------------------------------
+        Bra
+        [\P{L}]
+        Ket
+        End
+------------------------------------------------------------------
+Capturing subpattern count = 0
+No options
+No first char
+No need char
+
+/[\P{^L}]/DZ
+------------------------------------------------------------------
+        Bra
+        [\p{L}]
+        Ket
+        End
+------------------------------------------------------------------
+Capturing subpattern count = 0
+No options
+No first char
+No need char
+
+/[abc\p{L}\x{0660}]/8DZ
+------------------------------------------------------------------
+        Bra
+        [a-c\p{L}\x{660}]
+        Ket
+        End
+------------------------------------------------------------------
+Capturing subpattern count = 0
+Options: utf
+No first char
+No need char
+
+/[\p{Nd}]/8DZ
+------------------------------------------------------------------
+        Bra
+        [\p{Nd}]
+        Ket
+        End
+------------------------------------------------------------------
+Capturing subpattern count = 0
+Options: utf
+No first char
+No need char
+    1234
+ 0: 1
+
+/[\p{Nd}+-]+/8DZ
+------------------------------------------------------------------
+        Bra
+        [+\-\p{Nd}]+
+        Ket
+        End
+------------------------------------------------------------------
+Capturing subpattern count = 0
+Options: utf
+No first char
+No need char
+    1234
+ 0: 1234
+    12-34
+ 0: 12-34
+    12+\x{661}-34  
+ 0: 12+\x{661}-34
+    ** Failers
+No match
+    abcd  
+No match
+
+/[\x{105}-\x{109}]/8iDZ
+------------------------------------------------------------------
+        Bra
+        [\x{104}-\x{109}]
+        Ket
+        End
+------------------------------------------------------------------
+Capturing subpattern count = 0
+Options: caseless utf
+No first char
+No need char
+    \x{104}
+ 0: \x{104}
+    \x{105}
+ 0: \x{105}
+    \x{109}  
+ 0: \x{109}
+    ** Failers
+No match
+    \x{100}
+No match
+    \x{10a} 
+No match
+    
+/[z-\x{100}]/8iDZ 
+------------------------------------------------------------------
+        Bra
+        [Z\x{39c}\x{178}z-\x{101}]
+        Ket
+        End
+------------------------------------------------------------------
+Capturing subpattern count = 0
+Options: caseless utf
+No first char
+No need char
+    Z
+ 0: Z
+    z
+ 0: z
+    \x{39c}
+ 0: \x{39c}
+    \x{178}
+ 0: \x{178}
+    |
+ 0: |
+    \x{80}
+ 0: \x{80}
+    \x{ff}
+ 0: \x{ff}
+    \x{100}
+ 0: \x{100}
+    \x{101} 
+ 0: \x{101}
+    ** Failers
+No match
+    \x{102}
+No match
+    Y
+No match
+    y           
+No match
+
+/[z-\x{100}]/8DZi
+------------------------------------------------------------------
+        Bra
+        [Z\x{39c}\x{178}z-\x{101}]
+        Ket
+        End
+------------------------------------------------------------------
+Capturing subpattern count = 0
+Options: caseless utf
+No first char
+No need char
+
+/(?:[\PPa*]*){8,}/
+
+/[\P{Any}]/BZ
+------------------------------------------------------------------
+        Bra
+        [\P{Any}]
+        Ket
+        End
+------------------------------------------------------------------
+
+/[\P{Any}\E]/BZ
+------------------------------------------------------------------
+        Bra
+        [\P{Any}]
+        Ket
+        End
+------------------------------------------------------------------
+
+/(\P{Yi}+\277)/
+
+/(\P{Yi}+\277)?/
+
+/(?<=\P{Yi}{3}A)X/
+
+/\p{Yi}+(\P{Yi}+)(?1)/
+
+/(\P{Yi}{2}\277)?/
+
+/[\P{Yi}A]/
+
+/[\P{Yi}\P{Yi}\P{Yi}A]/
+
+/[^\P{Yi}A]/
+
+/[^\P{Yi}\P{Yi}\P{Yi}A]/
+
+/(\P{Yi}*\277)*/
+
+/(\P{Yi}*?\277)*/
+
+/(\p{Yi}*+\277)*/
+
+/(\P{Yi}?\277)*/
+
+/(\P{Yi}??\277)*/
+
+/(\p{Yi}?+\277)*/
+
+/(\P{Yi}{0,3}\277)*/
+
+/(\P{Yi}{0,3}?\277)*/
+
+/(\p{Yi}{0,3}+\277)*/
+
+/\p{Zl}{2,3}+/8BZ
+------------------------------------------------------------------
+        Bra
+        prop Zl {2}
+        prop Zl ?+
+        Ket
+        End
+------------------------------------------------------------------
+    \xe2\x80\xa8\xe2\x80\xa8
+ 0: \x{2028}\x{2028}
+    \x{2028}\x{2028}\x{2028}
+ 0: \x{2028}\x{2028}\x{2028}
+    
+/\p{Zl}/8BZ
+------------------------------------------------------------------
+        Bra
+        prop Zl
+        Ket
+        End
+------------------------------------------------------------------
+
+/\p{Lu}{3}+/8BZ
+------------------------------------------------------------------
+        Bra
+        prop Lu {3}
+        Ket
+        End
+------------------------------------------------------------------
+
+/\pL{2}+/8BZ
+------------------------------------------------------------------
+        Bra
+        prop L {2}
+        Ket
+        End
+------------------------------------------------------------------
+
+/\p{Cc}{2}+/8BZ
+------------------------------------------------------------------
+        Bra
+        prop Cc {2}
+        Ket
+        End
+------------------------------------------------------------------
+
+/^\p{Cs}/8
+    \?\x{dfff}
+ 0: \x{dfff}
+    ** Failers
+No match
+    \x{09f} 
+No match
+  
+/^\p{Sc}+/8
+    $\x{a2}\x{a3}\x{a4}\x{a5}\x{a6}
+ 0: $\x{a2}\x{a3}\x{a4}\x{a5}
+    \x{9f2}
+ 0: \x{9f2}
+    ** Failers
+No match
+    X
+No match
+    \x{2c2}
+No match
+  
+/^\p{Zs}/8
+    \ \
+ 0:  
+    \x{a0}
+ 0: \x{a0}
+    \x{1680}
+ 0: \x{1680}
+    \x{180e}
+ 0: \x{180e}
+    \x{2000}
+ 0: \x{2000}
+    \x{2001}     
+ 0: \x{2001}
+    ** Failers
+No match
+    \x{2028}
+No match
+    \x{200d} 
+No match
+  
+/-- These four are here rather than in test 6 because Perl has problems with
+    the negative versions of the properties. --/
+      
+/\p{^Lu}/8i
+    1234
+ 0: 1
+    ** Failers
+ 0: *
+    ABC 
+No match
+
+/\P{Lu}/8i
+    1234
+ 0: 1
+    ** Failers
+ 0: *
+    ABC 
+No match
+
+/\p{Ll}/8i 
+    a
+ 0: a
+    Az
+ 0: z
+    ** Failers
+ 0: a
+    ABC   
+No match
+
+/\p{Lu}/8i
+    A
+ 0: A
+    a\x{10a0}B 
+ 0: \x{10a0}
+    ** Failers 
+ 0: F
+    a
+No match
+    \x{1d00}  
+No match
+
+/[\x{c0}\x{391}]/8i
+    \x{c0}
+ 0: \x{c0}
+    \x{e0} 
+ 0: \x{e0}
+
+/-- The next two are special cases where the lengths of the different cases of
+the same character differ. The first went wrong with heap frame storage; the
+second was broken in all cases. --/
+
+/^\x{023a}+?(\x{0130}+)/8i
+  \x{023a}\x{2c65}\x{0130}
+ 0: \x{23a}\x{2c65}\x{130}
+ 1: \x{130}
+  
+/^\x{023a}+([^X])/8i
+  \x{023a}\x{2c65}X
+ 0: \x{23a}\x{2c65}
+ 1: \x{2c65}
+
+/\x{c0}+\x{116}+/8i
+    \x{c0}\x{e0}\x{116}\x{117}
+ 0: \x{c0}\x{e0}\x{116}\x{117}
+
+/[\x{c0}\x{116}]+/8i
+    \x{c0}\x{e0}\x{116}\x{117}
+ 0: \x{c0}\x{e0}\x{116}\x{117}
+
+/(\x{de})\1/8i
+    \x{de}\x{de}
+ 0: \x{de}\x{de}
+ 1: \x{de}
+    \x{de}\x{fe}
+ 0: \x{de}\x{fe}
+ 1: \x{de}
+    \x{fe}\x{fe}
+ 0: \x{fe}\x{fe}
+ 1: \x{fe}
+    \x{fe}\x{de}
+ 0: \x{fe}\x{de}
+ 1: \x{fe}
+
+/^\x{c0}$/8i
+    \x{c0}
+ 0: \x{c0}
+    \x{e0} 
+ 0: \x{e0}
+
+/^\x{e0}$/8i
+    \x{c0}
+ 0: \x{c0}
+    \x{e0} 
+ 0: \x{e0}
+
+/-- The next two should be Perl-compatible, but it fails to match \x{e0}. PCRE
+will match it only with UCP support, because without that it has no notion
+of case for anything other than the ASCII letters. --/ 
+
+/((?i)[\x{c0}])/8
+    \x{c0}
+ 0: \x{c0}
+ 1: \x{c0}
+    \x{e0} 
+ 0: \x{e0}
+ 1: \x{e0}
+
+/(?i:[\x{c0}])/8
+    \x{c0}
+ 0: \x{c0}
+    \x{e0} 
+ 0: \x{e0}
+
+/-- This should be Perl-compatible but Perl 5.11 gets \x{300} wrong. --/8
+    
+/^\X/8
+    A
+ 0: A
+    A\x{300}BC 
+ 0: A\x{300}
+    A\x{300}\x{301}\x{302}BC 
+ 0: A\x{300}\x{301}\x{302}
+    *** Failers
+ 0: *
+    \x{300}  
+No match
+    
+/-- These are PCRE's extra properties to help with Unicodizing \d etc. --/
+
+/^\p{Xan}/8
+    ABCD
+ 0: A
+    1234
+ 0: 1
+    \x{6ca}
+ 0: \x{6ca}
+    \x{a6c}
+ 0: \x{a6c}
+    \x{10a7}   
+ 0: \x{10a7}
+    ** Failers
+No match
+    _ABC   
+No match
+
+/^\p{Xan}+/8
+    ABCD1234\x{6ca}\x{a6c}\x{10a7}_
+ 0: ABCD1234\x{6ca}\x{a6c}\x{10a7}
+    ** Failers
+No match
+    _ABC   
+No match
+
+/^\p{Xan}+?/8
+    \x{6ca}\x{a6c}\x{10a7}_
+ 0: \x{6ca}
+
+/^\p{Xan}*/8
+    ABCD1234\x{6ca}\x{a6c}\x{10a7}_
+ 0: ABCD1234\x{6ca}\x{a6c}\x{10a7}
+    
+/^\p{Xan}{2,9}/8
+    ABCD1234\x{6ca}\x{a6c}\x{10a7}_
+ 0: ABCD1234\x{6ca}
+    
+/^\p{Xan}{2,9}?/8
+    \x{6ca}\x{a6c}\x{10a7}_
+ 0: \x{6ca}\x{a6c}
+    
+/^[\p{Xan}]/8
+    ABCD1234_
+ 0: A
+    1234abcd_
+ 0: 1
+    \x{6ca}
+ 0: \x{6ca}
+    \x{a6c}
+ 0: \x{a6c}
+    \x{10a7}   
+ 0: \x{10a7}
+    ** Failers
+No match
+    _ABC   
+No match
+ 
+/^[\p{Xan}]+/8
+    ABCD1234\x{6ca}\x{a6c}\x{10a7}_
+ 0: ABCD1234\x{6ca}\x{a6c}\x{10a7}
+    ** Failers
+No match
+    _ABC   
+No match
+
+/^>\p{Xsp}/8
+    >\x{1680}\x{2028}\x{0b}
+ 0: >\x{1680}
+    >\x{a0} 
+ 0: >\x{a0}
+    ** Failers
+No match
+    \x{0b} 
+No match
+
+/^>\p{Xsp}+/8
+    > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}\x{0b}
+ 0: > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}
+
+/^>\p{Xsp}+?/8
+    >\x{1680}\x{2028}\x{0b}
+ 0: >\x{1680}
+
+/^>\p{Xsp}*/8
+    > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}\x{0b}
+ 0: > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}
+    
+/^>\p{Xsp}{2,9}/8
+    > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}\x{0b}
+ 0: > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}
+    
+/^>\p{Xsp}{2,9}?/8
+    > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}\x{0b}
+ 0: > \x{09}
+    
+/^>[\p{Xsp}]/8
+    >\x{2028}\x{0b}
+ 0: >\x{2028}
+ 
+/^>[\p{Xsp}]+/8
+    > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}\x{0b}
+ 0: > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}
+
+/^>\p{Xps}/8
+    >\x{1680}\x{2028}\x{0b}
+ 0: >\x{1680}
+    >\x{a0} 
+ 0: >\x{a0}
+    ** Failers
+No match
+    \x{0b} 
+No match
+
+/^>\p{Xps}+/8
+    > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}\x{0b}
+ 0: > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}\x{0b}
+
+/^>\p{Xps}+?/8
+    >\x{1680}\x{2028}\x{0b}
+ 0: >\x{1680}
+
+/^>\p{Xps}*/8
+    > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}\x{0b}
+ 0: > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}\x{0b}
+    
+/^>\p{Xps}{2,9}/8
+    > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}\x{0b}
+ 0: > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}\x{0b}
+    
+/^>\p{Xps}{2,9}?/8
+    > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}\x{0b}
+ 0: > \x{09}
+    
+/^>[\p{Xps}]/8
+    >\x{2028}\x{0b}
+ 0: >\x{2028}
+ 
+/^>[\p{Xps}]+/8
+    > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}\x{0b}
+ 0: > \x{09}\x{0a}\x{0c}\x{0d}\x{a0}\x{1680}\x{2028}\x{0b}
+
+/^\p{Xwd}/8
+    ABCD
+ 0: A
+    1234
+ 0: 1
+    \x{6ca}
+ 0: \x{6ca}
+    \x{a6c}
+ 0: \x{a6c}
+    \x{10a7}
+ 0: \x{10a7}
+    _ABC    
+ 0: _
+    ** Failers
+No match
+    [] 
+No match
+
+/^\p{Xwd}+/8
+    ABCD1234\x{6ca}\x{a6c}\x{10a7}_
+ 0: ABCD1234\x{6ca}\x{a6c}\x{10a7}_
+
+/^\p{Xwd}+?/8
+    \x{6ca}\x{a6c}\x{10a7}_
+ 0: \x{6ca}
+
+/^\p{Xwd}*/8
+    ABCD1234\x{6ca}\x{a6c}\x{10a7}_
+ 0: ABCD1234\x{6ca}\x{a6c}\x{10a7}_
+    
+/^\p{Xwd}{2,9}/8
+    A_B12\x{6ca}\x{a6c}\x{10a7}
+ 0: A_B12\x{6ca}\x{a6c}\x{10a7}
+    
+/^\p{Xwd}{2,9}?/8
+    \x{6ca}\x{a6c}\x{10a7}_
+ 0: \x{6ca}\x{a6c}
+    
+/^[\p{Xwd}]/8
+    ABCD1234_
+ 0: A
+    1234abcd_
+ 0: 1
+    \x{6ca}
+ 0: \x{6ca}
+    \x{a6c}
+ 0: \x{a6c}
+    \x{10a7}   
+ 0: \x{10a7}
+    _ABC 
+ 0: _
+    ** Failers
+No match
+    []   
+No match
+ 
+/^[\p{Xwd}]+/8
+    ABCD1234\x{6ca}\x{a6c}\x{10a7}_
+ 0: ABCD1234\x{6ca}\x{a6c}\x{10a7}_
+
+/-- A check not in UTF-8 mode --/
+
+/^[\p{Xwd}]+/
+    ABCD1234_
+ 0: ABCD1234_
+    
+/-- Some negative checks --/
+
+/^[\P{Xwd}]+/8
+    !.+\x{019}\x{35a}AB
+ 0: !.+\x{19}\x{35a}
+
+/^[\p{^Xwd}]+/8
+    !.+\x{019}\x{35a}AB
+ 0: !.+\x{19}\x{35a}
+
+/[\D]/WBZ8
+------------------------------------------------------------------
+        Bra
+        [\P{Nd}]
+        Ket
+        End
+------------------------------------------------------------------
+    1\x{3c8}2
+ 0: \x{3c8}
+
+/[\d]/WBZ8
+------------------------------------------------------------------
+        Bra
+        [\p{Nd}]
+        Ket
+        End
+------------------------------------------------------------------
+    >\x{6f4}<
+ 0: \x{6f4}
+
+/[\S]/WBZ8
+------------------------------------------------------------------
+        Bra
+        [\P{Xsp}]
+        Ket
+        End
+------------------------------------------------------------------
+    \x{1680}\x{6f4}\x{1680}
+ 0: \x{6f4}
+
+/[\s]/WBZ8
+------------------------------------------------------------------
+        Bra
+        [\p{Xsp}]
+        Ket
+        End
+------------------------------------------------------------------
+    >\x{1680}<
+ 0: \x{1680}
+
+/[\W]/WBZ8
+------------------------------------------------------------------
+        Bra
+        [\P{Xwd}]
+        Ket
+        End
+------------------------------------------------------------------
+    A\x{1712}B
+ 0: \x{1712}
+
+/[\w]/WBZ8
+------------------------------------------------------------------
+        Bra
+        [\p{Xwd}]
+        Ket
+        End
+------------------------------------------------------------------
+    >\x{1723}<
+ 0: \x{1723}
+
+/\D/WBZ8
+------------------------------------------------------------------
+        Bra
+        notprop Nd
+        Ket
+        End
+------------------------------------------------------------------
+    1\x{3c8}2
+ 0: \x{3c8}
+
+/\d/WBZ8
+------------------------------------------------------------------
+        Bra
+        prop Nd
+        Ket
+        End
+------------------------------------------------------------------
+    >\x{6f4}<
+ 0: \x{6f4}
+
+/\S/WBZ8
+------------------------------------------------------------------
+        Bra
+        notprop Xsp
+        Ket
+        End
+------------------------------------------------------------------
+    \x{1680}\x{6f4}\x{1680}
+ 0: \x{6f4}
+
+/\s/WBZ8
+------------------------------------------------------------------
+        Bra
+        prop Xsp
+        Ket
+        End
+------------------------------------------------------------------
+    >\x{1680}>
+ 0: \x{1680}
+
+/\W/WBZ8
+------------------------------------------------------------------
+        Bra
+        notprop Xwd
+        Ket
+        End
+------------------------------------------------------------------
+    A\x{1712}B
+ 0: \x{1712}
+
+/\w/WBZ8
+------------------------------------------------------------------
+        Bra
+        prop Xwd
+        Ket
+        End
+------------------------------------------------------------------
+    >\x{1723}<
+ 0: \x{1723}
+
+/[[:alpha:]]/WBZ
+------------------------------------------------------------------
+        Bra
+        [\p{L}]
+        Ket
+        End
+------------------------------------------------------------------
+
+/[[:lower:]]/WBZ
+------------------------------------------------------------------
+        Bra
+        [\p{Ll}]
+        Ket
+        End
+------------------------------------------------------------------
+
+/[[:upper:]]/WBZ
+------------------------------------------------------------------
+        Bra
+        [\p{Lu}]
+        Ket
+        End
+------------------------------------------------------------------
+
+/[[:alnum:]]/WBZ
+------------------------------------------------------------------
+        Bra
+        [\p{Xan}]
+        Ket
+        End
+------------------------------------------------------------------
+
+/[[:ascii:]]/WBZ
+------------------------------------------------------------------
+        Bra
+        [\x00-\x7f]
+        Ket
+        End
+------------------------------------------------------------------
+
+/[[:cntrl:]]/WBZ
+------------------------------------------------------------------
+        Bra
+        [\x00-\x1f\x7f]
+        Ket
+        End
+------------------------------------------------------------------
+
+/[[:digit:]]/WBZ
+------------------------------------------------------------------
+        Bra
+        [\p{Nd}]
+        Ket
+        End
+------------------------------------------------------------------
+
+/[[:graph:]]/WBZ
+------------------------------------------------------------------
+        Bra
+        [!-~]
+        Ket
+        End
+------------------------------------------------------------------
+
+/[[:print:]]/WBZ
+------------------------------------------------------------------
+        Bra
+        [ -~]
+        Ket
+        End
+------------------------------------------------------------------
+
+/[[:punct:]]/WBZ
+------------------------------------------------------------------
+        Bra
+        [!-/:-@[-`{-~]
+        Ket
+        End
+------------------------------------------------------------------
+
+/[[:space:]]/WBZ
+------------------------------------------------------------------
+        Bra
+        [\p{Xps}]
+        Ket
+        End
+------------------------------------------------------------------
+
+/[[:word:]]/WBZ
+------------------------------------------------------------------
+        Bra
+        [\p{Xwd}]
+        Ket
+        End
+------------------------------------------------------------------
+
+/[[:xdigit:]]/WBZ
+------------------------------------------------------------------
+        Bra
+        [0-9A-Fa-f]
+        Ket
+        End
+------------------------------------------------------------------
+
+/-- Unicode properties for \b abd \B --/
+
+/\b...\B/8W
+    abc_
+ 0: abc
+    \x{37e}abc\x{376} 
+ 0: abc
+    \x{37e}\x{376}\x{371}\x{393}\x{394} 
+ 0: \x{376}\x{371}\x{393}
+    !\x{c0}++\x{c1}\x{c2} 
+ 0: ++\x{c1}
+    !\x{c0}+++++ 
+ 0: \x{c0}++
+
+/-- Without PCRE_UCP, non-ASCII always fail, even if < 256  --/
+
+/\b...\B/8
+    abc_
+ 0: abc
+    ** Failers 
+ 0: Fai
+    \x{37e}abc\x{376} 
+No match
+    \x{37e}\x{376}\x{371}\x{393}\x{394} 
+No match
+    !\x{c0}++\x{c1}\x{c2} 
+No match
+    !\x{c0}+++++ 
+No match
+
+/-- With PCRE_UCP, non-UTF8 chars that are < 256 still check properties  --/
+
+/\b...\B/W
+    abc_
+ 0: abc
+    !\x{c0}++\x{c1}\x{c2} 
+ 0: ++\xc1
+    !\x{c0}+++++ 
+ 0: \xc0++
+
+/-- Some of these are silly, but they check various combinations --/
+
+/[[:^alpha:][:^cntrl:]]+/8WBZ
+------------------------------------------------------------------
+        Bra
+        [ -~\x80-\xff\P{L}]+
+        Ket
+        End
+------------------------------------------------------------------
+    123
+ 0: 123
+    abc 
+ 0: abc
+
+/[[:^cntrl:][:^alpha:]]+/8WBZ
+------------------------------------------------------------------
+        Bra
+        [ -~\x80-\xff\P{L}]+
+        Ket
+        End
+------------------------------------------------------------------
+    123
+ 0: 123
+    abc 
+ 0: abc
+
+/[[:alpha:]]+/8WBZ
+------------------------------------------------------------------
+        Bra
+        [\p{L}]+
+        Ket
+        End
+------------------------------------------------------------------
+    abc
+ 0: abc
+
+/[[:^alpha:]\S]+/8WBZ
+------------------------------------------------------------------
+        Bra
+        [\P{L}\P{Xsp}]+
+        Ket
+        End
+------------------------------------------------------------------
+    123
+ 0: 123
+    abc 
+ 0: abc
+
+/[^\d]+/8WBZ
+------------------------------------------------------------------
+        Bra
+        [^\p{Nd}]+
+        Ket
+        End
+------------------------------------------------------------------
+    abc123
+ 0: abc
+    abc\x{123}
+ 0: abc\x{123}
+    \x{660}abc   
+ 0: abc
+
+/\p{Lu}+9\p{Lu}+B\p{Lu}+b/BZ
+------------------------------------------------------------------
+        Bra
+        prop Lu ++
+        9
+        prop Lu +
+        B
+        prop Lu ++
+        b
+        Ket
+        End
+------------------------------------------------------------------
+
+/\p{^Lu}+9\p{^Lu}+B\p{^Lu}+b/BZ
+------------------------------------------------------------------
+        Bra
+        notprop Lu +
+        9
+        notprop Lu ++
+        B
+        notprop Lu +
+        b
+        Ket
+        End
+------------------------------------------------------------------
+
+/\P{Lu}+9\P{Lu}+B\P{Lu}+b/BZ
+------------------------------------------------------------------
+        Bra
+        notprop Lu +
+        9
+        notprop Lu ++
+        B
+        notprop Lu +
+        b
+        Ket
+        End
+------------------------------------------------------------------
+
+/\p{Han}+X\p{Greek}+\x{370}/BZ8
+------------------------------------------------------------------
+        Bra
+        prop Han ++
+        X
+        prop Greek +
+        \x{370}
+        Ket
+        End
+------------------------------------------------------------------
+
+/\p{Xan}+!\p{Xan}+A/BZ
+------------------------------------------------------------------
+        Bra
+        prop Xan ++
+        !
+        prop Xan +
+        A
+        Ket
+        End
+------------------------------------------------------------------
+
+/\p{Xsp}+!\p{Xsp}\t/BZ
+------------------------------------------------------------------
+        Bra
+        prop Xsp ++
+        !
+        prop Xsp
+        \x09
+        Ket
+        End
+------------------------------------------------------------------
+
+/\p{Xps}+!\p{Xps}\t/BZ
+------------------------------------------------------------------
+        Bra
+        prop Xps ++
+        !
+        prop Xps
+        \x09
+        Ket
+        End
+------------------------------------------------------------------
+
+/\p{Xwd}+!\p{Xwd}_/BZ
+------------------------------------------------------------------
+        Bra
+        prop Xwd ++
+        !
+        prop Xwd
+        _
+        Ket
+        End
+------------------------------------------------------------------
+
+/A+\p{N}A+\dB+\p{N}*B+\d*/WBZ
+------------------------------------------------------------------
+        Bra
+        A++
+        prop N
+        A++
+        prop Nd
+        B+
+        prop N *+
+        B+
+        prop Nd *
+        Ket
+        End
+------------------------------------------------------------------
+
+/-- These behaved oddly in Perl, so they are kept in this test --/
+
+/(\x{23a}\x{23a}\x{23a})?\1/8i
+    \x{23a}\x{23a}\x{23a}\x{2c65}\x{2c65}
+No match
+
+/(ȺȺȺ)?\1/8i
+    ȺȺȺⱥⱥ
+No match
+
+/(\x{23a}\x{23a}\x{23a})?\1/8i
+    \x{23a}\x{23a}\x{23a}\x{2c65}\x{2c65}\x{2c65}
+ 0: \x{23a}\x{23a}\x{23a}\x{2c65}\x{2c65}\x{2c65}
+ 1: \x{23a}\x{23a}\x{23a}
+
+/(ȺȺȺ)?\1/8i
+    ȺȺȺⱥⱥⱥ
+ 0: \x{23a}\x{23a}\x{23a}\x{2c65}\x{2c65}\x{2c65}
+ 1: \x{23a}\x{23a}\x{23a}
+
+/(\x{23a}\x{23a}\x{23a})\1/8i
+    \x{23a}\x{23a}\x{23a}\x{2c65}\x{2c65}
+No match
+
+/(ȺȺȺ)\1/8i
+    ȺȺȺⱥⱥ
+No match
+
+/(\x{23a}\x{23a}\x{23a})\1/8i
+    \x{23a}\x{23a}\x{23a}\x{2c65}\x{2c65}\x{2c65}
+ 0: \x{23a}\x{23a}\x{23a}\x{2c65}\x{2c65}\x{2c65}
+ 1: \x{23a}\x{23a}\x{23a}
+
+/(ȺȺȺ)\1/8i
+    ȺȺȺⱥⱥⱥ
+ 0: \x{23a}\x{23a}\x{23a}\x{2c65}\x{2c65}\x{2c65}
+ 1: \x{23a}\x{23a}\x{23a}
+
+/(\x{2c65}\x{2c65})\1/8i
+    \x{2c65}\x{2c65}\x{23a}\x{23a}
+ 0: \x{2c65}\x{2c65}\x{23a}\x{23a}
+ 1: \x{2c65}\x{2c65}
+    
+/(ⱥⱥ)\1/8i
+    ⱥⱥȺȺ 
+ 0: \x{2c65}\x{2c65}\x{23a}\x{23a}
+ 1: \x{2c65}\x{2c65}
+    
+/(\x{23a}\x{23a}\x{23a})\1Y/8i
+    X\x{23a}\x{23a}\x{23a}\x{2c65}\x{2c65}\x{2c65}YZ
+ 0: \x{23a}\x{23a}\x{23a}\x{2c65}\x{2c65}\x{2c65}Y
+ 1: \x{23a}\x{23a}\x{23a}
+
+/(\x{2c65}\x{2c65})\1Y/8i
+    X\x{2c65}\x{2c65}\x{23a}\x{23a}YZ
+ 0: \x{2c65}\x{2c65}\x{23a}\x{23a}Y
+ 1: \x{2c65}\x{2c65}
+
+/-- --/ 
+
+/-- These scripts weren't yet in Perl when I added Unicode 6.0.0 to PCRE --/
+
+/^[\p{Batak}]/8
+    \x{1bc0}
+ 0: \x{1bc0}
+    \x{1bff}
+ 0: \x{1bff}
+    ** Failers
+No match
+    \x{1bf4}
+No match
+    
+/^[\p{Brahmi}]/8
+    \x{11000}
+ 0: \x{11000}
+    \x{1106f}
+ 0: \x{1106f}
+    ** Failers
+No match
+    \x{1104e}
+No match
+    
+/^[\p{Mandaic}]/8
+    \x{840}
+ 0: \x{840}
+    \x{85e}
+ 0: \x{85e}
+    ** Failers
+No match
+    \x{85c}
+No match
+    \x{85d}    
+No match
+
+/-- --/ 
+
+/(\X*)(.)/s8
+    A\x{300}
+ 0: A
+ 1: 
+ 2: A
+
+/^S(\X*)e(\X*)$/8
+    Ste�re�o
+No match
+    
+/^\X/8 
+    �re�o
+No match
+
+/^a\X41z/<JS>
+    aX41z
+ 0: aX41z
+    *** Failers
+No match
+    aAz
+No match
+
+/(?<=ab\Cde)X/8
+Failed: \C not allowed in lookbehind assertion at offset 10
+
+/\X/
+    a\P
+ 0: a
+    a\P\P
+Partial match: a
+
+/\Xa/
+    aa\P
+ 0: aa
+    aa\P\P
+ 0: aa
+
+/\X{2}/
+    aa\P
+ 0: aa
+    aa\P\P
+Partial match: aa
+
+/\X+a/
+    a\P
+Partial match: a
+    aa\P
+ 0: aa
+    aa\P\P
+Partial match: aa
+
+/\X+?a/
+    a\P
+Partial match: a
+    ab\P
+Partial match: ab
+    aa\P
+ 0: aa
+    aa\P\P
+ 0: aa
+    aba\P
+ 0: aba
+    
+/-- These Unicode 6.1.0 scripts are not known to Perl. --/ 
+
+/\p{Chakma}\d/8W
+    \x{11100}\x{1113c}
+ 0: \x{11100}\x{1113c}
+
+/\p{Takri}\d/8W
+    \x{11680}\x{116c0}
+ 0: \x{11680}\x{116c0}
+
+/^\X/8
+    A\P
+ 0: A
+    A\P\P 
+Partial match: A
+    A\x{300}\x{301}\P
+ 0: A\x{300}\x{301}
+    A\x{300}\x{301}\P\P  
+Partial match: A\x{300}\x{301}
+    A\x{301}\P
+ 0: A\x{301}
+    A\x{301}\P\P  
+Partial match: A\x{301}
+    
+/^\X{2,3}/8
+    A\P
+Partial match: A
+    A\P\P 
+Partial match: A
+    AA\P
+ 0: AA
+    AA\P\P  
+Partial match: AA
+    A\x{300}\x{301}\P
+Partial match: A\x{300}\x{301}
+    A\x{300}\x{301}\P\P  
+Partial match: A\x{300}\x{301}
+    A\x{300}\x{301}A\x{300}\x{301}\P
+ 0: A\x{300}\x{301}A\x{300}\x{301}
+    A\x{300}\x{301}A\x{300}\x{301}\P\P  
+Partial match: A\x{300}\x{301}A\x{300}\x{301}
+
+/^\X{2}/8
+    AA\P
+ 0: AA
+    AA\P\P  
+Partial match: AA
+    A\x{300}\x{301}A\x{300}\x{301}\P
+ 0: A\x{300}\x{301}A\x{300}\x{301}
+    A\x{300}\x{301}A\x{300}\x{301}\P\P  
+Partial match: A\x{300}\x{301}A\x{300}\x{301}
+    
+/^\X+/8
+    AA\P
+ 0: AA
+    AA\P\P  
+Partial match: AA
+
+/^\X+?Z/8
+    AA\P
+Partial match: AA
+    AA\P\P 
+Partial match: AA
+
+/-- End of testinput7 --/
diff --git a/ext/pcre/pcrelib/testdata/testoutput8 b/ext/pcre/pcrelib/testdata/testoutput8
new file mode 100644
index 0000000..73e0eae
--- /dev/null
+++ b/ext/pcre/pcrelib/testdata/testoutput8
@@ -0,0 +1,8019 @@
+/-- This set of tests check the DFA matching functionality of pcre_dfa_exec().
+    The -dfa flag must be used with pcretest when running it. --/
+     
+/abc/
+    abc
+ 0: abc
+    
+/ab*c/
+    abc
+ 0: abc
+    abbbbc
+ 0: abbbbc
+    ac
+ 0: ac
+    
+/ab+c/
+    abc
+ 0: abc
+    abbbbbbc
+ 0: abbbbbbc
+    *** Failers 
+No match
+    ac
+No match
+    ab
+No match
+    
+/a*/
+    a
+ 0: a
+ 1: 
+    aaaaaaaaaaaaaaaaa
+ 0: aaaaaaaaaaaaaaaaa
+ 1: aaaaaaaaaaaaaaaa
+ 2: aaaaaaaaaaaaaaa
+ 3: aaaaaaaaaaaaaa
+ 4: aaaaaaaaaaaaa
+ 5: aaaaaaaaaaaa
+ 6: aaaaaaaaaaa
+ 7: aaaaaaaaaa
+ 8: aaaaaaaaa
+ 9: aaaaaaaa
+10: aaaaaaa
+11: aaaaaa
+12: aaaaa
+13: aaaa
+14: aaa
+15: aa
+16: a
+17: 
+    aaaaaaaaaaaaaaaaaaaaaaaaaaaaaa 
+Matched, but too many subsidiary matches
+ 0: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+ 1: aaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+ 2: aaaaaaaaaaaaaaaaaaaaaaaaaaaa
+ 3: aaaaaaaaaaaaaaaaaaaaaaaaaaa
+ 4: aaaaaaaaaaaaaaaaaaaaaaaaaa
+ 5: aaaaaaaaaaaaaaaaaaaaaaaaa
+ 6: aaaaaaaaaaaaaaaaaaaaaaaa
+ 7: aaaaaaaaaaaaaaaaaaaaaaa
+ 8: aaaaaaaaaaaaaaaaaaaaaa
+ 9: aaaaaaaaaaaaaaaaaaaaa
+10: aaaaaaaaaaaaaaaaaaaa
+11: aaaaaaaaaaaaaaaaaaa
+12: aaaaaaaaaaaaaaaaaa
+13: aaaaaaaaaaaaaaaaa
+14: aaaaaaaaaaaaaaaa
+15: aaaaaaaaaaaaaaa
+16: aaaaaaaaaaaaaa
+17: aaaaaaaaaaaaa
+18: aaaaaaaaaaaa
+19: aaaaaaaaaaa
+20: aaaaaaaaaa
+21: aaaaaaaaa
+    aaaaaaaaaaaaaaaaaaaaaaaaaaaaaa\F 
+ 0: 
+    
+/(a|abcd|african)/
+    a
+ 0: a
+    abcd
+ 0: abcd
+ 1: a
+    african
+ 0: african
+ 1: a
+    
+/^abc/
+    abcdef
+ 0: abc
+    *** Failers
+No match
+    xyzabc
+No match
+    xyz\nabc    
+No match
+    
+/^abc/m
+    abcdef
+ 0: abc
+    xyz\nabc    
+ 0: abc
+    *** Failers
+No match
+    xyzabc
+No match
+    
+/\Aabc/
+    abcdef
+ 0: abc
+    *** Failers
+No match
+    xyzabc
+No match
+    xyz\nabc    
+No match
+    
+/\Aabc/m
+    abcdef
+ 0: abc
+    *** Failers
+No match
+    xyzabc
+No match
+    xyz\nabc    
+No match
+    
+/\Gabc/
+    abcdef
+ 0: abc
+    xyzabc\>3
+ 0: abc
+    *** Failers
+No match
+    xyzabc    
+No match
+    xyzabc\>2 
+No match
+    
+/x\dy\Dz/
+    x9yzz
+ 0: x9yzz
+    x0y+z
+ 0: x0y+z
+    *** Failers
+No match
+    xyz
+No match
+    xxy0z     
+No match
+    
+/x\sy\Sz/
+    x yzz
+ 0: x yzz
+    x y+z
+ 0: x y+z
+    *** Failers
+No match
+    xyz
+No match
+    xxyyz
+No match
+    
+/x\wy\Wz/
+    xxy+z
+ 0: xxy+z
+    *** Failers
+No match
+    xxy0z
+No match
+    x+y+z         
+No match
+    
+/x.y/
+    x+y
+ 0: x+y
+    x-y
+ 0: x-y
+    *** Failers
+No match
+    x\ny
+No match
+    
+/x.y/s
+    x+y
+ 0: x+y
+    x-y
+ 0: x-y
+    x\ny
+ 0: x\x0ay
+
+/(a.b(?s)c.d|x.y)p.q/
+    a+bc+dp+q
+ 0: a+bc+dp+q
+    a+bc\ndp+q
+ 0: a+bc\x0adp+q
+    x\nyp+q 
+ 0: x\x0ayp+q
+    *** Failers 
+No match
+    a\nbc\ndp+q
+No match
+    a+bc\ndp\nq
+No match
+    x\nyp\nq 
+No match
+
+/a\d\z/
+    ba0
+ 0: a0
+    *** Failers
+No match
+    ba0\n
+No match
+    ba0\ncd   
+No match
+
+/a\d\z/m
+    ba0
+ 0: a0
+    *** Failers
+No match
+    ba0\n
+No match
+    ba0\ncd   
+No match
+
+/a\d\Z/
+    ba0
+ 0: a0
+    ba0\n
+ 0: a0
+    *** Failers
+No match
+    ba0\ncd   
+No match
+
+/a\d\Z/m
+    ba0
+ 0: a0
+    ba0\n
+ 0: a0
+    *** Failers
+No match
+    ba0\ncd   
+No match
+
+/a\d$/
+    ba0
+ 0: a0
+    ba0\n
+ 0: a0
+    *** Failers
+No match
+    ba0\ncd   
+No match
+
+/a\d$/m
+    ba0
+ 0: a0
+    ba0\n
+ 0: a0
+    ba0\ncd   
+ 0: a0
+    *** Failers
+No match
+
+/abc/i
+    abc
+ 0: abc
+    aBc
+ 0: aBc
+    ABC
+ 0: ABC
+    
+/[^a]/
+    abcd
+ 0: b
+    
+/ab?\w/
+    abz
+ 0: abz
+ 1: ab
+    abbz
+ 0: abb
+ 1: ab
+    azz  
+ 0: az
+
+/x{0,3}yz/
+    ayzq
+ 0: yz
+    axyzq
+ 0: xyz
+    axxyz
+ 0: xxyz
+    axxxyzq
+ 0: xxxyz
+    axxxxyzq
+ 0: xxxyz
+    *** Failers
+No match
+    ax
+No match
+    axx     
+No match
+      
+/x{3}yz/
+    axxxyzq
+ 0: xxxyz
+    axxxxyzq
+ 0: xxxyz
+    *** Failers
+No match
+    ax
+No match
+    axx     
+No match
+    ayzq
+No match
+    axyzq
+No match
+    axxyz
+No match
+      
+/x{2,3}yz/
+    axxyz
+ 0: xxyz
+    axxxyzq
+ 0: xxxyz
+    axxxxyzq
+ 0: xxxyz
+    *** Failers
+No match
+    ax
+No match
+    axx     
+No match
+    ayzq
+No match
+    axyzq
+No match
+      
+/[^a]+/
+    bac
+ 0: b
+    bcdefax
+ 0: bcdef
+ 1: bcde
+ 2: bcd
+ 3: bc
+ 4: b
+    *** Failers
+ 0: *** F
+ 1: *** 
+ 2: ***
+ 3: **
+ 4: *
+    aaaaa   
+No match
+
+/[^a]*/
+    bac
+ 0: b
+ 1: 
+    bcdefax
+ 0: bcdef
+ 1: bcde
+ 2: bcd
+ 3: bc
+ 4: b
+ 5: 
+    *** Failers
+ 0: *** F
+ 1: *** 
+ 2: ***
+ 3: **
+ 4: *
+ 5: 
+    aaaaa   
+ 0: 
+    
+/[^a]{3,5}/
+    xyz
+ 0: xyz
+    awxyza
+ 0: wxyz
+ 1: wxy
+    abcdefa
+ 0: bcdef
+ 1: bcde
+ 2: bcd
+    abcdefghijk
+ 0: bcdef
+ 1: bcde
+ 2: bcd
+    *** Failers
+ 0: *** F
+ 1: *** 
+ 2: ***
+    axya
+No match
+    axa
+No match
+    aaaaa         
+No match
+
+/\d*/
+    1234b567
+ 0: 1234
+ 1: 123
+ 2: 12
+ 3: 1
+ 4: 
+    xyz
+ 0: 
+    
+/\D*/
+    a1234b567
+ 0: a
+ 1: 
+    xyz
+ 0: xyz
+ 1: xy
+ 2: x
+ 3: 
+     
+/\d+/
+    ab1234c56
+ 0: 1234
+ 1: 123
+ 2: 12
+ 3: 1
+    *** Failers
+No match
+    xyz
+No match
+    
+/\D+/
+    ab123c56
+ 0: ab
+ 1: a
+    *** Failers
+ 0: *** Failers
+ 1: *** Failer
+ 2: *** Faile
+ 3: *** Fail
+ 4: *** Fai
+ 5: *** Fa
+ 6: *** F
+ 7: *** 
+ 8: ***
+ 9: **
+10: *
+    789
+No match
+    
+/\d?A/
+    045ABC
+ 0: 5A
+    ABC
+ 0: A
+    *** Failers
+No match
+    XYZ
+No match
+    
+/\D?A/
+    ABC
+ 0: A
+    BAC
+ 0: BA
+    9ABC             
+ 0: A
+    *** Failers
+No match
+
+/a+/
+    aaaa
+ 0: aaaa
+ 1: aaa
+ 2: aa
+ 3: a
+
+/^.*xyz/
+    xyz
+ 0: xyz
+    ggggggggxyz
+ 0: ggggggggxyz
+    
+/^.+xyz/
+    abcdxyz
+ 0: abcdxyz
+    axyz
+ 0: axyz
+    *** Failers
+No match
+    xyz
+No match
+    
+/^.?xyz/
+    xyz
+ 0: xyz
+    cxyz       
+ 0: cxyz
+
+/^\d{2,3}X/
+    12X
+ 0: 12X
+    123X
+ 0: 123X
+    *** Failers
+No match
+    X
+No match
+    1X
+No match
+    1234X     
+No match
+
+/^[abcd]\d/
+    a45
+ 0: a4
+    b93
+ 0: b9
+    c99z
+ 0: c9
+    d04
+ 0: d0
+    *** Failers
+No match
+    e45
+No match
+    abcd      
+No match
+    abcd1234
+No match
+    1234  
+No match
+
+/^[abcd]*\d/
+    a45
+ 0: a4
+    b93
+ 0: b9
+    c99z
+ 0: c9
+    d04
+ 0: d0
+    abcd1234
+ 0: abcd1
+    1234  
+ 0: 1
+    *** Failers
+No match
+    e45
+No match
+    abcd      
+No match
+
+/^[abcd]+\d/
+    a45
+ 0: a4
+    b93
+ 0: b9
+    c99z
+ 0: c9
+    d04
+ 0: d0
+    abcd1234
+ 0: abcd1
+    *** Failers
+No match
+    1234  
+No match
+    e45
+No match
+    abcd      
+No match
+
+/^a+X/
+    aX
+ 0: aX
+    aaX 
+ 0: aaX
+
+/^[abcd]?\d/
+    a45
+ 0: a4
+    b93
+ 0: b9
+    c99z
+ 0: c9
+    d04
+ 0: d0
+    1234  
+ 0: 1
+    *** Failers
+No match
+    abcd1234
+No match
+    e45
+No match
+
+/^[abcd]{2,3}\d/
+    ab45
+ 0: ab4
+    bcd93
+ 0: bcd9
+    *** Failers
+No match
+    1234 
+No match
+    a36 
+No match
+    abcd1234
+No match
+    ee45
+No match
+
+/^(abc)*\d/
+    abc45
+ 0: abc4
+    abcabcabc45
+ 0: abcabcabc4
+    42xyz 
+ 0: 4
+    *** Failers
+No match
+
+/^(abc)+\d/
+    abc45
+ 0: abc4
+    abcabcabc45
+ 0: abcabcabc4
+    *** Failers
+No match
+    42xyz 
+No match
+
+/^(abc)?\d/
+    abc45
+ 0: abc4
+    42xyz 
+ 0: 4
+    *** Failers
+No match
+    abcabcabc45
+No match
+
+/^(abc){2,3}\d/
+    abcabc45
+ 0: abcabc4
+    abcabcabc45
+ 0: abcabcabc4
+    *** Failers
+No match
+    abcabcabcabc45
+No match
+    abc45
+No match
+    42xyz 
+No match
+
+/1(abc|xyz)2(?1)3/
+    1abc2abc3456
+ 0: 1abc2abc3
+    1abc2xyz3456 
+ 0: 1abc2xyz3
+
+/^(a*\w|ab)=(a*\w|ab)/
+    ab=ab
+ 0: ab=ab
+ 1: ab=a
+
+/^(a*\w|ab)=(?1)/
+    ab=ab
+ 0: ab=ab
+ 1: ab=a
+
+/^([^()]|\((?1)*\))*$/
+    abc
+ 0: abc
+    a(b)c
+ 0: a(b)c
+    a(b(c))d  
+ 0: a(b(c))d
+    *** Failers)
+No match
+    a(b(c)d  
+No match
+
+/^>abc>([^()]|\((?1)*\))*<xyz<$/
+    >abc>123<xyz<
+ 0: >abc>123<xyz<
+    >abc>1(2)3<xyz<
+ 0: >abc>1(2)3<xyz<
+    >abc>(1(2)3)<xyz<
+ 0: >abc>(1(2)3)<xyz<
+
+/^(?>a*)\d/
+    aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa9876
+ 0: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa9
+    *** Failers 
+No match
+    aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+No match
+
+/< (?: (?(R) \d++  | [^<>]*+) | (?R)) * >/x
+    <>
+ 0: <>
+    <abcd>
+ 0: <abcd>
+    <abc <123> hij>
+ 0: <abc <123> hij>
+    <abc <def> hij>
+ 0: <def>
+    <abc<>def> 
+ 0: <abc<>def>
+    <abc<>      
+ 0: <>
+    *** Failers
+No match
+    <abc
+No match
+
+/^(?(?=abc)\w{3}:|\d\d)$/        
+    abc:                          
+ 0: abc:
+    12                             
+ 0: 12
+    *** Failers                     
+No match
+    123                       
+No match
+    xyz                        
+No match
+                                
+/^(?(?!abc)\d\d|\w{3}:)$/      
+    abc:                        
+ 0: abc:
+    12         
+ 0: 12
+    *** Failers
+No match
+    123
+No match
+    xyz    
+No match
+
+/^(?=abc)\w{5}:$/        
+    abcde:                          
+ 0: abcde:
+    *** Failers                     
+No match
+    abc.. 
+No match
+    123                       
+No match
+    vwxyz                        
+No match
+                                
+/^(?!abc)\d\d$/      
+    12         
+ 0: 12
+    *** Failers
+No match
+    abcde:
+No match
+    abc..  
+No match
+    123
+No match
+    vwxyz    
+No match
+
+/(?<=abc|xy)123/
+    abc12345
+ 0: 123
+    wxy123z
+ 0: 123
+    *** Failers
+No match
+    123abc
+No match
+
+/(?<!abc|xy)123/
+    123abc
+ 0: 123
+    mno123456 
+ 0: 123
+    *** Failers
+No match
+    abc12345
+No match
+    wxy123z
+No match
+
+/abc(?C1)xyz/
+    abcxyz
+--->abcxyz
+  1 ^  ^       x
+ 0: abcxyz
+    123abcxyz999 
+--->123abcxyz999
+  1    ^  ^          x
+ 0: abcxyz
+
+/(ab|cd){3,4}/C
+  ababab
+--->ababab
+ +0 ^          (ab|cd){3,4}
+ +1 ^          a
+ +4 ^          c
+ +2 ^^         b
+ +3 ^ ^        |
+ +1 ^ ^        a
+ +4 ^ ^        c
+ +2 ^  ^       b
+ +3 ^   ^      |
+ +1 ^   ^      a
+ +4 ^   ^      c
+ +2 ^    ^     b
+ +3 ^     ^    |
++12 ^     ^    
+ +1 ^     ^    a
+ +4 ^     ^    c
+ 0: ababab
+  abcdabcd
+--->abcdabcd
+ +0 ^            (ab|cd){3,4}
+ +1 ^            a
+ +4 ^            c
+ +2 ^^           b
+ +3 ^ ^          |
+ +1 ^ ^          a
+ +4 ^ ^          c
+ +5 ^  ^         d
+ +6 ^   ^        )
+ +1 ^   ^        a
+ +4 ^   ^        c
+ +2 ^    ^       b
+ +3 ^     ^      |
++12 ^     ^      
+ +1 ^     ^      a
+ +4 ^     ^      c
+ +5 ^      ^     d
+ +6 ^       ^    )
++12 ^       ^    
+ 0: abcdabcd
+ 1: abcdab
+  abcdcdcdcdcd  
+--->abcdcdcdcdcd
+ +0 ^                (ab|cd){3,4}
+ +1 ^                a
+ +4 ^                c
+ +2 ^^               b
+ +3 ^ ^              |
+ +1 ^ ^              a
+ +4 ^ ^              c
+ +5 ^  ^             d
+ +6 ^   ^            )
+ +1 ^   ^            a
+ +4 ^   ^            c
+ +5 ^    ^           d
+ +6 ^     ^          )
++12 ^     ^          
+ +1 ^     ^          a
+ +4 ^     ^          c
+ +5 ^      ^         d
+ +6 ^       ^        )
++12 ^       ^        
+ 0: abcdcdcd
+ 1: abcdcd
+
+/^abc/
+    abcdef
+ 0: abc
+    *** Failers
+No match
+    abcdef\B  
+No match
+
+/^(a*|xyz)/
+    bcd
+ 0: 
+    aaabcd
+ 0: aaa
+ 1: aa
+ 2: a
+ 3: 
+    xyz
+ 0: xyz
+ 1: 
+    xyz\N  
+ 0: xyz
+    *** Failers
+ 0: 
+    bcd\N   
+No match
+    
+/xyz$/
+    xyz
+ 0: xyz
+    xyz\n
+ 0: xyz
+    *** Failers
+No match
+    xyz\Z
+No match
+    xyz\n\Z    
+No match
+    
+/xyz$/m
+    xyz
+ 0: xyz
+    xyz\n 
+ 0: xyz
+    abcxyz\npqr 
+ 0: xyz
+    abcxyz\npqr\Z 
+ 0: xyz
+    xyz\n\Z    
+ 0: xyz
+    *** Failers
+No match
+    xyz\Z
+No match
+
+/\Gabc/
+    abcdef
+ 0: abc
+    defabcxyz\>3 
+ 0: abc
+    *** Failers 
+No match
+    defabcxyz
+No match
+
+/^abcdef/
+    ab\P
+Partial match: ab
+    abcde\P
+Partial match: abcde
+    abcdef\P
+ 0: abcdef
+    *** Failers
+No match
+    abx\P    
+No match
+
+/^a{2,4}\d+z/
+    a\P
+Partial match: a
+    aa\P
+Partial match: aa
+    aa2\P 
+Partial match: aa2
+    aaa\P
+Partial match: aaa
+    aaa23\P 
+Partial match: aaa23
+    aaaa12345\P
+Partial match: aaaa12345
+    aa0z\P
+ 0: aa0z
+    aaaa4444444444444z\P 
+ 0: aaaa4444444444444z
+    *** Failers
+No match
+    az\P 
+No match
+    aaaaa\P 
+No match
+    a56\P 
+No match
+
+/^abcdef/
+   abc\P
+Partial match: abc
+   def\R 
+ 0: def
+   
+/(?<=foo)bar/
+   xyzfo\P 
+No match
+   foob\P\>2 
+Partial match: foob
+   foobar...\R\P\>4 
+ 0: ar
+   xyzfo\P
+No match
+   foobar\>2  
+ 0: bar
+   *** Failers
+No match
+   xyzfo\P
+No match
+   obar\R   
+No match
+
+/(ab*(cd|ef))+X/
+    adfadadaklhlkalkajhlkjahdfasdfasdfladsfjkj\P\Z
+No match
+    lkjhlkjhlkjhlkjhabbbbbbcdaefabbbbbbbefa\P\B\Z
+Partial match: abbbbbbcdaefabbbbbbbefa
+    cdabbbbbbbb\P\R\B\Z
+Partial match: cdabbbbbbbb
+    efabbbbbbbbbbbbbbbb\P\R\B\Z
+Partial match: efabbbbbbbbbbbbbbbb
+    bbbbbbbbbbbbcdXyasdfadf\P\R\B\Z    
+ 0: bbbbbbbbbbbbcdX
+
+/(a|b)/SF>testsavedregex
+Compiled pattern written to testsavedregex
+Study data written to testsavedregex
+<testsavedregex
+Compiled pattern (byte-inverted) loaded from testsavedregex
+Study data loaded from testsavedregex
+    abc
+ 0: a
+    ** Failers
+ 0: a
+    def  
+No match
+    
+/the quick brown fox/
+    the quick brown fox
+ 0: the quick brown fox
+    The quick brown FOX
+No match
+    What do you know about the quick brown fox?
+ 0: the quick brown fox
+    What do you know about THE QUICK BROWN FOX?
+No match
+
+/The quick brown fox/i
+    the quick brown fox
+ 0: the quick brown fox
+    The quick brown FOX
+ 0: The quick brown FOX
+    What do you know about the quick brown fox?
+ 0: the quick brown fox
+    What do you know about THE QUICK BROWN FOX?
+ 0: THE QUICK BROWN FOX
+
+/abcd\t\n\r\f\a\e\071\x3b\$\\\?caxyz/
+    abcd\t\n\r\f\a\e9;\$\\?caxyz
+ 0: abcd\x09\x0a\x0d\x0c\x07\x1b9;$\?caxyz
+
+/a*abc?xyz+pqr{3}ab{2,}xy{4,5}pq{0,6}AB{0,}zz/
+    abxyzpqrrrabbxyyyypqAzz
+ 0: abxyzpqrrrabbxyyyypqAzz
+    abxyzpqrrrabbxyyyypqAzz
+ 0: abxyzpqrrrabbxyyyypqAzz
+    aabxyzpqrrrabbxyyyypqAzz
+ 0: aabxyzpqrrrabbxyyyypqAzz
+    aaabxyzpqrrrabbxyyyypqAzz
+ 0: aaabxyzpqrrrabbxyyyypqAzz
+    aaaabxyzpqrrrabbxyyyypqAzz
+ 0: aaaabxyzpqrrrabbxyyyypqAzz
+    abcxyzpqrrrabbxyyyypqAzz
+ 0: abcxyzpqrrrabbxyyyypqAzz
+    aabcxyzpqrrrabbxyyyypqAzz
+ 0: aabcxyzpqrrrabbxyyyypqAzz
+    aaabcxyzpqrrrabbxyyyypAzz
+ 0: aaabcxyzpqrrrabbxyyyypAzz
+    aaabcxyzpqrrrabbxyyyypqAzz
+ 0: aaabcxyzpqrrrabbxyyyypqAzz
+    aaabcxyzpqrrrabbxyyyypqqAzz
+ 0: aaabcxyzpqrrrabbxyyyypqqAzz
+    aaabcxyzpqrrrabbxyyyypqqqAzz
+ 0: aaabcxyzpqrrrabbxyyyypqqqAzz
+    aaabcxyzpqrrrabbxyyyypqqqqAzz
+ 0: aaabcxyzpqrrrabbxyyyypqqqqAzz
+    aaabcxyzpqrrrabbxyyyypqqqqqAzz
+ 0: aaabcxyzpqrrrabbxyyyypqqqqqAzz
+    aaabcxyzpqrrrabbxyyyypqqqqqqAzz
+ 0: aaabcxyzpqrrrabbxyyyypqqqqqqAzz
+    aaaabcxyzpqrrrabbxyyyypqAzz
+ 0: aaaabcxyzpqrrrabbxyyyypqAzz
+    abxyzzpqrrrabbxyyyypqAzz
+ 0: abxyzzpqrrrabbxyyyypqAzz
+    aabxyzzzpqrrrabbxyyyypqAzz
+ 0: aabxyzzzpqrrrabbxyyyypqAzz
+    aaabxyzzzzpqrrrabbxyyyypqAzz
+ 0: aaabxyzzzzpqrrrabbxyyyypqAzz
+    aaaabxyzzzzpqrrrabbxyyyypqAzz
+ 0: aaaabxyzzzzpqrrrabbxyyyypqAzz
+    abcxyzzpqrrrabbxyyyypqAzz
+ 0: abcxyzzpqrrrabbxyyyypqAzz
+    aabcxyzzzpqrrrabbxyyyypqAzz
+ 0: aabcxyzzzpqrrrabbxyyyypqAzz
+    aaabcxyzzzzpqrrrabbxyyyypqAzz
+ 0: aaabcxyzzzzpqrrrabbxyyyypqAzz
+    aaaabcxyzzzzpqrrrabbxyyyypqAzz
+ 0: aaaabcxyzzzzpqrrrabbxyyyypqAzz
+    aaaabcxyzzzzpqrrrabbbxyyyypqAzz
+ 0: aaaabcxyzzzzpqrrrabbbxyyyypqAzz
+    aaaabcxyzzzzpqrrrabbbxyyyyypqAzz
+ 0: aaaabcxyzzzzpqrrrabbbxyyyyypqAzz
+    aaabcxyzpqrrrabbxyyyypABzz
+ 0: aaabcxyzpqrrrabbxyyyypABzz
+    aaabcxyzpqrrrabbxyyyypABBzz
+ 0: aaabcxyzpqrrrabbxyyyypABBzz
+    >>>aaabxyzpqrrrabbxyyyypqAzz
+ 0: aaabxyzpqrrrabbxyyyypqAzz
+    >aaaabxyzpqrrrabbxyyyypqAzz
+ 0: aaaabxyzpqrrrabbxyyyypqAzz
+    >>>>abcxyzpqrrrabbxyyyypqAzz
+ 0: abcxyzpqrrrabbxyyyypqAzz
+    *** Failers
+No match
+    abxyzpqrrabbxyyyypqAzz
+No match
+    abxyzpqrrrrabbxyyyypqAzz
+No match
+    abxyzpqrrrabxyyyypqAzz
+No match
+    aaaabcxyzzzzpqrrrabbbxyyyyyypqAzz
+No match
+    aaaabcxyzzzzpqrrrabbbxyyypqAzz
+No match
+    aaabcxyzpqrrrabbxyyyypqqqqqqqAzz
+No match
+
+/^(abc){1,2}zz/
+    abczz
+ 0: abczz
+    abcabczz
+ 0: abcabczz
+    *** Failers
+No match
+    zz
+No match
+    abcabcabczz
+No match
+    >>abczz
+No match
+
+/^(b+?|a){1,2}?c/
+    bc
+ 0: bc
+    bbc
+ 0: bbc
+    bbbc
+ 0: bbbc
+    bac
+ 0: bac
+    bbac
+ 0: bbac
+    aac
+ 0: aac
+    abbbbbbbbbbbc
+ 0: abbbbbbbbbbbc
+    bbbbbbbbbbbac
+ 0: bbbbbbbbbbbac
+    *** Failers
+No match
+    aaac
+No match
+    abbbbbbbbbbbac
+No match
+
+/^(b+|a){1,2}c/
+    bc
+ 0: bc
+    bbc
+ 0: bbc
+    bbbc
+ 0: bbbc
+    bac
+ 0: bac
+    bbac
+ 0: bbac
+    aac
+ 0: aac
+    abbbbbbbbbbbc
+ 0: abbbbbbbbbbbc
+    bbbbbbbbbbbac
+ 0: bbbbbbbbbbbac
+    *** Failers
+No match
+    aaac
+No match
+    abbbbbbbbbbbac
+No match
+
+/^(b+|a){1,2}?bc/
+    bbc
+ 0: bbc
+
+/^(b*|ba){1,2}?bc/
+    babc
+ 0: babc
+    bbabc
+ 0: bbabc
+    bababc
+ 0: bababc
+    *** Failers
+No match
+    bababbc
+No match
+    babababc
+No match
+
+/^(ba|b*){1,2}?bc/
+    babc
+ 0: babc
+    bbabc
+ 0: bbabc
+    bababc
+ 0: bababc
+    *** Failers
+No match
+    bababbc
+No match
+    babababc
+No match
+
+/^\ca\cA\c[\c{\c:/
+    \x01\x01\e;z
+ 0: \x01\x01\x1b;z
+
+/^[ab\]cde]/
+    athing
+ 0: a
+    bthing
+ 0: b
+    ]thing
+ 0: ]
+    cthing
+ 0: c
+    dthing
+ 0: d
+    ething
+ 0: e
+    *** Failers
+No match
+    fthing
+No match
+    [thing
+No match
+    \\thing
+No match
+
+/^[]cde]/
+    ]thing
+ 0: ]
+    cthing
+ 0: c
+    dthing
+ 0: d
+    ething
+ 0: e
+    *** Failers
+No match
+    athing
+No match
+    fthing
+No match
+
+/^[^ab\]cde]/
+    fthing
+ 0: f
+    [thing
+ 0: [
+    \\thing
+ 0: \
+    *** Failers
+ 0: *
+    athing
+No match
+    bthing
+No match
+    ]thing
+No match
+    cthing
+No match
+    dthing
+No match
+    ething
+No match
+
+/^[^]cde]/
+    athing
+ 0: a
+    fthing
+ 0: f
+    *** Failers
+ 0: *
+    ]thing
+No match
+    cthing
+No match
+    dthing
+No match
+    ething
+No match
+
+/^\�/
+    �
+ 0: \x81
+
+/^ÿ/
+    ÿ
+ 0: \xff
+
+/^[0-9]+$/
+    0
+ 0: 0
+    1
+ 0: 1
+    2
+ 0: 2
+    3
+ 0: 3
+    4
+ 0: 4
+    5
+ 0: 5
+    6
+ 0: 6
+    7
+ 0: 7
+    8
+ 0: 8
+    9
+ 0: 9
+    10
+ 0: 10
+    100
+ 0: 100
+    *** Failers
+No match
+    abc
+No match
+
+/^.*nter/
+    enter
+ 0: enter
+    inter
+ 0: inter
+    uponter
+ 0: uponter
+
+/^xxx[0-9]+$/
+    xxx0
+ 0: xxx0
+    xxx1234
+ 0: xxx1234
+    *** Failers
+No match
+    xxx
+No match
+
+/^.+[0-9][0-9][0-9]$/
+    x123
+ 0: x123
+    xx123
+ 0: xx123
+    123456
+ 0: 123456
+    *** Failers
+No match
+    123
+No match
+    x1234
+ 0: x1234
+
+/^.+?[0-9][0-9][0-9]$/
+    x123
+ 0: x123
+    xx123
+ 0: xx123
+    123456
+ 0: 123456
+    *** Failers
+No match
+    123
+No match
+    x1234
+ 0: x1234
+
+/^([^!]+)!(.+)=apquxz\.ixr\.zzz\.ac\.uk$/
+    abc!pqr=apquxz.ixr.zzz.ac.uk
+ 0: abc!pqr=apquxz.ixr.zzz.ac.uk
+    *** Failers
+No match
+    !pqr=apquxz.ixr.zzz.ac.uk
+No match
+    abc!=apquxz.ixr.zzz.ac.uk
+No match
+    abc!pqr=apquxz:ixr.zzz.ac.uk
+No match
+    abc!pqr=apquxz.ixr.zzz.ac.ukk
+No match
+
+/:/
+    Well, we need a colon: somewhere
+ 0: :
+    *** Fail if we don't
+No match
+
+/([\da-f:]+)$/i
+    0abc
+ 0: 0abc
+    abc
+ 0: abc
+    fed
+ 0: fed
+    E
+ 0: E
+    ::
+ 0: ::
+    5f03:12C0::932e
+ 0: 5f03:12C0::932e
+    fed def
+ 0: def
+    Any old stuff
+ 0: ff
+    *** Failers
+No match
+    0zzz
+No match
+    gzzz
+No match
+    fed\x20
+No match
+    Any old rubbish
+No match
+
+/^.*\.(\d{1,3})\.(\d{1,3})\.(\d{1,3})$/
+    .1.2.3
+ 0: .1.2.3
+    A.12.123.0
+ 0: A.12.123.0
+    *** Failers
+No match
+    .1.2.3333
+No match
+    1.2.3
+No match
+    1234.2.3
+No match
+
+/^(\d+)\s+IN\s+SOA\s+(\S+)\s+(\S+)\s*\(\s*$/
+    1 IN SOA non-sp1 non-sp2(
+ 0: 1 IN SOA non-sp1 non-sp2(
+    1    IN    SOA    non-sp1    non-sp2   (
+ 0: 1    IN    SOA    non-sp1    non-sp2   (
+    *** Failers
+No match
+    1IN SOA non-sp1 non-sp2(
+No match
+
+/^[a-zA-Z\d][a-zA-Z\d\-]*(\.[a-zA-Z\d][a-zA-z\d\-]*)*\.$/
+    a.
+ 0: a.
+    Z.
+ 0: Z.
+    2.
+ 0: 2.
+    ab-c.pq-r.
+ 0: ab-c.pq-r.
+    sxk.zzz.ac.uk.
+ 0: sxk.zzz.ac.uk.
+    x-.y-.
+ 0: x-.y-.
+    *** Failers
+No match
+    -abc.peq.
+No match
+
+/^\*\.[a-z]([a-z\-\d]*[a-z\d]+)?(\.[a-z]([a-z\-\d]*[a-z\d]+)?)*$/
+    *.a
+ 0: *.a
+    *.b0-a
+ 0: *.b0-a
+    *.c3-b.c
+ 0: *.c3-b.c
+    *.c-a.b-c
+ 0: *.c-a.b-c
+    *** Failers
+No match
+    *.0
+No match
+    *.a-
+No match
+    *.a-b.c-
+No match
+    *.c-a.0-c
+No match
+
+/^(?=ab(de))(abd)(e)/
+    abde
+ 0: abde
+
+/^(?!(ab)de|x)(abd)(f)/
+    abdf
+ 0: abdf
+
+/^(?=(ab(cd)))(ab)/
+    abcd
+ 0: ab
+
+/^[\da-f](\.[\da-f])*$/i
+    a.b.c.d
+ 0: a.b.c.d
+    A.B.C.D
+ 0: A.B.C.D
+    a.b.c.1.2.3.C
+ 0: a.b.c.1.2.3.C
+
+/^\".*\"\s*(;.*)?$/
+    \"1234\"
+ 0: "1234"
+    \"abcd\" ;
+ 0: "abcd" ;
+    \"\" ; rhubarb
+ 0: "" ; rhubarb
+    *** Failers
+No match
+    \"1234\" : things
+No match
+
+/^$/
+    \
+ 0: 
+    *** Failers
+No match
+
+/   ^    a   (?# begins with a)  b\sc (?# then b c) $ (?# then end)/x
+    ab c
+ 0: ab c
+    *** Failers
+No match
+    abc
+No match
+    ab cde
+No match
+
+/(?x)   ^    a   (?# begins with a)  b\sc (?# then b c) $ (?# then end)/
+    ab c
+ 0: ab c
+    *** Failers
+No match
+    abc
+No match
+    ab cde
+No match
+
+/^   a\ b[c ]d       $/x
+    a bcd
+ 0: a bcd
+    a b d
+ 0: a b d
+    *** Failers
+No match
+    abcd
+No match
+    ab d
+No match
+
+/^(a(b(c)))(d(e(f)))(h(i(j)))(k(l(m)))$/
+    abcdefhijklm
+ 0: abcdefhijklm
+
+/^(?:a(b(c)))(?:d(e(f)))(?:h(i(j)))(?:k(l(m)))$/
+    abcdefhijklm
+ 0: abcdefhijklm
+
+/^[\w][\W][\s][\S][\d][\D][\b][\n][\c]][\022]/
+    a+ Z0+\x08\n\x1d\x12
+ 0: a+ Z0+\x08\x0a\x1d\x12
+
+/^[.^$|()*+?{,}]+/
+    .^\$(*+)|{?,?}
+ 0: .^$(*+)|{?,?}
+ 1: .^$(*+)|{?,?
+ 2: .^$(*+)|{?,
+ 3: .^$(*+)|{?
+ 4: .^$(*+)|{
+ 5: .^$(*+)|
+ 6: .^$(*+)
+ 7: .^$(*+
+ 8: .^$(*
+ 9: .^$(
+10: .^$
+11: .^
+12: .
+
+/^a*\w/
+    z
+ 0: z
+    az
+ 0: az
+ 1: a
+    aaaz
+ 0: aaaz
+ 1: aaa
+ 2: aa
+ 3: a
+    a
+ 0: a
+    aa
+ 0: aa
+ 1: a
+    aaaa
+ 0: aaaa
+ 1: aaa
+ 2: aa
+ 3: a
+    a+
+ 0: a
+    aa+
+ 0: aa
+ 1: a
+
+/^a*?\w/
+    z
+ 0: z
+    az
+ 0: az
+ 1: a
+    aaaz
+ 0: aaaz
+ 1: aaa
+ 2: aa
+ 3: a
+    a
+ 0: a
+    aa
+ 0: aa
+ 1: a
+    aaaa
+ 0: aaaa
+ 1: aaa
+ 2: aa
+ 3: a
+    a+
+ 0: a
+    aa+
+ 0: aa
+ 1: a
+
+/^a+\w/
+    az
+ 0: az
+    aaaz
+ 0: aaaz
+ 1: aaa
+ 2: aa
+    aa
+ 0: aa
+    aaaa
+ 0: aaaa
+ 1: aaa
+ 2: aa
+    aa+
+ 0: aa
+
+/^a+?\w/
+    az
+ 0: az
+    aaaz
+ 0: aaaz
+ 1: aaa
+ 2: aa
+    aa
+ 0: aa
+    aaaa
+ 0: aaaa
+ 1: aaa
+ 2: aa
+    aa+
+ 0: aa
+
+/^\d{8}\w{2,}/
+    1234567890
+ 0: 1234567890
+    12345678ab
+ 0: 12345678ab
+    12345678__
+ 0: 12345678__
+    *** Failers
+No match
+    1234567
+No match
+
+/^[aeiou\d]{4,5}$/
+    uoie
+ 0: uoie
+    1234
+ 0: 1234
+    12345
+ 0: 12345
+    aaaaa
+ 0: aaaaa
+    *** Failers
+No match
+    123456
+No match
+
+/^[aeiou\d]{4,5}?/
+    uoie
+ 0: uoie
+    1234
+ 0: 1234
+    12345
+ 0: 12345
+ 1: 1234
+    aaaaa
+ 0: aaaaa
+ 1: aaaa
+    123456
+ 0: 12345
+ 1: 1234
+
+/^From +([^ ]+) +[a-zA-Z][a-zA-Z][a-zA-Z] +[a-zA-Z][a-zA-Z][a-zA-Z] +[0-9]?[0-9] +[0-9][0-9]:[0-9][0-9]/
+    From abcd  Mon Sep 01 12:33:02 1997
+ 0: From abcd  Mon Sep 01 12:33
+
+/^From\s+\S+\s+([a-zA-Z]{3}\s+){2}\d{1,2}\s+\d\d:\d\d/
+    From abcd  Mon Sep 01 12:33:02 1997
+ 0: From abcd  Mon Sep 01 12:33
+    From abcd  Mon Sep  1 12:33:02 1997
+ 0: From abcd  Mon Sep  1 12:33
+    *** Failers
+No match
+    From abcd  Sep 01 12:33:02 1997
+No match
+
+/^12.34/s
+    12\n34
+ 0: 12\x0a34
+    12\r34
+ 0: 12\x0d34
+
+/\w+(?=\t)/
+    the quick brown\t fox
+ 0: brown
+
+/foo(?!bar)(.*)/
+    foobar is foolish see?
+ 0: foolish see?
+ 1: foolish see
+ 2: foolish se
+ 3: foolish s
+ 4: foolish 
+ 5: foolish
+ 6: foolis
+ 7: fooli
+ 8: fool
+ 9: foo
+
+/(?:(?!foo)...|^.{0,2})bar(.*)/
+    foobar crowbar etc
+ 0: rowbar etc
+ 1: rowbar et
+ 2: rowbar e
+ 3: rowbar 
+ 4: rowbar
+    barrel
+ 0: barrel
+ 1: barre
+ 2: barr
+ 3: bar
+    2barrel
+ 0: 2barrel
+ 1: 2barre
+ 2: 2barr
+ 3: 2bar
+    A barrel
+ 0: A barrel
+ 1: A barre
+ 2: A barr
+ 3: A bar
+
+/^(\D*)(?=\d)(?!123)/
+    abc456
+ 0: abc
+    *** Failers
+No match
+    abc123
+No match
+
+/^1234(?# test newlines
+  inside)/
+    1234
+ 0: 1234
+
+/^1234 #comment in extended re
+  /x
+    1234
+ 0: 1234
+
+/#rhubarb
+  abcd/x
+    abcd
+ 0: abcd
+
+/^abcd#rhubarb/x
+    abcd
+ 0: abcd
+
+/(?!^)abc/
+    the abc
+ 0: abc
+    *** Failers
+No match
+    abc
+No match
+
+/(?=^)abc/
+    abc
+ 0: abc
+    *** Failers
+No match
+    the abc
+No match
+
+/^[ab]{1,3}(ab*|b)/
+    aabbbbb
+ 0: aabbbbb
+ 1: aabbbb
+ 2: aabbb
+ 3: aabb
+ 4: aab
+ 5: aa
+
+/^[ab]{1,3}?(ab*|b)/
+    aabbbbb
+ 0: aabbbbb
+ 1: aabbbb
+ 2: aabbb
+ 3: aabb
+ 4: aab
+ 5: aa
+
+/^[ab]{1,3}?(ab*?|b)/
+    aabbbbb
+ 0: aabbbbb
+ 1: aabbbb
+ 2: aabbb
+ 3: aabb
+ 4: aab
+ 5: aa
+
+/^[ab]{1,3}(ab*?|b)/
+    aabbbbb
+ 0: aabbbbb
+ 1: aabbbb
+ 2: aabbb
+ 3: aabb
+ 4: aab
+ 5: aa
+
+/  (?: [\040\t] |  \(
+(?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  |  \( (?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  )* \)  )*
+\)  )*                          # optional leading comment
+(?:    (?:
+[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+    # some number of atom characters...
+(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom
+|
+" (?:                      # opening quote...
+[^\\\x80-\xff\n\015"]                #   Anything except backslash and quote
+|                     #    or
+\\ [^\x80-\xff]           #   Escaped something (something != CR)
+)* "  # closing quote
+)                    # initial word
+(?:  (?: [\040\t] |  \(
+(?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  |  \( (?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  )* \)  )*
+\)  )*  \.  (?: [\040\t] |  \(
+(?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  |  \( (?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  )* \)  )*
+\)  )*   (?:
+[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+    # some number of atom characters...
+(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom
+|
+" (?:                      # opening quote...
+[^\\\x80-\xff\n\015"]                #   Anything except backslash and quote
+|                     #    or
+\\ [^\x80-\xff]           #   Escaped something (something != CR)
+)* "  # closing quote
+)  )* # further okay, if led by a period
+(?: [\040\t] |  \(
+(?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  |  \( (?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  )* \)  )*
+\)  )*  @  (?: [\040\t] |  \(
+(?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  |  \( (?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  )* \)  )*
+\)  )*    (?:
+[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+    # some number of atom characters...
+(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom
+|   \[                         # [
+(?: [^\\\x80-\xff\n\015\[\]] |  \\ [^\x80-\xff]  )*    #    stuff
+\]                        #           ]
+)                           # initial subdomain
+(?:                                  #
+(?: [\040\t] |  \(
+(?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  |  \( (?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  )* \)  )*
+\)  )*  \.                        # if led by a period...
+(?: [\040\t] |  \(
+(?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  |  \( (?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  )* \)  )*
+\)  )*   (?:
+[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+    # some number of atom characters...
+(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom
+|   \[                         # [
+(?: [^\\\x80-\xff\n\015\[\]] |  \\ [^\x80-\xff]  )*    #    stuff
+\]                        #           ]
+)                     #   ...further okay
+)*
+# address
+|                     #  or
+(?:
+[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+    # some number of atom characters...
+(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom
+|
+" (?:                      # opening quote...
+[^\\\x80-\xff\n\015"]                #   Anything except backslash and quote
+|                     #    or
+\\ [^\x80-\xff]           #   Escaped something (something != CR)
+)* "  # closing quote
+)             # one word, optionally followed by....
+(?:
+[^()<>@,;:".\\\[\]\x80-\xff\000-\010\012-\037]  |  # atom and space parts, or...
+\(
+(?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  |  \( (?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  )* \)  )*
+\)       |  # comments, or...
+
+" (?:                      # opening quote...
+[^\\\x80-\xff\n\015"]                #   Anything except backslash and quote
+|                     #    or
+\\ [^\x80-\xff]           #   Escaped something (something != CR)
+)* "  # closing quote
+# quoted strings
+)*
+<  (?: [\040\t] |  \(
+(?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  |  \( (?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  )* \)  )*
+\)  )*                     # leading <
+(?:  @  (?: [\040\t] |  \(
+(?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  |  \( (?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  )* \)  )*
+\)  )*    (?:
+[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+    # some number of atom characters...
+(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom
+|   \[                         # [
+(?: [^\\\x80-\xff\n\015\[\]] |  \\ [^\x80-\xff]  )*    #    stuff
+\]                        #           ]
+)                           # initial subdomain
+(?:                                  #
+(?: [\040\t] |  \(
+(?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  |  \( (?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  )* \)  )*
+\)  )*  \.                        # if led by a period...
+(?: [\040\t] |  \(
+(?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  |  \( (?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  )* \)  )*
+\)  )*   (?:
+[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+    # some number of atom characters...
+(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom
+|   \[                         # [
+(?: [^\\\x80-\xff\n\015\[\]] |  \\ [^\x80-\xff]  )*    #    stuff
+\]                        #           ]
+)                     #   ...further okay
+)*
+
+(?:  (?: [\040\t] |  \(
+(?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  |  \( (?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  )* \)  )*
+\)  )*  ,  (?: [\040\t] |  \(
+(?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  |  \( (?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  )* \)  )*
+\)  )*  @  (?: [\040\t] |  \(
+(?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  |  \( (?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  )* \)  )*
+\)  )*    (?:
+[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+    # some number of atom characters...
+(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom
+|   \[                         # [
+(?: [^\\\x80-\xff\n\015\[\]] |  \\ [^\x80-\xff]  )*    #    stuff
+\]                        #           ]
+)                           # initial subdomain
+(?:                                  #
+(?: [\040\t] |  \(
+(?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  |  \( (?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  )* \)  )*
+\)  )*  \.                        # if led by a period...
+(?: [\040\t] |  \(
+(?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  |  \( (?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  )* \)  )*
+\)  )*   (?:
+[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+    # some number of atom characters...
+(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom
+|   \[                         # [
+(?: [^\\\x80-\xff\n\015\[\]] |  \\ [^\x80-\xff]  )*    #    stuff
+\]                        #           ]
+)                     #   ...further okay
+)*
+)* # further okay, if led by comma
+:                                # closing colon
+(?: [\040\t] |  \(
+(?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  |  \( (?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  )* \)  )*
+\)  )*  )? #       optional route
+(?:
+[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+    # some number of atom characters...
+(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom
+|
+" (?:                      # opening quote...
+[^\\\x80-\xff\n\015"]                #   Anything except backslash and quote
+|                     #    or
+\\ [^\x80-\xff]           #   Escaped something (something != CR)
+)* "  # closing quote
+)                    # initial word
+(?:  (?: [\040\t] |  \(
+(?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  |  \( (?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  )* \)  )*
+\)  )*  \.  (?: [\040\t] |  \(
+(?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  |  \( (?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  )* \)  )*
+\)  )*   (?:
+[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+    # some number of atom characters...
+(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom
+|
+" (?:                      # opening quote...
+[^\\\x80-\xff\n\015"]                #   Anything except backslash and quote
+|                     #    or
+\\ [^\x80-\xff]           #   Escaped something (something != CR)
+)* "  # closing quote
+)  )* # further okay, if led by a period
+(?: [\040\t] |  \(
+(?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  |  \( (?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  )* \)  )*
+\)  )*  @  (?: [\040\t] |  \(
+(?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  |  \( (?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  )* \)  )*
+\)  )*    (?:
+[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+    # some number of atom characters...
+(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom
+|   \[                         # [
+(?: [^\\\x80-\xff\n\015\[\]] |  \\ [^\x80-\xff]  )*    #    stuff
+\]                        #           ]
+)                           # initial subdomain
+(?:                                  #
+(?: [\040\t] |  \(
+(?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  |  \( (?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  )* \)  )*
+\)  )*  \.                        # if led by a period...
+(?: [\040\t] |  \(
+(?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  |  \( (?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  )* \)  )*
+\)  )*   (?:
+[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+    # some number of atom characters...
+(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom
+|   \[                         # [
+(?: [^\\\x80-\xff\n\015\[\]] |  \\ [^\x80-\xff]  )*    #    stuff
+\]                        #           ]
+)                     #   ...further okay
+)*
+#       address spec
+(?: [\040\t] |  \(
+(?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  |  \( (?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  )* \)  )*
+\)  )*  > #                  trailing >
+# name and address
+)  (?: [\040\t] |  \(
+(?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  |  \( (?:  [^\\\x80-\xff\n\015()]  |  \\ [^\x80-\xff]  )* \)  )*
+\)  )*                       # optional trailing comment
+/x
+    Alan Other <user\@dom.ain>
+ 0: Alan Other <user@dom.ain>
+    <user\@dom.ain>
+ 0: user@dom.ain
+ 1: user@dom
+    user\@dom.ain
+ 0: user@dom.ain
+ 1: user@dom
+    \"A. Other\" <user.1234\@dom.ain> (a comment)
+ 0: "A. Other" <user.1234@dom.ain> (a comment)
+ 1: "A. Other" <user.1234@dom.ain> 
+ 2: "A. Other" <user.1234@dom.ain>
+    A. Other <user.1234\@dom.ain> (a comment)
+ 0:  Other <user.1234@dom.ain> (a comment)
+ 1:  Other <user.1234@dom.ain> 
+ 2:  Other <user.1234@dom.ain>
+    \"/s=user/ou=host/o=place/prmd=uu.yy/admd= /c=gb/\"\@x400-re.lay
+ 0: "/s=user/ou=host/o=place/prmd=uu.yy/admd= /c=gb/"@x400-re.lay
+ 1: "/s=user/ou=host/o=place/prmd=uu.yy/admd= /c=gb/"@x400-re
+    A missing angle <user\@some.where
+ 0: user@some.where
+ 1: user@some
+    *** Failers
+No match
+    The quick brown fox
+No match
+
+/[\040\t]*                    # Nab whitespace.
+(?:
+\(                              #  (
+[^\\\x80-\xff\n\015()] *                             #     normal*
+(?:                                 #       (
+(?:  \\ [^\x80-\xff]  |
+\(                            #  (
+[^\\\x80-\xff\n\015()] *                            #     normal*
+(?:  \\ [^\x80-\xff]   [^\\\x80-\xff\n\015()] * )*        #     (special normal*)*
+\)                           #                       )
+)    #         special
+[^\\\x80-\xff\n\015()] *                         #         normal*
+)*                                  #            )*
+\)                             #                )
+[\040\t]* )*    # If comment found, allow more spaces.
+# optional leading comment
+(?:
+(?:
+[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+    # some number of atom characters...
+(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom
+# Atom
+|                       #  or
+"                                     # "
+[^\\\x80-\xff\n\015"] *                            #   normal
+(?:  \\ [^\x80-\xff]  [^\\\x80-\xff\n\015"] * )*        #   ( special normal* )*
+"                                     #        "
+# Quoted string
+)
+[\040\t]*                    # Nab whitespace.
+(?:
+\(                              #  (
+[^\\\x80-\xff\n\015()] *                             #     normal*
+(?:                                 #       (
+(?:  \\ [^\x80-\xff]  |
+\(                            #  (
+[^\\\x80-\xff\n\015()] *                            #     normal*
+(?:  \\ [^\x80-\xff]   [^\\\x80-\xff\n\015()] * )*        #     (special normal*)*
+\)                           #                       )
+)    #         special
+[^\\\x80-\xff\n\015()] *                         #         normal*
+)*                                  #            )*
+\)                             #                )
+[\040\t]* )*    # If comment found, allow more spaces.
+(?:
+\.
+[\040\t]*                    # Nab whitespace.
+(?:
+\(                              #  (
+[^\\\x80-\xff\n\015()] *                             #     normal*
+(?:                                 #       (
+(?:  \\ [^\x80-\xff]  |
+\(                            #  (
+[^\\\x80-\xff\n\015()] *                            #     normal*
+(?:  \\ [^\x80-\xff]   [^\\\x80-\xff\n\015()] * )*        #     (special normal*)*
+\)                           #                       )
+)    #         special
+[^\\\x80-\xff\n\015()] *                         #         normal*
+)*                                  #            )*
+\)                             #                )
+[\040\t]* )*    # If comment found, allow more spaces.
+(?:
+[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+    # some number of atom characters...
+(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom
+# Atom
+|                       #  or
+"                                     # "
+[^\\\x80-\xff\n\015"] *                            #   normal
+(?:  \\ [^\x80-\xff]  [^\\\x80-\xff\n\015"] * )*        #   ( special normal* )*
+"                                     #        "
+# Quoted string
+)
+[\040\t]*                    # Nab whitespace.
+(?:
+\(                              #  (
+[^\\\x80-\xff\n\015()] *                             #     normal*
+(?:                                 #       (
+(?:  \\ [^\x80-\xff]  |
+\(                            #  (
+[^\\\x80-\xff\n\015()] *                            #     normal*
+(?:  \\ [^\x80-\xff]   [^\\\x80-\xff\n\015()] * )*        #     (special normal*)*
+\)                           #                       )
+)    #         special
+[^\\\x80-\xff\n\015()] *                         #         normal*
+)*                                  #            )*
+\)                             #                )
+[\040\t]* )*    # If comment found, allow more spaces.
+# additional words
+)*
+@
+[\040\t]*                    # Nab whitespace.
+(?:
+\(                              #  (
+[^\\\x80-\xff\n\015()] *                             #     normal*
+(?:                                 #       (
+(?:  \\ [^\x80-\xff]  |
+\(                            #  (
+[^\\\x80-\xff\n\015()] *                            #     normal*
+(?:  \\ [^\x80-\xff]   [^\\\x80-\xff\n\015()] * )*        #     (special normal*)*
+\)                           #                       )
+)    #         special
+[^\\\x80-\xff\n\015()] *                         #         normal*
+)*                                  #            )*
+\)                             #                )
+[\040\t]* )*    # If comment found, allow more spaces.
+(?:
+[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+    # some number of atom characters...
+(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom
+|
+\[                            # [
+(?: [^\\\x80-\xff\n\015\[\]] |  \\ [^\x80-\xff]  )*     #    stuff
+\]                           #           ]
+)
+[\040\t]*                    # Nab whitespace.
+(?:
+\(                              #  (
+[^\\\x80-\xff\n\015()] *                             #     normal*
+(?:                                 #       (
+(?:  \\ [^\x80-\xff]  |
+\(                            #  (
+[^\\\x80-\xff\n\015()] *                            #     normal*
+(?:  \\ [^\x80-\xff]   [^\\\x80-\xff\n\015()] * )*        #     (special normal*)*
+\)                           #                       )
+)    #         special
+[^\\\x80-\xff\n\015()] *                         #         normal*
+)*                                  #            )*
+\)                             #                )
+[\040\t]* )*    # If comment found, allow more spaces.
+# optional trailing comments
+(?:
+\.
+[\040\t]*                    # Nab whitespace.
+(?:
+\(                              #  (
+[^\\\x80-\xff\n\015()] *                             #     normal*
+(?:                                 #       (
+(?:  \\ [^\x80-\xff]  |
+\(                            #  (
+[^\\\x80-\xff\n\015()] *                            #     normal*
+(?:  \\ [^\x80-\xff]   [^\\\x80-\xff\n\015()] * )*        #     (special normal*)*
+\)                           #                       )
+)    #         special
+[^\\\x80-\xff\n\015()] *                         #         normal*
+)*                                  #            )*
+\)                             #                )
+[\040\t]* )*    # If comment found, allow more spaces.
+(?:
+[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+    # some number of atom characters...
+(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom
+|
+\[                            # [
+(?: [^\\\x80-\xff\n\015\[\]] |  \\ [^\x80-\xff]  )*     #    stuff
+\]                           #           ]
+)
+[\040\t]*                    # Nab whitespace.
+(?:
+\(                              #  (
+[^\\\x80-\xff\n\015()] *                             #     normal*
+(?:                                 #       (
+(?:  \\ [^\x80-\xff]  |
+\(                            #  (
+[^\\\x80-\xff\n\015()] *                            #     normal*
+(?:  \\ [^\x80-\xff]   [^\\\x80-\xff\n\015()] * )*        #     (special normal*)*
+\)                           #                       )
+)    #         special
+[^\\\x80-\xff\n\015()] *                         #         normal*
+)*                                  #            )*
+\)                             #                )
+[\040\t]* )*    # If comment found, allow more spaces.
+# optional trailing comments
+)*
+# address
+|                             #  or
+(?:
+[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+    # some number of atom characters...
+(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom
+# Atom
+|                       #  or
+"                                     # "
+[^\\\x80-\xff\n\015"] *                            #   normal
+(?:  \\ [^\x80-\xff]  [^\\\x80-\xff\n\015"] * )*        #   ( special normal* )*
+"                                     #        "
+# Quoted string
+)
+# leading word
+[^()<>@,;:".\\\[\]\x80-\xff\000-\010\012-\037] *               # "normal" atoms and or spaces
+(?:
+(?:
+\(                              #  (
+[^\\\x80-\xff\n\015()] *                             #     normal*
+(?:                                 #       (
+(?:  \\ [^\x80-\xff]  |
+\(                            #  (
+[^\\\x80-\xff\n\015()] *                            #     normal*
+(?:  \\ [^\x80-\xff]   [^\\\x80-\xff\n\015()] * )*        #     (special normal*)*
+\)                           #                       )
+)    #         special
+[^\\\x80-\xff\n\015()] *                         #         normal*
+)*                                  #            )*
+\)                             #                )
+|
+"                                     # "
+[^\\\x80-\xff\n\015"] *                            #   normal
+(?:  \\ [^\x80-\xff]  [^\\\x80-\xff\n\015"] * )*        #   ( special normal* )*
+"                                     #        "
+) # "special" comment or quoted string
+[^()<>@,;:".\\\[\]\x80-\xff\000-\010\012-\037] *            #  more "normal"
+)*
+<
+[\040\t]*                    # Nab whitespace.
+(?:
+\(                              #  (
+[^\\\x80-\xff\n\015()] *                             #     normal*
+(?:                                 #       (
+(?:  \\ [^\x80-\xff]  |
+\(                            #  (
+[^\\\x80-\xff\n\015()] *                            #     normal*
+(?:  \\ [^\x80-\xff]   [^\\\x80-\xff\n\015()] * )*        #     (special normal*)*
+\)                           #                       )
+)    #         special
+[^\\\x80-\xff\n\015()] *                         #         normal*
+)*                                  #            )*
+\)                             #                )
+[\040\t]* )*    # If comment found, allow more spaces.
+# <
+(?:
+@
+[\040\t]*                    # Nab whitespace.
+(?:
+\(                              #  (
+[^\\\x80-\xff\n\015()] *                             #     normal*
+(?:                                 #       (
+(?:  \\ [^\x80-\xff]  |
+\(                            #  (
+[^\\\x80-\xff\n\015()] *                            #     normal*
+(?:  \\ [^\x80-\xff]   [^\\\x80-\xff\n\015()] * )*        #     (special normal*)*
+\)                           #                       )
+)    #         special
+[^\\\x80-\xff\n\015()] *                         #         normal*
+)*                                  #            )*
+\)                             #                )
+[\040\t]* )*    # If comment found, allow more spaces.
+(?:
+[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+    # some number of atom characters...
+(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom
+|
+\[                            # [
+(?: [^\\\x80-\xff\n\015\[\]] |  \\ [^\x80-\xff]  )*     #    stuff
+\]                           #           ]
+)
+[\040\t]*                    # Nab whitespace.
+(?:
+\(                              #  (
+[^\\\x80-\xff\n\015()] *                             #     normal*
+(?:                                 #       (
+(?:  \\ [^\x80-\xff]  |
+\(                            #  (
+[^\\\x80-\xff\n\015()] *                            #     normal*
+(?:  \\ [^\x80-\xff]   [^\\\x80-\xff\n\015()] * )*        #     (special normal*)*
+\)                           #                       )
+)    #         special
+[^\\\x80-\xff\n\015()] *                         #         normal*
+)*                                  #            )*
+\)                             #                )
+[\040\t]* )*    # If comment found, allow more spaces.
+# optional trailing comments
+(?:
+\.
+[\040\t]*                    # Nab whitespace.
+(?:
+\(                              #  (
+[^\\\x80-\xff\n\015()] *                             #     normal*
+(?:                                 #       (
+(?:  \\ [^\x80-\xff]  |
+\(                            #  (
+[^\\\x80-\xff\n\015()] *                            #     normal*
+(?:  \\ [^\x80-\xff]   [^\\\x80-\xff\n\015()] * )*        #     (special normal*)*
+\)                           #                       )
+)    #         special
+[^\\\x80-\xff\n\015()] *                         #         normal*
+)*                                  #            )*
+\)                             #                )
+[\040\t]* )*    # If comment found, allow more spaces.
+(?:
+[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+    # some number of atom characters...
+(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom
+|
+\[                            # [
+(?: [^\\\x80-\xff\n\015\[\]] |  \\ [^\x80-\xff]  )*     #    stuff
+\]                           #           ]
+)
+[\040\t]*                    # Nab whitespace.
+(?:
+\(                              #  (
+[^\\\x80-\xff\n\015()] *                             #     normal*
+(?:                                 #       (
+(?:  \\ [^\x80-\xff]  |
+\(                            #  (
+[^\\\x80-\xff\n\015()] *                            #     normal*
+(?:  \\ [^\x80-\xff]   [^\\\x80-\xff\n\015()] * )*        #     (special normal*)*
+\)                           #                       )
+)    #         special
+[^\\\x80-\xff\n\015()] *                         #         normal*
+)*                                  #            )*
+\)                             #                )
+[\040\t]* )*    # If comment found, allow more spaces.
+# optional trailing comments
+)*
+(?: ,
+[\040\t]*                    # Nab whitespace.
+(?:
+\(                              #  (
+[^\\\x80-\xff\n\015()] *                             #     normal*
+(?:                                 #       (
+(?:  \\ [^\x80-\xff]  |
+\(                            #  (
+[^\\\x80-\xff\n\015()] *                            #     normal*
+(?:  \\ [^\x80-\xff]   [^\\\x80-\xff\n\015()] * )*        #     (special normal*)*
+\)                           #                       )
+)    #         special
+[^\\\x80-\xff\n\015()] *                         #         normal*
+)*                                  #            )*
+\)                             #                )
+[\040\t]* )*    # If comment found, allow more spaces.
+@
+[\040\t]*                    # Nab whitespace.
+(?:
+\(                              #  (
+[^\\\x80-\xff\n\015()] *                             #     normal*
+(?:                                 #       (
+(?:  \\ [^\x80-\xff]  |
+\(                            #  (
+[^\\\x80-\xff\n\015()] *                            #     normal*
+(?:  \\ [^\x80-\xff]   [^\\\x80-\xff\n\015()] * )*        #     (special normal*)*
+\)                           #                       )
+)    #         special
+[^\\\x80-\xff\n\015()] *                         #         normal*
+)*                                  #            )*
+\)                             #                )
+[\040\t]* )*    # If comment found, allow more spaces.
+(?:
+[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+    # some number of atom characters...
+(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom
+|
+\[                            # [
+(?: [^\\\x80-\xff\n\015\[\]] |  \\ [^\x80-\xff]  )*     #    stuff
+\]                           #           ]
+)
+[\040\t]*                    # Nab whitespace.
+(?:
+\(                              #  (
+[^\\\x80-\xff\n\015()] *                             #     normal*
+(?:                                 #       (
+(?:  \\ [^\x80-\xff]  |
+\(                            #  (
+[^\\\x80-\xff\n\015()] *                            #     normal*
+(?:  \\ [^\x80-\xff]   [^\\\x80-\xff\n\015()] * )*        #     (special normal*)*
+\)                           #                       )
+)    #         special
+[^\\\x80-\xff\n\015()] *                         #         normal*
+)*                                  #            )*
+\)                             #                )
+[\040\t]* )*    # If comment found, allow more spaces.
+# optional trailing comments
+(?:
+\.
+[\040\t]*                    # Nab whitespace.
+(?:
+\(                              #  (
+[^\\\x80-\xff\n\015()] *                             #     normal*
+(?:                                 #       (
+(?:  \\ [^\x80-\xff]  |
+\(                            #  (
+[^\\\x80-\xff\n\015()] *                            #     normal*
+(?:  \\ [^\x80-\xff]   [^\\\x80-\xff\n\015()] * )*        #     (special normal*)*
+\)                           #                       )
+)    #         special
+[^\\\x80-\xff\n\015()] *                         #         normal*
+)*                                  #            )*
+\)                             #                )
+[\040\t]* )*    # If comment found, allow more spaces.
+(?:
+[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+    # some number of atom characters...
+(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom
+|
+\[                            # [
+(?: [^\\\x80-\xff\n\015\[\]] |  \\ [^\x80-\xff]  )*     #    stuff
+\]                           #           ]
+)
+[\040\t]*                    # Nab whitespace.
+(?:
+\(                              #  (
+[^\\\x80-\xff\n\015()] *                             #     normal*
+(?:                                 #       (
+(?:  \\ [^\x80-\xff]  |
+\(                            #  (
+[^\\\x80-\xff\n\015()] *                            #     normal*
+(?:  \\ [^\x80-\xff]   [^\\\x80-\xff\n\015()] * )*        #     (special normal*)*
+\)                           #                       )
+)    #         special
+[^\\\x80-\xff\n\015()] *                         #         normal*
+)*                                  #            )*
+\)                             #                )
+[\040\t]* )*    # If comment found, allow more spaces.
+# optional trailing comments
+)*
+)*  # additional domains
+:
+[\040\t]*                    # Nab whitespace.
+(?:
+\(                              #  (
+[^\\\x80-\xff\n\015()] *                             #     normal*
+(?:                                 #       (
+(?:  \\ [^\x80-\xff]  |
+\(                            #  (
+[^\\\x80-\xff\n\015()] *                            #     normal*
+(?:  \\ [^\x80-\xff]   [^\\\x80-\xff\n\015()] * )*        #     (special normal*)*
+\)                           #                       )
+)    #         special
+[^\\\x80-\xff\n\015()] *                         #         normal*
+)*                                  #            )*
+\)                             #                )
+[\040\t]* )*    # If comment found, allow more spaces.
+# optional trailing comments
+)?     #       optional route
+(?:
+[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+    # some number of atom characters...
+(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom
+# Atom
+|                       #  or
+"                                     # "
+[^\\\x80-\xff\n\015"] *                            #   normal
+(?:  \\ [^\x80-\xff]  [^\\\x80-\xff\n\015"] * )*        #   ( special normal* )*
+"                                     #        "
+# Quoted string
+)
+[\040\t]*                    # Nab whitespace.
+(?:
+\(                              #  (
+[^\\\x80-\xff\n\015()] *                             #     normal*
+(?:                                 #       (
+(?:  \\ [^\x80-\xff]  |
+\(                            #  (
+[^\\\x80-\xff\n\015()] *                            #     normal*
+(?:  \\ [^\x80-\xff]   [^\\\x80-\xff\n\015()] * )*        #     (special normal*)*
+\)                           #                       )
+)    #         special
+[^\\\x80-\xff\n\015()] *                         #         normal*
+)*                                  #            )*
+\)                             #                )
+[\040\t]* )*    # If comment found, allow more spaces.
+(?:
+\.
+[\040\t]*                    # Nab whitespace.
+(?:
+\(                              #  (
+[^\\\x80-\xff\n\015()] *                             #     normal*
+(?:                                 #       (
+(?:  \\ [^\x80-\xff]  |
+\(                            #  (
+[^\\\x80-\xff\n\015()] *                            #     normal*
+(?:  \\ [^\x80-\xff]   [^\\\x80-\xff\n\015()] * )*        #     (special normal*)*
+\)                           #                       )
+)    #         special
+[^\\\x80-\xff\n\015()] *                         #         normal*
+)*                                  #            )*
+\)                             #                )
+[\040\t]* )*    # If comment found, allow more spaces.
+(?:
+[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+    # some number of atom characters...
+(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom
+# Atom
+|                       #  or
+"                                     # "
+[^\\\x80-\xff\n\015"] *                            #   normal
+(?:  \\ [^\x80-\xff]  [^\\\x80-\xff\n\015"] * )*        #   ( special normal* )*
+"                                     #        "
+# Quoted string
+)
+[\040\t]*                    # Nab whitespace.
+(?:
+\(                              #  (
+[^\\\x80-\xff\n\015()] *                             #     normal*
+(?:                                 #       (
+(?:  \\ [^\x80-\xff]  |
+\(                            #  (
+[^\\\x80-\xff\n\015()] *                            #     normal*
+(?:  \\ [^\x80-\xff]   [^\\\x80-\xff\n\015()] * )*        #     (special normal*)*
+\)                           #                       )
+)    #         special
+[^\\\x80-\xff\n\015()] *                         #         normal*
+)*                                  #            )*
+\)                             #                )
+[\040\t]* )*    # If comment found, allow more spaces.
+# additional words
+)*
+@
+[\040\t]*                    # Nab whitespace.
+(?:
+\(                              #  (
+[^\\\x80-\xff\n\015()] *                             #     normal*
+(?:                                 #       (
+(?:  \\ [^\x80-\xff]  |
+\(                            #  (
+[^\\\x80-\xff\n\015()] *                            #     normal*
+(?:  \\ [^\x80-\xff]   [^\\\x80-\xff\n\015()] * )*        #     (special normal*)*
+\)                           #                       )
+)    #         special
+[^\\\x80-\xff\n\015()] *                         #         normal*
+)*                                  #            )*
+\)                             #                )
+[\040\t]* )*    # If comment found, allow more spaces.
+(?:
+[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+    # some number of atom characters...
+(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom
+|
+\[                            # [
+(?: [^\\\x80-\xff\n\015\[\]] |  \\ [^\x80-\xff]  )*     #    stuff
+\]                           #           ]
+)
+[\040\t]*                    # Nab whitespace.
+(?:
+\(                              #  (
+[^\\\x80-\xff\n\015()] *                             #     normal*
+(?:                                 #       (
+(?:  \\ [^\x80-\xff]  |
+\(                            #  (
+[^\\\x80-\xff\n\015()] *                            #     normal*
+(?:  \\ [^\x80-\xff]   [^\\\x80-\xff\n\015()] * )*        #     (special normal*)*
+\)                           #                       )
+)    #         special
+[^\\\x80-\xff\n\015()] *                         #         normal*
+)*                                  #            )*
+\)                             #                )
+[\040\t]* )*    # If comment found, allow more spaces.
+# optional trailing comments
+(?:
+\.
+[\040\t]*                    # Nab whitespace.
+(?:
+\(                              #  (
+[^\\\x80-\xff\n\015()] *                             #     normal*
+(?:                                 #       (
+(?:  \\ [^\x80-\xff]  |
+\(                            #  (
+[^\\\x80-\xff\n\015()] *                            #     normal*
+(?:  \\ [^\x80-\xff]   [^\\\x80-\xff\n\015()] * )*        #     (special normal*)*
+\)                           #                       )
+)    #         special
+[^\\\x80-\xff\n\015()] *                         #         normal*
+)*                                  #            )*
+\)                             #                )
+[\040\t]* )*    # If comment found, allow more spaces.
+(?:
+[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+    # some number of atom characters...
+(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom
+|
+\[                            # [
+(?: [^\\\x80-\xff\n\015\[\]] |  \\ [^\x80-\xff]  )*     #    stuff
+\]                           #           ]
+)
+[\040\t]*                    # Nab whitespace.
+(?:
+\(                              #  (
+[^\\\x80-\xff\n\015()] *                             #     normal*
+(?:                                 #       (
+(?:  \\ [^\x80-\xff]  |
+\(                            #  (
+[^\\\x80-\xff\n\015()] *                            #     normal*
+(?:  \\ [^\x80-\xff]   [^\\\x80-\xff\n\015()] * )*        #     (special normal*)*
+\)                           #                       )
+)    #         special
+[^\\\x80-\xff\n\015()] *                         #         normal*
+)*                                  #            )*
+\)                             #                )
+[\040\t]* )*    # If comment found, allow more spaces.
+# optional trailing comments
+)*
+#       address spec
+>                    #                 >
+# name and address
+)
+/x
+    Alan Other <user\@dom.ain>
+ 0: Alan Other <user@dom.ain>
+    <user\@dom.ain>
+ 0: user@dom.ain
+ 1: user@dom
+    user\@dom.ain
+ 0: user@dom.ain
+ 1: user@dom
+    \"A. Other\" <user.1234\@dom.ain> (a comment)
+ 0: "A. Other" <user.1234@dom.ain>
+    A. Other <user.1234\@dom.ain> (a comment)
+ 0:  Other <user.1234@dom.ain>
+    \"/s=user/ou=host/o=place/prmd=uu.yy/admd= /c=gb/\"\@x400-re.lay
+ 0: "/s=user/ou=host/o=place/prmd=uu.yy/admd= /c=gb/"@x400-re.lay
+ 1: "/s=user/ou=host/o=place/prmd=uu.yy/admd= /c=gb/"@x400-re
+    A missing angle <user\@some.where
+ 0: user@some.where
+ 1: user@some
+    *** Failers
+No match
+    The quick brown fox
+No match
+
+/abc\0def\00pqr\000xyz\0000AB/
+    abc\0def\00pqr\000xyz\0000AB
+ 0: abc\x00def\x00pqr\x00xyz\x000AB
+    abc456 abc\0def\00pqr\000xyz\0000ABCDE
+ 0: abc\x00def\x00pqr\x00xyz\x000AB
+
+/abc\x0def\x00pqr\x000xyz\x0000AB/
+    abc\x0def\x00pqr\x000xyz\x0000AB
+ 0: abc\x0def\x00pqr\x000xyz\x0000AB
+    abc456 abc\x0def\x00pqr\x000xyz\x0000ABCDE
+ 0: abc\x0def\x00pqr\x000xyz\x0000AB
+
+/^[\000-\037]/
+    \0A
+ 0: \x00
+    \01B
+ 0: \x01
+    \037C
+ 0: \x1f
+
+/\0*/
+    \0\0\0\0
+ 0: \x00\x00\x00\x00
+ 1: \x00\x00\x00
+ 2: \x00\x00
+ 3: \x00
+ 4: 
+
+/A\x0{2,3}Z/
+    The A\x0\x0Z
+ 0: A\x00\x00Z
+    An A\0\x0\0Z
+ 0: A\x00\x00\x00Z
+    *** Failers
+No match
+    A\0Z
+No match
+    A\0\x0\0\x0Z
+No match
+
+/^\s/
+    \040abc
+ 0:  
+    \x0cabc
+ 0: \x0c
+    \nabc
+ 0: \x0a
+    \rabc
+ 0: \x0d
+    \tabc
+ 0: \x09
+    *** Failers
+No match
+    abc
+No match
+
+/^a	b
+      c/x
+    abc
+ 0: abc
+
+/ab{1,3}bc/
+    abbbbc
+ 0: abbbbc
+    abbbc
+ 0: abbbc
+    abbc
+ 0: abbc
+    *** Failers
+No match
+    abc
+No match
+    abbbbbc
+No match
+
+/([^.]*)\.([^:]*):[T ]+(.*)/
+    track1.title:TBlah blah blah
+ 0: track1.title:TBlah blah blah
+ 1: track1.title:TBlah blah bla
+ 2: track1.title:TBlah blah bl
+ 3: track1.title:TBlah blah b
+ 4: track1.title:TBlah blah 
+ 5: track1.title:TBlah blah
+ 6: track1.title:TBlah bla
+ 7: track1.title:TBlah bl
+ 8: track1.title:TBlah b
+ 9: track1.title:TBlah 
+10: track1.title:TBlah
+11: track1.title:TBla
+12: track1.title:TBl
+13: track1.title:TB
+14: track1.title:T
+
+/([^.]*)\.([^:]*):[T ]+(.*)/i
+    track1.title:TBlah blah blah
+ 0: track1.title:TBlah blah blah
+ 1: track1.title:TBlah blah bla
+ 2: track1.title:TBlah blah bl
+ 3: track1.title:TBlah blah b
+ 4: track1.title:TBlah blah 
+ 5: track1.title:TBlah blah
+ 6: track1.title:TBlah bla
+ 7: track1.title:TBlah bl
+ 8: track1.title:TBlah b
+ 9: track1.title:TBlah 
+10: track1.title:TBlah
+11: track1.title:TBla
+12: track1.title:TBl
+13: track1.title:TB
+14: track1.title:T
+
+/([^.]*)\.([^:]*):[t ]+(.*)/i
+    track1.title:TBlah blah blah
+ 0: track1.title:TBlah blah blah
+ 1: track1.title:TBlah blah bla
+ 2: track1.title:TBlah blah bl
+ 3: track1.title:TBlah blah b
+ 4: track1.title:TBlah blah 
+ 5: track1.title:TBlah blah
+ 6: track1.title:TBlah bla
+ 7: track1.title:TBlah bl
+ 8: track1.title:TBlah b
+ 9: track1.title:TBlah 
+10: track1.title:TBlah
+11: track1.title:TBla
+12: track1.title:TBl
+13: track1.title:TB
+14: track1.title:T
+
+/^[W-c]+$/
+    WXY_^abc
+ 0: WXY_^abc
+    *** Failers
+No match
+    wxy
+No match
+
+/^[W-c]+$/i
+    WXY_^abc
+ 0: WXY_^abc
+    wxy_^ABC
+ 0: wxy_^ABC
+
+/^[\x3f-\x5F]+$/i
+    WXY_^abc
+ 0: WXY_^abc
+    wxy_^ABC
+ 0: wxy_^ABC
+
+/^abc$/m
+    abc
+ 0: abc
+    qqq\nabc
+ 0: abc
+    abc\nzzz
+ 0: abc
+    qqq\nabc\nzzz
+ 0: abc
+
+/^abc$/
+    abc
+ 0: abc
+    *** Failers
+No match
+    qqq\nabc
+No match
+    abc\nzzz
+No match
+    qqq\nabc\nzzz
+No match
+
+/\Aabc\Z/m
+    abc
+ 0: abc
+    abc\n 
+ 0: abc
+    *** Failers
+No match
+    qqq\nabc
+No match
+    abc\nzzz
+No match
+    qqq\nabc\nzzz
+No match
+    
+/\A(.)*\Z/s
+    abc\ndef
+ 0: abc\x0adef
+
+/\A(.)*\Z/m
+    *** Failers
+ 0: *** Failers
+    abc\ndef
+No match
+
+/(?:b)|(?::+)/
+    b::c
+ 0: b
+    c::b
+ 0: ::
+ 1: :
+
+/[-az]+/
+    az-
+ 0: az-
+ 1: az
+ 2: a
+    *** Failers
+ 0: a
+    b
+No match
+
+/[az-]+/
+    za-
+ 0: za-
+ 1: za
+ 2: z
+    *** Failers
+ 0: a
+    b
+No match
+
+/[a\-z]+/
+    a-z
+ 0: a-z
+ 1: a-
+ 2: a
+    *** Failers
+ 0: a
+    b
+No match
+
+/[a-z]+/
+    abcdxyz
+ 0: abcdxyz
+ 1: abcdxy
+ 2: abcdx
+ 3: abcd
+ 4: abc
+ 5: ab
+ 6: a
+
+/[\d-]+/
+    12-34
+ 0: 12-34
+ 1: 12-3
+ 2: 12-
+ 3: 12
+ 4: 1
+    *** Failers
+No match
+    aaa
+No match
+
+/[\d-z]+/
+    12-34z
+ 0: 12-34z
+ 1: 12-34
+ 2: 12-3
+ 3: 12-
+ 4: 12
+ 5: 1
+    *** Failers
+No match
+    aaa
+No match
+
+/\x5c/
+    \\
+ 0: \
+
+/\x20Z/
+    the Zoo
+ 0:  Z
+    *** Failers
+No match
+    Zulu
+No match
+
+/ab{3cd/
+    ab{3cd
+ 0: ab{3cd
+
+/ab{3,cd/
+    ab{3,cd
+ 0: ab{3,cd
+
+/ab{3,4a}cd/
+    ab{3,4a}cd
+ 0: ab{3,4a}cd
+
+/{4,5a}bc/
+    {4,5a}bc
+ 0: {4,5a}bc
+
+/^a.b/<lf>
+    a\rb
+ 0: a\x0db
+    *** Failers
+No match
+    a\nb
+No match
+
+/abc$/
+    abc
+ 0: abc
+    abc\n
+ 0: abc
+    *** Failers
+No match
+    abc\ndef
+No match
+
+/(abc)\123/
+    abc\x53
+ 0: abcS
+
+/(abc)\223/
+    abc\x93
+ 0: abc\x93
+
+/(abc)\323/
+    abc\xd3
+ 0: abc\xd3
+
+/(abc)\100/
+    abc\x40
+ 0: abc@
+    abc\100
+ 0: abc@
+
+/(abc)\1000/
+    abc\x400
+ 0: abc@0
+    abc\x40\x30
+ 0: abc@0
+    abc\1000
+ 0: abc@0
+    abc\100\x30
+ 0: abc@0
+    abc\100\060
+ 0: abc@0
+    abc\100\60
+ 0: abc@0
+
+/abc\81/
+    abc\081
+ 0: abc\x0081
+    abc\0\x38\x31
+ 0: abc\x0081
+
+/abc\91/
+    abc\091
+ 0: abc\x0091
+    abc\0\x39\x31
+ 0: abc\x0091
+
+/(a)(b)(c)(d)(e)(f)(g)(h)(i)(j)(k)\12\123/
+    abcdefghijk\12S
+ 0: abcdefghijk\x0aS
+
+/ab\idef/
+    abidef
+ 0: abidef
+
+/a{0}bc/
+    bc
+ 0: bc
+
+/(a|(bc)){0,0}?xyz/
+    xyz
+ 0: xyz
+
+/abc[\10]de/
+    abc\010de
+ 0: abc\x08de
+
+/abc[\1]de/
+    abc\1de
+ 0: abc\x01de
+
+/(abc)[\1]de/
+    abc\1de
+ 0: abc\x01de
+
+/(?s)a.b/
+    a\nb
+ 0: a\x0ab
+
+/^([^a])([^\b])([^c]*)([^d]{3,4})/
+    baNOTccccd
+ 0: baNOTcccc
+ 1: baNOTccc
+ 2: baNOTcc
+ 3: baNOTc
+ 4: baNOT
+    baNOTcccd
+ 0: baNOTccc
+ 1: baNOTcc
+ 2: baNOTc
+ 3: baNOT
+    baNOTccd
+ 0: baNOTcc
+ 1: baNOTc
+ 2: baNOT
+    bacccd
+ 0: baccc
+    *** Failers
+ 0: *** Failers
+ 1: *** Failer
+ 2: *** Faile
+ 3: *** Fail
+ 4: *** Fai
+ 5: *** Fa
+ 6: *** F
+    anything
+No match
+    b\bc   
+No match
+    baccd
+No match
+
+/[^a]/
+    Abc
+ 0: A
+  
+/[^a]/i
+    Abc 
+ 0: b
+
+/[^a]+/
+    AAAaAbc
+ 0: AAA
+ 1: AA
+ 2: A
+  
+/[^a]+/i
+    AAAaAbc 
+ 0: bc
+ 1: b
+
+/[^a]+/
+    bbb\nccc
+ 0: bbb\x0accc
+ 1: bbb\x0acc
+ 2: bbb\x0ac
+ 3: bbb\x0a
+ 4: bbb
+ 5: bb
+ 6: b
+   
+/[^k]$/
+    abc
+ 0: c
+    *** Failers
+ 0: s
+    abk   
+No match
+   
+/[^k]{2,3}$/
+    abc
+ 0: abc
+    kbc
+ 0: bc
+    kabc 
+ 0: abc
+    *** Failers
+ 0: ers
+    abk
+No match
+    akb
+No match
+    akk 
+No match
+
+/^\d{8,}\@.+[^k]$/
+    12345678\@a.b.c.d
+ 0: 12345678@a.b.c.d
+    123456789\@x.y.z
+ 0: 123456789@x.y.z
+    *** Failers
+No match
+    12345678\@x.y.uk
+No match
+    1234567\@a.b.c.d       
+No match
+
+/[^a]/
+    aaaabcd
+ 0: b
+    aaAabcd 
+ 0: A
+
+/[^a]/i
+    aaaabcd
+ 0: b
+    aaAabcd 
+ 0: b
+
+/[^az]/
+    aaaabcd
+ 0: b
+    aaAabcd 
+ 0: A
+
+/[^az]/i
+    aaaabcd
+ 0: b
+    aaAabcd 
+ 0: b
+
+/\000\001\002\003\004\005\006\007\010\011\012\013\014\015\016\017\020\021\022\023\024\025\026\027\030\031\032\033\034\035\036\037\040\041\042\043\044\045\046\047\050\051\052\053\054\055\056\057\060\061\062\063\064\065\066\067\070\071\072\073\074\075\076\077\100\101\102\103\104\105\106\107\110\111\112\113\114\115\116\117\120\121\122\123\124\125\126\127\130\131\132\133\134\135\136\137\140\141\142\143\144\145\146\147\150\151\152\153\154\155\156\157\160\161\162\163\164\165\166\167\170\171\172\173\174\175\176\177\200\201\202\203\204\205\206\207\210\211\212\213\214\215\216\217\220\221\222\223\224\225\226\227\230\231\232\233\234\235\236\237\240\241\242\243\244\245\246\247\250\251\252\253\254\255\256\257\260\261\262\263\264\265\266\267\270\271\272\273\274\275\276\277\300\301\302\303\304\305\306\307\310\311\312\313\314\315\316\317\320\321\322\323\324\325\326\327\330\331\332\333\334\335\336\337\340\341\342\343\344\345\346\347\350\351\352\353\354\355\356\357\360\361\362\363\364\365\366\367\370\371\372\373\374\375\376\377/
+ \000\001\002\003\004\005\006\007\010\011\012\013\014\015\016\017\020\021\022\023\024\025\026\027\030\031\032\033\034\035\036\037\040\041\042\043\044\045\046\047\050\051\052\053\054\055\056\057\060\061\062\063\064\065\066\067\070\071\072\073\074\075\076\077\100\101\102\103\104\105\106\107\110\111\112\113\114\115\116\117\120\121\122\123\124\125\126\127\130\131\132\133\134\135\136\137\140\141\142\143\144\145\146\147\150\151\152\153\154\155\156\157\160\161\162\163\164\165\166\167\170\171\172\173\174\175\176\177\200\201\202\203\204\205\206\207\210\211\212\213\214\215\216\217\220\221\222\223\224\225\226\227\230\231\232\233\234\235\236\237\240\241\242\243\244\245\246\247\250\251\252\253\254\255\256\257\260\261\262\263\264\265\266\267\270\271\272\273\274\275\276\277\300\301\302\303\304\305\306\307\310\311\312\313\314\315\316\317\320\321\322\323\324\325\326\327\330\331\332\333\334\335\336\337\340\341\342\343\344\345\346\347\350\351\352\353\354\355\356\357\360\361\362\363\364\365\366\367\370\371\372\373\374\375\376\377
+ 0: \x00\x01\x02\x03\x04\x05\x06\x07\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f\x10\x11\x12\x13\x14\x15\x16\x17\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f !"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\]^_`abcdefghijklmnopqrstuvwxyz{|}~\x7f\x80\x81\x82\x83\x84\x85\x86\x87\x88\x89\x8a\x8b\x8c\x8d\x8e\x8f\x90\x91\x92\x93\x94\x95\x96\x97\x98\x99\x9a\x9b\x9c\x9d\x9e\x9f\xa0\xa1\xa2\xa3\xa4\xa5\xa6\xa7\xa8\xa9\xaa\xab\xac\xad\xae\xaf\xb0\xb1\xb2\xb3\xb4\xb5\xb6\xb7\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf\xc0\xc1\xc2\xc3\xc4\xc5\xc6\xc7\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf\xd0\xd1\xd2\xd3\xd4\xd5\xd6\xd7\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7\xe8\xe9\xea\xeb\xec\xed\xee\xef\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff
+
+/P[^*]TAIRE[^*]{1,6}?LL/
+    xxxxxxxxxxxPSTAIREISLLxxxxxxxxx
+ 0: PSTAIREISLL
+
+/P[^*]TAIRE[^*]{1,}?LL/
+    xxxxxxxxxxxPSTAIREISLLxxxxxxxxx
+ 0: PSTAIREISLL
+
+/(\.\d\d[1-9]?)\d+/
+    1.230003938
+ 0: .230003938
+ 1: .23000393
+ 2: .2300039
+ 3: .230003
+ 4: .23000
+ 5: .2300
+ 6: .230
+    1.875000282   
+ 0: .875000282
+ 1: .87500028
+ 2: .8750002
+ 3: .875000
+ 4: .87500
+ 5: .8750
+ 6: .875
+    1.235  
+ 0: .235
+                  
+/(\.\d\d((?=0)|\d(?=\d)))/
+    1.230003938      
+ 0: .230
+ 1: .23
+    1.875000282
+ 0: .875
+    *** Failers 
+No match
+    1.235 
+No match
+    
+/a(?)b/
+    ab 
+ 0: ab
+ 
+/\b(foo)\s+(\w+)/i
+    Food is on the foo table
+ 0: foo table
+ 1: foo tabl
+ 2: foo tab
+ 3: foo ta
+ 4: foo t
+    
+/foo(.*)bar/
+    The food is under the bar in the barn.
+ 0: food is under the bar in the bar
+ 1: food is under the bar
+    
+/foo(.*?)bar/  
+    The food is under the bar in the barn.
+ 0: food is under the bar in the bar
+ 1: food is under the bar
+
+/(.*)(\d*)/
+    I have 2 numbers: 53147
+Matched, but too many subsidiary matches
+ 0: I have 2 numbers: 53147
+ 1: I have 2 numbers: 5314
+ 2: I have 2 numbers: 531
+ 3: I have 2 numbers: 53
+ 4: I have 2 numbers: 5
+ 5: I have 2 numbers: 
+ 6: I have 2 numbers:
+ 7: I have 2 numbers
+ 8: I have 2 number
+ 9: I have 2 numbe
+10: I have 2 numb
+11: I have 2 num
+12: I have 2 nu
+13: I have 2 n
+14: I have 2 
+15: I have 2
+16: I have 
+17: I have
+18: I hav
+19: I ha
+20: I h
+21: I 
+    
+/(.*)(\d+)/
+    I have 2 numbers: 53147
+ 0: I have 2 numbers: 53147
+ 1: I have 2 numbers: 5314
+ 2: I have 2 numbers: 531
+ 3: I have 2 numbers: 53
+ 4: I have 2 numbers: 5
+ 5: I have 2
+ 
+/(.*?)(\d*)/
+    I have 2 numbers: 53147
+Matched, but too many subsidiary matches
+ 0: I have 2 numbers: 53147
+ 1: I have 2 numbers: 5314
+ 2: I have 2 numbers: 531
+ 3: I have 2 numbers: 53
+ 4: I have 2 numbers: 5
+ 5: I have 2 numbers: 
+ 6: I have 2 numbers:
+ 7: I have 2 numbers
+ 8: I have 2 number
+ 9: I have 2 numbe
+10: I have 2 numb
+11: I have 2 num
+12: I have 2 nu
+13: I have 2 n
+14: I have 2 
+15: I have 2
+16: I have 
+17: I have
+18: I hav
+19: I ha
+20: I h
+21: I 
+
+/(.*?)(\d+)/
+    I have 2 numbers: 53147
+ 0: I have 2 numbers: 53147
+ 1: I have 2 numbers: 5314
+ 2: I have 2 numbers: 531
+ 3: I have 2 numbers: 53
+ 4: I have 2 numbers: 5
+ 5: I have 2
+
+/(.*)(\d+)$/
+    I have 2 numbers: 53147
+ 0: I have 2 numbers: 53147
+
+/(.*?)(\d+)$/
+    I have 2 numbers: 53147
+ 0: I have 2 numbers: 53147
+
+/(.*)\b(\d+)$/
+    I have 2 numbers: 53147
+ 0: I have 2 numbers: 53147
+
+/(.*\D)(\d+)$/
+    I have 2 numbers: 53147
+ 0: I have 2 numbers: 53147
+
+/^\D*(?!123)/
+    ABC123
+ 0: AB
+ 1: A
+ 2: 
+     
+/^(\D*)(?=\d)(?!123)/
+    ABC445
+ 0: ABC
+    *** Failers
+No match
+    ABC123
+No match
+    
+/^[W-]46]/
+    W46]789 
+ 0: W46]
+    -46]789
+ 0: -46]
+    *** Failers
+No match
+    Wall
+No match
+    Zebra
+No match
+    42
+No match
+    [abcd] 
+No match
+    ]abcd[
+No match
+       
+/^[W-\]46]/
+    W46]789 
+ 0: W
+    Wall
+ 0: W
+    Zebra
+ 0: Z
+    Xylophone  
+ 0: X
+    42
+ 0: 4
+    [abcd] 
+ 0: [
+    ]abcd[
+ 0: ]
+    \\backslash 
+ 0: \
+    *** Failers
+No match
+    -46]789
+No match
+    well
+No match
+    
+/\d\d\/\d\d\/\d\d\d\d/
+    01/01/2000
+ 0: 01/01/2000
+
+/word (?:[a-zA-Z0-9]+ ){0,10}otherword/
+  word cat dog elephant mussel cow horse canary baboon snake shark otherword
+ 0: word cat dog elephant mussel cow horse canary baboon snake shark otherword
+  word cat dog elephant mussel cow horse canary baboon snake shark
+No match
+
+/word (?:[a-zA-Z0-9]+ ){0,300}otherword/
+  word cat dog elephant mussel cow horse canary baboon snake shark the quick brown fox and the lazy dog and several other words getting close to thirty by now I hope
+No match
+
+/^(a){0,0}/
+    bcd
+ 0: 
+    abc
+ 0: 
+    aab     
+ 0: 
+
+/^(a){0,1}/
+    bcd
+ 0: 
+    abc
+ 0: a
+ 1: 
+    aab  
+ 0: a
+ 1: 
+
+/^(a){0,2}/
+    bcd
+ 0: 
+    abc
+ 0: a
+ 1: 
+    aab  
+ 0: aa
+ 1: a
+ 2: 
+
+/^(a){0,3}/
+    bcd
+ 0: 
+    abc
+ 0: a
+ 1: 
+    aab
+ 0: aa
+ 1: a
+ 2: 
+    aaa   
+ 0: aaa
+ 1: aa
+ 2: a
+ 3: 
+
+/^(a){0,}/
+    bcd
+ 0: 
+    abc
+ 0: a
+ 1: 
+    aab
+ 0: aa
+ 1: a
+ 2: 
+    aaa
+ 0: aaa
+ 1: aa
+ 2: a
+ 3: 
+    aaaaaaaa    
+ 0: aaaaaaaa
+ 1: aaaaaaa
+ 2: aaaaaa
+ 3: aaaaa
+ 4: aaaa
+ 5: aaa
+ 6: aa
+ 7: a
+ 8: 
+
+/^(a){1,1}/
+    bcd
+No match
+    abc
+ 0: a
+    aab  
+ 0: a
+
+/^(a){1,2}/
+    bcd
+No match
+    abc
+ 0: a
+    aab  
+ 0: aa
+ 1: a
+
+/^(a){1,3}/
+    bcd
+No match
+    abc
+ 0: a
+    aab
+ 0: aa
+ 1: a
+    aaa   
+ 0: aaa
+ 1: aa
+ 2: a
+
+/^(a){1,}/
+    bcd
+No match
+    abc
+ 0: a
+    aab
+ 0: aa
+ 1: a
+    aaa
+ 0: aaa
+ 1: aa
+ 2: a
+    aaaaaaaa    
+ 0: aaaaaaaa
+ 1: aaaaaaa
+ 2: aaaaaa
+ 3: aaaaa
+ 4: aaaa
+ 5: aaa
+ 6: aa
+ 7: a
+
+/.*\.gif/
+    borfle\nbib.gif\nno
+ 0: bib.gif
+
+/.{0,}\.gif/
+    borfle\nbib.gif\nno
+ 0: bib.gif
+
+/.*\.gif/m
+    borfle\nbib.gif\nno
+ 0: bib.gif
+
+/.*\.gif/s
+    borfle\nbib.gif\nno
+ 0: borfle\x0abib.gif
+
+/.*\.gif/ms
+    borfle\nbib.gif\nno
+ 0: borfle\x0abib.gif
+    
+/.*$/
+    borfle\nbib.gif\nno
+ 0: no
+
+/.*$/m
+    borfle\nbib.gif\nno
+ 0: borfle
+
+/.*$/s
+    borfle\nbib.gif\nno
+ 0: borfle\x0abib.gif\x0ano
+
+/.*$/ms
+    borfle\nbib.gif\nno
+ 0: borfle\x0abib.gif\x0ano
+ 1: borfle\x0abib.gif
+ 2: borfle
+    
+/.*$/
+    borfle\nbib.gif\nno\n
+ 0: no
+
+/.*$/m
+    borfle\nbib.gif\nno\n
+ 0: borfle
+
+/.*$/s
+    borfle\nbib.gif\nno\n
+ 0: borfle\x0abib.gif\x0ano\x0a
+ 1: borfle\x0abib.gif\x0ano
+
+/.*$/ms
+    borfle\nbib.gif\nno\n
+ 0: borfle\x0abib.gif\x0ano\x0a
+ 1: borfle\x0abib.gif\x0ano
+ 2: borfle\x0abib.gif
+ 3: borfle
+    
+/(.*X|^B)/
+    abcde\n1234Xyz
+ 0: 1234X
+    BarFoo 
+ 0: B
+    *** Failers
+No match
+    abcde\nBar  
+No match
+
+/(.*X|^B)/m
+    abcde\n1234Xyz
+ 0: 1234X
+    BarFoo 
+ 0: B
+    abcde\nBar  
+ 0: B
+
+/(.*X|^B)/s
+    abcde\n1234Xyz
+ 0: abcde\x0a1234X
+    BarFoo 
+ 0: B
+    *** Failers
+No match
+    abcde\nBar  
+No match
+
+/(.*X|^B)/ms
+    abcde\n1234Xyz
+ 0: abcde\x0a1234X
+    BarFoo 
+ 0: B
+    abcde\nBar  
+ 0: B
+
+/(?s)(.*X|^B)/
+    abcde\n1234Xyz
+ 0: abcde\x0a1234X
+    BarFoo 
+ 0: B
+    *** Failers 
+No match
+    abcde\nBar  
+No match
+
+/(?s:.*X|^B)/
+    abcde\n1234Xyz
+ 0: abcde\x0a1234X
+    BarFoo 
+ 0: B
+    *** Failers 
+No match
+    abcde\nBar  
+No match
+
+/^.*B/
+    **** Failers
+No match
+    abc\nB
+No match
+     
+/(?s)^.*B/
+    abc\nB
+ 0: abc\x0aB
+
+/(?m)^.*B/
+    abc\nB
+ 0: B
+     
+/(?ms)^.*B/
+    abc\nB
+ 0: abc\x0aB
+
+/(?ms)^B/
+    abc\nB
+ 0: B
+
+/(?s)B$/
+    B\n
+ 0: B
+
+/^[0-9][0-9][0-9][0-9][0-9][0-9][0-9][0-9][0-9][0-9][0-9][0-9]/
+    123456654321
+ 0: 123456654321
+  
+/^\d\d\d\d\d\d\d\d\d\d\d\d/
+    123456654321 
+ 0: 123456654321
+
+/^[\d][\d][\d][\d][\d][\d][\d][\d][\d][\d][\d][\d]/
+    123456654321
+ 0: 123456654321
+  
+/^[abc]{12}/
+    abcabcabcabc
+ 0: abcabcabcabc
+    
+/^[a-c]{12}/
+    abcabcabcabc
+ 0: abcabcabcabc
+    
+/^(a|b|c){12}/
+    abcabcabcabc 
+ 0: abcabcabcabc
+
+/^[abcdefghijklmnopqrstuvwxy0123456789]/
+    n
+ 0: n
+    *** Failers 
+No match
+    z 
+No match
+
+/abcde{0,0}/
+    abcd
+ 0: abcd
+    *** Failers
+No match
+    abce  
+No match
+
+/ab[cd]{0,0}e/
+    abe
+ 0: abe
+    *** Failers
+No match
+    abcde 
+No match
+    
+/ab(c){0,0}d/
+    abd
+ 0: abd
+    *** Failers
+No match
+    abcd   
+No match
+
+/a(b*)/
+    a
+ 0: a
+    ab
+ 0: ab
+ 1: a
+    abbbb
+ 0: abbbb
+ 1: abbb
+ 2: abb
+ 3: ab
+ 4: a
+    *** Failers
+ 0: a
+    bbbbb    
+No match
+    
+/ab\d{0}e/
+    abe
+ 0: abe
+    *** Failers
+No match
+    ab1e   
+No match
+    
+/"([^\\"]+|\\.)*"/
+    the \"quick\" brown fox
+ 0: "quick"
+    \"the \\\"quick\\\" brown fox\" 
+ 0: "the \"quick\" brown fox"
+
+/.*?/g+
+    abc
+ 0: abc
+ 0+ 
+ 1: ab
+ 2: a
+ 3: 
+ 0: 
+ 0+ 
+  
+/\b/g+
+    abc 
+ 0: 
+ 0+ abc
+ 0: 
+ 0+ 
+
+/\b/+g
+    abc 
+ 0: 
+ 0+ abc
+ 0: 
+ 0+ 
+
+//g
+    abc
+ 0: 
+ 0: 
+ 0: 
+ 0: 
+
+/<tr([\w\W\s\d][^<>]{0,})><TD([\w\W\s\d][^<>]{0,})>([\d]{0,}\.)(.*)((<BR>([\w\W\s\d][^<>]{0,})|[\s]{0,}))<\/a><\/TD><TD([\w\W\s\d][^<>]{0,})>([\w\W\s\d][^<>]{0,})<\/TD><TD([\w\W\s\d][^<>]{0,})>([\w\W\s\d][^<>]{0,})<\/TD><\/TR>/is
+  <TR BGCOLOR='#DBE9E9'><TD align=left valign=top>43.<a href='joblist.cfm?JobID=94 6735&Keyword='>Word Processor<BR>(N-1286)</a></TD><TD align=left valign=top>Lega lstaff.com</TD><TD align=left valign=top>CA - Statewide</TD></TR>
+ 0: <TR BGCOLOR='#DBE9E9'><TD align=left valign=top>43.<a href='joblist.cfm?JobID=94 6735&Keyword='>Word Processor<BR>(N-1286)</a></TD><TD align=left valign=top>Lega lstaff.com</TD><TD align=left valign=top>CA - Statewide</TD></TR>
+
+/a[^a]b/
+    acb
+ 0: acb
+    a\nb
+ 0: a\x0ab
+    
+/a.b/
+    acb
+ 0: acb
+    *** Failers 
+No match
+    a\nb   
+No match
+    
+/a[^a]b/s
+    acb
+ 0: acb
+    a\nb  
+ 0: a\x0ab
+    
+/a.b/s
+    acb
+ 0: acb
+    a\nb  
+ 0: a\x0ab
+
+/^(b+?|a){1,2}?c/
+    bac
+ 0: bac
+    bbac
+ 0: bbac
+    bbbac
+ 0: bbbac
+    bbbbac
+ 0: bbbbac
+    bbbbbac 
+ 0: bbbbbac
+
+/^(b+|a){1,2}?c/
+    bac
+ 0: bac
+    bbac
+ 0: bbac
+    bbbac
+ 0: bbbac
+    bbbbac
+ 0: bbbbac
+    bbbbbac 
+ 0: bbbbbac
+    
+/(?!\A)x/m
+    x\nb\n
+No match
+    a\bx\n  
+ 0: x
+    
+/\x0{ab}/
+    \0{ab} 
+ 0: \x00{ab}
+
+/(A|B)*?CD/
+    CD 
+ 0: CD
+    
+/(A|B)*CD/
+    CD 
+ 0: CD
+
+/(?<!bar)foo/
+    foo
+ 0: foo
+    catfood
+ 0: foo
+    arfootle
+ 0: foo
+    rfoosh
+ 0: foo
+    *** Failers
+No match
+    barfoo
+No match
+    towbarfoo
+No match
+
+/\w{3}(?<!bar)foo/
+    catfood
+ 0: catfoo
+    *** Failers
+No match
+    foo
+No match
+    barfoo
+No match
+    towbarfoo
+No match
+
+/(?<=(foo)a)bar/
+    fooabar
+ 0: bar
+    *** Failers
+No match
+    bar
+No match
+    foobbar
+No match
+      
+/\Aabc\z/m
+    abc
+ 0: abc
+    *** Failers
+No match
+    abc\n   
+No match
+    qqq\nabc
+No match
+    abc\nzzz
+No match
+    qqq\nabc\nzzz
+No match
+
+"(?>.*/)foo"
+    /this/is/a/very/long/line/in/deed/with/very/many/slashes/in/it/you/see/
+No match
+
+"(?>.*/)foo"
+    /this/is/a/very/long/line/in/deed/with/very/many/slashes/in/and/foo
+ 0: /this/is/a/very/long/line/in/deed/with/very/many/slashes/in/and/foo
+
+/(?>(\.\d\d[1-9]?))\d+/
+    1.230003938
+ 0: .230003938
+ 1: .23000393
+ 2: .2300039
+ 3: .230003
+ 4: .23000
+ 5: .2300
+ 6: .230
+    1.875000282
+ 0: .875000282
+ 1: .87500028
+ 2: .8750002
+ 3: .875000
+ 4: .87500
+ 5: .8750
+    *** Failers 
+No match
+    1.235 
+No match
+
+/^((?>\w+)|(?>\s+))*$/
+    now is the time for all good men to come to the aid of the party
+ 0: now is the time for all good men to come to the aid of the party
+    *** Failers
+No match
+    this is not a line with only words and spaces!
+No match
+    
+/(\d+)(\w)/
+    12345a
+ 0: 12345a
+ 1: 12345
+ 2: 1234
+ 3: 123
+ 4: 12
+    12345+ 
+ 0: 12345
+ 1: 1234
+ 2: 123
+ 3: 12
+
+/((?>\d+))(\w)/
+    12345a
+ 0: 12345a
+    *** Failers
+No match
+    12345+ 
+No match
+
+/(?>a+)b/
+    aaab
+ 0: aaab
+
+/((?>a+)b)/
+    aaab
+ 0: aaab
+
+/(?>(a+))b/
+    aaab
+ 0: aaab
+
+/(?>b)+/
+    aaabbbccc
+ 0: bbb
+ 1: bb
+ 2: b
+
+/(?>a+|b+|c+)*c/
+    aaabbbbccccd
+ 0: aaabbbbcccc
+ 1: aaabbbbc
+    
+/(a+|b+|c+)*c/
+    aaabbbbccccd
+ 0: aaabbbbcccc
+ 1: aaabbbbccc
+ 2: aaabbbbcc
+ 3: aaabbbbc
+
+/((?>[^()]+)|\([^()]*\))+/
+    ((abc(ade)ufh()()x
+ 0: abc(ade)ufh()()x
+ 1: abc(ade)ufh()()
+ 2: abc(ade)ufh()
+ 3: abc(ade)ufh
+ 4: abc(ade)
+ 5: abc
+    
+/\(((?>[^()]+)|\([^()]+\))+\)/ 
+    (abc)
+ 0: (abc)
+    (abc(def)xyz)
+ 0: (abc(def)xyz)
+    *** Failers
+No match
+    ((()aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa   
+No match
+
+/a(?-i)b/i
+    ab
+ 0: ab
+    Ab
+ 0: Ab
+    *** Failers 
+No match
+    aB
+No match
+    AB
+No match
+        
+/(a (?x)b c)d e/
+    a bcd e
+ 0: a bcd e
+    *** Failers
+No match
+    a b cd e
+No match
+    abcd e   
+No match
+    a bcde 
+No match
+ 
+/(a b(?x)c d (?-x)e f)/
+    a bcde f
+ 0: a bcde f
+    *** Failers
+No match
+    abcdef  
+No match
+
+/(a(?i)b)c/
+    abc
+ 0: abc
+    aBc
+ 0: aBc
+    *** Failers
+No match
+    abC
+No match
+    aBC  
+No match
+    Abc
+No match
+    ABc
+No match
+    ABC
+No match
+    AbC
+No match
+    
+/a(?i:b)c/
+    abc
+ 0: abc
+    aBc
+ 0: aBc
+    *** Failers 
+No match
+    ABC
+No match
+    abC
+No match
+    aBC
+No match
+    
+/a(?i:b)*c/
+    aBc
+ 0: aBc
+    aBBc
+ 0: aBBc
+    *** Failers 
+No match
+    aBC
+No match
+    aBBC
+No match
+    
+/a(?=b(?i)c)\w\wd/
+    abcd
+ 0: abcd
+    abCd
+ 0: abCd
+    *** Failers
+No match
+    aBCd
+No match
+    abcD     
+No match
+    
+/(?s-i:more.*than).*million/i
+    more than million
+ 0: more than million
+    more than MILLION
+ 0: more than MILLION
+    more \n than Million 
+ 0: more \x0a than Million
+    *** Failers
+No match
+    MORE THAN MILLION    
+No match
+    more \n than \n million 
+No match
+
+/(?:(?s-i)more.*than).*million/i
+    more than million
+ 0: more than million
+    more than MILLION
+ 0: more than MILLION
+    more \n than Million 
+ 0: more \x0a than Million
+    *** Failers
+No match
+    MORE THAN MILLION    
+No match
+    more \n than \n million 
+No match
+    
+/(?>a(?i)b+)+c/ 
+    abc
+ 0: abc
+    aBbc
+ 0: aBbc
+    aBBc 
+ 0: aBBc
+    *** Failers
+No match
+    Abc
+No match
+    abAb    
+No match
+    abbC 
+No match
+    
+/(?=a(?i)b)\w\wc/
+    abc
+ 0: abc
+    aBc
+ 0: aBc
+    *** Failers
+No match
+    Ab 
+No match
+    abC
+No match
+    aBC     
+No match
+    
+/(?<=a(?i)b)(\w\w)c/
+    abxxc
+ 0: xxc
+    aBxxc
+ 0: xxc
+    *** Failers
+No match
+    Abxxc
+No match
+    ABxxc
+No match
+    abxxC      
+No match
+
+/^(?(?=abc)\w{3}:|\d\d)$/
+    abc:
+ 0: abc:
+    12
+ 0: 12
+    *** Failers
+No match
+    123
+No match
+    xyz    
+No match
+
+/^(?(?!abc)\d\d|\w{3}:)$/
+    abc:
+ 0: abc:
+    12
+ 0: 12
+    *** Failers
+No match
+    123
+No match
+    xyz    
+No match
+    
+/(?(?<=foo)bar|cat)/
+    foobar
+ 0: bar
+    cat
+ 0: cat
+    fcat
+ 0: cat
+    focat   
+ 0: cat
+    *** Failers
+No match
+    foocat  
+No match
+
+/(?(?<!foo)cat|bar)/
+    foobar
+ 0: bar
+    cat
+ 0: cat
+    fcat
+ 0: cat
+    focat   
+ 0: cat
+    *** Failers
+No match
+    foocat  
+No match
+
+/(?>a*)*/
+    a
+ 0: a
+ 1: 
+    aa
+ 0: aa
+ 1: 
+    aaaa
+ 0: aaaa
+ 1: 
+    
+/(abc|)+/
+    abc
+ 0: abc
+ 1: 
+    abcabc
+ 0: abcabc
+ 1: abc
+ 2: 
+    abcabcabc
+ 0: abcabcabc
+ 1: abcabc
+ 2: abc
+ 3: 
+    xyz      
+ 0: 
+
+/([a]*)*/
+    a
+ 0: a
+ 1: 
+    aaaaa 
+ 0: aaaaa
+ 1: aaaa
+ 2: aaa
+ 3: aa
+ 4: a
+ 5: 
+ 
+/([ab]*)*/
+    a
+ 0: a
+ 1: 
+    b
+ 0: b
+ 1: 
+    ababab
+ 0: ababab
+ 1: ababa
+ 2: abab
+ 3: aba
+ 4: ab
+ 5: a
+ 6: 
+    aaaabcde
+ 0: aaaab
+ 1: aaaa
+ 2: aaa
+ 3: aa
+ 4: a
+ 5: 
+    bbbb    
+ 0: bbbb
+ 1: bbb
+ 2: bb
+ 3: b
+ 4: 
+ 
+/([^a]*)*/
+    b
+ 0: b
+ 1: 
+    bbbb
+ 0: bbbb
+ 1: bbb
+ 2: bb
+ 3: b
+ 4: 
+    aaa   
+ 0: 
+ 
+/([^ab]*)*/
+    cccc
+ 0: cccc
+ 1: ccc
+ 2: cc
+ 3: c
+ 4: 
+    abab  
+ 0: 
+ 
+/([a]*?)*/
+    a
+ 0: a
+ 1: 
+    aaaa 
+ 0: aaaa
+ 1: aaa
+ 2: aa
+ 3: a
+ 4: 
+ 
+/([ab]*?)*/
+    a
+ 0: a
+ 1: 
+    b
+ 0: b
+ 1: 
+    abab
+ 0: abab
+ 1: aba
+ 2: ab
+ 3: a
+ 4: 
+    baba   
+ 0: baba
+ 1: bab
+ 2: ba
+ 3: b
+ 4: 
+ 
+/([^a]*?)*/
+    b
+ 0: b
+ 1: 
+    bbbb
+ 0: bbbb
+ 1: bbb
+ 2: bb
+ 3: b
+ 4: 
+    aaa   
+ 0: 
+ 
+/([^ab]*?)*/
+    c
+ 0: c
+ 1: 
+    cccc
+ 0: cccc
+ 1: ccc
+ 2: cc
+ 3: c
+ 4: 
+    baba   
+ 0: 
+ 
+/(?>a*)*/
+    a
+ 0: a
+ 1: 
+    aaabcde 
+ 0: aaa
+ 1: 
+ 
+/((?>a*))*/
+    aaaaa
+ 0: aaaaa
+ 1: 
+    aabbaa 
+ 0: aa
+ 1: 
+ 
+/((?>a*?))*/
+    aaaaa
+ 0: aaaaa
+ 1: 
+    aabbaa 
+ 0: aa
+ 1: 
+
+/(?(?=[^a-z]+[a-z])  \d{2}-[a-z]{3}-\d{2}  |  \d{2}-\d{2}-\d{2} ) /x
+    12-sep-98
+ 0: 12-sep-98
+    12-09-98
+ 0: 12-09-98
+    *** Failers
+No match
+    sep-12-98
+No match
+        
+/(?i:saturday|sunday)/
+    saturday
+ 0: saturday
+    sunday
+ 0: sunday
+    Saturday
+ 0: Saturday
+    Sunday
+ 0: Sunday
+    SATURDAY
+ 0: SATURDAY
+    SUNDAY
+ 0: SUNDAY
+    SunDay
+ 0: SunDay
+    
+/(a(?i)bc|BB)x/
+    abcx
+ 0: abcx
+    aBCx
+ 0: aBCx
+    bbx
+ 0: bbx
+    BBx
+ 0: BBx
+    *** Failers
+No match
+    abcX
+No match
+    aBCX
+No match
+    bbX
+No match
+    BBX               
+No match
+
+/^([ab](?i)[cd]|[ef])/
+    ac
+ 0: ac
+    aC
+ 0: aC
+    bD
+ 0: bD
+    elephant
+ 0: e
+    Europe 
+ 0: E
+    frog
+ 0: f
+    France
+ 0: F
+    *** Failers
+No match
+    Africa     
+No match
+
+/^(ab|a(?i)[b-c](?m-i)d|x(?i)y|z)/
+    ab
+ 0: ab
+    aBd
+ 0: aBd
+    xy
+ 0: xy
+    xY
+ 0: xY
+    zebra
+ 0: z
+    Zambesi
+ 0: Z
+    *** Failers
+No match
+    aCD  
+No match
+    XY  
+No match
+
+/(?<=foo\n)^bar/m
+    foo\nbar
+ 0: bar
+    *** Failers
+No match
+    bar
+No match
+    baz\nbar   
+No match
+
+/(?<=(?<!foo)bar)baz/
+    barbaz
+ 0: baz
+    barbarbaz 
+ 0: baz
+    koobarbaz 
+ 0: baz
+    *** Failers
+No match
+    baz
+No match
+    foobarbaz 
+No match
+
+/The following tests are taken from the Perl 5.005 test suite; some of them/
+/are compatible with 5.004, but I'd rather not have to sort them out./
+No match
+
+/abc/
+    abc
+ 0: abc
+    xabcy
+ 0: abc
+    ababc
+ 0: abc
+    *** Failers
+No match
+    xbc
+No match
+    axc
+No match
+    abx
+No match
+
+/ab*c/
+    abc
+ 0: abc
+
+/ab*bc/
+    abc
+ 0: abc
+    abbc
+ 0: abbc
+    abbbbc
+ 0: abbbbc
+
+/.{1}/
+    abbbbc
+ 0: a
+
+/.{3,4}/
+    abbbbc
+ 0: abbb
+ 1: abb
+
+/ab{0,}bc/
+    abbbbc
+ 0: abbbbc
+
+/ab+bc/
+    abbc
+ 0: abbc
+    *** Failers
+No match
+    abc
+No match
+    abq
+No match
+
+/ab+bc/
+    abbbbc
+ 0: abbbbc
+
+/ab{1,}bc/
+    abbbbc
+ 0: abbbbc
+
+/ab{1,3}bc/
+    abbbbc
+ 0: abbbbc
+
+/ab{3,4}bc/
+    abbbbc
+ 0: abbbbc
+
+/ab{4,5}bc/
+    *** Failers
+No match
+    abq
+No match
+    abbbbc
+No match
+
+/ab?bc/
+    abbc
+ 0: abbc
+    abc
+ 0: abc
+
+/ab{0,1}bc/
+    abc
+ 0: abc
+
+/ab?bc/
+
+/ab?c/
+    abc
+ 0: abc
+
+/ab{0,1}c/
+    abc
+ 0: abc
+
+/^abc$/
+    abc
+ 0: abc
+    *** Failers
+No match
+    abbbbc
+No match
+    abcc
+No match
+
+/^abc/
+    abcc
+ 0: abc
+
+/^abc$/
+
+/abc$/
+    aabc
+ 0: abc
+    *** Failers
+No match
+    aabc
+ 0: abc
+    aabcd
+No match
+
+/^/
+    abc
+ 0: 
+
+/$/
+    abc
+ 0: 
+
+/a.c/
+    abc
+ 0: abc
+    axc
+ 0: axc
+
+/a.*c/
+    axyzc
+ 0: axyzc
+
+/a[bc]d/
+    abd
+ 0: abd
+    *** Failers
+No match
+    axyzd
+No match
+    abc
+No match
+
+/a[b-d]e/
+    ace
+ 0: ace
+
+/a[b-d]/
+    aac
+ 0: ac
+
+/a[-b]/
+    a-
+ 0: a-
+
+/a[b-]/
+    a-
+ 0: a-
+
+/a]/
+    a]
+ 0: a]
+
+/a[]]b/
+    a]b
+ 0: a]b
+
+/a[^bc]d/
+    aed
+ 0: aed
+    *** Failers
+No match
+    abd
+No match
+    abd
+No match
+
+/a[^-b]c/
+    adc
+ 0: adc
+
+/a[^]b]c/
+    adc
+ 0: adc
+    *** Failers
+No match
+    a-c
+ 0: a-c
+    a]c
+No match
+
+/\ba\b/
+    a-
+ 0: a
+    -a
+ 0: a
+    -a-
+ 0: a
+
+/\by\b/
+    *** Failers
+No match
+    xy
+No match
+    yz
+No match
+    xyz
+No match
+
+/\Ba\B/
+    *** Failers
+ 0: a
+    a-
+No match
+    -a
+No match
+    -a-
+No match
+
+/\By\b/
+    xy
+ 0: y
+
+/\by\B/
+    yz
+ 0: y
+
+/\By\B/
+    xyz
+ 0: y
+
+/\w/
+    a
+ 0: a
+
+/\W/
+    -
+ 0: -
+    *** Failers
+ 0: *
+    -
+ 0: -
+    a
+No match
+
+/a\sb/
+    a b
+ 0: a b
+
+/a\Sb/
+    a-b
+ 0: a-b
+    *** Failers
+No match
+    a-b
+ 0: a-b
+    a b
+No match
+
+/\d/
+    1
+ 0: 1
+
+/\D/
+    -
+ 0: -
+    *** Failers
+ 0: *
+    -
+ 0: -
+    1
+No match
+
+/[\w]/
+    a
+ 0: a
+
+/[\W]/
+    -
+ 0: -
+    *** Failers
+ 0: *
+    -
+ 0: -
+    a
+No match
+
+/a[\s]b/
+    a b
+ 0: a b
+
+/a[\S]b/
+    a-b
+ 0: a-b
+    *** Failers
+No match
+    a-b
+ 0: a-b
+    a b
+No match
+
+/[\d]/
+    1
+ 0: 1
+
+/[\D]/
+    -
+ 0: -
+    *** Failers
+ 0: *
+    -
+ 0: -
+    1
+No match
+
+/ab|cd/
+    abc
+ 0: ab
+    abcd
+ 0: ab
+
+/()ef/
+    def
+ 0: ef
+
+/$b/
+
+/a\(b/
+    a(b
+ 0: a(b
+
+/a\(*b/
+    ab
+ 0: ab
+    a((b
+ 0: a((b
+
+/a\\b/
+    a\b
+No match
+
+/((a))/
+    abc
+ 0: a
+
+/(a)b(c)/
+    abc
+ 0: abc
+
+/a+b+c/
+    aabbabc
+ 0: abc
+
+/a{1,}b{1,}c/
+    aabbabc
+ 0: abc
+
+/a.+?c/
+    abcabc
+ 0: abcabc
+ 1: abc
+
+/(a+|b)*/
+    ab
+ 0: ab
+ 1: a
+ 2: 
+
+/(a+|b){0,}/
+    ab
+ 0: ab
+ 1: a
+ 2: 
+
+/(a+|b)+/
+    ab
+ 0: ab
+ 1: a
+
+/(a+|b){1,}/
+    ab
+ 0: ab
+ 1: a
+
+/(a+|b)?/
+    ab
+ 0: a
+ 1: 
+
+/(a+|b){0,1}/
+    ab
+ 0: a
+ 1: 
+
+/[^ab]*/
+    cde
+ 0: cde
+ 1: cd
+ 2: c
+ 3: 
+
+/abc/
+    *** Failers
+No match
+    b
+No match
+    
+
+/a*/
+    
+
+/([abc])*d/
+    abbbcd
+ 0: abbbcd
+
+/([abc])*bcd/
+    abcd
+ 0: abcd
+
+/a|b|c|d|e/
+    e
+ 0: e
+
+/(a|b|c|d|e)f/
+    ef
+ 0: ef
+
+/abcd*efg/
+    abcdefg
+ 0: abcdefg
+
+/ab*/
+    xabyabbbz
+ 0: ab
+ 1: a
+    xayabbbz
+ 0: a
+
+/(ab|cd)e/
+    abcde
+ 0: cde
+
+/[abhgefdc]ij/
+    hij
+ 0: hij
+
+/^(ab|cd)e/
+
+/(abc|)ef/
+    abcdef
+ 0: ef
+
+/(a|b)c*d/
+    abcd
+ 0: bcd
+
+/(ab|ab*)bc/
+    abc
+ 0: abc
+
+/a([bc]*)c*/
+    abc
+ 0: abc
+ 1: ab
+ 2: a
+
+/a([bc]*)(c*d)/
+    abcd
+ 0: abcd
+
+/a([bc]+)(c*d)/
+    abcd
+ 0: abcd
+
+/a([bc]*)(c+d)/
+    abcd
+ 0: abcd
+
+/a[bcd]*dcdcde/
+    adcdcde
+ 0: adcdcde
+
+/a[bcd]+dcdcde/
+    *** Failers
+No match
+    abcde
+No match
+    adcdcde
+No match
+
+/(ab|a)b*c/
+    abc
+ 0: abc
+
+/((a)(b)c)(d)/
+    abcd
+ 0: abcd
+
+/[a-zA-Z_][a-zA-Z0-9_]*/
+    alpha
+ 0: alpha
+ 1: alph
+ 2: alp
+ 3: al
+ 4: a
+
+/^a(bc+|b[eh])g|.h$/
+    abh
+ 0: bh
+
+/(bc+d$|ef*g.|h?i(j|k))/
+    effgz
+ 0: effgz
+    ij
+ 0: ij
+    reffgz
+ 0: effgz
+    *** Failers
+No match
+    effg
+No match
+    bcdd
+No match
+
+/((((((((((a))))))))))/
+    a
+ 0: a
+
+/(((((((((a)))))))))/
+    a
+ 0: a
+
+/multiple words of text/
+    *** Failers
+No match
+    aa
+No match
+    uh-uh
+No match
+
+/multiple words/
+    multiple words, yeah
+ 0: multiple words
+
+/(.*)c(.*)/
+    abcde
+ 0: abcde
+ 1: abcd
+ 2: abc
+
+/\((.*), (.*)\)/
+    (a, b)
+ 0: (a, b)
+
+/[k]/
+
+/abcd/
+    abcd
+ 0: abcd
+
+/a(bc)d/
+    abcd
+ 0: abcd
+
+/a[-]?c/
+    ac
+ 0: ac
+
+/abc/i
+    ABC
+ 0: ABC
+    XABCY
+ 0: ABC
+    ABABC
+ 0: ABC
+    *** Failers
+No match
+    aaxabxbaxbbx
+No match
+    XBC
+No match
+    AXC
+No match
+    ABX
+No match
+
+/ab*c/i
+    ABC
+ 0: ABC
+
+/ab*bc/i
+    ABC
+ 0: ABC
+    ABBC
+ 0: ABBC
+
+/ab*?bc/i
+    ABBBBC
+ 0: ABBBBC
+
+/ab{0,}?bc/i
+    ABBBBC
+ 0: ABBBBC
+
+/ab+?bc/i
+    ABBC
+ 0: ABBC
+
+/ab+bc/i
+    *** Failers
+No match
+    ABC
+No match
+    ABQ
+No match
+
+/ab{1,}bc/i
+
+/ab+bc/i
+    ABBBBC
+ 0: ABBBBC
+
+/ab{1,}?bc/i
+    ABBBBC
+ 0: ABBBBC
+
+/ab{1,3}?bc/i
+    ABBBBC
+ 0: ABBBBC
+
+/ab{3,4}?bc/i
+    ABBBBC
+ 0: ABBBBC
+
+/ab{4,5}?bc/i
+    *** Failers
+No match
+    ABQ
+No match
+    ABBBBC
+No match
+
+/ab??bc/i
+    ABBC
+ 0: ABBC
+    ABC
+ 0: ABC
+
+/ab{0,1}?bc/i
+    ABC
+ 0: ABC
+
+/ab??bc/i
+
+/ab??c/i
+    ABC
+ 0: ABC
+
+/ab{0,1}?c/i
+    ABC
+ 0: ABC
+
+/^abc$/i
+    ABC
+ 0: ABC
+    *** Failers
+No match
+    ABBBBC
+No match
+    ABCC
+No match
+
+/^abc/i
+    ABCC
+ 0: ABC
+
+/^abc$/i
+
+/abc$/i
+    AABC
+ 0: ABC
+
+/^/i
+    ABC
+ 0: 
+
+/$/i
+    ABC
+ 0: 
+
+/a.c/i
+    ABC
+ 0: ABC
+    AXC
+ 0: AXC
+
+/a.*?c/i
+    AXYZC
+ 0: AXYZC
+
+/a.*c/i
+    *** Failers
+No match
+    AABC
+ 0: AABC
+    AXYZD
+No match
+
+/a[bc]d/i
+    ABD
+ 0: ABD
+
+/a[b-d]e/i
+    ACE
+ 0: ACE
+    *** Failers
+No match
+    ABC
+No match
+    ABD
+No match
+
+/a[b-d]/i
+    AAC
+ 0: AC
+
+/a[-b]/i
+    A-
+ 0: A-
+
+/a[b-]/i
+    A-
+ 0: A-
+
+/a]/i
+    A]
+ 0: A]
+
+/a[]]b/i
+    A]B
+ 0: A]B
+
+/a[^bc]d/i
+    AED
+ 0: AED
+
+/a[^-b]c/i
+    ADC
+ 0: ADC
+    *** Failers
+No match
+    ABD
+No match
+    A-C
+No match
+
+/a[^]b]c/i
+    ADC
+ 0: ADC
+
+/ab|cd/i
+    ABC
+ 0: AB
+    ABCD
+ 0: AB
+
+/()ef/i
+    DEF
+ 0: EF
+
+/$b/i
+    *** Failers
+No match
+    A]C
+No match
+    B
+No match
+
+/a\(b/i
+    A(B
+ 0: A(B
+
+/a\(*b/i
+    AB
+ 0: AB
+    A((B
+ 0: A((B
+
+/a\\b/i
+    A\B
+No match
+
+/((a))/i
+    ABC
+ 0: A
+
+/(a)b(c)/i
+    ABC
+ 0: ABC
+
+/a+b+c/i
+    AABBABC
+ 0: ABC
+
+/a{1,}b{1,}c/i
+    AABBABC
+ 0: ABC
+
+/a.+?c/i
+    ABCABC
+ 0: ABCABC
+ 1: ABC
+
+/a.*?c/i
+    ABCABC
+ 0: ABCABC
+ 1: ABC
+
+/a.{0,5}?c/i
+    ABCABC
+ 0: ABCABC
+ 1: ABC
+
+/(a+|b)*/i
+    AB
+ 0: AB
+ 1: A
+ 2: 
+
+/(a+|b){0,}/i
+    AB
+ 0: AB
+ 1: A
+ 2: 
+
+/(a+|b)+/i
+    AB
+ 0: AB
+ 1: A
+
+/(a+|b){1,}/i
+    AB
+ 0: AB
+ 1: A
+
+/(a+|b)?/i
+    AB
+ 0: A
+ 1: 
+
+/(a+|b){0,1}/i
+    AB
+ 0: A
+ 1: 
+
+/(a+|b){0,1}?/i
+    AB
+ 0: A
+ 1: 
+
+/[^ab]*/i
+    CDE
+ 0: CDE
+ 1: CD
+ 2: C
+ 3: 
+
+/abc/i
+
+/a*/i
+    
+
+/([abc])*d/i
+    ABBBCD
+ 0: ABBBCD
+
+/([abc])*bcd/i
+    ABCD
+ 0: ABCD
+
+/a|b|c|d|e/i
+    E
+ 0: E
+
+/(a|b|c|d|e)f/i
+    EF
+ 0: EF
+
+/abcd*efg/i
+    ABCDEFG
+ 0: ABCDEFG
+
+/ab*/i
+    XABYABBBZ
+ 0: AB
+ 1: A
+    XAYABBBZ
+ 0: A
+
+/(ab|cd)e/i
+    ABCDE
+ 0: CDE
+
+/[abhgefdc]ij/i
+    HIJ
+ 0: HIJ
+
+/^(ab|cd)e/i
+    ABCDE
+No match
+
+/(abc|)ef/i
+    ABCDEF
+ 0: EF
+
+/(a|b)c*d/i
+    ABCD
+ 0: BCD
+
+/(ab|ab*)bc/i
+    ABC
+ 0: ABC
+
+/a([bc]*)c*/i
+    ABC
+ 0: ABC
+ 1: AB
+ 2: A
+
+/a([bc]*)(c*d)/i
+    ABCD
+ 0: ABCD
+
+/a([bc]+)(c*d)/i
+    ABCD
+ 0: ABCD
+
+/a([bc]*)(c+d)/i
+    ABCD
+ 0: ABCD
+
+/a[bcd]*dcdcde/i
+    ADCDCDE
+ 0: ADCDCDE
+
+/a[bcd]+dcdcde/i
+
+/(ab|a)b*c/i
+    ABC
+ 0: ABC
+
+/((a)(b)c)(d)/i
+    ABCD
+ 0: ABCD
+
+/[a-zA-Z_][a-zA-Z0-9_]*/i
+    ALPHA
+ 0: ALPHA
+ 1: ALPH
+ 2: ALP
+ 3: AL
+ 4: A
+
+/^a(bc+|b[eh])g|.h$/i
+    ABH
+ 0: BH
+
+/(bc+d$|ef*g.|h?i(j|k))/i
+    EFFGZ
+ 0: EFFGZ
+    IJ
+ 0: IJ
+    REFFGZ
+ 0: EFFGZ
+    *** Failers
+No match
+    ADCDCDE
+No match
+    EFFG
+No match
+    BCDD
+No match
+
+/((((((((((a))))))))))/i
+    A
+ 0: A
+
+/(((((((((a)))))))))/i
+    A
+ 0: A
+
+/(?:(?:(?:(?:(?:(?:(?:(?:(?:(a))))))))))/i
+    A
+ 0: A
+
+/(?:(?:(?:(?:(?:(?:(?:(?:(?:(a|b|c))))))))))/i
+    C
+ 0: C
+
+/multiple words of text/i
+    *** Failers
+No match
+    AA
+No match
+    UH-UH
+No match
+
+/multiple words/i
+    MULTIPLE WORDS, YEAH
+ 0: MULTIPLE WORDS
+
+/(.*)c(.*)/i
+    ABCDE
+ 0: ABCDE
+ 1: ABCD
+ 2: ABC
+
+/\((.*), (.*)\)/i
+    (A, B)
+ 0: (A, B)
+
+/[k]/i
+
+/abcd/i
+    ABCD
+ 0: ABCD
+
+/a(bc)d/i
+    ABCD
+ 0: ABCD
+
+/a[-]?c/i
+    AC
+ 0: AC
+
+/a(?!b)./
+    abad
+ 0: ad
+
+/a(?=d)./
+    abad
+ 0: ad
+
+/a(?=c|d)./
+    abad
+ 0: ad
+
+/a(?:b|c|d)(.)/
+    ace
+ 0: ace
+
+/a(?:b|c|d)*(.)/
+    ace
+ 0: ace
+ 1: ac
+
+/a(?:b|c|d)+?(.)/
+    ace
+ 0: ace
+    acdbcdbe
+ 0: acdbcdbe
+ 1: acdbcdb
+ 2: acdbcd
+ 3: acdbc
+ 4: acdb
+ 5: acd
+
+/a(?:b|c|d)+(.)/
+    acdbcdbe
+ 0: acdbcdbe
+ 1: acdbcdb
+ 2: acdbcd
+ 3: acdbc
+ 4: acdb
+ 5: acd
+
+/a(?:b|c|d){2}(.)/
+    acdbcdbe
+ 0: acdb
+
+/a(?:b|c|d){4,5}(.)/
+    acdbcdbe
+ 0: acdbcdb
+ 1: acdbcd
+
+/a(?:b|c|d){4,5}?(.)/
+    acdbcdbe
+ 0: acdbcdb
+ 1: acdbcd
+
+/((foo)|(bar))*/
+    foobar
+ 0: foobar
+ 1: foo
+ 2: 
+
+/a(?:b|c|d){6,7}(.)/
+    acdbcdbe
+ 0: acdbcdbe
+
+/a(?:b|c|d){6,7}?(.)/
+    acdbcdbe
+ 0: acdbcdbe
+
+/a(?:b|c|d){5,6}(.)/
+    acdbcdbe
+ 0: acdbcdbe
+ 1: acdbcdb
+
+/a(?:b|c|d){5,6}?(.)/
+    acdbcdbe
+ 0: acdbcdbe
+ 1: acdbcdb
+
+/a(?:b|c|d){5,7}(.)/
+    acdbcdbe
+ 0: acdbcdbe
+ 1: acdbcdb
+
+/a(?:b|c|d){5,7}?(.)/
+    acdbcdbe
+ 0: acdbcdbe
+ 1: acdbcdb
+
+/a(?:b|(c|e){1,2}?|d)+?(.)/
+    ace
+ 0: ace
+
+/^(.+)?B/
+    AB
+ 0: AB
+
+/^([^a-z])|(\^)$/
+    .
+ 0: .
+
+/^[<>]&/
+    <&OUT
+ 0: <&
+
+/(?:(f)(o)(o)|(b)(a)(r))*/
+    foobar
+ 0: foobar
+ 1: foo
+ 2: 
+
+/(?<=a)b/
+    ab
+ 0: b
+    *** Failers
+No match
+    cb
+No match
+    b
+No match
+
+/(?<!c)b/
+    ab
+ 0: b
+    b
+ 0: b
+    b
+ 0: b
+
+/(?:..)*a/
+    aba
+ 0: aba
+ 1: a
+
+/(?:..)*?a/
+    aba
+ 0: aba
+ 1: a
+
+/^(){3,5}/
+    abc
+ 0: 
+
+/^(a+)*ax/
+    aax
+ 0: aax
+
+/^((a|b)+)*ax/
+    aax
+ 0: aax
+
+/^((a|bc)+)*ax/
+    aax
+ 0: aax
+
+/(a|x)*ab/
+    cab
+ 0: ab
+
+/(a)*ab/
+    cab
+ 0: ab
+
+/(?:(?i)a)b/
+    ab
+ 0: ab
+
+/((?i)a)b/
+    ab
+ 0: ab
+
+/(?:(?i)a)b/
+    Ab
+ 0: Ab
+
+/((?i)a)b/
+    Ab
+ 0: Ab
+
+/(?:(?i)a)b/
+    *** Failers
+No match
+    cb
+No match
+    aB
+No match
+
+/((?i)a)b/
+
+/(?i:a)b/
+    ab
+ 0: ab
+
+/((?i:a))b/
+    ab
+ 0: ab
+
+/(?i:a)b/
+    Ab
+ 0: Ab
+
+/((?i:a))b/
+    Ab
+ 0: Ab
+
+/(?i:a)b/
+    *** Failers
+No match
+    aB
+No match
+    aB
+No match
+
+/((?i:a))b/
+
+/(?:(?-i)a)b/i
+    ab
+ 0: ab
+
+/((?-i)a)b/i
+    ab
+ 0: ab
+
+/(?:(?-i)a)b/i
+    aB
+ 0: aB
+
+/((?-i)a)b/i
+    aB
+ 0: aB
+
+/(?:(?-i)a)b/i
+    *** Failers
+No match
+    aB
+ 0: aB
+    Ab
+No match
+
+/((?-i)a)b/i
+
+/(?:(?-i)a)b/i
+    aB
+ 0: aB
+
+/((?-i)a)b/i
+    aB
+ 0: aB
+
+/(?:(?-i)a)b/i
+    *** Failers
+No match
+    Ab
+No match
+    AB
+No match
+
+/((?-i)a)b/i
+
+/(?-i:a)b/i
+    ab
+ 0: ab
+
+/((?-i:a))b/i
+    ab
+ 0: ab
+
+/(?-i:a)b/i
+    aB
+ 0: aB
+
+/((?-i:a))b/i
+    aB
+ 0: aB
+
+/(?-i:a)b/i
+    *** Failers
+No match
+    AB
+No match
+    Ab
+No match
+
+/((?-i:a))b/i
+
+/(?-i:a)b/i
+    aB
+ 0: aB
+
+/((?-i:a))b/i
+    aB
+ 0: aB
+
+/(?-i:a)b/i
+    *** Failers
+No match
+    Ab
+No match
+    AB
+No match
+
+/((?-i:a))b/i
+
+/((?-i:a.))b/i
+    *** Failers
+No match
+    AB
+No match
+    a\nB
+No match
+
+/((?s-i:a.))b/i
+    a\nB
+ 0: a\x0aB
+
+/(?:c|d)(?:)(?:a(?:)(?:b)(?:b(?:))(?:b(?:)(?:b)))/
+    cabbbb
+ 0: cabbbb
+
+/(?:c|d)(?:)(?:aaaaaaaa(?:)(?:bbbbbbbb)(?:bbbbbbbb(?:))(?:bbbbbbbb(?:)(?:bbbbbbbb)))/
+    caaaaaaaabbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbb
+ 0: caaaaaaaabbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbb
+
+/foo\w*\d{4}baz/
+    foobar1234baz
+ 0: foobar1234baz
+
+/x(~~)*(?:(?:F)?)?/
+    x~~
+ 0: x~~
+ 1: x
+
+/^a(?#xxx){3}c/
+    aaac
+ 0: aaac
+
+/^a (?#xxx) (?#yyy) {3}c/x
+    aaac
+ 0: aaac
+
+/(?<![cd])b/
+    *** Failers
+No match
+    B\nB
+No match
+    dbcb
+No match
+
+/(?<![cd])[ab]/
+    dbaacb
+ 0: a
+
+/(?<!(c|d))b/
+
+/(?<!(c|d))[ab]/
+    dbaacb
+ 0: a
+
+/(?<!cd)[ab]/
+    cdaccb
+ 0: b
+
+/^(?:a?b?)*$/
+    *** Failers
+No match
+    dbcb
+No match
+    a--
+No match
+
+/((?s)^a(.))((?m)^b$)/
+    a\nb\nc\n
+ 0: a\x0ab
+
+/((?m)^b$)/
+    a\nb\nc\n
+ 0: b
+
+/(?m)^b/
+    a\nb\n
+ 0: b
+
+/(?m)^(b)/
+    a\nb\n
+ 0: b
+
+/((?m)^b)/
+    a\nb\n
+ 0: b
+
+/\n((?m)^b)/
+    a\nb\n
+ 0: \x0ab
+
+/((?s).)c(?!.)/
+    a\nb\nc\n
+ 0: \x0ac
+    a\nb\nc\n
+ 0: \x0ac
+
+/((?s)b.)c(?!.)/
+    a\nb\nc\n
+ 0: b\x0ac
+    a\nb\nc\n
+ 0: b\x0ac
+
+/^b/
+
+/()^b/
+    *** Failers
+No match
+    a\nb\nc\n
+No match
+    a\nb\nc\n
+No match
+
+/((?m)^b)/
+    a\nb\nc\n
+ 0: b
+
+/(?(?!a)a|b)/
+
+/(?(?!a)b|a)/
+    a
+ 0: a
+
+/(?(?=a)b|a)/
+    *** Failers
+No match
+    a
+No match
+    a
+No match
+
+/(?(?=a)a|b)/
+    a
+ 0: a
+
+/(\w+:)+/
+    one:
+ 0: one:
+
+/$(?<=^(a))/
+    a
+ 0: 
+
+/([\w:]+::)?(\w+)$/
+    abcd
+ 0: abcd
+    xy:z:::abcd
+ 0: xy:z:::abcd
+
+/^[^bcd]*(c+)/
+    aexycd
+ 0: aexyc
+
+/(a*)b+/
+    caab
+ 0: aab
+
+/([\w:]+::)?(\w+)$/
+    abcd
+ 0: abcd
+    xy:z:::abcd
+ 0: xy:z:::abcd
+    *** Failers
+ 0: Failers
+    abcd:
+No match
+    abcd:
+No match
+
+/^[^bcd]*(c+)/
+    aexycd
+ 0: aexyc
+
+/(>a+)ab/
+
+/(?>a+)b/
+    aaab
+ 0: aaab
+
+/([[:]+)/
+    a:[b]:
+ 0: :[
+ 1: :
+
+/([[=]+)/
+    a=[b]=
+ 0: =[
+ 1: =
+
+/([[.]+)/
+    a.[b].
+ 0: .[
+ 1: .
+
+/((?>a+)b)/
+    aaab
+ 0: aaab
+
+/(?>(a+))b/
+    aaab
+ 0: aaab
+
+/((?>[^()]+)|\([^()]*\))+/
+    ((abc(ade)ufh()()x
+ 0: abc(ade)ufh()()x
+ 1: abc(ade)ufh()()
+ 2: abc(ade)ufh()
+ 3: abc(ade)ufh
+ 4: abc(ade)
+ 5: abc
+
+/a\Z/
+    *** Failers
+No match
+    aaab
+No match
+    a\nb\n
+No match
+
+/b\Z/
+    a\nb\n
+ 0: b
+
+/b\z/
+
+/b\Z/
+    a\nb
+ 0: b
+
+/b\z/
+    a\nb
+ 0: b
+    *** Failers
+No match
+    
+/(?>.*)(?<=(abcd|wxyz))/
+    alphabetabcd
+ 0: alphabetabcd
+    endingwxyz
+ 0: endingwxyz
+    *** Failers
+No match
+    a rather long string that doesn't end with one of them
+No match
+
+/word (?>(?:(?!otherword)[a-zA-Z0-9]+ ){0,30})otherword/
+    word cat dog elephant mussel cow horse canary baboon snake shark otherword
+ 0: word cat dog elephant mussel cow horse canary baboon snake shark otherword
+    word cat dog elephant mussel cow horse canary baboon snake shark
+No match
+  
+/word (?>[a-zA-Z0-9]+ ){0,30}otherword/
+    word cat dog elephant mussel cow horse canary baboon snake shark the quick brown fox and the lazy dog and several other words getting close to thirty by now I hope
+No match
+
+/(?<=\d{3}(?!999))foo/
+    999foo
+ 0: foo
+    123999foo 
+ 0: foo
+    *** Failers
+No match
+    123abcfoo
+No match
+    
+/(?<=(?!...999)\d{3})foo/
+    999foo
+ 0: foo
+    123999foo 
+ 0: foo
+    *** Failers
+No match
+    123abcfoo
+No match
+
+/(?<=\d{3}(?!999)...)foo/
+    123abcfoo
+ 0: foo
+    123456foo 
+ 0: foo
+    *** Failers
+No match
+    123999foo  
+No match
+    
+/(?<=\d{3}...)(?<!999)foo/
+    123abcfoo   
+ 0: foo
+    123456foo 
+ 0: foo
+    *** Failers
+No match
+    123999foo  
+No match
+
+/((Z)+|A)*/
+    ZABCDEFG
+ 0: ZA
+ 1: Z
+ 2: 
+
+/(Z()|A)*/
+    ZABCDEFG
+ 0: ZA
+ 1: Z
+ 2: 
+
+/(Z(())|A)*/
+    ZABCDEFG
+ 0: ZA
+ 1: Z
+ 2: 
+
+/((?>Z)+|A)*/
+    ZABCDEFG
+ 0: ZA
+ 1: Z
+ 2: 
+
+/((?>)+|A)*/
+    ZABCDEFG
+ 0: 
+
+/a*/g
+    abbab
+ 0: a
+ 1: 
+ 0: 
+ 0: 
+ 0: a
+ 1: 
+ 0: 
+ 0: 
+
+/^[a-\d]/
+    abcde
+ 0: a
+    -things
+ 0: -
+    0digit
+ 0: 0
+    *** Failers
+No match
+    bcdef    
+No match
+
+/^[\d-a]/
+    abcde
+ 0: a
+    -things
+ 0: -
+    0digit
+ 0: 0
+    *** Failers
+No match
+    bcdef    
+No match
+    
+/[[:space:]]+/
+    > \x09\x0a\x0c\x0d\x0b<
+ 0:  \x09\x0a\x0c\x0d\x0b
+ 1:  \x09\x0a\x0c\x0d
+ 2:  \x09\x0a\x0c
+ 3:  \x09\x0a
+ 4:  \x09
+ 5:  
+     
+/[[:blank:]]+/
+    > \x09\x0a\x0c\x0d\x0b<
+ 0:  \x09
+ 1:  
+     
+/[\s]+/
+    > \x09\x0a\x0c\x0d\x0b<
+ 0:  \x09\x0a\x0c\x0d
+ 1:  \x09\x0a\x0c
+ 2:  \x09\x0a
+ 3:  \x09
+ 4:  
+     
+/\s+/
+    > \x09\x0a\x0c\x0d\x0b<
+ 0:  \x09\x0a\x0c\x0d
+ 1:  \x09\x0a\x0c
+ 2:  \x09\x0a
+ 3:  \x09
+ 4:  
+     
+/ab/x
+    ab
+No match
+
+/(?!\A)x/m
+  a\nxb\n
+ 0: x
+
+/(?!^)x/m
+  a\nxb\n
+No match
+
+/abc\Qabc\Eabc/
+    abcabcabc
+ 0: abcabcabc
+    
+/abc\Q(*+|\Eabc/
+    abc(*+|abc 
+ 0: abc(*+|abc
+
+/   abc\Q abc\Eabc/x
+    abc abcabc
+ 0: abc abcabc
+    *** Failers
+No match
+    abcabcabc  
+No match
+    
+/abc#comment
+    \Q#not comment
+    literal\E/x
+    abc#not comment\n    literal     
+ 0: abc#not comment\x0a    literal
+
+/abc#comment
+    \Q#not comment
+    literal/x
+    abc#not comment\n    literal     
+ 0: abc#not comment\x0a    literal
+
+/abc#comment
+    \Q#not comment
+    literal\E #more comment
+    /x
+    abc#not comment\n    literal     
+ 0: abc#not comment\x0a    literal
+
+/abc#comment
+    \Q#not comment
+    literal\E #more comment/x
+    abc#not comment\n    literal     
+ 0: abc#not comment\x0a    literal
+
+/\Qabc\$xyz\E/
+    abc\\\$xyz
+ 0: abc\$xyz
+
+/\Qabc\E\$\Qxyz\E/
+    abc\$xyz
+ 0: abc$xyz
+
+/\Gabc/
+    abc
+ 0: abc
+    *** Failers
+No match
+    xyzabc  
+No match
+
+/\Gabc./g
+    abc1abc2xyzabc3
+ 0: abc1
+ 0: abc2
+
+/abc./g
+    abc1abc2xyzabc3 
+ 0: abc1
+ 0: abc2
+ 0: abc3
+
+/a(?x: b c )d/
+    XabcdY
+ 0: abcd
+    *** Failers 
+No match
+    Xa b c d Y 
+No match
+
+/((?x)x y z | a b c)/
+    XabcY
+ 0: abc
+    AxyzB 
+ 0: xyz
+
+/(?i)AB(?-i)C/
+    XabCY
+ 0: abC
+    *** Failers
+No match
+    XabcY  
+No match
+
+/((?i)AB(?-i)C|D)E/
+    abCE
+ 0: abCE
+    DE
+ 0: DE
+    *** Failers
+No match
+    abcE
+No match
+    abCe  
+No match
+    dE
+No match
+    De    
+No match
+
+/[z\Qa-d]\E]/
+    z
+ 0: z
+    a
+ 0: a
+    -
+ 0: -
+    d
+ 0: d
+    ] 
+ 0: ]
+    *** Failers
+ 0: a
+    b     
+No match
+
+/[\z\C]/
+    z
+ 0: z
+    C 
+ 0: C
+    
+/\M/
+    M 
+ 0: M
+    
+/(a+)*b/
+    aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa 
+No match
+    
+/(?i)reg(?:ul(?:[aä]|ae)r|ex)/
+    REGular
+ 0: REGular
+    regulaer
+ 0: regulaer
+    Regex  
+ 0: Regex
+    regulär 
+ 0: regul\xe4r
+
+/Åæåä[à-ÿÀ-ß]+/
+    Åæåäà
+ 0: \xc5\xe6\xe5\xe4\xe0
+    Åæåäÿ
+ 0: \xc5\xe6\xe5\xe4\xff
+    ÅæåäÀ
+ 0: \xc5\xe6\xe5\xe4\xc0
+    Åæåäß
+ 0: \xc5\xe6\xe5\xe4\xdf
+
+/(?<=Z)X./
+    \x84XAZXB
+ 0: XB
+
+/^(?(2)a|(1)(2))+$/
+    123a
+Error -17 (backreference condition or recursion test not supported for DFA matching)
+
+/(?<=a|bbbb)c/
+    ac
+ 0: c
+    bbbbc
+ 0: c
+
+/abc/SS>testsavedregex
+Compiled pattern written to testsavedregex
+<testsavedregex
+Compiled pattern loaded from testsavedregex
+No study data
+    abc
+ 0: abc
+    *** Failers
+No match
+    bca
+No match
+    
+/abc/FSS>testsavedregex
+Compiled pattern written to testsavedregex
+<testsavedregex
+Compiled pattern (byte-inverted) loaded from testsavedregex
+No study data
+    abc
+ 0: abc
+    *** Failers
+No match
+    bca
+No match
+
+/(a|b)/S>testsavedregex
+Compiled pattern written to testsavedregex
+Study data written to testsavedregex
+<testsavedregex
+Compiled pattern loaded from testsavedregex
+Study data loaded from testsavedregex
+    abc
+ 0: a
+    *** Failers
+ 0: a
+    def  
+No match
+    
+/(a|b)/SF>testsavedregex
+Compiled pattern written to testsavedregex
+Study data written to testsavedregex
+<testsavedregex
+Compiled pattern (byte-inverted) loaded from testsavedregex
+Study data loaded from testsavedregex
+    abc
+ 0: a
+    *** Failers
+ 0: a
+    def  
+No match
+    
+/line\nbreak/
+    this is a line\nbreak
+ 0: line\x0abreak
+    line one\nthis is a line\nbreak in the second line 
+ 0: line\x0abreak
+
+/line\nbreak/f
+    this is a line\nbreak
+ 0: line\x0abreak
+    ** Failers 
+No match
+    line one\nthis is a line\nbreak in the second line 
+No match
+
+/line\nbreak/mf
+    this is a line\nbreak
+ 0: line\x0abreak
+    ** Failers 
+No match
+    line one\nthis is a line\nbreak in the second line 
+No match
+
+/1234/
+    123\P
+Partial match: 123
+    a4\P\R
+No match
+
+/1234/
+    123\P
+Partial match: 123
+    4\P\R
+ 0: 4
+
+/^/mg
+    a\nb\nc\n
+ 0: 
+ 0: 
+ 0: 
+    \ 
+ 0: 
+    
+/(?<=C\n)^/mg
+    A\nC\nC\n 
+ 0: 
+
+/(?s)A?B/
+    AB
+ 0: AB
+    aB  
+ 0: B
+
+/(?s)A*B/
+    AB
+ 0: AB
+    aB  
+ 0: B
+
+/(?m)A?B/
+    AB
+ 0: AB
+    aB  
+ 0: B
+
+/(?m)A*B/
+    AB
+ 0: AB
+    aB  
+ 0: B
+
+/Content-Type\x3A[^\r\n]{6,}/
+    Content-Type:xxxxxyyy 
+ 0: Content-Type:xxxxxyyy
+ 1: Content-Type:xxxxxyy
+ 2: Content-Type:xxxxxy
+
+/Content-Type\x3A[^\r\n]{6,}z/
+    Content-Type:xxxxxyyyz
+ 0: Content-Type:xxxxxyyyz
+
+/Content-Type\x3A[^a]{6,}/
+    Content-Type:xxxyyy 
+ 0: Content-Type:xxxyyy
+
+/Content-Type\x3A[^a]{6,}z/
+    Content-Type:xxxyyyz
+ 0: Content-Type:xxxyyyz
+
+/^abc/m
+    xyz\nabc
+ 0: abc
+    xyz\nabc\<lf>
+ 0: abc
+    xyz\r\nabc\<lf>
+ 0: abc
+    xyz\rabc\<cr>
+ 0: abc
+    xyz\r\nabc\<crlf>
+ 0: abc
+    ** Failers 
+No match
+    xyz\nabc\<cr>
+No match
+    xyz\r\nabc\<cr>
+No match
+    xyz\nabc\<crlf>
+No match
+    xyz\rabc\<crlf>
+No match
+    xyz\rabc\<lf>
+No match
+    
+/abc$/m<lf>
+    xyzabc
+ 0: abc
+    xyzabc\n 
+ 0: abc
+    xyzabc\npqr 
+ 0: abc
+    xyzabc\r\<cr> 
+ 0: abc
+    xyzabc\rpqr\<cr> 
+ 0: abc
+    xyzabc\r\n\<crlf> 
+ 0: abc
+    xyzabc\r\npqr\<crlf> 
+ 0: abc
+    ** Failers
+No match
+    xyzabc\r 
+No match
+    xyzabc\rpqr 
+No match
+    xyzabc\r\n 
+No match
+    xyzabc\r\npqr 
+No match
+    
+/^abc/m<cr>
+    xyz\rabcdef
+ 0: abc
+    xyz\nabcdef\<lf>
+ 0: abc
+    ** Failers  
+No match
+    xyz\nabcdef
+No match
+       
+/^abc/m<lf>
+    xyz\nabcdef
+ 0: abc
+    xyz\rabcdef\<cr>
+ 0: abc
+    ** Failers  
+No match
+    xyz\rabcdef
+No match
+       
+/^abc/m<crlf>
+    xyz\r\nabcdef
+ 0: abc
+    xyz\rabcdef\<cr>
+ 0: abc
+    ** Failers  
+No match
+    xyz\rabcdef
+No match
+    
+/.*/<lf>
+    abc\ndef
+ 0: abc
+ 1: ab
+ 2: a
+ 3: 
+    abc\rdef
+ 0: abc\x0ddef
+ 1: abc\x0dde
+ 2: abc\x0dd
+ 3: abc\x0d
+ 4: abc
+ 5: ab
+ 6: a
+ 7: 
+    abc\r\ndef
+ 0: abc\x0d
+ 1: abc
+ 2: ab
+ 3: a
+ 4: 
+    \<cr>abc\ndef
+ 0: abc\x0adef
+ 1: abc\x0ade
+ 2: abc\x0ad
+ 3: abc\x0a
+ 4: abc
+ 5: ab
+ 6: a
+ 7: 
+    \<cr>abc\rdef
+ 0: abc
+ 1: ab
+ 2: a
+ 3: 
+    \<cr>abc\r\ndef
+ 0: abc
+ 1: ab
+ 2: a
+ 3: 
+    \<crlf>abc\ndef
+ 0: abc\x0adef
+ 1: abc\x0ade
+ 2: abc\x0ad
+ 3: abc\x0a
+ 4: abc
+ 5: ab
+ 6: a
+ 7: 
+    \<crlf>abc\rdef
+ 0: abc\x0ddef
+ 1: abc\x0dde
+ 2: abc\x0dd
+ 3: abc\x0d
+ 4: abc
+ 5: ab
+ 6: a
+ 7: 
+    \<crlf>abc\r\ndef
+ 0: abc
+ 1: ab
+ 2: a
+ 3: 
+
+/\w+(.)(.)?def/s
+    abc\ndef
+ 0: abc\x0adef
+    abc\rdef
+ 0: abc\x0ddef
+    abc\r\ndef
+ 0: abc\x0d\x0adef
+
+/^\w+=.*(\\\n.*)*/
+    abc=xyz\\\npqr
+ 0: abc=xyz\\x0apqr
+ 1: abc=xyz\\x0apq
+ 2: abc=xyz\\x0ap
+ 3: abc=xyz\\x0a
+ 4: abc=xyz\
+ 5: abc=xyz
+ 6: abc=xy
+ 7: abc=x
+ 8: abc=
+
+/^(a()*)*/
+    aaaa
+ 0: aaaa
+ 1: aaa
+ 2: aa
+ 3: a
+ 4: 
+
+/^(?:a(?:(?:))*)*/
+    aaaa
+ 0: aaaa
+ 1: aaa
+ 2: aa
+ 3: a
+ 4: 
+
+/^(a()+)+/
+    aaaa
+ 0: aaaa
+ 1: aaa
+ 2: aa
+ 3: a
+
+/^(?:a(?:(?:))+)+/
+    aaaa
+ 0: aaaa
+ 1: aaa
+ 2: aa
+ 3: a
+
+/(a|)*\d/
+  aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+No match
+  aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa4
+ 0: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa4
+
+/(?>a|)*\d/
+  aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+No match
+  aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa4
+ 0: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa4
+
+/(?:a|)*\d/
+  aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+No match
+  aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa4
+ 0: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa4
+
+/^a.b/<lf>
+    a\rb
+ 0: a\x0db
+    a\nb\<cr> 
+ 0: a\x0ab
+    ** Failers
+No match
+    a\nb
+No match
+    a\nb\<any>
+No match
+    a\rb\<cr>   
+No match
+    a\rb\<any>   
+No match
+
+/^abc./mgx<any>
+    abc1 \x0aabc2 \x0babc3xx \x0cabc4 \x0dabc5xx \x0d\x0aabc6 \x85abc7 JUNK
+ 0: abc1
+ 0: abc2
+ 0: abc3
+ 0: abc4
+ 0: abc5
+ 0: abc6
+ 0: abc7
+
+/abc.$/mgx<any>
+    abc1\x0a abc2\x0b abc3\x0c abc4\x0d abc5\x0d\x0a abc6\x85 abc9
+ 0: abc1
+ 0: abc2
+ 0: abc3
+ 0: abc4
+ 0: abc5
+ 0: abc6
+ 0: abc9
+
+/^a\Rb/<bsr_unicode>
+    a\nb
+ 0: a\x0ab
+    a\rb
+ 0: a\x0db
+    a\r\nb
+ 0: a\x0d\x0ab
+    a\x0bb
+ 0: a\x0bb
+    a\x0cb
+ 0: a\x0cb
+    a\x85b   
+ 0: a\x85b
+    ** Failers
+No match
+    a\n\rb    
+No match
+
+/^a\R*b/<bsr_unicode>
+    ab
+ 0: ab
+    a\nb
+ 0: a\x0ab
+    a\rb
+ 0: a\x0db
+    a\r\nb
+ 0: a\x0d\x0ab
+    a\x0bb
+ 0: a\x0bb
+    a\x0cb
+ 0: a\x0cb
+    a\x85b   
+ 0: a\x85b
+    a\n\rb    
+ 0: a\x0a\x0db
+    a\n\r\x85\x0cb 
+ 0: a\x0a\x0d\x85\x0cb
+
+/^a\R+b/<bsr_unicode>
+    a\nb
+ 0: a\x0ab
+    a\rb
+ 0: a\x0db
+    a\r\nb
+ 0: a\x0d\x0ab
+    a\x0bb
+ 0: a\x0bb
+    a\x0cb
+ 0: a\x0cb
+    a\x85b   
+ 0: a\x85b
+    a\n\rb    
+ 0: a\x0a\x0db
+    a\n\r\x85\x0cb 
+ 0: a\x0a\x0d\x85\x0cb
+    ** Failers
+No match
+    ab  
+No match
+    
+/^a\R{1,3}b/<bsr_unicode>
+    a\nb
+ 0: a\x0ab
+    a\n\rb
+ 0: a\x0a\x0db
+    a\n\r\x85b
+ 0: a\x0a\x0d\x85b
+    a\r\n\r\nb 
+ 0: a\x0d\x0a\x0d\x0ab
+    a\r\n\r\n\r\nb 
+ 0: a\x0d\x0a\x0d\x0a\x0d\x0ab
+    a\n\r\n\rb
+ 0: a\x0a\x0d\x0a\x0db
+    a\n\n\r\nb 
+ 0: a\x0a\x0a\x0d\x0ab
+    ** Failers
+No match
+    a\n\n\n\rb
+No match
+    a\r
+No match
+
+/^a[\R]b/<bsr_unicode>
+    aRb
+ 0: aRb
+    ** Failers
+No match
+    a\nb  
+No match
+
+/.+foo/
+    afoo
+ 0: afoo
+    ** Failers 
+No match
+    \r\nfoo 
+No match
+    \nfoo 
+No match
+
+/.+foo/<crlf>
+    afoo
+ 0: afoo
+    \nfoo 
+ 0: \x0afoo
+    ** Failers 
+No match
+    \r\nfoo 
+No match
+
+/.+foo/<any>
+    afoo
+ 0: afoo
+    ** Failers 
+No match
+    \nfoo 
+No match
+    \r\nfoo 
+No match
+
+/.+foo/s
+    afoo
+ 0: afoo
+    \r\nfoo 
+ 0: \x0d\x0afoo
+    \nfoo 
+ 0: \x0afoo
+
+/^$/mg<any>
+    abc\r\rxyz
+ 0: 
+    abc\n\rxyz  
+ 0: 
+    ** Failers 
+No match
+    abc\r\nxyz
+No match
+
+/^X/m
+    XABC
+ 0: X
+    ** Failers 
+No match
+    XABC\B
+No match
+
+/(?m)^$/<any>g+
+    abc\r\n\r\n
+ 0: 
+ 0+ \x0d\x0a
+
+/(?m)^$|^\r\n/<any>g+ 
+    abc\r\n\r\n
+ 0: \x0d\x0a
+ 0+ 
+ 1: 
+    
+/(?m)$/<any>g+ 
+    abc\r\n\r\n
+ 0: 
+ 0+ \x0d\x0a\x0d\x0a
+ 0: 
+ 0+ \x0d\x0a
+ 0: 
+ 0+ 
+
+/(?|(abc)|(xyz))/
+   >abc<
+ 0: abc
+   >xyz< 
+ 0: xyz
+
+/(x)(?|(abc)|(xyz))(x)/
+    xabcx
+ 0: xabcx
+    xxyzx 
+ 0: xxyzx
+
+/(x)(?|(abc)(pqr)|(xyz))(x)/
+    xabcpqrx
+ 0: xabcpqrx
+    xxyzx 
+ 0: xxyzx
+
+/(?|(abc)|(xyz))(?1)/
+    abcabc
+ 0: abcabc
+    xyzabc 
+ 0: xyzabc
+    ** Failers 
+No match
+    xyzxyz 
+No match
+ 
+/\H\h\V\v/
+    X X\x0a
+ 0: X X\x0a
+    X\x09X\x0b
+ 0: X\x09X\x0b
+    ** Failers
+No match
+    \xa0 X\x0a   
+No match
+    
+/\H*\h+\V?\v{3,4}/ 
+    \x09\x20\xa0X\x0a\x0b\x0c\x0d\x0a
+ 0: \x09 \xa0X\x0a\x0b\x0c\x0d
+ 1: \x09 \xa0X\x0a\x0b\x0c
+    \x09\x20\xa0\x0a\x0b\x0c\x0d\x0a
+ 0: \x09 \xa0\x0a\x0b\x0c\x0d
+ 1: \x09 \xa0\x0a\x0b\x0c
+    \x09\x20\xa0\x0a\x0b\x0c
+ 0: \x09 \xa0\x0a\x0b\x0c
+    ** Failers 
+No match
+    \x09\x20\xa0\x0a\x0b
+No match
+     
+/\H{3,4}/
+    XY  ABCDE
+ 0: ABCD
+ 1: ABC
+    XY  PQR ST 
+ 0: PQR
+    
+/.\h{3,4}./
+    XY  AB    PQRS
+ 0: B    P
+ 1: B    
+
+/\h*X\h?\H+Y\H?Z/
+    >XNNNYZ
+ 0: XNNNYZ
+    >  X NYQZ
+ 0:   X NYQZ
+    ** Failers
+No match
+    >XYZ   
+No match
+    >  X NY Z
+No match
+
+/\v*X\v?Y\v+Z\V*\x0a\V+\x0b\V{2,3}\x0c/
+    >XY\x0aZ\x0aA\x0bNN\x0c
+ 0: XY\x0aZ\x0aA\x0bNN\x0c
+    >\x0a\x0dX\x0aY\x0a\x0bZZZ\x0aAAA\x0bNNN\x0c
+ 0: \x0a\x0dX\x0aY\x0a\x0bZZZ\x0aAAA\x0bNNN\x0c
+
+/.+A/<crlf>
+    \r\nA
+No match
+    
+/\nA/<crlf>
+    \r\nA 
+ 0: \x0aA
+
+/[\r\n]A/<crlf>
+    \r\nA 
+ 0: \x0aA
+
+/(\r|\n)A/<crlf>
+    \r\nA 
+ 0: \x0aA
+
+/a\Rb/I<bsr_anycrlf>
+Capturing subpattern count = 0
+Options: bsr_anycrlf
+First char = 'a'
+Need char = 'b'
+    a\rb
+ 0: a\x0db
+    a\nb
+ 0: a\x0ab
+    a\r\nb
+ 0: a\x0d\x0ab
+    ** Failers
+No match
+    a\x85b
+No match
+    a\x0bb     
+No match
+
+/a\Rb/I<bsr_unicode>
+Capturing subpattern count = 0
+Options: bsr_unicode
+First char = 'a'
+Need char = 'b'
+    a\rb
+ 0: a\x0db
+    a\nb
+ 0: a\x0ab
+    a\r\nb
+ 0: a\x0d\x0ab
+    a\x85b
+ 0: a\x85b
+    a\x0bb     
+ 0: a\x0bb
+    ** Failers 
+No match
+    a\x85b\<bsr_anycrlf>
+No match
+    a\x0bb\<bsr_anycrlf>
+No match
+    
+/a\R?b/I<bsr_anycrlf>
+Capturing subpattern count = 0
+Options: bsr_anycrlf
+First char = 'a'
+Need char = 'b'
+    a\rb
+ 0: a\x0db
+    a\nb
+ 0: a\x0ab
+    a\r\nb
+ 0: a\x0d\x0ab
+    ** Failers
+No match
+    a\x85b
+No match
+    a\x0bb     
+No match
+
+/a\R?b/I<bsr_unicode>
+Capturing subpattern count = 0
+Options: bsr_unicode
+First char = 'a'
+Need char = 'b'
+    a\rb
+ 0: a\x0db
+    a\nb
+ 0: a\x0ab
+    a\r\nb
+ 0: a\x0d\x0ab
+    a\x85b
+ 0: a\x85b
+    a\x0bb     
+ 0: a\x0bb
+    ** Failers 
+No match
+    a\x85b\<bsr_anycrlf>
+No match
+    a\x0bb\<bsr_anycrlf>
+No match
+    
+/a\R{2,4}b/I<bsr_anycrlf>
+Capturing subpattern count = 0
+Options: bsr_anycrlf
+First char = 'a'
+Need char = 'b'
+    a\r\n\nb
+ 0: a\x0d\x0a\x0ab
+    a\n\r\rb
+ 0: a\x0a\x0d\x0db
+    a\r\n\r\n\r\n\r\nb
+ 0: a\x0d\x0a\x0d\x0a\x0d\x0a\x0d\x0ab
+    ** Failers
+No match
+    a\x85\85b
+No match
+    a\x0b\0bb     
+No match
+
+/a\R{2,4}b/I<bsr_unicode>
+Capturing subpattern count = 0
+Options: bsr_unicode
+First char = 'a'
+Need char = 'b'
+    a\r\rb
+ 0: a\x0d\x0db
+    a\n\n\nb
+ 0: a\x0a\x0a\x0ab
+    a\r\n\n\r\rb
+ 0: a\x0d\x0a\x0a\x0d\x0db
+    a\x85\85b
+No match
+    a\x0b\0bb     
+No match
+    ** Failers 
+No match
+    a\r\r\r\r\rb 
+No match
+    a\x85\85b\<bsr_anycrlf>
+No match
+    a\x0b\0bb\<bsr_anycrlf>
+No match
+    
+/a(?!)|\wbc/
+    abc 
+ 0: abc
+
+/a[]b/<JS>
+    ** Failers
+No match
+    ab
+No match
+
+/a[]+b/<JS>
+    ** Failers
+No match
+    ab 
+No match
+
+/a[]*+b/<JS>
+    ** Failers
+No match
+    ab 
+No match
+
+/a[^]b/<JS>
+    aXb
+ 0: aXb
+    a\nb 
+ 0: a\x0ab
+    ** Failers
+No match
+    ab  
+No match
+    
+/a[^]+b/<JS> 
+    aXb
+ 0: aXb
+    a\nX\nXb 
+ 0: a\x0aX\x0aXb
+    ** Failers
+No match
+    ab  
+No match
+
+/X$/E
+    X
+ 0: X
+    ** Failers 
+No match
+    X\n 
+No match
+
+/X$/
+    X
+ 0: X
+    X\n 
+ 0: X
+
+/xyz/C
+  xyz 
+--->xyz
+ +0 ^       x
+ +1 ^^      y
+ +2 ^ ^     z
+ +3 ^  ^    
+ 0: xyz
+  abcxyz 
+--->abcxyz
+ +0    ^       x
+ +1    ^^      y
+ +2    ^ ^     z
+ +3    ^  ^    
+ 0: xyz
+  abcxyz\Y
+--->abcxyz
+ +0 ^          x
+ +0  ^         x
+ +0   ^        x
+ +0    ^       x
+ +1    ^^      y
+ +2    ^ ^     z
+ +3    ^  ^    
+ 0: xyz
+  ** Failers 
+No match
+  abc
+No match
+  abc\Y
+--->abc
+ +0 ^       x
+ +0  ^      x
+ +0   ^     x
+ +0    ^    x
+No match
+  abcxypqr  
+No match
+  abcxypqr\Y  
+--->abcxypqr
+ +0 ^            x
+ +0  ^           x
+ +0   ^          x
+ +0    ^         x
+ +1    ^^        y
+ +2    ^ ^       z
+ +0     ^        x
+ +0      ^       x
+ +0       ^      x
+ +0        ^     x
+ +0         ^    x
+No match
+
+/(*NO_START_OPT)xyz/C
+  abcxyz 
+--->abcxyz
++15 ^          x
++15  ^         x
++15   ^        x
++15    ^       x
++16    ^^      y
++17    ^ ^     z
++18    ^  ^    
+ 0: xyz
+  
+/(?C)ab/
+  ab
+--->ab
+  0 ^      a
+ 0: ab
+  \C-ab
+ 0: ab
+  
+/ab/C
+  ab
+--->ab
+ +0 ^      a
+ +1 ^^     b
+ +2 ^ ^    
+ 0: ab
+  \C-ab    
+ 0: ab
+
+/^"((?(?=[a])[^"])|b)*"$/C
+    "ab"
+--->"ab"
+ +0 ^        ^
+ +1 ^        "
+ +2 ^^       ((?(?=[a])[^"])|b)*
++21 ^^       "
+ +3 ^^       (?(?=[a])[^"])
++18 ^^       b
+ +5 ^^       (?=[a])
+ +8  ^       [a]
++11  ^^      )
++12 ^^       [^"]
++16 ^ ^      )
++17 ^ ^      |
++21 ^ ^      "
+ +3 ^ ^      (?(?=[a])[^"])
++18 ^ ^      b
+ +5 ^ ^      (?=[a])
+ +8   ^      [a]
++19 ^  ^     )
++21 ^  ^     "
+ +3 ^  ^     (?(?=[a])[^"])
++18 ^  ^     b
+ +5 ^  ^     (?=[a])
+ +8    ^     [a]
++17 ^  ^     |
++22 ^   ^    $
++23 ^   ^    
+ 0: "ab"
+    \C-"ab"
+ 0: "ab"
+
+/\d+X|9+Y/
+    ++++123999\P
+Partial match: 123999
+    ++++123999Y\P
+ 0: 999Y
+
+/Z(*F)/
+    Z\P
+No match
+    ZA\P 
+No match
+    
+/Z(?!)/
+    Z\P 
+No match
+    ZA\P 
+No match
+
+/dog(sbody)?/
+    dogs\P
+ 0: dog
+    dogs\P\P 
+Partial match: dogs
+    
+/dog(sbody)??/
+    dogs\P
+ 0: dog
+    dogs\P\P 
+Partial match: dogs
+
+/dog|dogsbody/
+    dogs\P
+ 0: dog
+    dogs\P\P 
+Partial match: dogs
+ 
+/dogsbody|dog/
+    dogs\P
+ 0: dog
+    dogs\P\P 
+Partial match: dogs
+
+/Z(*F)Q|ZXY/
+    Z\P
+Partial match: Z
+    ZA\P 
+No match
+    X\P 
+No match
+
+/\bthe cat\b/
+    the cat\P
+ 0: the cat
+    the cat\P\P
+Partial match: the cat
+
+/dog(sbody)?/
+    dogs\D\P
+ 0: dog
+    body\D\R
+ 0: body
+
+/dog(sbody)?/
+    dogs\D\P\P
+Partial match: dogs
+    body\D\R
+ 0: body
+
+/abc/
+   abc\P
+ 0: abc
+   abc\P\P
+ 0: abc
+
+/abc\K123/
+    xyzabc123pqr
+Error -16 (item unsupported for DFA matching)
+    
+/(?<=abc)123/
+    xyzabc123pqr 
+ 0: 123
+    xyzabc12\P
+Partial match: abc12
+    xyzabc12\P\P
+Partial match: abc12
+
+/\babc\b/
+    +++abc+++
+ 0: abc
+    +++ab\P
+Partial match: +ab
+    +++ab\P\P  
+Partial match: +ab
+
+/(?=C)/g+
+    ABCDECBA
+ 0: 
+ 0+ CDECBA
+ 0: 
+ 0+ CBA
+
+/(abc|def|xyz)/I
+Capturing subpattern count = 1
+No options
+No first char
+No need char
+    terhjk;abcdaadsfe
+ 0: abc
+    the quick xyz brown fox 
+ 0: xyz
+    \Yterhjk;abcdaadsfe
+ 0: abc
+    \Ythe quick xyz brown fox 
+ 0: xyz
+    ** Failers
+No match
+    thejk;adlfj aenjl;fda asdfasd ehj;kjxyasiupd
+No match
+    \Ythejk;adlfj aenjl;fda asdfasd ehj;kjxyasiupd
+No match
+
+/(abc|def|xyz)/SI
+Capturing subpattern count = 1
+No options
+No first char
+No need char
+Subject length lower bound = 3
+Starting byte set: a d x 
+    terhjk;abcdaadsfe
+ 0: abc
+    the quick xyz brown fox 
+ 0: xyz
+    \Yterhjk;abcdaadsfe
+ 0: abc
+    \Ythe quick xyz brown fox 
+ 0: xyz
+    ** Failers
+No match
+    thejk;adlfj aenjl;fda asdfasd ehj;kjxyasiupd
+No match
+    \Ythejk;adlfj aenjl;fda asdfasd ehj;kjxyasiupd
+No match
+
+/abcd*/+
+    xxxxabcd\P
+ 0: abcd
+ 0+ 
+ 1: abc
+    xxxxabcd\P\P
+Partial match: abcd
+    dddxxx\R 
+ 0: ddd
+ 0+ xxx
+ 1: dd
+ 2: d
+ 3: 
+    xxxxabcd\P\P
+Partial match: abcd
+    xxx\R 
+ 0: 
+ 0+ xxx
+
+/abcd*/i
+    xxxxabcd\P
+ 0: abcd
+ 1: abc
+    xxxxabcd\P\P
+Partial match: abcd
+    XXXXABCD\P
+ 0: ABCD
+ 1: ABC
+    XXXXABCD\P\P
+Partial match: ABCD
+
+/abc\d*/
+    xxxxabc1\P
+ 0: abc1
+ 1: abc
+    xxxxabc1\P\P
+Partial match: abc1
+
+/abc[de]*/
+    xxxxabcde\P
+ 0: abcde
+ 1: abcd
+ 2: abc
+    xxxxabcde\P\P
+Partial match: abcde
+
+/(?:(?1)|B)(A(*F)|C)/
+    ABCD
+ 0: BC
+    CCD
+ 0: CC
+    ** Failers
+No match
+    CAD   
+No match
+
+/^(?:(?1)|B)(A(*F)|C)/
+    CCD
+ 0: CC
+    BCD 
+ 0: BC
+    ** Failers
+No match
+    ABCD
+No match
+    CAD
+No match
+    BAD    
+No match
+
+/^(?!a(*SKIP)b)/
+    ac
+Error -16 (item unsupported for DFA matching)
+    
+/^(?=a(*SKIP)b|ac)/
+    ** Failers
+No match
+    ac
+Error -16 (item unsupported for DFA matching)
+    
+/^(?=a(*THEN)b|ac)/
+    ac
+Error -16 (item unsupported for DFA matching)
+    
+/^(?=a(*PRUNE)b)/
+    ab  
+Error -16 (item unsupported for DFA matching)
+    ** Failers 
+No match
+    ac
+Error -16 (item unsupported for DFA matching)
+
+/^(?(?!a(*SKIP)b))/
+    ac
+Error -16 (item unsupported for DFA matching)
+
+/(?<=abc)def/
+    abc\P\P
+Partial match: abc
+
+/abc$/
+    abc
+ 0: abc
+    abc\P
+ 0: abc
+    abc\P\P
+Partial match: abc
+
+/abc$/m
+    abc
+ 0: abc
+    abc\n
+ 0: abc
+    abc\P\P
+Partial match: abc
+    abc\n\P\P 
+ 0: abc
+    abc\P
+ 0: abc
+    abc\n\P
+ 0: abc
+
+/abc\z/
+    abc
+ 0: abc
+    abc\P
+ 0: abc
+    abc\P\P
+Partial match: abc
+
+/abc\Z/
+    abc
+ 0: abc
+    abc\P
+ 0: abc
+    abc\P\P
+Partial match: abc
+
+/abc\b/
+    abc
+ 0: abc
+    abc\P
+ 0: abc
+    abc\P\P
+Partial match: abc
+
+/abc\B/
+    abc
+No match
+    abc\P
+Partial match: abc
+    abc\P\P
+Partial match: abc
+
+/.+/
+    abc\>0
+ 0: abc
+ 1: ab
+ 2: a
+    abc\>1
+ 0: bc
+ 1: b
+    abc\>2
+ 0: c
+    abc\>3
+No match
+    abc\>4
+Error -24 (bad offset value)
+    abc\>-4 
+Error -24 (bad offset value)
+
+/^(?:a)++\w/
+     aaaab
+ 0: aaaab
+     ** Failers 
+No match
+     aaaa 
+No match
+     bbb 
+No match
+
+/^(?:aa|(?:a)++\w)/
+     aaaab
+ 0: aaaab
+ 1: aa
+     aaaa 
+ 0: aa
+     ** Failers 
+No match
+     bbb 
+No match
+
+/^(?:a)*+\w/
+     aaaab
+ 0: aaaab
+     bbb 
+ 0: b
+     ** Failers 
+No match
+     aaaa 
+No match
+
+/^(a)++\w/
+     aaaab
+ 0: aaaab
+     ** Failers 
+No match
+     aaaa 
+No match
+     bbb 
+No match
+
+/^(a|)++\w/
+     aaaab
+ 0: aaaab
+     ** Failers 
+No match
+     aaaa 
+No match
+     bbb 
+No match
+
+/(?=abc){3}abc/+
+    abcabcabc
+ 0: abc
+ 0+ abcabc
+    ** Failers
+No match
+    xyz  
+No match
+    
+/(?=abc)+abc/+
+    abcabcabc
+ 0: abc
+ 0+ abcabc
+    ** Failers
+No match
+    xyz  
+No match
+    
+/(?=abc)++abc/+
+    abcabcabc
+ 0: abc
+ 0+ abcabc
+    ** Failers
+No match
+    xyz  
+No match
+    
+/(?=abc){0}xyz/
+    xyz 
+ 0: xyz
+
+/(?=abc){1}xyz/
+    ** Failers
+No match
+    xyz 
+No match
+    
+/(?=(a))?./
+    ab
+ 0: a
+    bc
+ 0: b
+      
+/(?=(a))??./
+    ab
+ 0: a
+    bc
+ 0: b
+
+/^(?=(a)){0}b(?1)/
+    backgammon
+ 0: ba
+
+/^(?=(?1))?[az]([abc])d/
+    abd 
+ 0: abd
+    zcdxx 
+ 0: zcd
+
+/^(?!a){0}\w+/
+    aaaaa
+ 0: aaaaa
+ 1: aaaa
+ 2: aaa
+ 3: aa
+ 4: a
+
+/(?<=(abc))?xyz/
+    abcxyz
+ 0: xyz
+    pqrxyz 
+ 0: xyz
+
+/((?2))((?1))/
+    abc
+Error -26 (nested recursion at the same subject position)
+
+/(?(R)a+|(?R)b)/
+    aaaabcde
+ 0: aaaab
+
+/(?(R)a+|((?R))b)/
+    aaaabcde
+ 0: aaaab
+
+/((?(R)a+|(?1)b))/
+    aaaabcde
+ 0: aaaab
+
+/((?(R2)a+|(?1)b))/
+    aaaabcde
+Error -17 (backreference condition or recursion test not supported for DFA matching)
+
+/(?(R)a*(?1)|((?R))b)/
+    aaaabcde
+Error -26 (nested recursion at the same subject position)
+
+/(a+)/
+    \O6aaaa
+Matched, but too many subsidiary matches
+ 0: aaaa
+ 1: aaa
+ 2: aa
+    \O8aaaa
+ 0: aaaa
+ 1: aaa
+ 2: aa
+ 3: a
+
+/ab\Cde/
+    abXde
+ 0: abXde
+    
+/(?<=ab\Cde)X/
+    abZdeX
+ 0: X
+
+/^\R/
+    \r\P
+ 0: \x0d
+    \r\P\P
+Partial match: \x0d
+    
+/^\R{2,3}x/
+    \r\P
+Partial match: \x0d
+    \r\P\P
+Partial match: \x0d
+    \r\r\P 
+Partial match: \x0d\x0d
+    \r\r\P\P
+Partial match: \x0d\x0d
+    \r\r\r\P  
+Partial match: \x0d\x0d\x0d
+    \r\r\r\P\P
+Partial match: \x0d\x0d\x0d
+    \r\rx
+ 0: \x0d\x0dx
+    \r\r\rx    
+ 0: \x0d\x0d\x0dx
+
+/^\R{2,3}?x/
+    \r\P
+Partial match: \x0d
+    \r\P\P
+Partial match: \x0d
+    \r\r\P 
+Partial match: \x0d\x0d
+    \r\r\P\P
+Partial match: \x0d\x0d
+    \r\r\r\P  
+Partial match: \x0d\x0d\x0d
+    \r\r\r\P\P
+Partial match: \x0d\x0d\x0d
+    \r\rx
+ 0: \x0d\x0dx
+    \r\r\rx    
+ 0: \x0d\x0d\x0dx
+    
+/^\R?x/
+    \r\P
+Partial match: \x0d
+    \r\P\P 
+Partial match: \x0d
+    x
+ 0: x
+    \rx  
+ 0: \x0dx
+
+/^\R+x/
+    \r\P
+Partial match: \x0d
+    \r\P\P 
+Partial match: \x0d
+    \r\n\P
+Partial match: \x0d\x0a
+    \r\n\P\P  
+Partial match: \x0d\x0a
+    \rx  
+ 0: \x0dx
+
+/^a$/<CRLF>
+    a\r\P
+Partial match: a\x0d
+    a\r\P\P 
+Partial match: a\x0d
+
+/^a$/m<CRLF>
+    a\r\P
+Partial match: a\x0d
+    a\r\P\P 
+Partial match: a\x0d
+
+/^(a$|a\r)/<CRLF>
+    a\r\P
+ 0: a\x0d
+    a\r\P\P 
+Partial match: a\x0d
+
+/^(a$|a\r)/m<CRLF>
+    a\r\P
+ 0: a\x0d
+    a\r\P\P 
+Partial match: a\x0d
+
+/./<CRLF>
+    \r\P
+ 0: \x0d
+    \r\P\P 
+Partial match: \x0d
+  
+/.{2,3}/<CRLF>
+    \r\P 
+Partial match: \x0d
+    \r\P\P
+Partial match: \x0d
+    \r\r\P
+ 0: \x0d\x0d
+    \r\r\P\P
+Partial match: \x0d\x0d
+    \r\r\r\P
+ 0: \x0d\x0d\x0d
+ 1: \x0d\x0d
+    \r\r\r\P\P     
+Partial match: \x0d\x0d\x0d
+
+/.{2,3}?/<CRLF>
+    \r\P 
+Partial match: \x0d
+    \r\P\P
+Partial match: \x0d
+    \r\r\P
+ 0: \x0d\x0d
+    \r\r\P\P
+Partial match: \x0d\x0d
+    \r\r\r\P
+ 0: \x0d\x0d\x0d
+ 1: \x0d\x0d
+    \r\r\r\P\P     
+Partial match: \x0d\x0d\x0d
+
+/-- Test simple validity check for restarts --/
+
+/abcdef/
+   abc\R
+Error -30 (invalid data in workspace for DFA restart)
+
+/<H((?(?!<H|F>)(.)|(?R))++)*F>/
+    text <H more text <H texting more  hexA0-"\xA0"    hex above 7F-"\xBC" F> text xxxxx <H text F> text F> text2 <H text sample F> more text.
+ 0: <H more text <H texting more  hexA0-"\xa0"    hex above 7F-"\xbc" F> text xxxxx <H text F> text F>
+
+/^(?>.{4})abc|^\w\w.xabcd/
+    xxxxabcd
+ 0: xxxxabcd
+ 1: xxxxabc
+    xx\xa0xabcd 
+ 0: xx\xa0xabcd
+ 1: xx\xa0xabc
+
+/^(.{4}){2}+abc|^\w\w.x\w\w\w\wabcd/
+    xxxxxxxxabcd
+ 0: xxxxxxxxabcd
+ 1: xxxxxxxxabc
+    xx\xa0xxxxxabcd 
+ 0: xx\xa0xxxxxabcd
+ 1: xx\xa0xxxxxabc
+
+/-- End of testinput8 --/
diff --git a/ext/pcre/pcrelib/testdata/testoutput9 b/ext/pcre/pcrelib/testdata/testoutput9
new file mode 100644
index 0000000..95cd618
--- /dev/null
+++ b/ext/pcre/pcrelib/testdata/testoutput9
@@ -0,0 +1,1371 @@
+/-- This set of tests checks UTF-8 support with the DFA matching functionality
+    of pcre_dfa_exec(). The -dfa flag must be used with pcretest when running 
+    it. --/
+
+/\x{100}ab/8
+  \x{100}ab
+ 0: \x{100}ab
+  
+/a\x{100}*b/8
+    ab
+ 0: ab
+    a\x{100}b  
+ 0: a\x{100}b
+    a\x{100}\x{100}b  
+ 0: a\x{100}\x{100}b
+    
+/a\x{100}+b/8
+    a\x{100}b  
+ 0: a\x{100}b
+    a\x{100}\x{100}b  
+ 0: a\x{100}\x{100}b
+    *** Failers 
+No match
+    ab
+No match
+     
+/\bX/8
+    Xoanon
+ 0: X
+    +Xoanon
+ 0: X
+    \x{300}Xoanon 
+ 0: X
+    *** Failers 
+No match
+    YXoanon  
+No match
+    
+/\BX/8
+    YXoanon
+ 0: X
+    *** Failers
+No match
+    Xoanon
+No match
+    +Xoanon    
+No match
+    \x{300}Xoanon 
+No match
+
+/X\b/8
+    X+oanon
+ 0: X
+    ZX\x{300}oanon 
+ 0: X
+    FAX 
+ 0: X
+    *** Failers 
+No match
+    Xoanon  
+No match
+    
+/X\B/8
+    Xoanon  
+ 0: X
+    *** Failers
+No match
+    X+oanon
+No match
+    ZX\x{300}oanon 
+No match
+    FAX 
+No match
+    
+/[^a]/8
+    abcd
+ 0: b
+    a\x{100}   
+ 0: \x{100}
+
+/^[abc\x{123}\x{400}-\x{402}]{2,3}\d/8
+    ab99
+ 0: ab9
+    \x{123}\x{123}45
+ 0: \x{123}\x{123}4
+    \x{400}\x{401}\x{402}6  
+ 0: \x{400}\x{401}\x{402}6
+    *** Failers
+No match
+    d99
+No match
+    \x{123}\x{122}4   
+No match
+    \x{400}\x{403}6  
+No match
+    \x{400}\x{401}\x{402}\x{402}6  
+No match
+
+/a.b/8
+    acb
+ 0: acb
+    a\x7fb
+ 0: a\x{7f}b
+    a\x{100}b 
+ 0: a\x{100}b
+    *** Failers
+No match
+    a\nb  
+No match
+
+/a(.{3})b/8
+    a\x{4000}xyb 
+ 0: a\x{4000}xyb
+    a\x{4000}\x7fyb 
+ 0: a\x{4000}\x{7f}yb
+    a\x{4000}\x{100}yb 
+ 0: a\x{4000}\x{100}yb
+    *** Failers
+No match
+    a\x{4000}b 
+No match
+    ac\ncb 
+No match
+
+/a(.*?)(.)/
+    a\xc0\x88b
+ 0: a\xc0\x88b
+ 1: a\xc0\x88
+ 2: a\xc0
+
+/a(.*?)(.)/8
+    a\x{100}b
+ 0: a\x{100}b
+ 1: a\x{100}
+
+/a(.*)(.)/
+    a\xc0\x88b
+ 0: a\xc0\x88b
+ 1: a\xc0\x88
+ 2: a\xc0
+
+/a(.*)(.)/8
+    a\x{100}b
+ 0: a\x{100}b
+ 1: a\x{100}
+
+/a(.)(.)/
+    a\xc0\x92bcd
+ 0: a\xc0\x92
+
+/a(.)(.)/8
+    a\x{240}bcd
+ 0: a\x{240}b
+
+/a(.?)(.)/
+    a\xc0\x92bcd
+ 0: a\xc0\x92
+ 1: a\xc0
+
+/a(.?)(.)/8
+    a\x{240}bcd
+ 0: a\x{240}b
+ 1: a\x{240}
+
+/a(.??)(.)/
+    a\xc0\x92bcd
+ 0: a\xc0\x92
+ 1: a\xc0
+
+/a(.??)(.)/8
+    a\x{240}bcd
+ 0: a\x{240}b
+ 1: a\x{240}
+
+/a(.{3})b/8
+    a\x{1234}xyb 
+ 0: a\x{1234}xyb
+    a\x{1234}\x{4321}yb 
+ 0: a\x{1234}\x{4321}yb
+    a\x{1234}\x{4321}\x{3412}b 
+ 0: a\x{1234}\x{4321}\x{3412}b
+    *** Failers
+No match
+    a\x{1234}b 
+No match
+    ac\ncb 
+No match
+
+/a(.{3,})b/8
+    a\x{1234}xyb 
+ 0: a\x{1234}xyb
+    a\x{1234}\x{4321}yb 
+ 0: a\x{1234}\x{4321}yb
+    a\x{1234}\x{4321}\x{3412}b 
+ 0: a\x{1234}\x{4321}\x{3412}b
+    axxxxbcdefghijb 
+ 0: axxxxbcdefghijb
+ 1: axxxxb
+    a\x{1234}\x{4321}\x{3412}\x{3421}b 
+ 0: a\x{1234}\x{4321}\x{3412}\x{3421}b
+    *** Failers
+No match
+    a\x{1234}b 
+No match
+
+/a(.{3,}?)b/8
+    a\x{1234}xyb 
+ 0: a\x{1234}xyb
+    a\x{1234}\x{4321}yb 
+ 0: a\x{1234}\x{4321}yb
+    a\x{1234}\x{4321}\x{3412}b 
+ 0: a\x{1234}\x{4321}\x{3412}b
+    axxxxbcdefghijb 
+ 0: axxxxbcdefghijb
+ 1: axxxxb
+    a\x{1234}\x{4321}\x{3412}\x{3421}b 
+ 0: a\x{1234}\x{4321}\x{3412}\x{3421}b
+    *** Failers
+No match
+    a\x{1234}b 
+No match
+
+/a(.{3,5})b/8
+    a\x{1234}xyb 
+ 0: a\x{1234}xyb
+    a\x{1234}\x{4321}yb 
+ 0: a\x{1234}\x{4321}yb
+    a\x{1234}\x{4321}\x{3412}b 
+ 0: a\x{1234}\x{4321}\x{3412}b
+    axxxxbcdefghijb 
+ 0: axxxxb
+    a\x{1234}\x{4321}\x{3412}\x{3421}b 
+ 0: a\x{1234}\x{4321}\x{3412}\x{3421}b
+    axbxxbcdefghijb 
+ 0: axbxxb
+    axxxxxbcdefghijb 
+ 0: axxxxxb
+    *** Failers
+No match
+    a\x{1234}b 
+No match
+    axxxxxxbcdefghijb 
+No match
+
+/a(.{3,5}?)b/8
+    a\x{1234}xyb 
+ 0: a\x{1234}xyb
+    a\x{1234}\x{4321}yb 
+ 0: a\x{1234}\x{4321}yb
+    a\x{1234}\x{4321}\x{3412}b 
+ 0: a\x{1234}\x{4321}\x{3412}b
+    axxxxbcdefghijb 
+ 0: axxxxb
+    a\x{1234}\x{4321}\x{3412}\x{3421}b 
+ 0: a\x{1234}\x{4321}\x{3412}\x{3421}b
+    axbxxbcdefghijb 
+ 0: axbxxb
+    axxxxxbcdefghijb 
+ 0: axxxxxb
+    *** Failers
+No match
+    a\x{1234}b 
+No match
+    axxxxxxbcdefghijb 
+No match
+
+/^[a\x{c0}]/8
+    *** Failers
+No match
+    \x{100}
+No match
+
+/(?<=aXb)cd/8
+    aXbcd
+ 0: cd
+
+/(?<=a\x{100}b)cd/8
+    a\x{100}bcd
+ 0: cd
+
+/(?<=a\x{100000}b)cd/8
+    a\x{100000}bcd
+ 0: cd
+    
+/(?:\x{100}){3}b/8
+    \x{100}\x{100}\x{100}b
+ 0: \x{100}\x{100}\x{100}b
+    *** Failers 
+No match
+    \x{100}\x{100}b
+No match
+
+/\x{ab}/8
+    \x{ab} 
+ 0: \x{ab}
+    \xc2\xab
+ 0: \x{ab}
+    *** Failers 
+No match
+    \x00{ab}
+No match
+
+/(?<=(.))X/8
+    WXYZ
+ 0: X
+    \x{256}XYZ 
+ 0: X
+    *** Failers
+No match
+    XYZ 
+No match
+
+/[^a]+/8g
+    bcd
+ 0: bcd
+ 1: bc
+ 2: b
+    \x{100}aY\x{256}Z 
+ 0: \x{100}
+ 0: Y\x{256}Z
+ 1: Y\x{256}
+ 2: Y
+    
+/^[^a]{2}/8
+    \x{100}bc
+ 0: \x{100}b
+ 
+/^[^a]{2,}/8
+    \x{100}bcAa
+ 0: \x{100}bcA
+ 1: \x{100}bc
+ 2: \x{100}b
+
+/^[^a]{2,}?/8
+    \x{100}bca
+ 0: \x{100}bc
+ 1: \x{100}b
+
+/[^a]+/8ig
+    bcd
+ 0: bcd
+ 1: bc
+ 2: b
+    \x{100}aY\x{256}Z 
+ 0: \x{100}
+ 0: Y\x{256}Z
+ 1: Y\x{256}
+ 2: Y
+    
+/^[^a]{2}/8i
+    \x{100}bc
+ 0: \x{100}b
+ 
+/^[^a]{2,}/8i
+    \x{100}bcAa
+ 0: \x{100}bc
+ 1: \x{100}b
+
+/^[^a]{2,}?/8i
+    \x{100}bca
+ 0: \x{100}bc
+ 1: \x{100}b
+
+/\x{100}{0,0}/8
+    abcd
+ 0: 
+ 
+/\x{100}?/8
+    abcd
+ 0: 
+    \x{100}\x{100} 
+ 0: \x{100}
+ 1: 
+
+/\x{100}{0,3}/8 
+    \x{100}\x{100} 
+ 0: \x{100}\x{100}
+ 1: \x{100}
+ 2: 
+    \x{100}\x{100}\x{100}\x{100} 
+ 0: \x{100}\x{100}\x{100}
+ 1: \x{100}\x{100}
+ 2: \x{100}
+ 3: 
+    
+/\x{100}*/8
+    abce
+ 0: 
+    \x{100}\x{100}\x{100}\x{100} 
+ 0: \x{100}\x{100}\x{100}\x{100}
+ 1: \x{100}\x{100}\x{100}
+ 2: \x{100}\x{100}
+ 3: \x{100}
+ 4: 
+
+/\x{100}{1,1}/8
+    abcd\x{100}\x{100}\x{100}\x{100} 
+ 0: \x{100}
+
+/\x{100}{1,3}/8
+    abcd\x{100}\x{100}\x{100}\x{100} 
+ 0: \x{100}\x{100}\x{100}
+ 1: \x{100}\x{100}
+ 2: \x{100}
+
+/\x{100}+/8
+    abcd\x{100}\x{100}\x{100}\x{100} 
+ 0: \x{100}\x{100}\x{100}\x{100}
+ 1: \x{100}\x{100}\x{100}
+ 2: \x{100}\x{100}
+ 3: \x{100}
+
+/\x{100}{3}/8
+    abcd\x{100}\x{100}\x{100}XX
+ 0: \x{100}\x{100}\x{100}
+
+/\x{100}{3,5}/8
+    abcd\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}XX
+ 0: \x{100}\x{100}\x{100}\x{100}\x{100}
+ 1: \x{100}\x{100}\x{100}\x{100}
+ 2: \x{100}\x{100}\x{100}
+
+/\x{100}{3,}/8
+    abcd\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}XX
+ 0: \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}
+ 1: \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}
+ 2: \x{100}\x{100}\x{100}\x{100}\x{100}
+ 3: \x{100}\x{100}\x{100}\x{100}
+ 4: \x{100}\x{100}\x{100}
+
+/(?<=a\x{100}{2}b)X/8
+    Xyyya\x{100}\x{100}bXzzz
+ 0: X
+
+/\D*/8
+  aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+Matched, but too many subsidiary matches
+ 0: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+ 1: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+ 2: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+ 3: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+ 4: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+ 5: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+ 6: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+ 7: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+ 8: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+ 9: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+10: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+11: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+12: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+13: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+14: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+15: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+16: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+17: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+18: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+19: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+20: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+21: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+
+/\D*/8
+  \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}
+Matched, but too many subsidiary matches
+ 0: \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}
+ 1: \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}
+ 2: \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}
+ 3: \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}
+ 4: \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}
+ 5: \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}
+ 6: \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}
+ 7: \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}
+ 8: \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}
+ 9: \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}
+10: \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}
+11: \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}
+12: \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}
+13: \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}
+14: \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}
+15: \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}
+16: \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}
+17: \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}
+18: \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}
+19: \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}
+20: \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}
+21: \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}
+
+/\D/8
+    1X2
+ 0: X
+    1\x{100}2 
+ 0: \x{100}
+  
+/>\S/8
+    > >X Y
+ 0: >X
+    > >\x{100} Y
+ 0: >\x{100}
+  
+/\d/8
+    \x{100}3
+ 0: 3
+    
+/\s/8
+    \x{100} X
+ 0:  
+    
+/\D+/8
+    12abcd34
+ 0: abcd
+ 1: abc
+ 2: ab
+ 3: a
+    *** Failers
+ 0: *** Failers
+ 1: *** Failer
+ 2: *** Faile
+ 3: *** Fail
+ 4: *** Fai
+ 5: *** Fa
+ 6: *** F
+ 7: *** 
+ 8: ***
+ 9: **
+10: *
+    1234  
+No match
+
+/\D{2,3}/8
+    12abcd34
+ 0: abc
+ 1: ab
+    12ab34
+ 0: ab
+    *** Failers  
+ 0: ***
+ 1: **
+    1234
+No match
+    12a34  
+No match
+
+/\D{2,3}?/8
+    12abcd34
+ 0: abc
+ 1: ab
+    12ab34
+ 0: ab
+    *** Failers  
+ 0: ***
+ 1: **
+    1234
+No match
+    12a34  
+No match
+
+/\d+/8
+    12abcd34
+ 0: 12
+ 1: 1
+    *** Failers
+No match
+
+/\d{2,3}/8
+    12abcd34
+ 0: 12
+    1234abcd
+ 0: 123
+ 1: 12
+    *** Failers  
+No match
+    1.4 
+No match
+
+/\d{2,3}?/8
+    12abcd34
+ 0: 12
+    1234abcd
+ 0: 123
+ 1: 12
+    *** Failers  
+No match
+    1.4 
+No match
+
+/\S+/8
+    12abcd34
+ 0: 12abcd34
+ 1: 12abcd3
+ 2: 12abcd
+ 3: 12abc
+ 4: 12ab
+ 5: 12a
+ 6: 12
+ 7: 1
+    *** Failers
+ 0: ***
+ 1: **
+ 2: *
+    \    \ 
+No match
+
+/\S{2,3}/8
+    12abcd34
+ 0: 12a
+ 1: 12
+    1234abcd
+ 0: 123
+ 1: 12
+    *** Failers
+ 0: ***
+ 1: **
+    \     \  
+No match
+
+/\S{2,3}?/8
+    12abcd34
+ 0: 12a
+ 1: 12
+    1234abcd
+ 0: 123
+ 1: 12
+    *** Failers
+ 0: ***
+ 1: **
+    \     \  
+No match
+
+/>\s+</8
+    12>      <34
+ 0: >      <
+    *** Failers
+No match
+
+/>\s{2,3}</8
+    ab>  <cd
+ 0: >  <
+    ab>   <ce
+ 0: >   <
+    *** Failers
+No match
+    ab>    <cd 
+No match
+
+/>\s{2,3}?</8
+    ab>  <cd
+ 0: >  <
+    ab>   <ce
+ 0: >   <
+    *** Failers
+No match
+    ab>    <cd 
+No match
+
+/\w+/8
+    12      34
+ 0: 12
+ 1: 1
+    *** Failers
+ 0: Failers
+ 1: Failer
+ 2: Faile
+ 3: Fail
+ 4: Fai
+ 5: Fa
+ 6: F
+    +++=*! 
+No match
+
+/\w{2,3}/8
+    ab  cd
+ 0: ab
+    abcd ce
+ 0: abc
+ 1: ab
+    *** Failers
+ 0: Fai
+ 1: Fa
+    a.b.c
+No match
+
+/\w{2,3}?/8
+    ab  cd
+ 0: ab
+    abcd ce
+ 0: abc
+ 1: ab
+    *** Failers
+ 0: Fai
+ 1: Fa
+    a.b.c
+No match
+
+/\W+/8
+    12====34
+ 0: ====
+ 1: ===
+ 2: ==
+ 3: =
+    *** Failers
+ 0: *** 
+ 1: ***
+ 2: **
+ 3: *
+    abcd 
+No match
+
+/\W{2,3}/8
+    ab====cd
+ 0: ===
+ 1: ==
+    ab==cd
+ 0: ==
+    *** Failers
+ 0: ***
+ 1: **
+    a.b.c
+No match
+
+/\W{2,3}?/8
+    ab====cd
+ 0: ===
+ 1: ==
+    ab==cd
+ 0: ==
+    *** Failers
+ 0: ***
+ 1: **
+    a.b.c
+No match
+
+/[\x{100}]/8
+    \x{100}
+ 0: \x{100}
+    Z\x{100}
+ 0: \x{100}
+    \x{100}Z
+ 0: \x{100}
+    *** Failers 
+No match
+
+/[Z\x{100}]/8
+    Z\x{100}
+ 0: Z
+    \x{100}
+ 0: \x{100}
+    \x{100}Z
+ 0: \x{100}
+    *** Failers 
+No match
+
+/[\x{100}\x{200}]/8
+   ab\x{100}cd
+ 0: \x{100}
+   ab\x{200}cd
+ 0: \x{200}
+   *** Failers  
+No match
+
+/[\x{100}-\x{200}]/8
+   ab\x{100}cd
+ 0: \x{100}
+   ab\x{200}cd
+ 0: \x{200}
+   ab\x{111}cd 
+ 0: \x{111}
+   *** Failers  
+No match
+
+/[z-\x{200}]/8
+   ab\x{100}cd
+ 0: \x{100}
+   ab\x{200}cd
+ 0: \x{200}
+   ab\x{111}cd 
+ 0: \x{111}
+   abzcd
+ 0: z
+   ab|cd  
+ 0: |
+   *** Failers  
+No match
+
+/[Q\x{100}\x{200}]/8
+   ab\x{100}cd
+ 0: \x{100}
+   ab\x{200}cd
+ 0: \x{200}
+   Q? 
+ 0: Q
+   *** Failers  
+No match
+
+/[Q\x{100}-\x{200}]/8
+   ab\x{100}cd
+ 0: \x{100}
+   ab\x{200}cd
+ 0: \x{200}
+   ab\x{111}cd 
+ 0: \x{111}
+   Q? 
+ 0: Q
+   *** Failers  
+No match
+
+/[Qz-\x{200}]/8
+   ab\x{100}cd
+ 0: \x{100}
+   ab\x{200}cd
+ 0: \x{200}
+   ab\x{111}cd 
+ 0: \x{111}
+   abzcd
+ 0: z
+   ab|cd  
+ 0: |
+   Q? 
+ 0: Q
+   *** Failers  
+No match
+
+/[\x{100}\x{200}]{1,3}/8
+   ab\x{100}cd
+ 0: \x{100}
+   ab\x{200}cd
+ 0: \x{200}
+   ab\x{200}\x{100}\x{200}\x{100}cd
+ 0: \x{200}\x{100}\x{200}
+ 1: \x{200}\x{100}
+ 2: \x{200}
+   *** Failers  
+No match
+
+/[\x{100}\x{200}]{1,3}?/8
+   ab\x{100}cd
+ 0: \x{100}
+   ab\x{200}cd
+ 0: \x{200}
+   ab\x{200}\x{100}\x{200}\x{100}cd
+ 0: \x{200}\x{100}\x{200}
+ 1: \x{200}\x{100}
+ 2: \x{200}
+   *** Failers  
+No match
+
+/[Q\x{100}\x{200}]{1,3}/8
+   ab\x{100}cd
+ 0: \x{100}
+   ab\x{200}cd
+ 0: \x{200}
+   ab\x{200}\x{100}\x{200}\x{100}cd
+ 0: \x{200}\x{100}\x{200}
+ 1: \x{200}\x{100}
+ 2: \x{200}
+   *** Failers  
+No match
+
+/[Q\x{100}\x{200}]{1,3}?/8
+   ab\x{100}cd
+ 0: \x{100}
+   ab\x{200}cd
+ 0: \x{200}
+   ab\x{200}\x{100}\x{200}\x{100}cd
+ 0: \x{200}\x{100}\x{200}
+ 1: \x{200}\x{100}
+ 2: \x{200}
+   *** Failers  
+No match
+
+/(?<=[\x{100}\x{200}])X/8
+    abc\x{200}X
+ 0: X
+    abc\x{100}X 
+ 0: X
+    *** Failers
+No match
+    X  
+No match
+
+/(?<=[Q\x{100}\x{200}])X/8
+    abc\x{200}X
+ 0: X
+    abc\x{100}X 
+ 0: X
+    abQX 
+ 0: X
+    *** Failers
+No match
+    X  
+No match
+
+/(?<=[\x{100}\x{200}]{3})X/8
+    abc\x{100}\x{200}\x{100}X
+ 0: X
+    *** Failers
+No match
+    abc\x{200}X
+No match
+    X  
+No match
+
+/[^\x{100}\x{200}]X/8
+    AX
+ 0: AX
+    \x{150}X
+ 0: \x{150}X
+    \x{500}X 
+ 0: \x{500}X
+    *** Failers
+No match
+    \x{100}X
+No match
+    \x{200}X   
+No match
+
+/[^Q\x{100}\x{200}]X/8
+    AX
+ 0: AX
+    \x{150}X
+ 0: \x{150}X
+    \x{500}X 
+ 0: \x{500}X
+    *** Failers
+No match
+    \x{100}X
+No match
+    \x{200}X   
+No match
+    QX 
+No match
+
+/[^\x{100}-\x{200}]X/8
+    AX
+ 0: AX
+    \x{500}X 
+ 0: \x{500}X
+    *** Failers
+No match
+    \x{100}X
+No match
+    \x{150}X
+No match
+    \x{200}X   
+No match
+
+/[z-\x{100}]/8i
+    z
+ 0: z
+    Z 
+ 0: Z
+    \x{100}
+ 0: \x{100}
+    *** Failers
+No match
+    \x{102}
+No match
+    y    
+No match
+
+/[\xFF]/
+    >\xff<
+ 0: \xff
+
+/[\xff]/8
+    >\x{ff}<
+ 0: \x{ff}
+
+/[^\xFF]/
+    XYZ
+ 0: X
+
+/[^\xff]/8
+    XYZ
+ 0: X
+    \x{123} 
+ 0: \x{123}
+
+/^[ac]*b/8
+  xb
+No match
+
+/^[ac\x{100}]*b/8
+  xb
+No match
+
+/^[^x]*b/8i
+  xb
+No match
+
+/^[^x]*b/8
+  xb
+No match
+  
+/^\d*b/8
+  xb 
+No match
+
+/(|a)/g8
+    catac
+ 0: 
+ 0: a
+ 1: 
+ 0: 
+ 0: a
+ 1: 
+ 0: 
+ 0: 
+    a\x{256}a 
+ 0: a
+ 1: 
+ 0: 
+ 0: a
+ 1: 
+ 0: 
+
+/^\x{85}$/8i
+    \x{85}
+ 0: \x{85}
+
+/^abc./mgx8<any>
+    abc1 \x0aabc2 \x0babc3xx \x0cabc4 \x0dabc5xx \x0d\x0aabc6 \x{0085}abc7 \x{2028}abc8 \x{2029}abc9 JUNK
+ 0: abc1
+ 0: abc2
+ 0: abc3
+ 0: abc4
+ 0: abc5
+ 0: abc6
+ 0: abc7
+ 0: abc8
+ 0: abc9
+
+/abc.$/mgx8<any>
+    abc1\x0a abc2\x0b abc3\x0c abc4\x0d abc5\x0d\x0a abc6\x{0085} abc7\x{2028} abc8\x{2029} abc9
+ 0: abc1
+ 0: abc2
+ 0: abc3
+ 0: abc4
+ 0: abc5
+ 0: abc6
+ 0: abc7
+ 0: abc8
+ 0: abc9
+
+/^a\Rb/8<bsr_unicode>
+    a\nb
+ 0: a\x{0a}b
+    a\rb
+ 0: a\x{0d}b
+    a\r\nb
+ 0: a\x{0d}\x{0a}b
+    a\x0bb
+ 0: a\x{0b}b
+    a\x0cb
+ 0: a\x{0c}b
+    a\x{85}b   
+ 0: a\x{85}b
+    a\x{2028}b 
+ 0: a\x{2028}b
+    a\x{2029}b 
+ 0: a\x{2029}b
+    ** Failers
+No match
+    a\n\rb    
+No match
+
+/^a\R*b/8<bsr_unicode>
+    ab
+ 0: ab
+    a\nb
+ 0: a\x{0a}b
+    a\rb
+ 0: a\x{0d}b
+    a\r\nb
+ 0: a\x{0d}\x{0a}b
+    a\x0bb
+ 0: a\x{0b}b
+    a\x0c\x{2028}\x{2029}b
+ 0: a\x{0c}\x{2028}\x{2029}b
+    a\x{85}b   
+ 0: a\x{85}b
+    a\n\rb    
+ 0: a\x{0a}\x{0d}b
+    a\n\r\x{85}\x0cb 
+ 0: a\x{0a}\x{0d}\x{85}\x{0c}b
+
+/^a\R+b/8<bsr_unicode>
+    a\nb
+ 0: a\x{0a}b
+    a\rb
+ 0: a\x{0d}b
+    a\r\nb
+ 0: a\x{0d}\x{0a}b
+    a\x0bb
+ 0: a\x{0b}b
+    a\x0c\x{2028}\x{2029}b
+ 0: a\x{0c}\x{2028}\x{2029}b
+    a\x{85}b   
+ 0: a\x{85}b
+    a\n\rb    
+ 0: a\x{0a}\x{0d}b
+    a\n\r\x{85}\x0cb 
+ 0: a\x{0a}\x{0d}\x{85}\x{0c}b
+    ** Failers
+No match
+    ab  
+No match
+
+/^a\R{1,3}b/8<bsr_unicode>
+    a\nb
+ 0: a\x{0a}b
+    a\n\rb
+ 0: a\x{0a}\x{0d}b
+    a\n\r\x{85}b
+ 0: a\x{0a}\x{0d}\x{85}b
+    a\r\n\r\nb 
+ 0: a\x{0d}\x{0a}\x{0d}\x{0a}b
+    a\r\n\r\n\r\nb 
+ 0: a\x{0d}\x{0a}\x{0d}\x{0a}\x{0d}\x{0a}b
+    a\n\r\n\rb
+ 0: a\x{0a}\x{0d}\x{0a}\x{0d}b
+    a\n\n\r\nb 
+ 0: a\x{0a}\x{0a}\x{0d}\x{0a}b
+    ** Failers
+No match
+    a\n\n\n\rb
+No match
+    a\r
+No match
+
+/\h+\V?\v{3,4}/8 
+    \x09\x20\x{a0}X\x0a\x0b\x0c\x0d\x0a
+ 0: \x{09} \x{a0}X\x{0a}\x{0b}\x{0c}\x{0d}
+ 1: \x{09} \x{a0}X\x{0a}\x{0b}\x{0c}
+
+/\V?\v{3,4}/8 
+    \x20\x{a0}X\x0a\x0b\x0c\x0d\x0a
+ 0: X\x{0a}\x{0b}\x{0c}\x{0d}
+ 1: X\x{0a}\x{0b}\x{0c}
+
+/\h+\V?\v{3,4}/8
+    >\x09\x20\x{a0}X\x0a\x0a\x0a<
+ 0: \x{09} \x{a0}X\x{0a}\x{0a}\x{0a}
+
+/\V?\v{3,4}/8
+    >\x09\x20\x{a0}X\x0a\x0a\x0a<
+ 0: X\x{0a}\x{0a}\x{0a}
+
+/\H\h\V\v/8
+    X X\x0a
+ 0: X X\x{0a}
+    X\x09X\x0b
+ 0: X\x{09}X\x{0b}
+    ** Failers
+No match
+    \x{a0} X\x0a   
+No match
+    
+/\H*\h+\V?\v{3,4}/8 
+    \x09\x20\x{a0}X\x0a\x0b\x0c\x0d\x0a
+ 0: \x{09} \x{a0}X\x{0a}\x{0b}\x{0c}\x{0d}
+ 1: \x{09} \x{a0}X\x{0a}\x{0b}\x{0c}
+    \x09\x20\x{a0}\x0a\x0b\x0c\x0d\x0a
+ 0: \x{09} \x{a0}\x{0a}\x{0b}\x{0c}\x{0d}
+ 1: \x{09} \x{a0}\x{0a}\x{0b}\x{0c}
+    \x09\x20\x{a0}\x0a\x0b\x0c
+ 0: \x{09} \x{a0}\x{0a}\x{0b}\x{0c}
+    ** Failers 
+No match
+    \x09\x20\x{a0}\x0a\x0b
+No match
+     
+/\H\h\V\v/8
+    \x{3001}\x{3000}\x{2030}\x{2028}
+ 0: \x{3001}\x{3000}\x{2030}\x{2028}
+    X\x{180e}X\x{85}
+ 0: X\x{180e}X\x{85}
+    ** Failers
+No match
+    \x{2009} X\x0a   
+No match
+    
+/\H*\h+\V?\v{3,4}/8 
+    \x{1680}\x{180e}\x{2007}X\x{2028}\x{2029}\x0c\x0d\x0a
+ 0: \x{1680}\x{180e}\x{2007}X\x{2028}\x{2029}\x{0c}\x{0d}
+ 1: \x{1680}\x{180e}\x{2007}X\x{2028}\x{2029}\x{0c}
+    \x09\x{205f}\x{a0}\x0a\x{2029}\x0c\x{2028}\x0a
+ 0: \x{09}\x{205f}\x{a0}\x{0a}\x{2029}\x{0c}\x{2028}
+ 1: \x{09}\x{205f}\x{a0}\x{0a}\x{2029}\x{0c}
+    \x09\x20\x{202f}\x0a\x0b\x0c
+ 0: \x{09} \x{202f}\x{0a}\x{0b}\x{0c}
+    ** Failers 
+No match
+    \x09\x{200a}\x{a0}\x{2028}\x0b
+No match
+     
+/a\Rb/I8<bsr_anycrlf>
+Capturing subpattern count = 0
+Options: bsr_anycrlf utf
+First char = 'a'
+Need char = 'b'
+    a\rb
+ 0: a\x{0d}b
+    a\nb
+ 0: a\x{0a}b
+    a\r\nb
+ 0: a\x{0d}\x{0a}b
+    ** Failers
+No match
+    a\x{85}b
+No match
+    a\x0bb     
+No match
+
+/a\Rb/I8<bsr_unicode>
+Capturing subpattern count = 0
+Options: bsr_unicode utf
+First char = 'a'
+Need char = 'b'
+    a\rb
+ 0: a\x{0d}b
+    a\nb
+ 0: a\x{0a}b
+    a\r\nb
+ 0: a\x{0d}\x{0a}b
+    a\x{85}b
+ 0: a\x{85}b
+    a\x0bb     
+ 0: a\x{0b}b
+    ** Failers 
+No match
+    a\x{85}b\<bsr_anycrlf>
+No match
+    a\x0bb\<bsr_anycrlf>
+No match
+    
+/a\R?b/I8<bsr_anycrlf>
+Capturing subpattern count = 0
+Options: bsr_anycrlf utf
+First char = 'a'
+Need char = 'b'
+    a\rb
+ 0: a\x{0d}b
+    a\nb
+ 0: a\x{0a}b
+    a\r\nb
+ 0: a\x{0d}\x{0a}b
+    ** Failers
+No match
+    a\x{85}b
+No match
+    a\x0bb     
+No match
+
+/a\R?b/I8<bsr_unicode>
+Capturing subpattern count = 0
+Options: bsr_unicode utf
+First char = 'a'
+Need char = 'b'
+    a\rb
+ 0: a\x{0d}b
+    a\nb
+ 0: a\x{0a}b
+    a\r\nb
+ 0: a\x{0d}\x{0a}b
+    a\x{85}b
+ 0: a\x{85}b
+    a\x0bb     
+ 0: a\x{0b}b
+    ** Failers 
+No match
+    a\x{85}b\<bsr_anycrlf>
+No match
+    a\x0bb\<bsr_anycrlf>
+No match
+ 
+/X/8f<any> 
+    A\x{1ec5}ABCXYZ
+ 0: X
+
+/abcd*/8
+    xxxxabcd\P
+ 0: abcd
+ 1: abc
+    xxxxabcd\P\P
+Partial match: abcd
+
+/abcd*/i8
+    xxxxabcd\P
+ 0: abcd
+ 1: abc
+    xxxxabcd\P\P
+Partial match: abcd
+    XXXXABCD\P
+ 0: ABCD
+ 1: ABC
+    XXXXABCD\P\P
+Partial match: ABCD
+
+/abc\d*/8
+    xxxxabc1\P
+ 0: abc1
+ 1: abc
+    xxxxabc1\P\P
+Partial match: abc1
+
+/abc[de]*/8
+    xxxxabcde\P
+ 0: abcde
+ 1: abcd
+ 2: abc
+    xxxxabcde\P\P
+Partial match: abcde
+
+/\bthe cat\b/8
+    the cat\P
+ 0: the cat
+    the cat\P\P
+Partial match: the cat
+
+/ab\Cde/8
+    abXde
+Error -16 (item unsupported for DFA matching)
+
+/(?<=ab\Cde)X/8
+Failed: \C not allowed in lookbehind assertion at offset 10
+
+/./8<CRLF>
+    \r\P
+ 0: \x{0d}
+    \r\P\P 
+Partial match: \x{0d}
+  
+/.{2,3}/8<CRLF>
+    \r\P 
+Partial match: \x{0d}
+    \r\P\P
+Partial match: \x{0d}
+    \r\r\P
+ 0: \x{0d}\x{0d}
+    \r\r\P\P
+Partial match: \x{0d}\x{0d}
+    \r\r\r\P
+ 0: \x{0d}\x{0d}\x{0d}
+ 1: \x{0d}\x{0d}
+    \r\r\r\P\P     
+Partial match: \x{0d}\x{0d}\x{0d}
+
+/.{2,3}?/8<CRLF>
+    \r\P 
+Partial match: \x{0d}
+    \r\P\P
+Partial match: \x{0d}
+    \r\r\P
+ 0: \x{0d}\x{0d}
+    \r\r\P\P
+Partial match: \x{0d}\x{0d}
+    \r\r\r\P
+ 0: \x{0d}\x{0d}\x{0d}
+ 1: \x{0d}\x{0d}
+    \r\r\r\P\P     
+Partial match: \x{0d}\x{0d}\x{0d}
+
+/[^\x{100}]/8
+    \x{100}\x{101}X
+ 0: \x{101}
+
+/[^\x{100}]+/8
+    \x{100}\x{101}X
+ 0: \x{101}X
+ 1: \x{101}
+
+/-- End of testinput9 --/ 
diff --git a/ext/pcre/pcrelib/ucp.h b/ext/pcre/pcrelib/ucp.h
new file mode 100644
index 0000000..59c3bec
--- /dev/null
+++ b/ext/pcre/pcrelib/ucp.h
@@ -0,0 +1,173 @@
+/*************************************************
+*          Unicode Property Table handler        *
+*************************************************/
+
+#ifndef _UCP_H
+#define _UCP_H
+
+/* This file contains definitions of the property values that are returned by
+the UCD access macros. New values that are added for new releases of Unicode
+should always be at the end of each enum, for backwards compatibility. */
+
+/* These are the general character categories. */
+
+enum {
+  ucp_C,     /* Other */
+  ucp_L,     /* Letter */
+  ucp_M,     /* Mark */
+  ucp_N,     /* Number */
+  ucp_P,     /* Punctuation */
+  ucp_S,     /* Symbol */
+  ucp_Z      /* Separator */
+};
+
+/* These are the particular character types. */
+
+enum {
+  ucp_Cc,    /* Control */
+  ucp_Cf,    /* Format */
+  ucp_Cn,    /* Unassigned */
+  ucp_Co,    /* Private use */
+  ucp_Cs,    /* Surrogate */
+  ucp_Ll,    /* Lower case letter */
+  ucp_Lm,    /* Modifier letter */
+  ucp_Lo,    /* Other letter */
+  ucp_Lt,    /* Title case letter */
+  ucp_Lu,    /* Upper case letter */
+  ucp_Mc,    /* Spacing mark */
+  ucp_Me,    /* Enclosing mark */
+  ucp_Mn,    /* Non-spacing mark */
+  ucp_Nd,    /* Decimal number */
+  ucp_Nl,    /* Letter number */
+  ucp_No,    /* Other number */
+  ucp_Pc,    /* Connector punctuation */
+  ucp_Pd,    /* Dash punctuation */
+  ucp_Pe,    /* Close punctuation */
+  ucp_Pf,    /* Final punctuation */
+  ucp_Pi,    /* Initial punctuation */
+  ucp_Po,    /* Other punctuation */
+  ucp_Ps,    /* Open punctuation */
+  ucp_Sc,    /* Currency symbol */
+  ucp_Sk,    /* Modifier symbol */
+  ucp_Sm,    /* Mathematical symbol */
+  ucp_So,    /* Other symbol */
+  ucp_Zl,    /* Line separator */
+  ucp_Zp,    /* Paragraph separator */
+  ucp_Zs     /* Space separator */
+};
+
+/* These are the script identifications. */
+
+enum {
+  ucp_Arabic,
+  ucp_Armenian,
+  ucp_Bengali,
+  ucp_Bopomofo,
+  ucp_Braille,
+  ucp_Buginese,
+  ucp_Buhid,
+  ucp_Canadian_Aboriginal,
+  ucp_Cherokee,
+  ucp_Common,
+  ucp_Coptic,
+  ucp_Cypriot,
+  ucp_Cyrillic,
+  ucp_Deseret,
+  ucp_Devanagari,
+  ucp_Ethiopic,
+  ucp_Georgian,
+  ucp_Glagolitic,
+  ucp_Gothic,
+  ucp_Greek,
+  ucp_Gujarati,
+  ucp_Gurmukhi,
+  ucp_Han,
+  ucp_Hangul,
+  ucp_Hanunoo,
+  ucp_Hebrew,
+  ucp_Hiragana,
+  ucp_Inherited,
+  ucp_Kannada,
+  ucp_Katakana,
+  ucp_Kharoshthi,
+  ucp_Khmer,
+  ucp_Lao,
+  ucp_Latin,
+  ucp_Limbu,
+  ucp_Linear_B,
+  ucp_Malayalam,
+  ucp_Mongolian,
+  ucp_Myanmar,
+  ucp_New_Tai_Lue,
+  ucp_Ogham,
+  ucp_Old_Italic,
+  ucp_Old_Persian,
+  ucp_Oriya,
+  ucp_Osmanya,
+  ucp_Runic,
+  ucp_Shavian,
+  ucp_Sinhala,
+  ucp_Syloti_Nagri,
+  ucp_Syriac,
+  ucp_Tagalog,
+  ucp_Tagbanwa,
+  ucp_Tai_Le,
+  ucp_Tamil,
+  ucp_Telugu,
+  ucp_Thaana,
+  ucp_Thai,
+  ucp_Tibetan,
+  ucp_Tifinagh,
+  ucp_Ugaritic,
+  ucp_Yi,
+  /* New for Unicode 5.0: */
+  ucp_Balinese,
+  ucp_Cuneiform,
+  ucp_Nko,
+  ucp_Phags_Pa,
+  ucp_Phoenician,
+  /* New for Unicode 5.1: */
+  ucp_Carian,
+  ucp_Cham,
+  ucp_Kayah_Li,
+  ucp_Lepcha,
+  ucp_Lycian,
+  ucp_Lydian,
+  ucp_Ol_Chiki,
+  ucp_Rejang,
+  ucp_Saurashtra,
+  ucp_Sundanese,
+  ucp_Vai,
+  /* New for Unicode 5.2: */
+  ucp_Avestan,
+  ucp_Bamum,
+  ucp_Egyptian_Hieroglyphs,
+  ucp_Imperial_Aramaic,
+  ucp_Inscriptional_Pahlavi,
+  ucp_Inscriptional_Parthian,
+  ucp_Javanese,
+  ucp_Kaithi,
+  ucp_Lisu,
+  ucp_Meetei_Mayek,
+  ucp_Old_South_Arabian,
+  ucp_Old_Turkic,
+  ucp_Samaritan,
+  ucp_Tai_Tham,
+  ucp_Tai_Viet,
+  /* New for Unicode 6.0.0: */
+  ucp_Batak,
+  ucp_Brahmi,
+  ucp_Mandaic,
+  /* New for Unicode 6.1.0: */
+  ucp_Chakma,
+  ucp_Meroitic_Cursive,
+  ucp_Meroitic_Hieroglyphs,
+  ucp_Miao,
+  ucp_Sharada,
+  ucp_Sora_Sompeng,
+  ucp_Takri
+};
+
+#endif
+
+/* End of ucp.h */
diff --git a/ext/pcre/php_pcre.c b/ext/pcre/php_pcre.c
new file mode 100644
index 0000000..b74b812
--- /dev/null
+++ b/ext/pcre/php_pcre.c
@@ -0,0 +1,1960 @@
+/*
+   +----------------------------------------------------------------------+
+   | PHP Version 5                                                        |
+   +----------------------------------------------------------------------+
+   | Copyright (c) 1997-2013 The PHP Group                                |
+   +----------------------------------------------------------------------+
+   | This source file is subject to version 3.01 of the PHP license,      |
+   | that is bundled with this package in the file LICENSE, and is        |
+   | available through the world-wide-web at the following url:           |
+   | http://www.php.net/license/3_01.txt                                  |
+   | If you did not receive a copy of the PHP license and are unable to   |
+   | obtain it through the world-wide-web, please send a note to          |
+   | license@php.net so we can mail you a copy immediately.               |
+   +----------------------------------------------------------------------+
+   | Author: Andrei Zmievski <andrei@php.net>                             |
+   +----------------------------------------------------------------------+
+ */
+
+/* $Id$ */
+
+#include "php.h"
+#include "php_ini.h"
+#include "php_globals.h"
+#include "php_pcre.h"
+#include "ext/standard/info.h"
+#include "ext/standard/php_smart_str.h"
+
+#if HAVE_PCRE || HAVE_BUNDLED_PCRE
+
+#include "ext/standard/php_string.h"
+
+#define PREG_PATTERN_ORDER			1
+#define PREG_SET_ORDER				2
+#define PREG_OFFSET_CAPTURE			(1<<8)
+
+#define	PREG_SPLIT_NO_EMPTY			(1<<0)
+#define PREG_SPLIT_DELIM_CAPTURE	(1<<1)
+#define PREG_SPLIT_OFFSET_CAPTURE	(1<<2)
+
+#define PREG_REPLACE_EVAL			(1<<0)
+
+#define PREG_GREP_INVERT			(1<<0)
+
+#define PCRE_CACHE_SIZE 4096
+
+enum {
+	PHP_PCRE_NO_ERROR = 0,
+	PHP_PCRE_INTERNAL_ERROR,
+	PHP_PCRE_BACKTRACK_LIMIT_ERROR,
+	PHP_PCRE_RECURSION_LIMIT_ERROR,
+	PHP_PCRE_BAD_UTF8_ERROR,
+	PHP_PCRE_BAD_UTF8_OFFSET_ERROR
+};
+
+
+ZEND_DECLARE_MODULE_GLOBALS(pcre)
+
+
+static void pcre_handle_exec_error(int pcre_code TSRMLS_DC) /* {{{ */
+{
+	int preg_code = 0;
+
+	switch (pcre_code) {
+		case PCRE_ERROR_MATCHLIMIT:
+			preg_code = PHP_PCRE_BACKTRACK_LIMIT_ERROR;
+			break;
+
+		case PCRE_ERROR_RECURSIONLIMIT:
+			preg_code = PHP_PCRE_RECURSION_LIMIT_ERROR;
+			break;
+
+		case PCRE_ERROR_BADUTF8:
+			preg_code = PHP_PCRE_BAD_UTF8_ERROR;
+			break;
+
+		case PCRE_ERROR_BADUTF8_OFFSET:
+			preg_code = PHP_PCRE_BAD_UTF8_OFFSET_ERROR;
+			break;
+
+		default:
+			preg_code = PHP_PCRE_INTERNAL_ERROR;
+			break;
+	}
+
+	PCRE_G(error_code) = preg_code;
+}
+/* }}} */
+
+static void php_free_pcre_cache(void *data) /* {{{ */
+{
+	pcre_cache_entry *pce = (pcre_cache_entry *) data;
+	if (!pce) return;
+	pefree(pce->re, 1);
+	if (pce->extra) pefree(pce->extra, 1);
+#if HAVE_SETLOCALE
+	if ((void*)pce->tables) pefree((void*)pce->tables, 1);
+	pefree(pce->locale, 1);
+#endif
+}
+/* }}} */
+
+static PHP_GINIT_FUNCTION(pcre) /* {{{ */
+{
+	zend_hash_init(&pcre_globals->pcre_cache, 0, NULL, php_free_pcre_cache, 1);
+	pcre_globals->backtrack_limit = 0;
+	pcre_globals->recursion_limit = 0;
+	pcre_globals->error_code      = PHP_PCRE_NO_ERROR;
+}
+/* }}} */
+
+static PHP_GSHUTDOWN_FUNCTION(pcre) /* {{{ */
+{
+	zend_hash_destroy(&pcre_globals->pcre_cache);
+}
+/* }}} */
+
+PHP_INI_BEGIN()
+	STD_PHP_INI_ENTRY("pcre.backtrack_limit", "1000000", PHP_INI_ALL, OnUpdateLong, backtrack_limit, zend_pcre_globals, pcre_globals)
+	STD_PHP_INI_ENTRY("pcre.recursion_limit", "100000", PHP_INI_ALL, OnUpdateLong, recursion_limit, zend_pcre_globals, pcre_globals)
+PHP_INI_END()
+
+
+/* {{{ PHP_MINFO_FUNCTION(pcre) */
+static PHP_MINFO_FUNCTION(pcre)
+{
+	php_info_print_table_start();
+	php_info_print_table_row(2, "PCRE (Perl Compatible Regular Expressions) Support", "enabled" );
+	php_info_print_table_row(2, "PCRE Library Version", pcre_version() );
+	php_info_print_table_end();
+
+	DISPLAY_INI_ENTRIES();
+}
+/* }}} */
+
+/* {{{ PHP_MINIT_FUNCTION(pcre) */
+static PHP_MINIT_FUNCTION(pcre)
+{
+	REGISTER_INI_ENTRIES();
+	
+	REGISTER_LONG_CONSTANT("PREG_PATTERN_ORDER", PREG_PATTERN_ORDER, CONST_CS | CONST_PERSISTENT);
+	REGISTER_LONG_CONSTANT("PREG_SET_ORDER", PREG_SET_ORDER, CONST_CS | CONST_PERSISTENT);
+	REGISTER_LONG_CONSTANT("PREG_OFFSET_CAPTURE", PREG_OFFSET_CAPTURE, CONST_CS | CONST_PERSISTENT);
+	REGISTER_LONG_CONSTANT("PREG_SPLIT_NO_EMPTY", PREG_SPLIT_NO_EMPTY, CONST_CS | CONST_PERSISTENT);
+	REGISTER_LONG_CONSTANT("PREG_SPLIT_DELIM_CAPTURE", PREG_SPLIT_DELIM_CAPTURE, CONST_CS | CONST_PERSISTENT);
+	REGISTER_LONG_CONSTANT("PREG_SPLIT_OFFSET_CAPTURE", PREG_SPLIT_OFFSET_CAPTURE, CONST_CS | CONST_PERSISTENT);
+	REGISTER_LONG_CONSTANT("PREG_GREP_INVERT", PREG_GREP_INVERT, CONST_CS | CONST_PERSISTENT);
+
+	REGISTER_LONG_CONSTANT("PREG_NO_ERROR", PHP_PCRE_NO_ERROR, CONST_CS | CONST_PERSISTENT);
+	REGISTER_LONG_CONSTANT("PREG_INTERNAL_ERROR", PHP_PCRE_INTERNAL_ERROR, CONST_CS | CONST_PERSISTENT);
+	REGISTER_LONG_CONSTANT("PREG_BACKTRACK_LIMIT_ERROR", PHP_PCRE_BACKTRACK_LIMIT_ERROR, CONST_CS | CONST_PERSISTENT);
+	REGISTER_LONG_CONSTANT("PREG_RECURSION_LIMIT_ERROR", PHP_PCRE_RECURSION_LIMIT_ERROR, CONST_CS | CONST_PERSISTENT);
+	REGISTER_LONG_CONSTANT("PREG_BAD_UTF8_ERROR", PHP_PCRE_BAD_UTF8_ERROR, CONST_CS | CONST_PERSISTENT);
+	REGISTER_LONG_CONSTANT("PREG_BAD_UTF8_OFFSET_ERROR", PHP_PCRE_BAD_UTF8_OFFSET_ERROR, CONST_CS | CONST_PERSISTENT);
+	REGISTER_STRING_CONSTANT("PCRE_VERSION", (char *)pcre_version(), CONST_CS | CONST_PERSISTENT);
+
+	return SUCCESS;
+}
+/* }}} */
+
+/* {{{ PHP_MSHUTDOWN_FUNCTION(pcre) */
+static PHP_MSHUTDOWN_FUNCTION(pcre)
+{
+	UNREGISTER_INI_ENTRIES();
+
+	return SUCCESS;
+}
+/* }}} */
+
+/* {{{ static pcre_clean_cache */
+static int pcre_clean_cache(void *data, void *arg TSRMLS_DC)
+{
+	int *num_clean = (int *)arg;
+
+	if (*num_clean > 0) {
+		(*num_clean)--;
+		return 1;
+	} else {
+		return 0;
+	}
+}
+/* }}} */
+
+/* {{{ static make_subpats_table */
+static char **make_subpats_table(int num_subpats, pcre_cache_entry *pce TSRMLS_DC)
+{
+	pcre_extra *extra = pce->extra;
+	int name_cnt = 0, name_size, ni = 0;
+	int rc;
+	char *name_table;
+	unsigned short name_idx;
+	char **subpat_names = (char **)ecalloc(num_subpats, sizeof(char *));
+
+	rc = pcre_fullinfo(pce->re, extra, PCRE_INFO_NAMECOUNT, &name_cnt);
+	if (rc < 0) {
+		php_error_docref(NULL TSRMLS_CC, E_WARNING, "Internal pcre_fullinfo() error %d", rc);
+		efree(subpat_names);
+		return NULL;
+	}
+	if (name_cnt > 0) {
+		int rc1, rc2;
+
+		rc1 = pcre_fullinfo(pce->re, extra, PCRE_INFO_NAMETABLE, &name_table);
+		rc2 = pcre_fullinfo(pce->re, extra, PCRE_INFO_NAMEENTRYSIZE, &name_size);
+		rc = rc2 ? rc2 : rc1;
+		if (rc < 0) {
+			php_error_docref(NULL TSRMLS_CC, E_WARNING, "Internal pcre_fullinfo() error %d", rc);
+			efree(subpat_names);
+			return NULL;
+		}
+
+		while (ni++ < name_cnt) {
+			name_idx = 0xff * (unsigned char)name_table[0] + (unsigned char)name_table[1];
+			subpat_names[name_idx] = name_table + 2;
+			if (is_numeric_string(subpat_names[name_idx], strlen(subpat_names[name_idx]), NULL, NULL, 0) > 0) {
+				php_error_docref(NULL TSRMLS_CC, E_WARNING, "Numeric named subpatterns are not allowed");
+				efree(subpat_names);
+				return NULL;
+			}
+			name_table += name_size;
+		}
+	}
+
+	return subpat_names;
+}
+/* }}} */
+
+/* {{{ pcre_get_compiled_regex_cache
+ */
+PHPAPI pcre_cache_entry* pcre_get_compiled_regex_cache(char *regex, int regex_len TSRMLS_DC)
+{
+	pcre				*re = NULL;
+	pcre_extra			*extra;
+	int					 coptions = 0;
+	int					 soptions = 0;
+	const char			*error;
+	int					 erroffset;
+	char				 delimiter;
+	char				 start_delimiter;
+	char				 end_delimiter;
+	char				*p, *pp;
+	char				*pattern;
+	int					 do_study = 0;
+	int					 poptions = 0;
+	int				count = 0;
+	unsigned const char *tables = NULL;
+#if HAVE_SETLOCALE
+	char				*locale = setlocale(LC_CTYPE, NULL);
+#endif
+	pcre_cache_entry	*pce;
+	pcre_cache_entry	 new_entry;
+	char                *tmp = NULL;
+
+	/* Try to lookup the cached regex entry, and if successful, just pass
+	   back the compiled pattern, otherwise go on and compile it. */
+	if (zend_hash_find(&PCRE_G(pcre_cache), regex, regex_len+1, (void **)&pce) == SUCCESS) {
+		/*
+		 * We use a quick pcre_fullinfo() check to see whether cache is corrupted, and if it
+		 * is, we flush it and compile the pattern from scratch.
+		 */
+		if (pcre_fullinfo(pce->re, NULL, PCRE_INFO_CAPTURECOUNT, &count) == PCRE_ERROR_BADMAGIC) {
+			zend_hash_clean(&PCRE_G(pcre_cache));
+		} else {
+#if HAVE_SETLOCALE
+			if (!strcmp(pce->locale, locale)) {
+#endif
+				return pce;
+#if HAVE_SETLOCALE
+			}
+#endif
+		}
+	}
+	
+	p = regex;
+	
+	/* Parse through the leading whitespace, and display a warning if we
+	   get to the end without encountering a delimiter. */
+	while (isspace((int)*(unsigned char *)p)) p++;
+	if (*p == 0) {
+		php_error_docref(NULL TSRMLS_CC, E_WARNING, 
+						 p < regex + regex_len ? "Null byte in regex" : "Empty regular expression");
+		return NULL;
+	}
+	
+	/* Get the delimiter and display a warning if it is alphanumeric
+	   or a backslash. */
+	delimiter = *p++;
+	if (isalnum((int)*(unsigned char *)&delimiter) || delimiter == '\\') {
+		php_error_docref(NULL TSRMLS_CC,E_WARNING, "Delimiter must not be alphanumeric or backslash");
+		return NULL;
+	}
+
+	start_delimiter = delimiter;
+	if ((pp = strchr("([{< )]}> )]}>", delimiter)))
+		delimiter = pp[5];
+	end_delimiter = delimiter;
+
+	pp = p;
+
+	if (start_delimiter == end_delimiter) {
+		/* We need to iterate through the pattern, searching for the ending delimiter,
+		   but skipping the backslashed delimiters.  If the ending delimiter is not
+		   found, display a warning. */
+		while (*pp != 0) {
+			if (*pp == '\\' && pp[1] != 0) pp++;
+			else if (*pp == delimiter)
+				break;
+			pp++;
+		}
+	} else {
+		/* We iterate through the pattern, searching for the matching ending
+		 * delimiter. For each matching starting delimiter, we increment nesting
+		 * level, and decrement it for each matching ending delimiter. If we
+		 * reach the end of the pattern without matching, display a warning.
+		 */
+		int brackets = 1; 	/* brackets nesting level */
+		while (*pp != 0) {
+			if (*pp == '\\' && pp[1] != 0) pp++;
+			else if (*pp == end_delimiter && --brackets <= 0)
+				break;
+			else if (*pp == start_delimiter)
+				brackets++;
+			pp++;
+		}
+	}
+
+	if (*pp == 0) {
+		if (pp < regex + regex_len) {
+			php_error_docref(NULL TSRMLS_CC,E_WARNING, "Null byte in regex");
+		} else if (start_delimiter == end_delimiter) {
+			php_error_docref(NULL TSRMLS_CC,E_WARNING, "No ending delimiter '%c' found", delimiter);
+		} else {
+			php_error_docref(NULL TSRMLS_CC,E_WARNING, "No ending matching delimiter '%c' found", delimiter);
+		}
+		return NULL;
+	}
+	
+	/* Make a copy of the actual pattern. */
+	pattern = estrndup(p, pp-p);
+
+	/* Move on to the options */
+	pp++;
+
+	/* Parse through the options, setting appropriate flags.  Display
+	   a warning if we encounter an unknown modifier. */	
+	while (pp < regex + regex_len) {
+		switch (*pp++) {
+			/* Perl compatible options */
+			case 'i':	coptions |= PCRE_CASELESS;		break;
+			case 'm':	coptions |= PCRE_MULTILINE;		break;
+			case 's':	coptions |= PCRE_DOTALL;		break;
+			case 'x':	coptions |= PCRE_EXTENDED;		break;
+			
+			/* PCRE specific options */
+			case 'A':	coptions |= PCRE_ANCHORED;		break;
+			case 'D':	coptions |= PCRE_DOLLAR_ENDONLY;break;
+			case 'S':	do_study  = 1;					break;
+			case 'U':	coptions |= PCRE_UNGREEDY;		break;
+			case 'X':	coptions |= PCRE_EXTRA;			break;
+			case 'u':	coptions |= PCRE_UTF8;
+	/* In  PCRE,  by  default, \d, \D, \s, \S, \w, and \W recognize only ASCII
+       characters, even in UTF-8 mode. However, this can be changed by setting
+       the PCRE_UCP option. */
+#ifdef PCRE_UCP
+						coptions |= PCRE_UCP;
+#endif			
+				break;
+
+			/* Custom preg options */
+			case 'e':	poptions |= PREG_REPLACE_EVAL;	break;
+			
+			case ' ':
+			case '\n':
+				break;
+
+			default:
+				if (pp[-1]) {
+					php_error_docref(NULL TSRMLS_CC,E_WARNING, "Unknown modifier '%c'", pp[-1]);
+				} else {
+					php_error_docref(NULL TSRMLS_CC,E_WARNING, "Null byte in regex");
+				}
+				efree(pattern);
+				return NULL;
+		}
+	}
+
+#if HAVE_SETLOCALE
+	if (strcmp(locale, "C"))
+		tables = pcre_maketables();
+#endif
+
+	/* Compile pattern and display a warning if compilation failed. */
+	re = pcre_compile(pattern,
+					  coptions,
+					  &error,
+					  &erroffset,
+					  tables);
+
+	if (re == NULL) {
+		php_error_docref(NULL TSRMLS_CC,E_WARNING, "Compilation failed: %s at offset %d", error, erroffset);
+		efree(pattern);
+		if (tables) {
+			pefree((void*)tables, 1);
+		}
+		return NULL;
+	}
+
+	/* If study option was specified, study the pattern and
+	   store the result in extra for passing to pcre_exec. */
+	if (do_study) {
+		extra = pcre_study(re, soptions, &error);
+		if (extra) {
+			extra->flags |= PCRE_EXTRA_MATCH_LIMIT | PCRE_EXTRA_MATCH_LIMIT_RECURSION;
+		}
+		if (error != NULL) {
+			php_error_docref(NULL TSRMLS_CC, E_WARNING, "Error while studying pattern");
+		}
+	} else {
+		extra = NULL;
+	}
+
+	efree(pattern);
+
+	/*
+	 * If we reached cache limit, clean out the items from the head of the list;
+	 * these are supposedly the oldest ones (but not necessarily the least used
+	 * ones).
+	 */
+	if (zend_hash_num_elements(&PCRE_G(pcre_cache)) == PCRE_CACHE_SIZE) {
+		int num_clean = PCRE_CACHE_SIZE / 8;
+		zend_hash_apply_with_argument(&PCRE_G(pcre_cache), pcre_clean_cache, &num_clean TSRMLS_CC);
+	}
+
+	/* Store the compiled pattern and extra info in the cache. */
+	new_entry.re = re;
+	new_entry.extra = extra;
+	new_entry.preg_options = poptions;
+	new_entry.compile_options = coptions;
+#if HAVE_SETLOCALE
+	new_entry.locale = pestrdup(locale, 1);
+	new_entry.tables = tables;
+#endif
+
+	/*
+	 * Interned strings are not duplicated when stored in HashTable,
+	 * but all the interned strings created during HTTP request are removed
+	 * at end of request. However PCRE_G(pcre_cache) must be consistent
+	 * on the next request as well. So we disable usage of interned strings
+	 * as hash keys especually for this table.
+	 * See bug #63180 
+	 */
+	if (IS_INTERNED(regex)) {
+		regex = tmp = estrndup(regex, regex_len);
+	}
+
+	zend_hash_update(&PCRE_G(pcre_cache), regex, regex_len+1, (void *)&new_entry,
+						sizeof(pcre_cache_entry), (void**)&pce);
+
+	if (tmp) {
+		efree(tmp);
+	}
+
+	return pce;
+}
+/* }}} */
+
+/* {{{ pcre_get_compiled_regex
+ */
+PHPAPI pcre* pcre_get_compiled_regex(char *regex, pcre_extra **extra, int *preg_options TSRMLS_DC)
+{
+	pcre_cache_entry * pce = pcre_get_compiled_regex_cache(regex, strlen(regex) TSRMLS_CC);
+
+	if (extra) {
+		*extra = pce ? pce->extra : NULL;
+	}
+	if (preg_options) {
+		*preg_options = pce ? pce->preg_options : 0;
+	}
+	
+	return pce ? pce->re : NULL;
+}
+/* }}} */
+
+/* {{{ pcre_get_compiled_regex_ex
+ */
+PHPAPI pcre* pcre_get_compiled_regex_ex(char *regex, pcre_extra **extra, int *preg_options, int *compile_options TSRMLS_DC)
+{
+	pcre_cache_entry * pce = pcre_get_compiled_regex_cache(regex, strlen(regex) TSRMLS_CC);
+	
+	if (extra) {
+		*extra = pce ? pce->extra : NULL;
+	}
+	if (preg_options) {
+		*preg_options = pce ? pce->preg_options : 0;
+	}
+	if (compile_options) {
+		*compile_options = pce ? pce->compile_options : 0;
+	}
+	
+	return pce ? pce->re : NULL;
+}
+/* }}} */
+
+/* {{{ add_offset_pair */
+static inline void add_offset_pair(zval *result, char *str, int len, int offset, char *name)
+{
+	zval *match_pair;
+
+	ALLOC_ZVAL(match_pair);
+	array_init(match_pair);
+	INIT_PZVAL(match_pair);
+
+	/* Add (match, offset) to the return value */
+	add_next_index_stringl(match_pair, str, len, 1);
+	add_next_index_long(match_pair, offset);
+	
+	if (name) {
+		zval_add_ref(&match_pair);
+		zend_hash_update(Z_ARRVAL_P(result), name, strlen(name)+1, &match_pair, sizeof(zval *), NULL);
+	}
+	zend_hash_next_index_insert(Z_ARRVAL_P(result), &match_pair, sizeof(zval *), NULL);
+}
+/* }}} */
+
+static void php_do_pcre_match(INTERNAL_FUNCTION_PARAMETERS, int global) /* {{{ */
+{
+	/* parameters */
+	char			 *regex;			/* Regular expression */
+	char			 *subject;			/* String to match against */
+	int				  regex_len;
+	int				  subject_len;
+	pcre_cache_entry *pce;				/* Compiled regular expression */
+	zval			 *subpats = NULL;	/* Array for subpatterns */
+	long			  flags = 0;		/* Match control flags */
+	long			  start_offset = 0;	/* Where the new search starts */
+
+	if (zend_parse_parameters(ZEND_NUM_ARGS() TSRMLS_CC, "ss|zll", &regex, &regex_len,
+							  &subject, &subject_len, &subpats, &flags, &start_offset) == FAILURE) {
+		RETURN_FALSE;
+	}
+	
+	/* Compile regex or get it from cache. */
+	if ((pce = pcre_get_compiled_regex_cache(regex, regex_len TSRMLS_CC)) == NULL) {
+		RETURN_FALSE;
+	}
+
+	php_pcre_match_impl(pce, subject, subject_len, return_value, subpats, 
+		global, ZEND_NUM_ARGS() >= 4, flags, start_offset TSRMLS_CC);
+}
+/* }}} */
+
+/* {{{ php_pcre_match_impl() */
+PHPAPI void php_pcre_match_impl(pcre_cache_entry *pce, char *subject, int subject_len, zval *return_value,
+	zval *subpats, int global, int use_flags, long flags, long start_offset TSRMLS_DC)
+{
+	zval			*result_set,		/* Holds a set of subpatterns after
+										   a global match */
+				   **match_sets = NULL;	/* An array of sets of matches for each
+										   subpattern after a global match */
+	pcre_extra		*extra = pce->extra;/* Holds results of studying */
+	pcre_extra		 extra_data;		/* Used locally for exec options */
+	int				 exoptions = 0;		/* Execution options */
+	int				 count = 0;			/* Count of matched subpatterns */
+	int				*offsets;			/* Array of subpattern offsets */
+	int				 num_subpats;		/* Number of captured subpatterns */
+	int				 size_offsets;		/* Size of the offsets array */
+	int				 matched;			/* Has anything matched */
+	int				 g_notempty = 0;	/* If the match should not be empty */
+	const char	   **stringlist;		/* Holds list of subpatterns */
+	char 		   **subpat_names;		/* Array for named subpatterns */
+	int				 i, rc;
+	int				 subpats_order;		/* Order of subpattern matches */
+	int				 offset_capture;    /* Capture match offsets: yes/no */
+
+	/* Overwrite the passed-in value for subpatterns with an empty array. */
+	if (subpats != NULL) {
+		zval_dtor(subpats);
+		array_init(subpats);
+	}
+
+	subpats_order = global ? PREG_PATTERN_ORDER : 0;
+
+	if (use_flags) {
+		offset_capture = flags & PREG_OFFSET_CAPTURE;
+
+		/*
+		 * subpats_order is pre-set to pattern mode so we change it only if
+		 * necessary.
+		 */
+		if (flags & 0xff) {
+			subpats_order = flags & 0xff;
+		}
+		if ((global && (subpats_order < PREG_PATTERN_ORDER || subpats_order > PREG_SET_ORDER)) ||
+			(!global && subpats_order != 0)) {
+			php_error_docref(NULL TSRMLS_CC, E_WARNING, "Invalid flags specified");
+			return;
+		}
+	} else {
+		offset_capture = 0;
+	}
+
+	/* Negative offset counts from the end of the string. */
+	if (start_offset < 0) {
+		start_offset = subject_len + start_offset;
+		if (start_offset < 0) {
+			start_offset = 0;
+		}
+	}
+
+	if (extra == NULL) {
+		extra_data.flags = PCRE_EXTRA_MATCH_LIMIT | PCRE_EXTRA_MATCH_LIMIT_RECURSION;
+		extra = &extra_data;
+	}
+	extra->match_limit = PCRE_G(backtrack_limit);
+	extra->match_limit_recursion = PCRE_G(recursion_limit);
+
+	/* Calculate the size of the offsets array, and allocate memory for it. */
+	rc = pcre_fullinfo(pce->re, extra, PCRE_INFO_CAPTURECOUNT, &num_subpats);
+	if (rc < 0) {
+		php_error_docref(NULL TSRMLS_CC, E_WARNING, "Internal pcre_fullinfo() error %d", rc);
+		RETURN_FALSE;
+	}
+	num_subpats++;
+	size_offsets = num_subpats * 3;
+
+	/*
+	 * Build a mapping from subpattern numbers to their names. We will always
+	 * allocate the table, even though there may be no named subpatterns. This
+	 * avoids somewhat more complicated logic in the inner loops.
+	 */
+	subpat_names = make_subpats_table(num_subpats, pce TSRMLS_CC);
+	if (!subpat_names) {
+		RETURN_FALSE;
+	}
+
+	offsets = (int *)safe_emalloc(size_offsets, sizeof(int), 0);
+
+	/* Allocate match sets array and initialize the values. */
+	if (global && subpats && subpats_order == PREG_PATTERN_ORDER) {
+		match_sets = (zval **)safe_emalloc(num_subpats, sizeof(zval *), 0);
+		for (i=0; i<num_subpats; i++) {
+			ALLOC_ZVAL(match_sets[i]);
+			array_init(match_sets[i]);
+			INIT_PZVAL(match_sets[i]);
+		}
+	}
+
+	matched = 0;
+	PCRE_G(error_code) = PHP_PCRE_NO_ERROR;
+	
+	do {
+		/* Execute the regular expression. */
+		count = pcre_exec(pce->re, extra, subject, subject_len, start_offset,
+						  exoptions|g_notempty, offsets, size_offsets);
+
+		/* the string was already proved to be valid UTF-8 */
+		exoptions |= PCRE_NO_UTF8_CHECK;
+
+		/* Check for too many substrings condition. */
+		if (count == 0) {
+			php_error_docref(NULL TSRMLS_CC, E_NOTICE, "Matched, but too many substrings");
+			count = size_offsets/3;
+		}
+
+		/* If something has matched */
+		if (count > 0) {
+			matched++;
+
+			/* If subpatterns array has been passed, fill it in with values. */
+			if (subpats != NULL) {
+				/* Try to get the list of substrings and display a warning if failed. */
+				if (pcre_get_substring_list(subject, offsets, count, &stringlist) < 0) {
+					efree(subpat_names);
+					efree(offsets);
+					if (match_sets) efree(match_sets);
+					php_error_docref(NULL TSRMLS_CC, E_WARNING, "Get subpatterns list failed");
+					RETURN_FALSE;
+				}
+
+				if (global) {	/* global pattern matching */
+					if (subpats && subpats_order == PREG_PATTERN_ORDER) {
+						/* For each subpattern, insert it into the appropriate array. */
+						for (i = 0; i < count; i++) {
+							if (offset_capture) {
+								add_offset_pair(match_sets[i], (char *)stringlist[i],
+												offsets[(i<<1)+1] - offsets[i<<1], offsets[i<<1], NULL);
+							} else {
+								add_next_index_stringl(match_sets[i], (char *)stringlist[i],
+													   offsets[(i<<1)+1] - offsets[i<<1], 1);
+							}
+						}
+						/*
+						 * If the number of captured subpatterns on this run is
+						 * less than the total possible number, pad the result
+						 * arrays with empty strings.
+						 */
+						if (count < num_subpats) {
+							for (; i < num_subpats; i++) {
+								add_next_index_string(match_sets[i], "", 1);
+							}
+						}
+					} else {
+						/* Allocate the result set array */
+						ALLOC_ZVAL(result_set);
+						array_init(result_set);
+						INIT_PZVAL(result_set);
+						
+						/* Add all the subpatterns to it */
+						for (i = 0; i < count; i++) {
+							if (offset_capture) {
+								add_offset_pair(result_set, (char *)stringlist[i],
+												offsets[(i<<1)+1] - offsets[i<<1], offsets[i<<1], subpat_names[i]);
+							} else {
+								if (subpat_names[i]) {
+									add_assoc_stringl(result_set, subpat_names[i], (char *)stringlist[i],
+														   offsets[(i<<1)+1] - offsets[i<<1], 1);
+								}
+								add_next_index_stringl(result_set, (char *)stringlist[i],
+													   offsets[(i<<1)+1] - offsets[i<<1], 1);
+							}
+						}
+						/* And add it to the output array */
+						zend_hash_next_index_insert(Z_ARRVAL_P(subpats), &result_set, sizeof(zval *), NULL);
+					}
+				} else {			/* single pattern matching */
+					/* For each subpattern, insert it into the subpatterns array. */
+					for (i = 0; i < count; i++) {
+						if (offset_capture) {
+							add_offset_pair(subpats, (char *)stringlist[i],
+											offsets[(i<<1)+1] - offsets[i<<1],
+											offsets[i<<1], subpat_names[i]);
+						} else {
+							if (subpat_names[i]) {
+								add_assoc_stringl(subpats, subpat_names[i], (char *)stringlist[i],
+												  offsets[(i<<1)+1] - offsets[i<<1], 1);
+							}
+							add_next_index_stringl(subpats, (char *)stringlist[i],
+												   offsets[(i<<1)+1] - offsets[i<<1], 1);
+						}
+					}
+				}
+
+				pcre_free((void *) stringlist);
+			}
+		} else if (count == PCRE_ERROR_NOMATCH) {
+			/* If we previously set PCRE_NOTEMPTY after a null match,
+			   this is not necessarily the end. We need to advance
+			   the start offset, and continue. Fudge the offset values
+			   to achieve this, unless we're already at the end of the string. */
+			if (g_notempty != 0 && start_offset < subject_len) {
+				offsets[0] = start_offset;
+				offsets[1] = start_offset + 1;
+			} else
+				break;
+		} else {
+			pcre_handle_exec_error(count TSRMLS_CC);
+			break;
+		}
+		
+		/* If we have matched an empty string, mimic what Perl's /g options does.
+		   This turns out to be rather cunning. First we set PCRE_NOTEMPTY and try
+		   the match again at the same point. If this fails (picked up above) we
+		   advance to the next character. */
+		g_notempty = (offsets[1] == offsets[0])? PCRE_NOTEMPTY | PCRE_ANCHORED : 0;
+		
+		/* Advance to the position right after the last full match */
+		start_offset = offsets[1];
+	} while (global);
+
+	/* Add the match sets to the output array and clean up */
+	if (global && subpats && subpats_order == PREG_PATTERN_ORDER) {
+		for (i = 0; i < num_subpats; i++) {
+			if (subpat_names[i]) {
+				zend_hash_update(Z_ARRVAL_P(subpats), subpat_names[i],
+								 strlen(subpat_names[i])+1, &match_sets[i], sizeof(zval *), NULL);
+				Z_ADDREF_P(match_sets[i]);
+			}
+			zend_hash_next_index_insert(Z_ARRVAL_P(subpats), &match_sets[i], sizeof(zval *), NULL);
+		}
+		efree(match_sets);
+	}
+	
+	efree(offsets);
+	efree(subpat_names);
+
+	/* Did we encounter an error? */
+	if (PCRE_G(error_code) == PHP_PCRE_NO_ERROR) {
+		RETVAL_LONG(matched);
+	} else {
+		RETVAL_FALSE;
+	}
+}
+/* }}} */
+
+/* {{{ proto int preg_match(string pattern, string subject [, array &subpatterns [, int flags [, int offset]]])
+   Perform a Perl-style regular expression match */
+static PHP_FUNCTION(preg_match)
+{
+	php_do_pcre_match(INTERNAL_FUNCTION_PARAM_PASSTHRU, 0);
+}
+/* }}} */
+
+/* {{{ proto int preg_match_all(string pattern, string subject [, array &subpatterns [, int flags [, int offset]]])
+   Perform a Perl-style global regular expression match */
+static PHP_FUNCTION(preg_match_all)
+{
+	php_do_pcre_match(INTERNAL_FUNCTION_PARAM_PASSTHRU, 1);
+}
+/* }}} */
+
+/* {{{ preg_get_backref
+ */
+static int preg_get_backref(char **str, int *backref)
+{
+	register char in_brace = 0;
+	register char *walk = *str;
+
+	if (walk[1] == 0)
+		return 0;
+
+	if (*walk == '$' && walk[1] == '{') {
+		in_brace = 1;
+		walk++;
+	}
+	walk++;
+
+	if (*walk >= '0' && *walk <= '9') {
+		*backref = *walk - '0';
+		walk++;
+	} else
+		return 0;
+	
+	if (*walk && *walk >= '0' && *walk <= '9') {
+		*backref = *backref * 10 + *walk - '0';
+		walk++;
+	}
+
+	if (in_brace) {
+		if (*walk == 0 || *walk != '}')
+			return 0;
+		else
+			walk++;
+	}
+	
+	*str = walk;
+	return 1;	
+}
+/* }}} */
+
+/* {{{ preg_do_repl_func
+ */
+static int preg_do_repl_func(zval *function, char *subject, int *offsets, char **subpat_names, int count, char **result TSRMLS_DC)
+{
+	zval		*retval_ptr;		/* Function return value */
+	zval	   **args[1];			/* Argument to pass to function */
+	zval		*subpats;			/* Captured subpatterns */ 
+	int			 result_len;		/* Return value length */
+	int			 i;
+
+	MAKE_STD_ZVAL(subpats);
+	array_init(subpats);
+	for (i = 0; i < count; i++) {
+		if (subpat_names[i]) {
+			add_assoc_stringl(subpats, subpat_names[i], &subject[offsets[i<<1]] , offsets[(i<<1)+1] - offsets[i<<1], 1);
+		}
+		add_next_index_stringl(subpats, &subject[offsets[i<<1]], offsets[(i<<1)+1] - offsets[i<<1], 1);
+	}
+	args[0] = &subpats;
+
+	if (call_user_function_ex(EG(function_table), NULL, function, &retval_ptr, 1, args, 0, NULL TSRMLS_CC) == SUCCESS && retval_ptr) {
+		convert_to_string_ex(&retval_ptr);
+		*result = estrndup(Z_STRVAL_P(retval_ptr), Z_STRLEN_P(retval_ptr));
+		result_len = Z_STRLEN_P(retval_ptr);
+		zval_ptr_dtor(&retval_ptr);
+	} else {
+		if (!EG(exception)) {
+			php_error_docref(NULL TSRMLS_CC, E_WARNING, "Unable to call custom replacement function");
+		}
+		result_len = offsets[1] - offsets[0];
+		*result = estrndup(&subject[offsets[0]], result_len);
+	}
+
+	zval_ptr_dtor(&subpats);
+
+	return result_len;
+}
+/* }}} */
+
+/* {{{ preg_do_eval
+ */
+static int preg_do_eval(char *eval_str, int eval_str_len, char *subject,
+						int *offsets, int count, char **result TSRMLS_DC)
+{
+	zval		 retval;			/* Return value from evaluation */
+	char		*eval_str_end,		/* End of eval string */
+				*match,				/* Current match for a backref */
+				*esc_match,			/* Quote-escaped match */
+				*walk,				/* Used to walk the code string */
+				*segment,			/* Start of segment to append while walking */
+				 walk_last;			/* Last walked character */
+	int			 match_len;			/* Length of the match */
+	int			 esc_match_len;		/* Length of the quote-escaped match */
+	int			 result_len;		/* Length of the result of the evaluation */
+	int			 backref;			/* Current backref */
+	char        *compiled_string_description;
+	smart_str    code = {0};
+	
+	eval_str_end = eval_str + eval_str_len;
+	walk = segment = eval_str;
+	walk_last = 0;
+	
+	while (walk < eval_str_end) {
+		/* If found a backreference.. */
+		if ('\\' == *walk || '$' == *walk) {
+			smart_str_appendl(&code, segment, walk - segment);
+			if (walk_last == '\\') {
+				code.c[code.len-1] = *walk++;
+				segment = walk;
+				walk_last = 0;
+				continue;
+			}
+			segment = walk;
+			if (preg_get_backref(&walk, &backref)) {
+				if (backref < count) {
+					/* Find the corresponding string match and substitute it
+					   in instead of the backref */
+					match = subject + offsets[backref<<1];
+					match_len = offsets[(backref<<1)+1] - offsets[backref<<1];
+					if (match_len) {
+						esc_match = php_addslashes(match, match_len, &esc_match_len, 0 TSRMLS_CC);
+					} else {
+						esc_match = match;
+						esc_match_len = 0;
+					}
+				} else {
+					esc_match = "";
+					esc_match_len = 0;
+				}
+				smart_str_appendl(&code, esc_match, esc_match_len);
+
+				segment = walk;
+
+				/* Clean up and reassign */
+				if (esc_match_len)
+					efree(esc_match);
+				continue;
+			}
+		}
+		walk++;
+		walk_last = walk[-1];
+	}
+	smart_str_appendl(&code, segment, walk - segment);
+	smart_str_0(&code);
+
+	compiled_string_description = zend_make_compiled_string_description("regexp code" TSRMLS_CC);
+	/* Run the code */
+	if (zend_eval_stringl(code.c, code.len, &retval, compiled_string_description TSRMLS_CC) == FAILURE) {
+		efree(compiled_string_description);
+		php_error_docref(NULL TSRMLS_CC,E_ERROR, "Failed evaluating code: %s%s", PHP_EOL, code.c);
+		/* zend_error() does not return in this case */
+	}
+	efree(compiled_string_description);
+	convert_to_string(&retval);
+	
+	/* Save the return value and its length */
+	*result = estrndup(Z_STRVAL(retval), Z_STRLEN(retval));
+	result_len = Z_STRLEN(retval);
+	
+	/* Clean up */
+	zval_dtor(&retval);
+	smart_str_free(&code);
+	
+	return result_len;
+}
+/* }}} */
+
+/* {{{ php_pcre_replace
+ */
+PHPAPI char *php_pcre_replace(char *regex,   int regex_len,
+							  char *subject, int subject_len,
+							  zval *replace_val, int is_callable_replace,
+							  int *result_len, int limit, int *replace_count TSRMLS_DC)
+{
+	pcre_cache_entry	*pce;			    /* Compiled regular expression */
+
+	/* Compile regex or get it from cache. */
+	if ((pce = pcre_get_compiled_regex_cache(regex, regex_len TSRMLS_CC)) == NULL) {
+		return NULL;
+	}
+
+	return php_pcre_replace_impl(pce, subject, subject_len, replace_val, 
+		is_callable_replace, result_len, limit, replace_count TSRMLS_CC);
+}
+/* }}} */
+
+/* {{{ php_pcre_replace_impl() */
+PHPAPI char *php_pcre_replace_impl(pcre_cache_entry *pce, char *subject, int subject_len, zval *replace_val, 
+	int is_callable_replace, int *result_len, int limit, int *replace_count TSRMLS_DC)
+{
+	pcre_extra		*extra = pce->extra;/* Holds results of studying */
+	pcre_extra		 extra_data;		/* Used locally for exec options */
+	int				 exoptions = 0;		/* Execution options */
+	int				 count = 0;			/* Count of matched subpatterns */
+	int				*offsets;			/* Array of subpattern offsets */
+	char 			**subpat_names;		/* Array for named subpatterns */
+	int				 num_subpats;		/* Number of captured subpatterns */
+	int				 size_offsets;		/* Size of the offsets array */
+	int				 new_len;			/* Length of needed storage */
+	int				 alloc_len;			/* Actual allocated length */
+	int				 eval_result_len=0;	/* Length of the eval'ed or
+										   function-returned string */
+	int				 match_len;			/* Length of the current match */
+	int				 backref;			/* Backreference number */
+	int				 eval;				/* If the replacement string should be eval'ed */
+	int				 start_offset;		/* Where the new search starts */
+	int				 g_notempty=0;		/* If the match should not be empty */
+	int				 replace_len=0;		/* Length of replacement string */
+	char			*result,			/* Result of replacement */
+					*replace=NULL,		/* Replacement string */
+					*new_buf,			/* Temporary buffer for re-allocation */
+					*walkbuf,			/* Location of current replacement in the result */
+					*walk,				/* Used to walk the replacement string */
+					*match,				/* The current match */
+					*piece,				/* The current piece of subject */
+					*replace_end=NULL,	/* End of replacement string */
+					*eval_result,		/* Result of eval or custom function */
+					 walk_last;			/* Last walked character */
+	int				 rc;
+
+	if (extra == NULL) {
+		extra_data.flags = PCRE_EXTRA_MATCH_LIMIT | PCRE_EXTRA_MATCH_LIMIT_RECURSION;
+		extra = &extra_data;
+	}
+	extra->match_limit = PCRE_G(backtrack_limit);
+	extra->match_limit_recursion = PCRE_G(recursion_limit);
+
+	eval = pce->preg_options & PREG_REPLACE_EVAL;
+	if (is_callable_replace) {
+		if (eval) {
+			php_error_docref(NULL TSRMLS_CC, E_WARNING, "Modifier /e cannot be used with replacement callback");
+			return NULL;
+		}
+	} else {
+		replace = Z_STRVAL_P(replace_val);
+		replace_len = Z_STRLEN_P(replace_val);
+		replace_end = replace + replace_len;
+	}
+
+	/* Calculate the size of the offsets array, and allocate memory for it. */
+	rc = pcre_fullinfo(pce->re, extra, PCRE_INFO_CAPTURECOUNT, &num_subpats);
+	if (rc < 0) {
+		php_error_docref(NULL TSRMLS_CC, E_WARNING, "Internal pcre_fullinfo() error %d", rc);
+		return NULL;
+	}
+	num_subpats++;
+	size_offsets = num_subpats * 3;
+
+	/*
+	 * Build a mapping from subpattern numbers to their names. We will always
+	 * allocate the table, even though there may be no named subpatterns. This
+	 * avoids somewhat more complicated logic in the inner loops.
+	 */
+	subpat_names = make_subpats_table(num_subpats, pce TSRMLS_CC);
+	if (!subpat_names) {
+		return NULL;
+	}
+
+	offsets = (int *)safe_emalloc(size_offsets, sizeof(int), 0);
+	
+	alloc_len = 2 * subject_len + 1;
+	result = safe_emalloc(alloc_len, sizeof(char), 0);
+
+	/* Initialize */
+	match = NULL;
+	*result_len = 0;
+	start_offset = 0;
+	PCRE_G(error_code) = PHP_PCRE_NO_ERROR;
+	
+	while (1) {
+		/* Execute the regular expression. */
+		count = pcre_exec(pce->re, extra, subject, subject_len, start_offset,
+						  exoptions|g_notempty, offsets, size_offsets);
+
+		/* the string was already proved to be valid UTF-8 */
+		exoptions |= PCRE_NO_UTF8_CHECK;
+
+		/* Check for too many substrings condition. */
+		if (count == 0) {
+			php_error_docref(NULL TSRMLS_CC,E_NOTICE, "Matched, but too many substrings");
+			count = size_offsets/3;
+		}
+
+		piece = subject + start_offset;
+
+		if (count > 0 && (limit == -1 || limit > 0)) {
+			if (replace_count) {
+				++*replace_count;
+			}
+			/* Set the match location in subject */
+			match = subject + offsets[0];
+
+			new_len = *result_len + offsets[0] - start_offset; /* part before the match */
+			
+			/* If evaluating, do it and add the return string's length */
+			if (eval) {
+				eval_result_len = preg_do_eval(replace, replace_len, subject,
+											   offsets, count, &eval_result TSRMLS_CC);
+				new_len += eval_result_len;
+			} else if (is_callable_replace) {
+				/* Use custom function to get replacement string and its length. */
+				eval_result_len = preg_do_repl_func(replace_val, subject, offsets, subpat_names, count, &eval_result TSRMLS_CC);
+				new_len += eval_result_len;
+			} else { /* do regular substitution */
+				walk = replace;
+				walk_last = 0;
+				while (walk < replace_end) {
+					if ('\\' == *walk || '$' == *walk) {
+						if (walk_last == '\\') {
+							walk++;
+							walk_last = 0;
+							continue;
+						}
+						if (preg_get_backref(&walk, &backref)) {
+							if (backref < count)
+								new_len += offsets[(backref<<1)+1] - offsets[backref<<1];
+							continue;
+						}
+					}
+					new_len++;
+					walk++;
+					walk_last = walk[-1];
+				}
+			}
+
+			if (new_len + 1 > alloc_len) {
+				alloc_len = 1 + alloc_len + 2 * new_len;
+				new_buf = emalloc(alloc_len);
+				memcpy(new_buf, result, *result_len);
+				efree(result);
+				result = new_buf;
+			}
+			/* copy the part of the string before the match */
+			memcpy(&result[*result_len], piece, match-piece);
+			*result_len += match-piece;
+
+			/* copy replacement and backrefs */
+			walkbuf = result + *result_len;
+			
+			/* If evaluating or using custom function, copy result to the buffer
+			 * and clean up. */
+			if (eval || is_callable_replace) {
+				memcpy(walkbuf, eval_result, eval_result_len);
+				*result_len += eval_result_len;
+				STR_FREE(eval_result);
+			} else { /* do regular backreference copying */
+				walk = replace;
+				walk_last = 0;
+				while (walk < replace_end) {
+					if ('\\' == *walk || '$' == *walk) {
+						if (walk_last == '\\') {
+							*(walkbuf-1) = *walk++;
+							walk_last = 0;
+							continue;
+						}
+						if (preg_get_backref(&walk, &backref)) {
+							if (backref < count) {
+								match_len = offsets[(backref<<1)+1] - offsets[backref<<1];
+								memcpy(walkbuf, subject + offsets[backref<<1], match_len);
+								walkbuf += match_len;
+							}
+							continue;
+						}
+					}
+					*walkbuf++ = *walk++;
+					walk_last = walk[-1];
+				}
+				*walkbuf = '\0';
+				/* increment the result length by how much we've added to the string */
+				*result_len += walkbuf - (result + *result_len);
+			}
+
+			if (limit != -1)
+				limit--;
+
+		} else if (count == PCRE_ERROR_NOMATCH || limit == 0) {
+			/* If we previously set PCRE_NOTEMPTY after a null match,
+			   this is not necessarily the end. We need to advance
+			   the start offset, and continue. Fudge the offset values
+			   to achieve this, unless we're already at the end of the string. */
+			if (g_notempty != 0 && start_offset < subject_len) {
+				offsets[0] = start_offset;
+				offsets[1] = start_offset + 1;
+				memcpy(&result[*result_len], piece, 1);
+				(*result_len)++;
+			} else {
+				new_len = *result_len + subject_len - start_offset;
+				if (new_len + 1 > alloc_len) {
+					alloc_len = new_len + 1; /* now we know exactly how long it is */
+					new_buf = safe_emalloc(alloc_len, sizeof(char), 0);
+					memcpy(new_buf, result, *result_len);
+					efree(result);
+					result = new_buf;
+				}
+				/* stick that last bit of string on our output */
+				memcpy(&result[*result_len], piece, subject_len - start_offset);
+				*result_len += subject_len - start_offset;
+				result[*result_len] = '\0';
+				break;
+			}
+		} else {
+			pcre_handle_exec_error(count TSRMLS_CC);
+			efree(result);
+			result = NULL;
+			break;
+		}
+			
+		/* If we have matched an empty string, mimic what Perl's /g options does.
+		   This turns out to be rather cunning. First we set PCRE_NOTEMPTY and try
+		   the match again at the same point. If this fails (picked up above) we
+		   advance to the next character. */
+		g_notempty = (offsets[1] == offsets[0])? PCRE_NOTEMPTY | PCRE_ANCHORED : 0;
+		
+		/* Advance to the next piece. */
+		start_offset = offsets[1];
+	}
+
+	efree(offsets);
+	efree(subpat_names);
+
+	return result;
+}
+/* }}} */
+
+/* {{{ php_replace_in_subject
+ */
+static char *php_replace_in_subject(zval *regex, zval *replace, zval **subject, int *result_len, int limit, int is_callable_replace, int *replace_count TSRMLS_DC)
+{
+	zval		**regex_entry,
+				**replace_entry = NULL,
+				 *replace_value,
+				  empty_replace;
+	char		*subject_value,
+				*result;
+	int			 subject_len;
+
+	/* Make sure we're dealing with strings. */	
+	convert_to_string_ex(subject);
+	/* FIXME: This might need to be changed to STR_EMPTY_ALLOC(). Check if this zval could be dtor()'ed somehow */
+	ZVAL_STRINGL(&empty_replace, "", 0, 0);
+	
+	/* If regex is an array */
+	if (Z_TYPE_P(regex) == IS_ARRAY) {
+		/* Duplicate subject string for repeated replacement */
+		subject_value = estrndup(Z_STRVAL_PP(subject), Z_STRLEN_PP(subject));
+		subject_len = Z_STRLEN_PP(subject);
+		*result_len = subject_len;
+		
+		zend_hash_internal_pointer_reset(Z_ARRVAL_P(regex));
+
+		replace_value = replace;
+		if (Z_TYPE_P(replace) == IS_ARRAY && !is_callable_replace)
+			zend_hash_internal_pointer_reset(Z_ARRVAL_P(replace));
+
+		/* For each entry in the regex array, get the entry */
+		while (zend_hash_get_current_data(Z_ARRVAL_P(regex), (void **)&regex_entry) == SUCCESS) {
+			/* Make sure we're dealing with strings. */	
+			convert_to_string_ex(regex_entry);
+		
+			/* If replace is an array and not a callable construct */
+			if (Z_TYPE_P(replace) == IS_ARRAY && !is_callable_replace) {
+				/* Get current entry */
+				if (zend_hash_get_current_data(Z_ARRVAL_P(replace), (void **)&replace_entry) == SUCCESS) {
+					if (!is_callable_replace) {
+						convert_to_string_ex(replace_entry);
+					}
+					replace_value = *replace_entry;
+					zend_hash_move_forward(Z_ARRVAL_P(replace));
+				} else {
+					/* We've run out of replacement strings, so use an empty one */
+					replace_value = &empty_replace;
+				}
+			}
+			
+			/* Do the actual replacement and put the result back into subject_value
+			   for further replacements. */
+			if ((result = php_pcre_replace(Z_STRVAL_PP(regex_entry),
+										   Z_STRLEN_PP(regex_entry),
+										   subject_value,
+										   subject_len,
+										   replace_value,
+										   is_callable_replace,
+										   result_len,
+										   limit,
+										   replace_count TSRMLS_CC)) != NULL) {
+				efree(subject_value);
+				subject_value = result;
+				subject_len = *result_len;
+			} else {
+				efree(subject_value);
+				return NULL;
+			}
+
+			zend_hash_move_forward(Z_ARRVAL_P(regex));
+		}
+
+		return subject_value;
+	} else {
+		result = php_pcre_replace(Z_STRVAL_P(regex),
+								  Z_STRLEN_P(regex),
+								  Z_STRVAL_PP(subject),
+								  Z_STRLEN_PP(subject),
+								  replace,
+								  is_callable_replace,
+								  result_len,
+								  limit,
+								  replace_count TSRMLS_CC);
+		return result;
+	}
+}
+/* }}} */
+
+/* {{{ preg_replace_impl
+ */
+static void preg_replace_impl(INTERNAL_FUNCTION_PARAMETERS, int is_callable_replace, int is_filter)
+{
+	zval		   **regex,
+				   **replace,
+				   **subject,
+				   **subject_entry,
+				   **zcount = NULL;
+	char			*result;
+	int				 result_len;
+	int				 limit_val = -1;
+	long			limit = -1;
+	char			*string_key;
+	ulong			 num_key;
+	char			*callback_name;
+	int				 replace_count=0, old_replace_count;
+	
+	/* Get function parameters and do error-checking. */
+	if (zend_parse_parameters(ZEND_NUM_ARGS() TSRMLS_CC, "ZZZ|lZ", &regex, &replace, &subject, &limit, &zcount) == FAILURE) {
+		return;
+	}
+	
+	if (!is_callable_replace && Z_TYPE_PP(replace) == IS_ARRAY && Z_TYPE_PP(regex) != IS_ARRAY) {
+		php_error_docref(NULL TSRMLS_CC, E_WARNING, "Parameter mismatch, pattern is a string while replacement is an array");
+		RETURN_FALSE;
+	}
+
+	SEPARATE_ZVAL(replace);
+	if (Z_TYPE_PP(replace) != IS_ARRAY && (Z_TYPE_PP(replace) != IS_OBJECT || !is_callable_replace)) {
+		convert_to_string_ex(replace);
+	}
+	if (is_callable_replace) {
+		if (!zend_is_callable(*replace, 0, &callback_name TSRMLS_CC)) {
+			php_error_docref(NULL TSRMLS_CC, E_WARNING, "Requires argument 2, '%s', to be a valid callback", callback_name);
+			efree(callback_name);
+			MAKE_COPY_ZVAL(subject, return_value);
+			return;
+		}
+		efree(callback_name);
+	}
+
+	SEPARATE_ZVAL(regex);
+	SEPARATE_ZVAL(subject);
+
+	if (ZEND_NUM_ARGS() > 3) {
+		limit_val = limit;
+	}
+		
+	if (Z_TYPE_PP(regex) != IS_ARRAY)
+		convert_to_string_ex(regex);
+	
+	/* if subject is an array */
+	if (Z_TYPE_PP(subject) == IS_ARRAY) {
+		array_init(return_value);
+		zend_hash_internal_pointer_reset(Z_ARRVAL_PP(subject));
+
+		/* For each subject entry, convert it to string, then perform replacement
+		   and add the result to the return_value array. */
+		while (zend_hash_get_current_data(Z_ARRVAL_PP(subject), (void **)&subject_entry) == SUCCESS) {
+			SEPARATE_ZVAL(subject_entry);
+			old_replace_count = replace_count;
+			if ((result = php_replace_in_subject(*regex, *replace, subject_entry, &result_len, limit_val, is_callable_replace, &replace_count TSRMLS_CC)) != NULL) {
+				if (!is_filter || replace_count > old_replace_count) {
+					/* Add to return array */
+					switch(zend_hash_get_current_key(Z_ARRVAL_PP(subject), &string_key, &num_key, 0))
+					{
+					case HASH_KEY_IS_STRING:
+						add_assoc_stringl(return_value, string_key, result, result_len, 0);
+						break;
+
+					case HASH_KEY_IS_LONG:
+						add_index_stringl(return_value, num_key, result, result_len, 0);
+						break;
+					}
+				} else {
+					efree(result);
+				}
+			}
+		
+			zend_hash_move_forward(Z_ARRVAL_PP(subject));
+		}
+	} else {	/* if subject is not an array */
+		old_replace_count = replace_count;
+		if ((result = php_replace_in_subject(*regex, *replace, subject, &result_len, limit_val, is_callable_replace, &replace_count TSRMLS_CC)) != NULL) {
+			if (!is_filter || replace_count > old_replace_count) {
+				RETVAL_STRINGL(result, result_len, 0);
+			} else {
+				efree(result);
+			}
+		}
+	}
+	if (ZEND_NUM_ARGS() > 4) {
+		zval_dtor(*zcount);
+		ZVAL_LONG(*zcount, replace_count);
+	}
+    	
+}
+/* }}} */
+
+/* {{{ proto mixed preg_replace(mixed regex, mixed replace, mixed subject [, int limit [, int &count]])
+   Perform Perl-style regular expression replacement. */
+static PHP_FUNCTION(preg_replace)
+{
+	preg_replace_impl(INTERNAL_FUNCTION_PARAM_PASSTHRU, 0, 0);
+}
+/* }}} */
+
+/* {{{ proto mixed preg_replace_callback(mixed regex, mixed callback, mixed subject [, int limit [, int &count]])
+   Perform Perl-style regular expression replacement using replacement callback. */
+static PHP_FUNCTION(preg_replace_callback)
+{
+	preg_replace_impl(INTERNAL_FUNCTION_PARAM_PASSTHRU, 1, 0);
+}
+/* }}} */
+
+/* {{{ proto mixed preg_filter(mixed regex, mixed replace, mixed subject [, int limit [, int &count]])
+   Perform Perl-style regular expression replacement and only return matches. */
+static PHP_FUNCTION(preg_filter)
+{
+	preg_replace_impl(INTERNAL_FUNCTION_PARAM_PASSTHRU, 0, 1);
+}
+/* }}} */
+
+/* {{{ proto array preg_split(string pattern, string subject [, int limit [, int flags]]) 
+   Split string into an array using a perl-style regular expression as a delimiter */
+static PHP_FUNCTION(preg_split)
+{
+	char				*regex;			/* Regular expression */
+	char				*subject;		/* String to match against */
+	int					 regex_len;
+	int					 subject_len;
+	long				 limit_val = -1;/* Integer value of limit */
+	long				 flags = 0;		/* Match control flags */
+	pcre_cache_entry	*pce;			/* Compiled regular expression */
+
+	/* Get function parameters and do error checking */	
+	if (zend_parse_parameters(ZEND_NUM_ARGS() TSRMLS_CC, "ss|ll", &regex, &regex_len,
+							  &subject, &subject_len, &limit_val, &flags) == FAILURE) {
+		RETURN_FALSE;
+	}
+	
+	/* Compile regex or get it from cache. */
+	if ((pce = pcre_get_compiled_regex_cache(regex, regex_len TSRMLS_CC)) == NULL) {
+		RETURN_FALSE;
+	}
+
+	php_pcre_split_impl(pce, subject, subject_len, return_value, limit_val, flags TSRMLS_CC);
+}
+/* }}} */
+
+/* {{{ php_pcre_split
+ */
+PHPAPI void php_pcre_split_impl(pcre_cache_entry *pce, char *subject, int subject_len, zval *return_value,
+	long limit_val, long flags TSRMLS_DC)
+{
+	pcre_extra		*extra = NULL;		/* Holds results of studying */
+	pcre			*re_bump = NULL;	/* Regex instance for empty matches */
+	pcre_extra		*extra_bump = NULL;	/* Almost dummy */
+	pcre_extra		 extra_data;		/* Used locally for exec options */
+	int				*offsets;			/* Array of subpattern offsets */
+	int				 size_offsets;		/* Size of the offsets array */
+	int				 exoptions = 0;		/* Execution options */
+	int				 count = 0;			/* Count of matched subpatterns */
+	int				 start_offset;		/* Where the new search starts */
+	int				 next_offset;		/* End of the last delimiter match + 1 */
+	int				 g_notempty = 0;	/* If the match should not be empty */
+	char			*last_match;		/* Location of last match */
+	int				 rc;
+	int				 no_empty;			/* If NO_EMPTY flag is set */
+	int				 delim_capture; 	/* If delimiters should be captured */
+	int				 offset_capture;	/* If offsets should be captured */
+
+	no_empty = flags & PREG_SPLIT_NO_EMPTY;
+	delim_capture = flags & PREG_SPLIT_DELIM_CAPTURE;
+	offset_capture = flags & PREG_SPLIT_OFFSET_CAPTURE;
+	
+	if (limit_val == 0) {
+		limit_val = -1;
+	}
+
+	if (extra == NULL) {
+		extra_data.flags = PCRE_EXTRA_MATCH_LIMIT | PCRE_EXTRA_MATCH_LIMIT_RECURSION;
+		extra = &extra_data;
+	}
+	extra->match_limit = PCRE_G(backtrack_limit);
+	extra->match_limit_recursion = PCRE_G(recursion_limit);
+	
+	/* Initialize return value */
+	array_init(return_value);
+
+	/* Calculate the size of the offsets array, and allocate memory for it. */
+	rc = pcre_fullinfo(pce->re, extra, PCRE_INFO_CAPTURECOUNT, &size_offsets);
+	if (rc < 0) {
+		php_error_docref(NULL TSRMLS_CC, E_WARNING, "Internal pcre_fullinfo() error %d", rc);
+		RETURN_FALSE;
+	}
+	size_offsets = (size_offsets + 1) * 3;
+	offsets = (int *)safe_emalloc(size_offsets, sizeof(int), 0);
+	
+	/* Start at the beginning of the string */
+	start_offset = 0;
+	next_offset = 0;
+	last_match = subject;
+	PCRE_G(error_code) = PHP_PCRE_NO_ERROR;
+	
+	/* Get next piece if no limit or limit not yet reached and something matched*/
+	while ((limit_val == -1 || limit_val > 1)) {
+		count = pcre_exec(pce->re, extra, subject,
+						  subject_len, start_offset,
+						  exoptions|g_notempty, offsets, size_offsets);
+
+		/* the string was already proved to be valid UTF-8 */
+		exoptions |= PCRE_NO_UTF8_CHECK;
+
+		/* Check for too many substrings condition. */
+		if (count == 0) {
+			php_error_docref(NULL TSRMLS_CC,E_NOTICE, "Matched, but too many substrings");
+			count = size_offsets/3;
+		}
+				
+		/* If something matched */
+		if (count > 0) {
+			if (!no_empty || &subject[offsets[0]] != last_match) {
+
+				if (offset_capture) {
+					/* Add (match, offset) pair to the return value */
+					add_offset_pair(return_value, last_match, &subject[offsets[0]]-last_match, next_offset, NULL);
+				} else {
+					/* Add the piece to the return value */
+					add_next_index_stringl(return_value, last_match,
+								   	   &subject[offsets[0]]-last_match, 1);
+				}
+
+				/* One less left to do */
+				if (limit_val != -1)
+					limit_val--;
+			}
+			
+			last_match = &subject[offsets[1]];
+			next_offset = offsets[1];
+
+			if (delim_capture) {
+				int i, match_len;
+				for (i = 1; i < count; i++) {
+					match_len = offsets[(i<<1)+1] - offsets[i<<1];
+					/* If we have matched a delimiter */
+					if (!no_empty || match_len > 0) {
+						if (offset_capture) {
+							add_offset_pair(return_value, &subject[offsets[i<<1]], match_len, offsets[i<<1], NULL);
+						} else {
+							add_next_index_stringl(return_value,
+												   &subject[offsets[i<<1]],
+												   match_len, 1);
+						}
+					}
+				}
+			}
+		} else if (count == PCRE_ERROR_NOMATCH) {
+			/* If we previously set PCRE_NOTEMPTY after a null match,
+			   this is not necessarily the end. We need to advance
+			   the start offset, and continue. Fudge the offset values
+			   to achieve this, unless we're already at the end of the string. */
+			if (g_notempty != 0 && start_offset < subject_len) {
+				if (pce->compile_options & PCRE_UTF8) {
+					if (re_bump == NULL) {
+						int dummy;
+
+						if ((re_bump = pcre_get_compiled_regex("/./us", &extra_bump, &dummy TSRMLS_CC)) == NULL) {
+							RETURN_FALSE;
+						}
+					}
+					count = pcre_exec(re_bump, extra_bump, subject,
+							  subject_len, start_offset,
+							  exoptions, offsets, size_offsets);
+					if (count < 1) {
+						php_error_docref(NULL TSRMLS_CC, E_WARNING, "Unknown error");
+						RETURN_FALSE;
+					}
+				} else {
+					offsets[0] = start_offset;
+					offsets[1] = start_offset + 1;
+				}
+			} else
+				break;
+		} else {
+			pcre_handle_exec_error(count TSRMLS_CC);
+			break;
+		}
+
+		/* If we have matched an empty string, mimic what Perl's /g options does.
+		   This turns out to be rather cunning. First we set PCRE_NOTEMPTY and try
+		   the match again at the same point. If this fails (picked up above) we
+		   advance to the next character. */
+		g_notempty = (offsets[1] == offsets[0])? PCRE_NOTEMPTY | PCRE_ANCHORED : 0;
+		
+		/* Advance to the position right after the last full match */
+		start_offset = offsets[1];
+	}
+
+
+	start_offset = last_match - subject; /* the offset might have been incremented, but without further successful matches */
+
+	if (!no_empty || start_offset < subject_len)
+	{
+		if (offset_capture) {
+			/* Add the last (match, offset) pair to the return value */
+			add_offset_pair(return_value, &subject[start_offset], subject_len - start_offset, start_offset, NULL);
+		} else {
+			/* Add the last piece to the return value */
+			add_next_index_stringl(return_value, last_match, subject + subject_len - last_match, 1);
+		}
+	}
+
+	
+	/* Clean up */
+	efree(offsets);
+}
+/* }}} */
+
+/* {{{ proto string preg_quote(string str [, string delim_char])
+   Quote regular expression characters plus an optional character */
+static PHP_FUNCTION(preg_quote)
+{
+	int		 in_str_len;
+	char	*in_str;		/* Input string argument */
+	char	*in_str_end;    /* End of the input string */
+	int		 delim_len = 0;
+	char	*delim = NULL;	/* Additional delimiter argument */
+	char	*out_str,		/* Output string with quoted characters */
+		 	*p,				/* Iterator for input string */
+			*q,				/* Iterator for output string */
+			 delim_char=0,	/* Delimiter character to be quoted */
+			 c;				/* Current character */
+	zend_bool quote_delim = 0; /* Whether to quote additional delim char */
+	
+	/* Get the arguments and check for errors */
+	if (zend_parse_parameters(ZEND_NUM_ARGS() TSRMLS_CC, "s|s", &in_str, &in_str_len,
+							  &delim, &delim_len) == FAILURE) {
+		return;
+	}
+	
+	in_str_end = in_str + in_str_len;
+
+	/* Nothing to do if we got an empty string */
+	if (in_str == in_str_end) {
+		RETURN_EMPTY_STRING();
+	}
+
+	if (delim && *delim) {
+		delim_char = delim[0];
+		quote_delim = 1;
+	}
+	
+	/* Allocate enough memory so that even if each character
+	   is quoted, we won't run out of room */
+	out_str = safe_emalloc(4, in_str_len, 1);
+	
+	/* Go through the string and quote necessary characters */
+	for(p = in_str, q = out_str; p != in_str_end; p++) {
+		c = *p;
+		switch(c) {
+			case '.':
+			case '\\':
+			case '+':
+			case '*':
+			case '?':
+			case '[':
+			case '^':
+			case ']':
+			case '$':
+			case '(':
+			case ')':
+			case '{':
+			case '}':
+			case '=':
+			case '!':
+			case '>':
+			case '<':
+			case '|':
+			case ':':
+			case '-':
+				*q++ = '\\';
+				*q++ = c;
+				break;
+
+			case '\0':
+				*q++ = '\\';
+				*q++ = '0';
+				*q++ = '0';
+				*q++ = '0';
+				break;
+
+			default:
+				if (quote_delim && c == delim_char)
+					*q++ = '\\';
+				*q++ = c;
+				break;
+		}
+	}
+	*q = '\0';
+	
+	/* Reallocate string and return it */
+	RETVAL_STRINGL(erealloc(out_str, q - out_str + 1), q - out_str, 0);
+}
+/* }}} */
+
+/* {{{ proto array preg_grep(string regex, array input [, int flags])
+   Searches array and returns entries which match regex */
+static PHP_FUNCTION(preg_grep)
+{
+	char				*regex;			/* Regular expression */
+	int				 	 regex_len;
+	zval				*input;			/* Input array */
+	long				 flags = 0;		/* Match control flags */
+	pcre_cache_entry	*pce;			/* Compiled regular expression */
+
+	/* Get arguments and do error checking */
+	if (zend_parse_parameters(ZEND_NUM_ARGS() TSRMLS_CC, "sa|l", &regex, &regex_len,
+							  &input, &flags) == FAILURE) {
+		return;
+	}
+	
+	/* Compile regex or get it from cache. */
+	if ((pce = pcre_get_compiled_regex_cache(regex, regex_len TSRMLS_CC)) == NULL) {
+		RETURN_FALSE;
+	}
+	
+	php_pcre_grep_impl(pce, input, return_value, flags TSRMLS_CC);
+}
+/* }}} */
+
+PHPAPI void  php_pcre_grep_impl(pcre_cache_entry *pce, zval *input, zval *return_value, long flags TSRMLS_DC) /* {{{ */
+{
+	zval		   **entry;				/* An entry in the input array */
+	pcre_extra		*extra = pce->extra;/* Holds results of studying */
+	pcre_extra		 extra_data;		/* Used locally for exec options */
+	int				*offsets;			/* Array of subpattern offsets */
+	int				 size_offsets;		/* Size of the offsets array */
+	int				 count = 0;			/* Count of matched subpatterns */
+	char			*string_key;
+	ulong			 num_key;
+	zend_bool		 invert;			/* Whether to return non-matching
+										   entries */
+	int				 rc;
+	
+	invert = flags & PREG_GREP_INVERT ? 1 : 0;
+	
+	if (extra == NULL) {
+		extra_data.flags = PCRE_EXTRA_MATCH_LIMIT | PCRE_EXTRA_MATCH_LIMIT_RECURSION;
+		extra = &extra_data;
+	}
+	extra->match_limit = PCRE_G(backtrack_limit);
+	extra->match_limit_recursion = PCRE_G(recursion_limit);
+
+	/* Calculate the size of the offsets array, and allocate memory for it. */
+	rc = pcre_fullinfo(pce->re, extra, PCRE_INFO_CAPTURECOUNT, &size_offsets);
+	if (rc < 0) {
+		php_error_docref(NULL TSRMLS_CC, E_WARNING, "Internal pcre_fullinfo() error %d", rc);
+		RETURN_FALSE;
+	}
+	size_offsets = (size_offsets + 1) * 3;
+	offsets = (int *)safe_emalloc(size_offsets, sizeof(int), 0);
+	
+	/* Initialize return array */
+	array_init(return_value);
+
+	PCRE_G(error_code) = PHP_PCRE_NO_ERROR;
+
+	/* Go through the input array */
+	zend_hash_internal_pointer_reset(Z_ARRVAL_P(input));
+	while (zend_hash_get_current_data(Z_ARRVAL_P(input), (void **)&entry) == SUCCESS) {
+		zval subject = **entry;
+
+		if (Z_TYPE_PP(entry) != IS_STRING) {
+			zval_copy_ctor(&subject);
+			convert_to_string(&subject);
+		}
+
+		/* Perform the match */
+		count = pcre_exec(pce->re, extra, Z_STRVAL(subject),
+						  Z_STRLEN(subject), 0,
+						  0, offsets, size_offsets);
+
+		/* Check for too many substrings condition. */
+		if (count == 0) {
+			php_error_docref(NULL TSRMLS_CC, E_NOTICE, "Matched, but too many substrings");
+			count = size_offsets/3;
+		} else if (count < 0 && count != PCRE_ERROR_NOMATCH) {
+			pcre_handle_exec_error(count TSRMLS_CC);
+			break;
+		}
+
+		/* If the entry fits our requirements */
+		if ((count > 0 && !invert) || (count == PCRE_ERROR_NOMATCH && invert)) {
+
+			Z_ADDREF_PP(entry);
+
+			/* Add to return array */
+			switch (zend_hash_get_current_key(Z_ARRVAL_P(input), &string_key, &num_key, 0))
+			{
+				case HASH_KEY_IS_STRING:
+					zend_hash_update(Z_ARRVAL_P(return_value), string_key,
+									 strlen(string_key)+1, entry, sizeof(zval *), NULL);
+					break;
+
+				case HASH_KEY_IS_LONG:
+					zend_hash_index_update(Z_ARRVAL_P(return_value), num_key, entry,
+										   sizeof(zval *), NULL);
+					break;
+			}
+		}
+
+		if (Z_TYPE_PP(entry) != IS_STRING) {
+			zval_dtor(&subject);
+		}
+
+		zend_hash_move_forward(Z_ARRVAL_P(input));
+	}
+	zend_hash_internal_pointer_reset(Z_ARRVAL_P(input));
+	/* Clean up */
+	efree(offsets);
+}
+/* }}} */
+
+/* {{{ proto int preg_last_error()
+   Returns the error code of the last regexp execution. */
+static PHP_FUNCTION(preg_last_error)
+{
+	if (zend_parse_parameters(ZEND_NUM_ARGS() TSRMLS_CC, "") == FAILURE) {
+		return;
+	}
+
+	RETURN_LONG(PCRE_G(error_code));
+}
+/* }}} */
+
+/* {{{ module definition structures */
+
+/* {{{ arginfo */
+ZEND_BEGIN_ARG_INFO_EX(arginfo_preg_match, 0, 0, 2)
+    ZEND_ARG_INFO(0, pattern)
+    ZEND_ARG_INFO(0, subject)
+    ZEND_ARG_INFO(1, subpatterns) /* array */
+    ZEND_ARG_INFO(0, flags)
+    ZEND_ARG_INFO(0, offset)
+ZEND_END_ARG_INFO()
+
+ZEND_BEGIN_ARG_INFO_EX(arginfo_preg_match_all, 0, 0, 2)
+    ZEND_ARG_INFO(0, pattern)
+    ZEND_ARG_INFO(0, subject)
+    ZEND_ARG_INFO(1, subpatterns) /* array */
+    ZEND_ARG_INFO(0, flags)
+    ZEND_ARG_INFO(0, offset)
+ZEND_END_ARG_INFO()
+
+ZEND_BEGIN_ARG_INFO_EX(arginfo_preg_replace, 0, 0, 3)
+    ZEND_ARG_INFO(0, regex)
+    ZEND_ARG_INFO(0, replace)
+    ZEND_ARG_INFO(0, subject)
+    ZEND_ARG_INFO(0, limit)
+    ZEND_ARG_INFO(1, count)
+ZEND_END_ARG_INFO()
+
+ZEND_BEGIN_ARG_INFO_EX(arginfo_preg_replace_callback, 0, 0, 3)
+    ZEND_ARG_INFO(0, regex)
+    ZEND_ARG_INFO(0, callback)
+    ZEND_ARG_INFO(0, subject)
+    ZEND_ARG_INFO(0, limit)
+    ZEND_ARG_INFO(1, count)
+ZEND_END_ARG_INFO()
+
+ZEND_BEGIN_ARG_INFO_EX(arginfo_preg_split, 0, 0, 2)
+    ZEND_ARG_INFO(0, pattern)
+    ZEND_ARG_INFO(0, subject)
+    ZEND_ARG_INFO(0, limit)
+    ZEND_ARG_INFO(0, flags) 
+ZEND_END_ARG_INFO()
+
+ZEND_BEGIN_ARG_INFO_EX(arginfo_preg_quote, 0, 0, 1)
+    ZEND_ARG_INFO(0, str)
+    ZEND_ARG_INFO(0, delim_char)
+ZEND_END_ARG_INFO()
+
+ZEND_BEGIN_ARG_INFO_EX(arginfo_preg_grep, 0, 0, 2)
+    ZEND_ARG_INFO(0, regex)
+    ZEND_ARG_INFO(0, input) /* array */
+    ZEND_ARG_INFO(0, flags)
+ZEND_END_ARG_INFO()
+
+ZEND_BEGIN_ARG_INFO(arginfo_preg_last_error, 0)
+ZEND_END_ARG_INFO()
+/* }}} */
+
+static const zend_function_entry pcre_functions[] = {
+	PHP_FE(preg_match,				arginfo_preg_match)
+	PHP_FE(preg_match_all,			arginfo_preg_match_all)
+	PHP_FE(preg_replace,			arginfo_preg_replace)
+	PHP_FE(preg_replace_callback,	arginfo_preg_replace_callback)
+	PHP_FE(preg_filter,				arginfo_preg_replace)
+	PHP_FE(preg_split,				arginfo_preg_split)
+	PHP_FE(preg_quote,				arginfo_preg_quote)
+	PHP_FE(preg_grep,				arginfo_preg_grep)
+	PHP_FE(preg_last_error,			arginfo_preg_last_error)
+	PHP_FE_END
+};
+
+zend_module_entry pcre_module_entry = {
+	STANDARD_MODULE_HEADER,
+   "pcre",
+	pcre_functions,
+	PHP_MINIT(pcre),
+	PHP_MSHUTDOWN(pcre),
+	NULL,
+	NULL,
+	PHP_MINFO(pcre),
+	NO_VERSION_YET,
+	PHP_MODULE_GLOBALS(pcre),
+	PHP_GINIT(pcre),
+	PHP_GSHUTDOWN(pcre),
+	NULL,
+	STANDARD_MODULE_PROPERTIES_EX
+};
+
+#ifdef COMPILE_DL_PCRE
+ZEND_GET_MODULE(pcre)
+#endif
+
+/* }}} */
+
+#endif /* HAVE_PCRE || HAVE_BUNDLED_PCRE */
+
+/*
+ * Local variables:
+ * tab-width: 4
+ * c-basic-offset: 4
+ * End:
+ * vim600: sw=4 ts=4 fdm=marker
+ * vim<600: sw=4 ts=4
+ */
diff --git a/ext/pcre/php_pcre.def b/ext/pcre/php_pcre.def
new file mode 100644
index 0000000..769b064
--- /dev/null
+++ b/ext/pcre/php_pcre.def
@@ -0,0 +1,11 @@
+EXPORTS
+php_pcre_compile
+php_pcre_copy_substring
+php_pcre_exec
+php_pcre_get_substring
+php_pcre_get_substring_list
+php_pcre_maketables
+php_pcre_study
+php_pcre_version
+php_pcre_fullinfo
+php_pcre_free
diff --git a/ext/pcre/php_pcre.h b/ext/pcre/php_pcre.h
new file mode 100644
index 0000000..db14ce3
--- /dev/null
+++ b/ext/pcre/php_pcre.h
@@ -0,0 +1,90 @@
+/*
+   +----------------------------------------------------------------------+
+   | PHP Version 5                                                        |
+   +----------------------------------------------------------------------+
+   | Copyright (c) 1997-2013 The PHP Group                                |
+   +----------------------------------------------------------------------+
+   | This source file is subject to version 3.01 of the PHP license,      |
+   | that is bundled with this package in the file LICENSE, and is        |
+   | available through the world-wide-web at the following url:           |
+   | http://www.php.net/license/3_01.txt                                  |
+   | If you did not receive a copy of the PHP license and are unable to   |
+   | obtain it through the world-wide-web, please send a note to          |
+   | license@php.net so we can mail you a copy immediately.               |
+   +----------------------------------------------------------------------+
+   | Author: Andrei Zmievski <andrei@php.net>                             |
+   +----------------------------------------------------------------------+
+ */
+ 
+/* $Id$ */
+
+#ifndef PHP_PCRE_H
+#define PHP_PCRE_H
+
+#if HAVE_PCRE || HAVE_BUNDLED_PCRE
+
+#if HAVE_BUNDLED_PCRE
+#include "pcrelib/pcre.h"
+#else
+#include "pcre.h"
+#endif
+
+#if HAVE_LOCALE_H
+#include <locale.h>
+#endif
+
+PHPAPI char *php_pcre_replace(char *regex, int regex_len, char *subject, int subject_len, zval *replace_val, int is_callable_replace, int *result_len, int limit, int *replace_count TSRMLS_DC);
+PHPAPI pcre* pcre_get_compiled_regex(char *regex, pcre_extra **extra, int *options TSRMLS_DC);
+PHPAPI pcre* pcre_get_compiled_regex_ex(char *regex, pcre_extra **extra, int *preg_options, int *coptions TSRMLS_DC);
+
+extern zend_module_entry pcre_module_entry;
+#define pcre_module_ptr &pcre_module_entry
+
+typedef struct {
+	pcre *re;
+	pcre_extra *extra;
+	int preg_options;
+#if HAVE_SETLOCALE
+	char *locale;
+	unsigned const char *tables;
+#endif
+	int compile_options;
+	int refcount;
+} pcre_cache_entry;
+
+PHPAPI pcre_cache_entry* pcre_get_compiled_regex_cache(char *regex, int regex_len TSRMLS_DC);
+
+PHPAPI void  php_pcre_match_impl(  pcre_cache_entry *pce, char *subject, int subject_len, zval *return_value,
+	zval *subpats, int global, int use_flags, long flags, long start_offset TSRMLS_DC);
+
+PHPAPI char *php_pcre_replace_impl(pcre_cache_entry *pce, char *subject, int subject_len, zval *return_value, 
+	int is_callable_replace, int *result_len, int limit, int *replace_count TSRMLS_DC);
+
+PHPAPI void  php_pcre_split_impl(  pcre_cache_entry *pce, char *subject, int subject_len, zval *return_value,
+	long limit_val, long flags TSRMLS_DC);
+
+PHPAPI void  php_pcre_grep_impl(   pcre_cache_entry *pce, zval *input, zval *return_value,
+	long flags TSRMLS_DC);
+
+ZEND_BEGIN_MODULE_GLOBALS(pcre)
+	HashTable pcre_cache;
+	long backtrack_limit;
+	long recursion_limit;
+	int  error_code;
+ZEND_END_MODULE_GLOBALS(pcre)
+
+#ifdef ZTS
+# define PCRE_G(v) TSRMG(pcre_globals_id, zend_pcre_globals *, v)
+#else
+# define PCRE_G(v)	(pcre_globals.v)
+#endif
+
+#else
+
+#define pcre_module_ptr NULL
+
+#endif /* HAVE_PCRE || HAVE_BUNDLED_PCRE */
+
+#define phpext_pcre_ptr pcre_module_ptr
+
+#endif /* PHP_PCRE_H */
diff --git a/ext/pcre/tests/001.phpt b/ext/pcre/tests/001.phpt
new file mode 100644
index 0000000..313f7fd
--- /dev/null
+++ b/ext/pcre/tests/001.phpt
@@ -0,0 +1,87 @@
+--TEST--
+abusing preg_match()
+--FILE--
+<?php
+
+foreach (array('2006-05-13', '06-12-12', 'data: "12-Aug-87"') as $s) {
+	var_dump(preg_match('~
+		(?P<date> 
+		(?P<year>(\d{2})?\d\d) -
+		(?P<month>(?:\d\d|[a-zA-Z]{2,3})) -
+		(?P<day>[0-3]?\d))
+	~x', $s, $m));
+
+	var_dump($m);
+}
+
+?>
+--EXPECT--
+int(1)
+array(10) {
+  [0]=>
+  string(10) "2006-05-13"
+  ["date"]=>
+  string(10) "2006-05-13"
+  [1]=>
+  string(10) "2006-05-13"
+  ["year"]=>
+  string(4) "2006"
+  [2]=>
+  string(4) "2006"
+  [3]=>
+  string(2) "20"
+  ["month"]=>
+  string(2) "05"
+  [4]=>
+  string(2) "05"
+  ["day"]=>
+  string(2) "13"
+  [5]=>
+  string(2) "13"
+}
+int(1)
+array(10) {
+  [0]=>
+  string(8) "06-12-12"
+  ["date"]=>
+  string(8) "06-12-12"
+  [1]=>
+  string(8) "06-12-12"
+  ["year"]=>
+  string(2) "06"
+  [2]=>
+  string(2) "06"
+  [3]=>
+  string(0) ""
+  ["month"]=>
+  string(2) "12"
+  [4]=>
+  string(2) "12"
+  ["day"]=>
+  string(2) "12"
+  [5]=>
+  string(2) "12"
+}
+int(1)
+array(10) {
+  [0]=>
+  string(8) "12-Aug-8"
+  ["date"]=>
+  string(8) "12-Aug-8"
+  [1]=>
+  string(8) "12-Aug-8"
+  ["year"]=>
+  string(2) "12"
+  [2]=>
+  string(2) "12"
+  [3]=>
+  string(0) ""
+  ["month"]=>
+  string(3) "Aug"
+  [4]=>
+  string(3) "Aug"
+  ["day"]=>
+  string(1) "8"
+  [5]=>
+  string(1) "8"
+}
diff --git a/ext/pcre/tests/002.phpt b/ext/pcre/tests/002.phpt
new file mode 100644
index 0000000..00f68f3
--- /dev/null
+++ b/ext/pcre/tests/002.phpt
@@ -0,0 +1,40 @@
+--TEST--
+preg_* with bogus vals
+--FILE--
+<?php
+
+var_dump(preg_match());
+var_dump(preg_match_all());
+var_dump(preg_match_all('//', '', $dummy, 0xdead));
+
+var_dump(preg_quote());
+var_dump(preg_quote(''));
+
+var_dump(preg_replace('/(.)/', '${1}${1', 'abc'));
+var_dump(preg_replace('/.++\d*+[/', 'for ($', 'abc'));
+var_dump(preg_replace('/(.)/e', 'for ($', 'abc'));
+
+?>
+--EXPECTF--
+
+Warning: preg_match() expects at least 2 parameters, 0 given in %s002.php on line 3
+bool(false)
+
+Warning: preg_match_all() expects at least 2 parameters, 0 given in %s002.php on line 4
+bool(false)
+
+Warning: preg_match_all(): Invalid flags specified in %s002.php on line 5
+NULL
+
+Warning: preg_quote() expects at least 1 parameter, 0 given in %s002.php on line 7
+NULL
+string(0) ""
+string(12) "a${1b${1c${1"
+
+Warning: preg_replace(): Compilation failed: missing terminating ] for character class at offset 8 in %s002.php on line 11
+NULL
+
+Parse error: %s in %s002.php(12) : regexp code on line 1
+
+Fatal error: preg_replace(): Failed evaluating code: 
+for ($ in %s002.php on line 12
diff --git a/ext/pcre/tests/003.phpt b/ext/pcre/tests/003.phpt
new file mode 100644
index 0000000..e697c37
--- /dev/null
+++ b/ext/pcre/tests/003.phpt
@@ -0,0 +1,140 @@
+--TEST--
+abusing preg_match_all()
+--FILE--
+<?php
+
+foreach (array(PREG_PATTERN_ORDER, PREG_SET_ORDER) as $flag) {
+	var_dump(preg_match_all('~
+		(?P<date> 
+		(?P<year>(\d{2})?\d\d) -
+		(?P<month>(?:\d\d|[a-zA-Z]{2,3})) -
+		(?P<day>[0-3]?\d))
+		~x',
+		'2006-05-13 e outra data: "12-Aug-37"', $m, $flag));
+
+	var_dump($m);
+}
+?>
+--EXPECT--
+int(2)
+array(10) {
+  [0]=>
+  array(2) {
+    [0]=>
+    string(10) "2006-05-13"
+    [1]=>
+    string(9) "12-Aug-37"
+  }
+  ["date"]=>
+  array(2) {
+    [0]=>
+    string(10) "2006-05-13"
+    [1]=>
+    string(9) "12-Aug-37"
+  }
+  [1]=>
+  array(2) {
+    [0]=>
+    string(10) "2006-05-13"
+    [1]=>
+    string(9) "12-Aug-37"
+  }
+  ["year"]=>
+  array(2) {
+    [0]=>
+    string(4) "2006"
+    [1]=>
+    string(2) "12"
+  }
+  [2]=>
+  array(2) {
+    [0]=>
+    string(4) "2006"
+    [1]=>
+    string(2) "12"
+  }
+  [3]=>
+  array(2) {
+    [0]=>
+    string(2) "20"
+    [1]=>
+    string(0) ""
+  }
+  ["month"]=>
+  array(2) {
+    [0]=>
+    string(2) "05"
+    [1]=>
+    string(3) "Aug"
+  }
+  [4]=>
+  array(2) {
+    [0]=>
+    string(2) "05"
+    [1]=>
+    string(3) "Aug"
+  }
+  ["day"]=>
+  array(2) {
+    [0]=>
+    string(2) "13"
+    [1]=>
+    string(2) "37"
+  }
+  [5]=>
+  array(2) {
+    [0]=>
+    string(2) "13"
+    [1]=>
+    string(2) "37"
+  }
+}
+int(2)
+array(2) {
+  [0]=>
+  array(10) {
+    [0]=>
+    string(10) "2006-05-13"
+    ["date"]=>
+    string(10) "2006-05-13"
+    [1]=>
+    string(10) "2006-05-13"
+    ["year"]=>
+    string(4) "2006"
+    [2]=>
+    string(4) "2006"
+    [3]=>
+    string(2) "20"
+    ["month"]=>
+    string(2) "05"
+    [4]=>
+    string(2) "05"
+    ["day"]=>
+    string(2) "13"
+    [5]=>
+    string(2) "13"
+  }
+  [1]=>
+  array(10) {
+    [0]=>
+    string(9) "12-Aug-37"
+    ["date"]=>
+    string(9) "12-Aug-37"
+    [1]=>
+    string(9) "12-Aug-37"
+    ["year"]=>
+    string(2) "12"
+    [2]=>
+    string(2) "12"
+    [3]=>
+    string(0) ""
+    ["month"]=>
+    string(3) "Aug"
+    [4]=>
+    string(3) "Aug"
+    ["day"]=>
+    string(2) "37"
+    [5]=>
+    string(2) "37"
+  }
+}
diff --git a/ext/pcre/tests/004.phpt b/ext/pcre/tests/004.phpt
new file mode 100644
index 0000000..b1e9586
--- /dev/null
+++ b/ext/pcre/tests/004.phpt
@@ -0,0 +1,149 @@
+--TEST--
+abusing pcre
+--FILE--
+<?php
+
+var_dump(preg_match_all('/((?:(?:unsigned|struct)\s+)?\w+)(?:\s*(\*+)\s+|\s+(\**))(\w+(?:\[\s*\w*\s*\])?)\s*(?:(=)[^,;]+)?((?:\s*,\s*\**\s*\w+(?:\[\s*\w*\s*\])?\s*(?:=[^,;]+)?)*)\s*;/S', 'unsigned int xpto = 124; short a, b;', $m, PREG_SET_ORDER));
+var_dump($m);
+
+var_dump(preg_match_all('/(?:\([^)]+\))?(&?)([\w>.()-]+(?:\[\w+\])?)\s*,?((?:\)*\s*=)?)/S', '&a, b, &c', $m, PREG_SET_ORDER));
+var_dump($m);
+
+var_dump(preg_match_all('/zend_parse_parameters(?:_ex\s*\([^,]+,[^,]+|\s*\([^,]+),\s*"([^"]*)"\s*,\s*([^{;]*)/S', 'zend_parse_parameters( 0, "addd|s/", a, b, &c);', $m, PREG_SET_ORDER | PREG_OFFSET_CAPTURE));
+var_dump($m);
+
+var_dump(preg_replace(array('@//.*@S', '@/\*.*\*/@SsUe'), array('', 'preg_replace("/[^\r\n]+/S", "", \'$0\')'), "hello\n//x \n/*\ns\n*/"));
+
+var_dump(preg_split('/PHP_(?:NAMED_)?(?:FUNCTION|METHOD)\s*\((\w+(?:,\s*\w+)?)\)/S', "PHP_FUNCTION(s, preg_match)\n{\nlalala", -1, PREG_SPLIT_DELIM_CAPTURE | PREG_SPLIT_OFFSET_CAPTURE));
+?>
+--EXPECT--
+int(2)
+array(2) {
+  [0]=>
+  array(7) {
+    [0]=>
+    string(24) "unsigned int xpto = 124;"
+    [1]=>
+    string(12) "unsigned int"
+    [2]=>
+    string(0) ""
+    [3]=>
+    string(0) ""
+    [4]=>
+    string(4) "xpto"
+    [5]=>
+    string(1) "="
+    [6]=>
+    string(0) ""
+  }
+  [1]=>
+  array(7) {
+    [0]=>
+    string(11) "short a, b;"
+    [1]=>
+    string(5) "short"
+    [2]=>
+    string(0) ""
+    [3]=>
+    string(0) ""
+    [4]=>
+    string(1) "a"
+    [5]=>
+    string(0) ""
+    [6]=>
+    string(3) ", b"
+  }
+}
+int(3)
+array(3) {
+  [0]=>
+  array(4) {
+    [0]=>
+    string(3) "&a,"
+    [1]=>
+    string(1) "&"
+    [2]=>
+    string(1) "a"
+    [3]=>
+    string(0) ""
+  }
+  [1]=>
+  array(4) {
+    [0]=>
+    string(2) "b,"
+    [1]=>
+    string(0) ""
+    [2]=>
+    string(1) "b"
+    [3]=>
+    string(0) ""
+  }
+  [2]=>
+  array(4) {
+    [0]=>
+    string(2) "&c"
+    [1]=>
+    string(1) "&"
+    [2]=>
+    string(1) "c"
+    [3]=>
+    string(0) ""
+  }
+}
+int(1)
+array(1) {
+  [0]=>
+  array(3) {
+    [0]=>
+    array(2) {
+      [0]=>
+      string(46) "zend_parse_parameters( 0, "addd|s/", a, b, &c)"
+      [1]=>
+      int(0)
+    }
+    [1]=>
+    array(2) {
+      [0]=>
+      string(7) "addd|s/"
+      [1]=>
+      int(27)
+    }
+    [2]=>
+    array(2) {
+      [0]=>
+      string(9) "a, b, &c)"
+      [1]=>
+      int(37)
+    }
+  }
+}
+string(9) "hello
+
+
+
+"
+array(3) {
+  [0]=>
+  array(2) {
+    [0]=>
+    string(0) ""
+    [1]=>
+    int(0)
+  }
+  [1]=>
+  array(2) {
+    [0]=>
+    string(13) "s, preg_match"
+    [1]=>
+    int(13)
+  }
+  [2]=>
+  array(2) {
+    [0]=>
+    string(9) "
+{
+lalala"
+    [1]=>
+    int(27)
+  }
+}
diff --git a/ext/pcre/tests/005.phpt b/ext/pcre/tests/005.phpt
new file mode 100644
index 0000000..5eff83e
--- /dev/null
+++ b/ext/pcre/tests/005.phpt
@@ -0,0 +1,476 @@
+--TEST--
+abusing preg_match_all() #2
+--FILE--
+<?php
+// this file is not used in the cron job
+// use it to test the gcc regex with the sample data provided
+
+$sampledata = "
+/p2/var/php_gcov/PHP_4_4/ext/ming/ming.c: In function `zif_swfbitmap_init':
+/p2/var/php_gcov/PHP_4_4/ext/ming/ming.c:323: warning: assignment from incompatible pointer type
+/p2/var/php_gcov/PHP_4_4/ext/ming/ming.c: In function `zif_swftextfield_setFont':
+/p2/var/php_gcov/PHP_4_4/ext/ming/ming.c:2597: warning: passing arg 2 of `SWFTextField_setFont' from incompatible pointer type
+/p2/var/php_gcov/PHP_4_4/ext/oci8/oci8.c:1027: warning: `oci_ping' defined but not used
+/p2/var/php_gcov/PHP_4_4/ext/posix/posix.c: In function `zif_posix_getpgid':
+/p2/var/php_gcov/PHP_4_4/ext/posix/posix.c:484: warning: implicit declaration of function `getpgid'
+/p2/var/php_gcov/PHP_4_4/ext/posix/posix.c: In function `zif_posix_getsid':
+/p2/var/php_gcov/PHP_4_4/ext/posix/posix.c:506: warning: implicit declaration of function `getsid'
+/p2/var/php_gcov/PHP_4_4/ext/session/mod_files.c: In function `ps_read_files':
+/p2/var/php_gcov/PHP_4_4/ext/session/mod_files.c:302: warning: implicit declaration of function `pread'
+/p2/var/php_gcov/PHP_4_4/ext/session/mod_files.c: In function `ps_write_files':
+/p2/var/php_gcov/PHP_4_4/ext/session/mod_files.c:340: warning: implicit declaration of function `pwrite'
+/p2/var/php_gcov/PHP_4_4/ext/sockets/sockets.c: In function `zif_socket_get_option':
+/p2/var/php_gcov/PHP_4_4/ext/sockets/sockets.c:1862: warning: unused variable `timeout'
+/p2/var/php_gcov/PHP_4_4/ext/sockets/sockets.c: In function `zif_socket_set_option':
+/p2/var/php_gcov/PHP_4_4/ext/sockets/sockets.c:1941: warning: unused variable `timeout'
+/p2/var/php_gcov/PHP_4_4/regex/regexec.c:19: warning: `nope' defined but not used
+/p2/var/php_gcov/PHP_4_4/ext/standard/exec.c:50: warning: `php_make_safe_mode_command' defined but not used
+/p2/var/php_gcov/PHP_4_4/ext/standard/image.c: In function `php_handle_jpc':
+/p2/var/php_gcov/PHP_4_4/ext/standard/image.c:604: warning: unused variable `dummy_int'
+/p2/var/php_gcov/PHP_4_4/ext/standard/parsedate.c: In function `php_gd_parse':
+/p2/var/php_gcov/PHP_4_4/ext/standard/parsedate.c:1138: warning: implicit declaration of function `php_gd_lex'
+/p2/var/php_gcov/PHP_4_4/ext/standard/parsedate.y: At top level:
+/p2/var/php_gcov/PHP_4_4/ext/standard/parsedate.y:864: warning: return type defaults to `int'
+/p2/var/php_gcov/PHP_4_4/ext/sysvmsg/sysvmsg.c: In function `zif_msg_receive':
+/p2/var/php_gcov/PHP_4_4/ext/sysvmsg/sysvmsg.c:318: warning: passing arg 2 of `php_var_unserialize' from incompatible pointer type
+/p2/var/php_gcov/PHP_4_4/ext/yp/yp.c: In function `zif_yp_err_string':
+/p2/var/php_gcov/PHP_4_4/ext/yp/yp.c:372: warning: assignment discards qualifiers from pointer target type
+Zend/zend_language_scanner.c:5944: warning: `yy_fatal_error' defined but not used
+Zend/zend_language_scanner.c:2627: warning: `yy_last_accepting_state' defined but not used
+Zend/zend_language_scanner.c:2628: warning: `yy_last_accepting_cpos' defined but not used
+Zend/zend_language_scanner.c:2634: warning: `yy_more_flag' defined but not used
+Zend/zend_language_scanner.c:2635: warning: `yy_more_len' defined but not used
+Zend/zend_language_scanner.c:5483: warning: `yyunput' defined but not used
+Zend/zend_language_scanner.c:5929: warning: `yy_top_state' defined but not used
+conflicts: 2 shift/reduce
+Zend/zend_ini_scanner.c:457: warning: `yy_last_accepting_state' defined but not used
+Zend/zend_ini_scanner.c:458: warning: `yy_last_accepting_cpos' defined but not used
+Zend/zend_ini_scanner.c:1361: warning: `yyunput' defined but not used
+/p2/var/php_gcov/PHP_4_4/Zend/zend_alloc.c: In function `_safe_emalloc':
+/p2/var/php_gcov/PHP_4_4/Zend/zend_alloc.c:237: warning: long int format, size_t arg (arg 3)
+/p2/var/php_gcov/PHP_4_4/Zend/zend_alloc.c:237: warning: long int format, size_t arg (arg 4)
+/p2/var/php_gcov/PHP_4_4/Zend/zend_alloc.c:237: warning: long int format, size_t arg (arg 5)
+/p2/var/php_gcov/PHP_4_4/Zend/zend_ini.c:338: warning: `zend_ini_displayer_cb' defined but not used
+ext/mysql/libmysql/my_tempnam.o(.text+0x80): In function `my_tempnam':
+/p2/var/php_gcov/PHP_4_4/ext/mysql/libmysql/my_tempnam.c:115: warning: the use of `tempnam' is dangerous, better use `mkstemp'
+ext/mysql/libmysql/my_tempnam.o(.text+0x80): In function `my_tempnam':
+/p2/var/php_gcov/PHP_4_4/ext/mysql/libmysql/my_tempnam.c:115: warning: the use of `tempnam' is dangerous, better use `mkstemp'
+ext/ming/ming.o(.text+0xc115): In function `zim_swfmovie_namedAnchor':
+/p2/var/php_gcov/PHP_5_2/ext/ming/ming.c:2207: undefined reference to `SWFMovie_namedAnchor'
+/p2/var/php_gcov/PHP_5_2/ext/ming/ming.c:2209: undefined reference to `SWFMovie_xpto'
+/p2/var/php_gcov/PHP_5_2/ext/ming/ming.c:2259: undefined reference to `SWFMovie_foo'
+ext/ming/ming.o(.text+0x851): In function `zif_ming_setSWFCompression':
+/p2/var/php_gcov/PHP_5_2/ext/ming/ming.c:154: undefined reference to `Ming_setSWFCompression'
+";
+
+	// Regular expression to select the error and warning information
+	// tuned for gcc 3.4, 4.0 and 4.1
+	$gcc_regex = '/^((.+)(\(\.text\+0x[[:xdigit:]]+\))?: In function [`\'](\w+)\':\s+)?'.
+		'((?(1)(?(3)[^:\n]+|\2)|[^:\n]+)):(\d+): (?:(error|warning):\s+)?(.+)'.
+		str_repeat('(?:\s+\5:(\d+): (?:(error|warning):\s+)?(.+))?', 99). // capture up to 100 errors
+		'/mS';
+
+
+var_dump(preg_match_all($gcc_regex, $sampledata, $m, PREG_SET_ORDER));
+print_r($m);
+
+?>
+--EXPECT--
+int(24)
+Array
+(
+    [0] => Array
+        (
+            [0] => /p2/var/php_gcov/PHP_4_4/ext/ming/ming.c: In function `zif_swfbitmap_init':
+/p2/var/php_gcov/PHP_4_4/ext/ming/ming.c:323: warning: assignment from incompatible pointer type
+            [1] => /p2/var/php_gcov/PHP_4_4/ext/ming/ming.c: In function `zif_swfbitmap_init':
+
+            [2] => /p2/var/php_gcov/PHP_4_4/ext/ming/ming.c
+            [3] => 
+            [4] => zif_swfbitmap_init
+            [5] => /p2/var/php_gcov/PHP_4_4/ext/ming/ming.c
+            [6] => 323
+            [7] => warning
+            [8] => assignment from incompatible pointer type
+        )
+
+    [1] => Array
+        (
+            [0] => /p2/var/php_gcov/PHP_4_4/ext/ming/ming.c: In function `zif_swftextfield_setFont':
+/p2/var/php_gcov/PHP_4_4/ext/ming/ming.c:2597: warning: passing arg 2 of `SWFTextField_setFont' from incompatible pointer type
+            [1] => /p2/var/php_gcov/PHP_4_4/ext/ming/ming.c: In function `zif_swftextfield_setFont':
+
+            [2] => /p2/var/php_gcov/PHP_4_4/ext/ming/ming.c
+            [3] => 
+            [4] => zif_swftextfield_setFont
+            [5] => /p2/var/php_gcov/PHP_4_4/ext/ming/ming.c
+            [6] => 2597
+            [7] => warning
+            [8] => passing arg 2 of `SWFTextField_setFont' from incompatible pointer type
+        )
+
+    [2] => Array
+        (
+            [0] => /p2/var/php_gcov/PHP_4_4/ext/oci8/oci8.c:1027: warning: `oci_ping' defined but not used
+            [1] => 
+            [2] => 
+            [3] => 
+            [4] => 
+            [5] => /p2/var/php_gcov/PHP_4_4/ext/oci8/oci8.c
+            [6] => 1027
+            [7] => warning
+            [8] => `oci_ping' defined but not used
+        )
+
+    [3] => Array
+        (
+            [0] => /p2/var/php_gcov/PHP_4_4/ext/posix/posix.c: In function `zif_posix_getpgid':
+/p2/var/php_gcov/PHP_4_4/ext/posix/posix.c:484: warning: implicit declaration of function `getpgid'
+            [1] => /p2/var/php_gcov/PHP_4_4/ext/posix/posix.c: In function `zif_posix_getpgid':
+
+            [2] => /p2/var/php_gcov/PHP_4_4/ext/posix/posix.c
+            [3] => 
+            [4] => zif_posix_getpgid
+            [5] => /p2/var/php_gcov/PHP_4_4/ext/posix/posix.c
+            [6] => 484
+            [7] => warning
+            [8] => implicit declaration of function `getpgid'
+        )
+
+    [4] => Array
+        (
+            [0] => /p2/var/php_gcov/PHP_4_4/ext/posix/posix.c: In function `zif_posix_getsid':
+/p2/var/php_gcov/PHP_4_4/ext/posix/posix.c:506: warning: implicit declaration of function `getsid'
+            [1] => /p2/var/php_gcov/PHP_4_4/ext/posix/posix.c: In function `zif_posix_getsid':
+
+            [2] => /p2/var/php_gcov/PHP_4_4/ext/posix/posix.c
+            [3] => 
+            [4] => zif_posix_getsid
+            [5] => /p2/var/php_gcov/PHP_4_4/ext/posix/posix.c
+            [6] => 506
+            [7] => warning
+            [8] => implicit declaration of function `getsid'
+        )
+
+    [5] => Array
+        (
+            [0] => /p2/var/php_gcov/PHP_4_4/ext/session/mod_files.c: In function `ps_read_files':
+/p2/var/php_gcov/PHP_4_4/ext/session/mod_files.c:302: warning: implicit declaration of function `pread'
+            [1] => /p2/var/php_gcov/PHP_4_4/ext/session/mod_files.c: In function `ps_read_files':
+
+            [2] => /p2/var/php_gcov/PHP_4_4/ext/session/mod_files.c
+            [3] => 
+            [4] => ps_read_files
+            [5] => /p2/var/php_gcov/PHP_4_4/ext/session/mod_files.c
+            [6] => 302
+            [7] => warning
+            [8] => implicit declaration of function `pread'
+        )
+
+    [6] => Array
+        (
+            [0] => /p2/var/php_gcov/PHP_4_4/ext/session/mod_files.c: In function `ps_write_files':
+/p2/var/php_gcov/PHP_4_4/ext/session/mod_files.c:340: warning: implicit declaration of function `pwrite'
+            [1] => /p2/var/php_gcov/PHP_4_4/ext/session/mod_files.c: In function `ps_write_files':
+
+            [2] => /p2/var/php_gcov/PHP_4_4/ext/session/mod_files.c
+            [3] => 
+            [4] => ps_write_files
+            [5] => /p2/var/php_gcov/PHP_4_4/ext/session/mod_files.c
+            [6] => 340
+            [7] => warning
+            [8] => implicit declaration of function `pwrite'
+        )
+
+    [7] => Array
+        (
+            [0] => /p2/var/php_gcov/PHP_4_4/ext/sockets/sockets.c: In function `zif_socket_get_option':
+/p2/var/php_gcov/PHP_4_4/ext/sockets/sockets.c:1862: warning: unused variable `timeout'
+            [1] => /p2/var/php_gcov/PHP_4_4/ext/sockets/sockets.c: In function `zif_socket_get_option':
+
+            [2] => /p2/var/php_gcov/PHP_4_4/ext/sockets/sockets.c
+            [3] => 
+            [4] => zif_socket_get_option
+            [5] => /p2/var/php_gcov/PHP_4_4/ext/sockets/sockets.c
+            [6] => 1862
+            [7] => warning
+            [8] => unused variable `timeout'
+        )
+
+    [8] => Array
+        (
+            [0] => /p2/var/php_gcov/PHP_4_4/ext/sockets/sockets.c: In function `zif_socket_set_option':
+/p2/var/php_gcov/PHP_4_4/ext/sockets/sockets.c:1941: warning: unused variable `timeout'
+            [1] => /p2/var/php_gcov/PHP_4_4/ext/sockets/sockets.c: In function `zif_socket_set_option':
+
+            [2] => /p2/var/php_gcov/PHP_4_4/ext/sockets/sockets.c
+            [3] => 
+            [4] => zif_socket_set_option
+            [5] => /p2/var/php_gcov/PHP_4_4/ext/sockets/sockets.c
+            [6] => 1941
+            [7] => warning
+            [8] => unused variable `timeout'
+        )
+
+    [9] => Array
+        (
+            [0] => /p2/var/php_gcov/PHP_4_4/regex/regexec.c:19: warning: `nope' defined but not used
+            [1] => 
+            [2] => 
+            [3] => 
+            [4] => 
+            [5] => /p2/var/php_gcov/PHP_4_4/regex/regexec.c
+            [6] => 19
+            [7] => warning
+            [8] => `nope' defined but not used
+        )
+
+    [10] => Array
+        (
+            [0] => /p2/var/php_gcov/PHP_4_4/ext/standard/exec.c:50: warning: `php_make_safe_mode_command' defined but not used
+            [1] => 
+            [2] => 
+            [3] => 
+            [4] => 
+            [5] => /p2/var/php_gcov/PHP_4_4/ext/standard/exec.c
+            [6] => 50
+            [7] => warning
+            [8] => `php_make_safe_mode_command' defined but not used
+        )
+
+    [11] => Array
+        (
+            [0] => /p2/var/php_gcov/PHP_4_4/ext/standard/image.c: In function `php_handle_jpc':
+/p2/var/php_gcov/PHP_4_4/ext/standard/image.c:604: warning: unused variable `dummy_int'
+            [1] => /p2/var/php_gcov/PHP_4_4/ext/standard/image.c: In function `php_handle_jpc':
+
+            [2] => /p2/var/php_gcov/PHP_4_4/ext/standard/image.c
+            [3] => 
+            [4] => php_handle_jpc
+            [5] => /p2/var/php_gcov/PHP_4_4/ext/standard/image.c
+            [6] => 604
+            [7] => warning
+            [8] => unused variable `dummy_int'
+        )
+
+    [12] => Array
+        (
+            [0] => /p2/var/php_gcov/PHP_4_4/ext/standard/parsedate.c: In function `php_gd_parse':
+/p2/var/php_gcov/PHP_4_4/ext/standard/parsedate.c:1138: warning: implicit declaration of function `php_gd_lex'
+            [1] => /p2/var/php_gcov/PHP_4_4/ext/standard/parsedate.c: In function `php_gd_parse':
+
+            [2] => /p2/var/php_gcov/PHP_4_4/ext/standard/parsedate.c
+            [3] => 
+            [4] => php_gd_parse
+            [5] => /p2/var/php_gcov/PHP_4_4/ext/standard/parsedate.c
+            [6] => 1138
+            [7] => warning
+            [8] => implicit declaration of function `php_gd_lex'
+        )
+
+    [13] => Array
+        (
+            [0] => /p2/var/php_gcov/PHP_4_4/ext/standard/parsedate.y:864: warning: return type defaults to `int'
+            [1] => 
+            [2] => 
+            [3] => 
+            [4] => 
+            [5] => /p2/var/php_gcov/PHP_4_4/ext/standard/parsedate.y
+            [6] => 864
+            [7] => warning
+            [8] => return type defaults to `int'
+        )
+
+    [14] => Array
+        (
+            [0] => /p2/var/php_gcov/PHP_4_4/ext/sysvmsg/sysvmsg.c: In function `zif_msg_receive':
+/p2/var/php_gcov/PHP_4_4/ext/sysvmsg/sysvmsg.c:318: warning: passing arg 2 of `php_var_unserialize' from incompatible pointer type
+            [1] => /p2/var/php_gcov/PHP_4_4/ext/sysvmsg/sysvmsg.c: In function `zif_msg_receive':
+
+            [2] => /p2/var/php_gcov/PHP_4_4/ext/sysvmsg/sysvmsg.c
+            [3] => 
+            [4] => zif_msg_receive
+            [5] => /p2/var/php_gcov/PHP_4_4/ext/sysvmsg/sysvmsg.c
+            [6] => 318
+            [7] => warning
+            [8] => passing arg 2 of `php_var_unserialize' from incompatible pointer type
+        )
+
+    [15] => Array
+        (
+            [0] => /p2/var/php_gcov/PHP_4_4/ext/yp/yp.c: In function `zif_yp_err_string':
+/p2/var/php_gcov/PHP_4_4/ext/yp/yp.c:372: warning: assignment discards qualifiers from pointer target type
+            [1] => /p2/var/php_gcov/PHP_4_4/ext/yp/yp.c: In function `zif_yp_err_string':
+
+            [2] => /p2/var/php_gcov/PHP_4_4/ext/yp/yp.c
+            [3] => 
+            [4] => zif_yp_err_string
+            [5] => /p2/var/php_gcov/PHP_4_4/ext/yp/yp.c
+            [6] => 372
+            [7] => warning
+            [8] => assignment discards qualifiers from pointer target type
+        )
+
+    [16] => Array
+        (
+            [0] => Zend/zend_language_scanner.c:5944: warning: `yy_fatal_error' defined but not used
+Zend/zend_language_scanner.c:2627: warning: `yy_last_accepting_state' defined but not used
+Zend/zend_language_scanner.c:2628: warning: `yy_last_accepting_cpos' defined but not used
+Zend/zend_language_scanner.c:2634: warning: `yy_more_flag' defined but not used
+Zend/zend_language_scanner.c:2635: warning: `yy_more_len' defined but not used
+Zend/zend_language_scanner.c:5483: warning: `yyunput' defined but not used
+Zend/zend_language_scanner.c:5929: warning: `yy_top_state' defined but not used
+            [1] => 
+            [2] => 
+            [3] => 
+            [4] => 
+            [5] => Zend/zend_language_scanner.c
+            [6] => 5944
+            [7] => warning
+            [8] => `yy_fatal_error' defined but not used
+            [9] => 2627
+            [10] => warning
+            [11] => `yy_last_accepting_state' defined but not used
+            [12] => 2628
+            [13] => warning
+            [14] => `yy_last_accepting_cpos' defined but not used
+            [15] => 2634
+            [16] => warning
+            [17] => `yy_more_flag' defined but not used
+            [18] => 2635
+            [19] => warning
+            [20] => `yy_more_len' defined but not used
+            [21] => 5483
+            [22] => warning
+            [23] => `yyunput' defined but not used
+            [24] => 5929
+            [25] => warning
+            [26] => `yy_top_state' defined but not used
+        )
+
+    [17] => Array
+        (
+            [0] => Zend/zend_ini_scanner.c:457: warning: `yy_last_accepting_state' defined but not used
+Zend/zend_ini_scanner.c:458: warning: `yy_last_accepting_cpos' defined but not used
+Zend/zend_ini_scanner.c:1361: warning: `yyunput' defined but not used
+            [1] => 
+            [2] => 
+            [3] => 
+            [4] => 
+            [5] => Zend/zend_ini_scanner.c
+            [6] => 457
+            [7] => warning
+            [8] => `yy_last_accepting_state' defined but not used
+            [9] => 458
+            [10] => warning
+            [11] => `yy_last_accepting_cpos' defined but not used
+            [12] => 1361
+            [13] => warning
+            [14] => `yyunput' defined but not used
+        )
+
+    [18] => Array
+        (
+            [0] => /p2/var/php_gcov/PHP_4_4/Zend/zend_alloc.c: In function `_safe_emalloc':
+/p2/var/php_gcov/PHP_4_4/Zend/zend_alloc.c:237: warning: long int format, size_t arg (arg 3)
+/p2/var/php_gcov/PHP_4_4/Zend/zend_alloc.c:237: warning: long int format, size_t arg (arg 4)
+/p2/var/php_gcov/PHP_4_4/Zend/zend_alloc.c:237: warning: long int format, size_t arg (arg 5)
+            [1] => /p2/var/php_gcov/PHP_4_4/Zend/zend_alloc.c: In function `_safe_emalloc':
+
+            [2] => /p2/var/php_gcov/PHP_4_4/Zend/zend_alloc.c
+            [3] => 
+            [4] => _safe_emalloc
+            [5] => /p2/var/php_gcov/PHP_4_4/Zend/zend_alloc.c
+            [6] => 237
+            [7] => warning
+            [8] => long int format, size_t arg (arg 3)
+            [9] => 237
+            [10] => warning
+            [11] => long int format, size_t arg (arg 4)
+            [12] => 237
+            [13] => warning
+            [14] => long int format, size_t arg (arg 5)
+        )
+
+    [19] => Array
+        (
+            [0] => /p2/var/php_gcov/PHP_4_4/Zend/zend_ini.c:338: warning: `zend_ini_displayer_cb' defined but not used
+            [1] => 
+            [2] => 
+            [3] => 
+            [4] => 
+            [5] => /p2/var/php_gcov/PHP_4_4/Zend/zend_ini.c
+            [6] => 338
+            [7] => warning
+            [8] => `zend_ini_displayer_cb' defined but not used
+        )
+
+    [20] => Array
+        (
+            [0] => ext/mysql/libmysql/my_tempnam.o(.text+0x80): In function `my_tempnam':
+/p2/var/php_gcov/PHP_4_4/ext/mysql/libmysql/my_tempnam.c:115: warning: the use of `tempnam' is dangerous, better use `mkstemp'
+            [1] => ext/mysql/libmysql/my_tempnam.o(.text+0x80): In function `my_tempnam':
+
+            [2] => ext/mysql/libmysql/my_tempnam.o
+            [3] => (.text+0x80)
+            [4] => my_tempnam
+            [5] => /p2/var/php_gcov/PHP_4_4/ext/mysql/libmysql/my_tempnam.c
+            [6] => 115
+            [7] => warning
+            [8] => the use of `tempnam' is dangerous, better use `mkstemp'
+        )
+
+    [21] => Array
+        (
+            [0] => ext/mysql/libmysql/my_tempnam.o(.text+0x80): In function `my_tempnam':
+/p2/var/php_gcov/PHP_4_4/ext/mysql/libmysql/my_tempnam.c:115: warning: the use of `tempnam' is dangerous, better use `mkstemp'
+            [1] => ext/mysql/libmysql/my_tempnam.o(.text+0x80): In function `my_tempnam':
+
+            [2] => ext/mysql/libmysql/my_tempnam.o
+            [3] => (.text+0x80)
+            [4] => my_tempnam
+            [5] => /p2/var/php_gcov/PHP_4_4/ext/mysql/libmysql/my_tempnam.c
+            [6] => 115
+            [7] => warning
+            [8] => the use of `tempnam' is dangerous, better use `mkstemp'
+        )
+
+    [22] => Array
+        (
+            [0] => ext/ming/ming.o(.text+0xc115): In function `zim_swfmovie_namedAnchor':
+/p2/var/php_gcov/PHP_5_2/ext/ming/ming.c:2207: undefined reference to `SWFMovie_namedAnchor'
+/p2/var/php_gcov/PHP_5_2/ext/ming/ming.c:2209: undefined reference to `SWFMovie_xpto'
+/p2/var/php_gcov/PHP_5_2/ext/ming/ming.c:2259: undefined reference to `SWFMovie_foo'
+            [1] => ext/ming/ming.o(.text+0xc115): In function `zim_swfmovie_namedAnchor':
+
+            [2] => ext/ming/ming.o
+            [3] => (.text+0xc115)
+            [4] => zim_swfmovie_namedAnchor
+            [5] => /p2/var/php_gcov/PHP_5_2/ext/ming/ming.c
+            [6] => 2207
+            [7] => 
+            [8] => undefined reference to `SWFMovie_namedAnchor'
+            [9] => 2209
+            [10] => 
+            [11] => undefined reference to `SWFMovie_xpto'
+            [12] => 2259
+            [13] => 
+            [14] => undefined reference to `SWFMovie_foo'
+        )
+
+    [23] => Array
+        (
+            [0] => ext/ming/ming.o(.text+0x851): In function `zif_ming_setSWFCompression':
+/p2/var/php_gcov/PHP_5_2/ext/ming/ming.c:154: undefined reference to `Ming_setSWFCompression'
+            [1] => ext/ming/ming.o(.text+0x851): In function `zif_ming_setSWFCompression':
+
+            [2] => ext/ming/ming.o
+            [3] => (.text+0x851)
+            [4] => zif_ming_setSWFCompression
+            [5] => /p2/var/php_gcov/PHP_5_2/ext/ming/ming.c
+            [6] => 154
+            [7] => 
+            [8] => undefined reference to `Ming_setSWFCompression'
+        )
+
+)
diff --git a/ext/pcre/tests/006.phpt b/ext/pcre/tests/006.phpt
new file mode 100644
index 0000000..2d39b6e
--- /dev/null
+++ b/ext/pcre/tests/006.phpt
@@ -0,0 +1,24 @@
+--TEST--
+preg_replace() with array of failing regular expressions
+--INI--
+pcre.backtrack_limit=100000
+--FILE--
+<?php
+
+$text = '[CODE]&lt;td align=&quot;$stylevar[right]&quot;&gt;[/CODE]';
+$result = preg_replace(array('#\[(right)\](((?R)|[^[]+?|\[)*)\[/\\1\]#siU', '#\[(right)\](((?R)|[^[]+?|\[)*)\[/\\1\]#siU'), '', $text);
+var_dump($text);
+var_dump($result);
+
+$result = preg_replace('#\[(right)\](((?R)|[^[]+?|\[)*)\[/\\1\]#siU', '', $text);
+var_dump($text);
+var_dump($result);
+
+echo "Done\n";
+?>
+--EXPECTF--	
+string(58) "[CODE]&lt;td align=&quot;$stylevar[right]&quot;&gt;[/CODE]"
+NULL
+string(58) "[CODE]&lt;td align=&quot;$stylevar[right]&quot;&gt;[/CODE]"
+NULL
+Done
diff --git a/ext/pcre/tests/007.phpt b/ext/pcre/tests/007.phpt
new file mode 100644
index 0000000..776bec2
--- /dev/null
+++ b/ext/pcre/tests/007.phpt
@@ -0,0 +1,59 @@
+--TEST--
+preg_replace_callback() with callback that modifies subject string
+--SKIPIF--
+<?php
+if (@preg_match('/./u', '') === false) {
+	die('skip no utf8 support in PCRE library');
+}
+?>
+--FILE--
+<?php
+
+function evil($x) {
+	global $txt;
+	$txt[3] = "\xFF";
+	var_dump($x);
+	return $x[0];
+}
+
+$txt = "ola123";
+var_dump(preg_replace_callback('#.#u', 'evil', $txt));
+var_dump($txt);
+var_dump(preg_last_error() == PREG_NO_ERROR);
+
+var_dump(preg_replace_callback('#.#u', 'evil', $txt));
+var_dump(preg_last_error() == PREG_BAD_UTF8_ERROR);
+
+echo "Done!\n";
+?>
+--EXPECT--
+array(1) {
+  [0]=>
+  string(1) "o"
+}
+array(1) {
+  [0]=>
+  string(1) "l"
+}
+array(1) {
+  [0]=>
+  string(1) "a"
+}
+array(1) {
+  [0]=>
+  string(1) "1"
+}
+array(1) {
+  [0]=>
+  string(1) "2"
+}
+array(1) {
+  [0]=>
+  string(1) "3"
+}
+string(6) "ola123"
+string(6) "olaÿ23"
+bool(true)
+NULL
+bool(true)
+Done!
diff --git a/ext/pcre/tests/backtrack_limit.phpt b/ext/pcre/tests/backtrack_limit.phpt
new file mode 100644
index 0000000..419e6c2
--- /dev/null
+++ b/ext/pcre/tests/backtrack_limit.phpt
@@ -0,0 +1,25 @@
+--TEST--
+Backtracking limit
+--SKIPIF--
+<?php
+if (@preg_match_all('/\p{N}/', '0123456789', $dummy) === false) {
+	die("skip no support for \p support PCRE library");
+}
+?>
+--INI--
+pcre.backtrack_limit=2
+--FILE--
+<?php
+
+var_dump(preg_match_all('/.*\p{N}/', '0123456789', $dummy));
+var_dump(preg_last_error() === PREG_BACKTRACK_LIMIT_ERROR);
+
+var_dump(preg_match_all('/\p{Nd}/', '0123456789', $dummy));
+var_dump(preg_last_error() === PREG_NO_ERROR);
+
+?>
+--EXPECT--
+bool(false)
+bool(true)
+int(10)
+bool(true)
diff --git a/ext/pcre/tests/bug20528.phpt b/ext/pcre/tests/bug20528.phpt
new file mode 100644
index 0000000..8182fd9
--- /dev/null
+++ b/ext/pcre/tests/bug20528.phpt
@@ -0,0 +1,24 @@
+--TEST--
+Bug #20528 (preg_split() drops characters (re-opens Bug #15413)) 
+--FILE--
+<?php
+	$data = '(#11/19/2002#)';
+	var_dump(preg_split('/\b/', $data));
+?>
+--EXPECT--
+array(7) {
+  [0]=>
+  string(2) "(#"
+  [1]=>
+  string(2) "11"
+  [2]=>
+  string(1) "/"
+  [3]=>
+  string(2) "19"
+  [4]=>
+  string(1) "/"
+  [5]=>
+  string(4) "2002"
+  [6]=>
+  string(2) "#)"
+}
diff --git a/ext/pcre/tests/bug21732.phpt b/ext/pcre/tests/bug21732.phpt
new file mode 100644
index 0000000..3dfc41e
--- /dev/null
+++ b/ext/pcre/tests/bug21732.phpt
@@ -0,0 +1,29 @@
+--TEST--
+Bug #21732 (preg_replace() segfaults with invalid parameters)
+--INI--
+error_reporting=0
+--FILE--
+<?php
+class foo {
+	function cb($param) {
+		var_dump($param);
+		return "yes!";
+	}
+}
+
+var_dump(preg_replace('', array(), ''));
+var_dump(preg_replace_callback("/(ab)(cd)(e)/", array(new foo(), "cb"), 'abcde'));
+?>
+--EXPECT--
+bool(false)
+array(4) {
+  [0]=>
+  string(5) "abcde"
+  [1]=>
+  string(2) "ab"
+  [2]=>
+  string(2) "cd"
+  [3]=>
+  string(1) "e"
+}
+string(4) "yes!"
diff --git a/ext/pcre/tests/bug21758.phpt b/ext/pcre/tests/bug21758.phpt
new file mode 100644
index 0000000..78a1d6a
--- /dev/null
+++ b/ext/pcre/tests/bug21758.phpt
@@ -0,0 +1,26 @@
+--TEST--
+Bug #21758 (preg_replace_callback() not working with class methods)
+--FILE--
+<?php
+  class Foo {
+    function foo() {
+      
+      $s = 'preg_replace() is broken';
+      
+      var_dump(preg_replace_callback(
+              '/broken/',
+              array(&$this, 'bar'),
+              $s
+           ));
+    }
+    
+    function bar() {
+      return 'working';
+    }
+    
+  } // of Foo
+
+  $o = new Foo;
+?>
+--EXPECT--
+string(25) "preg_replace() is working"
diff --git a/ext/pcre/tests/bug26927.phpt b/ext/pcre/tests/bug26927.phpt
new file mode 100644
index 0000000..5c64deb
--- /dev/null
+++ b/ext/pcre/tests/bug26927.phpt
@@ -0,0 +1,11 @@
+--TEST--
+Bug #26927 (preg_quote() does not escape \0) 
+--FILE--
+<?php
+	$str = "a\000b";
+	$str_quoted = preg_quote($str);
+	var_dump(preg_match("!{$str_quoted}!", $str), $str_quoted);
+?>
+--EXPECT--
+int(1)
+string(6) "a\000b"
diff --git a/ext/pcre/tests/bug27011.phpt b/ext/pcre/tests/bug27011.phpt
new file mode 100644
index 0000000..6fa88ef
--- /dev/null
+++ b/ext/pcre/tests/bug27011.phpt
@@ -0,0 +1,13 @@
+--TEST--
+Bug #27011 (segfault in preg_match_all())
+--FILE--
+<?php
+
+var_dump(preg_match_all('|(\w+)://([^\s"<]*[\w+#?/&=])|', "This is a text string", $matches, PREG_SET_ORDER));
+var_dump($matches);
+
+?>
+--EXPECT--
+int(0)
+array(0) {
+}
diff --git a/ext/pcre/tests/bug27103.phpt b/ext/pcre/tests/bug27103.phpt
new file mode 100644
index 0000000..163dc9f
--- /dev/null
+++ b/ext/pcre/tests/bug27103.phpt
@@ -0,0 +1,43 @@
+--TEST--
+Bug #27103 (preg_split('//u') incorrectly splits UTF-8 strings into octets)
+--SKIPIF--
+<?php
+if (@preg_match('/./u', '') === false) {
+	die('skip no utf8 support in PCRE library');
+}
+?>
+--FILE--
+<?php
+function iter($ar)
+{
+	foreach ($ar as $c) {
+		echo htmlentities($c, 0, "UTF-8"), ": ", strlen($c), "\n";
+	}
+}
+$teststr = "\xe2\x82\xac hi there";
+iter(preg_split('//u', $teststr, -1, PREG_SPLIT_NO_EMPTY));
+preg_match_all('/./u', $teststr, $matches);
+iter($matches[0]);
+?>
+--EXPECT--
+&euro;: 3
+ : 1
+h: 1
+i: 1
+ : 1
+t: 1
+h: 1
+e: 1
+r: 1
+e: 1
+&euro;: 3
+ : 1
+h: 1
+i: 1
+ : 1
+t: 1
+h: 1
+e: 1
+r: 1
+e: 1
+
diff --git a/ext/pcre/tests/bug34790.phpt b/ext/pcre/tests/bug34790.phpt
new file mode 100644
index 0000000..c375ae5
--- /dev/null
+++ b/ext/pcre/tests/bug34790.phpt
@@ -0,0 +1,23 @@
+--TEST--
+Bug #34790 (preg_match_all(), named capturing groups, variable assignment/return => crash)
+--FILE--
+<?php
+function func1(){
+        $string = 'what the word and the other word the';
+        preg_match_all('/(?P<word>the)/', $string, $matches);
+        return $matches['word'];
+}
+$words = func1();
+var_dump($words);
+?>
+--EXPECT--
+array(4) {
+  [0]=>
+  string(3) "the"
+  [1]=>
+  string(3) "the"
+  [2]=>
+  string(3) "the"
+  [3]=>
+  string(3) "the"
+}
diff --git a/ext/pcre/tests/bug37800.phpt b/ext/pcre/tests/bug37800.phpt
new file mode 100644
index 0000000..e8a0036
--- /dev/null
+++ b/ext/pcre/tests/bug37800.phpt
@@ -0,0 +1,31 @@
+--TEST--
+Bug #37800 (preg_replace() limit parameter odd behaviour)
+--FILE--
+<?php
+$s_string = '1111111111';
+$s_search = '/1/';
+$s_replace = 'One ';
+$i_limit = 1;
+$i_count = 0;
+
+$s_output = preg_replace($s_search, $s_replace, $s_string, $i_limit,
+$i_count);
+echo "Output = " . var_export($s_output, True) . "\n";
+echo "Count  = $i_count\n";
+var_dump(preg_last_error() === PREG_NO_ERROR);
+
+$i_limit = strlen($s_string);
+$s_output = preg_replace($s_search, $s_replace, $s_string, $i_limit,
+$i_count);
+echo "Output = " . var_export($s_output, True) . "\n";
+echo "Count  = $i_count\n";
+var_dump(preg_last_error() === PREG_NO_ERROR);
+
+?>
+--EXPECT--
+Output = 'One 111111111'
+Count  = 1
+bool(true)
+Output = 'One One One One One One One One One One '
+Count  = 10
+bool(true)
diff --git a/ext/pcre/tests/bug37911.phpt b/ext/pcre/tests/bug37911.phpt
new file mode 100644
index 0000000..f788119
--- /dev/null
+++ b/ext/pcre/tests/bug37911.phpt
@@ -0,0 +1,41 @@
+--TEST--
+Bug #37911 (preg_replace_callback ignores named groups)
+--FILE--
+<?php
+
+function callback($match)
+{
+	var_dump($match);
+	return $match[1].'/'.strlen($match['name']);
+}
+
+var_dump(preg_replace_callback('|(?P<name>blub)|', 'callback', 'bla blub blah'));
+
+var_dump(preg_match('|(?P<name>blub)|', 'bla blub blah', $m));
+var_dump($m);
+
+var_dump(preg_replace_callback('|(?P<1>blub)|', 'callback', 'bla blub blah'));
+
+?>
+--EXPECTF--
+array(3) {
+  [0]=>
+  string(4) "blub"
+  ["name"]=>
+  string(4) "blub"
+  [1]=>
+  string(4) "blub"
+}
+string(15) "bla blub/4 blah"
+int(1)
+array(3) {
+  [0]=>
+  string(4) "blub"
+  ["name"]=>
+  string(4) "blub"
+  [1]=>
+  string(4) "blub"
+}
+
+Warning: preg_replace_callback(): Numeric named subpatterns are not allowed in %sbug37911.php on line 14
+NULL
diff --git a/ext/pcre/tests/bug38600.phpt b/ext/pcre/tests/bug38600.phpt
new file mode 100644
index 0000000..fc954e4
--- /dev/null
+++ b/ext/pcre/tests/bug38600.phpt
@@ -0,0 +1,14 @@
+--TEST--
+Bug #38600 (infinite loop in pcre with extended class)
+--FILE--
+<?php
+$foo = 'bla bla bla';
+
+var_dump(preg_match('/(?<!\w)(0x[\p{N}]+[lL]?|[\p{Nd}]+(e[\p{Nd}]*)?[lLdDfF]?)(?!\w)/', $foo, $m));
+var_dump($m);
+
+?>
+--EXPECT--
+int(0)
+array(0) {
+}
diff --git a/ext/pcre/tests/bug40195.phpt b/ext/pcre/tests/bug40195.phpt
new file mode 100644
index 0000000..87ebf42
--- /dev/null
+++ b/ext/pcre/tests/bug40195.phpt
@@ -0,0 +1,45 @@
+--TEST--
+Bug #40195 (pcre 6.7 regression)
+--FILE--
+<?php
+
+var_dump(preg_match('@^(/([a-z]*))*$@', '//abcde', $m)); var_dump($m);
+var_dump(preg_match('@^(/(?:[a-z]*))*$@', '//abcde', $m)); var_dump($m);
+
+var_dump(preg_match('@^(/([a-z]+))+$@', '/a/abcde', $m)); var_dump($m);
+var_dump(preg_match('@^(/(?:[a-z]+))+$@', '/a/abcde', $m)); var_dump($m);
+
+?>
+--EXPECT--
+int(1)
+array(3) {
+  [0]=>
+  string(7) "//abcde"
+  [1]=>
+  string(6) "/abcde"
+  [2]=>
+  string(5) "abcde"
+}
+int(1)
+array(2) {
+  [0]=>
+  string(7) "//abcde"
+  [1]=>
+  string(6) "/abcde"
+}
+int(1)
+array(3) {
+  [0]=>
+  string(8) "/a/abcde"
+  [1]=>
+  string(6) "/abcde"
+  [2]=>
+  string(5) "abcde"
+}
+int(1)
+array(2) {
+  [0]=>
+  string(8) "/a/abcde"
+  [1]=>
+  string(6) "/abcde"
+}
diff --git a/ext/pcre/tests/bug40909.phpt b/ext/pcre/tests/bug40909.phpt
new file mode 100644
index 0000000..f66a8f9
--- /dev/null
+++ b/ext/pcre/tests/bug40909.phpt
@@ -0,0 +1,38 @@
+--TEST--
+Bug #40909 (pcre 7.0 regression)
+--FILE--
+<?php
+            
+$pattern =
+"/\s([\w_\.\/]+)(?:=([\'\"]?(?:[\w\d\s\?=\(\)\.,'_#\/\\:;&-]|(?:\\\\\"|\\\')?)+[\'\"]?))?/";
+$context = "<simpletag an_attribute=\"simpleValueInside\">";
+
+$match = array();
+
+if ($result =preg_match_all($pattern, $context, $match))
+{
+
+var_dump($result);
+var_dump($match);
+}
+
+?>
+--EXPECT--
+int(1)
+array(3) {
+  [0]=>
+  array(1) {
+    [0]=>
+    string(33) " an_attribute="simpleValueInside""
+  }
+  [1]=>
+  array(1) {
+    [0]=>
+    string(12) "an_attribute"
+  }
+  [2]=>
+  array(1) {
+    [0]=>
+    string(19) ""simpleValueInside""
+  }
+}
diff --git a/ext/pcre/tests/bug41050.phpt b/ext/pcre/tests/bug41050.phpt
new file mode 100644
index 0000000..ff58e11
--- /dev/null
+++ b/ext/pcre/tests/bug41050.phpt
@@ -0,0 +1,26 @@
+--TEST--
+Bug #41050 (pcre 7.0 regression)
+--FILE--
+<?php
+// by legolas558
+
+$regex = '/(insert|drop|create|select|delete|update)([^;\']*('."('[^']*')+".')?)*(;|$)/i';
+
+$sql = 'SELECT * FROM #__components';
+
+if (preg_match($regex,$sql, $m)) echo 'matched';
+else echo 'not matched';
+
+print_r($m);
+
+?>
+--EXPECT--
+matchedArray
+(
+    [0] => SELECT * FROM #__components
+    [1] => SELECT
+    [2] => 
+    [3] => 
+    [4] => 
+    [5] => 
+)
diff --git a/ext/pcre/tests/bug41148.phpt b/ext/pcre/tests/bug41148.phpt
new file mode 100644
index 0000000..f0a7937
--- /dev/null
+++ b/ext/pcre/tests/bug41148.phpt
@@ -0,0 +1,50 @@
+--TEST--
+Bug #41148 (pcre 7.0 regression)
+--FILE--
+<?php
+
+    $letexte="<br><br>";
+    $ligne_horizontale = $puce = $debut_intertitre = $fin_intertitre = '';
+
+    $cherche1 = array(
+        /* 0 */     "/\n(----+|____+)/S",
+        /* 1 */     "/\n-- */S",
+        /* 2 */     "/\n- */S",
+        /* 3 */     "/\n_ +/S",
+        /* 4 */   "/(^|[^{])[{][{][{]/S",
+        /* 5 */   "/[}][}][}]($|[^}])/S",
+        /* 6 */     "/(( *)\n){2,}(<br[[:space:]]*\/?".">)?/S",
+        /* 7 */     "/[{][{]/S",
+        /* 8 */     "/[}][}]/S",
+        /* 9 */     "/[{]/S",
+        /* 10 */    "/[}]/S",
+        /* 11 */    "/(<br[[:space:]]*\/?".">){2,}/S",
+        /* 12 */    "/<p>([\n]*(<br[[:space:]]*\/?".">)*)*/S",
+        /* 13 */    "/<quote>/S",
+        /* 14 */    "/<\/quote>/S"
+    );
+    $remplace1 = array(
+        /* 0 */     "\n\n$ligne_horizontale\n\n",
+        /* 1 */     "\n<br />&mdash;&nbsp;",
+        /* 2 */     "\n<br />$puce&nbsp;",
+        /* 3 */     "\n<br />",
+        /* 4 */     "\$1\n\n$debut_intertitre",
+        /* 5 */     "$fin_intertitre\n\n\$1",
+        /* 6 */     "<p>",
+        /* 7 */     "<strong class=\"spip\">",
+        /* 8 */     "</strong>",
+        /* 9 */     "<i class=\"spip\">",
+        /* 10 */    "</i>",
+        /* 11 */    "<p>",
+        /* 12 */    "<p>",
+        /* 13 */    "<blockquote class=\"spip\"><p>",
+        /* 14 */    "</blockquote><p>"
+    );
+    $letexte = preg_replace($cherche1, $remplace1, $letexte);
+    $letexte = preg_replace("@^ <br />@S", "", $letexte);
+
+    print $letexte;
+
+?>
+--EXPECT--
+<p>
diff --git a/ext/pcre/tests/bug41638.phpt b/ext/pcre/tests/bug41638.phpt
new file mode 100644
index 0000000..8c907f9
--- /dev/null
+++ b/ext/pcre/tests/bug41638.phpt
@@ -0,0 +1,82 @@
+--TEST--
+Bug #41638 (pcre 7.0 regression)
+--FILE--
+<?php
+$str = "repeater id='loopt' dataSrc=subject colums=2";
+
+preg_match_all("/(['\"])((.*(\\\\\\1)*)*)\\1/sU",$str,$str_instead);
+print_r($str_instead);
+
+// these two are from Magnus Holmgren (extracted from a pcre-dev mailing list post)
+preg_match_all("/(['\"])((?:\\\\\\1|.)*)\\1/sU", $str, $str_instead);
+print_r($str_instead);
+
+preg_match_all("/(['\"])(.*)(?<!\\\\)\\1/sU", $str, $str_instead);
+print_r($str_instead);
+
+?>
+--EXPECT--
+Array
+(
+    [0] => Array
+        (
+            [0] => 'loopt'
+        )
+
+    [1] => Array
+        (
+            [0] => '
+        )
+
+    [2] => Array
+        (
+            [0] => loopt
+        )
+
+    [3] => Array
+        (
+            [0] => t
+        )
+
+    [4] => Array
+        (
+            [0] => 
+        )
+
+)
+Array
+(
+    [0] => Array
+        (
+            [0] => 'loopt'
+        )
+
+    [1] => Array
+        (
+            [0] => '
+        )
+
+    [2] => Array
+        (
+            [0] => loopt
+        )
+
+)
+Array
+(
+    [0] => Array
+        (
+            [0] => 'loopt'
+        )
+
+    [1] => Array
+        (
+            [0] => '
+        )
+
+    [2] => Array
+        (
+            [0] => loopt
+        )
+
+)
diff --git a/ext/pcre/tests/bug42298.phpt b/ext/pcre/tests/bug42298.phpt
new file mode 100644
index 0000000..156f356
--- /dev/null
+++ b/ext/pcre/tests/bug42298.phpt
@@ -0,0 +1,46 @@
+--TEST--
+Bug #42298 (pcre gives bogus results with /u)
+--FILE--
+<?php
+$str = "A\xc2\xa3BC";
+preg_match_all('/\S\S/u', $str, $m);	var_dump($m);
+preg_match_all('/\S{2}/u', $str, $m);	var_dump($m);
+
+$str = "A\xe2\x82\xac ";
+preg_match_all('/\W\W/u', $str, $m);	var_dump($m);
+preg_match_all('/\W{2}/u', $str, $m);	var_dump($m);
+
+?>
+--EXPECT--
+array(1) {
+  [0]=>
+  array(2) {
+    [0]=>
+    string(3) "A£"
+    [1]=>
+    string(2) "BC"
+  }
+}
+array(1) {
+  [0]=>
+  array(2) {
+    [0]=>
+    string(3) "A£"
+    [1]=>
+    string(2) "BC"
+  }
+}
+array(1) {
+  [0]=>
+  array(1) {
+    [0]=>
+    string(4) "€ "
+  }
+}
+array(1) {
+  [0]=>
+  array(1) {
+    [0]=>
+    string(4) "€ "
+  }
+}
diff --git a/ext/pcre/tests/bug42737.phpt b/ext/pcre/tests/bug42737.phpt
new file mode 100644
index 0000000..8d9dd52
--- /dev/null
+++ b/ext/pcre/tests/bug42737.phpt
@@ -0,0 +1,19 @@
+--TEST--
+Bug #42737 (preg_split('//u') triggers a E_NOTICE with newlines)
+--FILE--
+<?php
+
+$string = chr(13).chr(10);
+
+$array = preg_split('//u', $string, - 1, PREG_SPLIT_NO_EMPTY);
+
+var_dump(array_map('ord', $array));
+
+?>
+--EXPECT--
+array(2) {
+  [0]=>
+  int(13)
+  [1]=>
+  int(10)
+}
diff --git a/ext/pcre/tests/bug42945.phpt b/ext/pcre/tests/bug42945.phpt
new file mode 100644
index 0000000..c6d2b82
--- /dev/null
+++ b/ext/pcre/tests/bug42945.phpt
@@ -0,0 +1,88 @@
+--TEST--
+Bug #42945 (preg_split() swallows part of the string)
+--FILE--
+<?php
+
+var_dump(preg_match_all('/\b/', "a'", $m, PREG_OFFSET_CAPTURE));
+var_dump($m);
+
+var_dump(preg_split('/\b/', "a'"));
+var_dump(preg_split('/\b/', "a'", -1, PREG_SPLIT_OFFSET_CAPTURE));
+var_dump(preg_split('/\b/', "a'", -1, PREG_SPLIT_NO_EMPTY));
+var_dump(preg_split('/\b/', "a'", -1, PREG_SPLIT_NO_EMPTY|PREG_SPLIT_OFFSET_CAPTURE));
+
+?>
+--EXPECT--
+int(2)
+array(1) {
+  [0]=>
+  array(2) {
+    [0]=>
+    array(2) {
+      [0]=>
+      string(0) ""
+      [1]=>
+      int(0)
+    }
+    [1]=>
+    array(2) {
+      [0]=>
+      string(0) ""
+      [1]=>
+      int(1)
+    }
+  }
+}
+array(3) {
+  [0]=>
+  string(0) ""
+  [1]=>
+  string(1) "a"
+  [2]=>
+  string(1) "'"
+}
+array(3) {
+  [0]=>
+  array(2) {
+    [0]=>
+    string(0) ""
+    [1]=>
+    int(0)
+  }
+  [1]=>
+  array(2) {
+    [0]=>
+    string(1) "a"
+    [1]=>
+    int(0)
+  }
+  [2]=>
+  array(2) {
+    [0]=>
+    string(1) "'"
+    [1]=>
+    int(1)
+  }
+}
+array(2) {
+  [0]=>
+  string(1) "a"
+  [1]=>
+  string(1) "'"
+}
+array(2) {
+  [0]=>
+  array(2) {
+    [0]=>
+    string(1) "a"
+    [1]=>
+    int(0)
+  }
+  [1]=>
+  array(2) {
+    [0]=>
+    string(1) "'"
+    [1]=>
+    int(1)
+  }
+}
diff --git a/ext/pcre/tests/bug44191.phpt b/ext/pcre/tests/bug44191.phpt
new file mode 100644
index 0000000..52b4490
--- /dev/null
+++ b/ext/pcre/tests/bug44191.phpt
@@ -0,0 +1,16 @@
+--TEST--
+Bug #44191 (preg_grep messes up array index)
+--FILE--
+<?php
+
+$array = range(1, 10);
+
+preg_grep('/asdf/', $array);
+
+while (list($x) = each($array)) {
+	print $x;
+}
+
+?>
+--EXPECT--
+0123456789
diff --git a/ext/pcre/tests/bug44214.phpt b/ext/pcre/tests/bug44214.phpt
new file mode 100644
index 0000000..90e4c86
--- /dev/null
+++ b/ext/pcre/tests/bug44214.phpt
@@ -0,0 +1,31 @@
+--TEST--
+Bug #44214 (crash with preg_replace_callback() and global variable)
+--FILE--
+<?php
+$string = 'aaa bbb ccc ddd eee ccc aaa bbb';
+
+$array = array();
+
+function myCallBack( $match ) {
+    global $array;
+    $array[] = $match;
+    return 'xxx';
+}
+
+var_dump(preg_replace_callback( '`a+`', 'myCallBack', $string));
+var_dump($array);
+?>
+--EXPECT--
+string(31) "xxx bbb ccc ddd eee ccc xxx bbb"
+array(2) {
+  [0]=>
+  array(1) {
+    [0]=>
+    string(3) "aaa"
+  }
+  [1]=>
+  array(1) {
+    [0]=>
+    string(3) "aaa"
+  }
+}
diff --git a/ext/pcre/tests/bug44214_2.phpt b/ext/pcre/tests/bug44214_2.phpt
new file mode 100644
index 0000000..d78846c
--- /dev/null
+++ b/ext/pcre/tests/bug44214_2.phpt
@@ -0,0 +1,25 @@
+--TEST--
+Bug #44214-2 (crash with preg_replace_callback() and global variable)
+--FILE--
+<?php
+$string = 'aaa bbb ccc ddd eee ccc aaa bbb';
+
+$array = array();
+
+function myCallBack( $match ) {
+    global $array;
+    $array[] = $match[0];
+    return 'xxx';
+}
+
+var_dump(preg_replace_callback( '`a+`', 'myCallBack', $string));
+var_dump($array);
+?>
+--EXPECT--
+string(31) "xxx bbb ccc ddd eee ccc xxx bbb"
+array(2) {
+  [0]=>
+  string(3) "aaa"
+  [1]=>
+  string(3) "aaa"
+}
diff --git a/ext/pcre/tests/bug44925.phpt b/ext/pcre/tests/bug44925.phpt
new file mode 100644
index 0000000..f6e0db4
--- /dev/null
+++ b/ext/pcre/tests/bug44925.phpt
@@ -0,0 +1,107 @@
+--TEST--
+Bug #44925 (preg_grep() modifies input array)
+--FILE--
+<?php
+$str1 = 'a';
+$str2 = 'b';
+
+$array=Array("1",2,3,1.1,FALSE,NULL,Array(), $str1, &$str2);
+
+var_dump($array);
+
+var_dump(preg_grep('/do not match/',$array));
+
+$a = preg_grep('/./',$array);
+var_dump($a);
+
+$str1 = 'x';
+$str2 = 'y';
+
+var_dump($a); // check if array is still ok
+
+var_dump($array);
+
+?>
+--EXPECTF--
+array(9) {
+  [0]=>
+  string(1) "1"
+  [1]=>
+  int(2)
+  [2]=>
+  int(3)
+  [3]=>
+  float(1.1)
+  [4]=>
+  bool(false)
+  [5]=>
+  NULL
+  [6]=>
+  array(0) {
+  }
+  [7]=>
+  string(1) "a"
+  [8]=>
+  &string(1) "b"
+}
+
+Notice: Array to string conversion in %sbug44925.php on line 9
+array(0) {
+}
+
+Notice: Array to string conversion in %sbug44925.php on line 11
+array(7) {
+  [0]=>
+  string(1) "1"
+  [1]=>
+  int(2)
+  [2]=>
+  int(3)
+  [3]=>
+  float(1.1)
+  [6]=>
+  array(0) {
+  }
+  [7]=>
+  string(1) "a"
+  [8]=>
+  &string(1) "b"
+}
+array(7) {
+  [0]=>
+  string(1) "1"
+  [1]=>
+  int(2)
+  [2]=>
+  int(3)
+  [3]=>
+  float(1.1)
+  [6]=>
+  array(0) {
+  }
+  [7]=>
+  string(1) "a"
+  [8]=>
+  &string(1) "y"
+}
+array(9) {
+  [0]=>
+  string(1) "1"
+  [1]=>
+  int(2)
+  [2]=>
+  int(3)
+  [3]=>
+  float(1.1)
+  [4]=>
+  bool(false)
+  [5]=>
+  NULL
+  [6]=>
+  array(0) {
+  }
+  [7]=>
+  string(1) "a"
+  [8]=>
+  &string(1) "y"
+}
diff --git a/ext/pcre/tests/bug47229.phpt b/ext/pcre/tests/bug47229.phpt
new file mode 100644
index 0000000..96b95a2
--- /dev/null
+++ b/ext/pcre/tests/bug47229.phpt
@@ -0,0 +1,37 @@
+--TEST--
+Bug #47229 (preg_quote() doesn't escape -)
+--FILE--
+<?php
+
+var_dump(preg_quote('-oh really?'));
+
+// make sure there's no regression in matching
+preg_match('/[a\-c]+/', 'a---b', $m);
+var_dump($m);
+
+preg_match('/[a\-c]+/', 'a\-', $m);
+var_dump($m);
+
+preg_match("/a\-{2,}/", 'a----a', $m);
+var_dump($m);
+
+preg_match("/a\-{1,}/", 'a\----a', $m);
+var_dump($m);
+
+?>
+--EXPECTF--
+%string|unicode%(13) "\-oh really\?"
+array(1) {
+  [0]=>
+  %string|unicode%(4) "a---"
+}
+array(1) {
+  [0]=>
+  %string|unicode%(1) "a"
+}
+array(1) {
+  [0]=>
+  %string|unicode%(5) "a----"
+}
+array(0) {
+}
diff --git a/ext/pcre/tests/bug47662.phpt b/ext/pcre/tests/bug47662.phpt
new file mode 100644
index 0000000..d605674
--- /dev/null
+++ b/ext/pcre/tests/bug47662.phpt
@@ -0,0 +1,18 @@
+--TEST--
+Bug #47662 (support more than 127 named subpatterns)
+--FILE--
+<?php
+
+$regex = '@';
+for($bar=0; $bar<1027; $bar++) {
+	$regex .= '((?P<x'.$bar.'>))';
+}
+$regex .= 'fo+bar@';
+
+var_dump(preg_match($regex, 'foobar'));
+echo "Done!\n";
+
+?>
+--EXPECT--
+int(1)
+Done!
diff --git a/ext/pcre/tests/bug52732.phpt b/ext/pcre/tests/bug52732.phpt
new file mode 100644
index 0000000..8cfa204
--- /dev/null
+++ b/ext/pcre/tests/bug52732.phpt
@@ -0,0 +1,13 @@
+--TEST--
+Bug #52732 (Docs say preg_match() returns FALSE on error, but it returns int(0))
+--INI--
+pcre.backtrack_limit=1
+--FILE--
+<?php
+$ret = preg_match('/(?:\D+|<\d+>)*[!?]/', 'foobar foobar foobar');
+
+var_dump($ret);
+
+?>
+--EXPECT--
+bool(false)
\ No newline at end of file
diff --git a/ext/pcre/tests/bug52971.phpt b/ext/pcre/tests/bug52971.phpt
new file mode 100644
index 0000000..5949cb2
--- /dev/null
+++ b/ext/pcre/tests/bug52971.phpt
@@ -0,0 +1,43 @@
+--TEST--
+Bug #52971 (PCRE-Meta-Characters not working with utf-8)
+--SKIPIF--
+<?php if ((double)PCRE_VERSION < 8.1) die('skip PCRE_VERSION >= 8.1 is required!'); ?>
+--FILE--
+<?php
+
+$message = 'Der ist ein Süßwasserpool Süsswasserpool ... verschiedene Wassersportmöglichkeiten bei ...';
+
+$pattern = '/\bwasser/iu';
+preg_match_all($pattern, $message, $match, PREG_OFFSET_CAPTURE);
+var_dump($match);
+
+$pattern = '/[^\w]wasser/iu';
+preg_match_all($pattern, $message, $match, PREG_OFFSET_CAPTURE);
+var_dump($match);
+
+?>
+--EXPECTF--
+array(1) {
+  [0]=>
+  array(1) {
+    [0]=>
+    array(2) {
+      [0]=>
+      string(6) "Wasser"
+      [1]=>
+      int(61)
+    }
+  }
+}
+array(1) {
+  [0]=>
+  array(1) {
+    [0]=>
+    array(2) {
+      [0]=>
+      string(7) " Wasser"
+      [1]=>
+      int(60)
+    }
+  }
+}
diff --git a/ext/pcre/tests/bug63055.phpt b/ext/pcre/tests/bug63055.phpt
new file mode 100644
index 0000000..16c50b5
--- /dev/null
+++ b/ext/pcre/tests/bug63055.phpt
@@ -0,0 +1,23 @@
+--TEST--
+Bug #63055 (Segfault in zend_gc with SF2 testsuite)
+--FILE--
+<?php
+/* the default gc root size is 10,000 */
+for ($i=0; $i<9998; $i++) {
+    $array = array();
+    $array[0] = &$array;
+    unset($array);
+}
+
+$matches = array("foo" => "bar"); /* this bucket will trigger the segfault */
+$dummy   = array("dummy");        /* used to trigger gc_collect_cycles */
+$dummy[1] = &$dummy;
+
+$matches[1] = &$matches;
+$matches[2] = $dummy;
+
+preg_match_all("/(\d)+/", "foo123456bar", $matches);
+echo "okey";
+?>
+--EXPECTF--
+okey
diff --git a/ext/pcre/tests/cache_limit.phpt b/ext/pcre/tests/cache_limit.phpt
new file mode 100644
index 0000000..bfe7f1b
--- /dev/null
+++ b/ext/pcre/tests/cache_limit.phpt
@@ -0,0 +1,25 @@
+--TEST--
+Compiled regex cache limit
+--FILE--
+<?php
+define('PREG_CACHE_SIZE', 4096+1);
+
+$re = '';
+$str = str_repeat('x', PREG_CACHE_SIZE);
+
+for ($i=0; $i < PREG_CACHE_SIZE; ++$i) {
+	$re .= '.';
+	if (!preg_match("/$re/", $str)) {
+		die('non match. error');
+	}
+}
+
+var_dump(preg_match('/./', $str));   // this one was already deleted from the cache
+var_dump(preg_match("/$re/", $str)); // but not this one
+
+echo "done\n";
+?>
+--EXPECT--
+int(1)
+int(1)
+done
diff --git a/ext/pcre/tests/delimiters.phpt b/ext/pcre/tests/delimiters.phpt
new file mode 100644
index 0000000..1826f87
--- /dev/null
+++ b/ext/pcre/tests/delimiters.phpt
@@ -0,0 +1,37 @@
+--TEST--
+Delimiters crash test
+--FILE--
+<?php
+
+var_dump(preg_match('', ''));
+var_dump(preg_match('      ', ''));
+var_dump(preg_match('@@', ''));
+var_dump(preg_match('12', ''));
+var_dump(preg_match('<>', ''));
+var_dump(preg_match('~a', ''));
+var_dump(preg_match('@\@\@@', '@@'));
+var_dump(preg_match('//z', '@@'));
+var_dump(preg_match('{', ''));
+
+?>
+--EXPECTF--
+Warning: preg_match(): Empty regular expression in %sdelimiters.php on line 3
+bool(false)
+
+Warning: preg_match(): Empty regular expression in %sdelimiters.php on line 4
+bool(false)
+int(1)
+
+Warning: preg_match(): Delimiter must not be alphanumeric or backslash in %sdelimiters.php on line 6
+bool(false)
+int(1)
+
+Warning: preg_match(): No ending delimiter '~' found in %sdelimiters.php on line 8
+bool(false)
+int(1)
+
+Warning: preg_match(): Unknown modifier 'z' in %sdelimiters.php on line 10
+bool(false)
+
+Warning: preg_match(): No ending matching delimiter '}' found in %sdelimiters.php on line 11
+bool(false)
diff --git a/ext/pcre/tests/dollar_endonly.phpt b/ext/pcre/tests/dollar_endonly.phpt
new file mode 100644
index 0000000..96a5244
--- /dev/null
+++ b/ext/pcre/tests/dollar_endonly.phpt
@@ -0,0 +1,39 @@
+--TEST--
+D (PCRE_DOLLAR_ENDONLY) modififer
+--FILE--
+<?php
+
+var_dump(preg_match_all('/^\S+.+$/', "aeiou\n", $m));
+var_dump($m);
+
+var_dump(preg_match_all('/^\S+.+$/D', "aeiou\n", $m));
+var_dump($m);
+
+var_dump(preg_match_all('/^\S+\s$/D', "aeiou\n", $m));
+var_dump($m);
+
+?>
+--EXPECT--
+int(1)
+array(1) {
+  [0]=>
+  array(1) {
+    [0]=>
+    string(5) "aeiou"
+  }
+}
+int(0)
+array(1) {
+  [0]=>
+  array(0) {
+  }
+}
+int(1)
+array(1) {
+  [0]=>
+  array(1) {
+    [0]=>
+    string(6) "aeiou
+"
+  }
+}
diff --git a/ext/pcre/tests/grep.phpt b/ext/pcre/tests/grep.phpt
new file mode 100644
index 0000000..d3d9032
--- /dev/null
+++ b/ext/pcre/tests/grep.phpt
@@ -0,0 +1,23 @@
+--TEST--
+preg_grep()
+--FILE--
+<?php
+$array = array('a', '1', 'q6', 'h20');
+
+var_dump(preg_grep('/^(\d|.\d)$/', $array));
+var_dump(preg_grep('/^(\d|.\d)$/', $array, PREG_GREP_INVERT));
+
+?>
+--EXPECT--
+array(2) {
+  [1]=>
+  string(1) "1"
+  [2]=>
+  string(2) "q6"
+}
+array(2) {
+  [0]=>
+  string(1) "a"
+  [3]=>
+  string(3) "h20"
+}
diff --git a/ext/pcre/tests/grep2.phpt b/ext/pcre/tests/grep2.phpt
new file mode 100644
index 0000000..0cf8d4a
--- /dev/null
+++ b/ext/pcre/tests/grep2.phpt
@@ -0,0 +1,45 @@
+--TEST--
+preg_grep() 2nd test
+--FILE--
+<?php
+
+var_dump(preg_grep(1,array(),3,4));
+var_dump(preg_grep(1, 2));
+var_dump(preg_grep('/+/', array()));
+
+$array = array(5=>'a', 'x' => '1', 'xyz'=>'q6', 'h20');
+
+var_dump(preg_grep('@^[a-z]+@', $array));
+var_dump(preg_grep('@^[a-z]+@', $array, PREG_GREP_INVERT));
+
+ini_set('pcre.recursion_limit', 1);
+var_dump(preg_last_error() == PREG_NO_ERROR);
+var_dump(preg_grep('@^[a-z]+@', $array));
+var_dump(preg_last_error() == PREG_RECURSION_LIMIT_ERROR);
+
+?>
+--EXPECTF--
+Warning: preg_grep() expects at most 3 parameters, 4 given in %sgrep2.php on line 3
+NULL
+
+Warning: preg_grep() expects parameter 2 to be array, integer given in %sgrep2.php on line 4
+NULL
+
+Warning: preg_grep(): Compilation failed: nothing to repeat at offset 0 in %sgrep2.php on line 5
+bool(false)
+array(3) {
+  [5]=>
+  string(1) "a"
+  ["xyz"]=>
+  string(2) "q6"
+  [6]=>
+  string(3) "h20"
+}
+array(1) {
+  ["x"]=>
+  string(1) "1"
+}
+bool(true)
+array(0) {
+}
+bool(true)
diff --git a/ext/pcre/tests/invalid_utf8.phpt b/ext/pcre/tests/invalid_utf8.phpt
new file mode 100644
index 0000000..56bad83
--- /dev/null
+++ b/ext/pcre/tests/invalid_utf8.phpt
@@ -0,0 +1,22 @@
+--TEST--
+preg_replace() and invalid UTF8
+--SKIPIF--
+<?php
+if (@preg_match('/./u', '') === false) {
+	die('skip no utf8 support in PCRE library');
+}
+?>
+--FILE--
+<?php
+
+$string = urldecode("search%e4"); 
+$result = preg_replace("#(&\#x*)([0-9A-F]+);*#iu","$1$2;",$string); 
+var_dump($result); 
+var_dump(preg_last_error());
+
+echo "Done\n";
+?>
+--EXPECT--	
+NULL
+int(4)
+Done
diff --git a/ext/pcre/tests/invalid_utf8_offset.phpt b/ext/pcre/tests/invalid_utf8_offset.phpt
new file mode 100644
index 0000000..50716ca
--- /dev/null
+++ b/ext/pcre/tests/invalid_utf8_offset.phpt
@@ -0,0 +1,35 @@
+--TEST--
+preg_replace() and invalid UTF8 offset
+--SKIPIF--
+<?php
+if (@preg_match('/./u', '') === false) {
+	die('skip no utf8 support in PCRE library');
+}
+?>
+--FILE--
+<?php
+
+$string = b"\xc3\xa9 uma string utf8 bem formada";
+
+var_dump(preg_match(b'~.*~u', $string, $m, 0, 1));
+var_dump($m);
+var_dump(preg_last_error() == PREG_BAD_UTF8_OFFSET_ERROR);
+
+var_dump(preg_match(b'~.*~u', $string, $m, 0, 2));
+var_dump($m);
+var_dump(preg_last_error() == PREG_NO_ERROR);
+
+echo "Done\n";
+?>
+--EXPECT--
+bool(false)
+array(0) {
+}
+bool(true)
+int(1)
+array(1) {
+  [0]=>
+  string(28) " uma string utf8 bem formada"
+}
+bool(true)
+Done
diff --git a/ext/pcre/tests/locales.phpt b/ext/pcre/tests/locales.phpt
new file mode 100644
index 0000000..a103020
--- /dev/null
+++ b/ext/pcre/tests/locales.phpt
@@ -0,0 +1,29 @@
+--TEST--
+Localized match
+--SKIPIF--
+<?php 
+
+if (!function_exists('setlocale')) die('skip: setlocale() not available');
+if (!@setlocale(LC_ALL, 'pt_PT', 'pt', 'pt_PT.ISO8859-1', 'portuguese')) die('skip pt locale not available');
+
+?>
+--FILE--
+<?php
+
+// this tests if the cache is working correctly, as the char tables
+// must be rebuilt after the locale change
+
+setlocale(LC_ALL, 'C', 'POSIX');
+var_dump(preg_match('/^\w{6}$/', 'aàáçéè'));
+
+setlocale(LC_ALL, 'pt_PT', 'pt', 'pt_PT.ISO8859-1', 'portuguese');
+var_dump(preg_match('/^\w{6}$/', 'aàáçéè'));
+
+setlocale(LC_ALL, 'C', 'POSIX');
+var_dump(preg_match('/^\w{6}$/', 'aàáçéè'));
+
+?>
+--EXPECT--
+int(0)
+int(1)
+int(0)
diff --git a/ext/pcre/tests/match_flags.phpt b/ext/pcre/tests/match_flags.phpt
new file mode 100644
index 0000000..ddd36bf
--- /dev/null
+++ b/ext/pcre/tests/match_flags.phpt
@@ -0,0 +1,127 @@
+--TEST--
+preg_match_all() flags
+--FILE--
+<?php
+
+var_dump(preg_match_all('/(.)x/', 'zxax', $match, PREG_PATTERN_ORDER));
+var_dump($match);
+
+var_dump(preg_match_all('/(.)x/', 'zxyx', $match, PREG_SET_ORDER));
+var_dump($match);
+
+var_dump(preg_match_all('/(.)x/', 'zxyx', $match, PREG_OFFSET_CAPTURE));
+var_dump($match);
+
+var_dump(preg_match_all('/(.)x/', 'zxyx', $match, PREG_SET_ORDER | PREG_OFFSET_CAPTURE));
+var_dump($match);
+
+?>
+--EXPECT--
+int(2)
+array(2) {
+  [0]=>
+  array(2) {
+    [0]=>
+    string(2) "zx"
+    [1]=>
+    string(2) "ax"
+  }
+  [1]=>
+  array(2) {
+    [0]=>
+    string(1) "z"
+    [1]=>
+    string(1) "a"
+  }
+}
+int(2)
+array(2) {
+  [0]=>
+  array(2) {
+    [0]=>
+    string(2) "zx"
+    [1]=>
+    string(1) "z"
+  }
+  [1]=>
+  array(2) {
+    [0]=>
+    string(2) "yx"
+    [1]=>
+    string(1) "y"
+  }
+}
+int(2)
+array(2) {
+  [0]=>
+  array(2) {
+    [0]=>
+    array(2) {
+      [0]=>
+      string(2) "zx"
+      [1]=>
+      int(0)
+    }
+    [1]=>
+    array(2) {
+      [0]=>
+      string(2) "yx"
+      [1]=>
+      int(2)
+    }
+  }
+  [1]=>
+  array(2) {
+    [0]=>
+    array(2) {
+      [0]=>
+      string(1) "z"
+      [1]=>
+      int(0)
+    }
+    [1]=>
+    array(2) {
+      [0]=>
+      string(1) "y"
+      [1]=>
+      int(2)
+    }
+  }
+}
+int(2)
+array(2) {
+  [0]=>
+  array(2) {
+    [0]=>
+    array(2) {
+      [0]=>
+      string(2) "zx"
+      [1]=>
+      int(0)
+    }
+    [1]=>
+    array(2) {
+      [0]=>
+      string(1) "z"
+      [1]=>
+      int(0)
+    }
+  }
+  [1]=>
+  array(2) {
+    [0]=>
+    array(2) {
+      [0]=>
+      string(2) "yx"
+      [1]=>
+      int(2)
+    }
+    [1]=>
+    array(2) {
+      [0]=>
+      string(1) "y"
+      [1]=>
+      int(2)
+    }
+  }
+}
diff --git a/ext/pcre/tests/match_flags2.phpt b/ext/pcre/tests/match_flags2.phpt
new file mode 100644
index 0000000..f703091
--- /dev/null
+++ b/ext/pcre/tests/match_flags2.phpt
@@ -0,0 +1,95 @@
+--TEST--
+preg_match() flags
+--FILE--
+<?php
+
+var_dump(preg_match('/x(.)/', 'fjszxax', $match, PREG_OFFSET_CAPTURE));
+var_dump($match);
+
+var_dump(preg_match('/(.)x/', 'fjszxax', $match, PREG_OFFSET_CAPTURE, 4));
+var_dump($match);
+
+var_dump(preg_match('/(?P<capt1>.)(x)(?P<letsmix>\S+)/', 'fjszxax', $match, PREG_OFFSET_CAPTURE));
+var_dump($match);
+
+?>
+--EXPECT--
+int(1)
+array(2) {
+  [0]=>
+  array(2) {
+    [0]=>
+    string(2) "xa"
+    [1]=>
+    int(4)
+  }
+  [1]=>
+  array(2) {
+    [0]=>
+    string(1) "a"
+    [1]=>
+    int(5)
+  }
+}
+int(1)
+array(2) {
+  [0]=>
+  array(2) {
+    [0]=>
+    string(2) "ax"
+    [1]=>
+    int(5)
+  }
+  [1]=>
+  array(2) {
+    [0]=>
+    string(1) "a"
+    [1]=>
+    int(5)
+  }
+}
+int(1)
+array(6) {
+  [0]=>
+  array(2) {
+    [0]=>
+    string(4) "zxax"
+    [1]=>
+    int(3)
+  }
+  ["capt1"]=>
+  array(2) {
+    [0]=>
+    string(1) "z"
+    [1]=>
+    int(3)
+  }
+  [1]=>
+  array(2) {
+    [0]=>
+    string(1) "z"
+    [1]=>
+    int(3)
+  }
+  [2]=>
+  array(2) {
+    [0]=>
+    string(1) "x"
+    [1]=>
+    int(4)
+  }
+  ["letsmix"]=>
+  array(2) {
+    [0]=>
+    string(2) "ax"
+    [1]=>
+    int(5)
+  }
+  [3]=>
+  array(2) {
+    [0]=>
+    string(2) "ax"
+    [1]=>
+    int(5)
+  }
+}
diff --git a/ext/pcre/tests/match_flags3.phpt b/ext/pcre/tests/match_flags3.phpt
new file mode 100644
index 0000000..f22205e
--- /dev/null
+++ b/ext/pcre/tests/match_flags3.phpt
@@ -0,0 +1,46 @@
+--TEST--
+preg_match() flags 3
+--FILE--
+<?php
+
+var_dump(preg_match('', '', $match, 0xfff));
+
+var_dump(preg_match('/\d+/', '123 456 789 012', $match, 0, -8));
+var_dump($match);
+
+var_dump(preg_match('/\d+/', '123 456 789 012', $match, 0, -500));
+var_dump($match);
+
+var_dump(preg_match_all('/\d+/', '123 456 789 012', $match, 0, -8));
+var_dump($match);
+
+var_dump(preg_match('/(?P<3>)/', ''));
+
+?>
+--EXPECTF--
+
+Warning: preg_match(): Empty regular expression in %smatch_flags3.php on line 3
+bool(false)
+int(1)
+array(1) {
+  [0]=>
+  string(3) "789"
+}
+int(1)
+array(1) {
+  [0]=>
+  string(3) "123"
+}
+int(2)
+array(1) {
+  [0]=>
+  array(2) {
+    [0]=>
+    string(3) "789"
+    [1]=>
+    string(3) "012"
+  }
+}
+
+Warning: preg_match(): Numeric named subpatterns are not allowed in %smatch_flags3.php on line 14
+bool(false)
diff --git a/ext/pcre/tests/multiline.phpt b/ext/pcre/tests/multiline.phpt
new file mode 100644
index 0000000..3568009
--- /dev/null
+++ b/ext/pcre/tests/multiline.phpt
@@ -0,0 +1,18 @@
+--TEST--
+Multi-line match
+--FILE--
+<?php
+
+var_dump(preg_match_all('/^.{2,3}$/', "aei\nou", $dummy));
+var_dump(preg_match_all('/^.{2,3}$/', "aei\nou\n", $dummy));
+var_dump(preg_match_all('/^.{2,3}$/m', "aei\nou", $dummy));
+var_dump(preg_match_all('/^.{2,3}$/m', "aei\nou\n", $dummy));
+
+echo "done\n";
+?>
+--EXPECT--
+int(0)
+int(0)
+int(2)
+int(2)
+done
diff --git a/ext/pcre/tests/null_bytes.phpt b/ext/pcre/tests/null_bytes.phpt
new file mode 100644
index 0000000..9a3f433
--- /dev/null
+++ b/ext/pcre/tests/null_bytes.phpt
@@ -0,0 +1,42 @@
+--TEST--
+Zero byte test
+--FILE--
+<?php
+
+preg_match("\0//i", "");
+preg_match("/\0/i", "");
+preg_match("//\0i", "");
+preg_match("//i\0", "");
+preg_match("/\\\0/i", "");
+
+preg_match("\0[]i", "");
+preg_match("[\0]i", "");
+preg_match("[]\0i", "");
+preg_match("[]i\0", "");
+preg_match("[\\\0]i", "");
+
+preg_replace("/foo/e\0/i", "echo('Eek');", "");
+
+?>
+--EXPECTF--
+Warning: preg_match(): Null byte in regex in %snull_bytes.php on line 3
+
+Warning: preg_match(): Null byte in regex in %snull_bytes.php on line 4
+
+Warning: preg_match(): Null byte in regex in %snull_bytes.php on line 5
+
+Warning: preg_match(): Null byte in regex in %snull_bytes.php on line 6
+
+Warning: preg_match(): Null byte in regex in %snull_bytes.php on line 7
+
+Warning: preg_match(): Null byte in regex in %snull_bytes.php on line 9
+
+Warning: preg_match(): Null byte in regex in %snull_bytes.php on line 10
+
+Warning: preg_match(): Null byte in regex in %snull_bytes.php on line 11
+
+Warning: preg_match(): Null byte in regex in %snull_bytes.php on line 12
+
+Warning: preg_match(): Null byte in regex in %snull_bytes.php on line 13
+
+Warning: preg_replace(): Null byte in regex in %snull_bytes.php on line 15
diff --git a/ext/pcre/tests/pcre.constants.phpt b/ext/pcre/tests/pcre.constants.phpt
new file mode 100644
index 0000000..0b10330
--- /dev/null
+++ b/ext/pcre/tests/pcre.constants.phpt
@@ -0,0 +1,35 @@
+--TEST--
+Test for pre-defined pcre constants 
+--FILE--
+<?php
+
+echo "PCRE constants test\n"; 
+
+echo "PREG_PATTERN_ORDER= ", PREG_PATTERN_ORDER, "\n";
+echo "PREG_OFFSET_CAPTURE= ", PREG_OFFSET_CAPTURE, "\n";
+echo "PREG_SPLIT_NO_EMPTY= ", PREG_SPLIT_NO_EMPTY, "\n"; 
+echo "PREG_SPLIT_DELIM_CAPTURE= ", PREG_SPLIT_DELIM_CAPTURE, "\n";
+echo "PREG_SPLIT_OFFSET_CAPTURE= ", PREG_SPLIT_OFFSET_CAPTURE, "\n";
+echo "PREG_GREP_INVERT= ", PREG_GREP_INVERT, "\n";
+echo "PREG_NO_ERROR= ", PREG_NO_ERROR, "\n";
+echo "PREG_INTERNAL_ERROR= ", PREG_INTERNAL_ERROR, "\n";
+echo "PREG_BACKTRACK_LIMIT_ERROR= ", PREG_BACKTRACK_LIMIT_ERROR, "\n";
+echo "PREG_RECURSION_LIMIT_ERROR= ", PREG_RECURSION_LIMIT_ERROR, "\n";
+echo "PREG_BAD_UTF8_ERROR= ", PREG_BAD_UTF8_ERROR, "\n";
+
+?>
+===Done===
+--EXPECT--
+PCRE constants test
+PREG_PATTERN_ORDER= 1
+PREG_OFFSET_CAPTURE= 256
+PREG_SPLIT_NO_EMPTY= 1
+PREG_SPLIT_DELIM_CAPTURE= 2
+PREG_SPLIT_OFFSET_CAPTURE= 4
+PREG_GREP_INVERT= 1
+PREG_NO_ERROR= 0
+PREG_INTERNAL_ERROR= 1
+PREG_BACKTRACK_LIMIT_ERROR= 2
+PREG_RECURSION_LIMIT_ERROR= 3
+PREG_BAD_UTF8_ERROR= 4
+===Done===
\ No newline at end of file
diff --git a/ext/pcre/tests/pcre_anchored.phpt b/ext/pcre/tests/pcre_anchored.phpt
new file mode 100644
index 0000000..a609fdb
--- /dev/null
+++ b/ext/pcre/tests/pcre_anchored.phpt
@@ -0,0 +1,28 @@
+--TEST--
+A (PCRE_ANCHORED) modififer
+--SKIPIF--
+<?php
+if (@preg_match_all('/\p{N}/', '0123456789', $dummy) === false) {
+	die("skip no support for \p support PCRE library");
+}
+?>
+--FILE--
+<?php
+
+var_dump(preg_match('/\PN+/', '123abc', $m));
+var_dump($m);
+
+var_dump(preg_match('/\P{N}+/A', '123abc'));
+var_dump(preg_match('/^\P{N}+/', '123abc'));
+var_dump(preg_match('/^\P{N}+/A', '123abc'));
+
+?>
+--EXPECT--
+int(1)
+array(1) {
+  [0]=>
+  string(3) "abc"
+}
+int(0)
+int(0)
+int(0)
diff --git a/ext/pcre/tests/pcre_count.phpt b/ext/pcre/tests/pcre_count.phpt
new file mode 100644
index 0000000..1239d48
--- /dev/null
+++ b/ext/pcre/tests/pcre_count.phpt
@@ -0,0 +1,40 @@
+--TEST--
+preg_replace() fifth parameter - count
+--FILE--
+<?php
+$regex = '/(([0-9a-z]+)-([0-9]+))-(([0-9]+)-([0-9]+))/';
+
+$string= '1-2-3-4 a-2-3-4 1-a-3-4 1-2-a-4 1-2-3-a a-a-a-a 4-3-2-1 100-200-300-400-500-600-700-800';
+$count = 0;
+var_dump(preg_replace($regex, 'xxxx', $string, -1, $count));
+var_dump($count);
+//////////////////////////////////////////////////////
+
+$regex = '/([a-z]+)/';
+
+$string= 'Here must only number like 42 and 13 appear';
+var_dump(preg_replace($regex, 'xxxx', $string, -1, $count));
+var_dump($count);
+
+////////////////////////////////////////////////////////
+$regex = '~((V(I|1)(4|A)GR(4|A))|(V(I|1)C(0|O)D(I|1)(N|\/\\\/)))~i';
+
+$string= 'Viagra V14GR4 Vicodin V1C0D1/\/ v1c0d1/|/';
+var_dump(preg_replace($regex, '...', $string, -1, $count));
+var_dump($count);
+////////////////////////////////////////////////////////
+$regex = '~((V(I|1)(4|A)GR(4|A))|(V(I|1)C(0|O)D(I|1)(N|\/\\\/)))~i';
+$count = NULL;
+$string= 'Viagra V14GR4 Vicodin V1C0D1/\/ v1c0d1/|/';
+var_dump(preg_replace($regex, '...', $string, -1));
+var_dump($count);
+?>
+--EXPECT--
+string(56) "xxxx xxxx 1-a-3-4 1-2-a-4 1-2-3-a a-a-a-a xxxx xxxx-xxxx"
+int(5)
+string(41) "Hxxxx xxxx xxxx xxxx xxxx 42 xxxx 13 xxxx"
+int(7)
+string(25) "... ... ... ... v1c0d1/|/"
+int(4)
+string(25) "... ... ... ... v1c0d1/|/"
+NULL
diff --git a/ext/pcre/tests/pcre_extended.phpt b/ext/pcre/tests/pcre_extended.phpt
new file mode 100644
index 0000000..6c4b20e
--- /dev/null
+++ b/ext/pcre/tests/pcre_extended.phpt
@@ -0,0 +1,29 @@
+--TEST--
+x (PCRE_EXTENDED) modififer
+--FILE--
+<?php
+
+var_dump(preg_match('/a e i o u/', 'aeiou', $m));
+var_dump($m);
+
+var_dump(preg_match('/a e i o u/x', 'aeiou', $m));
+var_dump($m);
+
+var_dump(preg_match("/a e\ni\to\ru/x", 'aeiou', $m));
+var_dump($m);
+
+?>
+--EXPECT--
+int(0)
+array(0) {
+}
+int(1)
+array(1) {
+  [0]=>
+  string(5) "aeiou"
+}
+int(1)
+array(1) {
+  [0]=>
+  string(5) "aeiou"
+}
diff --git a/ext/pcre/tests/pcre_extra.phpt b/ext/pcre/tests/pcre_extra.phpt
new file mode 100644
index 0000000..2bee408
--- /dev/null
+++ b/ext/pcre/tests/pcre_extra.phpt
@@ -0,0 +1,14 @@
+--TEST--
+X (PCRE_EXTRA) modififer
+--FILE--
+<?php
+
+var_dump(preg_match('/\y/', '\y'));
+var_dump(preg_match('/\y/X', '\y'));
+
+?>
+--EXPECTF--
+int(1)
+
+Warning: preg_match(): Compilation failed: unrecognized character follows \ at offset 1 in %spcre_extra.php on line 4
+bool(false)
diff --git a/ext/pcre/tests/preg_filter.phpt b/ext/pcre/tests/preg_filter.phpt
new file mode 100644
index 0000000..6cd9802
--- /dev/null
+++ b/ext/pcre/tests/preg_filter.phpt
@@ -0,0 +1,29 @@
+--TEST--
+preg_filter()
+--FILE--
+<?php
+
+$subject = array('1', 'a', '2', 'b', '3', 'A', 'B', '4');
+$pattern = array('/\d/', '/[a-z]/', '/[1a]/');
+$replace = array('A:$0', 'B:$0', 'C:$0');
+
+var_dump(preg_filter($pattern, $replace, $subject));
+
+?>
+===DONE===
+--EXPECT--
+array(6) {
+  [0]=>
+  string(5) "A:C:1"
+  [1]=>
+  string(5) "B:C:a"
+  [2]=>
+  string(3) "A:2"
+  [3]=>
+  string(3) "B:b"
+  [4]=>
+  string(3) "A:3"
+  [7]=>
+  string(3) "A:4"
+}
+===DONE===
diff --git a/ext/pcre/tests/preg_grep_basic.phpt b/ext/pcre/tests/preg_grep_basic.phpt
new file mode 100644
index 0000000..fe9d7ce
--- /dev/null
+++ b/ext/pcre/tests/preg_grep_basic.phpt
@@ -0,0 +1,62 @@
+--TEST--
+Test preg_grep() function : basic functionality 
+--FILE--
+<?php
+/*
+* proto array preg_grep(string regex, array input [, int flags])
+* Function is implemented in ext/pcre/php_pcre.c
+*/
+$array = array('HTTP://WWW.EXAMPLE.COM', '/index.html', '/info/stat/', 'http://test.uk.com/index/html', '/display/dept.php');
+var_dump($array);
+var_dump(preg_grep('@^HTTP(.*?)\w{2,}$@i', $array)); //finds a string starting with http (regardless of case) (matches two)
+var_dump(preg_grep('@(/\w+\.*/*)+@', $array)); //finds / followed by one or more of a-z, A-Z and 0-9, followed by zero or more . followed by zero or more / all more than once. (matches all)
+var_dump(preg_grep('@^http://[^w]{3}.*$@i', $array)); //finds http:// (at the beginning of a string) not followed by 3 characters that aren't w's then anything to the end of the sttring (matches one)
+var_dump(preg_grep('@.*?\.co\.uk$@i', $array)); //finds any address ending in .co.uk (matches none)
+var_dump(preg_grep('@^HTTP(.*?)\w{2,}$@i', $array, PREG_GREP_INVERT)); //same as first example but the array created contains everything that is NOT matched but the regex (matches three)
+
+?>
+--EXPECT--
+array(5) {
+  [0]=>
+  string(22) "HTTP://WWW.EXAMPLE.COM"
+  [1]=>
+  string(11) "/index.html"
+  [2]=>
+  string(11) "/info/stat/"
+  [3]=>
+  string(29) "http://test.uk.com/index/html"
+  [4]=>
+  string(17) "/display/dept.php"
+}
+array(2) {
+  [0]=>
+  string(22) "HTTP://WWW.EXAMPLE.COM"
+  [3]=>
+  string(29) "http://test.uk.com/index/html"
+}
+array(5) {
+  [0]=>
+  string(22) "HTTP://WWW.EXAMPLE.COM"
+  [1]=>
+  string(11) "/index.html"
+  [2]=>
+  string(11) "/info/stat/"
+  [3]=>
+  string(29) "http://test.uk.com/index/html"
+  [4]=>
+  string(17) "/display/dept.php"
+}
+array(1) {
+  [3]=>
+  string(29) "http://test.uk.com/index/html"
+}
+array(0) {
+}
+array(3) {
+  [1]=>
+  string(11) "/index.html"
+  [2]=>
+  string(11) "/info/stat/"
+  [4]=>
+  string(17) "/display/dept.php"
+}
diff --git a/ext/pcre/tests/preg_grep_error.phpt b/ext/pcre/tests/preg_grep_error.phpt
new file mode 100644
index 0000000..f2afdb9
--- /dev/null
+++ b/ext/pcre/tests/preg_grep_error.phpt
@@ -0,0 +1,43 @@
+--TEST--
+Test preg_grep() function : error conditions - wrong numbers of parameters
+--FILE--
+<?php
+/*
+* proto array preg_grep(string regex, array input [, int flags])
+* Function is implemented in ext/pcre/php_pcre.c
+*/
+echo "*** Testing preg_grep() : error conditions ***\n";
+// Zero arguments
+echo "\n-- Testing preg_grep() function with Zero arguments --\n";
+var_dump(preg_grep());
+//Test preg_grep with one more than the expected number of arguments
+echo "\n-- Testing preg_grep() function with more than expected no. of arguments --\n";
+$regex = '/\d/';
+$input = array(1, 2);
+$flags = 0;
+$extra_arg = 10;
+var_dump(preg_grep($regex, $input, $flags, $extra_arg));
+// Testing preg_grep withone less than the expected number of arguments
+echo "\n-- Testing preg_grep() function with less than expected no. of arguments --\n";
+$regex = 'string_val';
+var_dump(preg_grep($regex));
+echo "Done"
+?>
+--EXPECTF--
+*** Testing preg_grep() : error conditions ***
+
+-- Testing preg_grep() function with Zero arguments --
+
+Warning: preg_grep() expects at least 2 parameters, 0 given in %spreg_grep_error.php on line %d
+NULL
+
+-- Testing preg_grep() function with more than expected no. of arguments --
+
+Warning: preg_grep() expects at most 3 parameters, 4 given in %spreg_grep_error.php on line %d
+NULL
+
+-- Testing preg_grep() function with less than expected no. of arguments --
+
+Warning: preg_grep() expects at least 2 parameters, 1 given in %spreg_grep_error.php on line %d
+NULL
+Done
\ No newline at end of file
diff --git a/ext/pcre/tests/preg_grep_error1.phpt b/ext/pcre/tests/preg_grep_error1.phpt
new file mode 100644
index 0000000..29dfc5a
--- /dev/null
+++ b/ext/pcre/tests/preg_grep_error1.phpt
@@ -0,0 +1,68 @@
+--TEST--
+Test preg_grep() function : error conditions - bad regular expressions
+--FILE--
+<?php
+/*
+* proto array preg_grep(string regex, array input [, int flags])
+* Function is implemented in ext/pcre/php_pcre.c
+*/
+error_reporting(E_ALL&~E_NOTICE);
+/*
+* Testing how preg_grep reacts to being passed bad regexes
+*/
+echo "*** Testing preg_grep() : error conditions ***\n";
+$values = array('abcdef', //Regex without delimeter
+'/[a-zA-Z]', //Regex without closing delimeter
+'[a-zA-Z]/', //Regex without opening delimeter
+'/[a-zA-Z]/F', array('[a-z]', //Array of Regexes
+'[A-Z]', '[0-9]'), '/[a-zA-Z]/', //Regex string
+);
+$array = array(123, 'abc', 'test');
+foreach($values as $value) {
+    print "\nArg value is $value\n";
+    var_dump(preg_grep($value, $array));
+}
+$value = new stdclass(); //Object
+var_dump(preg_grep($value, $array));
+echo "Done"
+?>
+--EXPECTF--
+
+*** Testing preg_grep() : error conditions ***
+
+Arg value is abcdef
+
+Warning: preg_grep(): Delimiter must not be alphanumeric or backslash in %spreg_grep_error1.php on line %d
+bool(false)
+
+Arg value is /[a-zA-Z]
+
+Warning: preg_grep(): No ending delimiter '/' found in %spreg_grep_error1.php on line %d
+bool(false)
+
+Arg value is [a-zA-Z]/
+
+Warning: preg_grep(): Unknown modifier '/' in %spreg_grep_error1.php on line %d
+bool(false)
+
+Arg value is /[a-zA-Z]/F
+
+Warning: preg_grep(): Unknown modifier 'F' in %spreg_grep_error1.php on line %d
+bool(false)
+
+Arg value is Array
+
+Warning: preg_grep() expects parameter 1 to be string, array given in %spreg_grep_error1.php on line %d
+NULL
+
+Arg value is /[a-zA-Z]/
+array(2) {
+  [1]=>
+  string(3) "abc"
+  [2]=>
+  string(4) "test"
+}
+
+Warning: preg_grep() expects parameter 1 to be string, object given in %spreg_grep_error1.php on line %d
+NULL
+Done
\ No newline at end of file
diff --git a/ext/pcre/tests/preg_grep_error2.phpt b/ext/pcre/tests/preg_grep_error2.phpt
new file mode 100644
index 0000000..aa4dae9
--- /dev/null
+++ b/ext/pcre/tests/preg_grep_error2.phpt
@@ -0,0 +1,42 @@
+--TEST--
+Test preg_grep() function : error conditions - wrong arg types
+--FILE--
+<?php
+/*
+* proto array preg_grep(string regex, array input [, int flags])
+* Function is implemented in ext/pcre/php_pcre.c
+*/
+error_reporting(E_ALL&~E_NOTICE);
+/*
+* Testing how preg_grep reacts to being passed the wrong type of input argument
+*/
+echo "*** Testing preg_grep() : error conditions ***\n";
+$regex = '/[a-zA-Z]/';
+$input = array('this is a string', array('this is', 'a subarray'),);
+foreach($input as $value) {
+    print "\nArg value is: $value\n";
+    var_dump(preg_grep($regex, $value));
+}
+$value = new stdclass(); //Object
+var_dump(preg_grep($regex, $value));
+echo "Done";
+?>
+--EXPECTF--
+*** Testing preg_grep() : error conditions ***
+
+Arg value is: this is a string
+
+Warning: preg_grep() expects parameter 2 to be array, string given in %spreg_grep_error2.php on line %d
+NULL
+
+Arg value is: Array
+array(2) {
+  [0]=>
+  string(7) "this is"
+  [1]=>
+  string(10) "a subarray"
+}
+
+Warning: preg_grep() expects parameter 2 to be array, object given in %spreg_grep_error2.php on line %d
+NULL
+Done
\ No newline at end of file
diff --git a/ext/pcre/tests/preg_last_error_error.phpt b/ext/pcre/tests/preg_last_error_error.phpt
new file mode 100644
index 0000000..c75e2f8
--- /dev/null
+++ b/ext/pcre/tests/preg_last_error_error.phpt
@@ -0,0 +1,30 @@
+--TEST--
+Test preg_grep() function : error conditions -  wrong numbers of parameters
+--FILE--
+<?php
+
+/* Prototype  : int preg_last_error  ( void  )
+ * Description:  Returns the error code of the last PCRE regex execution
+ * Source code: ext/pcre/php_pcre.c
+ */
+
+/*
+ * Pass an incorrect number of arguments to preg_last_error() to test behaviour
+ */
+
+echo "*** Testing preg_last_error() : error conditions ***\n";
+
+// Test preg_last_error with one more than the expected number of arguments
+echo "\n-- Testing preg_last_error() function with more than expected no. of arguments --\n";
+$extra_arg = 10;
+var_dump( preg_last_error($extra_arg) );
+?>
+===Done===
+--EXPECTF--
+*** Testing preg_last_error() : error conditions ***
+
+-- Testing preg_last_error() function with more than expected no. of arguments --
+
+Warning: preg_last_error() expects exactly 0 parameters, 1 given in %s on line %d
+NULL
+===Done===
\ No newline at end of file
diff --git a/ext/pcre/tests/preg_match_all_basic.phpt b/ext/pcre/tests/preg_match_all_basic.phpt
new file mode 100644
index 0000000..20c4a96
--- /dev/null
+++ b/ext/pcre/tests/preg_match_all_basic.phpt
@@ -0,0 +1,92 @@
+--TEST--
+Test preg_match_all() function : basic functionality 
+--FILE--
+<?php
+/*
+* proto int preg_match_all(string pattern, string subject, [array subpatterns [, int flags [, int offset]]])
+* Function is implemented in ext/pcre/php_pcre.c
+*/
+$string = 'Hello, world! This is a test. This is another test. \[4]. 34534 string.';
+var_dump(preg_match_all('/[0-35-9]/', $string, $match1, PREG_OFFSET_CAPTURE|PREG_PATTERN_ORDER, -10)); //finds any digit that's not 4 10 digits from the end(1 match)
+var_dump($match1);
+var_dump(preg_match_all('/[tT]his is a(.*?)\./', $string, $match2, PREG_SET_ORDER)); //finds "This is a test." and "This is another test." (non-greedy) (2 matches)
+var_dump($match2);
+var_dump(preg_match_all('@\. \\\(.*).@', $string, $match3, PREG_PATTERN_ORDER)); //finds ".\ [...]" and everything else to the end of the string. (greedy) (1 match)
+var_dump($match3);
+var_dump(preg_match_all('/\d{2}$/', $string, $match4)); //tries to find 2 digits at the end of a string (0 matches)
+var_dump($match4);
+var_dump(preg_match_all('/(This is a ){2}(.*)\stest/', $string, $match5)); //tries to find "This is aThis is a [...] test" (0 matches)
+var_dump($match5);
+
+// Test not passing in a subpatterns array.
+var_dump(preg_match_all('/test/', $string));
+var_dump(preg_match_all('/this isn\'t in the string/', $string));
+var_dump(preg_match_all('/world/', $string));
+var_dump(preg_match_all('/[0-9]/', $string));
+?>
+--EXPECTF--
+int(1)
+array(1) {
+  [0]=>
+  array(1) {
+    [0]=>
+    array(2) {
+      [0]=>
+      string(1) "3"
+      [1]=>
+      int(61)
+    }
+  }
+}
+int(2)
+array(2) {
+  [0]=>
+  array(2) {
+    [0]=>
+    string(15) "This is a test."
+    [1]=>
+    string(5) " test"
+  }
+  [1]=>
+  array(2) {
+    [0]=>
+    string(21) "This is another test."
+    [1]=>
+    string(11) "nother test"
+  }
+}
+int(1)
+array(2) {
+  [0]=>
+  array(1) {
+    [0]=>
+    string(21) ". \[4]. 34534 string."
+  }
+  [1]=>
+  array(1) {
+    [0]=>
+    string(17) "[4]. 34534 string"
+  }
+}
+int(0)
+array(1) {
+  [0]=>
+  array(0) {
+  }
+}
+int(0)
+array(3) {
+  [0]=>
+  array(0) {
+  }
+  [1]=>
+  array(0) {
+  }
+  [2]=>
+  array(0) {
+  }
+}
+int(2)
+int(0)
+int(1)
+int(6)
diff --git a/ext/pcre/tests/preg_match_all_edit_basic.phpt b/ext/pcre/tests/preg_match_all_edit_basic.phpt
new file mode 100644
index 0000000..9edcf73
--- /dev/null
+++ b/ext/pcre/tests/preg_match_all_edit_basic.phpt
@@ -0,0 +1,89 @@
+--TEST--
+Test preg_match_all() function : basic functionality 
+--FILE--
+<?php
+/* Prototype  : proto int preg_match_all(string pattern, string subject, array subpatterns [, int flags [, int offset]])
+ * Description: Perform a Perl-style global regular expression match 
+ * Source code: ext/pcre/php_pcre.c
+ * Alias to functions: 
+*/
+
+$string = 'Hello, world! This is a test. This is another test. \[4]. 34534 string.';
+
+var_dump(preg_match_all('/[0-35-9]/', $string, $match1, PREG_OFFSET_CAPTURE|PREG_PATTERN_ORDER, -10));               	//finds any digit that's not 4 10 digits from the end(1 match)
+var_dump($match1);
+
+var_dump(preg_match_all('/[tT]his is a(.*?)\./', $string, $match2, PREG_SET_ORDER));    						//finds "This is a test." and "This is another test." (non-greedy) (2 matches)
+var_dump($match2);
+
+var_dump(preg_match_all('@\. \\\(.*).@', $string, $match3, PREG_PATTERN_ORDER));            				//finds ".\ [...]" and everything else to the end of the string. (greedy) (1 match)
+var_dump($match3);
+
+var_dump(preg_match_all('/\d{2}$/', $string, $match4));										//tries to find 2 digits at the end of a string (0 matches)
+var_dump($match4);
+
+var_dump(preg_match_all('/(This is a ){2}(.*)\stest/', $string, $match5));							//tries to find "This is aThis is a [...] test" (0 matches)	
+var_dump($match5);
+?>
+--EXPECTF--
+int(1)
+array(1) {
+  [0]=>
+  array(1) {
+    [0]=>
+    array(2) {
+      [0]=>
+      string(1) "3"
+      [1]=>
+      int(61)
+    }
+  }
+}
+int(2)
+array(2) {
+  [0]=>
+  array(2) {
+    [0]=>
+    string(15) "This is a test."
+    [1]=>
+    string(5) " test"
+  }
+  [1]=>
+  array(2) {
+    [0]=>
+    string(21) "This is another test."
+    [1]=>
+    string(11) "nother test"
+  }
+}
+int(1)
+array(2) {
+  [0]=>
+  array(1) {
+    [0]=>
+    string(21) ". \[4]. 34534 string."
+  }
+  [1]=>
+  array(1) {
+    [0]=>
+    string(17) "[4]. 34534 string"
+  }
+}
+int(0)
+array(1) {
+  [0]=>
+  array(0) {
+  }
+}
+int(0)
+array(3) {
+  [0]=>
+  array(0) {
+  }
+  [1]=>
+  array(0) {
+  }
+  [2]=>
+  array(0) {
+  }
+}
diff --git a/ext/pcre/tests/preg_match_all_error.phpt b/ext/pcre/tests/preg_match_all_error.phpt
new file mode 100644
index 0000000..f6e8928
--- /dev/null
+++ b/ext/pcre/tests/preg_match_all_error.phpt
@@ -0,0 +1,44 @@
+--TEST--
+Test preg_match_all() function : error conditions - incorrect number of parameters
+--FILE--
+<?php
+/*
+* proto int preg_match_all(string pattern, string subject, array subpatterns [, int flags [, int offset]])
+* Function is implemented in ext/pcre/php_pcre.c
+*/
+echo "*** Testing preg_match_all() : error conditions ***\n";
+// Zero arguments
+echo "\n-- Testing preg_match_all() function with Zero arguments --\n";
+var_dump(preg_match_all());
+//Test preg_match_all with one more than the expected number of arguments
+echo "\n-- Testing preg_match_all() function with more than expected no. of arguments --\n";
+$pattern = '/\w/';
+$subject = 'string_val';
+$flags = PREG_OFFSET_CAPTURE;
+$offset = 10;
+$extra_arg = 10;
+var_dump(preg_match_all($pattern, $subject, $matches, $flags, $offset, $extra_arg));
+// Testing preg_match_all withone less than the expected number of arguments
+echo "\n-- Testing preg_match_all() function with less than expected no. of arguments --\n";
+$pattern = '/\w/';
+var_dump(preg_match_all($pattern));
+echo "Done"
+?>
+--EXPECTF--
+*** Testing preg_match_all() : error conditions ***
+
+-- Testing preg_match_all() function with Zero arguments --
+
+Warning: preg_match_all() expects at least 2 parameters, 0 given in %spreg_match_all_error.php on line %d
+bool(false)
+
+-- Testing preg_match_all() function with more than expected no. of arguments --
+
+Warning: preg_match_all() expects at most 5 parameters, 6 given in %spreg_match_all_error.php on line %d
+bool(false)
+
+-- Testing preg_match_all() function with less than expected no. of arguments --
+
+Warning: preg_match_all() expects at least 2 parameters, 1 given in %spreg_match_all_error.php on line %d
+bool(false)
+Done
diff --git a/ext/pcre/tests/preg_match_all_error1.phpt b/ext/pcre/tests/preg_match_all_error1.phpt
new file mode 100644
index 0000000..a3cb684
--- /dev/null
+++ b/ext/pcre/tests/preg_match_all_error1.phpt
@@ -0,0 +1,81 @@
+--TEST--
+Test preg_match_all() function : error conditions - bad regular expressions
+--FILE--
+<?php
+/*
+* proto int preg_match_all(string pattern, string subject, array subpatterns [, int flags [, int offset]])
+* Function is implemented in ext/pcre/php_pcre.c
+*/
+error_reporting(E_ALL&~E_NOTICE);
+/*
+* Testing how preg_match_all reacts to being passed the wrong type of regex argument
+*/
+echo "*** Testing preg_match_all() : error conditions ***\n";
+$regex_array = array('abcdef', //Regex without delimeter
+'/[a-zA-Z]', //Regex without closing delimeter
+'[a-zA-Z]/', //Regex without opening delimeter
+'/[a-zA-Z]/F', array('[a-z]', //Array of Regexes
+'[A-Z]', '[0-9]'), '/[a-zA-Z]/', //Regex string
+);
+$subject = 'test';
+foreach($regex_array as $regex_value) {
+    print "\nArg value is $regex_value\n";
+    var_dump(preg_match_all($regex_value, $subject, $matches1));
+    var_dump($matches1);
+}
+$regex_value = new stdclass(); //Object
+var_dump(preg_match_all($regex_value, $subject, $matches));
+var_dump($matches);
+?>
+--EXPECTF--
+*** Testing preg_match_all() : error conditions ***
+
+Arg value is abcdef
+
+Warning: preg_match_all(): Delimiter must not be alphanumeric or backslash in %spreg_match_all_error1.php on line %d
+bool(false)
+NULL
+
+Arg value is /[a-zA-Z]
+
+Warning: preg_match_all(): No ending delimiter '/' found in %spreg_match_all_error1.php on line %d
+bool(false)
+NULL
+
+Arg value is [a-zA-Z]/
+
+Warning: preg_match_all(): Unknown modifier '/' in %spreg_match_all_error1.php on line %d
+bool(false)
+NULL
+
+Arg value is /[a-zA-Z]/F
+
+Warning: preg_match_all(): Unknown modifier 'F' in %spreg_match_all_error1.php on line %d
+bool(false)
+NULL
+
+Arg value is Array
+
+Warning: preg_match_all() expects parameter 1 to be string, array given in %spreg_match_all_error1.php on line %d
+bool(false)
+NULL
+
+Arg value is /[a-zA-Z]/
+int(4)
+array(1) {
+  [0]=>
+  array(4) {
+    [0]=>
+    string(1) "t"
+    [1]=>
+    string(1) "e"
+    [2]=>
+    string(1) "s"
+    [3]=>
+    string(1) "t"
+  }
+}
+
+Warning: preg_match_all() expects parameter 1 to be string, object given in %spreg_match_all_error1.php on line %d
+bool(false)
+NULL
diff --git a/ext/pcre/tests/preg_match_all_error2.phpt b/ext/pcre/tests/preg_match_all_error2.phpt
new file mode 100644
index 0000000..1c55cce
--- /dev/null
+++ b/ext/pcre/tests/preg_match_all_error2.phpt
@@ -0,0 +1,54 @@
+--TEST--
+Test preg_match_all() function : error conditions - wrong arg types
+--FILE--
+<?php
+/*
+* proto int preg_match_all(string pattern, string subject, array subpatterns [, int flags [, int offset]])
+* Function is implemented in ext/pcre/php_pcre.c
+*/
+error_reporting(E_ALL&~E_NOTICE);
+/*
+* Testing how preg_match_all reacts to being passed the wrong type of input argument
+*/
+echo "*** Testing preg_match_all() : error conditions ***\n";
+$regex = '/[a-zA-Z]/';
+$value = new stdclass(); //Object
+var_dump(preg_match_all($regex, $value, $matches));
+var_dump($matches);
+$input = array(array('this is', 'a subarray'), 'test',);
+foreach($input as $value) {
+    print "\nArg value is: $value\n";
+    var_dump(preg_match_all($regex, $value, $matches));
+    var_dump($matches);
+}
+echo "Done";
+?>
+--EXPECTF--
+*** Testing preg_match_all() : error conditions ***
+
+Warning: preg_match_all() expects parameter 2 to be string, object given in %spreg_match_all_error2.php on line %d
+bool(false)
+NULL
+
+Arg value is: Array
+
+Warning: preg_match_all() expects parameter 2 to be string, array given in %spreg_match_all_error2.php on line %d
+bool(false)
+NULL
+
+Arg value is: test
+int(4)
+array(1) {
+  [0]=>
+  array(4) {
+    [0]=>
+    string(1) "t"
+    [1]=>
+    string(1) "e"
+    [2]=>
+    string(1) "s"
+    [3]=>
+    string(1) "t"
+  }
+}
+Done
diff --git a/ext/pcre/tests/preg_match_all_error3.phpt b/ext/pcre/tests/preg_match_all_error3.phpt
new file mode 100644
index 0000000..547ff03
--- /dev/null
+++ b/ext/pcre/tests/preg_match_all_error3.phpt
@@ -0,0 +1,20 @@
+--TEST--
+Test preg_match_all() function : error conditions  
+--FILE--
+<?php
+/*
+* proto int preg_match_all(string pattern, string subject, array subpatterns [, int flags [, int offset]])
+* Function is implemented in ext/pcre/php_pcre.c
+*/
+/*
+* Testing how preg_match_all reacts to being passed the wrong type of subpatterns array argument
+*/
+echo "*** Testing preg_match_all() : error conditions ***\n";
+$regex = '/[a-z]/';
+$subject = 'string';
+var_dump(preg_match_all($regex, $subject, 'test'));
+echo "Done";
+?>
+--EXPECTF--
+
+Fatal error: Only variables can be passed by reference in %spreg_match_all_error3.php on line %d
diff --git a/ext/pcre/tests/preg_match_basic.phpt b/ext/pcre/tests/preg_match_basic.phpt
new file mode 100644
index 0000000..ddf54a0
--- /dev/null
+++ b/ext/pcre/tests/preg_match_basic.phpt
@@ -0,0 +1,52 @@
+--TEST--
+Test preg_match() function : basic functionality 
+--FILE--
+<?php
+/* 
+ *  proto int preg_match(string pattern, string subject [, array subpatterns [, int flags [, int offset]]])
+ * Function is implemented in ext/pcre/php_pcre.c
+*/
+$string = 'Hello, world. [*], this is \ a string';
+var_dump(preg_match('/^[hH]ello,\s/', $string, $match1)); //finds "Hello, "
+var_dump($match1);
+var_dump(preg_match('/l^o,\s\w{5}/', $string, $match2, PREG_OFFSET_CAPTURE)); // tries to find "lo, world" at start of string
+var_dump($match2);
+var_dump(preg_match('/\[\*\],\s(.*)/', $string, $match3)); //finds "[*], this is \ a string";
+var_dump($match3);
+var_dump(preg_match('@\w{4}\s\w{2}\s\\\(?:\s.*)@', $string, $match4, PREG_OFFSET_CAPTURE, 14)); //finds "this is \ a string" (with non-capturing parentheses)
+var_dump($match4);
+var_dump(preg_match('/hello world/', $string, $match5)); //tries to find "hello world" (should be Hello, world)
+var_dump($match5);
+?>
+
+--EXPECTF--
+
+int(1)
+array(1) {
+  [0]=>
+  string(7) "Hello, "
+}
+int(0)
+array(0) {
+}
+int(1)
+array(2) {
+  [0]=>
+  string(23) "[*], this is \ a string"
+  [1]=>
+  string(18) "this is \ a string"
+}
+int(1)
+array(1) {
+  [0]=>
+  array(2) {
+    [0]=>
+    string(18) "this is \ a string"
+    [1]=>
+    int(19)
+  }
+}
+int(0)
+array(0) {
+}
+
diff --git a/ext/pcre/tests/preg_match_basic_002.phpt b/ext/pcre/tests/preg_match_basic_002.phpt
new file mode 100644
index 0000000..977a67e
--- /dev/null
+++ b/ext/pcre/tests/preg_match_basic_002.phpt
@@ -0,0 +1,23 @@
+--TEST--
+preg_match() single line match with multi-line input
+--FILE--
+<?php
+/* Prototype  : int preg_match  ( string $pattern  , string $subject  [, array &$matches  [, int $flags  [, int $offset  ]]] )
+ * Description: Perform a regular expression match
+ * Source code: ext/pcre/php_pcre.c
+ */
+ 
+$string = "My\nName\nIs\nStrange";
+preg_match("/M(.*)/", $string, $matches);
+
+var_dump($matches);
+?>
+===Done===
+--EXPECTF--
+array(2) {
+  [0]=>
+  string(2) "My"
+  [1]=>
+  string(1) "y"
+}
+===Done===
\ No newline at end of file
diff --git a/ext/pcre/tests/preg_match_basic_edit.phpt b/ext/pcre/tests/preg_match_basic_edit.phpt
new file mode 100644
index 0000000..bd469d3
--- /dev/null
+++ b/ext/pcre/tests/preg_match_basic_edit.phpt
@@ -0,0 +1,60 @@
+--TEST--
+Test preg_match() function : basic functionality 
+--FILE--
+<?php
+/* Prototype  : proto int preg_match(string pattern, string subject [, array subpatterns [, int flags [, int offset]]])
+ * Description: Perform a Perl-style regular expression match 
+ * Source code: ext/pcre/php_pcre.c
+ * Alias to functions: 
+*/
+
+
+$string = 'Hello, world. [*], this is \ a string';
+
+var_dump(preg_match('/^[hH]ello,\s/', $string, $match1));							//finds "Hello, "
+var_dump($match1);
+
+var_dump(preg_match('/l^o,\s\w{5}/', $string, $match2, PREG_OFFSET_CAPTURE));				// tries to find "lo, world" at start of string
+var_dump($match2);
+
+var_dump(preg_match('/\[\*\],\s(.*)/', $string, $match3));							//finds "[*], this is \ a string";
+var_dump($match3);
+
+var_dump(preg_match('@\w{4}\s\w{2}\s\\\(?:\s.*)@', $string, $match4, PREG_OFFSET_CAPTURE, 14));	//finds "this is \ a string" (with non-capturing parentheses)
+var_dump($match4);
+
+var_dump(preg_match('/hello world/', $string, $match5));							//tries to find "hello world" (should be Hello, world)
+var_dump($match5);
+?>
+
+--EXPECTF--
+
+int(1)
+array(1) {
+  [0]=>
+  string(7) "Hello, "
+}
+int(0)
+array(0) {
+}
+int(1)
+array(2) {
+  [0]=>
+  string(23) "[*], this is \ a string"
+  [1]=>
+  string(18) "this is \ a string"
+}
+int(1)
+array(1) {
+  [0]=>
+  array(2) {
+    [0]=>
+    string(18) "this is \ a string"
+    [1]=>
+    int(19)
+  }
+}
+int(0)
+array(0) {
+}
+
diff --git a/ext/pcre/tests/preg_match_error.phpt b/ext/pcre/tests/preg_match_error.phpt
new file mode 100644
index 0000000..ca1f128
--- /dev/null
+++ b/ext/pcre/tests/preg_match_error.phpt
@@ -0,0 +1,44 @@
+--TEST--
+Test preg_match() function : error conditions - wrong numbers of parameters
+--FILE--
+<?php
+/* 
+ *  proto int preg_match(string pattern, string subject [, array subpatterns [, int flags [, int offset]]])
+ * Function is implemented in ext/pcre/php_pcre.c
+*/
+echo "*** Testing preg_match() : error conditions ***\n";
+// Zero arguments
+echo "\n-- Testing preg_match() function with Zero arguments --\n";
+var_dump(preg_match());
+//Test preg_match with one more than the expected number of arguments
+echo "\n-- Testing preg_match() function with more than expected no. of arguments --\n";
+$pattern = '/\w/';
+$subject = 'string_val';
+$flags = PREG_OFFSET_CAPTURE;
+$offset = 10;
+$extra_arg = 10;
+var_dump(preg_match($pattern, $subject, $matches, $flags, $offset, $extra_arg));
+// Testing preg_match withone less than the expected number of arguments
+echo "\n-- Testing preg_match() function with less than expected no. of arguments --\n";
+$pattern = '/\w/';
+var_dump(preg_match($pattern));
+echo "Done"
+?>
+--EXPECTF--
+*** Testing preg_match() : error conditions ***
+
+-- Testing preg_match() function with Zero arguments --
+
+Warning: preg_match() expects at least 2 parameters, 0 given in %spreg_match_error.php on line %d
+bool(false)
+
+-- Testing preg_match() function with more than expected no. of arguments --
+
+Warning: preg_match() expects at most 5 parameters, 6 given in %spreg_match_error.php on line %d
+bool(false)
+
+-- Testing preg_match() function with less than expected no. of arguments --
+
+Warning: preg_match() expects at least 2 parameters, 1 given in %spreg_match_error.php on line %d
+bool(false)
+Done
diff --git a/ext/pcre/tests/preg_match_error1.phpt b/ext/pcre/tests/preg_match_error1.phpt
new file mode 100644
index 0000000..7630481
--- /dev/null
+++ b/ext/pcre/tests/preg_match_error1.phpt
@@ -0,0 +1,61 @@
+--TEST--
+Test preg_match() function : error conditions - bad regular expressions
+--FILE--
+<?php
+/* 
+ *  proto int preg_match(string pattern, string subject [, array subpatterns [, int flags [, int offset]]])
+ * Function is implemented in ext/pcre/php_pcre.c
+*/
+error_reporting(E_ALL&~E_NOTICE);
+/*
+* Testing how preg_match reacts to being passed the wrong type of regex argument
+*/
+echo "*** Testing preg_match() : error conditions ***\n";
+$regex_array = array('abcdef', //Regex without delimeter
+'/[a-zA-Z]', //Regex without closing delimeter
+'[a-zA-Z]/', //Regex without opening delimeter
+'/[a-zA-Z]/F', array('[a-z]', //Array of Regexes
+'[A-Z]', '[0-9]'), '/[a-zA-Z]/', //Regex string
+);
+$subject = 'this is a test';
+foreach($regex_array as $regex_value) {
+    print "\nArg value is $regex_value\n";
+    var_dump(preg_match($regex_value, $subject));
+}
+$regex_value = new stdclass(); //Object
+var_dump(preg_match($regex_value, $subject));
+?>
+--EXPECTF--
+
+*** Testing preg_match() : error conditions ***
+
+Arg value is abcdef
+
+Warning: preg_match(): Delimiter must not be alphanumeric or backslash in %spreg_match_error1.php on line %d
+bool(false)
+
+Arg value is /[a-zA-Z]
+
+Warning: preg_match(): No ending delimiter '/' found in %spreg_match_error1.php on line %d
+bool(false)
+
+Arg value is [a-zA-Z]/
+
+Warning: preg_match(): Unknown modifier '/' in %spreg_match_error1.php on line %d
+bool(false)
+
+Arg value is /[a-zA-Z]/F
+
+Warning: preg_match(): Unknown modifier 'F' in %spreg_match_error1.php on line %d
+bool(false)
+
+Arg value is Array
+
+Warning: preg_match() expects parameter 1 to be string, array given in %spreg_match_error1.php on line %d
+bool(false)
+
+Arg value is /[a-zA-Z]/
+int(1)
+
+Warning: preg_match() expects parameter 1 to be string, object given in %spreg_match_error1.php on line %d
+bool(false)
diff --git a/ext/pcre/tests/preg_match_error2.phpt b/ext/pcre/tests/preg_match_error2.phpt
new file mode 100644
index 0000000..f30fb48
--- /dev/null
+++ b/ext/pcre/tests/preg_match_error2.phpt
@@ -0,0 +1,38 @@
+--TEST--
+Test preg_match() function : error conditions - wrong arg types
+--FILE--
+<?php
+/* 
+ *  proto int preg_match(string pattern, string subject [, array subpatterns [, int flags [, int offset]]])
+ * Function is implemented in ext/pcre/php_pcre.c
+*/
+error_reporting(E_ALL&~E_NOTICE);
+/*
+* Testing how preg_match reacts to being passed the wrong type of subject argument
+*/
+echo "*** Testing preg_match() : error conditions ***\n";
+$regex = '/[a-zA-Z]/';
+$input = array('this is a string', array('this is', 'a subarray'),);
+foreach($input as $value) {
+    print "\nArg value is: $value\n";
+    var_dump(preg_match($regex, $value));
+}
+$value = new stdclass(); //Object
+var_dump(preg_match($regex, $value));
+echo "Done";
+?>
+--EXPECTF--
+
+*** Testing preg_match() : error conditions ***
+
+Arg value is: this is a string
+int(1)
+
+Arg value is: Array
+
+Warning: preg_match() expects parameter 2 to be string, array given in %spreg_match_error2.php on line %d
+bool(false)
+
+Warning: preg_match() expects parameter 2 to be string, object given in %spreg_match_error2.php on line %d
+bool(false)
+Done
\ No newline at end of file
diff --git a/ext/pcre/tests/preg_match_variation1.phpt b/ext/pcre/tests/preg_match_variation1.phpt
new file mode 100644
index 0000000..a289ee4
--- /dev/null
+++ b/ext/pcre/tests/preg_match_variation1.phpt
@@ -0,0 +1,22 @@
+--TEST--
+Test preg_match() function : variation
+--FILE--
+<?php
+/* 
+ *  proto int preg_match(string pattern, string subject [, array subpatterns [, int flags [, int offset]]])
+ * Function is implemented in ext/pcre/php_pcre.c
+*/
+
+//test passing in the same variable where 1 is by value, the other is a different
+//type and by reference so should be updated to the new type.
+$string = "-1";
+preg_match('/[\-\+]?[0-9\.]*/', $string, $string);
+var_dump($string);
+?>
+===Done===
+--EXPECT--
+array(1) {
+  [0]=>
+  string(2) "-1"
+}
+===Done===
diff --git a/ext/pcre/tests/preg_quote_basic.phpt b/ext/pcre/tests/preg_quote_basic.phpt
new file mode 100644
index 0000000..c78f566
--- /dev/null
+++ b/ext/pcre/tests/preg_quote_basic.phpt
@@ -0,0 +1,25 @@
+--TEST--
+Test preg_quote() function : basic functionality 
+--FILE--
+<?php
+/*
+* proto string preg_quote(string str [, string delim_char])
+* Function is implemented in ext/pcre/php_pcre.c
+*/
+$string_before = '/this *-has \ metacharacters^ in $';
+print "\$string_before looks like: $string_before\n"; //$string_before is printed as is written
+$string_after = preg_quote($string_before, '/');
+print "\$string_after looks like: $string_after, with metacharacters and / (set as delimiter) escaped\n"; //$string_after is printed with metacharacters escaped.
+$string1 = 'testing - /this *-has \ metacharacters^ in $ should   work';
+var_dump(preg_match('/^[tT]\w{6} - ' . preg_quote($string_before, '/') . ' [a-z]*\s*work$/', $string1, $matches1));
+var_dump($matches1);
+?>
+--EXPECT--
+
+$string_before looks like: /this *-has \ metacharacters^ in $
+$string_after looks like: \/this \*\-has \\ metacharacters\^ in \$, with metacharacters and / (set as delimiter) escaped
+int(1)
+array(1) {
+  [0]=>
+  string(58) "testing - /this *-has \ metacharacters^ in $ should   work"
+}
\ No newline at end of file
diff --git a/ext/pcre/tests/preg_quote_error.phpt b/ext/pcre/tests/preg_quote_error.phpt
new file mode 100644
index 0000000..30b832d
--- /dev/null
+++ b/ext/pcre/tests/preg_quote_error.phpt
@@ -0,0 +1,33 @@
+--TEST--
+Test preg_quote() function : error conditions  - wrong numbers of parameters 
+--FILE--
+<?php
+/*
+* proto string preg_quote(string str [, string delim_char])
+* Function is implemented in ext/pcre/php_pcre.c
+*/
+echo "*** Testing preg_quote() : error conditions ***\n";
+// Zero arguments
+echo "\n-- Testing preg_quote() function with Zero arguments --\n";
+var_dump(preg_quote());
+//Test preg_quote with one more than the expected number of arguments
+echo "\n-- Testing preg_quote() function with more than expected no. of arguments --\n";
+$str = 'string_val';
+$delim_char = '/';
+$extra_arg = 10;
+var_dump(preg_quote($str, $delim_char, $extra_arg));
+echo "Done"
+?>
+--EXPECTF--
+*** Testing preg_quote() : error conditions ***
+
+-- Testing preg_quote() function with Zero arguments --
+
+Warning: preg_quote() expects at least 1 parameter, 0 given in %spreg_quote_error.php on line %d
+NULL
+
+-- Testing preg_quote() function with more than expected no. of arguments --
+
+Warning: preg_quote() expects at most 2 parameters, 3 given in %spreg_quote_error.php on line %d
+NULL
+Done
diff --git a/ext/pcre/tests/preg_quote_error1.phpt b/ext/pcre/tests/preg_quote_error1.phpt
new file mode 100644
index 0000000..a02c836
--- /dev/null
+++ b/ext/pcre/tests/preg_quote_error1.phpt
@@ -0,0 +1,36 @@
+--TEST--
+Test preg_quote() function : error conditions - wrong arg types
+--FILE--
+<?php
+/*
+* proto string preg_quote(string str [, string delim_char])
+* Function is implemented in ext/pcre/php_pcre.c
+*/
+error_reporting(E_ALL&~E_NOTICE);
+/*
+* Testing how preg_quote reacts to being passed the wrong type of input argument
+*/
+echo "*** Testing preg_quote() : error conditions ***\n";
+$input = array('this is a string', array('this is', 'a subarray'),);
+foreach($input as $value) {
+    print "\nArg value is: $value\n";
+    var_dump(preg_quote($value));
+}
+$value = new stdclass(); //Object
+var_dump(preg_quote($value));
+echo "Done";
+?>
+--EXPECTF--
+*** Testing preg_quote() : error conditions ***
+
+Arg value is: this is a string
+string(16) "this is a string"
+
+Arg value is: Array
+
+Warning: preg_quote() expects parameter 1 to be string, array given in %spreg_quote_error1.php on line %d
+NULL
+
+Warning: preg_quote() expects parameter 1 to be string, object given in %spreg_quote_error1.php on line %d
+NULL
+Done
\ No newline at end of file
diff --git a/ext/pcre/tests/preg_replace.phpt b/ext/pcre/tests/preg_replace.phpt
new file mode 100644
index 0000000..f7b5f74
--- /dev/null
+++ b/ext/pcre/tests/preg_replace.phpt
@@ -0,0 +1,25 @@
+--TEST--
+preg_replace()
+--FILE--
+<?php
+
+var_dump(preg_replace('{{\D+}}', 'x', '{abcd}'));
+var_dump(preg_replace('{{\D+}}', 'ddd', 'abcd'));
+
+var_dump(preg_replace('/(ab)(c)(d)(e)(f)(g)(h)(i)(j)(k)/', 'a${1}2$103', 'zabcdefghijkl'));
+
+var_dump(preg_replace_callback('//e', '', ''));
+
+var_dump(preg_replace_callback('//e', 'strtolower', ''));
+
+?>
+--EXPECTF--
+string(1) "x"
+string(4) "abcd"
+string(8) "zaab2k3l"
+
+Warning: preg_replace_callback(): Requires argument 2, '', to be a valid callback in %spreg_replace.php on line 8
+string(0) ""
+
+Warning: preg_replace_callback(): Modifier /e cannot be used with replacement callback in %spreg_replace.php on line 10
+NULL
diff --git a/ext/pcre/tests/preg_replace2.phpt b/ext/pcre/tests/preg_replace2.phpt
new file mode 100644
index 0000000..4a191f3
--- /dev/null
+++ b/ext/pcre/tests/preg_replace2.phpt
@@ -0,0 +1,48 @@
+--TEST--
+preg_replace()
+--SKIPIF--
+<?php
+if (@preg_match('/./u', '') === false) {
+	die('skip no utf8 support in PCRE library');
+}
+?>
+--FILE--
+<?php
+
+var_dump(preg_replace('', array(), ''));
+
+var_dump(preg_replace(array('/\da(.)/ui', '@..@'), '$1', '12Abc'));
+var_dump(preg_replace(array('/\da(.)/ui', '@(.)@'), '$1', array('x','a2aA', '1av2Ab')));
+
+
+var_dump(preg_replace(array('/[\w]+/'), array('$'), array('xyz', 'bdbd')));
+var_dump(preg_replace(array('/\s+/', '~[b-d]~'), array('$'), array('x y', 'bd bc')));
+
+echo "==done==\n";
+
+?>
+--EXPECTF--
+Warning: preg_replace(): Parameter mismatch, pattern is a string while replacement is an array in %spreg_replace2.php on line 3
+bool(false)
+string(1) "c"
+array(3) {
+  [0]=>
+  string(1) "x"
+  [1]=>
+  string(2) "aA"
+  [2]=>
+  string(2) "vb"
+}
+array(2) {
+  [0]=>
+  string(1) "$"
+  [1]=>
+  string(1) "$"
+}
+array(2) {
+  [0]=>
+  string(3) "x$y"
+  [1]=>
+  string(1) "$"
+}
+==done==
diff --git a/ext/pcre/tests/preg_replace_basic.phpt b/ext/pcre/tests/preg_replace_basic.phpt
new file mode 100644
index 0000000..33fb2d4
--- /dev/null
+++ b/ext/pcre/tests/preg_replace_basic.phpt
@@ -0,0 +1,25 @@
+--TEST--
+Test preg_replace() function : basic functionality 
+--FILE--
+<?php
+/*
+* proto string preg_replace(mixed regex, mixed replace, mixed subject [, int limit [, count]])
+* Function is implemented in ext/pcre/php_pcre.c
+*/
+$string = '123456789 - Hello, world -           This is a string.';
+var_dump($string);
+var_dump(preg_replace('<- This is a string$>', 'This shouldn\'t work', $string)); //tries to find '- This is a string' at the end of a string but can't so replaces nothing and prints the unchanged $string.
+var_dump(preg_replace('<[0-35-9]>', '4', $string)); //finds any number that's not 4 and replaces it with a 4 ('444444444')
+var_dump(preg_replace('<\b[hH]\w{2,4}>', 'Bonjour', $string)); //finds h or H at the beginning of a word followed by 2-4 characters and replaces it with Bonjour (i.e. Hello -> Bonjour) (was finding the 'his' in This and replacing it)
+var_dump(preg_replace('<(\w)\s*-\s*(\w)>', '\\1. \\2', $string)); //finds dashes with an indefinate amount of whitespace around them and replaces them with a full stop precedeby no spaces and followed by one space
+var_dump(preg_replace('<(^[a-z]\w+)@(\w+)\.(\w+)\.([a-z]{2,}$)>', '\\1 at \\2 dot \\3 dot \\4', 'josmessa@uk.ibm.com')); //finds the e-mail address and replaces the @ and . with "at" and "dot" (uses backreferences) ('josmessa at uk dot ibm dot com')
+
+?>
+--EXPECT--
+
+string(54) "123456789 - Hello, world -           This is a string."
+string(54) "123456789 - Hello, world -           This is a string."
+string(54) "444444444 - Hello, world -           This is a string."
+string(56) "123456789 - Bonjour, world -           This is a string."
+string(42) "123456789. Hello, world. This is a string."
+string(30) "josmessa at uk dot ibm dot com"
diff --git a/ext/pcre/tests/preg_replace_callback.phpt b/ext/pcre/tests/preg_replace_callback.phpt
new file mode 100644
index 0000000..0b0bc27
--- /dev/null
+++ b/ext/pcre/tests/preg_replace_callback.phpt
@@ -0,0 +1,25 @@
+--TEST--
+preg_replace_callback()
+--FILE--
+<?php
+$input = "plain [indent] deep [indent] [abcd]deeper[/abcd] [/indent] deep [/indent] plain"; 
+
+function parseTagsRecursive($input)
+{
+    
+    $regex = '#\[indent]((?:[^[]|\[(?!/?indent])|(?R))+)\[/indent]#';
+
+    if (is_array($input)) {
+        $input = '<div style="margin-left: 10px">'.$input[1].'</div>';
+    }
+
+    return preg_replace_callback($regex, 'parseTagsRecursive', $input);
+}
+
+$output = parseTagsRecursive($input);
+
+echo $output, "\n";
+
+?>
+--EXPECT--
+plain <div style="margin-left: 10px"> deep <div style="margin-left: 10px"> [abcd]deeper[/abcd] </div> deep </div> plain
diff --git a/ext/pcre/tests/preg_replace_callback2.phpt b/ext/pcre/tests/preg_replace_callback2.phpt
new file mode 100644
index 0000000..7989509
--- /dev/null
+++ b/ext/pcre/tests/preg_replace_callback2.phpt
@@ -0,0 +1,39 @@
+--TEST--
+preg_replace_callback() 2
+--FILE--
+<?php
+
+function f() {
+	throw new Exception();
+}
+
+try {
+var_dump(preg_replace_callback('/\w/', 'f', 'z'));
+} catch(Exception $e) {}
+
+function g($x) {
+	return "'$x[0]'";
+}
+
+var_dump(preg_replace_callback('@\b\w{1,2}\b@', 'g', array('a b3 bcd', 'v' => 'aksfjk', 12 => 'aa bb')));
+
+var_dump(preg_replace_callback('~\A.~', 'g', array(array('xyz'))));
+
+var_dump(preg_replace_callback('~\A.~', create_function('$m', 'return strtolower($m[0]);'), 'ABC'));
+?>
+--EXPECTF--
+array(3) {
+  [0]=>
+  string(12) "'a' 'b3' bcd"
+  ["v"]=>
+  string(6) "aksfjk"
+  [12]=>
+  string(9) "'aa' 'bb'"
+}
+
+Notice: Array to string conversion in %spreg_replace_callback2.php on line 17
+array(1) {
+  [0]=>
+  string(7) "'A'rray"
+}
+string(3) "aBC"
diff --git a/ext/pcre/tests/preg_replace_callback3.phpt b/ext/pcre/tests/preg_replace_callback3.phpt
new file mode 100644
index 0000000..30799e2
--- /dev/null
+++ b/ext/pcre/tests/preg_replace_callback3.phpt
@@ -0,0 +1,44 @@
+--TEST--
+preg_replace_callback() 3
+--FILE--
+<?php
+
+var_dump(preg_replace_callback());
+var_dump(preg_replace_callback(1));
+var_dump(preg_replace_callback(1,2));
+var_dump(preg_replace_callback(1,2,3));
+var_dump(preg_replace_callback(1,2,3,4));
+$a = 5;
+var_dump(preg_replace_callback(1,2,3,4,$a));
+$a = "";
+var_dump(preg_replace_callback("","","","",$a));
+$a = array();
+var_dump(preg_replace_callback($a,$a,$a,$a,$a));
+
+echo "Done\n";
+?>
+--EXPECTF--	
+Warning: preg_replace_callback() expects at least 3 parameters, 0 given in %s on line %d
+NULL
+
+Warning: preg_replace_callback() expects at least 3 parameters, 1 given in %s on line %d
+NULL
+
+Warning: preg_replace_callback() expects at least 3 parameters, 2 given in %s on line %d
+NULL
+
+Warning: preg_replace_callback(): Requires argument 2, '2', to be a valid callback in %s on line %d
+int(3)
+
+Warning: preg_replace_callback(): Requires argument 2, '2', to be a valid callback in %s on line %d
+int(3)
+
+Warning: preg_replace_callback(): Requires argument 2, '2', to be a valid callback in %s on line %d
+int(3)
+
+Warning: preg_replace_callback() expects parameter 4 to be long, string given in %s on line %d
+NULL
+
+Warning: preg_replace_callback() expects parameter 4 to be long, array given in %s on line %d
+NULL
+Done
diff --git a/ext/pcre/tests/preg_replace_callback_basic.phpt b/ext/pcre/tests/preg_replace_callback_basic.phpt
new file mode 100644
index 0000000..01d290a
--- /dev/null
+++ b/ext/pcre/tests/preg_replace_callback_basic.phpt
@@ -0,0 +1,33 @@
+--TEST--
+Test preg_replace_callback() function : basic functionality 
+--FILE--
+<?php
+/*
+* proto string preg_replace(mixed regex, mixed replace, mixed subject [, int limit [, count]])
+* Function is implemented in ext/pcre/php_pcre.c
+*/
+/*
+* Basic test for preg_replace_callback
+*/
+$replacement = array('zero', 'one', 'two', 'three', 'four', 'five', 'six', 'seven', 'eight', 'nine'); //array will have the default key values (0-9) and each value is the corresponding key written in words.
+function integer_word($matches) {
+    global $replacement;
+    return $replacement[$matches[0]]; //all examples will be looking for an integer value, if one is found it will be stored in $matches[0] which corresponds to a key in the $replacements array
+    
+}
+$subject1 = 'there are 7 words in this sentence.';
+$new_subject1 = preg_replace_callback('/\d/', "integer_word", $subject1);
+print "$new_subject1 \n";
+$subject2 = '1 2 3 4 is now written in words';
+$new_subject2 = preg_replace_callback('/\d/', "integer_word", $subject2, 3); //limits to three replacements
+print "$new_subject2 \n";
+$subject3 = 'there are no numbers in this string';
+$new_subject3 = preg_replace_callback('/\d/', "integer_word", $subject3, 5, $count); //limites to five replacements and counts the number of replacements made ands stores in $count variable
+print "$new_subject3 \n";
+print $count;
+?>
+--EXPECTF--
+there are seven words in this sentence. 
+one two three 4 is now written in words 
+there are no numbers in this string 
+0
diff --git a/ext/pcre/tests/preg_replace_callback_error.phpt b/ext/pcre/tests/preg_replace_callback_error.phpt
new file mode 100644
index 0000000..9371fcf
--- /dev/null
+++ b/ext/pcre/tests/preg_replace_callback_error.phpt
@@ -0,0 +1,48 @@
+--TEST--
+Test preg_replace_callback() function : error 
+--FILE--
+<?php
+/*
+* proto string preg_replace(mixed regex, mixed replace, mixed subject [, int limit [, count]])
+* Function is implemented in ext/pcre/php_pcre.c
+*/
+echo "***Testing preg_replace_callback() : error conditions***\n";
+//Zero arguments
+echo "\n-- Testing preg_replace_callback() function with Zero arguments --\n";
+var_dump(preg_replace_callback());
+//Test preg_replace_callback() with one more than the expected number of arguments
+echo "\n-- Testing preg_replace_callback() function with more than expected no. of arguments --\n";
+$replacement = array('zero', 'one', 'two', 'three', 'four', 'five', 'six', 'seven', 'eight', 'nine');
+function integer_word($matches) {
+    global $replacement;
+    return $replacement[$matches[0]];
+}
+$regex = '/\d/';
+$subject = 'there are 7 words in this sentence.';
+$limit = 10;
+$extra_arg = 10;
+var_dump(preg_replace_callback($regex, 'integer_word', $subject, $limit, $count, $extra_arg));
+//Testing preg_replace_callback() with one less than the expected number of arguments
+echo "\n-- Testing preg_replace_callback() function with less than expected no. of arguments --\n";
+$regex = '/\d/';
+var_dump(preg_replace_callback($regex, 'integer word'));
+echo "Done";
+?>
+--EXPECTF--
+***Testing preg_replace_callback() : error conditions***
+
+-- Testing preg_replace_callback() function with Zero arguments --
+
+Warning: preg_replace_callback() expects at least 3 parameters, 0 given in %s on line %d
+NULL
+
+-- Testing preg_replace_callback() function with more than expected no. of arguments --
+
+Warning: preg_replace_callback() expects at most 5 parameters, 6 given in %s on line %d
+NULL
+
+-- Testing preg_replace_callback() function with less than expected no. of arguments --
+
+Warning: preg_replace_callback() expects at least 3 parameters, 2 given in %s on line %d
+NULL
+Done
diff --git a/ext/pcre/tests/preg_replace_callback_error1.phpt b/ext/pcre/tests/preg_replace_callback_error1.phpt
new file mode 100644
index 0000000..a00b97c
--- /dev/null
+++ b/ext/pcre/tests/preg_replace_callback_error1.phpt
@@ -0,0 +1,59 @@
+--TEST--
+Test preg_replace_callback() function : error 
+--FILE--
+<?php
+/*
+* proto string preg_replace(mixed regex, mixed replace, mixed subject [, int limit [, count]])
+* Function is implemented in ext/pcre/php_pcre.c
+*/
+error_reporting(E_ALL&~E_NOTICE);
+/*
+* Testing how preg_replace_callback reacts to being passed the wrong type of regex argument
+*/
+echo "*** Testing preg_replace_callback() : error conditions ***\n";
+$regex_array = array('abcdef', //Regex without delimiters
+'/[a-zA-Z]', //Regex without closing delimiter
+'[a-zA-Z]/', //Regex without opening delimiter
+'/[a-zA-Z]/F', array('[a-z]', //Array of Regexes
+'[A-Z]', '[0-9]'), '/[a-zA-Z]/'); //Regex string
+$replacement = array('zero', 'one', 'two', 'three', 'four', 'five', 'six', 'seven', 'eight', 'nine');
+function integer_word($matches) {
+    global $replacement;
+    return $replacement[$matches[0]];
+}
+$subject = 'number 1.';
+foreach($regex_array as $regex_value) {
+    print "\nArg value is $regex_value\n";
+    var_dump(preg_replace_callback($regex_value, 'integer_word', $subject));
+}
+?>
+===Done===
+--EXPECTF--
+*** Testing preg_replace_callback() : error conditions ***
+
+Arg value is abcdef
+
+Warning: preg_replace_callback(): Delimiter must not be alphanumeric or backslash in %s on line %d
+NULL
+
+Arg value is /[a-zA-Z]
+
+Warning: preg_replace_callback(): No ending delimiter '/' found in %s on line %d
+NULL
+
+Arg value is [a-zA-Z]/
+
+Warning: preg_replace_callback(): Unknown modifier '/' in %s on line %d
+NULL
+
+Arg value is /[a-zA-Z]/F
+
+Warning: preg_replace_callback(): Unknown modifier 'F' in %s on line %d
+NULL
+
+Arg value is Array
+string(9) "number 1."
+
+Arg value is /[a-zA-Z]/
+string(3) " 1."
+===Done===
\ No newline at end of file
diff --git a/ext/pcre/tests/preg_replace_edit_basic.phpt b/ext/pcre/tests/preg_replace_edit_basic.phpt
new file mode 100644
index 0000000..97350e7
--- /dev/null
+++ b/ext/pcre/tests/preg_replace_edit_basic.phpt
@@ -0,0 +1,39 @@
+--TEST--
+Test preg_replace() function : basic 
+--FILE--
+<?php
+/* Prototype  : proto string preg_replace(mixed regex, mixed replace, mixed subject [, int limit [, count]])
+ * Description: Perform Perl-style regular expression replacement. 
+ * Source code: ext/pcre/php_pcre.c
+ * Alias to functions: 
+*/
+
+$string = '123456789 - Hello, world -           This is a string.';
+var_dump($string);
+
+var_dump(preg_replace('<- This is a string$>',
+                      'This shouldn\'t work', $string));				//tries to find '- This is a string' at the end of a string but can't so replaces nothing and prints the unchanged $string.
+
+var_dump(preg_replace('<[0-35-9]>', 
+                      '4', $string,               					//finds any number that's not 4 and replaces it with a 4
+			    '5', $count));							//limits to 5 replacements returns 444444789
+var_dump($count);											//counts the number of replacements made (5)
+
+
+var_dump(preg_replace('<\b[hH]\w{2,4}>',
+                      'Bonjour', $string));						//finds h or H at the beginning of a word followed by 2-4 characters and replaces it with Bonjour (i.e. Hello -> Bonjour) (was finding the 'his' in This and replacing it)
+
+var_dump(preg_replace('<(\w)\s*-\s*(\w)>',
+                      '\\1. \\2', $string));						//finds dashes with an indefinate amount of whitespace around them and replaces them with a full stop precedeby no spaces and followed by one space
+
+var_dump(preg_replace('<(^[a-z]\w+)@(\w+)\.(\w+)\.([a-z]{2,}$)>', 
+                      '\\1 at \\2 dot \\3 dot \\4', 'josmessa@uk.ibm.com'));	//finds the e-mail address and replaces the @ and . with "at" and "dot" (uses backreferences) ('josmessa at uk dot ibm dot com')
+?>
+--EXPECTF--
+string(54) "123456789 - Hello, world -           This is a string."
+string(54) "123456789 - Hello, world -           This is a string."
+string(54) "444444789 - Hello, world -           This is a string."
+int(5)
+string(56) "123456789 - Bonjour, world -           This is a string."
+string(42) "123456789. Hello, world. This is a string."
+string(30) "josmessa at uk dot ibm dot com"
diff --git a/ext/pcre/tests/preg_replace_error.phpt b/ext/pcre/tests/preg_replace_error.phpt
new file mode 100644
index 0000000..fc3427d
--- /dev/null
+++ b/ext/pcre/tests/preg_replace_error.phpt
@@ -0,0 +1,45 @@
+--TEST--
+Test preg_replace() function : error - incorrect number of parameters
+--FILE--
+<?php
+/*
+* proto string preg_replace(mixed regex, mixed replace, mixed subject [, int limit [, count]])
+* Function is implemented in ext/pcre/php_pcre.c
+*/
+echo "*** Testing preg_replace() : error conditions ***\n";
+//Zero arguments
+echo "\n-- Testing preg_replace() function with zero arguments --\n";
+var_dump(preg_replace());
+//Test preg_replace() with one more than the expected number of arguments
+echo "\n-- Testing preg_replace() function with more than expected no. of arguments --\n";
+$regex = '/\w/';
+$replace = '1';
+$subject = 'string_val';
+$limit = 10;
+$extra_arg = 10;
+var_dump(preg_replace($regex, $replace, $subject, $limit, $count, $extra_arg));
+//Testing preg_replace() with one less than the expected number of arguments
+echo "\n-- Testing preg_replace() function with less than expected no. of arguments --\n";
+$regex = '/\w/';
+$replace = '1';
+var_dump(preg_replace($regex, $replace));
+echo "Done"
+?>
+--EXPECTF--
+*** Testing preg_replace() : error conditions ***
+
+-- Testing preg_replace() function with zero arguments --
+
+Warning: preg_replace() expects at least 3 parameters, 0 given in %s on line %d
+NULL
+
+-- Testing preg_replace() function with more than expected no. of arguments --
+
+Warning: preg_replace() expects at most 5 parameters, 6 given in %s on line %d
+NULL
+
+-- Testing preg_replace() function with less than expected no. of arguments --
+
+Warning: preg_replace() expects at least 3 parameters, 2 given in %s on line %d
+NULL
+Done
diff --git a/ext/pcre/tests/preg_replace_error1.phpt b/ext/pcre/tests/preg_replace_error1.phpt
new file mode 100644
index 0000000..7ddfcfd
--- /dev/null
+++ b/ext/pcre/tests/preg_replace_error1.phpt
@@ -0,0 +1,59 @@
+--TEST--
+Test preg_replace() function : error - bad regular expressions
+--FILE--
+<?php
+/*
+* proto string preg_replace(mixed regex, mixed replace, mixed subject [, int limit [, count]])
+* Function is implemented in ext/pcre/php_pcre.c
+*/
+error_reporting(E_ALL&~E_NOTICE);
+/*
+* Testing how preg_replace reacts to being passed the wrong type of regex argument
+*/
+echo "*** Testing preg_replace() : error conditions***\n";
+$regex_array = array('abcdef', //Regex without delimeter
+'/[a-zA-Z]', //Regex without closing delimeter
+'[a-zA-Z]/', //Regex without opening delimeter
+'/[a-zA-Z]/F', array('[a-z]', //Array of Regexes
+'[A-Z]', '[0-9]'), '/[a-zA-Z]/', //Regex string
+);
+$replace = 1;
+$subject = 'a';
+foreach($regex_array as $regex_value) {
+    print "\nArg value is $regex_value\n";
+    var_dump(preg_replace($regex_value, $replace, $subject));
+}
+$regex_value = new stdclass(); //Object
+var_dump(preg_replace($regex_value, $replace, $subject));
+?>
+--EXPECTF--
+*** Testing preg_replace() : error conditions***
+
+Arg value is abcdef
+
+Warning: preg_replace(): Delimiter must not be alphanumeric or backslash in %spreg_replace_error1.php on line %d
+NULL
+
+Arg value is /[a-zA-Z]
+
+Warning: preg_replace(): No ending delimiter '/' found in %spreg_replace_error1.php on line %d
+NULL
+
+Arg value is [a-zA-Z]/
+
+Warning: preg_replace(): Unknown modifier '/' in %spreg_replace_error1.php on line %d
+NULL
+
+Arg value is /[a-zA-Z]/F
+
+Warning: preg_replace(): Unknown modifier 'F' in %spreg_replace_error1.php on line %d
+NULL
+
+Arg value is Array
+string(1) "a"
+
+Arg value is /[a-zA-Z]/
+string(1) "1"
+
+Catchable fatal error: Object of class stdClass could not be converted to string in %spreg_replace_error1.php on line %d
+
diff --git a/ext/pcre/tests/preg_replace_error2.phpt b/ext/pcre/tests/preg_replace_error2.phpt
new file mode 100644
index 0000000..bf5d3e0
--- /dev/null
+++ b/ext/pcre/tests/preg_replace_error2.phpt
@@ -0,0 +1,37 @@
+--TEST--
+Test preg_replace() function : error conditions - wrong arg types
+--FILE--
+<?php
+/*
+* proto string preg_replace(mixed regex, mixed replace, mixed subject [, int limit [, count]])
+* Function is implemented in ext/pcre/php_pcre.c
+*/
+error_reporting(E_ALL&~E_NOTICE);
+/*
+* Testing how preg_replace reacts to being passed the wrong type of replacement argument
+*/
+echo "*** Testing preg_replace() : error conditions ***\n";
+$regex = '/[a-zA-Z]/';
+$replace = array('this is a string', array('this is', 'a subarray'),);
+$subject = 'test';
+foreach($replace as $value) {
+    print "\nArg value is: $value\n";
+    var_dump(preg_replace($regex, $value, $subject));
+}
+$value = new stdclass(); //Object
+var_dump(preg_replace($regex, $value, $subject));
+echo "Done";
+?>
+--EXPECTF--
+*** Testing preg_replace() : error conditions ***
+
+Arg value is: this is a string
+string(64) "this is a stringthis is a stringthis is a stringthis is a string"
+
+Arg value is: Array
+
+Warning: preg_replace(): Parameter mismatch, pattern is a string while replacement is an array in %spreg_replace_error2.php on line %d
+bool(false)
+
+Catchable fatal error: Object of class stdClass could not be converted to string in %spreg_replace_error2.php on line %d
+
diff --git a/ext/pcre/tests/preg_replace_variation1.phpt b/ext/pcre/tests/preg_replace_variation1.phpt
new file mode 100644
index 0000000..ac79e0b
--- /dev/null
+++ b/ext/pcre/tests/preg_replace_variation1.phpt
@@ -0,0 +1,17 @@
+--TEST--
+Test preg_replace() function : variation both arguments are arrays
+--FILE--
+<?php
+/*
+* proto string preg_replace(mixed regex, mixed replace, mixed subject [, int limit [, count]])
+* Function is implemented in ext/pcre/php_pcre.c
+*/
+/*
+* Testing preg_replace when the regex and the replacement are both arrays.
+*/
+$string = 'This is a string. It contains numbers (0-9) as well as parentheses and some other things!';
+$new_string = preg_replace(array('/\b\w{1}s/', '/(\d{1})-(\d{1})/', '/[\(!\)]/'), array('test', '$1 to $2', '*'), $string);
+print $new_string;
+?>
+--EXPECTF--
+This test a string. It contains numbers *0 to 9* test well test parentheses and some other things*
diff --git a/ext/pcre/tests/preg_split_basic.phpt b/ext/pcre/tests/preg_split_basic.phpt
new file mode 100644
index 0000000..e94a94f
--- /dev/null
+++ b/ext/pcre/tests/preg_split_basic.phpt
@@ -0,0 +1,75 @@
+--TEST--
+Test preg_split() function : basic functionality 
+--FILE--
+<?php
+/*
+* proto array preg_split(string pattern, string subject [, int limit [, int flags]])
+* Function is implemented in ext/pcre/php_pcre.c
+*/
+$string = 'this is a_list: value1, Test__, string; Hello, world!_(parentheses)';
+var_dump(preg_split('/[:,;\(\)]/', $string, -1, PREG_SPLIT_NO_EMPTY)); //parts of $string seperated by : , ; ( or ) are put into an array.
+var_dump(preg_split('/:\s*(\w*,*\s*)+;/', $string)); //all text between : and ; is removed
+var_dump(preg_split('/(\(|\))/', $string, -1, PREG_SPLIT_DELIM_CAPTURE|PREG_SPLIT_NO_EMPTY)); //all text before (parentheses) is put into first element, ( into second, "parentheses" into third and ) into fourth.
+var_dump(preg_split('/NAME/i', $string)); //tries to find NAME regardless of case in $string (can't split it so just returns how string as first element)
+var_dump(preg_split('/\w/', $string, -1, PREG_SPLIT_NO_EMPTY)); //every character (including whitespace) is put into an array element
+
+?>
+--EXPECT--
+array(7) {
+  [0]=>
+  string(14) "this is a_list"
+  [1]=>
+  string(7) " value1"
+  [2]=>
+  string(7) " Test__"
+  [3]=>
+  string(7) " string"
+  [4]=>
+  string(6) " Hello"
+  [5]=>
+  string(8) " world!_"
+  [6]=>
+  string(11) "parentheses"
+}
+array(2) {
+  [0]=>
+  string(14) "this is a_list"
+  [1]=>
+  string(28) " Hello, world!_(parentheses)"
+}
+array(4) {
+  [0]=>
+  string(54) "this is a_list: value1, Test__, string; Hello, world!_"
+  [1]=>
+  string(1) "("
+  [2]=>
+  string(11) "parentheses"
+  [3]=>
+  string(1) ")"
+}
+array(1) {
+  [0]=>
+  string(67) "this is a_list: value1, Test__, string; Hello, world!_(parentheses)"
+}
+array(10) {
+  [0]=>
+  string(1) " "
+  [1]=>
+  string(1) " "
+  [2]=>
+  string(2) ": "
+  [3]=>
+  string(2) ", "
+  [4]=>
+  string(2) ", "
+  [5]=>
+  string(2) "; "
+  [6]=>
+  string(2) ", "
+  [7]=>
+  string(1) "!"
+  [8]=>
+  string(1) "("
+  [9]=>
+  string(1) ")"
+}
diff --git a/ext/pcre/tests/preg_split_error.phpt b/ext/pcre/tests/preg_split_error.phpt
new file mode 100644
index 0000000..960b286
--- /dev/null
+++ b/ext/pcre/tests/preg_split_error.phpt
@@ -0,0 +1,44 @@
+--TEST--
+Test preg_split() function : error conditions - incorrect number of parameters
+--FILE--
+<?php
+/*
+* proto array preg_split(string pattern, string subject [, int limit [, int flags]])
+* Function is implemented in ext/pcre/php_pcre.c
+*/
+echo "*** Testing preg_split() : error conditions ***\n";
+// Zero arguments
+echo "\n-- Testing preg_split() function with Zero arguments --\n";
+var_dump(preg_split());
+//Test preg_split with one more than the expected number of arguments
+echo "\n-- Testing preg_split() function with more than expected no. of arguments --\n";
+$pattern = '/_/';
+$subject = 'string_val';
+$limit = 10;
+$flags = PREG_SPLIT_NO_EMPTY;
+$extra_arg = 10;
+var_dump(preg_split($pattern, $subject, $limit, $flags, $extra_arg));
+// Testing preg_split withone less than the expected number of arguments
+echo "\n-- Testing preg_split() function with less than expected no. of arguments --\n";
+$pattern = '/\./';
+var_dump(preg_split($pattern));
+echo "Done"
+?>
+--EXPECTF--
+*** Testing preg_split() : error conditions ***
+
+-- Testing preg_split() function with Zero arguments --
+
+Warning: preg_split() expects at least 2 parameters, 0 given in %spreg_split_error.php on line %d
+bool(false)
+
+-- Testing preg_split() function with more than expected no. of arguments --
+
+Warning: preg_split() expects at most 4 parameters, 5 given in %spreg_split_error.php on line %d
+bool(false)
+
+-- Testing preg_split() function with less than expected no. of arguments --
+
+Warning: preg_split() expects at least 2 parameters, 1 given in %spreg_split_error.php on line %d
+bool(false)
+Done
\ No newline at end of file
diff --git a/ext/pcre/tests/preg_split_error1.phpt b/ext/pcre/tests/preg_split_error1.phpt
new file mode 100644
index 0000000..79942a9
--- /dev/null
+++ b/ext/pcre/tests/preg_split_error1.phpt
@@ -0,0 +1,67 @@
+--TEST--
+Test preg_split() function : error conditions - bad regular expressions
+--FILE--
+<?php
+/*
+* proto array preg_split(string pattern, string subject [, int limit [, int flags]])
+* Function is implemented in ext/pcre/php_pcre.c
+*/
+error_reporting(E_ALL&~E_NOTICE);
+/*
+* Testing how preg_split reacts to being passed the wrong type of regex argument
+*/
+echo "*** Testing preg_split() : error conditions ***\n";
+$regex_array = array('abcdef', //Regex without delimiter
+'/[a-zA-Z]', //Regex without closing delimiter
+'[a-zA-Z]/', //Regex without opening delimiter
+'/[a-zA-Z]/F', array('[a-z]', //Array of Regexes
+'[A-Z]', '[0-9]'), '/[a-zA-Z]/', //Regex string
+);
+$subject = '1 2 a 3 4 b 5 6';
+foreach($regex_array as $regex_value) {
+    print "\nArg value is $regex_value\n";
+    var_dump(preg_split($regex_value, $subject));
+}
+$regex_value = new stdclass(); //Object
+var_dump(preg_split($regex_value, $subject));
+?>
+--EXPECTF--
+*** Testing preg_split() : error conditions ***
+
+Arg value is abcdef
+
+Warning: preg_split(): Delimiter must not be alphanumeric or backslash in %spreg_split_error1.php on line %d
+bool(false)
+
+Arg value is /[a-zA-Z]
+
+Warning: preg_split(): No ending delimiter '/' found in %spreg_split_error1.php on line %d
+bool(false)
+
+Arg value is [a-zA-Z]/
+
+Warning: preg_split(): Unknown modifier '/' in %spreg_split_error1.php on line %d
+bool(false)
+
+Arg value is /[a-zA-Z]/F
+
+Warning: preg_split(): Unknown modifier 'F' in %spreg_split_error1.php on line %d
+bool(false)
+
+Arg value is Array
+
+Warning: preg_split() expects parameter 1 to be string, array given in %spreg_split_error1.php on line %d
+bool(false)
+
+Arg value is /[a-zA-Z]/
+array(3) {
+  [0]=>
+  string(4) "1 2 "
+  [1]=>
+  string(5) " 3 4 "
+  [2]=>
+  string(4) " 5 6"
+}
+
+Warning: preg_split() expects parameter 1 to be string, object given in %spreg_split_error1.php on line %d
+bool(false)
diff --git a/ext/pcre/tests/preg_split_error2.phpt b/ext/pcre/tests/preg_split_error2.phpt
new file mode 100644
index 0000000..e081821
--- /dev/null
+++ b/ext/pcre/tests/preg_split_error2.phpt
@@ -0,0 +1,34 @@
+--TEST--
+Test preg_split() function : error conditions - wrong arg types
+--FILE--
+<?php
+/*
+* proto array preg_split(string pattern, string subject [, int limit [, int flags]])
+* Function is implemented in ext/pcre/php_pcre.c
+*/
+error_reporting(E_ALL&~E_NOTICE);
+/*
+* Testing how preg_split reacts to being passed the wrong type of input argument
+*/
+echo "*** Testing preg_split() : error conditions ***\n";
+$regex = '/[a-zA-Z]/';
+$input = array(array('this is', 'a subarray'),);
+foreach($input as $value) {
+    print "\nArg value is: $value\n";
+    var_dump(preg_split($regex, $value));
+}
+$value = new stdclass(); //Object
+var_dump(preg_split($regex, $value));
+echo "Done";
+?>
+--EXPECTF--
+*** Testing preg_split() : error conditions ***
+
+Arg value is: Array
+
+Warning: preg_split() expects parameter 2 to be string, array given in %spreg_split_error2.php on line %d
+bool(false)
+
+Warning: preg_split() expects parameter 2 to be string, object given in %spreg_split_error2.php on line %d
+bool(false)
+Done
\ No newline at end of file
diff --git a/ext/pcre/tests/recursion_limit.phpt b/ext/pcre/tests/recursion_limit.phpt
new file mode 100644
index 0000000..7dee7ba
--- /dev/null
+++ b/ext/pcre/tests/recursion_limit.phpt
@@ -0,0 +1,25 @@
+--TEST--
+PCRE Recursion limit
+--SKIPIF--
+<?php
+if (@preg_match_all('/\p{N}/', '0123456789', $dummy) === false) {
+	die("skip no support for \p support PCRE library");
+}
+?>
+--INI--
+pcre.recursion_limit=2
+--FILE--
+<?php
+
+var_dump(preg_match_all('/\p{Ll}(\p{L}((\p{Ll}\p{Ll})))/', 'aeiou', $dummy));
+var_dump(preg_last_error() === PREG_RECURSION_LIMIT_ERROR);
+
+var_dump(preg_match_all('/\p{Ll}\p{L}\p{Ll}\p{Ll}/', 'aeiou', $dummy));
+var_dump(preg_last_error() === PREG_NO_ERROR);
+
+?>
+--EXPECT--
+bool(false)
+bool(true)
+int(1)
+bool(true)
diff --git a/ext/pcre/tests/skip.ini b/ext/pcre/tests/skip.ini
new file mode 100644
index 0000000..1388e92
--- /dev/null
+++ b/ext/pcre/tests/skip.ini
@@ -0,0 +1,17 @@
+[Locale checks]
+skip[]=skip_001.inc
+test[]=locales.phpt
+
+[No utf8 support in PCRE library]
+skip[]=skip_002.inc
+test[]=007.phpt
+test[]=bug27103.phpt
+test[]=invalid_utf8_offset.phpt
+test[]=invalid_utf8.phpt
+test[]=preg_replace2.phpt
+
+[No support for \p support PCRE library]
+skip[]=skip_003.inc
+test[]=backtrack_limit.phpt
+test[]=pcre_anchored.phpt
+test[]=recursion_limit.phpt
diff --git a/ext/pcre/tests/skip_001.inc b/ext/pcre/tests/skip_001.inc
new file mode 100644
index 0000000..410512d
--- /dev/null
+++ b/ext/pcre/tests/skip_001.inc
@@ -0,0 +1,9 @@
+<?php 
+
+if (!function_exists('setlocale')) {
+	die('skip: setlocale() not available');
+}
+
+if (!@setlocale(LC_ALL, 'pt_PT', 'pt', 'pt_PT.ISO8859-1', 'portuguese')) {
+	die('skip pt locale not available');
+}
diff --git a/ext/pcre/tests/skip_002.inc b/ext/pcre/tests/skip_002.inc
new file mode 100644
index 0000000..7f3a253
--- /dev/null
+++ b/ext/pcre/tests/skip_002.inc
@@ -0,0 +1,5 @@
+<?php
+
+if (@preg_match('/./u', '') === false) {
+	die('skip');
+}
diff --git a/ext/pcre/tests/skip_003.inc b/ext/pcre/tests/skip_003.inc
new file mode 100644
index 0000000..af2f548
--- /dev/null
+++ b/ext/pcre/tests/skip_003.inc
@@ -0,0 +1,5 @@
+<?php
+
+if (@preg_match_all('/\p{N}/', '0123456789', $dummy) === false) {
+	die('skip');
+}
diff --git a/ext/pcre/tests/split.phpt b/ext/pcre/tests/split.phpt
new file mode 100644
index 0000000..8ec8e65
--- /dev/null
+++ b/ext/pcre/tests/split.phpt
@@ -0,0 +1,86 @@
+--TEST--
+preg_split()
+--FILE--
+<?php
+
+var_dump(preg_split());
+var_dump(preg_split('/*/', 'x'));
+
+var_dump(preg_split('/[\s, ]+/', 'x yy,zzz'));
+var_dump(preg_split('/[\s, ]+/', 'x yy,zzz', -1));
+var_dump(preg_split('/[\s, ]+/', 'x yy,zzz', 0));
+var_dump(preg_split('/[\s, ]+/', 'x yy,zzz', 1));
+var_dump(preg_split('/[\s, ]+/', 'x yy,zzz', 2));
+
+var_dump(preg_split('/\d*/', 'ab2c3u'));
+var_dump(preg_split('/\d*/', 'ab2c3u', -1, PREG_SPLIT_NO_EMPTY));
+
+?>
+--EXPECTF--
+Warning: preg_split() expects at least 2 parameters, 0 given in %ssplit.php on line 3
+bool(false)
+
+Warning: preg_split(): Compilation failed: nothing to repeat at offset 0 in %ssplit.php on line 4
+bool(false)
+array(3) {
+  [0]=>
+  string(1) "x"
+  [1]=>
+  string(2) "yy"
+  [2]=>
+  string(3) "zzz"
+}
+array(3) {
+  [0]=>
+  string(1) "x"
+  [1]=>
+  string(2) "yy"
+  [2]=>
+  string(3) "zzz"
+}
+array(3) {
+  [0]=>
+  string(1) "x"
+  [1]=>
+  string(2) "yy"
+  [2]=>
+  string(3) "zzz"
+}
+array(1) {
+  [0]=>
+  string(8) "x yy,zzz"
+}
+array(2) {
+  [0]=>
+  string(1) "x"
+  [1]=>
+  string(6) "yy,zzz"
+}
+array(8) {
+  [0]=>
+  string(0) ""
+  [1]=>
+  string(1) "a"
+  [2]=>
+  string(1) "b"
+  [3]=>
+  string(0) ""
+  [4]=>
+  string(1) "c"
+  [5]=>
+  string(0) ""
+  [6]=>
+  string(1) "u"
+  [7]=>
+  string(0) ""
+}
+array(4) {
+  [0]=>
+  string(1) "a"
+  [1]=>
+  string(1) "b"
+  [2]=>
+  string(1) "c"
+  [3]=>
+  string(1) "u"
+}
diff --git a/ext/pcre/tests/split2.phpt b/ext/pcre/tests/split2.phpt
new file mode 100644
index 0000000..391acb9
--- /dev/null
+++ b/ext/pcre/tests/split2.phpt
@@ -0,0 +1,315 @@
+--TEST--
+preg_split() 2nd test
+--FILE--
+<?php
+
+var_dump(preg_split('/(\d*)/', 'ab2c3u', -1, PREG_SPLIT_DELIM_CAPTURE));
+var_dump(preg_split('/(\d*)/', 'ab2c3u', -1, PREG_SPLIT_OFFSET_CAPTURE));
+var_dump(preg_split('/(\d*)/', 'ab2c3u', -1, PREG_SPLIT_NO_EMPTY | PREG_SPLIT_DELIM_CAPTURE));
+var_dump(preg_split('/(\d*)/', 'ab2c3u', -1, PREG_SPLIT_NO_EMPTY | PREG_SPLIT_OFFSET_CAPTURE));;
+var_dump(preg_split('/(\d*)/', 'ab2c3u', -1, PREG_SPLIT_DELIM_CAPTURE | PREG_SPLIT_OFFSET_CAPTURE));
+var_dump(preg_split('/(\d*)/', 'ab2c3u', -1, PREG_SPLIT_NO_EMPTY | PREG_SPLIT_DELIM_CAPTURE | PREG_SPLIT_OFFSET_CAPTURE));
+
+
+var_dump(preg_last_error(1));
+ini_set('pcre.recursion_limit', 1);
+var_dump(preg_last_error() == PREG_NO_ERROR);
+var_dump(preg_split('/(\d*)/', 'ab2c3u'));
+var_dump(preg_last_error() == PREG_RECURSION_LIMIT_ERROR);
+
+?>
+--EXPECTF--
+array(15) {
+  [0]=>
+  string(0) ""
+  [1]=>
+  string(0) ""
+  [2]=>
+  string(1) "a"
+  [3]=>
+  string(0) ""
+  [4]=>
+  string(1) "b"
+  [5]=>
+  string(1) "2"
+  [6]=>
+  string(0) ""
+  [7]=>
+  string(0) ""
+  [8]=>
+  string(1) "c"
+  [9]=>
+  string(1) "3"
+  [10]=>
+  string(0) ""
+  [11]=>
+  string(0) ""
+  [12]=>
+  string(1) "u"
+  [13]=>
+  string(0) ""
+  [14]=>
+  string(0) ""
+}
+array(8) {
+  [0]=>
+  array(2) {
+    [0]=>
+    string(0) ""
+    [1]=>
+    int(0)
+  }
+  [1]=>
+  array(2) {
+    [0]=>
+    string(1) "a"
+    [1]=>
+    int(0)
+  }
+  [2]=>
+  array(2) {
+    [0]=>
+    string(1) "b"
+    [1]=>
+    int(1)
+  }
+  [3]=>
+  array(2) {
+    [0]=>
+    string(0) ""
+    [1]=>
+    int(3)
+  }
+  [4]=>
+  array(2) {
+    [0]=>
+    string(1) "c"
+    [1]=>
+    int(3)
+  }
+  [5]=>
+  array(2) {
+    [0]=>
+    string(0) ""
+    [1]=>
+    int(5)
+  }
+  [6]=>
+  array(2) {
+    [0]=>
+    string(1) "u"
+    [1]=>
+    int(5)
+  }
+  [7]=>
+  array(2) {
+    [0]=>
+    string(0) ""
+    [1]=>
+    int(6)
+  }
+}
+array(6) {
+  [0]=>
+  string(1) "a"
+  [1]=>
+  string(1) "b"
+  [2]=>
+  string(1) "2"
+  [3]=>
+  string(1) "c"
+  [4]=>
+  string(1) "3"
+  [5]=>
+  string(1) "u"
+}
+array(4) {
+  [0]=>
+  array(2) {
+    [0]=>
+    string(1) "a"
+    [1]=>
+    int(0)
+  }
+  [1]=>
+  array(2) {
+    [0]=>
+    string(1) "b"
+    [1]=>
+    int(1)
+  }
+  [2]=>
+  array(2) {
+    [0]=>
+    string(1) "c"
+    [1]=>
+    int(3)
+  }
+  [3]=>
+  array(2) {
+    [0]=>
+    string(1) "u"
+    [1]=>
+    int(5)
+  }
+}
+array(15) {
+  [0]=>
+  array(2) {
+    [0]=>
+    string(0) ""
+    [1]=>
+    int(0)
+  }
+  [1]=>
+  array(2) {
+    [0]=>
+    string(0) ""
+    [1]=>
+    int(0)
+  }
+  [2]=>
+  array(2) {
+    [0]=>
+    string(1) "a"
+    [1]=>
+    int(0)
+  }
+  [3]=>
+  array(2) {
+    [0]=>
+    string(0) ""
+    [1]=>
+    int(1)
+  }
+  [4]=>
+  array(2) {
+    [0]=>
+    string(1) "b"
+    [1]=>
+    int(1)
+  }
+  [5]=>
+  array(2) {
+    [0]=>
+    string(1) "2"
+    [1]=>
+    int(2)
+  }
+  [6]=>
+  array(2) {
+    [0]=>
+    string(0) ""
+    [1]=>
+    int(3)
+  }
+  [7]=>
+  array(2) {
+    [0]=>
+    string(0) ""
+    [1]=>
+    int(3)
+  }
+  [8]=>
+  array(2) {
+    [0]=>
+    string(1) "c"
+    [1]=>
+    int(3)
+  }
+  [9]=>
+  array(2) {
+    [0]=>
+    string(1) "3"
+    [1]=>
+    int(4)
+  }
+  [10]=>
+  array(2) {
+    [0]=>
+    string(0) ""
+    [1]=>
+    int(5)
+  }
+  [11]=>
+  array(2) {
+    [0]=>
+    string(0) ""
+    [1]=>
+    int(5)
+  }
+  [12]=>
+  array(2) {
+    [0]=>
+    string(1) "u"
+    [1]=>
+    int(5)
+  }
+  [13]=>
+  array(2) {
+    [0]=>
+    string(0) ""
+    [1]=>
+    int(6)
+  }
+  [14]=>
+  array(2) {
+    [0]=>
+    string(0) ""
+    [1]=>
+    int(6)
+  }
+}
+array(6) {
+  [0]=>
+  array(2) {
+    [0]=>
+    string(1) "a"
+    [1]=>
+    int(0)
+  }
+  [1]=>
+  array(2) {
+    [0]=>
+    string(1) "b"
+    [1]=>
+    int(1)
+  }
+  [2]=>
+  array(2) {
+    [0]=>
+    string(1) "2"
+    [1]=>
+    int(2)
+  }
+  [3]=>
+  array(2) {
+    [0]=>
+    string(1) "c"
+    [1]=>
+    int(3)
+  }
+  [4]=>
+  array(2) {
+    [0]=>
+    string(1) "3"
+    [1]=>
+    int(4)
+  }
+  [5]=>
+  array(2) {
+    [0]=>
+    string(1) "u"
+    [1]=>
+    int(5)
+  }
+}
+
+Warning: preg_last_error() expects exactly 0 parameters, 1 given in %s on line %d
+NULL
+bool(true)
+array(1) {
+  [0]=>
+  string(6) "ab2c3u"
+}
+bool(true)
diff --git a/ext/pcre/tests/study.phpt b/ext/pcre/tests/study.phpt
new file mode 100644
index 0000000..696a4c0
--- /dev/null
+++ b/ext/pcre/tests/study.phpt
@@ -0,0 +1,31 @@
+--TEST--
+Study regex
+--FILE--
+<?php
+
+var_dump(preg_match('/(?:(?:(?:(?:(?:(.))))))/  S', 'aeiou', $dump));
+var_dump($dump[1]);
+var_dump(preg_match('/(?:(?:(?:(?:(?:(.))))))/', 'aeiou', $dump));
+var_dump($dump[1]);
+
+var_dump(preg_match('/(?>..)((?:(?>.)|.|.|.|u))/S', 'aeiou', $dump));
+var_dump($dump[1]);
+
+// try to trigger usual "match known text" optimization
+var_dump(preg_match('/^aeiou$/S', 'aeiou', $dump));
+var_dump($dump[0]);
+var_dump(preg_match('/aeiou/S', 'aeiou', $dump));
+var_dump($dump[0]);
+
+?>
+--EXPECT--
+int(1)
+string(1) "a"
+int(1)
+string(1) "a"
+int(1)
+string(1) "i"
+int(1)
+string(5) "aeiou"
+int(1)
+string(5) "aeiou"
diff --git a/ext/pcre/tests/ungreedy.phpt b/ext/pcre/tests/ungreedy.phpt
new file mode 100644
index 0000000..cf5e8ad
--- /dev/null
+++ b/ext/pcre/tests/ungreedy.phpt
@@ -0,0 +1,31 @@
+--TEST--
+U (PCRE_UNGREEDY) modififer
+--FILE--
+<?php
+
+var_dump(preg_match('/<.*>/', '<aa> <bb> <cc>', $m));
+var_dump($m);
+
+var_dump(preg_match('/<.*>/U', '<aa> <bb> <cc>', $m));
+var_dump($m);
+
+var_dump(preg_match('/(?U)<.*>/', '<aa> <bb> <cc>', $m));
+var_dump($m);
+
+?>
+--EXPECT--
+int(1)
+array(1) {
+  [0]=>
+  string(14) "<aa> <bb> <cc>"
+}
+int(1)
+array(1) {
+  [0]=>
+  string(4) "<aa>"
+}
+int(1)
+array(1) {
+  [0]=>
+  string(4) "<aa>"
+}
diff --git a/ext/pcre/upgrade-pcre.php b/ext/pcre/upgrade-pcre.php
new file mode 100644
index 0000000..a48f8d7
--- /dev/null
+++ b/ext/pcre/upgrade-pcre.php
@@ -0,0 +1,137 @@
+<?php
+
+// script to upgrade PCRE. just drop the pcre-x.x.tar.xx here and run the script
+
+$pattern = 'pcre-*.tar.*';
+$newpcre = glob($pattern);
+
+if (count($newpcre) > 1) {
+	echo "more than one '$pattern' file. aborting\n";
+	print_r($newpcre);
+	exit;
+}
+
+if (count($newpcre) == 0) {
+	die("need one '$pattern' file. aborting.\n");
+}
+
+
+$newpcre = $newpcre[0];
+
+if (strpos($newpcre, 'gz')) {
+	system("tar xfz $newpcre");
+} elseif (strpos($newpcre, 'bz2')) {
+	system("tar xfj $newpcre");
+} else {
+	die("file type not recognized: $newpcre\n");
+}
+
+$newpcre = substr($newpcre, 0, strpos($newpcre, '.tar'));
+$dirlen = strlen('pcrelib');
+
+function recurse($path)
+{
+	global $newpcre, $dirlen;
+
+	foreach (scandir($path) as $file) {
+
+		if ($file[0] === '.' ||
+		$file === 'CVS' ||
+		@substr_compare($file, '.lo', -3, 3) === 0 ||
+		@substr_compare($file, '.loT', -4, 4) === 0 ||
+		@substr_compare($file, '.o', -2, 2) === 0) continue;
+
+		$file = "$path/$file";
+
+		if (is_dir($file)) {
+			recurse($file);
+			continue;
+		}
+
+		echo "processing $file... ";
+
+		$newfile = $newpcre . substr($file, $dirlen);
+
+		if (is_file($tmp = $newfile . '.generic') || is_file($tmp = $newfile . '.dist')) {
+			$newfile = $tmp;
+		}
+
+
+		if (!is_file($newfile)) {
+			die("$newfile is not available any more\n");
+		}
+
+		// maintain file mtimes so that cvs doesnt get crazy
+		if (file_get_contents($newfile) !== file_get_contents($file)) {
+			copy($newfile, $file);
+		}
+
+		// always include the config.h file
+		$content    = file_get_contents($newfile);
+		$newcontent = preg_replace('/#\s*ifdef HAVE_CONFIG_H\s*(.+)\s*#\s*endif/', '$1', $content);
+
+		if ($content !== $newcontent) {
+			file_put_contents($file, $newcontent);
+		}
+
+		echo "OK\n";
+	}
+
+}
+
+
+recurse('pcrelib');
+
+$dirorig = scandir('pcrelib/testdata');
+$k = array_search('CVS', $dirorig);
+if ($k !== false)
+	unset($dirorig[$k]);
+
+$k = array_search('.svn', $dirorig);
+if ($k !== false)
+	unset($dirorig[$k]);
+
+$dirnew = scandir("$newpcre/testdata");
+$diff   = array_diff($dirorig, $dirnew);
+
+foreach ($diff as $file) {
+	$file2 = 'pcrelib'.substr($file, strlen($newpcre));
+	copy($file, $file2);
+}
+
+
+// the config.h needs special care
+$prepend_config_h = '
+#include <php_compat.h>
+
+#ifndef PHP_WIN32
+# include <php_config.h>
+#endif
+
+#undef PACKAGE_NAME
+#undef PACKAGE_VERSION
+#undef PACKAGE_TARNAME
+#undef PACKAGE_STRING
+
+#define SUPPORT_UCP
+#define SUPPORT_UTF8
+
+#if defined(__GNUC__) && __GNUC__ >= 4
+# ifdef __cplusplus
+#  define PCRE_EXP_DECL		extern "C" __attribute__ ((visibility("default")))
+# else
+#  define PCRE_EXP_DECL		extern __attribute__ ((visibility("default")))
+# endif
+# define PCRE_EXP_DEFN		__attribute__ ((visibility("default")))
+# define PCRE_EXP_DATA_DEFN	__attribute__ ((visibility("default")))
+#endif
+
+
+';
+
+file_put_contents('pcrelib/config.h', $prepend_config_h . file_get_contents('pcrelib/config.h'));
+
+
+echo "\nThe End :-)\n\n"
+
+?>