diff options
Diffstat (limited to 'ext/pcre')
114 files changed, 0 insertions, 78206 deletions
diff --git a/ext/pcre/CREDITS b/ext/pcre/CREDITS deleted file mode 100644 index ae0fba35d4..0000000000 --- a/ext/pcre/CREDITS +++ /dev/null @@ -1,2 +0,0 @@ -Perl Compatible Regexps -Andrei Zmievski diff --git a/ext/pcre/config.w32 b/ext/pcre/config.w32 deleted file mode 100644 index 8700b3ca08..0000000000 --- a/ext/pcre/config.w32 +++ /dev/null @@ -1,14 +0,0 @@ -// $Id$ -// vim:ft=javascript - -ARG_WITH("pcre-regex", "Perl Compatible Regular Expressions", "yes"); - -if (PHP_PCRE_REGEX == "yes") { - EXTENSION("pcre", "php_pcre.c", PHP_PCRE_REGEX_SHARED, - "-DEXPORT= -DNEWLINE=10 -DSUPPORT_UTF8 -DSUPPORT_UCP -DLINK_SIZE=2 -DPOSIX_MALLOC_THRESHOLD=10 -DMATCH_LIMIT=10000000 -DMATCH_LIMIT_RECURSION=10000000 -DMAX_NAME_SIZE=32 -DMAX_NAME_COUNT=10000 -DMAX_DUPLENGTH=30000 -DNO_RECURSE -Iext/pcre/pcrelib"); - ADD_SOURCES("ext/pcre/pcrelib", "pcre_chartables.c pcre_ucp_searchfuncs.c pcre_compile.c pcre_config.c pcre_exec.c pcre_fullinfo.c pcre_get.c pcre_globals.c pcre_info.c pcre_maketables.c pcre_ord2utf8.c pcre_refcount.c pcre_study.c pcre_tables.c pcre_try_flipped.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'); -} diff --git a/ext/pcre/config0.m4 b/ext/pcre/config0.m4 deleted file mode 100644 index 323d9aefa1..0000000000 --- a/ext/pcre/config0.m4 +++ /dev/null @@ -1,57 +0,0 @@ -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,for PCRE support, -[ --without-pcre-regex Do not include Perl Compatible Regular Expressions - support. Use --with-pcre-regex=DIR to specify DIR - where PCRE's include and library files are located, - if not using bundled library.],yes) - -if test "$PHP_PCRE_REGEX" != "no"; then - if test "$PHP_PCRE_REGEX" = "yes"; then - PHP_NEW_EXTENSION(pcre, pcrelib/pcre_chartables.c pcrelib/pcre_ucp_searchfuncs.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_info.c pcrelib/pcre_maketables.c pcrelib/pcre_ord2utf8.c pcrelib/pcre_refcount.c pcrelib/pcre_study.c pcrelib/pcre_tables.c pcrelib/pcre_try_flipped.c pcrelib/pcre_valid_utf8.c pcrelib/pcre_version.c pcrelib/pcre_xclass.c php_pcre.c, $ext_shared,,-DEXPORT= -DNEWLINE=10 -DSUPPORT_UTF8 -DSUPPORT_UCP -DLINK_SIZE=2 -DPOSIX_MALLOC_THRESHOLD=10 -DMATCH_LIMIT=10000000 -DMATCH_LIMIT_RECURSION=10000000 -DMAX_NAME_SIZE=32 -DMAX_NAME_COUNT=10000 -DMAX_DUPLENGTH=30000 -I@ext_srcdir@/pcrelib) - PHP_ADD_BUILD_DIR($ext_builddir/pcrelib) - PHP_INSTALL_HEADERS([ext/pcre], [php_pcre.h pcrelib/]) - AC_DEFINE(HAVE_BUNDLED_PCRE, 1, [ ]) - else - for i in $PHP_PCRE_REGEX $PHP_PCRE_REGEX/include $PHP_PCRE_REGEX/include/pcre; 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 - - 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 - - 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, $PCRE_LIBDIR, PCRE_SHARED_LIBADD) - - AC_DEFINE(HAVE_PCRE, 1, [ ]) - PHP_ADD_INCLUDE($PCRE_INCDIR) - PHP_NEW_EXTENSION(pcre, php_pcre.c, $ext_shared,,-DEXPORT= -DNEWLINE=10 -DSUPPORT_UTF8 -DSUPPORT_UCP -DLINK_SIZE=2 -DPOSIX_MALLOC_THRESHOLD=10 -DMATCH_LIMIT=10000000 -DMATCH_LIMIT_RECURSION=10000000 -DMAX_NAME_SIZE=32 -DMAX_NAME_COUNT=10000 -DMAX_DUPLENGTH=30000) - fi - PHP_SUBST(PCRE_SHARED_LIBADD) -fi diff --git a/ext/pcre/pcrelib/AUTHORS b/ext/pcre/pcrelib/AUTHORS deleted file mode 100644 index adb4fc4019..0000000000 --- a/ext/pcre/pcrelib/AUTHORS +++ /dev/null @@ -1,23 +0,0 @@ -THE MAIN PCRE LIBRARY ---------------------- - -Written by: Philip Hazel -Email local part: ph10 -Email domain: cam.ac.uk - -University of Cambridge Computing Service, -Cambridge, England. Phone: +44 1223 334714. - -Copyright (c) 1997-2006 University of Cambridge -All rights reserved - - -THE C++ WRAPPER LIBRARY ------------------------ - -Written by: Google Inc. - -Copyright (c) 2006 Google Inc -All rights reserved - -#### diff --git a/ext/pcre/pcrelib/COPYING b/ext/pcre/pcrelib/COPYING deleted file mode 100644 index daea2e48a3..0000000000 --- a/ext/pcre/pcrelib/COPYING +++ /dev/null @@ -1,68 +0,0 @@ -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 6 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. - - -THE BASIC LIBRARY FUNCTIONS ---------------------------- - -Written by: Philip Hazel -Email local part: ph10 -Email domain: cam.ac.uk - -University of Cambridge Computing Service, -Cambridge, England. Phone: +44 1223 334714. - -Copyright (c) 1997-2006 University of Cambridge -All rights reserved. - - -THE C++ WRAPPER FUNCTIONS -------------------------- - -Contributed by: Google Inc. - -Copyright (c) 2006, 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/ChangeLog b/ext/pcre/pcrelib/ChangeLog deleted file mode 100644 index 2a14134848..0000000000 --- a/ext/pcre/pcrelib/ChangeLog +++ /dev/null @@ -1,2279 +0,0 @@ -ChangeLog for PCRE ------------------- - -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/LICENCE b/ext/pcre/pcrelib/LICENCE deleted file mode 100644 index daea2e48a3..0000000000 --- a/ext/pcre/pcrelib/LICENCE +++ /dev/null @@ -1,68 +0,0 @@ -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 6 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. - - -THE BASIC LIBRARY FUNCTIONS ---------------------------- - -Written by: Philip Hazel -Email local part: ph10 -Email domain: cam.ac.uk - -University of Cambridge Computing Service, -Cambridge, England. Phone: +44 1223 334714. - -Copyright (c) 1997-2006 University of Cambridge -All rights reserved. - - -THE C++ WRAPPER FUNCTIONS -------------------------- - -Contributed by: Google Inc. - -Copyright (c) 2006, 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 deleted file mode 100644 index 4f17b198a0..0000000000 --- a/ext/pcre/pcrelib/NEWS +++ /dev/null @@ -1,266 +0,0 @@ -News about PCRE releases ------------------------- - -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 deleted file mode 100644 index 459bdf2b4f..0000000000 --- a/ext/pcre/pcrelib/NON-UNIX-USE +++ /dev/null @@ -1,269 +0,0 @@ -Compiling PCRE on non-Unix systems ----------------------------------- - -See below for comments on Cygwin or MinGW and OpenVMS usage. I (Philip Hazel) -have no knowledge of Windows or VMS sytems and how their libraries work. The -items in the PCRE Makefile that relate to anything other than Unix-like systems -have been contributed by PCRE users. There are some other comments and files in -the Contrib directory on the ftp site that you may find useful. See - - ftp://ftp.csx.cam.ac.uk/pub/software/programming/pcre/Contrib - -If you want to compile PCRE for a non-Unix system (or perhaps, more strictly, -for a system that does not support "configure" and "make" files), note that -the basic PCRE library consists entirely of code written in Standard C, and so -should compile successfully on any system that has a Standard C compiler and -library. The C++ wrapper functions are a separate issue (see below). - - -GENERIC INSTRUCTIONS FOR THE C LIBRARY - -The following are generic comments about building PCRE. The interspersed -indented commands are suggestions from Mark Tetrode as to which commands you -might use on a Windows system to build a static library. - -(1) Copy or rename the file config.in as config.h, and change the macros that -define HAVE_STRERROR and HAVE_MEMMOVE to define them as 1 rather than 0. -Unfortunately, because of the way Unix autoconf works, the default setting has -to be 0. You may also want to make changes to other macros in config.h. In -particular, if you want to force a specific value for newline, you can define -the NEWLINE macro. The default is to use '\n', thereby using whatever value -your compiler gives to '\n'. - - rem Mark Tetrode's commands - copy config.in config.h - rem Use write, because notepad cannot handle UNIX files. Change values. - write config.h - -(2) Compile dftables.c as a stand-alone program, and then run it with -the single argument "pcre_chartables.c". This generates a set of standard -character tables and writes them to that file. - - rem Mark Tetrode's commands - rem Compile & run - cl -DSUPPORT_UTF8 -DSUPPORT_UCP dftables.c - dftables.exe pcre_chartables.c - -(3) Compile the following source files: - - pcre_chartables.c - pcre_compile.c - pcre_config.c - pcre_dfa_exec.c - pcre_exec.c - pcre_fullinfo.c - pcre_get.c - pcre_globals.c - pcre_info.c - pcre_maketables.c - pcre_ord2utf8.c - pcre_refcount.c - pcre_study.c - pcre_tables.c - pcre_try_flipped.c - pcre_ucp_searchfuncs.c - pcre_valid_utf8.c - pcre_version.c - pcre_xclass.c - -and link them all together into an object library in whichever form your system -keeps such libraries. This is the pcre C library. If your system has static and -shared libraries, you may have to do this once for each type. - - rem These comments are out-of-date, referring to a previous release which - rem had fewer source files. Replace with the file names from above. - rem Mark Tetrode's commands, for a static library - rem Compile & lib - cl -DSUPPORT_UTF8 -DSUPPORT_UCP -DPOSIX_MALLOC_THRESHOLD=10 /c maketables.c get.c study.c pcre.c - lib /OUT:pcre.lib maketables.obj get.obj study.obj pcre.obj - -(4) Similarly, compile pcreposix.c and link it (on its own) as the pcreposix -library. - - rem Mark Tetrode's commands, for a static library - rem Compile & lib - cl -DSUPPORT_UTF8 -DSUPPORT_UCP -DPOSIX_MALLOC_THRESHOLD=10 /c pcreposix.c - lib /OUT:pcreposix.lib pcreposix.obj - -(5) Compile the test program pcretest.c. This needs the functions in the -pcre and pcreposix libraries when linking. - - rem Mark Tetrode's commands - rem compile & link - cl /F0x400000 pcretest.c pcre.lib pcreposix.lib - -(6) Run pcretest on the testinput files in the testdata directory, and check -that the output matches the corresponding testoutput files. You must use the --i option when checking testinput2. Note that the supplied files are in Unix -format, with just LF characters as line terminators. You may need to edit them -to change this if your system uses a different convention. - - rem Mark Tetrode's commands - pcretest testdata\testinput1 testdata\myoutput1 - windiff testdata\testoutput1 testdata\myoutput1 - pcretest -i testdata\testinput2 testdata\myoutput2 - windiff testdata\testoutput2 testdata\myoutput2 - pcretest testdata\testinput3 testdata\myoutput3 - windiff testdata\testoutput3 testdata\myoutput3 - pcretest testdata\testinput4 testdata\myoutput4 - windiff testdata\testoutput4 testdata\myoutput4 - pcretest testdata\testinput5 testdata\myoutput5 - windiff testdata\testoutput5 testdata\myoutput5 - pcretest testdata\testinput6 testdata\myoutput6 - windiff testdata\testoutput6 testdata\myoutput6 - -Note that there are now three more tests (7, 8, 9) that did not exist when Mark -wrote those comments. The test the new pcre_dfa_exec() function. - -(7) If you want to use the pcregrep command, compile and link pcregrep.c; it -uses only the basic PCRE library. - - -THE C++ WRAPPER FUNCTIONS - -The PCRE distribution now contains some C++ wrapper functions and tests, -contributed by Google Inc. On a system that can use "configure" and "make", -the functions are automatically built into a library called pcrecpp. It should -be straightforward to compile the .cc files manually on other systems. The -files called xxx_unittest.cc are test programs for each of the corresponding -xxx.cc files. - - -FURTHER REMARKS - -If you have a system without "configure" but where you can use a Makefile, edit -Makefile.in to create Makefile, substituting suitable values for the variables -at the head of the file. - -Some help in building a Win32 DLL of PCRE in GnuWin32 environments was -contributed by Paul Sokolovsky. These environments are Mingw32 -(http://www.xraylith.wisc.edu/~khan/software/gnu-win32/) and CygWin -(http://sourceware.cygnus.com/cygwin/). Paul comments: - - For CygWin, set CFLAGS=-mno-cygwin, and do 'make dll'. You'll get - pcre.dll (containing pcreposix also), libpcre.dll.a, and dynamically - linked pgrep and pcretest. If you have /bin/sh, run RunTest (three - main test go ok, locale not supported). - -Changes to do MinGW with autoconf 2.50 were supplied by Fred Cox -<sailorFred@yahoo.com>, who comments as follows: - - If you are using the PCRE DLL, the normal Unix style configure && make && - make check && make install should just work[*]. If you want to statically - link against the .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 hilarious results. See the configure.in - and pcretest.c for how it is done for the static test. - - Also, there will only be a libpcre.la, not a libpcreposix.la, as you - would expect from the Unix version. The single DLL includes the pcreposix - interface. - -[*] But note that the supplied test files are in Unix format, with just LF -characters as line terminators. You will have to edit them to change to CR LF -terminators. - -A script for building PCRE using Borland's C++ compiler for use with VPASCAL -was contributed by Alexander Tokarev. It is called makevp.bat. - -These are some further comments about Win32 builds from Mark Evans. They -were contributed before Fred Cox's changes were made, so it is possible that -they may no longer be relevant. - -"The documentation for Win32 builds is a bit shy. Under MSVC6 I -followed their instructions to the letter, but there were still -some things missing. - -(1) Must #define STATIC for entire project if linking statically. - (I see no reason to use DLLs for code this compact.) This of - course is a project setting in MSVC under Preprocessor. - -(2) Missing some #ifdefs relating to the function pointers - pcre_malloc and pcre_free. See my solution below. (The stubs - may not be mandatory but they made me feel better.)" - -========================= -#ifdef _WIN32 -#include <malloc.h> - -void* malloc_stub(size_t N) -{ return malloc(N); } -void free_stub(void* p) -{ free(p); } -void *(*pcre_malloc)(size_t) = &malloc_stub; -void (*pcre_free)(void *) = &free_stub; - -#else - -void *(*pcre_malloc)(size_t) = malloc; -void (*pcre_free)(void *) = free; - -#endif -========================= - - -BUILDING PCRE ON OPENVMS - -Dan Mooney sent the following comments about building PCRE on OpenVMS. They -relate to an older version of PCRE that used fewer source files, so the exact -commands will need changing. See the current list of source files above. - -"It was quite easy to compile and link the library. I don't have a formal -make file but the attached file [reproduced below] contains the OpenVMS DCL -commands I used to build the library. I had to add #define -POSIX_MALLOC_THRESHOLD 10 to pcre.h since it was not defined anywhere. - -The library was built on: -O/S: HP OpenVMS v7.3-1 -Compiler: Compaq C v6.5-001-48BCD -Linker: vA13-01 - -The test results did not match 100% due to the issues you mention in your -documentation regarding isprint(), iscntrl(), isgraph() and ispunct(). I -modified some of the character tables temporarily and was able to get the -results to match. Tests using the fr locale did not match since I don't have -that locale loaded. The study size was always reported to be 3 less than the -value in the standard test output files." - -========================= -$! This DCL procedure builds PCRE on OpenVMS -$! -$! I followed the instructions in the non-unix-use file in the distribution. -$! -$ COMPILE == "CC/LIST/NOMEMBER_ALIGNMENT/PREFIX_LIBRARY_ENTRIES=ALL_ENTRIES -$ COMPILE DFTABLES.C -$ LINK/EXE=DFTABLES.EXE DFTABLES.OBJ -$ RUN DFTABLES.EXE/OUTPUT=CHARTABLES.C -$ COMPILE MAKETABLES.C -$ COMPILE GET.C -$ COMPILE STUDY.C -$! I had to set POSIX_MALLOC_THRESHOLD to 10 in PCRE.H since the symbol -$! did not seem to be defined anywhere. -$! I edited pcre.h and added #DEFINE SUPPORT_UTF8 to enable UTF8 support. -$ COMPILE PCRE.C -$ LIB/CREATE PCRE MAKETABLES.OBJ, GET.OBJ, STUDY.OBJ, PCRE.OBJ -$! I had to set POSIX_MALLOC_THRESHOLD to 10 in PCRE.H since the symbol -$! did not seem to be defined anywhere. -$ COMPILE PCREPOSIX.C -$ LIB/CREATE PCREPOSIX PCREPOSIX.OBJ -$ COMPILE PCRETEST.C -$ LINK/EXE=PCRETEST.EXE PCRETEST.OBJ, PCRE/LIB, PCREPOSIX/LIB -$! C programs that want access to command line arguments must be -$! defined as a symbol -$ PCRETEST :== "$ SYS$ROADSUSERS:[DMOONEY.REGEXP]PCRETEST.EXE" -$! Arguments must be enclosed in quotes. -$ PCRETEST "-C" -$! Test results: -$! -$! The test results did not match 100%. The functions isprint(), iscntrl(), -$! isgraph() and ispunct() on OpenVMS must not produce the same results -$! as the system that built the test output files provided with the -$! distribution. -$! -$! The study size did not match and was always 3 less on OpenVMS. -$! -$! Locale could not be set to fr -$! -========================= - -**** diff --git a/ext/pcre/pcrelib/README b/ext/pcre/pcrelib/README deleted file mode 100644 index 24d0b97497..0000000000 --- a/ext/pcre/pcrelib/README +++ /dev/null @@ -1,528 +0,0 @@ -README file for PCRE (Perl-compatible regular expression library) ------------------------------------------------------------------ - -The latest release of PCRE is always available from - - ftp://ftp.csx.cam.ac.uk/pub/software/programming/pcre/pcre-xxx.tar.gz - -Please read the NEWS file if you are upgrading from a previous release. - - -The PCRE APIs -------------- - -PCRE is written in C, and it has its own API. The distribution now includes a -set of C++ wrapper functions, courtesy of Google Inc. (see the pcrecpp man page -for details). - -Also included are a set of C wrapper functions that are based on the POSIX -API. 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 header file for the POSIX-style -functions is called pcreposix.h. The official POSIX name is regex.h, but I -didn't want to risk possible problems with existing files of that name by -distributing it that way. To use it with an existing program that uses the -POSIX API, it 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, you must take care when linking programs to -ensure that they link with PCRE's libpcreposix library. Otherwise they may pick -up the "real" POSIX functions of the same name. - - -Documentation for PCRE ----------------------- - -If you install PCRE in the normal way, you will end up with an installed 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; however, as there is no standard place to install -them, they are left in the doc directory of the unpacked source distribution. -These forms are: - - 1. Files called doc/pcre.txt, doc/pcregrep.txt, and doc/pcretest.txt. 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. Text forms are provided for ease of scanning with text - editors or similar tools. - - 2. A subdirectory called doc/html contains all the documentation in HTML - form, hyperlinked in various ways, and rooted in a file called - doc/index.html. - - -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 - -where there is also a README file giving brief descriptions of what they are. -Several of them provide support for compiling PCRE on various flavours of -Windows systems (I myself do not use Windows). Some are complete in themselves; -others are pointers to URLs containing relevant files. - - -Building PCRE on a Unix-like system ------------------------------------ - -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. - -To build PCRE on a Unix-like system, 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 -INSTALL. - -Most commonly, people build PCRE within its own distribution directory, and in -this case, on many systems, just running "./configure" is sufficient, but the -usual methods of changing standard defaults are available. For example: - -CFLAGS='-O2 -Wall' ./configure --prefix=/opt/local - -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. You can read more about them in the pcrebuild man page. - -. If you want to suppress the building of the C++ wrapper library, you can add - --disable-cpp to the "configure" command. Otherwise, when "configure" is run, - 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 make use of the support for UTF-8 character strings in PCRE, - you must add --enable-utf8 to the "configure" command. Without it, the code - for handling UTF-8 is not included in the library. (Even when included, it - still has to be enabled by an option at run time.) - -. If, in addition to support for UTF-8 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 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 --newline-is-cr or - --newline-is-lf or --newline-is-crlf to the "configure" command, - respectively. - -. 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. 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 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. You can - increase it even more by setting --with-link-size=4, but this is unlikely - ever to be necessary. If you build PCRE with an increased link size, test 2 - (and 5 if you are using UTF-8) will fail. Part of the output of these tests - is a representation of the compiled pattern, and this changes with the link - size. - -. You can build PCRE so that its internal match() function that is called from - pcre_exec() does not call itself recursively. Instead, it uses blocks of data - from the heap via 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 - pcre_exec() function; it does not apply to pcre_dfa_exec(), which does not - use deeply nested recursion. - -The "configure" script builds eight files for the basic C library: - -. Makefile is the makefile that builds the library -. config.h contains build-time configuration options for the library -. pcre-config is a script that shows the settings of "configure" options -. libpcre.pc is data for the pkg-config command -. libtool is a script that builds shared and/or static libraries -. RunTest is a script for running tests on the library -. RunGrepTest is a script for running tests on the pcregrep command - -In addition, if a C++ compiler is found, the following are also built: - -. pcrecpp.h is the header file for programs that call PCRE via the C++ wrapper -. pcre_stringpiece.h is the 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". It builds two libraries, called -libpcre and libpcreposix, a test program called pcretest, and the pcregrep -command. If a C++ compiler was found on your system, it also builds the C++ -wrapper library, which is called libpcrecpp, and some test programs called -pcrecpp_unittest, pcre_scanner_unittest, and pcre_stringpiece_unittest. - -The command "make test" runs all the appropriate tests. Details of the PCRE -tests are given in a separate section of this document, below. - -You can use "make install" to copy the libraries, the public header files -pcre.h, pcreposix.h, pcrecpp.h, and pcre_stringpiece.h (the last two only if -the C++ wrapper was built), and the man pages to appropriate live directories -on your system, in the normal way. - -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 on Unix-like systems ---------------------------------------------------------- - -Running "make install" also 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 -pkgconfig. - - -Shared libraries on Unix-like systems -------------------------------------- - -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 source 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 on a Unix-like system -------------------------------------- - -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, during the building -process, the dftables.c source file is compiled *and run* on the local host, in -order to generate the default character tables (the chartables.c file). It -therefore needs to be compiled with the local compiler, not the cross compiler. -You can do this by specifying CC_FOR_BUILD (and if necessary CFLAGS_FOR_BUILD; -there are also CXX_FOR_BUILD and CXXFLAGS_FOR_BUILD for the C++ wrapper) -when calling the "configure" command. If they are not specified, they default -to the values of CC and CFLAGS. - - -Using HP's ANSI C++ compiler (aCC) ----------------------------------- - -Unless C++ support is disabled by specifiying 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" - - -Building on non-Unix systems ----------------------------- - -For a non-Unix system, read the comments in the file NON-UNIX-USE, though if -the system supports the use of "configure" and "make" you may be able to build -PCRE in the same way as for Unix systems. - -PCRE has been compiled on Windows systems and on Macintoshes, but I don't know -the details because I don't use those systems. It should be straightforward to -build PCRE on any system that has a Standard C compiler, because it uses only -Standard C functions. - - -Testing PCRE ------------- - -To test PCRE on a Unix system, run the RunTest script that is created by the -configuring process. There is also a script called RunGrepTest that tests the -options of the pcregrep command. If the C++ wrapper library is build, three -test programs called pcrecpp_unittest, pcre_scanner_unittest, and -pcre_stringpiece_unittest are provided. - -Both the scripts and all the program tests are run if you obey "make runtest", -"make check", or "make test". For other systems, see the instructions in -NON-UNIX-USE. - -The RunTest script runs the pcretest test program (which is documented in its -own man page) on each of the testinput files (in the testdata directory) in -turn, and compares the output with the contents of the corresponding testoutput -file. A file called testtry is used to hold the main output from pcretest -(testsavedregex is also used as a working file). To run pcretest on just one of -the test files, give its number as an argument to RunTest, for example: - - RunTest 2 - -The first file can also be fed directly into the perltest 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_info(), 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 flag 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. - -The fourth test checks the UTF-8 support. It is not run automatically unless -PCRE is built with UTF-8 support. To do this you must set --enable-utf8 when -running "configure". This file can be also fed directly to the perltest script, -provided you are running Perl 5.8 or higher. (For Perl 5.6, a small patch, -commented in the script, can be be used.) - -The fifth test checks error handling with UTF-8 encoding, and internal UTF-8 -features of PCRE that are not relevant to Perl. - -The sixth and test checks the support for Unicode character properties. It it -not run automatically unless PCRE is built with Unicode property support. To to -this you must set --enable-unicode-properties when running "configure". - -The seventh, eighth, and ninth tests check the pcre_dfa_exec() alternative -matching function, in non-UTF-8 mode, UTF-8 mode, and UTF-8 mode with Unicode -property support, respectively. The eighth and ninth tests are not run -automatically unless PCRE is build with the relevant support. - - -Character tables ----------------- - -PCRE uses four tables for manipulating and identifying characters whose 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 chartables.c contains the default set of tables. This is -not supplied in the distribution, but 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 chartables.c and then re-building PCRE. If you do this, you should -probably also edit Makefile to ensure that the file doesn't ever get -re-generated. - -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. - -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. - - -Manifest --------- - -The distribution should contain the following files: - -(A) The actual source files of the PCRE library functions and their - headers: - - dftables.c auxiliary program for building chartables.c - - pcreposix.c ) - pcre_compile.c ) - pcre_config.c ) - pcre_dfa_exec.c ) - pcre_exec.c ) - pcre_fullinfo.c ) - pcre_get.c ) sources for the functions in the library, - pcre_globals.c ) and some internal functions that they use - pcre_info.c ) - pcre_maketables.c ) - pcre_ord2utf8.c ) - pcre_refcount.c ) - pcre_study.c ) - pcre_tables.c ) - pcre_try_flipped.c ) - pcre_ucp_searchfuncs.c) - pcre_valid_utf8.c ) - pcre_version.c ) - pcre_xclass.c ) - ucptable.c ) - - pcre_printint.src ) debugging function that is #included in pcretest, and - ) can also be #included in pcre_compile() - - pcre.h the public PCRE header file - pcreposix.h header for the external POSIX wrapper API - pcre_internal.h header for internal use - ucp.h ) headers concerned with - ucpinternal.h ) Unicode property handling - config.in template for config.h, which is built by configure - - pcrecpp.h the header file for the C++ wrapper - pcrecpparg.h.in "source" for another C++ header file - pcrecpp.cc ) - pcre_scanner.cc ) source for the C++ wrapper library - - pcre_stringpiece.h.in "source" for pcre_stringpiece.h, the header for the - C++ stringpiece functions - pcre_stringpiece.cc source for the C++ stringpiece functions - -(B) Auxiliary files: - - AUTHORS information about the author of PCRE - ChangeLog log of changes to the code - 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 - NEWS important changes in this release - NON-UNIX-USE notes on building PCRE on non-Unix systems - README this file - RunTest.in template for a Unix shell script for running tests - RunGrepTest.in template for a Unix shell script for pcregrep tests - config.guess ) files used by libtool, - config.sub ) used only when building a shared library - config.h.in "source" for the config.h header file - configure a configuring shell script (built by autoconf) - configure.ac the autoconf input used to build configure - doc/Tech.Notes notes on the encoding - doc/*.3 man page sources for the PCRE functions - doc/*.1 man page sources for pcregrep and pcretest - 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 - libpcre.pc.in "source" for libpcre.pc for pkg-config - ltmain.sh file used to build a libtool script - mkinstalldirs script for making install directories - pcretest.c comprehensive test program - pcredemo.c simple demonstration of coding calls to PCRE - perltest Perl test program - pcregrep.c source of a grep utility that uses PCRE - pcre-config.in source of script which retains PCRE information - pcrecpp_unittest.c ) - pcre_scanner_unittest.c ) test programs for the C++ wrapper - pcre_stringpiece_unittest.c ) - testdata/testinput* test data for main library tests - testdata/testoutput* expected test results - testdata/grep* input and output for pcregrep tests - -(C) Auxiliary files for Win32 DLL - - libpcre.def - libpcreposix.def - -(D) Auxiliary file for VPASCAL - - makevp.bat - -Philip Hazel -Email local part: ph10 -Email domain: cam.ac.uk -June 2006 diff --git a/ext/pcre/pcrelib/dftables.c b/ext/pcre/pcrelib/dftables.c deleted file mode 100644 index 5ba207aeb3..0000000000 --- a/ext/pcre/pcrelib/dftables.c +++ /dev/null @@ -1,172 +0,0 @@ -/************************************************* -* 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) 1997-2006 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 default -character tables for PCRE. The tables are built according to the default C -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 <ctype.h> -#include <stdio.h> -#include <string.h> - -#include "pcre_internal.h" - -#define DFTABLES /* pcre_maketables.c notices this */ -#include "pcre_maketables.c" - - -int main(int argc, char **argv) -{ -int i; -FILE *f; -const unsigned char *tables = pcre_maketables(); -const unsigned char *base_of_tables = tables; - -if (argc != 2) - { - fprintf(stderr, "dftables: one filename argument is required\n"); - return 1; - } - -f = fopen(argv[1], "wb"); -if (f == NULL) - { - fprintf(stderr, "dftables: failed to open %s for writing\n", argv[1]); - return 1; - } - -/* There are two 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 is automatically written by the dftables auxiliary \n" - "program. If you edit it by hand, you might like to edit the Makefile to \n" - "prevent its ever being regenerated.\n\n"); -fprintf(f, - "This file contains the default tables for characters with codes less than\n" - "128 (ASCII characters). These tables are used when no external tables are\n" - "passed to PCRE. */\n\n" - "const unsigned char _pcre_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 chartables.c */\n"); - -fclose(f); -free((void *)base_of_tables); -return 0; -} - -/* End of dftables.c */ diff --git a/ext/pcre/pcrelib/doc/Tech.Notes b/ext/pcre/pcrelib/doc/Tech.Notes deleted file mode 100644 index 21dbe1f9b5..0000000000 --- a/ext/pcre/pcrelib/doc/Tech.Notes +++ /dev/null @@ -1,348 +0,0 @@ -Technical Notes about PCRE --------------------------- - -These are very rough technical notes that record potentially useful information -about PCRE internals. - -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". 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 needed, for a number of reasons. PCRE works -by running a very degenerate first pass to calculate a maximum store size, and -then a second pass to do the real compile - which may use a bit less than the -predicted amount of store. The idea is that this is going to turn out faster -because the first pass is degenerate and the second pass can just store stuff -straight into the vector, which it knows is big enough. It does make the -compiling functions bigger, of course, but they have become quite big anyway to -handle all the Perl stuff. - -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. 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. - -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. - -Format of compiled patterns ---------------------------- - -The compiled form of a pattern is a vector of bytes, containing items of -variable length. The first byte in an item is an opcode, and the length of the -item is either implicit in the opcode or contained in the data bytes that -follow it. - -In many cases below "two-byte" data values are specified. This is in fact just -a default. PCRE can be compiled to use 3-byte or 4-byte values (impairing the -performance). This 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. - -A list of all the opcodes follows: - -Opcodes with no following data ------------------------------- - -These items are all just one byte long - - OP_END end of pattern - OP_ANY match any character - 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_CIRC ^ (start of data, or after \n in multiline) - OP_NOT_WORD_BOUNDARY \W - OP_WORD_BOUNDARY \w - OP_NOT_DIGIT \D - OP_DIGIT \d - OP_NOT_WHITESPACE \S - OP_WHITESPACE \s - 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 \n in multiline) - OP_EXTUNI match an extended Unicode character - - -Repeating single characters ---------------------------- - -The common repeats (*, +, ?) when applied to a single character use the -following opcodes: - - OP_STAR - OP_MINSTAR - OP_PLUS - OP_MINPLUS - OP_QUERY - OP_MINQUERY - -In ASCII mode, these are two-byte items; in UTF-8 mode, the length is variable. -Those with "MIN" in their name are the minimizing versions. Each is followed by -the character that is to be repeated. Other repeats make use of - - OP_UPTO - OP_MINUPTO - OP_EXACT - -which are followed by a two-byte count (most significant first) and 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). - - -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 -byte. The opcodes are: - - OP_TYPESTAR - OP_TYPEMINSTAR - OP_TYPEPLUS - OP_TYPEMINPLUS - OP_TYPEQUERY - OP_TYPEMINQUERY - OP_TYPEUPTO - OP_TYPEMINUPTO - 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 bytes 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 bytes: OP_PROP or OP_NOTPROP and then the desired property type and -value. - - -Matching literal characters ---------------------------- - -The OP_CHAR opcode is followed by a single character that is to be matched -casefully. For caseless matching, OP_CHARNC is used. In UTF-8 mode, the -character may be more than one byte long. (Earlier versions of PCRE used -multi-character strings, but this was changed to allow some new features to be -added.) - - -Character classes ------------------ - -If there is only one character, OP_CHAR or OP_CHARNC is used for a positive -class, and OP_NOT for a negative one (that is, for something like [^a]). -However, in UTF-8 mode, the use of OP_NOT applies only to characters with -values < 128, because OP_NOT is confined to single bytes. - -Another set of repeating opcodes (OP_NOTSTAR etc.) are used for a repeated, -negated, single-character class. The normal ones (OP_STAR etc.) are used for a -repeated positive single-character class. - -When there's 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 bit map containing a 1 -bit for every character that is acceptable. The bits are counted from the least -significant end of each byte. - -The reason for having both OP_CLASS and OP_NCLASS is so that, in UTF-8 mode, -subject characters with values greater than 256 can be handled correctly. For -OP_CLASS they don't match, whereas for OP_NCLASS they do. - -For classes containing characters with values > 255, OP_XCLASS is used. It -optionally uses a bit map (if any characters lie within it), followed by a list -of pairs and single characters. There is a flag character than indicates -whether it's a positive or a negative class. - - -Back references ---------------- - -OP_REF is followed by two bytes containing the reference number. - - -Repeating character classes and back references ------------------------------------------------ - -Single-character classes are handled specially (see above). This applies to -OP_CLASS and OP_REF. 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-byte items. The others are followed by -four bytes of data, comprising the minimum and maximum repeat counts. - - -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. - -Non-capturing brackets use the opcode OP_BRA, while capturing brackets use -OP_BRA+1, OP_BRA+2, etc. [Note for North Americans: "bracket" to some English -speakers, including myself, can be round, square, curly, or pointy. Hence this -usage.] - -Originally PCRE was limited to 99 capturing brackets (so as not to use up all -the opcodes). From release 3.5, there is no limit. What happens is that the -first ones, up to EXTRACT_BASIC_MAX are handled with separate opcodes, as -above. If there are more, the opcode is set to EXTRACT_BASIC_MAX+1, and the -first operation in the bracket is OP_BRANUMBER, followed by a 2-byte bracket -number. This opcode is ignored while matching, but is fished out when handling -the bracket itself. (They could have all been done like this, but I was making -minimal changes.) - -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. - -OP_KET is used for subpatterns that do not repeat indefinitely, while -OP_KETRMIN and OP_KETRMAX are used for indefinite repetitions, minimally or -maximally respectively. All three are followed by LINK_SIZE bytes giving (as a -positive number) the offset back to the matching OP_BRA opcode. - -If a subpattern is quantified such that it is permitted to match zero times, it -is preceded by one of OP_BRAZERO or OP_BRAMINZERO. These are single-byte -opcodes which tell the matcher that skipping this subpattern entirely is a -valid branch. - -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)?)?)?. - - -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 count of the number of characters to move -back the pointer in the subject string. When operating in UTF-8 mode, the count -is a character count rather than a byte count. A separate count is present in -each alternative of a lookbehind assertion, allowing them to have different -fixed lengths. - - -Once-only subpatterns ---------------------- - -These are also just like other subpatterns, but they start with the opcode -OP_ONCE. - - -Conditional subpatterns ------------------------ - -These are like other subpatterns, but they start with the opcode OP_COND. 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 containing the -reference number. If the condition is "in recursion" (coded as "(?(R)"), the -same scheme is used, with a "reference number" of 0xffff. 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 byte 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 value giving the offset in the pattern to the -start of the following item, and another two-byte item giving the length of the -next item. - - -Changing options ----------------- - -If any of the /i, /m, or /s options are changed within a pattern, an OP_OPT -opcode is compiled, followed by one byte containing the new settings of these -flags. If there are several alternatives, there is an occurrence of OP_OPT at -the start of all those following the first options change, to set appropriate -options for the start of the alternative. Immediately after the end of the -group there is another such item to reset the flags to their previous values. A -change of flag right at the very start of the pattern can be handled entirely -at compile time, and so does not cause anything to be put into the compiled -data. - -Philip Hazel -June 2006 diff --git a/ext/pcre/pcrelib/doc/pcre.txt b/ext/pcre/pcrelib/doc/pcre.txt deleted file mode 100644 index d6c204b574..0000000000 --- a/ext/pcre/pcrelib/doc/pcre.txt +++ /dev/null @@ -1,5153 +0,0 @@ ------------------------------------------------------------------------------ -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. 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. The current implementation of PCRE (release - 6.x) corresponds approximately with Perl 5.8, including support for - UTF-8 encoded strings and Unicode general category properties. However, - this support has to be explicitly enabled; it is not the default. - - In addition to the Perl-compatible matching function, PCRE also con- - tains an alternative matching function that matches the same compiled - patterns in a different 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. This is now - included as part of the PCRE distribution. The pcrecpp page has details - of this interface. Other people's contributions 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. - - 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 file - in the source distribution. - - The library 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_", 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 are concatenated, for ease - of searching. The sections are as follows: - - pcre this document - 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 - pcregrep description of the pcregrep command - 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 - pcreprecompile details of saving and re-using precompiled patterns - pcresample discussion of the sample program - pcrestack discussion of stack usage - pcretest description of the pcretest testing command - - In addition, in the "man" and HTML formats, there is a short page for - each C library function, listing its arguments and results. - - -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 65539 (sic) bytes if PCRE - is compiled with the default internal linkage size of 2. If you want to - process regular expressions that are truly enormous, you can compile - PCRE with an internal linkage size of 3 or 4 (see the README file in - the source distribution and the pcrebuild documentation for details). - In these cases the limit is substantially larger. However, the speed - of execution will be slower. - - All values in repeating quantifiers must be less than 65536. The maxi- - mum compiled length of subpattern with an explicit repeat count is - 30000 bytes. The maximum number of capturing subpatterns is 65535. - - There is no limit to the number of non-capturing subpatterns, but the - maximum depth of nesting of all kinds of parenthesized subpattern, - including capturing subpatterns, assertions, and other types of subpat- - tern, is 200. - - The maximum length of name for a named subpattern is 32, and the maxi- - mum number of named subpatterns is 10000. - - 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. - - -UTF-8 AND UNICODE PROPERTY SUPPORT - - From release 3.3, PCRE has had some support for character strings - encoded in the UTF-8 format. For release 4.0 this was greatly extended - to cover most common requirements, and in release 5.0 additional sup- - port for Unicode general category properties was added. - - In order process UTF-8 strings, you must build PCRE to include UTF-8 - support in the code, and, in addition, you must call pcre_compile() - with the PCRE_UTF8 option flag. When you do this, both the pattern and - any subject strings that are matched against it are treated as UTF-8 - strings instead of just strings of bytes. - - If you compile PCRE with UTF-8 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 flag in several places, so should - not be very large. - - If PCRE is built with Unicode character property support (which implies - UTF-8 support), the escape sequences \p{..}, \P{..}, and \X are sup- - ported. 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 sup- - ported. For example, \p{L} matches a letter. Its Perl synonym, \p{Let- - ter}, is not supported. Furthermore, in Perl, many properties may - optionally be prefixed by "Is", for compatibility with Perl 5.6. PCRE - does not support this. - - The following comments apply when PCRE is running in UTF-8 mode: - - 1. When you set the PCRE_UTF8 flag, the strings passed as patterns and - subjects are checked for validity on entry to the relevant functions. - If an invalid UTF-8 string is passed, an error return is given. In some - situations, you may already know that your strings are valid, and - therefore want to skip these checks in order to improve performance. 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 to PCRE when - PCRE_NO_UTF8_CHECK is set, the results are undefined. Your program may - crash. - - 2. An unbraced hexadecimal escape sequence (such as \xb3) matches a - two-byte UTF-8 character if the value is greater than 127. - - 3. Octal numbers up to \777 are recognized, and match two-byte UTF-8 - characters for values greater than \177. - - 4. Repeat quantifiers apply to complete UTF-8 characters, not to indi- - vidual bytes, for example: \x{100}{3}. - - 5. The dot metacharacter matches one UTF-8 character instead of a sin- - gle byte. - - 6. The escape sequence \C can be used to match a single byte in UTF-8 - mode, but its use can lead to some strange effects. This facility is - not available in the alternative matching function, pcre_dfa_exec(). - - 7. The character escapes \b, \B, \d, \D, \s, \S, \w, and \W correctly - test characters of any code value, but the characters that PCRE recog- - nizes as digits, spaces, or word characters remain the same set as - before, all with values less than 256. This remains true even when PCRE - includes Unicode property support, because to do otherwise would slow - down PCRE in many common cases. If you really want to test for a wider - sense of, say, "digit", you must use Unicode property tests such as - \p{Nd}. - - 8. Similarly, characters that match the POSIX named character classes - are all low-valued characters. - - 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. Even when Unicode property - support is available, 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 mappings in Unicode; these are not sup- - ported by PCRE. - - -AUTHOR - - Philip Hazel - University Computing Service, - Cambridge CB2 3QG, 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 initial and sur- - name, separated by a dot, at the domain ucs.cam.ac.uk. - -Last updated: 05 June 2006 -Copyright (c) 1997-2006 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. They are all selected, or dese- - lected, by providing options to the configure script that is run before - the make command. 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 describe certain 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 complementary - option always exists as well, but as it specifies the default, it is - not described. - - -C++ SUPPORT - - By default, the configure script will search for a C++ compiler and C++ - header files. If it finds them, it automatically builds the C++ wrapper - library for PCRE. You can disable this by adding - - --disable-cpp - - to the configure command. - - -UTF-8 SUPPORT - - To build PCRE with support for UTF-8 character strings, add - - --enable-utf8 - - to the configure command. Of itself, this does not make PCRE treat - strings as UTF-8. As well as compiling PCRE with this option, you also - have have to set the PCRE_UTF8 option when you call the pcre_compile() - function. - - -UNICODE CHARACTER PROPERTY SUPPORT - - UTF-8 support allows PCRE to process character values greater than 255 - in the strings that it handles. On its own, however, it does not pro- - vide any facilities for accessing the properties of such characters. 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-8 support, even if you have - not explicitly requested it. - - Including Unicode property support adds around 90K of tables to the - PCRE library, approximately doubling its size. Only the general cate- - gory properties such as Lu and Nd are supported. Details are given in - the pcrepattern documentation. - - -CODE VALUE OF NEWLINE - - By default, PCRE interprets character 10 (linefeed, LF) as indicating - the end of a line. This is the normal newline character on Unix-like - systems. You can compile PCRE to use character 13 (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. 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. - - -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. - - -POSIX MALLOC USAGE - - When PCRE is called through the POSIX interface (see the pcreposix doc- - umentation), 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 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 enormous patterns, so it - is possible to compile PCRE to use three-byte or four-byte offsets by - adding a setting such as - - --with-link-size=3 - - to the configure command. The value given must be 2, 3, or 4. Using - longer offsets slows down the operation of PCRE because it has to load - additional bytes when handling them. - - If you build PCRE with an increased link size, test 2 (and test 5 if - you are using UTF-8) will fail. Part of the output of these tests is a - representation of the compiled pattern, and this changes with the link - size. - - -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. Separate functions are provided 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 the - standard malloc() and free() functions. PCRE runs noticeably more - slowly when built in this way. This option affects only the pcre_exec() - function; it is not relevant for the the pcre_dfa_exec() function. - - -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. - - -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). - PCRE can, however, be compiled to run in an EBCDIC environment by - adding - - --enable-ebcdic - - to the configure command. - -Last updated: 06 June 2006 -Copyright (c) 1997-2006 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() function. This works in the same was as Perl's matching - function, and provides a Perl-compatible matching operation. - - An alternative algorithm is provided by the pcre_dfa_exec() function; - this operates in a different way, and is not Perl-compatible. It 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 DFA 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 DFA MATCHING ALGORITHM - - DFA stands for "deterministic finite automaton", but you do not need to - understand the origins of that name. 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, charac- - ter by character, and as it does this, it remembers all the paths - through the tree that represent valid matches. - - 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. In PCRE, there is an option to stop the algorithm after the first - match (which is necessarily the shortest) has been 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 "cat", "cater", and "caterpillar" that start - at the fourth character of the subject. The algorithm does not automat- - ically 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 DFA 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. - - 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 are not supported. - - 5. 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. - - 6. The \C escape sequence, which (in the standard algorithm) matches a - single byte, even in UTF-8 mode, is not supported because the DFA algo- - rithm moves through the subject string one character at a time, for all - active paths through the tree. - - -ADVANTAGES OF THE DFA ALGORITHM - - Using the DFA matching algorithm provides the following advantages: - - 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. There is much better support for partial matching. The restrictions - on the content of the pattern that apply when using the standard algo- - rithm for partial matching do not apply to the DFA algorithm. For non- - anchored patterns, the starting position of a partial match is avail- - able. - - 3. Because the DFA algorithm scans the subject string just once, and - never needs to backtrack, it is possible to pass very long subject - strings to the matching function in several pieces, checking for par- - tial matching each time. - - -DISADVANTAGES OF THE DFA ALGORITHM - - The DFA 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. The "atomic group" feature of PCRE regular expressions is supported, - but does not provide the advantage that it does for the standard algo- - rithm. - -Last updated: 06 June 2006 -Copyright (c) 1997-2006 University of Cambridge. ------------------------------------------------------------------------------- - - -PCREAPI(3) PCREAPI(3) - - -NAME - PCRE - Perl-compatible regular expressions - - -PCRE NATIVE API - - #include <pcre.h> - - 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); - - 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); - - 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); - - const unsigned char *pcre_maketables(void); - - int pcre_fullinfo(const pcre *code, const pcre_extra *extra, - int what, void *where); - - int pcre_info(const pcre *code, int *optptr, int *firstcharptr); - - int pcre_refcount(pcre *code, int adjust); - - int pcre_config(int what, void *where); - - char *pcre_version(void); - - 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 API OVERVIEW - - PCRE has its own native API, which is described in this document. There - is also a set of wrapper functions that correspond to the POSIX regular - expression API. These are described in the pcreposix documentation. - Both of these APIs define a set of C function calls. A C++ wrapper is - 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 systems the 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 num- - bers for the library. Applications can use these to include support - for different releases of PCRE. - - 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 source distribution. The pcresample documentation describes how to - run it. - - 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). 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 documenta- - tion. - - 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; pcre_info() is an obsolete version that returns only - some of the available information, but is retained for backwards com- - patibility. 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 three different conventions for indicating line breaks in - strings: a single CR character, a single LF character, or the two-char- - acter sequence CRLF. All three are used as "standard" by different - operating systems. When PCRE is built, a default can be specified. The - default default is LF, which is the Unix standard. When PCRE is run, - the default can be overridden, either when a pattern is compiled, or - when it is matched. - - In the PCRE documentation the word "newline" is used to mean "the char- - acter or pair of characters that indicate a line break". - - -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. - - -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. - - -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 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. - - 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_NEWLINE - - The output is an integer whose value specifies the default character - sequence that is recognized as meaning "newline". The three values that - are supported are: 10 for LF, 13 for CR, and 3338 for CRLF. The default - should normally be the standard sequence for your operating system. - - PCRE_CONFIG_LINK_SIZE - - The output is an integer that contains the number of bytes used for - internal linkage in compiled regular expressions. The value is 2, 3, or - 4. Larger values allow larger regular expressions to be compiled, at - the expense of slower matching. 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. - - 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 an integer that gives the default limit for the number 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 an 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. - - 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 independent bits that affect the compila- - tion. 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, can also be set and unset from within the - pattern (see the detailed description in the pcrepattern documenta- - tion). For these options, the contents of the options argument speci- - fies their initial settings at the start of compilation and execution. - The PCRE_ANCHORED and PCRE_NEWLINE_xxx 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. The offset from the start of the pattern to the charac- - ter where 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. - - 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_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 metacharater in the pattern matches all char- - acters, including those that indicate newline. Without it, 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 - newlines, independent of the setting 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, whitespace 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. - - This option makes it possible to include comments inside complicated - patterns. Note, however, that this applies only to data characters. - Whitespace characters may never appear within special character - sequences in a pattern, for example within the sequence (?( which - introduces 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 a warning for this.) - 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_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 - - 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 both of them specifies that a newline is indicated by the two- - character CRLF sequence. For convenience, PCRE_NEWLINE_CRLF is defined - to contain both bits. The only time that a line break is relevant when - compiling a pattern is if PCRE_EXTENDED is set, and an unescaped # out- - side a character class is encountered. This indicates a comment that - lasts until after the next newline. - - The newline option 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. - - 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 character strings. - However, it is available only when PCRE is built to include UTF-8 sup- - port. If not, the use of this option provokes an error. Details of how - this option changes the behaviour of PCRE are given in the section on - UTF-8 support in the main pcre page. - - PCRE_NO_UTF8_CHECK - - When PCRE_UTF8 is set, the validity of the pattern as a UTF-8 string is - automatically checked. If an invalid UTF-8 sequence of bytes 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 reasons, 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 UTF-8 validity check- - ing 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. - - 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 operand of unlimited repeat could match the empty string - 11 internal error: unexpected repeat - 12 unrecognized character after (? - 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 parentheses nested too deeply - 20 regular expression 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 not compiled with PCRE_UTF8 support - 33 spare error - 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, \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 after (?P - 43 two named subpatterns have the same name - 44 invalid UTF-8 string - 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 10,000) - 50 repeated subpattern is too long - 51 octal value is greater than \377 (not in UTF-8 mode) - - -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(). However, a pcre_extra block also contains 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 additional information - pcre_study() returns NULL. In that circumstance, if the calling program - wants to pass any of the other fields to pcre_exec(), it must set up - its own pcre_extra block. - - The second argument of pcre_study() contains option bits. At present, - no options are defined, and this argument should always be zero. - - 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. - - This is a typical call to pcre_study(): - - pcre_extra *pe; - pe = pcre_study( - re, /* result of pcre_compile() */ - 0, /* no options exist */ - &error); /* set to NULL or points to a message */ - - At present, studying a pattern is useful only for non-anchored patterns - that do not have a single fixed starting character. A bitmap of possi- - ble starting bytes is created. - - -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. Higher-valued codes never match - escapes such as \w or \d, but can be tested with \p if PCRE is built - with Unicode character property support. The use of locales with Uni- - code is discouraged. - - An internal set of tables is created in the default C locale when PCRE - is built. This is used when the final argument of pcre_compile() is - NULL, and is sufficient for many applications. An alternative set of - tables can, however, be supplied. These may be created in a different - locale from the default. As more and more applications change to using - Unicode, 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); - - 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 obsolete pcre_info() function, which is neverthe- - less retained for backwards compability (and is documented below). - - 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_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. 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() */ - pe, /* 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 byte of any matched string, for a - non-anchored pattern. The fourth argument should point to an int vari- - able. (This option used to be called PCRE_INFO_FIRSTCHAR; the old name - is still recognized for backwards compatibility.) - - If there is a fixed first byte, for example, from a pattern such as - (cat|cow|coyote). Otherwise, 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 bytes for the first byte in any - matching string, a pointer to the table is returned. Otherwise NULL is - returned. The fourth argument should point to an unsigned char * vari- - able. - - PCRE_INFO_LASTLITERAL - - Return the value of the rightmost literal byte that must exist in any - matched string, other than at its start, if such a byte has been - recorded. The fourth argument should point to an int variable. If there - is no such byte, -1 is returned. For anchored patterns, a last literal - byte 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_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 (a pointer to char). The - first two bytes of each entry are the number of the capturing parenthe- - sis, most significant byte first. The rest of the entry is the corre- - sponding name, zero terminated. The names are in alphabetical order. - When PCRE_DUPNAMES is set, duplicate names are in order of their paren- - theses numbers. For example, consider the following pattern (assume - PCRE_EXTENDED is set, so white space - including newlines - is - ignored): - - (?P<date> (?P<year>(\d\d)?\d\d) - - (?P<month>\d\d) - (?P<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_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 within the pattern itself. - - 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, that is, the value that was - passed as the argument to pcre_malloc() when PCRE was getting memory in - which to place the compiled data. The fourth argument should point to a - size_t variable. - - PCRE_INFO_STUDYSIZE - - Return the size of the data block pointed to by the study_data field in - a pcre_extra block. That is, it is the value that was passed to - pcre_malloc() when PCRE was getting memory into which to place the data - created by pcre_study(). The fourth argument should point to a size_t - variable. - - -OBSOLETE INFO FUNCTION - - int pcre_info(const pcre *code, int *optptr, int *firstcharptr); - - The pcre_info() function is now obsolete because its interface is too - restrictive to return all the available data about a compiled pattern. - New programs should use pcre_fullinfo() instead. The yield of - pcre_info() is the number of capturing subpatterns, or one of the fol- - lowing negative numbers: - - PCRE_ERROR_NULL the argument code was NULL - PCRE_ERROR_BADMAGIC the "magic number" was not found - - If the optptr argument is not NULL, a copy of the options with which - the pattern was compiled is placed in the integer it points to (see - PCRE_INFO_OPTIONS above). - - If the pattern is not anchored and the firstcharptr argument is not - NULL, it is used to pass back information about the first character of - any matched string (see PCRE_INFO_FIRSTBYTE above). - - -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 - has been studied, the result of the study should be passed in the extra - argument. 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 sec- - tion 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; - unsigned long int match_limit; - unsigned long int match_limit_recursion; - void *callout_data; - const unsigned char *tables; - - The flags field is a bitmap that specifies which of the other fields - are set. The flag bits are: - - PCRE_EXTRA_STUDY_DATA - PCRE_EXTRA_MATCH_LIMIT - PCRE_EXTRA_MATCH_LIMIT_RECURSION - PCRE_EXTRA_CALLOUT_DATA - PCRE_EXTRA_TABLES - - Other flag bits should be set to zero. The study_data field is set in - the pcre_extra block that is returned by pcre_study(), together with - the appropriate flag bit. You should not set this yourself, but you may - add to the block by setting the 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 the use of nested unlimited - repeats. - - Internally, PCRE uses a function called match() which it calls repeat- - edly (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. - - 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 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. - - 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 pcre_callout field is used in conjunction with the "callout" fea- - ture, which 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. - - 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_NO_UTF8_CHECK and - PCRE_PARTIAL. - - 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_NEWLINE_CR - PCRE_NEWLINE_LF - PCRE_NEWLINE_CRLF - - These options override the newline definition that was chosen or - defaulted when the pattern was compiled. For details, see the descrip- - tion pcre_compile() above. During matching, the newline choice affects - the behaviour of the dot, circumflex, and dollar metacharacters. - - 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 the - 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". - - Perl has no direct equivalent of PCRE_NOTEMPTY, but it does make a spe- - cial 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 offset with PCRE_NOTEMPTY and PCRE_ANCHORED, and then - if that fails by advancing the starting offset (see below) and trying - an ordinary match again. There is some code that demonstrates how to do - this in the pcredemo.c sample program. - - 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 value of startoffset is also checked to ensure that it - points to the start of a UTF-8 character. If an invalid UTF-8 sequence - of bytes is found, pcre_exec() returns the error PCRE_ERROR_BADUTF8. If - startoffset contains an invalid value, 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 UTF-8 character. When PCRE_NO_UTF8_CHECK is - set, the effect of passing an invalid UTF-8 string as a subject, or a - value of startoffset that does not point to the start of a UTF-8 char- - acter, is undefined. Your program may crash. - - PCRE_PARTIAL - - This option turns on the partial matching feature. If the subject - string fails to match the pattern, but at some point during the match- - ing process the end of the subject was reached (that is, the subject - partially matches the pattern and the failure to match occurred only - because there were not enough subject characters), pcre_exec() returns - PCRE_ERROR_PARTIAL instead of PCRE_ERROR_NOMATCH. When PCRE_PARTIAL is - used, there are restrictions on what may appear in the pattern. These - are discussed 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 length, and a starting byte offset in startoffset. In UTF-8 - mode, the byte offset must point to the start of a UTF-8 character. - Unlike the pattern string, the subject may contain binary zero bytes. - 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. - - 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. - - 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 integer - offsets whose address is passed in ovector. The number of elements in - the vector 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 length 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 a pair is set to the offset of the first character in a sub- - string, and the second is set to the offset of the first character - after the end of a substring. The first pair, ovector[0] and ovec- - tor[1], identify the portion of the subject string matched by the - entire pattern. The next pair is used for the first capturing subpat- - tern, 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. In particular, if the substring off- - sets are not of interest, pcre_exec() may be called with ovector passed - as NULL and ovecsize as zero. However, if the pattern 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. - - The pcre_info() 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. However, you can refer to the offsets - for the second and third capturing subpatterns if you wish (assuming - the vector is large enough, of course). - - 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_NODE (-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. - - 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_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_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. - - PCRE_ERROR_BADUTF8_OFFSET (-11) - - The UTF-8 byte sequence that was passed as a subject was valid, but the - value of startoffset did not point to the beginning of a UTF-8 charac- - ter. - - 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) - - The PCRE_PARTIAL option was used with a compiled pattern containing - items that are not supported for partial matching. See the pcrepartial - documentation for details of 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. - - -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 - - 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 - - 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(?P<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. - - -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. 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 docu- - mentation. 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, an empty string is - returned. The pcre_get_stringnumber() function returns one of the num- - bers 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 if there - are none. The format of the table is described above in the section - entitled Information about a pattern. Given all the relevant entries - for the name, you can extract each of their numbers, and hence the cap- - tured 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. - - -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 "DFA" matching algorithm. This has - different characteristics to the normal algorithm, and is not compati- - ble with Perl. Some of the features of PCRE patterns are not supported. - Nevertheless, there are times when this kind of matching can be useful. - For a discussion of the two matching algorithms, see the pcrematching - documentation. - - 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_NO_UTF8_CHECK, - PCRE_PARTIAL, PCRE_DFA_SHORTEST, and PCRE_DFA_RESTART. All but the last - three of these are the same as for pcre_exec(), so their description is - not repeated here. - - PCRE_PARTIAL - - This has the same general effect as it does for pcre_exec(), but the - details are slightly different. When PCRE_PARTIAL is set for - pcre_dfa_exec(), 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 pos- - sibility. The portion of the string that provided the partial match is - set as the first matching string. - - 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 DFA - 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() is called with the PCRE_PARTIAL option, and - returns a partial match, it is possible to call it again, with addi- - tional 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. 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. - - 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 in - a pattern that uses a back reference for the condition. This is 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 field. This is not supported - (it is meaningless). - - 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. - -Last updated: 08 June 2006 -Copyright (c) 1997-2006 University of Cambridge. ------------------------------------------------------------------------------- - - -PCRECALLOUT(3) PCRECALLOUT(3) - - -NAME - PCRE - Perl-compatible regular expressions - - -PCRE CALLOUTS - - int (*pcre_callout)(pcre_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. 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)eabc(?C2)def - - If the PCRE_AUTO_CALLOUT option bit is set when pcre_compile() is - called, 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. - - -MISSING CALLOUTS - - You should be aware that, because of optimizations in the way PCRE - matches patterns, 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. - - -THE CALLOUT INTERFACE - - During matching, when PCRE reaches a callout point, the external func- - tion defined by pcre_callout is called (if it is set). This applies to - both the pcre_exec() and the pcre_dfa_exec() matching functions. The - only argument to the callout function is a pointer to a pcre_callout - block. This structure contains the following fields: - - int version; - int callout_number; - int *offset_vector; - const char *subject; - 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; - - The version field is an integer containing the version number of the - block format. The initial version was 0; the current version is 1. 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 pcre_exec() or pcre_dfa_exec(). When - pcre_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 pcre_dfa_exec() - this field is not useful. - - The subject and subject_length fields contain copies of the values that - were passed to pcre_exec(). - - The start_match field contains the offset within the subject at which - the current match attempt started. 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() function is used, the capture_top field contains - one more than the number of the highest numbered captured substring so - far. If no substrings have been captured, the value of capture_top is - one. This is always the case when pcre_dfa_exec() is used, because it - does 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 when pcre_dfa_exec() is used. - - The callout_data field contains a value that is passed to pcre_exec() - or pcre_dfa_exec() specifically so that it can be passed back in call- - outs. It is passed in the pcre_callout field of the pcre_extra data - structure. If no such data was passed, the value of callout_data in a - pcre_callout block is NULL. There is a description of the pcre_extra - structure in the pcreapi documentation. - - The pattern_position field is present from version 1 of the pcre_call- - out 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 pcre_call- - out structure. It contains the length of the next item to be matched in - the pattern string. When the callout immediately precedes an alterna- - tion 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. - - -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, and - pcre_exec() (or pcre_dfa_exec()) 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. - -Last updated: 28 February 2005 -Copyright (c) 1997-2005 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 5.8. - - 1. PCRE has only a subset of Perl's UTF-8 and Unicode support. Details - of what it does have are given in the section on UTF-8 support in the - main pcre page. - - 2. PCRE does not allow repeat quantifiers on lookahead assertions. Perl - permits them, 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. - - 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. In fact these are implemented by Perl's general string-han- - dling and are not part of its pattern matching engine. If any of these - are encountered by PCRE, an error is generated. - - 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&. - - 7. 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$xyz - - The \Q...\E sequence is recognized both inside and outside character - classes. - - 8. Fairly obviously, PCRE does not support the (?{code}) and (?p{code}) - constructions. However, there is support for recursive patterns using - the non-Perl items (?R), (?number), and (?P>name). Also, the PCRE - "callout" feature allows an external function to be called during pat- - tern matching. See the pcrecallout documentation for details. - - 9. There are some differences that are concerned with the settings of - captured strings when part of a pattern is repeated. For example, - matching "aba" against the pattern /^(a(b)?)+$/ in Perl leaves $2 - unset, but in PCRE it is set to "b". - - 10. PCRE provides some extensions to the Perl regular expression facil- - ities: - - (a) Although lookbehind assertions 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 - 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, and PCRE_NO_AUTO_CAP- - TURE options for pcre_exec() have no Perl equivalents. - - (g) The (?R), (?number), and (?P>name) constructs allows for recursive - pattern matching (Perl can do this using the (?p{code}) construct, - which PCRE cannot support.) - - (h) PCRE supports named capturing substrings, using the Python syntax. - - (i) PCRE supports the possessive quantifier "++" syntax, taken from - Sun's Java package. - - (j) The (R) condition, for testing recursion, is a PCRE extension. - - (k) The callout facility is PCRE-specific. - - (l) The partial matching facility is PCRE-specific. - - (m) Patterns compiled by PCRE can be saved and re-used at a later time, - even on different hosts that have the other endianness. - - (n) The alternative matching function (pcre_dfa_exec()) matches in a - different way and is not Perl-compatible. - -Last updated: 06 June 2006 -Copyright (c) 1997-2006 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 supported by PCRE - are described below. Regular expressions are also described in the Perl - documentation and 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 descrip- - tion 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 character strings. To use - this, you must build PCRE to include UTF-8 support, and then call - pcre_compile() with the PCRE_UTF8 option. How this affects pattern - matching is mentioned in several places below. There is also a summary - of UTF-8 features in the section on UTF-8 support in the main pcre - page. - - The remainder of this document discusses the patterns that are sup- - ported by PCRE when its main matching function, pcre_exec(), is used. - From release 6.0, PCRE offers a second matching function, - pcre_dfa_exec(), which matches using a different algorithm that is not - Perl-compatible. The advantages and disadvantages of the alternative - function, and how it differs from the normal function, are discussed in - the pcrematching page. - - 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 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 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-8 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 in 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 non-alphanumeric character, 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 \\. - - If a pattern is compiled with the PCRE_EXTENDED option, whitespace 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 whitespace 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. - - 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 usually 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 character - \e escape (hex 1B) - \f formfeed (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.. - - 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, but \c{ becomes hex 3B, while \c; - becomes hex 7B. - - After \x, from zero to two hexadecimal digits are read (letters can be - in upper or lower case). Any number of hexadecimal digits may appear - between \x{ and }, but the value of the character code must be less - than 256 in non-UTF-8 mode, and less than 2**31 in UTF-8 mode (that is, - the maximum hexadecimal value is 7FFFFFFF). If characters other than - hexadecimal digits appear between \x{ and }, or if there is no termi- - nating }, 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. - - Characters whose value is less than 256 can be defined by either of the - two syntaxes for \x. There is no difference in the way they are han- - dled. For example, \xdc is exactly the same as \x{dc}. - - 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, ane uses them to gen- - erate a data character. Any subsequent digits stand for themselves. In - non-UTF-8 mode, the value of a character specified in octal must be - less than \400. In UTF-8 mode, values up to \777 are permitted. 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 byte consisting entirely of 1 bits - \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, the sequence \b is interpreted as the backspace character (hex - 08), and the sequence \X is interpreted as the character "X". Outside a - character class, these sequences have different meanings (see below). - - Generic character types - - The third use of backslash is for specifying generic character types. - The following are always recognized: - - \d any decimal digit - \D any character that is not a decimal digit - \s any whitespace character - \S any character that is not a whitespace character - \w any "word" character - \W any "non-word" character - - Each pair of escape sequences partitions the complete set of characters - into two disjoint sets. Any given character matches one, and only one, - of each pair. - - These character type sequences can appear both inside and outside char- - acter 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, since 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 less than 256 that - is a letter or digit. 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 the "fr_FR" (French) locale, some character - codes greater than 128 are used for accented letters, and these are - matched by \w. - - In UTF-8 mode, characters with values greater than 128 never match \d, - \s, or \w, and always match \D, \S, and \W. This is true even when Uni- - code character property support is available. The use of locales with - Unicode is discouraged. - - Unicode character properties - - When PCRE is built with Unicode character property support, three addi- - tional escape sequences to match character properties are available - when UTF-8 mode is selected. They 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, and "Any", which matches - any character (including newline). Other properties such as "InMusical- - Symbols" 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, Bengali, Bopomofo, Braille, Buginese, Buhid, Cana- - dian_Aboriginal, Cherokee, Common, Coptic, Cypriot, Cyrillic, Deseret, - Devanagari, Ethiopic, Georgian, Glagolitic, Gothic, Greek, Gujarati, - Gurmukhi, Han, Hangul, Hanunoo, Hebrew, Hiragana, Inherited, Kannada, - Katakana, Kharoshthi, Khmer, Lao, Latin, Limbu, Linear_B, Malayalam, - Mongolian, Myanmar, New_Tai_Lue, Ogham, Old_Italic, Old_Persian, Oriya, - Osmanya, Runic, Shavian, Sinhala, Syloti_Nagri, Syriac, Tagalog, Tag- - banwa, Tai_Le, Tamil, Telugu, Thaana, Thai, Tibetan, Tifinagh, - Ugaritic, Yi. - - Each character has exactly one general category property, specified by - a two-letter abbreviation. For compatibility with Perl, negation 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 long synonyms for these properties 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. - - 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. - - Simple assertions - - The fourth 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 start of subject - \Z matches at end of subject or before newline at end - \z matches at end of subject - \G matches at first matching position in subject - - These assertions may not appear in character classes (but note that \b - has a different meaning, namely the backspace character, inside a char- - acter class). - - 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. - - 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) - - 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. In UTF-8 mode, the matched character may be - more than one byte long. When a line ending is defined as a single - character (CR or LF), dot never matches that character; when the two- - character sequence CRLF is used, dot does not match CR if it is immedi- - ately followed by LF, but otherwise it matches all characters (includ- - ing isolated CRs and LFs). - - 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 newline is defined as the two-character sequence CRLF, 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. - - -MATCHING A SINGLE BYTE - - Outside a character class, the escape sequence \C matches any one byte, - both in and out of UTF-8 mode. Unlike a dot, it always matches CR and - LF. The feature is provided in Perl in order to match individual bytes - in UTF-8 mode. Because it breaks up UTF-8 characters into individual - bytes, what remains in the string may be a malformed UTF-8 string. For - this reason, the \C escape sequence is best avoided. - - PCRE does not allow \C to appear in lookbehind assertions (described - below), because in UTF-8 mode this would make it impossible to calcu- - late the length of the lookbehind. - - -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. 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 UTF-8 - mode, the character may occupy more than one byte. 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 mode, characters with values greater than 255 can be included - in a class as a literal string of bytes, 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 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 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-8 - support. - - Characters that might indicate line breaks (CR and LF) 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]. In UTF-8 mode, ranges can include characters whose values - are greater than 255, for example [\x{100}-\x{2ff}]. - - 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 non-UTF-8 mode, if - character tables for the "fr_FR" locale are in use, [\xc8-\xcb] matches - accented E characters in both cases. In UTF-8 mode, PCRE supports the - concept of case for characters with values greater than 128 only when - it is compiled with Unicode property support. - - The character types \d, \D, \p, \P, \s, \S, \w, and \W may also appear - in a character class, and add the characters that they match to the - class. For example, [\dABCDEF] matches any hexadecimal digit. A circum- - flex 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. - - 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 - 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. - - In UTF-8 mode, characters with values greater than 128 do not match any - of the POSIX character classes. - - -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 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. - - When an option change occurs at top level (that is, not inside subpat- - tern 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 therefore show up - in data extracted by the pcre_fullinfo() function). - - An option change within a subpattern affects only that part of the cur- - rent pattern 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. - - 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. - - -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 one of the words "cat", "cataract", or "caterpillar". Without - the parentheses, it would match "cataract", "erpillar" or the 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 pcre_exec(). 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 pat- - tern - - 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, and the - maximum depth of nesting of all subpatterns, both capturing and non- - capturing, is 200. - - 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". - - -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, something that Perl does not provide. The Python syntax - (?P<name>...) is used. References to capturing parentheses from other - parts of the pattern, such as backreferences, recursion, and condi- - tions, 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. The PCRE API provides function calls for extracting the name-to- - number translation table from a compiled pattern. There is also a con- - venience 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. This 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: - - (?P<DN>Mon|Fri|Sun)(?:day)?| - (?P<DN>Tue)(?:sday)?| - (?P<DN>Wed)(?:nesday)?| - (?P<DN>Thu)(?:rsday)?| - (?P<DN>Sat)(?:urday)? - - There are five capturing substrings, but only one is ever set after a - match. 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 reference to a non- - unique named subpattern from elsewhere in the pattern, the one that - corresponds to the lowest number is used. For further details of the - interfaces for handling named subpatterns, see the pcreapi documenta- - tion. - - -REPETITION - - Repetition is specified by quantifiers, which can follow any of the - following items: - - a literal data character - the . metacharacter - the \C escape sequence - the \X escape sequence (in UTF-8 mode with Unicode properties) - an escape such as \d that matches a single character - a character class - a back reference (see next section) - a parenthesized subpattern (unless it is an assertion) - - 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-8 mode, quantifiers apply to UTF-8 characters rather than to - individual bytes. Thus, for example, \x{100}{2} matches two UTF-8 char- - acters, each of which is represented by a two-byte sequence. Similarly, - when Unicode property support is available, \X{3} matches three Unicode - extended sequences, each of which may be several bytes 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. - - For convenience (and historical compatibility) the three most common - quantifiers have single-character 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 which 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 . 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 - backreference elsewhere in the pattern, a match at the start may fail, - and a later one succeed. 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 and minimizing repetition, failure of what follows - normally causes the repeated item to be re-evaluated to see if a dif- - ferent number of repeats allows the rest of the pattern to match. Some- - times 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 would - give up immediately on failing to match "foo" the first time. The nota- - tion 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 - - 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 or processing of a possessive quantifier and the equivalent - atomic group. - - The possessive quantifier syntax is an extension to the Perl syntax. - 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. - - 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 sub- - pattern whose number is 10 or more. However, a back reference to any - subpattern is possible using named parentheses (see below). See also - the subsection entitled "Non-printing characters" above for further - details of the handling of digits following a backslash. - - 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. - - Back references to named subpatterns use the Python syntax (?P=name). - We could rewrite the above example as follows: - - (?P<p1>(?i)rah)\s+(?P=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. For example, the pattern - - (a|(bc))\2 - - always fails if it starts to match "a" rather than "bc". Because there - may be many capturing parentheses in a pattern, all digits following - the backslash are taken as part of a potential back reference 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 whitespace. Otherwise an empty comment (see "Com- - ments" below) can be used. - - 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. - - -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, and may not be - repeated, because it makes no sense to assert the same thing several - times. If any kind of assertion contains capturing subpatterns within - it, these are counted for the purposes of numbering the capturing sub- - patterns in the whole pattern. However, substring capturing is carried - out only for positive assertions, because it does not make sense for - negative assertions. - - 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. - - 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 (at least for 5.8), 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 if rewritten to use two top- - level branches: - - (?<=abc|abde) - - The implementation of lookbehind assertions is, for each alternative, - to temporarily move the current position back by the fixed width and - then try to match. If there are insufficient characters before the cur- - rent position, the match is deemed to fail. - - PCRE does not allow the \C escape (which matches a single byte in UTF-8 - mode) to appear in lookbehind assertions, because it makes it impossi- - ble to calculate the length of the lookbehind. The \X escape, which can - match different numbers of bytes, is also not permitted. - - Atomic groups can be used in conjunction with lookbehind assertions to - specify efficient matching at the end of the subject string. 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) - - or, equivalently, using the possessive quantifier syntax, - - ^.*+(?<=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 previous capturing subpat- - tern matched or not. 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. - - There are three kinds of condition. If the text between the parentheses - consists of a sequence of digits, or a sequence of alphanumeric charac- - ters and underscores, the condition is satisfied if the capturing sub- - pattern of that number or name has previously matched. There is a pos- - sible ambiguity here, because subpattern names may consist entirely of - digits. PCRE looks first for a named subpattern; if it cannot find one - and the text consists entirely of digits, it looks for a subpattern of - that number, which must be greater than zero. Using subpattern names - that consist entirely of digits is not recommended. - - 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 the first set - of parentheses matched or not. If they did, that is, if subject started - with an opening parenthesis, the condition is true, and so the yes-pat- - tern is executed and a closing parenthesis is required. Otherwise, - 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. Rewriting it to use a named subpat- - tern gives this: - - (?P<OPEN> \( )? [^()]+ (?(OPEN) \) ) - - If the condition is the string (R), and there is no subpattern with the - name R, the condition is satisfied if a recursive call to the pattern - or subpattern has been made. At "top level", the condition is false. - This is a PCRE extension. Recursive patterns are described in the next - section. - - If the condition is not a sequence of digits or (R), 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 - - The sequence (?# marks the start of a comment that continues up to the - next closing parenthesis. Nested parentheses are not permitted. The - characters that make up a comment play no part in the pattern matching - at all. - - If the PCRE_EXTENDED option is set, an unescaped # character outside a - character class introduces a comment that continues to immediately - after the next newline in the pattern. - - -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. Perl provides a facility that allows regular expressions 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 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 - some special syntax for recursion of the entire pattern, and also for - individual subpattern recursion. - - The special item that consists of (? followed by a number greater than - zero and a closing parenthesis is a recursive call of the subpattern of - the given number, provided that it occurs inside that subpattern. (If - not, it is a "subroutine" call, which is described in the next sec- - tion.) The special item (?R) is a recursive call of the entire regular - expression. - - 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 subse- - quent matching failure. - - 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. - - 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, keep- - ing track of parenthesis numbers can be tricky. It may be more conve- - nient to use named parentheses instead. For this, PCRE uses (?P>name), - which is an extension to the Python syntax that PCRE uses for named - parentheses (Perl does not provide named parentheses). We could rewrite - the above example as follows: - - (?P<pn> \( ( (?>[^()]+) | (?P>pn) )* \) ) - - This particular example pattern contains nested unlimited repeats, and - so the use of atomic grouping for matching strings of non-parentheses - is important when applying the pattern to strings that do not match. - For example, when this pattern is applied to - - (aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa() - - it yields "no match" quickly. However, if atomic grouping 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 set for any capturing subpatterns are - those from the outermost level of the recursion at which the subpattern - value is set. If you want to obtain intermediate values, a callout - function can be used (see the next section and the pcrecallout documen- - tation). If the pattern above is matched against - - (ab(cd)ef) - - the value for the capturing parentheses is "ef", which is the last - value taken on at the top level. If additional parentheses are added, - giving - - \( ( ( (?>[^()]+) | (?R) )* ) \) - ^ ^ - ^ ^ - - the string they capture is "ab(cd)ef", the contents of the top level - parentheses. If there are more than 15 capturing parentheses in a pat- - tern, PCRE has to obtain extra memory to store data during a recursion, - which it does by using pcre_malloc, freeing it via pcre_free after- - wards. 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. - - -SUBPATTERNS AS SUBROUTINES - - If the syntax for a recursive subpattern reference (either by number or - by name) is used outside the parentheses to which it refers, it oper- - ates like a subroutine in a programming language. 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. Such references, if given numerically, must follow the - subpattern to which they refer. However, named references can refer to - later subpatterns. - - Like recursive subpatterns, a "subroutine" 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. - - -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. 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 pcre_compile(), callouts are - automatically installed before each item in the pattern. They are all - numbered 255. - - During matching, when PCRE reaches a callout point (and pcre_callout is - set), the external function 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 pcre_exec(). The callout - function may cause matching to proceed, to backtrack, or to fail alto- - gether. A complete description of the interface to the callout function - is given in the pcrecallout documentation. - -Last updated: 06 June 2006 -Copyright (c) 1997-2006 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 - pcre_exec() or pcre_dfa_exec() 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, possibly beeping and not - reflecting the character that has been typed. This immediate feedback - is likely to be a better user interface than a check that is delayed - until the entire string has been entered. - - PCRE supports the concept of partial matching by means of the PCRE_PAR- - TIAL option, which can be set when calling pcre_exec() or - pcre_dfa_exec(). When this flag is set for pcre_exec(), the return code - PCRE_ERROR_NOMATCH is converted into PCRE_ERROR_PARTIAL if at any time - during the matching process the last part of the subject string matched - part of the pattern. Unfortunately, for non-anchored matching, it is - not possible to obtain the position of the start of the partial match. - No captured data is set when PCRE_ERROR_PARTIAL is returned. - - When PCRE_PARTIAL is set for pcre_dfa_exec(), 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 provided the partial match is set as the first matching string. - - Using PCRE_PARTIAL disables one of PCRE's optimizations. PCRE remembers - the last literal byte in a pattern, and abandons matching immediately - if such a byte is not present in the subject string. This optimization - cannot be used for a subject string that might match only partially. - - -RESTRICTED PATTERNS FOR PCRE_PARTIAL - - Because of the way certain internal optimizations are implemented in - the pcre_exec() function, the PCRE_PARTIAL option cannot be used with - all patterns. These restrictions do not apply when pcre_dfa_exec() is - used. For pcre_exec(), repeated single characters such as - - a{2,4} - - and repeated single metasequences such as - - \d+ - - are not permitted if the maximum number of occurrences is greater than - one. Optional items such as \d? (where the maximum is one) are permit- - ted. Quantifiers with any values are permitted after parentheses, so - the invalid examples above can be coded thus: - - (a){2,4} - (\d)+ - - These constructions run more slowly, but for the kinds of application - that are envisaged for this facility, this is not felt to be a major - restriction. - - If PCRE_PARTIAL is set for a pattern that does not conform to the - restrictions, pcre_exec() returns the error code PCRE_ERROR_BADPARTIAL - (-13). - - -EXAMPLE OF PARTIAL MATCHING USING PCRETEST - - If the escape sequence \P is present in a pcretest data line, the - PCRE_PARTIAL flag 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$/ - data> 25jun04\P - 0: 25jun04 - 1: jun - data> 25dec3\P - Partial match - data> 3ju\P - Partial match - data> 3juj\P - No match - data> j\P - No match - - The first data string is matched completely, so pcretest shows the - matched substrings. The remaining four strings do not match the com- - plete pattern, but the first two are partial matches. The same test, - using DFA matching (by means of the \D escape sequence), produces the - following output: - - re> /^?(jan|feb|mar|apr|may|jun|jul|aug|sep|oct|nov|dec)$/ - data> 25jun04\P\D - 0: 25jun04 - data> 23dec3\P\D - Partial match: 23dec3 - data> 3ju\P\D - Partial match: 3ju - data> 3juj\P\D - No match - data> j\P\D - No match - - Notice that in this case the portion of the string that was matched is - made available. - - -MULTI-SEGMENT MATCHING WITH pcre_dfa_exec() - - When a partial match has been found using pcre_dfa_exec(), it is possi- - ble to continue the match by providing additional subject data and - calling pcre_dfa_exec() again with the PCRE_DFA_RESTART option and the - same working space (where details of the previous partial match are - stored). Here is an example using pcretest, where the \R escape - sequence sets the PCRE_DFA_RESTART option and the \D escape sequence - requests the use of pcre_dfa_exec(): - - re> /^?(jan|feb|mar|apr|may|jun|jul|aug|sep|oct|nov|dec)$/ - 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. - - This facility can be used to pass very long subject strings to - pcre_dfa_exec(). However, some care is needed for certain types of pat- - tern. - - 1. If the pattern contains tests for the beginning or end of a line, - you need to pass the PCRE_NOTBOL or PCRE_NOTEOL options, as appropri- - ate, when the subject string for any call does not contain the begin- - ning or end of a line. - - 2. If the pattern contains backward assertions (including \b or \B), - you need to arrange for some overlap in the subject strings to allow - for this. For example, you could pass the subject in chunks that were - 500 bytes long, but in a buffer of 700 bytes, with the starting offset - set to 200 and the previous 200 bytes at the start of the buffer. - - 3. Matching a subject string that is split into multiple segments does - not always produce exactly the same result as matching over one single - long string. The difference arises when there are multiple matching - possibilities, because a partial match result is given only when there - are no completed matches in a call to fBpcre_dfa_exec(). This means - that as soon as the shortest match has been found, continuation to a - new subject segment is no longer possible. Consider this pcretest - example: - - re> /dog(sbody)?/ - data> do\P\D - Partial match: do - data> gsb\R\P\D - 0: g - data> dogsbody\D - 0: dogsbody - 1: dog - - The pattern matches the words "dog" or "dogsbody". When the subject is - presented in several parts ("do" and "gsb" being the first two) the - match stops when "dog" has been found, and it is not possible to con- - tinue. On the other hand, if "dogsbody" is presented as a single - string, both matches are found. - - Because of this phenomenon, it does not usually make sense to end a - pattern that is going to be matched in this way with a variable repeat. - - 4. Patterns that contain alternatives at the top level which do not all - start with the same pattern item may not work as expected. 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 - "789" 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 alterna- - tive. There is no problem with anchored patterns or patterns such as: - - 1234|ABCD - - where no string can be a partial match for both alternatives. - -Last updated: 16 January 2006 -Copyright (c) 1997-2006 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. - - If you save compiled patterns to a file, you can copy them to a differ- - ent host and run them there. This works even if the new host has the - opposite endianness to the one on which the patterns were compiled. - There may be a small performance penalty, but it should be insignifi- - cant. - - -SAVING A COMPILED PATTERN - The value returned by pcre_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_fullinfo() with an argu- - ment of PCRE_INFO_SIZE. You can then save the data in any appropriate - manner. Here is sample code that compiles 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 study - data in a similar way to the compiled pattern itself. When studying - generates additional information, pcre_study() returns a pointer to a - pcre_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_extra block itself). The length of the study data can be obtained - by calling pcre_fullinfo() with an argument of PCRE_INFO_STUDYSIZE. - Remember to check that pcre_study() did return a non-NULL value before - trying to save the study data. - - -RE-USING A PRECOMPILED PATTERN - - Re-using a precompiled pattern is straightforward. Having reloaded it - into main memory, you pass its pointer to pcre_exec() or - pcre_dfa_exec() in the usual way. This should work even on another - host, and even if that host has the opposite endianness to the one - where the pattern was compiled. - - However, if you passed a pointer to custom character tables when the - pattern was compiled (the tableptr argument of pcre_compile()), you - must now pass a similar pointer to pcre_exec() or pcre_dfa_exec(), - because the value saved with the compiled pattern will obviously be - nonsense. A field in a pcre_extra() block is used to pass this data, as - described in the section on matching a pattern in the pcreapi documen- - tation. - - If you did not provide custom character tables when the pattern was - compiled, the pointer in the compiled pattern is NULL, which causes - pcre_exec() 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_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_extra block to pcre_exec() or pcre_dfa_exec() in the - usual way. - - -COMPATIBILITY WITH DIFFERENT PCRE RELEASES - - The layout of the control block that is at the start of the data that - makes up a compiled pattern was changed for release 5.0. If you have - any saved patterns that were compiled with previous releases (not a - facility that was previously advertised), you will have to recompile - them for release 5.0. However, from now on, it should be possible to - make changes in a compatible manner. - - Notwithstanding the above, if you have any saved patterns in UTF-8 mode - that use \p or \P that were compiled with any release up to and includ- - ing 6.4, you will have to recompile them for release 6.5 and above. - -Last updated: 01 February 2006 -Copyright (c) 1997-2006 University of Cambridge. ------------------------------------------------------------------------------- - - -PCREPERFORM(3) PCREPERFORM(3) - - -NAME - PCRE - Perl-compatible regular expressions - - -PCRE PERFORMANCE - - Certain items that may appear in regular expression patterns are more - efficient than others. It is more efficient to use a character class - like [aeiou] than a set of alternatives such as (a|e|i|o|u). In gen- - eral, 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. - - 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 33 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, 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. - - 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. - -Last updated: 28 February 2005 -Copyright (c) 1997-2005 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 to the PCRE regular - expression package. See the pcreapi documentation for a description of - PCRE's native API, which contains much additional functionality. - - 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 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. - - 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_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 aren't) 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. - - -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 terminated by a zero byte, 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_NOTEOL - - The PCRE_NOTEOL option is set when calling the underlying PCRE matching - function. - - 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. - - 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 3QG, England. - -Last updated: 16 January 2006 -Copyright (c) 1997-2006 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. - - -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 - NULL for the "i"th argument, or pass fewer arguments than - number of sub-patterns, "i"th captured sub-pattern is - ignored. - - 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. - - -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 whitespaces /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) 2005 Google Inc. ------------------------------------------------------------------------------- - - -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. - - The program 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 match- - ing 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 system, you should be able to compile the demonstration pro- - gram 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 - - Once you have compiled 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 the PCRE library. The pcredemo program is provided as a - simple coding example. - - On some operating systems (e.g. Solaris), when PCRE is not installed in - the standard library directory, you may get an error like this when you - try to run pcredemo: - - 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. - -Last updated: 09 September 2004 -Copyright (c) 1997-2004 University of Cambridge. ------------------------------------------------------------------------------- -PCRESTACK(3) PCRESTACK(3) - - -NAME - PCRE - Perl-compatible regular expressions - - -PCRE DISCUSSION OF STACK USAGE - - When you call pcre_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 pro- - ceeds deeper and deeper into the tree of possibilities, the recursion - depth increases. - - 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 pcre_dfa_exec() function operates in an entirely different way, and - hardly uses recursion at all. The limit on its complexity is the amount - of workspace it is given. The comments that follow do NOT apply to - pcre_dfa_exec(); they are relevant only for pcre_exec(). - - You can set limits on the number of times that match() is called, both - in total and recursively. If the limit is exceeded, an error occurs. - For details, see the section on extra data for pcre_exec() in the - pcreapi documentation. - - 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. - - 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. This makes it run a lot more slowly, however. Details of how - to do this are given in the pcrebuild documentation. - - In Unix-like environments, there is not often a problem with the stack, - 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 - - The effect of running out of stack is often SIGSEGV, though sometimes - an error message is given. You can normally 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_exec(). - - PCRE has an internal counter that can be used to limit the depth of - recursion, and thus cause pcre_exec() to give an error code before it - runs out of stack. By default, the limit is very large, and unlikely - ever to operate. It can be changed when PCRE is built, and it can also - be set when pcre_exec() is called. For details of these interfaces, see - the pcrebuild and 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. The pcretest test program - has a command line option (-S) that can be used to increase its stack. - -Last updated: 29 June 2006 -Copyright (c) 1997-2006 University of Cambridge. ------------------------------------------------------------------------------- - - diff --git a/ext/pcre/pcrelib/internal.h b/ext/pcre/pcrelib/internal.h deleted file mode 100644 index a3df3b5257..0000000000 --- a/ext/pcre/pcrelib/internal.h +++ /dev/null @@ -1,770 +0,0 @@ -/************************************************* -* Perl-Compatible Regular Expressions * -*************************************************/ - - -/* This 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. See -the file doc/Tech.Notes for some information on the internals. - -Written by: Philip Hazel <ph10@cam.ac.uk> - - Copyright (c) 1997-2004 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 outside. */ - -/* Get the definitions provided by running "configure" */ - -#ifdef PHP_WIN32 -# include "config.w32.h" -#else -# include <php_config.h> -#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 <setjmp.h> -#include <stdarg.h> -#include <stddef.h> -#include <stdio.h> -#include <stdlib.h> -#include <string.h> - -#ifndef PCRE_SPY -#define PCRE_DEFINITION /* Win32 __declspec(export) trigger for .dll */ -#endif - -/* The value of NEWLINE determines the newline character. The default is to -leave it up to the compiler, but some sites want to force a particular value. -On Unix systems, "configure" can be used to override this default. */ - -#ifndef NEWLINE -#define NEWLINE '\n' -#endif - -/* If you are compiling for a system that needs some magic to be inserted - * before the definition of an exported function, define this macro to contain - * the relevant magic. It apears at the start of every exported function. */ - -#define EXPORT - -/* We need to have types that specify unsigned 16-bit 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. */ - -#if USHRT_MAX == 65535 - typedef unsigned short pcre_uint16; -#elif UINT_MAX == 65535 - typedef unsigned int pcre_uint16; -#else - #error Cannot determine a type for 16-bit unsigned integers -#endif - -#if UINT_MAX == 4294967295 - typedef unsigned int pcre_uint32; -#elif ULONG_MAX == 4294967295 - typedef unsigned long int pcre_uint32; -#else - #error Cannot determine a type for 32-bit unsigned integers -#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 *, because that -should make things easier for callers. We define a short type for unsigned char -to save lots of typing. I tried "uchar", but it causes problems on Digital -Unix, where it is defined in sys/types, so use "uschar" instead. */ - -typedef unsigned char uschar; - -/* Include the public PCRE header */ - -#include "pcre.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 strncmp(s1,s2,m) _strncmp(s1,s2,m) -#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). This assumes -that all calls to memmove are moving strings upwards in store, which is the -case in PCRE. */ - -#if ! HAVE_MEMMOVE -#undef memmove /* some systems may have a macro */ -#if HAVE_BCOPY -#define memmove(a, b, c) bcopy(b, a, c) -#else /* HAVE_BCOPY */ -void * -pcre_memmove(unsigned char *dest, const unsigned char *src, size_t n) -{ -int i; -dest += n; -src += n; -for (i = 0; i < n; ++i) *(--dest) = *(--src); -} -#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. */ - -#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]) - -#define MAX_PATTERN_SIZE (1 << 30) /* Keep it positive */ - - -#else -#error LINK_SIZE must be either 2, 3, or 4 -#endif - - -/* 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. */ - -#define PUT2(a,n,d) \ - a[n] = (d) >> 8; \ - a[(n)+1] = (d) & 255 - -#define GET2(a,n) \ - (((a)[n] << 8) | (a)[(n)+1]) - -#define PUT2INC(a,n,d) PUT2(a,n,d), a += 2 - - -/* 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 - - -/* These are the public options that can change during matching. */ - -#define PCRE_IMS (PCRE_CASELESS|PCRE_MULTILINE|PCRE_DOTALL) - -/* Private options flags start at the most significant end of the four bytes, -but skip the top bit so we can use ints for convenience without getting tangled -with negative values. The public options defined in pcre.h start at the least -significant end. Make sure they don't overlap, though now that we have expanded -to four bytes, there is plenty of space. */ - -#define PCRE_FIRSTSET 0x40000000 /* first_byte is set */ -#define PCRE_REQCHSET 0x20000000 /* req_byte is set */ -#define PCRE_STARTLINE 0x10000000 /* start after \n for multiline */ -#define PCRE_ICHANGED 0x08000000 /* i option changes within regex */ -#define PCRE_NOPARTIAL 0x04000000 /* can't use partial with this regex */ - -/* Options for the "extra" block produced by pcre_study(). */ - -#define PCRE_STUDY_MAPPED 0x01 /* a map of starting chars exists */ - -/* Masks for identifying the public options which are permitted at compile -time, run time or study time, respectively. */ - -#define PUBLIC_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) - -#define PUBLIC_EXEC_OPTIONS \ - (PCRE_ANCHORED|PCRE_NOTBOL|PCRE_NOTEOL|PCRE_NOTEMPTY|PCRE_NO_UTF8_CHECK| \ - PCRE_PARTIAL) - -#define PUBLIC_STUDY_OPTIONS 0 /* None defined */ - -/* Magic number to provide a small check against being handed junk. */ - -#define MAGIC_NUMBER 0x50435245UL /* 'PCRE' */ - -/* Negative values for the firstchar and reqchar variables */ - -#define REQ_UNSET (-2) -#define REQ_NONE (-1) - -/* Flags added to firstbyte or reqbyte; a "non-literal" item is either a -variable-length repeat, or a anything other than literal characters. */ - -#define REQ_CASELESS 0x0100 /* indicates caselessness */ -#define REQ_VARY 0x0200 /* reqbyte followed non-literal item */ - -/* Miscellaneous definitions */ - -typedef int BOOL; - -#define FALSE 0 -#define TRUE 1 - -/* Escape items that are just an encoding of a particular data value. Note that -ESC_n is defined as yet another macro, which is set in config.h to either \n -(the default) or \r (which some people want). */ - -#ifndef ESC_e -#define ESC_e 27 -#endif - -#ifndef ESC_f -#define ESC_f '\f' -#endif - -#ifndef ESC_n -#define ESC_n NEWLINE -#endif - -#ifndef ESC_r -#define ESC_r '\r' -#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 '\t' -#endif - -/* 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_ANY because it -corresponds to "." rather than an escape sequence. The final one must be -ESC_REF as subsequent values are used for \1, \2, \3, etc. There is 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_B, ESC_b, ESC_D, ESC_d, ESC_S, ESC_s, ESC_W, - ESC_w, ESC_dum1, ESC_C, ESC_P, ESC_p, ESC_X, ESC_Z, ESC_z, ESC_E, - ESC_Q, ESC_REF }; - -/* Flag bits and data types for the extended class (OP_XCLASS) for classes that -contain UTF-8 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 (one property code) follows */ -#define XCL_NOTPROP 4 /* Unicode inverted property (ditto) */ - - -/* Opcode table: OP_BRA must be last, as all values >= it are used for brackets -that extract substrings. 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 that whenever this list is updated, the two macro definitions that follow -must also be updated to match. */ - -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_NOT_WORD_BOUNDARY, /* 3 \B */ - OP_WORD_BOUNDARY, /* 4 \b */ - OP_NOT_DIGIT, /* 5 \D */ - OP_DIGIT, /* 6 \d */ - OP_NOT_WHITESPACE, /* 7 \S */ - OP_WHITESPACE, /* 8 \s */ - OP_NOT_WORDCHAR, /* 9 \W */ - OP_WORDCHAR, /* 10 \w */ - OP_ANY, /* 11 Match any character */ - OP_ANYBYTE, /* 12 Match any byte (\C); different to OP_ANY for UTF-8 */ - OP_NOTPROP, /* 13 \P (not Unicode property) */ - OP_PROP, /* 14 \p (Unicode property) */ - OP_EXTUNI, /* 15 \X (extended Unicode sequence */ - OP_EODN, /* 16 End of data or \n at end of data: \Z. */ - OP_EOD, /* 17 End of data: \z */ - - OP_OPT, /* 18 Set runtime options */ - OP_CIRC, /* 19 Start of line - varies with multiline switch */ - OP_DOLL, /* 20 End of line - varies with multiline switch */ - OP_CHAR, /* 21 Match one character, casefully */ - OP_CHARNC, /* 22 Match one character, caselessly */ - OP_NOT, /* 23 Match anything but the following char */ - - OP_STAR, /* 24 The maximizing and minimizing versions of */ - OP_MINSTAR, /* 25 all these opcodes must come in pairs, with */ - OP_PLUS, /* 26 the minimizing one second. */ - OP_MINPLUS, /* 27 This first set applies to single characters */ - OP_QUERY, /* 28 */ - OP_MINQUERY, /* 29 */ - OP_UPTO, /* 30 From 0 to n matches */ - OP_MINUPTO, /* 31 */ - OP_EXACT, /* 32 Exactly n matches */ - - OP_NOTSTAR, /* 33 The maximizing and minimizing versions of */ - OP_NOTMINSTAR, /* 34 all these opcodes must come in pairs, with */ - OP_NOTPLUS, /* 35 the minimizing one second. */ - OP_NOTMINPLUS, /* 36 This set applies to "not" single characters */ - OP_NOTQUERY, /* 37 */ - OP_NOTMINQUERY, /* 38 */ - OP_NOTUPTO, /* 39 From 0 to n matches */ - OP_NOTMINUPTO, /* 40 */ - OP_NOTEXACT, /* 41 Exactly n matches */ - - OP_TYPESTAR, /* 42 The maximizing and minimizing versions of */ - OP_TYPEMINSTAR, /* 43 all these opcodes must come in pairs, with */ - OP_TYPEPLUS, /* 44 the minimizing one second. These codes must */ - OP_TYPEMINPLUS, /* 45 be in exactly the same order as those above. */ - OP_TYPEQUERY, /* 46 This set applies to character types such as \d */ - OP_TYPEMINQUERY, /* 47 */ - OP_TYPEUPTO, /* 48 From 0 to n matches */ - OP_TYPEMINUPTO, /* 49 */ - OP_TYPEEXACT, /* 50 Exactly n matches */ - - OP_CRSTAR, /* 51 The maximizing and minimizing versions of */ - OP_CRMINSTAR, /* 52 all these opcodes must come in pairs, with */ - OP_CRPLUS, /* 53 the minimizing one second. These codes must */ - OP_CRMINPLUS, /* 54 be in exactly the same order as those above. */ - OP_CRQUERY, /* 55 These are for character classes and back refs */ - OP_CRMINQUERY, /* 56 */ - OP_CRRANGE, /* 57 These are different to the three sets above. */ - OP_CRMINRANGE, /* 58 */ - - OP_CLASS, /* 59 Match a character class, chars < 256 only */ - OP_NCLASS, /* 60 Same, but the bitmap was created from a negative - class - the difference is relevant only when a UTF-8 - character > 255 is encountered. */ - - OP_XCLASS, /* 61 Extended class for handling UTF-8 chars within the - class. This does both positive and negative. */ - - OP_REF, /* 62 Match a back reference */ - OP_RECURSE, /* 63 Match a numbered subpattern (possibly recursive) */ - OP_CALLOUT, /* 64 Call out to external function if provided */ - - OP_ALT, /* 65 Start of alternation */ - OP_KET, /* 66 End of group that doesn't have an unbounded repeat */ - OP_KETRMAX, /* 67 These two must remain together and in this */ - OP_KETRMIN, /* 68 order. They are for groups the repeat for ever. */ - - /* The assertions must come before ONCE and COND */ - - OP_ASSERT, /* 69 Positive lookahead */ - OP_ASSERT_NOT, /* 70 Negative lookahead */ - OP_ASSERTBACK, /* 71 Positive lookbehind */ - OP_ASSERTBACK_NOT, /* 72 Negative lookbehind */ - OP_REVERSE, /* 73 Move pointer back - used in lookbehind assertions */ - - /* ONCE and COND must come after the assertions, with ONCE first, as there's - a test for >= ONCE for a subpattern that isn't an assertion. */ - - OP_ONCE, /* 74 Once matched, don't back up into the subpattern */ - OP_COND, /* 75 Conditional group */ - OP_CREF, /* 76 Used to hold an extraction string number (cond ref) */ - - OP_BRAZERO, /* 77 These two must remain together and in this */ - OP_BRAMINZERO, /* 78 order. */ - - OP_BRANUMBER, /* 79 Used for extracting brackets whose number is greater - than can fit into an opcode. */ - - OP_BRA /* 80 This and greater values are used for brackets that - extract substrings up to EXTRACT_BASIC_MAX. After - that, use is made of OP_BRANUMBER. */ -}; - -/* WARNING WARNING WARNING: There is an implicit assumption in pcre.c and -study.c that all opcodes are less than 128 in value. This makes handling UTF-8 -character sequences easier. */ - -/* The highest extraction number before we have to start using additional -bytes. (Originally PCRE didn't have support for extraction counts highter than -this number.) The value is limited by the number of opcodes left after OP_BRA, -i.e. 255 - OP_BRA. We actually set it a bit lower to leave room for additional -opcodes. */ - -#define EXTRACT_BASIC_MAX 100 - - -/* This macro defines textual names for all the opcodes. There are used only -for debugging, in pcre.c when DEBUG is defined, and also in pcretest.c. The -macro is referenced only in printint.c. */ - -#define OP_NAME_LIST \ - "End", "\\A", "\\G", "\\B", "\\b", "\\D", "\\d", \ - "\\S", "\\s", "\\W", "\\w", "Any", "Anybyte", \ - "notprop", "prop", "extuni", \ - "\\Z", "\\z", \ - "Opt", "^", "$", "char", "charnc", "not", \ - "*", "*?", "+", "+?", "?", "??", "{", "{", "{", \ - "*", "*?", "+", "+?", "?", "??", "{", "{", "{", \ - "*", "*?", "+", "+?", "?", "??", "{", "{", "{", \ - "*", "*?", "+", "+?", "?", "??", "{", "{", \ - "class", "nclass", "xclass", "Ref", "Recurse", "Callout", \ - "Alt", "Ket", "KetRmax", "KetRmin", "Assert", "Assert not", \ - "AssertB", "AssertB not", "Reverse", "Once", "Cond", "Cond ref",\ - "Brazero", "Braminzero", "Branumber", "Bra" - - -/* 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 -incorporated both into pcre.c and pcretest.c without being publicly exposed. - -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, 1, 1, 1, 1, 1, /* \A, \G, \B, \B, \D, \d, \S, \s, \W, \w */ \ - 1, 1, /* Any, Anybyte */ \ - 2, 2, 1, /* NOTPROP, PROP, EXTUNI */ \ - 1, 1, 2, 1, 1, /* \Z, \z, Opt, ^, $ */ \ - 2, /* Char - the minimum length */ \ - 2, /* Charnc - the minimum length */ \ - 2, /* not */ \ - /* Positive single-char repeats ** These are */ \ - 2, 2, 2, 2, 2, 2, /* *, *?, +, +?, ?, ?? ** minima in */ \ - 4, 4, 4, /* upto, minupto, exact ** UTF-8 mode */ \ - /* Negative single-char repeats - only for chars < 256 */ \ - 2, 2, 2, 2, 2, 2, /* NOT *, *?, +, +?, ?, ?? */ \ - 4, 4, 4, /* NOT upto, minupto, exact */ \ - /* Positive type repeats */ \ - 2, 2, 2, 2, 2, 2, /* Type *, *?, +, +?, ?, ?? */ \ - 4, 4, 4, /* Type upto, minupto, exact */ \ - /* Character class & ref repeats */ \ - 1, 1, 1, 1, 1, 1, /* *, *?, +, +?, ?, ?? */ \ - 5, 5, /* CRRANGE, CRMINRANGE */ \ - 33, /* CLASS */ \ - 33, /* NCLASS */ \ - 0, /* XCLASS - variable length */ \ - 3, /* REF */ \ - 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, /* Assert */ \ - 1+LINK_SIZE, /* Assert not */ \ - 1+LINK_SIZE, /* Assert behind */ \ - 1+LINK_SIZE, /* Assert behind not */ \ - 1+LINK_SIZE, /* Reverse */ \ - 1+LINK_SIZE, /* Once */ \ - 1+LINK_SIZE, /* COND */ \ - 3, /* CREF */ \ - 1, 1, /* BRAZERO, BRAMINZERO */ \ - 3, /* BRANUMBER */ \ - 1+LINK_SIZE /* BRA */ \ - - -/* A magic value for OP_CREF to indicate the "in recursion" condition. */ - -#define CREF_RECURSE 0xffff - -/* The texts of compile-time error messages are defined as macros here so that -they can be accessed by the POSIX wrapper and converted into error codes. Yes, -I could have used error codes in the first place, but didn't feel like changing -just to accommodate the POSIX wrapper. */ - -#define ERR1 "\\ at end of pattern" -#define ERR2 "\\c at end of pattern" -#define ERR3 "unrecognized character follows \\" -#define ERR4 "numbers out of order in {} quantifier" -#define ERR5 "number too big in {} quantifier" -#define ERR6 "missing terminating ] for character class" -#define ERR7 "invalid escape sequence in character class" -#define ERR8 "range out of order in character class" -#define ERR9 "nothing to repeat" -#define ERR10 "operand of unlimited repeat could match the empty string" -#define ERR11 "internal error: unexpected repeat" -#define ERR12 "unrecognized character after (?" -#define ERR13 "POSIX named classes are supported only within a class" -#define ERR14 "missing )" -#define ERR15 "reference to non-existent subpattern" -#define ERR16 "erroffset passed as NULL" -#define ERR17 "unknown option bit(s) set" -#define ERR18 "missing ) after comment" -#define ERR19 "parentheses nested too deeply" -#define ERR20 "regular expression too large" -#define ERR21 "failed to get memory" -#define ERR22 "unmatched parentheses" -#define ERR23 "internal error: code overflow" -#define ERR24 "unrecognized character after (?<" -#define ERR25 "lookbehind assertion is not fixed length" -#define ERR26 "malformed number after (?(" -#define ERR27 "conditional group contains more than two branches" -#define ERR28 "assertion expected after (?(" -#define ERR29 "(?R or (?digits must be followed by )" -#define ERR30 "unknown POSIX class name" -#define ERR31 "POSIX collating elements are not supported" -#define ERR32 "this version of PCRE is not compiled with PCRE_UTF8 support" -#define ERR33 "spare error" -#define ERR34 "character value in \\x{...} sequence is too large" -#define ERR35 "invalid condition (?(0)" -#define ERR36 "\\C not allowed in lookbehind assertion" -#define ERR37 "PCRE does not support \\L, \\l, \\N, \\U, or \\u" -#define ERR38 "number after (?C is > 255" -#define ERR39 "closing ) for (?C expected" -#define ERR40 "recursive call could loop indefinitely" -#define ERR41 "unrecognized character after (?P" -#define ERR42 "syntax error after (?P" -#define ERR43 "two named groups have the same name" -#define ERR44 "invalid UTF-8 string" -#define ERR45 "support for \\P, \\p, and \\X has not been compiled" -#define ERR46 "malformed \\P or \\p sequence" -#define ERR47 "unknown property name after \\P or \\p" - -/* 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, we also include a few dummy -fields - even though you can never get this planning right! - -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: -*/ - -typedef struct real_pcre { - pcre_uint32 magic_number; - pcre_uint32 size; /* Total that was malloced */ - pcre_uint32 options; - pcre_uint32 dummy1; /* For future use, maybe */ - - pcre_uint16 top_bracket; - pcre_uint16 top_backref; - pcre_uint16 first_byte; - pcre_uint16 req_byte; - 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 dummy2; /* For future use, maybe */ - - const unsigned char *tables; /* Pointer to tables or NULL for std */ - const unsigned char *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 options; - uschar start_bits[32]; -} pcre_study_data; - -/* Structure for passing "static" information around between the functions -doing the compiling, so that they are thread-safe. */ - -typedef struct compile_data { - const uschar *lcc; /* Points to lower casing table */ - const uschar *fcc; /* Points to case-flipping table */ - const uschar *cbits; /* Points to character type table */ - const uschar *ctypes; /* Points to table of type maps */ - const uschar *start_code; /* The start of the compiled code */ - const uschar *start_pattern; /* The start of the pattern */ - uschar *name_table; /* The name/number table */ - int names_found; /* Number of entries so far */ - int name_entry_size; /* Size of each entry */ - int top_backref; /* Maximum back reference */ - unsigned int backref_map; /* Bitmap of low back refs */ - int req_varyopt; /* "After variable item" flag for reqbyte */ - BOOL nopartial; /* Set TRUE if partial won't work */ -} compile_data; - -/* Structure for maintaining a chain of pointers to the currently incomplete -branches, for testing for left recursion. */ - -typedef struct branch_chain { - struct branch_chain *outer; - uschar *current; -} branch_chain; - -/* Structure for items in a linked list that represents an explicit recursive -call within the pattern. */ - -typedef struct recursion_info { - struct recursion_info *prevrec; /* Previous recursion record (or NULL) */ - int group_num; /* Number of group that was called */ - const uschar *after_call; /* "Return value": points after the call in the expr */ - const uschar *save_start; /* Old value of md->start_match */ - int *offset_save; /* Pointer to start of saved offsets */ - int saved_max; /* Number of saved offsets */ -} recursion_info; - -/* When compiling in a mode that doesn't use recursive calls to match(), -a structure is used to remember local variables on the heap. It is defined in -pcre.c, close to the match() function, so that it is easy to keep it in step -with any changes of local variable. However, the pointer to the current frame -must be saved in some "static" place over a longjmp(). We declare the -structure here so that we can put a pointer in the match_data structure. -NOTE: This isn't used for a "normal" compilation of pcre. */ - -struct heapframe; - -/* Structure for passing "static" information around between the functions -doing the 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 */ - int *offset_vector; /* Offset vector */ - int offset_end; /* One past the end */ - int offset_max; /* The maximum usable for return data */ - const uschar *lcc; /* Points to lower casing table */ - const uschar *ctypes; /* Points to table of type maps */ - BOOL offset_overflow; /* Set if too many extractions */ - BOOL notbol; /* NOTBOL flag */ - BOOL noteol; /* NOTEOL flag */ - BOOL utf8; /* UTF8 flag */ - BOOL endonly; /* Dollar not before final \n */ - BOOL notempty; /* Empty string match not wanted */ - BOOL partial; /* PARTIAL flag */ - BOOL hitend; /* Hit the end of the subject at some point */ - const uschar *start_code; /* For use when recursing */ - const uschar *start_subject; /* Start of the subject string */ - const uschar *end_subject; /* End of the subject string */ - const uschar *start_match; /* Start of this match attempt */ - const uschar *end_match_ptr; /* Subject position at end match */ - int end_offset_top; /* Highwater mark at end of match */ - int capture_last; /* Most recent capture number */ - int start_offset; /* The start offset value */ - recursion_info *recursive; /* Linked list of recursion data */ - void *callout_data; /* To pass back to callouts */ - struct heapframe *thisframe; /* Used only when compiling for no recursion */ -} 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 /* alphameric 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) - -/* End of internal.h */ diff --git a/ext/pcre/pcrelib/libpcre.def b/ext/pcre/pcrelib/libpcre.def deleted file mode 100644 index 01db4bd22c..0000000000 --- a/ext/pcre/pcrelib/libpcre.def +++ /dev/null @@ -1,20 +0,0 @@ -LIBRARY libpcre -EXPORTS -pcre_malloc -pcre_free -pcre_config -pcre_callout -pcre_compile -pcre_copy_substring -pcre_dfa_exec -pcre_exec -pcre_get_substring -pcre_get_stringnumber -pcre_get_substring_list -pcre_free_substring -pcre_free_substring_list -pcre_info -pcre_fullinfo -pcre_maketables -pcre_study -pcre_version diff --git a/ext/pcre/pcrelib/libpcreposix.def b/ext/pcre/pcrelib/libpcreposix.def deleted file mode 100644 index 5f30247969..0000000000 --- a/ext/pcre/pcrelib/libpcreposix.def +++ /dev/null @@ -1,25 +0,0 @@ -LIBRARY libpcreposix -EXPORTS -pcre_malloc -pcre_free -pcre_config -pcre_callout -pcre_compile -pcre_copy_substring -pcre_dfa_exec -pcre_exec -pcre_get_substring -pcre_get_stringnumber -pcre_get_substring_list -pcre_free_substring -pcre_free_substring_list -pcre_info -pcre_fullinfo -pcre_maketables -pcre_study -pcre_version - -regcomp -regexec -regerror -regfree diff --git a/ext/pcre/pcrelib/pcre.def b/ext/pcre/pcrelib/pcre.def deleted file mode 100644 index ec2c7b395b..0000000000 --- a/ext/pcre/pcrelib/pcre.def +++ /dev/null @@ -1,29 +0,0 @@ -EXPORTS - -pcre_malloc DATA -pcre_free DATA - -pcre_compile -pcre_compile2 -pcre_config -pcre_copy_named_substring -pcre_copy_substring -pcre_dfa_exec -pcre_exec -pcre_free_substring -pcre_free_substring_list -pcre_fullinfo -pcre_get_named_substring -pcre_get_stringnumber -pcre_get_substring -pcre_get_substring_list -pcre_info -pcre_maketables -pcre_refcount -pcre_study -pcre_version - -regcomp -regexec -regerror -regfree diff --git a/ext/pcre/pcrelib/pcre.h b/ext/pcre/pcrelib/pcre.h deleted file mode 100644 index b4a19d2fa1..0000000000 --- a/ext/pcre/pcrelib/pcre.h +++ /dev/null @@ -1,292 +0,0 @@ -/************************************************* -* 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) 1997-2005 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 - -#include "php_compat.h" - -/* The current PCRE version information. */ - -/* NOTES FOR FUTURE MAINTAINERS: Do not use numbers with leading zeros, because -they may be treated as octal constants. The PCRE_PRERELEASE feature is for -identifying release candidates. It might be defined as -RC2, for example. In -real releases, it should be defined empty. Do not change the alignment of these -statments. The code in ./configure greps out the version numbers by using "cut" -to get values from column 29 onwards. These are substituted into pcre-config -and libpcre.pc. The values are not put into configure.ac and substituted here -(which would simplify this issue) because that makes life harder for those who -cannot run ./configure. As it now stands, this file need not be edited in that -circumstance. */ - -#define PCRE_MAJOR 6 -#define PCRE_MINOR 7 -#define PCRE_PRERELEASE -#define PCRE_DATE 04-Jul-2006 - -/* Win32 uses DLL by default; it needs special stuff for exported functions -when building PCRE. */ - -#ifdef _WIN32 -# ifdef PCRE_DEFINITION -# ifdef DLL_EXPORT -# define PCRE_DATA_SCOPE __declspec(dllexport) -# endif -# else -# ifndef PCRE_STATIC -# define PCRE_DATA_SCOPE extern __declspec(dllimport) -# endif -# endif -#endif - -/* Otherwise, we use the standard "extern". */ - -#ifndef PCRE_DATA_SCOPE -# ifdef __cplusplus -# define PCRE_DATA_SCOPE extern "C" -# else -# define PCRE_DATA_SCOPE extern -# 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 */ - -#define PCRE_CASELESS 0x00000001 -#define PCRE_MULTILINE 0x00000002 -#define PCRE_DOTALL 0x00000004 -#define PCRE_EXTENDED 0x00000008 -#define PCRE_ANCHORED 0x00000010 -#define PCRE_DOLLAR_ENDONLY 0x00000020 -#define PCRE_EXTRA 0x00000040 -#define PCRE_NOTBOL 0x00000080 -#define PCRE_NOTEOL 0x00000100 -#define PCRE_UNGREEDY 0x00000200 -#define PCRE_NOTEMPTY 0x00000400 -#define PCRE_UTF8 0x00000800 -#define PCRE_NO_AUTO_CAPTURE 0x00001000 -#define PCRE_NO_UTF8_CHECK 0x00002000 -#define PCRE_AUTO_CALLOUT 0x00004000 -#define PCRE_PARTIAL 0x00008000 -#define PCRE_DFA_SHORTEST 0x00010000 -#define PCRE_DFA_RESTART 0x00020000 -#define PCRE_FIRSTLINE 0x00040000 -#define PCRE_DUPNAMES 0x00080000 -#define PCRE_NEWLINE_CR 0x00100000 -#define PCRE_NEWLINE_LF 0x00200000 -#define PCRE_NEWLINE_CRLF 0x00300000 - -/* 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_NODE (-5) -#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) -#define PCRE_ERROR_BADUTF8_OFFSET (-11) -#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) - -/* 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 - -/* 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 - -/* Bit flags for the pcre_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 - -/* Types */ - -struct real_pcre; /* declaration; the definition is private */ -typedef struct real_pcre pcre; - -/* 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() */ -} pcre_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 */ - /* ------------------------------------------------------------------ */ -} pcre_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_DATA_SCOPE void *(*pcre_malloc)(size_t); -PCRE_DATA_SCOPE void (*pcre_free)(void *); -PCRE_DATA_SCOPE void *(*pcre_stack_malloc)(size_t); -PCRE_DATA_SCOPE void (*pcre_stack_free)(void *); -PCRE_DATA_SCOPE int (*pcre_callout)(pcre_callout_block *); -#else /* VPCOMPAT */ -PCRE_DATA_SCOPE void *pcre_malloc(size_t); -PCRE_DATA_SCOPE void pcre_free(void *); -PCRE_DATA_SCOPE void *pcre_stack_malloc(size_t); -PCRE_DATA_SCOPE void pcre_stack_free(void *); -PCRE_DATA_SCOPE int pcre_callout(pcre_callout_block *); -#endif /* VPCOMPAT */ - -/* Exported PCRE functions */ - -PCRE_DATA_SCOPE pcre *pcre_compile(const char *, int, const char **, int *, - const unsigned char *); -PCRE_DATA_SCOPE pcre *pcre_compile2(const char *, int, int *, const char **, - int *, const unsigned char *); -PCRE_DATA_SCOPE int pcre_config(int, void *); -PCRE_DATA_SCOPE int pcre_copy_named_substring(const pcre *, const char *, - int *, int, const char *, char *, int); -PCRE_DATA_SCOPE int pcre_copy_substring(const char *, int *, int, int, char *, - int); -PCRE_DATA_SCOPE int pcre_dfa_exec(const pcre *, const pcre_extra *, - const char *, int, int, int, int *, int , int *, int); -PCRE_DATA_SCOPE int pcre_exec(const pcre *, const pcre_extra *, PCRE_SPTR, - int, int, int, int *, int); -PCRE_DATA_SCOPE void pcre_free_substring(const char *); -PCRE_DATA_SCOPE void pcre_free_substring_list(const char **); -PCRE_DATA_SCOPE int pcre_fullinfo(const pcre *, const pcre_extra *, int, - void *); -PCRE_DATA_SCOPE int pcre_get_named_substring(const pcre *, const char *, - int *, int, const char *, const char **); -PCRE_DATA_SCOPE int pcre_get_stringnumber(const pcre *, const char *); -PCRE_DATA_SCOPE int pcre_get_stringtable_entries(const pcre *, const char *, - char **, char **); -PCRE_DATA_SCOPE int pcre_get_substring(const char *, int *, int, int, - const char **); -PCRE_DATA_SCOPE int pcre_get_substring_list(const char *, int *, int, - const char ***); -PCRE_DATA_SCOPE int pcre_info(const pcre *, int *, int *); -PCRE_DATA_SCOPE const unsigned char *pcre_maketables(void); -PCRE_DATA_SCOPE int pcre_refcount(pcre *, int); -PCRE_DATA_SCOPE pcre_extra *pcre_study(const pcre *, int, const char **); -PCRE_DATA_SCOPE const char *pcre_version(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 deleted file mode 100644 index d491433e25..0000000000 --- a/ext/pcre/pcrelib/pcre_chartables.c +++ /dev/null @@ -1,183 +0,0 @@ -/************************************************* -* Perl-Compatible Regular Expressions * -*************************************************/ - -/* This file is automatically written by the dftables auxiliary -program. If you edit it by hand, you might like to edit the Makefile to -prevent its ever being regenerated. - -This file contains the default tables for characters with codes less than -128 (ASCII characters). These tables are used when no external tables are -passed to PCRE. */ - -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 */ - 0x12,0x12,0x12,0x80,0x00,0x00,0x80,0x10, /* 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 chartables.c */ diff --git a/ext/pcre/pcrelib/pcre_compile.c b/ext/pcre/pcrelib/pcre_compile.c deleted file mode 100644 index 4ea73d9d30..0000000000 --- a/ext/pcre/pcrelib/pcre_compile.c +++ /dev/null @@ -1,5281 +0,0 @@ -/************************************************* -* 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) 1997-2006 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. */ - - -#define NLBLOCK cd /* The block containing newline information */ -#include "pcre_internal.h" - - -/* When DEBUG is defined, we need the pcre_printint() function, which is also -used by pcretest. DEBUG is not defined when building a production library. */ - -#ifdef DEBUG -#include "pcre_printint.src" -#endif - - - -/************************************************* -* Code parameters and static tables * -*************************************************/ - -/* Maximum number of items on the nested bracket stacks at compile time. This -applies to the nesting of all kinds of parentheses. It does not limit -un-nested, non-capturing parentheses. This number can be made bigger if -necessary - it is used to dimension one int and one unsigned char vector at -compile time. */ - -#define BRASTACK_SIZE 200 - - -/* 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. */ - -#if !EBCDIC /* This is the "normal" table for ASCII systems */ -static const short int escapes[] = { - 0, 0, 0, 0, 0, 0, 0, 0, /* 0 - 7 */ - 0, 0, ':', ';', '<', '=', '>', '?', /* 8 - ? */ - '@', -ESC_A, -ESC_B, -ESC_C, -ESC_D, -ESC_E, 0, -ESC_G, /* @ - G */ - 0, 0, 0, 0, 0, 0, 0, 0, /* H - O */ --ESC_P, -ESC_Q, 0, -ESC_S, 0, 0, 0, -ESC_W, /* P - W */ --ESC_X, 0, -ESC_Z, '[', '\\', ']', '^', '_', /* X - _ */ - '`', 7, -ESC_b, 0, -ESC_d, ESC_e, ESC_f, 0, /* ` - g */ - 0, 0, 0, 0, 0, 0, ESC_n, 0, /* h - o */ --ESC_p, 0, ESC_r, -ESC_s, ESC_tee, 0, 0, -ESC_w, /* p - w */ - 0, 0, -ESC_z /* x - z */ -}; - -#else /* This is the "abnormal" table for EBCDIC systems */ -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 */ 0, 0, 0, '{', 0, 0, 0, 0, -/* 90 */ 0, 0, 0, 'l', 0, ESC_n, 0, -ESC_p, -/* 98 */ 0, ESC_r, 0, '}', 0, 0, 0, 0, -/* A0 */ 0, '~', -ESC_s, ESC_tee, 0, 0, -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 */ 0, 0, 0, 0, 0, 0, 0, 0, -/* D0 */ '}', 0, 0, 0, 0, 0, 0, -ESC_P, -/* D8 */-ESC_Q, 0, 0, 0, 0, 0, 0, 0, -/* E0 */ '\\', 0, -ESC_S, 0, 0, 0, -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 - - -/* Tables of names of POSIX character classes and their lengths. The list 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 *const posix_names[] = { - "alpha", "lower", "upper", - "alnum", "ascii", "blank", "cntrl", "digit", "graph", - "print", "punct", "space", "word", "xdigit" }; - -static const uschar 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 */ -}; - - -/* The texts of compile-time error messages. These are "char *" because they -are passed to the outside world. */ - -static const char *error_texts[] = { - "no error", - "\\ at end of pattern", - "\\c at end of pattern", - "unrecognized character follows \\", - "numbers out of order in {} quantifier", - /* 5 */ - "number too big in {} quantifier", - "missing terminating ] for character class", - "invalid escape sequence in character class", - "range out of order in character class", - "nothing to repeat", - /* 10 */ - "operand of unlimited repeat could match the empty string", - "internal error: unexpected repeat", - "unrecognized character after (?", - "POSIX named classes are supported only within a class", - "missing )", - /* 15 */ - "reference to non-existent subpattern", - "erroffset passed as NULL", - "unknown option bit(s) set", - "missing ) after comment", - "parentheses nested too deeply", - /* 20 */ - "regular expression too large", - "failed to get memory", - "unmatched parentheses", - "internal error: code overflow", - "unrecognized character after (?<", - /* 25 */ - "lookbehind assertion is not fixed length", - "malformed number or name after (?(", - "conditional group contains more than two branches", - "assertion expected after (?(", - "(?R or (?digits must be followed by )", - /* 30 */ - "unknown POSIX class name", - "POSIX collating elements are not supported", - "this version of PCRE is not compiled with PCRE_UTF8 support", - "spare error", - "character value in \\x{...} sequence is too large", - /* 35 */ - "invalid condition (?(0)", - "\\C not allowed in lookbehind assertion", - "PCRE does not support \\L, \\l, \\N, \\U, or \\u", - "number after (?C is > 255", - "closing ) for (?C expected", - /* 40 */ - "recursive call could loop indefinitely", - "unrecognized character after (?P", - "syntax error after (?P", - "two named subpatterns have the same name", - "invalid UTF-8 string", - /* 45 */ - "support for \\P, \\p, and \\X has not been compiled", - "malformed \\P or \\p sequence", - "unknown property name after \\P or \\p", - "subpattern name is too long (maximum 32 characters)", - "too many named subpatterns (maximum 10,000)", - /* 50 */ - "repeated subpattern is too long", - "octal value is greater than \\377 (not in UTF-8 mode)" -}; - - -/* 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. */ - -#if !EBCDIC /* This is the "normal" case, for ASCII systems */ -static const unsigned char 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 */ -static const unsigned char 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- ¬ */ - 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 unsigned char 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- ¬ */ - 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, int, int *, uschar **, const uschar **, int *, BOOL, int, - int *, int *, branch_chain *, compile_data *); - - - -/************************************************* -* 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. 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, errorptr is set -*/ - -static int -check_escape(const uschar **ptrptr, int *errorcodeptr, int bracount, - int options, BOOL isclass) -{ -BOOL utf8 = (options & PCRE_UTF8) != 0; -const uschar *ptr = *ptrptr + 1; -int c, 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-alphamerics 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. */ - -#if !EBCDIC /* ASCII coding */ -else if (c < '0' || c > 'z') {} /* Not alphameric */ -else if ((i = escapes[c - '0']) != 0) c = i; - -#else /* EBCDIC coding */ -else if (c < 'a' || (ebcdic_chartab[c] & 0x0E) == 0) {} /* Not alphameric */ -else if ((i = escapes[c - 0x48]) != 0) c = i; -#endif - -/* Escapes that need further processing, or are illegal. */ - -else - { - const uschar *oldptr; - switch (c) - { - /* A number of Perl escapes are not handled by PCRE. We give an explicit - error. */ - - case 'l': - case 'L': - case 'N': - case 'u': - case 'U': - *errorcodeptr = ERR37; - 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 '1': case '2': case '3': case '4': case '5': - case '6': case '7': case '8': case '9': - - if (!isclass) - { - oldptr = ptr; - c -= '0'; - while ((digitab[ptr[1]] & ctype_digit) != 0) - c = c * 10 + *(++ptr) - '0'; - 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) >= '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, but no more - than 3 octal digits. */ - - case '0': - c -= '0'; - while(i++ < 2 && ptr[1] >= '0' && ptr[1] <= '7') - c = c * 8 + *(++ptr) - '0'; - if (!utf8 && c > 255) *errorcodeptr = ERR51; - break; - - /* \x is complicated. \x{ddd} is a character number which can be greater - than 0xff in utf8 mode, but only if the ddd are hex digits. If not, { is - treated as a data character. */ - - case 'x': - if (ptr[1] == '{') - { - const uschar *pt = ptr + 2; - int count = 0; - - c = 0; - while ((digitab[*pt] & ctype_xdigit) != 0) - { - register int cc = *pt++; - if (c == 0 && cc == '0') continue; /* Leading zeroes */ - count++; - -#if !EBCDIC /* ASCII coding */ - if (cc >= 'a') cc -= 32; /* Convert to upper case */ - c = (c << 4) + cc - ((cc < 'A')? '0' : ('A' - 10)); -#else /* EBCDIC coding */ - if (cc >= 'a' && cc <= 'z') cc += 64; /* Convert to upper case */ - c = (c << 4) + cc - ((cc >= '0')? '0' : ('A' - 10)); -#endif - } - - if (*pt == '}') - { - if (c < 0 || count > (utf8? 8 : 2)) *errorcodeptr = ERR34; - 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 && (digitab[ptr[1]] & ctype_xdigit) != 0) - { - int cc; /* Some compilers don't like ++ */ - cc = *(++ptr); /* in initializers */ -#if !EBCDIC /* ASCII coding */ - if (cc >= 'a') cc -= 32; /* Convert to upper case */ - c = c * 16 + cc - ((cc < 'A')? '0' : ('A' - 10)); -#else /* EBCDIC coding */ - if (cc <= 'z') cc += 64; /* Convert to upper case */ - c = c * 16 + cc - ((cc >= '0')? '0' : ('A' - 10)); -#endif - } - break; - - /* Other special escapes not starting with a digit are straightforward */ - - case 'c': - c = *(++ptr); - if (c == 0) - { - *errorcodeptr = ERR2; - return 0; - } - - /* A letter is upper-cased; then the 0x40 bit is flipped. This coding - is ASCII-specific, but then the whole concept of \cx is ASCII-specific. - (However, an EBCDIC equivalent has now been added.) */ - -#if !EBCDIC /* ASCII coding */ - if (c >= 'a' && c <= 'z') c -= 32; - c ^= 0x40; -#else /* EBCDIC coding */ - if (c >= 'a' && c <= 'z') c += 64; - c ^= 0xC0; -#endif - break; - - /* PCRE_EXTRA enables extensions to Perl in the matter of escapes. Any - other alphameric 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; - } - } - -*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 uschar **ptrptr, BOOL *negptr, int *dptr, int *errorcodeptr) -{ -int c, i, bot, top; -const uschar *ptr = *ptrptr; -char 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 == '{') - { - if (ptr[1] == '^') - { - *negptr = TRUE; - ptr++; - } - for (i = 0; i < sizeof(name) - 1; i++) - { - c = *(++ptr); - if (c == 0) goto ERROR_RETURN; - if (c == '}') break; - name[i] = c; - } - if (c !='}') 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 = _pcre_utt_size; - -while (bot < top) - { - i = (bot + top) >> 1; - c = strcmp(name, _pcre_utt[i].name); - if (c == 0) - { - *dptr = _pcre_utt[i].value; - return _pcre_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 - - - - -/************************************************* -* 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 uschar *p) -{ -if ((digitab[*p++] & ctype_digit) == 0) return FALSE; -while ((digitab[*p] & ctype_digit) != 0) p++; -if (*p == '}') return TRUE; - -if (*p++ != ',') return FALSE; -if (*p == '}') return TRUE; - -if ((digitab[*p++] & ctype_digit) == 0) return FALSE; -while ((digitab[*p] & ctype_digit) != 0) p++; - -return (*p == '}'); -} - - - -/************************************************* -* 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 uschar * -read_repeat_counts(const uschar *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 ((digitab[*p] & ctype_digit) != 0) min = min * 10 + *p++ - '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 == '}') max = min; else - { - if (*(++p) != '}') - { - max = 0; - while((digitab[*p] & ctype_digit) != 0) max = max * 10 + *p++ - '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; -} - - - -/************************************************* -* Find forward referenced named subpattern * -*************************************************/ - -/* This function scans along a pattern looking for capturing subpatterns, and -counting them. If it finds a named pattern that matches the name it is given, -it returns its number. This is used for forward references to named -subpatterns. We know that if (?P< is encountered, the name will be terminated -by '>' because that is checked in the first pass. - -Arguments: - pointer current position in the pattern - count current count of capturing parens - name name to seek - namelen name length - -Returns: the number of the named subpattern, or -1 if not found -*/ - -static int -find_named_parens(const uschar *ptr, int count, const uschar *name, int namelen) -{ -const uschar *thisname; -for (; *ptr != 0; ptr++) - { - if (*ptr == '\\' && ptr[1] != 0) { ptr++; continue; } - if (*ptr != '(') continue; - if (ptr[1] != '?') { count++; continue; } - if (ptr[2] == '(') { ptr += 2; continue; } - if (ptr[2] != 'P' || ptr[3] != '<') continue; - count++; - ptr += 4; - thisname = ptr; - while (*ptr != '>') ptr++; - if (namelen == ptr - thisname && strncmp(name, thisname, namelen) == 0) - return count; - } -return -1; -} - - - -/************************************************* -* 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, a change of option is important. -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 - options pointer to external options - optbit the option bit whose changing is significant, or - zero if none are - skipassert TRUE if certain assertions are to be skipped - -Returns: pointer to the first significant opcode -*/ - -static const uschar* -first_significant_code(const uschar *code, int *options, int optbit, - BOOL skipassert) -{ -for (;;) - { - switch ((int)*code) - { - case OP_OPT: - if (optbit > 0 && ((int)code[1] & optbit) != (*options & optbit)) - *options = (int)code[1]; - code += 2; - break; - - 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 += _pcre_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_BRANUMBER: - code += _pcre_OP_lengths[*code]; - break; - - default: - return code; - } - } -/* Control never reaches here */ -} - - - - -/************************************************* -* Find the fixed length of a pattern * -*************************************************/ - -/* Scan a pattern 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. - -Arguments: - code points to the start of the pattern (the bracket) - options the compiling options - -Returns: the fixed length, or -1 if there is no fixed length, - or -2 if \C was encountered -*/ - -static int -find_fixedlength(uschar *code, int options) -{ -int length = -1; - -register int branchlength = 0; -register uschar *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; - register int op = *cc; - if (op >= OP_BRA) op = OP_BRA; - - switch (op) - { - case OP_BRA: - case OP_ONCE: - case OP_COND: - d = find_fixedlength(cc, options); - 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. If it is - END it's the end of the outer call. All can be handled by the same code. */ - - case OP_ALT: - case OP_KET: - case OP_KETRMAX: - case OP_KETRMIN: - case OP_END: - if (length < 0) length = branchlength; - else if (length != branchlength) return -1; - if (*cc != OP_ALT) return length; - cc += 1 + LINK_SIZE; - branchlength = 0; - 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_BRANUMBER: - case OP_CREF: - case OP_OPT: - case OP_CALLOUT: - case OP_SOD: - case OP_SOM: - case OP_EOD: - case OP_EODN: - case OP_CIRC: - case OP_DOLL: - case OP_NOT_WORD_BOUNDARY: - case OP_WORD_BOUNDARY: - cc += _pcre_OP_lengths[*cc]; - break; - - /* Handle literal characters */ - - case OP_CHAR: - case OP_CHARNC: - case OP_NOT: - branchlength++; - cc += 2; -#ifdef SUPPORT_UTF8 - if ((options & PCRE_UTF8) != 0) - { - while ((*cc & 0xc0) == 0x80) cc++; - } -#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: - branchlength += GET2(cc,1); - cc += 4; -#ifdef SUPPORT_UTF8 - if ((options & PCRE_UTF8) != 0) - { - while((*cc & 0x80) == 0x80) cc++; - } -#endif - break; - - case OP_TYPEEXACT: - branchlength += GET2(cc,1); - cc += 4; - break; - - /* Handle single-char 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: - branchlength++; - cc++; - break; - - /* The single-byte matcher isn't allowed */ - - case OP_ANYBYTE: - return -2; - - /* Check a class for variable quantification */ - -#ifdef SUPPORT_UTF8 - case OP_XCLASS: - cc += GET(cc, 1) - 33; - /* Fall through */ -#endif - - case OP_CLASS: - case OP_NCLASS: - cc += 33; - - switch (*cc) - { - 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,3)) return -1; - branchlength += GET2(cc,1); - cc += 5; - break; - - default: - branchlength++; - } - break; - - /* Anything else is variable length */ - - default: - return -1; - } - } -/* Control never gets here */ -} - - - - -/************************************************* -* Scan compiled regex for numbered bracket * -*************************************************/ - -/* This little function scans through a compiled pattern until it finds a -capturing bracket with the given number. - -Arguments: - code points to start of expression - utf8 TRUE in UTF-8 mode - number the required bracket number - -Returns: pointer to the opcode for the bracket, or NULL if not found -*/ - -static const uschar * -find_bracket(const uschar *code, BOOL utf8, 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 bracketed group */ - - else if (c > OP_BRA) - { - int n = c - OP_BRA; - if (n > EXTRACT_BASIC_MAX) n = GET2(code, 2+LINK_SIZE); - if (n == number) return (uschar *)code; - code += _pcre_OP_lengths[OP_BRA]; - } - - /* Otherwise, we get the item's length from the table. 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 scan along to skip the - extra bytes. All opcodes are less than 128, so we can use relatively - efficient code. */ - - else - { - code += _pcre_OP_lengths[c]; - if (utf8) switch(c) - { - case OP_CHAR: - case OP_CHARNC: - case OP_EXACT: - case OP_UPTO: - case OP_MINUPTO: - case OP_STAR: - case OP_MINSTAR: - case OP_PLUS: - case OP_MINPLUS: - case OP_QUERY: - case OP_MINQUERY: - while ((*code & 0xc0) == 0x80) code++; - break; - } - } - } -} - - - -/************************************************* -* 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 - utf8 TRUE in UTF-8 mode - -Returns: pointer to the opcode for OP_RECURSE, or NULL if not found -*/ - -static const uschar * -find_recurse(const uschar *code, BOOL utf8) -{ -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); - - /* All bracketed groups have the same length. */ - - else if (c > OP_BRA) - { - code += _pcre_OP_lengths[OP_BRA]; - } - - /* Otherwise, we get the item's length from the table. 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 scan along to skip the - extra bytes. All opcodes are less than 128, so we can use relatively - efficient code. */ - - else - { - code += _pcre_OP_lengths[c]; - if (utf8) switch(c) - { - case OP_CHAR: - case OP_CHARNC: - case OP_EXACT: - case OP_UPTO: - case OP_MINUPTO: - case OP_STAR: - case OP_MINSTAR: - case OP_PLUS: - case OP_MINPLUS: - case OP_QUERY: - case OP_MINQUERY: - while ((*code & 0xc0) == 0x80) code++; - break; - } - } - } -} - - - -/************************************************* -* 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 only from could_be_empty() -below. Note that first_significant_code() skips over assertions. 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 - utf8 TRUE if in UTF8 mode - -Returns: TRUE if what is matched could be empty -*/ - -static BOOL -could_be_empty_branch(const uschar *code, const uschar *endcode, BOOL utf8) -{ -register int c; -for (code = first_significant_code(code + 1 + LINK_SIZE, NULL, 0, TRUE); - code < endcode; - code = first_significant_code(code + _pcre_OP_lengths[c], NULL, 0, TRUE)) - { - const uschar *ccode; - - c = *code; - - if (c >= OP_BRA) - { - BOOL empty_branch; - if (GET(code, 1) == 0) return TRUE; /* Hit unclosed bracket */ - - /* Scan a closed bracket */ - - empty_branch = FALSE; - do - { - if (!empty_branch && could_be_empty_branch(code, endcode, utf8)) - empty_branch = TRUE; - code += GET(code, 1); - } - while (*code == OP_ALT); - if (!empty_branch) return FALSE; /* All branches are non-empty */ - code += 1 + LINK_SIZE; - c = *code; - } - - else switch (c) - { - /* Check for quantifiers after a class */ - -#ifdef SUPPORT_UTF8 - case OP_XCLASS: - ccode = code + GET(code, 1); - goto CHECK_CLASS_REPEAT; -#endif - - case OP_CLASS: - case OP_NCLASS: - ccode = code + 33; - -#ifdef SUPPORT_UTF8 - 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_ANYBYTE: - case OP_CHAR: - case OP_CHARNC: - case OP_NOT: - case OP_PLUS: - case OP_MINPLUS: - case OP_EXACT: - case OP_NOTPLUS: - case OP_NOTMINPLUS: - case OP_NOTEXACT: - case OP_TYPEPLUS: - case OP_TYPEMINPLUS: - case OP_TYPEEXACT: - return FALSE; - - /* End of branch */ - - case OP_KET: - case OP_KETRMAX: - case OP_KETRMIN: - case OP_ALT: - return TRUE; - - /* In UTF-8 mode, STAR, MINSTAR, QUERY, MINQUERY, UPTO, and MINUPTO may be - followed by a multibyte character */ - -#ifdef SUPPORT_UTF8 - case OP_STAR: - case OP_MINSTAR: - case OP_QUERY: - case OP_MINQUERY: - case OP_UPTO: - case OP_MINUPTO: - if (utf8) while ((code[2] & 0xc0) == 0x80) code++; - break; -#endif - } - } - -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. - -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 - utf8 TRUE if in UTF-8 mode - -Returns: TRUE if what is matched could be empty -*/ - -static BOOL -could_be_empty(const uschar *code, const uschar *endcode, branch_chain *bcptr, - BOOL utf8) -{ -while (bcptr != NULL && bcptr->current >= code) - { - if (!could_be_empty_branch(bcptr->current, endcode, utf8)) 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 an -optional ^ and then a sequence of letters, terminated by a matching ":]" or -".]" or "=]". - -Argument: - ptr pointer to the initial [ - endptr where to return the end pointer - cd pointer to compile data - -Returns: TRUE or FALSE -*/ - -static BOOL -check_posix_syntax(const uschar *ptr, const uschar **endptr, compile_data *cd) -{ -int terminator; /* Don't combine these lines; the Solaris cc */ -terminator = *(++ptr); /* compiler warns about "non-constant" initializer. */ -if (*(++ptr) == '^') ptr++; -while ((cd->ctypes[*ptr] & ctype_letter) != 0) ptr++; -if (*ptr == terminator && ptr[1] == ']') - { - *endptr = ptr; - return TRUE; - } -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 uschar *ptr, int len) -{ -register int yield = 0; -while (posix_name_lengths[yield] != 0) - { - if (len == posix_name_lengths[yield] && - strncmp((const char *)ptr, posix_names[yield], len) == 0) return yield; - 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 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 is the job of this function. Before it is called, the -partially compiled regex must be temporarily terminated with OP_END. - -Arguments: - group points to the start of the group - adjust the amount by which the group is to be moved - utf8 TRUE in UTF-8 mode - cd contains pointers to tables etc. - -Returns: nothing -*/ - -static void -adjust_recurse(uschar *group, int adjust, BOOL utf8, compile_data *cd) -{ -uschar *ptr = group; -while ((ptr = (uschar *)find_recurse(ptr, utf8)) != NULL) - { - int 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 uschar * -auto_callout(uschar *code, const uschar *ptr, compile_data *cd) -{ -*code++ = OP_CALLOUT; -*code++ = 255; -PUT(code, 0, 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(uschar *previous_callout, const uschar *ptr, compile_data *cd) -{ -int length = 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(int *cptr, int d, int *ocptr, int *odptr) -{ -int c, othercase, next; - -for (c = *cptr; c <= d; c++) - { if ((othercase = _pcre_ucp_othercase(c)) >= 0) break; } - -if (c > d) return FALSE; - -*ocptr = othercase; -next = othercase + 1; - -for (++c; c <= d; c++) - { - if (_pcre_ucp_othercase(c) != next) break; - next++; - } - -*odptr = next - 1; -*cptr = c; - -return TRUE; -} -#endif /* SUPPORT_UCP */ - - -/************************************************* -* Compile one branch * -*************************************************/ - -/* Scan the pattern, compiling it into the code vector. If the options are -changed during the branch, the pointer is used to change the external options -bits. - -Arguments: - optionsptr pointer to the option bits - brackets points to number of extracting brackets used - codeptr points to the pointer to the current code point - ptrptr points to the current pattern pointer - errorcodeptr points to error code variable - firstbyteptr set to initial literal character, or < 0 (REQ_UNSET, REQ_NONE) - reqbyteptr set to the last literal character required, else < 0 - bcptr points to current branch chain - cd contains pointers to tables etc. - -Returns: TRUE on success - FALSE, with *errorcodeptr set non-zero on error -*/ - -static BOOL -compile_branch(int *optionsptr, int *brackets, uschar **codeptr, - const uschar **ptrptr, int *errorcodeptr, int *firstbyteptr, - int *reqbyteptr, branch_chain *bcptr, compile_data *cd) -{ -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; -int firstbyte, reqbyte; -int zeroreqbyte, zerofirstbyte; -int req_caseopt, reqvary, tempreqvary; -int options = *optionsptr; -int after_manual_callout = 0; -register int c; -register uschar *code = *codeptr; -uschar *tempcode; -BOOL inescq = FALSE; -BOOL groupsetfirstbyte = FALSE; -const uschar *ptr = *ptrptr; -const uschar *tempptr; -uschar *previous = NULL; -uschar *previous_callout = NULL; -uschar classbits[32]; - -#ifdef SUPPORT_UTF8 -BOOL class_utf8; -BOOL utf8 = (options & PCRE_UTF8) != 0; -uschar *class_utf8data; -uschar utf8_char[6]; -#else -BOOL utf8 = FALSE; -#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; reqbyte 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 zeroreqbyte when such a repeat is encountered. The individual -item types that can be repeated set these backoff variables appropriately. */ - -firstbyte = reqbyte = zerofirstbyte = zeroreqbyte = REQ_UNSET; - -/* The variable req_caseopt contains either the REQ_CASELESS value or zero, -according to the current setting of the caseless flag. REQ_CASELESS is a bit -value > 255. It is added into the firstbyte or reqbyte 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 possessive_quantifier; - BOOL is_quantifier; - int class_charcount; - int class_lastchar; - int newoptions; - int recno; - int skipbytes; - int subreqbyte; - int subfirstbyte; - int mclength; - uschar mcbuffer[8]; - - /* Next byte in the pattern */ - - c = *ptr; - - /* If in \Q...\E, check for the end; if not, we have a literal */ - - if (inescq && c != 0) - { - if (c == '\\' && ptr[1] == 'E') - { - inescq = FALSE; - ptr++; - continue; - } - else - { - if (previous_callout != NULL) - { - 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 == '*' || c == '+' || c == '?' || - (c == '{' && is_counted_repeat(ptr+1)); - - if (!is_quantifier && previous_callout != NULL && - after_manual_callout-- <= 0) - { - complete_callout(previous_callout, ptr, cd); - previous_callout = NULL; - } - - /* In extended mode, skip white space and comments */ - - if ((options & PCRE_EXTENDED) != 0) - { - if ((cd->ctypes[c] & ctype_space) != 0) continue; - if (c == '#') - { - while (*(++ptr) != 0) if (IS_NEWLINE(ptr)) break; - if (*ptr != 0) - { - ptr += cd->nllen - 1; - 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) - { - /* The branch terminates at end of string, |, or ). */ - - case 0: - case '|': - case ')': - *firstbyteptr = firstbyte; - *reqbyteptr = reqbyte; - *codeptr = code; - *ptrptr = ptr; - return TRUE; - - /* Handle single-character metacharacters. In multiline mode, ^ disables - the setting of any following char as a first character. */ - - case '^': - if ((options & PCRE_MULTILINE) != 0) - { - if (firstbyte == REQ_UNSET) firstbyte = REQ_NONE; - } - previous = NULL; - *code++ = OP_CIRC; - break; - - case '$': - previous = NULL; - *code++ = OP_DOLL; - break; - - /* There can never be a first char if '.' is first, whatever happens about - repeats. The value of reqbyte doesn't change either. */ - - case '.': - if (firstbyte == REQ_UNSET) firstbyte = REQ_NONE; - zerofirstbyte = firstbyte; - zeroreqbyte = reqbyte; - previous = code; - *code++ = 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. - */ - - case '[': - 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] == ':' || ptr[1] == '.' || ptr[1] == '=') && - check_posix_syntax(ptr, &tempptr, cd)) - { - *errorcodeptr = (ptr[1] == ':')? ERR13 : ERR31; - goto FAILED; - } - - /* If the first character is '^', set the negation flag and skip it. */ - - if ((c = *(++ptr)) == '^') - { - negate_class = TRUE; - c = *(++ptr); - } - else - { - negate_class = FALSE; - } - - /* Keep a count of chars with values < 256 so that we can optimize the case - of just a single character (as long as it's < 256). For higher valued UTF-8 - characters, we don't yet do any optimization. */ - - class_charcount = 0; - class_lastchar = -1; - -#ifdef SUPPORT_UTF8 - class_utf8 = FALSE; /* No chars >= 256 */ - class_utf8data = code + LINK_SIZE + 34; /* For UTF-8 items */ -#endif - - /* Initialize the 32-char bit map to all zeros. We have to build the - map in a temporary bit of store, in case the class contains only 1 - character (< 256), because in that case the compiled code doesn't use the - bit map. */ - - memset(classbits, 0, 32 * sizeof(uschar)); - - /* Process characters until ] is reached. By writing this as a "do" it - means that an initial ] is taken as a data character. The first pass - through the regex checked the overall syntax, so we don't need to be very - strict here. At the start of the loop, c contains the first byte of the - character. */ - - do - { -#ifdef SUPPORT_UTF8 - if (utf8 && c > 127) - { /* Braces are required because the */ - GETCHARLEN(c, ptr, ptr); /* macro generates multiple statements */ - } -#endif - - /* Inside \Q...\E everything is literal except \E */ - - if (inescq) - { - if (c == '\\' && ptr[1] == 'E') - { - inescq = FALSE; - ptr++; - continue; - } - else goto LONE_SINGLE_CHARACTER; - } - - /* 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 == '[' && - (ptr[1] == ':' || ptr[1] == '.' || ptr[1] == '=') && - check_posix_syntax(ptr, &tempptr, cd)) - { - BOOL local_negate = FALSE; - int posix_class, taboffset, tabopt; - register const uschar *cbits = cd->cbits; - uschar pbits[32]; - - if (ptr[1] != ':') - { - *errorcodeptr = ERR31; - goto FAILED; - } - - ptr += 2; - if (*ptr == '^') - { - local_negate = TRUE; - ptr++; - } - - posix_class = check_posix_name(ptr, 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; - - /* 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(uschar)); - - /* 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; - class_charcount = 10; /* Set > 1; assumes more than 1 per class */ - 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. Escaped items are checked for - validity in the pre-compiling pass. The sequence \b is a special case. - Inside a class (and only there) it is treated as backspace. Elsewhere - it marks a word boundary. Other escapes have preset maps ready to - or into the one we are building. We assume they have more than one - character in them, so set class_charcount bigger than one. */ - - if (c == '\\') - { - c = check_escape(&ptr, errorcodeptr, *brackets, options, TRUE); - - if (-c == ESC_b) c = '\b'; /* \b is backslash in a class */ - else if (-c == ESC_X) c = 'X'; /* \X is literal X in a class */ - else if (-c == ESC_Q) /* Handle start of quoted string */ - { - if (ptr[1] == '\\' && ptr[2] == 'E') - { - ptr += 2; /* avoid empty string */ - } - else inescq = TRUE; - continue; - } - - if (c < 0) - { - register const uschar *cbits = cd->cbits; - class_charcount += 2; /* Greater than 1 is what matters */ - switch (-c) - { - case ESC_d: - for (c = 0; c < 32; c++) classbits[c] |= cbits[c+cbit_digit]; - continue; - - case ESC_D: - 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: - for (c = 0; c < 32; c++) classbits[c] |= ~cbits[c+cbit_word]; - continue; - - case ESC_s: - 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_S: - for (c = 0; c < 32; c++) classbits[c] |= ~cbits[c+cbit_space]; - classbits[1] |= 0x08; /* Perl 5.004 onwards omits VT from \s */ - 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; - class_utf8 = TRUE; - *class_utf8data++ = ((-c == ESC_p) != negated)? - XCL_PROP : XCL_NOTPROP; - *class_utf8data++ = ptype; - *class_utf8data++ = pdata; - class_charcount -= 2; /* Not a < 256 character */ - } - 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; - } - c = *ptr; /* The final character */ - class_charcount -= 2; /* Undo the default count from above */ - } - } - - /* Fall through if we have a single character (c >= 0). This may be - > 256 in UTF-8 mode. */ - - } /* 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 - here is treated as a literal. */ - - if (ptr[1] == '-' && ptr[2] != ']') - { - int d; - ptr += 2; - -#ifdef SUPPORT_UTF8 - if (utf8) - { /* 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 (d == '\\') - { - const uschar *oldptr = ptr; - d = check_escape(&ptr, errorcodeptr, *brackets, options, TRUE); - - /* \b is backslash; \X is literal X; any other special means the '-' - was literal */ - - if (d < 0) - { - if (d == -ESC_b) d = '\b'; - else if (d == -ESC_X) d = 'X'; else - { - ptr = oldptr - 2; - goto LONE_SINGLE_CHARACTER; /* A few lines below */ - } - } - } - - /* The check that the two values are in the correct order happens in - the pre-pass. Optimize one-character ranges */ - - if (d == c) goto LONE_SINGLE_CHARACTER; /* A few lines below */ - - /* 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. */ - -#ifdef SUPPORT_UTF8 - if (utf8 && (d > 255 || ((options & PCRE_CASELESS) != 0 && d > 127))) - { - class_utf8 = 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 - if ((options & PCRE_CASELESS) != 0) - { - int occ, ocd; - int cc = c; - int origd = d; - while (get_othercase_range(&cc, origd, &occ, &ocd)) - { - if (occ >= c && ocd <= d) continue; /* Skip embedded ranges */ - - if (occ < c && ocd >= 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 > d && occ <= d + 1) /* always shorter than */ - { /* the basic range. */ - d = ocd; - continue; - } - - if (occ == ocd) - { - *class_utf8data++ = XCL_SINGLE; - } - else - { - *class_utf8data++ = XCL_RANGE; - class_utf8data += _pcre_ord2utf8(occ, class_utf8data); - } - class_utf8data += _pcre_ord2utf8(ocd, class_utf8data); - } - } -#endif /* SUPPORT_UCP */ - - /* Now record the original range, possibly modified for UCP caseless - overlapping ranges. */ - - *class_utf8data++ = XCL_RANGE; - class_utf8data += _pcre_ord2utf8(c, class_utf8data); - class_utf8data += _pcre_ord2utf8(d, class_utf8data); - - /* With UCP support, we are done. Without UCP support, there is no - caseless matching for UTF-8 characters > 127; we can use the bit map - for the smaller ones. */ - -#ifdef SUPPORT_UCP - continue; /* With next character in the class */ -#else - if ((options & PCRE_CASELESS) == 0 || c > 127) continue; - - /* Adjust upper limit and fall through to set up the map */ - - d = 127; - -#endif /* SUPPORT_UCP */ - } -#endif /* SUPPORT_UTF8 */ - - /* We use the bit map for all cases when not in UTF-8 mode; else - ranges that lie entirely within 0-127 when there is UCP support; else - for partial ranges without UCP support. */ - - 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)); - } - class_charcount++; /* in case a one-char range */ - class_lastchar = c; - } - - 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: - - /* Handle a character that cannot go in the bit map */ - -#ifdef SUPPORT_UTF8 - if (utf8 && (c > 255 || ((options & PCRE_CASELESS) != 0 && c > 127))) - { - class_utf8 = TRUE; - *class_utf8data++ = XCL_SINGLE; - class_utf8data += _pcre_ord2utf8(c, class_utf8data); - -#ifdef SUPPORT_UCP - if ((options & PCRE_CASELESS) != 0) - { - int othercase; - if ((othercase = _pcre_ucp_othercase(c)) >= 0) - { - *class_utf8data++ = XCL_SINGLE; - class_utf8data += _pcre_ord2utf8(othercase, class_utf8data); - } - } -#endif /* SUPPORT_UCP */ - - } - else -#endif /* SUPPORT_UTF8 */ - - /* Handle a single-byte character */ - { - classbits[c/8] |= (1 << (c&7)); - if ((options & PCRE_CASELESS) != 0) - { - c = cd->fcc[c]; /* flip case */ - classbits[c/8] |= (1 << (c&7)); - } - class_charcount++; - class_lastchar = c; - } - } - - /* Loop until ']' reached; the check for end of string happens inside the - loop. This "while" is the end of the "do" above. */ - - while ((c = *(++ptr)) != ']' || inescq); - - /* If class_charcount is 1, we saw precisely one character whose value is - less than 256. In non-UTF-8 mode we can always optimize. In UTF-8 mode, we - can optimize the negative case only if there were no characters >= 128 - because OP_NOT and the related opcodes like OP_NOTSTAR operate on - single-bytes only. This is an historical hangover. Maybe one day we can - tidy these opcodes to handle multi-byte characters. - - The optimization throws away the bit map. We turn the item into a - 1-character OP_CHAR[NC] if it's positive, or OP_NOT if it's negative. Note - that OP_NOT does not support multibyte characters. In the positive case, it - can cause firstbyte to be set. Otherwise, there can be no first char if - this item is first, whatever repeat count may follow. In the case of - reqbyte, save the previous value for reinstating. */ - -#ifdef SUPPORT_UTF8 - if (class_charcount == 1 && - (!utf8 || - (!class_utf8 && (!negate_class || class_lastchar < 128)))) - -#else - if (class_charcount == 1) -#endif - { - zeroreqbyte = reqbyte; - - /* The OP_NOT opcode works on one-byte characters only. */ - - if (negate_class) - { - if (firstbyte == REQ_UNSET) firstbyte = REQ_NONE; - zerofirstbyte = firstbyte; - *code++ = OP_NOT; - *code++ = class_lastchar; - break; - } - - /* For a single, positive character, get the value into mcbuffer, and - then we can handle this with the normal one-character code. */ - -#ifdef SUPPORT_UTF8 - if (utf8 && class_lastchar > 127) - mclength = _pcre_ord2utf8(class_lastchar, mcbuffer); - else -#endif - { - mcbuffer[0] = class_lastchar; - mclength = 1; - } - goto ONE_CHAR; - } /* End of 1-char optimization */ - - /* The general case - not the one-char optimization. If this is the first - thing in the branch, there can be no first char setting, whatever the - repeat count. Any reqbyte setting must remain unchanged after any kind of - repeat. */ - - if (firstbyte == REQ_UNSET) firstbyte = REQ_NONE; - zerofirstbyte = firstbyte; - zeroreqbyte = reqbyte; - - /* If there are characters with values > 255, we have to compile an - extended class, with its own opcode. If there are no characters < 256, - we can omit the bitmap. */ - -#ifdef SUPPORT_UTF8 - if (class_utf8) - { - *class_utf8data++ = 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, install it, and move on to the end of - the extra data */ - - if (class_charcount > 0) - { - *code++ |= XCL_MAP; - memcpy(code, classbits, 32); - code = class_utf8data; - } - - /* If the map is not required, slide down the extra data. */ - - else - { - int len = class_utf8data - (code + 33); - memmove(code + 1, code + 33, len); - code += len + 1; - } - - /* Now fill in the complete length of the item */ - - PUT(previous, 1, code - previous); - break; /* End of class handling */ - } -#endif - - /* If there are no characters > 255, negate the 32-byte map if necessary, - and copy it into the code vector. If this is the first thing in the branch, - there can be no first char setting, whatever the repeat count. Any reqbyte - setting must remain unchanged after any kind of repeat. */ - - if (negate_class) - { - *code++ = OP_NCLASS; - for (c = 0; c < 32; c++) code[c] = ~classbits[c]; - } - else - { - *code++ = OP_CLASS; - memcpy(code, classbits, 32); - } - code += 32; - break; - - /* Various kinds of repeat; '{' is not necessarily a quantifier, but this - has been tested above. */ - - case '{': - 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 '*': - repeat_min = 0; - repeat_max = -1; - goto REPEAT; - - case '+': - repeat_min = 1; - repeat_max = -1; - goto REPEAT; - - case '?': - repeat_min = 0; - repeat_max = 1; - - REPEAT: - if (previous == NULL) - { - *errorcodeptr = ERR9; - goto FAILED; - } - - if (repeat_min == 0) - { - firstbyte = zerofirstbyte; /* Adjust for zero repeat */ - reqbyte = zeroreqbyte; /* 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 to make space - for an inserted OP_ONCE for the additional '+' extension. */ - - 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] == '+') - { - repeat_type = 0; /* Force greedy */ - possessive_quantifier = TRUE; - ptr++; - } - else if (ptr[1] == '?') - { - repeat_type = greedy_non_default; - ptr++; - } - else repeat_type = greedy_default; - - /* If previous was a recursion, we need to wrap it inside brackets so that - it can be replicated if necessary. */ - - if (*previous == OP_RECURSE) - { - memmove(previous + 1 + LINK_SIZE, previous, 1 + LINK_SIZE); - code += 1 + LINK_SIZE; - *previous = OP_BRA; - PUT(previous, 1, code - previous); - *code = OP_KET; - PUT(code, 1, code - previous); - code += 1 + LINK_SIZE; - } - - /* If previous was a character match, abolish the item and generate a - repeat item instead. If a char item has a minumum of more than one, ensure - that it is set in reqbyte - 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 firstbyte - instead. */ - - if (*previous == OP_CHAR || *previous == OP_CHARNC) - { - /* Deal with UTF-8 characters that take up more than one byte. 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 0x80 to flag that it's a - length rather than a small character. */ - -#ifdef SUPPORT_UTF8 - if (utf8 && (code[-1] & 0x80) != 0) - { - uschar *lastchar = code - 1; - while((*lastchar & 0xc0) == 0x80) lastchar--; - c = code - lastchar; /* Length of UTF-8 character */ - memcpy(utf8_char, lastchar, c); /* Save the char */ - c |= 0x80; /* Flag c as a length */ - } - else -#endif - - /* Handle the case of a single byte - either with no UTF8 support, or - with UTF-8 disabled, or for a UTF-8 character < 128. */ - - { - c = code[-1]; - if (repeat_min > 1) reqbyte = c | req_caseopt | cd->req_varyopt; - } - - goto OUTPUT_SINGLE_REPEAT; /* Code shared with single character types */ - } - - /* If previous was a single negated character ([^a] or similar), we use - one of the special opcodes, replacing it. The code is shared with single- - character repeats by setting opt_type to add a suitable offset into - repeat_type. OP_NOT is currently used only for single-byte chars. */ - - else if (*previous == OP_NOT) - { - op_type = OP_NOTSTAR - OP_STAR; /* Use "not" opcodes */ - c = previous[1]; - goto OUTPUT_SINGLE_REPEAT; - } - - /* 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) - { - uschar *oldcode; - int prop_type, prop_value; - op_type = OP_TYPESTAR - OP_STAR; /* Use type opcodes */ - c = *previous; - - 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; - - /* 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->nopartial = TRUE; - - /* 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 it - 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 0x80 bit as a flag. */ - - if (repeat_max < 0) - { -#ifdef SUPPORT_UTF8 - if (utf8 && c >= 128) - { - memcpy(code, utf8_char, 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. */ - - else if (repeat_max != repeat_min) - { -#ifdef SUPPORT_UTF8 - if (utf8 && c >= 128) - { - memcpy(code, utf8_char, c & 7); - code += c & 7; - } - else -#endif - *code++ = c; - if (prop_type >= 0) - { - *code++ = prop_type; - *code++ = prop_value; - } - repeat_max -= repeat_min; - *code++ = OP_UPTO + repeat_type; - PUT2INC(code, 0, repeat_max); - } - } - - /* The character or character type itself comes last in all cases. */ - -#ifdef SUPPORT_UTF8 - if (utf8 && c >= 128) - { - memcpy(code, utf8_char, 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 || -#ifdef SUPPORT_UTF8 - *previous == OP_XCLASS || -#endif - *previous == OP_REF) - { - if (repeat_max == 0) - { - code = previous; - goto END_REPEAT; - } - - /* 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->nopartial = TRUE; - - 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. */ - - else if (*previous >= OP_BRA || *previous == OP_ONCE || - *previous == OP_COND) - { - register int i; - int ketoffset = 0; - int len = code - previous; - uschar *bralink = NULL; - - /* If the maximum repeat count is unlimited, find the end of the bracket - by scanning through from the start, and compute the offset back to it - from the current code pointer. There may be an OP_OPT setting following - the final KET, so we can't find the end just by going back from the code - pointer. */ - - if (repeat_max == -1) - { - register uschar *ket = previous; - do ket += GET(ket, 1); while (*ket != OP_KET); - ketoffset = code - ket; - } - - /* 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 just omit the group from the output - altogether. */ - - if (repeat_max == 0) - { - code = previous; - goto END_REPEAT; - } - - /* 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 group, because the offset is from the start of the whole - regex. Temporarily terminate the pattern while doing this. */ - - if (repeat_max <= 1) - { - *code = OP_END; - adjust_recurse(previous, 1, utf8, cd); - memmove(previous+1, previous, len); - code++; - *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, utf8, cd); - memmove(previous + 2 + LINK_SIZE, previous, 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 : 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. */ - - else - { - if (repeat_min > 1) - { - if (groupsetfirstbyte && reqbyte < 0) reqbyte = firstbyte; - for (i = 1; i < repeat_min; i++) - { - memcpy(code, previous, len); - 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. */ - - if (repeat_max >= 0) - { - for (i = repeat_max - 1; i >= 0; i--) - { - *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 : code - bralink; - bralink = code; - PUTINC(code, 0, offset); - } - - memcpy(code, previous, len); - 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 = code - bralink + 1; - uschar *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. We - can't just offset backwards from the current code point, because we - don't know if there's been an options resetting after the ket. The - correct offset was computed above. */ - - else code[-ketoffset] = OP_KETRMAX + repeat_type; - } - - /* Else there's some kind of shambles */ - - else - { - *errorcodeptr = ERR11; - goto FAILED; - } - - /* If the character following a repeat is '+', we wrap the entire repeated - item inside OP_ONCE brackets. This is just syntactic sugar, taken from - Sun's Java package. The repeated item starts at tempcode, not at previous, - which might be the first part of a string whose (former) last char we - repeated. However, we don't support '+' after a greediness '?'. */ - - if (possessive_quantifier) - { - int len = code - tempcode; - memmove(tempcode + 1+LINK_SIZE, tempcode, len); - code += 1 + LINK_SIZE; - len += 1 + LINK_SIZE; - tempcode[0] = OP_ONCE; - *code++ = OP_KET; - PUTINC(code, 0, len); - PUT(tempcode, 1, len); - } - - /* In all case we no longer have a previous item. We also set the - "follows varying string" flag for subsequently encountered reqbytes 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 bracket sub-expression, or comment or lookahead or - lookbehind or option setting or condition. First deal with special things - that can come after a bracket; all are introduced by ?, and the appearance - of any of them means that this is not a referencing group. They were - checked for validity in the first pass over the string, so we don't have to - check for syntax errors here. */ - - case '(': - newoptions = options; - skipbytes = 0; - - if (*(++ptr) == '?') - { - int set, unset; - int *optset; - - switch (*(++ptr)) - { - case '#': /* Comment; skip to ket */ - ptr++; - while (*ptr != ')') ptr++; - continue; - - case ':': /* Non-extracting bracket */ - bravalue = OP_BRA; - ptr++; - break; - - case '(': - bravalue = OP_COND; /* Conditional group */ - - /* A condition can be a number, referring to a numbered group, a name, - referring to a named group, 'R', referring to recursion, or an - assertion. There are two unfortunate ambiguities, caused by history. - (a) 'R' can be the recursive thing or the name 'R', 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. If the first - character after (?( is a word character, we know the rest up to ) will - also be word characters because the syntax was checked in the first - pass. */ - - if ((cd->ctypes[ptr[1]] & ctype_word) != 0) - { - int i, namelen; - int condref = 0; - const uschar *name; - uschar *slot = cd->name_table; - - /* This is needed for all successful cases. */ - - skipbytes = 3; - - /* Read the name, but also get it as a number if it's all digits */ - - name = ++ptr; - while (*ptr != ')') - { - if (condref >= 0) - condref = ((digitab[*ptr] & ctype_digit) != 0)? - condref * 10 + *ptr - '0' : -1; - ptr++; - } - namelen = ptr - name; - ptr++; - - for (i = 0; i < cd->names_found; i++) - { - if (strncmp((char *)name, (char *)slot+2, namelen) == 0) break; - slot += cd->name_entry_size; - } - - /* Found a previous named subpattern */ - - if (i < cd->names_found) - { - condref = GET2(slot, 0); - code[1+LINK_SIZE] = OP_CREF; - PUT2(code, 2+LINK_SIZE, condref); - } - - /* Search the pattern for a forward reference */ - - else if ((i = find_named_parens(ptr, *brackets, name, namelen)) > 0) - { - code[1+LINK_SIZE] = OP_CREF; - PUT2(code, 2+LINK_SIZE, i); - } - - /* Check for 'R' for recursion */ - - else if (namelen == 1 && *name == 'R') - { - code[1+LINK_SIZE] = OP_CREF; - PUT2(code, 2+LINK_SIZE, CREF_RECURSE); - } - - /* Check for a subpattern number */ - - else if (condref > 0) - { - code[1+LINK_SIZE] = OP_CREF; - PUT2(code, 2+LINK_SIZE, condref); - } - - /* Either an unidentified subpattern, or a reference to (?(0) */ - - else - { - *errorcodeptr = (condref == 0)? ERR35: ERR15; - goto FAILED; - } - } - - /* For conditions that are assertions, we just fall through, having - set bravalue above. */ - - break; - - case '=': /* Positive lookahead */ - bravalue = OP_ASSERT; - ptr++; - break; - - case '!': /* Negative lookahead */ - bravalue = OP_ASSERT_NOT; - ptr++; - break; - - case '<': /* Lookbehinds */ - switch (*(++ptr)) - { - case '=': /* Positive lookbehind */ - bravalue = OP_ASSERTBACK; - ptr++; - break; - - case '!': /* Negative lookbehind */ - bravalue = OP_ASSERTBACK_NOT; - ptr++; - break; - } - break; - - case '>': /* One-time brackets */ - bravalue = OP_ONCE; - ptr++; - break; - - case '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; /* Already checked that the terminating */ - { /* closing parenthesis is present. */ - int n = 0; - while ((digitab[*(++ptr)] & ctype_digit) != 0) - n = n * 10 + *ptr - '0'; - if (n > 255) - { - *errorcodeptr = ERR38; - goto FAILED; - } - *code++ = n; - PUT(code, 0, ptr - cd->start_pattern + 1); /* Pattern offset */ - PUT(code, LINK_SIZE, 0); /* Default length */ - code += 2 * LINK_SIZE; - } - previous = NULL; - continue; - - case 'P': /* Named subpattern handling */ - if (*(++ptr) == '<') /* Definition */ - { - int i, namelen; - uschar *slot = cd->name_table; - const uschar *name; /* Don't amalgamate; some compilers */ - name = ++ptr; /* grumble at autoincrement in declaration */ - - while (*ptr++ != '>'); - namelen = ptr - name - 1; - - for (i = 0; i < cd->names_found; i++) - { - int crc = memcmp(name, slot+2, namelen); - if (crc == 0) - { - if (slot[2+namelen] == 0) - { - if ((options & PCRE_DUPNAMES) == 0) - { - *errorcodeptr = ERR43; - goto FAILED; - } - } - else crc = -1; /* Current name is substring */ - } - if (crc < 0) - { - memmove(slot + cd->name_entry_size, slot, - (cd->names_found - i) * cd->name_entry_size); - break; - } - slot += cd->name_entry_size; - } - - PUT2(slot, 0, *brackets + 1); - memcpy(slot + 2, name, namelen); - slot[2+namelen] = 0; - cd->names_found++; - goto NUMBERED_GROUP; - } - - if (*ptr == '=' || *ptr == '>') /* Reference or recursion */ - { - int i, namelen; - int type = *ptr++; - const uschar *name = ptr; - uschar *slot = cd->name_table; - - while (*ptr != ')') ptr++; - namelen = ptr - name; - - for (i = 0; i < cd->names_found; i++) - { - if (strncmp((char *)name, (char *)slot+2, 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_named_parens(ptr, *brackets, name, namelen)) <= 0) - { - *errorcodeptr = ERR15; - goto FAILED; - } - - if (type == '>') goto HANDLE_RECURSION; /* A few lines below */ - - /* Back reference */ - - previous = code; - *code++ = OP_REF; - PUT2INC(code, 0, recno); - cd->backref_map |= (recno < 32)? (1 << recno) : 1; - if (recno > cd->top_backref) cd->top_backref = recno; - continue; - } - - /* Should never happen */ - break; - - case 'R': /* Pattern recursion */ - ptr++; /* Same as (?0) */ - /* Fall through */ - - /* Recursion or "subroutine" call */ - - case '0': case '1': case '2': case '3': case '4': - case '5': case '6': case '7': case '8': case '9': - { - const uschar *called; - recno = 0; - while((digitab[*ptr] & ctype_digit) != 0) - recno = recno * 10 + *ptr++ - '0'; - - /* Come here from code above that handles a named recursion */ - - HANDLE_RECURSION: - - previous = code; - - /* Find the bracket that is being referenced. Temporarily end the - regex in case it doesn't exist. */ - - *code = OP_END; - called = (recno == 0)? cd->start_code : - find_bracket(cd->start_code, utf8, recno); - if (called == NULL) - { - *errorcodeptr = ERR15; - goto FAILED; - } - - /* If 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. */ - - if (GET(called, 1) == 0 && could_be_empty(called, code, bcptr, utf8)) - { - *errorcodeptr = ERR40; - goto FAILED; - } - - /* Insert the recursion/subroutine item, automatically wrapped inside - "once" brackets. */ - - *code = OP_ONCE; - PUT(code, 1, 2 + 2*LINK_SIZE); - code += 1 + LINK_SIZE; - - *code = OP_RECURSE; - PUT(code, 1, called - cd->start_code); - code += 1 + LINK_SIZE; - - *code = OP_KET; - PUT(code, 1, 2 + 2*LINK_SIZE); - code += 1 + LINK_SIZE; - } - continue; - - /* Character after (? not specially recognized */ - - default: /* Option setting */ - set = unset = 0; - optset = &set; - - while (*ptr != ')' && *ptr != ':') - { - switch (*ptr++) - { - case '-': optset = &unset; break; - - case 'i': *optset |= PCRE_CASELESS; break; - case 'J': *optset |= PCRE_DUPNAMES; break; - case 'm': *optset |= PCRE_MULTILINE; break; - case 's': *optset |= PCRE_DOTALL; break; - case 'x': *optset |= PCRE_EXTENDED; break; - case 'U': *optset |= PCRE_UNGREEDY; break; - case 'X': *optset |= PCRE_EXTRA; break; - } - } - - /* 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. Compile - code to change the ims options if this setting actually changes any of - them. We also pass the new setting back so that it can be put at the - start of any following branches, and when this group ends (if we are in - a group), a resetting item can be compiled. - - Note that if this item is right at the start of the pattern, the - options will have been abstracted and made global, so there will be no - change to compile. */ - - if (*ptr == ')') - { - if ((options & PCRE_IMS) != (newoptions & PCRE_IMS)) - { - *code++ = OP_OPT; - *code++ = newoptions & PCRE_IMS; - } - - /* Change options at this level, and pass them back for use - in subsequent branches. Reset the greedy defaults and the case - value for firstbyte and reqbyte. */ - - *optionsptr = options = newoptions; - greedy_default = ((newoptions & PCRE_UNGREEDY) != 0); - greedy_non_default = greedy_default ^ 1; - req_caseopt = ((options & PCRE_CASELESS) != 0)? REQ_CASELESS : 0; - - 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++; - } - } - - /* 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 referencing group; adjust the opcode. If the bracket - number is greater than EXTRACT_BASIC_MAX, we set the opcode one higher, and - arrange for the true number to follow later, in an OP_BRANUMBER item. */ - - else - { - NUMBERED_GROUP: - if (++(*brackets) > EXTRACT_BASIC_MAX) - { - bravalue = OP_BRA + EXTRACT_BASIC_MAX + 1; - code[1+LINK_SIZE] = OP_BRANUMBER; - PUT2(code, 2+LINK_SIZE, *brackets); - skipbytes = 3; - } - else bravalue = OP_BRA + *brackets; - } - - /* Process nested bracketed re. Assertions may not be repeated, but other - kinds can be. We copy code into a non-register variable in order to be able - to pass its address because some compilers complain otherwise. Pass in a - new setting for the ims options if they have changed. */ - - previous = (bravalue >= OP_ONCE)? code : NULL; - *code = bravalue; - tempcode = code; - tempreqvary = cd->req_varyopt; /* Save value before bracket */ - - if (!compile_regex( - newoptions, /* The complete new option state */ - options & PCRE_IMS, /* The previous ims option state */ - brackets, /* Extracting bracket count */ - &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 */ - skipbytes, /* Skip over OP_COND/OP_BRANUMBER */ - &subfirstbyte, /* For possible first char */ - &subreqbyte, /* For possible last char */ - bcptr, /* Current branch chain */ - cd)) /* Tables block */ - goto FAILED; - - /* 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 - and any option resetting that may follow it. 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. */ - - else if (bravalue == OP_COND) - { - uschar *tc = code; - int condcount = 0; - - do { - condcount++; - tc += GET(tc,1); - } - while (*tc != OP_KET); - - if (condcount > 2) - { - *errorcodeptr = ERR27; - goto FAILED; - } - - /* If there is just one branch, we must not make use of its firstbyte or - reqbyte, because this is equivalent to an empty second branch. */ - - if (condcount == 1) subfirstbyte = subreqbyte = REQ_NONE; - } - - /* Handle updating of the required and first characters. 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 zeroreqbyte and zerofirstbyte outside the - main loop so that they can be accessed for the back off. */ - - zeroreqbyte = reqbyte; - zerofirstbyte = firstbyte; - groupsetfirstbyte = FALSE; - - if (bravalue >= OP_BRA || bravalue == OP_ONCE || bravalue == OP_COND) - { - /* If we have not yet set a firstbyte 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 reqbyte if necessary. If the subpattern has - no firstbyte, set "none" for the whole branch. In both cases, a zero - repeat forces firstbyte to "none". */ - - if (firstbyte == REQ_UNSET) - { - if (subfirstbyte >= 0) - { - firstbyte = subfirstbyte; - groupsetfirstbyte = TRUE; - } - else firstbyte = REQ_NONE; - zerofirstbyte = REQ_NONE; - } - - /* If firstbyte was previously set, convert the subpattern's firstbyte - into reqbyte if there wasn't one, using the vary flag that was in - existence beforehand. */ - - else if (subfirstbyte >= 0 && subreqbyte < 0) - subreqbyte = subfirstbyte | 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 (subreqbyte >= 0) reqbyte = subreqbyte; - } - - /* For a forward assertion, we take the reqbyte, 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 firstbyte - for an assertion, however because it leads to incorrect effect for patterns - such as /(?=a)a.+/ when the "real" "a" would then become a reqbyte instead - of a firstbyte. This is overcome by a scan at the end if there's no - firstbyte, looking for an asserted first char. */ - - else if (bravalue == OP_ASSERT && subreqbyte >= 0) reqbyte = subreqbyte; - - /* Now update the main code pointer to the end of the group. */ - - code = tempcode; - - /* Error if hit end of pattern */ - - if (*ptr != ')') - { - *errorcodeptr = ERR14; - goto FAILED; - } - break; - - /* Check \ for being a real metacharacter; if not, fall through and handle - it as a data character at the start of a string. Escape items are checked - for validity in the pre-compiling pass. */ - - case '\\': - tempptr = ptr; - c = check_escape(&ptr, errorcodeptr, *brackets, options, FALSE); - - /* Handle metacharacters introduced by \. For ones like \d, the ESC_ values - are arranged to be the negation of the corresponding OP_values. 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. */ - - if (c < 0) - { - if (-c == ESC_Q) /* Handle start of quoted string */ - { - if (ptr[1] == '\\' && ptr[2] == 'E') ptr += 2; /* avoid empty string */ - else inescq = TRUE; - continue; - } - - /* For metasequences that actually match a character, we disable the - setting of a first character if it hasn't already been set. */ - - if (firstbyte == REQ_UNSET && -c > ESC_b && -c < ESC_Z) - firstbyte = REQ_NONE; - - /* Set values to reset to if this is followed by a zero repeat. */ - - zerofirstbyte = firstbyte; - zeroreqbyte = reqbyte; - - /* Back references are handled specially */ - - if (-c >= ESC_REF) - { - int number = -c - ESC_REF; - previous = code; - *code++ = OP_REF; - PUT2INC(code, 0, number); - } - - /* So are Unicode property matches, if supported. We know that get_ucp - won't fail because it was tested in the pre-pass. */ - -#ifdef SUPPORT_UCP - else if (-c == ESC_P || -c == ESC_p) - { - BOOL negated; - int pdata; - int ptype = get_ucp(&ptr, &negated, &pdata, errorcodeptr); - previous = code; - *code++ = ((-c == ESC_p) != negated)? OP_PROP : OP_NOTPROP; - *code++ = ptype; - *code++ = pdata; - } -#endif - - /* For the rest, we can obtain the OP value by negating the escape - value */ - - else - { - previous = (-c > ESC_b && -c < ESC_Z)? code : NULL; - *code++ = -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_UTF8 - if (utf8 && c > 127) - mclength = _pcre_ord2utf8(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_UTF8 - if (utf8 && (c & 0xc0) == 0xc0) - { - while ((ptr[1] & 0xc0) == 0x80) - 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_CHARNC : OP_CHAR; - for (c = 0; c < mclength; c++) *code++ = mcbuffer[c]; - - /* 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 firstbyte value alone, and don't change it on a zero - repeat. */ - - if (firstbyte == REQ_UNSET) - { - zerofirstbyte = REQ_NONE; - zeroreqbyte = reqbyte; - - /* If the character is more than one byte long, we can set firstbyte - only if it is not to be matched caselessly. */ - - if (mclength == 1 || req_caseopt == 0) - { - firstbyte = mcbuffer[0] | req_caseopt; - if (mclength != 1) reqbyte = code[-1] | cd->req_varyopt; - } - else firstbyte = reqbyte = REQ_NONE; - } - - /* firstbyte was previously set; we can set reqbyte only the length is - 1 or the matching is caseful. */ - - else - { - zerofirstbyte = firstbyte; - zeroreqbyte = reqbyte; - if (mclength == 1 || req_caseopt == 0) - reqbyte = 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. If the ims options are changed at the start (for a (?ims: group) or -during any branch, we need to insert an OP_OPT item at the start of every -following branch to ensure they get set correctly at run time, and also pass -the new options into every subsequent branch compile. - -Argument: - options option bits, including any changes for this subpattern - oldims previous settings of ims option bits - brackets -> int containing the number of extracting brackets used - 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 - skipbytes skip this many bytes at start (for OP_COND, OP_BRANUMBER) - firstbyteptr place to put the first required character, or a negative number - reqbyteptr 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. - -Returns: TRUE on success -*/ - -static BOOL -compile_regex(int options, int oldims, int *brackets, uschar **codeptr, - const uschar **ptrptr, int *errorcodeptr, BOOL lookbehind, int skipbytes, - int *firstbyteptr, int *reqbyteptr, branch_chain *bcptr, compile_data *cd) -{ -const uschar *ptr = *ptrptr; -uschar *code = *codeptr; -uschar *last_branch = code; -uschar *start_bracket = code; -uschar *reverse_count = NULL; -int firstbyte, reqbyte; -int branchfirstbyte, branchreqbyte; -branch_chain bc; - -bc.outer = bcptr; -bc.current = code; - -firstbyte = reqbyte = REQ_UNSET; - -/* 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 */ - -for (;;) - { - /* Handle a change of ims options at the start of the branch */ - - if ((options & PCRE_IMS) != oldims) - { - *code++ = OP_OPT; - *code++ = options & PCRE_IMS; - } - - /* Set up dummy OP_REVERSE if lookbehind assertion */ - - if (lookbehind) - { - *code++ = OP_REVERSE; - reverse_count = code; - PUTINC(code, 0, 0); - } - - /* Now compile the branch */ - - if (!compile_branch(&options, brackets, &code, &ptr, errorcodeptr, - &branchfirstbyte, &branchreqbyte, &bc, cd)) - { - *ptrptr = ptr; - return FALSE; - } - - /* If this is the first branch, the firstbyte and reqbyte values for the - branch become the values for the regex. */ - - if (*last_branch != OP_ALT) - { - firstbyte = branchfirstbyte; - reqbyte = branchreqbyte; - } - - /* If this is not the first branch, the first char and reqbyte have to - match the values from all the previous branches, except that if the previous - value for reqbyte didn't have REQ_VARY set, it can still match, and we set - REQ_VARY for the regex. */ - - else - { - /* If we previously had a firstbyte, but it doesn't match the new branch, - we have to abandon the firstbyte for the regex, but if there was previously - no reqbyte, it takes on the value of the old firstbyte. */ - - if (firstbyte >= 0 && firstbyte != branchfirstbyte) - { - if (reqbyte < 0) reqbyte = firstbyte; - firstbyte = REQ_NONE; - } - - /* If we (now or from before) have no firstbyte, a firstbyte from the - branch becomes a reqbyte if there isn't a branch reqbyte. */ - - if (firstbyte < 0 && branchfirstbyte >= 0 && branchreqbyte < 0) - branchreqbyte = branchfirstbyte; - - /* Now ensure that the reqbytes match */ - - if ((reqbyte & ~REQ_VARY) != (branchreqbyte & ~REQ_VARY)) - reqbyte = REQ_NONE; - else reqbyte |= branchreqbyte; /* 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 (lookbehind) - { - int length; - *code = OP_END; - length = find_fixedlength(last_branch, options); - DPRINTF(("fixed length = %d\n", length)); - if (length < 0) - { - *errorcodeptr = (length == -2)? ERR36 : ERR25; - *ptrptr = ptr; - return FALSE; - } - PUT(reverse_count, 0, length); - } - - /* Reached end of expression, either ')' or end of pattern. 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. If any of - the ims options were changed inside the group, compile a resetting op-code - following, except at the very end of the pattern. Return leaving the pointer - at the terminating char. */ - - if (*ptr != '|') - { - int length = code - last_branch; - do - { - int prev_length = GET(last_branch, 1); - PUT(last_branch, 1, length); - length = prev_length; - last_branch -= length; - } - while (length > 0); - - /* Fill in the ket */ - - *code = OP_KET; - PUT(code, 1, code - start_bracket); - code += 1 + LINK_SIZE; - - /* Resetting option if needed */ - - if ((options & PCRE_IMS) != oldims && *ptr == ')') - { - *code++ = OP_OPT; - *code++ = oldims; - } - - /* Set values to pass back */ - - *codeptr = code; - *ptrptr = ptr; - *firstbyteptr = firstbyte; - *reqbyteptr = reqbyte; - return TRUE; - } - - /* Another branch follows; insert an "or" 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. */ - - *code = OP_ALT; - PUT(code, 1, code - last_branch); - bc.current = 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 -counts, since OP_CIRC can match in the middle. - -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) - options points to the options setting - 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 uschar *code, int *options, unsigned int bracket_map, - unsigned int backref_map) -{ -do { - const uschar *scode = - first_significant_code(code + 1+LINK_SIZE, options, PCRE_MULTILINE, FALSE); - register int op = *scode; - - /* Capturing brackets */ - - if (op > OP_BRA) - { - int new_map; - op -= OP_BRA; - if (op > EXTRACT_BASIC_MAX) op = GET2(scode, 2+LINK_SIZE); - new_map = bracket_map | ((op < 32)? (1 << op) : 1); - if (!is_anchored(scode, options, new_map, backref_map)) return FALSE; - } - - /* Other brackets */ - - else if (op == OP_BRA || op == OP_ASSERT || op == OP_ONCE || op == OP_COND) - { - if (!is_anchored(scode, options, bracket_map, backref_map)) return FALSE; - } - - /* .* is not anchored unless DOTALL is set and it isn't in brackets that - are or may be referenced. */ - - else if ((op == OP_TYPESTAR || op == OP_TYPEMINSTAR) && - (*options & PCRE_DOTALL) != 0) - { - if (scode[1] != OP_ANY || (bracket_map & backref_map) != 0) return FALSE; - } - - /* Check for explicit anchoring */ - - else if (op != OP_SOD && op != OP_SOM && - ((*options & PCRE_MULTILINE) != 0 || 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 uschar *code, unsigned int bracket_map, - unsigned int backref_map) -{ -do { - const uschar *scode = first_significant_code(code + 1+LINK_SIZE, NULL, 0, - FALSE); - register int op = *scode; - - /* Capturing brackets */ - - if (op > OP_BRA) - { - int new_map; - op -= OP_BRA; - if (op > EXTRACT_BASIC_MAX) op = GET2(scode, 2+LINK_SIZE); - new_map = bracket_map | ((op < 32)? (1 << op) : 1); - if (!is_startline(scode, new_map, backref_map)) return FALSE; - } - - /* Other brackets */ - - else if (op == OP_BRA || op == OP_ASSERT || op == OP_ONCE || op == OP_COND) - { 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) - { - if (scode[1] != OP_ANY || (bracket_map & backref_map) != 0) return FALSE; - } - - /* Check for explicit circumflex */ - - else if (op != OP_CIRC) 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) - options pointer to the options (used to check casing changes) - inassert TRUE if in an assertion - -Returns: -1 or the fixed first char -*/ - -static int -find_firstassertedchar(const uschar *code, int *options, BOOL inassert) -{ -register int c = -1; -do { - int d; - const uschar *scode = - first_significant_code(code + 1+LINK_SIZE, options, PCRE_CASELESS, TRUE); - register int op = *scode; - - if (op >= OP_BRA) op = OP_BRA; - - switch(op) - { - default: - return -1; - - case OP_BRA: - case OP_ASSERT: - case OP_ONCE: - case OP_COND: - if ((d = find_firstassertedchar(scode, options, op == OP_ASSERT)) < 0) - return -1; - if (c < 0) c = d; else if (c != d) return -1; - break; - - case OP_EXACT: /* Fall through */ - scode += 2; - - case OP_CHAR: - case OP_CHARNC: - case OP_PLUS: - case OP_MINPLUS: - if (!inassert) return -1; - if (c < 0) - { - c = scode[1]; - if ((*options & PCRE_CASELESS) != 0) c |= 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 -*/ - -PCRE_DATA_SCOPE pcre * -pcre_compile(const char *pattern, int options, const char **errorptr, - int *erroroffset, const unsigned char *tables) -{ -return pcre_compile2(pattern, options, NULL, errorptr, erroroffset, tables); -} - - - -PCRE_DATA_SCOPE pcre * -pcre_compile2(const char *pattern, int options, int *errorcodeptr, - const char **errorptr, int *erroroffset, const unsigned char *tables) -{ -real_pcre *re; -int length = 1 + LINK_SIZE; /* For initial BRA plus length */ -int c, firstbyte, reqbyte, newline; -int bracount = 0; -int branch_extra = 0; -int branch_newextra; -int item_count = -1; -int name_count = 0; -int max_name_size = 0; -int lastitemlength = 0; -int errorcode = 0; -#ifdef SUPPORT_UTF8 -BOOL utf8; -BOOL class_utf8; -#endif -BOOL inescq = FALSE; -BOOL capturing; -unsigned int brastackptr = 0; -size_t size; -uschar *code; -const uschar *codestart; -const uschar *ptr; -compile_data compile_block; -compile_data *cd = &compile_block; -int brastack[BRASTACK_SIZE]; -uschar bralenstack[BRASTACK_SIZE]; - -/* 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_RETURN; - } - -*erroroffset = 0; - -/* Can't support UTF8 unless PCRE has been compiled to include the code. */ - -#ifdef SUPPORT_UTF8 -utf8 = (options & PCRE_UTF8) != 0; -if (utf8 && (options & PCRE_NO_UTF8_CHECK) == 0 && - (*erroroffset = _pcre_valid_utf8((uschar *)pattern, -1)) >= 0) - { - errorcode = ERR44; - goto PCRE_EARLY_ERROR_RETURN; - } -#else -if ((options & PCRE_UTF8) != 0) - { - errorcode = ERR32; - goto PCRE_EARLY_ERROR_RETURN; - } -#endif - -if ((options & ~PUBLIC_OPTIONS) != 0) - { - errorcode = ERR17; - goto PCRE_EARLY_ERROR_RETURN; - } - -/* Set up pointers to the individual character tables */ - -if (tables == NULL) tables = _pcre_default_tables; -cd->lcc = tables + lcc_offset; -cd->fcc = tables + fcc_offset; -cd->cbits = tables + cbits_offset; -cd->ctypes = tables + ctypes_offset; - -/* Handle different types of newline. The two bits give four cases. The current -code allows for one- or two-byte sequences. */ - -switch (options & PCRE_NEWLINE_CRLF) - { - default: newline = NEWLINE; break; /* Compile-time default */ - case PCRE_NEWLINE_CR: newline = '\r'; break; - case PCRE_NEWLINE_LF: newline = '\n'; break; - case PCRE_NEWLINE_CR+ - PCRE_NEWLINE_LF: newline = ('\r' << 8) | '\n'; break; - } - -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. This is updated for numeric -references during the first pass, but for named references during the actual -compile pass. 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")); -DPRINTF(("%s\n", pattern)); - -/* The first thing to do is to make a pass over the pattern to compute the -amount of store required to hold the compiled code. This does not have to be -perfect as long as errors are overestimates. At the same time we can detect any -flag settings right at the start, and extract them. Make an attempt to correct -for any counted white space if an "extended" flag setting appears late in the -pattern. We can't be so clever for #-comments. */ - -ptr = (const uschar *)(pattern - 1); -while ((c = *(++ptr)) != 0) - { - int min, max; - int class_optcount; - int bracket_length; - int duplength; - - /* If we are inside a \Q...\E sequence, all chars are literal */ - - if (inescq) - { - if ((options & PCRE_AUTO_CALLOUT) != 0) length += 2 + 2*LINK_SIZE; - goto NORMAL_CHAR; - } - - /* Otherwise, first check for ignored whitespace and comments */ - - if ((options & PCRE_EXTENDED) != 0) - { - if ((cd->ctypes[c] & ctype_space) != 0) continue; - if (c == '#') - { - while (*(++ptr) != 0) if (IS_NEWLINE(ptr)) break; - if (*ptr != 0) - { - ptr += cd->nllen - 1; - continue; - } - break; /* End loop at end of pattern */ - } - } - - item_count++; /* Is zero for the first non-comment item */ - - /* Allow space for auto callout before every item except quantifiers. */ - - if ((options & PCRE_AUTO_CALLOUT) != 0 && - c != '*' && c != '+' && c != '?' && - (c != '{' || !is_counted_repeat(ptr + 1))) - length += 2 + 2*LINK_SIZE; - - switch(c) - { - /* A backslashed item may be an escaped data character or it may be a - character type. */ - - case '\\': - c = check_escape(&ptr, &errorcode, bracount, options, FALSE); - if (errorcode != 0) goto PCRE_ERROR_RETURN; - - lastitemlength = 1; /* Default length of last item for repeats */ - - if (c >= 0) /* Data character */ - { - length += 2; /* For a one-byte character */ - -#ifdef SUPPORT_UTF8 - if (utf8 && c > 127) - { - int i; - for (i = 0; i < _pcre_utf8_table1_size; i++) - if (c <= _pcre_utf8_table1[i]) break; - length += i; - lastitemlength += i; - } -#endif - - continue; - } - - /* If \Q, enter "literal" mode */ - - if (-c == ESC_Q) - { - inescq = TRUE; - continue; - } - - /* \X is supported only if Unicode property support is compiled */ - -#ifndef SUPPORT_UCP - if (-c == ESC_X) - { - errorcode = ERR45; - goto PCRE_ERROR_RETURN; - } -#endif - - /* \P and \p are for Unicode properties, but only when the support has - been compiled. Each item needs 3 bytes. */ - - else if (-c == ESC_P || -c == ESC_p) - { -#ifdef SUPPORT_UCP - BOOL negated; - BOOL pdata; - length += 3; - lastitemlength = 3; - if (get_ucp(&ptr, &negated, &pdata, &errorcode) < 0) - goto PCRE_ERROR_RETURN; - continue; -#else - errorcode = ERR45; - goto PCRE_ERROR_RETURN; -#endif - } - - /* Other escapes need one byte */ - - length++; - - /* A back reference needs an additional 2 bytes, plus either one or 5 - bytes for a repeat. We also need to keep the value of the highest - back reference. */ - - if (c <= -ESC_REF) - { - int refnum = -c - ESC_REF; - cd->backref_map |= (refnum < 32)? (1 << refnum) : 1; - if (refnum > cd->top_backref) - cd->top_backref = refnum; - length += 2; /* For single back reference */ - if (ptr[1] == '{' && is_counted_repeat(ptr+2)) - { - ptr = read_repeat_counts(ptr+2, &min, &max, &errorcode); - if (errorcode != 0) goto PCRE_ERROR_RETURN; - if ((min == 0 && (max == 1 || max == -1)) || - (min == 1 && max == -1)) - length++; - else length += 5; - if (ptr[1] == '?') ptr++; - } - } - continue; - - case '^': /* Single-byte metacharacters */ - case '.': - case '$': - length++; - lastitemlength = 1; - continue; - - case '*': /* These repeats won't be after brackets; */ - case '+': /* those are handled separately */ - case '?': - length++; - goto POSESSIVE; /* A few lines below */ - - /* This covers the cases of braced repeats after a single char, metachar, - class, or back reference. */ - - case '{': - if (!is_counted_repeat(ptr+1)) goto NORMAL_CHAR; - ptr = read_repeat_counts(ptr+1, &min, &max, &errorcode); - if (errorcode != 0) goto PCRE_ERROR_RETURN; - - /* These special cases just insert one extra opcode */ - - if ((min == 0 && (max == 1 || max == -1)) || - (min == 1 && max == -1)) - length++; - - /* These cases might insert additional copies of a preceding character. */ - - else - { - if (min != 1) - { - length -= lastitemlength; /* Uncount the original char or metachar */ - if (min > 0) length += 3 + lastitemlength; - } - length += lastitemlength + ((max > 0)? 3 : 1); - } - - if (ptr[1] == '?') ptr++; /* Needs no extra length */ - - POSESSIVE: /* Test for possessive quantifier */ - if (ptr[1] == '+') - { - ptr++; - length += 2 + 2*LINK_SIZE; /* Allow for atomic brackets */ - } - continue; - - /* An alternation contains an offset to the next branch or ket. If any ims - options changed in the previous branch(es), and/or if we are in a - lookbehind assertion, extra space will be needed at the start of the - branch. This is handled by branch_extra. */ - - case '|': - length += 1 + LINK_SIZE + branch_extra; - continue; - - /* A character class uses 33 characters provided that all the character - values are less than 256. Otherwise, it uses a bit map for low valued - characters, and individual items for others. Don't worry about character - types that aren't allowed in classes - they'll get picked up during the - compile. A character class that contains only one single-byte character - uses 2 or 3 bytes, depending on whether it is negated or not. Notice this - where we can. (In UTF-8 mode we can do this only for chars < 128.) */ - - case '[': - if (*(++ptr) == '^') - { - class_optcount = 10; /* Greater than one */ - ptr++; - } - else class_optcount = 0; - -#ifdef SUPPORT_UTF8 - class_utf8 = FALSE; -#endif - - /* Written as a "do" so that an initial ']' is taken as data */ - - if (*ptr != 0) do - { - /* Inside \Q...\E everything is literal except \E */ - - if (inescq) - { - if (*ptr != '\\' || ptr[1] != 'E') goto GET_ONE_CHARACTER; - inescq = FALSE; - ptr += 1; - continue; - } - - /* Outside \Q...\E, check for escapes */ - - if (*ptr == '\\') - { - c = check_escape(&ptr, &errorcode, bracount, options, TRUE); - if (errorcode != 0) goto PCRE_ERROR_RETURN; - - /* \b is backspace inside a class; \X is literal */ - - if (-c == ESC_b) c = '\b'; - else if (-c == ESC_X) c = 'X'; - - /* \Q enters quoting mode */ - - else if (-c == ESC_Q) - { - inescq = TRUE; - continue; - } - - /* Handle escapes that turn into characters */ - - if (c >= 0) goto NON_SPECIAL_CHARACTER; - - /* Escapes that are meta-things. The normal ones just affect the - bit map, but Unicode properties require an XCLASS extended item. */ - - else - { - class_optcount = 10; /* \d, \s etc; make sure > 1 */ -#ifdef SUPPORT_UTF8 - if (-c == ESC_p || -c == ESC_P) - { - if (!class_utf8) - { - class_utf8 = TRUE; - length += LINK_SIZE + 2; - } - length += 3; - } -#endif - } - } - - /* Check the syntax for POSIX stuff. The bits we actually handle are - checked during the real compile phase. */ - - else if (*ptr == '[' && - (ptr[1] == ':' || ptr[1] == '.' || ptr[1] == '=') && - check_posix_syntax(ptr, &ptr, cd)) - { - ptr++; - class_optcount = 10; /* Make sure > 1 */ - } - - /* Anything else increments the possible optimization count. We have to - detect ranges here so that we can compute the number of extra ranges for - caseless wide characters when UCP support is available. If there are wide - characters, we are going to have to use an XCLASS, even for single - characters. */ - - else - { - int d; - - GET_ONE_CHARACTER: - -#ifdef SUPPORT_UTF8 - if (utf8) - { - int extra = 0; - GETCHARLEN(c, ptr, extra); - ptr += extra; - } - else c = *ptr; -#else - c = *ptr; -#endif - - /* Come here from handling \ above when it escapes to a char value */ - - NON_SPECIAL_CHARACTER: - class_optcount++; - - d = -1; - if (ptr[1] == '-') - { - uschar const *hyptr = ptr++; - if (ptr[1] == '\\') - { - ptr++; - d = check_escape(&ptr, &errorcode, bracount, options, TRUE); - if (errorcode != 0) goto PCRE_ERROR_RETURN; - if (-d == ESC_b) d = '\b'; /* backspace */ - else if (-d == ESC_X) d = 'X'; /* literal X in a class */ - } - else if (ptr[1] != 0 && ptr[1] != ']') - { - ptr++; -#ifdef SUPPORT_UTF8 - if (utf8) - { - int extra = 0; - GETCHARLEN(d, ptr, extra); - ptr += extra; - } - else -#endif - d = *ptr; - } - if (d < 0) ptr = hyptr; /* go back to hyphen as data */ - } - - /* If d >= 0 we have a range. In UTF-8 mode, if the end is > 255, or > - 127 for caseless matching, we will need to use an XCLASS. */ - - if (d >= 0) - { - class_optcount = 10; /* Ensure > 1 */ - if (d < c) - { - errorcode = ERR8; - goto PCRE_ERROR_RETURN; - } - -#ifdef SUPPORT_UTF8 - if (utf8 && (d > 255 || ((options & PCRE_CASELESS) != 0 && d > 127))) - { - uschar buffer[6]; - if (!class_utf8) /* Allow for XCLASS overhead */ - { - class_utf8 = TRUE; - length += LINK_SIZE + 2; - } - -#ifdef SUPPORT_UCP - /* If we have UCP support, find out how many extra ranges are - needed to map the other case of characters within this range. We - have to mimic the range optimization here, because extending the - range upwards might push d over a boundary that makes is use - another byte in the UTF-8 representation. */ - - if ((options & PCRE_CASELESS) != 0) - { - int occ, ocd; - int cc = c; - int origd = d; - while (get_othercase_range(&cc, origd, &occ, &ocd)) - { - if (occ >= c && ocd <= d) continue; /* Skip embedded */ - - if (occ < c && ocd >= 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 > d && occ <= d + 1) /* always shorter than */ - { /* the basic range. */ - d = ocd; - continue; - } - - /* An extra item is needed */ - - length += 1 + _pcre_ord2utf8(occ, buffer) + - ((occ == ocd)? 0 : _pcre_ord2utf8(ocd, buffer)); - } - } -#endif /* SUPPORT_UCP */ - - /* The length of the (possibly extended) range */ - - length += 1 + _pcre_ord2utf8(c, buffer) + _pcre_ord2utf8(d, buffer); - } -#endif /* SUPPORT_UTF8 */ - - } - - /* We have a single character. There is nothing to be done unless we - are in UTF-8 mode. If the char is > 255, or 127 when caseless, we must - allow for an XCL_SINGLE item, doubled for caselessness if there is UCP - support. */ - - else - { -#ifdef SUPPORT_UTF8 - if (utf8 && (c > 255 || ((options & PCRE_CASELESS) != 0 && c > 127))) - { - uschar buffer[6]; - class_optcount = 10; /* Ensure > 1 */ - if (!class_utf8) /* Allow for XCLASS overhead */ - { - class_utf8 = TRUE; - length += LINK_SIZE + 2; - } -#ifdef SUPPORT_UCP - length += (((options & PCRE_CASELESS) != 0)? 2 : 1) * - (1 + _pcre_ord2utf8(c, buffer)); -#else /* SUPPORT_UCP */ - length += 1 + _pcre_ord2utf8(c, buffer); -#endif /* SUPPORT_UCP */ - } -#endif /* SUPPORT_UTF8 */ - } - } - } - while (*(++ptr) != 0 && (inescq || *ptr != ']')); /* Concludes "do" above */ - - if (*ptr == 0) /* Missing terminating ']' */ - { - errorcode = ERR6; - goto PCRE_ERROR_RETURN; - } - - /* We can optimize when there was only one optimizable character. Repeats - for positive and negated single one-byte chars are handled by the general - code. Here, we handle repeats for the class opcodes. */ - - if (class_optcount == 1) length += 3; else - { - length += 33; - - /* A repeat needs either 1 or 5 bytes. If it is a possessive quantifier, - we also need extra for wrapping the whole thing in a sub-pattern. */ - - if (*ptr != 0 && ptr[1] == '{' && is_counted_repeat(ptr+2)) - { - ptr = read_repeat_counts(ptr+2, &min, &max, &errorcode); - if (errorcode != 0) goto PCRE_ERROR_RETURN; - if ((min == 0 && (max == 1 || max == -1)) || - (min == 1 && max == -1)) - length++; - else length += 5; - if (ptr[1] == '+') - { - ptr++; - length += 2 + 2*LINK_SIZE; - } - else if (ptr[1] == '?') ptr++; - } - } - continue; - - /* Brackets may be genuine groups or special things */ - - case '(': - branch_newextra = 0; - bracket_length = 1 + LINK_SIZE; - capturing = FALSE; - - /* Handle special forms of bracket, which all start (? */ - - if (ptr[1] == '?') - { - int set, unset; - int *optset; - - switch (c = ptr[2]) - { - /* Skip over comments entirely */ - case '#': - ptr += 3; - while (*ptr != 0 && *ptr != ')') ptr++; - if (*ptr == 0) - { - errorcode = ERR18; - goto PCRE_ERROR_RETURN; - } - continue; - - /* Non-referencing groups and lookaheads just move the pointer on, and - then behave like a non-special bracket, except that they don't increment - the count of extracting brackets. Ditto for the "once only" bracket, - which is in Perl from version 5.005. */ - - case ':': - case '=': - case '!': - case '>': - ptr += 2; - break; - - /* Named subpatterns are an extension copied from Python */ - - case 'P': - ptr += 3; - - /* Handle the definition of a named subpattern */ - - if (*ptr == '<') - { - const uschar *p; /* Don't amalgamate; some compilers */ - p = ++ptr; /* grumble at autoincrement in declaration */ - while ((cd->ctypes[*ptr] & ctype_word) != 0) ptr++; - if (*ptr != '>') - { - errorcode = ERR42; - goto PCRE_ERROR_RETURN; - } - name_count++; - if (name_count > MAX_NAME_COUNT) - { - errorcode = ERR49; - goto PCRE_ERROR_RETURN; - } - if (ptr - p > max_name_size) - { - max_name_size = (ptr - p); - if (max_name_size > MAX_NAME_SIZE) - { - errorcode = ERR48; - goto PCRE_ERROR_RETURN; - } - } - capturing = TRUE; /* Named parentheses are always capturing */ - break; /* Go handle capturing parentheses */ - } - - /* Handle back references and recursive calls to named subpatterns */ - - if (*ptr == '=' || *ptr == '>') - { - length += 3 + 3*LINK_SIZE; /* Allow for the automatic "once" */ - while ((cd->ctypes[*(++ptr)] & ctype_word) != 0); - if (*ptr != ')') - { - errorcode = ERR42; - goto PCRE_ERROR_RETURN; - } - goto RECURSE_CHECK_QUANTIFIED; - } - - /* Unknown character after (?P */ - - errorcode = ERR41; - goto PCRE_ERROR_RETURN; - - /* (?R) specifies a recursive call to the regex, which is an extension - to provide the facility which can be obtained by (?p{perl-code}) in - Perl 5.6. In Perl 5.8 this has become (??{perl-code}). - - From PCRE 4.00, items such as (?3) specify subroutine-like "calls" to - the appropriate numbered brackets. This includes both recursive and - non-recursive calls. (?R) is now synonymous with (?0). */ - - case 'R': - ptr++; - - case '0': case '1': case '2': case '3': case '4': - case '5': case '6': case '7': case '8': case '9': - ptr += 2; - if (c != 'R') - while ((digitab[*(++ptr)] & ctype_digit) != 0); - if (*ptr != ')') - { - errorcode = ERR29; - goto PCRE_ERROR_RETURN; - } - length += 3 + 3*LINK_SIZE; /* Allows for the automatic "once" */ - - /* If this item is quantified, it will get wrapped inside brackets so - as to use the code for quantified brackets. We jump down and use the - code that handles this for real brackets. Come here from code for - named recursions/subroutines. */ - - RECURSE_CHECK_QUANTIFIED: - if (ptr[1] == '+' || ptr[1] == '*' || ptr[1] == '?' || ptr[1] == '{') - { - length += 2 + 2 * LINK_SIZE; /* to make bracketed */ - duplength = 5 + 3 * LINK_SIZE; - goto HANDLE_QUANTIFIED_BRACKETS; - } - continue; - - /* (?C) is an extension which provides "callout" - to provide a bit of - the functionality of the Perl (?{...}) feature. An optional number may - follow (default is zero). */ - - case 'C': - ptr += 2; - while ((digitab[*(++ptr)] & ctype_digit) != 0); - if (*ptr != ')') - { - errorcode = ERR39; - goto PCRE_ERROR_RETURN; - } - length += 2 + 2*LINK_SIZE; - continue; - - /* Lookbehinds are in Perl from version 5.005 */ - - case '<': - ptr += 3; - if (*ptr == '=' || *ptr == '!') - { - branch_newextra = 1 + LINK_SIZE; - length += 1 + LINK_SIZE; /* For the first branch */ - break; - } - errorcode = ERR24; - goto PCRE_ERROR_RETURN; - - /* Conditionals are in Perl from version 5.005. The bracket must either - be followed by a number (for bracket reference) or by an assertion - group. PCRE extends this by allowing a name to reference a named group; - unfortunately, previously 'R' was implemented for a recursion test. - When this is compiled, we look for the named group 'R' first. At this - point we just do a basic syntax check. */ - - case '(': - if ((cd->ctypes[ptr[3]] & ctype_word) != 0) - { - ptr += 4; - length += 3; - while ((cd->ctypes[*ptr] & ctype_word) != 0) ptr++; - if (*ptr != ')') - { - errorcode = ERR26; - goto PCRE_ERROR_RETURN; - } - } - else /* An assertion must follow */ - { - ptr++; /* Can treat like ':' as far as spacing is concerned */ - if (ptr[2] != '?' || - (ptr[3] != '=' && ptr[3] != '!' && ptr[3] != '<') ) - { - ptr += 2; /* To get right offset in message */ - errorcode = ERR28; - goto PCRE_ERROR_RETURN; - } - } - break; - - /* Else loop checking valid options until ) is met. Anything else is an - error. If we are without any brackets, i.e. at top level, the settings - act as if specified in the options, so massage the options immediately. - This is for backward compatibility with Perl 5.004. */ - - default: - set = unset = 0; - optset = &set; - ptr += 2; - - for (;; ptr++) - { - c = *ptr; - switch (c) - { - case 'i': - *optset |= PCRE_CASELESS; - continue; - - case 'J': - *optset |= PCRE_DUPNAMES; - options |= PCRE_JCHANGED; /* Record that it changed */ - continue; - - case 'm': - *optset |= PCRE_MULTILINE; - continue; - - case 's': - *optset |= PCRE_DOTALL; - continue; - - case 'x': - *optset |= PCRE_EXTENDED; - continue; - - case 'X': - *optset |= PCRE_EXTRA; - continue; - - case 'U': - *optset |= PCRE_UNGREEDY; - continue; - - case '-': - optset = &unset; - continue; - - /* A termination by ')' indicates an options-setting-only item; if - this is at the very start of the pattern (indicated by item_count - being zero), we use it to set the global options. This is helpful - when analyzing the pattern for first characters, etc. Otherwise - nothing is done here and it is handled during the compiling - process. - - We allow for more than one options setting at the start. If such - settings do not change the existing options, nothing is compiled. - However, we must leave space just in case something is compiled. - This can happen for pathological sequences such as (?i)(?-i) - because the global options will end up with -i set. The space is - small and not significant. (Before I did this there was a reported - bug with (?i)(?-i) in a machine-generated pattern.) - - [Historical note: Up to Perl 5.8, options settings at top level - were always global settings, wherever they appeared in the pattern. - That is, they were equivalent to an external setting. From 5.8 - onwards, they apply only to what follows (which is what you might - expect).] */ - - case ')': - if (item_count == 0) - { - options = (options | set) & (~unset); - set = unset = 0; /* To save length */ - item_count--; /* To allow for several */ - length += 2; - } - - /* Fall through */ - - /* A termination by ':' indicates the start of a nested group with - the given options set. This is again handled at compile time, but - we must allow for compiled space if any of the ims options are - set. We also have to allow for resetting space at the end of - the group, which is why 4 is added to the length and not just 2. - If there are several changes of options within the same group, this - will lead to an over-estimate on the length, but this shouldn't - matter very much. We also have to allow for resetting options at - the start of any alternations, which we do by setting - branch_newextra to 2. */ - - case ':': - if (((set|unset) & PCRE_IMS) != 0) - { - length += 4; - branch_newextra = 2; - } - goto END_OPTIONS; - - /* Unrecognized option character */ - - default: - errorcode = ERR12; - goto PCRE_ERROR_RETURN; - } - } - - /* If we hit a closing bracket, that's it - this is a freestanding - option-setting. We need to ensure that branch_extra is updated if - necessary. The only values branch_newextra can have here are 0 or 2. - If the value is 2, then branch_extra must either be 2 or 5, depending - on whether this is a lookbehind group or not. */ - - END_OPTIONS: - if (c == ')') - { - if (branch_newextra == 2 && - (branch_extra == 0 || branch_extra == 1+LINK_SIZE)) - branch_extra += branch_newextra; - continue; - } - - /* If options were terminated by ':' control comes here. This is a - non-capturing group with an options change. There is nothing more that - needs to be done because "capturing" is already set FALSE by default; - we can just fall through. */ - - } - } - - /* Ordinary parentheses, not followed by '?', are capturing unless - PCRE_NO_AUTO_CAPTURE is set. */ - - else capturing = (options & PCRE_NO_AUTO_CAPTURE) == 0; - - /* Capturing brackets must be counted so we can process escapes in a - Perlish way. If the number exceeds EXTRACT_BASIC_MAX we are going to need - an additional 3 bytes of memory per capturing bracket. */ - - if (capturing) - { - bracount++; - if (bracount > EXTRACT_BASIC_MAX) bracket_length += 3; - } - - /* Save length for computing whole length at end if there's a repeat that - requires duplication of the group. Also save the current value of - branch_extra, and start the new group with the new value. If non-zero, this - will either be 2 for a (?imsx: group, or 3 for a lookbehind assertion. */ - - if (brastackptr >= sizeof(brastack)/sizeof(int)) - { - errorcode = ERR19; - goto PCRE_ERROR_RETURN; - } - - bralenstack[brastackptr] = branch_extra; - branch_extra = branch_newextra; - - brastack[brastackptr++] = length; - length += bracket_length; - continue; - - /* Handle ket. Look for subsequent max/min; for certain sets of values we - have to replicate this bracket up to that many times. If brastackptr is - 0 this is an unmatched bracket which will generate an error, but take care - not to try to access brastack[-1] when computing the length and restoring - the branch_extra value. */ - - case ')': - length += 1 + LINK_SIZE; - if (brastackptr > 0) - { - duplength = length - brastack[--brastackptr]; - branch_extra = bralenstack[brastackptr]; - /* This is a paranoid check to stop integer overflow later on */ - if (duplength > MAX_DUPLENGTH) - { - errorcode = ERR50; - goto PCRE_ERROR_RETURN; - } - } - else duplength = 0; - - /* The following code is also used when a recursion such as (?3) is - followed by a quantifier, because in that case, it has to be wrapped inside - brackets so that the quantifier works. The value of duplength must be - set before arrival. */ - - HANDLE_QUANTIFIED_BRACKETS: - - /* Leave ptr at the final char; for read_repeat_counts this happens - automatically; for the others we need an increment. */ - - if ((c = ptr[1]) == '{' && is_counted_repeat(ptr+2)) - { - ptr = read_repeat_counts(ptr+2, &min, &max, &errorcode); - if (errorcode != 0) goto PCRE_ERROR_RETURN; - } - else if (c == '*') { min = 0; max = -1; ptr++; } - else if (c == '+') { min = 1; max = -1; ptr++; } - else if (c == '?') { min = 0; max = 1; ptr++; } - else { min = 1; max = 1; } - - /* If the minimum is zero, we have to allow for an OP_BRAZERO before the - group, and if the maximum is greater than zero, we have to replicate - maxval-1 times; each replication acquires an OP_BRAZERO plus a nesting - bracket set. */ - - if (min == 0) - { - length++; - if (max > 0) length += (max - 1) * (duplength + 3 + 2*LINK_SIZE); - } - - /* When the minimum is greater than zero, we have to replicate up to - minval-1 times, with no additions required in the copies. Then, if there - is a limited maximum we have to replicate up to maxval-1 times allowing - for a BRAZERO item before each optional copy and nesting brackets for all - but one of the optional copies. */ - - else - { - length += (min - 1) * duplength; - if (max > min) /* Need this test as max=-1 means no limit */ - length += (max - min) * (duplength + 3 + 2*LINK_SIZE) - - (2 + 2*LINK_SIZE); - } - - /* Allow space for once brackets for "possessive quantifier" */ - - if (ptr[1] == '+') - { - ptr++; - length += 2 + 2*LINK_SIZE; - } - continue; - - /* Non-special character. It won't be space or # in extended mode, so it is - always a genuine character. If we are in a \Q...\E sequence, check for the - end; if not, we have a literal. */ - - default: - NORMAL_CHAR: - - if (inescq && c == '\\' && ptr[1] == 'E') - { - inescq = FALSE; - ptr++; - continue; - } - - length += 2; /* For a one-byte character */ - lastitemlength = 1; /* Default length of last item for repeats */ - - /* In UTF-8 mode, check for additional bytes. */ - -#ifdef SUPPORT_UTF8 - if (utf8 && (c & 0xc0) == 0xc0) - { - while ((ptr[1] & 0xc0) == 0x80) /* Can't flow over the end */ - { /* because the end is marked */ - lastitemlength++; /* by a zero byte. */ - length++; - ptr++; - } - } -#endif - - continue; - } - } - -length += 2 + LINK_SIZE; /* For final KET and END */ - -if ((options & PCRE_AUTO_CALLOUT) != 0) - length += 2 + 2*LINK_SIZE; /* For final callout */ - -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 name_count and max_name size. */ - -size = length + sizeof(real_pcre) + name_count * (max_name_size + 3); -re = (real_pcre *)(pcre_malloc)(size); - -if (re == NULL) - { - errorcode = ERR21; - goto PCRE_EARLY_ERROR_RETURN; - } - -/* Put in the magic number, and save the sizes, options, 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 = size; -re->options = options; -re->dummy1 = 0; -re->name_table_offset = sizeof(real_pcre); -re->name_entry_size = max_name_size + 3; -re->name_count = name_count; -re->ref_count = 0; -re->tables = (tables == _pcre_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. */ - -cd->names_found = 0; -cd->name_entry_size = max_name_size + 3; -cd->name_table = (uschar *)re + re->name_table_offset; -codestart = cd->name_table + re->name_entry_size * re->name_count; -cd->start_code = codestart; -cd->start_pattern = (const uschar *)pattern; -cd->req_varyopt = 0; -cd->nopartial = FALSE; - -/* 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 uschar *)pattern; -code = (uschar *)codestart; -*code = OP_BRA; -bracount = 0; -(void)compile_regex(options, options & PCRE_IMS, &bracount, &code, &ptr, - &errorcode, FALSE, 0, &firstbyte, &reqbyte, NULL, cd); -re->top_bracket = bracount; -re->top_backref = cd->top_backref; - -if (cd->nopartial) re->options |= PCRE_NOPARTIAL; - -/* 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 DEBUG -if (code - codestart > length) errorcode = ERR23; -#endif - -/* Give an error if there's back reference to a non-existent capturing -subpattern. */ - -if (re->top_backref > re->top_bracket) errorcode = ERR15; - -/* Failed to compile, or error while post-processing */ - -if (errorcode != 0) - { - (pcre_free)(re); - PCRE_ERROR_RETURN: - *erroroffset = ptr - (const uschar *)pattern; - PCRE_EARLY_ERROR_RETURN: - *errorptr = error_texts[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 character 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 ((options & PCRE_ANCHORED) == 0) - { - int temp_options = options; - if (is_anchored(codestart, &temp_options, 0, cd->backref_map)) - re->options |= PCRE_ANCHORED; - else - { - if (firstbyte < 0) - firstbyte = find_firstassertedchar(codestart, &temp_options, FALSE); - if (firstbyte >= 0) /* Remove caseless flag for non-caseable chars */ - { - int ch = firstbyte & 255; - re->first_byte = ((firstbyte & REQ_CASELESS) != 0 && - cd->fcc[ch] == ch)? ch : firstbyte; - re->options |= PCRE_FIRSTSET; - } - else if (is_startline(codestart, 0, cd->backref_map)) - re->options |= 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 (reqbyte >= 0 && - ((re->options & PCRE_ANCHORED) == 0 || (reqbyte & REQ_VARY) != 0)) - { - int ch = reqbyte & 255; - re->req_byte = ((reqbyte & REQ_CASELESS) != 0 && - cd->fcc[ch] == ch)? (reqbyte & ~REQ_CASELESS) : reqbyte; - re->options |= PCRE_REQCHSET; - } - -/* Print out the compiled data if debugging is enabled. This is never the -case when building a production library. */ - -#ifdef DEBUG - -printf("Length = %d top_bracket = %d top_backref = %d\n", - length, re->top_bracket, re->top_backref); - -if (re->options != 0) - { - printf("%s%s%s%s%s%s%s%s%s\n", - ((re->options & PCRE_NOPARTIAL) != 0)? "nopartial " : "", - ((re->options & PCRE_ANCHORED) != 0)? "anchored " : "", - ((re->options & PCRE_CASELESS) != 0)? "caseless " : "", - ((re->options & PCRE_EXTENDED) != 0)? "extended " : "", - ((re->options & PCRE_MULTILINE) != 0)? "multiline " : "", - ((re->options & PCRE_DOTALL) != 0)? "dotall " : "", - ((re->options & PCRE_DOLLAR_ENDONLY) != 0)? "endonly " : "", - ((re->options & PCRE_EXTRA) != 0)? "extra " : "", - ((re->options & PCRE_UNGREEDY) != 0)? "ungreedy " : ""); - } - -if ((re->options & PCRE_FIRSTSET) != 0) - { - int ch = re->first_byte & 255; - const char *caseless = ((re->first_byte & REQ_CASELESS) == 0)? - "" : " (caseless)"; - if (isprint(ch)) printf("First char = %c%s\n", ch, caseless); - else printf("First char = \\x%02x%s\n", ch, caseless); - } - -if ((re->options & PCRE_REQCHSET) != 0) - { - int ch = re->req_byte & 255; - const char *caseless = ((re->req_byte & REQ_CASELESS) == 0)? - "" : " (caseless)"; - if (isprint(ch)) printf("Req char = %c%s\n", ch, caseless); - else printf("Req char = \\x%02x%s\n", ch, caseless); - } - -pcre_printint(re, stdout); - -/* This check is done here in the debugging case so that the code that -was compiled can be seen. */ - -if (code - codestart > length) - { - (pcre_free)(re); - *errorptr = error_texts[ERR23]; - *erroroffset = ptr - (uschar *)pattern; - if (errorcodeptr != NULL) *errorcodeptr = ERR23; - return NULL; - } -#endif - -return (pcre *)re; -} - -/* End of pcre_compile.c */ diff --git a/ext/pcre/pcrelib/pcre_config.c b/ext/pcre/pcrelib/pcre_config.c deleted file mode 100644 index 29e6c1a358..0000000000 --- a/ext/pcre/pcrelib/pcre_config.c +++ /dev/null @@ -1,116 +0,0 @@ -/************************************************* -* 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) 1997-2006 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 "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 -*/ - -PCRE_DATA_SCOPE int -pcre_config(int what, void *where) -{ -switch (what) - { - case PCRE_CONFIG_UTF8: -#ifdef SUPPORT_UTF8 - *((int *)where) = 1; -#else - *((int *)where) = 0; -#endif - break; - - case PCRE_CONFIG_UNICODE_PROPERTIES: -#ifdef SUPPORT_UCP - *((int *)where) = 1; -#else - *((int *)where) = 0; -#endif - break; - - case PCRE_CONFIG_NEWLINE: - *((int *)where) = NEWLINE; - break; - - case PCRE_CONFIG_LINK_SIZE: - *((int *)where) = LINK_SIZE; - break; - - case PCRE_CONFIG_POSIX_MALLOC_THRESHOLD: - *((int *)where) = POSIX_MALLOC_THRESHOLD; - break; - - case PCRE_CONFIG_MATCH_LIMIT: - *((unsigned int *)where) = MATCH_LIMIT; - break; - - case PCRE_CONFIG_MATCH_LIMIT_RECURSION: - *((unsigned 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 deleted file mode 100644 index 882a1d1c06..0000000000 --- a/ext/pcre/pcrelib/pcre_exec.c +++ /dev/null @@ -1,3933 +0,0 @@ -/************************************************* -* 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) 1997-2006 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. */ - -#define NLBLOCK md /* The block containing newline information */ -#include "pcre_internal.h" - - -/* Structure for building a chain of data that actually lives on the -stack, 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. When NO_RECURSE is set, these blocks -are on the heap, not on the stack. */ - -typedef struct eptrblock { - struct eptrblock *epb_prev; - USPTR epb_saved_eptr; -} eptrblock; - -/* Flag bits for the match() function */ - -#define match_condassert 0x01 /* Called to check a condition assertion */ -#define match_isgroup 0x02 /* Set if start of bracketed 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 - -/* 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 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 uschar *p, int length, BOOL is_subject, match_data *md) -{ -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 * -*************************************************/ - -/* If a back reference hasn't been set, the length that is passed is greater -than the number of characters left in the string, so the match fails. - -Arguments: - offset index into the offset vector - eptr points into the subject - length length to be matched - md points to match data block - ims the ims flags - -Returns: TRUE if matched -*/ - -static BOOL -match_ref(int offset, register USPTR eptr, int length, match_data *md, - unsigned long int ims) -{ -USPTR p = md->start_subject + md->offset_vector[offset]; - -#ifdef 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 not enough characters left */ - -if (length > md->end_subject - eptr) return FALSE; - -/* Separate the caselesss case for speed */ - -if ((ims & PCRE_CASELESS) != 0) - { - while (length-- > 0) - if (md->lcc[*p++] != md->lcc[*eptr++]) return FALSE; - } -else - { while (length-- > 0) if (*p++ != *eptr++) return FALSE; } - -return TRUE; -} - - - -/*************************************************************************** -**************************************************************************** - 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. -**************************************************************************** -***************************************************************************/ - - -/* These versions of the macros use the stack, as normal. There are debugging -versions and production versions. */ - -#ifndef NO_RECURSE -#define REGISTER register -#ifdef DEBUG -#define RMATCH(rx,ra,rb,rc,rd,re,rf,rg) \ - { \ - printf("match() called in line %d\n", __LINE__); \ - rx = match(ra,rb,rc,rd,re,rf,rg,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(rx,ra,rb,rc,rd,re,rf,rg) \ - rx = match(ra,rb,rc,rd,re,rf,rg,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. It's the md argument of -match(), which never changes. */ - -#define REGISTER - -#define RMATCH(rx,ra,rb,rc,rd,re,rf,rg)\ - {\ - heapframe *newframe = (pcre_stack_malloc)(sizeof(heapframe));\ - if (setjmp(frame->Xwhere) == 0)\ - {\ - newframe->Xeptr = ra;\ - newframe->Xecode = rb;\ - newframe->Xoffset_top = rc;\ - newframe->Xims = re;\ - newframe->Xeptrb = rf;\ - newframe->Xflags = rg;\ - newframe->Xrdepth = frame->Xrdepth + 1;\ - newframe->Xprevframe = frame;\ - frame = newframe;\ - DPRINTF(("restarting from line %d\n", __LINE__));\ - goto HEAP_RECURSE;\ - }\ - else\ - {\ - DPRINTF(("longjumped back to line %d\n", __LINE__));\ - frame = md->thisframe;\ - rx = frame->Xresult;\ - }\ - } - -#define RRETURN(ra)\ - {\ - heapframe *newframe = frame;\ - frame = newframe->Xprevframe;\ - (pcre_stack_free)(newframe);\ - if (frame != NULL)\ - {\ - frame->Xresult = ra;\ - md->thisframe = frame;\ - longjmp(frame->Xwhere, 1);\ - }\ - return ra;\ - } - - -/* Structure for remembering the local variables in a private frame */ - -typedef struct heapframe { - struct heapframe *Xprevframe; - - /* Function arguments that may change */ - - const uschar *Xeptr; - const uschar *Xecode; - int Xoffset_top; - long int Xims; - eptrblock *Xeptrb; - int Xflags; - unsigned int Xrdepth; - - /* Function local variables */ - - const uschar *Xcallpat; - const uschar *Xcharptr; - const uschar *Xdata; - const uschar *Xnext; - const uschar *Xpp; - const uschar *Xprev; - const uschar *Xsaved_eptr; - - recursion_info Xnew_recursive; - - BOOL Xcur_is_word; - BOOL Xcondition; - BOOL Xminimize; - BOOL Xprev_is_word; - - unsigned long int Xoriginal_ims; - -#ifdef SUPPORT_UCP - int Xprop_type; - int Xprop_value; - int Xprop_fail_result; - int Xprop_category; - int Xprop_chartype; - int Xprop_script; - int *Xprop_test_variable; -#endif - - int Xctype; - 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; - - /* Place to pass back result, and where to jump back to */ - - int Xresult; - jmp_buf Xwhere; - -} heapframe; - -#endif - - -/*************************************************************************** -***************************************************************************/ - - - -/************************************************* -* Match from current position * -*************************************************/ - -/* On entry ecode points to the first opcode, and eptr to the first character -in the subject string, while eptrb holds the value of eptr at the start of the -last bracketed group - used for breaking infinite loops matching zero-length -strings. This function is called recursively in many circumstances. Whenever it -returns a negative (error) response, the outer incarnation must also return the -same response. - -Performance note: It might be tempting to extract commonly used fields from the -md structure (e.g. utf8, 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 in subject - ecode position in code - offset_top current top pointer - md pointer to "static" info for the match - ims current /i, /m, and /s options - eptrb pointer to chain of blocks containing eptr at start of - brackets - for testing for empty matches - flags can contain - match_condassert - this is an assertion condition - match_isgroup - this is the start of a bracketed group - rdepth the recursion depth - -Returns: MATCH_MATCH if matched ) these values are >= 0 - MATCH_NOMATCH if failed to match ) - 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 USPTR eptr, REGISTER const uschar *ecode, - int offset_top, match_data *md, unsigned long int ims, eptrblock *eptrb, - int flags, 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 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 utf8; /* Local copy of UTF-8 flag for speed */ - -/* When recursion is not being used, all "local" variables that have to be -preserved over calls to RMATCH() are part of a "frame" which is obtained from -heap storage. Set up the top-level frame here; others are obtained from the -heap whenever RMATCH() does a "recursion". See the macro definitions above. */ - -#ifdef NO_RECURSE -heapframe *frame = (pcre_stack_malloc)(sizeof(heapframe)); -frame->Xprevframe = NULL; /* Marks the top level */ - -/* Copy in the original argument variables */ - -frame->Xeptr = eptr; -frame->Xecode = ecode; -frame->Xoffset_top = offset_top; -frame->Xims = ims; -frame->Xeptrb = eptrb; -frame->Xflags = flags; -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 offset_top frame->Xoffset_top -#define ims frame->Xims -#define eptrb frame->Xeptrb -#define flags frame->Xflags -#define rdepth frame->Xrdepth - -/* Ditto for the local variables */ - -#ifdef SUPPORT_UTF8 -#define charptr frame->Xcharptr -#endif -#define callpat frame->Xcallpat -#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 minimize frame->Xminimize -#define prev_is_word frame->Xprev_is_word - -#define original_ims frame->Xoriginal_ims - -#ifdef SUPPORT_UCP -#define prop_type frame->Xprop_type -#define prop_value frame->Xprop_value -#define prop_fail_result frame->Xprop_fail_result -#define prop_category frame->Xprop_category -#define prop_chartype frame->Xprop_chartype -#define prop_script frame->Xprop_script -#define prop_test_variable frame->Xprop_test_variable -#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 -#define fi i -#define fc c - - -#ifdef SUPPORT_UTF8 /* Many of these variables are used only */ -const uschar *charptr; /* in small blocks of the code. My normal */ -#endif /* style of coding would have declared */ -const uschar *callpat; /* them within each of those blocks. */ -const uschar *data; /* However, in order to accommodate the */ -const uschar *next; /* version of this code that uses an */ -USPTR pp; /* external "stack" implemented on the */ -const uschar *prev; /* heap, it is easier to declare them all */ -USPTR saved_eptr; /* here, so the declarations can be cut */ - /* out in a block. The only declarations */ -recursion_info new_recursive; /* within blocks below are for variables */ - /* that do not have to be preserved over */ -BOOL cur_is_word; /* a recursive call to RMATCH(). */ -BOOL condition; -BOOL minimize; -BOOL prev_is_word; - -unsigned long int original_ims; - -#ifdef SUPPORT_UCP -int prop_type; -int prop_value; -int prop_fail_result; -int prop_category; -int prop_chartype; -int prop_script; -int *prop_test_variable; -#endif - -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; -#endif - -/* These statements are here to stop the compiler complaining about unitialized -variables. */ - -#ifdef SUPPORT_UCP -prop_value = 0; -prop_fail_result = 0; -prop_test_variable = NULL; -#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 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. */ - -/* 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); - -original_ims = ims; /* Save for resetting on ')' */ - -#ifdef SUPPORT_UTF8 -utf8 = md->utf8; /* Local copy of the flag */ -#else -utf8 = FALSE; -#endif - -/* At the start of a bracketed group, add the current subject pointer to the -stack of such pointers, to be re-instated at the end of the group when we hit -the closing ket. When match() is called in other circumstances, we don't add to -this stack. */ - -if ((flags & match_isgroup) != 0) - { - newptrb.epb_prev = eptrb; - newptrb.epb_saved_eptr = eptr; - eptrb = &newptrb; - } - -/* Now start processing the operations. */ - -for (;;) - { - op = *ecode; - minimize = FALSE; - - /* For partial matching, remember if we ever hit the end of the subject after - matching at least one subject character. */ - - if (md->partial && - eptr >= md->end_subject && - eptr > md->start_match) - md->hitend = TRUE; - - /* Opening capturing bracket. 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. - - If the bracket fails to match, we need to restore this 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. */ - - if (op > OP_BRA) - { - number = op - OP_BRA; - - /* For extended extraction brackets (large number), we have to fish out the - number from a dummy opcode at the start. */ - - if (number > EXTRACT_BASIC_MAX) - number = GET2(ecode, 2+LINK_SIZE); - offset = number << 1; - -#ifdef DEBUG - printf("start bracket %d subject=", number); - 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; - - DPRINTF(("saving %d %d %d\n", save_offset1, save_offset2, save_offset3)); - md->offset_vector[md->offset_end - number] = eptr - md->start_subject; - - do - { - RMATCH(rrc, eptr, ecode + 1 + LINK_SIZE, offset_top, md, ims, eptrb, - match_isgroup); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - md->capture_last = save_capture_last; - ecode += GET(ecode, 1); - } - while (*ecode == OP_ALT); - - 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; - - RRETURN(MATCH_NOMATCH); - } - - /* Insufficient room for saving captured contents */ - - else op = OP_BRA; - } - - /* Other types of node can be handled by a switch */ - - switch(op) - { - case OP_BRA: /* Non-capturing bracket: optimized */ - DPRINTF(("start bracket 0\n")); - - /* Loop for all the alternatives */ - - for (;;) - { - /* When we get to the final alternative within the brackets, we would - return the result of a recursive call to match() whatever happened. We - can reduce stack usage by turning this into a tail recursion. */ - - if (ecode[GET(ecode, 1)] != OP_ALT) - { - ecode += 1 + LINK_SIZE; - flags = match_isgroup; - DPRINTF(("bracket 0 tail recursion\n")); - goto TAIL_RECURSE; - } - - /* For non-final alternatives, continue the loop for a NOMATCH result; - otherwise return. */ - - RMATCH(rrc, eptr, ecode + 1 + LINK_SIZE, offset_top, md, ims, eptrb, - match_isgroup); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - ecode += GET(ecode, 1); - } - /* 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. As there is only one branch to be - obeyed, we can use tail recursion to avoid using another stack frame. */ - - case OP_COND: - if (ecode[LINK_SIZE+1] == OP_CREF) /* Condition extract or recurse test */ - { - offset = GET2(ecode, LINK_SIZE+2) << 1; /* Doubled ref number */ - condition = (offset == CREF_RECURSE * 2)? - (md->recursive != NULL) : - (offset < offset_top && md->offset_vector[offset] >= 0); - ecode += condition? (LINK_SIZE + 4) : (LINK_SIZE + 1 + GET(ecode, 1)); - flags = match_isgroup; - goto TAIL_RECURSE; - } - - /* The condition is an assertion. Call match() to evaluate it - setting - the final argument TRUE causes it to stop at the end of an assertion. */ - - else - { - RMATCH(rrc, eptr, ecode + 1 + LINK_SIZE, offset_top, md, ims, NULL, - match_condassert | match_isgroup); - if (rrc == MATCH_MATCH) - { - ecode += 1 + LINK_SIZE + GET(ecode, LINK_SIZE+2); - while (*ecode == OP_ALT) ecode += GET(ecode, 1); - } - else if (rrc != MATCH_NOMATCH) - { - RRETURN(rrc); /* Need braces because of following else */ - } - else ecode += GET(ecode, 1); - - /* We are now at the branch that is to be obeyed. As there is only one, - we can use tail recursion to avoid using another stack frame. */ - - ecode += 1 + LINK_SIZE; - flags = match_isgroup; - goto TAIL_RECURSE; - } - /* Control never reaches here */ - - /* Skip over conditional reference or large extraction number data if - encountered. */ - - case OP_CREF: - case OP_BRANUMBER: - ecode += 3; - break; - - /* End of the pattern. If we are in a recursion, we should restore the - offsets appropriately and continue from after the call. */ - - case OP_END: - if (md->recursive != NULL && md->recursive->group_num == 0) - { - recursion_info *rec = md->recursive; - DPRINTF(("End of pattern in a (?0) recursion\n")); - md->recursive = rec->prevrec; - memmove(md->offset_vector, rec->offset_save, - rec->saved_max * sizeof(int)); - md->start_match = rec->save_start; - ims = original_ims; - ecode = rec->after_call; - break; - } - - /* Otherwise, if PCRE_NOTEMPTY is set, fail if we have matched an empty - string - backtracking will then try other alternatives, if any. */ - - if (md->notempty && eptr == md->start_match) RRETURN(MATCH_NOMATCH); - md->end_match_ptr = eptr; /* Record where we ended */ - md->end_offset_top = offset_top; /* and how many extracts were taken */ - RRETURN(MATCH_MATCH); - - /* Change option settings */ - - case OP_OPT: - ims = ecode[1]; - ecode += 2; - DPRINTF(("ims set to %02lx\n", ims)); - break; - - /* 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. */ - - case OP_ASSERT: - case OP_ASSERTBACK: - do - { - RMATCH(rrc, eptr, ecode + 1 + LINK_SIZE, offset_top, md, ims, NULL, - match_isgroup); - if (rrc == MATCH_MATCH) break; - if (rrc != MATCH_NOMATCH) 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 ((flags & match_condassert) != 0) 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 */ - - case OP_ASSERT_NOT: - case OP_ASSERTBACK_NOT: - do - { - RMATCH(rrc, eptr, ecode + 1 + LINK_SIZE, offset_top, md, ims, NULL, - match_isgroup); - if (rrc == MATCH_MATCH) RRETURN(MATCH_NOMATCH); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - ecode += GET(ecode,1); - } - while (*ecode == OP_ALT); - - if ((flags & match_condassert) != 0) RRETURN(MATCH_MATCH); - - 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_UTF8 - if (utf8) - { - c = GET(ecode,1); - for (i = 0; i < c; i++) - { - 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); - } - - /* Skip to next op code */ - - 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 (pcre_callout != NULL) - { - pcre_callout_block cb; - cb.version = 1; /* Version 1 of the callout block */ - cb.callout_number = ecode[1]; - cb.offset_vector = md->offset_vector; - cb.subject = (PCRE_SPTR)md->start_subject; - cb.subject_length = md->end_subject - md->start_subject; - cb.start_match = md->start_match - md->start_subject; - cb.current_position = 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; - if ((rrc = (*pcre_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.) - - If there are any capturing brackets started but not finished, we have to - save their starting points and reinstate them after the recursion. However, - we don't know how many such there are (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. A problem is what to do if the malloc fails ... there is no way of - returning to the top level with an error. Save the top REC_STACK_SAVE_MAX - values on the stack, and accept that the rest may be wrong. - - 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. */ - - case OP_RECURSE: - { - callpat = md->start_code + GET(ecode, 1); - new_recursive.group_num = *callpat - OP_BRA; - - /* For extended extraction brackets (large number), we have to fish out - the number from a dummy opcode at the start. */ - - if (new_recursive.group_num > EXTRACT_BASIC_MAX) - new_recursive.group_num = GET2(callpat, 2+LINK_SIZE); - - /* Add to "recursing stack" */ - - new_recursive.prevrec = md->recursive; - md->recursive = &new_recursive; - - /* Find where to continue from afterwards */ - - ecode += 1 + LINK_SIZE; - new_recursive.after_call = ecode; - - /* 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 *)(pcre_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)); - new_recursive.save_start = md->start_match; - md->start_match = eptr; - - /* OK, now we can do the recursion. For each top-level alternative we - restore the offset and recursion data. */ - - DPRINTF(("Recursing into group %d\n", new_recursive.group_num)); - do - { - RMATCH(rrc, eptr, callpat + 1 + LINK_SIZE, offset_top, md, ims, - eptrb, match_isgroup); - if (rrc == MATCH_MATCH) - { - DPRINTF(("Recursion matched\n")); - md->recursive = new_recursive.prevrec; - if (new_recursive.offset_save != stacksave) - (pcre_free)(new_recursive.offset_save); - RRETURN(MATCH_MATCH); - } - else if (rrc != MATCH_NOMATCH) - { - DPRINTF(("Recursion gave error %d\n", rrc)); - RRETURN(rrc); - } - - md->recursive = &new_recursive; - memcpy(md->offset_vector, new_recursive.offset_save, - new_recursive.saved_max * sizeof(int)); - 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) - (pcre_free)(new_recursive.offset_save); - RRETURN(MATCH_NOMATCH); - } - /* Control never reaches here */ - - /* "Once" brackets are like assertion brackets except that after a match, - the point in the subject string is not moved back. Thus there can never be - a move back into the brackets. Friedl calls these "atomic" subpatterns. - 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. */ - - case OP_ONCE: - prev = ecode; - saved_eptr = eptr; - - do - { - RMATCH(rrc, eptr, ecode + 1 + LINK_SIZE, offset_top, md, ims, - eptrb, match_isgroup); - if (rrc == MATCH_MATCH) break; - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - ecode += GET(ecode,1); - } - while (*ecode == OP_ALT); - - /* If hit the end of the group (which could be repeated), fail */ - - if (*ecode != OP_ONCE && *ecode != OP_ALT) RRETURN(MATCH_NOMATCH); - - /* Continue as from after the assertion, 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 there is an options reset, it will get obeyed in the normal - course of events. */ - - 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. We need to reset - any options that changed within the bracket before re-running it, so - check the next opcode. */ - - if (ecode[1+LINK_SIZE] == OP_OPT) - { - ims = (ims & ~PCRE_IMS) | ecode[4]; - DPRINTF(("ims set to %02lx at group repeat\n", ims)); - } - - if (*ecode == OP_KETRMIN) - { - RMATCH(rrc, eptr, ecode + 1 + LINK_SIZE, offset_top, md, ims, eptrb, 0); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - ecode = prev; - flags = match_isgroup; - goto TAIL_RECURSE; - } - else /* OP_KETRMAX */ - { - RMATCH(rrc, eptr, prev, offset_top, md, ims, eptrb, match_isgroup); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - ecode += 1 + LINK_SIZE; - flags = 0; - goto TAIL_RECURSE; - } - /* Control never gets here */ - - /* 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 and BRAMINZERO 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 ()? 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(rrc, eptr, next, offset_top, md, ims, eptrb, match_isgroup); - 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(rrc, eptr, next + 1+LINK_SIZE, offset_top, md, ims, eptrb, - match_isgroup); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - ecode++; - } - break; - - /* End of a group, repeated or non-repeating. If we are at the end of - an assertion "group", stop matching and return MATCH_MATCH, but record the - current high water mark for use by positive assertions. Do this also - for the "once" (not-backup up) groups. */ - - case OP_KET: - case OP_KETRMIN: - case OP_KETRMAX: - prev = ecode - GET(ecode, 1); - saved_eptr = eptrb->epb_saved_eptr; - - /* Back up the stack of bracket start pointers. */ - - eptrb = eptrb->epb_prev; - - if (*prev == OP_ASSERT || *prev == OP_ASSERT_NOT || - *prev == OP_ASSERTBACK || *prev == OP_ASSERTBACK_NOT || - *prev == OP_ONCE) - { - md->end_match_ptr = eptr; /* For ONCE */ - md->end_offset_top = offset_top; - RRETURN(MATCH_MATCH); - } - - /* In all other cases except a conditional group 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. */ - - if (*prev != OP_COND) - { - number = *prev - OP_BRA; - - /* For extended extraction brackets (large number), we have to fish out - the number from a dummy opcode at the start. */ - - if (number > EXTRACT_BASIC_MAX) number = GET2(prev, 2+LINK_SIZE); - offset = number << 1; - -#ifdef DEBUG - printf("end bracket %d", number); - printf("\n"); -#endif - - /* Test for a numbered group. This includes groups called as a result - of recursion. Note that 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. */ - - if (number > 0) - { - 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] = eptr - md->start_subject; - if (offset_top <= offset) offset_top = offset + 2; - } - - /* Handle a recursively called group. Restore the offsets - appropriately and continue from after the call. */ - - if (md->recursive != NULL && md->recursive->group_num == number) - { - recursion_info *rec = md->recursive; - DPRINTF(("Recursion (%d) succeeded - continuing\n", number)); - md->recursive = rec->prevrec; - md->start_match = rec->save_start; - memcpy(md->offset_vector, rec->offset_save, - rec->saved_max * sizeof(int)); - ecode = rec->after_call; - ims = original_ims; - break; - } - } - } - - /* Reset the value of the ims flags, in case they got changed during - the group. */ - - ims = original_ims; - DPRINTF(("ims reset to %02lx\n", ims)); - - /* 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 there is an options reset, it will get obeyed in the normal - course of events. */ - - 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. In the second case, we can use - tail recursion to avoid using another stack frame. */ - - if (*ecode == OP_KETRMIN) - { - RMATCH(rrc, eptr, ecode + 1+LINK_SIZE, offset_top, md, ims, eptrb, 0); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - ecode = prev; - flags = match_isgroup; - goto TAIL_RECURSE; - } - else /* OP_KETRMAX */ - { - RMATCH(rrc, eptr, prev, offset_top, md, ims, eptrb, match_isgroup); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - ecode += 1 + LINK_SIZE; - flags = 0; - goto TAIL_RECURSE; - } - /* Control never gets here */ - - /* Start of subject unless notbol, or after internal newline if multiline */ - - case OP_CIRC: - if (md->notbol && eptr == md->start_subject) RRETURN(MATCH_NOMATCH); - if ((ims & PCRE_MULTILINE) != 0) - { - if (eptr != md->start_subject && - (eptr == md->end_subject || - eptr < md->start_subject + md->nllen || - !IS_NEWLINE(eptr - md->nllen))) - RRETURN(MATCH_NOMATCH); - ecode++; - break; - } - /* ... else fall through */ - - /* Start of subject assertion */ - - case OP_SOD: - if (eptr != md->start_subject) 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; - - /* Assert before internal newline if multiline, or before a terminating - newline unless endonly is set, else end of subject unless noteol is set. */ - - case OP_DOLL: - if ((ims & PCRE_MULTILINE) != 0) - { - if (eptr < md->end_subject) - { if (!IS_NEWLINE(eptr)) RRETURN(MATCH_NOMATCH); } - else - { if (md->noteol) RRETURN(MATCH_NOMATCH); } - ecode++; - break; - } - else - { - if (md->noteol) RRETURN(MATCH_NOMATCH); - if (!md->endonly) - { - if (eptr != md->end_subject && - (eptr != md->end_subject - md->nllen || !IS_NEWLINE(eptr))) - RRETURN(MATCH_NOMATCH); - ecode++; - break; - } - } - /* ... else fall through for endonly */ - - /* End of subject assertion (\z) */ - - case OP_EOD: - if (eptr < md->end_subject) RRETURN(MATCH_NOMATCH); - ecode++; - break; - - /* End of subject or ending \n assertion (\Z) */ - - case OP_EODN: - if (eptr != md->end_subject && - (eptr != md->end_subject - md->nllen || !IS_NEWLINE(eptr))) - RRETURN(MATCH_NOMATCH); - 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. */ - -#ifdef SUPPORT_UTF8 - if (utf8) - { - if (eptr == md->start_subject) prev_is_word = FALSE; else - { - const uschar *lastptr = eptr - 1; - while((*lastptr & 0xc0) == 0x80) lastptr--; - GETCHAR(c, lastptr); - prev_is_word = c < 256 && (md->ctypes[c] & ctype_word) != 0; - } - if (eptr >= md->end_subject) cur_is_word = FALSE; else - { - GETCHAR(c, eptr); - cur_is_word = c < 256 && (md->ctypes[c] & ctype_word) != 0; - } - } - else -#endif - - /* More streamlined when not in UTF-8 mode */ - - { - prev_is_word = (eptr != md->start_subject) && - ((md->ctypes[eptr[-1]] & ctype_word) != 0); - cur_is_word = (eptr < md->end_subject) && - ((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 a single character type; inline for speed */ - - case OP_ANY: - if ((ims & PCRE_DOTALL) == 0) - { - if (eptr <= md->end_subject - md->nllen && IS_NEWLINE(eptr)) - RRETURN(MATCH_NOMATCH); - } - if (eptr++ >= md->end_subject) RRETURN(MATCH_NOMATCH); - if (utf8) - while (eptr < md->end_subject && (*eptr & 0xc0) == 0x80) eptr++; - 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) RRETURN(MATCH_NOMATCH); - ecode++; - break; - - case OP_NOT_DIGIT: - if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); - GETCHARINCTEST(c, eptr); - if ( -#ifdef SUPPORT_UTF8 - c < 256 && -#endif - (md->ctypes[c] & ctype_digit) != 0 - ) - RRETURN(MATCH_NOMATCH); - ecode++; - break; - - case OP_DIGIT: - if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); - GETCHARINCTEST(c, eptr); - if ( -#ifdef SUPPORT_UTF8 - c >= 256 || -#endif - (md->ctypes[c] & ctype_digit) == 0 - ) - RRETURN(MATCH_NOMATCH); - ecode++; - break; - - case OP_NOT_WHITESPACE: - if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); - GETCHARINCTEST(c, eptr); - if ( -#ifdef SUPPORT_UTF8 - c < 256 && -#endif - (md->ctypes[c] & ctype_space) != 0 - ) - RRETURN(MATCH_NOMATCH); - ecode++; - break; - - case OP_WHITESPACE: - if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); - GETCHARINCTEST(c, eptr); - if ( -#ifdef SUPPORT_UTF8 - c >= 256 || -#endif - (md->ctypes[c] & ctype_space) == 0 - ) - RRETURN(MATCH_NOMATCH); - ecode++; - break; - - case OP_NOT_WORDCHAR: - if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); - GETCHARINCTEST(c, eptr); - if ( -#ifdef SUPPORT_UTF8 - c < 256 && -#endif - (md->ctypes[c] & ctype_word) != 0 - ) - RRETURN(MATCH_NOMATCH); - ecode++; - break; - - case OP_WORDCHAR: - if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); - GETCHARINCTEST(c, eptr); - if ( -#ifdef SUPPORT_UTF8 - c >= 256 || -#endif - (md->ctypes[c] & ctype_word) == 0 - ) - RRETURN(MATCH_NOMATCH); - 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) RRETURN(MATCH_NOMATCH); - GETCHARINCTEST(c, eptr); - { - int chartype, script; - int category = _pcre_ucp_findprop(c, &chartype, &script); - - switch(ecode[1]) - { - case PT_ANY: - if (op == OP_NOTPROP) RRETURN(MATCH_NOMATCH); - break; - - case PT_LAMP: - if ((chartype == ucp_Lu || - chartype == ucp_Ll || - chartype == ucp_Lt) == (op == OP_NOTPROP)) - RRETURN(MATCH_NOMATCH); - break; - - case PT_GC: - if ((ecode[2] != category) == (op == OP_PROP)) - RRETURN(MATCH_NOMATCH); - break; - - case PT_PC: - if ((ecode[2] != chartype) == (op == OP_PROP)) - RRETURN(MATCH_NOMATCH); - break; - - case PT_SC: - if ((ecode[2] != script) == (op == OP_PROP)) - RRETURN(MATCH_NOMATCH); - break; - - default: - RRETURN(PCRE_ERROR_INTERNAL); - break; - } - - 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) RRETURN(MATCH_NOMATCH); - GETCHARINCTEST(c, eptr); - { - int chartype, script; - int category = _pcre_ucp_findprop(c, &chartype, &script); - if (category == ucp_M) RRETURN(MATCH_NOMATCH); - while (eptr < md->end_subject) - { - int len = 1; - if (!utf8) c = *eptr; else - { - GETCHARLEN(c, eptr, len); - } - category = _pcre_ucp_findprop(c, &chartype, &script); - if (category != ucp_M) break; - eptr += len; - } - } - 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: - { - offset = GET2(ecode, 1) << 1; /* Doubled ref number */ - ecode += 3; /* Advance past item */ - - /* If the reference is unset, set the length to be longer than the amount - of subject left; this ensures that every attempt at a match fails. We - can't just fail here, because of the possibility of quantifiers with zero - minima. */ - - length = (offset >= offset_top || md->offset_vector[offset] < 0)? - md->end_subject - eptr + 1 : - 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, 3); - if (max == 0) max = INT_MAX; - ecode += 5; - break; - - default: /* No repeat follows */ - if (!match_ref(offset, eptr, length, md, ims)) RRETURN(MATCH_NOMATCH); - eptr += length; - continue; /* With the main loop */ - } - - /* If the length of the reference is zero, just continue with the - main loop. */ - - if (length == 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++) - { - if (!match_ref(offset, eptr, length, md, ims)) RRETURN(MATCH_NOMATCH); - eptr += length; - } - - /* 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++) - { - RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - if (fi >= max || !match_ref(offset, eptr, length, md, ims)) - RRETURN(MATCH_NOMATCH); - eptr += length; - } - /* Control never gets here */ - } - - /* If maximizing, find the longest string and work backwards */ - - else - { - pp = eptr; - for (i = min; i < max; i++) - { - if (!match_ref(offset, eptr, length, md, ims)) break; - eptr += length; - } - while (eptr >= pp) - { - RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); - 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: - { - data = ecode + 1; /* Save for matching */ - ecode += 33; /* 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, 3); - if (max == 0) max = INT_MAX; - ecode += 5; - break; - - default: /* No repeat follows */ - min = max = 1; - break; - } - - /* First, ensure the minimum number of matches are present. */ - -#ifdef SUPPORT_UTF8 - /* UTF-8 mode */ - if (utf8) - { - for (i = 1; i <= min; i++) - { - if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); - GETCHARINC(c, eptr); - if (c > 255) - { - if (op == OP_CLASS) RRETURN(MATCH_NOMATCH); - } - else - { - if ((data[c/8] & (1 << (c&7))) == 0) RRETURN(MATCH_NOMATCH); - } - } - } - else -#endif - /* Not UTF-8 mode */ - { - for (i = 1; i <= min; i++) - { - if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); - c = *eptr++; - if ((data[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_UTF8 - /* UTF-8 mode */ - if (utf8) - { - for (fi = min;; fi++) - { - RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - if (fi >= max || eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); - GETCHARINC(c, eptr); - if (c > 255) - { - if (op == OP_CLASS) RRETURN(MATCH_NOMATCH); - } - else - { - if ((data[c/8] & (1 << (c&7))) == 0) RRETURN(MATCH_NOMATCH); - } - } - } - else -#endif - /* Not UTF-8 mode */ - { - for (fi = min;; fi++) - { - RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - if (fi >= max || eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); - c = *eptr++; - if ((data[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_UTF8 - /* UTF-8 mode */ - if (utf8) - { - for (i = min; i < max; i++) - { - int len = 1; - if (eptr >= md->end_subject) break; - GETCHARLEN(c, eptr, len); - if (c > 255) - { - if (op == OP_CLASS) break; - } - else - { - if ((data[c/8] & (1 << (c&7))) == 0) break; - } - eptr += len; - } - for (;;) - { - RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - if (eptr-- == pp) break; /* Stop if tried at original pos */ - BACKCHAR(eptr); - } - } - else -#endif - /* Not UTF-8 mode */ - { - for (i = min; i < max; i++) - { - if (eptr >= md->end_subject) break; - c = *eptr; - if ((data[c/8] & (1 << (c&7))) == 0) break; - eptr++; - } - while (eptr >= pp) - { - RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - eptr--; - } - } - - RRETURN(MATCH_NOMATCH); - } - } - /* Control never gets here */ - - - /* Match an extended character class. This opcode is encountered only - in UTF-8 mode, because that's the only time it is compiled. */ - -#ifdef SUPPORT_UTF8 - 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, 3); - if (max == 0) max = INT_MAX; - ecode += 5; - 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) RRETURN(MATCH_NOMATCH); - GETCHARINC(c, eptr); - if (!_pcre_xclass(c, data)) 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(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - if (fi >= max || eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); - GETCHARINC(c, eptr); - if (!_pcre_xclass(c, data)) 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) break; - GETCHARLEN(c, eptr, len); - if (!_pcre_xclass(c, data)) break; - eptr += len; - } - for(;;) - { - RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - if (eptr-- == pp) break; /* Stop if tried at original pos */ - BACKCHAR(eptr) - } - RRETURN(MATCH_NOMATCH); - } - - /* Control never gets here */ - } -#endif /* End of XCLASS */ - - /* Match a single character, casefully */ - - case OP_CHAR: -#ifdef SUPPORT_UTF8 - if (utf8) - { - length = 1; - ecode++; - GETCHARLEN(fc, ecode, length); - if (length > md->end_subject - eptr) RRETURN(MATCH_NOMATCH); - while (length-- > 0) if (*ecode++ != *eptr++) RRETURN(MATCH_NOMATCH); - } - else -#endif - - /* Non-UTF-8 mode */ - { - if (md->end_subject - eptr < 1) RRETURN(MATCH_NOMATCH); - if (ecode[1] != *eptr++) RRETURN(MATCH_NOMATCH); - ecode += 2; - } - break; - - /* Match a single character, caselessly */ - - case OP_CHARNC: -#ifdef SUPPORT_UTF8 - if (utf8) - { - length = 1; - ecode++; - GETCHARLEN(fc, ecode, length); - - if (length > md->end_subject - eptr) RRETURN(MATCH_NOMATCH); - - /* If the pattern character's value is < 128, we have only one byte, and - can use the fast lookup table. */ - - if (fc < 128) - { - if (md->lcc[*ecode++] != md->lcc[*eptr++]) RRETURN(MATCH_NOMATCH); - } - - /* Otherwise we must pick up the subject character */ - - else - { - 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 != _pcre_ucp_othercase(fc)) -#endif - RRETURN(MATCH_NOMATCH); - } - } - } - else -#endif /* SUPPORT_UTF8 */ - - /* Non-UTF-8 mode */ - { - if (md->end_subject - eptr < 1) RRETURN(MATCH_NOMATCH); - if (md->lcc[ecode[1]] != md->lcc[*eptr++]) RRETURN(MATCH_NOMATCH); - ecode += 2; - } - break; - - /* Match a single character repeatedly; different opcodes share code. */ - - case OP_EXACT: - min = max = GET2(ecode, 1); - ecode += 3; - goto REPEATCHAR; - - case OP_UPTO: - case OP_MINUPTO: - min = 0; - max = GET2(ecode, 1); - minimize = *ecode == OP_MINUPTO; - ecode += 3; - goto REPEATCHAR; - - case OP_STAR: - case OP_MINSTAR: - case OP_PLUS: - case OP_MINPLUS: - case OP_QUERY: - case OP_MINQUERY: - c = *ecode++ - OP_STAR; - 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. We can give - up quickly if there are fewer than the minimum number of characters left in - the subject. */ - - REPEATCHAR: -#ifdef SUPPORT_UTF8 - if (utf8) - { - length = 1; - charptr = ecode; - GETCHARLEN(fc, ecode, length); - if (min * length > md->end_subject - eptr) RRETURN(MATCH_NOMATCH); - ecode += length; - - /* Handle multibyte character matching specially here. There is - support for caseless matching if UCP support is present. */ - - if (length > 1) - { - int oclength = 0; - uschar occhars[8]; - -#ifdef SUPPORT_UCP - int othercase; - if ((ims & PCRE_CASELESS) != 0 && - (othercase = _pcre_ucp_othercase(fc)) >= 0 && - othercase >= 0) - oclength = _pcre_ord2utf8(othercase, occhars); -#endif /* SUPPORT_UCP */ - - for (i = 1; i <= min; i++) - { - if (memcmp(eptr, charptr, length) == 0) eptr += length; - /* Need braces because of following else */ - else if (oclength == 0) { RRETURN(MATCH_NOMATCH); } - else - { - if (memcmp(eptr, occhars, oclength) != 0) RRETURN(MATCH_NOMATCH); - eptr += oclength; - } - } - - if (min == max) continue; - - if (minimize) - { - for (fi = min;; fi++) - { - RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - if (fi >= max || eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); - if (memcmp(eptr, charptr, length) == 0) eptr += length; - /* Need braces because of following else */ - else if (oclength == 0) { RRETURN(MATCH_NOMATCH); } - else - { - if (memcmp(eptr, occhars, oclength) != 0) RRETURN(MATCH_NOMATCH); - eptr += oclength; - } - } - /* Control never gets here */ - } - else - { - pp = eptr; - for (i = min; i < max; i++) - { - if (eptr > md->end_subject - length) break; - if (memcmp(eptr, charptr, length) == 0) eptr += length; - else if (oclength == 0) break; - else - { - if (memcmp(eptr, occhars, oclength) != 0) break; - eptr += oclength; - } - } - while (eptr >= pp) - { - RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - eptr -= length; - } - RRETURN(MATCH_NOMATCH); - } - /* 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_UTF8 */ - - /* When not in UTF-8 mode, load a single-byte character. */ - { - if (min > md->end_subject - eptr) RRETURN(MATCH_NOMATCH); - fc = *ecode++; - } - - /* The value of fc at this point is always less than 256, though we may or - may not be in UTF-8 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, eptr)); - - if ((ims & PCRE_CASELESS) != 0) - { - fc = md->lcc[fc]; - for (i = 1; i <= min; i++) - if (fc != md->lcc[*eptr++]) RRETURN(MATCH_NOMATCH); - if (min == max) continue; - if (minimize) - { - for (fi = min;; fi++) - { - RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - if (fi >= max || eptr >= md->end_subject || - fc != md->lcc[*eptr++]) - RRETURN(MATCH_NOMATCH); - } - /* Control never gets here */ - } - else - { - pp = eptr; - for (i = min; i < max; i++) - { - if (eptr >= md->end_subject || fc != md->lcc[*eptr]) break; - eptr++; - } - while (eptr >= pp) - { - RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); - 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 (fc != *eptr++) RRETURN(MATCH_NOMATCH); - if (min == max) continue; - if (minimize) - { - for (fi = min;; fi++) - { - RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - if (fi >= max || eptr >= md->end_subject || fc != *eptr++) - RRETURN(MATCH_NOMATCH); - } - /* Control never gets here */ - } - else - { - pp = eptr; - for (i = min; i < max; i++) - { - if (eptr >= md->end_subject || fc != *eptr) break; - eptr++; - } - while (eptr >= pp) - { - RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); - 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: - if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); - ecode++; - GETCHARINCTEST(c, eptr); - if ((ims & PCRE_CASELESS) != 0) - { -#ifdef SUPPORT_UTF8 - if (c < 256) -#endif - c = md->lcc[c]; - if (md->lcc[*ecode++] == c) RRETURN(MATCH_NOMATCH); - } - else - { - if (*ecode++ == c) RRETURN(MATCH_NOMATCH); - } - 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: - min = max = GET2(ecode, 1); - ecode += 3; - goto REPEATNOTCHAR; - - case OP_NOTUPTO: - case OP_NOTMINUPTO: - min = 0; - max = GET2(ecode, 1); - minimize = *ecode == OP_NOTMINUPTO; - ecode += 3; - goto REPEATNOTCHAR; - - case OP_NOTSTAR: - case OP_NOTMINSTAR: - case OP_NOTPLUS: - case OP_NOTMINPLUS: - case OP_NOTQUERY: - case OP_NOTMINQUERY: - c = *ecode++ - 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. We can give up quickly - if there are fewer than the minimum number of bytes left in the - subject. */ - - REPEATNOTCHAR: - if (min > md->end_subject - eptr) RRETURN(MATCH_NOMATCH); - 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, eptr)); - - if ((ims & PCRE_CASELESS) != 0) - { - fc = md->lcc[fc]; - -#ifdef SUPPORT_UTF8 - /* UTF-8 mode */ - if (utf8) - { - register int d; - for (i = 1; i <= min; i++) - { - GETCHARINC(d, eptr); - if (d < 256) d = md->lcc[d]; - if (fc == d) RRETURN(MATCH_NOMATCH); - } - } - else -#endif - - /* Not UTF-8 mode */ - { - for (i = 1; i <= min; i++) - if (fc == md->lcc[*eptr++]) RRETURN(MATCH_NOMATCH); - } - - if (min == max) continue; - - if (minimize) - { -#ifdef SUPPORT_UTF8 - /* UTF-8 mode */ - if (utf8) - { - register int d; - for (fi = min;; fi++) - { - RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - GETCHARINC(d, eptr); - if (d < 256) d = md->lcc[d]; - if (fi >= max || eptr >= md->end_subject || fc == d) - RRETURN(MATCH_NOMATCH); - } - } - else -#endif - /* Not UTF-8 mode */ - { - for (fi = min;; fi++) - { - RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - if (fi >= max || eptr >= md->end_subject || fc == md->lcc[*eptr++]) - RRETURN(MATCH_NOMATCH); - } - } - /* Control never gets here */ - } - - /* Maximize case */ - - else - { - pp = eptr; - -#ifdef SUPPORT_UTF8 - /* UTF-8 mode */ - if (utf8) - { - register int d; - for (i = min; i < max; i++) - { - int len = 1; - if (eptr >= md->end_subject) break; - GETCHARLEN(d, eptr, len); - if (d < 256) d = md->lcc[d]; - if (fc == d) break; - eptr += len; - } - for(;;) - { - RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - if (eptr-- == pp) break; /* Stop if tried at original pos */ - BACKCHAR(eptr); - } - } - else -#endif - /* Not UTF-8 mode */ - { - for (i = min; i < max; i++) - { - if (eptr >= md->end_subject || fc == md->lcc[*eptr]) break; - eptr++; - } - while (eptr >= pp) - { - RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - eptr--; - } - } - - RRETURN(MATCH_NOMATCH); - } - /* Control never gets here */ - } - - /* Caseful comparisons */ - - else - { -#ifdef SUPPORT_UTF8 - /* UTF-8 mode */ - if (utf8) - { - register int d; - for (i = 1; i <= min; i++) - { - GETCHARINC(d, eptr); - if (fc == d) RRETURN(MATCH_NOMATCH); - } - } - else -#endif - /* Not UTF-8 mode */ - { - for (i = 1; i <= min; i++) - if (fc == *eptr++) RRETURN(MATCH_NOMATCH); - } - - if (min == max) continue; - - if (minimize) - { -#ifdef SUPPORT_UTF8 - /* UTF-8 mode */ - if (utf8) - { - register int d; - for (fi = min;; fi++) - { - RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - GETCHARINC(d, eptr); - if (fi >= max || eptr >= md->end_subject || fc == d) - RRETURN(MATCH_NOMATCH); - } - } - else -#endif - /* Not UTF-8 mode */ - { - for (fi = min;; fi++) - { - RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - if (fi >= max || eptr >= md->end_subject || fc == *eptr++) - RRETURN(MATCH_NOMATCH); - } - } - /* Control never gets here */ - } - - /* Maximize case */ - - else - { - pp = eptr; - -#ifdef SUPPORT_UTF8 - /* UTF-8 mode */ - if (utf8) - { - register int d; - for (i = min; i < max; i++) - { - int len = 1; - if (eptr >= md->end_subject) break; - GETCHARLEN(d, eptr, len); - if (fc == d) break; - eptr += len; - } - for(;;) - { - RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - if (eptr-- == pp) break; /* Stop if tried at original pos */ - BACKCHAR(eptr); - } - } - else -#endif - /* Not UTF-8 mode */ - { - for (i = min; i < max; i++) - { - if (eptr >= md->end_subject || fc == *eptr) break; - eptr++; - } - while (eptr >= pp) - { - RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); - 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 += 3; - goto REPEATTYPE; - - case OP_TYPEUPTO: - case OP_TYPEMINUPTO: - min = 0; - max = GET2(ecode, 1); - minimize = *ecode == OP_TYPEMINUPTO; - ecode += 3; - 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). Also we can test that there are at least - the minimum number of bytes before we start. This isn't as effective in - UTF-8 mode, but it does no harm. 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 > md->end_subject - eptr) RRETURN(MATCH_NOMATCH); - 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) RRETURN(MATCH_NOMATCH); - GETCHARINC(c, eptr); - } - break; - - case PT_LAMP: - for (i = 1; i <= min; i++) - { - if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); - GETCHARINC(c, eptr); - prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script); - if ((prop_chartype == ucp_Lu || - prop_chartype == ucp_Ll || - prop_chartype == ucp_Lt) == prop_fail_result) - RRETURN(MATCH_NOMATCH); - } - break; - - case PT_GC: - for (i = 1; i <= min; i++) - { - if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); - GETCHARINC(c, eptr); - prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script); - if ((prop_category == prop_value) == prop_fail_result) - RRETURN(MATCH_NOMATCH); - } - break; - - case PT_PC: - for (i = 1; i <= min; i++) - { - if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); - GETCHARINC(c, eptr); - prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script); - if ((prop_chartype == prop_value) == prop_fail_result) - RRETURN(MATCH_NOMATCH); - } - break; - - case PT_SC: - for (i = 1; i <= min; i++) - { - if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); - GETCHARINC(c, eptr); - prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script); - if ((prop_script == prop_value) == prop_fail_result) - RRETURN(MATCH_NOMATCH); - } - break; - - default: - RRETURN(PCRE_ERROR_INTERNAL); - break; - } - } - - /* 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++) - { - GETCHARINCTEST(c, eptr); - prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script); - if (prop_category == ucp_M) RRETURN(MATCH_NOMATCH); - while (eptr < md->end_subject) - { - int len = 1; - if (!utf8) c = *eptr; else - { - GETCHARLEN(c, eptr, len); - } - prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script); - if (prop_category != ucp_M) break; - eptr += len; - } - } - } - - else -#endif /* SUPPORT_UCP */ - -/* Handle all other cases when the coding is UTF-8 */ - -#ifdef SUPPORT_UTF8 - if (utf8) switch(ctype) - { - case OP_ANY: - for (i = 1; i <= min; i++) - { - if (eptr >= md->end_subject || - ((ims & PCRE_DOTALL) == 0 && - eptr <= md->end_subject - md->nllen && - IS_NEWLINE(eptr))) - RRETURN(MATCH_NOMATCH); - eptr++; - while (eptr < md->end_subject && (*eptr & 0xc0) == 0x80) eptr++; - } - break; - - case OP_ANYBYTE: - eptr += min; - break; - - case OP_NOT_DIGIT: - for (i = 1; i <= min; i++) - { - if (eptr >= md->end_subject) 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 || - *eptr >= 128 || (md->ctypes[*eptr++] & ctype_digit) == 0) - RRETURN(MATCH_NOMATCH); - /* 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 || - (*eptr < 128 && (md->ctypes[*eptr++] & ctype_space) != 0)) - RRETURN(MATCH_NOMATCH); - while (eptr < md->end_subject && (*eptr & 0xc0) == 0x80) eptr++; - } - break; - - case OP_WHITESPACE: - for (i = 1; i <= min; i++) - { - if (eptr >= md->end_subject || - *eptr >= 128 || (md->ctypes[*eptr++] & ctype_space) == 0) - RRETURN(MATCH_NOMATCH); - /* 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 || - (*eptr < 128 && (md->ctypes[*eptr++] & ctype_word) != 0)) - RRETURN(MATCH_NOMATCH); - while (eptr < md->end_subject && (*eptr & 0xc0) == 0x80) eptr++; - } - break; - - case OP_WORDCHAR: - for (i = 1; i <= min; i++) - { - if (eptr >= md->end_subject || - *eptr >= 128 || (md->ctypes[*eptr++] & ctype_word) == 0) - RRETURN(MATCH_NOMATCH); - /* 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_UTF8 */ - - /* Code for the non-UTF-8 case for minimum matching of operators other - than OP_PROP and OP_NOTPROP. */ - - switch(ctype) - { - case OP_ANY: - if ((ims & PCRE_DOTALL) == 0) - { - for (i = 1; i <= min; i++) - { - if (eptr <= md->end_subject - md->nllen && IS_NEWLINE(eptr)) - RRETURN(MATCH_NOMATCH); - eptr++; - } - } - else eptr += min; - break; - - case OP_ANYBYTE: - eptr += min; - break; - - case OP_NOT_DIGIT: - for (i = 1; i <= min; i++) - if ((md->ctypes[*eptr++] & ctype_digit) != 0) RRETURN(MATCH_NOMATCH); - break; - - case OP_DIGIT: - for (i = 1; i <= min; i++) - if ((md->ctypes[*eptr++] & ctype_digit) == 0) RRETURN(MATCH_NOMATCH); - break; - - case OP_NOT_WHITESPACE: - for (i = 1; i <= min; i++) - if ((md->ctypes[*eptr++] & ctype_space) != 0) RRETURN(MATCH_NOMATCH); - break; - - case OP_WHITESPACE: - for (i = 1; i <= min; i++) - if ((md->ctypes[*eptr++] & ctype_space) == 0) RRETURN(MATCH_NOMATCH); - break; - - case OP_NOT_WORDCHAR: - for (i = 1; i <= min; i++) - if ((md->ctypes[*eptr++] & ctype_word) != 0) - RRETURN(MATCH_NOMATCH); - break; - - case OP_WORDCHAR: - for (i = 1; i <= min; i++) - if ((md->ctypes[*eptr++] & ctype_word) == 0) - RRETURN(MATCH_NOMATCH); - 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(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - if (fi >= max || eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); - GETCHARINC(c, eptr); - if (prop_fail_result) RRETURN(MATCH_NOMATCH); - } - break; - - case PT_LAMP: - for (fi = min;; fi++) - { - RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - if (fi >= max || eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); - GETCHARINC(c, eptr); - prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script); - if ((prop_chartype == ucp_Lu || - prop_chartype == ucp_Ll || - prop_chartype == ucp_Lt) == prop_fail_result) - RRETURN(MATCH_NOMATCH); - } - break; - - case PT_GC: - for (fi = min;; fi++) - { - RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - if (fi >= max || eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); - GETCHARINC(c, eptr); - prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script); - if ((prop_category == prop_value) == prop_fail_result) - RRETURN(MATCH_NOMATCH); - } - break; - - case PT_PC: - for (fi = min;; fi++) - { - RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - if (fi >= max || eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); - GETCHARINC(c, eptr); - prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script); - if ((prop_chartype == prop_value) == prop_fail_result) - RRETURN(MATCH_NOMATCH); - } - break; - - case PT_SC: - for (fi = min;; fi++) - { - RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - if (fi >= max || eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); - GETCHARINC(c, eptr); - prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script); - if ((prop_script == prop_value) == prop_fail_result) - RRETURN(MATCH_NOMATCH); - } - break; - - default: - RRETURN(PCRE_ERROR_INTERNAL); - break; - } - } - - /* 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(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - if (fi >= max || eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); - GETCHARINCTEST(c, eptr); - prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script); - if (prop_category == ucp_M) RRETURN(MATCH_NOMATCH); - while (eptr < md->end_subject) - { - int len = 1; - if (!utf8) c = *eptr; else - { - GETCHARLEN(c, eptr, len); - } - prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script); - if (prop_category != ucp_M) break; - eptr += len; - } - } - } - - else -#endif /* SUPPORT_UCP */ - -#ifdef SUPPORT_UTF8 - /* UTF-8 mode */ - if (utf8) - { - for (fi = min;; fi++) - { - RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - if (fi >= max || eptr >= md->end_subject || - (ctype == OP_ANY && (ims & PCRE_DOTALL) == 0 && - eptr <= md->end_subject - md->nllen && IS_NEWLINE(eptr))) - RRETURN(MATCH_NOMATCH); - - GETCHARINC(c, eptr); - switch(ctype) - { - case OP_ANY: /* This is the DOTALL case */ - break; - - case OP_ANYBYTE: - 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-8 mode */ - { - for (fi = min;; fi++) - { - RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - if (fi >= max || eptr >= md->end_subject || - ((ims & PCRE_DOTALL) == 0 && - eptr <= md->end_subject - md->nllen && IS_NEWLINE(eptr))) - RRETURN(MATCH_NOMATCH); - - c = *eptr++; - switch(ctype) - { - case OP_ANY: /* This is the DOTALL case */ - break; - - case OP_ANYBYTE: - break; - - case OP_NOT_DIGIT: - if ((md->ctypes[c] & ctype_digit) != 0) RRETURN(MATCH_NOMATCH); - break; - - case OP_DIGIT: - if ((md->ctypes[c] & ctype_digit) == 0) RRETURN(MATCH_NOMATCH); - break; - - case OP_NOT_WHITESPACE: - if ((md->ctypes[c] & ctype_space) != 0) RRETURN(MATCH_NOMATCH); - break; - - case OP_WHITESPACE: - if ((md->ctypes[c] & ctype_space) == 0) RRETURN(MATCH_NOMATCH); - break; - - case OP_NOT_WORDCHAR: - if ((md->ctypes[c] & ctype_word) != 0) RRETURN(MATCH_NOMATCH); - break; - - case OP_WORDCHAR: - if ((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) break; - GETCHARLEN(c, eptr, len); - if (prop_fail_result) break; - eptr+= len; - } - break; - - case PT_LAMP: - for (i = min; i < max; i++) - { - int len = 1; - if (eptr >= md->end_subject) break; - GETCHARLEN(c, eptr, len); - prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script); - if ((prop_chartype == ucp_Lu || - prop_chartype == ucp_Ll || - prop_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) break; - GETCHARLEN(c, eptr, len); - prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script); - if ((prop_category == 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) break; - GETCHARLEN(c, eptr, len); - prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script); - if ((prop_chartype == 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) break; - GETCHARLEN(c, eptr, len); - prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script); - if ((prop_script == prop_value) == prop_fail_result) - break; - eptr+= len; - } - break; - } - - /* eptr is now past the end of the maximum run */ - - for(;;) - { - RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - if (eptr-- == pp) break; /* Stop if tried at original pos */ - 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++) - { - if (eptr >= md->end_subject) break; - GETCHARINCTEST(c, eptr); - prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script); - if (prop_category == ucp_M) break; - while (eptr < md->end_subject) - { - int len = 1; - if (!utf8) c = *eptr; else - { - GETCHARLEN(c, eptr, len); - } - prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script); - if (prop_category != ucp_M) break; - eptr += len; - } - } - - /* eptr is now past the end of the maximum run */ - - for(;;) - { - RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - if (eptr-- == pp) break; /* Stop if tried at original pos */ - for (;;) /* Move back over one extended */ - { - int len = 1; - BACKCHAR(eptr); - if (!utf8) c = *eptr; else - { - GETCHARLEN(c, eptr, len); - } - prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script); - if (prop_category != ucp_M) break; - eptr--; - } - } - } - - else -#endif /* SUPPORT_UCP */ - -#ifdef SUPPORT_UTF8 - /* UTF-8 mode */ - - if (utf8) - { - switch(ctype) - { - case OP_ANY: - - /* Special code is required for UTF8, but when the maximum is - unlimited we don't need it, so we repeat the non-UTF8 code. This is - probably worth it, because .* is quite a common idiom. */ - - if (max < INT_MAX) - { - if ((ims & PCRE_DOTALL) == 0) - { - for (i = min; i < max; i++) - { - if (eptr >= md->end_subject || - (eptr <= md->end_subject - md->nllen && IS_NEWLINE(eptr))) - break; - eptr++; - while (eptr < md->end_subject && (*eptr & 0xc0) == 0x80) eptr++; - } - } - else - { - for (i = min; i < max; i++) - { - if (eptr >= md->end_subject) break; - eptr++; - while (eptr < md->end_subject && (*eptr & 0xc0) == 0x80) eptr++; - } - } - } - - /* Handle unlimited UTF-8 repeat */ - - else - { - if ((ims & PCRE_DOTALL) == 0) - { - for (i = min; i < max; i++) - { - if (eptr >= md->end_subject || - (eptr <= md->end_subject - md->nllen && IS_NEWLINE(eptr))) - break; - eptr++; - } - break; - } - else - { - c = max - min; - if (c > md->end_subject - eptr) c = md->end_subject - eptr; - eptr += c; - } - } - break; - - /* The byte case is the same as non-UTF8 */ - - case OP_ANYBYTE: - c = max - min; - if (c > md->end_subject - eptr) c = md->end_subject - eptr; - eptr += c; - break; - - case OP_NOT_DIGIT: - for (i = min; i < max; i++) - { - int len = 1; - if (eptr >= md->end_subject) 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) 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) 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) 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) 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) 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 */ - - for(;;) - { - RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - if (eptr-- == pp) break; /* Stop if tried at original pos */ - BACKCHAR(eptr); - } - } - else -#endif - - /* Not UTF-8 mode */ - { - switch(ctype) - { - case OP_ANY: - if ((ims & PCRE_DOTALL) == 0) - { - for (i = min; i < max; i++) - { - if (eptr >= md->end_subject || - (eptr <= md->end_subject - md->nllen && IS_NEWLINE(eptr))) - break; - eptr++; - } - break; - } - /* For DOTALL case, fall through and treat as \C */ - - case OP_ANYBYTE: - c = max - min; - if (c > md->end_subject - eptr) c = md->end_subject - eptr; - eptr += c; - break; - - case OP_NOT_DIGIT: - for (i = min; i < max; i++) - { - if (eptr >= md->end_subject || (md->ctypes[*eptr] & ctype_digit) != 0) - break; - eptr++; - } - break; - - case OP_DIGIT: - for (i = min; i < max; i++) - { - if (eptr >= md->end_subject || (md->ctypes[*eptr] & ctype_digit) == 0) - break; - eptr++; - } - break; - - case OP_NOT_WHITESPACE: - for (i = min; i < max; i++) - { - if (eptr >= md->end_subject || (md->ctypes[*eptr] & ctype_space) != 0) - break; - eptr++; - } - break; - - case OP_WHITESPACE: - for (i = min; i < max; i++) - { - if (eptr >= md->end_subject || (md->ctypes[*eptr] & ctype_space) == 0) - break; - eptr++; - } - break; - - case OP_NOT_WORDCHAR: - for (i = min; i < max; i++) - { - if (eptr >= md->end_subject || (md->ctypes[*eptr] & ctype_word) != 0) - break; - eptr++; - } - break; - - case OP_WORDCHAR: - for (i = min; i < max; i++) - { - if (eptr >= md->end_subject || (md->ctypes[*eptr] & ctype_word) == 0) - break; - eptr++; - } - break; - - default: - RRETURN(PCRE_ERROR_INTERNAL); - } - - /* eptr is now past the end of the maximum run */ - - while (eptr >= pp) - { - RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); - eptr--; - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - } - } - - /* 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. Since all codes > OP_BRA are - for capturing brackets, and there shouldn't be any gaps between 0 and - OP_BRA, 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_NODE); - } - - /* 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 */ -} - - -/*************************************************************************** -**************************************************************************** - RECURSION IN THE match() FUNCTION - -Undefine all the macros that were defined above to handle this. */ - -#ifdef NO_RECURSE -#undef eptr -#undef ecode -#undef offset_top -#undef ims -#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 minimize -#undef prev_is_word - -#undef original_ims - -#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 - -/*************************************************************************** -***************************************************************************/ - - - -/************************************************* -* 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 -*/ - -PCRE_DATA_SCOPE int -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) -{ -int rc, resetcount, ocount; -int first_byte = -1; -int req_byte = -1; -int req_byte2 = -1; -int newline; -unsigned long int ims; -BOOL using_temporary_offsets = FALSE; -BOOL anchored; -BOOL startline; -BOOL firstline; -BOOL first_byte_caseless = FALSE; -BOOL req_byte_caseless = FALSE; -match_data match_block; -match_data *md = &match_block; -const uschar *tables; -const uschar *start_bits = NULL; -USPTR start_match = (USPTR)subject + start_offset; -USPTR end_subject; -USPTR req_byte_ptr = start_match - 1; - -pcre_study_data internal_study; -const pcre_study_data *study; - -real_pcre internal_re; -const real_pcre *external_re = (const real_pcre *)argument_re; -const real_pcre *re = external_re; - -/* 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; - -/* 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 = external_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 = _pcre_default_tables; - -/* Check that the first field in the block is the magic number. If it is not, -test for a regex that was compiled on a host of opposite endianness. If this is -the case, flipped values are put in internal_re and internal_study if there was -study data too. */ - -if (re->magic_number != MAGIC_NUMBER) - { - re = _pcre_try_flipped(re, &internal_re, study, &internal_study); - if (re == NULL) return PCRE_ERROR_BADMAGIC; - if (study != NULL) study = &internal_study; - } - -/* Set up other data */ - -anchored = ((re->options | options) & PCRE_ANCHORED) != 0; -startline = (re->options & 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 uschar *)external_re + re->name_table_offset + - re->name_count * re->name_entry_size; - -md->start_subject = (USPTR)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->utf8 = (re->options & PCRE_UTF8) != 0; - -md->notbol = (options & PCRE_NOTBOL) != 0; -md->noteol = (options & PCRE_NOTEOL) != 0; -md->notempty = (options & PCRE_NOTEMPTY) != 0; -md->partial = (options & PCRE_PARTIAL) != 0; -md->hitend = FALSE; - -md->recursive = NULL; /* No recursion at top level */ - -md->lcc = tables + lcc_offset; -md->ctypes = tables + ctypes_offset; - -/* Handle different types of newline. The two bits give four cases. If nothing -is set at run time, whatever was used at compile time applies. */ - -switch ((((options & PCRE_NEWLINE_CRLF) == 0)? re->options : options) & - PCRE_NEWLINE_CRLF) - { - default: newline = NEWLINE; break; /* Compile-time default */ - case PCRE_NEWLINE_CR: newline = '\r'; break; - case PCRE_NEWLINE_LF: newline = '\n'; break; - case PCRE_NEWLINE_CR+ - PCRE_NEWLINE_LF: newline = ('\r' << 8) | '\n'; break; - } - -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 is supported only for a restricted set of regexes at the -moment. */ - -if (md->partial && (re->options & PCRE_NOPARTIAL) != 0) - return PCRE_ERROR_BADPARTIAL; - -/* Check a UTF-8 string if required. Unfortunately there's no way of passing -back the character offset. */ - -#ifdef SUPPORT_UTF8 -if (md->utf8 && (options & PCRE_NO_UTF8_CHECK) == 0) - { - if (_pcre_valid_utf8((uschar *)subject, length) >= 0) - return PCRE_ERROR_BADUTF8; - if (start_offset > 0 && start_offset < length) - { - int tb = ((uschar *)subject)[start_offset]; - if (tb > 127) - { - tb &= 0xc0; - if (tb != 0 && tb != 0xc0) return PCRE_ERROR_BADUTF8_OFFSET; - } - } - } -#endif - -/* The ims options can vary during the matching as a result of the presence -of (?ims) items in the pattern. They are kept in a local variable so that -restoring at the exit of a group is easy. */ - -ims = re->options & (PCRE_CASELESS|PCRE_MULTILINE|PCRE_DOTALL); - -/* 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); - -if (re->top_backref > 0 && re->top_backref >= ocount/3) - { - ocount = re->top_backref * 3 + 3; - md->offset_vector = (int *)(pcre_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; - -/* Compute the minimum number of offsets that we need to reset each time. Doing -this makes a huge difference to execution time when there aren't many brackets -in the pattern. */ - -resetcount = 2 + re->top_bracket * 2; -if (resetcount > offsetcount) resetcount = ocount; - -/* 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. */ - -if (md->offset_vector != NULL) - { - register int *iptr = md->offset_vector + ocount; - register int *iend = iptr - resetcount/2 + 1; - while (--iptr >= iend) *iptr = -1; - } - -/* Set up the first character to match, if available. The first_byte 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->options & PCRE_FIRSTSET) != 0) - { - first_byte = re->first_byte & 255; - if ((first_byte_caseless = ((re->first_byte & REQ_CASELESS) != 0)) == TRUE) - first_byte = md->lcc[first_byte]; - } - else - if (!startline && study != NULL && - (study->options & 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->options & PCRE_REQCHSET) != 0) - { - req_byte = re->req_byte & 255; - req_byte_caseless = (re->req_byte & REQ_CASELESS) != 0; - req_byte2 = (tables + fcc_offset)[req_byte]; /* case flipped */ - } - -/* Loop for handling unanchored repeated matching attempts; for anchored regexs -the loop runs just once. */ - -do - { - USPTR save_end_subject = end_subject; - - /* Reset the maximum number of extractions we might see. */ - - if (md->offset_vector != NULL) - { - register int *iptr = md->offset_vector; - register int *iend = iptr + resetcount; - while (iptr < iend) *iptr++ = -1; - } - - /* Advance to a unique first char if possible. If firstline is TRUE, the - start of the match is constrained to the first line of a multiline string. - 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) - { - USPTR t = start_match; - while (t <= save_end_subject - md->nllen && !IS_NEWLINE(t)) t++; - end_subject = t; - } - - /* Now test for a unique first byte */ - - if (first_byte >= 0) - { - if (first_byte_caseless) - while (start_match < end_subject && - md->lcc[*start_match] != first_byte) - start_match++; - else - while (start_match < end_subject && *start_match != first_byte) - start_match++; - } - - /* Or to just after a linebreak for a multiline match if possible */ - - else if (startline) - { - if (start_match >= md->start_subject + md->nllen + - start_offset) - { - while (start_match <= end_subject && - !IS_NEWLINE(start_match - md->nllen)) - start_match++; - } - } - - /* Or to a non-unique first char after study */ - - else if (start_bits != NULL) - { - while (start_match < end_subject) - { - register unsigned int c = *start_match; - if ((start_bits[c/8] & (1 << (c&7))) == 0) start_match++; else break; - } - } - - /* Restore fudged end_subject */ - - end_subject = save_end_subject; - -#ifdef DEBUG /* Sigh. Some compilers never learn. */ - printf(">>>> Match against: "); - pchars(start_match, end_subject - start_match, TRUE, md); - printf("\n"); -#endif - - /* If req_byte is set, we know that that character must appear in the subject - for the match to succeed. If the first character is set, req_byte 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 /^C/ on a 32-megabyte string... so we - don't do this when the string is sufficiently long. - - ALSO: this processing is disabled when partial matching is requested. - */ - - if (req_byte >= 0 && - end_subject - start_match < REQ_BYTE_MAX && - !md->partial) - { - register USPTR p = start_match + ((first_byte >= 0)? 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_byte_ptr) - { - if (req_byte_caseless) - { - while (p < end_subject) - { - register int pp = *p++; - if (pp == req_byte || pp == req_byte2) { p--; break; } - } - } - else - { - while (p < end_subject) - { - if (*p++ == req_byte) { p--; break; } - } - } - - /* If we can't find the required character, break the matching loop */ - - if (p >= end_subject) 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_byte_ptr = p; - } - } - - /* When a match occurs, substrings will be set for all internal extractions; - we just need to set up the whole thing as substring 0 before returning. If - there were too many extractions, set the return code to zero. In the case - where we had to get some local store to hold offsets for backreferences, copy - those back references that we can. In this case there need not be overflow - if certain parts of the pattern were not used. */ - - md->start_match = start_match; - md->match_call_count = 0; - - rc = match(start_match, md->start_code, 2, md, ims, NULL, match_isgroup, 0); - - /* When the result is no match, if the subject's first character was a - newline and the PCRE_FIRSTLINE option is set, break (which will return - PCRE_ERROR_NOMATCH). The option requests that a match occur before the first - newline in the subject. Otherwise, advance the pointer to the next character - and continue - but the continuation will actually happen only when the - pattern is not anchored. */ - - if (rc == MATCH_NOMATCH) - { - if (firstline && - start_match <= md->end_subject - md->nllen && - IS_NEWLINE(start_match)) - break; - start_match++; -#ifdef SUPPORT_UTF8 - if (md->utf8) - while(start_match < end_subject && (*start_match & 0xc0) == 0x80) - start_match++; -#endif - continue; - } - - if (rc != MATCH_MATCH) - { - DPRINTF((">>>> error: returning %d\n", rc)); - return rc; - } - - /* We have a match! Copy the offset information from temporary store if - necessary */ - - if (using_temporary_offsets) - { - if (offsetcount >= 4) - { - memcpy(offsets + 2, md->offset_vector + 2, - (offsetcount - 2) * sizeof(int)); - DPRINTF(("Copied offsets from temporary memory\n")); - } - if (md->end_offset_top > offsetcount) - md->offset_overflow = TRUE; - - DPRINTF(("Freeing temporary memory\n")); - (pcre_free)(md->offset_vector); - } - - rc = md->offset_overflow? 0 : md->end_offset_top/2; - - if (offsetcount < 2) rc = 0; else - { - offsets[0] = start_match - md->start_subject; - offsets[1] = md->end_match_ptr - md->start_subject; - } - - DPRINTF((">>>> returning %d\n", rc)); - return rc; - } - -/* This "while" is the end of the "do" above */ - -while (!anchored && start_match <= end_subject); - -if (using_temporary_offsets) - { - DPRINTF(("Freeing temporary memory\n")); - (pcre_free)(md->offset_vector); - } - -if (md->partial && md->hitend) - { - DPRINTF((">>>> returning PCRE_ERROR_PARTIAL\n")); - return PCRE_ERROR_PARTIAL; - } -else - { - DPRINTF((">>>> returning PCRE_ERROR_NOMATCH\n")); - return PCRE_ERROR_NOMATCH; - } -} - -/* End of pcre_exec.c */ diff --git a/ext/pcre/pcrelib/pcre_fullinfo.c b/ext/pcre/pcrelib/pcre_fullinfo.c deleted file mode 100644 index 4a8edc6f47..0000000000 --- a/ext/pcre/pcrelib/pcre_fullinfo.c +++ /dev/null @@ -1,149 +0,0 @@ -/************************************************* -* 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) 1997-2006 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 "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 -*/ - -PCRE_DATA_SCOPE int -pcre_fullinfo(const pcre *argument_re, const pcre_extra *extra_data, int what, - void *where) -{ -real_pcre internal_re; -pcre_study_data internal_study; -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; - -if (re->magic_number != MAGIC_NUMBER) - { - re = _pcre_try_flipped(re, &internal_re, study, &internal_study); - if (re == NULL) return PCRE_ERROR_BADMAGIC; - if (study != NULL) study = &internal_study; - } - -switch (what) - { - case PCRE_INFO_OPTIONS: - *((unsigned long int *)where) = re->options & PUBLIC_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_CAPTURECOUNT: - *((int *)where) = re->top_bracket; - break; - - case PCRE_INFO_BACKREFMAX: - *((int *)where) = re->top_backref; - break; - - case PCRE_INFO_FIRSTBYTE: - *((int *)where) = - ((re->options & PCRE_FIRSTSET) != 0)? re->first_byte : - ((re->options & 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 uschar **)where) = - (study != NULL && (study->options & PCRE_STUDY_MAPPED) != 0)? - ((const pcre_study_data *)extra_data->study_data)->start_bits : NULL; - break; - - case PCRE_INFO_LASTLITERAL: - *((int *)where) = - ((re->options & PCRE_REQCHSET) != 0)? re->req_byte : -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 uschar **)where) = (const uschar *)re + re->name_table_offset; - break; - - case PCRE_INFO_DEFAULT_TABLES: - *((const uschar **)where) = (const uschar *)(_pcre_default_tables); - 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 deleted file mode 100644 index 0588c61a7f..0000000000 --- a/ext/pcre/pcrelib/pcre_get.c +++ /dev/null @@ -1,462 +0,0 @@ -/************************************************* -* 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) 1997-2006 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 "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 -*/ - -int -pcre_get_stringnumber(const pcre *code, const char *stringname) -{ -int rc; -int entrysize; -int top, bot; -uschar *nametable; - -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; - -bot = 0; -while (top > bot) - { - int mid = (top + bot) / 2; - uschar *entry = nametable + entrysize*mid; - int c = strcmp(stringname, (char *)(entry + 2)); - if (c == 0) return (entry[0] << 8) + entry[1]; - 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 -*/ - -int -pcre_get_stringtable_entries(const pcre *code, const char *stringname, - char **firstptr, char **lastptr) -{ -int rc; -int entrysize; -int top, bot; -uschar *nametable, *lastentry; - -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; - -lastentry = nametable + entrysize * (top - 1); -bot = 0; -while (top > bot) - { - int mid = (top + bot) / 2; - uschar *entry = nametable + entrysize*mid; - int c = strcmp(stringname, (char *)(entry + 2)); - if (c == 0) - { - uschar *first = entry; - uschar *last = entry; - while (first > nametable) - { - if (strcmp(stringname, (char *)(first - entrysize + 2)) != 0) break; - first -= entrysize; - } - while (last < lastentry) - { - if (strcmp(stringname, (char *)(last + entrysize + 2)) != 0) break; - last += entrysize; - } - *firstptr = (char *)first; - *lastptr = (char *)last; - 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 -*/ - -static int -get_first_set(const pcre *code, const char *stringname, int *ovector) -{ -const real_pcre *re = (const real_pcre *)code; -int entrysize; -char *first, *last; -uschar *entry; -if ((re->options & (PCRE_DUPNAMES | PCRE_JCHANGED)) == 0) - return pcre_get_stringnumber(code, stringname); -entrysize = pcre_get_stringtable_entries(code, stringname, &first, &last); -if (entrysize <= 0) return entrysize; -for (entry = (uschar *)first; entry <= (uschar *)last; entry += entrysize) - { - int n = (entry[0] << 8) + entry[1]; - if (ovector[n*2] >= 0) return n; - } -return (first[0] << 8) + first[1]; -} - - - - -/************************************************* -* 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 -*/ - -int -pcre_copy_substring(const char *subject, int *ovector, int stringcount, - int stringnumber, char *buffer, int size) -{ -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], 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 -*/ - -int -pcre_copy_named_substring(const pcre *code, const char *subject, int *ovector, - int stringcount, const char *stringname, char *buffer, int size) -{ -int n = get_first_set(code, stringname, ovector); -if (n <= 0) return n; -return pcre_copy_substring(subject, ovector, stringcount, n, buffer, size); -} - - - -/************************************************* -* 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 -*/ - -int -pcre_get_substring_list(const char *subject, int *ovector, int stringcount, - const char ***listptr) -{ -int i; -int size = sizeof(char *); -int double_count = stringcount * 2; -char **stringlist; -char *p; - -for (i = 0; i < double_count; i += 2) - size += sizeof(char *) + ovector[i+1] - ovector[i] + 1; - -stringlist = (char **)(pcre_malloc)(size); -if (stringlist == NULL) return PCRE_ERROR_NOMEMORY; - -*listptr = (const char **)stringlist; -p = (char *)(stringlist + stringcount + 1); - -for (i = 0; i < double_count; i += 2) - { - int len = ovector[i+1] - ovector[i]; - memcpy(p, subject + ovector[i], 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 (pcre_free)() directly. - -Argument: the result of a previous pcre_get_substring_list() -Returns: nothing -*/ - -void -pcre_free_substring_list(const char **pointer) -{ -(pcre_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 -*/ - -int -pcre_get_substring(const char *subject, int *ovector, int stringcount, - int stringnumber, const char **stringptr) -{ -int yield; -char *substring; -if (stringnumber < 0 || stringnumber >= stringcount) - return PCRE_ERROR_NOSUBSTRING; -stringnumber *= 2; -yield = ovector[stringnumber+1] - ovector[stringnumber]; -substring = (char *)(pcre_malloc)(yield + 1); -if (substring == NULL) return PCRE_ERROR_NOMEMORY; -memcpy(substring, subject + ovector[stringnumber], yield); -substring[yield] = 0; -*stringptr = substring; -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 -*/ - -int -pcre_get_named_substring(const pcre *code, const char *subject, int *ovector, - int stringcount, const char *stringname, const char **stringptr) -{ -int n = get_first_set(code, stringname, ovector); -if (n <= 0) return n; -return pcre_get_substring(subject, ovector, stringcount, n, stringptr); - -} - - - - -/************************************************* -* 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 (pcre_free)() directly. - -Argument: the result of a previous pcre_get_substring() -Returns: nothing -*/ - -void -pcre_free_substring(const char *pointer) -{ -(pcre_free)((void *)pointer); -} - -/* End of pcre_get.c */ diff --git a/ext/pcre/pcrelib/pcre_globals.c b/ext/pcre/pcrelib/pcre_globals.c deleted file mode 100644 index f829acfb1b..0000000000 --- a/ext/pcre/pcrelib/pcre_globals.c +++ /dev/null @@ -1,69 +0,0 @@ -/************************************************* -* 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) 1997-2006 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. However, when compiling for Virtual Pascal, things are done -differently, and global variables are not used (see pcre.in). */ - - -#include "pcre_internal.h" - - -#ifndef VPCOMPAT -#ifdef __cplusplus -extern "C" void *(*pcre_malloc)(size_t) = malloc; -extern "C" void (*pcre_free)(void *) = free; -extern "C" void *(*pcre_stack_malloc)(size_t) = malloc; -extern "C" void (*pcre_stack_free)(void *) = free; -extern "C" int (*pcre_callout)(pcre_callout_block *) = NULL; -#else -void *(*pcre_malloc)(size_t) = malloc; -void (*pcre_free)(void *) = free; -void *(*pcre_stack_malloc)(size_t) = malloc; -void (*pcre_stack_free)(void *) = free; -int (*pcre_callout)(pcre_callout_block *) = NULL; -#endif -#endif - -/* End of pcre_globals.c */ diff --git a/ext/pcre/pcrelib/pcre_info.c b/ext/pcre/pcrelib/pcre_info.c deleted file mode 100644 index b318b93eaa..0000000000 --- a/ext/pcre/pcrelib/pcre_info.c +++ /dev/null @@ -1,89 +0,0 @@ -/************************************************* -* 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) 1997-2006 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_info(), which gives some -information about a compiled pattern. However, use of this function is now -deprecated, as it has been superseded by pcre_fullinfo(). */ - - -#include "pcre_internal.h" - - -/************************************************* -* (Obsolete) Return info about compiled pattern * -*************************************************/ - -/* This is the original "info" function. It picks potentially useful data out -of the private structure, but its interface was too rigid. It remains for -backwards compatibility. The public options are passed back in an int - though -the re->options field has been expanded to a long int, all the public options -at the low end of it, and so even on 16-bit systems this will still be OK. -Therefore, I haven't changed the API for pcre_info(). - -Arguments: - argument_re points to compiled code - optptr where to pass back the options - first_byte where to pass back the first character, - or -1 if multiline and all branches start ^, - or -2 otherwise - -Returns: number of capturing subpatterns - or negative values on error -*/ - -PCRE_DATA_SCOPE int -pcre_info(const pcre *argument_re, int *optptr, int *first_byte) -{ -real_pcre internal_re; -const real_pcre *re = (const real_pcre *)argument_re; -if (re == NULL) return PCRE_ERROR_NULL; -if (re->magic_number != MAGIC_NUMBER) - { - re = _pcre_try_flipped(re, &internal_re, NULL, NULL); - if (re == NULL) return PCRE_ERROR_BADMAGIC; - } -if (optptr != NULL) *optptr = (int)(re->options & PUBLIC_OPTIONS); -if (first_byte != NULL) - *first_byte = ((re->options & PCRE_FIRSTSET) != 0)? re->first_byte : - ((re->options & PCRE_STARTLINE) != 0)? -1 : -2; -return re->top_bracket; -} - -/* End of pcre_info.c */ diff --git a/ext/pcre/pcrelib/pcre_internal.h b/ext/pcre/pcrelib/pcre_internal.h deleted file mode 100644 index 6f91020f90..0000000000 --- a/ext/pcre/pcrelib/pcre_internal.h +++ /dev/null @@ -1,954 +0,0 @@ -/************************************************* -* 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) 1997-2006 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_". */ - -#ifndef PCRE_INTERNAL_H -#define PCRE_INTERNAL_H - -/* Define DEBUG to get debugging output on stdout. */ - -#if 0 -#define DEBUG -#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... */ - -#ifdef DEBUG -#define DPRINTF(p) printf p -#else -#define DPRINTF(p) /*nothing*/ -#endif - - -/* Get the definitions provided by running "configure" */ - -#ifdef PHP_WIN32 -# include "config.w32.h" -#else -# include <php_config.h> -#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 <setjmp.h> -#include <stdarg.h> -#include <stddef.h> -#include <stdio.h> -#include <stdlib.h> -#include <string.h> - -#ifndef PCRE_SPY -#define PCRE_DEFINITION /* Win32 __declspec(export) trigger for .dll */ -#endif - -/* We need to have types that specify unsigned 16-bit 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. */ - -#if USHRT_MAX == 65535 - typedef unsigned short pcre_uint16; -#elif UINT_MAX == 65535 - typedef unsigned int pcre_uint16; -#else - #error Cannot determine a type for 16-bit unsigned integers -#endif - -#if UINT_MAX == 4294967295 - typedef unsigned int pcre_uint32; -#elif ULONG_MAX == 4294967295 - typedef unsigned long int pcre_uint32; -#else - #error Cannot determine a type for 32-bit unsigned integers -#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 *, because that -should make things easier for callers. We define a short type for unsigned char -to save lots of typing. I tried "uchar", but it causes problems on Digital -Unix, where it is defined in sys/types, so use "uschar" instead. */ - -typedef unsigned char uschar; - -/* PCRE is able to support 3 different kinds of newline (CR, LF, CRLF). The -following macro is used to package up testing for newlines. NLBLOCK is defined -in the various modules to indicate in which datablock the parameters exist. */ - -#define IS_NEWLINE(p) \ - ((p)[0] == NLBLOCK->nl[0] && \ - (NLBLOCK->nllen == 1 || (p)[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_SPTR CUSTOM_SUBJECT_PTR -#define USPTR CUSTOM_SUBJECT_PTR -#else -#define PCRE_SPTR const char * -#define USPTR const unsigned char * -#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 strncmp(s1,s2,m) _strncmp(s1,s2,m) -#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). This assumes -that all calls to memmove are moving strings upwards in store, which is the -case in PCRE. */ - -#if ! HAVE_MEMMOVE -#undef memmove /* some systems may have a macro */ -#if HAVE_BCOPY -#define memmove(a, b, c) bcopy(b, a, c) -#else /* HAVE_BCOPY */ -static void * -pcre_memmove(unsigned char *dest, const unsigned char *src, size_t n) -{ -size_t i; -dest += n; -src += n; -for (i = 0; i < n; ++i) *(--dest) = *(--src); -return dest; -} -#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. */ - -#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]) - -#define MAX_PATTERN_SIZE (1 << 30) /* Keep it positive */ - - -#else -#error LINK_SIZE must be either 2, 3, or 4 -#endif - - -/* 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. */ - -#define PUT2(a,n,d) \ - a[n] = (d) >> 8; \ - a[(n)+1] = (d) & 255 - -#define GET2(a,n) \ - (((a)[n] << 8) | (a)[(n)+1]) - -#define PUT2INC(a,n,d) PUT2(a,n,d), a += 2 - - -/* When UTF-8 encoding is being used, a character is no longer just a single -byte. The macros for character handling generate simple sequences when used in -byte-mode, and more complicated ones for UTF-8 characters. */ - -#ifndef SUPPORT_UTF8 -#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 BACKCHAR(eptr) - -#else /* SUPPORT_UTF8 */ - -/* 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) == 0xc0) \ - { \ - int gcii; \ - int gcaa = _pcre_utf8_table4[c & 0x3f]; /* Number of additional bytes */ \ - int gcss = 6*gcaa; \ - c = (c & _pcre_utf8_table3[gcaa]) << gcss; \ - for (gcii = 1; gcii <= gcaa; gcii++) \ - { \ - gcss -= 6; \ - c |= (eptr[gcii] & 0x3f) << gcss; \ - } \ - } - -/* Get the next UTF-8 character, testing for UTF-8 mode, and not advancing the -pointer. */ - -#define GETCHARTEST(c, eptr) \ - c = *eptr; \ - if (utf8 && (c & 0xc0) == 0xc0) \ - { \ - int gcii; \ - int gcaa = _pcre_utf8_table4[c & 0x3f]; /* Number of additional bytes */ \ - int gcss = 6*gcaa; \ - c = (c & _pcre_utf8_table3[gcaa]) << gcss; \ - for (gcii = 1; gcii <= gcaa; gcii++) \ - { \ - gcss -= 6; \ - c |= (eptr[gcii] & 0x3f) << gcss; \ - } \ - } - -/* 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) == 0xc0) \ - { \ - int gcaa = _pcre_utf8_table4[c & 0x3f]; /* Number of additional bytes */ \ - int gcss = 6*gcaa; \ - c = (c & _pcre_utf8_table3[gcaa]) << gcss; \ - while (gcaa-- > 0) \ - { \ - gcss -= 6; \ - c |= (*eptr++ & 0x3f) << gcss; \ - } \ - } - -/* Get the next character, testing for UTF-8 mode, and advancing the pointer */ - -#define GETCHARINCTEST(c, eptr) \ - c = *eptr++; \ - if (utf8 && (c & 0xc0) == 0xc0) \ - { \ - int gcaa = _pcre_utf8_table4[c & 0x3f]; /* Number of additional bytes */ \ - int gcss = 6*gcaa; \ - c = (c & _pcre_utf8_table3[gcaa]) << gcss; \ - while (gcaa-- > 0) \ - { \ - gcss -= 6; \ - c |= (*eptr++ & 0x3f) << gcss; \ - } \ - } - -/* 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) == 0xc0) \ - { \ - int gcii; \ - int gcaa = _pcre_utf8_table4[c & 0x3f]; /* Number of additional bytes */ \ - int gcss = 6*gcaa; \ - c = (c & _pcre_utf8_table3[gcaa]) << gcss; \ - for (gcii = 1; gcii <= gcaa; gcii++) \ - { \ - gcss -= 6; \ - c |= (eptr[gcii] & 0x3f) << gcss; \ - } \ - len += gcaa; \ - } - -/* If the pointer is not at the start of a character, move it back until -it is. Called only in UTF-8 mode. */ - -#define BACKCHAR(eptr) while((*eptr & 0xc0) == 0x80) eptr--; - -#endif - - -/* 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 - - -/* These are the public options that can change during matching. */ - -#define PCRE_IMS (PCRE_CASELESS|PCRE_MULTILINE|PCRE_DOTALL) - -/* Private options flags start at the most significant end of the four bytes. -The public options defined in pcre.h start at the least significant end. Make -sure they don't overlap! The bits are getting a bit scarce now -- when we run -out, there is a dummy word in the structure that could be used for the private -bits. */ - -#define PCRE_NOPARTIAL 0x80000000 /* can't use partial with this regex */ -#define PCRE_FIRSTSET 0x40000000 /* first_byte is set */ -#define PCRE_REQCHSET 0x20000000 /* req_byte is set */ -#define PCRE_STARTLINE 0x10000000 /* start after \n for multiline */ -#define PCRE_JCHANGED 0x08000000 /* j option changes within regex */ - -/* Options for the "extra" block produced by pcre_study(). */ - -#define PCRE_STUDY_MAPPED 0x01 /* a map of starting chars exists */ - -/* Masks for identifying the public options that are permitted at compile -time, run time, or study time, respectively. */ - -#define PUBLIC_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_CR|PCRE_NEWLINE_LF) - -#define PUBLIC_EXEC_OPTIONS \ - (PCRE_ANCHORED|PCRE_NOTBOL|PCRE_NOTEOL|PCRE_NOTEMPTY|PCRE_NO_UTF8_CHECK| \ - PCRE_PARTIAL|PCRE_NEWLINE_CR|PCRE_NEWLINE_LF) - -#define PUBLIC_DFA_EXEC_OPTIONS \ - (PCRE_ANCHORED|PCRE_NOTBOL|PCRE_NOTEOL|PCRE_NOTEMPTY|PCRE_NO_UTF8_CHECK| \ - PCRE_PARTIAL|PCRE_DFA_SHORTEST|PCRE_DFA_RESTART|PCRE_NEWLINE_CR| \ - PCRE_NEWLINE_LF) - -#define PUBLIC_STUDY_OPTIONS 0 /* None defined */ - -/* Magic number to provide a small check against being handed junk. Also used -to detect whether a pattern was compiled on a host of different endianness. */ - -#define MAGIC_NUMBER 0x50435245UL /* 'PCRE' */ - -/* 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 - -/* Flags added to firstbyte or reqbyte; a "non-literal" item is either a -variable-length repeat, or a anything other than literal characters. */ - -#define REQ_CASELESS 0x0100 /* indicates caselessness */ -#define REQ_VARY 0x0200 /* reqbyte followed non-literal item */ - -/* Miscellaneous definitions */ - -typedef int BOOL; - -#define FALSE 0 -#define TRUE 1 - -/* Escape items that are just an encoding of a particular data value. Note that -ESC_n is defined as yet another macro, which is set in config.h to either \n -(the default) or \r (which some people want). */ - -#ifndef ESC_e -#define ESC_e 27 -#endif - -#ifndef ESC_f -#define ESC_f '\f' -#endif - -#ifndef ESC_n -#define ESC_n NEWLINE -#endif - -#ifndef ESC_r -#define ESC_r '\r' -#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 '\t' -#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 /* General characteristic (e.g. L) */ -#define PT_PC 3 /* Particular characteristic (e.g. Lu) */ -#define PT_SC 4 /* Script (e.g. Han) */ - -/* Flag bits and data types for the extended class (OP_XCLASS) for classes that -contain UTF-8 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_ANY because it -corresponds to "." rather than an escape sequence. The final one must be -ESC_REF as subsequent values are used for \1, \2, \3, etc. There is 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_B, ESC_b, ESC_D, ESC_d, ESC_S, ESC_s, ESC_W, - ESC_w, ESC_dum1, ESC_C, ESC_P, ESC_p, ESC_X, ESC_Z, ESC_z, ESC_E, - ESC_Q, ESC_REF }; - -/* Opcode table: OP_BRA must be last, as all values >= it are used for brackets -that extract substrings. 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 that whenever this list is updated, the two macro definitions that follow -must also be updated to match. */ - -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_NOT_WORD_BOUNDARY, /* 3 \B */ - OP_WORD_BOUNDARY, /* 4 \b */ - OP_NOT_DIGIT, /* 5 \D */ - OP_DIGIT, /* 6 \d */ - OP_NOT_WHITESPACE, /* 7 \S */ - OP_WHITESPACE, /* 8 \s */ - OP_NOT_WORDCHAR, /* 9 \W */ - OP_WORDCHAR, /* 10 \w */ - OP_ANY, /* 11 Match any character */ - OP_ANYBYTE, /* 12 Match any byte (\C); different to OP_ANY for UTF-8 */ - OP_NOTPROP, /* 13 \P (not Unicode property) */ - OP_PROP, /* 14 \p (Unicode property) */ - OP_EXTUNI, /* 15 \X (extended Unicode sequence */ - OP_EODN, /* 16 End of data or \n at end of data: \Z. */ - OP_EOD, /* 17 End of data: \z */ - - OP_OPT, /* 18 Set runtime options */ - OP_CIRC, /* 19 Start of line - varies with multiline switch */ - OP_DOLL, /* 20 End of line - varies with multiline switch */ - OP_CHAR, /* 21 Match one character, casefully */ - OP_CHARNC, /* 22 Match one character, caselessly */ - OP_NOT, /* 23 Match one character, not the following one */ - - OP_STAR, /* 24 The maximizing and minimizing versions of */ - OP_MINSTAR, /* 25 all these opcodes must come in pairs, with */ - OP_PLUS, /* 26 the minimizing one second. */ - OP_MINPLUS, /* 27 This first set applies to single characters */ - OP_QUERY, /* 28 */ - OP_MINQUERY, /* 29 */ - OP_UPTO, /* 30 From 0 to n matches */ - OP_MINUPTO, /* 31 */ - OP_EXACT, /* 32 Exactly n matches */ - - OP_NOTSTAR, /* 33 The maximizing and minimizing versions of */ - OP_NOTMINSTAR, /* 34 all these opcodes must come in pairs, with */ - OP_NOTPLUS, /* 35 the minimizing one second. */ - OP_NOTMINPLUS, /* 36 This set applies to "not" single characters */ - OP_NOTQUERY, /* 37 */ - OP_NOTMINQUERY, /* 38 */ - OP_NOTUPTO, /* 39 From 0 to n matches */ - OP_NOTMINUPTO, /* 40 */ - OP_NOTEXACT, /* 41 Exactly n matches */ - - OP_TYPESTAR, /* 42 The maximizing and minimizing versions of */ - OP_TYPEMINSTAR, /* 43 all these opcodes must come in pairs, with */ - OP_TYPEPLUS, /* 44 the minimizing one second. These codes must */ - OP_TYPEMINPLUS, /* 45 be in exactly the same order as those above. */ - OP_TYPEQUERY, /* 46 This set applies to character types such as \d */ - OP_TYPEMINQUERY, /* 47 */ - OP_TYPEUPTO, /* 48 From 0 to n matches */ - OP_TYPEMINUPTO, /* 49 */ - OP_TYPEEXACT, /* 50 Exactly n matches */ - - OP_CRSTAR, /* 51 The maximizing and minimizing versions of */ - OP_CRMINSTAR, /* 52 all these opcodes must come in pairs, with */ - OP_CRPLUS, /* 53 the minimizing one second. These codes must */ - OP_CRMINPLUS, /* 54 be in exactly the same order as those above. */ - OP_CRQUERY, /* 55 These are for character classes and back refs */ - OP_CRMINQUERY, /* 56 */ - OP_CRRANGE, /* 57 These are different to the three sets above. */ - OP_CRMINRANGE, /* 58 */ - - OP_CLASS, /* 59 Match a character class, chars < 256 only */ - OP_NCLASS, /* 60 Same, but the bitmap was created from a negative - class - the difference is relevant only when a UTF-8 - character > 255 is encountered. */ - - OP_XCLASS, /* 61 Extended class for handling UTF-8 chars within the - class. This does both positive and negative. */ - - OP_REF, /* 62 Match a back reference */ - OP_RECURSE, /* 63 Match a numbered subpattern (possibly recursive) */ - OP_CALLOUT, /* 64 Call out to external function if provided */ - - OP_ALT, /* 65 Start of alternation */ - OP_KET, /* 66 End of group that doesn't have an unbounded repeat */ - OP_KETRMAX, /* 67 These two must remain together and in this */ - OP_KETRMIN, /* 68 order. They are for groups the repeat for ever. */ - - /* The assertions must come before ONCE and COND */ - - OP_ASSERT, /* 69 Positive lookahead */ - OP_ASSERT_NOT, /* 70 Negative lookahead */ - OP_ASSERTBACK, /* 71 Positive lookbehind */ - OP_ASSERTBACK_NOT, /* 72 Negative lookbehind */ - OP_REVERSE, /* 73 Move pointer back - used in lookbehind assertions */ - - /* ONCE and COND must come after the assertions, with ONCE first, as there's - a test for >= ONCE for a subpattern that isn't an assertion. */ - - OP_ONCE, /* 74 Once matched, don't back up into the subpattern */ - OP_COND, /* 75 Conditional group */ - OP_CREF, /* 76 Used to hold an extraction string number (cond ref) */ - - OP_BRAZERO, /* 77 These two must remain together and in this */ - OP_BRAMINZERO, /* 78 order. */ - - OP_BRANUMBER, /* 79 Used for extracting brackets whose number is greater - than can fit into an opcode. */ - - OP_BRA /* 80 This and greater values are used for brackets that - extract substrings up to EXTRACT_BASIC_MAX. After - that, use is made of OP_BRANUMBER. */ -}; - -/* WARNING WARNING WARNING: There is an implicit assumption in pcre.c and -study.c that all opcodes are less than 128 in value. This makes handling UTF-8 -character sequences easier. */ - -/* The highest extraction number before we have to start using additional -bytes. (Originally PCRE didn't have support for extraction counts highter than -this number.) The value is limited by the number of opcodes left after OP_BRA, -i.e. 255 - OP_BRA. We actually set it a bit lower to leave room for additional -opcodes. */ - -#define EXTRACT_BASIC_MAX 100 - - -/* This macro defines textual names for all the opcodes. These are used only -for debugging. The macro is referenced only in pcre_printint.c. */ - -#define OP_NAME_LIST \ - "End", "\\A", "\\G", "\\B", "\\b", "\\D", "\\d", \ - "\\S", "\\s", "\\W", "\\w", "Any", "Anybyte", \ - "notprop", "prop", "extuni", \ - "\\Z", "\\z", \ - "Opt", "^", "$", "char", "charnc", "not", \ - "*", "*?", "+", "+?", "?", "??", "{", "{", "{", \ - "*", "*?", "+", "+?", "?", "??", "{", "{", "{", \ - "*", "*?", "+", "+?", "?", "??", "{", "{", "{", \ - "*", "*?", "+", "+?", "?", "??", "{", "{", \ - "class", "nclass", "xclass", "Ref", "Recurse", "Callout", \ - "Alt", "Ket", "KetRmax", "KetRmin", "Assert", "Assert not", \ - "AssertB", "AssertB not", "Reverse", "Once", "Cond", "Cond ref",\ - "Brazero", "Braminzero", "Branumber", "Bra" - - -/* 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, 1, 1, 1, 1, 1, /* \A, \G, \B, \B, \D, \d, \S, \s, \W, \w */ \ - 1, 1, /* Any, Anybyte */ \ - 3, 3, 1, /* NOTPROP, PROP, EXTUNI */ \ - 1, 1, 2, 1, 1, /* \Z, \z, Opt, ^, $ */ \ - 2, /* Char - the minimum length */ \ - 2, /* Charnc - the minimum length */ \ - 2, /* not */ \ - /* Positive single-char repeats ** These are */ \ - 2, 2, 2, 2, 2, 2, /* *, *?, +, +?, ?, ?? ** minima in */ \ - 4, 4, 4, /* upto, minupto, exact ** UTF-8 mode */ \ - /* Negative single-char repeats - only for chars < 256 */ \ - 2, 2, 2, 2, 2, 2, /* NOT *, *?, +, +?, ?, ?? */ \ - 4, 4, 4, /* NOT upto, minupto, exact */ \ - /* Positive type repeats */ \ - 2, 2, 2, 2, 2, 2, /* Type *, *?, +, +?, ?, ?? */ \ - 4, 4, 4, /* Type upto, minupto, exact */ \ - /* Character class & ref repeats */ \ - 1, 1, 1, 1, 1, 1, /* *, *?, +, +?, ?, ?? */ \ - 5, 5, /* CRRANGE, CRMINRANGE */ \ - 33, /* CLASS */ \ - 33, /* NCLASS */ \ - 0, /* XCLASS - variable length */ \ - 3, /* REF */ \ - 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, /* Assert */ \ - 1+LINK_SIZE, /* Assert not */ \ - 1+LINK_SIZE, /* Assert behind */ \ - 1+LINK_SIZE, /* Assert behind not */ \ - 1+LINK_SIZE, /* Reverse */ \ - 1+LINK_SIZE, /* Once */ \ - 1+LINK_SIZE, /* COND */ \ - 3, /* CREF */ \ - 1, 1, /* BRAZERO, BRAMINZERO */ \ - 3, /* BRANUMBER */ \ - 1+LINK_SIZE /* BRA */ \ - - -/* A magic value for OP_CREF to indicate the "in recursion" condition. */ - -#define CREF_RECURSE 0xffff - -/* Error code numbers. They are given names so that they can more easily be -tracked. */ - -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 }; - -/* 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: -*/ - -typedef struct real_pcre { - pcre_uint32 magic_number; - pcre_uint32 size; /* Total that was malloced */ - pcre_uint32 options; - pcre_uint32 dummy1; /* For future use, maybe */ - - pcre_uint16 top_bracket; - pcre_uint16 top_backref; - pcre_uint16 first_byte; - pcre_uint16 req_byte; - 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 unsigned char *tables; /* Pointer to tables or NULL for std */ - const unsigned char *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 options; - uschar start_bits[32]; -} pcre_study_data; - -/* Structure for passing "static" information around between the functions -doing the compiling, so that they are thread-safe. */ - -typedef struct compile_data { - const uschar *lcc; /* Points to lower casing table */ - const uschar *fcc; /* Points to case-flipping table */ - const uschar *cbits; /* Points to character type table */ - const uschar *ctypes; /* Points to table of type maps */ - const uschar *start_code; /* The start of the compiled code */ - const uschar *start_pattern; /* The start of the pattern */ - uschar *name_table; /* The name/number table */ - int names_found; /* Number of entries so far */ - int name_entry_size; /* Size of each entry */ - int top_backref; /* Maximum back reference */ - unsigned int backref_map; /* Bitmap of low back refs */ - int req_varyopt; /* "After variable item" flag for reqbyte */ - BOOL nopartial; /* Set TRUE if partial won't work */ - int nllen; /* 1 or 2 for newline string length */ - uschar nl[4]; /* Newline string */ -} compile_data; - -/* Structure for maintaining a chain of pointers to the currently incomplete -branches, for testing for left recursion. */ - -typedef struct branch_chain { - struct branch_chain *outer; - uschar *current; -} branch_chain; - -/* Structure for items in a linked list that represents an explicit recursive -call within the pattern. */ - -typedef struct recursion_info { - struct recursion_info *prevrec; /* Previous recursion record (or NULL) */ - int group_num; /* Number of group that was called */ - const uschar *after_call; /* "Return value": points after the call in the expr */ - USPTR save_start; /* Old value of md->start_match */ - int *offset_save; /* Pointer to start of saved offsets */ - int saved_max; /* Number of saved offsets */ -} recursion_info; - -/* When compiling in a mode that doesn't use recursive calls to match(), -a structure is used to remember local variables on the heap. It is defined in -pcre_exec.c, close to the match() function, so that it is easy to keep it in -step with any changes of local variable. However, the pointer to the current -frame must be saved in some "static" place over a longjmp(). We declare the -structure here so that we can put a pointer in the match_data structure. NOTE: -This isn't used for a "normal" compilation of pcre. */ - -struct heapframe; - -/* 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 nllen; /* 1 or 2 for newline string length */ - uschar nl[4]; /* Newline string */ - const uschar *lcc; /* Points to lower casing table */ - const uschar *ctypes; /* Points to table of type maps */ - BOOL offset_overflow; /* Set if too many extractions */ - BOOL notbol; /* NOTBOL flag */ - BOOL noteol; /* NOTEOL flag */ - BOOL utf8; /* UTF8 flag */ - BOOL endonly; /* Dollar not before final \n */ - BOOL notempty; /* Empty string match not wanted */ - BOOL partial; /* PARTIAL flag */ - BOOL hitend; /* Hit the end of the subject at some point */ - const uschar *start_code; /* For use when recursing */ - USPTR start_subject; /* Start of the subject string */ - USPTR end_subject; /* End of the subject string */ - USPTR start_match; /* Start of this match attempt */ - USPTR end_match_ptr; /* Subject position at end match */ - int end_offset_top; /* Highwater mark at end of match */ - int capture_last; /* Most recent capture number */ - int start_offset; /* The start offset value */ - recursion_info *recursive; /* Linked list of recursion data */ - void *callout_data; /* To pass back to callouts */ - struct heapframe *thisframe; /* Used only when compiling for no recursion */ -} match_data; - -/* A similar structure is used for the same purpose by the DFA matching -functions. */ - -typedef struct dfa_match_data { - const uschar *start_code; /* Start of the compiled pattern */ - const uschar *start_subject; /* Start of the subject string */ - const uschar *end_subject; /* End of subject string */ - const uschar *tables; /* Character tables */ - int moptions; /* Match options */ - int poptions; /* Pattern options */ - int nllen; /* 1 or 2 for newline string length */ - uschar nl[4]; /* Newline string */ - void *callout_data; /* To pass back to callouts */ -} 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 /* alphameric 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) - -/* Layout of the UCP type table that translates property names into types and -codes. */ - -typedef struct { - const char *name; - 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. */ - -extern const int _pcre_utf8_table1[]; -extern const int _pcre_utf8_table2[]; -extern const int _pcre_utf8_table3[]; -extern const uschar _pcre_utf8_table4[]; - -extern const int _pcre_utf8_table1_size; - -extern const ucp_type_table _pcre_utt[]; -extern const int _pcre_utt_size; - -extern const uschar _pcre_default_tables[]; - -extern const uschar _pcre_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. */ - -extern int _pcre_ord2utf8(int, uschar *); -extern real_pcre * _pcre_try_flipped(const real_pcre *, real_pcre *, - const pcre_study_data *, pcre_study_data *); -extern int _pcre_ucp_findprop(const unsigned int, int *, int *); -extern int _pcre_ucp_othercase(const int); -extern int _pcre_valid_utf8(const uschar *, int); -extern BOOL _pcre_xclass(int, const uschar *); - -#endif - -/* End of pcre_internal.h */ diff --git a/ext/pcre/pcrelib/pcre_maketables.c b/ext/pcre/pcrelib/pcre_maketables.c deleted file mode 100644 index afe63d1b18..0000000000 --- a/ext/pcre/pcrelib/pcre_maketables.c +++ /dev/null @@ -1,140 +0,0 @@ -/************************************************* -* 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) 1997-2006 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 "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 pcre_malloc(), but when compiled -inside dftables, use malloc(). - -Arguments: none -Returns: pointer to the contiguous block of data -*/ - -const unsigned char * -pcre_maketables(void) -{ -unsigned char *yield, *p; -int i; - -#ifndef DFTABLES -yield = (unsigned char*)(pcre_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_ord2utf8.c b/ext/pcre/pcrelib/pcre_ord2utf8.c deleted file mode 100644 index fc4d6de812..0000000000 --- a/ext/pcre/pcrelib/pcre_ord2utf8.c +++ /dev/null @@ -1,78 +0,0 @@ -/************************************************* -* 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) 1997-2006 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 "pcre_internal.h" - - -/************************************************* -* Convert character value to UTF-8 * -*************************************************/ - -/* This function takes an integer value in the range 0 - 0x7fffffff -and encodes it as a UTF-8 character in 0 to 6 bytes. - -Arguments: - cvalue the character value - buffer pointer to buffer for result - at least 6 bytes long - -Returns: number of characters placed in the buffer -*/ - -int -_pcre_ord2utf8(int cvalue, uschar *buffer) -{ -register int i, j; -for (i = 0; i < _pcre_utf8_table1_size; i++) - if (cvalue <= _pcre_utf8_table1[i]) break; -buffer += i; -for (j = i; j > 0; j--) - { - *buffer-- = 0x80 | (cvalue & 0x3f); - cvalue >>= 6; - } -*buffer = _pcre_utf8_table2[i] | cvalue; -return i + 1; -} - -/* End of pcre_ord2utf8.c */ diff --git a/ext/pcre/pcrelib/pcre_printint.src b/ext/pcre/pcrelib/pcre_printint.src deleted file mode 100644 index e4de825a9b..0000000000 --- a/ext/pcre/pcrelib/pcre_printint.src +++ /dev/null @@ -1,460 +0,0 @@ -/************************************************* -* 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) 1997-2005 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 -(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. */ - - -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; - -if (!utf8 || (c & 0xc0) != 0xc0) - { - if (isprint(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; - } -} - - - -/************************************************* -* Find Unicode property name * -*************************************************/ - -static const char * -get_ucpname(int ptype, int pvalue) -{ -#ifdef SUPPORT_UCP -int i; -for (i = _pcre_utt_size; i >= 0; i--) - { - if (ptype == _pcre_utt[i].type && pvalue == _pcre_utt[i].value) break; - } -return (i >= 0)? _pcre_utt[i].name : "??"; -#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. */ - -static void -pcre_printint(pcre *external_re, FILE *f) -{ -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; - - fprintf(f, "%3d ", (int)(code - codestart)); - - if (*code >= OP_BRA) - { - if (*code - OP_BRA > EXTRACT_BASIC_MAX) - fprintf(f, "%3d Bra extra\n", GET(code, 1)); - else - fprintf(f, "%3d Bra %d\n", GET(code, 1), *code - OP_BRA); - code += _pcre_OP_lengths[OP_BRA]; - continue; - } - - switch(*code) - { - 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_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_REVERSE: - fprintf(f, "%3d %s", GET(code, 1), OP_names[*code]); - break; - - case OP_BRANUMBER: - printf("%3d %s", GET2(code, 1), OP_names[*code]); - break; - - case OP_CREF: - if (GET2(code, 1) == CREF_RECURSE) - fprintf(f, " Cond recurse"); - else - fprintf(f, "%3d %s", GET2(code,1), OP_names[*code]); - break; - - case OP_STAR: - case OP_MINSTAR: - case OP_PLUS: - case OP_MINPLUS: - case OP_QUERY: - case OP_MINQUERY: - case OP_TYPESTAR: - case OP_TYPEMINSTAR: - case OP_TYPEPLUS: - case OP_TYPEMINPLUS: - case OP_TYPEQUERY: - case OP_TYPEMINQUERY: - 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: - fprintf(f, " "); - extra = print_char(f, code+3, utf8); - fprintf(f, "{"); - if (*code != OP_EXACT) fprintf(f, ","); - fprintf(f, "%d}", GET2(code,1)); - if (*code == OP_MINUPTO) fprintf(f, "?"); - break; - - case OP_TYPEEXACT: - case OP_TYPEUPTO: - case OP_TYPEMINUPTO: - 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, "?"); - break; - - case OP_NOT: - if (isprint(c = code[1])) fprintf(f, " [^%c]", c); - else fprintf(f, " [^\\x%02x]", c); - break; - - case OP_NOTSTAR: - case OP_NOTMINSTAR: - case OP_NOTPLUS: - case OP_NOTMINPLUS: - case OP_NOTQUERY: - case OP_NOTMINQUERY: - if (isprint(c = code[1])) 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: - if (isprint(c = code[3])) 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, "?"); - break; - - case OP_RECURSE: - fprintf(f, "%3d %s", GET(code, 1), 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 (isprint(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 (isprint(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; - - /* 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 deleted file mode 100644 index e6965812ef..0000000000 --- a/ext/pcre/pcrelib/pcre_refcount.c +++ /dev/null @@ -1,77 +0,0 @@ -/************************************************* -* 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) 1997-2006 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 "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 -*/ - -PCRE_DATA_SCOPE int -pcre_refcount(pcre *argument_re, int adjust) -{ -real_pcre *re = (real_pcre *)argument_re; -if (re == NULL) return PCRE_ERROR_NULL; -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_scanner.cc b/ext/pcre/pcrelib/pcre_scanner.cc deleted file mode 100644 index 29e0d8400b..0000000000 --- a/ext/pcre/pcrelib/pcre_scanner.cc +++ /dev/null @@ -1,173 +0,0 @@ -// Copyright (c) 2005, Google Inc. -// All rights reserved. -// -// 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 Google Inc. 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. -// -// Author: Sanjay Ghemawat - -#include <vector> -#include <assert.h> -#include "config.h" -#include "pcre_scanner.h" - -using std::vector; - -namespace pcrecpp { - -Scanner::Scanner() - : data_(), - input_(data_), - skip_(NULL), - should_skip_(false), - save_comments_(false), - comments_(NULL), - comments_offset_(0) { -} - -Scanner::Scanner(const string& in) - : data_(in), - input_(data_), - skip_(NULL), - should_skip_(false), - save_comments_(false), - comments_(NULL), - comments_offset_(0) { -} - -Scanner::~Scanner() { - delete skip_; - delete comments_; -} - -void Scanner::Skip(const char* re) { - delete skip_; - if (re != NULL) { - skip_ = new RE(re); - should_skip_ = true; - ConsumeSkip(); - } else { - skip_ = NULL; - should_skip_ = false; - } -} - -void Scanner::DisableSkip() { - assert(skip_ != NULL); - should_skip_ = false; -} - -void Scanner::EnableSkip() { - assert(skip_ != NULL); - should_skip_ = true; - ConsumeSkip(); -} - -int Scanner::LineNumber() const { - // TODO: Make it more efficient by keeping track of the last point - // where we computed line numbers and counting newlines since then. - // We could use std:count, but not all systems have it. :-( - int count = 1; - for (const char* p = data_.data(); p < input_.data(); ++p) - if (*p == '\n') - ++count; - return count; -} - -int Scanner::Offset() const { - return input_.data() - data_.c_str(); -} - -bool Scanner::LookingAt(const RE& re) const { - int consumed; - return re.DoMatch(input_, RE::ANCHOR_START, &consumed, 0, 0); -} - - -bool Scanner::Consume(const RE& re, - const Arg& arg0, - const Arg& arg1, - const Arg& arg2) { - const bool result = re.Consume(&input_, arg0, arg1, arg2); - if (result && should_skip_) ConsumeSkip(); - return result; -} - -// helper function to consume *skip_ and honour save_comments_ -void Scanner::ConsumeSkip() { - if (save_comments_) { - if (NULL == comments_) { - comments_ = new vector<StringPiece>; - } - const char *start_data = input_.data(); - skip_->Consume(&input_); - // already pointing one past end, so no need to +1 - int length = input_.data() - start_data; - if (length > 0) { - comments_->push_back(StringPiece(start_data, length)); - } - } else { - skip_->Consume(&input_); - } -} - - -void Scanner::GetComments(int start, int end, vector<StringPiece> *ranges) { - // short circuit out if we've not yet initialized comments_ - // (e.g., when save_comments is false) - if (!comments_) { - return; - } - // TODO: if we guarantee that comments_ will contain StringPieces - // that are ordered by their start, then we can do a binary search - // for the first StringPiece at or past start and then scan for the - // ones contained in the range, quit early (use equal_range or - // lower_bound) - for (vector<StringPiece>::const_iterator it = comments_->begin(); - it != comments_->end(); ++it) { - if ((it->data() >= data_.c_str() + start && - it->data() + it->size() <= data_.c_str() + end)) { - ranges->push_back(*it); - } - } -} - - -void Scanner::GetNextComments(vector<StringPiece> *ranges) { - // short circuit out if we've not yet initialized comments_ - // (e.g., when save_comments is false) - if (!comments_) { - return; - } - for (vector<StringPiece>::const_iterator it = - comments_->begin() + comments_offset_; - it != comments_->end(); ++it) { - ranges->push_back(*it); - ++comments_offset_; - } -} - -} // namespace pcrecpp diff --git a/ext/pcre/pcrelib/pcre_scanner.h b/ext/pcre/pcrelib/pcre_scanner.h deleted file mode 100644 index a73b72fd2d..0000000000 --- a/ext/pcre/pcrelib/pcre_scanner.h +++ /dev/null @@ -1,163 +0,0 @@ -// Copyright (c) 2005, Google Inc. -// All rights reserved. -// -// 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 Google Inc. 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. -// -// Author: Sanjay Ghemawat -// -// Regular-expression based scanner for parsing an input stream. -// -// Example 1: parse a sequence of "var = number" entries from input: -// -// Scanner scanner(input); -// string var; -// int number; -// scanner.Skip("\\s+"); // Skip any white space we encounter -// while (scanner.Consume("(\\w+) = (\\d+)", &var, &number)) { -// ...; -// } - -#ifndef _PCRE_SCANNER_H -#define _PCRE_SCANNER_H - -#include <assert.h> -#include <string> -#include <vector> -#include <pcrecpp.h> -#include <pcre_stringpiece.h> - -namespace pcrecpp { - -class Scanner { - public: - Scanner(); - explicit Scanner(const std::string& input); - ~Scanner(); - - // Return current line number. The returned line-number is - // one-based. I.e. it returns 1 + the number of consumed newlines. - // - // Note: this method may be slow. It may take time proportional to - // the size of the input. - int LineNumber() const; - - // Return the byte-offset that the scanner is looking in the - // input data; - int Offset() const; - - // Return true iff the start of the remaining input matches "re" - bool LookingAt(const RE& re) const; - - // Return true iff all of the following are true - // a. the start of the remaining input matches "re", - // b. if any arguments are supplied, matched sub-patterns can be - // parsed and stored into the arguments. - // If it returns true, it skips over the matched input and any - // following input that matches the "skip" regular expression. - bool Consume(const RE& re, - const Arg& arg0 = no_arg, - const Arg& arg1 = no_arg, - const Arg& arg2 = no_arg - // TODO: Allow more arguments? - ); - - // Set the "skip" regular expression. If after consuming some data, - // a prefix of the input matches this RE, it is automatically - // skipped. For example, a programming language scanner would use - // a skip RE that matches white space and comments. - // - // scanner.Skip("(\\s|//.*|/[*](.|\n)*?[*]/)*"); - // - // You can pass NULL for "re" if you do not want any data to be skipped. - void Skip(const char* re); - - // Temporarily pause "skip"ing. This - // Skip("Foo"); code ; DisableSkip(); code; EnableSkip() - // is similar to - // Skip("Foo"); code ; Skip(NULL); code ; Skip("Foo"); - // but avoids creating/deleting new RE objects. - void DisableSkip(); - - // Reenable previously paused skipping. Any prefix of the input - // that matches the skip pattern is immediately dropped. - void EnableSkip(); - - /***** Special wrappers around SetSkip() for some common idioms *****/ - - // Arranges to skip whitespace, C comments, C++ comments. - // The overall RE is a repeated disjunction of the following REs: - // \\s whitespace - // //.*\n C++ comment - // /[*](.|\n)*?[*]/ C comment (x*? means minimal repetitions of x) - void SkipCXXComments() { - Skip("((\\s|//.*\n|/[*](.|\n)*?[*]/)*)"); - } - - void set_save_comments(bool comments) { - save_comments_ = comments; - } - - bool save_comments() { - return save_comments_; - } - - // Append to vector ranges the comments found in the - // byte range [start,end] (inclusive) of the input data. - // Only comments that were extracted entirely within that - // range are returned: no range splitting of atomically-extracted - // comments is performed. - void GetComments(int start, int end, std::vector<StringPiece> *ranges); - - // Append to vector ranges the comments added - // since the last time this was called. This - // functionality is provided for efficiency when - // interleaving scanning with parsing. - void GetNextComments(std::vector<StringPiece> *ranges); - - private: - std::string data_; // All the input data - StringPiece input_; // Unprocessed input - RE* skip_; // If non-NULL, RE for skipping input - bool should_skip_; // If true, use skip_ - bool save_comments_; // If true, aggregate the skip expression - - // the skipped comments - // TODO: later consider requiring that the StringPieces be added - // in order by their start position - std::vector<StringPiece> *comments_; - - // the offset into comments_ that has been returned by GetNextComments - int comments_offset_; - - // helper function to consume *skip_ and honour - // save_comments_ - void ConsumeSkip(); -}; - -} // namespace pcrecpp - -#endif /* _PCRE_SCANNER_H */ diff --git a/ext/pcre/pcrelib/pcre_scanner_unittest.cc b/ext/pcre/pcrelib/pcre_scanner_unittest.cc deleted file mode 100644 index 756823cbb1..0000000000 --- a/ext/pcre/pcrelib/pcre_scanner_unittest.cc +++ /dev/null @@ -1,126 +0,0 @@ -// Copyright (c) 2005, Google Inc. -// All rights reserved. -// -// 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 Google Inc. 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. -// -// Author: Greg J. Badros -// -// Unittest for scanner, especially GetNextComments and GetComments() -// functionality. - -#include <stdio.h> -#include <vector> -#include <pcre_stringpiece.h> -#include <pcre_scanner.h> - -// Dies with a fatal error if the two values are not equal. -#define CHECK_EQ(a, b) do { \ - if ( (a) != (b) ) { \ - fprintf(stderr, "%s:%d: Check failed because %s != %s\n", \ - __FILE__, __LINE__, #a, #b); \ - exit(1); \ - } \ -} while (0) - -using std::vector; -using pcrecpp::StringPiece; -using pcrecpp::Scanner; - -static void TestScanner() { - const char input[] = "\n" - "alpha = 1; // this sets alpha\n" - "bravo = 2; // bravo is set here\n" - "gamma = 33; /* and here is gamma */\n"; - - const char *re = "(\\w+) = (\\d+);"; - - Scanner s(input); - string var; - int number; - s.SkipCXXComments(); - s.set_save_comments(true); - vector<StringPiece> comments; - - s.Consume(re, &var, &number); - CHECK_EQ(var, "alpha"); - CHECK_EQ(number, 1); - CHECK_EQ(s.LineNumber(), 3); - s.GetNextComments(&comments); - CHECK_EQ(comments.size(), 1); - CHECK_EQ(comments[0].as_string(), " // this sets alpha\n"); - comments.resize(0); - - s.Consume(re, &var, &number); - CHECK_EQ(var, "bravo"); - CHECK_EQ(number, 2); - s.GetNextComments(&comments); - CHECK_EQ(comments.size(), 1); - CHECK_EQ(comments[0].as_string(), " // bravo is set here\n"); - comments.resize(0); - - s.Consume(re, &var, &number); - CHECK_EQ(var, "gamma"); - CHECK_EQ(number, 33); - s.GetNextComments(&comments); - CHECK_EQ(comments.size(), 1); - CHECK_EQ(comments[0].as_string(), " /* and here is gamma */\n"); - comments.resize(0); - - s.GetComments(0, sizeof(input), &comments); - CHECK_EQ(comments.size(), 3); - CHECK_EQ(comments[0].as_string(), " // this sets alpha\n"); - CHECK_EQ(comments[1].as_string(), " // bravo is set here\n"); - CHECK_EQ(comments[2].as_string(), " /* and here is gamma */\n"); - comments.resize(0); - - s.GetComments(0, strchr(input, '/') - input, &comments); - CHECK_EQ(comments.size(), 0); - comments.resize(0); - - s.GetComments(strchr(input, '/') - input - 1, sizeof(input), - &comments); - CHECK_EQ(comments.size(), 3); - CHECK_EQ(comments[0].as_string(), " // this sets alpha\n"); - CHECK_EQ(comments[1].as_string(), " // bravo is set here\n"); - CHECK_EQ(comments[2].as_string(), " /* and here is gamma */\n"); - comments.resize(0); - - s.GetComments(strchr(input, '/') - input - 1, - strchr(input + 1, '\n') - input + 1, &comments); - CHECK_EQ(comments.size(), 1); - CHECK_EQ(comments[0].as_string(), " // this sets alpha\n"); - comments.resize(0); -} - -int main(int argc, char** argv) { - TestScanner(); - - // Done - printf("OK\n"); - - return 0; -} diff --git a/ext/pcre/pcrelib/pcre_stringpiece.cc b/ext/pcre/pcrelib/pcre_stringpiece.cc deleted file mode 100644 index dbdb509b3b..0000000000 --- a/ext/pcre/pcrelib/pcre_stringpiece.cc +++ /dev/null @@ -1,39 +0,0 @@ -// Copyright (c) 2005, Google Inc. -// All rights reserved. -// -// 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 Google Inc. 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. -// -// Author: wilsonh@google.com (Wilson Hsieh) -// - -#include <iostream> -#include "config.h" -#include "pcre_stringpiece.h" - -std::ostream& operator<<(std::ostream& o, const pcrecpp::StringPiece& piece) { - return (o << piece.as_string()); -} diff --git a/ext/pcre/pcrelib/pcre_stringpiece.h b/ext/pcre/pcrelib/pcre_stringpiece.h deleted file mode 100644 index 89d5449651..0000000000 --- a/ext/pcre/pcrelib/pcre_stringpiece.h +++ /dev/null @@ -1,172 +0,0 @@ -// Copyright (c) 2005, Google Inc. -// All rights reserved. -// -// 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 Google Inc. 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. -// -// Author: Sanjay Ghemawat -// -// A string like object that points into another piece of memory. -// Useful for providing an interface that allows clients to easily -// pass in either a "const char*" or a "string". -// -// Arghh! I wish C++ literals were automatically of type "string". - -#ifndef _PCRE_STRINGPIECE_H -#define _PCRE_STRINGPIECE_H - -#include <string.h> -#include <string> -#include <iosfwd> // for ostream forward-declaration - -#if 1 -#define HAVE_TYPE_TRAITS -#include <type_traits.h> -#elif 0 -#define HAVE_TYPE_TRAITS -#include <bits/type_traits.h> -#endif - -using std::string; - -namespace pcrecpp { - -class StringPiece { - private: - const char* ptr_; - int length_; - - public: - // We provide non-explicit singleton constructors so users can pass - // in a "const char*" or a "string" wherever a "StringPiece" is - // expected. - StringPiece() - : ptr_(NULL), length_(0) { } - StringPiece(const char* str) - : ptr_(str), length_(static_cast<int>(strlen(str))) { } - StringPiece(const string& str) - : ptr_(str.data()), length_(static_cast<int>(str.size())) { } - StringPiece(const char* offset, int len) - : ptr_(offset), length_(len) { } - - // data() may return a pointer to a buffer with embedded NULs, and the - // returned buffer may or may not be null terminated. Therefore it is - // typically a mistake to pass data() to a routine that expects a NUL - // terminated string. Use "as_string().c_str()" if you really need to do - // this. Or better yet, change your routine so it does not rely on NUL - // termination. - const char* data() const { return ptr_; } - int size() const { return length_; } - bool empty() const { return length_ == 0; } - - void clear() { ptr_ = NULL; length_ = 0; } - void set(const char* buffer, int len) { ptr_ = buffer; length_ = len; } - void set(const char* str) { - ptr_ = str; - length_ = static_cast<int>(strlen(str)); - } - void set(const void* buffer, int len) { - ptr_ = reinterpret_cast<const char*>(buffer); - length_ = len; - } - - char operator[](int i) const { return ptr_[i]; } - - void remove_prefix(int n) { - ptr_ += n; - length_ -= n; - } - - void remove_suffix(int n) { - length_ -= n; - } - - bool operator==(const StringPiece& x) const { - return ((length_ == x.length_) && - (memcmp(ptr_, x.ptr_, length_) == 0)); - } - bool operator!=(const StringPiece& x) const { - return !(*this == x); - } - -#define STRINGPIECE_BINARY_PREDICATE(cmp,auxcmp) \ - bool operator cmp (const StringPiece& x) const { \ - int r = memcmp(ptr_, x.ptr_, length_ < x.length_ ? length_ : x.length_); \ - return ((r auxcmp 0) || ((r == 0) && (length_ cmp x.length_))); \ - } - STRINGPIECE_BINARY_PREDICATE(<, <); - STRINGPIECE_BINARY_PREDICATE(<=, <); - STRINGPIECE_BINARY_PREDICATE(>=, >); - STRINGPIECE_BINARY_PREDICATE(>, >); -#undef STRINGPIECE_BINARY_PREDICATE - - int compare(const StringPiece& x) const { - int r = memcmp(ptr_, x.ptr_, length_ < x.length_ ? length_ : x.length_); - if (r == 0) { - if (length_ < x.length_) r = -1; - else if (length_ > x.length_) r = +1; - } - return r; - } - - string as_string() const { - return string(data(), size()); - } - - void CopyToString(string* target) const { - target->assign(ptr_, length_); - } - - // Does "this" start with "x" - bool starts_with(const StringPiece& x) const { - return ((length_ >= x.length_) && (memcmp(ptr_, x.ptr_, x.length_) == 0)); - } -}; - -} // namespace pcrecpp - -// ------------------------------------------------------------------ -// Functions used to create STL containers that use StringPiece -// Remember that a StringPiece's lifetime had better be less than -// that of the underlying string or char*. If it is not, then you -// cannot safely store a StringPiece into an STL container -// ------------------------------------------------------------------ - -#ifdef HAVE_TYPE_TRAITS -// This makes vector<StringPiece> really fast for some STL implementations -template<> struct __type_traits<pcrecpp::StringPiece> { - typedef __true_type has_trivial_default_constructor; - typedef __true_type has_trivial_copy_constructor; - typedef __true_type has_trivial_assignment_operator; - typedef __true_type has_trivial_destructor; - typedef __true_type is_POD_type; -}; -#endif - -// allow StringPiece to be logged -std::ostream& operator<<(std::ostream& o, const pcrecpp::StringPiece& piece); - -#endif /* _PCRE_STRINGPIECE_H */ diff --git a/ext/pcre/pcrelib/pcre_stringpiece_unittest.cc b/ext/pcre/pcrelib/pcre_stringpiece_unittest.cc deleted file mode 100644 index d6a89e8c7a..0000000000 --- a/ext/pcre/pcrelib/pcre_stringpiece_unittest.cc +++ /dev/null @@ -1,145 +0,0 @@ -// Copyright 2003 and onwards Google Inc. -// Author: Sanjay Ghemawat - -#include <stdio.h> -#include <map> -#include <algorithm> // for make_pair -#include <pcre_stringpiece.h> - -// CHECK dies with a fatal error if condition is not true. It is *not* -// controlled by NDEBUG, so the check will be executed regardless of -// compilation mode. Therefore, it is safe to do things like: -// CHECK(fp->Write(x) == 4) -#define CHECK(condition) do { \ - if (!(condition)) { \ - fprintf(stderr, "%s:%d: Check failed: %s\n", \ - __FILE__, __LINE__, #condition); \ - exit(1); \ - } \ -} while (0) - -using std::map; -using std::make_pair; -using pcrecpp::StringPiece; - -static void CheckSTLComparator() { - string s1("foo"); - string s2("bar"); - string s3("baz"); - - StringPiece p1(s1); - StringPiece p2(s2); - StringPiece p3(s3); - - typedef map<StringPiece, int> TestMap; - TestMap map; - - map.insert(make_pair(p1, 0)); - map.insert(make_pair(p2, 1)); - map.insert(make_pair(p3, 2)); - CHECK(map.size() == 3); - - TestMap::const_iterator iter = map.begin(); - CHECK(iter->second == 1); - ++iter; - CHECK(iter->second == 2); - ++iter; - CHECK(iter->second == 0); - ++iter; - CHECK(iter == map.end()); - - TestMap::iterator new_iter = map.find("zot"); - CHECK(new_iter == map.end()); - - new_iter = map.find("bar"); - CHECK(new_iter != map.end()); - - map.erase(new_iter); - CHECK(map.size() == 2); - - iter = map.begin(); - CHECK(iter->second == 2); - ++iter; - CHECK(iter->second == 0); - ++iter; - CHECK(iter == map.end()); -} - -static void CheckComparisonOperators() { -#define CMP_Y(op, x, y) \ - CHECK( (StringPiece((x)) op StringPiece((y)))); \ - CHECK( (StringPiece((x)).compare(StringPiece((y))) op 0)) - -#define CMP_N(op, x, y) \ - CHECK(!(StringPiece((x)) op StringPiece((y)))); \ - CHECK(!(StringPiece((x)).compare(StringPiece((y))) op 0)) - - CMP_Y(==, "", ""); - CMP_Y(==, "a", "a"); - CMP_Y(==, "aa", "aa"); - CMP_N(==, "a", ""); - CMP_N(==, "", "a"); - CMP_N(==, "a", "b"); - CMP_N(==, "a", "aa"); - CMP_N(==, "aa", "a"); - - CMP_N(!=, "", ""); - CMP_N(!=, "a", "a"); - CMP_N(!=, "aa", "aa"); - CMP_Y(!=, "a", ""); - CMP_Y(!=, "", "a"); - CMP_Y(!=, "a", "b"); - CMP_Y(!=, "a", "aa"); - CMP_Y(!=, "aa", "a"); - - CMP_Y(<, "a", "b"); - CMP_Y(<, "a", "aa"); - CMP_Y(<, "aa", "b"); - CMP_Y(<, "aa", "bb"); - CMP_N(<, "a", "a"); - CMP_N(<, "b", "a"); - CMP_N(<, "aa", "a"); - CMP_N(<, "b", "aa"); - CMP_N(<, "bb", "aa"); - - CMP_Y(<=, "a", "a"); - CMP_Y(<=, "a", "b"); - CMP_Y(<=, "a", "aa"); - CMP_Y(<=, "aa", "b"); - CMP_Y(<=, "aa", "bb"); - CMP_N(<=, "b", "a"); - CMP_N(<=, "aa", "a"); - CMP_N(<=, "b", "aa"); - CMP_N(<=, "bb", "aa"); - - CMP_N(>=, "a", "b"); - CMP_N(>=, "a", "aa"); - CMP_N(>=, "aa", "b"); - CMP_N(>=, "aa", "bb"); - CMP_Y(>=, "a", "a"); - CMP_Y(>=, "b", "a"); - CMP_Y(>=, "aa", "a"); - CMP_Y(>=, "b", "aa"); - CMP_Y(>=, "bb", "aa"); - - CMP_N(>, "a", "a"); - CMP_N(>, "a", "b"); - CMP_N(>, "a", "aa"); - CMP_N(>, "aa", "b"); - CMP_N(>, "aa", "bb"); - CMP_Y(>, "b", "a"); - CMP_Y(>, "aa", "a"); - CMP_Y(>, "b", "aa"); - CMP_Y(>, "bb", "aa"); - -#undef CMP_Y -#undef CMP_N -} - -int main(int argc, char** argv) { - CheckComparisonOperators(); - CheckSTLComparator(); - - printf("OK\n"); - return 0; -} diff --git a/ext/pcre/pcrelib/pcre_study.c b/ext/pcre/pcrelib/pcre_study.c deleted file mode 100644 index 5091324ae6..0000000000 --- a/ext/pcre/pcrelib/pcre_study.c +++ /dev/null @@ -1,525 +0,0 @@ -/************************************************* -* 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) 1997-2006 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 "pcre_internal.h" - - -/************************************************* -* Set a bit and maybe its alternate case * -*************************************************/ - -/* Given a character, set its bit in the table, and also the bit for the other -version of a letter if we are caseless. - -Arguments: - start_bits points to the bit map - c is the character - caseless the caseless flag - cd the block with char table pointers - -Returns: nothing -*/ - -static void -set_bit(uschar *start_bits, unsigned int c, BOOL caseless, compile_data *cd) -{ -start_bits[c/8] |= (1 << (c&7)); -if (caseless && (cd->ctypes[c] & ctype_letter) != 0) - start_bits[cd->fcc[c]/8] |= (1 << (cd->fcc[c]&7)); -} - - - -/************************************************* -* Create bitmap of starting chars * -*************************************************/ - -/* This function scans a compiled unanchored expression and attempts to build a -bitmap of the set of initial characters. If it can't, it returns FALSE. As time -goes by, we may be able to get more clever at doing this. - -Arguments: - code points to an expression - start_bits points to a 32-byte table, initialized to 0 - caseless the current state of the caseless flag - utf8 TRUE if in UTF-8 mode - cd the block with char table pointers - -Returns: TRUE if table built, FALSE otherwise -*/ - -static BOOL -set_start_bits(const uschar *code, uschar *start_bits, BOOL caseless, - BOOL utf8, compile_data *cd) -{ -register int c; - -#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 - { - const uschar *tcode = code + 1 + LINK_SIZE; - BOOL try_next = TRUE; - - while (try_next) - { - /* If a branch starts with a bracket or a positive lookahead assertion, - recurse to set bits from within them. That's all for this branch. */ - - if ((int)*tcode >= OP_BRA || *tcode == OP_ASSERT) - { - if (!set_start_bits(tcode, start_bits, caseless, utf8, cd)) - return FALSE; - try_next = FALSE; - } - - else switch(*tcode) - { - default: - return FALSE; - - /* Skip over callout */ - - case OP_CALLOUT: - tcode += 2 + 2*LINK_SIZE; - break; - - /* Skip over extended extraction bracket number */ - - case OP_BRANUMBER: - tcode += 3; - 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; - - /* Skip over an option setting, changing the caseless flag */ - - case OP_OPT: - caseless = (tcode[1] & PCRE_CASELESS) != 0; - tcode += 2; - break; - - /* BRAZERO does the bracket, but carries on. */ - - case OP_BRAZERO: - case OP_BRAMINZERO: - if (!set_start_bits(++tcode, start_bits, caseless, utf8, cd)) - return FALSE; -/* ========================================================================= - 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; - - /* Single-char * or ? sets the bit and tries the next item */ - - case OP_STAR: - case OP_MINSTAR: - case OP_QUERY: - case OP_MINQUERY: - set_bit(start_bits, tcode[1], caseless, cd); - tcode += 2; -#ifdef SUPPORT_UTF8 - if (utf8) while ((*tcode & 0xc0) == 0x80) tcode++; -#endif - break; - - /* Single-char upto sets the bit and tries the next */ - - case OP_UPTO: - case OP_MINUPTO: - set_bit(start_bits, tcode[3], caseless, cd); - tcode += 4; -#ifdef SUPPORT_UTF8 - if (utf8) while ((*tcode & 0xc0) == 0x80) tcode++; -#endif - break; - - /* At least one single char sets the bit and stops */ - - case OP_EXACT: /* Fall through */ - tcode += 2; - - case OP_CHAR: - case OP_CHARNC: - case OP_PLUS: - case OP_MINPLUS: - set_bit(start_bits, tcode[1], caseless, cd); - try_next = FALSE; - break; - - /* Single character type sets the bits and stops */ - - case OP_NOT_DIGIT: - for (c = 0; c < 32; c++) - start_bits[c] |= ~cd->cbits[c+cbit_digit]; - try_next = FALSE; - break; - - case OP_DIGIT: - for (c = 0; c < 32; c++) - start_bits[c] |= cd->cbits[c+cbit_digit]; - try_next = FALSE; - break; - - /* The cbit_space table has vertical tab as whitespace; we have to - discard it. */ - - case OP_NOT_WHITESPACE: - for (c = 0; c < 32; c++) - { - int d = cd->cbits[c+cbit_space]; - if (c == 1) d &= ~0x08; - start_bits[c] |= ~d; - } - try_next = FALSE; - break; - - /* The cbit_space table has vertical tab as whitespace; we have to - discard it. */ - - case OP_WHITESPACE: - for (c = 0; c < 32; c++) - { - int d = cd->cbits[c+cbit_space]; - if (c == 1) d &= ~0x08; - start_bits[c] |= d; - } - try_next = FALSE; - break; - - case OP_NOT_WORDCHAR: - for (c = 0; c < 32; c++) - start_bits[c] |= ~cd->cbits[c+cbit_word]; - try_next = FALSE; - break; - - case OP_WORDCHAR: - for (c = 0; c < 32; c++) - start_bits[c] |= cd->cbits[c+cbit_word]; - 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: - tcode++; - break; - - case OP_TYPEEXACT: - tcode += 3; - break; - - /* Zero or more repeats of character types set the bits and then - try again. */ - - case OP_TYPEUPTO: - case OP_TYPEMINUPTO: - tcode += 2; /* Fall through */ - - case OP_TYPESTAR: - case OP_TYPEMINSTAR: - case OP_TYPEQUERY: - case OP_TYPEMINQUERY: - switch(tcode[1]) - { - case OP_ANY: - return FALSE; - - case OP_NOT_DIGIT: - for (c = 0; c < 32; c++) - start_bits[c] |= ~cd->cbits[c+cbit_digit]; - break; - - case OP_DIGIT: - for (c = 0; c < 32; c++) - start_bits[c] |= cd->cbits[c+cbit_digit]; - break; - - /* The cbit_space table has vertical tab as whitespace; we have to - discard it. */ - - case OP_NOT_WHITESPACE: - for (c = 0; c < 32; c++) - { - int d = cd->cbits[c+cbit_space]; - if (c == 1) d &= ~0x08; - start_bits[c] |= ~d; - } - break; - - /* The cbit_space table has vertical tab as whitespace; we have to - discard it. */ - - case OP_WHITESPACE: - for (c = 0; c < 32; c++) - { - int d = cd->cbits[c+cbit_space]; - if (c == 1) d &= ~0x08; - start_bits[c] |= d; - } - break; - - case OP_NOT_WORDCHAR: - for (c = 0; c < 32; c++) - start_bits[c] |= ~cd->cbits[c+cbit_word]; - break; - - case OP_WORDCHAR: - for (c = 0; c < 32; c++) - start_bits[c] |= cd->cbits[c+cbit_word]; - 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 (utf8) - { - start_bits[24] |= 0xf0; /* Bits for 0xc4 - 0xc8 */ - memset(start_bits+25, 0xff, 7); /* Bits for 0xc9 - 0xff */ - } - /* Fall through */ - - case OP_CLASS: - { - 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 (utf8) - { - for (c = 0; c < 16; c++) start_bits[c] |= tcode[c]; - for (c = 128; c < 256; c++) - { - if ((tcode[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. */ - } - } - } - - /* In non-UTF-8 mode, the two bit maps are completely compatible. */ - - else - { - for (c = 0; c < 32; c++) start_bits[c] |= tcode[c]; - } - - /* Advance past the bit map, and act on what follows */ - - tcode += 32; - switch (*tcode) - { - case OP_CRSTAR: - case OP_CRMINSTAR: - case OP_CRQUERY: - case OP_CRMINQUERY: - tcode++; - break; - - case OP_CRRANGE: - case OP_CRMINRANGE: - if (((tcode[1] << 8) + tcode[2]) == 0) tcode += 5; - 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 TRUE; -} - - - -/************************************************* -* 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_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_extra block, with study_data filled in and the - appropriate flag set; - NULL on error or if no optimization possible -*/ - -PCRE_DATA_SCOPE pcre_extra * -pcre_study(const pcre *external_re, int options, const char **errorptr) -{ -uschar start_bits[32]; -pcre_extra *extra; -pcre_study_data *study; -const uschar *tables; -uschar *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 ((options & ~PUBLIC_STUDY_OPTIONS) != 0) - { - *errorptr = "unknown or incorrect option bit(s) set"; - return NULL; - } - -code = (uschar *)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", no further processing -at present. */ - -if ((re->options & (PCRE_ANCHORED|PCRE_FIRSTSET|PCRE_STARTLINE)) != 0) - return NULL; - -/* Set the character tables in the block that is passed around */ - -tables = re->tables; -if (tables == NULL) - (void)pcre_fullinfo(external_re, NULL, PCRE_INFO_DEFAULT_TABLES, - (void *)(&tables)); - -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(uschar)); -if (!set_start_bits(code, start_bits, (re->options & PCRE_CASELESS) != 0, - (re->options & PCRE_UTF8) != 0, &compile_block)) return NULL; - -/* Get a pcre_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. */ - -extra = (pcre_extra *)(pcre_malloc) - (sizeof(pcre_extra) + sizeof(pcre_study_data)); - -if (extra == NULL) - { - *errorptr = "failed to get memory"; - return NULL; - } - -study = (pcre_study_data *)((char *)extra + sizeof(pcre_extra)); -extra->flags = PCRE_EXTRA_STUDY_DATA; -extra->study_data = study; - -study->size = sizeof(pcre_study_data); -study->options = PCRE_STUDY_MAPPED; -memcpy(study->start_bits, start_bits, sizeof(start_bits)); - -return extra; -} - -/* End of pcre_study.c */ diff --git a/ext/pcre/pcrelib/pcre_tables.c b/ext/pcre/pcrelib/pcre_tables.c deleted file mode 100644 index 480257cab8..0000000000 --- a/ext/pcre/pcrelib/pcre_tables.c +++ /dev/null @@ -1,193 +0,0 @@ -/************************************************* -* 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) 1997-2006 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 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 "pcre_internal.h" - - -/* 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 uschar _pcre_OP_lengths[] = { OP_LENGTHS }; - - - -/************************************************* -* Tables for UTF-8 support * -*************************************************/ - -/* These are the breakpoints for different numbers of bytes in a UTF-8 -character. */ - -const int _pcre_utf8_table1[] = - { 0x7f, 0x7ff, 0xffff, 0x1fffff, 0x3ffffff, 0x7fffffff}; - -const int _pcre_utf8_table1_size = sizeof(_pcre_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 _pcre_utf8_table2[] = { 0, 0xc0, 0xe0, 0xf0, 0xf8, 0xfc}; -const int _pcre_utf8_table3[] = { 0xff, 0x1f, 0x0f, 0x07, 0x03, 0x01}; - -/* Table of the number of extra characters, indexed by the first character -masked with 0x3f. The highest number for a valid UTF-8 character is in fact -0x3d. */ - -const uschar _pcre_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 }; - -/* This table translates Unicode property names into type and code values. It -is searched by binary chop, so must be in collating sequence of name. */ - -const ucp_type_table _pcre_utt[] = { - { "Any", PT_ANY, 0 }, - { "Arabic", PT_SC, ucp_Arabic }, - { "Armenian", PT_SC, ucp_Armenian }, - { "Bengali", PT_SC, ucp_Bengali }, - { "Bopomofo", PT_SC, ucp_Bopomofo }, - { "Braille", PT_SC, ucp_Braille }, - { "Buginese", PT_SC, ucp_Buginese }, - { "Buhid", PT_SC, ucp_Buhid }, - { "C", PT_GC, ucp_C }, - { "Canadian_Aboriginal", PT_SC, ucp_Canadian_Aboriginal }, - { "Cc", PT_PC, ucp_Cc }, - { "Cf", PT_PC, ucp_Cf }, - { "Cherokee", PT_SC, ucp_Cherokee }, - { "Cn", PT_PC, ucp_Cn }, - { "Co", PT_PC, ucp_Co }, - { "Common", PT_SC, ucp_Common }, - { "Coptic", PT_SC, ucp_Coptic }, - { "Cs", PT_PC, ucp_Cs }, - { "Cypriot", PT_SC, ucp_Cypriot }, - { "Cyrillic", PT_SC, ucp_Cyrillic }, - { "Deseret", PT_SC, ucp_Deseret }, - { "Devanagari", PT_SC, ucp_Devanagari }, - { "Ethiopic", PT_SC, ucp_Ethiopic }, - { "Georgian", PT_SC, ucp_Georgian }, - { "Glagolitic", PT_SC, ucp_Glagolitic }, - { "Gothic", PT_SC, ucp_Gothic }, - { "Greek", PT_SC, ucp_Greek }, - { "Gujarati", PT_SC, ucp_Gujarati }, - { "Gurmukhi", PT_SC, ucp_Gurmukhi }, - { "Han", PT_SC, ucp_Han }, - { "Hangul", PT_SC, ucp_Hangul }, - { "Hanunoo", PT_SC, ucp_Hanunoo }, - { "Hebrew", PT_SC, ucp_Hebrew }, - { "Hiragana", PT_SC, ucp_Hiragana }, - { "Inherited", PT_SC, ucp_Inherited }, - { "Kannada", PT_SC, ucp_Kannada }, - { "Katakana", PT_SC, ucp_Katakana }, - { "Kharoshthi", PT_SC, ucp_Kharoshthi }, - { "Khmer", PT_SC, ucp_Khmer }, - { "L", PT_GC, ucp_L }, - { "L&", PT_LAMP, 0 }, - { "Lao", PT_SC, ucp_Lao }, - { "Latin", PT_SC, ucp_Latin }, - { "Limbu", PT_SC, ucp_Limbu }, - { "Linear_B", PT_SC, ucp_Linear_B }, - { "Ll", PT_PC, ucp_Ll }, - { "Lm", PT_PC, ucp_Lm }, - { "Lo", PT_PC, ucp_Lo }, - { "Lt", PT_PC, ucp_Lt }, - { "Lu", PT_PC, ucp_Lu }, - { "M", PT_GC, ucp_M }, - { "Malayalam", PT_SC, ucp_Malayalam }, - { "Mc", PT_PC, ucp_Mc }, - { "Me", PT_PC, ucp_Me }, - { "Mn", PT_PC, ucp_Mn }, - { "Mongolian", PT_SC, ucp_Mongolian }, - { "Myanmar", PT_SC, ucp_Myanmar }, - { "N", PT_GC, ucp_N }, - { "Nd", PT_PC, ucp_Nd }, - { "New_Tai_Lue", PT_SC, ucp_New_Tai_Lue }, - { "Nl", PT_PC, ucp_Nl }, - { "No", PT_PC, ucp_No }, - { "Ogham", PT_SC, ucp_Ogham }, - { "Old_Italic", PT_SC, ucp_Old_Italic }, - { "Old_Persian", PT_SC, ucp_Old_Persian }, - { "Oriya", PT_SC, ucp_Oriya }, - { "Osmanya", PT_SC, ucp_Osmanya }, - { "P", PT_GC, ucp_P }, - { "Pc", PT_PC, ucp_Pc }, - { "Pd", PT_PC, ucp_Pd }, - { "Pe", PT_PC, ucp_Pe }, - { "Pf", PT_PC, ucp_Pf }, - { "Pi", PT_PC, ucp_Pi }, - { "Po", PT_PC, ucp_Po }, - { "Ps", PT_PC, ucp_Ps }, - { "Runic", PT_SC, ucp_Runic }, - { "S", PT_GC, ucp_S }, - { "Sc", PT_PC, ucp_Sc }, - { "Shavian", PT_SC, ucp_Shavian }, - { "Sinhala", PT_SC, ucp_Sinhala }, - { "Sk", PT_PC, ucp_Sk }, - { "Sm", PT_PC, ucp_Sm }, - { "So", PT_PC, ucp_So }, - { "Syloti_Nagri", PT_SC, ucp_Syloti_Nagri }, - { "Syriac", PT_SC, ucp_Syriac }, - { "Tagalog", PT_SC, ucp_Tagalog }, - { "Tagbanwa", PT_SC, ucp_Tagbanwa }, - { "Tai_Le", PT_SC, ucp_Tai_Le }, - { "Tamil", PT_SC, ucp_Tamil }, - { "Telugu", PT_SC, ucp_Telugu }, - { "Thaana", PT_SC, ucp_Thaana }, - { "Thai", PT_SC, ucp_Thai }, - { "Tibetan", PT_SC, ucp_Tibetan }, - { "Tifinagh", PT_SC, ucp_Tifinagh }, - { "Ugaritic", PT_SC, ucp_Ugaritic }, - { "Yi", PT_SC, ucp_Yi }, - { "Z", PT_GC, ucp_Z }, - { "Zl", PT_PC, ucp_Zl }, - { "Zp", PT_PC, ucp_Zp }, - { "Zs", PT_PC, ucp_Zs } -}; - -const int _pcre_utt_size = sizeof(_pcre_utt)/sizeof(ucp_type_table); - -/* End of pcre_tables.c */ diff --git a/ext/pcre/pcrelib/pcre_try_flipped.c b/ext/pcre/pcrelib/pcre_try_flipped.c deleted file mode 100644 index 00c94fccf5..0000000000 --- a/ext/pcre/pcrelib/pcre_try_flipped.c +++ /dev/null @@ -1,132 +0,0 @@ -/************************************************* -* 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) 1997-2006 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 tests a compiled pattern to -see if it was compiled with the opposite endianness. If so, it uses an -auxiliary local function to flip the appropriate bytes. */ - - -#include "pcre_internal.h" - - -/************************************************* -* Flip bytes in an integer * -*************************************************/ - -/* This function is called when the magic number in a regex doesn't match, in -order to flip its bytes to see if we are dealing with a pattern that was -compiled on a host of different endianness. If so, this function is used to -flip other byte values. - -Arguments: - value the number to flip - n the number of bytes to flip (assumed to be 2 or 4) - -Returns: the flipped value -*/ - -static unsigned long int -byteflip(unsigned long int value, int n) -{ -if (n == 2) return ((value & 0x00ff) << 8) | ((value & 0xff00) >> 8); -return ((value & 0x000000ff) << 24) | - ((value & 0x0000ff00) << 8) | - ((value & 0x00ff0000) >> 8) | - ((value & 0xff000000) >> 24); -} - - - -/************************************************* -* Test for a byte-flipped compiled regex * -*************************************************/ - -/* This function is called from pcre_exec(), pcre_dfa_exec(), and also from -pcre_fullinfo(). Its job is to test whether the regex is byte-flipped - that -is, it was compiled on a system of opposite endianness. The function is called -only when the native MAGIC_NUMBER test fails. If the regex is indeed flipped, -we flip all the relevant values into a different data block, and return it. - -Arguments: - re points to the regex - study points to study data, or NULL - internal_re points to a new regex block - internal_study points to a new study block - -Returns: the new block if is is indeed a byte-flipped regex - NULL if it is not -*/ - -real_pcre * -_pcre_try_flipped(const real_pcre *re, real_pcre *internal_re, - const pcre_study_data *study, pcre_study_data *internal_study) -{ -if (byteflip(re->magic_number, sizeof(re->magic_number)) != MAGIC_NUMBER) - return NULL; - -*internal_re = *re; /* To copy other fields */ -internal_re->size = byteflip(re->size, sizeof(re->size)); -internal_re->options = byteflip(re->options, sizeof(re->options)); -internal_re->top_bracket = - (pcre_uint16)byteflip(re->top_bracket, sizeof(re->top_bracket)); -internal_re->top_backref = - (pcre_uint16)byteflip(re->top_backref, sizeof(re->top_backref)); -internal_re->first_byte = - (pcre_uint16)byteflip(re->first_byte, sizeof(re->first_byte)); -internal_re->req_byte = - (pcre_uint16)byteflip(re->req_byte, sizeof(re->req_byte)); -internal_re->name_table_offset = - (pcre_uint16)byteflip(re->name_table_offset, sizeof(re->name_table_offset)); -internal_re->name_entry_size = - (pcre_uint16)byteflip(re->name_entry_size, sizeof(re->name_entry_size)); -internal_re->name_count = - (pcre_uint16)byteflip(re->name_count, sizeof(re->name_count)); - -if (study != NULL) - { - *internal_study = *study; /* To copy other fields */ - internal_study->size = byteflip(study->size, sizeof(study->size)); - internal_study->options = byteflip(study->options, sizeof(study->options)); - } - -return internal_re; -} - -/* End of pcre_tryflipped.c */ diff --git a/ext/pcre/pcrelib/pcre_ucp_searchfuncs.c b/ext/pcre/pcrelib/pcre_ucp_searchfuncs.c deleted file mode 100644 index 7a4be94861..0000000000 --- a/ext/pcre/pcrelib/pcre_ucp_searchfuncs.c +++ /dev/null @@ -1,175 +0,0 @@ -/************************************************* -* 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) 1997-2006 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 code for searching the table of Unicode character -properties. */ - -#include "pcre_internal.h" - -#include "ucp.h" /* Category definitions */ -#include "ucpinternal.h" /* Internal table details */ -#include "ucptable.c" /* The table itself */ - - -/* Table to translate from particular type value to the general value. */ - -static int 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 */ -}; - - - -/************************************************* -* Search table and return type * -*************************************************/ - -/* Three values are returned: the category is ucp_C, ucp_L, etc. The detailed -character type is ucp_Lu, ucp_Nd, etc. The script is ucp_Latin, etc. - -Arguments: - c the character value - type_ptr the detailed character type is returned here - script_ptr the script is returned here - -Returns: the character type category -*/ - -int -_pcre_ucp_findprop(const unsigned int c, int *type_ptr, int *script_ptr) -{ -int bot = 0; -int top = sizeof(ucp_table)/sizeof(cnode); -int mid; - -/* The table is searched using a binary chop. You might think that using -intermediate variables to hold some of the common expressions would speed -things up, but tests with gcc 3.4.4 on Linux showed that, on the contrary, it -makes things a lot slower. */ - -for (;;) - { - if (top <= bot) - { - *type_ptr = ucp_Cn; - *script_ptr = ucp_Common; - return ucp_C; - } - mid = (bot + top) >> 1; - if (c == (ucp_table[mid].f0 & f0_charmask)) break; - if (c < (ucp_table[mid].f0 & f0_charmask)) top = mid; - else - { - if ((ucp_table[mid].f0 & f0_rangeflag) != 0 && - c <= (ucp_table[mid].f0 & f0_charmask) + - (ucp_table[mid].f1 & f1_rangemask)) break; - bot = mid + 1; - } - } - -/* Found an entry in the table. Set the script and detailed type values, and -return the general type. */ - -*script_ptr = (ucp_table[mid].f0 & f0_scriptmask) >> f0_scriptshift; -*type_ptr = (ucp_table[mid].f1 & f1_typemask) >> f1_typeshift; - -return ucp_gentype[*type_ptr]; -} - - - -/************************************************* -* Search table and return other case * -*************************************************/ - -/* If the given character is a letter, and there is another case for the -letter, return the other case. Otherwise, return -1. - -Arguments: - c the character value - -Returns: the other case or -1 if none -*/ - -int -_pcre_ucp_othercase(const int c) -{ -int bot = 0; -int top = sizeof(ucp_table)/sizeof(cnode); -int mid, offset; - -/* The table is searched using a binary chop. You might think that using -intermediate variables to hold some of the common expressions would speed -things up, but tests with gcc 3.4.4 on Linux showed that, on the contrary, it -makes things a lot slower. */ - -for (;;) - { - if (top <= bot) return -1; - mid = (bot + top) >> 1; - if (c == (ucp_table[mid].f0 & f0_charmask)) break; - if (c < (ucp_table[mid].f0 & f0_charmask)) top = mid; - else - { - if ((ucp_table[mid].f0 & f0_rangeflag) != 0 && - c <= (ucp_table[mid].f0 & f0_charmask) + - (ucp_table[mid].f1 & f1_rangemask)) break; - bot = mid + 1; - } - } - -/* Found an entry in the table. Return -1 for a range entry. Otherwise return -the other case if there is one, else -1. */ - -if ((ucp_table[mid].f0 & f0_rangeflag) != 0) return -1; - -offset = ucp_table[mid].f1 & f1_casemask; -if ((offset & f1_caseneg) != 0) offset |= f1_caseneg; -return (offset == 0)? -1 : c + offset; -} - - -/* End of pcre_ucp_searchfuncs.c */ diff --git a/ext/pcre/pcrelib/pcre_valid_utf8.c b/ext/pcre/pcrelib/pcre_valid_utf8.c deleted file mode 100644 index 1c6094a0c9..0000000000 --- a/ext/pcre/pcrelib/pcre_valid_utf8.c +++ /dev/null @@ -1,130 +0,0 @@ -/************************************************* -* 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) 1997-2006 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 "pcre_internal.h" - - -/************************************************* -* Validate a UTF-8 string * -*************************************************/ - -/* This function is called (optionally) at the start of compile or match, to -validate 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. - -Arguments: - string points to the string - length length of string, or -1 if the string is zero-terminated - -Returns: < 0 if the string is a valid UTF-8 string - >= 0 otherwise; the value is the offset of the bad byte -*/ - -int -_pcre_valid_utf8(const uschar *string, int length) -{ -register const uschar *p; - -if (length < 0) - { - for (p = string; *p != 0; p++); - length = p - string; - } - -for (p = string; length-- > 0; p++) - { - register int ab; - register int c = *p; - if (c < 128) continue; - if ((c & 0xc0) != 0xc0) return p - string; - ab = _pcre_utf8_table4[c & 0x3f]; /* Number of additional bytes */ - if (length < ab) return p - string; - length -= ab; - - /* Check top bits in the second byte */ - if ((*(++p) & 0xc0) != 0x80) return p - string; - - /* Check for overlong sequences for each different length */ - switch (ab) - { - /* Check for xx00 000x */ - case 1: - if ((c & 0x3e) == 0) return p - string; - continue; /* We know there aren't any more bytes to check */ - - /* Check for 1110 0000, xx0x xxxx */ - case 2: - if (c == 0xe0 && (*p & 0x20) == 0) return p - string; - break; - - /* Check for 1111 0000, xx00 xxxx */ - case 3: - if (c == 0xf0 && (*p & 0x30) == 0) return p - string; - break; - - /* Check for 1111 1000, xx00 0xxx */ - case 4: - if (c == 0xf8 && (*p & 0x38) == 0) return p - string; - break; - - /* Check for leading 0xfe or 0xff, and then for 1111 1100, xx00 00xx */ - case 5: - if (c == 0xfe || c == 0xff || - (c == 0xfc && (*p & 0x3c) == 0)) return p - string; - break; - } - - /* Check for valid bytes after the 2nd, if any; all must start 10 */ - while (--ab > 0) - { - if ((*(++p) & 0xc0) != 0x80) return p - string; - } - } - -return -1; -} - -/* End of pcre_valid_utf8.c */ diff --git a/ext/pcre/pcrelib/pcre_version.c b/ext/pcre/pcrelib/pcre_version.c deleted file mode 100644 index c2aad4da06..0000000000 --- a/ext/pcre/pcrelib/pcre_version.c +++ /dev/null @@ -1,64 +0,0 @@ -/************************************************* -* 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) 1997-2006 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 "pcre_internal.h" - - -/************************************************* -* Return version string * -*************************************************/ - -#define STRING(a) # a -#define XSTRING(s) STRING(s) - -PCRE_DATA_SCOPE const char * -pcre_version(void) -{ -return XSTRING(PCRE_MAJOR) - "." XSTRING(PCRE_MINOR) - XSTRING(PCRE_PRERELEASE) - " " XSTRING(PCRE_DATE); -} - -/* End of pcre_version.c */ diff --git a/ext/pcre/pcrelib/pcre_xclass.c b/ext/pcre/pcrelib/pcre_xclass.c deleted file mode 100644 index 57c514b78a..0000000000 --- a/ext/pcre/pcrelib/pcre_xclass.c +++ /dev/null @@ -1,144 +0,0 @@ -/************************************************* -* 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) 1997-2006 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 (one that contains characters whose values are > 255). It is used by both -pcre_exec() and pcre_def_exec(). */ - - -#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. - -Arguments: - c the character - data points to the flag byte of the XCLASS data - -Returns: TRUE if character matches, else FALSE -*/ - -BOOL -_pcre_xclass(int c, const uschar *data) -{ -int t; -BOOL negated = (*data & XCL_NOT) != 0; - -/* 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 && (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; - -while ((t = *data++) != XCL_END) - { - int x, y; - if (t == XCL_SINGLE) - { - GETCHARINC(x, data); - if (c == x) return !negated; - } - else if (t == XCL_RANGE) - { - GETCHARINC(x, data); - GETCHARINC(y, data); - if (c >= x && c <= y) return !negated; - } - -#ifdef SUPPORT_UCP - else /* XCL_PROP & XCL_NOTPROP */ - { - int chartype, script; - int category = _pcre_ucp_findprop(c, &chartype, &script); - - switch(*data) - { - case PT_ANY: - if (t == XCL_PROP) return !negated; - break; - - case PT_LAMP: - if ((chartype == ucp_Lu || chartype == ucp_Ll || chartype == ucp_Lt) == - (t == XCL_PROP)) return !negated; - break; - - case PT_GC: - if ((data[1] == category) == (t == XCL_PROP)) return !negated; - break; - - case PT_PC: - if ((data[1] == chartype) == (t == XCL_PROP)) return !negated; - break; - - case PT_SC: - if ((data[1] == script) == (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/pcrecpp.cc b/ext/pcre/pcrelib/pcrecpp.cc deleted file mode 100644 index f828de732e..0000000000 --- a/ext/pcre/pcrelib/pcrecpp.cc +++ /dev/null @@ -1,823 +0,0 @@ -// Copyright (c) 2005, Google Inc. -// All rights reserved. -// -// 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 Google Inc. 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. -// -// Author: Sanjay Ghemawat - -#include <stdlib.h> -#include <stdio.h> -#include <ctype.h> -#include <limits.h> /* for SHRT_MIN, USHRT_MAX, etc */ -#include <assert.h> -#include <errno.h> -#include <string> -#include <algorithm> -#include "config.h" -// We need this to compile the proper dll on windows/msys. This is copied -// from pcre_internal.h. It would probably be better just to include that. -#define PCRE_DEFINITION /* Win32 __declspec(export) trigger for .dll */ -#include "pcre.h" -#include "pcre_stringpiece.h" -#include "pcrecpp.h" - - -namespace pcrecpp { - -// Maximum number of args we can set -static const int kMaxArgs = 16; -static const int kVecSize = (1 + kMaxArgs) * 3; // results + PCRE workspace - -// Special object that stands-in for no argument -Arg no_arg((void*)NULL); - -// If a regular expression has no error, its error_ field points here -static const string empty_string; - -// If the user doesn't ask for any options, we just use this one -static RE_Options default_options; - -void RE::Init(const char* pat, const RE_Options* options) { - pattern_ = pat; - if (options == NULL) { - options_ = default_options; - } else { - options_ = *options; - } - error_ = &empty_string; - re_full_ = NULL; - re_partial_ = NULL; - - re_partial_ = Compile(UNANCHORED); - if (re_partial_ != NULL) { - // Check for complicated patterns. The following change is - // conservative in that it may treat some "simple" patterns - // as "complex" (e.g., if the vertical bar is in a character - // class or is escaped). But it seems good enough. - if (strchr(pat, '|') == NULL) { - // Simple pattern: we can use position-based checks to perform - // fully anchored matches - re_full_ = re_partial_; - } else { - // We need a special pattern for anchored matches - re_full_ = Compile(ANCHOR_BOTH); - } - } -} - -RE::~RE() { - if (re_full_ != NULL && re_full_ != re_partial_) (*pcre_free)(re_full_); - if (re_partial_ != NULL) (*pcre_free)(re_partial_); - if (error_ != &empty_string) delete error_; -} - -pcre* RE::Compile(Anchor anchor) { - // First, convert RE_Options into pcre options - int pcre_options = 0; - pcre_options = options_.all_options(); - - // Special treatment for anchoring. This is needed because at - // runtime pcre only provides an option for anchoring at the - // beginning of a string (unless you use offset). - // - // There are three types of anchoring we want: - // UNANCHORED Compile the original pattern, and use - // a pcre unanchored match. - // ANCHOR_START Compile the original pattern, and use - // a pcre anchored match. - // ANCHOR_BOTH Tack a "\z" to the end of the original pattern - // and use a pcre anchored match. - - const char* compile_error; - int eoffset; - pcre* re; - if (anchor != ANCHOR_BOTH) { - re = pcre_compile(pattern_.c_str(), pcre_options, - &compile_error, &eoffset, NULL); - } else { - // Tack a '\z' at the end of RE. Parenthesize it first so that - // the '\z' applies to all top-level alternatives in the regexp. - string wrapped = "(?:"; // A non-counting grouping operator - wrapped += pattern_; - wrapped += ")\\z"; - re = pcre_compile(wrapped.c_str(), pcre_options, - &compile_error, &eoffset, NULL); - } - if (re == NULL) { - if (error_ == &empty_string) error_ = new string(compile_error); - } - return re; -} - -/***** Matching interfaces *****/ - -bool RE::FullMatch(const StringPiece& text, - const Arg& ptr1, - const Arg& ptr2, - const Arg& ptr3, - const Arg& ptr4, - const Arg& ptr5, - const Arg& ptr6, - const Arg& ptr7, - const Arg& ptr8, - const Arg& ptr9, - const Arg& ptr10, - const Arg& ptr11, - const Arg& ptr12, - const Arg& ptr13, - const Arg& ptr14, - const Arg& ptr15, - const Arg& ptr16) const { - const Arg* args[kMaxArgs]; - int n = 0; - if (&ptr1 == &no_arg) goto done; args[n++] = &ptr1; - if (&ptr2 == &no_arg) goto done; args[n++] = &ptr2; - if (&ptr3 == &no_arg) goto done; args[n++] = &ptr3; - if (&ptr4 == &no_arg) goto done; args[n++] = &ptr4; - if (&ptr5 == &no_arg) goto done; args[n++] = &ptr5; - if (&ptr6 == &no_arg) goto done; args[n++] = &ptr6; - if (&ptr7 == &no_arg) goto done; args[n++] = &ptr7; - if (&ptr8 == &no_arg) goto done; args[n++] = &ptr8; - if (&ptr9 == &no_arg) goto done; args[n++] = &ptr9; - if (&ptr10 == &no_arg) goto done; args[n++] = &ptr10; - if (&ptr11 == &no_arg) goto done; args[n++] = &ptr11; - if (&ptr12 == &no_arg) goto done; args[n++] = &ptr12; - if (&ptr13 == &no_arg) goto done; args[n++] = &ptr13; - if (&ptr14 == &no_arg) goto done; args[n++] = &ptr14; - if (&ptr15 == &no_arg) goto done; args[n++] = &ptr15; - if (&ptr16 == &no_arg) goto done; args[n++] = &ptr16; - done: - - int consumed; - int vec[kVecSize]; - return DoMatchImpl(text, ANCHOR_BOTH, &consumed, args, n, vec, kVecSize); -} - -bool RE::PartialMatch(const StringPiece& text, - const Arg& ptr1, - const Arg& ptr2, - const Arg& ptr3, - const Arg& ptr4, - const Arg& ptr5, - const Arg& ptr6, - const Arg& ptr7, - const Arg& ptr8, - const Arg& ptr9, - const Arg& ptr10, - const Arg& ptr11, - const Arg& ptr12, - const Arg& ptr13, - const Arg& ptr14, - const Arg& ptr15, - const Arg& ptr16) const { - const Arg* args[kMaxArgs]; - int n = 0; - if (&ptr1 == &no_arg) goto done; args[n++] = &ptr1; - if (&ptr2 == &no_arg) goto done; args[n++] = &ptr2; - if (&ptr3 == &no_arg) goto done; args[n++] = &ptr3; - if (&ptr4 == &no_arg) goto done; args[n++] = &ptr4; - if (&ptr5 == &no_arg) goto done; args[n++] = &ptr5; - if (&ptr6 == &no_arg) goto done; args[n++] = &ptr6; - if (&ptr7 == &no_arg) goto done; args[n++] = &ptr7; - if (&ptr8 == &no_arg) goto done; args[n++] = &ptr8; - if (&ptr9 == &no_arg) goto done; args[n++] = &ptr9; - if (&ptr10 == &no_arg) goto done; args[n++] = &ptr10; - if (&ptr11 == &no_arg) goto done; args[n++] = &ptr11; - if (&ptr12 == &no_arg) goto done; args[n++] = &ptr12; - if (&ptr13 == &no_arg) goto done; args[n++] = &ptr13; - if (&ptr14 == &no_arg) goto done; args[n++] = &ptr14; - if (&ptr15 == &no_arg) goto done; args[n++] = &ptr15; - if (&ptr16 == &no_arg) goto done; args[n++] = &ptr16; - done: - - int consumed; - int vec[kVecSize]; - return DoMatchImpl(text, UNANCHORED, &consumed, args, n, vec, kVecSize); -} - -bool RE::Consume(StringPiece* input, - const Arg& ptr1, - const Arg& ptr2, - const Arg& ptr3, - const Arg& ptr4, - const Arg& ptr5, - const Arg& ptr6, - const Arg& ptr7, - const Arg& ptr8, - const Arg& ptr9, - const Arg& ptr10, - const Arg& ptr11, - const Arg& ptr12, - const Arg& ptr13, - const Arg& ptr14, - const Arg& ptr15, - const Arg& ptr16) const { - const Arg* args[kMaxArgs]; - int n = 0; - if (&ptr1 == &no_arg) goto done; args[n++] = &ptr1; - if (&ptr2 == &no_arg) goto done; args[n++] = &ptr2; - if (&ptr3 == &no_arg) goto done; args[n++] = &ptr3; - if (&ptr4 == &no_arg) goto done; args[n++] = &ptr4; - if (&ptr5 == &no_arg) goto done; args[n++] = &ptr5; - if (&ptr6 == &no_arg) goto done; args[n++] = &ptr6; - if (&ptr7 == &no_arg) goto done; args[n++] = &ptr7; - if (&ptr8 == &no_arg) goto done; args[n++] = &ptr8; - if (&ptr9 == &no_arg) goto done; args[n++] = &ptr9; - if (&ptr10 == &no_arg) goto done; args[n++] = &ptr10; - if (&ptr11 == &no_arg) goto done; args[n++] = &ptr11; - if (&ptr12 == &no_arg) goto done; args[n++] = &ptr12; - if (&ptr13 == &no_arg) goto done; args[n++] = &ptr13; - if (&ptr14 == &no_arg) goto done; args[n++] = &ptr14; - if (&ptr15 == &no_arg) goto done; args[n++] = &ptr15; - if (&ptr16 == &no_arg) goto done; args[n++] = &ptr16; - done: - - int consumed; - int vec[kVecSize]; - if (DoMatchImpl(*input, ANCHOR_START, &consumed, - args, n, vec, kVecSize)) { - input->remove_prefix(consumed); - return true; - } else { - return false; - } -} - -bool RE::FindAndConsume(StringPiece* input, - const Arg& ptr1, - const Arg& ptr2, - const Arg& ptr3, - const Arg& ptr4, - const Arg& ptr5, - const Arg& ptr6, - const Arg& ptr7, - const Arg& ptr8, - const Arg& ptr9, - const Arg& ptr10, - const Arg& ptr11, - const Arg& ptr12, - const Arg& ptr13, - const Arg& ptr14, - const Arg& ptr15, - const Arg& ptr16) const { - const Arg* args[kMaxArgs]; - int n = 0; - if (&ptr1 == &no_arg) goto done; args[n++] = &ptr1; - if (&ptr2 == &no_arg) goto done; args[n++] = &ptr2; - if (&ptr3 == &no_arg) goto done; args[n++] = &ptr3; - if (&ptr4 == &no_arg) goto done; args[n++] = &ptr4; - if (&ptr5 == &no_arg) goto done; args[n++] = &ptr5; - if (&ptr6 == &no_arg) goto done; args[n++] = &ptr6; - if (&ptr7 == &no_arg) goto done; args[n++] = &ptr7; - if (&ptr8 == &no_arg) goto done; args[n++] = &ptr8; - if (&ptr9 == &no_arg) goto done; args[n++] = &ptr9; - if (&ptr10 == &no_arg) goto done; args[n++] = &ptr10; - if (&ptr11 == &no_arg) goto done; args[n++] = &ptr11; - if (&ptr12 == &no_arg) goto done; args[n++] = &ptr12; - if (&ptr13 == &no_arg) goto done; args[n++] = &ptr13; - if (&ptr14 == &no_arg) goto done; args[n++] = &ptr14; - if (&ptr15 == &no_arg) goto done; args[n++] = &ptr15; - if (&ptr16 == &no_arg) goto done; args[n++] = &ptr16; - done: - - int consumed; - int vec[kVecSize]; - if (DoMatchImpl(*input, UNANCHORED, &consumed, - args, n, vec, kVecSize)) { - input->remove_prefix(consumed); - return true; - } else { - return false; - } -} - -bool RE::Replace(const StringPiece& rewrite, - string *str) const { - int vec[kVecSize]; - int matches = TryMatch(*str, 0, UNANCHORED, vec, kVecSize); - if (matches == 0) - return false; - - string s; - if (!Rewrite(&s, rewrite, *str, vec, matches)) - return false; - - assert(vec[0] >= 0); - assert(vec[1] >= 0); - str->replace(vec[0], vec[1] - vec[0], s); - return true; -} - -// Returns PCRE_NEWLINE_CRLF, PCRE_NEWLINE_CR, or PCRE_NEWLINE_LF. -// Note that PCRE_NEWLINE_CRLF is defined to be P_N_CR | P_N_LF. -static int NewlineMode(int pcre_options) { - // TODO: if we can make it threadsafe, cache this var - int newline_mode = 0; - /* if (newline_mode) return newline_mode; */ // do this once it's cached - if (pcre_options & (PCRE_NEWLINE_CRLF|PCRE_NEWLINE_CR|PCRE_NEWLINE_LF)) { - newline_mode = (pcre_options & - (PCRE_NEWLINE_CRLF|PCRE_NEWLINE_CR|PCRE_NEWLINE_LF)); - } else { - int newline; - pcre_config(PCRE_CONFIG_NEWLINE, &newline); - if (newline == 10) - newline_mode = PCRE_NEWLINE_LF; - else if (newline == 13) - newline_mode = PCRE_NEWLINE_CR; - else if (newline == 3338) - newline_mode = PCRE_NEWLINE_CRLF; - else - assert("" == "Unexpected return value from pcre_config(NEWLINE)"); - } - return newline_mode; -} - -int RE::GlobalReplace(const StringPiece& rewrite, - string *str) const { - int count = 0; - int vec[kVecSize]; - string out; - int start = 0; - int lastend = -1; - - for (; start <= static_cast<int>(str->length()); count++) { - int matches = TryMatch(*str, start, UNANCHORED, vec, kVecSize); - if (matches <= 0) - break; - int matchstart = vec[0], matchend = vec[1]; - assert(matchstart >= start); - assert(matchend >= matchstart); - if (matchstart == matchend && matchstart == lastend) { - // advance one character if we matched an empty string at the same - // place as the last match occurred - matchend = start + 1; - // If the current char is CR and we're in CRLF mode, skip LF too. - // Note it's better to call pcre_fullinfo() than to examine - // all_options(), since options_ could have changed bewteen - // compile-time and now, but this is simpler and safe enough. - if (start+1 < static_cast<int>(str->length()) && - (*str)[start] == '\r' && (*str)[start+1] == '\n' && - NewlineMode(options_.all_options()) == PCRE_NEWLINE_CRLF) { - matchend++; - } - // We also need to advance more than one char if we're in utf8 mode. -#ifdef SUPPORT_UTF8 - if (options_.utf8()) { - while (matchend < static_cast<int>(str->length()) && - ((*str)[matchend] & 0xc0) == 0x80) - matchend++; - } -#endif - if (matchend <= static_cast<int>(str->length())) - out.append(*str, start, matchend - start); - start = matchend; - } else { - out.append(*str, start, matchstart - start); - Rewrite(&out, rewrite, *str, vec, matches); - start = matchend; - lastend = matchend; - count++; - } - } - - if (count == 0) - return 0; - - if (start < static_cast<int>(str->length())) - out.append(*str, start, str->length() - start); - swap(out, *str); - return count; -} - -bool RE::Extract(const StringPiece& rewrite, - const StringPiece& text, - string *out) const { - int vec[kVecSize]; - int matches = TryMatch(text, 0, UNANCHORED, vec, kVecSize); - if (matches == 0) - return false; - out->erase(); - return Rewrite(out, rewrite, text, vec, matches); -} - -/***** Actual matching and rewriting code *****/ - -int RE::TryMatch(const StringPiece& text, - int startpos, - Anchor anchor, - int *vec, - int vecsize) const { - pcre* re = (anchor == ANCHOR_BOTH) ? re_full_ : re_partial_; - if (re == NULL) { - //fprintf(stderr, "Matching against invalid re: %s\n", error_->c_str()); - return 0; - } - - pcre_extra extra = { 0 }; - if (options_.match_limit() > 0) { - extra.flags |= PCRE_EXTRA_MATCH_LIMIT; - extra.match_limit = options_.match_limit(); - } - if (options_.match_limit_recursion() > 0) { - extra.flags |= PCRE_EXTRA_MATCH_LIMIT_RECURSION; - extra.match_limit_recursion = options_.match_limit_recursion(); - } - int rc = pcre_exec(re, // The regular expression object - &extra, - (text.data() == NULL) ? "" : text.data(), - text.size(), - startpos, - (anchor == UNANCHORED) ? 0 : PCRE_ANCHORED, - vec, - vecsize); - - // Handle errors - if (rc == PCRE_ERROR_NOMATCH) { - return 0; - } else if (rc < 0) { - //fprintf(stderr, "Unexpected return code: %d when matching '%s'\n", - // re, pattern_.c_str()); - return 0; - } else if (rc == 0) { - // pcre_exec() returns 0 as a special case when the number of - // capturing subpatterns exceeds the size of the vector. - // When this happens, there is a match and the output vector - // is filled, but we miss out on the positions of the extra subpatterns. - rc = vecsize / 2; - } - - if ((anchor == ANCHOR_BOTH) && (re_full_ == re_partial_)) { - // We need an extra check to make sure that the match extended - // to the end of the input string - assert(vec[0] == 0); // PCRE_ANCHORED forces starting match - if (vec[1] != text.size()) return 0; // Did not get ending match - } - - return rc; -} - -bool RE::DoMatchImpl(const StringPiece& text, - Anchor anchor, - int* consumed, - const Arg* const* args, - int n, - int* vec, - int vecsize) const { - assert((1 + n) * 3 <= vecsize); // results + PCRE workspace - int matches = TryMatch(text, 0, anchor, vec, vecsize); - assert(matches >= 0); // TryMatch never returns negatives - if (matches == 0) - return false; - - *consumed = vec[1]; - - if (n == 0 || args == NULL) { - // We are not interested in results - return true; - } - - if (NumberOfCapturingGroups() < n) { - // RE has fewer capturing groups than number of arg pointers passed in - return false; - } - - // If we got here, we must have matched the whole pattern. - // We do not need (can not do) any more checks on the value of 'matches' here - // -- see the comment for TryMatch. - for (int i = 0; i < n; i++) { - const int start = vec[2*(i+1)]; - const int limit = vec[2*(i+1)+1]; - if (!args[i]->Parse(text.data() + start, limit-start)) { - // TODO: Should we indicate what the error was? - return false; - } - } - - return true; -} - -bool RE::DoMatch(const StringPiece& text, - Anchor anchor, - int* consumed, - const Arg* const args[], - int n) const { - assert(n >= 0); - size_t const vecsize = (1 + n) * 3; // results + PCRE workspace - // (as for kVecSize) - int space[21]; // use stack allocation for small vecsize (common case) - int* vec = vecsize <= 21 ? space : new int[vecsize]; - bool retval = DoMatchImpl(text, anchor, consumed, args, n, vec, vecsize); - if (vec != space) delete [] vec; - return retval; -} - -bool RE::Rewrite(string *out, const StringPiece &rewrite, - const StringPiece &text, int *vec, int veclen) const { - for (const char *s = rewrite.data(), *end = s + rewrite.size(); - s < end; s++) { - int c = *s; - if (c == '\\') { - c = *++s; - if (isdigit(c)) { - int n = (c - '0'); - if (n >= veclen) { - //fprintf(stderr, requested group %d in regexp %.*s\n", - // n, rewrite.size(), rewrite.data()); - return false; - } - int start = vec[2 * n]; - if (start >= 0) - out->append(text.data() + start, vec[2 * n + 1] - start); - } else if (c == '\\') { - out->push_back('\\'); - } else { - //fprintf(stderr, "invalid rewrite pattern: %.*s\n", - // rewrite.size(), rewrite.data()); - return false; - } - } else { - out->push_back(c); - } - } - return true; -} - -// Return the number of capturing subpatterns, or -1 if the -// regexp wasn't valid on construction. -int RE::NumberOfCapturingGroups() const { - if (re_partial_ == NULL) return -1; - - int result; - int pcre_retval = pcre_fullinfo(re_partial_, // The regular expression object - NULL, // We did not study the pattern - PCRE_INFO_CAPTURECOUNT, - &result); - assert(pcre_retval == 0); - return result; -} - -/***** Parsers for various types *****/ - -bool Arg::parse_null(const char* str, int n, void* dest) { - // We fail if somebody asked us to store into a non-NULL void* pointer - return (dest == NULL); -} - -bool Arg::parse_string(const char* str, int n, void* dest) { - reinterpret_cast<string*>(dest)->assign(str, n); - return true; -} - -bool Arg::parse_stringpiece(const char* str, int n, void* dest) { - reinterpret_cast<StringPiece*>(dest)->set(str, n); - return true; -} - -bool Arg::parse_char(const char* str, int n, void* dest) { - if (n != 1) return false; - *(reinterpret_cast<char*>(dest)) = str[0]; - return true; -} - -bool Arg::parse_uchar(const char* str, int n, void* dest) { - if (n != 1) return false; - *(reinterpret_cast<unsigned char*>(dest)) = str[0]; - return true; -} - -// Largest number spec that we are willing to parse -static const int kMaxNumberLength = 32; - -// REQUIRES "buf" must have length at least kMaxNumberLength+1 -// REQUIRES "n > 0" -// Copies "str" into "buf" and null-terminates if necessary. -// Returns one of: -// a. "str" if no termination is needed -// b. "buf" if the string was copied and null-terminated -// c. "" if the input was invalid and has no hope of being parsed -static const char* TerminateNumber(char* buf, const char* str, int n) { - if ((n > 0) && isspace(*str)) { - // We are less forgiving than the strtoxxx() routines and do not - // allow leading spaces. - return ""; - } - - // See if the character right after the input text may potentially - // look like a digit. - if (isdigit(str[n]) || - ((str[n] >= 'a') && (str[n] <= 'f')) || - ((str[n] >= 'A') && (str[n] <= 'F'))) { - if (n > kMaxNumberLength) return ""; // Input too big to be a valid number - memcpy(buf, str, n); - buf[n] = '\0'; - return buf; - } else { - // We can parse right out of the supplied string, so return it. - return str; - } -} - -bool Arg::parse_long_radix(const char* str, - int n, - void* dest, - int radix) { - if (n == 0) return false; - char buf[kMaxNumberLength+1]; - str = TerminateNumber(buf, str, n); - char* end; - errno = 0; - long r = strtol(str, &end, radix); - if (end != str + n) return false; // Leftover junk - if (errno) return false; - *(reinterpret_cast<long*>(dest)) = r; - return true; -} - -bool Arg::parse_ulong_radix(const char* str, - int n, - void* dest, - int radix) { - if (n == 0) return false; - char buf[kMaxNumberLength+1]; - str = TerminateNumber(buf, str, n); - if (str[0] == '-') return false; // strtoul() on a negative number?! - char* end; - errno = 0; - unsigned long r = strtoul(str, &end, radix); - if (end != str + n) return false; // Leftover junk - if (errno) return false; - *(reinterpret_cast<unsigned long*>(dest)) = r; - return true; -} - -bool Arg::parse_short_radix(const char* str, - int n, - void* dest, - int radix) { - long r; - if (!parse_long_radix(str, n, &r, radix)) return false; // Could not parse - if (r < SHRT_MIN || r > SHRT_MAX) return false; // Out of range - *(reinterpret_cast<short*>(dest)) = r; - return true; -} - -bool Arg::parse_ushort_radix(const char* str, - int n, - void* dest, - int radix) { - unsigned long r; - if (!parse_ulong_radix(str, n, &r, radix)) return false; // Could not parse - if (r > USHRT_MAX) return false; // Out of range - *(reinterpret_cast<unsigned short*>(dest)) = r; - return true; -} - -bool Arg::parse_int_radix(const char* str, - int n, - void* dest, - int radix) { - long r; - if (!parse_long_radix(str, n, &r, radix)) return false; // Could not parse - if (r < INT_MIN || r > INT_MAX) return false; // Out of range - *(reinterpret_cast<int*>(dest)) = r; - return true; -} - -bool Arg::parse_uint_radix(const char* str, - int n, - void* dest, - int radix) { - unsigned long r; - if (!parse_ulong_radix(str, n, &r, radix)) return false; // Could not parse - if (r > UINT_MAX) return false; // Out of range - *(reinterpret_cast<unsigned int*>(dest)) = r; - return true; -} - -bool Arg::parse_longlong_radix(const char* str, - int n, - void* dest, - int radix) { -#ifndef HAVE_LONG_LONG - return false; -#else - if (n == 0) return false; - char buf[kMaxNumberLength+1]; - str = TerminateNumber(buf, str, n); - char* end; - errno = 0; -#if defined HAVE_STRTOQ - long long r = strtoq(str, &end, radix); -#elif defined HAVE_STRTOLL - long long r = strtoll(str, &end, radix); -#else -#error parse_longlong_radix: cannot convert input to a long-long -#endif - if (end != str + n) return false; // Leftover junk - if (errno) return false; - *(reinterpret_cast<long long*>(dest)) = r; - return true; -#endif /* HAVE_LONG_LONG */ -} - -bool Arg::parse_ulonglong_radix(const char* str, - int n, - void* dest, - int radix) { -#ifndef HAVE_UNSIGNED_LONG_LONG - return false; -#else - if (n == 0) return false; - char buf[kMaxNumberLength+1]; - str = TerminateNumber(buf, str, n); - if (str[0] == '-') return false; // strtoull() on a negative number?! - char* end; - errno = 0; -#if defined HAVE_STRTOQ - unsigned long long r = strtouq(str, &end, radix); -#elif defined HAVE_STRTOLL - unsigned long long r = strtoull(str, &end, radix); -#else -#error parse_ulonglong_radix: cannot convert input to a long-long -#endif - if (end != str + n) return false; // Leftover junk - if (errno) return false; - *(reinterpret_cast<unsigned long long*>(dest)) = r; - return true; -#endif /* HAVE_UNSIGNED_LONG_LONG */ -} - -bool Arg::parse_double(const char* str, int n, void* dest) { - if (n == 0) return false; - static const int kMaxLength = 200; - char buf[kMaxLength]; - if (n >= kMaxLength) return false; - memcpy(buf, str, n); - buf[n] = '\0'; - errno = 0; - char* end; - double r = strtod(buf, &end); - if (end != buf + n) return false; // Leftover junk - if (errno) return false; - *(reinterpret_cast<double*>(dest)) = r; - return true; -} - -bool Arg::parse_float(const char* str, int n, void* dest) { - double r; - if (!parse_double(str, n, &r)) return false; - *(reinterpret_cast<float*>(dest)) = static_cast<float>(r); - return true; -} - - -#define DEFINE_INTEGER_PARSERS(name) \ - bool Arg::parse_##name(const char* str, int n, void* dest) { \ - return parse_##name##_radix(str, n, dest, 10); \ - } \ - bool Arg::parse_##name##_hex(const char* str, int n, void* dest) { \ - return parse_##name##_radix(str, n, dest, 16); \ - } \ - bool Arg::parse_##name##_octal(const char* str, int n, void* dest) { \ - return parse_##name##_radix(str, n, dest, 8); \ - } \ - bool Arg::parse_##name##_cradix(const char* str, int n, void* dest) { \ - return parse_##name##_radix(str, n, dest, 0); \ - } - -DEFINE_INTEGER_PARSERS(short); -DEFINE_INTEGER_PARSERS(ushort); -DEFINE_INTEGER_PARSERS(int); -DEFINE_INTEGER_PARSERS(uint); -DEFINE_INTEGER_PARSERS(long); -DEFINE_INTEGER_PARSERS(ulong); -DEFINE_INTEGER_PARSERS(longlong); -DEFINE_INTEGER_PARSERS(ulonglong); - -#undef DEFINE_INTEGER_PARSERS - -} // namespace pcrecpp diff --git a/ext/pcre/pcrelib/pcrecpp.h b/ext/pcre/pcrelib/pcrecpp.h deleted file mode 100644 index 5916d86432..0000000000 --- a/ext/pcre/pcrelib/pcrecpp.h +++ /dev/null @@ -1,667 +0,0 @@ -// Copyright (c) 2005, Google Inc. -// All rights reserved. -// -// 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 Google Inc. 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. -// -// Author: Sanjay Ghemawat -// Support for PCRE_XXX modifiers added by Giuseppe Maxia, July 2005 - -#ifndef _PCRECPP_H -#define _PCRECPP_H - -// C++ interface to the pcre regular-expression library. RE supports -// Perl-style regular expressions (with extensions like \d, \w, \s, -// ...). -// -// ----------------------------------------------------------------------- -// REGEXP SYNTAX: -// -// This module is part of the pcre library and hence supports its syntax -// for regular expressions. -// -// The syntax is pretty similar to Perl's. For those not familiar -// with Perl's regular expressions, here are some examples of the most -// commonly used extensions: -// -// "hello (\\w+) world" -- \w matches a "word" character -// "version (\\d+)" -- \d matches a digit -// "hello\\s+world" -- \s matches any whitespace character -// "\\b(\\w+)\\b" -- \b matches empty string at a word boundary -// "(?i)hello" -- (?i) turns on case-insensitive matching -// "/\\*(.*?)\\*/" -- .*? matches . minimum no. of times possible -// -// ----------------------------------------------------------------------- -// MATCHING INTERFACE: -// -// The "FullMatch" operation checks that supplied text matches a -// supplied pattern exactly. -// -// 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. -// -// ----------------------------------------------------------------------- -// MATCHING WITH SUB-STRING EXTRACTION: -// -// You can 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) -// -// ----------------------------------------------------------------------- -// DO_MATCH -// -// 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. -// -// ----------------------------------------------------------------------- -// 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. E.g., "." 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 option 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. -// -// Currently, 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 whitespaces /x -// PCRE_UTF8 handles UTF8 chars built-in -// PCRE_UNGREEDY reverses * and *? N/A -// PCRE_NO_AUTO_CAPTURE disables matching parens N/A (*) -// -// (For a full account on how each modifier works, please check the -// PCRE API reference manual). -// -// (*) Both Perl and PCRE allow non matching parentheses by means of the -// "?:" modifier within the pattern itself. e.g. (?:ab|cd) does not -// capture, while (ab|cd) does. -// -// 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 executation 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 will -// disable match limiting. Alternately, you can set match_limit_recursion() -// which uses PCRE_EXTRA_MATCH_LIMIT_RECURSION to limit how much pcre -// recurses. match_limit() caps the number of matches pcre does; -// match_limit_recrusion() caps the depth of recursion. -// -// 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 -// arguments 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); -// -// But new code is better off doing -// RE(pattern, -// RE_Options().set_caseless(true).set_multiline(true)).PartialMatch(str); -// (See below) -// -// 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 -// appropriate modifier already set: -// CASELESS(), UTF8(), MULTILINE(), DOTALL(), 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. e.g.: 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 pattern. \0 in "rewrite" refers to the entire -// matching text. E.g., -// -// 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, or 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. E.g., -// -// 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. - - -#include <string> -#include <pcrecpparg.h> // defines the Arg class -// These aren't technically needed here, but we include them -// anyway so folks who include pcrecpp.h don't have to include -// all these other header files as well. -#include <pcre.h> -#include <pcre_stringpiece.h> - -namespace pcrecpp { - -#define PCRE_SET_OR_CLEAR(b, o) \ - if (b) all_options_ |= (o); else all_options_ &= ~(o); \ - return *this - -#define PCRE_IS_SET(o) \ - (all_options_ & o) == o - -// We convert user-passed pointers into special Arg objects -extern Arg no_arg; - -/***** Compiling regular expressions: the RE class *****/ - -// RE_Options allow you to set options to be passed along to pcre, -// along with other options we put on top of pcre. -// Only 9 modifiers, plus match_limit and match_limit_recursion, -// are supported now. -class RE_Options { - public: - // constructor - RE_Options() : match_limit_(0), match_limit_recursion_(0), all_options_(0) {} - - // alternative constructor. - // To facilitate transfer of legacy code from C programs - // - // This lets you do - // RE(pattern, RE_Options(PCRE_CASELESS|PCRE_MULTILINE)).PartialMatch(str); - // But new code is better off doing - // RE(pattern, - // RE_Options().set_caseless(true).set_multiline(true)).PartialMatch(str); - RE_Options(int option_flags) : match_limit_(0), match_limit_recursion_(0), - all_options_(option_flags) {} - // we're fine with the default destructor, copy constructor, etc. - - // accessors and mutators - int match_limit() const { return match_limit_; }; - RE_Options &set_match_limit(int limit) { - match_limit_ = limit; - return *this; - } - - int match_limit_recursion() const { return match_limit_recursion_; }; - RE_Options &set_match_limit_recursion(int limit) { - match_limit_recursion_ = limit; - return *this; - } - - bool caseless() const { - return PCRE_IS_SET(PCRE_CASELESS); - } - RE_Options &set_caseless(bool x) { - PCRE_SET_OR_CLEAR(x, PCRE_CASELESS); - } - - bool multiline() const { - return PCRE_IS_SET(PCRE_MULTILINE); - } - RE_Options &set_multiline(bool x) { - PCRE_SET_OR_CLEAR(x, PCRE_MULTILINE); - } - - bool dotall() const { - return PCRE_IS_SET(PCRE_DOTALL); - } - RE_Options &set_dotall(bool x) { - PCRE_SET_OR_CLEAR(x,PCRE_DOTALL); - } - - bool extended() const { - return PCRE_IS_SET(PCRE_EXTENDED); - } - RE_Options &set_extended(bool x) { - PCRE_SET_OR_CLEAR(x,PCRE_EXTENDED); - } - - bool dollar_endonly() const { - return PCRE_IS_SET(PCRE_DOLLAR_ENDONLY); - } - RE_Options &set_dollar_endonly(bool x) { - PCRE_SET_OR_CLEAR(x,PCRE_DOLLAR_ENDONLY); - } - - bool extra() const { - return PCRE_IS_SET( PCRE_EXTRA); - } - RE_Options &set_extra(bool x) { - PCRE_SET_OR_CLEAR(x, PCRE_EXTRA); - } - - bool ungreedy() const { - return PCRE_IS_SET(PCRE_UNGREEDY); - } - RE_Options &set_ungreedy(bool x) { - PCRE_SET_OR_CLEAR(x, PCRE_UNGREEDY); - } - - bool utf8() const { - return PCRE_IS_SET(PCRE_UTF8); - } - RE_Options &set_utf8(bool x) { - PCRE_SET_OR_CLEAR(x, PCRE_UTF8); - } - - bool no_auto_capture() const { - return PCRE_IS_SET(PCRE_NO_AUTO_CAPTURE); - } - RE_Options &set_no_auto_capture(bool x) { - PCRE_SET_OR_CLEAR(x, PCRE_NO_AUTO_CAPTURE); - } - - RE_Options &set_all_options(int opt) { - all_options_ = opt; - return *this; - } - int all_options() const { - return all_options_ ; - } - - // TODO: add other pcre flags - - private: - int match_limit_; - int match_limit_recursion_; - int all_options_; -}; - -// These functions return some common RE_Options -static inline RE_Options UTF8() { - return RE_Options().set_utf8(true); -} - -static inline RE_Options CASELESS() { - return RE_Options().set_caseless(true); -} -static inline RE_Options MULTILINE() { - return RE_Options().set_multiline(true); -} - -static inline RE_Options DOTALL() { - return RE_Options().set_dotall(true); -} - -static inline RE_Options EXTENDED() { - return RE_Options().set_extended(true); -} - -// Interface for regular expression matching. Also corresponds to a -// pre-compiled regular expression. An "RE" object is safe for -// concurrent use by multiple threads. -class RE { - public: - // We provide implicit conversions from strings so that users can - // pass in a string or a "const char*" wherever an "RE" is expected. - RE(const char* pat) { Init(pat, NULL); } - RE(const char *pat, const RE_Options& option) { Init(pat, &option); } - RE(const string& pat) { Init(pat.c_str(), NULL); } - RE(const string& pat, const RE_Options& option) { Init(pat.c_str(), &option); } - - ~RE(); - - // The string specification for this RE. E.g. - // RE re("ab*c?d+"); - // re.pattern(); // "ab*c?d+" - const string& pattern() const { return pattern_; } - - // If RE could not be created properly, returns an error string. - // Else returns the empty string. - const string& error() const { return *error_; } - - /***** The useful part: the matching interface *****/ - - // This is provided so one can do pattern.ReplaceAll() just as - // easily as ReplaceAll(pattern-text, ....) - - bool FullMatch(const StringPiece& text, - const Arg& ptr1 = no_arg, - const Arg& ptr2 = no_arg, - const Arg& ptr3 = no_arg, - const Arg& ptr4 = no_arg, - const Arg& ptr5 = no_arg, - const Arg& ptr6 = no_arg, - const Arg& ptr7 = no_arg, - const Arg& ptr8 = no_arg, - const Arg& ptr9 = no_arg, - const Arg& ptr10 = no_arg, - const Arg& ptr11 = no_arg, - const Arg& ptr12 = no_arg, - const Arg& ptr13 = no_arg, - const Arg& ptr14 = no_arg, - const Arg& ptr15 = no_arg, - const Arg& ptr16 = no_arg) const; - - bool PartialMatch(const StringPiece& text, - const Arg& ptr1 = no_arg, - const Arg& ptr2 = no_arg, - const Arg& ptr3 = no_arg, - const Arg& ptr4 = no_arg, - const Arg& ptr5 = no_arg, - const Arg& ptr6 = no_arg, - const Arg& ptr7 = no_arg, - const Arg& ptr8 = no_arg, - const Arg& ptr9 = no_arg, - const Arg& ptr10 = no_arg, - const Arg& ptr11 = no_arg, - const Arg& ptr12 = no_arg, - const Arg& ptr13 = no_arg, - const Arg& ptr14 = no_arg, - const Arg& ptr15 = no_arg, - const Arg& ptr16 = no_arg) const; - - bool Consume(StringPiece* input, - const Arg& ptr1 = no_arg, - const Arg& ptr2 = no_arg, - const Arg& ptr3 = no_arg, - const Arg& ptr4 = no_arg, - const Arg& ptr5 = no_arg, - const Arg& ptr6 = no_arg, - const Arg& ptr7 = no_arg, - const Arg& ptr8 = no_arg, - const Arg& ptr9 = no_arg, - const Arg& ptr10 = no_arg, - const Arg& ptr11 = no_arg, - const Arg& ptr12 = no_arg, - const Arg& ptr13 = no_arg, - const Arg& ptr14 = no_arg, - const Arg& ptr15 = no_arg, - const Arg& ptr16 = no_arg) const; - - bool FindAndConsume(StringPiece* input, - const Arg& ptr1 = no_arg, - const Arg& ptr2 = no_arg, - const Arg& ptr3 = no_arg, - const Arg& ptr4 = no_arg, - const Arg& ptr5 = no_arg, - const Arg& ptr6 = no_arg, - const Arg& ptr7 = no_arg, - const Arg& ptr8 = no_arg, - const Arg& ptr9 = no_arg, - const Arg& ptr10 = no_arg, - const Arg& ptr11 = no_arg, - const Arg& ptr12 = no_arg, - const Arg& ptr13 = no_arg, - const Arg& ptr14 = no_arg, - const Arg& ptr15 = no_arg, - const Arg& ptr16 = no_arg) const; - - bool Replace(const StringPiece& rewrite, - string *str) const; - - int GlobalReplace(const StringPiece& rewrite, - string *str) const; - - bool Extract(const StringPiece &rewrite, - const StringPiece &text, - string *out) const; - - /***** Generic matching interface *****/ - - // Type of match (TODO: Should be restructured as part of RE_Options) - enum Anchor { - UNANCHORED, // No anchoring - ANCHOR_START, // Anchor at start only - ANCHOR_BOTH // Anchor at start and end - }; - - // General matching routine. Stores the length of the match in - // "*consumed" if successful. - bool DoMatch(const StringPiece& text, - Anchor anchor, - int* consumed, - const Arg* const* args, int n) const; - - // Return the number of capturing subpatterns, or -1 if the - // regexp wasn't valid on construction. - int NumberOfCapturingGroups() const; - - private: - - void Init(const char* pattern, const RE_Options* options); - - // Match against "text", filling in "vec" (up to "vecsize" * 2/3) with - // pairs of integers for the beginning and end positions of matched - // text. The first pair corresponds to the entire matched text; - // subsequent pairs correspond, in order, to parentheses-captured - // matches. Returns the number of pairs (one more than the number of - // the last subpattern with a match) if matching was successful - // and zero if the match failed. - // I.e. for RE("(foo)|(bar)|(baz)") it will return 2, 3, and 4 when matching - // against "foo", "bar", and "baz" respectively. - // When matching RE("(foo)|hello") against "hello", it will return 1. - // But the values for all subpattern are filled in into "vec". - int TryMatch(const StringPiece& text, - int startpos, - Anchor anchor, - int *vec, - int vecsize) const; - - // Append the "rewrite" string, with backslash subsitutions from "text" - // and "vec", to string "out". - bool Rewrite(string *out, - const StringPiece& rewrite, - const StringPiece& text, - int *vec, - int veclen) const; - - // internal implementation for DoMatch - bool DoMatchImpl(const StringPiece& text, - Anchor anchor, - int* consumed, - const Arg* const args[], - int n, - int* vec, - int vecsize) const; - - // Compile the regexp for the specified anchoring mode - pcre* Compile(Anchor anchor); - - string pattern_; - RE_Options options_; - pcre* re_full_; // For full matches - pcre* re_partial_; // For partial matches - const string* error_; // Error indicator (or points to empty string) - - // Don't allow the default copy or assignment constructors -- - // they're expensive and too easy to do by accident. - RE(const RE&); - void operator=(const RE&); -}; - -} // namespace pcrecpp - -#endif /* _PCRECPP_H */ diff --git a/ext/pcre/pcrelib/pcrecpp_unittest.cc b/ext/pcre/pcrelib/pcrecpp_unittest.cc deleted file mode 100644 index ccd876d081..0000000000 --- a/ext/pcre/pcrelib/pcrecpp_unittest.cc +++ /dev/null @@ -1,1116 +0,0 @@ -// Copyright (c) 2005, Google Inc. -// All rights reserved. -// -// 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 Google Inc. 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. -// -// Author: Sanjay Ghemawat -// -// TODO: Test extractions for PartialMatch/Consume - -#include <stdio.h> -#include <cassert> -#include <vector> -#include "config.h" -#include "pcrecpp.h" - -using pcrecpp::StringPiece; -using pcrecpp::RE; -using pcrecpp::RE_Options; -using pcrecpp::Hex; -using pcrecpp::Octal; -using pcrecpp::CRadix; - -static bool VERBOSE_TEST = false; - -// CHECK dies with a fatal error if condition is not true. It is *not* -// controlled by NDEBUG, so the check will be executed regardless of -// compilation mode. Therefore, it is safe to do things like: -// CHECK_EQ(fp->Write(x), 4) -#define CHECK(condition) do { \ - if (!(condition)) { \ - fprintf(stderr, "%s:%d: Check failed: %s\n", \ - __FILE__, __LINE__, #condition); \ - exit(1); \ - } \ -} while (0) - -#define CHECK_EQ(a, b) CHECK(a == b) - -static void Timing1(int num_iters) { - // Same pattern lots of times - RE pattern("ruby:\\d+"); - StringPiece p("ruby:1234"); - for (int j = num_iters; j > 0; j--) { - CHECK(pattern.FullMatch(p)); - } -} - -static void Timing2(int num_iters) { - // Same pattern lots of times - RE pattern("ruby:(\\d+)"); - int i; - for (int j = num_iters; j > 0; j--) { - CHECK(pattern.FullMatch("ruby:1234", &i)); - CHECK_EQ(i, 1234); - } -} - -static void Timing3(int num_iters) { - string text_string; - for (int j = num_iters; j > 0; j--) { - text_string += "this is another line\n"; - } - - RE line_matcher(".*\n"); - string line; - StringPiece text(text_string); - int counter = 0; - while (line_matcher.Consume(&text)) { - counter++; - } - printf("Matched %d lines\n", counter); -} - -#if 0 // uncomment this if you have a way of defining VirtualProcessSize() - -static void LeakTest() { - // Check for memory leaks - unsigned long long initial_size = 0; - for (int i = 0; i < 100000; i++) { - if (i == 50000) { - initial_size = VirtualProcessSize(); - printf("Size after 50000: %llu\n", initial_size); - } - char buf[100]; - snprintf(buf, sizeof(buf), "pat%09d", i); - RE newre(buf); - } - uint64 final_size = VirtualProcessSize(); - printf("Size after 100000: %llu\n", final_size); - const double growth = double(final_size - initial_size) / final_size; - printf("Growth: %0.2f%%", growth * 100); - CHECK(growth < 0.02); // Allow < 2% growth -} - -#endif - -static void RadixTests() { - printf("Testing hex\n"); - -#define CHECK_HEX(type, value) \ - do { \ - type v; \ - CHECK(RE("([0-9a-fA-F]+)[uUlL]*").FullMatch(#value, Hex(&v))); \ - CHECK_EQ(v, 0x ## value); \ - CHECK(RE("([0-9a-fA-FxX]+)[uUlL]*").FullMatch("0x" #value, CRadix(&v))); \ - CHECK_EQ(v, 0x ## value); \ - } while(0) - - CHECK_HEX(short, 2bad); - CHECK_HEX(unsigned short, 2badU); - CHECK_HEX(int, dead); - CHECK_HEX(unsigned int, deadU); - CHECK_HEX(long, 7eadbeefL); - CHECK_HEX(unsigned long, deadbeefUL); -#ifdef HAVE_LONG_LONG - CHECK_HEX(long long, 12345678deadbeefLL); -#endif -#ifdef HAVE_UNSIGNED_LONG_LONG - CHECK_HEX(unsigned long long, cafebabedeadbeefULL); -#endif - -#undef CHECK_HEX - - printf("Testing octal\n"); - -#define CHECK_OCTAL(type, value) \ - do { \ - type v; \ - CHECK(RE("([0-7]+)[uUlL]*").FullMatch(#value, Octal(&v))); \ - CHECK_EQ(v, 0 ## value); \ - CHECK(RE("([0-9a-fA-FxX]+)[uUlL]*").FullMatch("0" #value, CRadix(&v))); \ - CHECK_EQ(v, 0 ## value); \ - } while(0) - - CHECK_OCTAL(short, 77777); - CHECK_OCTAL(unsigned short, 177777U); - CHECK_OCTAL(int, 17777777777); - CHECK_OCTAL(unsigned int, 37777777777U); - CHECK_OCTAL(long, 17777777777L); - CHECK_OCTAL(unsigned long, 37777777777UL); -#ifdef HAVE_LONG_LONG - CHECK_OCTAL(long long, 777777777777777777777LL); -#endif -#ifdef HAVE_UNSIGNED_LONG_LONG - CHECK_OCTAL(unsigned long long, 1777777777777777777777ULL); -#endif - -#undef CHECK_OCTAL - - printf("Testing decimal\n"); - -#define CHECK_DECIMAL(type, value) \ - do { \ - type v; \ - CHECK(RE("(-?[0-9]+)[uUlL]*").FullMatch(#value, &v)); \ - CHECK_EQ(v, value); \ - CHECK(RE("(-?[0-9a-fA-FxX]+)[uUlL]*").FullMatch(#value, CRadix(&v))); \ - CHECK_EQ(v, value); \ - } while(0) - - CHECK_DECIMAL(short, -1); - CHECK_DECIMAL(unsigned short, 9999); - CHECK_DECIMAL(int, -1000); - CHECK_DECIMAL(unsigned int, 12345U); - CHECK_DECIMAL(long, -10000000L); - CHECK_DECIMAL(unsigned long, 3083324652U); -#ifdef HAVE_LONG_LONG - CHECK_DECIMAL(long long, -100000000000000LL); -#endif -#ifdef HAVE_UNSIGNED_LONG_LONG - CHECK_DECIMAL(unsigned long long, 1234567890987654321ULL); -#endif - -#undef CHECK_DECIMAL - -} - -static void TestReplace() { - printf("Testing Replace\n"); - - struct ReplaceTest { - const char *regexp; - const char *rewrite; - const char *original; - const char *single; - const char *global; - }; - static const ReplaceTest tests[] = { - { "(qu|[b-df-hj-np-tv-z]*)([a-z]+)", - "\\2\\1ay", - "the quick brown fox jumps over the lazy dogs.", - "ethay quick brown fox jumps over the lazy dogs.", - "ethay ickquay ownbray oxfay umpsjay overay ethay azylay ogsday." }, - { "\\w+", - "\\0-NOSPAM", - "paul.haahr@google.com", - "paul-NOSPAM.haahr@google.com", - "paul-NOSPAM.haahr-NOSPAM@google-NOSPAM.com-NOSPAM" }, - { "^", - "(START)", - "foo", - "(START)foo", - "(START)foo" }, - { "^", - "(START)", - "", - "(START)", - "(START)" }, - { "$", - "(END)", - "", - "(END)", - "(END)" }, - { "b", - "bb", - "ababababab", - "abbabababab", - "abbabbabbabbabb" }, - { "b", - "bb", - "bbbbbb", - "bbbbbbb", - "bbbbbbbbbbbb" }, - { "b+", - "bb", - "bbbbbb", - "bb", - "bb" }, - { "b*", - "bb", - "bbbbbb", - "bb", - "bb" }, - { "b*", - "bb", - "aaaaa", - "bbaaaaa", - "bbabbabbabbabbabb" }, - { "b*", - "bb", - "aa\naa\n", - "bbaa\naa\n", - "bbabbabb\nbbabbabb\nbb" }, - { "b*", - "bb", - "aa\raa\r", - "bbaa\raa\r", - "bbabbabb\rbbabbabb\rbb" }, - { "b*", - "bb", - "aa\r\naa\r\n", - "bbaa\r\naa\r\n", - "bbabbabb\r\nbbabbabb\r\nbb" }, -#ifdef SUPPORT_UTF8 - { "b*", - "bb", - "\xE3\x83\x9B\xE3\x83\xBC\xE3\x83\xA0\xE3\x81\xB8", // utf8 - "bb\xE3\x83\x9B\xE3\x83\xBC\xE3\x83\xA0\xE3\x81\xB8", - "bb\xE3\x83\x9B""bb""\xE3\x83\xBC""bb""\xE3\x83\xA0""bb""\xE3\x81\xB8""bb" }, - { "b*", - "bb", - "\xE3\x83\x9B\r\n\xE3\x83\xBC\r\xE3\x83\xA0\n\xE3\x81\xB8\r\n", // utf8 - "bb\xE3\x83\x9B\r\n\xE3\x83\xBC\r\xE3\x83\xA0\n\xE3\x81\xB8\r\n", - ("bb\xE3\x83\x9B""bb\r\nbb""\xE3\x83\xBC""bb\rbb""\xE3\x83\xA0" - "bb\nbb""\xE3\x81\xB8""bb\r\nbb") }, -#endif - { "", NULL, NULL, NULL, NULL } - }; - -#ifdef SUPPORT_UTF8 - const bool support_utf8 = true; -#else - const bool support_utf8 = false; -#endif - - for (const ReplaceTest *t = tests; t->original != NULL; ++t) { - RE re(t->regexp, RE_Options(PCRE_NEWLINE_CRLF).set_utf8(support_utf8)); - assert(re.error().empty()); - string one(t->original); - CHECK(re.Replace(t->rewrite, &one)); - CHECK_EQ(one, t->single); - string all(t->original); - CHECK(re.GlobalReplace(t->rewrite, &all) > 0); - CHECK_EQ(all, t->global); - } - - // One final test: test \r\n replacement when we're not in CRLF mode - { - RE re("b*", RE_Options(PCRE_NEWLINE_CR).set_utf8(support_utf8)); - assert(re.error().empty()); - string all("aa\r\naa\r\n"); - CHECK(re.GlobalReplace("bb", &all) > 0); - CHECK_EQ(all, string("bbabbabb\rbb\nbbabbabb\rbb\nbb")); - } - { - RE re("b*", RE_Options(PCRE_NEWLINE_LF).set_utf8(support_utf8)); - assert(re.error().empty()); - string all("aa\r\naa\r\n"); - CHECK(re.GlobalReplace("bb", &all) > 0); - CHECK_EQ(all, string("bbabbabb\rbb\nbbabbabb\rbb\nbb")); - } - // TODO: test what happens when no PCRE_NEWLINE_* flag is set. - // Alas, the answer depends on how pcre was compiled. -} - -static void TestExtract() { - printf("Testing Extract\n"); - - string s; - - CHECK(RE("(.*)@([^.]*)").Extract("\\2!\\1", "boris@kremvax.ru", &s)); - CHECK_EQ(s, "kremvax!boris"); - - // check the RE interface as well - CHECK(RE(".*").Extract("'\\0'", "foo", &s)); - CHECK_EQ(s, "'foo'"); - CHECK(!RE("bar").Extract("'\\0'", "baz", &s)); - CHECK_EQ(s, "'foo'"); -} - -static void TestConsume() { - printf("Testing Consume\n"); - - string word; - - string s(" aaa b!@#$@#$cccc"); - StringPiece input(s); - - RE r("\\s*(\\w+)"); // matches a word, possibly proceeded by whitespace - CHECK(r.Consume(&input, &word)); - CHECK_EQ(word, "aaa"); - CHECK(r.Consume(&input, &word)); - CHECK_EQ(word, "b"); - CHECK(! r.Consume(&input, &word)); -} - -static void TestFindAndConsume() { - printf("Testing FindAndConsume\n"); - - string word; - - string s(" aaa b!@#$@#$cccc"); - StringPiece input(s); - - RE r("(\\w+)"); // matches a word - CHECK(r.FindAndConsume(&input, &word)); - CHECK_EQ(word, "aaa"); - CHECK(r.FindAndConsume(&input, &word)); - CHECK_EQ(word, "b"); - CHECK(r.FindAndConsume(&input, &word)); - CHECK_EQ(word, "cccc"); - CHECK(! r.FindAndConsume(&input, &word)); -} - -static void TestMatchNumberPeculiarity() { - printf("Testing match-number peculiaraity\n"); - - string word1; - string word2; - string word3; - - RE r("(foo)|(bar)|(baz)"); - CHECK(r.PartialMatch("foo", &word1, &word2, &word3)); - CHECK_EQ(word1, "foo"); - CHECK_EQ(word2, ""); - CHECK_EQ(word3, ""); - CHECK(r.PartialMatch("bar", &word1, &word2, &word3)); - CHECK_EQ(word1, ""); - CHECK_EQ(word2, "bar"); - CHECK_EQ(word3, ""); - CHECK(r.PartialMatch("baz", &word1, &word2, &word3)); - CHECK_EQ(word1, ""); - CHECK_EQ(word2, ""); - CHECK_EQ(word3, "baz"); - CHECK(!r.PartialMatch("f", &word1, &word2, &word3)); - - string a; - CHECK(RE("(foo)|hello").FullMatch("hello", &a)); - CHECK_EQ(a, ""); -} - -static void TestRecursion() { - printf("Testing recursion\n"); - - // Get one string that passes (sometimes), one that never does. - string text_good("abcdefghijk"); - string text_bad("acdefghijkl"); - - // According to pcretest, matching text_good against (\w+)*b - // requires match_limit of at least 8192, and match_recursion_limit - // of at least 37. - - RE_Options options_ml; - options_ml.set_match_limit(8192); - RE re("(\\w+)*b", options_ml); - CHECK(re.PartialMatch(text_good) == true); - CHECK(re.PartialMatch(text_bad) == false); - CHECK(re.FullMatch(text_good) == false); - CHECK(re.FullMatch(text_bad) == false); - - options_ml.set_match_limit(1024); - RE re2("(\\w+)*b", options_ml); - CHECK(re2.PartialMatch(text_good) == false); // because of match_limit - CHECK(re2.PartialMatch(text_bad) == false); - CHECK(re2.FullMatch(text_good) == false); - CHECK(re2.FullMatch(text_bad) == false); - - RE_Options options_mlr; - options_mlr.set_match_limit_recursion(50); - RE re3("(\\w+)*b", options_mlr); - CHECK(re3.PartialMatch(text_good) == true); - CHECK(re3.PartialMatch(text_bad) == false); - CHECK(re3.FullMatch(text_good) == false); - CHECK(re3.FullMatch(text_bad) == false); - - options_mlr.set_match_limit_recursion(10); - RE re4("(\\w+)*b", options_mlr); - CHECK(re4.PartialMatch(text_good) == false); - CHECK(re4.PartialMatch(text_bad) == false); - CHECK(re4.FullMatch(text_good) == false); - CHECK(re4.FullMatch(text_bad) == false); -} - -// -// Options tests contributed by -// Giuseppe Maxia, CTO, Stardata s.r.l. -// July 2005 -// -static void GetOneOptionResult( - const char *option_name, - const char *regex, - const char *str, - RE_Options options, - bool full, - string expected) { - - printf("Testing Option <%s>\n", option_name); - if(VERBOSE_TEST) - printf("/%s/ finds \"%s\" within \"%s\" \n", - regex, - expected.c_str(), - str); - string captured(""); - if (full) - RE(regex,options).FullMatch(str, &captured); - else - RE(regex,options).PartialMatch(str, &captured); - CHECK_EQ(captured, expected); -} - -static void TestOneOption( - const char *option_name, - const char *regex, - const char *str, - RE_Options options, - bool full, - bool assertive = true) { - - printf("Testing Option <%s>\n", option_name); - if (VERBOSE_TEST) - printf("'%s' %s /%s/ \n", - str, - (assertive? "matches" : "doesn't match"), - regex); - if (assertive) { - if (full) - CHECK(RE(regex,options).FullMatch(str)); - else - CHECK(RE(regex,options).PartialMatch(str)); - } else { - if (full) - CHECK(!RE(regex,options).FullMatch(str)); - else - CHECK(!RE(regex,options).PartialMatch(str)); - } -} - -static void Test_CASELESS() { - RE_Options options; - RE_Options options2; - - options.set_caseless(true); - TestOneOption("CASELESS (class)", "HELLO", "hello", options, false); - TestOneOption("CASELESS (class2)", "HELLO", "hello", options2.set_caseless(true), false); - TestOneOption("CASELESS (class)", "^[A-Z]+$", "Hello", options, false); - - TestOneOption("CASELESS (function)", "HELLO", "hello", pcrecpp::CASELESS(), false); - TestOneOption("CASELESS (function)", "^[A-Z]+$", "Hello", pcrecpp::CASELESS(), false); - options.set_caseless(false); - TestOneOption("no CASELESS", "HELLO", "hello", options, false, false); -} - -static void Test_MULTILINE() { - RE_Options options; - RE_Options options2; - const char *str = "HELLO\n" "cruel\n" "world\n"; - - options.set_multiline(true); - TestOneOption("MULTILINE (class)", "^cruel$", str, options, false); - TestOneOption("MULTILINE (class2)", "^cruel$", str, options2.set_multiline(true), false); - TestOneOption("MULTILINE (function)", "^cruel$", str, pcrecpp::MULTILINE(), false); - options.set_multiline(false); - TestOneOption("no MULTILINE", "^cruel$", str, options, false, false); -} - -static void Test_DOTALL() { - RE_Options options; - RE_Options options2; - const char *str = "HELLO\n" "cruel\n" "world"; - - options.set_dotall(true); - TestOneOption("DOTALL (class)", "HELLO.*world", str, options, true); - TestOneOption("DOTALL (class2)", "HELLO.*world", str, options2.set_dotall(true), true); - TestOneOption("DOTALL (function)", "HELLO.*world", str, pcrecpp::DOTALL(), true); - options.set_dotall(false); - TestOneOption("no DOTALL", "HELLO.*world", str, options, true, false); -} - -static void Test_DOLLAR_ENDONLY() { - RE_Options options; - RE_Options options2; - const char *str = "HELLO world\n"; - - TestOneOption("no DOLLAR_ENDONLY", "world$", str, options, false); - options.set_dollar_endonly(true); - TestOneOption("DOLLAR_ENDONLY 1", "world$", str, options, false, false); - TestOneOption("DOLLAR_ENDONLY 2", "world$", str, options2.set_dollar_endonly(true), false, false); -} - -static void Test_EXTRA() { - RE_Options options; - const char *str = "HELLO"; - - options.set_extra(true); - TestOneOption("EXTRA 1", "\\HELL\\O", str, options, true, false ); - TestOneOption("EXTRA 2", "\\HELL\\O", str, RE_Options().set_extra(true), true, false ); - options.set_extra(false); - TestOneOption("no EXTRA", "\\HELL\\O", str, options, true ); -} - -static void Test_EXTENDED() { - RE_Options options; - RE_Options options2; - const char *str = "HELLO world"; - - options.set_extended(true); - TestOneOption("EXTENDED (class)", "HELLO world", str, options, false, false); - TestOneOption("EXTENDED (class2)", "HELLO world", str, options2.set_extended(true), false, false); - TestOneOption("EXTENDED (class)", - "^ HE L{2} O " - "\\s+ " - "\\w+ $ ", - str, - options, - false); - - TestOneOption("EXTENDED (function)", "HELLO world", str, pcrecpp::EXTENDED(), false, false); - TestOneOption("EXTENDED (function)", - "^ HE L{2} O " - "\\s+ " - "\\w+ $ ", - str, - pcrecpp::EXTENDED(), - false); - - options.set_extended(false); - TestOneOption("no EXTENDED", "HELLO world", str, options, false); -} - -static void Test_NO_AUTO_CAPTURE() { - RE_Options options; - const char *str = "HELLO world"; - string captured; - - printf("Testing Option <no NO_AUTO_CAPTURE>\n"); - if (VERBOSE_TEST) - printf("parentheses capture text\n"); - RE re("(world|universe)$", options); - CHECK(re.Extract("\\1", str , &captured)); - CHECK_EQ(captured, "world"); - options.set_no_auto_capture(true); - printf("testing Option <NO_AUTO_CAPTURE>\n"); - if (VERBOSE_TEST) - printf("parentheses do not capture text\n"); - re.Extract("\\1",str, &captured ); - CHECK_EQ(captured, "world"); -} - -static void Test_UNGREEDY() { - RE_Options options; - const char *str = "HELLO, 'this' is the 'world'"; - - options.set_ungreedy(true); - GetOneOptionResult("UNGREEDY 1", "('.*')", str, options, false, "'this'" ); - GetOneOptionResult("UNGREEDY 2", "('.*')", str, RE_Options().set_ungreedy(true), false, "'this'" ); - GetOneOptionResult("UNGREEDY", "('.*?')", str, options, false, "'this' is the 'world'" ); - - options.set_ungreedy(false); - GetOneOptionResult("no UNGREEDY", "('.*')", str, options, false, "'this' is the 'world'" ); - GetOneOptionResult("no UNGREEDY", "('.*?')", str, options, false, "'this'" ); -} - -static void Test_all_options() { - const char *str = "HELLO\n" "cruel\n" "world"; - RE_Options options; - options.set_all_options(PCRE_CASELESS | PCRE_DOTALL); - - TestOneOption("all_options (CASELESS|DOTALL)", "^hello.*WORLD", str , options, false); - options.set_all_options(0); - TestOneOption("all_options (0)", "^hello.*WORLD", str , options, false, false); - options.set_all_options(PCRE_MULTILINE | PCRE_EXTENDED); - - TestOneOption("all_options (MULTILINE|EXTENDED)", " ^ c r u e l $ ", str, options, false); - TestOneOption("all_options (MULTILINE|EXTENDED) with constructor", - " ^ c r u e l $ ", - str, - RE_Options(PCRE_MULTILINE | PCRE_EXTENDED), - false); - - TestOneOption("all_options (MULTILINE|EXTENDED) with concatenation", - " ^ c r u e l $ ", - str, - RE_Options() - .set_multiline(true) - .set_extended(true), - false); - - options.set_all_options(0); - TestOneOption("all_options (0)", "^ c r u e l $", str, options, false, false); - -} - -static void TestOptions() { - printf("Testing Options\n"); - Test_CASELESS(); - Test_MULTILINE(); - Test_DOTALL(); - Test_DOLLAR_ENDONLY(); - Test_EXTENDED(); - Test_NO_AUTO_CAPTURE(); - Test_UNGREEDY(); - Test_EXTRA(); - Test_all_options(); -} - -int main(int argc, char** argv) { - // Treat any flag as --help - if (argc > 1 && argv[1][0] == '-') { - printf("Usage: %s [timing1|timing2|timing3 num-iters]\n" - " If 'timingX ###' is specified, run the given timing test\n" - " with the given number of iterations, rather than running\n" - " the default corectness test.\n", argv[0]); - return 0; - } - - if (argc > 1) { - if ( argc == 2 || atoi(argv[2]) == 0) { - printf("timing mode needs a num-iters argument\n"); - return 1; - } - if (!strcmp(argv[1], "timing1")) - Timing1(atoi(argv[2])); - else if (!strcmp(argv[1], "timing2")) - Timing2(atoi(argv[2])); - else if (!strcmp(argv[1], "timing3")) - Timing3(atoi(argv[2])); - else - printf("Unknown argument '%s'\n", argv[1]); - return 0; - } - - printf("Testing FullMatch\n"); - - int i; - string s; - - /***** FullMatch with no args *****/ - - CHECK(RE("h.*o").FullMatch("hello")); - CHECK(!RE("h.*o").FullMatch("othello")); - CHECK(!RE("h.*o").FullMatch("hello!")); - - /***** FullMatch with args *****/ - - // Zero-arg - CHECK(RE("\\d+").FullMatch("1001")); - - // Single-arg - CHECK(RE("(\\d+)").FullMatch("1001", &i)); - CHECK_EQ(i, 1001); - CHECK(RE("(-?\\d+)").FullMatch("-123", &i)); - CHECK_EQ(i, -123); - CHECK(!RE("()\\d+").FullMatch("10", &i)); - CHECK(!RE("(\\d+)").FullMatch("1234567890123456789012345678901234567890", - &i)); - - // Digits surrounding integer-arg - CHECK(RE("1(\\d*)4").FullMatch("1234", &i)); - CHECK_EQ(i, 23); - CHECK(RE("(\\d)\\d+").FullMatch("1234", &i)); - CHECK_EQ(i, 1); - CHECK(RE("(-\\d)\\d+").FullMatch("-1234", &i)); - CHECK_EQ(i, -1); - CHECK(RE("(\\d)").PartialMatch("1234", &i)); - CHECK_EQ(i, 1); - CHECK(RE("(-\\d)").PartialMatch("-1234", &i)); - CHECK_EQ(i, -1); - - // String-arg - CHECK(RE("h(.*)o").FullMatch("hello", &s)); - CHECK_EQ(s, string("ell")); - - // StringPiece-arg - StringPiece sp; - CHECK(RE("(\\w+):(\\d+)").FullMatch("ruby:1234", &sp, &i)); - CHECK_EQ(sp.size(), 4); - CHECK(memcmp(sp.data(), "ruby", 4) == 0); - CHECK_EQ(i, 1234); - - // Multi-arg - CHECK(RE("(\\w+):(\\d+)").FullMatch("ruby:1234", &s, &i)); - CHECK_EQ(s, string("ruby")); - CHECK_EQ(i, 1234); - - // Ignored arg - CHECK(RE("(\\w+)(:)(\\d+)").FullMatch("ruby:1234", &s, (void*)NULL, &i)); - CHECK_EQ(s, string("ruby")); - CHECK_EQ(i, 1234); - - // Type tests - { - char c; - CHECK(RE("(H)ello").FullMatch("Hello", &c)); - CHECK_EQ(c, 'H'); - } - { - unsigned char c; - CHECK(RE("(H)ello").FullMatch("Hello", &c)); - CHECK_EQ(c, static_cast<unsigned char>('H')); - } - { - short v; - CHECK(RE("(-?\\d+)").FullMatch("100", &v)); CHECK_EQ(v, 100); - CHECK(RE("(-?\\d+)").FullMatch("-100", &v)); CHECK_EQ(v, -100); - CHECK(RE("(-?\\d+)").FullMatch("32767", &v)); CHECK_EQ(v, 32767); - CHECK(RE("(-?\\d+)").FullMatch("-32768", &v)); CHECK_EQ(v, -32768); - CHECK(!RE("(-?\\d+)").FullMatch("-32769", &v)); - CHECK(!RE("(-?\\d+)").FullMatch("32768", &v)); - } - { - unsigned short v; - CHECK(RE("(\\d+)").FullMatch("100", &v)); CHECK_EQ(v, 100); - CHECK(RE("(\\d+)").FullMatch("32767", &v)); CHECK_EQ(v, 32767); - CHECK(RE("(\\d+)").FullMatch("65535", &v)); CHECK_EQ(v, 65535); - CHECK(!RE("(\\d+)").FullMatch("65536", &v)); - } - { - int v; - static const int max_value = 0x7fffffff; - static const int min_value = -max_value - 1; - CHECK(RE("(-?\\d+)").FullMatch("100", &v)); CHECK_EQ(v, 100); - CHECK(RE("(-?\\d+)").FullMatch("-100", &v)); CHECK_EQ(v, -100); - CHECK(RE("(-?\\d+)").FullMatch("2147483647", &v)); CHECK_EQ(v, max_value); - CHECK(RE("(-?\\d+)").FullMatch("-2147483648", &v)); CHECK_EQ(v, min_value); - CHECK(!RE("(-?\\d+)").FullMatch("-2147483649", &v)); - CHECK(!RE("(-?\\d+)").FullMatch("2147483648", &v)); - } - { - unsigned int v; - static const unsigned int max_value = 0xfffffffful; - CHECK(RE("(\\d+)").FullMatch("100", &v)); CHECK_EQ(v, 100); - CHECK(RE("(\\d+)").FullMatch("4294967295", &v)); CHECK_EQ(v, max_value); - CHECK(!RE("(\\d+)").FullMatch("4294967296", &v)); - } -#ifdef HAVE_LONG_LONG - { - long long v; - static const long long max_value = 0x7fffffffffffffffLL; - static const long long min_value = -max_value - 1; - char buf[32]; - - CHECK(RE("(-?\\d+)").FullMatch("100", &v)); CHECK_EQ(v, 100); - CHECK(RE("(-?\\d+)").FullMatch("-100",&v)); CHECK_EQ(v, -100); - - snprintf(buf, sizeof(buf), "%lld", max_value); - CHECK(RE("(-?\\d+)").FullMatch(buf,&v)); CHECK_EQ(v, max_value); - - snprintf(buf, sizeof(buf), "%lld", min_value); - CHECK(RE("(-?\\d+)").FullMatch(buf,&v)); CHECK_EQ(v, min_value); - - snprintf(buf, sizeof(buf), "%lld", max_value); - assert(buf[strlen(buf)-1] != '9'); - buf[strlen(buf)-1]++; - CHECK(!RE("(-?\\d+)").FullMatch(buf, &v)); - - snprintf(buf, sizeof(buf), "%lld", min_value); - assert(buf[strlen(buf)-1] != '9'); - buf[strlen(buf)-1]++; - CHECK(!RE("(-?\\d+)").FullMatch(buf, &v)); - } -#endif -#if defined HAVE_UNSIGNED_LONG_LONG && defined HAVE_LONG_LONG - { - unsigned long long v; - long long v2; - static const unsigned long long max_value = 0xffffffffffffffffULL; - char buf[32]; - - CHECK(RE("(-?\\d+)").FullMatch("100",&v)); CHECK_EQ(v, 100); - CHECK(RE("(-?\\d+)").FullMatch("-100",&v2)); CHECK_EQ(v2, -100); - - snprintf(buf, sizeof(buf), "%llu", max_value); - CHECK(RE("(-?\\d+)").FullMatch(buf,&v)); CHECK_EQ(v, max_value); - - assert(buf[strlen(buf)-1] != '9'); - buf[strlen(buf)-1]++; - CHECK(!RE("(-?\\d+)").FullMatch(buf, &v)); - } -#endif - { - float v; - CHECK(RE("(.*)").FullMatch("100", &v)); - CHECK(RE("(.*)").FullMatch("-100.", &v)); - CHECK(RE("(.*)").FullMatch("1e23", &v)); - } - { - double v; - CHECK(RE("(.*)").FullMatch("100", &v)); - CHECK(RE("(.*)").FullMatch("-100.", &v)); - CHECK(RE("(.*)").FullMatch("1e23", &v)); - } - - // Check that matching is fully anchored - CHECK(!RE("(\\d+)").FullMatch("x1001", &i)); - CHECK(!RE("(\\d+)").FullMatch("1001x", &i)); - CHECK(RE("x(\\d+)").FullMatch("x1001", &i)); CHECK_EQ(i, 1001); - CHECK(RE("(\\d+)x").FullMatch("1001x", &i)); CHECK_EQ(i, 1001); - - // Braces - CHECK(RE("[0-9a-f+.-]{5,}").FullMatch("0abcd")); - CHECK(RE("[0-9a-f+.-]{5,}").FullMatch("0abcde")); - CHECK(!RE("[0-9a-f+.-]{5,}").FullMatch("0abc")); - - // Complicated RE - CHECK(RE("foo|bar|[A-Z]").FullMatch("foo")); - CHECK(RE("foo|bar|[A-Z]").FullMatch("bar")); - CHECK(RE("foo|bar|[A-Z]").FullMatch("X")); - CHECK(!RE("foo|bar|[A-Z]").FullMatch("XY")); - - // Check full-match handling (needs '$' tacked on internally) - CHECK(RE("fo|foo").FullMatch("fo")); - CHECK(RE("fo|foo").FullMatch("foo")); - CHECK(RE("fo|foo$").FullMatch("fo")); - CHECK(RE("fo|foo$").FullMatch("foo")); - CHECK(RE("foo$").FullMatch("foo")); - CHECK(!RE("foo\\$").FullMatch("foo$bar")); - CHECK(!RE("fo|bar").FullMatch("fox")); - - // Uncomment the following if we change the handling of '$' to - // prevent it from matching a trailing newline - if (false) { - // Check that we don't get bitten by pcre's special handling of a - // '\n' at the end of the string matching '$' - CHECK(!RE("foo$").PartialMatch("foo\n")); - } - - // Number of args - int a[16]; - CHECK(RE("").FullMatch("")); - - memset(a, 0, sizeof(0)); - CHECK(RE("(\\d){1}").FullMatch("1", - &a[0])); - CHECK_EQ(a[0], 1); - - memset(a, 0, sizeof(0)); - CHECK(RE("(\\d)(\\d)").FullMatch("12", - &a[0], &a[1])); - CHECK_EQ(a[0], 1); - CHECK_EQ(a[1], 2); - - memset(a, 0, sizeof(0)); - CHECK(RE("(\\d)(\\d)(\\d)").FullMatch("123", - &a[0], &a[1], &a[2])); - CHECK_EQ(a[0], 1); - CHECK_EQ(a[1], 2); - CHECK_EQ(a[2], 3); - - memset(a, 0, sizeof(0)); - CHECK(RE("(\\d)(\\d)(\\d)(\\d)").FullMatch("1234", - &a[0], &a[1], &a[2], &a[3])); - CHECK_EQ(a[0], 1); - CHECK_EQ(a[1], 2); - CHECK_EQ(a[2], 3); - CHECK_EQ(a[3], 4); - - memset(a, 0, sizeof(0)); - CHECK(RE("(\\d)(\\d)(\\d)(\\d)(\\d)").FullMatch("12345", - &a[0], &a[1], &a[2], - &a[3], &a[4])); - CHECK_EQ(a[0], 1); - CHECK_EQ(a[1], 2); - CHECK_EQ(a[2], 3); - CHECK_EQ(a[3], 4); - CHECK_EQ(a[4], 5); - - memset(a, 0, sizeof(0)); - CHECK(RE("(\\d)(\\d)(\\d)(\\d)(\\d)(\\d)").FullMatch("123456", - &a[0], &a[1], &a[2], - &a[3], &a[4], &a[5])); - CHECK_EQ(a[0], 1); - CHECK_EQ(a[1], 2); - CHECK_EQ(a[2], 3); - CHECK_EQ(a[3], 4); - CHECK_EQ(a[4], 5); - CHECK_EQ(a[5], 6); - - memset(a, 0, sizeof(0)); - CHECK(RE("(\\d)(\\d)(\\d)(\\d)(\\d)(\\d)(\\d)").FullMatch("1234567", - &a[0], &a[1], &a[2], &a[3], - &a[4], &a[5], &a[6])); - CHECK_EQ(a[0], 1); - CHECK_EQ(a[1], 2); - CHECK_EQ(a[2], 3); - CHECK_EQ(a[3], 4); - CHECK_EQ(a[4], 5); - CHECK_EQ(a[5], 6); - CHECK_EQ(a[6], 7); - - memset(a, 0, sizeof(0)); - CHECK(RE("(\\d)(\\d)(\\d)(\\d)(\\d)(\\d)(\\d)(\\d)" - "(\\d)(\\d)(\\d)(\\d)(\\d)(\\d)(\\d)(\\d)").FullMatch( - "1234567890123456", - &a[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[15])); - CHECK_EQ(a[0], 1); - CHECK_EQ(a[1], 2); - CHECK_EQ(a[2], 3); - CHECK_EQ(a[3], 4); - CHECK_EQ(a[4], 5); - CHECK_EQ(a[5], 6); - CHECK_EQ(a[6], 7); - CHECK_EQ(a[7], 8); - CHECK_EQ(a[8], 9); - CHECK_EQ(a[9], 0); - CHECK_EQ(a[10], 1); - CHECK_EQ(a[11], 2); - CHECK_EQ(a[12], 3); - CHECK_EQ(a[13], 4); - CHECK_EQ(a[14], 5); - CHECK_EQ(a[15], 6); - - /***** PartialMatch *****/ - - printf("Testing PartialMatch\n"); - - CHECK(RE("h.*o").PartialMatch("hello")); - CHECK(RE("h.*o").PartialMatch("othello")); - CHECK(RE("h.*o").PartialMatch("hello!")); - CHECK(RE("((((((((((((((((((((x))))))))))))))))))))").PartialMatch("x")); - - RadixTests(); - TestReplace(); - TestExtract(); - TestConsume(); - TestFindAndConsume(); - TestMatchNumberPeculiarity(); - - // Check the pattern() accessor - { - const string kPattern = "http://([^/]+)/.*"; - const RE re(kPattern); - CHECK_EQ(kPattern, re.pattern()); - } - - // Check RE error field. - { - RE re("foo"); - CHECK(re.error().empty()); // Must have no error - } - -#ifdef SUPPORT_UTF8 - // Check UTF-8 handling - { - printf("Testing UTF-8 handling\n"); - - // Three Japanese characters (nihongo) - const char utf8_string[] = { - 0xe6, 0x97, 0xa5, // 65e5 - 0xe6, 0x9c, 0xac, // 627c - 0xe8, 0xaa, 0x9e, // 8a9e - 0 - }; - const char utf8_pattern[] = { - '.', - 0xe6, 0x9c, 0xac, // 627c - '.', - 0 - }; - - // Both should match in either mode, bytes or UTF-8 - RE re_test1("........."); - CHECK(re_test1.FullMatch(utf8_string)); - RE re_test2("...", pcrecpp::UTF8()); - CHECK(re_test2.FullMatch(utf8_string)); - - // Check that '.' matches one byte or UTF-8 character - // according to the mode. - string ss; - RE re_test3("(.)"); - CHECK(re_test3.PartialMatch(utf8_string, &ss)); - CHECK_EQ(ss, string("\xe6")); - RE re_test4("(.)", pcrecpp::UTF8()); - CHECK(re_test4.PartialMatch(utf8_string, &ss)); - CHECK_EQ(ss, string("\xe6\x97\xa5")); - - // Check that string matches itself in either mode - RE re_test5(utf8_string); - CHECK(re_test5.FullMatch(utf8_string)); - RE re_test6(utf8_string, pcrecpp::UTF8()); - CHECK(re_test6.FullMatch(utf8_string)); - - // Check that pattern matches string only in UTF8 mode - RE re_test7(utf8_pattern); - CHECK(!re_test7.FullMatch(utf8_string)); - RE re_test8(utf8_pattern, pcrecpp::UTF8()); - CHECK(re_test8.FullMatch(utf8_string)); - } - - // Check that ungreedy, UTF8 regular expressions don't match when they - // oughtn't -- see bug 82246. - { - // This code always worked. - const char* pattern = "\\w+X"; - const string target = "a aX"; - RE match_sentence(pattern); - RE match_sentence_re(pattern, pcrecpp::UTF8()); - - CHECK(!match_sentence.FullMatch(target)); - CHECK(!match_sentence_re.FullMatch(target)); - } - - { - const char* pattern = "(?U)\\w+X"; - const string target = "a aX"; - RE match_sentence(pattern); - RE match_sentence_re(pattern, pcrecpp::UTF8()); - - CHECK(!match_sentence.FullMatch(target)); - CHECK(!match_sentence_re.FullMatch(target)); - } -#endif /* def SUPPORT_UTF8 */ - - printf("Testing error reporting\n"); - - { RE re("a\\1"); CHECK(!re.error().empty()); } - { - RE re("a[x"); - CHECK(!re.error().empty()); - } - { - RE re("a[z-a]"); - CHECK(!re.error().empty()); - } - { - RE re("a[[:foobar:]]"); - CHECK(!re.error().empty()); - } - { - RE re("a(b"); - CHECK(!re.error().empty()); - } - { - RE re("a\\"); - CHECK(!re.error().empty()); - } - - // Test that recursion is stopped - TestRecursion(); - - // Test Options - if (getenv("VERBOSE_TEST") != NULL) - VERBOSE_TEST = true; - TestOptions(); - - // Done - printf("OK\n"); - - return 0; -} diff --git a/ext/pcre/pcrelib/pcrecpparg.h b/ext/pcre/pcrelib/pcrecpparg.h deleted file mode 100644 index 323dde58e5..0000000000 --- a/ext/pcre/pcrelib/pcrecpparg.h +++ /dev/null @@ -1,171 +0,0 @@ -// Copyright (c) 2005, Google Inc. -// All rights reserved. -// -// 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 Google Inc. 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. -// -// Author: Sanjay Ghemawat - -#ifndef _PCRECPPARG_H -#define _PCRECPPARG_H - -#include <stdlib.h> // for NULL -#include <string> - -namespace pcrecpp { - -class StringPiece; - -// Hex/Octal/Binary? - -// Special class for parsing into objects that define a ParseFrom() method -template <class T> -class _RE_MatchObject { - public: - static inline bool Parse(const char* str, int n, void* dest) { - T* object = reinterpret_cast<T*>(dest); - return object->ParseFrom(str, n); - } -}; - -class Arg { - public: - // Empty constructor so we can declare arrays of Arg - Arg(); - - // Constructor specially designed for NULL arguments - Arg(void*); - - typedef bool (*Parser)(const char* str, int n, void* dest); - -// Type-specific parsers -#define PCRE_MAKE_PARSER(type,name) \ - Arg(type* p) : arg_(p), parser_(name) { } \ - Arg(type* p, Parser parser) : arg_(p), parser_(parser) { } - - - PCRE_MAKE_PARSER(char, parse_char); - PCRE_MAKE_PARSER(unsigned char, parse_uchar); - PCRE_MAKE_PARSER(short, parse_short); - PCRE_MAKE_PARSER(unsigned short, parse_ushort); - PCRE_MAKE_PARSER(int, parse_int); - PCRE_MAKE_PARSER(unsigned int, parse_uint); - PCRE_MAKE_PARSER(long, parse_long); - PCRE_MAKE_PARSER(unsigned long, parse_ulong); -#if 1 - PCRE_MAKE_PARSER(long long, parse_longlong); -#endif -#if 1 - PCRE_MAKE_PARSER(unsigned long long, parse_ulonglong); -#endif - PCRE_MAKE_PARSER(float, parse_float); - PCRE_MAKE_PARSER(double, parse_double); - PCRE_MAKE_PARSER(std::string, parse_string); - PCRE_MAKE_PARSER(StringPiece, parse_stringpiece); - -#undef PCRE_MAKE_PARSER - - // Generic constructor - template <class T> Arg(T*, Parser parser); - // Generic constructor template - template <class T> Arg(T* p) - : arg_(p), parser_(_RE_MatchObject<T>::Parse) { - } - - // Parse the data - bool Parse(const char* str, int n) const; - - private: - void* arg_; - Parser parser_; - - static bool parse_null (const char* str, int n, void* dest); - static bool parse_char (const char* str, int n, void* dest); - static bool parse_uchar (const char* str, int n, void* dest); - static bool parse_float (const char* str, int n, void* dest); - static bool parse_double (const char* str, int n, void* dest); - static bool parse_string (const char* str, int n, void* dest); - static bool parse_stringpiece (const char* str, int n, void* dest); - -#define PCRE_DECLARE_INTEGER_PARSER(name) \ - private: \ - static bool parse_ ## name(const char* str, int n, void* dest); \ - static bool parse_ ## name ## _radix( \ - const char* str, int n, void* dest, int radix); \ - public: \ - static bool parse_ ## name ## _hex(const char* str, int n, void* dest); \ - static bool parse_ ## name ## _octal(const char* str, int n, void* dest); \ - static bool parse_ ## name ## _cradix(const char* str, int n, void* dest) - - PCRE_DECLARE_INTEGER_PARSER(short); - PCRE_DECLARE_INTEGER_PARSER(ushort); - PCRE_DECLARE_INTEGER_PARSER(int); - PCRE_DECLARE_INTEGER_PARSER(uint); - PCRE_DECLARE_INTEGER_PARSER(long); - PCRE_DECLARE_INTEGER_PARSER(ulong); - PCRE_DECLARE_INTEGER_PARSER(longlong); - PCRE_DECLARE_INTEGER_PARSER(ulonglong); - -#undef PCRE_DECLARE_INTEGER_PARSER -}; - -inline Arg::Arg() : arg_(NULL), parser_(parse_null) { } -inline Arg::Arg(void* p) : arg_(p), parser_(parse_null) { } - -inline bool Arg::Parse(const char* str, int n) const { - return (*parser_)(str, n, arg_); -} - -// This part of the parser, appropriate only for ints, deals with bases -#define MAKE_INTEGER_PARSER(type, name) \ - inline Arg Hex(type* ptr) { \ - return Arg(ptr, Arg::parse_ ## name ## _hex); } \ - inline Arg Octal(type* ptr) { \ - return Arg(ptr, Arg::parse_ ## name ## _octal); } \ - inline Arg CRadix(type* ptr) { \ - return Arg(ptr, Arg::parse_ ## name ## _cradix); } - -MAKE_INTEGER_PARSER(short, short); -MAKE_INTEGER_PARSER(unsigned short, ushort); -MAKE_INTEGER_PARSER(int, int); -MAKE_INTEGER_PARSER(unsigned int, uint); -MAKE_INTEGER_PARSER(long, long); -MAKE_INTEGER_PARSER(unsigned long, ulong); -#if 1 -MAKE_INTEGER_PARSER(long long, longlong); -#endif -#if 1 -MAKE_INTEGER_PARSER(unsigned long long, ulonglong); -#endif - -#undef PCRE_IS_SET -#undef PCRE_SET_OR_CLEAR -#undef MAKE_INTEGER_PARSER - -} // namespace pcrecpp - - -#endif /* _PCRECPPARG_H */ diff --git a/ext/pcre/pcrelib/pcredemo.c b/ext/pcre/pcrelib/pcredemo.c deleted file mode 100644 index 8b06a9ce63..0000000000 --- a/ext/pcre/pcrelib/pcredemo.c +++ /dev/null @@ -1,324 +0,0 @@ -/************************************************* -* 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. - -Compile thuswise: - gcc -Wall pcredemo.c -I/usr/local/include -L/usr/local/lib \ - -R/usr/local/lib -lpcre - -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. -*/ - - -#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; -int erroffset; -int find_all; -int namecount; -int name_entry_size; -int ovector[OVECCOUNT]; -int subject_length; -int rc, i; - - -/************************************************************************** -* 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, set its size to the maximum. 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 * -* first shows 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 and PCRE_ANCHORED flags set. The first * -* of these tells PCRE that an empty string 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 * -* proceed round the loop. * -*************************************************************************/ - -if (!find_all) - { - pcre_free(re); /* Release the memory used for the compiled pattern */ - return 0; /* Finish unless -g was given */ - } - -/* 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 | 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, 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. */ - - if (rc == PCRE_ERROR_NOMATCH) - { - if (options == 0) break; - ovector[1] = start_offset + 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/pcregrep.c b/ext/pcre/pcrelib/pcregrep.c deleted file mode 100644 index 001588be2c..0000000000 --- a/ext/pcre/pcrelib/pcregrep.c +++ /dev/null @@ -1,1758 +0,0 @@ -/************************************************* -* pcregrep program * -*************************************************/ - -/* This is a grep program that uses the PCRE regular expression library to do -its pattern matching. On a Unix or Win32 system it can recurse into -directories. - - Copyright (c) 1997-2006 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. ------------------------------------------------------------------------------ -*/ - -#include <ctype.h> -#include <locale.h> -#include <stdio.h> -#include <string.h> -#include <stdlib.h> -#include <errno.h> - -#include <sys/types.h> -#include <sys/stat.h> -#include <unistd.h> - -#include "config.h" -#include "pcre.h" - -#define FALSE 0 -#define TRUE 1 - -typedef int BOOL; - -#define VERSION "4.3 01-Jun-2006" -#define MAX_PATTERN_COUNT 100 - -#if BUFSIZ > 8192 -#define MBUFTHIRD BUFSIZ -#else -#define MBUFTHIRD 8192 -#endif - - -/* Values for the "filenames" variable, which specifies options for file name -output. The order is important; it is assumed that a file name is wanted for -all values greater than FN_DEFAULT. */ - -enum { FN_NONE, FN_DEFAULT, FN_ONLY, FN_NOMATCH_ONLY, FN_FORCE }; - -/* Actions for the -d and -D options */ - -enum { dee_READ, dee_SKIP, dee_RECURSE }; -enum { DEE_READ, DEE_SKIP }; - -/* Actions for special processing options (flag bits) */ - -#define PO_WORD_MATCH 0x0001 -#define PO_LINE_MATCH 0x0002 -#define PO_FIXED_STRINGS 0x0004 - - - -/************************************************* -* Global variables * -*************************************************/ - -/* Jeffrey Friedl has some debugging requirements that are not part of the -regular code. */ - -#ifdef JFRIEDL_DEBUG -static int S_arg = -1; -static unsigned int jfriedl_XR = 0; /* repeat regex attempt this many times */ -static unsigned int jfriedl_XT = 0; /* replicate text this many times */ -static const char *jfriedl_prefix = ""; -static const char *jfriedl_postfix = ""; -#endif - -static int endlinebyte = '\n'; /* Last byte of endline sequence */ -static int endlineextra = 0; /* Extra bytes for endline sequence */ - -static char *colour_string = (char *)"1;31"; -static char *colour_option = NULL; -static char *dee_option = NULL; -static char *DEE_option = NULL; -static char *newline = NULL; -static char *pattern_filename = NULL; -static char *stdin_name = (char *)"(standard input)"; -static char *locale = NULL; - -static const unsigned char *pcretables = NULL; - -static int pattern_count = 0; -static pcre **pattern_list; -static pcre_extra **hints_list; - -static char *include_pattern = NULL; -static char *exclude_pattern = NULL; - -static pcre *include_compiled = NULL; -static pcre *exclude_compiled = NULL; - -static int after_context = 0; -static int before_context = 0; -static int both_context = 0; -static int dee_action = dee_READ; -static int DEE_action = DEE_READ; -static int error_count = 0; -static int filenames = FN_DEFAULT; -static int process_options = 0; - -static BOOL count_only = FALSE; -static BOOL do_colour = FALSE; -static BOOL hyphenpending = FALSE; -static BOOL invert = FALSE; -static BOOL multiline = FALSE; -static BOOL number = FALSE; -static BOOL only_matching = FALSE; -static BOOL quiet = FALSE; -static BOOL silent = FALSE; - -/* Structure for options and list of them */ - -enum { OP_NODATA, OP_STRING, OP_OP_STRING, OP_NUMBER, OP_OP_NUMBER, - OP_PATLIST }; - -typedef struct option_item { - int type; - int one_char; - void *dataptr; - const char *long_name; - const char *help_text; -} option_item; - -/* Options without a single-letter equivalent get a negative value. This can be -used to identify them. */ - -#define N_COLOUR (-1) -#define N_EXCLUDE (-2) -#define N_HELP (-3) -#define N_INCLUDE (-4) -#define N_LABEL (-5) -#define N_LOCALE (-6) -#define N_NULL (-7) - -static option_item optionlist[] = { - { OP_NODATA, N_NULL, NULL, "", " terminate options" }, - { OP_NODATA, N_HELP, NULL, "help", "display this help and exit" }, - { OP_NUMBER, 'A', &after_context, "after-context=number", "set number of following context lines" }, - { OP_NUMBER, 'B', &before_context, "before-context=number", "set number of prior context lines" }, - { OP_OP_STRING, N_COLOUR, &colour_option, "color=option", "matched text color option" }, - { OP_NUMBER, 'C', &both_context, "context=number", "set number of context lines, before & after" }, - { OP_NODATA, 'c', NULL, "count", "print only a count of matching lines per FILE" }, - { OP_OP_STRING, N_COLOUR, &colour_option, "colour=option", "matched text colour option" }, - { OP_STRING, 'D', &DEE_option, "devices=action","how to handle devices, FIFOs, and sockets" }, - { OP_STRING, 'd', &dee_option, "directories=action", "how to handle directories" }, - { OP_PATLIST, 'e', NULL, "regex(p)", "specify pattern (may be used more than once)" }, - { OP_NODATA, 'F', NULL, "fixed_strings", "patterns are sets of newline-separated strings" }, - { OP_STRING, 'f', &pattern_filename, "file=path", "read patterns from file" }, - { OP_NODATA, 'H', NULL, "with-filename", "force the prefixing filename on output" }, - { OP_NODATA, 'h', NULL, "no-filename", "suppress the prefixing filename on output" }, - { OP_NODATA, 'i', NULL, "ignore-case", "ignore case distinctions" }, - { OP_NODATA, 'l', NULL, "files-with-matches", "print only FILE names containing matches" }, - { OP_NODATA, 'L', NULL, "files-without-match","print only FILE names not containing matches" }, - { OP_STRING, N_LABEL, &stdin_name, "label=name", "set name for standard input" }, - { OP_STRING, N_LOCALE, &locale, "locale=locale", "use the named locale" }, - { OP_NODATA, 'M', NULL, "multiline", "run in multiline mode" }, - { OP_STRING, 'N', &newline, "newline=type", "specify newline type (CR, LR, CRLF)" }, - { OP_NODATA, 'n', NULL, "line-number", "print line number with output lines" }, - { OP_NODATA, 'o', NULL, "only-matching", "show only the part of the line that matched" }, - { OP_NODATA, 'q', NULL, "quiet", "suppress output, just set return code" }, - { OP_NODATA, 'r', NULL, "recursive", "recursively scan sub-directories" }, - { OP_STRING, N_EXCLUDE,&exclude_pattern, "exclude=pattern","exclude matching files when recursing" }, - { OP_STRING, N_INCLUDE,&include_pattern, "include=pattern","include matching files when recursing" }, -#ifdef JFRIEDL_DEBUG - { OP_OP_NUMBER, 'S', &S_arg, "jeffS", "replace matched (sub)string with X" }, -#endif - { OP_NODATA, 's', NULL, "no-messages", "suppress error messages" }, - { OP_NODATA, 'u', NULL, "utf-8", "use UTF-8 mode" }, - { OP_NODATA, 'V', NULL, "version", "print version information and exit" }, - { OP_NODATA, 'v', NULL, "invert-match", "select non-matching lines" }, - { OP_NODATA, 'w', NULL, "word-regex(p)", "force patterns to match only as words" }, - { OP_NODATA, 'x', NULL, "line-regex(p)", "force patterns to match only whole lines" }, - { OP_NODATA, 0, NULL, NULL, NULL } -}; - -/* Tables for prefixing and suffixing patterns, according to the -w, -x, and -F -options. These set the 1, 2, and 4 bits in process_options, respectively. Note -that the combination of -w and -x has the same effect as -x on its own, so we -can treat them as the same. */ - -static const char *prefix[] = { - "", "\\b", "^(?:", "^(?:", "\\Q", "\\b\\Q", "^(?:\\Q", "^(?:\\Q" }; - -static const char *suffix[] = { - "", "\\b", ")$", ")$", "\\E", "\\E\\b", "\\E)$", "\\E)$" }; - - - -/************************************************* -* OS-specific functions * -*************************************************/ - -/* These functions are defined so that they can be made system specific, -although at present the only ones are for Unix, Win32, and for "no support". */ - - -/************* Directory scanning in Unix ***********/ - -#if IS_UNIX -#include <sys/types.h> -#include <sys/stat.h> -#include <dirent.h> - -typedef DIR directory_type; - -static int -isdirectory(char *filename) -{ -struct stat statbuf; -if (stat(filename, &statbuf) < 0) - return 0; /* In the expectation that opening as a file will fail */ -return ((statbuf.st_mode & S_IFMT) == S_IFDIR)? '/' : 0; -} - -static directory_type * -opendirectory(char *filename) -{ -return opendir(filename); -} - -static char * -readdirectory(directory_type *dir) -{ -for (;;) - { - struct dirent *dent = readdir(dir); - if (dent == NULL) return NULL; - if (strcmp(dent->d_name, ".") != 0 && strcmp(dent->d_name, "..") != 0) - return dent->d_name; - } -return NULL; /* Keep compiler happy; never executed */ -} - -static void -closedirectory(directory_type *dir) -{ -closedir(dir); -} - - -/************* Test for regular file in Unix **********/ - -static int -isregfile(char *filename) -{ -struct stat statbuf; -if (stat(filename, &statbuf) < 0) - return 1; /* In the expectation that opening as a file will fail */ -return (statbuf.st_mode & S_IFMT) == S_IFREG; -} - - -/************* Test stdout for being a terminal in Unix **********/ - -static BOOL -is_stdout_tty(void) -{ -return isatty(fileno(stdout)); -} - - -/************* Directory scanning in Win32 ***********/ - -/* I (Philip Hazel) have no means of testing this code. It was contributed by -Lionel Fourquaux. David Burgess added a patch to define INVALID_FILE_ATTRIBUTES -when it did not exist. */ - - -#elif HAVE_WIN32API - -#ifndef STRICT -# define STRICT -#endif -#ifndef WIN32_LEAN_AND_MEAN -# define WIN32_LEAN_AND_MEAN -#endif -#ifndef INVALID_FILE_ATTRIBUTES -#define INVALID_FILE_ATTRIBUTES 0xFFFFFFFF -#endif - -#include <windows.h> - -typedef struct directory_type -{ -HANDLE handle; -BOOL first; -WIN32_FIND_DATA data; -} directory_type; - -int -isdirectory(char *filename) -{ -DWORD attr = GetFileAttributes(filename); -if (attr == INVALID_FILE_ATTRIBUTES) - return 0; -return ((attr & FILE_ATTRIBUTE_DIRECTORY) != 0) ? '/' : 0; -} - -directory_type * -opendirectory(char *filename) -{ -size_t len; -char *pattern; -directory_type *dir; -DWORD err; -len = strlen(filename); -pattern = (char *) malloc(len + 3); -dir = (directory_type *) malloc(sizeof(*dir)); -if ((pattern == NULL) || (dir == NULL)) - { - fprintf(stderr, "pcregrep: malloc failed\n"); - exit(2); - } -memcpy(pattern, filename, len); -memcpy(&(pattern[len]), "\\*", 3); -dir->handle = FindFirstFile(pattern, &(dir->data)); -if (dir->handle != INVALID_HANDLE_VALUE) - { - free(pattern); - dir->first = TRUE; - return dir; - } -err = GetLastError(); -free(pattern); -free(dir); -errno = (err == ERROR_ACCESS_DENIED) ? EACCES : ENOENT; -return NULL; -} - -char * -readdirectory(directory_type *dir) -{ -for (;;) - { - if (!dir->first) - { - if (!FindNextFile(dir->handle, &(dir->data))) - return NULL; - } - else - { - dir->first = FALSE; - } - if (strcmp(dir->data.cFileName, ".") != 0 && strcmp(dir->data.cFileName, "..") != 0) - return dir->data.cFileName; - } -#ifndef _MSC_VER -return NULL; /* Keep compiler happy; never executed */ -#endif -} - -void -closedirectory(directory_type *dir) -{ -FindClose(dir->handle); -free(dir); -} - - -/************* Test for regular file in Win32 **********/ - -/* I don't know how to do this, or if it can be done; assume all paths are -regular if they are not directories. */ - -int isregfile(char *filename) -{ -return !isdirectory(filename) -} - - -/************* Test stdout for being a terminal in Win32 **********/ - -/* I don't know how to do this; assume never */ - -static BOOL -is_stdout_tty(void) -{ -FALSE; -} - - -/************* Directory scanning when we can't do it ***********/ - -/* The type is void, and apart from isdirectory(), the functions do nothing. */ - -#else - -typedef void directory_type; - -int isdirectory(char *filename) { return 0; } -directory_type * opendirectory(char *filename) {} -char *readdirectory(directory_type *dir) {} -void closedirectory(directory_type *dir) {} - - -/************* Test for regular when we can't do it **********/ - -/* Assume all files are regular. */ - -int isregfile(char *filename) { return 1; } - - -/************* Test stdout for being a terminal when we can't do it **********/ - -static BOOL -is_stdout_tty(void) -{ -return FALSE; -} - - -#endif - - - -#if ! HAVE_STRERROR -/************************************************* -* Provide strerror() for non-ANSI libraries * -*************************************************/ - -/* Some old-fashioned systems still around (e.g. SunOS4) don't have strerror() -in their libraries, but can provide the same facility by this simple -alternative function. */ - -extern int sys_nerr; -extern char *sys_errlist[]; - -char * -strerror(int n) -{ -if (n < 0 || n >= sys_nerr) return "unknown error number"; -return sys_errlist[n]; -} -#endif /* HAVE_STRERROR */ - - - -/************************************************* -* Print the previous "after" lines * -*************************************************/ - -/* This is called if we are about to lose said lines because of buffer filling, -and at the end of the file. The data in the line is written using fwrite() so -that a binary zero does not terminate it. - -Arguments: - lastmatchnumber the number of the last matching line, plus one - lastmatchrestart where we restarted after the last match - endptr end of available data - printname filename for printing - -Returns: nothing -*/ - -static void do_after_lines(int lastmatchnumber, char *lastmatchrestart, - char *endptr, char *printname) -{ -if (after_context > 0 && lastmatchnumber > 0) - { - int count = 0; - while (lastmatchrestart < endptr && count++ < after_context) - { - char *pp = lastmatchrestart; - if (printname != NULL) fprintf(stdout, "%s-", printname); - if (number) fprintf(stdout, "%d-", lastmatchnumber++); - while (*pp != endlinebyte) pp++; - fwrite(lastmatchrestart, 1, pp - lastmatchrestart + (1 + endlineextra), - stdout); - lastmatchrestart = pp + 1; - } - hyphenpending = TRUE; - } -} - - - -/************************************************* -* Grep an individual file * -*************************************************/ - -/* This is called from grep_or_recurse() below. It uses a buffer that is three -times the value of MBUFTHIRD. The matching point is never allowed to stray into -the top third of the buffer, thus keeping more of the file available for -context printing or for multiline scanning. For large files, the pointer will -be in the middle third most of the time, so the bottom third is available for -"before" context printing. - -Arguments: - in the fopened FILE stream - printname the file name if it is to be printed for each match - or NULL if the file name is not to be printed - it cannot be NULL if filenames[_nomatch]_only is set - -Returns: 0 if there was at least one match - 1 otherwise (no matches) -*/ - -static int -pcregrep(FILE *in, char *printname) -{ -int rc = 1; -int linenumber = 1; -int lastmatchnumber = 0; -int count = 0; -int offsets[99]; -char *lastmatchrestart = NULL; -char buffer[3*MBUFTHIRD]; -char *ptr = buffer; -char *endptr; -size_t bufflength; -BOOL endhyphenpending = FALSE; - -/* Do the first read into the start of the buffer and set up the pointer to -end of what we have. */ - -bufflength = fread(buffer, 1, 3*MBUFTHIRD, in); -endptr = buffer + bufflength; - -/* Loop while the current pointer is not at the end of the file. For large -files, endptr will be at the end of the buffer when we are in the middle of the -file, but ptr will never get there, because as soon as it gets over 2/3 of the -way, the buffer is shifted left and re-filled. */ - -while (ptr < endptr) - { - int i; - int mrc = 0; - BOOL match = FALSE; - char *t = ptr; - size_t length, linelength; - - /* At this point, ptr is at the start of a line. We need to find the length - of the subject string to pass to pcre_exec(). In multiline mode, it is the - length remainder of the data in the buffer. Otherwise, it is the length of - the next line. After matching, we always advance by the length of the next - line. In multiline mode the PCRE_FIRSTLINE option is used for compiling, so - that any match is constrained to be in the first line. */ - - linelength = 0; - while (t < endptr && *t++ != endlinebyte) linelength++; - length = multiline? endptr - ptr : linelength; - - - /* Extra processing for Jeffrey Friedl's debugging. */ - -#ifdef JFRIEDL_DEBUG - if (jfriedl_XT || jfriedl_XR) - { - #include <sys/time.h> - #include <time.h> - struct timeval start_time, end_time; - struct timezone dummy; - - if (jfriedl_XT) - { - unsigned long newlen = length * jfriedl_XT + strlen(jfriedl_prefix) + strlen(jfriedl_postfix); - const char *orig = ptr; - ptr = malloc(newlen + 1); - if (!ptr) { - printf("out of memory"); - exit(2); - } - endptr = ptr; - strcpy(endptr, jfriedl_prefix); endptr += strlen(jfriedl_prefix); - for (i = 0; i < jfriedl_XT; i++) { - strncpy(endptr, orig, length); - endptr += length; - } - strcpy(endptr, jfriedl_postfix); endptr += strlen(jfriedl_postfix); - length = newlen; - } - - if (gettimeofday(&start_time, &dummy) != 0) - perror("bad gettimeofday"); - - - for (i = 0; i < jfriedl_XR; i++) - match = (pcre_exec(pattern_list[0], hints_list[0], ptr, length, 0, 0, offsets, 99) >= 0); - - if (gettimeofday(&end_time, &dummy) != 0) - perror("bad gettimeofday"); - - double delta = ((end_time.tv_sec + (end_time.tv_usec / 1000000.0)) - - - (start_time.tv_sec + (start_time.tv_usec / 1000000.0))); - - printf("%s TIMER[%.4f]\n", match ? "MATCH" : "FAIL", delta); - return 0; - } -#endif - - - /* Run through all the patterns until one matches. Note that we don't include - the final newline in the subject string. */ - - for (i = 0; i < pattern_count; i++) - { - mrc = pcre_exec(pattern_list[i], hints_list[i], ptr, length, 0, 0, - offsets, 99); - if (mrc >= 0) { match = TRUE; break; } - if (mrc != PCRE_ERROR_NOMATCH) - { - fprintf(stderr, "pcregrep: pcre_exec() error %d while matching ", mrc); - if (pattern_count > 1) fprintf(stderr, "pattern number %d to ", i+1); - fprintf(stderr, "this line:\n"); - fwrite(ptr, 1, linelength, stderr); /* In case binary zero included */ - fprintf(stderr, "\n"); - if (error_count == 0 && - (mrc == PCRE_ERROR_MATCHLIMIT || mrc == PCRE_ERROR_RECURSIONLIMIT)) - { - fprintf(stderr, "pcregrep: error %d means that a resource limit " - "was exceeded\n", mrc); - fprintf(stderr, "pcregrep: check your regex for nested unlimited loops\n"); - } - if (error_count++ > 20) - { - fprintf(stderr, "pcregrep: too many errors - abandoned\n"); - exit(2); - } - match = invert; /* No more matching; don't show the line again */ - break; - } - } - - /* If it's a match or a not-match (as required), do what's wanted. */ - - if (match != invert) - { - BOOL hyphenprinted = FALSE; - - /* We've failed if we want a file that doesn't have any matches. */ - - if (filenames == FN_NOMATCH_ONLY) return 1; - - /* Just count if just counting is wanted. */ - - if (count_only) count++; - - /* If all we want is a file name, there is no need to scan any more lines - in the file. */ - - else if (filenames == FN_ONLY) - { - fprintf(stdout, "%s\n", printname); - return 0; - } - - /* Likewise, if all we want is a yes/no answer. */ - - else if (quiet) return 0; - - /* The --only-matching option prints just the substring that matched, and - does not pring any context. */ - - else if (only_matching) - { - if (printname != NULL) fprintf(stdout, "%s:", printname); - if (number) fprintf(stdout, "%d:", linenumber); - fwrite(ptr + offsets[0], 1, offsets[1] - offsets[0], stdout); - fprintf(stdout, "\n"); - } - - /* This is the default case when none of the above options is set. We print - the matching lines(s), possibly preceded and/or followed by other lines of - context. */ - - else - { - /* See if there is a requirement to print some "after" lines from a - previous match. We never print any overlaps. */ - - if (after_context > 0 && lastmatchnumber > 0) - { - int linecount = 0; - char *p = lastmatchrestart; - - while (p < ptr && linecount < after_context) - { - while (*p != endlinebyte) p++; - p++; - linecount++; - } - - /* It is important to advance lastmatchrestart during this printing so - that it interacts correctly with any "before" printing below. Print - each line's data using fwrite() in case there are binary zeroes. */ - - while (lastmatchrestart < p) - { - char *pp = lastmatchrestart; - if (printname != NULL) fprintf(stdout, "%s-", printname); - if (number) fprintf(stdout, "%d-", lastmatchnumber++); - while (*pp != endlinebyte) pp++; - fwrite(lastmatchrestart, 1, pp - lastmatchrestart + - (1 + endlineextra), stdout); - lastmatchrestart = pp + 1; - } - if (lastmatchrestart != ptr) hyphenpending = TRUE; - } - - /* If there were non-contiguous lines printed above, insert hyphens. */ - - if (hyphenpending) - { - fprintf(stdout, "--\n"); - hyphenpending = FALSE; - hyphenprinted = TRUE; - } - - /* See if there is a requirement to print some "before" lines for this - match. Again, don't print overlaps. */ - - if (before_context > 0) - { - int linecount = 0; - char *p = ptr; - - while (p > buffer && (lastmatchnumber == 0 || p > lastmatchrestart) && - linecount < before_context) - { - linecount++; - p--; - while (p > buffer && p[-1] != endlinebyte) p--; - } - - if (lastmatchnumber > 0 && p > lastmatchrestart && !hyphenprinted) - fprintf(stdout, "--\n"); - - while (p < ptr) - { - char *pp = p; - if (printname != NULL) fprintf(stdout, "%s-", printname); - if (number) fprintf(stdout, "%d-", linenumber - linecount--); - while (*pp != endlinebyte) pp++; - fwrite(p, 1, pp - p + (1 + endlineextra), stdout); - p = pp + 1; - } - } - - /* Now print the matching line(s); ensure we set hyphenpending at the end - of the file if any context lines are being output. */ - - if (after_context > 0 || before_context > 0) - endhyphenpending = TRUE; - - if (printname != NULL) fprintf(stdout, "%s:", printname); - if (number) fprintf(stdout, "%d:", linenumber); - - /* In multiline mode, we want to print to the end of the line in which - the end of the matched string is found, so we adjust linelength and the - line number appropriately. Because the PCRE_FIRSTLINE option is set, the - start of the match will always be before the first newline sequence. */ - - if (multiline) - { - char *endmatch = ptr + offsets[1]; - t = ptr; - while (t < endmatch) { if (*t++ == endlinebyte) linenumber++; } - while (endmatch < endptr && *endmatch != endlinebyte) endmatch++; - linelength = endmatch - ptr; - } - - /*** NOTE: Use only fwrite() to output the data line, so that binary - zeroes are treated as just another data character. */ - - /* This extra option, for Jeffrey Friedl's debugging requirements, - replaces the matched string, or a specific captured string if it exists, - with X. When this happens, colouring is ignored. */ - -#ifdef JFRIEDL_DEBUG - if (S_arg >= 0 && S_arg < mrc) - { - int first = S_arg * 2; - int last = first + 1; - fwrite(ptr, 1, offsets[first], stdout); - fprintf(stdout, "X"); - fwrite(ptr + offsets[last], 1, linelength - offsets[last], stdout); - } - else -#endif - - /* We have to split the line(s) up if colouring. */ - - if (do_colour) - { - fwrite(ptr, 1, offsets[0], stdout); - fprintf(stdout, "%c[%sm", 0x1b, colour_string); - fwrite(ptr + offsets[0], 1, offsets[1] - offsets[0], stdout); - fprintf(stdout, "%c[00m", 0x1b); - fwrite(ptr + offsets[1], 1, linelength - offsets[1], stdout); - } - else fwrite(ptr, 1, linelength, stdout); - - fprintf(stdout, "\n"); - } - - /* End of doing what has to be done for a match */ - - rc = 0; /* Had some success */ - - /* Remember where the last match happened for after_context. We remember - where we are about to restart, and that line's number. */ - - lastmatchrestart = ptr + linelength + 1; - lastmatchnumber = linenumber + 1; - } - - /* Advance to after the newline and increment the line number. */ - - ptr += linelength + 1; - linenumber++; - - /* If we haven't yet reached the end of the file (the buffer is full), and - the current point is in the top 1/3 of the buffer, slide the buffer down by - 1/3 and refill it. Before we do this, if some unprinted "after" lines are - about to be lost, print them. */ - - if (bufflength >= sizeof(buffer) && ptr > buffer + 2*MBUFTHIRD) - { - if (after_context > 0 && - lastmatchnumber > 0 && - lastmatchrestart < buffer + MBUFTHIRD) - { - do_after_lines(lastmatchnumber, lastmatchrestart, endptr, printname); - lastmatchnumber = 0; - } - - /* Now do the shuffle */ - - memmove(buffer, buffer + MBUFTHIRD, 2*MBUFTHIRD); - ptr -= MBUFTHIRD; - bufflength = 2*MBUFTHIRD + fread(buffer + 2*MBUFTHIRD, 1, MBUFTHIRD, in); - endptr = buffer + bufflength; - - /* Adjust any last match point */ - - if (lastmatchnumber > 0) lastmatchrestart -= MBUFTHIRD; - } - } /* Loop through the whole file */ - -/* End of file; print final "after" lines if wanted; do_after_lines sets -hyphenpending if it prints something. */ - -if (!only_matching && !count_only) - { - do_after_lines(lastmatchnumber, lastmatchrestart, endptr, printname); - hyphenpending |= endhyphenpending; - } - -/* Print the file name if we are looking for those without matches and there -were none. If we found a match, we won't have got this far. */ - -if (filenames == FN_NOMATCH_ONLY) - { - fprintf(stdout, "%s\n", printname); - return 0; - } - -/* Print the match count if wanted */ - -if (count_only) - { - if (printname != NULL) fprintf(stdout, "%s:", printname); - fprintf(stdout, "%d\n", count); - } - -return rc; -} - - - -/************************************************* -* Grep a file or recurse into a directory * -*************************************************/ - -/* Given a path name, if it's a directory, scan all the files if we are -recursing; if it's a file, grep it. - -Arguments: - pathname the path to investigate - dir_recurse TRUE if recursing is wanted (-r or -drecurse) - only_one_at_top TRUE if the path is the only one at toplevel - -Returns: 0 if there was at least one match - 1 if there were no matches - 2 there was some kind of error - -However, file opening failures are suppressed if "silent" is set. -*/ - -static int -grep_or_recurse(char *pathname, BOOL dir_recurse, BOOL only_one_at_top) -{ -int rc = 1; -int sep; -FILE *in; - -/* If the file name is "-" we scan stdin */ - -if (strcmp(pathname, "-") == 0) - { - return pcregrep(stdin, - (filenames > FN_DEFAULT || (filenames == FN_DEFAULT && !only_one_at_top))? - stdin_name : NULL); - } - - -/* If the file is a directory, skip if skipping or if we are recursing, scan -each file within it, subject to any include or exclude patterns that were set. -The scanning code is localized so it can be made system-specific. */ - -if ((sep = isdirectory(pathname)) != 0) - { - if (dee_action == dee_SKIP) return 1; - if (dee_action == dee_RECURSE) - { - char buffer[1024]; - char *nextfile; - directory_type *dir = opendirectory(pathname); - - if (dir == NULL) - { - if (!silent) - fprintf(stderr, "pcregrep: Failed to open directory %s: %s\n", pathname, - strerror(errno)); - return 2; - } - - while ((nextfile = readdirectory(dir)) != NULL) - { - int frc, blen; - sprintf(buffer, "%.512s%c%.128s", pathname, sep, nextfile); - blen = strlen(buffer); - - if (exclude_compiled != NULL && - pcre_exec(exclude_compiled, NULL, buffer, blen, 0, 0, NULL, 0) >= 0) - continue; - - if (include_compiled != NULL && - pcre_exec(include_compiled, NULL, buffer, blen, 0, 0, NULL, 0) < 0) - continue; - - frc = grep_or_recurse(buffer, dir_recurse, FALSE); - if (frc > 1) rc = frc; - else if (frc == 0 && rc == 1) rc = 0; - } - - closedirectory(dir); - return rc; - } - } - -/* If the file is not a directory and not a regular file, skip it if that's -been requested. */ - -else if (!isregfile(pathname) && DEE_action == DEE_SKIP) return 1; - -/* Control reaches here if we have a regular file, or if we have a directory -and recursion or skipping was not requested, or if we have anything else and -skipping was not requested. The scan proceeds. If this is the first and only -argument at top level, we don't show the file name, unless we are only showing -the file name, or the filename was forced (-H). */ - -in = fopen(pathname, "r"); -if (in == NULL) - { - if (!silent) - fprintf(stderr, "pcregrep: Failed to open %s: %s\n", pathname, - strerror(errno)); - return 2; - } - -rc = pcregrep(in, (filenames > FN_DEFAULT || - (filenames == FN_DEFAULT && !only_one_at_top))? pathname : NULL); - -fclose(in); -return rc; -} - - - - -/************************************************* -* Usage function * -*************************************************/ - -static int -usage(int rc) -{ -option_item *op; -fprintf(stderr, "Usage: pcregrep [-"); -for (op = optionlist; op->one_char != 0; op++) - { - if (op->one_char > 0) fprintf(stderr, "%c", op->one_char); - } -fprintf(stderr, "] [long options] [pattern] [files]\n"); -fprintf(stderr, "Type `pcregrep --help' for more information.\n"); -return rc; -} - - - - -/************************************************* -* Help function * -*************************************************/ - -static void -help(void) -{ -option_item *op; - -printf("Usage: pcregrep [OPTION]... [PATTERN] [FILE1 FILE2 ...]\n"); -printf("Search for PATTERN in each FILE or standard input.\n"); -printf("PATTERN must be present if neither -e nor -f is used.\n"); -printf("\"-\" can be used as a file name to mean STDIN.\n\n"); -printf("Example: pcregrep -i 'hello.*world' menu.h main.c\n\n"); - -printf("Options:\n"); - -for (op = optionlist; op->one_char != 0; op++) - { - int n; - char s[4]; - if (op->one_char > 0) sprintf(s, "-%c,", op->one_char); else strcpy(s, " "); - printf(" %s --%s%n", s, op->long_name, &n); - n = 30 - n; - if (n < 1) n = 1; - printf("%.*s%s\n", n, " ", op->help_text); - } - -printf("\nWhen reading patterns from a file instead of using a command line option,\n"); -printf("trailing white space is removed and blank lines are ignored.\n"); -printf("There is a maximum of %d patterns.\n", MAX_PATTERN_COUNT); - -printf("\nWith no FILEs, read standard input. If fewer than two FILEs given, assume -h.\n"); -printf("Exit status is 0 if any matches, 1 if no matches, and 2 if trouble.\n"); -} - - - - -/************************************************* -* Handle a single-letter, no data option * -*************************************************/ - -static int -handle_option(int letter, int options) -{ -switch(letter) - { - case N_HELP: help(); exit(0); - case 'c': count_only = TRUE; break; - case 'F': process_options |= PO_FIXED_STRINGS; break; - case 'H': filenames = FN_FORCE; break; - case 'h': filenames = FN_NONE; break; - case 'i': options |= PCRE_CASELESS; break; - case 'l': filenames = FN_ONLY; break; - case 'L': filenames = FN_NOMATCH_ONLY; break; - case 'M': multiline = TRUE; options |= PCRE_MULTILINE|PCRE_FIRSTLINE; break; - case 'n': number = TRUE; break; - case 'o': only_matching = TRUE; break; - case 'q': quiet = TRUE; break; - case 'r': dee_action = dee_RECURSE; break; - case 's': silent = TRUE; break; - case 'u': options |= PCRE_UTF8; break; - case 'v': invert = TRUE; break; - case 'w': process_options |= PO_WORD_MATCH; break; - case 'x': process_options |= PO_LINE_MATCH; break; - - case 'V': - fprintf(stderr, "pcregrep version %s using ", VERSION); - fprintf(stderr, "PCRE version %s\n", pcre_version()); - exit(0); - break; - - default: - fprintf(stderr, "pcregrep: Unknown option -%c\n", letter); - exit(usage(2)); - } - -return options; -} - - - - -/************************************************* -* Construct printed ordinal * -*************************************************/ - -/* This turns a number into "1st", "3rd", etc. */ - -static char * -ordin(int n) -{ -static char buffer[8]; -char *p = buffer; -sprintf(p, "%d", n); -while (*p != 0) p++; -switch (n%10) - { - case 1: strcpy(p, "st"); break; - case 2: strcpy(p, "nd"); break; - case 3: strcpy(p, "rd"); break; - default: strcpy(p, "th"); break; - } -return buffer; -} - - - -/************************************************* -* Compile a single pattern * -*************************************************/ - -/* When the -F option has been used, this is called for each substring. -Otherwise it's called for each supplied pattern. - -Arguments: - pattern the pattern string - options the PCRE options - filename the file name, or NULL for a command-line pattern - count 0 if this is the only command line pattern, or - number of the command line pattern, or - linenumber for a pattern from a file - -Returns: TRUE on success, FALSE after an error -*/ - -static BOOL -compile_single_pattern(char *pattern, int options, char *filename, int count) -{ -char buffer[MBUFTHIRD + 16]; -const char *error; -int errptr; - -if (pattern_count >= MAX_PATTERN_COUNT) - { - fprintf(stderr, "pcregrep: Too many %spatterns (max %d)\n", - (filename == NULL)? "command-line " : "", MAX_PATTERN_COUNT); - return FALSE; - } - -sprintf(buffer, "%s%.*s%s", prefix[process_options], MBUFTHIRD, pattern, - suffix[process_options]); -pattern_list[pattern_count] = - pcre_compile(buffer, options, &error, &errptr, pcretables); -if (pattern_list[pattern_count++] != NULL) return TRUE; - -/* Handle compile errors */ - -errptr -= (int)strlen(prefix[process_options]); -if (errptr > (int)strlen(pattern)) errptr = (int)strlen(pattern); - -if (filename == NULL) - { - if (count == 0) - fprintf(stderr, "pcregrep: Error in command-line regex " - "at offset %d: %s\n", errptr, error); - else - fprintf(stderr, "pcregrep: Error in %s command-line regex " - "at offset %d: %s\n", ordin(count), errptr, error); - } -else - { - fprintf(stderr, "pcregrep: Error in regex in line %d of %s " - "at offset %d: %s\n", count, filename, errptr, error); - } - -return FALSE; -} - - - -/************************************************* -* Compile one supplied pattern * -*************************************************/ - -/* When the -F option has been used, each string may be a list of strings, -separated by line breaks. They will be matched literally. - -Arguments: - pattern the pattern string - options the PCRE options - filename the file name, or NULL for a command-line pattern - count 0 if this is the only command line pattern, or - number of the command line pattern, or - linenumber for a pattern from a file - -Returns: TRUE on success, FALSE after an error -*/ - -static BOOL -compile_pattern(char *pattern, int options, char *filename, int count) -{ -if ((process_options & PO_FIXED_STRINGS) != 0) - { - char buffer[MBUFTHIRD]; - for(;;) - { - char *p = strchr(pattern, endlinebyte); - if (p == NULL) - return compile_single_pattern(pattern, options, filename, count); - sprintf(buffer, "%.*s", p - pattern - endlineextra, pattern); - pattern = p + 1; - if (!compile_single_pattern(buffer, options, filename, count)) - return FALSE; - } - } -else return compile_single_pattern(pattern, options, filename, count); -} - - - -/************************************************* -* Main program * -*************************************************/ - -/* Returns 0 if something matched, 1 if nothing matched, 2 after an error. */ - -int -main(int argc, char **argv) -{ -int i, j; -int rc = 1; -int pcre_options = 0; -int cmd_pattern_count = 0; -int errptr; -BOOL only_one_at_top; -char *patterns[MAX_PATTERN_COUNT]; -const char *locale_from = "--locale"; -const char *error; - -/* Set the default line ending value from the default in the PCRE library. */ - -(void)pcre_config(PCRE_CONFIG_NEWLINE, &i); -switch(i) - { - default: newline = (char *)"lf"; break; - case '\r': newline = (char *)"cr"; break; - case ('\r' << 8) | '\n': newline = (char *)"crlf"; break; - } - -/* Process the options */ - -for (i = 1; i < argc; i++) - { - option_item *op = NULL; - char *option_data = (char *)""; /* default to keep compiler happy */ - BOOL longop; - BOOL longopwasequals = FALSE; - - if (argv[i][0] != '-') break; - - /* If we hit an argument that is just "-", it may be a reference to STDIN, - but only if we have previously had -e or -f to define the patterns. */ - - if (argv[i][1] == 0) - { - if (pattern_filename != NULL || pattern_count > 0) break; - else exit(usage(2)); - } - - /* Handle a long name option, or -- to terminate the options */ - - if (argv[i][1] == '-') - { - char *arg = argv[i] + 2; - char *argequals = strchr(arg, '='); - - if (*arg == 0) /* -- terminates options */ - { - i++; - break; /* out of the options-handling loop */ - } - - longop = TRUE; - - /* Some long options have data that follows after =, for example file=name. - Some options have variations in the long name spelling: specifically, we - allow "regexp" because GNU grep allows it, though I personally go along - with Jeffrey Friedl and Larry Wall in preferring "regex" without the "p". - These options are entered in the table as "regex(p)". No option is in both - these categories, fortunately. */ - - for (op = optionlist; op->one_char != 0; op++) - { - char *opbra = strchr(op->long_name, '('); - char *equals = strchr(op->long_name, '='); - if (opbra == NULL) /* Not a (p) case */ - { - if (equals == NULL) /* Not thing=data case */ - { - if (strcmp(arg, op->long_name) == 0) break; - } - else /* Special case xxx=data */ - { - int oplen = equals - op->long_name; - int arglen = (argequals == NULL)? strlen(arg) : argequals - arg; - if (oplen == arglen && strncmp(arg, op->long_name, oplen) == 0) - { - option_data = arg + arglen; - if (*option_data == '=') - { - option_data++; - longopwasequals = TRUE; - } - break; - } - } - } - else /* Special case xxxx(p) */ - { - char buff1[24]; - char buff2[24]; - int baselen = opbra - op->long_name; - sprintf(buff1, "%.*s", baselen, op->long_name); - sprintf(buff2, "%s%.*s", buff1, strlen(op->long_name) - baselen - 2, - opbra + 1); - if (strcmp(arg, buff1) == 0 || strcmp(arg, buff2) == 0) - break; - } - } - - if (op->one_char == 0) - { - fprintf(stderr, "pcregrep: Unknown option %s\n", argv[i]); - exit(usage(2)); - } - } - - - /* Jeffrey Friedl's debugging harness uses these additional options which - are not in the right form for putting in the option table because they use - only one hyphen, yet are more than one character long. By putting them - separately here, they will not get displayed as part of the help() output, - but I don't think Jeffrey will care about that. */ - -#ifdef JFRIEDL_DEBUG - else if (strcmp(argv[i], "-pre") == 0) { - jfriedl_prefix = argv[++i]; - continue; - } else if (strcmp(argv[i], "-post") == 0) { - jfriedl_postfix = argv[++i]; - continue; - } else if (strcmp(argv[i], "-XT") == 0) { - sscanf(argv[++i], "%d", &jfriedl_XT); - continue; - } else if (strcmp(argv[i], "-XR") == 0) { - sscanf(argv[++i], "%d", &jfriedl_XR); - continue; - } -#endif - - - /* One-char options; many that have no data may be in a single argument; we - continue till we hit the last one or one that needs data. */ - - else - { - char *s = argv[i] + 1; - longop = FALSE; - while (*s != 0) - { - for (op = optionlist; op->one_char != 0; op++) - { if (*s == op->one_char) break; } - if (op->one_char == 0) - { - fprintf(stderr, "pcregrep: Unknown option letter '%c' in \"%s\"\n", - *s, argv[i]); - exit(usage(2)); - } - if (op->type != OP_NODATA || s[1] == 0) - { - option_data = s+1; - break; - } - pcre_options = handle_option(*s++, pcre_options); - } - } - - /* At this point we should have op pointing to a matched option. If the type - is NO_DATA, it means that there is no data, and the option might set - something in the PCRE options. */ - - if (op->type == OP_NODATA) - { - pcre_options = handle_option(op->one_char, pcre_options); - continue; - } - - /* If the option type is OP_OP_STRING or OP_OP_NUMBER, it's an option that - either has a value or defaults to something. It cannot have data in a - separate item. At the moment, the only such options are "colo(u)r" and - Jeffrey Friedl's special -S debugging option. */ - - if (*option_data == 0 && - (op->type == OP_OP_STRING || op->type == OP_OP_NUMBER)) - { - switch (op->one_char) - { - case N_COLOUR: - colour_option = (char *)"auto"; - break; -#ifdef JFRIEDL_DEBUG - case 'S': - S_arg = 0; - break; -#endif - } - continue; - } - - /* Otherwise, find the data string for the option. */ - - if (*option_data == 0) - { - if (i >= argc - 1 || longopwasequals) - { - fprintf(stderr, "pcregrep: Data missing after %s\n", argv[i]); - exit(usage(2)); - } - option_data = argv[++i]; - } - - /* If the option type is OP_PATLIST, it's the -e option, which can be called - multiple times to create a list of patterns. */ - - if (op->type == OP_PATLIST) - { - if (cmd_pattern_count >= MAX_PATTERN_COUNT) - { - fprintf(stderr, "pcregrep: Too many command-line patterns (max %d)\n", - MAX_PATTERN_COUNT); - return 2; - } - patterns[cmd_pattern_count++] = option_data; - } - - /* Otherwise, deal with single string or numeric data values. */ - - else if (op->type != OP_NUMBER && op->type != OP_OP_NUMBER) - { - *((char **)op->dataptr) = option_data; - } - else - { - char *endptr; - int n = strtoul(option_data, &endptr, 10); - if (*endptr != 0) - { - if (longop) - { - char *equals = strchr(op->long_name, '='); - int nlen = (equals == NULL)? (int)strlen(op->long_name) : - equals - op->long_name; - fprintf(stderr, "pcregrep: Malformed number \"%s\" after --%.*s\n", - option_data, nlen, op->long_name); - } - else - fprintf(stderr, "pcregrep: Malformed number \"%s\" after -%c\n", - option_data, op->one_char); - exit(usage(2)); - } - *((int *)op->dataptr) = n; - } - } - -/* Options have been decoded. If -C was used, its value is used as a default -for -A and -B. */ - -if (both_context > 0) - { - if (after_context == 0) after_context = both_context; - if (before_context == 0) before_context = both_context; - } - -/* If a locale has not been provided as an option, see if the LC_CTYPE or -LC_ALL environment variable is set, and if so, use it. */ - -if (locale == NULL) - { - locale = getenv("LC_ALL"); - locale_from = "LCC_ALL"; - } - -if (locale == NULL) - { - locale = getenv("LC_CTYPE"); - locale_from = "LC_CTYPE"; - } - -/* If a locale has been provided, set it, and generate the tables the PCRE -needs. Otherwise, pcretables==NULL, which causes the use of default tables. */ - -if (locale != NULL) - { - if (setlocale(LC_CTYPE, locale) == NULL) - { - fprintf(stderr, "pcregrep: Failed to set locale %s (obtained from %s)\n", - locale, locale_from); - return 2; - } - pcretables = pcre_maketables(); - } - -/* Sort out colouring */ - -if (colour_option != NULL && strcmp(colour_option, "never") != 0) - { - if (strcmp(colour_option, "always") == 0) do_colour = TRUE; - else if (strcmp(colour_option, "auto") == 0) do_colour = is_stdout_tty(); - else - { - fprintf(stderr, "pcregrep: Unknown colour setting \"%s\"\n", - colour_option); - return 2; - } - if (do_colour) - { - char *cs = getenv("PCREGREP_COLOUR"); - if (cs == NULL) cs = getenv("PCREGREP_COLOR"); - if (cs != NULL) colour_string = cs; - } - } - -/* Interpret the newline type; the default settings are Unix-like. */ - -if (strcmp(newline, "cr") == 0 || strcmp(newline, "CR") == 0) - { - pcre_options |= PCRE_NEWLINE_CR; - endlinebyte = '\r'; - } -else if (strcmp(newline, "lf") == 0 || strcmp(newline, "LF") == 0) - { - pcre_options |= PCRE_NEWLINE_LF; - } -else if (strcmp(newline, "crlf") == 0 || strcmp(newline, "CRLF") == 0) - { - pcre_options |= PCRE_NEWLINE_CRLF; - endlineextra = 1; - } -else - { - fprintf(stderr, "pcregrep: Invalid newline specifier \"%s\"\n", newline); - return 2; - } - -/* Interpret the text values for -d and -D */ - -if (dee_option != NULL) - { - if (strcmp(dee_option, "read") == 0) dee_action = dee_READ; - else if (strcmp(dee_option, "recurse") == 0) dee_action = dee_RECURSE; - else if (strcmp(dee_option, "skip") == 0) dee_action = dee_SKIP; - else - { - fprintf(stderr, "pcregrep: Invalid value \"%s\" for -d\n", dee_option); - return 2; - } - } - -if (DEE_option != NULL) - { - if (strcmp(DEE_option, "read") == 0) DEE_action = DEE_READ; - else if (strcmp(DEE_option, "skip") == 0) DEE_action = DEE_SKIP; - else - { - fprintf(stderr, "pcregrep: Invalid value \"%s\" for -D\n", DEE_option); - return 2; - } - } - -/* Check the values for Jeffrey Friedl's debugging options. */ - -#ifdef JFRIEDL_DEBUG -if (S_arg > 9) - { - fprintf(stderr, "pcregrep: bad value for -S option\n"); - return 2; - } -if (jfriedl_XT != 0 || jfriedl_XR != 0) - { - if (jfriedl_XT == 0) jfriedl_XT = 1; - if (jfriedl_XR == 0) jfriedl_XR = 1; - } -#endif - -/* Get memory to store the pattern and hints lists. */ - -pattern_list = (pcre **)malloc(MAX_PATTERN_COUNT * sizeof(pcre *)); -hints_list = (pcre_extra **)malloc(MAX_PATTERN_COUNT * sizeof(pcre_extra *)); - -if (pattern_list == NULL || hints_list == NULL) - { - fprintf(stderr, "pcregrep: malloc failed\n"); - return 2; - } - -/* If no patterns were provided by -e, and there is no file provided by -f, -the first argument is the one and only pattern, and it must exist. */ - -if (cmd_pattern_count == 0 && pattern_filename == NULL) - { - if (i >= argc) return usage(2); - patterns[cmd_pattern_count++] = argv[i++]; - } - -/* Compile the patterns that were provided on the command line, either by -multiple uses of -e or as a single unkeyed pattern. */ - -for (j = 0; j < cmd_pattern_count; j++) - { - if (!compile_pattern(patterns[j], pcre_options, NULL, - (j == 0 && cmd_pattern_count == 1)? 0 : j + 1)) - return 2; - } - -/* Compile the regular expressions that are provided in a file. */ - -if (pattern_filename != NULL) - { - int linenumber = 0; - FILE *f; - char *filename; - char buffer[MBUFTHIRD]; - - if (strcmp(pattern_filename, "-") == 0) - { - f = stdin; - filename = stdin_name; - } - else - { - f = fopen(pattern_filename, "r"); - if (f == NULL) - { - fprintf(stderr, "pcregrep: Failed to open %s: %s\n", pattern_filename, - strerror(errno)); - return 2; - } - filename = pattern_filename; - } - - while (fgets(buffer, MBUFTHIRD, f) != NULL) - { - char *s = buffer + (int)strlen(buffer); - while (s > buffer && isspace((unsigned char)(s[-1]))) s--; - *s = 0; - linenumber++; - if (buffer[0] == 0) continue; /* Skip blank lines */ - if (!compile_pattern(buffer, pcre_options, filename, linenumber)) - return 2; - } - - if (f != stdin) fclose(f); - } - -/* Study the regular expressions, as we will be running them many times */ - -for (j = 0; j < pattern_count; j++) - { - hints_list[j] = pcre_study(pattern_list[j], 0, &error); - if (error != NULL) - { - char s[16]; - if (pattern_count == 1) s[0] = 0; else sprintf(s, " number %d", j); - fprintf(stderr, "pcregrep: Error while studying regex%s: %s\n", s, error); - return 2; - } - } - -/* If there are include or exclude patterns, compile them. */ - -if (exclude_pattern != NULL) - { - exclude_compiled = pcre_compile(exclude_pattern, 0, &error, &errptr, - pcretables); - if (exclude_compiled == NULL) - { - fprintf(stderr, "pcregrep: Error in 'exclude' regex at offset %d: %s\n", - errptr, error); - return 2; - } - } - -if (include_pattern != NULL) - { - include_compiled = pcre_compile(include_pattern, 0, &error, &errptr, - pcretables); - if (include_compiled == NULL) - { - fprintf(stderr, "pcregrep: Error in 'include' regex at offset %d: %s\n", - errptr, error); - return 2; - } - } - -/* If there are no further arguments, do the business on stdin and exit. */ - -if (i >= argc) - return pcregrep(stdin, (filenames > FN_DEFAULT)? stdin_name : NULL); - -/* Otherwise, work through the remaining arguments as files or directories. -Pass in the fact that there is only one argument at top level - this suppresses -the file name if the argument is not a directory and filenames are not -otherwise forced. */ - -only_one_at_top = i == argc - 1; /* Catch initial value of i */ - -for (; i < argc; i++) - { - int frc = grep_or_recurse(argv[i], dee_action == dee_RECURSE, - only_one_at_top); - if (frc > 1) rc = frc; - else if (frc == 0 && rc == 1) rc = 0; - } - -return rc; -} - -/* End of pcregrep */ diff --git a/ext/pcre/pcrelib/pcreposix.c b/ext/pcre/pcrelib/pcreposix.c deleted file mode 100644 index b3472361c9..0000000000 --- a/ext/pcre/pcrelib/pcreposix.c +++ /dev/null @@ -1,315 +0,0 @@ -/************************************************* -* 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) 1997-2006 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 "pcre_internal.h" -#include "pcreposix.h" -#include "stdlib.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 */ - 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 */ - 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 ) */ - 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 */ - REG_ESIZE, /* regular expression too large */ - REG_ESPACE, /* failed to get memory */ - REG_EPAREN, /* unmatched brackets */ - REG_ASSERT, /* internal error: code overflow */ - REG_BADPAT, /* unrecognized character after (?< */ - REG_BADPAT, /* lookbehind assertion is not fixed length */ - REG_BADPAT, /* malformed number or name after (?( */ - REG_BADPAT, /* conditional group containe more than two branches */ - REG_BADPAT, /* assertion expected after (?( */ - REG_BADPAT, /* (?R or (?digits must be followed by ) */ - 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 */ - 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 */ - REG_BADPAT, /* recursive call could loop indefinitely */ - REG_BADPAT, /* unrecognized character after (?P */ - REG_BADPAT, /* syntax error after (?P */ - REG_BADPAT, /* two named subpatterns have the same name */ - REG_BADPAT, /* invalid UTF-8 string */ - 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) */ - REG_BADPAT, /* repeated subpattern is too long */ - REG_BADPAT /* octal value is greater than \377 (not in UTF-8 mode) */ -}; - -/* 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 * -*************************************************/ - -PCRE_DATA_SCOPE size_t -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 * -*************************************************/ - -PCRE_DATA_SCOPE void -regfree(regex_t *preg) -{ -(pcre_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 -*/ - -PCRE_DATA_SCOPE int -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; - -preg->re_pcre = pcre_compile2(pattern, options, &errorcode, &errorptr, - &erroffset, NULL); -preg->re_erroffset = erroffset; - -if (preg->re_pcre == NULL) return eint[errorcode]; - -preg->re_nsub = pcre_info((const pcre *)preg->re_pcre, NULL, NULL); -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. */ - -PCRE_DATA_SCOPE int -regexec(const regex_t *preg, const char *string, size_t nmatch, - regmatch_t pmatch[], int eflags) -{ -int rc; -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; - -((regex_t *)preg)->re_erroffset = (size_t)(-1); /* Only has meaning after compile */ - -/* When no string data is being returned, ensure that nmatch is zero. -Otherwise, ensure the vector for holding the return data is large enough. */ - -if (nosub) 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; - } - } - -rc = pcre_exec((const pcre *)preg->re_pcre, NULL, string, (int)strlen(string), - 0, options, ovector, nmatch * 3); - -if (rc == 0) rc = nmatch; /* All captured slots were filled in */ - -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; - } - -else - { - if (allocated_ovector) free(ovector); - switch(rc) - { - 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; - default: return REG_ASSERT; - } - } -} - -/* End of pcreposix.c */ diff --git a/ext/pcre/pcrelib/pcreposix.h b/ext/pcre/pcrelib/pcreposix.h deleted file mode 100644 index 31ee03749c..0000000000 --- a/ext/pcre/pcrelib/pcreposix.h +++ /dev/null @@ -1,147 +0,0 @@ -/************************************************* -* 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) 1997-2006 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 a couple of extras. */ - -#define REG_ICASE 0x0001 -#define REG_NEWLINE 0x0002 -#define REG_NOTBOL 0x0004 -#define REG_NOTEOL 0x0008 -#define REG_DOTALL 0x0010 /* NOT defined by POSIX. */ -#define REG_NOSUB 0x0020 -#define REG_UTF8 0x0040 /* NOT defined by POSIX. */ - -/* 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; - -/* Win32 uses DLL by default; it needs special stuff for exported functions -when building PCRE. */ - -#ifndef PCRE_DATA_SCOPE -#ifdef _WIN32 -# ifdef PCRE_DEFINITION -# ifdef DLL_EXPORT -# define PCRE_DATA_SCOPE __declspec(dllexport) -# endif -# else -# ifndef PCRE_STATIC -# define PCRE_DATA_SCOPE extern __declspec(dllimport) -# endif -# endif -#endif -#endif - -/* Otherwise, we use the standard "extern". */ - -#ifndef PCRE_DATA_SCOPE -# ifdef __cplusplus -# define PCRE_DATA_SCOPE extern "C" -# else -# define PCRE_DATA_SCOPE extern -# endif -#endif - -/* The functions */ - -PCRE_DATA_SCOPE int regcomp(regex_t *, const char *, int); -PCRE_DATA_SCOPE int regexec(const regex_t *, const char *, size_t, - regmatch_t *, int); -PCRE_DATA_SCOPE size_t regerror(int, const regex_t *, char *, size_t); -PCRE_DATA_SCOPE void regfree(regex_t *); - -#ifdef __cplusplus -} /* extern "C" */ -#endif - -#endif /* End of pcreposix.h */ diff --git a/ext/pcre/pcrelib/pcretest.c b/ext/pcre/pcrelib/pcretest.c deleted file mode 100644 index 431378c6dc..0000000000 --- a/ext/pcre/pcrelib/pcretest.c +++ /dev/null @@ -1,2186 +0,0 @@ -/************************************************* -* PCRE testing program * -*************************************************/ - -/* This program was hacked up as a tester for PCRE. I really should have -written it more tidily in the first place. Will I ever learn? It has grown and -been extended and consequently is now rather, er, *very* untidy in places. - ------------------------------------------------------------------------------ -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. ------------------------------------------------------------------------------ -*/ - - -#include <ctype.h> -#include <stdio.h> -#include <string.h> -#include <stdlib.h> -#include <time.h> -#include <locale.h> -#include <errno.h> - -#ifndef _WIN32 -#include <sys/resource.h> -#endif - -#define PCRE_SPY /* For Win32 build, import data, not export */ - -/* We include pcre_internal.h because we need the internal info for displaying -the results of pcre_study() and we also need to know about the internal -macros, structures, and other internal data values; pcretest has "inside -information" compared to a program that strictly follows the PCRE API. */ - -#include "pcre_internal.h" - -/* We need access to the data tables that PCRE uses. So as not to have to keep -two copies, we include the source file here, changing the names of the external -symbols to prevent clashes. */ - -#define _pcre_utf8_table1 utf8_table1 -#define _pcre_utf8_table1_size utf8_table1_size -#define _pcre_utf8_table2 utf8_table2 -#define _pcre_utf8_table3 utf8_table3 -#define _pcre_utf8_table4 utf8_table4 -#define _pcre_utt utt -#define _pcre_utt_size utt_size -#define _pcre_OP_lengths OP_lengths - -#include "pcre_tables.c" - -/* We also need the pcre_printint() function for printing out compiled -patterns. This function is in a separate file so that it can be included in -pcre_compile.c when that module is compiled with debugging enabled. */ - -#include "pcre_printint.src" - - -/* It is possible to compile this test program without including support for -testing the POSIX interface, though this is not available via the standard -Makefile. */ - -#if !defined NOPOSIX -#include "pcreposix.h" -#endif - -/* It is also possible, for the benefit of the version imported into Exim, to -build pcretest without support for UTF8 (define NOUTF8), without the interface -to the DFA matcher (NODFA), and without the doublecheck of the old "info" -function (define NOINFOCHECK). */ - - -/* Other parameters */ - -#ifndef CLOCKS_PER_SEC -#ifdef CLK_TCK -#define CLOCKS_PER_SEC CLK_TCK -#else -#define CLOCKS_PER_SEC 100 -#endif -#endif - -#define LOOPREPEAT 500000 - -/* Static variables */ - -static FILE *outfile; -static int log_store = 0; -static int callout_count; -static int callout_extra; -static int callout_fail_count; -static int callout_fail_id; -static int first_callout; -static int show_malloc; -static int use_utf8; -static size_t gotten_store; - -/* The buffers grow automatically if very long input lines are encountered. */ - -static int buffer_size = 50000; -static uschar *buffer = NULL; -static uschar *dbuffer = NULL; -static uschar *pbuffer = NULL; - - - -/************************************************* -* Read or extend an input line * -*************************************************/ - -/* Input lines are read into buffer, but both patterns and data lines can be -continued over multiple input lines. In addition, if the buffer fills up, we -want to automatically expand it so as to be able to handle extremely large -lines that are needed for certain stress tests. When the input buffer is -expanded, the other two buffers must also be expanded likewise, and the -contents of pbuffer, which are a copy of the input for callouts, must be -preserved (for when expansion happens for a data line). This is not the most -optimal way of handling this, but hey, this is just a test program! - -Arguments: - f the file to read - start where in buffer to start (this *must* be within buffer) - -Returns: pointer to the start of new data - could be a copy of start, or could be moved - NULL if no data read and EOF reached -*/ - -static uschar * -extend_inputline(FILE *f, uschar *start) -{ -uschar *here = start; - -for (;;) - { - int rlen = buffer_size - (here - buffer); - if (rlen > 1000) - { - int dlen; - if (fgets((char *)here, rlen, f) == NULL) - return (here == start)? NULL : start; - dlen = (int)strlen((char *)here); - if (dlen > 0 && here[dlen - 1] == '\n') return start; - here += dlen; - } - - else - { - int new_buffer_size = 2*buffer_size; - uschar *new_buffer = (unsigned char *)malloc(new_buffer_size); - uschar *new_dbuffer = (unsigned char *)malloc(new_buffer_size); - uschar *new_pbuffer = (unsigned char *)malloc(new_buffer_size); - - if (new_buffer == NULL || new_dbuffer == NULL || new_pbuffer == NULL) - { - fprintf(stderr, "pcretest: malloc(%d) failed\n", new_buffer_size); - exit(1); - } - - memcpy(new_buffer, buffer, buffer_size); - memcpy(new_pbuffer, pbuffer, buffer_size); - - buffer_size = new_buffer_size; - - start = new_buffer + (start - buffer); - here = new_buffer + (here - buffer); - - free(buffer); - free(dbuffer); - free(pbuffer); - - buffer = new_buffer; - dbuffer = new_dbuffer; - pbuffer = new_pbuffer; - } - } - -return NULL; /* Control never gets here */ -} - - - - - - - -/************************************************* -* Read number from string * -*************************************************/ - -/* We don't use strtoul() because SunOS4 doesn't have it. Rather than mess -around with conditional compilation, just do the job by hand. It is only used -for unpicking the -o argument, so just keep it simple. - -Arguments: - str string to be converted - endptr where to put the end pointer - -Returns: the unsigned long -*/ - -static int -get_value(unsigned char *str, unsigned char **endptr) -{ -int result = 0; -while(*str != 0 && isspace(*str)) str++; -while (isdigit(*str)) result = result * 10 + (int)(*str++ - '0'); -*endptr = str; -return(result); -} - - - - -/************************************************* -* Convert UTF-8 string to value * -*************************************************/ - -/* This function takes one or more bytes that represents a UTF-8 character, -and returns the value of the character. - -Argument: - utf8bytes a pointer to the byte vector - vptr a pointer to an int to receive the value - -Returns: > 0 => the number of bytes consumed - -6 to 0 => malformed UTF-8 character at offset = (-return) -*/ - -#if !defined NOUTF8 - -static int -utf82ord(unsigned char *utf8bytes, int *vptr) -{ -int c = *utf8bytes++; -int d = c; -int i, j, s; - -for (i = -1; i < 6; i++) /* i is number of additional bytes */ - { - if ((d & 0x80) == 0) break; - d <<= 1; - } - -if (i == -1) { *vptr = c; return 1; } /* ascii character */ -if (i == 0 || i == 6) return 0; /* invalid UTF-8 */ - -/* i now has a value in the range 1-5 */ - -s = 6*i; -d = (c & utf8_table3[i]) << s; - -for (j = 0; j < i; j++) - { - c = *utf8bytes++; - if ((c & 0xc0) != 0x80) return -(j+1); - s -= 6; - d |= (c & 0x3f) << s; - } - -/* Check that encoding was the correct unique one */ - -for (j = 0; j < utf8_table1_size; j++) - if (d <= utf8_table1[j]) break; -if (j != i) return -(i+1); - -/* Valid value */ - -*vptr = d; -return i+1; -} - -#endif - - - -/************************************************* -* Convert character value to UTF-8 * -*************************************************/ - -/* This function takes an integer value in the range 0 - 0x7fffffff -and encodes it as a UTF-8 character in 0 to 6 bytes. - -Arguments: - cvalue the character value - utf8bytes pointer to buffer for result - at least 6 bytes long - -Returns: number of characters placed in the buffer -*/ - -static int -ord2utf8(int cvalue, uschar *utf8bytes) -{ -register int i, j; -for (i = 0; i < utf8_table1_size; i++) - if (cvalue <= utf8_table1[i]) break; -utf8bytes += i; -for (j = i; j > 0; j--) - { - *utf8bytes-- = 0x80 | (cvalue & 0x3f); - cvalue >>= 6; - } -*utf8bytes = utf8_table2[i] | cvalue; -return i + 1; -} - - - -/************************************************* -* Print character string * -*************************************************/ - -/* Character string printing function. Must handle UTF-8 strings in utf8 -mode. Yields number of characters printed. If handed a NULL file, just counts -chars without printing. */ - -static int pchars(unsigned char *p, int length, FILE *f) -{ -int c = 0; -int yield = 0; - -while (length-- > 0) - { -#if !defined NOUTF8 - if (use_utf8) - { - int rc = utf82ord(p, &c); - - if (rc > 0 && rc <= length + 1) /* Mustn't run over the end */ - { - length -= rc - 1; - p += rc; - if (c < 256 && isprint(c)) - { - if (f != NULL) fprintf(f, "%c", c); - yield++; - } - else - { - int n; - if (f != NULL) fprintf(f, "\\x{%02x}%n", c, &n); - yield += n; - } - continue; - } - } -#endif - - /* Not UTF-8, or malformed UTF-8 */ - - if (isprint(c = *(p++))) - { - if (f != NULL) fprintf(f, "%c", c); - yield++; - } - else - { - if (f != NULL) fprintf(f, "\\x%02x", c); - yield += 4; - } - } - -return yield; -} - - - -/************************************************* -* Callout function * -*************************************************/ - -/* Called from PCRE as a result of the (?C) item. We print out where we are in -the match. Yield zero unless more callouts than the fail count, or the callout -data is not zero. */ - -static int callout(pcre_callout_block *cb) -{ -FILE *f = (first_callout | callout_extra)? outfile : NULL; -int i, pre_start, post_start, subject_length; - -if (callout_extra) - { - fprintf(f, "Callout %d: last capture = %d\n", - cb->callout_number, cb->capture_last); - - for (i = 0; i < cb->capture_top * 2; i += 2) - { - if (cb->offset_vector[i] < 0) - fprintf(f, "%2d: <unset>\n", i/2); - else - { - fprintf(f, "%2d: ", i/2); - (void)pchars((unsigned char *)cb->subject + cb->offset_vector[i], - cb->offset_vector[i+1] - cb->offset_vector[i], f); - fprintf(f, "\n"); - } - } - } - -/* Re-print the subject in canonical form, the first time or if giving full -datails. On subsequent calls in the same match, we use pchars just to find the -printed lengths of the substrings. */ - -if (f != NULL) fprintf(f, "--->"); - -pre_start = pchars((unsigned char *)cb->subject, cb->start_match, f); -post_start = pchars((unsigned char *)(cb->subject + cb->start_match), - cb->current_position - cb->start_match, f); - -subject_length = pchars((unsigned char *)cb->subject, cb->subject_length, NULL); - -(void)pchars((unsigned char *)(cb->subject + cb->current_position), - cb->subject_length - cb->current_position, f); - -if (f != NULL) fprintf(f, "\n"); - -/* Always print appropriate indicators, with callout number if not already -shown. For automatic callouts, show the pattern offset. */ - -if (cb->callout_number == 255) - { - fprintf(outfile, "%+3d ", cb->pattern_position); - if (cb->pattern_position > 99) fprintf(outfile, "\n "); - } -else - { - if (callout_extra) fprintf(outfile, " "); - else fprintf(outfile, "%3d ", cb->callout_number); - } - -for (i = 0; i < pre_start; i++) fprintf(outfile, " "); -fprintf(outfile, "^"); - -if (post_start > 0) - { - for (i = 0; i < post_start - 1; i++) fprintf(outfile, " "); - fprintf(outfile, "^"); - } - -for (i = 0; i < subject_length - pre_start - post_start + 4; i++) - fprintf(outfile, " "); - -fprintf(outfile, "%.*s", (cb->next_item_length == 0)? 1 : cb->next_item_length, - pbuffer + cb->pattern_position); - -fprintf(outfile, "\n"); -first_callout = 0; - -if (cb->callout_data != NULL) - { - int callout_data = *((int *)(cb->callout_data)); - if (callout_data != 0) - { - fprintf(outfile, "Callout data = %d\n", callout_data); - return callout_data; - } - } - -return (cb->callout_number != callout_fail_id)? 0 : - (++callout_count >= callout_fail_count)? 1 : 0; -} - - -/************************************************* -* Local malloc functions * -*************************************************/ - -/* Alternative malloc function, to test functionality and show the size of the -compiled re. */ - -static void *new_malloc(size_t size) -{ -void *block = malloc(size); -gotten_store = size; -if (show_malloc) - fprintf(outfile, "malloc %3d %p\n", (int)size, block); -return block; -} - -static void new_free(void *block) -{ -if (show_malloc) - fprintf(outfile, "free %p\n", block); -free(block); -} - - -/* For recursion malloc/free, to test stacking calls */ - -static void *stack_malloc(size_t size) -{ -void *block = malloc(size); -if (show_malloc) - fprintf(outfile, "stack_malloc %3d %p\n", (int)size, block); -return block; -} - -static void stack_free(void *block) -{ -if (show_malloc) - fprintf(outfile, "stack_free %p\n", block); -free(block); -} - - -/************************************************* -* Call pcre_fullinfo() * -*************************************************/ - -/* Get one piece of information from the pcre_fullinfo() function */ - -static void new_info(pcre *re, pcre_extra *study, int option, void *ptr) -{ -int rc; -if ((rc = pcre_fullinfo(re, study, option, ptr)) < 0) - fprintf(outfile, "Error %d from pcre_fullinfo(%d)\n", rc, option); -} - - - -/************************************************* -* Byte flipping function * -*************************************************/ - -static unsigned long int -byteflip(unsigned long int value, int n) -{ -if (n == 2) return ((value & 0x00ff) << 8) | ((value & 0xff00) >> 8); -return ((value & 0x000000ff) << 24) | - ((value & 0x0000ff00) << 8) | - ((value & 0x00ff0000) >> 8) | - ((value & 0xff000000) >> 24); -} - - - - -/************************************************* -* Check match or recursion limit * -*************************************************/ - -static int -check_match_limit(pcre *re, pcre_extra *extra, uschar *bptr, int len, - int start_offset, int options, int *use_offsets, int use_size_offsets, - int flag, unsigned long int *limit, int errnumber, const char *msg) -{ -int count; -int min = 0; -int mid = 64; -int max = -1; - -extra->flags |= flag; - -for (;;) - { - *limit = mid; - - count = pcre_exec(re, extra, (char *)bptr, len, start_offset, options, - use_offsets, use_size_offsets); - - if (count == errnumber) - { - /* fprintf(outfile, "Testing %s limit = %d\n", msg, mid); */ - min = mid; - mid = (mid == max - 1)? max : (max > 0)? (min + max)/2 : mid*2; - } - - else if (count >= 0 || count == PCRE_ERROR_NOMATCH || - count == PCRE_ERROR_PARTIAL) - { - if (mid == min + 1) - { - fprintf(outfile, "Minimum %s limit = %d\n", msg, mid); - break; - } - /* fprintf(outfile, "Testing %s limit = %d\n", msg, mid); */ - max = mid; - mid = (min + mid)/2; - } - else break; /* Some other error */ - } - -extra->flags &= ~flag; -return count; -} - - - -/************************************************* -* Check newline indicator * -*************************************************/ - -/* This is used both at compile and run-time to check for <xxx> escapes, where -xxx is LF, CR, or CRLF. Print a message and return 0 if there is no match. - -Arguments: - p points after the leading '<' - f file for error message - -Returns: appropriate PCRE_NEWLINE_xxx flags, or 0 -*/ - -static int -check_newline(uschar *p, FILE *f) -{ -if (strncmp((char *)p, "cr>", 3) == 0) return PCRE_NEWLINE_CR; -if (strncmp((char *)p, "lf>", 3) == 0) return PCRE_NEWLINE_LF; -if (strncmp((char *)p, "crlf>", 5) == 0) return PCRE_NEWLINE_CRLF; -fprintf(f, "Unknown newline type at: <%s\n", p); -return 0; -} - - - -/************************************************* -* Main Program * -*************************************************/ - -/* Read lines from named file or stdin and write to named file or stdout; lines -consist of a regular expression, in delimiters and optionally followed by -options, followed by a set of test data, terminated by an empty line. */ - -int main(int argc, char **argv) -{ -FILE *infile = stdin; -int options = 0; -int study_options = 0; -int op = 1; -int timeit = 0; -int showinfo = 0; -int showstore = 0; -int quiet = 0; -int size_offsets = 45; -int size_offsets_max; -int *offsets = NULL; -#if !defined NOPOSIX -int posix = 0; -#endif -int debug = 0; -int done = 0; -int all_use_dfa = 0; -int yield = 0; -int stack_size; - -/* These vectors store, end-to-end, a list of captured substring names. Assume -that 1024 is plenty long enough for the few names we'll be testing. */ - -uschar copynames[1024]; -uschar getnames[1024]; - -uschar *copynamesptr; -uschar *getnamesptr; - -/* Get buffers from malloc() so that Electric Fence will check their misuse -when I am debugging. They grow automatically when very long lines are read. */ - -buffer = (unsigned char *)malloc(buffer_size); -dbuffer = (unsigned char *)malloc(buffer_size); -pbuffer = (unsigned char *)malloc(buffer_size); - -/* The outfile variable is static so that new_malloc can use it. The _setmode() -stuff is some magic that I don't understand, but which apparently does good -things in Windows. It's related to line terminations. */ - -#if defined(_WIN32) || defined(WIN32) -_setmode( _fileno( stdout ), 0x8000 ); -#endif /* defined(_WIN32) || defined(WIN32) */ - -outfile = stdout; - -/* Scan options */ - -while (argc > 1 && argv[op][0] == '-') - { - unsigned char *endptr; - - if (strcmp(argv[op], "-s") == 0 || strcmp(argv[op], "-m") == 0) - showstore = 1; - else if (strcmp(argv[op], "-t") == 0) timeit = 1; - else if (strcmp(argv[op], "-q") == 0) quiet = 1; - else if (strcmp(argv[op], "-i") == 0) showinfo = 1; - else if (strcmp(argv[op], "-d") == 0) showinfo = debug = 1; -#if !defined NODFA - else if (strcmp(argv[op], "-dfa") == 0) all_use_dfa = 1; -#endif - else if (strcmp(argv[op], "-o") == 0 && argc > 2 && - ((size_offsets = get_value((unsigned char *)argv[op+1], &endptr)), - *endptr == 0)) - { - op++; - argc--; - } - else if (strcmp(argv[op], "-S") == 0 && argc > 2 && - ((stack_size = get_value((unsigned char *)argv[op+1], &endptr)), - *endptr == 0)) - { -#ifdef _WIN32 - printf("PCRE: -S not supported on this OS\n"); - exit(1); -#else - int rc; - struct rlimit rlim; - getrlimit(RLIMIT_STACK, &rlim); - rlim.rlim_cur = stack_size * 1024 * 1024; - rc = setrlimit(RLIMIT_STACK, &rlim); - if (rc != 0) - { - printf("PCRE: setrlimit() failed with error %d\n", rc); - exit(1); - } - op++; - argc--; -#endif - } -#if !defined NOPOSIX - else if (strcmp(argv[op], "-p") == 0) posix = 1; -#endif - else if (strcmp(argv[op], "-C") == 0) - { - int rc; - printf("PCRE version %s\n", pcre_version()); - printf("Compiled with\n"); - (void)pcre_config(PCRE_CONFIG_UTF8, &rc); - printf(" %sUTF-8 support\n", rc? "" : "No "); - (void)pcre_config(PCRE_CONFIG_UNICODE_PROPERTIES, &rc); - printf(" %sUnicode properties support\n", rc? "" : "No "); - (void)pcre_config(PCRE_CONFIG_NEWLINE, &rc); - printf(" Newline sequence is %s\n", (rc == '\r')? "CR" : - (rc == '\n')? "LF" : "CRLF"); - (void)pcre_config(PCRE_CONFIG_LINK_SIZE, &rc); - printf(" Internal link size = %d\n", rc); - (void)pcre_config(PCRE_CONFIG_POSIX_MALLOC_THRESHOLD, &rc); - printf(" POSIX malloc threshold = %d\n", rc); - (void)pcre_config(PCRE_CONFIG_MATCH_LIMIT, &rc); - printf(" Default match limit = %d\n", rc); - (void)pcre_config(PCRE_CONFIG_MATCH_LIMIT_RECURSION, &rc); - printf(" Default recursion depth limit = %d\n", rc); - (void)pcre_config(PCRE_CONFIG_STACKRECURSE, &rc); - printf(" Match recursion uses %s\n", rc? "stack" : "heap"); - exit(0); - } - else - { - printf("** Unknown or malformed option %s\n", argv[op]); - printf("Usage: pcretest [options] [<input> [<output>]]\n"); - printf(" -C show PCRE compile-time options and exit\n"); - printf(" -d debug: show compiled code; implies -i\n"); -#if !defined NODFA - printf(" -dfa force DFA matching for all subjects\n"); -#endif - printf(" -i show information about compiled pattern\n" - " -m output memory used information\n" - " -o <n> set size of offsets vector to <n>\n"); -#if !defined NOPOSIX - printf(" -p use POSIX interface\n"); -#endif - printf(" -S <n> set stack size to <n> megabytes\n"); - printf(" -s output store (memory) used information\n" - " -t time compilation and execution\n"); - yield = 1; - goto EXIT; - } - op++; - argc--; - } - -/* Get the store for the offsets vector, and remember what it was */ - -size_offsets_max = size_offsets; -offsets = (int *)malloc(size_offsets_max * sizeof(int)); -if (offsets == NULL) - { - printf("** Failed to get %d bytes of memory for offsets vector\n", - size_offsets_max * sizeof(int)); - yield = 1; - goto EXIT; - } - -/* Sort out the input and output files */ - -if (argc > 1) - { - infile = fopen(argv[op], "rb"); - if (infile == NULL) - { - printf("** Failed to open %s\n", argv[op]); - yield = 1; - goto EXIT; - } - } - -if (argc > 2) - { - outfile = fopen(argv[op+1], "wb"); - if (outfile == NULL) - { - printf("** Failed to open %s\n", argv[op+1]); - yield = 1; - goto EXIT; - } - } - -/* Set alternative malloc function */ - -pcre_malloc = new_malloc; -pcre_free = new_free; -pcre_stack_malloc = stack_malloc; -pcre_stack_free = stack_free; - -/* Heading line unless quiet, then prompt for first regex if stdin */ - -if (!quiet) fprintf(outfile, "PCRE version %s\n\n", pcre_version()); - -/* Main loop */ - -while (!done) - { - pcre *re = NULL; - pcre_extra *extra = NULL; - -#if !defined NOPOSIX /* There are still compilers that require no indent */ - regex_t preg; - int do_posix = 0; -#endif - - const char *error; - unsigned char *p, *pp, *ppp; - unsigned char *to_file = NULL; - const unsigned char *tables = NULL; - unsigned long int true_size, true_study_size = 0; - size_t size, regex_gotten_store; - int do_study = 0; - int do_debug = debug; - int do_G = 0; - int do_g = 0; - int do_showinfo = showinfo; - int do_showrest = 0; - int do_flip = 0; - int erroroffset, len, delimiter; - - use_utf8 = 0; - - if (infile == stdin) printf(" re> "); - if (extend_inputline(infile, buffer) == NULL) break; - if (infile != stdin) fprintf(outfile, "%s", (char *)buffer); - fflush(outfile); - - p = buffer; - while (isspace(*p)) p++; - if (*p == 0) continue; - - /* See if the pattern is to be loaded pre-compiled from a file. */ - - if (*p == '<' && strchr((char *)(p+1), '<') == NULL) - { - unsigned long int magic, get_options; - uschar sbuf[8]; - FILE *f; - - p++; - pp = p + (int)strlen((char *)p); - while (isspace(pp[-1])) pp--; - *pp = 0; - - f = fopen((char *)p, "rb"); - if (f == NULL) - { - fprintf(outfile, "Failed to open %s: %s\n", p, strerror(errno)); - continue; - } - - if (fread(sbuf, 1, 8, f) != 8) goto FAIL_READ; - - true_size = - (sbuf[0] << 24) | (sbuf[1] << 16) | (sbuf[2] << 8) | sbuf[3]; - true_study_size = - (sbuf[4] << 24) | (sbuf[5] << 16) | (sbuf[6] << 8) | sbuf[7]; - - re = (real_pcre *)new_malloc(true_size); - regex_gotten_store = gotten_store; - - if (fread(re, 1, true_size, f) != true_size) goto FAIL_READ; - - magic = ((real_pcre *)re)->magic_number; - if (magic != MAGIC_NUMBER) - { - if (byteflip(magic, sizeof(magic)) == MAGIC_NUMBER) - { - do_flip = 1; - } - else - { - fprintf(outfile, "Data in %s is not a compiled PCRE regex\n", p); - fclose(f); - continue; - } - } - - fprintf(outfile, "Compiled regex%s loaded from %s\n", - do_flip? " (byte-inverted)" : "", p); - - /* Need to know if UTF-8 for printing data strings */ - - new_info(re, NULL, PCRE_INFO_OPTIONS, &get_options); - use_utf8 = (get_options & PCRE_UTF8) != 0; - - /* Now see if there is any following study data */ - - if (true_study_size != 0) - { - pcre_study_data *psd; - - extra = (pcre_extra *)new_malloc(sizeof(pcre_extra) + true_study_size); - extra->flags = PCRE_EXTRA_STUDY_DATA; - - psd = (pcre_study_data *)(((char *)extra) + sizeof(pcre_extra)); - extra->study_data = psd; - - if (fread(psd, 1, true_study_size, f) != true_study_size) - { - FAIL_READ: - fprintf(outfile, "Failed to read data from %s\n", p); - if (extra != NULL) new_free(extra); - if (re != NULL) new_free(re); - fclose(f); - continue; - } - fprintf(outfile, "Study data loaded from %s\n", p); - do_study = 1; /* To get the data output if requested */ - } - else fprintf(outfile, "No study data\n"); - - fclose(f); - goto SHOW_INFO; - } - - /* In-line pattern (the usual case). Get the delimiter and seek the end of - the pattern; if is isn't complete, read more. */ - - delimiter = *p++; - - if (isalnum(delimiter) || delimiter == '\\') - { - fprintf(outfile, "** Delimiter must not be alphameric or \\\n"); - goto SKIP_DATA; - } - - pp = p; - - for(;;) - { - while (*pp != 0) - { - if (*pp == '\\' && pp[1] != 0) pp++; - else if (*pp == delimiter) break; - pp++; - } - if (*pp != 0) break; - if (infile == stdin) printf(" > "); - if ((pp = extend_inputline(infile, pp)) == NULL) - { - fprintf(outfile, "** Unexpected EOF\n"); - done = 1; - goto CONTINUE; - } - if (infile != stdin) fprintf(outfile, "%s", (char *)pp); - } - - /* If the first character after the delimiter is backslash, make - the pattern end with backslash. This is purely to provide a way - of testing for the error message when a pattern ends with backslash. */ - - if (pp[1] == '\\') *pp++ = '\\'; - - /* Terminate the pattern at the delimiter, and save a copy of the pattern - for callouts. */ - - *pp++ = 0; - strcpy((char *)pbuffer, (char *)p); - - /* Look for options after final delimiter */ - - options = 0; - study_options = 0; - log_store = showstore; /* default from command line */ - - while (*pp != 0) - { - switch (*pp++) - { - case 'f': options |= PCRE_FIRSTLINE; break; - case 'g': do_g = 1; break; - case 'i': options |= PCRE_CASELESS; break; - case 'm': options |= PCRE_MULTILINE; break; - case 's': options |= PCRE_DOTALL; break; - case 'x': options |= PCRE_EXTENDED; break; - - case '+': do_showrest = 1; break; - case 'A': options |= PCRE_ANCHORED; break; - case 'C': options |= PCRE_AUTO_CALLOUT; break; - case 'D': do_debug = do_showinfo = 1; break; - case 'E': options |= PCRE_DOLLAR_ENDONLY; break; - case 'F': do_flip = 1; break; - case 'G': do_G = 1; break; - case 'I': do_showinfo = 1; break; - case 'J': options |= PCRE_DUPNAMES; break; - case 'M': log_store = 1; break; - case 'N': options |= PCRE_NO_AUTO_CAPTURE; break; - -#if !defined NOPOSIX - case 'P': do_posix = 1; break; -#endif - - case 'S': do_study = 1; break; - case 'U': options |= PCRE_UNGREEDY; break; - case 'X': options |= PCRE_EXTRA; break; - case '8': options |= PCRE_UTF8; use_utf8 = 1; break; - case '?': options |= PCRE_NO_UTF8_CHECK; break; - - case 'L': - ppp = pp; - /* The '\r' test here is so that it works on Windows */ - while (*ppp != '\n' && *ppp != '\r' && *ppp != ' ') ppp++; - *ppp = 0; - if (setlocale(LC_CTYPE, (const char *)pp) == NULL) - { - fprintf(outfile, "** Failed to set locale \"%s\"\n", pp); - goto SKIP_DATA; - } - tables = pcre_maketables(); - pp = ppp; - break; - - case '>': - to_file = pp; - while (*pp != 0) pp++; - while (isspace(pp[-1])) pp--; - *pp = 0; - break; - - case '<': - { - int x = check_newline(pp, outfile); - if (x == 0) goto SKIP_DATA; - options |= x; - while (*pp++ != '>'); - } - break; - - case '\r': /* So that it works in Windows */ - case '\n': - case ' ': - break; - - default: - fprintf(outfile, "** Unknown option '%c'\n", pp[-1]); - goto SKIP_DATA; - } - } - - /* Handle compiling via the POSIX interface, which doesn't support the - timing, showing, or debugging options, nor the ability to pass over - local character tables. */ - -#if !defined NOPOSIX - if (posix || do_posix) - { - int rc; - int cflags = 0; - - if ((options & PCRE_CASELESS) != 0) cflags |= REG_ICASE; - if ((options & PCRE_MULTILINE) != 0) cflags |= REG_NEWLINE; - if ((options & PCRE_DOTALL) != 0) cflags |= REG_DOTALL; - if ((options & PCRE_NO_AUTO_CAPTURE) != 0) cflags |= REG_NOSUB; - if ((options & PCRE_UTF8) != 0) cflags |= REG_UTF8; - - rc = regcomp(&preg, (char *)p, cflags); - - /* Compilation failed; go back for another re, skipping to blank line - if non-interactive. */ - - if (rc != 0) - { - (void)regerror(rc, &preg, (char *)buffer, buffer_size); - fprintf(outfile, "Failed: POSIX code %d: %s\n", rc, buffer); - goto SKIP_DATA; - } - } - - /* Handle compiling via the native interface */ - - else -#endif /* !defined NOPOSIX */ - - { - if (timeit) - { - register int i; - clock_t time_taken; - clock_t start_time = clock(); - for (i = 0; i < LOOPREPEAT; i++) - { - re = pcre_compile((char *)p, options, &error, &erroroffset, tables); - if (re != NULL) free(re); - } - time_taken = clock() - start_time; - fprintf(outfile, "Compile time %.3f milliseconds\n", - (((double)time_taken * 1000.0) / (double)LOOPREPEAT) / - (double)CLOCKS_PER_SEC); - } - - re = pcre_compile((char *)p, options, &error, &erroroffset, tables); - - /* Compilation failed; go back for another re, skipping to blank line - if non-interactive. */ - - if (re == NULL) - { - fprintf(outfile, "Failed: %s at offset %d\n", error, erroroffset); - SKIP_DATA: - if (infile != stdin) - { - for (;;) - { - if (extend_inputline(infile, buffer) == NULL) - { - done = 1; - goto CONTINUE; - } - len = (int)strlen((char *)buffer); - while (len > 0 && isspace(buffer[len-1])) len--; - if (len == 0) break; - } - fprintf(outfile, "\n"); - } - goto CONTINUE; - } - - /* Compilation succeeded; print data if required. There are now two - info-returning functions. The old one has a limited interface and - returns only limited data. Check that it agrees with the newer one. */ - - if (log_store) - fprintf(outfile, "Memory allocation (code space): %d\n", - (int)(gotten_store - - sizeof(real_pcre) - - ((real_pcre *)re)->name_count * ((real_pcre *)re)->name_entry_size)); - - /* Extract the size for possible writing before possibly flipping it, - and remember the store that was got. */ - - true_size = ((real_pcre *)re)->size; - regex_gotten_store = gotten_store; - - /* If /S was present, study the regexp to generate additional info to - help with the matching. */ - - if (do_study) - { - if (timeit) - { - register int i; - clock_t time_taken; - clock_t start_time = clock(); - for (i = 0; i < LOOPREPEAT; i++) - extra = pcre_study(re, study_options, &error); - time_taken = clock() - start_time; - if (extra != NULL) free(extra); - fprintf(outfile, " Study time %.3f milliseconds\n", - (((double)time_taken * 1000.0) / (double)LOOPREPEAT) / - (double)CLOCKS_PER_SEC); - } - extra = pcre_study(re, study_options, &error); - if (error != NULL) - fprintf(outfile, "Failed to study: %s\n", error); - else if (extra != NULL) - true_study_size = ((pcre_study_data *)(extra->study_data))->size; - } - - /* If the 'F' option was present, we flip the bytes of all the integer - fields in the regex data block and the study block. This is to make it - possible to test PCRE's handling of byte-flipped patterns, e.g. those - compiled on a different architecture. */ - - if (do_flip) - { - real_pcre *rre = (real_pcre *)re; - rre->magic_number = byteflip(rre->magic_number, sizeof(rre->magic_number)); - rre->size = byteflip(rre->size, sizeof(rre->size)); - rre->options = byteflip(rre->options, sizeof(rre->options)); - rre->top_bracket = byteflip(rre->top_bracket, sizeof(rre->top_bracket)); - rre->top_backref = byteflip(rre->top_backref, sizeof(rre->top_backref)); - rre->first_byte = byteflip(rre->first_byte, sizeof(rre->first_byte)); - rre->req_byte = byteflip(rre->req_byte, sizeof(rre->req_byte)); - rre->name_table_offset = byteflip(rre->name_table_offset, - sizeof(rre->name_table_offset)); - rre->name_entry_size = byteflip(rre->name_entry_size, - sizeof(rre->name_entry_size)); - rre->name_count = byteflip(rre->name_count, sizeof(rre->name_count)); - - if (extra != NULL) - { - pcre_study_data *rsd = (pcre_study_data *)(extra->study_data); - rsd->size = byteflip(rsd->size, sizeof(rsd->size)); - rsd->options = byteflip(rsd->options, sizeof(rsd->options)); - } - } - - /* Extract information from the compiled data if required */ - - SHOW_INFO: - - if (do_showinfo) - { - unsigned long int get_options, all_options; -#if !defined NOINFOCHECK - int old_first_char, old_options, old_count; -#endif - int count, backrefmax, first_char, need_char; - int nameentrysize, namecount; - const uschar *nametable; - - if (do_debug) - { - fprintf(outfile, "------------------------------------------------------------------\n"); - pcre_printint(re, outfile); - } - - new_info(re, NULL, PCRE_INFO_OPTIONS, &get_options); - new_info(re, NULL, PCRE_INFO_SIZE, &size); - new_info(re, NULL, PCRE_INFO_CAPTURECOUNT, &count); - new_info(re, NULL, PCRE_INFO_BACKREFMAX, &backrefmax); - new_info(re, NULL, PCRE_INFO_FIRSTBYTE, &first_char); - new_info(re, NULL, PCRE_INFO_LASTLITERAL, &need_char); - new_info(re, NULL, PCRE_INFO_NAMEENTRYSIZE, &nameentrysize); - new_info(re, NULL, PCRE_INFO_NAMECOUNT, &namecount); - new_info(re, NULL, PCRE_INFO_NAMETABLE, (void *)&nametable); - -#if !defined NOINFOCHECK - old_count = pcre_info(re, &old_options, &old_first_char); - if (count < 0) fprintf(outfile, - "Error %d from pcre_info()\n", count); - else - { - if (old_count != count) fprintf(outfile, - "Count disagreement: pcre_fullinfo=%d pcre_info=%d\n", count, - old_count); - - if (old_first_char != first_char) fprintf(outfile, - "First char disagreement: pcre_fullinfo=%d pcre_info=%d\n", - first_char, old_first_char); - - if (old_options != (int)get_options) fprintf(outfile, - "Options disagreement: pcre_fullinfo=%ld pcre_info=%d\n", - get_options, old_options); - } -#endif - - if (size != regex_gotten_store) fprintf(outfile, - "Size disagreement: pcre_fullinfo=%d call to malloc for %d\n", - (int)size, (int)regex_gotten_store); - - fprintf(outfile, "Capturing subpattern count = %d\n", count); - if (backrefmax > 0) - fprintf(outfile, "Max back reference = %d\n", backrefmax); - - if (namecount > 0) - { - fprintf(outfile, "Named capturing subpatterns:\n"); - while (namecount-- > 0) - { - fprintf(outfile, " %s %*s%3d\n", nametable + 2, - nameentrysize - 3 - (int)strlen((char *)nametable + 2), "", - GET2(nametable, 0)); - nametable += nameentrysize; - } - } - - /* The NOPARTIAL bit is a private bit in the options, so we have - to fish it out via out back door */ - - all_options = ((real_pcre *)re)->options; - if (do_flip) - { - all_options = byteflip(all_options, sizeof(all_options)); - } - - if ((all_options & PCRE_NOPARTIAL) != 0) - fprintf(outfile, "Partial matching not supported\n"); - - if (get_options == 0) fprintf(outfile, "No options\n"); - else fprintf(outfile, "Options:%s%s%s%s%s%s%s%s%s%s%s%s%s\n", - ((get_options & PCRE_ANCHORED) != 0)? " anchored" : "", - ((get_options & PCRE_CASELESS) != 0)? " caseless" : "", - ((get_options & PCRE_EXTENDED) != 0)? " extended" : "", - ((get_options & PCRE_MULTILINE) != 0)? " multiline" : "", - ((get_options & PCRE_FIRSTLINE) != 0)? " firstline" : "", - ((get_options & PCRE_DOTALL) != 0)? " dotall" : "", - ((get_options & PCRE_DOLLAR_ENDONLY) != 0)? " dollar_endonly" : "", - ((get_options & PCRE_EXTRA) != 0)? " extra" : "", - ((get_options & PCRE_UNGREEDY) != 0)? " ungreedy" : "", - ((get_options & PCRE_NO_AUTO_CAPTURE) != 0)? " no_auto_capture" : "", - ((get_options & PCRE_UTF8) != 0)? " utf8" : "", - ((get_options & PCRE_NO_UTF8_CHECK) != 0)? " no_utf8_check" : "", - ((get_options & PCRE_DUPNAMES) != 0)? " dupnames" : ""); - - switch (get_options & PCRE_NEWLINE_CRLF) - { - case PCRE_NEWLINE_CR: - fprintf(outfile, "Forced newline sequence: CR\n"); - break; - - case PCRE_NEWLINE_LF: - fprintf(outfile, "Forced newline sequence: LF\n"); - break; - - case PCRE_NEWLINE_CRLF: - fprintf(outfile, "Forced newline sequence: CRLF\n"); - break; - - default: - break; - } - - if (first_char == -1) - { - fprintf(outfile, "First char at start or follows newline\n"); - } - else if (first_char < 0) - { - fprintf(outfile, "No first char\n"); - } - else - { - int ch = first_char & 255; - const char *caseless = ((first_char & REQ_CASELESS) == 0)? - "" : " (caseless)"; - if (isprint(ch)) - fprintf(outfile, "First char = \'%c\'%s\n", ch, caseless); - else - fprintf(outfile, "First char = %d%s\n", ch, caseless); - } - - if (need_char < 0) - { - fprintf(outfile, "No need char\n"); - } - else - { - int ch = need_char & 255; - const char *caseless = ((need_char & REQ_CASELESS) == 0)? - "" : " (caseless)"; - if (isprint(ch)) - fprintf(outfile, "Need char = \'%c\'%s\n", ch, caseless); - else - fprintf(outfile, "Need char = %d%s\n", ch, caseless); - } - - /* Don't output study size; at present it is in any case a fixed - value, but it varies, depending on the computer architecture, and - so messes up the test suite. (And with the /F option, it might be - flipped.) */ - - if (do_study) - { - if (extra == NULL) - fprintf(outfile, "Study returned NULL\n"); - else - { - uschar *start_bits = NULL; - new_info(re, extra, PCRE_INFO_FIRSTTABLE, &start_bits); - - if (start_bits == NULL) - fprintf(outfile, "No starting byte set\n"); - else - { - int i; - int c = 24; - fprintf(outfile, "Starting byte set: "); - for (i = 0; i < 256; i++) - { - if ((start_bits[i/8] & (1<<(i&7))) != 0) - { - if (c > 75) - { - fprintf(outfile, "\n "); - c = 2; - } - if (isprint(i) && i != ' ') - { - fprintf(outfile, "%c ", i); - c += 2; - } - else - { - fprintf(outfile, "\\x%02x ", i); - c += 5; - } - } - } - fprintf(outfile, "\n"); - } - } - } - } - - /* If the '>' option was present, we write out the regex to a file, and - that is all. The first 8 bytes of the file are the regex length and then - the study length, in big-endian order. */ - - if (to_file != NULL) - { - FILE *f = fopen((char *)to_file, "wb"); - if (f == NULL) - { - fprintf(outfile, "Unable to open %s: %s\n", to_file, strerror(errno)); - } - else - { - uschar sbuf[8]; - sbuf[0] = (true_size >> 24) & 255; - sbuf[1] = (true_size >> 16) & 255; - sbuf[2] = (true_size >> 8) & 255; - sbuf[3] = (true_size) & 255; - - sbuf[4] = (true_study_size >> 24) & 255; - sbuf[5] = (true_study_size >> 16) & 255; - sbuf[6] = (true_study_size >> 8) & 255; - sbuf[7] = (true_study_size) & 255; - - if (fwrite(sbuf, 1, 8, f) < 8 || - fwrite(re, 1, true_size, f) < true_size) - { - fprintf(outfile, "Write error on %s: %s\n", to_file, strerror(errno)); - } - else - { - fprintf(outfile, "Compiled regex written to %s\n", to_file); - if (extra != NULL) - { - if (fwrite(extra->study_data, 1, true_study_size, f) < - true_study_size) - { - fprintf(outfile, "Write error on %s: %s\n", to_file, - strerror(errno)); - } - else fprintf(outfile, "Study data written to %s\n", to_file); - } - } - fclose(f); - } - - new_free(re); - if (extra != NULL) new_free(extra); - if (tables != NULL) new_free((void *)tables); - continue; /* With next regex */ - } - } /* End of non-POSIX compile */ - - /* Read data lines and test them */ - - for (;;) - { - uschar *q; - uschar *bptr = dbuffer; - int *use_offsets = offsets; - int use_size_offsets = size_offsets; - int callout_data = 0; - int callout_data_set = 0; - int count, c; - int copystrings = 0; - int find_match_limit = 0; - int getstrings = 0; - int getlist = 0; - int gmatched = 0; - int start_offset = 0; - int g_notempty = 0; - int use_dfa = 0; - - options = 0; - - *copynames = 0; - *getnames = 0; - - copynamesptr = copynames; - getnamesptr = getnames; - - pcre_callout = callout; - first_callout = 1; - callout_extra = 0; - callout_count = 0; - callout_fail_count = 999999; - callout_fail_id = -1; - show_malloc = 0; - - if (extra != NULL) extra->flags &= - ~(PCRE_EXTRA_MATCH_LIMIT|PCRE_EXTRA_MATCH_LIMIT_RECURSION); - - len = 0; - for (;;) - { - if (infile == stdin) printf("data> "); - if (extend_inputline(infile, buffer + len) == NULL) - { - if (len > 0) break; - done = 1; - goto CONTINUE; - } - if (infile != stdin) fprintf(outfile, "%s", (char *)buffer); - len = (int)strlen((char *)buffer); - if (buffer[len-1] == '\n') break; - } - - while (len > 0 && isspace(buffer[len-1])) len--; - buffer[len] = 0; - if (len == 0) break; - - p = buffer; - while (isspace(*p)) p++; - - q = dbuffer; - while ((c = *p++) != 0) - { - int i = 0; - int n = 0; - - if (c == '\\') switch ((c = *p++)) - { - case 'a': c = 7; break; - case 'b': c = '\b'; break; - case 'e': c = 27; break; - case 'f': c = '\f'; break; - case 'n': c = '\n'; break; - case 'r': c = '\r'; break; - case 't': c = '\t'; break; - case 'v': c = '\v'; break; - - case '0': case '1': case '2': case '3': - case '4': case '5': case '6': case '7': - c -= '0'; - while (i++ < 2 && isdigit(*p) && *p != '8' && *p != '9') - c = c * 8 + *p++ - '0'; - -#if !defined NOUTF8 - if (use_utf8 && c > 255) - { - unsigned char buff8[8]; - int ii, utn; - utn = ord2utf8(c, buff8); - for (ii = 0; ii < utn - 1; ii++) *q++ = buff8[ii]; - c = buff8[ii]; /* Last byte */ - } -#endif - break; - - case 'x': - - /* Handle \x{..} specially - new Perl thing for utf8 */ - -#if !defined NOUTF8 - if (*p == '{') - { - unsigned char *pt = p; - c = 0; - while (isxdigit(*(++pt))) - c = c * 16 + tolower(*pt) - ((isdigit(*pt))? '0' : 'W'); - if (*pt == '}') - { - unsigned char buff8[8]; - int ii, utn; - utn = ord2utf8(c, buff8); - for (ii = 0; ii < utn - 1; ii++) *q++ = buff8[ii]; - c = buff8[ii]; /* Last byte */ - p = pt + 1; - break; - } - /* Not correct form; fall through */ - } -#endif - - /* Ordinary \x */ - - c = 0; - while (i++ < 2 && isxdigit(*p)) - { - c = c * 16 + tolower(*p) - ((isdigit(*p))? '0' : 'W'); - p++; - } - break; - - case 0: /* \ followed by EOF allows for an empty line */ - p--; - continue; - - case '>': - while(isdigit(*p)) start_offset = start_offset * 10 + *p++ - '0'; - continue; - - case 'A': /* Option setting */ - options |= PCRE_ANCHORED; - continue; - - case 'B': - options |= PCRE_NOTBOL; - continue; - - case 'C': - if (isdigit(*p)) /* Set copy string */ - { - while(isdigit(*p)) n = n * 10 + *p++ - '0'; - copystrings |= 1 << n; - } - else if (isalnum(*p)) - { - uschar *npp = copynamesptr; - while (isalnum(*p)) *npp++ = *p++; - *npp++ = 0; - *npp = 0; - n = pcre_get_stringnumber(re, (char *)copynamesptr); - if (n < 0) - fprintf(outfile, "no parentheses with name \"%s\"\n", copynamesptr); - copynamesptr = npp; - } - else if (*p == '+') - { - callout_extra = 1; - p++; - } - else if (*p == '-') - { - pcre_callout = NULL; - p++; - } - else if (*p == '!') - { - callout_fail_id = 0; - p++; - while(isdigit(*p)) - callout_fail_id = callout_fail_id * 10 + *p++ - '0'; - callout_fail_count = 0; - if (*p == '!') - { - p++; - while(isdigit(*p)) - callout_fail_count = callout_fail_count * 10 + *p++ - '0'; - } - } - else if (*p == '*') - { - int sign = 1; - callout_data = 0; - if (*(++p) == '-') { sign = -1; p++; } - while(isdigit(*p)) - callout_data = callout_data * 10 + *p++ - '0'; - callout_data *= sign; - callout_data_set = 1; - } - continue; - -#if !defined NODFA - case 'D': -#if !defined NOPOSIX - if (posix || do_posix) - printf("** Can't use dfa matching in POSIX mode: \\D ignored\n"); - else -#endif - use_dfa = 1; - continue; - - case 'F': - options |= PCRE_DFA_SHORTEST; - continue; -#endif - - case 'G': - if (isdigit(*p)) - { - while(isdigit(*p)) n = n * 10 + *p++ - '0'; - getstrings |= 1 << n; - } - else if (isalnum(*p)) - { - uschar *npp = getnamesptr; - while (isalnum(*p)) *npp++ = *p++; - *npp++ = 0; - *npp = 0; - n = pcre_get_stringnumber(re, (char *)getnamesptr); - if (n < 0) - fprintf(outfile, "no parentheses with name \"%s\"\n", getnamesptr); - getnamesptr = npp; - } - continue; - - case 'L': - getlist = 1; - continue; - - case 'M': - find_match_limit = 1; - continue; - - case 'N': - options |= PCRE_NOTEMPTY; - continue; - - case 'O': - while(isdigit(*p)) n = n * 10 + *p++ - '0'; - if (n > size_offsets_max) - { - size_offsets_max = n; - free(offsets); - use_offsets = offsets = (int *)malloc(size_offsets_max * sizeof(int)); - if (offsets == NULL) - { - printf("** Failed to get %d bytes of memory for offsets vector\n", - size_offsets_max * sizeof(int)); - yield = 1; - goto EXIT; - } - } - use_size_offsets = n; - if (n == 0) use_offsets = NULL; /* Ensures it can't write to it */ - continue; - - case 'P': - options |= PCRE_PARTIAL; - continue; - - case 'Q': - while(isdigit(*p)) n = n * 10 + *p++ - '0'; - if (extra == NULL) - { - extra = (pcre_extra *)malloc(sizeof(pcre_extra)); - extra->flags = 0; - } - extra->flags |= PCRE_EXTRA_MATCH_LIMIT_RECURSION; - extra->match_limit_recursion = n; - continue; - - case 'q': - while(isdigit(*p)) n = n * 10 + *p++ - '0'; - if (extra == NULL) - { - extra = (pcre_extra *)malloc(sizeof(pcre_extra)); - extra->flags = 0; - } - extra->flags |= PCRE_EXTRA_MATCH_LIMIT; - extra->match_limit = n; - continue; - -#if !defined NODFA - case 'R': - options |= PCRE_DFA_RESTART; - continue; -#endif - - case 'S': - show_malloc = 1; - continue; - - case 'Z': - options |= PCRE_NOTEOL; - continue; - - case '?': - options |= PCRE_NO_UTF8_CHECK; - continue; - - case '<': - { - int x = check_newline(p, outfile); - if (x == 0) goto NEXT_DATA; - options |= x; - while (*p++ != '>'); - } - continue; - } - *q++ = c; - } - *q = 0; - len = q - dbuffer; - - if ((all_use_dfa || use_dfa) && find_match_limit) - { - printf("**Match limit not relevant for DFA matching: ignored\n"); - find_match_limit = 0; - } - - /* Handle matching via the POSIX interface, which does not - support timing or playing with the match limit or callout data. */ - -#if !defined NOPOSIX - if (posix || do_posix) - { - int rc; - int eflags = 0; - regmatch_t *pmatch = NULL; - if (use_size_offsets > 0) - pmatch = (regmatch_t *)malloc(sizeof(regmatch_t) * use_size_offsets); - if ((options & PCRE_NOTBOL) != 0) eflags |= REG_NOTBOL; - if ((options & PCRE_NOTEOL) != 0) eflags |= REG_NOTEOL; - - rc = regexec(&preg, (const char *)bptr, use_size_offsets, pmatch, eflags); - - if (rc != 0) - { - (void)regerror(rc, &preg, (char *)buffer, buffer_size); - fprintf(outfile, "No match: POSIX code %d: %s\n", rc, buffer); - } - else if ((((const pcre *)preg.re_pcre)->options & PCRE_NO_AUTO_CAPTURE) - != 0) - { - fprintf(outfile, "Matched with REG_NOSUB\n"); - } - else - { - size_t i; - for (i = 0; i < (size_t)use_size_offsets; i++) - { - if (pmatch[i].rm_so >= 0) - { - fprintf(outfile, "%2d: ", (int)i); - (void)pchars(dbuffer + pmatch[i].rm_so, - pmatch[i].rm_eo - pmatch[i].rm_so, outfile); - fprintf(outfile, "\n"); - if (i == 0 && do_showrest) - { - fprintf(outfile, " 0+ "); - (void)pchars(dbuffer + pmatch[i].rm_eo, len - pmatch[i].rm_eo, - outfile); - fprintf(outfile, "\n"); - } - } - } - } - free(pmatch); - } - - /* Handle matching via the native interface - repeats for /g and /G */ - - else -#endif /* !defined NOPOSIX */ - - for (;; gmatched++) /* Loop for /g or /G */ - { - if (timeit) - { - register int i; - clock_t time_taken; - clock_t start_time = clock(); - -#if !defined NODFA - if (all_use_dfa || use_dfa) - { - int workspace[1000]; - for (i = 0; i < LOOPREPEAT; i++) - count = pcre_dfa_exec(re, NULL, (char *)bptr, len, start_offset, - options | g_notempty, use_offsets, use_size_offsets, workspace, - sizeof(workspace)/sizeof(int)); - } - else -#endif - - for (i = 0; i < LOOPREPEAT; i++) - count = pcre_exec(re, extra, (char *)bptr, len, - start_offset, options | g_notempty, use_offsets, use_size_offsets); - - time_taken = clock() - start_time; - fprintf(outfile, "Execute time %.3f milliseconds\n", - (((double)time_taken * 1000.0) / (double)LOOPREPEAT) / - (double)CLOCKS_PER_SEC); - } - - /* If find_match_limit is set, we want to do repeated matches with - varying limits in order to find the minimum value for the match limit and - for the recursion limit. */ - - if (find_match_limit) - { - if (extra == NULL) - { - extra = (pcre_extra *)malloc(sizeof(pcre_extra)); - extra->flags = 0; - } - - (void)check_match_limit(re, extra, bptr, len, start_offset, - options|g_notempty, use_offsets, use_size_offsets, - PCRE_EXTRA_MATCH_LIMIT, &(extra->match_limit), - PCRE_ERROR_MATCHLIMIT, "match()"); - - count = check_match_limit(re, extra, bptr, len, start_offset, - options|g_notempty, use_offsets, use_size_offsets, - PCRE_EXTRA_MATCH_LIMIT_RECURSION, &(extra->match_limit_recursion), - PCRE_ERROR_RECURSIONLIMIT, "match() recursion"); - } - - /* If callout_data is set, use the interface with additional data */ - - else if (callout_data_set) - { - if (extra == NULL) - { - extra = (pcre_extra *)malloc(sizeof(pcre_extra)); - extra->flags = 0; - } - extra->flags |= PCRE_EXTRA_CALLOUT_DATA; - extra->callout_data = &callout_data; - count = pcre_exec(re, extra, (char *)bptr, len, start_offset, - options | g_notempty, use_offsets, use_size_offsets); - extra->flags &= ~PCRE_EXTRA_CALLOUT_DATA; - } - - /* The normal case is just to do the match once, with the default - value of match_limit. */ - -#if !defined NODFA - else if (all_use_dfa || use_dfa) - { - int workspace[1000]; - count = pcre_dfa_exec(re, NULL, (char *)bptr, len, start_offset, - options | g_notempty, use_offsets, use_size_offsets, workspace, - sizeof(workspace)/sizeof(int)); - if (count == 0) - { - fprintf(outfile, "Matched, but too many subsidiary matches\n"); - count = use_size_offsets/2; - } - } -#endif - - else - { - count = pcre_exec(re, extra, (char *)bptr, len, - start_offset, options | g_notempty, use_offsets, use_size_offsets); - if (count == 0) - { - fprintf(outfile, "Matched, but too many substrings\n"); - count = use_size_offsets/3; - } - } - - /* Matched */ - - if (count >= 0) - { - int i; - for (i = 0; i < count * 2; i += 2) - { - if (use_offsets[i] < 0) - fprintf(outfile, "%2d: <unset>\n", i/2); - else - { - fprintf(outfile, "%2d: ", i/2); - (void)pchars(bptr + use_offsets[i], - use_offsets[i+1] - use_offsets[i], outfile); - fprintf(outfile, "\n"); - if (i == 0) - { - if (do_showrest) - { - fprintf(outfile, " 0+ "); - (void)pchars(bptr + use_offsets[i+1], len - use_offsets[i+1], - outfile); - fprintf(outfile, "\n"); - } - } - } - } - - for (i = 0; i < 32; i++) - { - if ((copystrings & (1 << i)) != 0) - { - char copybuffer[256]; - int rc = pcre_copy_substring((char *)bptr, use_offsets, count, - i, copybuffer, sizeof(copybuffer)); - if (rc < 0) - fprintf(outfile, "copy substring %d failed %d\n", i, rc); - else - fprintf(outfile, "%2dC %s (%d)\n", i, copybuffer, rc); - } - } - - for (copynamesptr = copynames; - *copynamesptr != 0; - copynamesptr += (int)strlen((char*)copynamesptr) + 1) - { - char copybuffer[256]; - int rc = pcre_copy_named_substring(re, (char *)bptr, use_offsets, - count, (char *)copynamesptr, copybuffer, sizeof(copybuffer)); - if (rc < 0) - fprintf(outfile, "copy substring %s failed %d\n", copynamesptr, rc); - else - fprintf(outfile, " C %s (%d) %s\n", copybuffer, rc, copynamesptr); - } - - for (i = 0; i < 32; i++) - { - if ((getstrings & (1 << i)) != 0) - { - const char *substring; - int rc = pcre_get_substring((char *)bptr, use_offsets, count, - i, &substring); - if (rc < 0) - fprintf(outfile, "get substring %d failed %d\n", i, rc); - else - { - fprintf(outfile, "%2dG %s (%d)\n", i, substring, rc); - pcre_free_substring(substring); - } - } - } - - for (getnamesptr = getnames; - *getnamesptr != 0; - getnamesptr += (int)strlen((char*)getnamesptr) + 1) - { - const char *substring; - int rc = pcre_get_named_substring(re, (char *)bptr, use_offsets, - count, (char *)getnamesptr, &substring); - if (rc < 0) - fprintf(outfile, "copy substring %s failed %d\n", getnamesptr, rc); - else - { - fprintf(outfile, " G %s (%d) %s\n", substring, rc, getnamesptr); - pcre_free_substring(substring); - } - } - - if (getlist) - { - const char **stringlist; - int rc = pcre_get_substring_list((char *)bptr, use_offsets, count, - &stringlist); - if (rc < 0) - fprintf(outfile, "get substring list failed %d\n", rc); - else - { - for (i = 0; i < count; i++) - fprintf(outfile, "%2dL %s\n", i, stringlist[i]); - if (stringlist[i] != NULL) - fprintf(outfile, "string list not terminated by NULL\n"); - /* free((void *)stringlist); */ - pcre_free_substring_list(stringlist); - } - } - } - - /* There was a partial match */ - - else if (count == PCRE_ERROR_PARTIAL) - { - fprintf(outfile, "Partial match"); -#if !defined NODFA - if ((all_use_dfa || use_dfa) && use_size_offsets > 2) - fprintf(outfile, ": %.*s", use_offsets[1] - use_offsets[0], - bptr + use_offsets[0]); -#endif - fprintf(outfile, "\n"); - break; /* Out of the /g loop */ - } - - /* Failed to match. If this is a /g or /G loop and we previously set - g_notempty after a null match, this is not necessarily the end. - We want to advance the start offset, and continue. In the case of UTF-8 - matching, the advance must be one character, not one byte. Fudge the - offset values to achieve this. We won't be at the end of the string - - that was checked before setting g_notempty. */ - - else - { - if (g_notempty != 0) - { - int onechar = 1; - use_offsets[0] = start_offset; - if (use_utf8) - { - while (start_offset + onechar < len) - { - int tb = bptr[start_offset+onechar]; - if (tb <= 127) break; - tb &= 0xc0; - if (tb != 0 && tb != 0xc0) onechar++; - } - } - use_offsets[1] = start_offset + onechar; - } - else - { - if (count == PCRE_ERROR_NOMATCH) - { - if (gmatched == 0) fprintf(outfile, "No match\n"); - } - else fprintf(outfile, "Error %d\n", count); - break; /* Out of the /g loop */ - } - } - - /* If not /g or /G we are done */ - - if (!do_g && !do_G) break; - - /* If we have matched an empty string, first check to see if we are at - the end of the subject. If so, the /g loop is over. Otherwise, mimic - what Perl's /g options does. This turns out to be rather cunning. First - we set PCRE_NOTEMPTY and PCRE_ANCHORED and try the match again at the - same point. If this fails (picked up above) we advance to the next - character. */ - - g_notempty = 0; - if (use_offsets[0] == use_offsets[1]) - { - if (use_offsets[0] == len) break; - g_notempty = PCRE_NOTEMPTY | PCRE_ANCHORED; - } - - /* For /g, update the start offset, leaving the rest alone */ - - if (do_g) start_offset = use_offsets[1]; - - /* For /G, update the pointer and length */ - - else - { - bptr += use_offsets[1]; - len -= use_offsets[1]; - } - } /* End of loop for /g and /G */ - - NEXT_DATA: continue; - } /* End of loop for data lines */ - - CONTINUE: - -#if !defined NOPOSIX - if (posix || do_posix) regfree(&preg); -#endif - - if (re != NULL) new_free(re); - if (extra != NULL) new_free(extra); - if (tables != NULL) - { - new_free((void *)tables); - setlocale(LC_CTYPE, "C"); - } - } - -if (infile == stdin) fprintf(outfile, "\n"); - -EXIT: - -if (infile != NULL && infile != stdin) fclose(infile); -if (outfile != NULL && outfile != stdout) fclose(outfile); - -free(buffer); -free(dbuffer); -free(pbuffer); -free(offsets); - -return yield; -} - -/* End of pcretest.c */ diff --git a/ext/pcre/pcrelib/testdata/grepinput b/ext/pcre/pcrelib/testdata/grepinput deleted file mode 100644 index 0ded82475c..0000000000 --- a/ext/pcre/pcrelib/testdata/grepinput +++ /dev/null @@ -1,608 +0,0 @@ -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 - -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/grepinputx b/ext/pcre/pcrelib/testdata/grepinputx deleted file mode 100644 index 4c02567552..0000000000 --- a/ext/pcre/pcrelib/testdata/grepinputx +++ /dev/null @@ -1,49 +0,0 @@ -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 - -Here follows some CR/LF/CRLF test data. - -abc -def -ghi -jkl - -This is the last line of this file. diff --git a/ext/pcre/pcrelib/testdata/greplist b/ext/pcre/pcrelib/testdata/greplist deleted file mode 100644 index 1434ae96f6..0000000000 --- a/ext/pcre/pcrelib/testdata/greplist +++ /dev/null @@ -1,7 +0,0 @@ -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 deleted file mode 100644 index 1dd375b65a..0000000000 --- a/ext/pcre/pcrelib/testdata/grepoutput +++ /dev/null @@ -1,380 +0,0 @@ ----------------------------- Test 1 ------------------------------ -PATTERN at the start of a line. -In the middle of a line, PATTERN appears. -Check up on PATTERN near the end. ----------------------------- Test 2 ------------------------------ -PATTERN at the start of a line. ----------------------------- 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. -608:Check up on PATTERN near the end. ----------------------------- Test 4 ------------------------------ -4 ----------------------------- 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:608:Check up on PATTERN near the end. -./testdata/grepinputx:3:Here is the pattern again. -./testdata/grepinputx:5:Pattern ----------------------------- 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. -608:Check up on PATTERN near the end. -3:Here is the pattern again. -5:Pattern ----------------------------- Test 7 ------------------------------ -./testdata/grepinput -./testdata/grepinputx ----------------------------- Test 8 ------------------------------ -./testdata/grepinput ----------------------------- 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: -42:This is the last line of this file. ----------------------------- Test 12 ----------------------------- -Pattern ----------------------------- Test 13 ----------------------------- -Here is the pattern again. -That time it was on a line by itself. ----------------------------- Test 14 ----------------------------- -./testdata/grepinputx:To pat or not to pat, that is the question. ----------------------------- Test 15 ----------------------------- -pcregrep: Error in command-line regex at offset 4: nothing to repeat ----------------------------- Test 16 ----------------------------- -pcregrep: Failed to open ./testdata/nonexistfile: No such file or directory ----------------------------- 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. ----------------------------- 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. -------------------------------------------------------------------------------- ----------------------------- Test 19 ----------------------------- -Pattern ----------------------------- Test 20 ----------------------------- -10:complete pair -of lines -16:complete pair -of lines ----------------------------- Test 21 ----------------------------- -24:four -25-five -26-six -27-seven --- -34:fourteen -35-fifteen -36-sixteen -37-seventeen ----------------------------- Test 22 ----------------------------- -21-one -22-two -23-three -24:four --- -31-eleven -32-twelve -33-thirteen -34:fourteen ----------------------------- Test 23 ----------------------------- -one -two -three -four -five -six -seven --- -eleven -twelve -thirteen -fourteen -fifteen -sixteen -seventeen ----------------------------- Test 24 ----------------------------- -four -five -six -seven -eight -nine -ten -eleven -twelve -thirteen -fourteen -fifteen -sixteen -seventeen -eighteen -nineteen -twenty - -This is the last line of this file. ----------------------------- 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 ----------------------------- 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 is the last line of this file. ----------------------------- Test 27 ----------------------------- -four -five -six -seven -eight -nine -ten -eleven -twelve -thirteen -fourteen -fifteen -sixteen -seventeen -eighteen -nineteen -twenty - -This is the last line of this file. ----------------------------- 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 ----------------------------- 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 is the last line of this file. ----------------------------- 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-605-PUT NEW DATA ABOVE THIS LINE. -./testdata/grepinput-606-============================= -./testdata/grepinput-607- -./testdata/grepinput:608: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 ----------------------------- 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:608:Check up on PATTERN near the end. -./testdata/grepinput-609-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. ----------------------------- Test 32 ----------------------------- -./testdata/grepinputx ----------------------------- 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/grepinputx -RC=0 ----------------------------- Test 37 ----------------------------- -aaaaa0 -aaaaa2 -RC=0 -======== STDERR ======== -pcregrep: pcre_exec() error -8 while matching this line: -aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa -pcregrep: error -8 means that a resource limit was exceeded -pcregrep: check your regex for nested unlimited loops -pcregrep: pcre_exec() error -8 while matching this line: -aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa ----------------------------- Test 38 ------------------------------ -This line contains a binary zero here >---------------------------- Test 39 ------------------------------ -This is a line before the binary zero. -This line contains a binary zero here >---------------------------- Test 40 ------------------------------ -This line contains a binary zero here >This is a line after the binary zero. ----------------------------- Test 41 ------------------------------ -before the binary zero -after the binary zero ----------------------------- Test 41 ------------------------------ -./testdata/grepinput:595:before the binary zero -./testdata/grepinput:597:after the binary zero ----------------------------- Test 42 ------------------------------ -595:before -596:zero -597:after ----------------------------- Test 43 ------------------------------ -595:before -596:zero -597:zero ----------------------------- Test 44 ------------------------------ -10:pattern -595:binary -596:binary -597:binary ----------------------------- Test 45 ------------------------------ -pcregrep: Error in 2nd command-line regex at offset 9: missing ) ----------------------------- Test 46 ------------------------------ -AB.VE ----------------------------- Test 47 ------------------------------ -ABOVE the elephant -AB.VE -AB.VE the turtle ----------------------------- Test 48 ------------------------------ -ABOVE the elephant -AB.VE -AB.VE the turtle -PUT NEW DATA ABOVE THIS LINE. diff --git a/ext/pcre/pcrelib/testdata/testinput1 b/ext/pcre/pcrelib/testdata/testinput1 deleted file mode 100644 index 6cb400bd70..0000000000 --- a/ext/pcre/pcrelib/testdata/testinput1 +++ /dev/null @@ -1,3887 +0,0 @@ -/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 - -/^\/ - - -/^/ - - -/^[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$/ - abc - *** Failers - qqq\nabc - abc\nzzz - qqq\nabc\nzzz - -/\Aabc\Z/m - abc - abc\n - *** Failers - qqq\nabc - abc\nzzz - qqq\nabc\nzzz - -/\A(.)*\Z/s - abc\ndef - -/\A(.)*\Z/m - *** Failers - abc\ndef - -/(?:b)|(?::+)/ - b::c - c::b - -/[-az]+/ - az- - *** Failers - b - -/[az-]+/ - za- - *** Failers - b - -/[a\-z]+/ - a-z - *** Failers - b - -/[a-z]+/ - abcdxyz - -/[\d-]+/ - 12-34 - *** Failers - aaa - -/[\d-z]+/ - 12-34z - *** Failers - aaa - -/\x5c/ - \\ - -/\x20Z/ - the Zoo - *** Failers - Zulu - -/(abc)\1/i - abcabc - ABCabc - abcABC - -/ab{3cd/ - ab{3cd - -/ab{3,cd/ - ab{3,cd - -/ab{3,4a}cd/ - ab{3,4a}cd - -/{4,5a}bc/ - {4,5a}bc - -/^a.b/ - a\rb - *** Failers - a\nb - -/abc$/ - 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)(l)\12\123/ - abcdefghijkllS - -/(a)(b)(c)(d)(e)(f)(g)(h)(i)(j)(k)\12\123/ - abcdefghijk\12S - -/ab\gdef/ - abgdef - -/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 case of aaaaaa is missed out below because I think Perl 5.005_02 gets/ -/it wrong; it sets $1 to aaa rather than aa. Compare the following test,/ -/where it does set $1 to aa when matching aaaaaa./ - -/^(a\1?){4}$/ - a - aa - aaa - aaaa - 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}$/ - aaaaaaaaaa - *** Failers - aaaaaaaaa - aaaaaaaaaaa - -/(?:(f)(o)(o)|(b)(a)(r))*/ - foobar - -/(?<=a)b/ - ab - *** Failers - cb - b - -/(?<!c)b/ - ab - b - b - -/(?:..)*a/ - aba - -/(?:..)*?a/ - aba - -/^(?:b|a(?=(.)))*\1/ - abc - -/^(){3,5}/ - abc - -/^(a+)*ax/ - aax - -/^((a|b)+)*ax/ - aax - -/^((a|bc)+)*ax/ - aax - -/(a|x)*ab/ - cab - -/(a)*ab/ - cab - -/(?:(?i)a)b/ - ab - -/((?i)a)b/ - ab - -/(?:(?i)a)b/ - Ab - -/((?i)a)b/ - Ab - -/(?:(?i)a)b/ - *** Failers - cb - aB - -/((?i)a)b/ - -/(?i:a)b/ - ab - -/((?i:a))b/ - ab - -/(?i:a)b/ - Ab - -/((?i:a))b/ - Ab - -/(?i:a)b/ - *** Failers - aB - aB - -/((?i:a))b/ - -/(?:(?-i)a)b/i - ab - -/((?-i)a)b/i - ab - -/(?:(?-i)a)b/i - aB - -/((?-i)a)b/i - aB - -/(?:(?-i)a)b/i - *** Failers - aB - Ab - -/((?-i)a)b/i - -/(?:(?-i)a)b/i - aB - -/((?-i)a)b/i - aB - -/(?:(?-i)a)b/i - *** Failers - Ab - AB - -/((?-i)a)b/i - -/(?-i:a)b/i - ab - -/((?-i:a))b/i - ab - -/(?-i:a)b/i - aB - -/((?-i:a))b/i - aB - -/(?-i:a)b/i - *** Failers - AB - Ab - -/((?-i:a))b/i - -/(?-i:a)b/i - aB - -/((?-i:a))b/i - aB - -/(?-i:a)b/i - *** Failers - Ab - AB - -/((?-i:a))b/i - -/((?-i:a.))b/i - *** Failers - AB - a\nB - -/((?s-i:a.))b/i - a\nB - -/(?:c|d)(?:)(?:a(?:)(?:b)(?:b(?:))(?:b(?:)(?:b)))/ - cabbbb - -/(?:c|d)(?:)(?:aaaaaaaa(?:)(?:bbbbbbbb)(?:bbbbbbbb(?:))(?:bbbbbbbb(?:)(?:bbbbbbbb)))/ - caaaaaaaabbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbb - -/(ab)\d\1/i - Ab4ab - ab4Ab - -/foo\w*\d{4}baz/ - foobar1234baz - -/x(~~)*(?:(?:F)?)?/ - x~~ - -/^a(?#xxx){3}c/ - aaac - -/^a (?#xxx) (?#yyy) {3}c/x - aaac - -/(?<![cd])b/ - *** Failers - B\nB - dbcb - -/(?<![cd])[ab]/ - dbaacb - -/(?<!(c|d))b/ - -/(?<!(c|d))[ab]/ - dbaacb - -/(?<!cd)[ab]/ - cdaccb - -/^(?:a?b?)*$/ - *** 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 - -/(?(1)a|b)/ - -/(?(1)b|a)/ - a - -/(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< - -/a b/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(?:[aה]|ae)r|ex)/ - REGular - regulaer - Regex - regulהr - -/ֵזוה[א-ְ-]+/ - ֵזוהא - ֵזוה - ֵזוהְ - ֵזוה - -/(?<=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] - -/ End of testinput1 / diff --git a/ext/pcre/pcrelib/testdata/testinput2 b/ext/pcre/pcrelib/testdata/testinput2 deleted file mode 100644 index 0a87466ae7..0000000000 --- a/ext/pcre/pcrelib/testdata/testinput2 +++ /dev/null @@ -1,1646 +0,0 @@ -/(a)b|/ - -/abc/ - abc - defabc - \Aabc - *** Failers - \Adefabc - ABC - -/^abc/ - abc - \Aabc - *** Failers - defabc - \Adefabc - -/a+bc/ - -/a*bc/ - -/a{3}bc/ - -/(abc|a+z)/ - -/^abc$/ - abc - *** Failers - def\nabc - -/ab\gdef/X - -/(?X)ab\gdef/X - -/x{5,4}/ - -/z{65536}/ - -/[abcd/ - -/(?X)[\B]/ - -/[z-a]/ - -/^*/ - -/(abc/ - -/(?# abc/ - -/(?z)abc/ - -/.*b/ - -/.*?b/ - -/cat|dog|elephant/ - this sentence eventually mentions a cat - this sentences rambles on and on for a while and then reaches elephant - -/cat|dog|elephant/S - this sentence eventually mentions a cat - this sentences rambles on and on for a while and then reaches elephant - -/cat|dog|elephant/iS - this sentence eventually mentions a CAT cat - this sentences rambles on and on for a while to elephant ElePhant - -/a|[bcd]/S - -/(a|[^\dZ])/S - -/(a|b)*[\s]/S - -/(ab\2)/ - -/{4,5}abc/ - -/(a)(b)(c)\2/ - abcb - \O0abcb - \O3abcb - \O6abcb - \O9abcb - \O12abcb - -/(a)bc|(a)(b)\2/ - abc - \O0abc - \O3abc - \O6abc - aba - \O0aba - \O3aba - \O6aba - \O9aba - \O12aba - -/abc$/E - abc - *** Failers - abc\n - abc\ndef - -/(a)(b)(c)(d)(e)\6/ - -/the quick brown fox/ - the quick brown fox - this is a line with the quick brown fox - -/the quick brown fox/A - the quick brown fox - *** Failers - this is a line with the quick brown fox - -/ab(?z)cd/ - -/^abc|def/ - abcdef - abcdef\B - -/.*((abc)$|(def))/ - defabc - \Zdefabc - -/abc/P - abc - *** Failers - -/^abc|def/P - abcdef - abcdef\B - -/.*((abc)$|(def))/P - defabc - \Zdefabc - -/the quick brown fox/P - the quick brown fox - *** Failers - The Quick Brown Fox - -/the quick brown fox/Pi - the quick brown fox - The Quick Brown Fox - -/abc.def/P - *** Failers - abc\ndef - -/abc$/P - abc - abc\n - -/(abc)\2/P - -/(abc\1)/P - abc - -/)/ - -/a[]b/ - -/[^aeiou ]{3,}/ - co-processors, and for - -/<.*>/ - abc<def>ghi<klm>nop - -/<.*?>/ - abc<def>ghi<klm>nop - -/<.*>/U - abc<def>ghi<klm>nop - -/(?U)<.*>/ - abc<def>ghi<klm>nop - -/<.*?>/U - abc<def>ghi<klm>nop - -/={3,}/U - abc========def - -/(?U)={3,}?/ - abc========def - -/(?<!bar|cattle)foo/ - foo - catfoo - *** Failers - the barfoo - and cattlefoo - -/(?<=a+)b/ - -/(?<=aaa|b{0,3})b/ - -/(?<!(foo)a\1)bar/ - -/(?i)abc/ - -/(a|(?m)a)/ - -/(?i)^1234/ - -/(^b|(?i)^d)/ - -/(?s).*/ - -/[abcd]/S - -/(?i)[abcd]/S - -/(?m)[xy]|(b|c)/S - -/(^a|^b)/m - -/(?i)(^a|^b)/m - -/(a)(?(1)a|b|c)/ - -/(?(?=a)a|b|c)/ - -/(?(1a)/ - -/(?(?i))/ - -/(?(abc))/ - -/(?(?<ab))/ - -/((?s)blah)\s+\1/ - -/((?i)blah)\s+\1/ - -/((?i)b)/DS - -/(a*b|(?i:c*(?-i)d))/S - -/a$/ - a - a\n - *** Failers - \Za - \Za\n - -/a$/m - a - a\n - \Za\n - *** Failers - \Za - -/\Aabc/m - -/^abc/m - -/^((a+)(?U)([ab]+)(?-U)([bc]+)(\w*))/ - aaaaabbbbbcccccdef - -/(?<=foo)[ab]/S - -/(?<!foo)(alpha|omega)/S - -/(?!alphabet)[ab]/S - -/(?<=foo\n)^bar/m - foo\nbarbar - ***Failers - rhubarb - barbell - abc\nbarton - -/^(?<=foo\n)bar/m - foo\nbarbar - ***Failers - rhubarb - barbell - abc\nbarton - -/(?>^abc)/m - abc - def\nabc - *** Failers - defabc - -/(?<=ab(c+)d)ef/ - -/(?<=ab(?<=c+)d)ef/ - -/(?<=ab(c|de)f)g/ - -/The next three are in testinput2 because they have variable length branches/ - -/(?<=bullock|donkey)-cart/ - the bullock-cart - a donkey-cart race - *** Failers - cart - horse-and-cart - -/(?<=ab(?i)x|y|z)/ - -/(?>.*)(?<=(abcd)|(xyz))/ - alphabetabcd - endingxyz - -/(?<=ab(?i)x(?-i)y|(?i)z|b)ZZ/ - abxyZZ - abXyZZ - ZZZ - zZZ - bZZ - BZZ - *** Failers - ZZ - abXYZZ - zzz - bzz - -/(?<!(foo)a)bar/ - bar - foobbar - *** Failers - fooabar - -/This one is here because Perl 5.005_02 doesn't fail it/ - -/^(a)?(?(1)a|b)+$/ - *** Failers - a - -/This one is here because I think Perl 5.005_02 gets the setting of $1 wrong/ - -/^(a\1?){4}$/ - aaaaaa - -/These are syntax tests from Perl 5.005/ - -/a[b-a]/ - -/a[]b/ - -/a[/ - -/*a/ - -/(*)b/ - -/abc)/ - -/(abc/ - -/a**/ - -/)(/ - -/\1/ - -/\2/ - -/(a)|\2/ - -/a[b-a]/i - -/a[]b/i - -/a[/i - -/*a/i - -/(*)b/i - -/abc)/i - -/(abc/i - -/a**/i - -/)(/i - -/:(?:/ - -/(?<%)b/ - -/a(?{)b/ - -/a(?{{})b/ - -/a(?{}})b/ - -/a(?{"{"})b/ - -/a(?{"{"}})b/ - -/(?(1?)a|b)/ - -/(?(1)a|b|c)/ - -/[a[:xyz:/ - -/(?<=x+)y/ - -/a{37,17}/ - -/abc/\ - -/abc/\P - -/abc/\i - -/(a)bc(d)/ - abcd - abcd\C2 - abcd\C5 - -/(.{20})/ - abcdefghijklmnopqrstuvwxyz - abcdefghijklmnopqrstuvwxyz\C1 - abcdefghijklmnopqrstuvwxyz\G1 - -/(.{15})/ - abcdefghijklmnopqrstuvwxyz - abcdefghijklmnopqrstuvwxyz\C1\G1 - -/(.{16})/ - abcdefghijklmnopqrstuvwxyz - abcdefghijklmnopqrstuvwxyz\C1\G1\L - -/^(a|(bc))de(f)/ - adef\G1\G2\G3\G4\L - bcdef\G1\G2\G3\G4\L - adefghijk\C0 - -/^abc\00def/ - 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/M - -/.*X/D - -/.*X/Ds - -/(.*X|^B)/D - -/(.*X|^B)/Ds - -/(?s)(.*X|^B)/D - -/(?s:.*X|^B)/D - -/\Biss\B/+ - Mississippi - -/\Biss\B/+P - Mississippi - -/iss/G+ - Mississippi - -/\Biss\B/G+ - Mississippi - -/\Biss\B/g+ - Mississippi - *** Failers - Mississippi\A - -/(?<=[Ms])iss/g+ - Mississippi - -/(?<=[Ms])iss/G+ - Mississippi - -/^iss/g+ - ississippi - -/.*iss/g+ - abciss\nxyzisspqr - -/.i./+g - Mississippi - Mississippi\A - Missouri river - Missouri river\A - -/^.is/+g - Mississippi - -/^ab\n/g+ - ab\nab\ncd - -/^ab\n/mg+ - ab\nab\ncd - -/abc/ - -/abc|bac/ - -/(abc|bac)/ - -/(abc|(c|dc))/ - -/(abc|(d|de)c)/ - -/a*/ - -/a+/ - -/(baa|a+)/ - -/a{0,3}/ - -/baa{3,}/ - -/"([^\\"]+|\\.)*"/ - -/(abc|ab[cd])/ - -/(a|.)/ - -/a|ba|\w/ - -/abc(?=pqr)/ - -/...(?<=abc)/ - -/abc(?!pqr)/ - -/ab./ - -/ab[xyz]/ - -/abc*/ - -/ab.c*/ - -/a.c*/ - -/.c*/ - -/ac*/ - -/(a.c*|b.c*)/ - -/a.c*|aba/ - -/.+a/ - -/(?=abcda)a.*/ - -/(?=a)a.*/ - -/a(b)*/ - -/a\d*/ - -/ab\d*/ - -/a(\d)*/ - -/abcde{0,0}/ - -/ab\d+/ - -/a(?(1)b)/ - -/a(?(1)bag|big)/ - -/a(?(1)bag|big)*/ - -/a(?(1)bag|big)+/ - -/a(?(1)b..|b..)/ - -/ab\d{0}e/ - -/a?b?/ - a - b - ab - \ - *** Failers - \N - -/|-/ - abcd - -abc - \Nab-c - *** Failers - \Nabc - -/a*(b+)(z)(z)/P - aaaabbbbzzzz - aaaabbbbzzzz\O0 - aaaabbbbzzzz\O1 - aaaabbbbzzzz\O2 - aaaabbbbzzzz\O3 - aaaabbbbzzzz\O4 - aaaabbbbzzzz\O5 - -/^.?abcd/S - -/\( # ( at start - (?: # Non-capturing bracket - (?>[^()]+) # Either a sequence of non-brackets (no backtracking) - | # Or - (?R) # Recurse - i.e. nested bracketed string - )* # Zero or more contents - \) # Closing ) - /x - (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 - -/\( ( (?>[^()]+) | (?R) )* \) /xg - (ab(xy)cd)pqr - 1(abcd)(x(y)z)pqr - -/\( (?: (?>[^()]+) | (?R) ) \) /x - (abcd) - (ab(xy)cd) - (a(b(c)d)e) - ((ab)) - *** Failers - () - -/\( (?: (?>[^()]+) | (?R) )? \) /x - () - 12(abcde(fsh)xyz(foo(bar))lmno)89 - -/\( ( (?>[^()]+) | (?R) )* \) /x - (ab(xy)cd) - -/\( ( ( (?>[^()]+) | (?R) )* ) \) /x - (ab(xy)cd) - -/\( (123)? ( ( (?>[^()]+) | (?R) )* ) \) /x - (ab(xy)cd) - (123ab(xy)cd) - -/\( ( (123)? ( (?>[^()]+) | (?R) )* ) \) /x - (ab(xy)cd) - (123ab(xy)cd) - -/\( (((((((((( ( (?>[^()]+) | (?R) )* )))))))))) \) /x - (ab(xy)cd) - -/\( ( ( (?>[^()<>]+) | ((?>[^()]+)) | (?R) )* ) \) /x - (abcd(xyz<p>qrs)123) - -/\( ( ( (?>[^()]+) | ((?R)) )* ) \) /x - (ab(cd)ef) - (ab(cd(ef)gh)ij) - -/^[[:alnum:]]/D - -/^[[:^alnum:]]/D - -/^[[:alpha:]]/D - -/^[[:^alpha:]]/D - -/[_[:alpha:]]/IS - -/^[[:ascii:]]/D - -/^[[:^ascii:]]/D - -/^[[:blank:]]/D - -/^[[:^blank:]]/D - -/[\n\x0b\x0c\x0d[:blank:]]/IS - -/^[[:cntrl:]]/D - -/^[[:digit:]]/D - -/^[[:graph:]]/D - -/^[[:lower:]]/D - -/^[[:print:]]/D - -/^[[:punct:]]/D - -/^[[:space:]]/D - -/^[[:upper:]]/D - -/^[[:xdigit:]]/D - -/^[[:word:]]/D - -/^[[:^cntrl:]]/D - -/^[12[:^digit:]]/D - -/^[[:^blank:]]/D - -/[01[:alpha:]%]/D - -/[[.ch.]]/ - -/[[=ch=]]/ - -/[[:rhubarb:]]/ - -/[[:upper:]]/i - A - a - -/[[:lower:]]/i - A - a - -/((?-i)[[:lower:]])[[:lower:]]/i - ab - aB - *** Failers - Ab - AB - -/[\200-\110]/ - -/^(?(0)f|b)oo/ - -/This one's here because of the large output vector needed/ - -/(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\w+)\s+(\270)/ - \O900 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 ABC ABC - -/This one's here because Perl does this differently and PCRE can't at present/ - -/(main(O)?)+/ - mainmain - mainOmain - -/These are all cases where Perl does it differently (nested captures)/ - -/^(a(b)?)+$/ - aba - -/^(aa(bb)?)+$/ - aabbaa - -/^(aa|aa(bb))+$/ - aabbaa - -/^(aa(bb)??)+$/ - aabbaa - -/^(?:aa(bb)?)+$/ - aabbaa - -/^(aa(b(b))?)+$/ - aabbaa - -/^(?:aa(b(b))?)+$/ - aabbaa - -/^(?:aa(b(?:b))?)+$/ - aabbaa - -/^(?:aa(bb(?:b))?)+$/ - aabbbaa - -/^(?:aa(b(?:bb))?)+$/ - aabbbaa - -/^(?:aa(?:b(b))?)+$/ - aabbaa - -/^(?:aa(?:b(bb))?)+$/ - aabbbaa - -/^(aa(b(bb))?)+$/ - aabbbaa - -/^(aa(bb(bb))?)+$/ - aabbbbaa - -/--------------------------------------------------------------------/ - -/#/xMD - -/a#/xMD - -/[\s]/D - -/[\S]/D - -/a(?i)b/D - ab - aB - *** Failers - AB - -/(a(?i)b)/D - ab - aB - *** Failers - AB - -/ (?i)abc/xD - -/#this is a comment - (?i)abc/xD - -/123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890/D - -/\Q123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890/D - -/\Q\E/D - \ - -/\Q\Ex/D - -/ \Q\E/D - -/a\Q\E/D - abc - bca - bac - -/a\Q\Eb/D - abc - -/\Q\Eabc/D - -/x*+\w/D - *** Failers - xxxxx - -/x?+/D - -/x++/D - -/x{1,3}+/D - -/(x)*+/D - -/^(\w++|\s++)*$/ - 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 - -/(abc){1,3}+/D - -/a+?+/ - -/a{2,3}?+b/ - -/(?U)a+?+/ - -/a{2,3}?+b/U - -/x(?U)a++b/D - xaaaab - -/(?U)xa++b/D - xaaaab - -/^((a+)(?U)([ab]+)(?-U)([bc]+)(\w*))/D - -/^x(?U)a+b/D - -/^x(?U)(a+)b/D - -/[.x.]/ - -/[=x=]/ - -/[:x:]/ - -/\l/ - -/\L/ - -/\N{name}/ - -/\u/ - -/\U/ - -/[/ - -/[a-/ - -/[[:space:]/ - -/[\s]/DM - -/[[:space:]]/DM - -/[[:space:]abcde]/DM - -/< (?: (?(R) \d++ | [^<>]*+) | (?R)) * >/x - <> - <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|DM - -|\$\<\.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|DM - -/(.*)\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/iI - -/(?=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)123/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/mI - abcde - xy\nabc - *** Failers - xyabc - -/c|abc/I - -/(?i)[ab]/IS - -/[ab](?i)cd/IS - -/abc(?C)def/ - abcdef - 1234abcdef - *** Failers - abcxyz - abcxyzf - -/abc(?C)de(?C1)f/ - 123abcdef - -/(?C1)\dabc(?C2)def/ - 1234abcdef - *** Failers - abcdef - -/(?C255)ab/ - -/(?C256)ab/ - -/(?Cab)xx/ - -/(?C12vr)x/ - -/abc(?C)def/ - *** Failers - \x83\x0\x61bcdef - -/(abc)(?C)de(?C1)f/ - 123abcdef - 123abcdef\C+ - 123abcdef\C- - *** Failers - 123abcdef\C!1 - -/(?C0)(abc(?C1))*/ - abcabcabc - abcabc\C!1!3 - *** Failers - abcabcabc\C!1!3 - -/(\d{3}(?C))*/ - 123\C+ - 123456\C+ - 123456789\C+ - -/((xyz)(?C)p|(?C1)xyzabc)/ - xyzabc\C+ - -/(X)((xyz)(?C)p|(?C1)xyzabc)/ - Xxyzabc\C+ - -/(?=(abc))(?C)abcdef/ - abcdef\C+ - -/(?!(abc)(?C1)d)(?C2)abcxyz/ - abcxyz\C+ - -/(?<=(abc)(?C))xyz/ - abcxyz\C+ - -/a(b+)(c*)(?C1)/ - abbbbbccc\C*1 - -/a(b+?)(c*?)(?C1)/ - abbbbbccc\C*1 - -/(?C)abc/ - -/(?C)^abc/ - -/(?C)a|b/S - -/(?R)/ - -/(a|(?R))/ - -/(ab|(bc|(de|(?R))))/ - -/x(ab|(bc|(de|(?R))))/ - xab - xbc - xde - xxab - xxxab - *** Failers - xyab - -/(ab|(bc|(de|(?1))))/ - -/x(ab|(bc|(de|(?1)x)x)x)/ - -/^([^()]|\((?1)*\))*$/ - abc - a(b)c - a(b(c))d - *** Failers) - a(b(c)d - -/^>abc>([^()]|\((?1)*\))*<xyz<$/ - >abc>123<xyz< - >abc>1(2)3<xyz< - >abc>(1(2)3)<xyz< - -/(a(?1)b)/D - -/(a(?1)+b)/D - -/^\W*(?:((.)\W*(?1)\W*\2|)|((.)\W*(?3)\W*\4|\W*.\W*))\W*$/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 - -/^(\d+|\((?1)([+*-])(?1)\)|-(?1))$/ - 12 - (((2+2)*-3)-7) - -12 - *** Failers - ((2+2)*-3)-7) - -/^(x(y|(?1){2})z)/ - xyz - xxyzxyzz - *** Failers - xxyzz - xxyzxyzxyzz - -/((< (?: (?(R) \d++ | [^<>]*+) | (?2)) * >))/x - <> - <abcd> - <abc <123> hij> - <abc <def> hij> - <abc<>def> - <abc<> - *** Failers - <abc - -/(?1)/ - -/((?2)(abc)/ - -/^(abc)def(?1)/ - abcdefabc - -/^(a|b|c)=(?1)+/ - a=a - a=b - a=bc - -/^(a|b|c)=((?1))+/ - a=a - a=b - a=bc - -/a(?P<name1>b|c)d(?P<longername2>e)/D - abde - acde - -/(?:a(?P<c>c(?P<d>d)))(?P<a>a)/D - -/(?P<a>a)...(?P=a)bbb(?P>a)d/D - -/^\W*(?:(?P<one>(?P<two>.)\W*(?P>one)\W*(?P=two)|)|(?P<three>(?P<four>.)\W*(?P>three)\W*(?P=four)|\W*.\W*))\W*$/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 - -/((?(R)a|b))\1(?1)?/ - bb - bbaa - -/(.*)a/sI - -/(.*)a\1/sI - -/(.*)a(b)\2/sI - -/((.*)a|(.*)b)z/sI - -/((.*)a|(.*)b)z\1/sI - -/((.*)a|(.*)b)z\2/sI - -/((.*)a|(.*)b)z\3/sI - -/((.*)a|^(.*)b)z\3/sI - -/(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)a/sI - -/(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)a\31/sI - -/(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)a\32/sI - -/(a)(bc)/ND - abc - -/(?P<one>a)(bc)/ND - abc - -/(a)(?P<named>bc)/ND - -/(a+)*zz/ - aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaazzbbbbbb\M - aaaaaaaaaaaaaz\M - -/(aaa(?C1)bbb|ab)/ - aaabbb - aaabbb\C*0 - aaabbb\C*1 - aaabbb\C*-1 - -/ab(?P<one>cd)ef(?P<two>gh)/ - abcdefgh - abcdefgh\C1\Gtwo - abcdefgh\Cone\Ctwo - abcdefgh\Cthree - -/(?P<Tes>)(?P<Test>)/D - -/(?P<Test>)(?P<Tes>)/D - -/(?P<Z>zz)(?P<A>aa)/ - zzaa\CZ - zzaa\CA - -/(?P<x>eks)(?P<x>eccs)/ - -/(?P<abc>abc(?P<def>def)(?P<abc>xyz))/ - -"\[((?P<elem>\d+)(,(?P>elem))*)\]" - [10,20,30,5,5,4,4,2,43,23,4234] - *** Failers - [] - -"\[((?P<elem>\d+)(,(?P>elem))*)?\]" - [10,20,30,5,5,4,4,2,43,23,4234] - [] - -/(a(b(?2)c))?/D - -/(a(b(?2)c))*/D - -/(a(b(?2)c)){0,2}/D - -/[ab]{1}+/D - -/((w\/|-|with)*(free|immediate)*.*?shipping\s*[!.-]*)/i - Baby Bjorn Active Carrier - With free SHIPPING!! - -/((w\/|-|with)*(free|immediate)*.*?shipping\s*[!.-]*)/iS - Baby Bjorn Active Carrier - With free SHIPPING!! - -/a*.*b/SD - -/(a|b)*.?c/SD - -/abc(?C255)de(?C)f/D - -/abcde/CD - abcde - abcdfe - -/a*b/CD - ab - aaaab - aaaacb - -/a+b/CD - ab - aaaab - aaaacb - -/(abc|def)x/CD - abcx - defx - abcdefzx - -/(ab|cd){3,4}/C - ababab - abcdabcd - abcdcdcdcdcd - -/([ab]{,4}c|xy)/CD - Note: that { does NOT introduce a quantifier - -/([ab]{1,4}c|xy){4,5}?123/CD - aacaacaacaacaac123 - -/\b.*/I - ab cd\>1 - -/\b.*/Is - ab cd\>1 - -/(?!.bcd).*/I - Xbcd12345 - -/abcde/ - 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$" - 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/ - 123\P - a\P - b\P - c\P - c12\P - c123\P - -/^(?:\d){3,5}X/ - 1\P - 123\P - 123X - 1234\P - 1234X - 12345\P - 12345X - *** Failers - 1X - 123456\P - -/abc/>testsavedregex -<testsavedregex - abc - ** Failers - bca - -/abc/F>testsavedregex -<testsavedregex - abc - ** Failers - bca - -/(a|b)/S>testsavedregex -<testsavedregex - abc - ** Failers - def - -/(a|b)/SF>testsavedregex -<testsavedregex - abc - ** Failers - def - -~<(\w+)/?>(.)*</(\1)>~smg - <!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/ - 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 - -/ab.cd/P - ab-cd - ab=cd - ** Failers - ab\ncd - -/ab.cd/Ps - ab-cd - ab=cd - ab\ncd - -/(?i)(?-i)AbCd/ - AbCd - ** Failers - abcd - -/a{11111111111111111111}/ - -/(){64294967295}/ - -/(){2,4294967295}/ - -"(?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" - 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" - abcdefghijklAkB - -"(a)(b)(c)(d)(e)(f)(g)(h)(i)(j)(k)(l)A\11B" - 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)" - 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)" - aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa - -/[^()]*(?:\((?R)\)[^()]*)*/ - (this(and)that - (this(and)that) - (this(and)that)stuff - -/[^()]*(?:\((?>(?R))\)[^()]*)*/ - (this(and)that - (this(and)that) - -/[^()]*(?:\((?R)\))*[^()]*/ - (this(and)that - (this(and)that) - -/(?:\((?R)\))*[^()]*/ - (this(and)that - (this(and)that) - ((this)) - -/(?:\((?R)\))|[^()]*/ - (this(and)that - (this(and)that) - (this) - ((this)) - -/a(b)c/PN - abc - -/a(?P<name>b)c/PN - abc - -/\x{100}/ - -/\x{0000ff}/ - -/^((?P<A>a1)|(?P<A>a2)b)/ - -/^((?P<A>a1)|(?P<A>a2)b)/J - a1b\CA - a2b\CA - ** Failers - a1b\CZ\CA - -/^(?P<A>a)(?P<A>b)/J - ab\CA - -/^(?P<A>a)(?P<A>b)|cd/J - ab\CA - cd\CA - -/^(?P<A>a)(?P<A>b)|cd(?P<A>ef)(?P<A>gh)/J - cdefgh\CA - -/^((?P<A>a1)|(?P<A>a2)b)/J - a1b\GA - a2b\GA - ** Failers - a1b\GZ\GA - -/^(?P<A>a)(?P<A>b)/J - ab\GA - -/^(?P<A>a)(?P<A>b)|cd/J - ab\GA - cd\GA - -/^(?P<A>a)(?P<A>b)|cd(?P<A>ef)(?P<A>gh)/J - cdefgh\GA - -/(?J)^((?P<A>a1)|(?P<A>a2)b)/ - a1b\CA - a2b\CA - -/^(?P<A>a) (?J:(?P<B>b)(?P<B>c)) (?P<A>d)/ - -/ 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. /x - -/^(?P<A>a) (?J:(?P<B>b)(?P<B>c)) (?P<C>d)/ - a bc d\CA\CB\CC - -/^(?P<A>a)?(?(A)a|b)/ - aabc - bc - ** Failers - abc - -/(?:(?(ZZ)a|b)(?P<ZZ>X))+/ - bXaX - -/(?:(?(2y)a|b)(X))+/ - -/(?:(?(ZA)a|b)(?P<ZZ>X))+/ - -/(?:(?(ZZ)a|b)(?(ZZ)a|b)(?P<ZZ>X))+/ - bbXaaX - -/(?:(?(ZZ)a|\(b\))\\(?P<ZZ>X))+/ - (b)\\Xa\\X - -/(?P<ABC/ - -/(?:(?(A)(?P=A)a|b)(?P<A>X|Y))+/ - bXXaYYaY - bXYaXXaX - -/()()()()()()()()()(?:(?(A)(?P=A)a|b)(?P<A>X|Y))+/ - bXXaYYaY - -/\777/ - -/\s*,\s*/S - \x0b,\x0b - \x0c,\x0d - -/^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 - 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 - -/^abc/m<bad> - -/abc/ - xyz\rabc\<bad> - abc - -/.*/ - 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 - -+((?:\s|//.*\\n|/[*](?:\\n|.)*?[*]/)*)+ - /* this is a C style comment */\M - -/(?P<B>25[0-5]|2[0-4]\d|[01]?\d?\d)(?:\.(?P>B)){3}/ - -/ End of testinput2 / diff --git a/ext/pcre/pcrelib/testdata/testinput3 b/ext/pcre/pcrelib/testdata/testinput3 deleted file mode 100644 index e6ac826f77..0000000000 --- a/ext/pcre/pcrelib/testdata/testinput3 +++ /dev/null @@ -1,91 +0,0 @@ -/^[\w]+/ - *** Failers - ֹcole - -/^[\w]+/Lfr_FR - ֹcole - -/^[\w]+/ - *** Failers - ֹcole - -/^[\W]+/ - ֹcole - -/^[\W]+/Lfr_FR - *** Failers - ֹcole - -/[\b]/ - \b - *** Failers - a - -/[\b]/Lfr_FR - \b - *** Failers - a - -/^\w+/ - *** Failers - ֹcole - -/^\w+/Lfr_FR - ֹcole - -/(.+)\b(.+)/ - ֹcole - -/(.+)\b(.+)/Lfr_FR - *** Failers - ֹcole - -/ֹcole/i - ֹcole - *** Failers - יcole - -/ֹcole/iLfr_FR - ֹcole - יcole - -/\w/IS - -/\w/ISLfr_FR - -/^[\xc8-\xc9]/iLfr_FR - ֹcole - יcole - -/^[\xc8-\xc9]/Lfr_FR - ֹcole - *** Failers - יcole - -/\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:]]/DLfr_FR - -/ End of testinput3 / diff --git a/ext/pcre/pcrelib/testdata/testinput4 b/ext/pcre/pcrelib/testdata/testinput4 deleted file mode 100644 index 9ff0fc7a64..0000000000 --- a/ext/pcre/pcrelib/testdata/testinput4 +++ /dev/null @@ -1,523 +0,0 @@ -/-- Do not use the \x{} construct except with patterns that have the --/ -/-- /8 option set, because PCRE doesn't recognize them as UTF-8 unless --/ -/-- that option is set. However, the latest Perls recognize them always. --/ - -/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 - -/X(\C{3})/8 - X\x{1234} - -/X(\C{4})/8 - X\x{1234}YZ - -/X\C*/8 - XYZabcdce - -/X\C*?/8 - XYZabcde - -/X\C{3,5}/8 - Xabcdefg - X\x{1234} - X\x{1234}YZ - X\x{1234}\x{512} - X\x{1234}\x{512}YZ - -/X\C{3,5}?/8 - Xabcdefg - X\x{1234} - X\x{1234}YZ - X\x{1234}\x{512} - -/[^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 - -/a\Cb/ - aXb - a\nb - -/a\Cb/8 - aXb - a\nb - *** Failers - a\x{100}b - -/[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} - -/^בˆ´/8 - בˆ´ - -/^\בˆ´/8 - בˆ´ - -"(?s)(.{1,5})"8 - abcdefg - ab - -/ End of testinput4 / diff --git a/ext/pcre/pcrelib/testdata/testinput5 b/ext/pcre/pcrelib/testdata/testinput5 deleted file mode 100644 index 54643f6516..0000000000 --- a/ext/pcre/pcrelib/testdata/testinput5 +++ /dev/null @@ -1,274 +0,0 @@ -/\x{100}/8DM - -/\x{1000}/8DM - -/\x{10000}/8DM - -/\x{100000}/8DM - -/\x{1000000}/8DM - -/\x{4000000}/8DM - -/\x{7fffFFFF}/8DM - -/[\x{ff}]/8DM - -/[\x{100}]/8DM - -/\x{ffffffff}/8 - -/\x{100000000}/8 - -/^\x{100}a\x{1234}/8 - \x{100}a\x{1234}bcd - -/\x80/8D - -/\xff/8D - -/\x{0041}\x{2262}\x{0391}\x{002e}/D8 - \x{0041}\x{2262}\x{0391}\x{002e} - -/\x{D55c}\x{ad6d}\x{C5B4}/D8 - \x{D55c}\x{ad6d}\x{C5B4} - -/\x{65e5}\x{672c}\x{8a9e}/D8 - \x{65e5}\x{672c}\x{8a9e} - -/\x{80}/D8 - -/\x{084}/D8 - -/\x{104}/D8 - -/\x{861}/D8 - -/\x{212ab}/D8 - -/.{3,5}X/D8 - \x{212ab}\x{212ab}\x{212ab}\x{861}X - - -/.{3,5}?/D8 - \x{212ab}\x{212ab}\x{212ab}\x{861} - -/-- These tests are here rather than in testinput4 because Perl 5.6 has --/ -/-- some problems with UTF-8 support, in the area of \x{..} where the --/ -/-- value is < 255. It grumbles about invalid UTF-8 strings. --/ - -/^[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/ - -/-- --/ - -/(?<=\C)X/8 - Should produce an error diagnostic - -/-- This one is here not because it's different to Perl, but because the --/ -/-- way the captured single-byte is displayed. (In Perl it becomes a --/ -/-- character, and you can't tell the difference.) --/ - -/X(\C)(.*)/8 - X\x{1234} - X\nabc - -/^[ab]/8D - bar - *** Failers - c - \x{ff} - \x{100} - -/^[^ab]/8D - c - \x{ff} - \x{100} - *** Failers - aaa - -/[^ab\xC0-\xF0]/8SD - \x{f1} - \x{bf} - \x{100} - \x{1000} - *** Failers - \x{c0} - \x{f0} - -/ִ€{3,4}/8SD - \x{100}\x{100}\x{100}\x{100\x{100} - -/(\x{100}+|x)/8SD - -/(\x{100}*a|x)/8SD - -/(\x{100}{0,2}a|x)/8SD - -/(\x{100}{1,2}a|x)/8SD - -/\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}/8D - -/\x{100}*/8D - -/a\x{100}*/8D - -/ab\x{100}*/8D - -/a\x{100}\x{101}*/8D - -/a\x{100}\x{101}+/8D - -/\x{100}*A/8D - A - -/\x{100}*\d(?R)/8D - -/[^\x{c4}]/D - -/[^\x{c4}]/8D - -/[\x{100}]/8DM - \x{100} - Z\x{100} - \x{100}Z - *** Failers - -/[Z\x{100}]/8DM - Z\x{100} - \x{100} - \x{100}Z - *** Failers - -/[\x{200}-\x{100}]/8 - -/[ִ€-ִ„]/8 - \x{100} - \x{104} - *** Failers - \x{105} - \x{ff} - -/[z-\x{100}]/8D - -/[z\Qa-d]ִ€\E]/8D - \x{100} - ִ€ - -/[\xFF]/D - >\xff< - -/[\xff]/D8 - >\x{ff}< - -/[^\xFF]/D - -/[^\xff]/8D - -/[ֳ„-ֳ]/8 - ֳ– # Matches without Study - \x{d6} - -/[ֳ„-ֳ]/8S - ֳ– <-- Same with Study - \x{d6} - -/[\x{c4}-\x{dc}]/8 - ֳ– # Matches without Study - \x{d6} - -/[\x{c4}-\x{dc}]/8S - ֳ– <-- Same with Study - \x{d6} - -/[ֳ]/8 - -/ֳ/8 - -/ֳֳֳxxx/8 - -/ֳֳֳxxx/8?D - -/abc/8 - ֳ] - ֳ - ֳֳֳ - ֳֳֳ\? - -/anything/8 - \xc0\x80 - \xc1\x8f - \xe0\x9f\x80 - \xf0\x8f\x80\x80 - \xf8\x87\x80\x80\x80 - \xfc\x83\x80\x80\x80\x80 - \xfe\x80\x80\x80\x80\x80 - \xff\x80\x80\x80\x80\x80 - \xc3\x8f - \xe0\xaf\x80 - \xe1\x80\x80 - \xf0\x9f\x80\x80 - \xf1\x8f\x80\x80 - \xf8\x88\x80\x80\x80 - \xf9\x87\x80\x80\x80 - \xfc\x84\x80\x80\x80\x80 - \xfd\x83\x80\x80\x80\x80 - -/\x{100}abc(xyz(?1))/8D - -/[^\x{100}]abc(xyz(?1))/8D - -/[ab\x{100}]abc(xyz(?1))/8D - -/(\x{100}(b(?2)c))?/D8 - -/(\x{100}(b(?2)c)){0,2}/D8 - -/(\x{100}(b(?1)c))?/D8 - -/(\x{100}(b(?1)c)){0,2}/D8 - -/\W/8 - A.B - A\x{100}B - -/\w/8 - \x{100}X - -/a\x{1234}b/P8 - a\x{1234}b - -/^\בˆ´/8D - -/\777/I - -/\777/8I - \x{1ff} - \777 - -/ End of testinput5 / diff --git a/ext/pcre/pcrelib/testdata/testinput6 b/ext/pcre/pcrelib/testdata/testinput6 deleted file mode 100644 index da5b9ca236..0000000000 --- a/ext/pcre/pcrelib/testdata/testinput6 +++ /dev/null @@ -1,750 +0,0 @@ -/^\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{Cs}/8 - \x{dfff} - ** Failers - \x{09f} - -/^\p{Ll}/8 - a - ** Failers - Z - \x{dfff} - -/^\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{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{L}]/D - -/[\p{^L}]/D - -/[\P{L}]/D - -/[\P{^L}]/D - -/[abc\p{L}\x{0660}]/8D - -/[\p{Nd}]/8DM - 1234 - -/[\p{Nd}+-]+/8DM - 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} - -/A\x{391}\x{10427}\x{ff3a}\x{1fb0}/8iD - -/A\x{391}\x{10427}\x{ff3a}\x{1fb0}/8D - -/AB\x{1fb0}/8D - -/AB\x{1fb0}/8Di - -/\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}]/8iD - \x{104} - \x{105} - \x{109} - ** Failers - \x{100} - \x{10a} - -/[z-\x{100}]/8iD - Z - z - \x{39c} - \x{178} - | - \x{80} - \x{ff} - \x{100} - \x{101} - ** Failers - \x{102} - Y - y - -/[z-\x{100}]/8Di - -/^\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 - -/^\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 - -/ End of testinput6 / diff --git a/ext/pcre/pcrelib/testdata/testinput7 b/ext/pcre/pcrelib/testdata/testinput7 deleted file mode 100644 index 8e2d7c3ba0..0000000000 --- a/ext/pcre/pcrelib/testdata/testinput7 +++ /dev/null @@ -1,4118 +0,0 @@ -/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 - -/^\/ - - -/^/ - - -/^[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$/ - abc - *** Failers - qqq\nabc - abc\nzzz - qqq\nabc\nzzz - -/\Aabc\Z/m - abc - abc\n - *** Failers - qqq\nabc - abc\nzzz - qqq\nabc\nzzz - -/\A(.)*\Z/s - abc\ndef - -/\A(.)*\Z/m - *** Failers - abc\ndef - -/(?:b)|(?::+)/ - b::c - c::b - -/[-az]+/ - az- - *** Failers - b - -/[az-]+/ - za- - *** Failers - b - -/[a\-z]+/ - a-z - *** Failers - b - -/[a-z]+/ - abcdxyz - -/[\d-]+/ - 12-34 - *** Failers - aaa - -/[\d-z]+/ - 12-34z - *** Failers - aaa - -/\x5c/ - \\ - -/\x20Z/ - the Zoo - *** Failers - Zulu - -/ab{3cd/ - ab{3cd - -/ab{3,cd/ - ab{3,cd - -/ab{3,4a}cd/ - ab{3,4a}cd - -/{4,5a}bc/ - {4,5a}bc - -/^a.b/ - a\rb - *** Failers - a\nb - -/abc$/ - 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\gdef/ - abgdef - -/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{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)))))))))/ - 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< - -/a b/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(?:[aה]|ae)r|ex)/ - REGular - regulaer - Regex - regulהr - -/ֵזוה[א-ְ-]+/ - ֵזוהא - ֵזוה - ֵזוהְ - ֵזוה - -/(?<=Z)X./ - \x84XAZXB - -/^(?(2)a|(1)(2))+$/ - 123a - -/(?<=a|bbbb)c/ - ac - bbbbc - -/abc/>testsavedregex -<testsavedregex - abc - *** Failers - bca - -/abc/F>testsavedregex -<testsavedregex - abc - *** Failers - bca - -/(a|b)/S>testsavedregex -<testsavedregex - abc - *** Failers - def - -/(a|b)/SF>testsavedregex -<testsavedregex - abc - *** Failers - def - -/line\nbreak/ - this is a line\nbreak - line one\nthis is a line\nbreak in the second line - -/line\nbreak/f - this is a line\nbreak - ** Failers - line one\nthis is a line\nbreak in the second line - -/line\nbreak/mf - this is a line\nbreak - ** Failers - line one\nthis is a line\nbreak in the second line - -/1234/ - 123\P - a4\P\R - -/1234/ - 123\P - 4\P\R - -/^/mg - a\nb\nc\n - \ - -/(?<=C\n)^/mg - A\nC\nC\n - -/(?s)A?B/ - AB - aB - -/(?s)A*B/ - AB - aB - -/(?m)A?B/ - AB - aB - -/(?m)A*B/ - AB - aB - -/Content-Type\x3A[^\r\n]{6,}/ - Content-Type:xxxxxyyy - -/Content-Type\x3A[^\r\n]{6,}z/ - Content-Type:xxxxxyyyz - -/Content-Type\x3A[^a]{6,}/ - Content-Type:xxxyyy - -/Content-Type\x3A[^a]{6,}z/ - Content-Type:xxxyyyz - -/^abc/m - xyz\nabc - xyz\nabc\<lf> - xyz\r\nabc\<lf> - xyz\rabc\<cr> - xyz\r\nabc\<crlf> - ** Failers - xyz\nabc\<cr> - xyz\r\nabc\<cr> - xyz\nabc\<crlf> - xyz\rabc\<crlf> - xyz\rabc\<lf> - -/abc$/m - 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 - -/.*/ - 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 - -/ End of testinput7 / diff --git a/ext/pcre/pcrelib/testdata/testinput8 b/ext/pcre/pcrelib/testdata/testinput8 deleted file mode 100644 index 36db2433e4..0000000000 --- a/ext/pcre/pcrelib/testdata/testinput8 +++ /dev/null @@ -1,540 +0,0 @@ -/-- Do not use the \x{} construct except with patterns that have the --/ -/-- /8 option set, because PCRE doesn't recognize them as UTF-8 unless --/ -/-- that option is set. However, the latest Perls recognize them always. --/ - -/\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 - -/abc/8 - ֳ] - ֳ - ֳֳֳ - ֳֳֳ\? - -/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} - -/ End of testinput 8 / diff --git a/ext/pcre/pcrelib/testdata/testinput9 b/ext/pcre/pcrelib/testdata/testinput9 deleted file mode 100644 index 23d3d3e434..0000000000 --- a/ext/pcre/pcrelib/testdata/testinput9 +++ /dev/null @@ -1,816 +0,0 @@ -/\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{dfff} - -/^\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 - -/ End / diff --git a/ext/pcre/pcrelib/testdata/testoutput1 b/ext/pcre/pcrelib/testdata/testoutput1 deleted file mode 100644 index 6f5ae19b9f..0000000000 --- a/ext/pcre/pcrelib/testdata/testoutput1 +++ /dev/null @@ -1,6357 +0,0 @@ -/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 - -/^/ - - 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$/ - abc - 0: abc - *** Failers -No match - qqq\nabc -No match - abc\nzzz -No match - qqq\nabc\nzzz -No match - -/\Aabc\Z/m - abc - 0: abc - abc\n - 0: abc - *** Failers -No match - qqq\nabc -No match - abc\nzzz -No match - qqq\nabc\nzzz -No match - -/\A(.)*\Z/s - abc\ndef - 0: abc\x0adef - 1: f - -/\A(.)*\Z/m - *** Failers - 0: *** Failers - 1: s - abc\ndef -No match - -/(?:b)|(?::+)/ - b::c - 0: b - c::b - 0: :: - -/[-az]+/ - az- - 0: az- - *** Failers - 0: a - b -No match - -/[az-]+/ - za- - 0: za- - *** Failers - 0: a - b -No match - -/[a\-z]+/ - a-z - 0: a-z - *** Failers - 0: a - b -No match - -/[a-z]+/ - abcdxyz - 0: abcdxyz - -/[\d-]+/ - 12-34 - 0: 12-34 - *** Failers -No match - aaa -No match - -/[\d-z]+/ - 12-34z - 0: 12-34z - *** Failers -No match - aaa -No match - -/\x5c/ - \\ - 0: \ - -/\x20Z/ - the Zoo - 0: Z - *** Failers -No match - Zulu -No match - -/(abc)\1/i - abcabc - 0: abcabc - 1: abc - ABCabc - 0: ABCabc - 1: ABC - abcABC - 0: abcABC - 1: abc - -/ab{3cd/ - ab{3cd - 0: ab{3cd - -/ab{3,cd/ - ab{3,cd - 0: ab{3,cd - -/ab{3,4a}cd/ - ab{3,4a}cd - 0: ab{3,4a}cd - -/{4,5a}bc/ - {4,5a}bc - 0: {4,5a}bc - -/^a.b/ - a\rb - 0: a\x0db - *** Failers -No match - a\nb -No match - -/abc$/ - abc - 0: abc - abc\n - 0: abc - *** Failers -No match - abc\ndef -No match - -/(abc)\123/ - abc\x53 - 0: abcS - 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\gdef/ - abgdef - 0: abgdef - -/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 case of aaaaaa is missed out below because I think Perl 5.005_02 gets/ -/it wrong; it sets $1 to aaa rather than aa. Compare the following test,/ -No match -/where it does set $1 to aa when matching aaaaaa./ -No match - -/^(a\1?){4}$/ - a -No match - aa -No match - aaa -No match - aaaa - 0: aaaa - 1: a - 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?)*$/ - *** Failers -No match - dbcb -No match - a-- -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 - -/(?(1)a|b)/ - -/(?(1)b|a)/ - a - 0: a - -/(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 - -/a b/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(?:[aה]|ae)r|ex)/ - REGular - 0: REGular - regulaer - 0: regulaer - Regex - 0: Regex - regulהr - 0: regul\xe4r - -/ֵזוה[א-ְ-]+/ - ֵזוהא - 0: \xc5\xe6\xe5\xe4\xe0 - ֵזוה - 0: \xc5\xe6\xe5\xe4\xff - ֵזוהְ - 0: \xc5\xe6\xe5\xe4\xc0 - ֵזוה - 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] - -/ End of testinput1 / diff --git a/ext/pcre/pcrelib/testdata/testoutput2 b/ext/pcre/pcrelib/testdata/testoutput2 deleted file mode 100644 index bcde708569..0000000000 --- a/ext/pcre/pcrelib/testdata/testoutput2 +++ /dev/null @@ -1,6554 +0,0 @@ -/(a)b|/ -Capturing subpattern count = 1 -No options -No first char -No need char - -/abc/ -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/ -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/ -Capturing subpattern count = 0 -Partial matching not supported -No options -First char = 'a' -Need char = 'c' - -/a*bc/ -Capturing subpattern count = 0 -Partial matching not supported -No options -No first char -Need char = 'c' - -/a{3}bc/ -Capturing subpattern count = 0 -Partial matching not supported -No options -First char = 'a' -Need char = 'c' - -/(abc|a+z)/ -Capturing subpattern count = 1 -Partial matching not supported -No options -First char = 'a' -No need char - -/^abc$/ -Capturing subpattern count = 0 -Options: anchored -No first char -No need char - abc - 0: abc - *** Failers -No match - def\nabc -No match - -/ab\gdef/X -Failed: unrecognized character follows \ at offset 3 - -/(?X)ab\gdef/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 - -/[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 (? at offset 2 - -/.*b/ -Capturing subpattern count = 0 -Partial matching not supported -No options -First char at start or follows newline -Need char = 'b' - -/.*?b/ -Capturing subpattern count = 0 -Partial matching not supported -No options -First char at start or follows newline -Need char = 'b' - -/cat|dog|elephant/ -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/S -Capturing subpattern count = 0 -No options -No first char -No need char -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/iS -Capturing subpattern count = 0 -Options: caseless -No first char -No need char -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]/S -Capturing subpattern count = 0 -No options -No first char -No need char -Starting byte set: a b c d - -/(a|[^\dZ])/S -Capturing subpattern count = 1 -No options -No first char -No need char -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]/S -Capturing subpattern count = 1 -No options -No first char -No need char -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/ -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/ -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$/E -Capturing subpattern count = 0 -Options: dollar_endonly -First char = 'a' -Need char = 'c' - abc - 0: abc - *** Failers -No match - abc\n -No match - abc\ndef -No match - -/(a)(b)(c)(d)(e)\6/ -Failed: reference to non-existent subpattern at offset 17 - -/the quick brown fox/ -Capturing subpattern count = 0 -No options -First char = 't' -Need char = 'x' - the quick brown fox - 0: the quick brown fox - this is a line with the quick brown fox - 0: the quick brown fox - -/the quick brown fox/A -Capturing subpattern count = 0 -Options: anchored -No first char -No need char - the quick brown fox - 0: the quick brown fox - *** Failers -No match - this is a line with the quick brown fox -No match - -/ab(?z)cd/ -Failed: unrecognized character after (? at offset 4 - -/^abc|def/ -Capturing subpattern count = 0 -No options -No first char -No need char - abcdef - 0: abc - abcdef\B - 0: def - -/.*((abc)$|(def))/ -Capturing subpattern count = 3 -Partial matching not supported -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 - -/abc/P - abc - 0: abc - *** Failers -No match: POSIX code 17: match failed - -/^abc|def/P - abcdef - 0: abc - abcdef\B - 0: def - -/.*((abc)$|(def))/P - defabc - 0: defabc - 1: abc - 2: abc - \Zdefabc - 0: def - 1: def - 3: def - -/the quick brown fox/P - the quick brown fox - 0: the quick brown fox - *** Failers -No match: POSIX code 17: match failed - The Quick Brown Fox -No match: POSIX code 17: match failed - -/the quick brown fox/Pi - the quick brown fox - 0: the quick brown fox - The Quick Brown Fox - 0: The Quick Brown Fox - -/abc.def/P - *** Failers -No match: POSIX code 17: match failed - abc\ndef -No match: POSIX code 17: match failed - -/abc$/P - abc - 0: abc - abc\n - 0: abc - -/(abc)\2/P -Failed: POSIX code 15: bad back reference at offset 7 - -/(abc\1)/P - abc -No match: POSIX code 17: match failed - -/)/ -Failed: unmatched parentheses at offset 0 - -/a[]b/ -Failed: missing terminating ] for character class at offset 4 - -/[^aeiou ]{3,}/ -Capturing subpattern count = 0 -Partial matching not supported -No options -No first char -No need char - co-processors, and for - 0: -pr - -/<.*>/ -Capturing subpattern count = 0 -Partial matching not supported -No options -First char = '<' -Need char = '>' - abc<def>ghi<klm>nop - 0: <def>ghi<klm> - -/<.*?>/ -Capturing subpattern count = 0 -Partial matching not supported -No options -First char = '<' -Need char = '>' - abc<def>ghi<klm>nop - 0: <def> - -/<.*>/U -Capturing subpattern count = 0 -Partial matching not supported -Options: ungreedy -First char = '<' -Need char = '>' - abc<def>ghi<klm>nop - 0: <def> - -/(?U)<.*>/ -Capturing subpattern count = 0 -Partial matching not supported -Options: ungreedy -First char = '<' -Need char = '>' - abc<def>ghi<klm>nop - 0: <def> - -/<.*?>/U -Capturing subpattern count = 0 -Partial matching not supported -Options: ungreedy -First char = '<' -Need char = '>' - abc<def>ghi<klm>nop - 0: <def>ghi<klm> - -/={3,}/U -Capturing subpattern count = 0 -Partial matching not supported -Options: ungreedy -First char = '=' -Need char = '=' - abc========def - 0: === - -/(?U)={3,}?/ -Capturing subpattern count = 0 -Partial matching not supported -Options: ungreedy -First char = '=' -Need char = '=' - abc========def - 0: ======== - -/(?<!bar|cattle)foo/ -Capturing subpattern count = 0 -No options -First char = 'f' -Need char = 'o' - 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/ -Capturing subpattern count = 0 -Options: caseless -First char = 'a' (caseless) -Need char = 'c' (caseless) - -/(a|(?m)a)/ -Capturing subpattern count = 1 -No options -First char = 'a' -No need char - -/(?i)^1234/ -Capturing subpattern count = 0 -Options: anchored caseless -No first char -No need char - -/(^b|(?i)^d)/ -Capturing subpattern count = 1 -Options: anchored -No first char -No need char - -/(?s).*/ -Capturing subpattern count = 0 -Partial matching not supported -Options: anchored dotall -No first char -No need char - -/[abcd]/S -Capturing subpattern count = 0 -No options -No first char -No need char -Starting byte set: a b c d - -/(?i)[abcd]/S -Capturing subpattern count = 0 -Options: caseless -No first char -No need char -Starting byte set: A B C D a b c d - -/(?m)[xy]|(b|c)/S -Capturing subpattern count = 1 -Options: multiline -No first char -No need char -Starting byte set: b c x y - -/(^a|^b)/m -Capturing subpattern count = 1 -Options: multiline -First char at start or follows newline -No need char - -/(?i)(^a|^b)/m -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: 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: unrecognized character after (?< at offset 5 - -/((?s)blah)\s+\1/ -Capturing subpattern count = 1 -Max back reference = 1 -Partial matching not supported -No options -First char = 'b' -Need char = 'h' - -/((?i)blah)\s+\1/ -Capturing subpattern count = 1 -Max back reference = 1 -Partial matching not supported -No options -First char = 'b' (caseless) -Need char = 'h' (caseless) - -/((?i)b)/DS ------------------------------------------------------------------- - 0 15 Bra 0 - 3 7 Bra 1 - 6 01 Opt - 8 NC b - 10 7 Ket - 13 00 Opt - 15 15 Ket - 18 End ------------------------------------------------------------------- -Capturing subpattern count = 1 -No options -First char = 'b' (caseless) -No need char -Study returned NULL - -/(a*b|(?i:c*(?-i)d))/S -Capturing subpattern count = 1 -Partial matching not supported -No options -No first char -No need char -Starting byte set: C a b c d - -/a$/ -Capturing subpattern count = 0 -No options -First char = 'a' -No need char - a - 0: a - a\n - 0: a - *** Failers -No match - \Za -No match - \Za\n -No match - -/a$/m -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/m -Capturing subpattern count = 0 -Options: anchored multiline -No first char -No need char - -/^abc/m -Capturing subpattern count = 0 -Options: multiline -First char at start or follows newline -Need char = 'c' - -/^((a+)(?U)([ab]+)(?-U)([bc]+)(\w*))/ -Capturing subpattern count = 5 -Partial matching not supported -Options: anchored -No first char -No need char - aaaaabbbbbcccccdef - 0: aaaaabbbbbcccccdef - 1: aaaaabbbbbcccccdef - 2: aaaaa - 3: b - 4: bbbbccccc - 5: def - -/(?<=foo)[ab]/S -Capturing subpattern count = 0 -No options -No first char -No need char -Starting byte set: a b - -/(?<!foo)(alpha|omega)/S -Capturing subpattern count = 1 -No options -No first char -Need char = 'a' -Starting byte set: a o - -/(?!alphabet)[ab]/S -Capturing subpattern count = 0 -No options -No first char -No need char -Starting byte set: a b - -/(?<=foo\n)^bar/m -Capturing subpattern count = 0 -Options: multiline -No first char -Need char = 'r' - foo\nbarbar - 0: bar - ***Failers -No match - rhubarb -No match - barbell -No match - abc\nbarton -No match - -/^(?<=foo\n)bar/m -Capturing subpattern count = 0 -Options: multiline -First char at start or follows newline -Need char = 'r' - foo\nbarbar - 0: bar - ***Failers -No match - rhubarb -No match - barbell -No match - abc\nbarton -No match - -/(?>^abc)/m -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/ -Capturing subpattern count = 0 -No options -First char = 'T' -Need char = 's' - -/(?<=bullock|donkey)-cart/ -Capturing subpattern count = 0 -No options -First char = '-' -Need char = 't' - 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)/ -Capturing subpattern count = 0 -No options -No first char -No need char - -/(?>.*)(?<=(abcd)|(xyz))/ -Capturing subpattern count = 2 -Partial matching not supported -No options -First char at start or follows newline -No need char - alphabetabcd - 0: alphabetabcd - 1: abcd - endingxyz - 0: endingxyz - 1: <unset> - 2: xyz - -/(?<=ab(?i)x(?-i)y|(?i)z|b)ZZ/ -Capturing subpattern count = 0 -No options -First char = 'Z' -Need char = 'Z' - 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/ -Capturing subpattern count = 1 -No options -First char = 'b' -Need char = 'r' - 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/ -Capturing subpattern count = 0 -No options -First char = 'T' -Need char = 't' - -/^(a)?(?(1)a|b)+$/ -Capturing subpattern count = 1 -Options: anchored -No first char -No need char - *** Failers -No match - a -No match - -/This one is here because I think Perl 5.005_02 gets the setting of $1 wrong/ -Capturing subpattern count = 0 -No options -First char = 'T' -Need char = 'g' - -/^(a\1?){4}$/ -Capturing subpattern count = 1 -Max back reference = 1 -Options: anchored -No first char -No need char - aaaaaa - 0: aaaaaa - 1: aa - -/These are syntax tests from Perl 5.005/ -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]/i -Failed: range out of order in character class at offset 4 - -/a[]b/i -Failed: missing terminating ] for character class at offset 4 - -/a[/i -Failed: missing terminating ] for character class at offset 2 - -/*a/i -Failed: nothing to repeat at offset 0 - -/(*)b/i -Failed: nothing to repeat at offset 1 - -/abc)/i -Failed: unmatched parentheses at offset 3 - -/(abc/i -Failed: missing ) at offset 4 - -/a**/i -Failed: nothing to repeat at offset 2 - -/)(/i -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 (? at offset 3 - -/a(?{{})b/ -Failed: unrecognized character after (? at offset 3 - -/a(?{}})b/ -Failed: unrecognized character after (? at offset 3 - -/a(?{"{"})b/ -Failed: unrecognized character after (? at offset 3 - -/a(?{"{"}})b/ -Failed: unrecognized character after (? at offset 3 - -/(?(1?)a|b)/ -Failed: malformed number or name after (?( at offset 4 - -/(?(1)a|b|c)/ -Failed: conditional group contains more than two branches at offset 10 - -/[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/\P -Failed: POSIX code 9: bad escape sequence at offset 4 - -/abc/\i -Failed: \ at end of pattern at offset 4 - -/(a)bc(d)/ -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})/ -Capturing subpattern count = 1 -Partial matching not supported -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})/ -Capturing subpattern count = 1 -Partial matching not supported -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})/ -Capturing subpattern count = 1 -Partial matching not supported -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)/ -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/ -Capturing subpattern count = 0 -Options: anchored -No first char -No need char - abc\00def\L\C0 - 0: abc\x00def - 0C abc (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/M -Memory allocation (code space): 432 -Capturing subpattern count = 8 -Partial matching not supported -No options -First char = 'w' -Need char = 'd' - -/.*X/D ------------------------------------------------------------------- - 0 7 Bra 0 - 3 Any* - 5 X - 7 7 Ket - 10 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Partial matching not supported -No options -First char at start or follows newline -Need char = 'X' - -/.*X/Ds ------------------------------------------------------------------- - 0 7 Bra 0 - 3 Any* - 5 X - 7 7 Ket - 10 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Partial matching not supported -Options: anchored dotall -No first char -Need char = 'X' - -/(.*X|^B)/D ------------------------------------------------------------------- - 0 19 Bra 0 - 3 7 Bra 1 - 6 Any* - 8 X - 10 6 Alt - 13 ^ - 14 B - 16 13 Ket - 19 19 Ket - 22 End ------------------------------------------------------------------- -Capturing subpattern count = 1 -Partial matching not supported -No options -First char at start or follows newline -No need char - -/(.*X|^B)/Ds ------------------------------------------------------------------- - 0 19 Bra 0 - 3 7 Bra 1 - 6 Any* - 8 X - 10 6 Alt - 13 ^ - 14 B - 16 13 Ket - 19 19 Ket - 22 End ------------------------------------------------------------------- -Capturing subpattern count = 1 -Partial matching not supported -Options: anchored dotall -No first char -No need char - -/(?s)(.*X|^B)/D ------------------------------------------------------------------- - 0 19 Bra 0 - 3 7 Bra 1 - 6 Any* - 8 X - 10 6 Alt - 13 ^ - 14 B - 16 13 Ket - 19 19 Ket - 22 End ------------------------------------------------------------------- -Capturing subpattern count = 1 -Partial matching not supported -Options: anchored dotall -No first char -No need char - -/(?s:.*X|^B)/D ------------------------------------------------------------------- - 0 25 Bra 0 - 3 9 Bra 0 - 6 04 Opt - 8 Any* - 10 X - 12 8 Alt - 15 04 Opt - 17 ^ - 18 B - 20 17 Ket - 23 00 Opt - 25 25 Ket - 28 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Partial matching not supported -No options -First char at start or follows newline -No need char - -/\Biss\B/+ -Capturing subpattern count = 0 -No options -First char = 'i' -Need char = 's' - Mississippi - 0: iss - 0+ issippi - -/\Biss\B/+P - Mississippi - 0: iss - 0+ issippi - -/iss/G+ -Capturing subpattern count = 0 -No options -First char = 'i' -Need char = 's' - Mississippi - 0: iss - 0+ issippi - 0: iss - 0+ ippi - -/\Biss\B/G+ -Capturing subpattern count = 0 -No options -First char = 'i' -Need char = 's' - Mississippi - 0: iss - 0+ issippi - -/\Biss\B/g+ -Capturing subpattern count = 0 -No options -First char = 'i' -Need char = 's' - Mississippi - 0: iss - 0+ issippi - 0: iss - 0+ ippi - *** Failers -No match - Mississippi\A -No match - -/(?<=[Ms])iss/g+ -Capturing subpattern count = 0 -No options -First char = 'i' -Need char = 's' - Mississippi - 0: iss - 0+ issippi - 0: iss - 0+ ippi - -/(?<=[Ms])iss/G+ -Capturing subpattern count = 0 -No options -First char = 'i' -Need char = 's' - Mississippi - 0: iss - 0+ issippi - -/^iss/g+ -Capturing subpattern count = 0 -Options: anchored -No first char -No need char - ississippi - 0: iss - 0+ issippi - -/.*iss/g+ -Capturing subpattern count = 0 -Partial matching not supported -No options -First char at start or follows newline -Need char = 's' - abciss\nxyzisspqr - 0: abciss - 0+ \x0axyzisspqr - 0: xyziss - 0+ pqr - -/.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/+g -Capturing subpattern count = 0 -Options: anchored -No first char -No need char - Mississippi - 0: Mis - 0+ sissippi - -/^ab\n/g+ -Capturing subpattern count = 0 -Options: anchored -No first char -No need char - ab\nab\ncd - 0: ab\x0a - 0+ ab\x0acd - -/^ab\n/mg+ -Capturing subpattern count = 0 -Options: multiline -First char at start or follows newline -Need char = 10 - ab\nab\ncd - 0: ab\x0a - 0+ ab\x0acd - 0: ab\x0a - 0+ cd - -/abc/ -Capturing subpattern count = 0 -No options -First char = 'a' -Need char = 'c' - -/abc|bac/ -Capturing subpattern count = 0 -No options -No first char -Need char = 'c' - -/(abc|bac)/ -Capturing subpattern count = 1 -No options -No first char -Need char = 'c' - -/(abc|(c|dc))/ -Capturing subpattern count = 2 -No options -No first char -Need char = 'c' - -/(abc|(d|de)c)/ -Capturing subpattern count = 2 -No options -No first char -Need char = 'c' - -/a*/ -Capturing subpattern count = 0 -Partial matching not supported -No options -No first char -No need char - -/a+/ -Capturing subpattern count = 0 -Partial matching not supported -No options -First char = 'a' -No need char - -/(baa|a+)/ -Capturing subpattern count = 1 -Partial matching not supported -No options -No first char -Need char = 'a' - -/a{0,3}/ -Capturing subpattern count = 0 -Partial matching not supported -No options -No first char -No need char - -/baa{3,}/ -Capturing subpattern count = 0 -Partial matching not supported -No options -First char = 'b' -Need char = 'a' - -/"([^\\"]+|\\.)*"/ -Capturing subpattern count = 1 -Partial matching not supported -No options -First char = '"' -Need char = '"' - -/(abc|ab[cd])/ -Capturing subpattern count = 1 -No options -First char = 'a' -No need char - -/(a|.)/ -Capturing subpattern count = 1 -No options -No first char -No need char - -/a|ba|\w/ -Capturing subpattern count = 0 -No options -No first char -No need char - -/abc(?=pqr)/ -Capturing subpattern count = 0 -No options -First char = 'a' -Need char = 'r' - -/...(?<=abc)/ -Capturing subpattern count = 0 -No options -No first char -No need char - -/abc(?!pqr)/ -Capturing subpattern count = 0 -No options -First char = 'a' -Need char = 'c' - -/ab./ -Capturing subpattern count = 0 -No options -First char = 'a' -Need char = 'b' - -/ab[xyz]/ -Capturing subpattern count = 0 -No options -First char = 'a' -Need char = 'b' - -/abc*/ -Capturing subpattern count = 0 -Partial matching not supported -No options -First char = 'a' -Need char = 'b' - -/ab.c*/ -Capturing subpattern count = 0 -Partial matching not supported -No options -First char = 'a' -Need char = 'b' - -/a.c*/ -Capturing subpattern count = 0 -Partial matching not supported -No options -First char = 'a' -No need char - -/.c*/ -Capturing subpattern count = 0 -Partial matching not supported -No options -No first char -No need char - -/ac*/ -Capturing subpattern count = 0 -Partial matching not supported -No options -First char = 'a' -No need char - -/(a.c*|b.c*)/ -Capturing subpattern count = 1 -Partial matching not supported -No options -No first char -No need char - -/a.c*|aba/ -Capturing subpattern count = 0 -Partial matching not supported -No options -First char = 'a' -No need char - -/.+a/ -Capturing subpattern count = 0 -Partial matching not supported -No options -No first char -Need char = 'a' - -/(?=abcda)a.*/ -Capturing subpattern count = 0 -Partial matching not supported -No options -First char = 'a' -Need char = 'a' - -/(?=a)a.*/ -Capturing subpattern count = 0 -Partial matching not supported -No options -First char = 'a' -No need char - -/a(b)*/ -Capturing subpattern count = 1 -No options -First char = 'a' -No need char - -/a\d*/ -Capturing subpattern count = 0 -Partial matching not supported -No options -First char = 'a' -No need char - -/ab\d*/ -Capturing subpattern count = 0 -Partial matching not supported -No options -First char = 'a' -Need char = 'b' - -/a(\d)*/ -Capturing subpattern count = 1 -No options -First char = 'a' -No need char - -/abcde{0,0}/ -Capturing subpattern count = 0 -No options -First char = 'a' -Need char = 'd' - -/ab\d+/ -Capturing subpattern count = 0 -Partial matching not supported -No options -First char = 'a' -Need char = 'b' - -/a(?(1)b)/ -Capturing subpattern count = 0 -No options -First char = 'a' -No need char - -/a(?(1)bag|big)/ -Capturing subpattern count = 0 -No options -First char = 'a' -Need char = 'g' - -/a(?(1)bag|big)*/ -Capturing subpattern count = 0 -No options -First char = 'a' -No need char - -/a(?(1)bag|big)+/ -Capturing subpattern count = 0 -No options -First char = 'a' -Need char = 'g' - -/a(?(1)b..|b..)/ -Capturing subpattern count = 0 -No options -First char = 'a' -Need char = 'b' - -/ab\d{0}e/ -Capturing subpattern count = 0 -No options -First char = 'a' -Need char = 'e' - -/a?b?/ -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 - -/|-/ -Capturing subpattern count = 0 -No options -No first char -No need char - abcd - 0: - -abc - 0: - \Nab-c - 0: - - *** Failers - 0: - \Nabc -No match - -/a*(b+)(z)(z)/P - aaaabbbbzzzz - 0: aaaabbbbzz - 1: bbbb - 2: z - 3: z - aaaabbbbzzzz\O0 - aaaabbbbzzzz\O1 - 0: aaaabbbbzz - aaaabbbbzzzz\O2 - 0: aaaabbbbzz - 1: bbbb - aaaabbbbzzzz\O3 - 0: aaaabbbbzz - 1: bbbb - 2: z - aaaabbbbzzzz\O4 - 0: aaaabbbbzz - 1: bbbb - 2: z - 3: z - aaaabbbbzzzz\O5 - 0: aaaabbbbzz - 1: bbbb - 2: z - 3: z - -/^.?abcd/S -Capturing subpattern count = 0 -Options: anchored -No first char -Need char = 'd' -Study returned NULL - -/\( # ( at start - (?: # Non-capturing bracket - (?>[^()]+) # Either a sequence of non-brackets (no backtracking) - | # Or - (?R) # Recurse - i.e. nested bracketed string - )* # Zero or more contents - \) # Closing ) - /x -Capturing subpattern count = 0 -Partial matching not supported -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 - -/\( ( (?>[^()]+) | (?R) )* \) /xg -Capturing subpattern count = 1 -Partial matching not supported -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 - -/\( (?: (?>[^()]+) | (?R) ) \) /x -Capturing subpattern count = 0 -Partial matching not supported -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 - -/\( (?: (?>[^()]+) | (?R) )? \) /x -Capturing subpattern count = 0 -Partial matching not supported -Options: extended -First char = '(' -Need char = ')' - () - 0: () - 12(abcde(fsh)xyz(foo(bar))lmno)89 - 0: (fsh) - -/\( ( (?>[^()]+) | (?R) )* \) /x -Capturing subpattern count = 1 -Partial matching not supported -Options: extended -First char = '(' -Need char = ')' - (ab(xy)cd) - 0: (ab(xy)cd) - 1: cd - -/\( ( ( (?>[^()]+) | (?R) )* ) \) /x -Capturing subpattern count = 2 -Partial matching not supported -Options: extended -First char = '(' -Need char = ')' - (ab(xy)cd) - 0: (ab(xy)cd) - 1: ab(xy)cd - 2: cd - -/\( (123)? ( ( (?>[^()]+) | (?R) )* ) \) /x -Capturing subpattern count = 3 -Partial matching not supported -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 - -/\( ( (123)? ( (?>[^()]+) | (?R) )* ) \) /x -Capturing subpattern count = 3 -Partial matching not supported -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 - -/\( (((((((((( ( (?>[^()]+) | (?R) )* )))))))))) \) /x -Capturing subpattern count = 11 -Partial matching not supported -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 - -/\( ( ( (?>[^()<>]+) | ((?>[^()]+)) | (?R) )* ) \) /x -Capturing subpattern count = 3 -Partial matching not supported -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 - 3: <unset> - -/\( ( ( (?>[^()]+) | ((?R)) )* ) \) /x -Capturing subpattern count = 3 -Partial matching not supported -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:]]/D ------------------------------------------------------------------- - 0 37 Bra 0 - 3 ^ - 4 [0-9A-Za-z] - 37 37 Ket - 40 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: anchored -No first char -No need char - -/^[[:^alnum:]]/D ------------------------------------------------------------------- - 0 37 Bra 0 - 3 ^ - 4 [\x00-/:-@[-`{-\xff] - 37 37 Ket - 40 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: anchored -No first char -No need char - -/^[[:alpha:]]/D ------------------------------------------------------------------- - 0 37 Bra 0 - 3 ^ - 4 [A-Za-z] - 37 37 Ket - 40 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: anchored -No first char -No need char - -/^[[:^alpha:]]/D ------------------------------------------------------------------- - 0 37 Bra 0 - 3 ^ - 4 [\x00-@[-`{-\xff] - 37 37 Ket - 40 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 -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:]]/D ------------------------------------------------------------------- - 0 37 Bra 0 - 3 ^ - 4 [\x00-\x7f] - 37 37 Ket - 40 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: anchored -No first char -No need char - -/^[[:^ascii:]]/D ------------------------------------------------------------------- - 0 37 Bra 0 - 3 ^ - 4 [\x80-\xff] - 37 37 Ket - 40 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: anchored -No first char -No need char - -/^[[:blank:]]/D ------------------------------------------------------------------- - 0 37 Bra 0 - 3 ^ - 4 [\x09 ] - 37 37 Ket - 40 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: anchored -No first char -No need char - -/^[[:^blank:]]/D ------------------------------------------------------------------- - 0 37 Bra 0 - 3 ^ - 4 [\x00-\x08\x0a-\x1f!-\xff] - 37 37 Ket - 40 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: anchored -No first char -No need char - -/[\n\x0b\x0c\x0d[:blank:]]/IS -Capturing subpattern count = 0 -No options -No first char -No need char -Starting byte set: \x09 \x0a \x0b \x0c \x0d \x20 - -/^[[:cntrl:]]/D ------------------------------------------------------------------- - 0 37 Bra 0 - 3 ^ - 4 [\x00-\x1f\x7f] - 37 37 Ket - 40 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: anchored -No first char -No need char - -/^[[:digit:]]/D ------------------------------------------------------------------- - 0 37 Bra 0 - 3 ^ - 4 [0-9] - 37 37 Ket - 40 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: anchored -No first char -No need char - -/^[[:graph:]]/D ------------------------------------------------------------------- - 0 37 Bra 0 - 3 ^ - 4 [!-~] - 37 37 Ket - 40 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: anchored -No first char -No need char - -/^[[:lower:]]/D ------------------------------------------------------------------- - 0 37 Bra 0 - 3 ^ - 4 [a-z] - 37 37 Ket - 40 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: anchored -No first char -No need char - -/^[[:print:]]/D ------------------------------------------------------------------- - 0 37 Bra 0 - 3 ^ - 4 [ -~] - 37 37 Ket - 40 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: anchored -No first char -No need char - -/^[[:punct:]]/D ------------------------------------------------------------------- - 0 37 Bra 0 - 3 ^ - 4 [!-/:-@[-`{-~] - 37 37 Ket - 40 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: anchored -No first char -No need char - -/^[[:space:]]/D ------------------------------------------------------------------- - 0 37 Bra 0 - 3 ^ - 4 [\x09-\x0d ] - 37 37 Ket - 40 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: anchored -No first char -No need char - -/^[[:upper:]]/D ------------------------------------------------------------------- - 0 37 Bra 0 - 3 ^ - 4 [A-Z] - 37 37 Ket - 40 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: anchored -No first char -No need char - -/^[[:xdigit:]]/D ------------------------------------------------------------------- - 0 37 Bra 0 - 3 ^ - 4 [0-9A-Fa-f] - 37 37 Ket - 40 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: anchored -No first char -No need char - -/^[[:word:]]/D ------------------------------------------------------------------- - 0 37 Bra 0 - 3 ^ - 4 [0-9A-Z_a-z] - 37 37 Ket - 40 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: anchored -No first char -No need char - -/^[[:^cntrl:]]/D ------------------------------------------------------------------- - 0 37 Bra 0 - 3 ^ - 4 [ -~\x80-\xff] - 37 37 Ket - 40 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: anchored -No first char -No need char - -/^[12[:^digit:]]/D ------------------------------------------------------------------- - 0 37 Bra 0 - 3 ^ - 4 [\x00-/12:-\xff] - 37 37 Ket - 40 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: anchored -No first char -No need char - -/^[[:^blank:]]/D ------------------------------------------------------------------- - 0 37 Bra 0 - 3 ^ - 4 [\x00-\x08\x0a-\x1f!-\xff] - 37 37 Ket - 40 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: anchored -No first char -No need char - -/[01[:alpha:]%]/D ------------------------------------------------------------------- - 0 36 Bra 0 - 3 [%01A-Za-z] - 36 36 Ket - 39 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -No options -No first char -No need char - -/[[.ch.]]/ -Failed: POSIX collating elements are not supported at offset 1 - -/[[=ch=]]/ -Failed: POSIX collating elements are not supported at offset 1 - -/[[:rhubarb:]]/ -Failed: unknown POSIX class name at offset 3 - -/[[:upper:]]/i -Capturing subpattern count = 0 -Options: caseless -No first char -No need char - A - 0: A - a - 0: a - -/[[:lower:]]/i -Capturing subpattern count = 0 -Options: caseless -No first char -No need char - A - 0: A - a - 0: a - -/((?-i)[[:lower:]])[[:lower:]]/i -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]/ -Failed: range out of order in character class at offset 9 - -/^(?(0)f|b)oo/ -Failed: invalid condition (?(0) at offset 6 - -/This one's here because of the large output vector needed/ -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)/ -Capturing subpattern count = 271 -Max back reference = 270 -Partial matching not supported -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/ -Capturing subpattern count = 0 -No options -First char = 'T' -Need char = 't' - -/(main(O)?)+/ -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)/ -Capturing subpattern count = 1 -No options -First char = 'T' -Need char = 's' - -/^(a(b)?)+$/ -Capturing subpattern count = 2 -Options: anchored -No first char -No need char - aba - 0: aba - 1: a - 2: b - -/^(aa(bb)?)+$/ -Capturing subpattern count = 2 -Options: anchored -No first char -No need char - aabbaa - 0: aabbaa - 1: aa - 2: bb - -/^(aa|aa(bb))+$/ -Capturing subpattern count = 2 -Options: anchored -No first char -No need char - aabbaa - 0: aabbaa - 1: aa - 2: bb - -/^(aa(bb)??)+$/ -Capturing subpattern count = 2 -Options: anchored -No first char -No need char - aabbaa - 0: aabbaa - 1: aa - 2: bb - -/^(?:aa(bb)?)+$/ -Capturing subpattern count = 1 -Options: anchored -No first char -No need char - aabbaa - 0: aabbaa - 1: bb - -/^(aa(b(b))?)+$/ -Capturing subpattern count = 3 -Options: anchored -No first char -No need char - aabbaa - 0: aabbaa - 1: aa - 2: bb - 3: b - -/^(?:aa(b(b))?)+$/ -Capturing subpattern count = 2 -Options: anchored -No first char -No need char - aabbaa - 0: aabbaa - 1: bb - 2: b - -/^(?:aa(b(?:b))?)+$/ -Capturing subpattern count = 1 -Options: anchored -No first char -No need char - aabbaa - 0: aabbaa - 1: bb - -/^(?:aa(bb(?:b))?)+$/ -Capturing subpattern count = 1 -Options: anchored -No first char -No need char - aabbbaa - 0: aabbbaa - 1: bbb - -/^(?:aa(b(?:bb))?)+$/ -Capturing subpattern count = 1 -Options: anchored -No first char -No need char - aabbbaa - 0: aabbbaa - 1: bbb - -/^(?:aa(?:b(b))?)+$/ -Capturing subpattern count = 1 -Options: anchored -No first char -No need char - aabbaa - 0: aabbaa - 1: b - -/^(?:aa(?:b(bb))?)+$/ -Capturing subpattern count = 1 -Options: anchored -No first char -No need char - aabbbaa - 0: aabbbaa - 1: bb - -/^(aa(b(bb))?)+$/ -Capturing subpattern count = 3 -Options: anchored -No first char -No need char - aabbbaa - 0: aabbbaa - 1: aa - 2: bbb - 3: bb - -/^(aa(bb(bb))?)+$/ -Capturing subpattern count = 3 -Options: anchored -No first char -No need char - aabbbbaa - 0: aabbbbaa - 1: aa - 2: bbbb - 3: bb - -/--------------------------------------------------------------------/ -Capturing subpattern count = 0 -No options -First char = '-' -Need char = '-' - -/#/xMD -Memory allocation (code space): 7 ------------------------------------------------------------------- - 0 3 Bra 0 - 3 3 Ket - 6 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: extended -No first char -No need char - -/a#/xMD -Memory allocation (code space): 9 ------------------------------------------------------------------- - 0 5 Bra 0 - 3 a - 5 5 Ket - 8 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: extended -First char = 'a' -No need char - -/[\s]/D ------------------------------------------------------------------- - 0 36 Bra 0 - 3 [\x09\x0a\x0c\x0d ] - 36 36 Ket - 39 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -No options -No first char -No need char - -/[\S]/D ------------------------------------------------------------------- - 0 36 Bra 0 - 3 [\x00-\x08\x0b\x0e-\x1f!-\xff] - 36 36 Ket - 39 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -No options -No first char -No need char - -/a(?i)b/D ------------------------------------------------------------------- - 0 9 Bra 0 - 3 a - 5 01 Opt - 7 NC b - 9 9 Ket - 12 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)/D ------------------------------------------------------------------- - 0 17 Bra 0 - 3 9 Bra 1 - 6 a - 8 01 Opt - 10 NC b - 12 9 Ket - 15 00 Opt - 17 17 Ket - 20 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/xD ------------------------------------------------------------------- - 0 9 Bra 0 - 3 NC abc - 9 9 Ket - 12 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: caseless extended -First char = 'a' (caseless) -Need char = 'c' (caseless) - -/#this is a comment - (?i)abc/xD ------------------------------------------------------------------- - 0 9 Bra 0 - 3 NC abc - 9 9 Ket - 12 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: caseless extended -First char = 'a' (caseless) -Need char = 'c' (caseless) - -/123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890/D ------------------------------------------------------------------- - 0 603 Bra 0 - 3 123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890 -603 603 Ket -606 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -No options -First char = '1' -Need char = '0' - -/\Q123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890/D ------------------------------------------------------------------- - 0 603 Bra 0 - 3 123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890 -603 603 Ket -606 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -No options -First char = '1' -Need char = '0' - -/\Q\E/D ------------------------------------------------------------------- - 0 3 Bra 0 - 3 3 Ket - 6 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -No options -No first char -No need char - \ - 0: - -/\Q\Ex/D ------------------------------------------------------------------- - 0 5 Bra 0 - 3 x - 5 5 Ket - 8 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -No options -First char = 'x' -No need char - -/ \Q\E/D ------------------------------------------------------------------- - 0 5 Bra 0 - 3 - 5 5 Ket - 8 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -No options -First char = ' ' -No need char - -/a\Q\E/D ------------------------------------------------------------------- - 0 5 Bra 0 - 3 a - 5 5 Ket - 8 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/D ------------------------------------------------------------------- - 0 7 Bra 0 - 3 ab - 7 7 Ket - 10 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -No options -First char = 'a' -Need char = 'b' - abc - 0: ab - -/\Q\Eabc/D ------------------------------------------------------------------- - 0 9 Bra 0 - 3 abc - 9 9 Ket - 12 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -No options -First char = 'a' -Need char = 'c' - -/x*+\w/D ------------------------------------------------------------------- - 0 12 Bra 0 - 3 5 Once - 6 x* - 8 5 Ket - 11 \w - 12 12 Ket - 15 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Partial matching not supported -No options -No first char -No need char - *** Failers - 0: F - xxxxx -No match - -/x?+/D ------------------------------------------------------------------- - 0 11 Bra 0 - 3 5 Once - 6 x? - 8 5 Ket - 11 11 Ket - 14 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -No options -No first char -No need char - -/x++/D ------------------------------------------------------------------- - 0 11 Bra 0 - 3 5 Once - 6 x+ - 8 5 Ket - 11 11 Ket - 14 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Partial matching not supported -No options -First char = 'x' -No need char - -/x{1,3}+/D ------------------------------------------------------------------- - 0 15 Bra 0 - 3 9 Once - 6 x - 8 x{,2} - 12 9 Ket - 15 15 Ket - 18 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Partial matching not supported -No options -First char = 'x' -No need char - -/(x)*+/D ------------------------------------------------------------------- - 0 18 Bra 0 - 3 12 Once - 6 Brazero - 7 5 Bra 1 - 10 x - 12 5 KetRmax - 15 12 Ket - 18 18 Ket - 21 End ------------------------------------------------------------------- -Capturing subpattern count = 1 -No options -No first char -No need char - -/^(\w++|\s++)*$/ -Capturing subpattern count = 1 -Partial matching not supported -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)/ -Capturing subpattern count = 2 -Partial matching not supported -No options -No first char -No need char - 12345a - 0: 12345a - 1: 12345 - 2: a - *** Failers -No match - 12345+ -No match - -/a++b/ -Capturing subpattern count = 0 -Partial matching not supported -No options -First char = 'a' -Need char = 'b' - aaab - 0: aaab - -/(a++b)/ -Capturing subpattern count = 1 -Partial matching not supported -No options -First char = 'a' -Need char = 'b' - aaab - 0: aaab - 1: aaab - -/(a++)b/ -Capturing subpattern count = 1 -Partial matching not supported -No options -First char = 'a' -Need char = 'b' - aaab - 0: aaab - 1: aaa - -/([^()]++|\([^()]*\))+/ -Capturing subpattern count = 1 -Partial matching not supported -No options -No first char -No need char - ((abc(ade)ufh()()x - 0: abc(ade)ufh()()x - 1: x - -/\(([^()]++|\([^()]+\))+\)/ -Capturing subpattern count = 1 -Partial matching not supported -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}+/D ------------------------------------------------------------------- - 0 53 Bra 0 - 3 47 Once - 6 9 Bra 1 - 9 abc - 15 9 Ket - 18 Brazero - 19 28 Bra 0 - 22 9 Bra 1 - 25 abc - 31 9 Ket - 34 Brazero - 35 9 Bra 1 - 38 abc - 44 9 Ket - 47 28 Ket - 50 47 Ket - 53 53 Ket - 56 End ------------------------------------------------------------------- -Capturing subpattern count = 1 -No options -First char = 'a' -Need char = 'c' - -/a+?+/ -Failed: nothing to repeat at offset 3 - -/a{2,3}?+b/ -Failed: nothing to repeat at offset 7 - -/(?U)a+?+/ -Failed: nothing to repeat at offset 7 - -/a{2,3}?+b/U -Failed: nothing to repeat at offset 7 - -/x(?U)a++b/D ------------------------------------------------------------------- - 0 15 Bra 0 - 3 x - 5 5 Once - 8 a+ - 10 5 Ket - 13 b - 15 15 Ket - 18 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Partial matching not supported -No options -First char = 'x' -Need char = 'b' - xaaaab - 0: xaaaab - -/(?U)xa++b/D ------------------------------------------------------------------- - 0 15 Bra 0 - 3 x - 5 5 Once - 8 a+ - 10 5 Ket - 13 b - 15 15 Ket - 18 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Partial matching not supported -Options: ungreedy -First char = 'x' -Need char = 'b' - xaaaab - 0: xaaaab - -/^((a+)(?U)([ab]+)(?-U)([bc]+)(\w*))/D ------------------------------------------------------------------- - 0 106 Bra 0 - 3 ^ - 4 99 Bra 1 - 7 5 Bra 2 - 10 a+ - 12 5 Ket - 15 37 Bra 3 - 18 [ab]+? - 52 37 Ket - 55 37 Bra 4 - 58 [bc]+ - 92 37 Ket - 95 5 Bra 5 - 98 \w* -100 5 Ket -103 99 Ket -106 106 Ket -109 End ------------------------------------------------------------------- -Capturing subpattern count = 5 -Partial matching not supported -Options: anchored -No first char -No need char - -/^x(?U)a+b/D ------------------------------------------------------------------- - 0 10 Bra 0 - 3 ^ - 4 x - 6 a+? - 8 b - 10 10 Ket - 13 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Partial matching not supported -Options: anchored -No first char -Need char = 'b' - -/^x(?U)(a+)b/D ------------------------------------------------------------------- - 0 16 Bra 0 - 3 ^ - 4 x - 6 5 Bra 1 - 9 a+? - 11 5 Ket - 14 b - 16 16 Ket - 19 End ------------------------------------------------------------------- -Capturing subpattern count = 1 -Partial matching not supported -Options: anchored -No first char -Need char = 'b' - -/[.x.]/ -Failed: POSIX collating elements are not supported at offset 0 - -/[=x=]/ -Failed: POSIX collating elements are not supported at offset 0 - -/[:x:]/ -Failed: POSIX named classes are supported only within a class at offset 0 - -/\l/ -Failed: PCRE does not support \L, \l, \N, \U, or \u at offset 1 - -/\L/ -Failed: PCRE does not support \L, \l, \N, \U, or \u at offset 1 - -/\N{name}/ -Failed: PCRE does not support \L, \l, \N, \U, or \u at offset 1 - -/\u/ -Failed: PCRE does not support \L, \l, \N, \U, or \u at offset 1 - -/\U/ -Failed: PCRE does not support \L, \l, \N, \U, or \u at offset 1 - -/[/ -Failed: missing terminating ] for character class at offset 1 - -/[a-/ -Failed: missing terminating ] for character class at offset 3 - -/[[:space:]/ -Failed: missing terminating ] for character class at offset 10 - -/[\s]/DM -Memory allocation (code space): 40 ------------------------------------------------------------------- - 0 36 Bra 0 - 3 [\x09\x0a\x0c\x0d ] - 36 36 Ket - 39 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -No options -No first char -No need char - -/[[:space:]]/DM -Memory allocation (code space): 40 ------------------------------------------------------------------- - 0 36 Bra 0 - 3 [\x09-\x0d ] - 36 36 Ket - 39 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -No options -No first char -No need char - -/[[:space:]abcde]/DM -Memory allocation (code space): 40 ------------------------------------------------------------------- - 0 36 Bra 0 - 3 [\x09-\x0d a-e] - 36 36 Ket - 39 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -No options -No first char -No need char - -/< (?: (?(R) \d++ | [^<>]*+) | (?R)) * >/x -Capturing subpattern count = 0 -Partial matching not supported -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|DM -Memory allocation (code space): 826 ------------------------------------------------------------------- - 0 822 Bra 0 - 3 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 -821 \b -822 822 Ket -825 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -No options -First char = '8' -Need char = 'X' - -|\$\<\.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|DM -Memory allocation (code space): 816 ------------------------------------------------------------------- - 0 812 Bra 0 - 3 $<.X+ix[d1b!H#?vV0vrK:ZH1=2M>iV;?aPhFB<*vW@QW@sO9}cfZA-i'w%hKd6gt1UJP,15_#QY$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 -811 \b -812 812 Ket -815 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -No options -First char = '$' -Need char = 'X' - -/(.*)\d+\1/I -Capturing subpattern count = 1 -Max back reference = 1 -Partial matching not supported -No options -No first char -No need char - -/(.*)\d+/I -Capturing subpattern count = 1 -Partial matching not supported -No options -First char at start or follows newline -No need char - -/(.*)\d+\1/Is -Capturing subpattern count = 1 -Max back reference = 1 -Partial matching not supported -Options: dotall -No first char -No need char - -/(.*)\d+/Is -Capturing subpattern count = 1 -Partial matching not supported -Options: anchored dotall -No first char -No need char - -/(.*(xyz))\d+\2/I -Capturing subpattern count = 2 -Max back reference = 2 -Partial matching not supported -No options -First char at start or follows newline -Need char = 'z' - -/((.*))\d+\1/I -Capturing subpattern count = 2 -Max back reference = 1 -Partial matching not supported -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 -Partial matching not supported -No options -First char = 'a' -No need char - -/(?=abc).xyz/iI -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 = 0 -No options -First char = 'a' -No need char - -/(?(1)abz|acz)/I -Capturing subpattern count = 0 -No options -First char = 'a' -Need char = 'z' - -/(?(1)abz)/I -Capturing subpattern count = 0 -No options -No first char -No need char - -/(?(1)abz)123/I -Capturing subpattern count = 0 -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 -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' -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/mI -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 -Starting byte set: A B a b - -/[ab](?i)cd/IS -Capturing subpattern count = 0 -No options -No first char -Need char = 'd' (caseless) -Starting byte set: a b - -/abc(?C)def/ -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/ -Capturing subpattern count = 0 -No options -First char = 'a' -Need char = 'f' - 123abcdef ---->123abcdef - 0 ^ ^ d - 1 ^ ^ f - 0: abcdef - -/(?C1)\dabc(?C2)def/ -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/ -Capturing subpattern count = 0 -No options -First char = 'a' -Need char = 'b' - -/(?C256)ab/ -Failed: number after (?C is > 255 at offset 6 - -/(?Cab)xx/ -Failed: closing ) for (?C expected at offset 3 - -/(?C12vr)x/ -Failed: closing ) for (?C expected at offset 5 - -/abc(?C)def/ -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/ -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))*/ -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))*/ -Capturing subpattern count = 1 -Partial matching not supported -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)/ -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)/ -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/ -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/ -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/ -Capturing subpattern count = 1 -No options -First char = 'x' -Need char = 'z' - abcxyz\C+ -Callout 0: last capture = 1 - 0: <unset> - 1: abc ---->abcxyz - ^ ) - 0: xyz - 1: abc - -/a(b+)(c*)(?C1)/ -Capturing subpattern count = 2 -Partial matching not supported -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)/ -Capturing subpattern count = 2 -Partial matching not supported -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/ -Capturing subpattern count = 0 -No options -First char = 'a' -Need char = 'c' - -/(?C)^abc/ -Capturing subpattern count = 0 -Options: anchored -No first char -No need char - -/(?C)a|b/S -Capturing subpattern count = 0 -No options -No first char -No need char -Starting byte set: a b - -/(?R)/ -Failed: recursive call could loop indefinitely at offset 3 - -/(a|(?R))/ -Failed: recursive call could loop indefinitely at offset 6 - -/(ab|(bc|(de|(?R))))/ -Failed: recursive call could loop indefinitely at offset 15 - -/x(ab|(bc|(de|(?R))))/ -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))))/ -Failed: recursive call could loop indefinitely at offset 15 - -/x(ab|(bc|(de|(?1)x)x)x)/ -Failed: recursive call could loop indefinitely at offset 16 - -/^([^()]|\((?1)*\))*$/ -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<$/ -Capturing subpattern count = 1 -Options: anchored -No first char -Need char = '<' - >abc>123<xyz< - 0: >abc>123<xyz< - 1: 3 - >abc>1(2)3<xyz< - 0: >abc>1(2)3<xyz< - 1: 3 - >abc>(1(2)3)<xyz< - 0: >abc>(1(2)3)<xyz< - 1: (1(2)3) - -/(a(?1)b)/D ------------------------------------------------------------------- - 0 22 Bra 0 - 3 16 Bra 1 - 6 a - 8 6 Once - 11 3 Recurse - 14 6 Ket - 17 b - 19 16 Ket - 22 22 Ket - 25 End ------------------------------------------------------------------- -Capturing subpattern count = 1 -No options -First char = 'a' -Need char = 'b' - -/(a(?1)+b)/D ------------------------------------------------------------------- - 0 22 Bra 0 - 3 16 Bra 1 - 6 a - 8 6 Once - 11 3 Recurse - 14 6 KetRmax - 17 b - 19 16 Ket - 22 22 Ket - 25 End ------------------------------------------------------------------- -Capturing subpattern count = 1 -No options -First char = 'a' -Need char = 'b' - -/^\W*(?:((.)\W*(?1)\W*\2|)|((.)\W*(?3)\W*\4|\W*.\W*))\W*$/i -Capturing subpattern count = 4 -Max back reference = 4 -Partial matching not supported -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 - -/^(\d+|\((?1)([+*-])(?1)\)|-(?1))$/ -Capturing subpattern count = 2 -Partial matching not supported -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)/ -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)) * >))/x -Capturing subpattern count = 2 -Partial matching not supported -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)/ -Failed: reference to non-existent subpattern at offset 3 - -/((?2)(abc)/ -Failed: reference to non-existent subpattern at offset 4 - -/^(abc)def(?1)/ -Capturing subpattern count = 1 -Options: anchored -No first char -No need char - abcdefabc - 0: abcdefabc - 1: abc - -/^(a|b|c)=(?1)+/ -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))+/ -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)/D ------------------------------------------------------------------- - 0 28 Bra 0 - 3 a - 5 5 Bra 1 - 8 b - 10 5 Alt - 13 c - 15 10 Ket - 18 d - 20 5 Bra 2 - 23 e - 25 5 Ket - 28 28 Ket - 31 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)/D ------------------------------------------------------------------- - 0 35 Bra 0 - 3 21 Bra 0 - 6 a - 8 13 Bra 1 - 11 c - 13 5 Bra 2 - 16 d - 18 5 Ket - 21 13 Ket - 24 21 Ket - 27 5 Bra 3 - 30 a - 32 5 Ket - 35 35 Ket - 38 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/D ------------------------------------------------------------------- - 0 34 Bra 0 - 3 5 Bra 1 - 6 a - 8 5 Ket - 11 Any - 12 Any - 13 Any - 14 \1 - 17 bbb - 23 6 Once - 26 3 Recurse - 29 6 Ket - 32 d - 34 34 Ket - 37 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*$/i -Capturing subpattern count = 4 -Max back reference = 4 -Named capturing subpatterns: - four 4 - one 1 - three 3 - two 2 -Partial matching not supported -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)?/ -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/sI -Capturing subpattern count = 1 -Partial matching not supported -Options: anchored dotall -No first char -Need char = 'a' - -/(.*)a\1/sI -Capturing subpattern count = 1 -Max back reference = 1 -Partial matching not supported -Options: dotall -No first char -Need char = 'a' - -/(.*)a(b)\2/sI -Capturing subpattern count = 2 -Max back reference = 2 -Partial matching not supported -Options: anchored dotall -No first char -Need char = 'b' - -/((.*)a|(.*)b)z/sI -Capturing subpattern count = 3 -Partial matching not supported -Options: anchored dotall -No first char -Need char = 'z' - -/((.*)a|(.*)b)z\1/sI -Capturing subpattern count = 3 -Max back reference = 1 -Partial matching not supported -Options: dotall -No first char -Need char = 'z' - -/((.*)a|(.*)b)z\2/sI -Capturing subpattern count = 3 -Max back reference = 2 -Partial matching not supported -Options: dotall -No first char -Need char = 'z' - -/((.*)a|(.*)b)z\3/sI -Capturing subpattern count = 3 -Max back reference = 3 -Partial matching not supported -Options: dotall -No first char -Need char = 'z' - -/((.*)a|^(.*)b)z\3/sI -Capturing subpattern count = 3 -Max back reference = 3 -Partial matching not supported -Options: anchored dotall -No first char -Need char = 'z' - -/(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)a/sI -Capturing subpattern count = 31 -Partial matching not supported -Options: anchored dotall -No first char -No need char - -/(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)a\31/sI -Capturing subpattern count = 31 -Max back reference = 31 -Partial matching not supported -Options: dotall -No first char -No need char - -/(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)a\32/sI -Capturing subpattern count = 32 -Max back reference = 32 -Partial matching not supported -Options: dotall -No first char -No need char - -/(a)(bc)/ND ------------------------------------------------------------------- - 0 21 Bra 0 - 3 5 Bra 0 - 6 a - 8 5 Ket - 11 7 Bra 0 - 14 bc - 18 7 Ket - 21 21 Ket - 24 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: no_auto_capture -First char = 'a' -Need char = 'c' - abc - 0: abc - -/(?P<one>a)(bc)/ND ------------------------------------------------------------------- - 0 21 Bra 0 - 3 5 Bra 1 - 6 a - 8 5 Ket - 11 7 Bra 0 - 14 bc - 18 7 Ket - 21 21 Ket - 24 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)/ND ------------------------------------------------------------------- - 0 21 Bra 0 - 3 5 Bra 0 - 6 a - 8 5 Ket - 11 7 Bra 1 - 14 bc - 18 7 Ket - 21 21 Ket - 24 End ------------------------------------------------------------------- -Capturing subpattern count = 1 -Named capturing subpatterns: - named 1 -Options: no_auto_capture -First char = 'a' -Need char = 'c' - -/(a+)*zz/ -Capturing subpattern count = 1 -Partial matching not supported -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)/ -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)/ -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>)/D ------------------------------------------------------------------- - 0 15 Bra 0 - 3 3 Bra 1 - 6 3 Ket - 9 3 Bra 2 - 12 3 Ket - 15 15 Ket - 18 End ------------------------------------------------------------------- -Capturing subpattern count = 2 -Named capturing subpatterns: - Tes 1 - Test 2 -No options -No first char -No need char - -/(?P<Test>)(?P<Tes>)/D ------------------------------------------------------------------- - 0 15 Bra 0 - 3 3 Bra 1 - 6 3 Ket - 9 3 Bra 2 - 12 3 Ket - 15 15 Ket - 18 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)/ -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)/ -Failed: two named subpatterns have the same name at offset 16 - -/(?P<abc>abc(?P<def>def)(?P<abc>xyz))/ -Failed: two named subpatterns have the same name at offset 31 - -"\[((?P<elem>\d+)(,(?P>elem))*)\]" -Capturing subpattern count = 3 -Named capturing subpatterns: - elem 2 -Partial matching not supported -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 - -"\[((?P<elem>\d+)(,(?P>elem))*)?\]" -Capturing subpattern count = 3 -Named capturing subpatterns: - elem 2 -Partial matching not supported -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))?/D ------------------------------------------------------------------- - 0 31 Bra 0 - 3 Brazero - 4 24 Bra 1 - 7 a - 9 16 Bra 2 - 12 b - 14 6 Once - 17 9 Recurse - 20 6 Ket - 23 c - 25 16 Ket - 28 24 Ket - 31 31 Ket - 34 End ------------------------------------------------------------------- -Capturing subpattern count = 2 -No options -No first char -No need char - -/(a(b(?2)c))*/D ------------------------------------------------------------------- - 0 31 Bra 0 - 3 Brazero - 4 24 Bra 1 - 7 a - 9 16 Bra 2 - 12 b - 14 6 Once - 17 9 Recurse - 20 6 Ket - 23 c - 25 16 Ket - 28 24 KetRmax - 31 31 Ket - 34 End ------------------------------------------------------------------- -Capturing subpattern count = 2 -No options -No first char -No need char - -/(a(b(?2)c)){0,2}/D ------------------------------------------------------------------- - 0 65 Bra 0 - 3 Brazero - 4 58 Bra 0 - 7 24 Bra 1 - 10 a - 12 16 Bra 2 - 15 b - 17 6 Once - 20 12 Recurse - 23 6 Ket - 26 c - 28 16 Ket - 31 24 Ket - 34 Brazero - 35 24 Bra 1 - 38 a - 40 16 Bra 2 - 43 b - 45 6 Once - 48 12 Recurse - 51 6 Ket - 54 c - 56 16 Ket - 59 24 Ket - 62 58 Ket - 65 65 Ket - 68 End ------------------------------------------------------------------- -Capturing subpattern count = 2 -No options -No first char -No need char - -/[ab]{1}+/D ------------------------------------------------------------------- - 0 47 Bra 0 - 3 41 Once - 6 [ab]{1,1} - 44 41 Ket - 47 47 Ket - 50 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -No options -No first char -No need char - -/((w\/|-|with)*(free|immediate)*.*?shipping\s*[!.-]*)/i -Capturing subpattern count = 3 -Partial matching not supported -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*[!.-]*)/iS -Capturing subpattern count = 3 -Partial matching not supported -Options: caseless -No first char -Need char = 'g' (caseless) -Study returned NULL - 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/SD ------------------------------------------------------------------- - 0 9 Bra 0 - 3 a* - 5 Any* - 7 b - 9 9 Ket - 12 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Partial matching not supported -No options -No first char -Need char = 'b' -Study returned NULL - -/(a|b)*.?c/SD ------------------------------------------------------------------- - 0 21 Bra 0 - 3 Brazero - 4 5 Bra 1 - 7 a - 9 5 Alt - 12 b - 14 10 KetRmax - 17 Any? - 19 c - 21 21 Ket - 24 End ------------------------------------------------------------------- -Capturing subpattern count = 1 -No options -No first char -Need char = 'c' -Study returned NULL - -/abc(?C255)de(?C)f/D ------------------------------------------------------------------- - 0 27 Bra 0 - 3 abc - 9 Callout 255 10 1 - 15 de - 19 Callout 0 16 1 - 25 f - 27 27 Ket - 30 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -No options -First char = 'a' -Need char = 'f' - -/abcde/CD ------------------------------------------------------------------- - 0 49 Bra 0 - 3 Callout 255 0 1 - 9 a - 11 Callout 255 1 1 - 17 b - 19 Callout 255 2 1 - 25 c - 27 Callout 255 3 1 - 33 d - 35 Callout 255 4 1 - 41 e - 43 Callout 255 5 0 - 49 49 Ket - 52 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/CD ------------------------------------------------------------------- - 0 25 Bra 0 - 3 Callout 255 0 2 - 9 a* - 11 Callout 255 2 1 - 17 b - 19 Callout 255 3 0 - 25 25 Ket - 28 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Partial matching not supported -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 - +2 ^ ^ b - +2 ^ ^ b - +2 ^^ b - +2 ^ b - +0 ^ a* - +2 ^ ^ b - +2 ^ ^ b - +2 ^^ b - +2 ^ b - +0 ^ a* - +2 ^ ^ b - +2 ^^ b - +2 ^ b - +0 ^ a* - +2 ^^ b - +2 ^ b - +0 ^ a* - +2 ^ b - +0 ^ a* - +2 ^ b - +3 ^^ - 0: b - -/a+b/CD ------------------------------------------------------------------- - 0 25 Bra 0 - 3 Callout 255 0 2 - 9 a+ - 11 Callout 255 2 1 - 17 b - 19 Callout 255 3 0 - 25 25 Ket - 28 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Partial matching not supported -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 - +2 ^ ^ b - +2 ^ ^ b - +2 ^^ b - +0 ^ a+ - +2 ^ ^ b - +2 ^ ^ b - +2 ^^ b - +0 ^ a+ - +2 ^ ^ b - +2 ^^ b - +0 ^ a+ - +2 ^^ b -No match - -/(abc|def)x/CD ------------------------------------------------------------------- - 0 92 Bra 0 - 3 Callout 255 0 9 - 9 33 Bra 1 - 12 Callout 255 1 1 - 18 a - 20 Callout 255 2 1 - 26 b - 28 Callout 255 3 1 - 34 c - 36 Callout 255 4 0 - 42 33 Alt - 45 Callout 255 5 1 - 51 d - 53 Callout 255 6 1 - 59 e - 61 Callout 255 7 1 - 67 f - 69 Callout 255 8 0 - 75 66 Ket - 78 Callout 255 9 1 - 84 x - 86 Callout 255 10 0 - 92 92 Ket - 95 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 - 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}/C -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)/CD ------------------------------------------------------------------- - 0 131 Bra 0 - 3 Callout 255 0 14 - 9 88 Bra 1 - 12 Callout 255 1 4 - 18 [ab] - 51 Callout 255 5 1 - 57 { - 59 Callout 255 6 1 - 65 , - 67 Callout 255 7 1 - 73 4 - 75 Callout 255 8 1 - 81 } - 83 Callout 255 9 1 - 89 c - 91 Callout 255 10 0 - 97 25 Alt -100 Callout 255 11 1 -106 x -108 Callout 255 12 1 -114 y -116 Callout 255 13 0 -122 113 Ket -125 Callout 255 14 0 -131 131 Ket -134 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/CD ------------------------------------------------------------------- - 0 485 Bra 0 - 3 Callout 255 0 21 - 9 61 Bra 1 - 12 Callout 255 1 9 - 18 [ab]{1,4} - 56 Callout 255 10 1 - 62 c - 64 Callout 255 11 0 - 70 25 Alt - 73 Callout 255 12 1 - 79 x - 81 Callout 255 13 1 - 87 y - 89 Callout 255 14 0 - 95 86 Ket - 98 61 Bra 1 -101 Callout 255 1 9 -107 [ab]{1,4} -145 Callout 255 10 1 -151 c -153 Callout 255 11 0 -159 25 Alt -162 Callout 255 12 1 -168 x -170 Callout 255 13 1 -176 y -178 Callout 255 14 0 -184 86 Ket -187 61 Bra 1 -190 Callout 255 1 9 -196 [ab]{1,4} -234 Callout 255 10 1 -240 c -242 Callout 255 11 0 -248 25 Alt -251 Callout 255 12 1 -257 x -259 Callout 255 13 1 -265 y -267 Callout 255 14 0 -273 86 Ket -276 61 Bra 1 -279 Callout 255 1 9 -285 [ab]{1,4} -323 Callout 255 10 1 -329 c -331 Callout 255 11 0 -337 25 Alt -340 Callout 255 12 1 -346 x -348 Callout 255 13 1 -354 y -356 Callout 255 14 0 -362 86 Ket -365 Braminzero -366 61 Bra 1 -369 Callout 255 1 9 -375 [ab]{1,4} -413 Callout 255 10 1 -419 c -421 Callout 255 11 0 -427 25 Alt -430 Callout 255 12 1 -436 x -438 Callout 255 13 1 -444 y -446 Callout 255 14 0 -452 86 Ket -455 Callout 255 21 1 -461 1 -463 Callout 255 22 1 -469 2 -471 Callout 255 23 1 -477 3 -479 Callout 255 24 0 -485 485 Ket -488 End ------------------------------------------------------------------- -Capturing subpattern count = 1 -Partial matching not supported -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 -Partial matching not supported -No options -No first char -No need char - ab cd\>1 - 0: cd - -/\b.*/Is -Capturing subpattern count = 0 -Partial matching not supported -Options: dotall -No first char -No need char - ab cd\>1 - 0: cd - -/(?!.bcd).*/I -Capturing subpattern count = 0 -Partial matching not supported -No options -No first char -No need char - Xbcd12345 - 0: bcd12345 - -/abcde/ -Capturing subpattern count = 0 -No options -First char = 'a' -Need char = 'e' - ab\P -Partial match - abc\P -Partial match - abcd\P -Partial match - abcde\P - 0: abcde - the quick brown abc\P -Partial match - ** 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$" -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 - 1/2\P -Partial match - 1/2/0\P -Partial match - 1/2/04\P - 0: 1/2/04 - 1: 1 - 2: 2 - 0\P -Partial match - 02/\P -Partial match - 02/0\P -Partial match - 02/1\P -Partial match - ** 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 -Partial matching not supported -No options -No first char -Need char = 'C' - -/\d{3,}ABC/I -Capturing subpattern count = 0 -Partial matching not supported -No options -No first char -Need char = 'C' - -/\d*ABC/I -Capturing subpattern count = 0 -Partial matching not supported -No options -No first char -Need char = 'C' - -/[abc]+DE/I -Capturing subpattern count = 0 -Partial matching not supported -No options -No first char -Need char = 'E' - -/[abc]?123/ -Capturing subpattern count = 0 -No options -No first char -Need char = '3' - 123\P - 0: 123 - a\P -Partial match - b\P -Partial match - c\P -Partial match - c12\P -Partial match - c123\P - 0: c123 - -/^(?:\d){3,5}X/ -Capturing subpattern count = 0 -Options: anchored -No first char -Need char = 'X' - 1\P -Partial match - 123\P -Partial match - 123X - 0: 123X - 1234\P -Partial match - 1234X - 0: 1234X - 12345\P -Partial match - 12345X - 0: 12345X - *** Failers -No match - 1X -No match - 123456\P -No match - -/abc/>testsavedregex -Capturing subpattern count = 0 -No options -First char = 'a' -Need char = 'c' -Compiled regex written to testsavedregex -<testsavedregex -Compiled regex loaded from testsavedregex -No study data -Capturing subpattern count = 0 -No options -First char = 'a' -Need char = 'c' - abc - 0: abc - ** Failers -No match - bca -No match - -/abc/F>testsavedregex -Capturing subpattern count = 0 -No options -First char = 'a' -Need char = 'c' -Compiled regex written to testsavedregex -<testsavedregex -Compiled regex (byte-inverted) loaded from testsavedregex -No study data -Capturing subpattern count = 0 -No options -First char = 'a' -Need char = 'c' - abc - 0: abc - ** Failers -No match - bca -No match - -/(a|b)/S>testsavedregex -Capturing subpattern count = 1 -No options -No first char -No need char -Starting byte set: a b -Compiled regex written to testsavedregex -Study data written to testsavedregex -<testsavedregex -Compiled regex loaded from testsavedregex -Study data loaded from testsavedregex -Capturing subpattern count = 1 -No options -No first char -No need char -Starting byte set: a b - abc - 0: a - 1: a - ** Failers - 0: a - 1: a - def -No match - -/(a|b)/SF>testsavedregex -Capturing subpattern count = 1 -No options -No first char -No need char -Starting byte set: a b -Compiled regex written to testsavedregex -Study data written to testsavedregex -<testsavedregex -Compiled regex (byte-inverted) loaded from testsavedregex -Study data loaded from testsavedregex -Capturing subpattern count = 1 -No options -No first char -No need char -Starting byte set: a b - abc - 0: a - 1: a - ** Failers - 0: a - 1: a - def -No match - -~<(\w+)/?>(.)*</(\1)>~smg -Capturing subpattern count = 3 -Max back reference = 1 -Partial matching not supported -Options: multiline dotall -First char = '<' -Need char = '>' - <!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/ -Capturing subpattern count = 0 -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/f -Capturing subpattern count = 0 -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/mf -Capturing subpattern count = 0 -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 - -/ab.cd/P - ab-cd - 0: ab-cd - ab=cd - 0: ab=cd - ** Failers -No match: POSIX code 17: match failed - ab\ncd -No match: POSIX code 17: match failed - -/ab.cd/Ps - ab-cd - 0: ab-cd - ab=cd - 0: ab=cd - ab\ncd - 0: ab\x0acd - -/(?i)(?-i)AbCd/ -Capturing subpattern count = 0 -No options -First char = 'A' -Need char = 'd' - AbCd - 0: AbCd - ** Failers -No match - abcd -No match - -/a{11111111111111111111}/ -Failed: number too big in {} quantifier at offset 22 - -/(){64294967295}/ -Failed: number too big in {} quantifier at offset 14 - -/(){2,4294967295}/ -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" -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" -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" -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)" -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)" -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 - -/[^()]*(?:\((?R)\)[^()]*)*/ -Capturing subpattern count = 0 -Partial matching not supported -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 - -/[^()]*(?:\((?>(?R))\)[^()]*)*/ -Capturing subpattern count = 0 -Partial matching not supported -No options -No first char -No need char - (this(and)that - 0: - (this(and)that) - 0: (this(and)that) - -/[^()]*(?:\((?R)\))*[^()]*/ -Capturing subpattern count = 0 -Partial matching not supported -No options -No first char -No need char - (this(and)that - 0: - (this(and)that) - 0: (this(and)that) - -/(?:\((?R)\))*[^()]*/ -Capturing subpattern count = 0 -Partial matching not supported -No options -No first char -No need char - (this(and)that - 0: - (this(and)that) - 0: - ((this)) - 0: ((this)) - -/(?:\((?R)\))|[^()]*/ -Capturing subpattern count = 0 -Partial matching not supported -No options -No first char -No need char - (this(and)that - 0: - (this(and)that) - 0: - (this) - 0: (this) - ((this)) - 0: ((this)) - -/a(b)c/PN - abc -Matched with REG_NOSUB - -/a(?P<name>b)c/PN - abc -Matched with REG_NOSUB - -/\x{100}/ -Failed: character value in \x{...} sequence is too large at offset 6 - -/\x{0000ff}/ -Capturing subpattern count = 0 -No options -First char = 255 -No need char - -/^((?P<A>a1)|(?P<A>a2)b)/ -Failed: two named subpatterns have the same name at offset 18 - -/^((?P<A>a1)|(?P<A>a2)b)/J -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)/J -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/J -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)/J -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)/J -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 -copy substring Z failed -7 - G a1 (2) A - -/^(?P<A>a)(?P<A>b)/J -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/J -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 -copy substring A failed -7 - -/^(?P<A>a)(?P<A>b)|cd(?P<A>ef)(?P<A>gh)/J -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)/ -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 - -/^(?P<A>a) (?J:(?P<B>b)(?P<B>c)) (?P<A>d)/ -Failed: two named subpatterns have the same name at offset 38 - -/ 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. /x -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)/ -Capturing subpattern count = 4 -Named capturing subpatterns: - A 1 - B 2 - B 3 - C 4 -Options: anchored -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)/ -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))+/ -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))+/ -Failed: reference to non-existent subpattern at offset 9 - -/(?:(?(ZA)a|b)(?P<ZZ>X))+/ -Failed: reference to non-existent subpattern at offset 9 - -/(?:(?(ZZ)a|b)(?(ZZ)a|b)(?P<ZZ>X))+/ -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))+/ -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/ -Failed: syntax error after (?P at offset 7 - -/(?:(?(A)(?P=A)a|b)(?P<A>X|Y))+/ -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))+/ -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 - -/\777/ -Failed: octal value is greater than \377 (not in UTF-8 mode) at offset 3 - -/\s*,\s*/S -Capturing subpattern count = 0 -Partial matching not supported -No options -No first char -Need char = ',' -Starting byte set: \x09 \x0a \x0c \x0d \x20 , - \x0b,\x0b - 0: , - \x0c,\x0d - 0: \x0c,\x0d - -/^abc/m -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$/m -Capturing subpattern count = 0 -Options: multiline -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/m<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/m<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/m<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/m<bad> -Unknown newline type at: <bad> - - -/abc/ -Capturing subpattern count = 0 -No options -First char = 'a' -Need char = 'c' - xyz\rabc\<bad> -Unknown newline type at: <bad> - abc - 0: abc - -/.*/ -Capturing subpattern count = 0 -Partial matching not supported -No options -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/s -Capturing subpattern count = 2 -Partial matching not supported -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|.)*?[*]/)*)+ -Capturing subpattern count = 1 -Partial matching not supported -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}/ -Capturing subpattern count = 1 -Named capturing subpatterns: - B 1 -No options -No first char -Need char = '.' - -/ End of testinput2 / -Capturing subpattern count = 0 -No options -First char = ' ' -Need char = ' ' diff --git a/ext/pcre/pcrelib/testdata/testoutput3 b/ext/pcre/pcrelib/testdata/testoutput3 deleted file mode 100644 index 06e2888d91..0000000000 --- a/ext/pcre/pcrelib/testdata/testoutput3 +++ /dev/null @@ -1,163 +0,0 @@ -/^[\w]+/ - *** Failers -No match - ֹcole -No match - -/^[\w]+/Lfr_FR - ֹcole - 0: ֹcole - -/^[\w]+/ - *** Failers -No match - ֹcole -No match - -/^[\W]+/ - ֹcole - 0: \xc9 - -/^[\W]+/Lfr_FR - *** Failers - 0: *** - ֹcole -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 - ֹcole -No match - -/^\w+/Lfr_FR - ֹcole - 0: ֹcole - -/(.+)\b(.+)/ - ֹcole - 0: \xc9cole - 1: \xc9 - 2: cole - -/(.+)\b(.+)/Lfr_FR - *** Failers - 0: *** Failers - 1: *** - 2: Failers - ֹcole -No match - -/ֹcole/i - ֹcole - 0: \xc9cole - *** Failers -No match - יcole -No match - -/ֹcole/iLfr_FR - ֹcole - 0: ֹcole - יcole - 0: יcole - -/\w/IS -Capturing subpattern count = 0 -No options -No first char -No need char -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 -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 - × µ ÷ ְ ֱ ֲ ֳ ִ ֵ ֶ ַ ָ ֹ ֻ ּ ֽ ־ ֿ ׀ ׁ ׂ ׃ װ ױ ײ ״ א ב ג - ד ה ו ז ח ט י ך כ ל ם מ ן נ ס ע ף פ ץ צ ר ש ת - -/^[\xc8-\xc9]/iLfr_FR - ֹcole - 0: ֹ - יcole - 0: י - -/^[\xc8-\xc9]/Lfr_FR - ֹcole - 0: ֹ - *** Failers -No match - יcole -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: × - >>>\xba<<< - 0: ÷ - -/[\w]+/Lfr_FR - >>>\xaa<<< - 0: × - >>>\xba<<< - 0: ÷ - -/[[:alpha:]]+/Lfr_FR - >>>\xaa<<< - 0: × - >>>\xba<<< - 0: ÷ - -/[[:alpha:]][[:lower:]][[:upper:]]/DLfr_FR ------------------------------------------------------------------- - 0 102 Bra 0 - 3 [A-Za-z×µ÷ְ-ײ״-צר-] - 36 [a-zµ-צר-] - 69 [A-Zְ-ײ״-] -102 102 Ket -105 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 deleted file mode 100644 index 3b49455075..0000000000 --- a/ext/pcre/pcrelib/testdata/testoutput4 +++ /dev/null @@ -1,917 +0,0 @@ -/-- Do not use the \x{} construct except with patterns that have the --/ -/-- /8 option set, because PCRE doesn't recognize them as UTF-8 unless --/ -No match -/-- that option is set. However, the latest Perls recognize them always. --/ -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 - 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 - -/X(\C{3})/8 - X\x{1234} - 0: X\x{1234} - 1: \x{1234} - -/X(\C{4})/8 - X\x{1234}YZ - 0: X\x{1234}Y - 1: \x{1234}Y - -/X\C*/8 - XYZabcdce - 0: XYZabcdce - -/X\C*?/8 - XYZabcde - 0: X - -/X\C{3,5}/8 - Xabcdefg - 0: Xabcde - X\x{1234} - 0: X\x{1234} - X\x{1234}YZ - 0: X\x{1234}YZ - X\x{1234}\x{512} - 0: X\x{1234}\x{512} - X\x{1234}\x{512}YZ - 0: X\x{1234}\x{512} - -/X\C{3,5}?/8 - Xabcdefg - 0: Xabc - X\x{1234} - 0: X\x{1234} - X\x{1234}YZ - 0: X\x{1234} - X\x{1234}\x{512} - 0: X\x{1234} - -/[^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 - -/a\Cb/ - aXb - 0: aXb - a\nb - 0: a\x0ab - -/a\Cb/8 - aXb - 0: aXb - a\nb - 0: a\x{0a}b - *** Failers -No match - a\x{100}b -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} - -/^בˆ´/8 - בˆ´ - 0: \x{1234} - -/^\בˆ´/8 - בˆ´ - 0: \x{1234} - -"(?s)(.{1,5})"8 - abcdefg - 0: abcde - 1: abcde - ab - 0: ab - 1: ab - -/ End of testinput4 / diff --git a/ext/pcre/pcrelib/testdata/testoutput5 b/ext/pcre/pcrelib/testdata/testoutput5 deleted file mode 100644 index 2c5e3c09cd..0000000000 --- a/ext/pcre/pcrelib/testdata/testoutput5 +++ /dev/null @@ -1,1123 +0,0 @@ -/\x{100}/8DM -Memory allocation (code space): 10 ------------------------------------------------------------------- - 0 6 Bra 0 - 3 \x{100} - 6 6 Ket - 9 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: utf8 -First char = 196 -Need char = 128 - -/\x{1000}/8DM -Memory allocation (code space): 11 ------------------------------------------------------------------- - 0 7 Bra 0 - 3 \x{1000} - 7 7 Ket - 10 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: utf8 -First char = 225 -Need char = 128 - -/\x{10000}/8DM -Memory allocation (code space): 12 ------------------------------------------------------------------- - 0 8 Bra 0 - 3 \x{10000} - 8 8 Ket - 11 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: utf8 -First char = 240 -Need char = 128 - -/\x{100000}/8DM -Memory allocation (code space): 12 ------------------------------------------------------------------- - 0 8 Bra 0 - 3 \x{100000} - 8 8 Ket - 11 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: utf8 -First char = 244 -Need char = 128 - -/\x{1000000}/8DM -Memory allocation (code space): 13 ------------------------------------------------------------------- - 0 9 Bra 0 - 3 \x{1000000} - 9 9 Ket - 12 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: utf8 -First char = 249 -Need char = 128 - -/\x{4000000}/8DM -Memory allocation (code space): 14 ------------------------------------------------------------------- - 0 10 Bra 0 - 3 \x{4000000} - 10 10 Ket - 13 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: utf8 -First char = 252 -Need char = 128 - -/\x{7fffFFFF}/8DM -Memory allocation (code space): 14 ------------------------------------------------------------------- - 0 10 Bra 0 - 3 \x{7fffffff} - 10 10 Ket - 13 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: utf8 -First char = 253 -Need char = 191 - -/[\x{ff}]/8DM -Memory allocation (code space): 10 ------------------------------------------------------------------- - 0 6 Bra 0 - 3 \x{ff} - 6 6 Ket - 9 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: utf8 -First char = 195 -Need char = 191 - -/[\x{100}]/8DM -Memory allocation (code space): 47 ------------------------------------------------------------------- - 0 11 Bra 0 - 3 [\x{100}] - 11 11 Ket - 14 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: utf8 -No first char -No need char - -/\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{100}a\x{1234}/8 - \x{100}a\x{1234}bcd - 0: \x{100}a\x{1234} - -/\x80/8D ------------------------------------------------------------------- - 0 6 Bra 0 - 3 \x{80} - 6 6 Ket - 9 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: utf8 -First char = 194 -Need char = 128 - -/\xff/8D ------------------------------------------------------------------- - 0 6 Bra 0 - 3 \x{ff} - 6 6 Ket - 9 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: utf8 -First char = 195 -Need char = 191 - -/\x{0041}\x{2262}\x{0391}\x{002e}/D8 ------------------------------------------------------------------- - 0 14 Bra 0 - 3 A\x{2262}\x{391}. - 14 14 Ket - 17 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: utf8 -First char = 'A' -Need char = '.' - \x{0041}\x{2262}\x{0391}\x{002e} - 0: A\x{2262}\x{391}. - -/\x{D55c}\x{ad6d}\x{C5B4}/D8 ------------------------------------------------------------------- - 0 15 Bra 0 - 3 \x{d55c}\x{ad6d}\x{c5b4} - 15 15 Ket - 18 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: utf8 -First char = 237 -Need char = 180 - \x{D55c}\x{ad6d}\x{C5B4} - 0: \x{d55c}\x{ad6d}\x{c5b4} - -/\x{65e5}\x{672c}\x{8a9e}/D8 ------------------------------------------------------------------- - 0 15 Bra 0 - 3 \x{65e5}\x{672c}\x{8a9e} - 15 15 Ket - 18 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: utf8 -First char = 230 -Need char = 158 - \x{65e5}\x{672c}\x{8a9e} - 0: \x{65e5}\x{672c}\x{8a9e} - -/\x{80}/D8 ------------------------------------------------------------------- - 0 6 Bra 0 - 3 \x{80} - 6 6 Ket - 9 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: utf8 -First char = 194 -Need char = 128 - -/\x{084}/D8 ------------------------------------------------------------------- - 0 6 Bra 0 - 3 \x{84} - 6 6 Ket - 9 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: utf8 -First char = 194 -Need char = 132 - -/\x{104}/D8 ------------------------------------------------------------------- - 0 6 Bra 0 - 3 \x{104} - 6 6 Ket - 9 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: utf8 -First char = 196 -Need char = 132 - -/\x{861}/D8 ------------------------------------------------------------------- - 0 7 Bra 0 - 3 \x{861} - 7 7 Ket - 10 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: utf8 -First char = 224 -Need char = 161 - -/\x{212ab}/D8 ------------------------------------------------------------------- - 0 8 Bra 0 - 3 \x{212ab} - 8 8 Ket - 11 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: utf8 -First char = 240 -Need char = 171 - -/.{3,5}X/D8 ------------------------------------------------------------------- - 0 13 Bra 0 - 3 Any{3} - 7 Any{0,2} - 11 X - 13 13 Ket - 16 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Partial matching not supported -Options: utf8 -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}?/D8 ------------------------------------------------------------------- - 0 11 Bra 0 - 3 Any{3} - 7 Any{0,2}? - 11 11 Ket - 14 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Partial matching not supported -Options: utf8 -No first char -No need char - \x{212ab}\x{212ab}\x{212ab}\x{861} - 0: \x{212ab}\x{212ab}\x{212ab} - -/-- These tests are here rather than in testinput4 because Perl 5.6 has --/ -/-- some problems with UTF-8 support, in the area of \x{..} where the --/ -No match -/-- value is < 255. It grumbles about invalid UTF-8 strings. --/ -No match - -/^[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} - -/-- --/ - -/(?<=\C)X/8 -Failed: \C not allowed in lookbehind assertion at offset 6 - -/-- This one is here not because it's different to Perl, but because the --/ -/-- way the captured single-byte is displayed. (In Perl it becomes a --/ -No match -/-- character, and you can't tell the difference.) --/ -No match - -/X(\C)(.*)/8 - X\x{1234} - 0: X\x{1234} - 1: \xe1 - 2: \x88\xb4 - X\nabc - 0: X\x{0a}abc - 1: \x{0a} - 2: abc - -/^[ab]/8D ------------------------------------------------------------------- - 0 37 Bra 0 - 3 ^ - 4 [ab] - 37 37 Ket - 40 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: anchored utf8 -No first char -No need char - bar - 0: b - *** Failers -No match - c -No match - \x{ff} -No match - \x{100} -No match - -/^[^ab]/8D ------------------------------------------------------------------- - 0 37 Bra 0 - 3 ^ - 4 [\x00-`c-\xff] (neg) - 37 37 Ket - 40 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: anchored utf8 -No first char -No need char - c - 0: c - \x{ff} - 0: \x{ff} - \x{100} - 0: \x{100} - *** Failers - 0: * - aaa -No match - -/[^ab\xC0-\xF0]/8SD ------------------------------------------------------------------- - 0 36 Bra 0 - 3 [\x00-`c-\xbf\xf1-\xff] (neg) - 36 36 Ket - 39 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: utf8 -No first char -No need char -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 ! " # $ % & ' ( ) * + , - . / 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 [ \ ] ^ _ ` 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 - \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 - \x{f1} - 0: \x{f1} - \x{bf} - 0: \x{bf} - \x{100} - 0: \x{100} - \x{1000} - 0: \x{1000} - *** Failers - 0: * - \x{c0} -No match - \x{f0} -No match - -/ִ€{3,4}/8SD ------------------------------------------------------------------- - 0 13 Bra 0 - 3 \x{100}{3} - 8 \x{100}{,1} - 13 13 Ket - 16 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Partial matching not supported -Options: utf8 -First char = 196 -Need char = 128 -Study returned NULL - \x{100}\x{100}\x{100}\x{100\x{100} - 0: \x{100}\x{100}\x{100} - -/(\x{100}+|x)/8SD ------------------------------------------------------------------- - 0 17 Bra 0 - 3 6 Bra 1 - 6 \x{100}+ - 9 5 Alt - 12 x - 14 11 Ket - 17 17 Ket - 20 End ------------------------------------------------------------------- -Capturing subpattern count = 1 -Partial matching not supported -Options: utf8 -No first char -No need char -Starting byte set: x \xc4 - -/(\x{100}*a|x)/8SD ------------------------------------------------------------------- - 0 19 Bra 0 - 3 8 Bra 1 - 6 \x{100}* - 9 a - 11 5 Alt - 14 x - 16 13 Ket - 19 19 Ket - 22 End ------------------------------------------------------------------- -Capturing subpattern count = 1 -Partial matching not supported -Options: utf8 -No first char -No need char -Starting byte set: a x \xc4 - -/(\x{100}{0,2}a|x)/8SD ------------------------------------------------------------------- - 0 21 Bra 0 - 3 10 Bra 1 - 6 \x{100}{,2} - 11 a - 13 5 Alt - 16 x - 18 15 Ket - 21 21 Ket - 24 End ------------------------------------------------------------------- -Capturing subpattern count = 1 -Partial matching not supported -Options: utf8 -No first char -No need char -Starting byte set: a x \xc4 - -/(\x{100}{1,2}a|x)/8SD ------------------------------------------------------------------- - 0 24 Bra 0 - 3 13 Bra 1 - 6 \x{100} - 9 \x{100}{,1} - 14 a - 16 5 Alt - 19 x - 21 18 Ket - 24 24 Ket - 27 End ------------------------------------------------------------------- -Capturing subpattern count = 1 -Partial matching not supported -Options: utf8 -No first char -No need char -Starting byte set: x \xc4 - -/\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}/8D ------------------------------------------------------------------- - 0 6 Bra 0 - 3 \x{100} - 6 6 Ket - 9 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: utf8 -First char = 196 -Need char = 128 - -/\x{100}*/8D ------------------------------------------------------------------- - 0 6 Bra 0 - 3 \x{100}* - 6 6 Ket - 9 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Partial matching not supported -Options: utf8 -No first char -No need char - -/a\x{100}*/8D ------------------------------------------------------------------- - 0 8 Bra 0 - 3 a - 5 \x{100}* - 8 8 Ket - 11 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Partial matching not supported -Options: utf8 -First char = 'a' -No need char - -/ab\x{100}*/8D ------------------------------------------------------------------- - 0 10 Bra 0 - 3 ab - 7 \x{100}* - 10 10 Ket - 13 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Partial matching not supported -Options: utf8 -First char = 'a' -Need char = 'b' - -/a\x{100}\x{101}*/8D ------------------------------------------------------------------- - 0 11 Bra 0 - 3 a\x{100} - 8 \x{101}* - 11 11 Ket - 14 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Partial matching not supported -Options: utf8 -First char = 'a' -Need char = 128 - -/a\x{100}\x{101}+/8D ------------------------------------------------------------------- - 0 11 Bra 0 - 3 a\x{100} - 8 \x{101}+ - 11 11 Ket - 14 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Partial matching not supported -Options: utf8 -First char = 'a' -Need char = 129 - -/\x{100}*A/8D ------------------------------------------------------------------- - 0 8 Bra 0 - 3 \x{100}* - 6 A - 8 8 Ket - 11 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Partial matching not supported -Options: utf8 -No first char -Need char = 'A' - A - 0: A - -/\x{100}*\d(?R)/8D ------------------------------------------------------------------- - 0 16 Bra 0 - 3 \x{100}* - 6 \d - 7 6 Once - 10 0 Recurse - 13 6 Ket - 16 16 Ket - 19 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Partial matching not supported -Options: utf8 -No first char -No need char - -/[^\x{c4}]/D ------------------------------------------------------------------- - 0 5 Bra 0 - 3 [^\xc4] - 5 5 Ket - 8 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -No options -No first char -No need char - -/[^\x{c4}]/8D ------------------------------------------------------------------- - 0 36 Bra 0 - 3 [\x00-\xc3\xc5-\xff] (neg) - 36 36 Ket - 39 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: utf8 -No first char -No need char - -/[\x{100}]/8DM -Memory allocation (code space): 47 ------------------------------------------------------------------- - 0 11 Bra 0 - 3 [\x{100}] - 11 11 Ket - 14 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: utf8 -No first char -No need char - \x{100} - 0: \x{100} - Z\x{100} - 0: \x{100} - \x{100}Z - 0: \x{100} - *** Failers -No match - -/[Z\x{100}]/8DM -Memory allocation (code space): 47 ------------------------------------------------------------------- - 0 43 Bra 0 - 3 [Z\x{100}] - 43 43 Ket - 46 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: utf8 -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 - -/[ִ€-ִ„]/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}]/8D ------------------------------------------------------------------- - 0 12 Bra 0 - 3 [z-\x{100}] - 12 12 Ket - 15 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: utf8 -No first char -No need char - -/[z\Qa-d]ִ€\E]/8D ------------------------------------------------------------------- - 0 43 Bra 0 - 3 [\-\]adz\x{100}] - 43 43 Ket - 46 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: utf8 -No first char -No need char - \x{100} - 0: \x{100} - ִ€ - 0: \x{100} - -/[\xFF]/D ------------------------------------------------------------------- - 0 5 Bra 0 - 3 \xff - 5 5 Ket - 8 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -No options -First char = 255 -No need char - >\xff< - 0: \xff - -/[\xff]/D8 ------------------------------------------------------------------- - 0 6 Bra 0 - 3 \x{ff} - 6 6 Ket - 9 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: utf8 -First char = 195 -Need char = 191 - >\x{ff}< - 0: \x{ff} - -/[^\xFF]/D ------------------------------------------------------------------- - 0 5 Bra 0 - 3 [^\xff] - 5 5 Ket - 8 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -No options -No first char -No need char - -/[^\xff]/8D ------------------------------------------------------------------- - 0 36 Bra 0 - 3 [\x00-\xfe] (neg) - 36 36 Ket - 39 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: utf8 -No first char -No need char - -/[ֳ„-ֳ]/8 - ֳ– # Matches without Study - 0: \x{d6} - \x{d6} - 0: \x{d6} - -/[ֳ„-ֳ]/8S - ֳ– <-- Same with Study - 0: \x{d6} - \x{d6} - 0: \x{d6} - -/[\x{c4}-\x{dc}]/8 - ֳ– # Matches without Study - 0: \x{d6} - \x{d6} - 0: \x{d6} - -/[\x{c4}-\x{dc}]/8S - ֳ– <-- Same with Study - 0: \x{d6} - \x{d6} - 0: \x{d6} - -/[ֳ]/8 -Failed: invalid UTF-8 string at offset 2 - -/ֳ/8 -Failed: invalid UTF-8 string at offset 0 - -/ֳֳֳxxx/8 -Failed: invalid UTF-8 string at offset 1 - -/ֳֳֳxxx/8?D ------------------------------------------------------------------- - 0 15 Bra 0 - 3 \X{c0}\X{c0}\X{c0}xxx - 15 15 Ket - 18 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: utf8 no_utf8_check -First char = 195 -Need char = 'x' - -/abc/8 - ֳ] -Error -10 - ֳ -Error -10 - ֳֳֳ -Error -10 - ֳֳֳ\? -No match - -/anything/8 - \xc0\x80 -Error -10 - \xc1\x8f -Error -10 - \xe0\x9f\x80 -Error -10 - \xf0\x8f\x80\x80 -Error -10 - \xf8\x87\x80\x80\x80 -Error -10 - \xfc\x83\x80\x80\x80\x80 -Error -10 - \xfe\x80\x80\x80\x80\x80 -Error -10 - \xff\x80\x80\x80\x80\x80 -Error -10 - \xc3\x8f -No match - \xe0\xaf\x80 -No match - \xe1\x80\x80 -No match - \xf0\x9f\x80\x80 -No match - \xf1\x8f\x80\x80 -No match - \xf8\x88\x80\x80\x80 -No match - \xf9\x87\x80\x80\x80 -No match - \xfc\x84\x80\x80\x80\x80 -No match - \xfd\x83\x80\x80\x80\x80 -No match - -/\x{100}abc(xyz(?1))/8D ------------------------------------------------------------------- - 0 33 Bra 0 - 3 \x{100}abc - 12 18 Bra 1 - 15 xyz - 21 6 Once - 24 12 Recurse - 27 6 Ket - 30 18 Ket - 33 33 Ket - 36 End ------------------------------------------------------------------- -Capturing subpattern count = 1 -Options: utf8 -First char = 196 -Need char = 'z' - -/[^\x{100}]abc(xyz(?1))/8D ------------------------------------------------------------------- - 0 38 Bra 0 - 3 [^\x{100}] - 11 abc - 17 18 Bra 1 - 20 xyz - 26 6 Once - 29 17 Recurse - 32 6 Ket - 35 18 Ket - 38 38 Ket - 41 End ------------------------------------------------------------------- -Capturing subpattern count = 1 -Options: utf8 -No first char -Need char = 'z' - -/[ab\x{100}]abc(xyz(?1))/8D ------------------------------------------------------------------- - 0 70 Bra 0 - 3 [ab\x{100}] - 43 abc - 49 18 Bra 1 - 52 xyz - 58 6 Once - 61 49 Recurse - 64 6 Ket - 67 18 Ket - 70 70 Ket - 73 End ------------------------------------------------------------------- -Capturing subpattern count = 1 -Options: utf8 -No first char -Need char = 'z' - -/(\x{100}(b(?2)c))?/D8 ------------------------------------------------------------------- - 0 32 Bra 0 - 3 Brazero - 4 25 Bra 1 - 7 \x{100} - 10 16 Bra 2 - 13 b - 15 6 Once - 18 10 Recurse - 21 6 Ket - 24 c - 26 16 Ket - 29 25 Ket - 32 32 Ket - 35 End ------------------------------------------------------------------- -Capturing subpattern count = 2 -Options: utf8 -No first char -No need char - -/(\x{100}(b(?2)c)){0,2}/D8 ------------------------------------------------------------------- - 0 67 Bra 0 - 3 Brazero - 4 60 Bra 0 - 7 25 Bra 1 - 10 \x{100} - 13 16 Bra 2 - 16 b - 18 6 Once - 21 13 Recurse - 24 6 Ket - 27 c - 29 16 Ket - 32 25 Ket - 35 Brazero - 36 25 Bra 1 - 39 \x{100} - 42 16 Bra 2 - 45 b - 47 6 Once - 50 13 Recurse - 53 6 Ket - 56 c - 58 16 Ket - 61 25 Ket - 64 60 Ket - 67 67 Ket - 70 End ------------------------------------------------------------------- -Capturing subpattern count = 2 -Options: utf8 -No first char -No need char - -/(\x{100}(b(?1)c))?/D8 ------------------------------------------------------------------- - 0 32 Bra 0 - 3 Brazero - 4 25 Bra 1 - 7 \x{100} - 10 16 Bra 2 - 13 b - 15 6 Once - 18 4 Recurse - 21 6 Ket - 24 c - 26 16 Ket - 29 25 Ket - 32 32 Ket - 35 End ------------------------------------------------------------------- -Capturing subpattern count = 2 -Options: utf8 -No first char -No need char - -/(\x{100}(b(?1)c)){0,2}/D8 ------------------------------------------------------------------- - 0 67 Bra 0 - 3 Brazero - 4 60 Bra 0 - 7 25 Bra 1 - 10 \x{100} - 13 16 Bra 2 - 16 b - 18 6 Once - 21 7 Recurse - 24 6 Ket - 27 c - 29 16 Ket - 32 25 Ket - 35 Brazero - 36 25 Bra 1 - 39 \x{100} - 42 16 Bra 2 - 45 b - 47 6 Once - 50 7 Recurse - 53 6 Ket - 56 c - 58 16 Ket - 61 25 Ket - 64 60 Ket - 67 67 Ket - 70 End ------------------------------------------------------------------- -Capturing subpattern count = 2 -Options: utf8 -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 - -/a\x{1234}b/P8 - a\x{1234}b - 0: a\x{1234}b - -/^\בˆ´/8D ------------------------------------------------------------------- - 0 8 Bra 0 - 3 ^ - 4 \x{1234} - 8 8 Ket - 11 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: anchored utf8 -No first char -No need char - -/\777/I -Failed: octal value is greater than \377 (not in UTF-8 mode) at offset 3 - -/\777/8I -Capturing subpattern count = 0 -Options: utf8 -First char = 199 -Need char = 191 - \x{1ff} - 0: \x{1ff} - \777 - 0: \x{1ff} - -/ End of testinput5 / diff --git a/ext/pcre/pcrelib/testdata/testoutput6 b/ext/pcre/pcrelib/testdata/testoutput6 deleted file mode 100644 index ee174a6b01..0000000000 --- a/ext/pcre/pcrelib/testdata/testoutput6 +++ /dev/null @@ -1,1413 +0,0 @@ -/^\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{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{dfff} -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{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{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{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: 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 - -/\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{L}]/D ------------------------------------------------------------------- - 0 11 Bra 0 - 3 [\p{L}] - 11 11 Ket - 14 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -No options -No first char -No need char - -/[\p{^L}]/D ------------------------------------------------------------------- - 0 11 Bra 0 - 3 [\P{L}] - 11 11 Ket - 14 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -No options -No first char -No need char - -/[\P{L}]/D ------------------------------------------------------------------- - 0 11 Bra 0 - 3 [\P{L}] - 11 11 Ket - 14 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -No options -No first char -No need char - -/[\P{^L}]/D ------------------------------------------------------------------- - 0 11 Bra 0 - 3 [\p{L}] - 11 11 Ket - 14 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -No options -No first char -No need char - -/[abc\p{L}\x{0660}]/8D ------------------------------------------------------------------- - 0 46 Bra 0 - 3 [a-c\p{L}\x{660}] - 46 46 Ket - 49 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: utf8 -No first char -No need char - -/[\p{Nd}]/8DM -Memory allocation (code space): 47 ------------------------------------------------------------------- - 0 11 Bra 0 - 3 [\p{Nd}] - 11 11 Ket - 14 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: utf8 -No first char -No need char - 1234 - 0: 1 - -/[\p{Nd}+-]+/8DM -Memory allocation (code space): 48 ------------------------------------------------------------------- - 0 44 Bra 0 - 3 [+\-\p{Nd}]+ - 44 44 Ket - 47 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Partial matching not supported -Options: utf8 -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 - -/[\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 - -/\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} - -/A\x{391}\x{10427}\x{ff3a}\x{1fb0}/8iD ------------------------------------------------------------------- - 0 21 Bra 0 - 3 NC A\x{391}\x{10427}\x{ff3a}\x{1fb0} - 21 21 Ket - 24 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: caseless utf8 -First char = 'A' (caseless) -No need char - -/A\x{391}\x{10427}\x{ff3a}\x{1fb0}/8D ------------------------------------------------------------------- - 0 21 Bra 0 - 3 A\x{391}\x{10427}\x{ff3a}\x{1fb0} - 21 21 Ket - 24 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: utf8 -First char = 'A' -Need char = 176 - -/AB\x{1fb0}/8D ------------------------------------------------------------------- - 0 11 Bra 0 - 3 AB\x{1fb0} - 11 11 Ket - 14 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: utf8 -First char = 'A' -Need char = 176 - -/AB\x{1fb0}/8Di ------------------------------------------------------------------- - 0 11 Bra 0 - 3 NC AB\x{1fb0} - 11 11 Ket - 14 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: caseless utf8 -First char = 'A' (caseless) -Need char = 'B' (caseless) - -/\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{c0}\x{391}]/8i - \x{c0} - 0: \x{c0} - \x{e0} - 0: \x{e0} - -/[\x{105}-\x{109}]/8iD ------------------------------------------------------------------- - 0 13 Bra 0 - 3 [\x{104}-\x{109}] - 13 13 Ket - 16 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: caseless utf8 -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}]/8iD ------------------------------------------------------------------- - 0 20 Bra 0 - 3 [Z\x{39c}\x{178}z-\x{101}] - 20 20 Ket - 23 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: caseless utf8 -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}]/8Di ------------------------------------------------------------------- - 0 20 Bra 0 - 3 [Z\x{39c}\x{178}z-\x{101}] - 20 20 Ket - 23 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: caseless utf8 -No first char -No need char - -/^\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 - 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 - -/ End of testinput6 / diff --git a/ext/pcre/pcrelib/testdata/testoutput7 b/ext/pcre/pcrelib/testdata/testoutput7 deleted file mode 100644 index 53d4e5a301..0000000000 --- a/ext/pcre/pcrelib/testdata/testoutput7 +++ /dev/null @@ -1,6732 +0,0 @@ -/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 - -/^([^()]|\((?1)*\))*$/ - 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: b - 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 regex written to testsavedregex -Study data written to testsavedregex -<testsavedregex -Compiled regex (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 - -/^/ - - 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$/ - abc - 0: abc - *** Failers -No match - qqq\nabc -No match - abc\nzzz -No match - qqq\nabc\nzzz -No match - -/\Aabc\Z/m - abc - 0: abc - abc\n - 0: abc - *** Failers -No match - qqq\nabc -No match - abc\nzzz -No match - qqq\nabc\nzzz -No match - -/\A(.)*\Z/s - abc\ndef - 0: abc\x0adef - -/\A(.)*\Z/m - *** Failers - 0: *** Failers - abc\ndef -No match - -/(?:b)|(?::+)/ - b::c - 0: b - c::b - 0: :: - 1: : - -/[-az]+/ - az- - 0: az- - 1: az - 2: a - *** Failers - 0: a - b -No match - -/[az-]+/ - za- - 0: za- - 1: za - 2: z - *** Failers - 0: a - b -No match - -/[a\-z]+/ - a-z - 0: a-z - 1: a- - 2: a - *** Failers - 0: a - b -No match - -/[a-z]+/ - abcdxyz - 0: abcdxyz - 1: abcdxy - 2: abcdx - 3: abcd - 4: abc - 5: ab - 6: a - -/[\d-]+/ - 12-34 - 0: 12-34 - 1: 12-3 - 2: 12- - 3: 12 - 4: 1 - *** Failers -No match - aaa -No match - -/[\d-z]+/ - 12-34z - 0: 12-34z - 1: 12-34 - 2: 12-3 - 3: 12- - 4: 12 - 5: 1 - *** Failers -No match - aaa -No match - -/\x5c/ - \\ - 0: \ - -/\x20Z/ - the Zoo - 0: Z - *** Failers -No match - Zulu -No match - -/ab{3cd/ - ab{3cd - 0: ab{3cd - -/ab{3,cd/ - ab{3,cd - 0: ab{3,cd - -/ab{3,4a}cd/ - ab{3,4a}cd - 0: ab{3,4a}cd - -/{4,5a}bc/ - {4,5a}bc - 0: {4,5a}bc - -/^a.b/ - a\rb - 0: a\x0db - *** Failers -No match - a\nb -No match - -/abc$/ - 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\gdef/ - abgdef - 0: abgdef - -/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{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 - -/$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: - -/a b/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$xyz - -/\Gabc/ - abc - 0: abc - *** Failers -No match - xyzabc -No match - -/\Gabc./g - abc1abc2xyzabc3 - 0: abc1 - 0: abc2 - -/abc./g - abc1abc2xyzabc3 - 0: abc1 - 0: abc2 - 0: abc3 - -/a(?x: b c )d/ - XabcdY - 0: abcd - *** Failers -No match - Xa b c d Y -No match - -/((?x)x y z | a b c)/ - XabcY - 0: abc - AxyzB - 0: xyz - -/(?i)AB(?-i)C/ - XabCY - 0: abC - *** Failers -No match - XabcY -No match - -/((?i)AB(?-i)C|D)E/ - abCE - 0: abCE - DE - 0: DE - *** Failers -No match - abcE -No match - abCe -No match - dE -No match - De -No match - -/[z\Qa-d]\E]/ - z - 0: z - a - 0: a - - - 0: - - d - 0: d - ] - 0: ] - *** Failers - 0: a - b -No match - -/[\z\C]/ - z - 0: z - C - 0: C - -/\M/ - M - 0: M - -/(a+)*b/ - aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa -No match - -/(?i)reg(?:ul(?:[aה]|ae)r|ex)/ - REGular - 0: REGular - regulaer - 0: regulaer - Regex - 0: Regex - regulהr - 0: regul\xe4r - -/ֵזוה[א-ְ-]+/ - ֵזוהא - 0: \xc5\xe6\xe5\xe4\xe0 - ֵזוה - 0: \xc5\xe6\xe5\xe4\xff - ֵזוהְ - 0: \xc5\xe6\xe5\xe4\xc0 - ֵזוה - 0: \xc5\xe6\xe5\xe4\xdf - -/(?<=Z)X./ - \x84XAZXB - 0: XB - -/^(?(2)a|(1)(2))+$/ - 123a -Error -17 - -/(?<=a|bbbb)c/ - ac - 0: c - bbbbc - 0: c - -/abc/>testsavedregex -Compiled regex written to testsavedregex -<testsavedregex -Compiled regex loaded from testsavedregex -No study data - abc - 0: abc - *** Failers -No match - bca -No match - -/abc/F>testsavedregex -Compiled regex written to testsavedregex -<testsavedregex -Compiled regex (byte-inverted) loaded from testsavedregex -No study data - abc - 0: abc - *** Failers -No match - bca -No match - -/(a|b)/S>testsavedregex -Compiled regex written to testsavedregex -Study data written to testsavedregex -<testsavedregex -Compiled regex loaded from testsavedregex -Study data loaded from testsavedregex - abc - 0: a - *** Failers - 0: a - def -No match - -/(a|b)/SF>testsavedregex -Compiled regex written to testsavedregex -Study data written to testsavedregex -<testsavedregex -Compiled regex (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 - 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 - -/.*/ - 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 - -/ End of testinput7 / diff --git a/ext/pcre/pcrelib/testdata/testoutput8 b/ext/pcre/pcrelib/testdata/testoutput8 deleted file mode 100644 index 72e7673f56..0000000000 --- a/ext/pcre/pcrelib/testdata/testoutput8 +++ /dev/null @@ -1,1031 +0,0 @@ -/-- Do not use the \x{} construct except with patterns that have the --/ -/-- /8 option set, because PCRE doesn't recognize them as UTF-8 unless --/ -No match -/-- that option is set. However, the latest Perls recognize them always. --/ -No match - -/\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 - -/abc/8 - ֳ] -Error -10 - ֳ -Error -10 - ֳֳֳ -Error -10 - ֳֳֳ\? -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} - -/ End of testinput 8 / diff --git a/ext/pcre/pcrelib/testdata/testoutput9 b/ext/pcre/pcrelib/testdata/testoutput9 deleted file mode 100644 index 000e2b9882..0000000000 --- a/ext/pcre/pcrelib/testdata/testoutput9 +++ /dev/null @@ -1,1627 +0,0 @@ -/\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{dfff} -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 - -/ End / diff --git a/ext/pcre/pcrelib/ucp.h b/ext/pcre/pcrelib/ucp.h deleted file mode 100644 index 1ca23c9c10..0000000000 --- a/ext/pcre/pcrelib/ucp.h +++ /dev/null @@ -1,126 +0,0 @@ -/************************************************* -* Unicode Property Table handler * -*************************************************/ - -#ifndef _UCP_H -#define _UCP_H - -/* This file contains definitions of the property values that are returned by -the function _pcre_ucp_findprop(). */ - -/* 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 -}; - -#endif - -/* End of ucp.h */ diff --git a/ext/pcre/pcrelib/ucpinternal.h b/ext/pcre/pcrelib/ucpinternal.h deleted file mode 100644 index 16dfbe9b0f..0000000000 --- a/ext/pcre/pcrelib/ucpinternal.h +++ /dev/null @@ -1,87 +0,0 @@ -/************************************************* -* Unicode Property Table handler * -*************************************************/ - -/* Internal header file defining the layout of the bits in each pair of 32-bit -words that form a data item in the table. */ - -typedef struct cnode { - pcre_uint32 f0; - pcre_uint32 f1; -} cnode; - -/* Things for the f0 field */ - -#define f0_scriptmask 0xff000000 /* Mask for script field */ -#define f0_scriptshift 24 /* Shift for script value */ -#define f0_rangeflag 0x00f00000 /* Flag for a range item */ -#define f0_charmask 0x001fffff /* Mask for code point value */ - -/* Things for the f1 field */ - -#define f1_typemask 0xfc000000 /* Mask for char type field */ -#define f1_typeshift 26 /* Shift for the type field */ -#define f1_rangemask 0x0000ffff /* Mask for a range offset */ -#define f1_casemask 0x0000ffff /* Mask for a case offset */ -#define f1_caseneg 0xffff8000 /* Bits for negation */ - -/* The data consists of a vector of structures of type cnode. The two unsigned -32-bit integers are used as follows: - -(f0) (1) The most significant byte holds the script number. The numbers are - defined by the enum in ucp.h. - - (2) The 0x00800000 bit is set if this entry defines a range of characters. - It is not set if this entry defines a single character - - (3) The 0x00600000 bits are spare. - - (4) The 0x001fffff bits contain the code point. No Unicode code point will - ever be greater than 0x0010ffff, so this should be OK for ever. - -(f1) (1) The 0xfc000000 bits contain the character type number. The numbers are - defined by an enum in ucp.h. - - (2) The 0x03ff0000 bits are spare. - - (3) The 0x0000ffff bits contain EITHER the unsigned offset to the top of - range if this entry defines a range, OR the *signed* offset to the - character's "other case" partner if this entry defines a single - character. There is no partner if the value is zero. - -------------------------------------------------------------------------------- -| script (8) |.|.|.| codepoint (21) || type (6) |.|.| spare (8) | offset (16) | -------------------------------------------------------------------------------- - | | | | | - | | |-> spare | |-> spare - | | | - | |-> spare |-> spare - | - |-> range flag - -The upper/lower casing information is set only for characters that come in -pairs. The non-one-to-one mappings in the Unicode data are ignored. - -When searching the data, proceed as follows: - -(1) Set up for a binary chop search. - -(2) If the top is not greater than the bottom, the character is not in the - table. Its type must therefore be "Cn" ("Undefined"). - -(3) Find the middle vector element. - -(4) Extract the code point and compare. If equal, we are done. - -(5) If the test character is smaller, set the top to the current point, and - goto (2). - -(6) If the current entry defines a range, compute the last character by adding - the offset, and see if the test character is within the range. If it is, - we are done. - -(7) Otherwise, set the bottom to one element past the current point and goto - (2). -*/ - -/* End of ucpinternal.h */ diff --git a/ext/pcre/pcrelib/ucptable.c b/ext/pcre/pcrelib/ucptable.c deleted file mode 100644 index ae665b3760..0000000000 --- a/ext/pcre/pcrelib/ucptable.c +++ /dev/null @@ -1,2968 +0,0 @@ -/* This source module is automatically generated from the Unicode -property table. See ucpinternal.h for a description of the layout. */ - -static cnode ucp_table[] = { - { 0x09800000, 0x0000001f }, - { 0x09000020, 0x74000000 }, - { 0x09800021, 0x54000002 }, - { 0x09000024, 0x5c000000 }, - { 0x09800025, 0x54000002 }, - { 0x09000028, 0x58000000 }, - { 0x09000029, 0x48000000 }, - { 0x0900002a, 0x54000000 }, - { 0x0900002b, 0x64000000 }, - { 0x0900002c, 0x54000000 }, - { 0x0900002d, 0x44000000 }, - { 0x0980002e, 0x54000001 }, - { 0x09800030, 0x34000009 }, - { 0x0980003a, 0x54000001 }, - { 0x0980003c, 0x64000002 }, - { 0x0980003f, 0x54000001 }, - { 0x21000041, 0x24000020 }, - { 0x21000042, 0x24000020 }, - { 0x21000043, 0x24000020 }, - { 0x21000044, 0x24000020 }, - { 0x21000045, 0x24000020 }, - { 0x21000046, 0x24000020 }, - { 0x21000047, 0x24000020 }, - { 0x21000048, 0x24000020 }, - { 0x21000049, 0x24000020 }, - { 0x2100004a, 0x24000020 }, - { 0x2100004b, 0x24000020 }, - { 0x2100004c, 0x24000020 }, - { 0x2100004d, 0x24000020 }, - { 0x2100004e, 0x24000020 }, - { 0x2100004f, 0x24000020 }, - { 0x21000050, 0x24000020 }, - { 0x21000051, 0x24000020 }, - { 0x21000052, 0x24000020 }, - { 0x21000053, 0x24000020 }, - { 0x21000054, 0x24000020 }, - { 0x21000055, 0x24000020 }, - { 0x21000056, 0x24000020 }, - { 0x21000057, 0x24000020 }, - { 0x21000058, 0x24000020 }, - { 0x21000059, 0x24000020 }, - { 0x2100005a, 0x24000020 }, - { 0x0900005b, 0x58000000 }, - { 0x0900005c, 0x54000000 }, - { 0x0900005d, 0x48000000 }, - { 0x0900005e, 0x60000000 }, - { 0x0900005f, 0x40000000 }, - { 0x09000060, 0x60000000 }, - { 0x21000061, 0x1400ffe0 }, - { 0x21000062, 0x1400ffe0 }, - { 0x21000063, 0x1400ffe0 }, - { 0x21000064, 0x1400ffe0 }, - { 0x21000065, 0x1400ffe0 }, - { 0x21000066, 0x1400ffe0 }, - { 0x21000067, 0x1400ffe0 }, - { 0x21000068, 0x1400ffe0 }, - { 0x21000069, 0x1400ffe0 }, - { 0x2100006a, 0x1400ffe0 }, - { 0x2100006b, 0x1400ffe0 }, - { 0x2100006c, 0x1400ffe0 }, - { 0x2100006d, 0x1400ffe0 }, - { 0x2100006e, 0x1400ffe0 }, - { 0x2100006f, 0x1400ffe0 }, - { 0x21000070, 0x1400ffe0 }, - { 0x21000071, 0x1400ffe0 }, - { 0x21000072, 0x1400ffe0 }, - { 0x21000073, 0x1400ffe0 }, - { 0x21000074, 0x1400ffe0 }, - { 0x21000075, 0x1400ffe0 }, - { 0x21000076, 0x1400ffe0 }, - { 0x21000077, 0x1400ffe0 }, - { 0x21000078, 0x1400ffe0 }, - { 0x21000079, 0x1400ffe0 }, - { 0x2100007a, 0x1400ffe0 }, - { 0x0900007b, 0x58000000 }, - { 0x0900007c, 0x64000000 }, - { 0x0900007d, 0x48000000 }, - { 0x0900007e, 0x64000000 }, - { 0x0980007f, 0x00000020 }, - { 0x090000a0, 0x74000000 }, - { 0x090000a1, 0x54000000 }, - { 0x098000a2, 0x5c000003 }, - { 0x098000a6, 0x68000001 }, - { 0x090000a8, 0x60000000 }, - { 0x090000a9, 0x68000000 }, - { 0x210000aa, 0x14000000 }, - { 0x090000ab, 0x50000000 }, - { 0x090000ac, 0x64000000 }, - { 0x090000ad, 0x04000000 }, - { 0x090000ae, 0x68000000 }, - { 0x090000af, 0x60000000 }, - { 0x090000b0, 0x68000000 }, - { 0x090000b1, 0x64000000 }, - { 0x098000b2, 0x3c000001 }, - { 0x090000b4, 0x60000000 }, - { 0x090000b5, 0x140002e7 }, - { 0x090000b6, 0x68000000 }, - { 0x090000b7, 0x54000000 }, - { 0x090000b8, 0x60000000 }, - { 0x090000b9, 0x3c000000 }, - { 0x210000ba, 0x14000000 }, - { 0x090000bb, 0x4c000000 }, - { 0x098000bc, 0x3c000002 }, - { 0x090000bf, 0x54000000 }, - { 0x210000c0, 0x24000020 }, - { 0x210000c1, 0x24000020 }, - { 0x210000c2, 0x24000020 }, - { 0x210000c3, 0x24000020 }, - { 0x210000c4, 0x24000020 }, - { 0x210000c5, 0x24000020 }, - { 0x210000c6, 0x24000020 }, - { 0x210000c7, 0x24000020 }, - { 0x210000c8, 0x24000020 }, - { 0x210000c9, 0x24000020 }, - { 0x210000ca, 0x24000020 }, - { 0x210000cb, 0x24000020 }, - { 0x210000cc, 0x24000020 }, - { 0x210000cd, 0x24000020 }, - { 0x210000ce, 0x24000020 }, - { 0x210000cf, 0x24000020 }, - { 0x210000d0, 0x24000020 }, - { 0x210000d1, 0x24000020 }, - { 0x210000d2, 0x24000020 }, - { 0x210000d3, 0x24000020 }, - { 0x210000d4, 0x24000020 }, - { 0x210000d5, 0x24000020 }, - { 0x210000d6, 0x24000020 }, - { 0x090000d7, 0x64000000 }, - { 0x210000d8, 0x24000020 }, - { 0x210000d9, 0x24000020 }, - { 0x210000da, 0x24000020 }, - { 0x210000db, 0x24000020 }, - { 0x210000dc, 0x24000020 }, - { 0x210000dd, 0x24000020 }, - { 0x210000de, 0x24000020 }, - { 0x210000df, 0x14000000 }, - { 0x210000e0, 0x1400ffe0 }, - { 0x210000e1, 0x1400ffe0 }, - { 0x210000e2, 0x1400ffe0 }, - { 0x210000e3, 0x1400ffe0 }, - { 0x210000e4, 0x1400ffe0 }, - { 0x210000e5, 0x1400ffe0 }, - { 0x210000e6, 0x1400ffe0 }, - { 0x210000e7, 0x1400ffe0 }, - { 0x210000e8, 0x1400ffe0 }, - { 0x210000e9, 0x1400ffe0 }, - { 0x210000ea, 0x1400ffe0 }, - { 0x210000eb, 0x1400ffe0 }, - { 0x210000ec, 0x1400ffe0 }, - { 0x210000ed, 0x1400ffe0 }, - { 0x210000ee, 0x1400ffe0 }, - { 0x210000ef, 0x1400ffe0 }, - { 0x210000f0, 0x1400ffe0 }, - { 0x210000f1, 0x1400ffe0 }, - { 0x210000f2, 0x1400ffe0 }, - { 0x210000f3, 0x1400ffe0 }, - { 0x210000f4, 0x1400ffe0 }, - { 0x210000f5, 0x1400ffe0 }, - { 0x210000f6, 0x1400ffe0 }, - { 0x090000f7, 0x64000000 }, - { 0x210000f8, 0x1400ffe0 }, - { 0x210000f9, 0x1400ffe0 }, - { 0x210000fa, 0x1400ffe0 }, - { 0x210000fb, 0x1400ffe0 }, - { 0x210000fc, 0x1400ffe0 }, - { 0x210000fd, 0x1400ffe0 }, - { 0x210000fe, 0x1400ffe0 }, - { 0x210000ff, 0x14000079 }, - { 0x21000100, 0x24000001 }, - { 0x21000101, 0x1400ffff }, - { 0x21000102, 0x24000001 }, - { 0x21000103, 0x1400ffff }, - { 0x21000104, 0x24000001 }, - { 0x21000105, 0x1400ffff }, - { 0x21000106, 0x24000001 }, - { 0x21000107, 0x1400ffff }, - { 0x21000108, 0x24000001 }, - { 0x21000109, 0x1400ffff }, - { 0x2100010a, 0x24000001 }, - { 0x2100010b, 0x1400ffff }, - { 0x2100010c, 0x24000001 }, - { 0x2100010d, 0x1400ffff }, - { 0x2100010e, 0x24000001 }, - { 0x2100010f, 0x1400ffff }, - { 0x21000110, 0x24000001 }, - { 0x21000111, 0x1400ffff }, - { 0x21000112, 0x24000001 }, - { 0x21000113, 0x1400ffff }, - { 0x21000114, 0x24000001 }, - { 0x21000115, 0x1400ffff }, - { 0x21000116, 0x24000001 }, - { 0x21000117, 0x1400ffff }, - { 0x21000118, 0x24000001 }, - { 0x21000119, 0x1400ffff }, - { 0x2100011a, 0x24000001 }, - { 0x2100011b, 0x1400ffff }, - { 0x2100011c, 0x24000001 }, - { 0x2100011d, 0x1400ffff }, - { 0x2100011e, 0x24000001 }, - { 0x2100011f, 0x1400ffff }, - { 0x21000120, 0x24000001 }, - { 0x21000121, 0x1400ffff }, - { 0x21000122, 0x24000001 }, - { 0x21000123, 0x1400ffff }, - { 0x21000124, 0x24000001 }, - { 0x21000125, 0x1400ffff }, - { 0x21000126, 0x24000001 }, - { 0x21000127, 0x1400ffff }, - { 0x21000128, 0x24000001 }, - { 0x21000129, 0x1400ffff }, - { 0x2100012a, 0x24000001 }, - { 0x2100012b, 0x1400ffff }, - { 0x2100012c, 0x24000001 }, - { 0x2100012d, 0x1400ffff }, - { 0x2100012e, 0x24000001 }, - { 0x2100012f, 0x1400ffff }, - { 0x21000130, 0x2400ff39 }, - { 0x21000131, 0x1400ff18 }, - { 0x21000132, 0x24000001 }, - { 0x21000133, 0x1400ffff }, - { 0x21000134, 0x24000001 }, - { 0x21000135, 0x1400ffff }, - { 0x21000136, 0x24000001 }, - { 0x21000137, 0x1400ffff }, - { 0x21000138, 0x14000000 }, - { 0x21000139, 0x24000001 }, - { 0x2100013a, 0x1400ffff }, - { 0x2100013b, 0x24000001 }, - { 0x2100013c, 0x1400ffff }, - { 0x2100013d, 0x24000001 }, - { 0x2100013e, 0x1400ffff }, - { 0x2100013f, 0x24000001 }, - { 0x21000140, 0x1400ffff }, - { 0x21000141, 0x24000001 }, - { 0x21000142, 0x1400ffff }, - { 0x21000143, 0x24000001 }, - { 0x21000144, 0x1400ffff }, - { 0x21000145, 0x24000001 }, - { 0x21000146, 0x1400ffff }, - { 0x21000147, 0x24000001 }, - { 0x21000148, 0x1400ffff }, - { 0x21000149, 0x14000000 }, - { 0x2100014a, 0x24000001 }, - { 0x2100014b, 0x1400ffff }, - { 0x2100014c, 0x24000001 }, - { 0x2100014d, 0x1400ffff }, - { 0x2100014e, 0x24000001 }, - { 0x2100014f, 0x1400ffff }, - { 0x21000150, 0x24000001 }, - { 0x21000151, 0x1400ffff }, - { 0x21000152, 0x24000001 }, - { 0x21000153, 0x1400ffff }, - { 0x21000154, 0x24000001 }, - { 0x21000155, 0x1400ffff }, - { 0x21000156, 0x24000001 }, - { 0x21000157, 0x1400ffff }, - { 0x21000158, 0x24000001 }, - { 0x21000159, 0x1400ffff }, - { 0x2100015a, 0x24000001 }, - { 0x2100015b, 0x1400ffff }, - { 0x2100015c, 0x24000001 }, - { 0x2100015d, 0x1400ffff }, - { 0x2100015e, 0x24000001 }, - { 0x2100015f, 0x1400ffff }, - { 0x21000160, 0x24000001 }, - { 0x21000161, 0x1400ffff }, - { 0x21000162, 0x24000001 }, - { 0x21000163, 0x1400ffff }, - { 0x21000164, 0x24000001 }, - { 0x21000165, 0x1400ffff }, - { 0x21000166, 0x24000001 }, - { 0x21000167, 0x1400ffff }, - { 0x21000168, 0x24000001 }, - { 0x21000169, 0x1400ffff }, - { 0x2100016a, 0x24000001 }, - { 0x2100016b, 0x1400ffff }, - { 0x2100016c, 0x24000001 }, - { 0x2100016d, 0x1400ffff }, - { 0x2100016e, 0x24000001 }, - { 0x2100016f, 0x1400ffff }, - { 0x21000170, 0x24000001 }, - { 0x21000171, 0x1400ffff }, - { 0x21000172, 0x24000001 }, - { 0x21000173, 0x1400ffff }, - { 0x21000174, 0x24000001 }, - { 0x21000175, 0x1400ffff }, - { 0x21000176, 0x24000001 }, - { 0x21000177, 0x1400ffff }, - { 0x21000178, 0x2400ff87 }, - { 0x21000179, 0x24000001 }, - { 0x2100017a, 0x1400ffff }, - { 0x2100017b, 0x24000001 }, - { 0x2100017c, 0x1400ffff }, - { 0x2100017d, 0x24000001 }, - { 0x2100017e, 0x1400ffff }, - { 0x2100017f, 0x1400fed4 }, - { 0x21000180, 0x14000000 }, - { 0x21000181, 0x240000d2 }, - { 0x21000182, 0x24000001 }, - { 0x21000183, 0x1400ffff }, - { 0x21000184, 0x24000001 }, - { 0x21000185, 0x1400ffff }, - { 0x21000186, 0x240000ce }, - { 0x21000187, 0x24000001 }, - { 0x21000188, 0x1400ffff }, - { 0x21000189, 0x240000cd }, - { 0x2100018a, 0x240000cd }, - { 0x2100018b, 0x24000001 }, - { 0x2100018c, 0x1400ffff }, - { 0x2100018d, 0x14000000 }, - { 0x2100018e, 0x2400004f }, - { 0x2100018f, 0x240000ca }, - { 0x21000190, 0x240000cb }, - { 0x21000191, 0x24000001 }, - { 0x21000192, 0x1400ffff }, - { 0x21000193, 0x240000cd }, - { 0x21000194, 0x240000cf }, - { 0x21000195, 0x14000061 }, - { 0x21000196, 0x240000d3 }, - { 0x21000197, 0x240000d1 }, - { 0x21000198, 0x24000001 }, - { 0x21000199, 0x1400ffff }, - { 0x2100019a, 0x140000a3 }, - { 0x2100019b, 0x14000000 }, - { 0x2100019c, 0x240000d3 }, - { 0x2100019d, 0x240000d5 }, - { 0x2100019e, 0x14000082 }, - { 0x2100019f, 0x240000d6 }, - { 0x210001a0, 0x24000001 }, - { 0x210001a1, 0x1400ffff }, - { 0x210001a2, 0x24000001 }, - { 0x210001a3, 0x1400ffff }, - { 0x210001a4, 0x24000001 }, - { 0x210001a5, 0x1400ffff }, - { 0x210001a6, 0x240000da }, - { 0x210001a7, 0x24000001 }, - { 0x210001a8, 0x1400ffff }, - { 0x210001a9, 0x240000da }, - { 0x218001aa, 0x14000001 }, - { 0x210001ac, 0x24000001 }, - { 0x210001ad, 0x1400ffff }, - { 0x210001ae, 0x240000da }, - { 0x210001af, 0x24000001 }, - { 0x210001b0, 0x1400ffff }, - { 0x210001b1, 0x240000d9 }, - { 0x210001b2, 0x240000d9 }, - { 0x210001b3, 0x24000001 }, - { 0x210001b4, 0x1400ffff }, - { 0x210001b5, 0x24000001 }, - { 0x210001b6, 0x1400ffff }, - { 0x210001b7, 0x240000db }, - { 0x210001b8, 0x24000001 }, - { 0x210001b9, 0x1400ffff }, - { 0x210001ba, 0x14000000 }, - { 0x210001bb, 0x1c000000 }, - { 0x210001bc, 0x24000001 }, - { 0x210001bd, 0x1400ffff }, - { 0x210001be, 0x14000000 }, - { 0x210001bf, 0x14000038 }, - { 0x218001c0, 0x1c000003 }, - { 0x210001c4, 0x24000002 }, - { 0x210001c5, 0x2000ffff }, - { 0x210001c6, 0x1400fffe }, - { 0x210001c7, 0x24000002 }, - { 0x210001c8, 0x2000ffff }, - { 0x210001c9, 0x1400fffe }, - { 0x210001ca, 0x24000002 }, - { 0x210001cb, 0x2000ffff }, - { 0x210001cc, 0x1400fffe }, - { 0x210001cd, 0x24000001 }, - { 0x210001ce, 0x1400ffff }, - { 0x210001cf, 0x24000001 }, - { 0x210001d0, 0x1400ffff }, - { 0x210001d1, 0x24000001 }, - { 0x210001d2, 0x1400ffff }, - { 0x210001d3, 0x24000001 }, - { 0x210001d4, 0x1400ffff }, - { 0x210001d5, 0x24000001 }, - { 0x210001d6, 0x1400ffff }, - { 0x210001d7, 0x24000001 }, - { 0x210001d8, 0x1400ffff }, - { 0x210001d9, 0x24000001 }, - { 0x210001da, 0x1400ffff }, - { 0x210001db, 0x24000001 }, - { 0x210001dc, 0x1400ffff }, - { 0x210001dd, 0x1400ffb1 }, - { 0x210001de, 0x24000001 }, - { 0x210001df, 0x1400ffff }, - { 0x210001e0, 0x24000001 }, - { 0x210001e1, 0x1400ffff }, - { 0x210001e2, 0x24000001 }, - { 0x210001e3, 0x1400ffff }, - { 0x210001e4, 0x24000001 }, - { 0x210001e5, 0x1400ffff }, - { 0x210001e6, 0x24000001 }, - { 0x210001e7, 0x1400ffff }, - { 0x210001e8, 0x24000001 }, - { 0x210001e9, 0x1400ffff }, - { 0x210001ea, 0x24000001 }, - { 0x210001eb, 0x1400ffff }, - { 0x210001ec, 0x24000001 }, - { 0x210001ed, 0x1400ffff }, - { 0x210001ee, 0x24000001 }, - { 0x210001ef, 0x1400ffff }, - { 0x210001f0, 0x14000000 }, - { 0x210001f1, 0x24000002 }, - { 0x210001f2, 0x2000ffff }, - { 0x210001f3, 0x1400fffe }, - { 0x210001f4, 0x24000001 }, - { 0x210001f5, 0x1400ffff }, - { 0x210001f6, 0x2400ff9f }, - { 0x210001f7, 0x2400ffc8 }, - { 0x210001f8, 0x24000001 }, - { 0x210001f9, 0x1400ffff }, - { 0x210001fa, 0x24000001 }, - { 0x210001fb, 0x1400ffff }, - { 0x210001fc, 0x24000001 }, - { 0x210001fd, 0x1400ffff }, - { 0x210001fe, 0x24000001 }, - { 0x210001ff, 0x1400ffff }, - { 0x21000200, 0x24000001 }, - { 0x21000201, 0x1400ffff }, - { 0x21000202, 0x24000001 }, - { 0x21000203, 0x1400ffff }, - { 0x21000204, 0x24000001 }, - { 0x21000205, 0x1400ffff }, - { 0x21000206, 0x24000001 }, - { 0x21000207, 0x1400ffff }, - { 0x21000208, 0x24000001 }, - { 0x21000209, 0x1400ffff }, - { 0x2100020a, 0x24000001 }, - { 0x2100020b, 0x1400ffff }, - { 0x2100020c, 0x24000001 }, - { 0x2100020d, 0x1400ffff }, - { 0x2100020e, 0x24000001 }, - { 0x2100020f, 0x1400ffff }, - { 0x21000210, 0x24000001 }, - { 0x21000211, 0x1400ffff }, - { 0x21000212, 0x24000001 }, - { 0x21000213, 0x1400ffff }, - { 0x21000214, 0x24000001 }, - { 0x21000215, 0x1400ffff }, - { 0x21000216, 0x24000001 }, - { 0x21000217, 0x1400ffff }, - { 0x21000218, 0x24000001 }, - { 0x21000219, 0x1400ffff }, - { 0x2100021a, 0x24000001 }, - { 0x2100021b, 0x1400ffff }, - { 0x2100021c, 0x24000001 }, - { 0x2100021d, 0x1400ffff }, - { 0x2100021e, 0x24000001 }, - { 0x2100021f, 0x1400ffff }, - { 0x21000220, 0x2400ff7e }, - { 0x21000221, 0x14000000 }, - { 0x21000222, 0x24000001 }, - { 0x21000223, 0x1400ffff }, - { 0x21000224, 0x24000001 }, - { 0x21000225, 0x1400ffff }, - { 0x21000226, 0x24000001 }, - { 0x21000227, 0x1400ffff }, - { 0x21000228, 0x24000001 }, - { 0x21000229, 0x1400ffff }, - { 0x2100022a, 0x24000001 }, - { 0x2100022b, 0x1400ffff }, - { 0x2100022c, 0x24000001 }, - { 0x2100022d, 0x1400ffff }, - { 0x2100022e, 0x24000001 }, - { 0x2100022f, 0x1400ffff }, - { 0x21000230, 0x24000001 }, - { 0x21000231, 0x1400ffff }, - { 0x21000232, 0x24000001 }, - { 0x21000233, 0x1400ffff }, - { 0x21800234, 0x14000005 }, - { 0x2100023a, 0x24000000 }, - { 0x2100023b, 0x24000001 }, - { 0x2100023c, 0x1400ffff }, - { 0x2100023d, 0x2400ff5d }, - { 0x2100023e, 0x24000000 }, - { 0x2180023f, 0x14000001 }, - { 0x21000241, 0x24000053 }, - { 0x21800250, 0x14000002 }, - { 0x21000253, 0x1400ff2e }, - { 0x21000254, 0x1400ff32 }, - { 0x21000255, 0x14000000 }, - { 0x21000256, 0x1400ff33 }, - { 0x21000257, 0x1400ff33 }, - { 0x21000258, 0x14000000 }, - { 0x21000259, 0x1400ff36 }, - { 0x2100025a, 0x14000000 }, - { 0x2100025b, 0x1400ff35 }, - { 0x2180025c, 0x14000003 }, - { 0x21000260, 0x1400ff33 }, - { 0x21800261, 0x14000001 }, - { 0x21000263, 0x1400ff31 }, - { 0x21800264, 0x14000003 }, - { 0x21000268, 0x1400ff2f }, - { 0x21000269, 0x1400ff2d }, - { 0x2180026a, 0x14000004 }, - { 0x2100026f, 0x1400ff2d }, - { 0x21800270, 0x14000001 }, - { 0x21000272, 0x1400ff2b }, - { 0x21800273, 0x14000001 }, - { 0x21000275, 0x1400ff2a }, - { 0x21800276, 0x14000009 }, - { 0x21000280, 0x1400ff26 }, - { 0x21800281, 0x14000001 }, - { 0x21000283, 0x1400ff26 }, - { 0x21800284, 0x14000003 }, - { 0x21000288, 0x1400ff26 }, - { 0x21000289, 0x14000000 }, - { 0x2100028a, 0x1400ff27 }, - { 0x2100028b, 0x1400ff27 }, - { 0x2180028c, 0x14000005 }, - { 0x21000292, 0x1400ff25 }, - { 0x21000293, 0x14000000 }, - { 0x21000294, 0x1400ffad }, - { 0x21800295, 0x1400001a }, - { 0x218002b0, 0x18000011 }, - { 0x098002c2, 0x60000003 }, - { 0x098002c6, 0x1800000b }, - { 0x098002d2, 0x6000000d }, - { 0x218002e0, 0x18000004 }, - { 0x098002e5, 0x60000008 }, - { 0x090002ee, 0x18000000 }, - { 0x098002ef, 0x60000010 }, - { 0x1b800300, 0x30000044 }, - { 0x1b000345, 0x30000054 }, - { 0x1b800346, 0x30000029 }, - { 0x13800374, 0x60000001 }, - { 0x1300037a, 0x18000000 }, - { 0x0900037e, 0x54000000 }, - { 0x13800384, 0x60000001 }, - { 0x13000386, 0x24000026 }, - { 0x09000387, 0x54000000 }, - { 0x13000388, 0x24000025 }, - { 0x13000389, 0x24000025 }, - { 0x1300038a, 0x24000025 }, - { 0x1300038c, 0x24000040 }, - { 0x1300038e, 0x2400003f }, - { 0x1300038f, 0x2400003f }, - { 0x13000390, 0x14000000 }, - { 0x13000391, 0x24000020 }, - { 0x13000392, 0x24000020 }, - { 0x13000393, 0x24000020 }, - { 0x13000394, 0x24000020 }, - { 0x13000395, 0x24000020 }, - { 0x13000396, 0x24000020 }, - { 0x13000397, 0x24000020 }, - { 0x13000398, 0x24000020 }, - { 0x13000399, 0x24000020 }, - { 0x1300039a, 0x24000020 }, - { 0x1300039b, 0x24000020 }, - { 0x1300039c, 0x24000020 }, - { 0x1300039d, 0x24000020 }, - { 0x1300039e, 0x24000020 }, - { 0x1300039f, 0x24000020 }, - { 0x130003a0, 0x24000020 }, - { 0x130003a1, 0x24000020 }, - { 0x130003a3, 0x24000020 }, - { 0x130003a4, 0x24000020 }, - { 0x130003a5, 0x24000020 }, - { 0x130003a6, 0x24000020 }, - { 0x130003a7, 0x24000020 }, - { 0x130003a8, 0x24000020 }, - { 0x130003a9, 0x24000020 }, - { 0x130003aa, 0x24000020 }, - { 0x130003ab, 0x24000020 }, - { 0x130003ac, 0x1400ffda }, - { 0x130003ad, 0x1400ffdb }, - { 0x130003ae, 0x1400ffdb }, - { 0x130003af, 0x1400ffdb }, - { 0x130003b0, 0x14000000 }, - { 0x130003b1, 0x1400ffe0 }, - { 0x130003b2, 0x1400ffe0 }, - { 0x130003b3, 0x1400ffe0 }, - { 0x130003b4, 0x1400ffe0 }, - { 0x130003b5, 0x1400ffe0 }, - { 0x130003b6, 0x1400ffe0 }, - { 0x130003b7, 0x1400ffe0 }, - { 0x130003b8, 0x1400ffe0 }, - { 0x130003b9, 0x1400ffe0 }, - { 0x130003ba, 0x1400ffe0 }, - { 0x130003bb, 0x1400ffe0 }, - { 0x130003bc, 0x1400ffe0 }, - { 0x130003bd, 0x1400ffe0 }, - { 0x130003be, 0x1400ffe0 }, - { 0x130003bf, 0x1400ffe0 }, - { 0x130003c0, 0x1400ffe0 }, - { 0x130003c1, 0x1400ffe0 }, - { 0x130003c2, 0x1400ffe1 }, - { 0x130003c3, 0x1400ffe0 }, - { 0x130003c4, 0x1400ffe0 }, - { 0x130003c5, 0x1400ffe0 }, - { 0x130003c6, 0x1400ffe0 }, - { 0x130003c7, 0x1400ffe0 }, - { 0x130003c8, 0x1400ffe0 }, - { 0x130003c9, 0x1400ffe0 }, - { 0x130003ca, 0x1400ffe0 }, - { 0x130003cb, 0x1400ffe0 }, - { 0x130003cc, 0x1400ffc0 }, - { 0x130003cd, 0x1400ffc1 }, - { 0x130003ce, 0x1400ffc1 }, - { 0x130003d0, 0x1400ffc2 }, - { 0x130003d1, 0x1400ffc7 }, - { 0x138003d2, 0x24000002 }, - { 0x130003d5, 0x1400ffd1 }, - { 0x130003d6, 0x1400ffca }, - { 0x130003d7, 0x14000000 }, - { 0x130003d8, 0x24000001 }, - { 0x130003d9, 0x1400ffff }, - { 0x130003da, 0x24000001 }, - { 0x130003db, 0x1400ffff }, - { 0x130003dc, 0x24000001 }, - { 0x130003dd, 0x1400ffff }, - { 0x130003de, 0x24000001 }, - { 0x130003df, 0x1400ffff }, - { 0x130003e0, 0x24000001 }, - { 0x130003e1, 0x1400ffff }, - { 0x0a0003e2, 0x24000001 }, - { 0x0a0003e3, 0x1400ffff }, - { 0x0a0003e4, 0x24000001 }, - { 0x0a0003e5, 0x1400ffff }, - { 0x0a0003e6, 0x24000001 }, - { 0x0a0003e7, 0x1400ffff }, - { 0x0a0003e8, 0x24000001 }, - { 0x0a0003e9, 0x1400ffff }, - { 0x0a0003ea, 0x24000001 }, - { 0x0a0003eb, 0x1400ffff }, - { 0x0a0003ec, 0x24000001 }, - { 0x0a0003ed, 0x1400ffff }, - { 0x0a0003ee, 0x24000001 }, - { 0x0a0003ef, 0x1400ffff }, - { 0x130003f0, 0x1400ffaa }, - { 0x130003f1, 0x1400ffb0 }, - { 0x130003f2, 0x14000007 }, - { 0x130003f3, 0x14000000 }, - { 0x130003f4, 0x2400ffc4 }, - { 0x130003f5, 0x1400ffa0 }, - { 0x130003f6, 0x64000000 }, - { 0x130003f7, 0x24000001 }, - { 0x130003f8, 0x1400ffff }, - { 0x130003f9, 0x2400fff9 }, - { 0x130003fa, 0x24000001 }, - { 0x130003fb, 0x1400ffff }, - { 0x130003fc, 0x14000000 }, - { 0x138003fd, 0x24000002 }, - { 0x0c000400, 0x24000050 }, - { 0x0c000401, 0x24000050 }, - { 0x0c000402, 0x24000050 }, - { 0x0c000403, 0x24000050 }, - { 0x0c000404, 0x24000050 }, - { 0x0c000405, 0x24000050 }, - { 0x0c000406, 0x24000050 }, - { 0x0c000407, 0x24000050 }, - { 0x0c000408, 0x24000050 }, - { 0x0c000409, 0x24000050 }, - { 0x0c00040a, 0x24000050 }, - { 0x0c00040b, 0x24000050 }, - { 0x0c00040c, 0x24000050 }, - { 0x0c00040d, 0x24000050 }, - { 0x0c00040e, 0x24000050 }, - { 0x0c00040f, 0x24000050 }, - { 0x0c000410, 0x24000020 }, - { 0x0c000411, 0x24000020 }, - { 0x0c000412, 0x24000020 }, - { 0x0c000413, 0x24000020 }, - { 0x0c000414, 0x24000020 }, - { 0x0c000415, 0x24000020 }, - { 0x0c000416, 0x24000020 }, - { 0x0c000417, 0x24000020 }, - { 0x0c000418, 0x24000020 }, - { 0x0c000419, 0x24000020 }, - { 0x0c00041a, 0x24000020 }, - { 0x0c00041b, 0x24000020 }, - { 0x0c00041c, 0x24000020 }, - { 0x0c00041d, 0x24000020 }, - { 0x0c00041e, 0x24000020 }, - { 0x0c00041f, 0x24000020 }, - { 0x0c000420, 0x24000020 }, - { 0x0c000421, 0x24000020 }, - { 0x0c000422, 0x24000020 }, - { 0x0c000423, 0x24000020 }, - { 0x0c000424, 0x24000020 }, - { 0x0c000425, 0x24000020 }, - { 0x0c000426, 0x24000020 }, - { 0x0c000427, 0x24000020 }, - { 0x0c000428, 0x24000020 }, - { 0x0c000429, 0x24000020 }, - { 0x0c00042a, 0x24000020 }, - { 0x0c00042b, 0x24000020 }, - { 0x0c00042c, 0x24000020 }, - { 0x0c00042d, 0x24000020 }, - { 0x0c00042e, 0x24000020 }, - { 0x0c00042f, 0x24000020 }, - { 0x0c000430, 0x1400ffe0 }, - { 0x0c000431, 0x1400ffe0 }, - { 0x0c000432, 0x1400ffe0 }, - { 0x0c000433, 0x1400ffe0 }, - { 0x0c000434, 0x1400ffe0 }, - { 0x0c000435, 0x1400ffe0 }, - { 0x0c000436, 0x1400ffe0 }, - { 0x0c000437, 0x1400ffe0 }, - { 0x0c000438, 0x1400ffe0 }, - { 0x0c000439, 0x1400ffe0 }, - { 0x0c00043a, 0x1400ffe0 }, - { 0x0c00043b, 0x1400ffe0 }, - { 0x0c00043c, 0x1400ffe0 }, - { 0x0c00043d, 0x1400ffe0 }, - { 0x0c00043e, 0x1400ffe0 }, - { 0x0c00043f, 0x1400ffe0 }, - { 0x0c000440, 0x1400ffe0 }, - { 0x0c000441, 0x1400ffe0 }, - { 0x0c000442, 0x1400ffe0 }, - { 0x0c000443, 0x1400ffe0 }, - { 0x0c000444, 0x1400ffe0 }, - { 0x0c000445, 0x1400ffe0 }, - { 0x0c000446, 0x1400ffe0 }, - { 0x0c000447, 0x1400ffe0 }, - { 0x0c000448, 0x1400ffe0 }, - { 0x0c000449, 0x1400ffe0 }, - { 0x0c00044a, 0x1400ffe0 }, - { 0x0c00044b, 0x1400ffe0 }, - { 0x0c00044c, 0x1400ffe0 }, - { 0x0c00044d, 0x1400ffe0 }, - { 0x0c00044e, 0x1400ffe0 }, - { 0x0c00044f, 0x1400ffe0 }, - { 0x0c000450, 0x1400ffb0 }, - { 0x0c000451, 0x1400ffb0 }, - { 0x0c000452, 0x1400ffb0 }, - { 0x0c000453, 0x1400ffb0 }, - { 0x0c000454, 0x1400ffb0 }, - { 0x0c000455, 0x1400ffb0 }, - { 0x0c000456, 0x1400ffb0 }, - { 0x0c000457, 0x1400ffb0 }, - { 0x0c000458, 0x1400ffb0 }, - { 0x0c000459, 0x1400ffb0 }, - { 0x0c00045a, 0x1400ffb0 }, - { 0x0c00045b, 0x1400ffb0 }, - { 0x0c00045c, 0x1400ffb0 }, - { 0x0c00045d, 0x1400ffb0 }, - { 0x0c00045e, 0x1400ffb0 }, - { 0x0c00045f, 0x1400ffb0 }, - { 0x0c000460, 0x24000001 }, - { 0x0c000461, 0x1400ffff }, - { 0x0c000462, 0x24000001 }, - { 0x0c000463, 0x1400ffff }, - { 0x0c000464, 0x24000001 }, - { 0x0c000465, 0x1400ffff }, - { 0x0c000466, 0x24000001 }, - { 0x0c000467, 0x1400ffff }, - { 0x0c000468, 0x24000001 }, - { 0x0c000469, 0x1400ffff }, - { 0x0c00046a, 0x24000001 }, - { 0x0c00046b, 0x1400ffff }, - { 0x0c00046c, 0x24000001 }, - { 0x0c00046d, 0x1400ffff }, - { 0x0c00046e, 0x24000001 }, - { 0x0c00046f, 0x1400ffff }, - { 0x0c000470, 0x24000001 }, - { 0x0c000471, 0x1400ffff }, - { 0x0c000472, 0x24000001 }, - { 0x0c000473, 0x1400ffff }, - { 0x0c000474, 0x24000001 }, - { 0x0c000475, 0x1400ffff }, - { 0x0c000476, 0x24000001 }, - { 0x0c000477, 0x1400ffff }, - { 0x0c000478, 0x24000001 }, - { 0x0c000479, 0x1400ffff }, - { 0x0c00047a, 0x24000001 }, - { 0x0c00047b, 0x1400ffff }, - { 0x0c00047c, 0x24000001 }, - { 0x0c00047d, 0x1400ffff }, - { 0x0c00047e, 0x24000001 }, - { 0x0c00047f, 0x1400ffff }, - { 0x0c000480, 0x24000001 }, - { 0x0c000481, 0x1400ffff }, - { 0x0c000482, 0x68000000 }, - { 0x0c800483, 0x30000003 }, - { 0x0c800488, 0x2c000001 }, - { 0x0c00048a, 0x24000001 }, - { 0x0c00048b, 0x1400ffff }, - { 0x0c00048c, 0x24000001 }, - { 0x0c00048d, 0x1400ffff }, - { 0x0c00048e, 0x24000001 }, - { 0x0c00048f, 0x1400ffff }, - { 0x0c000490, 0x24000001 }, - { 0x0c000491, 0x1400ffff }, - { 0x0c000492, 0x24000001 }, - { 0x0c000493, 0x1400ffff }, - { 0x0c000494, 0x24000001 }, - { 0x0c000495, 0x1400ffff }, - { 0x0c000496, 0x24000001 }, - { 0x0c000497, 0x1400ffff }, - { 0x0c000498, 0x24000001 }, - { 0x0c000499, 0x1400ffff }, - { 0x0c00049a, 0x24000001 }, - { 0x0c00049b, 0x1400ffff }, - { 0x0c00049c, 0x24000001 }, - { 0x0c00049d, 0x1400ffff }, - { 0x0c00049e, 0x24000001 }, - { 0x0c00049f, 0x1400ffff }, - { 0x0c0004a0, 0x24000001 }, - { 0x0c0004a1, 0x1400ffff }, - { 0x0c0004a2, 0x24000001 }, - { 0x0c0004a3, 0x1400ffff }, - { 0x0c0004a4, 0x24000001 }, - { 0x0c0004a5, 0x1400ffff }, - { 0x0c0004a6, 0x24000001 }, - { 0x0c0004a7, 0x1400ffff }, - { 0x0c0004a8, 0x24000001 }, - { 0x0c0004a9, 0x1400ffff }, - { 0x0c0004aa, 0x24000001 }, - { 0x0c0004ab, 0x1400ffff }, - { 0x0c0004ac, 0x24000001 }, - { 0x0c0004ad, 0x1400ffff }, - { 0x0c0004ae, 0x24000001 }, - { 0x0c0004af, 0x1400ffff }, - { 0x0c0004b0, 0x24000001 }, - { 0x0c0004b1, 0x1400ffff }, - { 0x0c0004b2, 0x24000001 }, - { 0x0c0004b3, 0x1400ffff }, - { 0x0c0004b4, 0x24000001 }, - { 0x0c0004b5, 0x1400ffff }, - { 0x0c0004b6, 0x24000001 }, - { 0x0c0004b7, 0x1400ffff }, - { 0x0c0004b8, 0x24000001 }, - { 0x0c0004b9, 0x1400ffff }, - { 0x0c0004ba, 0x24000001 }, - { 0x0c0004bb, 0x1400ffff }, - { 0x0c0004bc, 0x24000001 }, - { 0x0c0004bd, 0x1400ffff }, - { 0x0c0004be, 0x24000001 }, - { 0x0c0004bf, 0x1400ffff }, - { 0x0c0004c0, 0x24000000 }, - { 0x0c0004c1, 0x24000001 }, - { 0x0c0004c2, 0x1400ffff }, - { 0x0c0004c3, 0x24000001 }, - { 0x0c0004c4, 0x1400ffff }, - { 0x0c0004c5, 0x24000001 }, - { 0x0c0004c6, 0x1400ffff }, - { 0x0c0004c7, 0x24000001 }, - { 0x0c0004c8, 0x1400ffff }, - { 0x0c0004c9, 0x24000001 }, - { 0x0c0004ca, 0x1400ffff }, - { 0x0c0004cb, 0x24000001 }, - { 0x0c0004cc, 0x1400ffff }, - { 0x0c0004cd, 0x24000001 }, - { 0x0c0004ce, 0x1400ffff }, - { 0x0c0004d0, 0x24000001 }, - { 0x0c0004d1, 0x1400ffff }, - { 0x0c0004d2, 0x24000001 }, - { 0x0c0004d3, 0x1400ffff }, - { 0x0c0004d4, 0x24000001 }, - { 0x0c0004d5, 0x1400ffff }, - { 0x0c0004d6, 0x24000001 }, - { 0x0c0004d7, 0x1400ffff }, - { 0x0c0004d8, 0x24000001 }, - { 0x0c0004d9, 0x1400ffff }, - { 0x0c0004da, 0x24000001 }, - { 0x0c0004db, 0x1400ffff }, - { 0x0c0004dc, 0x24000001 }, - { 0x0c0004dd, 0x1400ffff }, - { 0x0c0004de, 0x24000001 }, - { 0x0c0004df, 0x1400ffff }, - { 0x0c0004e0, 0x24000001 }, - { 0x0c0004e1, 0x1400ffff }, - { 0x0c0004e2, 0x24000001 }, - { 0x0c0004e3, 0x1400ffff }, - { 0x0c0004e4, 0x24000001 }, - { 0x0c0004e5, 0x1400ffff }, - { 0x0c0004e6, 0x24000001 }, - { 0x0c0004e7, 0x1400ffff }, - { 0x0c0004e8, 0x24000001 }, - { 0x0c0004e9, 0x1400ffff }, - { 0x0c0004ea, 0x24000001 }, - { 0x0c0004eb, 0x1400ffff }, - { 0x0c0004ec, 0x24000001 }, - { 0x0c0004ed, 0x1400ffff }, - { 0x0c0004ee, 0x24000001 }, - { 0x0c0004ef, 0x1400ffff }, - { 0x0c0004f0, 0x24000001 }, - { 0x0c0004f1, 0x1400ffff }, - { 0x0c0004f2, 0x24000001 }, - { 0x0c0004f3, 0x1400ffff }, - { 0x0c0004f4, 0x24000001 }, - { 0x0c0004f5, 0x1400ffff }, - { 0x0c0004f6, 0x24000001 }, - { 0x0c0004f7, 0x1400ffff }, - { 0x0c0004f8, 0x24000001 }, - { 0x0c0004f9, 0x1400ffff }, - { 0x0c000500, 0x24000001 }, - { 0x0c000501, 0x1400ffff }, - { 0x0c000502, 0x24000001 }, - { 0x0c000503, 0x1400ffff }, - { 0x0c000504, 0x24000001 }, - { 0x0c000505, 0x1400ffff }, - { 0x0c000506, 0x24000001 }, - { 0x0c000507, 0x1400ffff }, - { 0x0c000508, 0x24000001 }, - { 0x0c000509, 0x1400ffff }, - { 0x0c00050a, 0x24000001 }, - { 0x0c00050b, 0x1400ffff }, - { 0x0c00050c, 0x24000001 }, - { 0x0c00050d, 0x1400ffff }, - { 0x0c00050e, 0x24000001 }, - { 0x0c00050f, 0x1400ffff }, - { 0x01000531, 0x24000030 }, - { 0x01000532, 0x24000030 }, - { 0x01000533, 0x24000030 }, - { 0x01000534, 0x24000030 }, - { 0x01000535, 0x24000030 }, - { 0x01000536, 0x24000030 }, - { 0x01000537, 0x24000030 }, - { 0x01000538, 0x24000030 }, - { 0x01000539, 0x24000030 }, - { 0x0100053a, 0x24000030 }, - { 0x0100053b, 0x24000030 }, - { 0x0100053c, 0x24000030 }, - { 0x0100053d, 0x24000030 }, - { 0x0100053e, 0x24000030 }, - { 0x0100053f, 0x24000030 }, - { 0x01000540, 0x24000030 }, - { 0x01000541, 0x24000030 }, - { 0x01000542, 0x24000030 }, - { 0x01000543, 0x24000030 }, - { 0x01000544, 0x24000030 }, - { 0x01000545, 0x24000030 }, - { 0x01000546, 0x24000030 }, - { 0x01000547, 0x24000030 }, - { 0x01000548, 0x24000030 }, - { 0x01000549, 0x24000030 }, - { 0x0100054a, 0x24000030 }, - { 0x0100054b, 0x24000030 }, - { 0x0100054c, 0x24000030 }, - { 0x0100054d, 0x24000030 }, - { 0x0100054e, 0x24000030 }, - { 0x0100054f, 0x24000030 }, - { 0x01000550, 0x24000030 }, - { 0x01000551, 0x24000030 }, - { 0x01000552, 0x24000030 }, - { 0x01000553, 0x24000030 }, - { 0x01000554, 0x24000030 }, - { 0x01000555, 0x24000030 }, - { 0x01000556, 0x24000030 }, - { 0x01000559, 0x18000000 }, - { 0x0180055a, 0x54000005 }, - { 0x01000561, 0x1400ffd0 }, - { 0x01000562, 0x1400ffd0 }, - { 0x01000563, 0x1400ffd0 }, - { 0x01000564, 0x1400ffd0 }, - { 0x01000565, 0x1400ffd0 }, - { 0x01000566, 0x1400ffd0 }, - { 0x01000567, 0x1400ffd0 }, - { 0x01000568, 0x1400ffd0 }, - { 0x01000569, 0x1400ffd0 }, - { 0x0100056a, 0x1400ffd0 }, - { 0x0100056b, 0x1400ffd0 }, - { 0x0100056c, 0x1400ffd0 }, - { 0x0100056d, 0x1400ffd0 }, - { 0x0100056e, 0x1400ffd0 }, - { 0x0100056f, 0x1400ffd0 }, - { 0x01000570, 0x1400ffd0 }, - { 0x01000571, 0x1400ffd0 }, - { 0x01000572, 0x1400ffd0 }, - { 0x01000573, 0x1400ffd0 }, - { 0x01000574, 0x1400ffd0 }, - { 0x01000575, 0x1400ffd0 }, - { 0x01000576, 0x1400ffd0 }, - { 0x01000577, 0x1400ffd0 }, - { 0x01000578, 0x1400ffd0 }, - { 0x01000579, 0x1400ffd0 }, - { 0x0100057a, 0x1400ffd0 }, - { 0x0100057b, 0x1400ffd0 }, - { 0x0100057c, 0x1400ffd0 }, - { 0x0100057d, 0x1400ffd0 }, - { 0x0100057e, 0x1400ffd0 }, - { 0x0100057f, 0x1400ffd0 }, - { 0x01000580, 0x1400ffd0 }, - { 0x01000581, 0x1400ffd0 }, - { 0x01000582, 0x1400ffd0 }, - { 0x01000583, 0x1400ffd0 }, - { 0x01000584, 0x1400ffd0 }, - { 0x01000585, 0x1400ffd0 }, - { 0x01000586, 0x1400ffd0 }, - { 0x01000587, 0x14000000 }, - { 0x09000589, 0x54000000 }, - { 0x0100058a, 0x44000000 }, - { 0x19800591, 0x30000028 }, - { 0x198005bb, 0x30000002 }, - { 0x190005be, 0x54000000 }, - { 0x190005bf, 0x30000000 }, - { 0x190005c0, 0x54000000 }, - { 0x198005c1, 0x30000001 }, - { 0x190005c3, 0x54000000 }, - { 0x198005c4, 0x30000001 }, - { 0x190005c6, 0x54000000 }, - { 0x190005c7, 0x30000000 }, - { 0x198005d0, 0x1c00001a }, - { 0x198005f0, 0x1c000002 }, - { 0x198005f3, 0x54000001 }, - { 0x09800600, 0x04000003 }, - { 0x0000060b, 0x5c000000 }, - { 0x0980060c, 0x54000001 }, - { 0x0080060e, 0x68000001 }, - { 0x00800610, 0x30000005 }, - { 0x0900061b, 0x54000000 }, - { 0x0080061e, 0x54000001 }, - { 0x00800621, 0x1c000019 }, - { 0x09000640, 0x18000000 }, - { 0x00800641, 0x1c000009 }, - { 0x1b80064b, 0x30000013 }, - { 0x09800660, 0x34000009 }, - { 0x0080066a, 0x54000003 }, - { 0x0080066e, 0x1c000001 }, - { 0x1b000670, 0x30000000 }, - { 0x00800671, 0x1c000062 }, - { 0x000006d4, 0x54000000 }, - { 0x000006d5, 0x1c000000 }, - { 0x008006d6, 0x30000006 }, - { 0x090006dd, 0x04000000 }, - { 0x000006de, 0x2c000000 }, - { 0x008006df, 0x30000005 }, - { 0x008006e5, 0x18000001 }, - { 0x008006e7, 0x30000001 }, - { 0x000006e9, 0x68000000 }, - { 0x008006ea, 0x30000003 }, - { 0x008006ee, 0x1c000001 }, - { 0x008006f0, 0x34000009 }, - { 0x008006fa, 0x1c000002 }, - { 0x008006fd, 0x68000001 }, - { 0x000006ff, 0x1c000000 }, - { 0x31800700, 0x5400000d }, - { 0x3100070f, 0x04000000 }, - { 0x31000710, 0x1c000000 }, - { 0x31000711, 0x30000000 }, - { 0x31800712, 0x1c00001d }, - { 0x31800730, 0x3000001a }, - { 0x3180074d, 0x1c000020 }, - { 0x37800780, 0x1c000025 }, - { 0x378007a6, 0x3000000a }, - { 0x370007b1, 0x1c000000 }, - { 0x0e800901, 0x30000001 }, - { 0x0e000903, 0x28000000 }, - { 0x0e800904, 0x1c000035 }, - { 0x0e00093c, 0x30000000 }, - { 0x0e00093d, 0x1c000000 }, - { 0x0e80093e, 0x28000002 }, - { 0x0e800941, 0x30000007 }, - { 0x0e800949, 0x28000003 }, - { 0x0e00094d, 0x30000000 }, - { 0x0e000950, 0x1c000000 }, - { 0x0e800951, 0x30000003 }, - { 0x0e800958, 0x1c000009 }, - { 0x0e800962, 0x30000001 }, - { 0x09800964, 0x54000001 }, - { 0x0e800966, 0x34000009 }, - { 0x09000970, 0x54000000 }, - { 0x0e00097d, 0x1c000000 }, - { 0x02000981, 0x30000000 }, - { 0x02800982, 0x28000001 }, - { 0x02800985, 0x1c000007 }, - { 0x0280098f, 0x1c000001 }, - { 0x02800993, 0x1c000015 }, - { 0x028009aa, 0x1c000006 }, - { 0x020009b2, 0x1c000000 }, - { 0x028009b6, 0x1c000003 }, - { 0x020009bc, 0x30000000 }, - { 0x020009bd, 0x1c000000 }, - { 0x028009be, 0x28000002 }, - { 0x028009c1, 0x30000003 }, - { 0x028009c7, 0x28000001 }, - { 0x028009cb, 0x28000001 }, - { 0x020009cd, 0x30000000 }, - { 0x020009ce, 0x1c000000 }, - { 0x020009d7, 0x28000000 }, - { 0x028009dc, 0x1c000001 }, - { 0x028009df, 0x1c000002 }, - { 0x028009e2, 0x30000001 }, - { 0x028009e6, 0x34000009 }, - { 0x028009f0, 0x1c000001 }, - { 0x028009f2, 0x5c000001 }, - { 0x028009f4, 0x3c000005 }, - { 0x020009fa, 0x68000000 }, - { 0x15800a01, 0x30000001 }, - { 0x15000a03, 0x28000000 }, - { 0x15800a05, 0x1c000005 }, - { 0x15800a0f, 0x1c000001 }, - { 0x15800a13, 0x1c000015 }, - { 0x15800a2a, 0x1c000006 }, - { 0x15800a32, 0x1c000001 }, - { 0x15800a35, 0x1c000001 }, - { 0x15800a38, 0x1c000001 }, - { 0x15000a3c, 0x30000000 }, - { 0x15800a3e, 0x28000002 }, - { 0x15800a41, 0x30000001 }, - { 0x15800a47, 0x30000001 }, - { 0x15800a4b, 0x30000002 }, - { 0x15800a59, 0x1c000003 }, - { 0x15000a5e, 0x1c000000 }, - { 0x15800a66, 0x34000009 }, - { 0x15800a70, 0x30000001 }, - { 0x15800a72, 0x1c000002 }, - { 0x14800a81, 0x30000001 }, - { 0x14000a83, 0x28000000 }, - { 0x14800a85, 0x1c000008 }, - { 0x14800a8f, 0x1c000002 }, - { 0x14800a93, 0x1c000015 }, - { 0x14800aaa, 0x1c000006 }, - { 0x14800ab2, 0x1c000001 }, - { 0x14800ab5, 0x1c000004 }, - { 0x14000abc, 0x30000000 }, - { 0x14000abd, 0x1c000000 }, - { 0x14800abe, 0x28000002 }, - { 0x14800ac1, 0x30000004 }, - { 0x14800ac7, 0x30000001 }, - { 0x14000ac9, 0x28000000 }, - { 0x14800acb, 0x28000001 }, - { 0x14000acd, 0x30000000 }, - { 0x14000ad0, 0x1c000000 }, - { 0x14800ae0, 0x1c000001 }, - { 0x14800ae2, 0x30000001 }, - { 0x14800ae6, 0x34000009 }, - { 0x14000af1, 0x5c000000 }, - { 0x2b000b01, 0x30000000 }, - { 0x2b800b02, 0x28000001 }, - { 0x2b800b05, 0x1c000007 }, - { 0x2b800b0f, 0x1c000001 }, - { 0x2b800b13, 0x1c000015 }, - { 0x2b800b2a, 0x1c000006 }, - { 0x2b800b32, 0x1c000001 }, - { 0x2b800b35, 0x1c000004 }, - { 0x2b000b3c, 0x30000000 }, - { 0x2b000b3d, 0x1c000000 }, - { 0x2b000b3e, 0x28000000 }, - { 0x2b000b3f, 0x30000000 }, - { 0x2b000b40, 0x28000000 }, - { 0x2b800b41, 0x30000002 }, - { 0x2b800b47, 0x28000001 }, - { 0x2b800b4b, 0x28000001 }, - { 0x2b000b4d, 0x30000000 }, - { 0x2b000b56, 0x30000000 }, - { 0x2b000b57, 0x28000000 }, - { 0x2b800b5c, 0x1c000001 }, - { 0x2b800b5f, 0x1c000002 }, - { 0x2b800b66, 0x34000009 }, - { 0x2b000b70, 0x68000000 }, - { 0x2b000b71, 0x1c000000 }, - { 0x35000b82, 0x30000000 }, - { 0x35000b83, 0x1c000000 }, - { 0x35800b85, 0x1c000005 }, - { 0x35800b8e, 0x1c000002 }, - { 0x35800b92, 0x1c000003 }, - { 0x35800b99, 0x1c000001 }, - { 0x35000b9c, 0x1c000000 }, - { 0x35800b9e, 0x1c000001 }, - { 0x35800ba3, 0x1c000001 }, - { 0x35800ba8, 0x1c000002 }, - { 0x35800bae, 0x1c00000b }, - { 0x35800bbe, 0x28000001 }, - { 0x35000bc0, 0x30000000 }, - { 0x35800bc1, 0x28000001 }, - { 0x35800bc6, 0x28000002 }, - { 0x35800bca, 0x28000002 }, - { 0x35000bcd, 0x30000000 }, - { 0x35000bd7, 0x28000000 }, - { 0x35800be6, 0x34000009 }, - { 0x35800bf0, 0x3c000002 }, - { 0x35800bf3, 0x68000005 }, - { 0x35000bf9, 0x5c000000 }, - { 0x35000bfa, 0x68000000 }, - { 0x36800c01, 0x28000002 }, - { 0x36800c05, 0x1c000007 }, - { 0x36800c0e, 0x1c000002 }, - { 0x36800c12, 0x1c000016 }, - { 0x36800c2a, 0x1c000009 }, - { 0x36800c35, 0x1c000004 }, - { 0x36800c3e, 0x30000002 }, - { 0x36800c41, 0x28000003 }, - { 0x36800c46, 0x30000002 }, - { 0x36800c4a, 0x30000003 }, - { 0x36800c55, 0x30000001 }, - { 0x36800c60, 0x1c000001 }, - { 0x36800c66, 0x34000009 }, - { 0x1c800c82, 0x28000001 }, - { 0x1c800c85, 0x1c000007 }, - { 0x1c800c8e, 0x1c000002 }, - { 0x1c800c92, 0x1c000016 }, - { 0x1c800caa, 0x1c000009 }, - { 0x1c800cb5, 0x1c000004 }, - { 0x1c000cbc, 0x30000000 }, - { 0x1c000cbd, 0x1c000000 }, - { 0x1c000cbe, 0x28000000 }, - { 0x1c000cbf, 0x30000000 }, - { 0x1c800cc0, 0x28000004 }, - { 0x1c000cc6, 0x30000000 }, - { 0x1c800cc7, 0x28000001 }, - { 0x1c800cca, 0x28000001 }, - { 0x1c800ccc, 0x30000001 }, - { 0x1c800cd5, 0x28000001 }, - { 0x1c000cde, 0x1c000000 }, - { 0x1c800ce0, 0x1c000001 }, - { 0x1c800ce6, 0x34000009 }, - { 0x24800d02, 0x28000001 }, - { 0x24800d05, 0x1c000007 }, - { 0x24800d0e, 0x1c000002 }, - { 0x24800d12, 0x1c000016 }, - { 0x24800d2a, 0x1c00000f }, - { 0x24800d3e, 0x28000002 }, - { 0x24800d41, 0x30000002 }, - { 0x24800d46, 0x28000002 }, - { 0x24800d4a, 0x28000002 }, - { 0x24000d4d, 0x30000000 }, - { 0x24000d57, 0x28000000 }, - { 0x24800d60, 0x1c000001 }, - { 0x24800d66, 0x34000009 }, - { 0x2f800d82, 0x28000001 }, - { 0x2f800d85, 0x1c000011 }, - { 0x2f800d9a, 0x1c000017 }, - { 0x2f800db3, 0x1c000008 }, - { 0x2f000dbd, 0x1c000000 }, - { 0x2f800dc0, 0x1c000006 }, - { 0x2f000dca, 0x30000000 }, - { 0x2f800dcf, 0x28000002 }, - { 0x2f800dd2, 0x30000002 }, - { 0x2f000dd6, 0x30000000 }, - { 0x2f800dd8, 0x28000007 }, - { 0x2f800df2, 0x28000001 }, - { 0x2f000df4, 0x54000000 }, - { 0x38800e01, 0x1c00002f }, - { 0x38000e31, 0x30000000 }, - { 0x38800e32, 0x1c000001 }, - { 0x38800e34, 0x30000006 }, - { 0x09000e3f, 0x5c000000 }, - { 0x38800e40, 0x1c000005 }, - { 0x38000e46, 0x18000000 }, - { 0x38800e47, 0x30000007 }, - { 0x38000e4f, 0x54000000 }, - { 0x38800e50, 0x34000009 }, - { 0x38800e5a, 0x54000001 }, - { 0x20800e81, 0x1c000001 }, - { 0x20000e84, 0x1c000000 }, - { 0x20800e87, 0x1c000001 }, - { 0x20000e8a, 0x1c000000 }, - { 0x20000e8d, 0x1c000000 }, - { 0x20800e94, 0x1c000003 }, - { 0x20800e99, 0x1c000006 }, - { 0x20800ea1, 0x1c000002 }, - { 0x20000ea5, 0x1c000000 }, - { 0x20000ea7, 0x1c000000 }, - { 0x20800eaa, 0x1c000001 }, - { 0x20800ead, 0x1c000003 }, - { 0x20000eb1, 0x30000000 }, - { 0x20800eb2, 0x1c000001 }, - { 0x20800eb4, 0x30000005 }, - { 0x20800ebb, 0x30000001 }, - { 0x20000ebd, 0x1c000000 }, - { 0x20800ec0, 0x1c000004 }, - { 0x20000ec6, 0x18000000 }, - { 0x20800ec8, 0x30000005 }, - { 0x20800ed0, 0x34000009 }, - { 0x20800edc, 0x1c000001 }, - { 0x39000f00, 0x1c000000 }, - { 0x39800f01, 0x68000002 }, - { 0x39800f04, 0x5400000e }, - { 0x39800f13, 0x68000004 }, - { 0x39800f18, 0x30000001 }, - { 0x39800f1a, 0x68000005 }, - { 0x39800f20, 0x34000009 }, - { 0x39800f2a, 0x3c000009 }, - { 0x39000f34, 0x68000000 }, - { 0x39000f35, 0x30000000 }, - { 0x39000f36, 0x68000000 }, - { 0x39000f37, 0x30000000 }, - { 0x39000f38, 0x68000000 }, - { 0x39000f39, 0x30000000 }, - { 0x39000f3a, 0x58000000 }, - { 0x39000f3b, 0x48000000 }, - { 0x39000f3c, 0x58000000 }, - { 0x39000f3d, 0x48000000 }, - { 0x39800f3e, 0x28000001 }, - { 0x39800f40, 0x1c000007 }, - { 0x39800f49, 0x1c000021 }, - { 0x39800f71, 0x3000000d }, - { 0x39000f7f, 0x28000000 }, - { 0x39800f80, 0x30000004 }, - { 0x39000f85, 0x54000000 }, - { 0x39800f86, 0x30000001 }, - { 0x39800f88, 0x1c000003 }, - { 0x39800f90, 0x30000007 }, - { 0x39800f99, 0x30000023 }, - { 0x39800fbe, 0x68000007 }, - { 0x39000fc6, 0x30000000 }, - { 0x39800fc7, 0x68000005 }, - { 0x39000fcf, 0x68000000 }, - { 0x39800fd0, 0x54000001 }, - { 0x26801000, 0x1c000021 }, - { 0x26801023, 0x1c000004 }, - { 0x26801029, 0x1c000001 }, - { 0x2600102c, 0x28000000 }, - { 0x2680102d, 0x30000003 }, - { 0x26001031, 0x28000000 }, - { 0x26001032, 0x30000000 }, - { 0x26801036, 0x30000001 }, - { 0x26001038, 0x28000000 }, - { 0x26001039, 0x30000000 }, - { 0x26801040, 0x34000009 }, - { 0x2680104a, 0x54000005 }, - { 0x26801050, 0x1c000005 }, - { 0x26801056, 0x28000001 }, - { 0x26801058, 0x30000001 }, - { 0x100010a0, 0x24001c60 }, - { 0x100010a1, 0x24001c60 }, - { 0x100010a2, 0x24001c60 }, - { 0x100010a3, 0x24001c60 }, - { 0x100010a4, 0x24001c60 }, - { 0x100010a5, 0x24001c60 }, - { 0x100010a6, 0x24001c60 }, - { 0x100010a7, 0x24001c60 }, - { 0x100010a8, 0x24001c60 }, - { 0x100010a9, 0x24001c60 }, - { 0x100010aa, 0x24001c60 }, - { 0x100010ab, 0x24001c60 }, - { 0x100010ac, 0x24001c60 }, - { 0x100010ad, 0x24001c60 }, - { 0x100010ae, 0x24001c60 }, - { 0x100010af, 0x24001c60 }, - { 0x100010b0, 0x24001c60 }, - { 0x100010b1, 0x24001c60 }, - { 0x100010b2, 0x24001c60 }, - { 0x100010b3, 0x24001c60 }, - { 0x100010b4, 0x24001c60 }, - { 0x100010b5, 0x24001c60 }, - { 0x100010b6, 0x24001c60 }, - { 0x100010b7, 0x24001c60 }, - { 0x100010b8, 0x24001c60 }, - { 0x100010b9, 0x24001c60 }, - { 0x100010ba, 0x24001c60 }, - { 0x100010bb, 0x24001c60 }, - { 0x100010bc, 0x24001c60 }, - { 0x100010bd, 0x24001c60 }, - { 0x100010be, 0x24001c60 }, - { 0x100010bf, 0x24001c60 }, - { 0x100010c0, 0x24001c60 }, - { 0x100010c1, 0x24001c60 }, - { 0x100010c2, 0x24001c60 }, - { 0x100010c3, 0x24001c60 }, - { 0x100010c4, 0x24001c60 }, - { 0x100010c5, 0x24001c60 }, - { 0x108010d0, 0x1c00002a }, - { 0x090010fb, 0x54000000 }, - { 0x100010fc, 0x18000000 }, - { 0x17801100, 0x1c000059 }, - { 0x1780115f, 0x1c000043 }, - { 0x178011a8, 0x1c000051 }, - { 0x0f801200, 0x1c000048 }, - { 0x0f80124a, 0x1c000003 }, - { 0x0f801250, 0x1c000006 }, - { 0x0f001258, 0x1c000000 }, - { 0x0f80125a, 0x1c000003 }, - { 0x0f801260, 0x1c000028 }, - { 0x0f80128a, 0x1c000003 }, - { 0x0f801290, 0x1c000020 }, - { 0x0f8012b2, 0x1c000003 }, - { 0x0f8012b8, 0x1c000006 }, - { 0x0f0012c0, 0x1c000000 }, - { 0x0f8012c2, 0x1c000003 }, - { 0x0f8012c8, 0x1c00000e }, - { 0x0f8012d8, 0x1c000038 }, - { 0x0f801312, 0x1c000003 }, - { 0x0f801318, 0x1c000042 }, - { 0x0f00135f, 0x30000000 }, - { 0x0f001360, 0x68000000 }, - { 0x0f801361, 0x54000007 }, - { 0x0f801369, 0x3c000013 }, - { 0x0f801380, 0x1c00000f }, - { 0x0f801390, 0x68000009 }, - { 0x088013a0, 0x1c000054 }, - { 0x07801401, 0x1c00026b }, - { 0x0780166d, 0x54000001 }, - { 0x0780166f, 0x1c000007 }, - { 0x28001680, 0x74000000 }, - { 0x28801681, 0x1c000019 }, - { 0x2800169b, 0x58000000 }, - { 0x2800169c, 0x48000000 }, - { 0x2d8016a0, 0x1c00004a }, - { 0x098016eb, 0x54000002 }, - { 0x2d8016ee, 0x38000002 }, - { 0x32801700, 0x1c00000c }, - { 0x3280170e, 0x1c000003 }, - { 0x32801712, 0x30000002 }, - { 0x18801720, 0x1c000011 }, - { 0x18801732, 0x30000002 }, - { 0x09801735, 0x54000001 }, - { 0x06801740, 0x1c000011 }, - { 0x06801752, 0x30000001 }, - { 0x33801760, 0x1c00000c }, - { 0x3380176e, 0x1c000002 }, - { 0x33801772, 0x30000001 }, - { 0x1f801780, 0x1c000033 }, - { 0x1f8017b4, 0x04000001 }, - { 0x1f0017b6, 0x28000000 }, - { 0x1f8017b7, 0x30000006 }, - { 0x1f8017be, 0x28000007 }, - { 0x1f0017c6, 0x30000000 }, - { 0x1f8017c7, 0x28000001 }, - { 0x1f8017c9, 0x3000000a }, - { 0x1f8017d4, 0x54000002 }, - { 0x1f0017d7, 0x18000000 }, - { 0x1f8017d8, 0x54000002 }, - { 0x1f0017db, 0x5c000000 }, - { 0x1f0017dc, 0x1c000000 }, - { 0x1f0017dd, 0x30000000 }, - { 0x1f8017e0, 0x34000009 }, - { 0x1f8017f0, 0x3c000009 }, - { 0x25801800, 0x54000005 }, - { 0x25001806, 0x44000000 }, - { 0x25801807, 0x54000003 }, - { 0x2580180b, 0x30000002 }, - { 0x2500180e, 0x74000000 }, - { 0x25801810, 0x34000009 }, - { 0x25801820, 0x1c000022 }, - { 0x25001843, 0x18000000 }, - { 0x25801844, 0x1c000033 }, - { 0x25801880, 0x1c000028 }, - { 0x250018a9, 0x30000000 }, - { 0x22801900, 0x1c00001c }, - { 0x22801920, 0x30000002 }, - { 0x22801923, 0x28000003 }, - { 0x22801927, 0x30000001 }, - { 0x22801929, 0x28000002 }, - { 0x22801930, 0x28000001 }, - { 0x22001932, 0x30000000 }, - { 0x22801933, 0x28000005 }, - { 0x22801939, 0x30000002 }, - { 0x22001940, 0x68000000 }, - { 0x22801944, 0x54000001 }, - { 0x22801946, 0x34000009 }, - { 0x34801950, 0x1c00001d }, - { 0x34801970, 0x1c000004 }, - { 0x27801980, 0x1c000029 }, - { 0x278019b0, 0x28000010 }, - { 0x278019c1, 0x1c000006 }, - { 0x278019c8, 0x28000001 }, - { 0x278019d0, 0x34000009 }, - { 0x278019de, 0x54000001 }, - { 0x1f8019e0, 0x6800001f }, - { 0x05801a00, 0x1c000016 }, - { 0x05801a17, 0x30000001 }, - { 0x05801a19, 0x28000002 }, - { 0x05801a1e, 0x54000001 }, - { 0x21801d00, 0x1400002b }, - { 0x21801d2c, 0x18000035 }, - { 0x21801d62, 0x14000015 }, - { 0x0c001d78, 0x18000000 }, - { 0x21801d79, 0x14000021 }, - { 0x21801d9b, 0x18000024 }, - { 0x1b801dc0, 0x30000003 }, - { 0x21001e00, 0x24000001 }, - { 0x21001e01, 0x1400ffff }, - { 0x21001e02, 0x24000001 }, - { 0x21001e03, 0x1400ffff }, - { 0x21001e04, 0x24000001 }, - { 0x21001e05, 0x1400ffff }, - { 0x21001e06, 0x24000001 }, - { 0x21001e07, 0x1400ffff }, - { 0x21001e08, 0x24000001 }, - { 0x21001e09, 0x1400ffff }, - { 0x21001e0a, 0x24000001 }, - { 0x21001e0b, 0x1400ffff }, - { 0x21001e0c, 0x24000001 }, - { 0x21001e0d, 0x1400ffff }, - { 0x21001e0e, 0x24000001 }, - { 0x21001e0f, 0x1400ffff }, - { 0x21001e10, 0x24000001 }, - { 0x21001e11, 0x1400ffff }, - { 0x21001e12, 0x24000001 }, - { 0x21001e13, 0x1400ffff }, - { 0x21001e14, 0x24000001 }, - { 0x21001e15, 0x1400ffff }, - { 0x21001e16, 0x24000001 }, - { 0x21001e17, 0x1400ffff }, - { 0x21001e18, 0x24000001 }, - { 0x21001e19, 0x1400ffff }, - { 0x21001e1a, 0x24000001 }, - { 0x21001e1b, 0x1400ffff }, - { 0x21001e1c, 0x24000001 }, - { 0x21001e1d, 0x1400ffff }, - { 0x21001e1e, 0x24000001 }, - { 0x21001e1f, 0x1400ffff }, - { 0x21001e20, 0x24000001 }, - { 0x21001e21, 0x1400ffff }, - { 0x21001e22, 0x24000001 }, - { 0x21001e23, 0x1400ffff }, - { 0x21001e24, 0x24000001 }, - { 0x21001e25, 0x1400ffff }, - { 0x21001e26, 0x24000001 }, - { 0x21001e27, 0x1400ffff }, - { 0x21001e28, 0x24000001 }, - { 0x21001e29, 0x1400ffff }, - { 0x21001e2a, 0x24000001 }, - { 0x21001e2b, 0x1400ffff }, - { 0x21001e2c, 0x24000001 }, - { 0x21001e2d, 0x1400ffff }, - { 0x21001e2e, 0x24000001 }, - { 0x21001e2f, 0x1400ffff }, - { 0x21001e30, 0x24000001 }, - { 0x21001e31, 0x1400ffff }, - { 0x21001e32, 0x24000001 }, - { 0x21001e33, 0x1400ffff }, - { 0x21001e34, 0x24000001 }, - { 0x21001e35, 0x1400ffff }, - { 0x21001e36, 0x24000001 }, - { 0x21001e37, 0x1400ffff }, - { 0x21001e38, 0x24000001 }, - { 0x21001e39, 0x1400ffff }, - { 0x21001e3a, 0x24000001 }, - { 0x21001e3b, 0x1400ffff }, - { 0x21001e3c, 0x24000001 }, - { 0x21001e3d, 0x1400ffff }, - { 0x21001e3e, 0x24000001 }, - { 0x21001e3f, 0x1400ffff }, - { 0x21001e40, 0x24000001 }, - { 0x21001e41, 0x1400ffff }, - { 0x21001e42, 0x24000001 }, - { 0x21001e43, 0x1400ffff }, - { 0x21001e44, 0x24000001 }, - { 0x21001e45, 0x1400ffff }, - { 0x21001e46, 0x24000001 }, - { 0x21001e47, 0x1400ffff }, - { 0x21001e48, 0x24000001 }, - { 0x21001e49, 0x1400ffff }, - { 0x21001e4a, 0x24000001 }, - { 0x21001e4b, 0x1400ffff }, - { 0x21001e4c, 0x24000001 }, - { 0x21001e4d, 0x1400ffff }, - { 0x21001e4e, 0x24000001 }, - { 0x21001e4f, 0x1400ffff }, - { 0x21001e50, 0x24000001 }, - { 0x21001e51, 0x1400ffff }, - { 0x21001e52, 0x24000001 }, - { 0x21001e53, 0x1400ffff }, - { 0x21001e54, 0x24000001 }, - { 0x21001e55, 0x1400ffff }, - { 0x21001e56, 0x24000001 }, - { 0x21001e57, 0x1400ffff }, - { 0x21001e58, 0x24000001 }, - { 0x21001e59, 0x1400ffff }, - { 0x21001e5a, 0x24000001 }, - { 0x21001e5b, 0x1400ffff }, - { 0x21001e5c, 0x24000001 }, - { 0x21001e5d, 0x1400ffff }, - { 0x21001e5e, 0x24000001 }, - { 0x21001e5f, 0x1400ffff }, - { 0x21001e60, 0x24000001 }, - { 0x21001e61, 0x1400ffff }, - { 0x21001e62, 0x24000001 }, - { 0x21001e63, 0x1400ffff }, - { 0x21001e64, 0x24000001 }, - { 0x21001e65, 0x1400ffff }, - { 0x21001e66, 0x24000001 }, - { 0x21001e67, 0x1400ffff }, - { 0x21001e68, 0x24000001 }, - { 0x21001e69, 0x1400ffff }, - { 0x21001e6a, 0x24000001 }, - { 0x21001e6b, 0x1400ffff }, - { 0x21001e6c, 0x24000001 }, - { 0x21001e6d, 0x1400ffff }, - { 0x21001e6e, 0x24000001 }, - { 0x21001e6f, 0x1400ffff }, - { 0x21001e70, 0x24000001 }, - { 0x21001e71, 0x1400ffff }, - { 0x21001e72, 0x24000001 }, - { 0x21001e73, 0x1400ffff }, - { 0x21001e74, 0x24000001 }, - { 0x21001e75, 0x1400ffff }, - { 0x21001e76, 0x24000001 }, - { 0x21001e77, 0x1400ffff }, - { 0x21001e78, 0x24000001 }, - { 0x21001e79, 0x1400ffff }, - { 0x21001e7a, 0x24000001 }, - { 0x21001e7b, 0x1400ffff }, - { 0x21001e7c, 0x24000001 }, - { 0x21001e7d, 0x1400ffff }, - { 0x21001e7e, 0x24000001 }, - { 0x21001e7f, 0x1400ffff }, - { 0x21001e80, 0x24000001 }, - { 0x21001e81, 0x1400ffff }, - { 0x21001e82, 0x24000001 }, - { 0x21001e83, 0x1400ffff }, - { 0x21001e84, 0x24000001 }, - { 0x21001e85, 0x1400ffff }, - { 0x21001e86, 0x24000001 }, - { 0x21001e87, 0x1400ffff }, - { 0x21001e88, 0x24000001 }, - { 0x21001e89, 0x1400ffff }, - { 0x21001e8a, 0x24000001 }, - { 0x21001e8b, 0x1400ffff }, - { 0x21001e8c, 0x24000001 }, - { 0x21001e8d, 0x1400ffff }, - { 0x21001e8e, 0x24000001 }, - { 0x21001e8f, 0x1400ffff }, - { 0x21001e90, 0x24000001 }, - { 0x21001e91, 0x1400ffff }, - { 0x21001e92, 0x24000001 }, - { 0x21001e93, 0x1400ffff }, - { 0x21001e94, 0x24000001 }, - { 0x21001e95, 0x1400ffff }, - { 0x21801e96, 0x14000004 }, - { 0x21001e9b, 0x1400ffc5 }, - { 0x21001ea0, 0x24000001 }, - { 0x21001ea1, 0x1400ffff }, - { 0x21001ea2, 0x24000001 }, - { 0x21001ea3, 0x1400ffff }, - { 0x21001ea4, 0x24000001 }, - { 0x21001ea5, 0x1400ffff }, - { 0x21001ea6, 0x24000001 }, - { 0x21001ea7, 0x1400ffff }, - { 0x21001ea8, 0x24000001 }, - { 0x21001ea9, 0x1400ffff }, - { 0x21001eaa, 0x24000001 }, - { 0x21001eab, 0x1400ffff }, - { 0x21001eac, 0x24000001 }, - { 0x21001ead, 0x1400ffff }, - { 0x21001eae, 0x24000001 }, - { 0x21001eaf, 0x1400ffff }, - { 0x21001eb0, 0x24000001 }, - { 0x21001eb1, 0x1400ffff }, - { 0x21001eb2, 0x24000001 }, - { 0x21001eb3, 0x1400ffff }, - { 0x21001eb4, 0x24000001 }, - { 0x21001eb5, 0x1400ffff }, - { 0x21001eb6, 0x24000001 }, - { 0x21001eb7, 0x1400ffff }, - { 0x21001eb8, 0x24000001 }, - { 0x21001eb9, 0x1400ffff }, - { 0x21001eba, 0x24000001 }, - { 0x21001ebb, 0x1400ffff }, - { 0x21001ebc, 0x24000001 }, - { 0x21001ebd, 0x1400ffff }, - { 0x21001ebe, 0x24000001 }, - { 0x21001ebf, 0x1400ffff }, - { 0x21001ec0, 0x24000001 }, - { 0x21001ec1, 0x1400ffff }, - { 0x21001ec2, 0x24000001 }, - { 0x21001ec3, 0x1400ffff }, - { 0x21001ec4, 0x24000001 }, - { 0x21001ec5, 0x1400ffff }, - { 0x21001ec6, 0x24000001 }, - { 0x21001ec7, 0x1400ffff }, - { 0x21001ec8, 0x24000001 }, - { 0x21001ec9, 0x1400ffff }, - { 0x21001eca, 0x24000001 }, - { 0x21001ecb, 0x1400ffff }, - { 0x21001ecc, 0x24000001 }, - { 0x21001ecd, 0x1400ffff }, - { 0x21001ece, 0x24000001 }, - { 0x21001ecf, 0x1400ffff }, - { 0x21001ed0, 0x24000001 }, - { 0x21001ed1, 0x1400ffff }, - { 0x21001ed2, 0x24000001 }, - { 0x21001ed3, 0x1400ffff }, - { 0x21001ed4, 0x24000001 }, - { 0x21001ed5, 0x1400ffff }, - { 0x21001ed6, 0x24000001 }, - { 0x21001ed7, 0x1400ffff }, - { 0x21001ed8, 0x24000001 }, - { 0x21001ed9, 0x1400ffff }, - { 0x21001eda, 0x24000001 }, - { 0x21001edb, 0x1400ffff }, - { 0x21001edc, 0x24000001 }, - { 0x21001edd, 0x1400ffff }, - { 0x21001ede, 0x24000001 }, - { 0x21001edf, 0x1400ffff }, - { 0x21001ee0, 0x24000001 }, - { 0x21001ee1, 0x1400ffff }, - { 0x21001ee2, 0x24000001 }, - { 0x21001ee3, 0x1400ffff }, - { 0x21001ee4, 0x24000001 }, - { 0x21001ee5, 0x1400ffff }, - { 0x21001ee6, 0x24000001 }, - { 0x21001ee7, 0x1400ffff }, - { 0x21001ee8, 0x24000001 }, - { 0x21001ee9, 0x1400ffff }, - { 0x21001eea, 0x24000001 }, - { 0x21001eeb, 0x1400ffff }, - { 0x21001eec, 0x24000001 }, - { 0x21001eed, 0x1400ffff }, - { 0x21001eee, 0x24000001 }, - { 0x21001eef, 0x1400ffff }, - { 0x21001ef0, 0x24000001 }, - { 0x21001ef1, 0x1400ffff }, - { 0x21001ef2, 0x24000001 }, - { 0x21001ef3, 0x1400ffff }, - { 0x21001ef4, 0x24000001 }, - { 0x21001ef5, 0x1400ffff }, - { 0x21001ef6, 0x24000001 }, - { 0x21001ef7, 0x1400ffff }, - { 0x21001ef8, 0x24000001 }, - { 0x21001ef9, 0x1400ffff }, - { 0x13001f00, 0x14000008 }, - { 0x13001f01, 0x14000008 }, - { 0x13001f02, 0x14000008 }, - { 0x13001f03, 0x14000008 }, - { 0x13001f04, 0x14000008 }, - { 0x13001f05, 0x14000008 }, - { 0x13001f06, 0x14000008 }, - { 0x13001f07, 0x14000008 }, - { 0x13001f08, 0x2400fff8 }, - { 0x13001f09, 0x2400fff8 }, - { 0x13001f0a, 0x2400fff8 }, - { 0x13001f0b, 0x2400fff8 }, - { 0x13001f0c, 0x2400fff8 }, - { 0x13001f0d, 0x2400fff8 }, - { 0x13001f0e, 0x2400fff8 }, - { 0x13001f0f, 0x2400fff8 }, - { 0x13001f10, 0x14000008 }, - { 0x13001f11, 0x14000008 }, - { 0x13001f12, 0x14000008 }, - { 0x13001f13, 0x14000008 }, - { 0x13001f14, 0x14000008 }, - { 0x13001f15, 0x14000008 }, - { 0x13001f18, 0x2400fff8 }, - { 0x13001f19, 0x2400fff8 }, - { 0x13001f1a, 0x2400fff8 }, - { 0x13001f1b, 0x2400fff8 }, - { 0x13001f1c, 0x2400fff8 }, - { 0x13001f1d, 0x2400fff8 }, - { 0x13001f20, 0x14000008 }, - { 0x13001f21, 0x14000008 }, - { 0x13001f22, 0x14000008 }, - { 0x13001f23, 0x14000008 }, - { 0x13001f24, 0x14000008 }, - { 0x13001f25, 0x14000008 }, - { 0x13001f26, 0x14000008 }, - { 0x13001f27, 0x14000008 }, - { 0x13001f28, 0x2400fff8 }, - { 0x13001f29, 0x2400fff8 }, - { 0x13001f2a, 0x2400fff8 }, - { 0x13001f2b, 0x2400fff8 }, - { 0x13001f2c, 0x2400fff8 }, - { 0x13001f2d, 0x2400fff8 }, - { 0x13001f2e, 0x2400fff8 }, - { 0x13001f2f, 0x2400fff8 }, - { 0x13001f30, 0x14000008 }, - { 0x13001f31, 0x14000008 }, - { 0x13001f32, 0x14000008 }, - { 0x13001f33, 0x14000008 }, - { 0x13001f34, 0x14000008 }, - { 0x13001f35, 0x14000008 }, - { 0x13001f36, 0x14000008 }, - { 0x13001f37, 0x14000008 }, - { 0x13001f38, 0x2400fff8 }, - { 0x13001f39, 0x2400fff8 }, - { 0x13001f3a, 0x2400fff8 }, - { 0x13001f3b, 0x2400fff8 }, - { 0x13001f3c, 0x2400fff8 }, - { 0x13001f3d, 0x2400fff8 }, - { 0x13001f3e, 0x2400fff8 }, - { 0x13001f3f, 0x2400fff8 }, - { 0x13001f40, 0x14000008 }, - { 0x13001f41, 0x14000008 }, - { 0x13001f42, 0x14000008 }, - { 0x13001f43, 0x14000008 }, - { 0x13001f44, 0x14000008 }, - { 0x13001f45, 0x14000008 }, - { 0x13001f48, 0x2400fff8 }, - { 0x13001f49, 0x2400fff8 }, - { 0x13001f4a, 0x2400fff8 }, - { 0x13001f4b, 0x2400fff8 }, - { 0x13001f4c, 0x2400fff8 }, - { 0x13001f4d, 0x2400fff8 }, - { 0x13001f50, 0x14000000 }, - { 0x13001f51, 0x14000008 }, - { 0x13001f52, 0x14000000 }, - { 0x13001f53, 0x14000008 }, - { 0x13001f54, 0x14000000 }, - { 0x13001f55, 0x14000008 }, - { 0x13001f56, 0x14000000 }, - { 0x13001f57, 0x14000008 }, - { 0x13001f59, 0x2400fff8 }, - { 0x13001f5b, 0x2400fff8 }, - { 0x13001f5d, 0x2400fff8 }, - { 0x13001f5f, 0x2400fff8 }, - { 0x13001f60, 0x14000008 }, - { 0x13001f61, 0x14000008 }, - { 0x13001f62, 0x14000008 }, - { 0x13001f63, 0x14000008 }, - { 0x13001f64, 0x14000008 }, - { 0x13001f65, 0x14000008 }, - { 0x13001f66, 0x14000008 }, - { 0x13001f67, 0x14000008 }, - { 0x13001f68, 0x2400fff8 }, - { 0x13001f69, 0x2400fff8 }, - { 0x13001f6a, 0x2400fff8 }, - { 0x13001f6b, 0x2400fff8 }, - { 0x13001f6c, 0x2400fff8 }, - { 0x13001f6d, 0x2400fff8 }, - { 0x13001f6e, 0x2400fff8 }, - { 0x13001f6f, 0x2400fff8 }, - { 0x13001f70, 0x1400004a }, - { 0x13001f71, 0x1400004a }, - { 0x13001f72, 0x14000056 }, - { 0x13001f73, 0x14000056 }, - { 0x13001f74, 0x14000056 }, - { 0x13001f75, 0x14000056 }, - { 0x13001f76, 0x14000064 }, - { 0x13001f77, 0x14000064 }, - { 0x13001f78, 0x14000080 }, - { 0x13001f79, 0x14000080 }, - { 0x13001f7a, 0x14000070 }, - { 0x13001f7b, 0x14000070 }, - { 0x13001f7c, 0x1400007e }, - { 0x13001f7d, 0x1400007e }, - { 0x13001f80, 0x14000008 }, - { 0x13001f81, 0x14000008 }, - { 0x13001f82, 0x14000008 }, - { 0x13001f83, 0x14000008 }, - { 0x13001f84, 0x14000008 }, - { 0x13001f85, 0x14000008 }, - { 0x13001f86, 0x14000008 }, - { 0x13001f87, 0x14000008 }, - { 0x13001f88, 0x2000fff8 }, - { 0x13001f89, 0x2000fff8 }, - { 0x13001f8a, 0x2000fff8 }, - { 0x13001f8b, 0x2000fff8 }, - { 0x13001f8c, 0x2000fff8 }, - { 0x13001f8d, 0x2000fff8 }, - { 0x13001f8e, 0x2000fff8 }, - { 0x13001f8f, 0x2000fff8 }, - { 0x13001f90, 0x14000008 }, - { 0x13001f91, 0x14000008 }, - { 0x13001f92, 0x14000008 }, - { 0x13001f93, 0x14000008 }, - { 0x13001f94, 0x14000008 }, - { 0x13001f95, 0x14000008 }, - { 0x13001f96, 0x14000008 }, - { 0x13001f97, 0x14000008 }, - { 0x13001f98, 0x2000fff8 }, - { 0x13001f99, 0x2000fff8 }, - { 0x13001f9a, 0x2000fff8 }, - { 0x13001f9b, 0x2000fff8 }, - { 0x13001f9c, 0x2000fff8 }, - { 0x13001f9d, 0x2000fff8 }, - { 0x13001f9e, 0x2000fff8 }, - { 0x13001f9f, 0x2000fff8 }, - { 0x13001fa0, 0x14000008 }, - { 0x13001fa1, 0x14000008 }, - { 0x13001fa2, 0x14000008 }, - { 0x13001fa3, 0x14000008 }, - { 0x13001fa4, 0x14000008 }, - { 0x13001fa5, 0x14000008 }, - { 0x13001fa6, 0x14000008 }, - { 0x13001fa7, 0x14000008 }, - { 0x13001fa8, 0x2000fff8 }, - { 0x13001fa9, 0x2000fff8 }, - { 0x13001faa, 0x2000fff8 }, - { 0x13001fab, 0x2000fff8 }, - { 0x13001fac, 0x2000fff8 }, - { 0x13001fad, 0x2000fff8 }, - { 0x13001fae, 0x2000fff8 }, - { 0x13001faf, 0x2000fff8 }, - { 0x13001fb0, 0x14000008 }, - { 0x13001fb1, 0x14000008 }, - { 0x13001fb2, 0x14000000 }, - { 0x13001fb3, 0x14000009 }, - { 0x13001fb4, 0x14000000 }, - { 0x13801fb6, 0x14000001 }, - { 0x13001fb8, 0x2400fff8 }, - { 0x13001fb9, 0x2400fff8 }, - { 0x13001fba, 0x2400ffb6 }, - { 0x13001fbb, 0x2400ffb6 }, - { 0x13001fbc, 0x2000fff7 }, - { 0x13001fbd, 0x60000000 }, - { 0x13001fbe, 0x1400e3db }, - { 0x13801fbf, 0x60000002 }, - { 0x13001fc2, 0x14000000 }, - { 0x13001fc3, 0x14000009 }, - { 0x13001fc4, 0x14000000 }, - { 0x13801fc6, 0x14000001 }, - { 0x13001fc8, 0x2400ffaa }, - { 0x13001fc9, 0x2400ffaa }, - { 0x13001fca, 0x2400ffaa }, - { 0x13001fcb, 0x2400ffaa }, - { 0x13001fcc, 0x2000fff7 }, - { 0x13801fcd, 0x60000002 }, - { 0x13001fd0, 0x14000008 }, - { 0x13001fd1, 0x14000008 }, - { 0x13801fd2, 0x14000001 }, - { 0x13801fd6, 0x14000001 }, - { 0x13001fd8, 0x2400fff8 }, - { 0x13001fd9, 0x2400fff8 }, - { 0x13001fda, 0x2400ff9c }, - { 0x13001fdb, 0x2400ff9c }, - { 0x13801fdd, 0x60000002 }, - { 0x13001fe0, 0x14000008 }, - { 0x13001fe1, 0x14000008 }, - { 0x13801fe2, 0x14000002 }, - { 0x13001fe5, 0x14000007 }, - { 0x13801fe6, 0x14000001 }, - { 0x13001fe8, 0x2400fff8 }, - { 0x13001fe9, 0x2400fff8 }, - { 0x13001fea, 0x2400ff90 }, - { 0x13001feb, 0x2400ff90 }, - { 0x13001fec, 0x2400fff9 }, - { 0x13801fed, 0x60000002 }, - { 0x13001ff2, 0x14000000 }, - { 0x13001ff3, 0x14000009 }, - { 0x13001ff4, 0x14000000 }, - { 0x13801ff6, 0x14000001 }, - { 0x13001ff8, 0x2400ff80 }, - { 0x13001ff9, 0x2400ff80 }, - { 0x13001ffa, 0x2400ff82 }, - { 0x13001ffb, 0x2400ff82 }, - { 0x13001ffc, 0x2000fff7 }, - { 0x13801ffd, 0x60000001 }, - { 0x09802000, 0x7400000a }, - { 0x0980200b, 0x04000004 }, - { 0x09802010, 0x44000005 }, - { 0x09802016, 0x54000001 }, - { 0x09002018, 0x50000000 }, - { 0x09002019, 0x4c000000 }, - { 0x0900201a, 0x58000000 }, - { 0x0980201b, 0x50000001 }, - { 0x0900201d, 0x4c000000 }, - { 0x0900201e, 0x58000000 }, - { 0x0900201f, 0x50000000 }, - { 0x09802020, 0x54000007 }, - { 0x09002028, 0x6c000000 }, - { 0x09002029, 0x70000000 }, - { 0x0980202a, 0x04000004 }, - { 0x0900202f, 0x74000000 }, - { 0x09802030, 0x54000008 }, - { 0x09002039, 0x50000000 }, - { 0x0900203a, 0x4c000000 }, - { 0x0980203b, 0x54000003 }, - { 0x0980203f, 0x40000001 }, - { 0x09802041, 0x54000002 }, - { 0x09002044, 0x64000000 }, - { 0x09002045, 0x58000000 }, - { 0x09002046, 0x48000000 }, - { 0x09802047, 0x5400000a }, - { 0x09002052, 0x64000000 }, - { 0x09002053, 0x54000000 }, - { 0x09002054, 0x40000000 }, - { 0x09802055, 0x54000009 }, - { 0x0900205f, 0x74000000 }, - { 0x09802060, 0x04000003 }, - { 0x0980206a, 0x04000005 }, - { 0x09002070, 0x3c000000 }, - { 0x21002071, 0x14000000 }, - { 0x09802074, 0x3c000005 }, - { 0x0980207a, 0x64000002 }, - { 0x0900207d, 0x58000000 }, - { 0x0900207e, 0x48000000 }, - { 0x2100207f, 0x14000000 }, - { 0x09802080, 0x3c000009 }, - { 0x0980208a, 0x64000002 }, - { 0x0900208d, 0x58000000 }, - { 0x0900208e, 0x48000000 }, - { 0x21802090, 0x18000004 }, - { 0x098020a0, 0x5c000015 }, - { 0x1b8020d0, 0x3000000c }, - { 0x1b8020dd, 0x2c000003 }, - { 0x1b0020e1, 0x30000000 }, - { 0x1b8020e2, 0x2c000002 }, - { 0x1b8020e5, 0x30000006 }, - { 0x09802100, 0x68000001 }, - { 0x09002102, 0x24000000 }, - { 0x09802103, 0x68000003 }, - { 0x09002107, 0x24000000 }, - { 0x09802108, 0x68000001 }, - { 0x0900210a, 0x14000000 }, - { 0x0980210b, 0x24000002 }, - { 0x0980210e, 0x14000001 }, - { 0x09802110, 0x24000002 }, - { 0x09002113, 0x14000000 }, - { 0x09002114, 0x68000000 }, - { 0x09002115, 0x24000000 }, - { 0x09802116, 0x68000002 }, - { 0x09802119, 0x24000004 }, - { 0x0980211e, 0x68000005 }, - { 0x09002124, 0x24000000 }, - { 0x09002125, 0x68000000 }, - { 0x13002126, 0x2400e2a3 }, - { 0x09002127, 0x68000000 }, - { 0x09002128, 0x24000000 }, - { 0x09002129, 0x68000000 }, - { 0x2100212a, 0x2400df41 }, - { 0x2100212b, 0x2400dfba }, - { 0x0980212c, 0x24000001 }, - { 0x0900212e, 0x68000000 }, - { 0x0900212f, 0x14000000 }, - { 0x09802130, 0x24000001 }, - { 0x09002132, 0x68000000 }, - { 0x09002133, 0x24000000 }, - { 0x09002134, 0x14000000 }, - { 0x09802135, 0x1c000003 }, - { 0x09002139, 0x14000000 }, - { 0x0980213a, 0x68000001 }, - { 0x0980213c, 0x14000001 }, - { 0x0980213e, 0x24000001 }, - { 0x09802140, 0x64000004 }, - { 0x09002145, 0x24000000 }, - { 0x09802146, 0x14000003 }, - { 0x0900214a, 0x68000000 }, - { 0x0900214b, 0x64000000 }, - { 0x0900214c, 0x68000000 }, - { 0x09802153, 0x3c00000c }, - { 0x09002160, 0x38000010 }, - { 0x09002161, 0x38000010 }, - { 0x09002162, 0x38000010 }, - { 0x09002163, 0x38000010 }, - { 0x09002164, 0x38000010 }, - { 0x09002165, 0x38000010 }, - { 0x09002166, 0x38000010 }, - { 0x09002167, 0x38000010 }, - { 0x09002168, 0x38000010 }, - { 0x09002169, 0x38000010 }, - { 0x0900216a, 0x38000010 }, - { 0x0900216b, 0x38000010 }, - { 0x0900216c, 0x38000010 }, - { 0x0900216d, 0x38000010 }, - { 0x0900216e, 0x38000010 }, - { 0x0900216f, 0x38000010 }, - { 0x09002170, 0x3800fff0 }, - { 0x09002171, 0x3800fff0 }, - { 0x09002172, 0x3800fff0 }, - { 0x09002173, 0x3800fff0 }, - { 0x09002174, 0x3800fff0 }, - { 0x09002175, 0x3800fff0 }, - { 0x09002176, 0x3800fff0 }, - { 0x09002177, 0x3800fff0 }, - { 0x09002178, 0x3800fff0 }, - { 0x09002179, 0x3800fff0 }, - { 0x0900217a, 0x3800fff0 }, - { 0x0900217b, 0x3800fff0 }, - { 0x0900217c, 0x3800fff0 }, - { 0x0900217d, 0x3800fff0 }, - { 0x0900217e, 0x3800fff0 }, - { 0x0900217f, 0x3800fff0 }, - { 0x09802180, 0x38000003 }, - { 0x09802190, 0x64000004 }, - { 0x09802195, 0x68000004 }, - { 0x0980219a, 0x64000001 }, - { 0x0980219c, 0x68000003 }, - { 0x090021a0, 0x64000000 }, - { 0x098021a1, 0x68000001 }, - { 0x090021a3, 0x64000000 }, - { 0x098021a4, 0x68000001 }, - { 0x090021a6, 0x64000000 }, - { 0x098021a7, 0x68000006 }, - { 0x090021ae, 0x64000000 }, - { 0x098021af, 0x6800001e }, - { 0x098021ce, 0x64000001 }, - { 0x098021d0, 0x68000001 }, - { 0x090021d2, 0x64000000 }, - { 0x090021d3, 0x68000000 }, - { 0x090021d4, 0x64000000 }, - { 0x098021d5, 0x6800001e }, - { 0x098021f4, 0x6400010b }, - { 0x09802300, 0x68000007 }, - { 0x09802308, 0x64000003 }, - { 0x0980230c, 0x68000013 }, - { 0x09802320, 0x64000001 }, - { 0x09802322, 0x68000006 }, - { 0x09002329, 0x58000000 }, - { 0x0900232a, 0x48000000 }, - { 0x0980232b, 0x68000050 }, - { 0x0900237c, 0x64000000 }, - { 0x0980237d, 0x6800001d }, - { 0x0980239b, 0x64000018 }, - { 0x090023b4, 0x58000000 }, - { 0x090023b5, 0x48000000 }, - { 0x090023b6, 0x54000000 }, - { 0x098023b7, 0x68000024 }, - { 0x09802400, 0x68000026 }, - { 0x09802440, 0x6800000a }, - { 0x09802460, 0x3c00003b }, - { 0x0980249c, 0x68000019 }, - { 0x090024b6, 0x6800001a }, - { 0x090024b7, 0x6800001a }, - { 0x090024b8, 0x6800001a }, - { 0x090024b9, 0x6800001a }, - { 0x090024ba, 0x6800001a }, - { 0x090024bb, 0x6800001a }, - { 0x090024bc, 0x6800001a }, - { 0x090024bd, 0x6800001a }, - { 0x090024be, 0x6800001a }, - { 0x090024bf, 0x6800001a }, - { 0x090024c0, 0x6800001a }, - { 0x090024c1, 0x6800001a }, - { 0x090024c2, 0x6800001a }, - { 0x090024c3, 0x6800001a }, - { 0x090024c4, 0x6800001a }, - { 0x090024c5, 0x6800001a }, - { 0x090024c6, 0x6800001a }, - { 0x090024c7, 0x6800001a }, - { 0x090024c8, 0x6800001a }, - { 0x090024c9, 0x6800001a }, - { 0x090024ca, 0x6800001a }, - { 0x090024cb, 0x6800001a }, - { 0x090024cc, 0x6800001a }, - { 0x090024cd, 0x6800001a }, - { 0x090024ce, 0x6800001a }, - { 0x090024cf, 0x6800001a }, - { 0x090024d0, 0x6800ffe6 }, - { 0x090024d1, 0x6800ffe6 }, - { 0x090024d2, 0x6800ffe6 }, - { 0x090024d3, 0x6800ffe6 }, - { 0x090024d4, 0x6800ffe6 }, - { 0x090024d5, 0x6800ffe6 }, - { 0x090024d6, 0x6800ffe6 }, - { 0x090024d7, 0x6800ffe6 }, - { 0x090024d8, 0x6800ffe6 }, - { 0x090024d9, 0x6800ffe6 }, - { 0x090024da, 0x6800ffe6 }, - { 0x090024db, 0x6800ffe6 }, - { 0x090024dc, 0x6800ffe6 }, - { 0x090024dd, 0x6800ffe6 }, - { 0x090024de, 0x6800ffe6 }, - { 0x090024df, 0x6800ffe6 }, - { 0x090024e0, 0x6800ffe6 }, - { 0x090024e1, 0x6800ffe6 }, - { 0x090024e2, 0x6800ffe6 }, - { 0x090024e3, 0x6800ffe6 }, - { 0x090024e4, 0x6800ffe6 }, - { 0x090024e5, 0x6800ffe6 }, - { 0x090024e6, 0x6800ffe6 }, - { 0x090024e7, 0x6800ffe6 }, - { 0x090024e8, 0x6800ffe6 }, - { 0x090024e9, 0x6800ffe6 }, - { 0x098024ea, 0x3c000015 }, - { 0x09802500, 0x680000b6 }, - { 0x090025b7, 0x64000000 }, - { 0x098025b8, 0x68000008 }, - { 0x090025c1, 0x64000000 }, - { 0x098025c2, 0x68000035 }, - { 0x098025f8, 0x64000007 }, - { 0x09802600, 0x6800006e }, - { 0x0900266f, 0x64000000 }, - { 0x09802670, 0x6800002c }, - { 0x098026a0, 0x68000011 }, - { 0x09802701, 0x68000003 }, - { 0x09802706, 0x68000003 }, - { 0x0980270c, 0x6800001b }, - { 0x09802729, 0x68000022 }, - { 0x0900274d, 0x68000000 }, - { 0x0980274f, 0x68000003 }, - { 0x09002756, 0x68000000 }, - { 0x09802758, 0x68000006 }, - { 0x09802761, 0x68000006 }, - { 0x09002768, 0x58000000 }, - { 0x09002769, 0x48000000 }, - { 0x0900276a, 0x58000000 }, - { 0x0900276b, 0x48000000 }, - { 0x0900276c, 0x58000000 }, - { 0x0900276d, 0x48000000 }, - { 0x0900276e, 0x58000000 }, - { 0x0900276f, 0x48000000 }, - { 0x09002770, 0x58000000 }, - { 0x09002771, 0x48000000 }, - { 0x09002772, 0x58000000 }, - { 0x09002773, 0x48000000 }, - { 0x09002774, 0x58000000 }, - { 0x09002775, 0x48000000 }, - { 0x09802776, 0x3c00001d }, - { 0x09002794, 0x68000000 }, - { 0x09802798, 0x68000017 }, - { 0x098027b1, 0x6800000d }, - { 0x098027c0, 0x64000004 }, - { 0x090027c5, 0x58000000 }, - { 0x090027c6, 0x48000000 }, - { 0x098027d0, 0x64000015 }, - { 0x090027e6, 0x58000000 }, - { 0x090027e7, 0x48000000 }, - { 0x090027e8, 0x58000000 }, - { 0x090027e9, 0x48000000 }, - { 0x090027ea, 0x58000000 }, - { 0x090027eb, 0x48000000 }, - { 0x098027f0, 0x6400000f }, - { 0x04802800, 0x680000ff }, - { 0x09802900, 0x64000082 }, - { 0x09002983, 0x58000000 }, - { 0x09002984, 0x48000000 }, - { 0x09002985, 0x58000000 }, - { 0x09002986, 0x48000000 }, - { 0x09002987, 0x58000000 }, - { 0x09002988, 0x48000000 }, - { 0x09002989, 0x58000000 }, - { 0x0900298a, 0x48000000 }, - { 0x0900298b, 0x58000000 }, - { 0x0900298c, 0x48000000 }, - { 0x0900298d, 0x58000000 }, - { 0x0900298e, 0x48000000 }, - { 0x0900298f, 0x58000000 }, - { 0x09002990, 0x48000000 }, - { 0x09002991, 0x58000000 }, - { 0x09002992, 0x48000000 }, - { 0x09002993, 0x58000000 }, - { 0x09002994, 0x48000000 }, - { 0x09002995, 0x58000000 }, - { 0x09002996, 0x48000000 }, - { 0x09002997, 0x58000000 }, - { 0x09002998, 0x48000000 }, - { 0x09802999, 0x6400003e }, - { 0x090029d8, 0x58000000 }, - { 0x090029d9, 0x48000000 }, - { 0x090029da, 0x58000000 }, - { 0x090029db, 0x48000000 }, - { 0x098029dc, 0x6400001f }, - { 0x090029fc, 0x58000000 }, - { 0x090029fd, 0x48000000 }, - { 0x098029fe, 0x64000101 }, - { 0x09802b00, 0x68000013 }, - { 0x11002c00, 0x24000030 }, - { 0x11002c01, 0x24000030 }, - { 0x11002c02, 0x24000030 }, - { 0x11002c03, 0x24000030 }, - { 0x11002c04, 0x24000030 }, - { 0x11002c05, 0x24000030 }, - { 0x11002c06, 0x24000030 }, - { 0x11002c07, 0x24000030 }, - { 0x11002c08, 0x24000030 }, - { 0x11002c09, 0x24000030 }, - { 0x11002c0a, 0x24000030 }, - { 0x11002c0b, 0x24000030 }, - { 0x11002c0c, 0x24000030 }, - { 0x11002c0d, 0x24000030 }, - { 0x11002c0e, 0x24000030 }, - { 0x11002c0f, 0x24000030 }, - { 0x11002c10, 0x24000030 }, - { 0x11002c11, 0x24000030 }, - { 0x11002c12, 0x24000030 }, - { 0x11002c13, 0x24000030 }, - { 0x11002c14, 0x24000030 }, - { 0x11002c15, 0x24000030 }, - { 0x11002c16, 0x24000030 }, - { 0x11002c17, 0x24000030 }, - { 0x11002c18, 0x24000030 }, - { 0x11002c19, 0x24000030 }, - { 0x11002c1a, 0x24000030 }, - { 0x11002c1b, 0x24000030 }, - { 0x11002c1c, 0x24000030 }, - { 0x11002c1d, 0x24000030 }, - { 0x11002c1e, 0x24000030 }, - { 0x11002c1f, 0x24000030 }, - { 0x11002c20, 0x24000030 }, - { 0x11002c21, 0x24000030 }, - { 0x11002c22, 0x24000030 }, - { 0x11002c23, 0x24000030 }, - { 0x11002c24, 0x24000030 }, - { 0x11002c25, 0x24000030 }, - { 0x11002c26, 0x24000030 }, - { 0x11002c27, 0x24000030 }, - { 0x11002c28, 0x24000030 }, - { 0x11002c29, 0x24000030 }, - { 0x11002c2a, 0x24000030 }, - { 0x11002c2b, 0x24000030 }, - { 0x11002c2c, 0x24000030 }, - { 0x11002c2d, 0x24000030 }, - { 0x11002c2e, 0x24000030 }, - { 0x11002c30, 0x1400ffd0 }, - { 0x11002c31, 0x1400ffd0 }, - { 0x11002c32, 0x1400ffd0 }, - { 0x11002c33, 0x1400ffd0 }, - { 0x11002c34, 0x1400ffd0 }, - { 0x11002c35, 0x1400ffd0 }, - { 0x11002c36, 0x1400ffd0 }, - { 0x11002c37, 0x1400ffd0 }, - { 0x11002c38, 0x1400ffd0 }, - { 0x11002c39, 0x1400ffd0 }, - { 0x11002c3a, 0x1400ffd0 }, - { 0x11002c3b, 0x1400ffd0 }, - { 0x11002c3c, 0x1400ffd0 }, - { 0x11002c3d, 0x1400ffd0 }, - { 0x11002c3e, 0x1400ffd0 }, - { 0x11002c3f, 0x1400ffd0 }, - { 0x11002c40, 0x1400ffd0 }, - { 0x11002c41, 0x1400ffd0 }, - { 0x11002c42, 0x1400ffd0 }, - { 0x11002c43, 0x1400ffd0 }, - { 0x11002c44, 0x1400ffd0 }, - { 0x11002c45, 0x1400ffd0 }, - { 0x11002c46, 0x1400ffd0 }, - { 0x11002c47, 0x1400ffd0 }, - { 0x11002c48, 0x1400ffd0 }, - { 0x11002c49, 0x1400ffd0 }, - { 0x11002c4a, 0x1400ffd0 }, - { 0x11002c4b, 0x1400ffd0 }, - { 0x11002c4c, 0x1400ffd0 }, - { 0x11002c4d, 0x1400ffd0 }, - { 0x11002c4e, 0x1400ffd0 }, - { 0x11002c4f, 0x1400ffd0 }, - { 0x11002c50, 0x1400ffd0 }, - { 0x11002c51, 0x1400ffd0 }, - { 0x11002c52, 0x1400ffd0 }, - { 0x11002c53, 0x1400ffd0 }, - { 0x11002c54, 0x1400ffd0 }, - { 0x11002c55, 0x1400ffd0 }, - { 0x11002c56, 0x1400ffd0 }, - { 0x11002c57, 0x1400ffd0 }, - { 0x11002c58, 0x1400ffd0 }, - { 0x11002c59, 0x1400ffd0 }, - { 0x11002c5a, 0x1400ffd0 }, - { 0x11002c5b, 0x1400ffd0 }, - { 0x11002c5c, 0x1400ffd0 }, - { 0x11002c5d, 0x1400ffd0 }, - { 0x11002c5e, 0x1400ffd0 }, - { 0x0a002c80, 0x24000001 }, - { 0x0a002c81, 0x1400ffff }, - { 0x0a002c82, 0x24000001 }, - { 0x0a002c83, 0x1400ffff }, - { 0x0a002c84, 0x24000001 }, - { 0x0a002c85, 0x1400ffff }, - { 0x0a002c86, 0x24000001 }, - { 0x0a002c87, 0x1400ffff }, - { 0x0a002c88, 0x24000001 }, - { 0x0a002c89, 0x1400ffff }, - { 0x0a002c8a, 0x24000001 }, - { 0x0a002c8b, 0x1400ffff }, - { 0x0a002c8c, 0x24000001 }, - { 0x0a002c8d, 0x1400ffff }, - { 0x0a002c8e, 0x24000001 }, - { 0x0a002c8f, 0x1400ffff }, - { 0x0a002c90, 0x24000001 }, - { 0x0a002c91, 0x1400ffff }, - { 0x0a002c92, 0x24000001 }, - { 0x0a002c93, 0x1400ffff }, - { 0x0a002c94, 0x24000001 }, - { 0x0a002c95, 0x1400ffff }, - { 0x0a002c96, 0x24000001 }, - { 0x0a002c97, 0x1400ffff }, - { 0x0a002c98, 0x24000001 }, - { 0x0a002c99, 0x1400ffff }, - { 0x0a002c9a, 0x24000001 }, - { 0x0a002c9b, 0x1400ffff }, - { 0x0a002c9c, 0x24000001 }, - { 0x0a002c9d, 0x1400ffff }, - { 0x0a002c9e, 0x24000001 }, - { 0x0a002c9f, 0x1400ffff }, - { 0x0a002ca0, 0x24000001 }, - { 0x0a002ca1, 0x1400ffff }, - { 0x0a002ca2, 0x24000001 }, - { 0x0a002ca3, 0x1400ffff }, - { 0x0a002ca4, 0x24000001 }, - { 0x0a002ca5, 0x1400ffff }, - { 0x0a002ca6, 0x24000001 }, - { 0x0a002ca7, 0x1400ffff }, - { 0x0a002ca8, 0x24000001 }, - { 0x0a002ca9, 0x1400ffff }, - { 0x0a002caa, 0x24000001 }, - { 0x0a002cab, 0x1400ffff }, - { 0x0a002cac, 0x24000001 }, - { 0x0a002cad, 0x1400ffff }, - { 0x0a002cae, 0x24000001 }, - { 0x0a002caf, 0x1400ffff }, - { 0x0a002cb0, 0x24000001 }, - { 0x0a002cb1, 0x1400ffff }, - { 0x0a002cb2, 0x24000001 }, - { 0x0a002cb3, 0x1400ffff }, - { 0x0a002cb4, 0x24000001 }, - { 0x0a002cb5, 0x1400ffff }, - { 0x0a002cb6, 0x24000001 }, - { 0x0a002cb7, 0x1400ffff }, - { 0x0a002cb8, 0x24000001 }, - { 0x0a002cb9, 0x1400ffff }, - { 0x0a002cba, 0x24000001 }, - { 0x0a002cbb, 0x1400ffff }, - { 0x0a002cbc, 0x24000001 }, - { 0x0a002cbd, 0x1400ffff }, - { 0x0a002cbe, 0x24000001 }, - { 0x0a002cbf, 0x1400ffff }, - { 0x0a002cc0, 0x24000001 }, - { 0x0a002cc1, 0x1400ffff }, - { 0x0a002cc2, 0x24000001 }, - { 0x0a002cc3, 0x1400ffff }, - { 0x0a002cc4, 0x24000001 }, - { 0x0a002cc5, 0x1400ffff }, - { 0x0a002cc6, 0x24000001 }, - { 0x0a002cc7, 0x1400ffff }, - { 0x0a002cc8, 0x24000001 }, - { 0x0a002cc9, 0x1400ffff }, - { 0x0a002cca, 0x24000001 }, - { 0x0a002ccb, 0x1400ffff }, - { 0x0a002ccc, 0x24000001 }, - { 0x0a002ccd, 0x1400ffff }, - { 0x0a002cce, 0x24000001 }, - { 0x0a002ccf, 0x1400ffff }, - { 0x0a002cd0, 0x24000001 }, - { 0x0a002cd1, 0x1400ffff }, - { 0x0a002cd2, 0x24000001 }, - { 0x0a002cd3, 0x1400ffff }, - { 0x0a002cd4, 0x24000001 }, - { 0x0a002cd5, 0x1400ffff }, - { 0x0a002cd6, 0x24000001 }, - { 0x0a002cd7, 0x1400ffff }, - { 0x0a002cd8, 0x24000001 }, - { 0x0a002cd9, 0x1400ffff }, - { 0x0a002cda, 0x24000001 }, - { 0x0a002cdb, 0x1400ffff }, - { 0x0a002cdc, 0x24000001 }, - { 0x0a002cdd, 0x1400ffff }, - { 0x0a002cde, 0x24000001 }, - { 0x0a002cdf, 0x1400ffff }, - { 0x0a002ce0, 0x24000001 }, - { 0x0a002ce1, 0x1400ffff }, - { 0x0a002ce2, 0x24000001 }, - { 0x0a002ce3, 0x1400ffff }, - { 0x0a002ce4, 0x14000000 }, - { 0x0a802ce5, 0x68000005 }, - { 0x0a802cf9, 0x54000003 }, - { 0x0a002cfd, 0x3c000000 }, - { 0x0a802cfe, 0x54000001 }, - { 0x10002d00, 0x1400e3a0 }, - { 0x10002d01, 0x1400e3a0 }, - { 0x10002d02, 0x1400e3a0 }, - { 0x10002d03, 0x1400e3a0 }, - { 0x10002d04, 0x1400e3a0 }, - { 0x10002d05, 0x1400e3a0 }, - { 0x10002d06, 0x1400e3a0 }, - { 0x10002d07, 0x1400e3a0 }, - { 0x10002d08, 0x1400e3a0 }, - { 0x10002d09, 0x1400e3a0 }, - { 0x10002d0a, 0x1400e3a0 }, - { 0x10002d0b, 0x1400e3a0 }, - { 0x10002d0c, 0x1400e3a0 }, - { 0x10002d0d, 0x1400e3a0 }, - { 0x10002d0e, 0x1400e3a0 }, - { 0x10002d0f, 0x1400e3a0 }, - { 0x10002d10, 0x1400e3a0 }, - { 0x10002d11, 0x1400e3a0 }, - { 0x10002d12, 0x1400e3a0 }, - { 0x10002d13, 0x1400e3a0 }, - { 0x10002d14, 0x1400e3a0 }, - { 0x10002d15, 0x1400e3a0 }, - { 0x10002d16, 0x1400e3a0 }, - { 0x10002d17, 0x1400e3a0 }, - { 0x10002d18, 0x1400e3a0 }, - { 0x10002d19, 0x1400e3a0 }, - { 0x10002d1a, 0x1400e3a0 }, - { 0x10002d1b, 0x1400e3a0 }, - { 0x10002d1c, 0x1400e3a0 }, - { 0x10002d1d, 0x1400e3a0 }, - { 0x10002d1e, 0x1400e3a0 }, - { 0x10002d1f, 0x1400e3a0 }, - { 0x10002d20, 0x1400e3a0 }, - { 0x10002d21, 0x1400e3a0 }, - { 0x10002d22, 0x1400e3a0 }, - { 0x10002d23, 0x1400e3a0 }, - { 0x10002d24, 0x1400e3a0 }, - { 0x10002d25, 0x1400e3a0 }, - { 0x3a802d30, 0x1c000035 }, - { 0x3a002d6f, 0x18000000 }, - { 0x0f802d80, 0x1c000016 }, - { 0x0f802da0, 0x1c000006 }, - { 0x0f802da8, 0x1c000006 }, - { 0x0f802db0, 0x1c000006 }, - { 0x0f802db8, 0x1c000006 }, - { 0x0f802dc0, 0x1c000006 }, - { 0x0f802dc8, 0x1c000006 }, - { 0x0f802dd0, 0x1c000006 }, - { 0x0f802dd8, 0x1c000006 }, - { 0x09802e00, 0x54000001 }, - { 0x09002e02, 0x50000000 }, - { 0x09002e03, 0x4c000000 }, - { 0x09002e04, 0x50000000 }, - { 0x09002e05, 0x4c000000 }, - { 0x09802e06, 0x54000002 }, - { 0x09002e09, 0x50000000 }, - { 0x09002e0a, 0x4c000000 }, - { 0x09002e0b, 0x54000000 }, - { 0x09002e0c, 0x50000000 }, - { 0x09002e0d, 0x4c000000 }, - { 0x09802e0e, 0x54000008 }, - { 0x09002e17, 0x44000000 }, - { 0x09002e1c, 0x50000000 }, - { 0x09002e1d, 0x4c000000 }, - { 0x16802e80, 0x68000019 }, - { 0x16802e9b, 0x68000058 }, - { 0x16802f00, 0x680000d5 }, - { 0x09802ff0, 0x6800000b }, - { 0x09003000, 0x74000000 }, - { 0x09803001, 0x54000002 }, - { 0x09003004, 0x68000000 }, - { 0x16003005, 0x18000000 }, - { 0x09003006, 0x1c000000 }, - { 0x16003007, 0x38000000 }, - { 0x09003008, 0x58000000 }, - { 0x09003009, 0x48000000 }, - { 0x0900300a, 0x58000000 }, - { 0x0900300b, 0x48000000 }, - { 0x0900300c, 0x58000000 }, - { 0x0900300d, 0x48000000 }, - { 0x0900300e, 0x58000000 }, - { 0x0900300f, 0x48000000 }, - { 0x09003010, 0x58000000 }, - { 0x09003011, 0x48000000 }, - { 0x09803012, 0x68000001 }, - { 0x09003014, 0x58000000 }, - { 0x09003015, 0x48000000 }, - { 0x09003016, 0x58000000 }, - { 0x09003017, 0x48000000 }, - { 0x09003018, 0x58000000 }, - { 0x09003019, 0x48000000 }, - { 0x0900301a, 0x58000000 }, - { 0x0900301b, 0x48000000 }, - { 0x0900301c, 0x44000000 }, - { 0x0900301d, 0x58000000 }, - { 0x0980301e, 0x48000001 }, - { 0x09003020, 0x68000000 }, - { 0x16803021, 0x38000008 }, - { 0x1b80302a, 0x30000005 }, - { 0x09003030, 0x44000000 }, - { 0x09803031, 0x18000004 }, - { 0x09803036, 0x68000001 }, - { 0x16803038, 0x38000002 }, - { 0x1600303b, 0x18000000 }, - { 0x0900303c, 0x1c000000 }, - { 0x0900303d, 0x54000000 }, - { 0x0980303e, 0x68000001 }, - { 0x1a803041, 0x1c000055 }, - { 0x1b803099, 0x30000001 }, - { 0x0980309b, 0x60000001 }, - { 0x1a80309d, 0x18000001 }, - { 0x1a00309f, 0x1c000000 }, - { 0x090030a0, 0x44000000 }, - { 0x1d8030a1, 0x1c000059 }, - { 0x090030fb, 0x54000000 }, - { 0x098030fc, 0x18000002 }, - { 0x1d0030ff, 0x1c000000 }, - { 0x03803105, 0x1c000027 }, - { 0x17803131, 0x1c00005d }, - { 0x09803190, 0x68000001 }, - { 0x09803192, 0x3c000003 }, - { 0x09803196, 0x68000009 }, - { 0x038031a0, 0x1c000017 }, - { 0x098031c0, 0x6800000f }, - { 0x1d8031f0, 0x1c00000f }, - { 0x17803200, 0x6800001e }, - { 0x09803220, 0x3c000009 }, - { 0x0980322a, 0x68000019 }, - { 0x09003250, 0x68000000 }, - { 0x09803251, 0x3c00000e }, - { 0x17803260, 0x6800001f }, - { 0x09803280, 0x3c000009 }, - { 0x0980328a, 0x68000026 }, - { 0x098032b1, 0x3c00000e }, - { 0x098032c0, 0x6800003e }, - { 0x09803300, 0x680000ff }, - { 0x16803400, 0x1c0019b5 }, - { 0x09804dc0, 0x6800003f }, - { 0x16804e00, 0x1c0051bb }, - { 0x3c80a000, 0x1c000014 }, - { 0x3c00a015, 0x18000000 }, - { 0x3c80a016, 0x1c000476 }, - { 0x3c80a490, 0x68000036 }, - { 0x0980a700, 0x60000016 }, - { 0x3080a800, 0x1c000001 }, - { 0x3000a802, 0x28000000 }, - { 0x3080a803, 0x1c000002 }, - { 0x3000a806, 0x30000000 }, - { 0x3080a807, 0x1c000003 }, - { 0x3000a80b, 0x30000000 }, - { 0x3080a80c, 0x1c000016 }, - { 0x3080a823, 0x28000001 }, - { 0x3080a825, 0x30000001 }, - { 0x3000a827, 0x28000000 }, - { 0x3080a828, 0x68000003 }, - { 0x1780ac00, 0x1c002ba3 }, - { 0x0980d800, 0x1000037f }, - { 0x0980db80, 0x1000007f }, - { 0x0980dc00, 0x100003ff }, - { 0x0980e000, 0x0c0018ff }, - { 0x1680f900, 0x1c00012d }, - { 0x1680fa30, 0x1c00003a }, - { 0x1680fa70, 0x1c000069 }, - { 0x2180fb00, 0x14000006 }, - { 0x0180fb13, 0x14000004 }, - { 0x1900fb1d, 0x1c000000 }, - { 0x1900fb1e, 0x30000000 }, - { 0x1980fb1f, 0x1c000009 }, - { 0x1900fb29, 0x64000000 }, - { 0x1980fb2a, 0x1c00000c }, - { 0x1980fb38, 0x1c000004 }, - { 0x1900fb3e, 0x1c000000 }, - { 0x1980fb40, 0x1c000001 }, - { 0x1980fb43, 0x1c000001 }, - { 0x1980fb46, 0x1c00006b }, - { 0x0080fbd3, 0x1c00016a }, - { 0x0900fd3e, 0x58000000 }, - { 0x0900fd3f, 0x48000000 }, - { 0x0080fd50, 0x1c00003f }, - { 0x0080fd92, 0x1c000035 }, - { 0x0080fdf0, 0x1c00000b }, - { 0x0000fdfc, 0x5c000000 }, - { 0x0900fdfd, 0x68000000 }, - { 0x1b80fe00, 0x3000000f }, - { 0x0980fe10, 0x54000006 }, - { 0x0900fe17, 0x58000000 }, - { 0x0900fe18, 0x48000000 }, - { 0x0900fe19, 0x54000000 }, - { 0x1b80fe20, 0x30000003 }, - { 0x0900fe30, 0x54000000 }, - { 0x0980fe31, 0x44000001 }, - { 0x0980fe33, 0x40000001 }, - { 0x0900fe35, 0x58000000 }, - { 0x0900fe36, 0x48000000 }, - { 0x0900fe37, 0x58000000 }, - { 0x0900fe38, 0x48000000 }, - { 0x0900fe39, 0x58000000 }, - { 0x0900fe3a, 0x48000000 }, - { 0x0900fe3b, 0x58000000 }, - { 0x0900fe3c, 0x48000000 }, - { 0x0900fe3d, 0x58000000 }, - { 0x0900fe3e, 0x48000000 }, - { 0x0900fe3f, 0x58000000 }, - { 0x0900fe40, 0x48000000 }, - { 0x0900fe41, 0x58000000 }, - { 0x0900fe42, 0x48000000 }, - { 0x0900fe43, 0x58000000 }, - { 0x0900fe44, 0x48000000 }, - { 0x0980fe45, 0x54000001 }, - { 0x0900fe47, 0x58000000 }, - { 0x0900fe48, 0x48000000 }, - { 0x0980fe49, 0x54000003 }, - { 0x0980fe4d, 0x40000002 }, - { 0x0980fe50, 0x54000002 }, - { 0x0980fe54, 0x54000003 }, - { 0x0900fe58, 0x44000000 }, - { 0x0900fe59, 0x58000000 }, - { 0x0900fe5a, 0x48000000 }, - { 0x0900fe5b, 0x58000000 }, - { 0x0900fe5c, 0x48000000 }, - { 0x0900fe5d, 0x58000000 }, - { 0x0900fe5e, 0x48000000 }, - { 0x0980fe5f, 0x54000002 }, - { 0x0900fe62, 0x64000000 }, - { 0x0900fe63, 0x44000000 }, - { 0x0980fe64, 0x64000002 }, - { 0x0900fe68, 0x54000000 }, - { 0x0900fe69, 0x5c000000 }, - { 0x0980fe6a, 0x54000001 }, - { 0x0080fe70, 0x1c000004 }, - { 0x0080fe76, 0x1c000086 }, - { 0x0900feff, 0x04000000 }, - { 0x0980ff01, 0x54000002 }, - { 0x0900ff04, 0x5c000000 }, - { 0x0980ff05, 0x54000002 }, - { 0x0900ff08, 0x58000000 }, - { 0x0900ff09, 0x48000000 }, - { 0x0900ff0a, 0x54000000 }, - { 0x0900ff0b, 0x64000000 }, - { 0x0900ff0c, 0x54000000 }, - { 0x0900ff0d, 0x44000000 }, - { 0x0980ff0e, 0x54000001 }, - { 0x0980ff10, 0x34000009 }, - { 0x0980ff1a, 0x54000001 }, - { 0x0980ff1c, 0x64000002 }, - { 0x0980ff1f, 0x54000001 }, - { 0x2100ff21, 0x24000020 }, - { 0x2100ff22, 0x24000020 }, - { 0x2100ff23, 0x24000020 }, - { 0x2100ff24, 0x24000020 }, - { 0x2100ff25, 0x24000020 }, - { 0x2100ff26, 0x24000020 }, - { 0x2100ff27, 0x24000020 }, - { 0x2100ff28, 0x24000020 }, - { 0x2100ff29, 0x24000020 }, - { 0x2100ff2a, 0x24000020 }, - { 0x2100ff2b, 0x24000020 }, - { 0x2100ff2c, 0x24000020 }, - { 0x2100ff2d, 0x24000020 }, - { 0x2100ff2e, 0x24000020 }, - { 0x2100ff2f, 0x24000020 }, - { 0x2100ff30, 0x24000020 }, - { 0x2100ff31, 0x24000020 }, - { 0x2100ff32, 0x24000020 }, - { 0x2100ff33, 0x24000020 }, - { 0x2100ff34, 0x24000020 }, - { 0x2100ff35, 0x24000020 }, - { 0x2100ff36, 0x24000020 }, - { 0x2100ff37, 0x24000020 }, - { 0x2100ff38, 0x24000020 }, - { 0x2100ff39, 0x24000020 }, - { 0x2100ff3a, 0x24000020 }, - { 0x0900ff3b, 0x58000000 }, - { 0x0900ff3c, 0x54000000 }, - { 0x0900ff3d, 0x48000000 }, - { 0x0900ff3e, 0x60000000 }, - { 0x0900ff3f, 0x40000000 }, - { 0x0900ff40, 0x60000000 }, - { 0x2100ff41, 0x1400ffe0 }, - { 0x2100ff42, 0x1400ffe0 }, - { 0x2100ff43, 0x1400ffe0 }, - { 0x2100ff44, 0x1400ffe0 }, - { 0x2100ff45, 0x1400ffe0 }, - { 0x2100ff46, 0x1400ffe0 }, - { 0x2100ff47, 0x1400ffe0 }, - { 0x2100ff48, 0x1400ffe0 }, - { 0x2100ff49, 0x1400ffe0 }, - { 0x2100ff4a, 0x1400ffe0 }, - { 0x2100ff4b, 0x1400ffe0 }, - { 0x2100ff4c, 0x1400ffe0 }, - { 0x2100ff4d, 0x1400ffe0 }, - { 0x2100ff4e, 0x1400ffe0 }, - { 0x2100ff4f, 0x1400ffe0 }, - { 0x2100ff50, 0x1400ffe0 }, - { 0x2100ff51, 0x1400ffe0 }, - { 0x2100ff52, 0x1400ffe0 }, - { 0x2100ff53, 0x1400ffe0 }, - { 0x2100ff54, 0x1400ffe0 }, - { 0x2100ff55, 0x1400ffe0 }, - { 0x2100ff56, 0x1400ffe0 }, - { 0x2100ff57, 0x1400ffe0 }, - { 0x2100ff58, 0x1400ffe0 }, - { 0x2100ff59, 0x1400ffe0 }, - { 0x2100ff5a, 0x1400ffe0 }, - { 0x0900ff5b, 0x58000000 }, - { 0x0900ff5c, 0x64000000 }, - { 0x0900ff5d, 0x48000000 }, - { 0x0900ff5e, 0x64000000 }, - { 0x0900ff5f, 0x58000000 }, - { 0x0900ff60, 0x48000000 }, - { 0x0900ff61, 0x54000000 }, - { 0x0900ff62, 0x58000000 }, - { 0x0900ff63, 0x48000000 }, - { 0x0980ff64, 0x54000001 }, - { 0x1d80ff66, 0x1c000009 }, - { 0x0900ff70, 0x18000000 }, - { 0x1d80ff71, 0x1c00002c }, - { 0x0980ff9e, 0x18000001 }, - { 0x1780ffa0, 0x1c00001e }, - { 0x1780ffc2, 0x1c000005 }, - { 0x1780ffca, 0x1c000005 }, - { 0x1780ffd2, 0x1c000005 }, - { 0x1780ffda, 0x1c000002 }, - { 0x0980ffe0, 0x5c000001 }, - { 0x0900ffe2, 0x64000000 }, - { 0x0900ffe3, 0x60000000 }, - { 0x0900ffe4, 0x68000000 }, - { 0x0980ffe5, 0x5c000001 }, - { 0x0900ffe8, 0x68000000 }, - { 0x0980ffe9, 0x64000003 }, - { 0x0980ffed, 0x68000001 }, - { 0x0980fff9, 0x04000002 }, - { 0x0980fffc, 0x68000001 }, - { 0x23810000, 0x1c00000b }, - { 0x2381000d, 0x1c000019 }, - { 0x23810028, 0x1c000012 }, - { 0x2381003c, 0x1c000001 }, - { 0x2381003f, 0x1c00000e }, - { 0x23810050, 0x1c00000d }, - { 0x23810080, 0x1c00007a }, - { 0x09810100, 0x54000001 }, - { 0x09010102, 0x68000000 }, - { 0x09810107, 0x3c00002c }, - { 0x09810137, 0x68000008 }, - { 0x13810140, 0x38000034 }, - { 0x13810175, 0x3c000003 }, - { 0x13810179, 0x68000010 }, - { 0x1301018a, 0x3c000000 }, - { 0x29810300, 0x1c00001e }, - { 0x29810320, 0x3c000003 }, - { 0x12810330, 0x1c000019 }, - { 0x1201034a, 0x38000000 }, - { 0x3b810380, 0x1c00001d }, - { 0x3b01039f, 0x54000000 }, - { 0x2a8103a0, 0x1c000023 }, - { 0x2a8103c8, 0x1c000007 }, - { 0x2a0103d0, 0x68000000 }, - { 0x2a8103d1, 0x38000004 }, - { 0x0d010400, 0x24000028 }, - { 0x0d010401, 0x24000028 }, - { 0x0d010402, 0x24000028 }, - { 0x0d010403, 0x24000028 }, - { 0x0d010404, 0x24000028 }, - { 0x0d010405, 0x24000028 }, - { 0x0d010406, 0x24000028 }, - { 0x0d010407, 0x24000028 }, - { 0x0d010408, 0x24000028 }, - { 0x0d010409, 0x24000028 }, - { 0x0d01040a, 0x24000028 }, - { 0x0d01040b, 0x24000028 }, - { 0x0d01040c, 0x24000028 }, - { 0x0d01040d, 0x24000028 }, - { 0x0d01040e, 0x24000028 }, - { 0x0d01040f, 0x24000028 }, - { 0x0d010410, 0x24000028 }, - { 0x0d010411, 0x24000028 }, - { 0x0d010412, 0x24000028 }, - { 0x0d010413, 0x24000028 }, - { 0x0d010414, 0x24000028 }, - { 0x0d010415, 0x24000028 }, - { 0x0d010416, 0x24000028 }, - { 0x0d010417, 0x24000028 }, - { 0x0d010418, 0x24000028 }, - { 0x0d010419, 0x24000028 }, - { 0x0d01041a, 0x24000028 }, - { 0x0d01041b, 0x24000028 }, - { 0x0d01041c, 0x24000028 }, - { 0x0d01041d, 0x24000028 }, - { 0x0d01041e, 0x24000028 }, - { 0x0d01041f, 0x24000028 }, - { 0x0d010420, 0x24000028 }, - { 0x0d010421, 0x24000028 }, - { 0x0d010422, 0x24000028 }, - { 0x0d010423, 0x24000028 }, - { 0x0d010424, 0x24000028 }, - { 0x0d010425, 0x24000028 }, - { 0x0d010426, 0x24000028 }, - { 0x0d010427, 0x24000028 }, - { 0x0d010428, 0x1400ffd8 }, - { 0x0d010429, 0x1400ffd8 }, - { 0x0d01042a, 0x1400ffd8 }, - { 0x0d01042b, 0x1400ffd8 }, - { 0x0d01042c, 0x1400ffd8 }, - { 0x0d01042d, 0x1400ffd8 }, - { 0x0d01042e, 0x1400ffd8 }, - { 0x0d01042f, 0x1400ffd8 }, - { 0x0d010430, 0x1400ffd8 }, - { 0x0d010431, 0x1400ffd8 }, - { 0x0d010432, 0x1400ffd8 }, - { 0x0d010433, 0x1400ffd8 }, - { 0x0d010434, 0x1400ffd8 }, - { 0x0d010435, 0x1400ffd8 }, - { 0x0d010436, 0x1400ffd8 }, - { 0x0d010437, 0x1400ffd8 }, - { 0x0d010438, 0x1400ffd8 }, - { 0x0d010439, 0x1400ffd8 }, - { 0x0d01043a, 0x1400ffd8 }, - { 0x0d01043b, 0x1400ffd8 }, - { 0x0d01043c, 0x1400ffd8 }, - { 0x0d01043d, 0x1400ffd8 }, - { 0x0d01043e, 0x1400ffd8 }, - { 0x0d01043f, 0x1400ffd8 }, - { 0x0d010440, 0x1400ffd8 }, - { 0x0d010441, 0x1400ffd8 }, - { 0x0d010442, 0x1400ffd8 }, - { 0x0d010443, 0x1400ffd8 }, - { 0x0d010444, 0x1400ffd8 }, - { 0x0d010445, 0x1400ffd8 }, - { 0x0d010446, 0x1400ffd8 }, - { 0x0d010447, 0x1400ffd8 }, - { 0x0d010448, 0x1400ffd8 }, - { 0x0d010449, 0x1400ffd8 }, - { 0x0d01044a, 0x1400ffd8 }, - { 0x0d01044b, 0x1400ffd8 }, - { 0x0d01044c, 0x1400ffd8 }, - { 0x0d01044d, 0x1400ffd8 }, - { 0x0d01044e, 0x1400ffd8 }, - { 0x0d01044f, 0x1400ffd8 }, - { 0x2e810450, 0x1c00004d }, - { 0x2c8104a0, 0x34000009 }, - { 0x0b810800, 0x1c000005 }, - { 0x0b010808, 0x1c000000 }, - { 0x0b81080a, 0x1c00002b }, - { 0x0b810837, 0x1c000001 }, - { 0x0b01083c, 0x1c000000 }, - { 0x0b01083f, 0x1c000000 }, - { 0x1e010a00, 0x1c000000 }, - { 0x1e810a01, 0x30000002 }, - { 0x1e810a05, 0x30000001 }, - { 0x1e810a0c, 0x30000003 }, - { 0x1e810a10, 0x1c000003 }, - { 0x1e810a15, 0x1c000002 }, - { 0x1e810a19, 0x1c00001a }, - { 0x1e810a38, 0x30000002 }, - { 0x1e010a3f, 0x30000000 }, - { 0x1e810a40, 0x3c000007 }, - { 0x1e810a50, 0x54000008 }, - { 0x0981d000, 0x680000f5 }, - { 0x0981d100, 0x68000026 }, - { 0x0981d12a, 0x6800003a }, - { 0x0981d165, 0x28000001 }, - { 0x1b81d167, 0x30000002 }, - { 0x0981d16a, 0x68000002 }, - { 0x0981d16d, 0x28000005 }, - { 0x0981d173, 0x04000007 }, - { 0x1b81d17b, 0x30000007 }, - { 0x0981d183, 0x68000001 }, - { 0x1b81d185, 0x30000006 }, - { 0x0981d18c, 0x6800001d }, - { 0x1b81d1aa, 0x30000003 }, - { 0x0981d1ae, 0x6800002f }, - { 0x1381d200, 0x68000041 }, - { 0x1381d242, 0x30000002 }, - { 0x1301d245, 0x68000000 }, - { 0x0981d300, 0x68000056 }, - { 0x0981d400, 0x24000019 }, - { 0x0981d41a, 0x14000019 }, - { 0x0981d434, 0x24000019 }, - { 0x0981d44e, 0x14000006 }, - { 0x0981d456, 0x14000011 }, - { 0x0981d468, 0x24000019 }, - { 0x0981d482, 0x14000019 }, - { 0x0901d49c, 0x24000000 }, - { 0x0981d49e, 0x24000001 }, - { 0x0901d4a2, 0x24000000 }, - { 0x0981d4a5, 0x24000001 }, - { 0x0981d4a9, 0x24000003 }, - { 0x0981d4ae, 0x24000007 }, - { 0x0981d4b6, 0x14000003 }, - { 0x0901d4bb, 0x14000000 }, - { 0x0981d4bd, 0x14000006 }, - { 0x0981d4c5, 0x1400000a }, - { 0x0981d4d0, 0x24000019 }, - { 0x0981d4ea, 0x14000019 }, - { 0x0981d504, 0x24000001 }, - { 0x0981d507, 0x24000003 }, - { 0x0981d50d, 0x24000007 }, - { 0x0981d516, 0x24000006 }, - { 0x0981d51e, 0x14000019 }, - { 0x0981d538, 0x24000001 }, - { 0x0981d53b, 0x24000003 }, - { 0x0981d540, 0x24000004 }, - { 0x0901d546, 0x24000000 }, - { 0x0981d54a, 0x24000006 }, - { 0x0981d552, 0x14000019 }, - { 0x0981d56c, 0x24000019 }, - { 0x0981d586, 0x14000019 }, - { 0x0981d5a0, 0x24000019 }, - { 0x0981d5ba, 0x14000019 }, - { 0x0981d5d4, 0x24000019 }, - { 0x0981d5ee, 0x14000019 }, - { 0x0981d608, 0x24000019 }, - { 0x0981d622, 0x14000019 }, - { 0x0981d63c, 0x24000019 }, - { 0x0981d656, 0x14000019 }, - { 0x0981d670, 0x24000019 }, - { 0x0981d68a, 0x1400001b }, - { 0x0981d6a8, 0x24000018 }, - { 0x0901d6c1, 0x64000000 }, - { 0x0981d6c2, 0x14000018 }, - { 0x0901d6db, 0x64000000 }, - { 0x0981d6dc, 0x14000005 }, - { 0x0981d6e2, 0x24000018 }, - { 0x0901d6fb, 0x64000000 }, - { 0x0981d6fc, 0x14000018 }, - { 0x0901d715, 0x64000000 }, - { 0x0981d716, 0x14000005 }, - { 0x0981d71c, 0x24000018 }, - { 0x0901d735, 0x64000000 }, - { 0x0981d736, 0x14000018 }, - { 0x0901d74f, 0x64000000 }, - { 0x0981d750, 0x14000005 }, - { 0x0981d756, 0x24000018 }, - { 0x0901d76f, 0x64000000 }, - { 0x0981d770, 0x14000018 }, - { 0x0901d789, 0x64000000 }, - { 0x0981d78a, 0x14000005 }, - { 0x0981d790, 0x24000018 }, - { 0x0901d7a9, 0x64000000 }, - { 0x0981d7aa, 0x14000018 }, - { 0x0901d7c3, 0x64000000 }, - { 0x0981d7c4, 0x14000005 }, - { 0x0981d7ce, 0x34000031 }, - { 0x16820000, 0x1c00a6d6 }, - { 0x1682f800, 0x1c00021d }, - { 0x090e0001, 0x04000000 }, - { 0x098e0020, 0x0400005f }, - { 0x1b8e0100, 0x300000ef }, - { 0x098f0000, 0x0c00fffd }, - { 0x09900000, 0x0c00fffd }, -}; diff --git a/ext/pcre/php_pcre.c b/ext/pcre/php_pcre.c deleted file mode 100644 index b6cf8d050a..0000000000 --- a/ext/pcre/php_pcre.c +++ /dev/null @@ -1,1802 +0,0 @@ -/* - +----------------------------------------------------------------------+ - | PHP Version 5 | - +----------------------------------------------------------------------+ - | Copyright (c) 1997-2006 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> | - +----------------------------------------------------------------------+ - */ - -/* $Id$ */ - -#ifdef HAVE_CONFIG_H -#include "config.h" -#endif - -#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, -}; - - -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; - - 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", "100000", 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(); -} -/* }}} */ - -/* {{{ 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); - - 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; - } -} -/* }}} */ - -/* {{{ 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; - unsigned const char *tables = NULL; -#if HAVE_SETLOCALE - char *locale = setlocale(LC_CTYPE, NULL); -#endif - pcre_cache_entry *pce; - pcre_cache_entry new_entry; - - /* Try to lookup the cached regex entry, and if successful, just pass - back the compiled pattern, otherwise go on and compile it. */ - regex_len = strlen(regex); - if (zend_hash_find(&PCRE_G(pcre_cache), regex, regex_len+1, (void **)&pce) == SUCCESS) { - /* - * We use a quick pcre_info() check to see whether cache is corrupted, and if it - * is, we flush it and compile the pattern from scratch. - */ - if (pcre_info(pce->re, NULL, NULL) == 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, "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; - - 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. */ - pp = p; - while (*pp != 0) { - if (*pp == '\\' && pp[1] != 0) pp++; - else if (*pp == delimiter) - break; - pp++; - } - if (*pp == 0) { - php_error_docref(NULL TSRMLS_CC,E_WARNING, "No ending delimiter '%c' found", delimiter); - return NULL; - } - } 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 */ - pp = p; - 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) { - php_error_docref(NULL TSRMLS_CC,E_WARNING, "No ending matching delimiter '%c' found", end_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 != 0) { - 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; break; - - /* Custom preg options */ - case 'e': poptions |= PREG_REPLACE_EVAL; break; - - case ' ': - case '\n': - break; - - default: - php_error_docref(NULL TSRMLS_CC,E_WARNING, "Unknown modifier '%c'", pp[-1]); - 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 - zend_hash_update(&PCRE_G(pcre_cache), regex, regex_len+1, (void *)&new_entry, - sizeof(pcre_cache_entry), (void**)&pce); - - 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, ((global) ? "ssz|ll" : "ss|zll"), ®ex, ®ex_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); -} - -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 *match; /* The current match */ - char **subpat_names = NULL;/* 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; - offsets = (int *)safe_emalloc(size_offsets, sizeof(int), 0); - - /* - * 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 = (char **)safe_emalloc(num_subpats, sizeof(char *), 0); - memset(subpat_names, 0, sizeof(char *) * num_subpats); - { - int name_cnt = 0, name_size, ni = 0; - char *name_table; - unsigned short name_idx; - - 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(offsets); - efree(subpat_names); - RETURN_FALSE; - } - if (name_cnt > 0) { - int rc1, rc2; - long dummy_l; - double dummy_d; - 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(offsets); - efree(subpat_names); - RETURN_FALSE; - } - - while (ni++ < name_cnt) { - name_idx = 0xff * name_table[0] + name_table[1]; - subpat_names[name_idx] = name_table + 2; - if (is_numeric_string(subpat_names[name_idx], strlen(subpat_names[name_idx]), &dummy_l, &dummy_d, 0) > 0) { - php_error_docref(NULL TSRMLS_CC, E_WARNING, "Numeric named subpatterns are not allowed"); - efree(offsets); - efree(subpat_names); - RETURN_FALSE; - } - name_table += name_size; - } - } - } - - /* Allocate match sets array and initialize the values. */ - if (global && 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]); - } - } - - match = NULL; - 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); - - /* 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++; - match = subject + offsets[0]; - - /* 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); - php_error_docref(NULL TSRMLS_CC, E_WARNING, "Get subpatterns list failed"); - RETURN_FALSE; - } - - if (global) { /* global pattern matching */ - if (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_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); - ZVAL_ADDREF(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); - - RETVAL_LONG(matched); -} -/* }}} */ - -/* {{{ proto int preg_match(string pattern, string subject [, array subpatterns [, int flags [, int offset]]]) - Perform a Perl-style regular expression match */ -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 */ -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, 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++) - 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 { - 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_dtor(subpats); - FREE_ZVAL(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_ex(match, match_len, &esc_match_len, 0, 1 TSRMLS_CC); - } else { - esc_match = match; - esc_match_len = 0; - } - } else { - esc_match = ""; - esc_match_len = 0; - 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_string(code.c, &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); -} - -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 */ - 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, &size_offsets); - if (rc < 0) { - php_error_docref(NULL TSRMLS_CC, E_WARNING, "Internal pcre_fullinfo() error %d", rc); - return NULL; - } - size_offsets = (size_offsets + 1) * 3; - 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); - - /* 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, - 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); - - return result; -} -/* }}} */ - -/* {{{ php_replace_in_subject - */ -static char *php_replace_in_subject(zval *regex, zval *replace, zval **subject, int *result_len, int limit, zend_bool 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 **)®ex_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; - } - - 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, zend_bool is_callable_replace) -{ - zval **regex, - **replace, - **subject, - **limit, - **subject_entry, - **zcount; - char *result; - int result_len; - int limit_val = -1; - char *string_key; - ulong num_key; - char *callback_name; - int replace_count=0; - int *replace_count_ptr=NULL; - - /* Get function parameters and do error-checking. */ - if (ZEND_NUM_ARGS() < 3 || ZEND_NUM_ARGS() > 5 || - zend_get_parameters_ex(ZEND_NUM_ARGS(), ®ex, &replace, &subject, &limit, &zcount) == FAILURE) { - WRONG_PARAM_COUNT; - } - 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) - convert_to_string_ex(replace); - if (is_callable_replace) { - if (!zend_is_callable(*replace, 0, &callback_name)) { - php_error_docref(NULL TSRMLS_CC, E_WARNING, "Requires argument 2, '%s', to be a valid callback", callback_name); - efree(callback_name); - *return_value = **subject; - zval_copy_ctor(return_value); - INIT_PZVAL(return_value); - return; - } - efree(callback_name); - } - - SEPARATE_ZVAL(regex); - SEPARATE_ZVAL(subject); - - if (ZEND_NUM_ARGS() > 3) { - convert_to_long_ex(limit); - limit_val = Z_LVAL_PP(limit); - } - if (ZEND_NUM_ARGS() > 4) { - replace_count_ptr =& replace_count; - } - - 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); - if ((result = php_replace_in_subject(*regex, *replace, subject_entry, &result_len, limit_val, is_callable_replace, replace_count_ptr TSRMLS_CC)) != NULL) { - /* 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; - } - } - - zend_hash_move_forward(Z_ARRVAL_PP(subject)); - } - } else { /* if subject is not an array */ - if ((result = php_replace_in_subject(*regex, *replace, subject, &result_len, limit_val, is_callable_replace, replace_count_ptr TSRMLS_CC)) != NULL) { - RETVAL_STRINGL(result, result_len, 0); - } - } - if (replace_count_ptr) { - zval_dtor(*zcount); - ZVAL_LONG(*zcount, replace_count); - } - -} -/* }}} */ - -/* {{{ proto string preg_replace(mixed regex, mixed replace, mixed subject [, int limit [, count]]) - Perform Perl-style regular expression replacement. */ -PHP_FUNCTION(preg_replace) -{ - preg_replace_impl(INTERNAL_FUNCTION_PARAM_PASSTHRU, 0); -} -/* }}} */ - -/* {{{ proto string preg_replace_callback(mixed regex, mixed callback, mixed subject [, int limit [, count]]) - Perform Perl-style regular expression replacement using replacement callback. */ -PHP_FUNCTION(preg_replace_callback) -{ - preg_replace_impl(INTERNAL_FUNCTION_PARAM_PASSTHRU, 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 */ -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", ®ex, ®ex_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 *match, /* The current match */ - *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; - match = NULL; - 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); - - /* 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) { - match = subject + offsets[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("/./u", &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_NOTICE, "Unknown error"); - offsets[0] = start_offset; - offsets[1] = start_offset + 1; - } - } 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]; - } - - - 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 */ -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; - 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 ':': - *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 */ -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", ®ex, ®ex_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) { - - convert_to_string_ex(entry); - - /* Perform the match */ - count = pcre_exec(pce->re, extra, Z_STRVAL_PP(entry), - Z_STRLEN_PP(entry), 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)) { - (*entry)->refcount++; - - /* 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; - } - } - - zend_hash_move_forward(Z_ARRVAL_P(input)); - } - - /* Clean up */ - efree(offsets); -} -/* }}} */ - -/* {{{ proto int preg_last_error() - Returns the error code of the last regexp execution. */ -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 */ - -zend_function_entry pcre_functions[] = { - PHP_FE(preg_match, third_arg_force_ref) - PHP_FE(preg_match_all, third_arg_force_ref) - PHP_FE(preg_replace, fifth_arg_force_ref) - PHP_FE(preg_replace_callback, fifth_arg_force_ref) - PHP_FE(preg_split, NULL) - PHP_FE(preg_quote, NULL) - PHP_FE(preg_grep, NULL) - PHP_FE(preg_last_error, NULL) - {NULL, NULL, NULL} -}; - -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) -# ifdef PHP_WIN32 -# include "zend_arg_defs.c" -# endif -#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 deleted file mode 100644 index d47b3773ed..0000000000 --- a/ext/pcre/php_pcre.def +++ /dev/null @@ -1,11 +0,0 @@ -EXPORTS -php_pcre_compile -php_pcre_copy_substring -php_pcre_exec -php_pcre_substring -php_pcre_get_substring_list -php_pcre_info -php_pcre_maketables -php_pcre_study -php_pcre_version -php_pcre_fullinfo diff --git a/ext/pcre/php_pcre.h b/ext/pcre/php_pcre.h deleted file mode 100644 index 859d3a8126..0000000000 --- a/ext/pcre/php_pcre.h +++ /dev/null @@ -1,98 +0,0 @@ -/* - +----------------------------------------------------------------------+ - | PHP Version 5 | - +----------------------------------------------------------------------+ - | Copyright (c) 1997-2006 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 - -PHP_FUNCTION(preg_match); -PHP_FUNCTION(preg_match_all); -PHP_FUNCTION(preg_replace); -PHP_FUNCTION(preg_replace_callback); -PHP_FUNCTION(preg_split); -PHP_FUNCTION(preg_quote); -PHP_FUNCTION(preg_grep); - -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/backtrack_limit.phpt b/ext/pcre/tests/backtrack_limit.phpt deleted file mode 100644 index ebfd720c3c..0000000000 --- a/ext/pcre/tests/backtrack_limit.phpt +++ /dev/null @@ -1,19 +0,0 @@ ---TEST-- -Backtracking limit ---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-- -int(0) -bool(true) -int(10) -bool(true) diff --git a/ext/pcre/tests/bug20528.phpt b/ext/pcre/tests/bug20528.phpt deleted file mode 100644 index 8182fd9bfe..0000000000 --- a/ext/pcre/tests/bug20528.phpt +++ /dev/null @@ -1,24 +0,0 @@ ---TEST-- -Bug #20528 (preg_split() drops characters (re-opens Bug #15413)) ---FILE-- -<?php - $data = '(#11/19/2002#)'; - var_dump(preg_split('/\b/', $data)); -?> ---EXPECT-- -array(7) { - [0]=> - string(2) "(#" - [1]=> - string(2) "11" - [2]=> - string(1) "/" - [3]=> - string(2) "19" - [4]=> - string(1) "/" - [5]=> - string(4) "2002" - [6]=> - string(2) "#)" -} diff --git a/ext/pcre/tests/bug21732.phpt b/ext/pcre/tests/bug21732.phpt deleted file mode 100644 index 3dfc41e19f..0000000000 --- a/ext/pcre/tests/bug21732.phpt +++ /dev/null @@ -1,29 +0,0 @@ ---TEST-- -Bug #21732 (preg_replace() segfaults with invalid parameters) ---INI-- -error_reporting=0 ---FILE-- -<?php -class foo { - function cb($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/bug26927.phpt b/ext/pcre/tests/bug26927.phpt deleted file mode 100644 index 5c64deb37c..0000000000 --- a/ext/pcre/tests/bug26927.phpt +++ /dev/null @@ -1,11 +0,0 @@ ---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), $str_quoted); -?> ---EXPECT-- -int(1) -string(6) "a\000b" diff --git a/ext/pcre/tests/bug27103.phpt b/ext/pcre/tests/bug27103.phpt deleted file mode 100644 index 185225d310..0000000000 --- a/ext/pcre/tests/bug27103.phpt +++ /dev/null @@ -1,37 +0,0 @@ ---TEST-- -Bug #27103 (preg_split('//u') incorrectly splits UTF-8 strings into octets) ---FILE-- -<?php -function iter($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-- -€: 3 - : 1 -h: 1 -i: 1 - : 1 -t: 1 -h: 1 -e: 1 -r: 1 -e: 1 -€: 3 - : 1 -h: 1 -i: 1 - : 1 -t: 1 -h: 1 -e: 1 -r: 1 -e: 1 - diff --git a/ext/pcre/tests/bug33200.phpt b/ext/pcre/tests/bug33200.phpt deleted file mode 100644 index b00b72ac28..0000000000 --- a/ext/pcre/tests/bug33200.phpt +++ /dev/null @@ -1,12 +0,0 @@ ---TEST-- -Bug #33200 (magic_quotes_sybase = On makes 'e' modifier misbehave) ---INI-- -magic_quotes_sybase=1 ---FILE-- -<?php -$str = 'some \'$sample\' text'; -$str = preg_replace("/(some.*text)/e", "strtoupper('\\1')", $str); -echo $str; -?> ---EXPECT-- -SOME '$SAMPLE' TEXT diff --git a/ext/pcre/tests/bug34790.phpt b/ext/pcre/tests/bug34790.phpt deleted file mode 100755 index c375ae5ac8..0000000000 --- a/ext/pcre/tests/bug34790.phpt +++ /dev/null @@ -1,23 +0,0 @@ ---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($words); -?> ---EXPECT-- -array(4) { - [0]=> - string(3) "the" - [1]=> - string(3) "the" - [2]=> - string(3) "the" - [3]=> - string(3) "the" -} diff --git a/ext/pcre/tests/bug37800.phpt b/ext/pcre/tests/bug37800.phpt deleted file mode 100644 index e8a0036ebe..0000000000 --- a/ext/pcre/tests/bug37800.phpt +++ /dev/null @@ -1,31 +0,0 @@ ---TEST-- -Bug #37800 (preg_replace() limit parameter odd behaviour) ---FILE-- -<?php -$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 = $i_count\n"; -var_dump(preg_last_error() === PREG_NO_ERROR); - -?> ---EXPECT-- -Output = 'One 111111111' -Count = 1 -bool(true) -Output = 'One One One One One One One One One One ' -Count = 10 -bool(true) diff --git a/ext/pcre/tests/cache_limit.phpt b/ext/pcre/tests/cache_limit.phpt deleted file mode 100644 index bfe7f1b9a9..0000000000 --- a/ext/pcre/tests/cache_limit.phpt +++ /dev/null @@ -1,25 +0,0 @@ ---TEST-- -Compiled regex cache limit ---FILE-- -<?php -define('PREG_CACHE_SIZE', 4096+1); - -$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/", $str)); // but not this one - -echo "done\n"; -?> ---EXPECT-- -int(1) -int(1) -done diff --git a/ext/pcre/tests/delimiters.phpt b/ext/pcre/tests/delimiters.phpt deleted file mode 100644 index 1826f8730a..0000000000 --- a/ext/pcre/tests/delimiters.phpt +++ /dev/null @@ -1,37 +0,0 @@ ---TEST-- -Delimiters crash test ---FILE-- -<?php - -var_dump(preg_match('', '')); -var_dump(preg_match(' ', '')); -var_dump(preg_match('@@', '')); -var_dump(preg_match('12', '')); -var_dump(preg_match('<>', '')); -var_dump(preg_match('~a', '')); -var_dump(preg_match('@\@\@@', '@@')); -var_dump(preg_match('//z', '@@')); -var_dump(preg_match('{', '')); - -?> ---EXPECTF-- -Warning: preg_match(): Empty regular expression in %sdelimiters.php on line 3 -bool(false) - -Warning: preg_match(): Empty regular expression in %sdelimiters.php on line 4 -bool(false) -int(1) - -Warning: preg_match(): Delimiter must not be alphanumeric or backslash in %sdelimiters.php on line 6 -bool(false) -int(1) - -Warning: preg_match(): No ending delimiter '~' found in %sdelimiters.php on line 8 -bool(false) -int(1) - -Warning: preg_match(): Unknown modifier 'z' in %sdelimiters.php on line 10 -bool(false) - -Warning: preg_match(): No ending matching delimiter '}' found in %sdelimiters.php on line 11 -bool(false) diff --git a/ext/pcre/tests/dollar_endonly.phpt b/ext/pcre/tests/dollar_endonly.phpt deleted file mode 100644 index 96a52441df..0000000000 --- a/ext/pcre/tests/dollar_endonly.phpt +++ /dev/null @@ -1,39 +0,0 @@ ---TEST-- -D (PCRE_DOLLAR_ENDONLY) modififer ---FILE-- -<?php - -var_dump(preg_match_all('/^\S+.+$/', "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 deleted file mode 100644 index d3d9032e49..0000000000 --- a/ext/pcre/tests/grep.phpt +++ /dev/null @@ -1,23 +0,0 @@ ---TEST-- -preg_grep() ---FILE-- -<?php -$array = array('a', '1', 'q6', 'h20'); - -var_dump(preg_grep('/^(\d|.\d)$/', $array)); -var_dump(preg_grep('/^(\d|.\d)$/', $array, PREG_GREP_INVERT)); - -?> ---EXPECT-- -array(2) { - [1]=> - string(1) "1" - [2]=> - string(2) "q6" -} -array(2) { - [0]=> - string(1) "a" - [3]=> - string(3) "h20" -} diff --git a/ext/pcre/tests/grep2.phpt b/ext/pcre/tests/grep2.phpt deleted file mode 100644 index 0cf8d4aebc..0000000000 --- a/ext/pcre/tests/grep2.phpt +++ /dev/null @@ -1,45 +0,0 @@ ---TEST-- -preg_grep() 2nd test ---FILE-- -<?php - -var_dump(preg_grep(1,array(),3,4)); -var_dump(preg_grep(1, 2)); -var_dump(preg_grep('/+/', array())); - -$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]+@', $array)); -var_dump(preg_last_error() == PREG_RECURSION_LIMIT_ERROR); - -?> ---EXPECTF-- -Warning: preg_grep() expects at most 3 parameters, 4 given in %sgrep2.php on line 3 -NULL - -Warning: preg_grep() expects parameter 2 to be array, integer given in %sgrep2.php on line 4 -NULL - -Warning: preg_grep(): Compilation failed: nothing to repeat at offset 0 in %sgrep2.php on line 5 -bool(false) -array(3) { - [5]=> - string(1) "a" - ["xyz"]=> - string(2) "q6" - [6]=> - string(3) "h20" -} -array(1) { - ["x"]=> - string(1) "1" -} -bool(true) -array(0) { -} -bool(true) diff --git a/ext/pcre/tests/invalid_utf8.phpt b/ext/pcre/tests/invalid_utf8.phpt deleted file mode 100644 index df2de2da9b..0000000000 --- a/ext/pcre/tests/invalid_utf8.phpt +++ /dev/null @@ -1,16 +0,0 @@ ---TEST-- -preg_replace() and invalid UTF8 ---FILE-- -<?php - -$string = urldecode("search%e4"); -$result = preg_replace("#(&\#x*)([0-9A-F]+);*#iu","$1$2;",$string); -var_dump($result); -var_dump(preg_last_error()); - -echo "Done\n"; -?> ---EXPECT-- -NULL -int(4) -Done diff --git a/ext/pcre/tests/locales.phpt b/ext/pcre/tests/locales.phpt deleted file mode 100644 index 6b600236cf..0000000000 --- a/ext/pcre/tests/locales.phpt +++ /dev/null @@ -1,25 +0,0 @@ ---TEST-- -Localized match ---SKIPIF-- -<?php if (!function_exists('setlocale')) die('skip: setlocale() not available'); ?> -<?php if (!@setlocale(LC_ALL, 'pt_PT', 'pt', 'pt_PT.ISO8859-1', 'portuguese')) die('skip pt locale not available'); ---FILE-- -<?php - -// this tests if the cache is working correctly, as the char tables -// must be rebuilt after the locale change - -setlocale(LC_ALL, 'C', 'POSIX'); -var_dump(preg_match('/^\w{6}$/', 'aאבחיט')); - -setlocale(LC_ALL, 'pt_PT', 'pt', 'pt_PT.ISO8859-1', 'portuguese'); -var_dump(preg_match('/^\w{6}$/', 'aאבחיט')); - -setlocale(LC_ALL, 'C', 'POSIX'); -var_dump(preg_match('/^\w{6}$/', 'aאבחיט')); - -?> ---EXPECT-- -int(0) -int(1) -int(0) diff --git a/ext/pcre/tests/match_flags.phpt b/ext/pcre/tests/match_flags.phpt deleted file mode 100644 index ddd36bf9ba..0000000000 --- a/ext/pcre/tests/match_flags.phpt +++ /dev/null @@ -1,127 +0,0 @@ ---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 deleted file mode 100644 index f703091735..0000000000 --- a/ext/pcre/tests/match_flags2.phpt +++ /dev/null @@ -1,95 +0,0 @@ ---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 deleted file mode 100644 index f22205e3d8..0000000000 --- a/ext/pcre/tests/match_flags3.phpt +++ /dev/null @@ -1,46 +0,0 @@ ---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 deleted file mode 100644 index 356800917b..0000000000 --- a/ext/pcre/tests/multiline.phpt +++ /dev/null @@ -1,18 +0,0 @@ ---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/pcre_anchored.phpt b/ext/pcre/tests/pcre_anchored.phpt deleted file mode 100644 index caa96437e1..0000000000 --- a/ext/pcre/tests/pcre_anchored.phpt +++ /dev/null @@ -1,22 +0,0 @@ ---TEST-- -A (PCRE_ANCHORED) modififer ---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 deleted file mode 100644 index 1239d48ffb..0000000000 --- a/ext/pcre/tests/pcre_count.phpt +++ /dev/null @@ -1,40 +0,0 @@ ---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 deleted file mode 100644 index 6c4b20e7f0..0000000000 --- a/ext/pcre/tests/pcre_extended.phpt +++ /dev/null @@ -1,29 +0,0 @@ ---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 deleted file mode 100644 index 2bee408fbf..0000000000 --- a/ext/pcre/tests/pcre_extra.phpt +++ /dev/null @@ -1,14 +0,0 @@ ---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_replace.phpt b/ext/pcre/tests/preg_replace.phpt deleted file mode 100644 index f7b5f74157..0000000000 --- a/ext/pcre/tests/preg_replace.phpt +++ /dev/null @@ -1,25 +0,0 @@ ---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 deleted file mode 100644 index 4e2f39f8ca..0000000000 --- a/ext/pcre/tests/preg_replace2.phpt +++ /dev/null @@ -1,42 +0,0 @@ ---TEST-- -preg_replace() ---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) "$" -} -==done== diff --git a/ext/pcre/tests/preg_replace_callback.phpt b/ext/pcre/tests/preg_replace_callback.phpt deleted file mode 100644 index 0b0bc27576..0000000000 --- a/ext/pcre/tests/preg_replace_callback.phpt +++ /dev/null @@ -1,25 +0,0 @@ ---TEST-- -preg_replace_callback() ---FILE-- -<?php -$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 deleted file mode 100644 index a7f5a362dc..0000000000 --- a/ext/pcre/tests/preg_replace_callback2.phpt +++ /dev/null @@ -1,40 +0,0 @@ ---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($m[0]);'), 'ABC')); -?> ---EXPECTF-- -Warning: preg_replace_callback(): Unable to call custom replacement function in %spreg_replace_callback2.php on line %d -array(3) { - [0]=> - string(12) "'a' 'b3' bcd" - ["v"]=> - string(6) "aksfjk" - [12]=> - string(9) "'aa' 'bb'" -} - -Notice: Array to string conversion in %spreg_replace_callback2.php on line 17 -array(1) { - [0]=> - string(7) "'A'rray" -} -string(3) "aBC" diff --git a/ext/pcre/tests/preg_replace_callback3.phpt b/ext/pcre/tests/preg_replace_callback3.phpt deleted file mode 100644 index fafd966f47..0000000000 --- a/ext/pcre/tests/preg_replace_callback3.phpt +++ /dev/null @@ -1,45 +0,0 @@ ---TEST-- -preg_replace_callback() 3 ---FILE-- -<?php - -var_dump(preg_replace_callback()); -var_dump(preg_replace_callback(1)); -var_dump(preg_replace_callback(1,2)); -var_dump(preg_replace_callback(1,2,3)); -var_dump(preg_replace_callback(1,2,3,4)); -$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: Wrong parameter count for preg_replace_callback() in %s on line %d -NULL - -Warning: Wrong parameter count for preg_replace_callback() in %s on line %d -NULL - -Warning: Wrong parameter count for preg_replace_callback() 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(): Requires argument 2, '', to be a valid callback in %s on line 1%d -string(0) "" - -Warning: preg_replace_callback(): Requires argument 2, 'Array', to be a valid callback in %s on line %d -array(0) { -} -Done diff --git a/ext/pcre/tests/recursion_limit.phpt b/ext/pcre/tests/recursion_limit.phpt deleted file mode 100644 index 2a43aa27d6..0000000000 --- a/ext/pcre/tests/recursion_limit.phpt +++ /dev/null @@ -1,19 +0,0 @@ ---TEST-- -PCRE Recursion limit ---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-- -int(0) -bool(true) -int(1) -bool(true) diff --git a/ext/pcre/tests/split.phpt b/ext/pcre/tests/split.phpt deleted file mode 100644 index 8ec8e655cf..0000000000 --- a/ext/pcre/tests/split.phpt +++ /dev/null @@ -1,86 +0,0 @@ ---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 deleted file mode 100644 index 391acb951e..0000000000 --- a/ext/pcre/tests/split2.phpt +++ /dev/null @@ -1,315 +0,0 @@ ---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 deleted file mode 100644 index 696a4c0ef0..0000000000 --- a/ext/pcre/tests/study.phpt +++ /dev/null @@ -1,31 +0,0 @@ ---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 deleted file mode 100644 index cf5e8adafd..0000000000 --- a/ext/pcre/tests/ungreedy.phpt +++ /dev/null @@ -1,31 +0,0 @@ ---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>" -} |