diff options
| author | Ben Wagner <bungeman@chromium.org> | 2019-12-05 14:19:15 +0100 |
|---|---|---|
| committer | Michael Brüning <michael.bruning@qt.io> | 2019-12-05 18:23:22 +0000 |
| commit | 0ee076e7a6507637efad493edc367fd63b7e7fb1 (patch) | |
| tree | 95857f1b7fa78bc243904c91f96b0db76b74444f | |
| parent | d00dd9bddf1b2c78aff0b858ef0cc5c2a59b2817 (diff) | |
| download | qtwebengine-chromium-0ee076e7a6507637efad493edc367fd63b7e7fb1.tar.gz | |
[Backport] CVE-2019-15903v5.9.9
Roll expat to R_2_2_8-5-g4f23e05
Diffs here should match those at
https://github.com/libexpat/libexpat/compare/39e487da353b20bb3a724311d179ba0fddffc65b..4f23e05a33a66c5962589a32c87df4fe68144fce
Bug: chromium:1004341
Change-Id: I9a105b4e7635c262be4d090415b011e74b00c143
Reviewed-by: Allan Sandfeld Jensen <allan.jensen@qt.io>
37 files changed, 6942 insertions, 12328 deletions
diff --git a/chromium/third_party/expat/0001-Do-not-claim-getrandom.patch b/chromium/third_party/expat/0001-Do-not-claim-getrandom.patch new file mode 100644 index 00000000000..cbf77db3b0f --- /dev/null +++ b/chromium/third_party/expat/0001-Do-not-claim-getrandom.patch @@ -0,0 +1,22 @@ +diff --git a/third_party/expat/files/lib/expat_config.h b/third_party/expat/files/lib/expat_config.h +index 278d7a8..c693a14a 100644 +--- a/third_party/expat/files/lib/expat_config.h ++++ b/third_party/expat/files/lib/expat_config.h +@@ -23,7 +23,7 @@ + #define HAVE_GETPAGESIZE 1 + + /* Define to 1 if you have the `getrandom' function. */ +-#define HAVE_GETRANDOM 1 ++/* #define HAVE_GETRANDOM 1 */ + + /* Define to 1 if you have the <inttypes.h> header file. */ + #define HAVE_INTTYPES_H 1 +@@ -50,7 +50,7 @@ + #define HAVE_STRING_H 1 + + /* Define to 1 if you have `syscall' and `SYS_getrandom'. */ +-#define HAVE_SYSCALL_GETRANDOM 1 ++/* #define HAVE_SYSCALL_GETRANDOM 1 */ + + /* Define to 1 if you have the <sys/param.h> header file. */ + #define HAVE_SYS_PARAM_H 1 diff --git a/chromium/third_party/expat/BUILD.gn b/chromium/third_party/expat/BUILD.gn index a2c2d0c637c..842d0f9ddd0 100644 --- a/chromium/third_party/expat/BUILD.gn +++ b/chromium/third_party/expat/BUILD.gn @@ -9,7 +9,7 @@ import("//testing/libfuzzer/fuzzer_test.gni") # let's not pull it in twice. # Chromecast doesn't ship expat as a system library. # Libfuzzer and AFL need to build library from sources. -if (is_linux && !is_chromecast && !use_libfuzzer && !use_afl) { +if (is_linux && !is_chromecast && !use_fuzzing_engine) { config("expat_config") { libs = [ "expat" ] } @@ -33,8 +33,15 @@ if (is_linux && !is_chromecast && !use_libfuzzer && !use_afl) { public_configs = [ ":expat_config" ] + # TODO(thakis): Remove this once clang no longer crashes when building + # libexpat with -Oz. + configs -= [ "//build/config/compiler:default_optimization" ] + configs += [ "//build/config/compiler:optimize_max" ] + defines = [ "_LIB" ] if (is_win) { + # expat expects to define WIN32_LEAN_AND_MEAN itself + configs -= [ "//build/config/win:lean_and_mean" ] defines += [ "COMPILED_FROM_DSP" ] } else { defines += [ "HAVE_EXPAT_CONFIG_H" ] @@ -49,5 +56,6 @@ fuzzer_test("expat_xml_parse_fuzzer") { deps = [ ":expat", ] - dict = "//testing/libfuzzer/fuzzers/dicts/xml.dict" + dict = "//third_party/libxml/fuzz/xml.dict" + seed_corpus = "//third_party/libxml/fuzz/seed_corpus" } diff --git a/chromium/third_party/expat/OWNERS b/chromium/third_party/expat/OWNERS index 9b408890986..40ca48beb34 100644 --- a/chromium/third_party/expat/OWNERS +++ b/chromium/third_party/expat/OWNERS @@ -1,2 +1,2 @@ -nick@chromium.org -dominicc@chromium.org +bungeman@chromium.org +dcheng@chromium.org diff --git a/chromium/third_party/expat/README.chromium b/chromium/third_party/expat/README.chromium index e3dda3aea97..435a7b9882a 100644 --- a/chromium/third_party/expat/README.chromium +++ b/chromium/third_party/expat/README.chromium @@ -1,7 +1,7 @@ Name: Expat XML Parser Short Name: expat -URL: http://sourceforge.net/projects/expat/ -Version: 2.2.0 +URL: https://github.com/libexpat/libexpat +Version: R_2_2_8-5-g4f23e05 License: MIT License File: files/COPYING Security Critical: yes @@ -12,52 +12,20 @@ Description: We include it here because libjingle depends on it. -Local Modifications: - Removed files that Chromium didn't need: - lib/expat*.dsp - lib/Makefile.MPW - amiga/* - bcb5/* - conftools/* - doc/* - examples/* - m4/* - tests/* - vms/* - win32/* - xmlwf/* - aclocal.m4 - CMake.README - CMakeLists.txt - configure - configure.ac - configureChecks.cmake - Makefile.in - expat.dsw - expat.pc.in - expat_config.h.cmake - expat_config.h.in - Makefile.in - Edited: - lib/winconfig.h (see winconfig.h.original for unmodified version) - lib/xmlparse.c (see xmlparse.c.original for unmodified version) - * Added line 713 of xmlparse.c to suppress compiling error. - * Apply expat patch, Fix double free error. - https://github.com/libexpat/libexpat/commit/7ae9c3d3af433cd4defe95234eae7dc8ed15637f - * Apply expat patch. expat 2.2.0 fixed CVE-2016-0718 but cause - other regression. expat's issue number is #539. - https://github.com/libexpat/libexpat/commit/af507cef2c93cb8d40062a0abe43a4f4e9158fb2 - https://sourceforge.net/p/expat/bugs/539/ - lib/xmltok.c (see xmltok.c.original for unmodified version) - Also expat issue #539. - https://github.com/libexpat/libexpat/commit/896b6c1fd3b842f377d1b62135dccf0a579cf65d - lib/expat_external.h(see expat_external.h for unmodified version) - * Disallow adding symbol visibility attribute automatically to - function for static linked library. - Added files: - lib/expat_config.h (a generated config file) +Import process: + git clone https://github.com/libexpat/libexpat.git + cd libexpat/expat + ./buildconf.sh + ./configure + cp expat_config.h $CHROMIUM_SRC/third_party/expat/files/lib + cd lib + cp *.c *.def *.h $CHROMIUM_SRC/third_party/expat/files/lib + cd $CHROMIUM_SRC/third_party/expat + patch -p3 < 0001-Do-not-claim-getrandom.patch - Old CVE-2015-1283 fix for expat 2.1.0 from mozilla hg - https://hg.mozilla.org/releases/mozilla-esr31/rev/2f3e78643f5c - is included in expat 2.2.0. - https://github.com/libexpat/libexpat/commit/ba0f9c3b40c264b8dd392e02a7a060a8fa54f032 +Patches: + 0001-Do-not-claim-getrandom.patch: + * Not all platforms have getrandom. + +Added files: + lib/expat_config.h (a generated config file) diff --git a/chromium/third_party/expat/files/AUTHORS b/chromium/third_party/expat/files/AUTHORS new file mode 100644 index 00000000000..99475bb1b2e --- /dev/null +++ b/chromium/third_party/expat/files/AUTHORS @@ -0,0 +1,10 @@ +Expat is brought to you by: + +Clark Cooper +Fred L. Drake, Jr. +Greg Stein +James Clark +Karl Waclawek +Rhodri James +Sebastian Pipping +Steven Solie diff --git a/chromium/third_party/expat/files/COPYING b/chromium/third_party/expat/files/COPYING index 092c83baee1..8d288f0f28f 100644 --- a/chromium/third_party/expat/files/COPYING +++ b/chromium/third_party/expat/files/COPYING @@ -1,5 +1,5 @@ Copyright (c) 1998-2000 Thai Open Source Software Center Ltd and Clark Cooper -Copyright (c) 2001-2016 Expat maintainers +Copyright (c) 2001-2017 Expat maintainers Permission is hereby granted, free of charge, to any person obtaining a copy of this software and associated documentation files (the diff --git a/chromium/third_party/expat/files/Changes b/chromium/third_party/expat/files/Changes index 583c8685762..7fb561eab68 100644 --- a/chromium/third_party/expat/files/Changes +++ b/chromium/third_party/expat/files/Changes @@ -1,3 +1,478 @@ +NOTE: We are looking for help with a few things: + https://github.com/libexpat/libexpat/labels/help%20wanted + If you can help, please get in touch. Thanks! + +Release x.x.x xxx xxxxxxxxx xx xxxx + Other changes: + examples: Drop executable bits from elements.c + +Release 2.2.8 Fri Septemper 13 2019 + Security fixes: + #317 #318 CVE-2019-15903 -- Fix heap overflow triggered by + XML_GetCurrentLineNumber (or XML_GetCurrentColumnNumber), + and deny internal entities closing the doctype; + fixed in commit c20b758c332d9a13afbbb276d30db1d183a85d43 + + Bug fixes: + #240 Fix cases where XML_StopParser did not have any effect + when called from inside of an end element handler + #341 xmlwf: Fix exit code for operation without "-d DIRECTORY"; + previously, only "-d DIRECTORY" would give you a proper + exit code: + # xmlwf -d . <<<'<not well-formed>' 2>/dev/null ; echo $? + 2 + # xmlwf <<<'<not well-formed>' 2>/dev/null ; echo $? + 0 + Now both cases return exit code 2. + + Other changes: + #299 #302 Windows: Replace LoadLibrary hack to access + unofficial API function SystemFunction036 (RtlGenRandom) + by using official API function rand_s (needs WinXP+) + #325 Windows: Drop support for Visual Studio <=7.1/2003 + and document supported compilers in README.md + #286 Windows: Remove COM code from xmlwf; in case it turns + out needed later, there will be a dedicated repository + below https://github.com/libexpat/ for that code + #322 Windows: Remove explicit MSVC solution and project files. + You can generate Visual Studio solution files through + CMake, e.g.: cmake -G"Visual Studio 15 2017" . + #338 xmlwf: Make "xmlwf -h" help output more friendly + #339 examples: Improve elements.c + #244 #264 Autotools: Add argument --enable-xml-attr-info + #239 #301 Autotools: Add arguments + --with-getrandom + --without-getrandom + --with-sys-getrandom + --without-sys-getrandom + #312 #343 Autotools: Fix linking issues with "./configure LD=clang" + Autotools: Fix "make run-xmltest" for out-of-source builds + #329 #336 CMake: Pull all options from Expat <=2.2.7 into namespace + prefix EXPAT_ with the exception of DOCBOOK_TO_MAN: + - BUILD_doc -> EXPAT_BUILD_DOCS (plural) + - BUILD_examples -> EXPAT_BUILD_EXAMPLES + - BUILD_shared -> EXPAT_SHARED_LIBS + - BUILD_tests -> EXPAT_BUILD_TESTS + - BUILD_tools -> EXPAT_BUILD_TOOLS + - DOCBOOK_TO_MAN -> DOCBOOK_TO_MAN (unchanged) + - INSTALL -> EXPAT_ENABLE_INSTALL + - MSVC_USE_STATIC_CRT -> EXPAT_MSVC_STATIC_CRT + - USE_libbsd -> EXPAT_WITH_LIBBSD + - WARNINGS_AS_ERRORS -> EXPAT_WARNINGS_AS_ERRORS + - XML_CONTEXT_BYTES -> EXPAT_CONTEXT_BYTES + - XML_DEV_URANDOM -> EXPAT_DEV_URANDOM + - XML_DTD -> EXPAT_DTD + - XML_NS -> EXPAT_NS + - XML_UNICODE -> EXPAT_CHAR_TYPE=ushort (!) + - XML_UNICODE_WCHAR_T -> EXPAT_CHAR_TYPE=wchar_t (!) + #244 #264 CMake: Add argument -DEXPAT_ATTR_INFO=(ON|OFF), + default OFF + #326 CMake: Add argument -DEXPAT_LARGE_SIZE=(ON|OFF), + default OFF + #328 CMake: Add argument -DEXPAT_MIN_SIZE=(ON|OFF), + default OFF + #239 #277 CMake: Add arguments + -DEXPAT_WITH_GETRANDOM=(ON|OFF|AUTO), default AUTO + -DEXPAT_WITH_SYS_GETRANDOM=(ON|OFF|AUTO), default AUTO + #326 CMake: Install expat_config.h to include directory + #326 CMake: Generate and install configuration files for + future find_package(expat [..] CONFIG [..]) + CMake: Now produces a summary of applied configuration + CMake: Require C++ compiler only when tests are enabled + #330 CMake: Fix compilation for 16bit character types, + i.e. ex -DXML_UNICODE=ON (and ex -DXML_UNICODE_WCHAR_T=ON) + #265 CMake: Fix linking with MinGW + #330 CMake: Add full support for MinGW; to enable, use + -DCMAKE_TOOLCHAIN_FILE=[expat]/cmake/mingw-toolchain.cmake + #330 CMake: Port "make run-xmltest" from GNU Autotools to CMake + #316 CMake: Windows: Make binary postfix match MSVC + Old: expat[d].lib + New: expat[w][d][MD|MT].lib + CMake: Migrate files from Windows to Unix line endings + #308 CMake: Integrate OSS-Fuzz fuzzers, option + -DEXPAT_BUILD_FUZZERS=(ON|OFF), default OFF + #14 Drop an OpenVMS support leftover + #235 #268 .. + #270 #310 .. + #313 #331 #333 Address compiler warnings + #282 #283 .. + #284 #285 Address cppcheck warnings + #294 #295 Address Clang Static Analyzer warnings + #24 #293 Mass-apply clang-format 9 (and ensure conformance during CI) + Version info bumped from 7:9:6 to 7:10:6 + + Special thanks to: + David Loffredo + Joonun Jang + Khajapasha Mohammed + Kishore Kunche + Marco Maggi + Mitch Phillips + Rolf Ade + xantares + Zhongyuan Zhou + +Release 2.2.7 Wed June 19 2019 + Security fixes: + #186 #262 CVE-2018-20843 -- Fix extraction of namespace prefixes from + XML names; XML names with multiple colons could end up in + the wrong namespace, and take a high amount of RAM and CPU + resources while processing, opening the door to + use for denial-of-service attacks + + Other changes: + #195 #197 Autotools/CMake: Utilize -fvisibility=hidden to stop + exporting non-API symbols + #227 Autotools: Add --without-examples and --without-tests + #228 Autotools: Modernize configure.ac + #245 #246 Autotools: Fix check for -fvisibility=hidden for Clang + #247 #248 Autotools: Fix compilation for lack of docbook2x-man + #236 #258 Autotools: Produce .tar.{gz,lz,xz} release archives + #212 CMake: Make libdir of pkgconfig expat.pc support multilib + #158 #263 CMake: Build man page in PROJECT_BINARY_DIR not _SOURCE_DIR + #219 Remove fallback to bcopy, assume that memmove(3) exists + #257 Use portable "/usr/bin/env bash" shebang (e.g. for OpenBSD) + #243 Windows: Fix syntax of .def module definition files + Version info bumped from 7:8:6 to 7:9:6 + + Special thanks to: + Benjamin Peterson + Caolán McNamara + Hanno Böck + KangLin + Kishore Kunche + Marco Maggi + Rhodri James + Sebastian Dröge + userwithuid + Yury Gribov + +Release 2.2.6 Sun August 12 2018 + Bug fixes: + #170 #206 Avoid doing arithmetic with NULL pointers in XML_GetBuffer + #204 #205 Fix 2.2.5 regression with suspend-resume while parsing + a document like '<root/>' + + Other changes: + #165 #168 Autotools: Fix docbook-related configure syntax error + #166 Autotools: Avoid grep option `-q` for Solaris + #167 Autotools: Support + ./configure DOCBOOK_TO_MAN="xmlto man --skip-validation" + #159 #167 Autotools: Support DOCBOOK_TO_MAN command which produces + xmlwf.1 rather than XMLWF.1; also covers case insensitive + file systems + #181 Autotools: Drop -rpath option passed to libtool + #188 Autotools: Detect and deny SGML docbook2man as ours is XML + #188 Autotools/CMake: Support command db2x_docbook2man as well + #174 CMake: Introduce option WARNINGS_AS_ERRORS, defaults to OFF + #184 #185 CMake: Introduce option MSVC_USE_STATIC_CRT, defaults to OFF + #207 #208 CMake: Introduce option XML_UNICODE and XML_UNICODE_WCHAR_T, + both defaulting to OFF + #175 CMake: Prefer check_symbol_exists over check_function_exists + #176 CMake: Create the same pkg-config file as with GNU Autotools + #178 #179 CMake: Use GNUInstallDirs module to set proper defaults for + install directories + #208 CMake: Utilize expat_config.h.cmake for XML_DEV_URANDOM + #180 Windows: Fix compilation of test suite for Visual Studio 2008 + #131 #173 #202 Address compiler warnings + #187 #190 #200 Fix miscellaneous typos + Version info bumped from 7:7:6 to 7:8:6 + + Special thanks to: + Anton Maklakov + Benjamin Peterson + Brad King + Franek Korta + Frank Rast + Joe Orton + luzpaz + Pedro Vicente + Rainer Jung + Rhodri James + Rolf Ade + Rolf Eike Beer + Thomas Beutlich + Tomasz Kłoczko + +Release 2.2.5 Tue October 31 2017 + Bug fixes: + #8 If the parser runs out of memory, make sure its internal + state reflects the memory it actually has, not the memory + it wanted to have. + #11 The default handler wasn't being called when it should for + a SYSTEM or PUBLIC doctype if an entity declaration handler + was registered. + #137 #138 Fix a case of mistakenly reported parsing success where + XML_StopParser was called from an element handler + #162 Function XML_ErrorString was returning NULL rather than + a message for code XML_ERROR_INVALID_ARGUMENT + introduced with release 2.2.1 + + Other changes: + #106 xmlwf: Add argument -N adding notation declarations + #75 #106 Test suite: Resolve expected failure cases where xmlwf + output was incomplete + #127 Windows: Fix test suite compilation + #126 #127 Windows: Fix compilation for Visual Studio 2012 + Windows: Upgrade shipped project files to Visual Studio 2017 + #33 #132 tests: Mass-fix compilation for XML_UNICODE_WCHAR_T + #129 examples: Fix compilation for XML_UNICODE_WCHAR_T + #130 benchmark: Fix compilation for XML_UNICODE_WCHAR_T + #144 xmlwf: Fix compilation for XML_UNICODE_WCHAR_T; still needs + Windows or MinGW for 2-byte wchar_t + #9 Address two Clang Static Analyzer false positives + #59 Resolve troublesome macros hiding parser struct membership + and dereferencing that pointer + #6 Resolve superfluous internal malloc/realloc switch + #153 #155 Improve docbook2x-man detection + #160 Undefine NDEBUG in the test suite (rather than rejecting it) + #161 Address compiler warnings + Version info bumped from 7:6:6 to 7:7:6 + + Special thanks to: + Benbuck Nason + Hans Wennborg + José Gutiérrez de la Concha + Pedro Monreal Gonzalez + Rhodri James + Rolf Ade + Stephen Groat + and + Core Infrastructure Initiative + +Release 2.2.4 Sat August 19 2017 + Bug fixes: + #115 Fix copying of partial characters for UTF-8 input + + Other changes: + #109 Fix "make check" for non-x86 architectures that default + to unsigned type char (-128..127 rather than 0..255) + #109 coverage.sh: Cover -funsigned-char + Autotools: Introduce --without-xmlwf argument + #65 Autotools: Replace handwritten Makefile with GNU Automake + #43 CMake: Auto-detect high quality entropy extractors, add new + option USE_libbsd=ON to use arc4random_buf of libbsd + #74 CMake: Add -fno-strict-aliasing only where supported + #114 CMake: Always honor manually set BUILD_* options + #114 CMake: Compile man page if docbook2x-man is available, only + #117 Include file tests/xmltest.log.expected in source tarball + (required for "make run-xmltest") + #117 Include (existing) Visual Studio 2013 files in source tarball + Improve test suite error output + #111 Fix some typos in documentation + Version info bumped from 7:5:6 to 7:6:6 + + Special thanks to: + Jakub Wilk + Joe Orton + Lin Tian + Rolf Eike Beer + +Release 2.2.3 Wed August 2 2017 + Security fixes: + #82 CVE-2017-11742 -- Windows: Fix DLL hijacking vulnerability + using Steve Holme's LoadLibrary wrapper for/of cURL + + Bug fixes: + #85 Fix a dangling pointer issue related to realloc + + Other changes: + Increase code coverage + #91 Linux: Allow getrandom to fail if nonblocking pool has not + yet been initialized and read /dev/urandom then, instead. + This is in line with what recent Python does. + #81 Pre-10.7/Lion macOS: Support entropy from arc4random + #86 Check that a UTF-16 encoding in an XML declaration has the + right endianness + #4 #5 #7 Recover correctly when some reallocations fail + Repair "./configure && make" for systems without any + provider of high quality entropy + and try reading /dev/urandom on those + Ensure that user-defined character encodings have converter + functions when they are needed + Fix mis-leading description of argument -c in xmlwf.1 + Rely on macro HAVE_ARC4RANDOM_BUF (rather than __CloudABI__) + for CloudABI + #100 Fix use of SIPHASH_MAIN in siphash.h + #23 Test suite: Fix memory leaks + Version info bumped from 7:4:6 to 7:5:6 + + Special thanks to: + Chanho Park + Joe Orton + Pascal Cuoq + Rhodri James + Simon McVittie + Vadim Zeitlin + Viktor Szakats + and + Core Infrastructure Initiative + +Release 2.2.2 Wed July 12 2017 + Security fixes: + #43 Protect against compilation without any source of high + quality entropy enabled, e.g. with CMake build system; + commit ff0207e6076e9828e536b8d9cd45c9c92069b895 + #60 Windows with _UNICODE: + Unintended use of LoadLibraryW with a non-wide string + resulted in failure to load advapi32.dll and degradation + in quality of used entropy when compiled with _UNICODE for + Windows; you can launch existing binaries with + EXPAT_ENTROPY_DEBUG=1 in the environment to inspect the + quality of entropy used during runtime; commits + * 95b95032f907ef1cd17ee7a9a1768010a825d61d + * 73a5a2e9c081f49f2d775cf7ced864158b68dc80 + [MOX-006] Fix non-NULL parser parameter validation in XML_Parse; + resulted in NULL dereference, previously; + commit ac256dafdffc9622ab0dc2c62fcecb0dfcfa71fe + + Bug fixes: + #69 Fix improper use of unsigned long long integer literals + + Other changes: + #73 Start requiring a C99 compiler + #49 Fix "==" Bashism in configure script + #50 Fix too eager getrandom detection for Debian GNU/kFreeBSD + #52 and macOS + #51 Address lack of stdint.h in Visual Studio 2003 to 2008 + #58 Address compile warnings + #68 Fix "./buildconf.sh && ./configure" for some versions + of Dash for /bin/sh + #72 CMake: Ease use of Expat in context of a parent project + with multiple CMakeLists.txt files + #72 CMake: Resolve mistaken executable permissions + #76 Address compile warning with -DNDEBUG (not recommended!) + #77 Address compile warning about macro redefinition + + Special thanks to: + Alexander Bluhm + Ben Boeckel + Cătălin Răceanu + Kerin Millar + László Böszörményi + S. P. Zeidler + Segev Finer + Václav Slavík + Victor Stinner + Viktor Szakats + and + Radically Open Security + +Release 2.2.1 Sat June 17 2017 + Security fixes: + CVE-2017-9233 -- External entity infinite loop DoS + Details: https://libexpat.github.io/doc/cve-2017-9233/ + Commit c4bf96bb51dd2a1b0e185374362ee136fe2c9d7f + [MOX-002] CVE-2016-9063 -- Detect integer overflow; commit + d4f735b88d9932bd5039df2335eefdd0723dbe20 + (Fixed version of existing downstream patches!) + (SF.net) #539 Fix regression from fix to CVE-2016-0718 cutting off + longer tag names; commits + * 896b6c1fd3b842f377d1b62135dccf0a579cf65d + * af507cef2c93cb8d40062a0abe43a4f4e9158fb2 + #16 * 0dbbf43fdb20f593ddf4fa1ff67288000dd4a7fd + #25 More integer overflow detection (function poolGrow); commits + * 810b74e4703dcfdd8f404e3cb177d44684775143 + * 44178553f3539ce69d34abee77a05e879a7982ac + [MOX-002] Detect overflow from len=INT_MAX call to XML_Parse; commits + * 4be2cb5afcc018d996f34bbbce6374b7befad47f + * 7e5b71b748491b6e459e5c9a1d090820f94544d8 + [MOX-005] #30 Use high quality entropy for hash initialization: + * arc4random_buf on BSD, systems with libbsd + (when configured with --with-libbsd), CloudABI + * RtlGenRandom on Windows XP / Server 2003 and later + * getrandom on Linux 3.17+ + In a way, that's still part of CVE-2016-5300. + https://github.com/libexpat/libexpat/pull/30/commits + [MOX-005] For the low quality entropy extraction fallback code, + the parser instance address can no longer leak, commit + 04ad658bd3079dd15cb60fc67087900f0ff4b083 + [MOX-003] Prevent use of uninitialised variable; commit + [MOX-004] a4dc944f37b664a3ca7199c624a98ee37babdb4b + Add missing parameter validation to public API functions + and dedicated error code XML_ERROR_INVALID_ARGUMENT: + [MOX-006] * NULL checks; commits + * d37f74b2b7149a3a95a680c4c4cd2a451a51d60a (merge/many) + * 9ed727064b675b7180c98cb3d4f75efba6966681 + * 6a747c837c50114dfa413994e07c0ba477be4534 + * Negative length (XML_Parse); commit + [MOX-002] 70db8d2538a10f4c022655d6895e4c3e78692e7f + [MOX-001] #35 Change hash algorithm to William Ahern's version of SipHash + to go further with fixing CVE-2012-0876. + https://github.com/libexpat/libexpat/pull/39/commits + + Bug fixes: + #32 Fix sharing of hash salt across parsers; + relevant where XML_ExternalEntityParserCreate is called + prior to XML_Parse, in particular (e.g. FBReader) + #28 xmlwf: Auto-disable use of memory-mapping (and parsing + as a single chunk) for files larger than ~1 GB (2^30 bytes) + rather than failing with error "out of memory" + #3 Fix double free after malloc failure in DTD code; commit + 7ae9c3d3af433cd4defe95234eae7dc8ed15637f + #17 Fix memory leak on parser error for unbound XML attribute + prefix with new namespaces defined in the same tag; + found by Google's OSS-Fuzz; commits + * 16f87daae5a16132e479e4f71862128c7a915c73 + * b47dbc9745932c160893d433220e462bd605f8cd + xmlwf on Windows: Add missing calls to CloseHandle + + New features: + #30 Introduced environment switch EXPAT_ENTROPY_DEBUG=1 + for runtime debugging of entropy extraction + + Other changes: + Increase code coverage + #33 Reject use of XML_UNICODE_WCHAR_T with sizeof(wchar_t) != 2; + XML_UNICODE_WCHAR_T was never meant to be used outside + of Windows; 4-byte wchar_t is common on Linux + (SF.net) #538 Start using -fno-strict-aliasing + (SF.net) #540 Support compilation against cloudlibc of CloudABI + Allow MinGW cross-compilation + (SF.net) #534 CMake: Introduce option "BUILD_doc" (enabled by default) + to bypass compilation of the xmlwf.1 man page + (SF.net) pr2 CMake: Introduce option "INSTALL" (enabled by default) + to bypass installation of expat files + CMake: Fix ninja support + Autotools: Add parameters --enable-xml-context [COUNT] + and --disable-xml-context; default of context of 1024 + bytes enabled unchanged + #14 Drop AmigaOS 4.x code and includes + #14 Drop ancient build systems: + * Borland C++ Builder + * OpenVMS + * Open Watcom + * Visual Studio 6.0 + * Pre-X Mac OS (MPW Makefile) + If you happen to rely on some of these, please get in + touch for joining with maintenance. + #10 Move from WIN32 to _WIN32 + #13 Fix "make run-xmltest" order instability + Address compile warnings + Bump version info from 7:2:6 to 7:3:6 + Add AUTHORS file + + Infrastructure: + #1 Migrate from SourceForge to GitHub (except downloads): + https://github.com/libexpat/ + #1 Re-create http://libexpat.org/ project website + Start utilizing Travis CI + + Special thanks to: + Andy Wang + Don Lewis + Ed Schouten + Karl Waclawek + Pascal Cuoq + Rhodri James + Sergei Nikulov + Tobias Taschner + Viktor Szakats + and + Core Infrastructure Initiative + Mozilla Foundation (MOSS Track 3: Secure Open Source) + Radically Open Security + Release 2.2.0 Tue June 21 2016 Security fixes: #537 CVE-2016-0718 -- Fix crash on malformed input @@ -63,24 +538,25 @@ Release 2.1.1 Sat March 12 2016 libtool now invoked with --verbose Release 2.1.0 Sat March 24 2012 + - Security fixes: + #2958794: CVE-2012-1148 - Memory leak in poolGrow. + #2895533: CVE-2012-1147 - Resource leak in readfilemap.c. + #3496608: CVE-2012-0876 - Hash DOS attack. + #2894085: CVE-2009-3560 - Buffer over-read and crash in big2_toUtf8(). + #1990430: CVE-2009-3720 - Parser crash with special UTF-8 sequences. - Bug Fixes: #1742315: Harmful XML_ParserCreateNS suggestion. - #2895533: CVE-2012-1147 - Resource leak in readfilemap.c. #1785430: Expat build fails on linux-amd64 with gcc version>=4.1 -O3. #1983953, 2517952, 2517962, 2649838: Build modifications using autoreconf instead of buildconf.sh. #2815947, #2884086: OBJEXT and EXEEXT support while building. - #1990430: CVE-2009-3720 - Parser crash with special UTF-8 sequences. #2517938: xmlwf should return non-zero exit status if not well-formed. #2517946: Wrong statement about XMLDecl in xmlwf.1 and xmlwf.sgml. #2855609: Dangling positionPtr after error. - #2894085: CVE-2009-3560 - Buffer over-read and crash in big2_toUtf8(). - #2958794: CVE-2012-1148 - Memory leak in poolGrow. #2990652: CMake support. #3010819: UNEXPECTED_STATE with a trailing "%" in entity value. - #3206497: Unitialized memory returned from XML_Parse. + #3206497: Uninitialized memory returned from XML_Parse. #3287849: make check fails on mingw-w64. - #3496608: CVE-2012-0876 - Hash DOS attack. - Patches: #1749198: pkg-config support. #3010222: Fix for bug #3010819. diff --git a/chromium/third_party/expat/files/MANIFEST b/chromium/third_party/expat/files/MANIFEST index afb9acacdf0..f602b4b206a 100644 --- a/chromium/third_party/expat/files/MANIFEST +++ b/chromium/third_party/expat/files/MANIFEST @@ -1,44 +1,4 @@ -amiga/launch.c -amiga/expat_68k.c -amiga/expat_68k.h -amiga/expat_68k_handler_stubs.c -amiga/expat_base.h -amiga/expat_vectors.c -amiga/expat_lib.c -amiga/expat.xml -amiga/README.txt -amiga/Makefile -amiga/include/proto/expat.h -amiga/include/libraries/expat.h -amiga/include/interfaces/expat.h -amiga/include/inline4/expat.h -bcb5/README.txt -bcb5/all_projects.bpg -bcb5/elements.bpf -bcb5/elements.bpr -bcb5/elements.mak -bcb5/expat.bpf -bcb5/expat.bpr -bcb5/expat.mak -bcb5/expat_static.bpf -bcb5/expat_static.bpr -bcb5/expat_static.mak -bcb5/expatw.bpf -bcb5/expatw.bpr -bcb5/expatw.mak -bcb5/expatw_static.bpf -bcb5/expatw_static.bpr -bcb5/expatw_static.mak -bcb5/libexpat_mtd.def -bcb5/libexpatw_mtd.def -bcb5/makefile.mak -bcb5/outline.bpf -bcb5/outline.bpr -bcb5/outline.mak -bcb5/setup.bat -bcb5/xmlwf.bpf -bcb5/xmlwf.bpr -bcb5/xmlwf.mak +AUTHORS doc/expat.png doc/reference.html doc/style.css @@ -52,14 +12,14 @@ Changes ConfigureChecks.cmake MANIFEST Makefile.in -README +README.md configure configure.ac expat_config.h.in expat_config.h.cmake expat.pc.in -expat.dsw aclocal.m4 +run.sh.in conftools/PrintPath conftools/ac_c_bigendian_cross.m4 conftools/expat.m4 @@ -75,26 +35,19 @@ m4/ltoptions.m4 m4/ltsugar.m4 m4/lt~obsolete.m4 examples/elements.c -examples/elements.dsp examples/outline.c -examples/outline.dsp -lib/Makefile.MPW -lib/amigaconfig.h lib/ascii.h lib/asciitab.h -lib/expat.dsp lib/expat.h lib/expat_external.h -lib/expat_static.dsp -lib/expatw.dsp -lib/expatw_static.dsp lib/iasciitab.h lib/internal.h lib/latin1tab.h lib/libexpat.def lib/libexpatw.def -lib/macconfig.h +lib/loadlibrary.c lib/nametab.h +lib/siphash.h lib/utf8tab.h lib/winconfig.h lib/xmlparse.c @@ -107,19 +60,16 @@ lib/xmltok_impl.h lib/xmltok_ns.c tests/benchmark/README.txt tests/benchmark/benchmark.c -tests/benchmark/benchmark.dsp -tests/benchmark/benchmark.dsw tests/README.txt tests/chardata.c tests/chardata.h +tests/memcheck.c +tests/memcheck.h tests/minicheck.c tests/minicheck.h tests/runtests.c tests/runtestspp.cpp tests/xmltest.sh -vms/README.vms -vms/descrip.mms -vms/expat_config.h win32/MANIFEST.txt win32/README.txt win32/expat.iss @@ -137,5 +87,4 @@ xmlwf/xmlmime.h xmlwf/xmltchar.h xmlwf/xmlurl.h xmlwf/xmlwf.c -xmlwf/xmlwf.dsp xmlwf/xmlwin32url.cxx diff --git a/chromium/third_party/expat/files/README b/chromium/third_party/expat/files/README deleted file mode 100644 index a7d28450d54..00000000000 --- a/chromium/third_party/expat/files/README +++ /dev/null @@ -1,139 +0,0 @@ - - Expat, Release 2.2.0 - -This is Expat, a C library for parsing XML, written by James Clark. -Expat is a stream-oriented XML parser. This means that you register -handlers with the parser before starting the parse. These handlers -are called when the parser discovers the associated structures in the -document being parsed. A start tag is an example of the kind of -structures for which you may register handlers. - -Windows users should use the expat_win32bin package, which includes -both precompiled libraries and executables, and source code for -developers. - -Expat is free software. You may copy, distribute, and modify it under -the terms of the License contained in the file COPYING distributed -with this package. This license is the same as the MIT/X Consortium -license. - -Versions of Expat that have an odd minor version (the middle number in -the release above), are development releases and should be considered -as beta software. Releases with even minor version numbers are -intended to be production grade software. - -If you are building Expat from a check-out from the CVS repository, -you need to run a script that generates the configure script using the -GNU autoconf and libtool tools. To do this, you need to have -autoconf 2.58 or newer. Run the script like this: - - ./buildconf.sh - -Once this has been done, follow the same instructions as for building -from a source distribution. - -To build Expat from a source distribution, you first run the -configuration shell script in the top level distribution directory: - - ./configure - -There are many options which you may provide to configure (which you -can discover by running configure with the --help option). But the -one of most interest is the one that sets the installation directory. -By default, the configure script will set things up to install -libexpat into /usr/local/lib, expat.h into /usr/local/include, and -xmlwf into /usr/local/bin. If, for example, you'd prefer to install -into /home/me/mystuff/lib, /home/me/mystuff/include, and -/home/me/mystuff/bin, you can tell configure about that with: - - ./configure --prefix=/home/me/mystuff - -Another interesting option is to enable 64-bit integer support for -line and column numbers and the over-all byte index: - - ./configure CPPFLAGS=-DXML_LARGE_SIZE - -However, such a modification would be a breaking change to the ABI -and is therefore not recommended for general use - e.g. as part of -a Linux distribution - but rather for builds with special requirements. - -After running the configure script, the "make" command will build -things and "make install" will install things into their proper -location. Have a look at the "Makefile" to learn about additional -"make" options. Note that you need to have write permission into -the directories into which things will be installed. - -If you are interested in building Expat to provide document -information in UTF-16 encoding rather than the default UTF-8, follow -these instructions (after having run "make distclean"): - - 1. For UTF-16 output as unsigned short (and version/error - strings as char), run: - - ./configure CPPFLAGS=-DXML_UNICODE - - For UTF-16 output as wchar_t (incl. version/error strings), - run: - - ./configure CFLAGS="-g -O2 -fshort-wchar" \ - CPPFLAGS=-DXML_UNICODE_WCHAR_T - - 2. Edit the MakeFile, changing: - - LIBRARY = libexpat.la - - to: - - LIBRARY = libexpatw.la - - (Note the additional "w" in the library name.) - - 3. Run "make buildlib" (which builds the library only). - Or, to save step 2, run "make buildlib LIBRARY=libexpatw.la". - - 4. Run "make installlib" (which installs the library only). - Or, if step 2 was omitted, run "make installlib LIBRARY=libexpatw.la". - -Using DESTDIR or INSTALL_ROOT is enabled, with INSTALL_ROOT being the default -value for DESTDIR, and the rest of the make file using only DESTDIR. -It works as follows: - $ make install DESTDIR=/path/to/image -overrides the in-makefile set DESTDIR, while both - $ INSTALL_ROOT=/path/to/image make install - $ make install INSTALL_ROOT=/path/to/image -use DESTDIR=$(INSTALL_ROOT), even if DESTDIR eventually is defined in the -environment, because variable-setting priority is -1) commandline -2) in-makefile -3) environment - -Note: This only applies to the Expat library itself, building UTF-16 versions -of xmlwf and the tests is currently not supported. - -Note for Solaris users: The "ar" command is usually located in -"/usr/ccs/bin", which is not in the default PATH. You will need to -add this to your path for the "make" command, and probably also switch -to GNU make (the "make" found in /usr/ccs/bin does not seem to work -properly -- apparently it does not understand .PHONY directives). If -you're using ksh or bash, use this command to build: - - PATH=/usr/ccs/bin:$PATH make - -When using Expat with a project using autoconf for configuration, you -can use the probing macro in conftools/expat.m4 to determine how to -include Expat. See the comments at the top of that file for more -information. - -A reference manual is available in the file doc/reference.html in this -distribution. - -The homepage for this project is http://www.libexpat.org/. There -are links there to connect you to the bug reports page. If you need -to report a bug when you don't have access to a browser, you may also -send a bug report by email to expat-bugs@mail.libexpat.org. - -Discussion related to the direction of future expat development takes -place on expat-discuss@mail.libexpat.org. Archives of this list and -other Expat-related lists may be found at: - - http://mail.libexpat.org/mailman/listinfo/ diff --git a/chromium/third_party/expat/files/lib/amigaconfig.h b/chromium/third_party/expat/files/lib/amigaconfig.h deleted file mode 100644 index 49c92c70149..00000000000 --- a/chromium/third_party/expat/files/lib/amigaconfig.h +++ /dev/null @@ -1,29 +0,0 @@ -#ifndef AMIGACONFIG_H -#define AMIGACONFIG_H - -/* 1234 = LIL_ENDIAN, 4321 = BIGENDIAN */ -#define BYTEORDER 4321 - -/* Define to 1 if you have the `bcopy' function. */ -#define HAVE_BCOPY 1 - -/* Define to 1 if you have the `memmove' function. */ -#define HAVE_MEMMOVE 1 - -/* Define to 1 if you have the <unistd.h> header file. */ -#define HAVE_UNISTD_H 1 - -/* whether byteorder is bigendian */ -#define WORDS_BIGENDIAN - -/* Define to specify how much context to retain around the current parse - point. */ -#define XML_CONTEXT_BYTES 1024 - -/* Define to make parameter entity parsing functionality available. */ -#define XML_DTD - -/* Define to make XML Namespaces functionality available. */ -#define XML_NS - -#endif /* AMIGACONFIG_H */ diff --git a/chromium/third_party/expat/files/lib/ascii.h b/chromium/third_party/expat/files/lib/ascii.h index d10530b09bd..c3587e57332 100644 --- a/chromium/third_party/expat/files/lib/ascii.h +++ b/chromium/third_party/expat/files/lib/ascii.h @@ -1,5 +1,33 @@ -/* Copyright (c) 1998, 1999 Thai Open Source Software Center Ltd - See the file COPYING for copying permission. +/* + __ __ _ + ___\ \/ /_ __ __ _| |_ + / _ \\ /| '_ \ / _` | __| + | __// \| |_) | (_| | |_ + \___/_/\_\ .__/ \__,_|\__| + |_| XML parser + + Copyright (c) 1997-2000 Thai Open Source Software Center Ltd + Copyright (c) 2000-2017 Expat development team + Licensed under the MIT license: + + Permission is hereby granted, free of charge, to any person obtaining + a copy of this software and associated documentation files (the + "Software"), to deal in the Software without restriction, including + without limitation the rights to use, copy, modify, merge, publish, + distribute, sublicense, and/or sell copies of the Software, and to permit + persons to whom the Software is furnished to do so, subject to the + following conditions: + + The above copyright notice and this permission notice shall be included + in all copies or substantial portions of the Software. + + THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN + NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, + DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR + OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE + USE OR OTHER DEALINGS IN THE SOFTWARE. */ #define ASCII_A 0x41 diff --git a/chromium/third_party/expat/files/lib/asciitab.h b/chromium/third_party/expat/files/lib/asciitab.h index 79a15c28ca1..63b1d1b4482 100644 --- a/chromium/third_party/expat/files/lib/asciitab.h +++ b/chromium/third_party/expat/files/lib/asciitab.h @@ -1,36 +1,64 @@ -/* Copyright (c) 1998, 1999 Thai Open Source Software Center Ltd - See the file COPYING for copying permission. +/* + __ __ _ + ___\ \/ /_ __ __ _| |_ + / _ \\ /| '_ \ / _` | __| + | __// \| |_) | (_| | |_ + \___/_/\_\ .__/ \__,_|\__| + |_| XML parser + + Copyright (c) 1997-2000 Thai Open Source Software Center Ltd + Copyright (c) 2000-2017 Expat development team + Licensed under the MIT license: + + Permission is hereby granted, free of charge, to any person obtaining + a copy of this software and associated documentation files (the + "Software"), to deal in the Software without restriction, including + without limitation the rights to use, copy, modify, merge, publish, + distribute, sublicense, and/or sell copies of the Software, and to permit + persons to whom the Software is furnished to do so, subject to the + following conditions: + + The above copyright notice and this permission notice shall be included + in all copies or substantial portions of the Software. + + THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN + NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, + DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR + OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE + USE OR OTHER DEALINGS IN THE SOFTWARE. */ /* 0x00 */ BT_NONXML, BT_NONXML, BT_NONXML, BT_NONXML, -/* 0x04 */ BT_NONXML, BT_NONXML, BT_NONXML, BT_NONXML, -/* 0x08 */ BT_NONXML, BT_S, BT_LF, BT_NONXML, -/* 0x0C */ BT_NONXML, BT_CR, BT_NONXML, BT_NONXML, -/* 0x10 */ BT_NONXML, BT_NONXML, BT_NONXML, BT_NONXML, -/* 0x14 */ BT_NONXML, BT_NONXML, BT_NONXML, BT_NONXML, -/* 0x18 */ BT_NONXML, BT_NONXML, BT_NONXML, BT_NONXML, -/* 0x1C */ BT_NONXML, BT_NONXML, BT_NONXML, BT_NONXML, -/* 0x20 */ BT_S, BT_EXCL, BT_QUOT, BT_NUM, -/* 0x24 */ BT_OTHER, BT_PERCNT, BT_AMP, BT_APOS, -/* 0x28 */ BT_LPAR, BT_RPAR, BT_AST, BT_PLUS, -/* 0x2C */ BT_COMMA, BT_MINUS, BT_NAME, BT_SOL, -/* 0x30 */ BT_DIGIT, BT_DIGIT, BT_DIGIT, BT_DIGIT, -/* 0x34 */ BT_DIGIT, BT_DIGIT, BT_DIGIT, BT_DIGIT, -/* 0x38 */ BT_DIGIT, BT_DIGIT, BT_COLON, BT_SEMI, -/* 0x3C */ BT_LT, BT_EQUALS, BT_GT, BT_QUEST, -/* 0x40 */ BT_OTHER, BT_HEX, BT_HEX, BT_HEX, -/* 0x44 */ BT_HEX, BT_HEX, BT_HEX, BT_NMSTRT, -/* 0x48 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, -/* 0x4C */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, -/* 0x50 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, -/* 0x54 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, -/* 0x58 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_LSQB, -/* 0x5C */ BT_OTHER, BT_RSQB, BT_OTHER, BT_NMSTRT, -/* 0x60 */ BT_OTHER, BT_HEX, BT_HEX, BT_HEX, -/* 0x64 */ BT_HEX, BT_HEX, BT_HEX, BT_NMSTRT, -/* 0x68 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, -/* 0x6C */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, -/* 0x70 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, -/* 0x74 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, -/* 0x78 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_OTHER, -/* 0x7C */ BT_VERBAR, BT_OTHER, BT_OTHER, BT_OTHER, + /* 0x04 */ BT_NONXML, BT_NONXML, BT_NONXML, BT_NONXML, + /* 0x08 */ BT_NONXML, BT_S, BT_LF, BT_NONXML, + /* 0x0C */ BT_NONXML, BT_CR, BT_NONXML, BT_NONXML, + /* 0x10 */ BT_NONXML, BT_NONXML, BT_NONXML, BT_NONXML, + /* 0x14 */ BT_NONXML, BT_NONXML, BT_NONXML, BT_NONXML, + /* 0x18 */ BT_NONXML, BT_NONXML, BT_NONXML, BT_NONXML, + /* 0x1C */ BT_NONXML, BT_NONXML, BT_NONXML, BT_NONXML, + /* 0x20 */ BT_S, BT_EXCL, BT_QUOT, BT_NUM, + /* 0x24 */ BT_OTHER, BT_PERCNT, BT_AMP, BT_APOS, + /* 0x28 */ BT_LPAR, BT_RPAR, BT_AST, BT_PLUS, + /* 0x2C */ BT_COMMA, BT_MINUS, BT_NAME, BT_SOL, + /* 0x30 */ BT_DIGIT, BT_DIGIT, BT_DIGIT, BT_DIGIT, + /* 0x34 */ BT_DIGIT, BT_DIGIT, BT_DIGIT, BT_DIGIT, + /* 0x38 */ BT_DIGIT, BT_DIGIT, BT_COLON, BT_SEMI, + /* 0x3C */ BT_LT, BT_EQUALS, BT_GT, BT_QUEST, + /* 0x40 */ BT_OTHER, BT_HEX, BT_HEX, BT_HEX, + /* 0x44 */ BT_HEX, BT_HEX, BT_HEX, BT_NMSTRT, + /* 0x48 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, + /* 0x4C */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, + /* 0x50 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, + /* 0x54 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, + /* 0x58 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_LSQB, + /* 0x5C */ BT_OTHER, BT_RSQB, BT_OTHER, BT_NMSTRT, + /* 0x60 */ BT_OTHER, BT_HEX, BT_HEX, BT_HEX, + /* 0x64 */ BT_HEX, BT_HEX, BT_HEX, BT_NMSTRT, + /* 0x68 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, + /* 0x6C */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, + /* 0x70 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, + /* 0x74 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, + /* 0x78 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_OTHER, + /* 0x7C */ BT_VERBAR, BT_OTHER, BT_OTHER, BT_OTHER, diff --git a/chromium/third_party/expat/files/lib/expat.h b/chromium/third_party/expat/files/lib/expat.h index 086e24b39c5..6c8eb1fda4a 100644 --- a/chromium/third_party/expat/files/lib/expat.h +++ b/chromium/third_party/expat/files/lib/expat.h @@ -1,19 +1,38 @@ -/* Copyright (c) 1998, 1999, 2000 Thai Open Source Software Center Ltd - See the file COPYING for copying permission. +/* + __ __ _ + ___\ \/ /_ __ __ _| |_ + / _ \\ /| '_ \ / _` | __| + | __// \| |_) | (_| | |_ + \___/_/\_\ .__/ \__,_|\__| + |_| XML parser + + Copyright (c) 1997-2000 Thai Open Source Software Center Ltd + Copyright (c) 2000-2017 Expat development team + Licensed under the MIT license: + + Permission is hereby granted, free of charge, to any person obtaining + a copy of this software and associated documentation files (the + "Software"), to deal in the Software without restriction, including + without limitation the rights to use, copy, modify, merge, publish, + distribute, sublicense, and/or sell copies of the Software, and to permit + persons to whom the Software is furnished to do so, subject to the + following conditions: + + The above copyright notice and this permission notice shall be included + in all copies or substantial portions of the Software. + + THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN + NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, + DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR + OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE + USE OR OTHER DEALINGS IN THE SOFTWARE. */ #ifndef Expat_INCLUDED #define Expat_INCLUDED 1 -#ifdef __VMS -/* 0 1 2 3 0 1 2 3 - 1234567890123456789012345678901 1234567890123456789012345678901 */ -#define XML_SetProcessingInstructionHandler XML_SetProcessingInstrHandler -#define XML_SetUnparsedEntityDeclHandler XML_SetUnparsedEntDeclHandler -#define XML_SetStartNamespaceDeclHandler XML_SetStartNamespcDeclHandler -#define XML_SetExternalEntityRefHandlerArg XML_SetExternalEntRefHandlerArg -#endif - #include <stdlib.h> #include "expat_external.h" @@ -24,10 +43,9 @@ extern "C" { struct XML_ParserStruct; typedef struct XML_ParserStruct *XML_Parser; -/* Should this be defined using stdbool.h when C99 is available? */ typedef unsigned char XML_Bool; -#define XML_TRUE ((XML_Bool) 1) -#define XML_FALSE ((XML_Bool) 0) +#define XML_TRUE ((XML_Bool)1) +#define XML_FALSE ((XML_Bool)0) /* The XML_Status enum gives the possible return values for several API functions. The preprocessor #defines are included so this @@ -95,7 +113,9 @@ enum XML_Error { /* Added in 2.0. */ XML_ERROR_RESERVED_PREFIX_XML, XML_ERROR_RESERVED_PREFIX_XMLNS, - XML_ERROR_RESERVED_NAMESPACE_URI + XML_ERROR_RESERVED_NAMESPACE_URI, + /* Added in 2.2.1. */ + XML_ERROR_INVALID_ARGUMENT }; enum XML_Content_Type { @@ -135,25 +155,23 @@ enum XML_Content_Quant { typedef struct XML_cp XML_Content; struct XML_cp { - enum XML_Content_Type type; - enum XML_Content_Quant quant; - XML_Char * name; - unsigned int numchildren; - XML_Content * children; + enum XML_Content_Type type; + enum XML_Content_Quant quant; + XML_Char *name; + unsigned int numchildren; + XML_Content *children; }; - /* This is called for an element declaration. See above for description of the model argument. It's the caller's responsibility to free model when finished with it. */ -typedef void (XMLCALL *XML_ElementDeclHandler) (void *userData, - const XML_Char *name, - XML_Content *model); +typedef void(XMLCALL *XML_ElementDeclHandler)(void *userData, + const XML_Char *name, + XML_Content *model); XMLPARSEAPI(void) -XML_SetElementDeclHandler(XML_Parser parser, - XML_ElementDeclHandler eldecl); +XML_SetElementDeclHandler(XML_Parser parser, XML_ElementDeclHandler eldecl); /* The Attlist declaration handler is called for *each* attribute. So a single Attlist declaration with multiple attributes declared will @@ -163,17 +181,12 @@ XML_SetElementDeclHandler(XML_Parser parser, value will be NULL in the case of "#REQUIRED". If "isrequired" is true and default is non-NULL, then this is a "#FIXED" default. */ -typedef void (XMLCALL *XML_AttlistDeclHandler) ( - void *userData, - const XML_Char *elname, - const XML_Char *attname, - const XML_Char *att_type, - const XML_Char *dflt, - int isrequired); +typedef void(XMLCALL *XML_AttlistDeclHandler)( + void *userData, const XML_Char *elname, const XML_Char *attname, + const XML_Char *att_type, const XML_Char *dflt, int isrequired); XMLPARSEAPI(void) -XML_SetAttlistDeclHandler(XML_Parser parser, - XML_AttlistDeclHandler attdecl); +XML_SetAttlistDeclHandler(XML_Parser parser, XML_AttlistDeclHandler attdecl); /* The XML declaration handler is called for *both* XML declarations and text declarations. The way to distinguish is that the version @@ -183,15 +196,13 @@ XML_SetAttlistDeclHandler(XML_Parser parser, was no standalone parameter in the declaration, that it was given as no, or that it was given as yes. */ -typedef void (XMLCALL *XML_XmlDeclHandler) (void *userData, - const XML_Char *version, - const XML_Char *encoding, - int standalone); +typedef void(XMLCALL *XML_XmlDeclHandler)(void *userData, + const XML_Char *version, + const XML_Char *encoding, + int standalone); XMLPARSEAPI(void) -XML_SetXmlDeclHandler(XML_Parser parser, - XML_XmlDeclHandler xmldecl); - +XML_SetXmlDeclHandler(XML_Parser parser, XML_XmlDeclHandler xmldecl); typedef struct { void *(*malloc_fcn)(size_t size); @@ -219,7 +230,6 @@ XML_ParserCreate(const XML_Char *encoding); XMLPARSEAPI(XML_Parser) XML_ParserCreateNS(const XML_Char *encoding, XML_Char namespaceSeparator); - /* Constructs a new parser using the memory management suite referred to by memsuite. If memsuite is NULL, then use the standard library memory suite. If namespaceSeparator is non-NULL it creates a parser with @@ -235,7 +245,7 @@ XML_ParserCreate_MM(const XML_Char *encoding, const XML_Char *namespaceSeparator); /* Prepare a parser object to be re-used. This is particularly - valuable when memory allocation overhead is disproportionatly high, + valuable when memory allocation overhead is disproportionately high, such as when a large number of small documnents need to be parsed. All handlers are cleared from the parser, except for the unknownEncodingHandler. The parser's external state is re-initialized @@ -249,31 +259,27 @@ XML_ParserReset(XML_Parser parser, const XML_Char *encoding); /* atts is array of name/value pairs, terminated by 0; names and values are 0 terminated. */ -typedef void (XMLCALL *XML_StartElementHandler) (void *userData, - const XML_Char *name, - const XML_Char **atts); - -typedef void (XMLCALL *XML_EndElementHandler) (void *userData, - const XML_Char *name); +typedef void(XMLCALL *XML_StartElementHandler)(void *userData, + const XML_Char *name, + const XML_Char **atts); +typedef void(XMLCALL *XML_EndElementHandler)(void *userData, + const XML_Char *name); /* s is not 0 terminated. */ -typedef void (XMLCALL *XML_CharacterDataHandler) (void *userData, - const XML_Char *s, - int len); +typedef void(XMLCALL *XML_CharacterDataHandler)(void *userData, + const XML_Char *s, int len); /* target and data are 0 terminated */ -typedef void (XMLCALL *XML_ProcessingInstructionHandler) ( - void *userData, - const XML_Char *target, - const XML_Char *data); +typedef void(XMLCALL *XML_ProcessingInstructionHandler)(void *userData, + const XML_Char *target, + const XML_Char *data); /* data is 0 terminated */ -typedef void (XMLCALL *XML_CommentHandler) (void *userData, - const XML_Char *data); +typedef void(XMLCALL *XML_CommentHandler)(void *userData, const XML_Char *data); -typedef void (XMLCALL *XML_StartCdataSectionHandler) (void *userData); -typedef void (XMLCALL *XML_EndCdataSectionHandler) (void *userData); +typedef void(XMLCALL *XML_StartCdataSectionHandler)(void *userData); +typedef void(XMLCALL *XML_EndCdataSectionHandler)(void *userData); /* This is called for any characters in the XML document for which there is no applicable handler. This includes both characters that @@ -288,25 +294,23 @@ typedef void (XMLCALL *XML_EndCdataSectionHandler) (void *userData); default handler: for example, a comment might be split between multiple calls. */ -typedef void (XMLCALL *XML_DefaultHandler) (void *userData, - const XML_Char *s, - int len); +typedef void(XMLCALL *XML_DefaultHandler)(void *userData, const XML_Char *s, + int len); /* This is called for the start of the DOCTYPE declaration, before any DTD or internal subset is parsed. */ -typedef void (XMLCALL *XML_StartDoctypeDeclHandler) ( - void *userData, - const XML_Char *doctypeName, - const XML_Char *sysid, - const XML_Char *pubid, - int has_internal_subset); +typedef void(XMLCALL *XML_StartDoctypeDeclHandler)(void *userData, + const XML_Char *doctypeName, + const XML_Char *sysid, + const XML_Char *pubid, + int has_internal_subset); /* This is called for the start of the DOCTYPE declaration when the closing > is encountered, but after processing any external subset. */ -typedef void (XMLCALL *XML_EndDoctypeDeclHandler)(void *userData); +typedef void(XMLCALL *XML_EndDoctypeDeclHandler)(void *userData); /* This is called for entity declarations. The is_parameter_entity argument will be non-zero if the entity is a parameter entity, zero @@ -326,20 +330,14 @@ typedef void (XMLCALL *XML_EndDoctypeDeclHandler)(void *userData); Note that is_parameter_entity can't be changed to XML_Bool, since that would break binary compatibility. */ -typedef void (XMLCALL *XML_EntityDeclHandler) ( - void *userData, - const XML_Char *entityName, - int is_parameter_entity, - const XML_Char *value, - int value_length, - const XML_Char *base, - const XML_Char *systemId, - const XML_Char *publicId, - const XML_Char *notationName); +typedef void(XMLCALL *XML_EntityDeclHandler)( + void *userData, const XML_Char *entityName, int is_parameter_entity, + const XML_Char *value, int value_length, const XML_Char *base, + const XML_Char *systemId, const XML_Char *publicId, + const XML_Char *notationName); XMLPARSEAPI(void) -XML_SetEntityDeclHandler(XML_Parser parser, - XML_EntityDeclHandler handler); +XML_SetEntityDeclHandler(XML_Parser parser, XML_EntityDeclHandler handler); /* OBSOLETE -- OBSOLETE -- OBSOLETE This handler has been superseded by the EntityDeclHandler above. @@ -350,24 +348,20 @@ XML_SetEntityDeclHandler(XML_Parser parser, entityName, systemId and notationName arguments will never be NULL. The other arguments may be. */ -typedef void (XMLCALL *XML_UnparsedEntityDeclHandler) ( - void *userData, - const XML_Char *entityName, - const XML_Char *base, - const XML_Char *systemId, - const XML_Char *publicId, - const XML_Char *notationName); +typedef void(XMLCALL *XML_UnparsedEntityDeclHandler)( + void *userData, const XML_Char *entityName, const XML_Char *base, + const XML_Char *systemId, const XML_Char *publicId, + const XML_Char *notationName); /* This is called for a declaration of notation. The base argument is whatever was set by XML_SetBase. The notationName will never be NULL. The other arguments can be. */ -typedef void (XMLCALL *XML_NotationDeclHandler) ( - void *userData, - const XML_Char *notationName, - const XML_Char *base, - const XML_Char *systemId, - const XML_Char *publicId); +typedef void(XMLCALL *XML_NotationDeclHandler)(void *userData, + const XML_Char *notationName, + const XML_Char *base, + const XML_Char *systemId, + const XML_Char *publicId); /* When namespace processing is enabled, these are called once for each namespace declaration. The call to the start and end element @@ -375,14 +369,12 @@ typedef void (XMLCALL *XML_NotationDeclHandler) ( declaration handlers. For an xmlns attribute, prefix will be NULL. For an xmlns="" attribute, uri will be NULL. */ -typedef void (XMLCALL *XML_StartNamespaceDeclHandler) ( - void *userData, - const XML_Char *prefix, - const XML_Char *uri); +typedef void(XMLCALL *XML_StartNamespaceDeclHandler)(void *userData, + const XML_Char *prefix, + const XML_Char *uri); -typedef void (XMLCALL *XML_EndNamespaceDeclHandler) ( - void *userData, - const XML_Char *prefix); +typedef void(XMLCALL *XML_EndNamespaceDeclHandler)(void *userData, + const XML_Char *prefix); /* This is called if the document is not standalone, that is, it has an external subset or a reference to a parameter entity, but does not @@ -393,7 +385,7 @@ typedef void (XMLCALL *XML_EndNamespaceDeclHandler) ( conditions above this handler will only be called if the referenced entity was actually read. */ -typedef int (XMLCALL *XML_NotStandaloneHandler) (void *userData); +typedef int(XMLCALL *XML_NotStandaloneHandler)(void *userData); /* This is called for a reference to an external parsed general entity. The referenced entity is not automatically parsed. The @@ -429,12 +421,11 @@ typedef int (XMLCALL *XML_NotStandaloneHandler) (void *userData); Note that unlike other handlers the first argument is the parser, not userData. */ -typedef int (XMLCALL *XML_ExternalEntityRefHandler) ( - XML_Parser parser, - const XML_Char *context, - const XML_Char *base, - const XML_Char *systemId, - const XML_Char *publicId); +typedef int(XMLCALL *XML_ExternalEntityRefHandler)(XML_Parser parser, + const XML_Char *context, + const XML_Char *base, + const XML_Char *systemId, + const XML_Char *publicId); /* This is called in two situations: 1) An entity reference is encountered for which no declaration @@ -446,10 +437,9 @@ typedef int (XMLCALL *XML_ExternalEntityRefHandler) ( the event would be out of sync with the reporting of the declarations or attribute values */ -typedef void (XMLCALL *XML_SkippedEntityHandler) ( - void *userData, - const XML_Char *entityName, - int is_parameter_entity); +typedef void(XMLCALL *XML_SkippedEntityHandler)(void *userData, + const XML_Char *entityName, + int is_parameter_entity); /* This structure is filled in by the XML_UnknownEncodingHandler to provide information to the parser about encodings that are unknown @@ -506,8 +496,8 @@ typedef void (XMLCALL *XML_SkippedEntityHandler) ( typedef struct { int map[256]; void *data; - int (XMLCALL *convert)(void *data, const char *s); - void (XMLCALL *release)(void *data); + int(XMLCALL *convert)(void *data, const char *s); + void(XMLCALL *release)(void *data); } XML_Encoding; /* This is called for an encoding that is unknown to the parser. @@ -525,23 +515,19 @@ typedef struct { If info does not describe a suitable encoding, then the parser will return an XML_UNKNOWN_ENCODING error. */ -typedef int (XMLCALL *XML_UnknownEncodingHandler) ( - void *encodingHandlerData, - const XML_Char *name, - XML_Encoding *info); +typedef int(XMLCALL *XML_UnknownEncodingHandler)(void *encodingHandlerData, + const XML_Char *name, + XML_Encoding *info); XMLPARSEAPI(void) -XML_SetElementHandler(XML_Parser parser, - XML_StartElementHandler start, +XML_SetElementHandler(XML_Parser parser, XML_StartElementHandler start, XML_EndElementHandler end); XMLPARSEAPI(void) -XML_SetStartElementHandler(XML_Parser parser, - XML_StartElementHandler handler); +XML_SetStartElementHandler(XML_Parser parser, XML_StartElementHandler handler); XMLPARSEAPI(void) -XML_SetEndElementHandler(XML_Parser parser, - XML_EndElementHandler handler); +XML_SetEndElementHandler(XML_Parser parser, XML_EndElementHandler handler); XMLPARSEAPI(void) XML_SetCharacterDataHandler(XML_Parser parser, @@ -551,8 +537,7 @@ XMLPARSEAPI(void) XML_SetProcessingInstructionHandler(XML_Parser parser, XML_ProcessingInstructionHandler handler); XMLPARSEAPI(void) -XML_SetCommentHandler(XML_Parser parser, - XML_CommentHandler handler); +XML_SetCommentHandler(XML_Parser parser, XML_CommentHandler handler); XMLPARSEAPI(void) XML_SetCdataSectionHandler(XML_Parser parser, @@ -572,20 +557,17 @@ XML_SetEndCdataSectionHandler(XML_Parser parser, default handler, or to the skipped entity handler, if one is set. */ XMLPARSEAPI(void) -XML_SetDefaultHandler(XML_Parser parser, - XML_DefaultHandler handler); +XML_SetDefaultHandler(XML_Parser parser, XML_DefaultHandler handler); /* This sets the default handler but does not inhibit expansion of internal entities. The entity reference will not be passed to the default handler. */ XMLPARSEAPI(void) -XML_SetDefaultHandlerExpand(XML_Parser parser, - XML_DefaultHandler handler); +XML_SetDefaultHandlerExpand(XML_Parser parser, XML_DefaultHandler handler); XMLPARSEAPI(void) -XML_SetDoctypeDeclHandler(XML_Parser parser, - XML_StartDoctypeDeclHandler start, +XML_SetDoctypeDeclHandler(XML_Parser parser, XML_StartDoctypeDeclHandler start, XML_EndDoctypeDeclHandler end); XMLPARSEAPI(void) @@ -593,16 +575,14 @@ XML_SetStartDoctypeDeclHandler(XML_Parser parser, XML_StartDoctypeDeclHandler start); XMLPARSEAPI(void) -XML_SetEndDoctypeDeclHandler(XML_Parser parser, - XML_EndDoctypeDeclHandler end); +XML_SetEndDoctypeDeclHandler(XML_Parser parser, XML_EndDoctypeDeclHandler end); XMLPARSEAPI(void) XML_SetUnparsedEntityDeclHandler(XML_Parser parser, XML_UnparsedEntityDeclHandler handler); XMLPARSEAPI(void) -XML_SetNotationDeclHandler(XML_Parser parser, - XML_NotationDeclHandler handler); +XML_SetNotationDeclHandler(XML_Parser parser, XML_NotationDeclHandler handler); XMLPARSEAPI(void) XML_SetNamespaceDeclHandler(XML_Parser parser, @@ -630,8 +610,7 @@ XML_SetExternalEntityRefHandler(XML_Parser parser, instead of the parser object. */ XMLPARSEAPI(void) -XML_SetExternalEntityRefHandlerArg(XML_Parser parser, - void *arg); +XML_SetExternalEntityRefHandlerArg(XML_Parser parser, void *arg); XMLPARSEAPI(void) XML_SetSkippedEntityHandler(XML_Parser parser, @@ -706,11 +685,11 @@ XML_UseParserAsHandlerArg(XML_Parser parser); be called, despite an external subset being parsed. Note: If XML_DTD is not defined when Expat is compiled, returns XML_ERROR_FEATURE_REQUIRES_XML_DTD. + Note: If parser == NULL, returns XML_ERROR_INVALID_ARGUMENT. */ XMLPARSEAPI(enum XML_Error) XML_UseForeignDTD(XML_Parser parser, XML_Bool useDTD); - /* Sets the base to be used for resolving relative URIs in system identifiers in declarations. Resolving relative identifiers is left to the application: this value will be passed through as the @@ -729,15 +708,16 @@ XML_GetBase(XML_Parser parser); to the XML_StartElementHandler that were specified in the start-tag rather than defaulted. Each attribute/value pair counts as 2; thus this correspondds to an index into the atts array passed to the - XML_StartElementHandler. + XML_StartElementHandler. Returns -1 if parser == NULL. */ XMLPARSEAPI(int) XML_GetSpecifiedAttributeCount(XML_Parser parser); /* Returns the index of the ID attribute passed in the last call to - XML_StartElementHandler, or -1 if there is no ID attribute. Each - attribute/value pair counts as 2; thus this correspondds to an - index into the atts array passed to the XML_StartElementHandler. + XML_StartElementHandler, or -1 if there is no ID attribute or + parser == NULL. Each attribute/value pair counts as 2; thus this + correspondds to an index into the atts array passed to the + XML_StartElementHandler. */ XMLPARSEAPI(int) XML_GetIdAttributeIndex(XML_Parser parser); @@ -749,10 +729,10 @@ XML_GetIdAttributeIndex(XML_Parser parser); info->valueEnd - info->valueStart = 4 bytes. */ typedef struct { - XML_Index nameStart; /* Offset to beginning of the attribute name. */ - XML_Index nameEnd; /* Offset after the attribute name's last byte. */ - XML_Index valueStart; /* Offset to beginning of the attribute value. */ - XML_Index valueEnd; /* Offset after the attribute value's last byte. */ + XML_Index nameStart; /* Offset to beginning of the attribute name. */ + XML_Index nameEnd; /* Offset after the attribute name's last byte. */ + XML_Index valueStart; /* Offset to beginning of the attribute value. */ + XML_Index valueEnd; /* Offset after the attribute value's last byte. */ } XML_AttrInfo; /* Returns an array of XML_AttrInfo structures for the attribute/value pairs @@ -788,20 +768,20 @@ XML_ParseBuffer(XML_Parser parser, int len, int isFinal); (resumable = 0) an already suspended parser. Some call-backs may still follow because they would otherwise get lost. Examples: - endElementHandler() for empty elements when stopped in - startElementHandler(), - - endNameSpaceDeclHandler() when stopped in endElementHandler(), + startElementHandler(), + - endNameSpaceDeclHandler() when stopped in endElementHandler(), and possibly others. Can be called from most handlers, including DTD related call-backs, except when parsing an external parameter entity and resumable != 0. Returns XML_STATUS_OK when successful, XML_STATUS_ERROR otherwise. - Possible error codes: + Possible error codes: - XML_ERROR_SUSPENDED: when suspending an already suspended parser. - XML_ERROR_FINISHED: when the parser has already finished. - XML_ERROR_SUSPEND_PE: when suspending while parsing an external PE. - When resumable != 0 (true) then parsing is suspended, that is, - XML_Parse() and XML_ParseBuffer() return XML_STATUS_SUSPENDED. + When resumable != 0 (true) then parsing is suspended, that is, + XML_Parse() and XML_ParseBuffer() return XML_STATUS_SUSPENDED. Otherwise, parsing is aborted, that is, XML_Parse() and XML_ParseBuffer() return XML_STATUS_ERROR with error code XML_ERROR_ABORTED. @@ -812,7 +792,7 @@ XML_ParseBuffer(XML_Parser parser, int len, int isFinal); the externalEntityRefHandler() to call XML_StopParser() on the parent parser (recursively), if one wants to stop parsing altogether. - When suspended, parsing can be resumed by calling XML_ResumeParser(). + When suspended, parsing can be resumed by calling XML_ResumeParser(). */ XMLPARSEAPI(enum XML_Status) XML_StopParser(XML_Parser parser, XML_Bool resumable); @@ -820,7 +800,7 @@ XML_StopParser(XML_Parser parser, XML_Bool resumable); /* Resumes parsing after it has been suspended with XML_StopParser(). Must not be called from within a handler call-back. Returns same status codes as XML_Parse() or XML_ParseBuffer(). - Additional error code XML_ERROR_NOT_SUSPENDED possible. + Additional error code XML_ERROR_NOT_SUSPENDED possible. *Note*: This must be called on the most deeply nested child parser instance @@ -832,12 +812,7 @@ XML_StopParser(XML_Parser parser, XML_Bool resumable); XMLPARSEAPI(enum XML_Status) XML_ResumeParser(XML_Parser parser); -enum XML_Parsing { - XML_INITIALIZED, - XML_PARSING, - XML_FINISHED, - XML_SUSPENDED -}; +enum XML_Parsing { XML_INITIALIZED, XML_PARSING, XML_FINISHED, XML_SUSPENDED }; typedef struct { enum XML_Parsing parsing; @@ -869,8 +844,7 @@ XML_GetParsingStatus(XML_Parser parser, XML_ParsingStatus *status); Otherwise returns a new XML_Parser object. */ XMLPARSEAPI(XML_Parser) -XML_ExternalEntityParserCreate(XML_Parser parser, - const XML_Char *context, +XML_ExternalEntityParserCreate(XML_Parser parser, const XML_Char *context, const XML_Char *encoding); enum XML_ParamEntityParsing { @@ -901,6 +875,7 @@ enum XML_ParamEntityParsing { entities is requested; otherwise it will return non-zero. Note: If XML_SetParamEntityParsing is called after XML_Parse or XML_ParseBuffer, then it has no effect and will always return 0. + Note: If parser == NULL, the function will do nothing and return 0. */ XMLPARSEAPI(int) XML_SetParamEntityParsing(XML_Parser parser, @@ -910,10 +885,10 @@ XML_SetParamEntityParsing(XML_Parser parser, Helps in preventing DoS attacks based on predicting hash function behavior. This must be called before parsing is started. Returns 1 if successful, 0 when called after parsing has started. + Note: If parser == NULL, the function will do nothing and return 0. */ XMLPARSEAPI(int) -XML_SetHashSalt(XML_Parser parser, - unsigned long hash_salt); +XML_SetHashSalt(XML_Parser parser, unsigned long hash_salt); /* If XML_Parse or XML_ParseBuffer have returned XML_STATUS_ERROR, then XML_GetErrorCode returns information about the error. @@ -930,12 +905,16 @@ XML_GetErrorCode(XML_Parser parser); be within the relevant markup. When called outside of the callback functions, the position indicated will be just past the last parse event (regardless of whether there was an associated callback). - + They may also be called after returning from a call to XML_Parse or XML_ParseBuffer. If the return value is XML_STATUS_ERROR then the location is the location of the character at which the error was detected; otherwise the location is the location of the last parse event, as described above. + + Note: XML_GetCurrentLineNumber and XML_GetCurrentColumnNumber + return 0 to indicate an error. + Note: XML_GetCurrentByteIndex returns -1 to indicate an error. */ XMLPARSEAPI(XML_Size) XML_GetCurrentLineNumber(XML_Parser parser); XMLPARSEAPI(XML_Size) XML_GetCurrentColumnNumber(XML_Parser parser); @@ -958,14 +937,12 @@ XML_GetCurrentByteCount(XML_Parser parser); the handler that makes the call. */ XMLPARSEAPI(const char *) -XML_GetInputContext(XML_Parser parser, - int *offset, - int *size); +XML_GetInputContext(XML_Parser parser, int *offset, int *size); /* For backwards compatibility with previous versions. */ -#define XML_GetErrorLineNumber XML_GetCurrentLineNumber +#define XML_GetErrorLineNumber XML_GetCurrentLineNumber #define XML_GetErrorColumnNumber XML_GetCurrentColumnNumber -#define XML_GetErrorByteIndex XML_GetCurrentByteIndex +#define XML_GetErrorByteIndex XML_GetCurrentByteIndex /* Frees the content model passed to the element declaration handler */ XMLPARSEAPI(void) @@ -1025,21 +1002,20 @@ enum XML_FeatureEnum { }; typedef struct { - enum XML_FeatureEnum feature; - const XML_LChar *name; - long int value; + enum XML_FeatureEnum feature; + const XML_LChar *name; + long int value; } XML_Feature; XMLPARSEAPI(const XML_Feature *) XML_GetFeatureList(void); - /* Expat follows the semantic versioning convention. See http://semver.org. */ #define XML_MAJOR_VERSION 2 #define XML_MINOR_VERSION 2 -#define XML_MICRO_VERSION 0 +#define XML_MICRO_VERSION 8 #ifdef __cplusplus } diff --git a/chromium/third_party/expat/files/lib/expat_config.h b/chromium/third_party/expat/files/lib/expat_config.h index 1eaa22aee50..c693a14a2d9 100644 --- a/chromium/third_party/expat/files/lib/expat_config.h +++ b/chromium/third_party/expat/files/lib/expat_config.h @@ -1,16 +1,17 @@ -// No copyright notice; this file based on autogenerated header - -#ifndef THIRD_PARTY_EXPAT_V2_2_0_SOURCE_LIB_EXPAT_CONFIG_H__ -#define THIRD_PARTY_EXPAT_V2_2_0_SOURCE_LIB_EXPAT_CONFIG_H__ - /* expat_config.h. Generated from expat_config.h.in by configure. */ /* expat_config.h.in. Generated from configure.ac by autoheader. */ -/* 1234 = LIL_ENDIAN, 4321 = BIGENDIAN */ +/* Define if building universal (internal helper macro) */ +/* #undef AC_APPLE_UNIVERSAL_BUILD */ + +/* 1234 = LILENDIAN, 4321 = BIGENDIAN */ #define BYTEORDER 1234 -/* Define to 1 if you have the `bcopy' function. */ -#define HAVE_BCOPY 1 +/* Define to 1 if you have the `arc4random' function. */ +/* #undef HAVE_ARC4RANDOM */ + +/* Define to 1 if you have the `arc4random_buf' function. */ +/* #undef HAVE_ARC4RANDOM_BUF */ /* Define to 1 if you have the <dlfcn.h> header file. */ #define HAVE_DLFCN_H 1 @@ -21,11 +22,14 @@ /* Define to 1 if you have the `getpagesize' function. */ #define HAVE_GETPAGESIZE 1 +/* Define to 1 if you have the `getrandom' function. */ +/* #define HAVE_GETRANDOM 1 */ + /* Define to 1 if you have the <inttypes.h> header file. */ #define HAVE_INTTYPES_H 1 -/* Define to 1 if you have the `memmove' function. */ -#define HAVE_MEMMOVE 1 +/* Define to 1 if you have the `bsd' library (-lbsd). */ +/* #undef HAVE_LIBBSD */ /* Define to 1 if you have the <memory.h> header file. */ #define HAVE_MEMORY_H 1 @@ -45,6 +49,9 @@ /* Define to 1 if you have the <string.h> header file. */ #define HAVE_STRING_H 1 +/* Define to 1 if you have `syscall' and `SYS_getrandom'. */ +/* #define HAVE_SYSCALL_GETRANDOM 1 */ + /* Define to 1 if you have the <sys/param.h> header file. */ #define HAVE_SYS_PARAM_H 1 @@ -60,6 +67,9 @@ /* Define to the sub-directory where libtool stores uninstalled libraries. */ #define LT_OBJDIR ".libs/" +/* Name of package */ +#define PACKAGE "expat" + /* Define to the address where bug reports for this package should be sent. */ #define PACKAGE_BUGREPORT "expat-bugs@libexpat.org" @@ -67,7 +77,7 @@ #define PACKAGE_NAME "expat" /* Define to the full name and version of this package. */ -#define PACKAGE_STRING "expat 2.2.0" +#define PACKAGE_STRING "expat 2.2.8" /* Define to the one symbol short name of this package. */ #define PACKAGE_TARNAME "expat" @@ -76,27 +86,43 @@ #define PACKAGE_URL "" /* Define to the version of this package. */ -#define PACKAGE_VERSION "2.2.0" +#define PACKAGE_VERSION "2.2.8" /* Define to 1 if you have the ANSI C header files. */ #define STDC_HEADERS 1 -/* whether byteorder is bigendian */ -/* #undef WORDS_BIGENDIAN */ +/* Version number of package */ +#define VERSION "2.2.8" + +/* Define WORDS_BIGENDIAN to 1 if your processor stores words with the most + significant byte first (like Motorola and SPARC, unlike Intel). */ +#if defined AC_APPLE_UNIVERSAL_BUILD +# if defined __BIG_ENDIAN__ +# define WORDS_BIGENDIAN 1 +# endif +#else +# ifndef WORDS_BIGENDIAN +/* # undef WORDS_BIGENDIAN */ +# endif +#endif + +/* Define to allow retrieving the byte offsets for attribute names and values. + */ +/* #undef XML_ATTR_INFO */ /* Define to specify how much context to retain around the current parse point. */ #define XML_CONTEXT_BYTES 1024 +/* Define to include code reading entropy from `/dev/urandom'. */ +#define XML_DEV_URANDOM 1 + /* Define to make parameter entity parsing functionality available. */ #define XML_DTD 1 /* Define to make XML Namespaces functionality available. */ #define XML_NS 1 -/* Define to __FUNCTION__ or "" if `__func__' does not conform to ANSI C. */ -/* #undef __func__ */ - /* Define to empty if `const' does not conform to ANSI C. */ /* #undef const */ @@ -105,5 +131,3 @@ /* Define to `unsigned int' if <sys/types.h> does not define. */ /* #undef size_t */ - -#endif // THIRD_PARTY_EXPAT_V2_2_0_SOURCE_LIB_EXPAT_CONFIG_H__ diff --git a/chromium/third_party/expat/files/lib/expat_external.h b/chromium/third_party/expat/files/lib/expat_external.h index 124c7777f14..b3b6e74d9d2 100644 --- a/chromium/third_party/expat/files/lib/expat_external.h +++ b/chromium/third_party/expat/files/lib/expat_external.h @@ -1,5 +1,33 @@ -/* Copyright (c) 1998, 1999, 2000 Thai Open Source Software Center Ltd - See the file COPYING for copying permission. +/* + __ __ _ + ___\ \/ /_ __ __ _| |_ + / _ \\ /| '_ \ / _` | __| + | __// \| |_) | (_| | |_ + \___/_/\_\ .__/ \__,_|\__| + |_| XML parser + + Copyright (c) 1997-2000 Thai Open Source Software Center Ltd + Copyright (c) 2000-2017 Expat development team + Licensed under the MIT license: + + Permission is hereby granted, free of charge, to any person obtaining + a copy of this software and associated documentation files (the + "Software"), to deal in the Software without restriction, including + without limitation the rights to use, copy, modify, merge, publish, + distribute, sublicense, and/or sell copies of the Software, and to permit + persons to whom the Software is furnished to do so, subject to the + following conditions: + + The above copyright notice and this permission notice shall be included + in all copies or substantial portions of the Software. + + THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN + NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, + DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR + OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE + USE OR OTHER DEALINGS IN THE SOFTWARE. */ #ifndef Expat_External_INCLUDED @@ -7,10 +35,6 @@ /* External API definitions */ -#if defined(_MSC_EXTENSIONS) && !defined(__BEOS__) && !defined(__CYGWIN__) -#define XML_USE_MSC_EXTENSIONS 1 -#endif - /* Expat tries very hard to make the API boundary very specifically defined. There are two macros defined to control this boundary; each of these can be defined before including this header to @@ -34,11 +58,11 @@ system headers may assume the cdecl convention. */ #ifndef XMLCALL -#if defined(_MSC_VER) -#define XMLCALL __cdecl -#elif defined(__GNUC__) && defined(__i386) && !defined(__INTEL_COMPILER) -#define XMLCALL __attribute__((cdecl)) -#else +# if defined(_MSC_VER) +# define XMLCALL __cdecl +# elif defined(__GNUC__) && defined(__i386) && ! defined(__INTEL_COMPILER) +# define XMLCALL __attribute__((cdecl)) +# else /* For any platform which uses this definition and supports more than one calling convention, we need to extend this definition to declare the convention used on that platform, if it's possible to @@ -49,42 +73,46 @@ pre-processor and how to specify the same calling convention as the platform's malloc() implementation. */ -#define XMLCALL -#endif -#endif /* not defined XMLCALL */ - +# define XMLCALL +# endif +#endif /* not defined XMLCALL */ -#if !defined(XML_STATIC) && !defined(XMLIMPORT) -#ifndef XML_BUILDING_EXPAT +#if ! defined(XML_STATIC) && ! defined(XMLIMPORT) +# ifndef XML_BUILDING_EXPAT /* using Expat from an application */ -#ifdef XML_USE_MSC_EXTENSIONS -#define XMLIMPORT __declspec(dllimport) -#endif +# if defined(_MSC_EXTENSIONS) && ! defined(__BEOS__) && ! defined(__CYGWIN__) +# define XMLIMPORT __declspec(dllimport) +# endif +# endif +#endif /* not defined XML_STATIC */ + +#ifndef XML_ENABLE_VISIBILITY +# define XML_ENABLE_VISIBILITY 0 #endif -#endif /* not defined XML_STATIC */ -/* Don't change symbol visibility if used as a static link libraray */ -#if !defined(XML_STATIC) && !defined(XMLIMPORT) && defined(__GNUC__) && (__GNUC__ >= 4) -#define XMLIMPORT __attribute__ ((visibility ("default"))) +#if ! defined(XMLIMPORT) && XML_ENABLE_VISIBILITY +# define XMLIMPORT __attribute__((visibility("default"))) #endif /* If we didn't define it above, define it away: */ #ifndef XMLIMPORT -#define XMLIMPORT +# define XMLIMPORT #endif -#if defined(__GNUC__) && (__GNUC__ > 2 || (__GNUC__ == 2 && __GNUC_MINOR__ >= 96)) -#define XML_ATTR_MALLOC __attribute__((__malloc__)) +#if defined(__GNUC__) \ + && (__GNUC__ > 2 || (__GNUC__ == 2 && __GNUC_MINOR__ >= 96)) +# define XML_ATTR_MALLOC __attribute__((__malloc__)) #else -#define XML_ATTR_MALLOC +# define XML_ATTR_MALLOC #endif -#if defined(__GNUC__) && ((__GNUC__ > 4) || (__GNUC__ == 4 && __GNUC_MINOR__ >= 3)) -#define XML_ATTR_ALLOC_SIZE(x) __attribute__((__alloc_size__(x))) +#if defined(__GNUC__) \ + && ((__GNUC__ > 4) || (__GNUC__ == 4 && __GNUC_MINOR__ >= 3)) +# define XML_ATTR_ALLOC_SIZE(x) __attribute__((__alloc_size__(x))) #else -#define XML_ATTR_ALLOC_SIZE(x) +# define XML_ATTR_ALLOC_SIZE(x) #endif #define XMLPARSEAPI(type) XMLIMPORT type XMLCALL @@ -94,30 +122,30 @@ extern "C" { #endif #ifdef XML_UNICODE_WCHAR_T -#define XML_UNICODE +# ifndef XML_UNICODE +# define XML_UNICODE +# endif +# if defined(__SIZEOF_WCHAR_T__) && (__SIZEOF_WCHAR_T__ != 2) +# error "sizeof(wchar_t) != 2; Need -fshort-wchar for both Expat and libc" +# endif #endif -#ifdef XML_UNICODE /* Information is UTF-16 encoded. */ -#ifdef XML_UNICODE_WCHAR_T +#ifdef XML_UNICODE /* Information is UTF-16 encoded. */ +# ifdef XML_UNICODE_WCHAR_T typedef wchar_t XML_Char; typedef wchar_t XML_LChar; -#else +# else typedef unsigned short XML_Char; typedef char XML_LChar; -#endif /* XML_UNICODE_WCHAR_T */ -#else /* Information is UTF-8 encoded. */ +# endif /* XML_UNICODE_WCHAR_T */ +#else /* Information is UTF-8 encoded. */ typedef char XML_Char; typedef char XML_LChar; -#endif /* XML_UNICODE */ +#endif /* XML_UNICODE */ -#ifdef XML_LARGE_SIZE /* Use large integers for file/stream positions. */ -#if defined(XML_USE_MSC_EXTENSIONS) && _MSC_VER < 1400 -typedef __int64 XML_Index; -typedef unsigned __int64 XML_Size; -#else +#ifdef XML_LARGE_SIZE /* Use large integers for file/stream positions. */ typedef long long XML_Index; typedef unsigned long long XML_Size; -#endif #else typedef long XML_Index; typedef unsigned long XML_Size; diff --git a/chromium/third_party/expat/files/lib/iasciitab.h b/chromium/third_party/expat/files/lib/iasciitab.h index 24a1d5ccc9a..ea97cfcf678 100644 --- a/chromium/third_party/expat/files/lib/iasciitab.h +++ b/chromium/third_party/expat/files/lib/iasciitab.h @@ -1,37 +1,65 @@ -/* Copyright (c) 1998, 1999 Thai Open Source Software Center Ltd - See the file COPYING for copying permission. +/* + __ __ _ + ___\ \/ /_ __ __ _| |_ + / _ \\ /| '_ \ / _` | __| + | __// \| |_) | (_| | |_ + \___/_/\_\ .__/ \__,_|\__| + |_| XML parser + + Copyright (c) 1997-2000 Thai Open Source Software Center Ltd + Copyright (c) 2000-2017 Expat development team + Licensed under the MIT license: + + Permission is hereby granted, free of charge, to any person obtaining + a copy of this software and associated documentation files (the + "Software"), to deal in the Software without restriction, including + without limitation the rights to use, copy, modify, merge, publish, + distribute, sublicense, and/or sell copies of the Software, and to permit + persons to whom the Software is furnished to do so, subject to the + following conditions: + + The above copyright notice and this permission notice shall be included + in all copies or substantial portions of the Software. + + THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN + NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, + DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR + OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE + USE OR OTHER DEALINGS IN THE SOFTWARE. */ /* Like asciitab.h, except that 0xD has code BT_S rather than BT_CR */ /* 0x00 */ BT_NONXML, BT_NONXML, BT_NONXML, BT_NONXML, -/* 0x04 */ BT_NONXML, BT_NONXML, BT_NONXML, BT_NONXML, -/* 0x08 */ BT_NONXML, BT_S, BT_LF, BT_NONXML, -/* 0x0C */ BT_NONXML, BT_S, BT_NONXML, BT_NONXML, -/* 0x10 */ BT_NONXML, BT_NONXML, BT_NONXML, BT_NONXML, -/* 0x14 */ BT_NONXML, BT_NONXML, BT_NONXML, BT_NONXML, -/* 0x18 */ BT_NONXML, BT_NONXML, BT_NONXML, BT_NONXML, -/* 0x1C */ BT_NONXML, BT_NONXML, BT_NONXML, BT_NONXML, -/* 0x20 */ BT_S, BT_EXCL, BT_QUOT, BT_NUM, -/* 0x24 */ BT_OTHER, BT_PERCNT, BT_AMP, BT_APOS, -/* 0x28 */ BT_LPAR, BT_RPAR, BT_AST, BT_PLUS, -/* 0x2C */ BT_COMMA, BT_MINUS, BT_NAME, BT_SOL, -/* 0x30 */ BT_DIGIT, BT_DIGIT, BT_DIGIT, BT_DIGIT, -/* 0x34 */ BT_DIGIT, BT_DIGIT, BT_DIGIT, BT_DIGIT, -/* 0x38 */ BT_DIGIT, BT_DIGIT, BT_COLON, BT_SEMI, -/* 0x3C */ BT_LT, BT_EQUALS, BT_GT, BT_QUEST, -/* 0x40 */ BT_OTHER, BT_HEX, BT_HEX, BT_HEX, -/* 0x44 */ BT_HEX, BT_HEX, BT_HEX, BT_NMSTRT, -/* 0x48 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, -/* 0x4C */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, -/* 0x50 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, -/* 0x54 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, -/* 0x58 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_LSQB, -/* 0x5C */ BT_OTHER, BT_RSQB, BT_OTHER, BT_NMSTRT, -/* 0x60 */ BT_OTHER, BT_HEX, BT_HEX, BT_HEX, -/* 0x64 */ BT_HEX, BT_HEX, BT_HEX, BT_NMSTRT, -/* 0x68 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, -/* 0x6C */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, -/* 0x70 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, -/* 0x74 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, -/* 0x78 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_OTHER, -/* 0x7C */ BT_VERBAR, BT_OTHER, BT_OTHER, BT_OTHER, + /* 0x04 */ BT_NONXML, BT_NONXML, BT_NONXML, BT_NONXML, + /* 0x08 */ BT_NONXML, BT_S, BT_LF, BT_NONXML, + /* 0x0C */ BT_NONXML, BT_S, BT_NONXML, BT_NONXML, + /* 0x10 */ BT_NONXML, BT_NONXML, BT_NONXML, BT_NONXML, + /* 0x14 */ BT_NONXML, BT_NONXML, BT_NONXML, BT_NONXML, + /* 0x18 */ BT_NONXML, BT_NONXML, BT_NONXML, BT_NONXML, + /* 0x1C */ BT_NONXML, BT_NONXML, BT_NONXML, BT_NONXML, + /* 0x20 */ BT_S, BT_EXCL, BT_QUOT, BT_NUM, + /* 0x24 */ BT_OTHER, BT_PERCNT, BT_AMP, BT_APOS, + /* 0x28 */ BT_LPAR, BT_RPAR, BT_AST, BT_PLUS, + /* 0x2C */ BT_COMMA, BT_MINUS, BT_NAME, BT_SOL, + /* 0x30 */ BT_DIGIT, BT_DIGIT, BT_DIGIT, BT_DIGIT, + /* 0x34 */ BT_DIGIT, BT_DIGIT, BT_DIGIT, BT_DIGIT, + /* 0x38 */ BT_DIGIT, BT_DIGIT, BT_COLON, BT_SEMI, + /* 0x3C */ BT_LT, BT_EQUALS, BT_GT, BT_QUEST, + /* 0x40 */ BT_OTHER, BT_HEX, BT_HEX, BT_HEX, + /* 0x44 */ BT_HEX, BT_HEX, BT_HEX, BT_NMSTRT, + /* 0x48 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, + /* 0x4C */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, + /* 0x50 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, + /* 0x54 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, + /* 0x58 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_LSQB, + /* 0x5C */ BT_OTHER, BT_RSQB, BT_OTHER, BT_NMSTRT, + /* 0x60 */ BT_OTHER, BT_HEX, BT_HEX, BT_HEX, + /* 0x64 */ BT_HEX, BT_HEX, BT_HEX, BT_NMSTRT, + /* 0x68 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, + /* 0x6C */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, + /* 0x70 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, + /* 0x74 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, + /* 0x78 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_OTHER, + /* 0x7C */ BT_VERBAR, BT_OTHER, BT_OTHER, BT_OTHER, diff --git a/chromium/third_party/expat/files/lib/internal.h b/chromium/third_party/expat/files/lib/internal.h index 94cb98e15ca..60913dab762 100644 --- a/chromium/third_party/expat/files/lib/internal.h +++ b/chromium/third_party/expat/files/lib/internal.h @@ -18,9 +18,38 @@ Note: Use of these macros is based on judgement, not hard rules, and therefore subject to change. + __ __ _ + ___\ \/ /_ __ __ _| |_ + / _ \\ /| '_ \ / _` | __| + | __// \| |_) | (_| | |_ + \___/_/\_\ .__/ \__,_|\__| + |_| XML parser + + Copyright (c) 1997-2000 Thai Open Source Software Center Ltd + Copyright (c) 2000-2017 Expat development team + Licensed under the MIT license: + + Permission is hereby granted, free of charge, to any person obtaining + a copy of this software and associated documentation files (the + "Software"), to deal in the Software without restriction, including + without limitation the rights to use, copy, modify, merge, publish, + distribute, sublicense, and/or sell copies of the Software, and to permit + persons to whom the Software is furnished to do so, subject to the + following conditions: + + The above copyright notice and this permission notice shall be included + in all copies or substantial portions of the Software. + + THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN + NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, + DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR + OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE + USE OR OTHER DEALINGS IN THE SOFTWARE. */ -#if defined(__GNUC__) && defined(__i386__) && !defined(__MINGW32__) +#if defined(__GNUC__) && defined(__i386__) && ! defined(__MINGW32__) /* We'll use this version by default only where we know it helps. regparm() generates warnings on Solaris boxes. See SF bug #692878. @@ -30,8 +59,8 @@ #define FASTCALL __attribute__((stdcall, regparm(3))) and let's try this: */ -#define FASTCALL __attribute__((regparm(3))) -#define PTRFASTCALL __attribute__((regparm(3))) +# define FASTCALL __attribute__((regparm(3))) +# define PTRFASTCALL __attribute__((regparm(3))) #endif /* Using __fastcall seems to have an unexpected negative effect under @@ -45,50 +74,49 @@ /* Make sure all of these are defined if they aren't already. */ #ifndef FASTCALL -#define FASTCALL +# define FASTCALL #endif #ifndef PTRCALL -#define PTRCALL +# define PTRCALL #endif #ifndef PTRFASTCALL -#define PTRFASTCALL +# define PTRFASTCALL #endif #ifndef XML_MIN_SIZE -#if !defined(__cplusplus) && !defined(inline) -#ifdef __GNUC__ -#define inline __inline -#endif /* __GNUC__ */ -#endif +# if ! defined(__cplusplus) && ! defined(inline) +# ifdef __GNUC__ +# define inline __inline +# endif /* __GNUC__ */ +# endif #endif /* XML_MIN_SIZE */ #ifdef __cplusplus -#define inline inline +# define inline inline #else -#ifndef inline -#define inline -#endif +# ifndef inline +# define inline +# endif #endif #ifndef UNUSED_P -# ifdef __GNUC__ -# define UNUSED_P(p) UNUSED_ ## p __attribute__((__unused__)) -# else -# define UNUSED_P(p) UNUSED_ ## p -# endif +# define UNUSED_P(p) (void)p #endif - #ifdef __cplusplus extern "C" { #endif - +#ifdef XML_ENABLE_VISIBILITY +# if XML_ENABLE_VISIBILITY +__attribute__((visibility("default"))) +# endif +#endif void -align_limit_to_full_utf8_characters(const char * from, const char ** fromLimRef); - +_INTERNAL_trim_to_complete_utf8_characters(const char *from, + const char **fromLimRef); #ifdef __cplusplus } diff --git a/chromium/third_party/expat/files/lib/latin1tab.h b/chromium/third_party/expat/files/lib/latin1tab.h index 53c25d76b26..6f916041355 100644 --- a/chromium/third_party/expat/files/lib/latin1tab.h +++ b/chromium/third_party/expat/files/lib/latin1tab.h @@ -1,36 +1,64 @@ -/* Copyright (c) 1998, 1999 Thai Open Source Software Center Ltd - See the file COPYING for copying permission. +/* + __ __ _ + ___\ \/ /_ __ __ _| |_ + / _ \\ /| '_ \ / _` | __| + | __// \| |_) | (_| | |_ + \___/_/\_\ .__/ \__,_|\__| + |_| XML parser + + Copyright (c) 1997-2000 Thai Open Source Software Center Ltd + Copyright (c) 2000-2017 Expat development team + Licensed under the MIT license: + + Permission is hereby granted, free of charge, to any person obtaining + a copy of this software and associated documentation files (the + "Software"), to deal in the Software without restriction, including + without limitation the rights to use, copy, modify, merge, publish, + distribute, sublicense, and/or sell copies of the Software, and to permit + persons to whom the Software is furnished to do so, subject to the + following conditions: + + The above copyright notice and this permission notice shall be included + in all copies or substantial portions of the Software. + + THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN + NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, + DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR + OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE + USE OR OTHER DEALINGS IN THE SOFTWARE. */ /* 0x80 */ BT_OTHER, BT_OTHER, BT_OTHER, BT_OTHER, -/* 0x84 */ BT_OTHER, BT_OTHER, BT_OTHER, BT_OTHER, -/* 0x88 */ BT_OTHER, BT_OTHER, BT_OTHER, BT_OTHER, -/* 0x8C */ BT_OTHER, BT_OTHER, BT_OTHER, BT_OTHER, -/* 0x90 */ BT_OTHER, BT_OTHER, BT_OTHER, BT_OTHER, -/* 0x94 */ BT_OTHER, BT_OTHER, BT_OTHER, BT_OTHER, -/* 0x98 */ BT_OTHER, BT_OTHER, BT_OTHER, BT_OTHER, -/* 0x9C */ BT_OTHER, BT_OTHER, BT_OTHER, BT_OTHER, -/* 0xA0 */ BT_OTHER, BT_OTHER, BT_OTHER, BT_OTHER, -/* 0xA4 */ BT_OTHER, BT_OTHER, BT_OTHER, BT_OTHER, -/* 0xA8 */ BT_OTHER, BT_OTHER, BT_NMSTRT, BT_OTHER, -/* 0xAC */ BT_OTHER, BT_OTHER, BT_OTHER, BT_OTHER, -/* 0xB0 */ BT_OTHER, BT_OTHER, BT_OTHER, BT_OTHER, -/* 0xB4 */ BT_OTHER, BT_NMSTRT, BT_OTHER, BT_NAME, -/* 0xB8 */ BT_OTHER, BT_OTHER, BT_NMSTRT, BT_OTHER, -/* 0xBC */ BT_OTHER, BT_OTHER, BT_OTHER, BT_OTHER, -/* 0xC0 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, -/* 0xC4 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, -/* 0xC8 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, -/* 0xCC */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, -/* 0xD0 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, -/* 0xD4 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_OTHER, -/* 0xD8 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, -/* 0xDC */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, -/* 0xE0 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, -/* 0xE4 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, -/* 0xE8 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, -/* 0xEC */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, -/* 0xF0 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, -/* 0xF4 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_OTHER, -/* 0xF8 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, -/* 0xFC */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, + /* 0x84 */ BT_OTHER, BT_OTHER, BT_OTHER, BT_OTHER, + /* 0x88 */ BT_OTHER, BT_OTHER, BT_OTHER, BT_OTHER, + /* 0x8C */ BT_OTHER, BT_OTHER, BT_OTHER, BT_OTHER, + /* 0x90 */ BT_OTHER, BT_OTHER, BT_OTHER, BT_OTHER, + /* 0x94 */ BT_OTHER, BT_OTHER, BT_OTHER, BT_OTHER, + /* 0x98 */ BT_OTHER, BT_OTHER, BT_OTHER, BT_OTHER, + /* 0x9C */ BT_OTHER, BT_OTHER, BT_OTHER, BT_OTHER, + /* 0xA0 */ BT_OTHER, BT_OTHER, BT_OTHER, BT_OTHER, + /* 0xA4 */ BT_OTHER, BT_OTHER, BT_OTHER, BT_OTHER, + /* 0xA8 */ BT_OTHER, BT_OTHER, BT_NMSTRT, BT_OTHER, + /* 0xAC */ BT_OTHER, BT_OTHER, BT_OTHER, BT_OTHER, + /* 0xB0 */ BT_OTHER, BT_OTHER, BT_OTHER, BT_OTHER, + /* 0xB4 */ BT_OTHER, BT_NMSTRT, BT_OTHER, BT_NAME, + /* 0xB8 */ BT_OTHER, BT_OTHER, BT_NMSTRT, BT_OTHER, + /* 0xBC */ BT_OTHER, BT_OTHER, BT_OTHER, BT_OTHER, + /* 0xC0 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, + /* 0xC4 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, + /* 0xC8 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, + /* 0xCC */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, + /* 0xD0 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, + /* 0xD4 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_OTHER, + /* 0xD8 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, + /* 0xDC */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, + /* 0xE0 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, + /* 0xE4 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, + /* 0xE8 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, + /* 0xEC */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, + /* 0xF0 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, + /* 0xF4 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_OTHER, + /* 0xF8 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, + /* 0xFC */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, diff --git a/chromium/third_party/expat/files/lib/libexpat.def b/chromium/third_party/expat/files/lib/libexpat.def index e4f1afc8333..16faf5955e7 100644 --- a/chromium/third_party/expat/files/lib/libexpat.def +++ b/chromium/third_party/expat/files/lib/libexpat.def @@ -73,4 +73,6 @@ EXPORTS XML_GetParsingStatus @65 ; added with version 2.1.1 ; XML_GetAttributeInfo @66 - XML_SetHashSalt @66 + XML_SetHashSalt @67 +; added with version 2.2.5 + _INTERNAL_trim_to_complete_utf8_characters @68 diff --git a/chromium/third_party/expat/files/lib/libexpatw.def b/chromium/third_party/expat/files/lib/libexpatw.def index e4f1afc8333..16faf5955e7 100644 --- a/chromium/third_party/expat/files/lib/libexpatw.def +++ b/chromium/third_party/expat/files/lib/libexpatw.def @@ -73,4 +73,6 @@ EXPORTS XML_GetParsingStatus @65 ; added with version 2.1.1 ; XML_GetAttributeInfo @66 - XML_SetHashSalt @66 + XML_SetHashSalt @67 +; added with version 2.2.5 + _INTERNAL_trim_to_complete_utf8_characters @68 diff --git a/chromium/third_party/expat/files/lib/macconfig.h b/chromium/third_party/expat/files/lib/macconfig.h deleted file mode 100644 index 2725caaf54a..00000000000 --- a/chromium/third_party/expat/files/lib/macconfig.h +++ /dev/null @@ -1,53 +0,0 @@ -/*================================================================ -** Copyright 2000, Clark Cooper -** All rights reserved. -** -** This is free software. You are permitted to copy, distribute, or modify -** it under the terms of the MIT/X license (contained in the COPYING file -** with this distribution.) -** -*/ - -#ifndef MACCONFIG_H -#define MACCONFIG_H - - -/* 1234 = LIL_ENDIAN, 4321 = BIGENDIAN */ -#define BYTEORDER 4321 - -/* Define to 1 if you have the `bcopy' function. */ -#undef HAVE_BCOPY - -/* Define to 1 if you have the `memmove' function. */ -#define HAVE_MEMMOVE - -/* Define to 1 if you have a working `mmap' system call. */ -#undef HAVE_MMAP - -/* Define to 1 if you have the <unistd.h> header file. */ -#undef HAVE_UNISTD_H - -/* whether byteorder is bigendian */ -#define WORDS_BIGENDIAN - -/* Define to specify how much context to retain around the current parse - point. */ -#undef XML_CONTEXT_BYTES - -/* Define to make parameter entity parsing functionality available. */ -#define XML_DTD - -/* Define to make XML Namespaces functionality available. */ -#define XML_NS - -/* Define to empty if `const' does not conform to ANSI C. */ -#undef const - -/* Define to `long' if <sys/types.h> does not define. */ -#define off_t long - -/* Define to `unsigned' if <sys/types.h> does not define. */ -#undef size_t - - -#endif /* ifndef MACCONFIG_H */ diff --git a/chromium/third_party/expat/files/lib/nametab.h b/chromium/third_party/expat/files/lib/nametab.h index b05e62c77a6..3681df348ee 100644 --- a/chromium/third_party/expat/files/lib/nametab.h +++ b/chromium/third_party/expat/files/lib/nametab.h @@ -1,150 +1,136 @@ +/* + __ __ _ + ___\ \/ /_ __ __ _| |_ + / _ \\ /| '_ \ / _` | __| + | __// \| |_) | (_| | |_ + \___/_/\_\ .__/ \__,_|\__| + |_| XML parser + + Copyright (c) 1997-2000 Thai Open Source Software Center Ltd + Copyright (c) 2000-2017 Expat development team + Licensed under the MIT license: + + Permission is hereby granted, free of charge, to any person obtaining + a copy of this software and associated documentation files (the + "Software"), to deal in the Software without restriction, including + without limitation the rights to use, copy, modify, merge, publish, + distribute, sublicense, and/or sell copies of the Software, and to permit + persons to whom the Software is furnished to do so, subject to the + following conditions: + + The above copyright notice and this permission notice shall be included + in all copies or substantial portions of the Software. + + THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN + NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, + DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR + OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE + USE OR OTHER DEALINGS IN THE SOFTWARE. +*/ + static const unsigned namingBitmap[] = { -0x00000000, 0x00000000, 0x00000000, 0x00000000, -0x00000000, 0x00000000, 0x00000000, 0x00000000, -0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, -0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, -0x00000000, 0x04000000, 0x87FFFFFE, 0x07FFFFFE, -0x00000000, 0x00000000, 0xFF7FFFFF, 0xFF7FFFFF, -0xFFFFFFFF, 0x7FF3FFFF, 0xFFFFFDFE, 0x7FFFFFFF, -0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFE00F, 0xFC31FFFF, -0x00FFFFFF, 0x00000000, 0xFFFF0000, 0xFFFFFFFF, -0xFFFFFFFF, 0xF80001FF, 0x00000003, 0x00000000, -0x00000000, 0x00000000, 0x00000000, 0x00000000, -0xFFFFD740, 0xFFFFFFFB, 0x547F7FFF, 0x000FFFFD, -0xFFFFDFFE, 0xFFFFFFFF, 0xDFFEFFFF, 0xFFFFFFFF, -0xFFFF0003, 0xFFFFFFFF, 0xFFFF199F, 0x033FCFFF, -0x00000000, 0xFFFE0000, 0x027FFFFF, 0xFFFFFFFE, -0x0000007F, 0x00000000, 0xFFFF0000, 0x000707FF, -0x00000000, 0x07FFFFFE, 0x000007FE, 0xFFFE0000, -0xFFFFFFFF, 0x7CFFFFFF, 0x002F7FFF, 0x00000060, -0xFFFFFFE0, 0x23FFFFFF, 0xFF000000, 0x00000003, -0xFFF99FE0, 0x03C5FDFF, 0xB0000000, 0x00030003, -0xFFF987E0, 0x036DFDFF, 0x5E000000, 0x001C0000, -0xFFFBAFE0, 0x23EDFDFF, 0x00000000, 0x00000001, -0xFFF99FE0, 0x23CDFDFF, 0xB0000000, 0x00000003, -0xD63DC7E0, 0x03BFC718, 0x00000000, 0x00000000, -0xFFFDDFE0, 0x03EFFDFF, 0x00000000, 0x00000003, -0xFFFDDFE0, 0x03EFFDFF, 0x40000000, 0x00000003, -0xFFFDDFE0, 0x03FFFDFF, 0x00000000, 0x00000003, -0x00000000, 0x00000000, 0x00000000, 0x00000000, -0xFFFFFFFE, 0x000D7FFF, 0x0000003F, 0x00000000, -0xFEF02596, 0x200D6CAE, 0x0000001F, 0x00000000, -0x00000000, 0x00000000, 0xFFFFFEFF, 0x000003FF, -0x00000000, 0x00000000, 0x00000000, 0x00000000, -0x00000000, 0x00000000, 0x00000000, 0x00000000, -0x00000000, 0xFFFFFFFF, 0xFFFF003F, 0x007FFFFF, -0x0007DAED, 0x50000000, 0x82315001, 0x002C62AB, -0x40000000, 0xF580C900, 0x00000007, 0x02010800, -0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, -0x0FFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0x03FFFFFF, -0x3F3FFFFF, 0xFFFFFFFF, 0xAAFF3F3F, 0x3FFFFFFF, -0xFFFFFFFF, 0x5FDFFFFF, 0x0FCF1FDC, 0x1FDC1FFF, -0x00000000, 0x00004C40, 0x00000000, 0x00000000, -0x00000007, 0x00000000, 0x00000000, 0x00000000, -0x00000080, 0x000003FE, 0xFFFFFFFE, 0xFFFFFFFF, -0x001FFFFF, 0xFFFFFFFE, 0xFFFFFFFF, 0x07FFFFFF, -0xFFFFFFE0, 0x00001FFF, 0x00000000, 0x00000000, -0x00000000, 0x00000000, 0x00000000, 0x00000000, -0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, -0xFFFFFFFF, 0x0000003F, 0x00000000, 0x00000000, -0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, -0xFFFFFFFF, 0x0000000F, 0x00000000, 0x00000000, -0x00000000, 0x07FF6000, 0x87FFFFFE, 0x07FFFFFE, -0x00000000, 0x00800000, 0xFF7FFFFF, 0xFF7FFFFF, -0x00FFFFFF, 0x00000000, 0xFFFF0000, 0xFFFFFFFF, -0xFFFFFFFF, 0xF80001FF, 0x00030003, 0x00000000, -0xFFFFFFFF, 0xFFFFFFFF, 0x0000003F, 0x00000003, -0xFFFFD7C0, 0xFFFFFFFB, 0x547F7FFF, 0x000FFFFD, -0xFFFFDFFE, 0xFFFFFFFF, 0xDFFEFFFF, 0xFFFFFFFF, -0xFFFF007B, 0xFFFFFFFF, 0xFFFF199F, 0x033FCFFF, -0x00000000, 0xFFFE0000, 0x027FFFFF, 0xFFFFFFFE, -0xFFFE007F, 0xBBFFFFFB, 0xFFFF0016, 0x000707FF, -0x00000000, 0x07FFFFFE, 0x0007FFFF, 0xFFFF03FF, -0xFFFFFFFF, 0x7CFFFFFF, 0xFFEF7FFF, 0x03FF3DFF, -0xFFFFFFEE, 0xF3FFFFFF, 0xFF1E3FFF, 0x0000FFCF, -0xFFF99FEE, 0xD3C5FDFF, 0xB080399F, 0x0003FFCF, -0xFFF987E4, 0xD36DFDFF, 0x5E003987, 0x001FFFC0, -0xFFFBAFEE, 0xF3EDFDFF, 0x00003BBF, 0x0000FFC1, -0xFFF99FEE, 0xF3CDFDFF, 0xB0C0398F, 0x0000FFC3, -0xD63DC7EC, 0xC3BFC718, 0x00803DC7, 0x0000FF80, -0xFFFDDFEE, 0xC3EFFDFF, 0x00603DDF, 0x0000FFC3, -0xFFFDDFEC, 0xC3EFFDFF, 0x40603DDF, 0x0000FFC3, -0xFFFDDFEC, 0xC3FFFDFF, 0x00803DCF, 0x0000FFC3, -0x00000000, 0x00000000, 0x00000000, 0x00000000, -0xFFFFFFFE, 0x07FF7FFF, 0x03FF7FFF, 0x00000000, -0xFEF02596, 0x3BFF6CAE, 0x03FF3F5F, 0x00000000, -0x03000000, 0xC2A003FF, 0xFFFFFEFF, 0xFFFE03FF, -0xFEBF0FDF, 0x02FE3FFF, 0x00000000, 0x00000000, -0x00000000, 0x00000000, 0x00000000, 0x00000000, -0x00000000, 0x00000000, 0x1FFF0000, 0x00000002, -0x000000A0, 0x003EFFFE, 0xFFFFFFFE, 0xFFFFFFFF, -0x661FFFFF, 0xFFFFFFFE, 0xFFFFFFFF, 0x77FFFFFF, + 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, + 0x00000000, 0x00000000, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, + 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0x00000000, 0x04000000, + 0x87FFFFFE, 0x07FFFFFE, 0x00000000, 0x00000000, 0xFF7FFFFF, 0xFF7FFFFF, + 0xFFFFFFFF, 0x7FF3FFFF, 0xFFFFFDFE, 0x7FFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, + 0xFFFFE00F, 0xFC31FFFF, 0x00FFFFFF, 0x00000000, 0xFFFF0000, 0xFFFFFFFF, + 0xFFFFFFFF, 0xF80001FF, 0x00000003, 0x00000000, 0x00000000, 0x00000000, + 0x00000000, 0x00000000, 0xFFFFD740, 0xFFFFFFFB, 0x547F7FFF, 0x000FFFFD, + 0xFFFFDFFE, 0xFFFFFFFF, 0xDFFEFFFF, 0xFFFFFFFF, 0xFFFF0003, 0xFFFFFFFF, + 0xFFFF199F, 0x033FCFFF, 0x00000000, 0xFFFE0000, 0x027FFFFF, 0xFFFFFFFE, + 0x0000007F, 0x00000000, 0xFFFF0000, 0x000707FF, 0x00000000, 0x07FFFFFE, + 0x000007FE, 0xFFFE0000, 0xFFFFFFFF, 0x7CFFFFFF, 0x002F7FFF, 0x00000060, + 0xFFFFFFE0, 0x23FFFFFF, 0xFF000000, 0x00000003, 0xFFF99FE0, 0x03C5FDFF, + 0xB0000000, 0x00030003, 0xFFF987E0, 0x036DFDFF, 0x5E000000, 0x001C0000, + 0xFFFBAFE0, 0x23EDFDFF, 0x00000000, 0x00000001, 0xFFF99FE0, 0x23CDFDFF, + 0xB0000000, 0x00000003, 0xD63DC7E0, 0x03BFC718, 0x00000000, 0x00000000, + 0xFFFDDFE0, 0x03EFFDFF, 0x00000000, 0x00000003, 0xFFFDDFE0, 0x03EFFDFF, + 0x40000000, 0x00000003, 0xFFFDDFE0, 0x03FFFDFF, 0x00000000, 0x00000003, + 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0xFFFFFFFE, 0x000D7FFF, + 0x0000003F, 0x00000000, 0xFEF02596, 0x200D6CAE, 0x0000001F, 0x00000000, + 0x00000000, 0x00000000, 0xFFFFFEFF, 0x000003FF, 0x00000000, 0x00000000, + 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, + 0x00000000, 0xFFFFFFFF, 0xFFFF003F, 0x007FFFFF, 0x0007DAED, 0x50000000, + 0x82315001, 0x002C62AB, 0x40000000, 0xF580C900, 0x00000007, 0x02010800, + 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0x0FFFFFFF, 0xFFFFFFFF, + 0xFFFFFFFF, 0x03FFFFFF, 0x3F3FFFFF, 0xFFFFFFFF, 0xAAFF3F3F, 0x3FFFFFFF, + 0xFFFFFFFF, 0x5FDFFFFF, 0x0FCF1FDC, 0x1FDC1FFF, 0x00000000, 0x00004C40, + 0x00000000, 0x00000000, 0x00000007, 0x00000000, 0x00000000, 0x00000000, + 0x00000080, 0x000003FE, 0xFFFFFFFE, 0xFFFFFFFF, 0x001FFFFF, 0xFFFFFFFE, + 0xFFFFFFFF, 0x07FFFFFF, 0xFFFFFFE0, 0x00001FFF, 0x00000000, 0x00000000, + 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0xFFFFFFFF, 0xFFFFFFFF, + 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0x0000003F, 0x00000000, 0x00000000, + 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0x0000000F, + 0x00000000, 0x00000000, 0x00000000, 0x07FF6000, 0x87FFFFFE, 0x07FFFFFE, + 0x00000000, 0x00800000, 0xFF7FFFFF, 0xFF7FFFFF, 0x00FFFFFF, 0x00000000, + 0xFFFF0000, 0xFFFFFFFF, 0xFFFFFFFF, 0xF80001FF, 0x00030003, 0x00000000, + 0xFFFFFFFF, 0xFFFFFFFF, 0x0000003F, 0x00000003, 0xFFFFD7C0, 0xFFFFFFFB, + 0x547F7FFF, 0x000FFFFD, 0xFFFFDFFE, 0xFFFFFFFF, 0xDFFEFFFF, 0xFFFFFFFF, + 0xFFFF007B, 0xFFFFFFFF, 0xFFFF199F, 0x033FCFFF, 0x00000000, 0xFFFE0000, + 0x027FFFFF, 0xFFFFFFFE, 0xFFFE007F, 0xBBFFFFFB, 0xFFFF0016, 0x000707FF, + 0x00000000, 0x07FFFFFE, 0x0007FFFF, 0xFFFF03FF, 0xFFFFFFFF, 0x7CFFFFFF, + 0xFFEF7FFF, 0x03FF3DFF, 0xFFFFFFEE, 0xF3FFFFFF, 0xFF1E3FFF, 0x0000FFCF, + 0xFFF99FEE, 0xD3C5FDFF, 0xB080399F, 0x0003FFCF, 0xFFF987E4, 0xD36DFDFF, + 0x5E003987, 0x001FFFC0, 0xFFFBAFEE, 0xF3EDFDFF, 0x00003BBF, 0x0000FFC1, + 0xFFF99FEE, 0xF3CDFDFF, 0xB0C0398F, 0x0000FFC3, 0xD63DC7EC, 0xC3BFC718, + 0x00803DC7, 0x0000FF80, 0xFFFDDFEE, 0xC3EFFDFF, 0x00603DDF, 0x0000FFC3, + 0xFFFDDFEC, 0xC3EFFDFF, 0x40603DDF, 0x0000FFC3, 0xFFFDDFEC, 0xC3FFFDFF, + 0x00803DCF, 0x0000FFC3, 0x00000000, 0x00000000, 0x00000000, 0x00000000, + 0xFFFFFFFE, 0x07FF7FFF, 0x03FF7FFF, 0x00000000, 0xFEF02596, 0x3BFF6CAE, + 0x03FF3F5F, 0x00000000, 0x03000000, 0xC2A003FF, 0xFFFFFEFF, 0xFFFE03FF, + 0xFEBF0FDF, 0x02FE3FFF, 0x00000000, 0x00000000, 0x00000000, 0x00000000, + 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x1FFF0000, 0x00000002, + 0x000000A0, 0x003EFFFE, 0xFFFFFFFE, 0xFFFFFFFF, 0x661FFFFF, 0xFFFFFFFE, + 0xFFFFFFFF, 0x77FFFFFF, }; static const unsigned char nmstrtPages[] = { -0x02, 0x03, 0x04, 0x05, 0x06, 0x07, 0x08, 0x00, -0x00, 0x09, 0x0A, 0x0B, 0x0C, 0x0D, 0x0E, 0x0F, -0x10, 0x11, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x12, 0x13, -0x00, 0x14, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, -0x15, 0x16, 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, 0x01, 0x01, -0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, -0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, -0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, -0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, -0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, -0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, -0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, -0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, -0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, -0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x17, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0x00, 0x00, 0x01, 0x01, 0x01, 0x01, -0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, -0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, -0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, -0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, -0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x18, -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, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, 0x08, 0x00, 0x00, 0x09, 0x0A, 0x0B, + 0x0C, 0x0D, 0x0E, 0x0F, 0x10, 0x11, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x12, 0x13, 0x00, 0x14, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + 0x15, 0x16, 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, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, + 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, + 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, + 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, + 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, + 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, + 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, + 0x01, 0x01, 0x01, 0x17, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, + 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, + 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, + 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x18, + 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, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, }; static const unsigned char namePages[] = { -0x19, 0x03, 0x1A, 0x1B, 0x1C, 0x1D, 0x1E, 0x00, -0x00, 0x1F, 0x20, 0x21, 0x22, 0x23, 0x24, 0x25, -0x10, 0x11, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x12, 0x13, -0x26, 0x14, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, -0x27, 0x16, 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, 0x01, 0x01, -0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, -0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, -0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, -0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, -0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, -0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, -0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, -0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, -0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, -0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x17, -0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, -0x00, 0x00, 0x00, 0x00, 0x01, 0x01, 0x01, 0x01, -0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, -0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, -0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, -0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, -0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x18, -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, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + 0x19, 0x03, 0x1A, 0x1B, 0x1C, 0x1D, 0x1E, 0x00, 0x00, 0x1F, 0x20, 0x21, + 0x22, 0x23, 0x24, 0x25, 0x10, 0x11, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x12, 0x13, 0x26, 0x14, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + 0x27, 0x16, 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, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, + 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, + 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, + 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, + 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, + 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, + 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, + 0x01, 0x01, 0x01, 0x17, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, + 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, + 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, + 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x18, + 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, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, }; diff --git a/chromium/third_party/expat/files/lib/siphash.h b/chromium/third_party/expat/files/lib/siphash.h new file mode 100644 index 00000000000..bfee65a332f --- /dev/null +++ b/chromium/third_party/expat/files/lib/siphash.h @@ -0,0 +1,398 @@ +/* ========================================================================== + * siphash.h - SipHash-2-4 in a single header file + * -------------------------------------------------------------------------- + * Derived by William Ahern from the reference implementation[1] published[2] + * by Jean-Philippe Aumasson and Daniel J. Berstein. + * Minimal changes by Sebastian Pipping and Victor Stinner on top, see below. + * Licensed under the CC0 Public Domain Dedication license. + * + * 1. https://www.131002.net/siphash/siphash24.c + * 2. https://www.131002.net/siphash/ + * -------------------------------------------------------------------------- + * HISTORY: + * + * 2019-08-03 (Sebastian Pipping) + * - Mark part of sip24_valid as to be excluded from clang-format + * - Re-format code using clang-format 9 + * + * 2018-07-08 (Anton Maklakov) + * - Add "fall through" markers for GCC's -Wimplicit-fallthrough + * + * 2017-11-03 (Sebastian Pipping) + * - Hide sip_tobin and sip_binof unless SIPHASH_TOBIN macro is defined + * + * 2017-07-25 (Vadim Zeitlin) + * - Fix use of SIPHASH_MAIN macro + * + * 2017-07-05 (Sebastian Pipping) + * - Use _SIP_ULL macro to not require a C++11 compiler if compiled as C++ + * - Add const qualifiers at two places + * - Ensure <=80 characters line length (assuming tab width 4) + * + * 2017-06-23 (Victor Stinner) + * - Address Win64 compile warnings + * + * 2017-06-18 (Sebastian Pipping) + * - Clarify license note in the header + * - Address C89 issues: + * - Stop using inline keyword (and let compiler decide) + * - Replace _Bool by int + * - Turn macro siphash24 into a function + * - Address invalid conversion (void pointer) by explicit cast + * - Address lack of stdint.h for Visual Studio 2003 to 2008 + * - Always expose sip24_valid (for self-tests) + * + * 2012-11-04 - Born. (William Ahern) + * -------------------------------------------------------------------------- + * USAGE: + * + * SipHash-2-4 takes as input two 64-bit words as the key, some number of + * message bytes, and outputs a 64-bit word as the message digest. This + * implementation employs two data structures: a struct sipkey for + * representing the key, and a struct siphash for representing the hash + * state. + * + * For converting a 16-byte unsigned char array to a key, use either the + * macro sip_keyof or the routine sip_tokey. The former instantiates a + * compound literal key, while the latter requires a key object as a + * parameter. + * + * unsigned char secret[16]; + * arc4random_buf(secret, sizeof secret); + * struct sipkey *key = sip_keyof(secret); + * + * For hashing a message, use either the convenience macro siphash24 or the + * routines sip24_init, sip24_update, and sip24_final. + * + * struct siphash state; + * void *msg; + * size_t len; + * uint64_t hash; + * + * sip24_init(&state, key); + * sip24_update(&state, msg, len); + * hash = sip24_final(&state); + * + * or + * + * hash = siphash24(msg, len, key); + * + * To convert the 64-bit hash value to a canonical 8-byte little-endian + * binary representation, use either the macro sip_binof or the routine + * sip_tobin. The former instantiates and returns a compound literal array, + * while the latter requires an array object as a parameter. + * -------------------------------------------------------------------------- + * NOTES: + * + * o Neither sip_keyof, sip_binof, nor siphash24 will work with compilers + * lacking compound literal support. Instead, you must use the lower-level + * interfaces which take as parameters the temporary state objects. + * + * o Uppercase macros may evaluate parameters more than once. Lowercase + * macros should not exhibit any such side effects. + * ========================================================================== + */ +#ifndef SIPHASH_H +#define SIPHASH_H + +#include <stddef.h> /* size_t */ + +#if defined(_WIN32) && defined(_MSC_VER) && (_MSC_VER < 1600) +/* For vs2003/7.1 up to vs2008/9.0; _MSC_VER 1600 is vs2010/10.0 */ +typedef unsigned __int8 uint8_t; +typedef unsigned __int32 uint32_t; +typedef unsigned __int64 uint64_t; +#else +# include <stdint.h> /* uint64_t uint32_t uint8_t */ +#endif + +/* + * Workaround to not require a C++11 compiler for using ULL suffix + * if this code is included and compiled as C++; related GCC warning is: + * warning: use of C++11 long long integer constant [-Wlong-long] + */ +#define _SIP_ULL(high, low) (((uint64_t)high << 32) | low) + +#define SIP_ROTL(x, b) (uint64_t)(((x) << (b)) | ((x) >> (64 - (b)))) + +#define SIP_U32TO8_LE(p, v) \ + (p)[0] = (uint8_t)((v) >> 0); \ + (p)[1] = (uint8_t)((v) >> 8); \ + (p)[2] = (uint8_t)((v) >> 16); \ + (p)[3] = (uint8_t)((v) >> 24); + +#define SIP_U64TO8_LE(p, v) \ + SIP_U32TO8_LE((p) + 0, (uint32_t)((v) >> 0)); \ + SIP_U32TO8_LE((p) + 4, (uint32_t)((v) >> 32)); + +#define SIP_U8TO64_LE(p) \ + (((uint64_t)((p)[0]) << 0) | ((uint64_t)((p)[1]) << 8) \ + | ((uint64_t)((p)[2]) << 16) | ((uint64_t)((p)[3]) << 24) \ + | ((uint64_t)((p)[4]) << 32) | ((uint64_t)((p)[5]) << 40) \ + | ((uint64_t)((p)[6]) << 48) | ((uint64_t)((p)[7]) << 56)) + +#define SIPHASH_INITIALIZER \ + { 0, 0, 0, 0, {0}, 0, 0 } + +struct siphash { + uint64_t v0, v1, v2, v3; + + unsigned char buf[8], *p; + uint64_t c; +}; /* struct siphash */ + +#define SIP_KEYLEN 16 + +struct sipkey { + uint64_t k[2]; +}; /* struct sipkey */ + +#define sip_keyof(k) sip_tokey(&(struct sipkey){{0}}, (k)) + +static struct sipkey * +sip_tokey(struct sipkey *key, const void *src) { + key->k[0] = SIP_U8TO64_LE((const unsigned char *)src); + key->k[1] = SIP_U8TO64_LE((const unsigned char *)src + 8); + return key; +} /* sip_tokey() */ + +#ifdef SIPHASH_TOBIN + +# define sip_binof(v) sip_tobin((unsigned char[8]){0}, (v)) + +static void * +sip_tobin(void *dst, uint64_t u64) { + SIP_U64TO8_LE((unsigned char *)dst, u64); + return dst; +} /* sip_tobin() */ + +#endif /* SIPHASH_TOBIN */ + +static void +sip_round(struct siphash *H, const int rounds) { + int i; + + for (i = 0; i < rounds; i++) { + H->v0 += H->v1; + H->v1 = SIP_ROTL(H->v1, 13); + H->v1 ^= H->v0; + H->v0 = SIP_ROTL(H->v0, 32); + + H->v2 += H->v3; + H->v3 = SIP_ROTL(H->v3, 16); + H->v3 ^= H->v2; + + H->v0 += H->v3; + H->v3 = SIP_ROTL(H->v3, 21); + H->v3 ^= H->v0; + + H->v2 += H->v1; + H->v1 = SIP_ROTL(H->v1, 17); + H->v1 ^= H->v2; + H->v2 = SIP_ROTL(H->v2, 32); + } +} /* sip_round() */ + +static struct siphash * +sip24_init(struct siphash *H, const struct sipkey *key) { + H->v0 = _SIP_ULL(0x736f6d65U, 0x70736575U) ^ key->k[0]; + H->v1 = _SIP_ULL(0x646f7261U, 0x6e646f6dU) ^ key->k[1]; + H->v2 = _SIP_ULL(0x6c796765U, 0x6e657261U) ^ key->k[0]; + H->v3 = _SIP_ULL(0x74656462U, 0x79746573U) ^ key->k[1]; + + H->p = H->buf; + H->c = 0; + + return H; +} /* sip24_init() */ + +#define sip_endof(a) (&(a)[sizeof(a) / sizeof *(a)]) + +static struct siphash * +sip24_update(struct siphash *H, const void *src, size_t len) { + const unsigned char *p = (const unsigned char *)src, *pe = p + len; + uint64_t m; + + do { + while (p < pe && H->p < sip_endof(H->buf)) + *H->p++ = *p++; + + if (H->p < sip_endof(H->buf)) + break; + + m = SIP_U8TO64_LE(H->buf); + H->v3 ^= m; + sip_round(H, 2); + H->v0 ^= m; + + H->p = H->buf; + H->c += 8; + } while (p < pe); + + return H; +} /* sip24_update() */ + +static uint64_t +sip24_final(struct siphash *H) { + const char left = (char)(H->p - H->buf); + uint64_t b = (H->c + left) << 56; + + switch (left) { + case 7: + b |= (uint64_t)H->buf[6] << 48; + /* fall through */ + case 6: + b |= (uint64_t)H->buf[5] << 40; + /* fall through */ + case 5: + b |= (uint64_t)H->buf[4] << 32; + /* fall through */ + case 4: + b |= (uint64_t)H->buf[3] << 24; + /* fall through */ + case 3: + b |= (uint64_t)H->buf[2] << 16; + /* fall through */ + case 2: + b |= (uint64_t)H->buf[1] << 8; + /* fall through */ + case 1: + b |= (uint64_t)H->buf[0] << 0; + /* fall through */ + case 0: + break; + } + + H->v3 ^= b; + sip_round(H, 2); + H->v0 ^= b; + H->v2 ^= 0xff; + sip_round(H, 4); + + return H->v0 ^ H->v1 ^ H->v2 ^ H->v3; +} /* sip24_final() */ + +static uint64_t +siphash24(const void *src, size_t len, const struct sipkey *key) { + struct siphash state = SIPHASH_INITIALIZER; + return sip24_final(sip24_update(sip24_init(&state, key), src, len)); +} /* siphash24() */ + +/* + * SipHash-2-4 output with + * k = 00 01 02 ... + * and + * in = (empty string) + * in = 00 (1 byte) + * in = 00 01 (2 bytes) + * in = 00 01 02 (3 bytes) + * ... + * in = 00 01 02 ... 3e (63 bytes) + */ +static int +sip24_valid(void) { + /* clang-format off */ + static const unsigned char vectors[64][8] = { + { 0x31, 0x0e, 0x0e, 0xdd, 0x47, 0xdb, 0x6f, 0x72, }, + { 0xfd, 0x67, 0xdc, 0x93, 0xc5, 0x39, 0xf8, 0x74, }, + { 0x5a, 0x4f, 0xa9, 0xd9, 0x09, 0x80, 0x6c, 0x0d, }, + { 0x2d, 0x7e, 0xfb, 0xd7, 0x96, 0x66, 0x67, 0x85, }, + { 0xb7, 0x87, 0x71, 0x27, 0xe0, 0x94, 0x27, 0xcf, }, + { 0x8d, 0xa6, 0x99, 0xcd, 0x64, 0x55, 0x76, 0x18, }, + { 0xce, 0xe3, 0xfe, 0x58, 0x6e, 0x46, 0xc9, 0xcb, }, + { 0x37, 0xd1, 0x01, 0x8b, 0xf5, 0x00, 0x02, 0xab, }, + { 0x62, 0x24, 0x93, 0x9a, 0x79, 0xf5, 0xf5, 0x93, }, + { 0xb0, 0xe4, 0xa9, 0x0b, 0xdf, 0x82, 0x00, 0x9e, }, + { 0xf3, 0xb9, 0xdd, 0x94, 0xc5, 0xbb, 0x5d, 0x7a, }, + { 0xa7, 0xad, 0x6b, 0x22, 0x46, 0x2f, 0xb3, 0xf4, }, + { 0xfb, 0xe5, 0x0e, 0x86, 0xbc, 0x8f, 0x1e, 0x75, }, + { 0x90, 0x3d, 0x84, 0xc0, 0x27, 0x56, 0xea, 0x14, }, + { 0xee, 0xf2, 0x7a, 0x8e, 0x90, 0xca, 0x23, 0xf7, }, + { 0xe5, 0x45, 0xbe, 0x49, 0x61, 0xca, 0x29, 0xa1, }, + { 0xdb, 0x9b, 0xc2, 0x57, 0x7f, 0xcc, 0x2a, 0x3f, }, + { 0x94, 0x47, 0xbe, 0x2c, 0xf5, 0xe9, 0x9a, 0x69, }, + { 0x9c, 0xd3, 0x8d, 0x96, 0xf0, 0xb3, 0xc1, 0x4b, }, + { 0xbd, 0x61, 0x79, 0xa7, 0x1d, 0xc9, 0x6d, 0xbb, }, + { 0x98, 0xee, 0xa2, 0x1a, 0xf2, 0x5c, 0xd6, 0xbe, }, + { 0xc7, 0x67, 0x3b, 0x2e, 0xb0, 0xcb, 0xf2, 0xd0, }, + { 0x88, 0x3e, 0xa3, 0xe3, 0x95, 0x67, 0x53, 0x93, }, + { 0xc8, 0xce, 0x5c, 0xcd, 0x8c, 0x03, 0x0c, 0xa8, }, + { 0x94, 0xaf, 0x49, 0xf6, 0xc6, 0x50, 0xad, 0xb8, }, + { 0xea, 0xb8, 0x85, 0x8a, 0xde, 0x92, 0xe1, 0xbc, }, + { 0xf3, 0x15, 0xbb, 0x5b, 0xb8, 0x35, 0xd8, 0x17, }, + { 0xad, 0xcf, 0x6b, 0x07, 0x63, 0x61, 0x2e, 0x2f, }, + { 0xa5, 0xc9, 0x1d, 0xa7, 0xac, 0xaa, 0x4d, 0xde, }, + { 0x71, 0x65, 0x95, 0x87, 0x66, 0x50, 0xa2, 0xa6, }, + { 0x28, 0xef, 0x49, 0x5c, 0x53, 0xa3, 0x87, 0xad, }, + { 0x42, 0xc3, 0x41, 0xd8, 0xfa, 0x92, 0xd8, 0x32, }, + { 0xce, 0x7c, 0xf2, 0x72, 0x2f, 0x51, 0x27, 0x71, }, + { 0xe3, 0x78, 0x59, 0xf9, 0x46, 0x23, 0xf3, 0xa7, }, + { 0x38, 0x12, 0x05, 0xbb, 0x1a, 0xb0, 0xe0, 0x12, }, + { 0xae, 0x97, 0xa1, 0x0f, 0xd4, 0x34, 0xe0, 0x15, }, + { 0xb4, 0xa3, 0x15, 0x08, 0xbe, 0xff, 0x4d, 0x31, }, + { 0x81, 0x39, 0x62, 0x29, 0xf0, 0x90, 0x79, 0x02, }, + { 0x4d, 0x0c, 0xf4, 0x9e, 0xe5, 0xd4, 0xdc, 0xca, }, + { 0x5c, 0x73, 0x33, 0x6a, 0x76, 0xd8, 0xbf, 0x9a, }, + { 0xd0, 0xa7, 0x04, 0x53, 0x6b, 0xa9, 0x3e, 0x0e, }, + { 0x92, 0x59, 0x58, 0xfc, 0xd6, 0x42, 0x0c, 0xad, }, + { 0xa9, 0x15, 0xc2, 0x9b, 0xc8, 0x06, 0x73, 0x18, }, + { 0x95, 0x2b, 0x79, 0xf3, 0xbc, 0x0a, 0xa6, 0xd4, }, + { 0xf2, 0x1d, 0xf2, 0xe4, 0x1d, 0x45, 0x35, 0xf9, }, + { 0x87, 0x57, 0x75, 0x19, 0x04, 0x8f, 0x53, 0xa9, }, + { 0x10, 0xa5, 0x6c, 0xf5, 0xdf, 0xcd, 0x9a, 0xdb, }, + { 0xeb, 0x75, 0x09, 0x5c, 0xcd, 0x98, 0x6c, 0xd0, }, + { 0x51, 0xa9, 0xcb, 0x9e, 0xcb, 0xa3, 0x12, 0xe6, }, + { 0x96, 0xaf, 0xad, 0xfc, 0x2c, 0xe6, 0x66, 0xc7, }, + { 0x72, 0xfe, 0x52, 0x97, 0x5a, 0x43, 0x64, 0xee, }, + { 0x5a, 0x16, 0x45, 0xb2, 0x76, 0xd5, 0x92, 0xa1, }, + { 0xb2, 0x74, 0xcb, 0x8e, 0xbf, 0x87, 0x87, 0x0a, }, + { 0x6f, 0x9b, 0xb4, 0x20, 0x3d, 0xe7, 0xb3, 0x81, }, + { 0xea, 0xec, 0xb2, 0xa3, 0x0b, 0x22, 0xa8, 0x7f, }, + { 0x99, 0x24, 0xa4, 0x3c, 0xc1, 0x31, 0x57, 0x24, }, + { 0xbd, 0x83, 0x8d, 0x3a, 0xaf, 0xbf, 0x8d, 0xb7, }, + { 0x0b, 0x1a, 0x2a, 0x32, 0x65, 0xd5, 0x1a, 0xea, }, + { 0x13, 0x50, 0x79, 0xa3, 0x23, 0x1c, 0xe6, 0x60, }, + { 0x93, 0x2b, 0x28, 0x46, 0xe4, 0xd7, 0x06, 0x66, }, + { 0xe1, 0x91, 0x5f, 0x5c, 0xb1, 0xec, 0xa4, 0x6c, }, + { 0xf3, 0x25, 0x96, 0x5c, 0xa1, 0x6d, 0x62, 0x9f, }, + { 0x57, 0x5f, 0xf2, 0x8e, 0x60, 0x38, 0x1b, 0xe5, }, + { 0x72, 0x45, 0x06, 0xeb, 0x4c, 0x32, 0x8a, 0x95, } + }; + /* clang-format on */ + + unsigned char in[64]; + struct sipkey k; + size_t i; + + sip_tokey(&k, "\000\001\002\003\004\005\006\007\010\011" + "\012\013\014\015\016\017"); + + for (i = 0; i < sizeof in; ++i) { + in[i] = (unsigned char)i; + + if (siphash24(in, i, &k) != SIP_U8TO64_LE(vectors[i])) + return 0; + } + + return 1; +} /* sip24_valid() */ + +#ifdef SIPHASH_MAIN + +# include <stdio.h> + +int +main(void) { + const int ok = sip24_valid(); + + if (ok) + puts("OK"); + else + puts("FAIL"); + + return ! ok; +} /* main() */ + +#endif /* SIPHASH_MAIN */ + +#endif /* SIPHASH_H */ diff --git a/chromium/third_party/expat/files/lib/utf8tab.h b/chromium/third_party/expat/files/lib/utf8tab.h index 7bb3e77603f..a22986acbb9 100644 --- a/chromium/third_party/expat/files/lib/utf8tab.h +++ b/chromium/third_party/expat/files/lib/utf8tab.h @@ -1,37 +1,64 @@ -/* Copyright (c) 1998, 1999 Thai Open Source Software Center Ltd - See the file COPYING for copying permission. -*/ +/* + __ __ _ + ___\ \/ /_ __ __ _| |_ + / _ \\ /| '_ \ / _` | __| + | __// \| |_) | (_| | |_ + \___/_/\_\ .__/ \__,_|\__| + |_| XML parser + + Copyright (c) 1997-2000 Thai Open Source Software Center Ltd + Copyright (c) 2000-2017 Expat development team + Licensed under the MIT license: + + Permission is hereby granted, free of charge, to any person obtaining + a copy of this software and associated documentation files (the + "Software"), to deal in the Software without restriction, including + without limitation the rights to use, copy, modify, merge, publish, + distribute, sublicense, and/or sell copies of the Software, and to permit + persons to whom the Software is furnished to do so, subject to the + following conditions: + The above copyright notice and this permission notice shall be included + in all copies or substantial portions of the Software. + + THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN + NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, + DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR + OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE + USE OR OTHER DEALINGS IN THE SOFTWARE. +*/ /* 0x80 */ BT_TRAIL, BT_TRAIL, BT_TRAIL, BT_TRAIL, -/* 0x84 */ BT_TRAIL, BT_TRAIL, BT_TRAIL, BT_TRAIL, -/* 0x88 */ BT_TRAIL, BT_TRAIL, BT_TRAIL, BT_TRAIL, -/* 0x8C */ BT_TRAIL, BT_TRAIL, BT_TRAIL, BT_TRAIL, -/* 0x90 */ BT_TRAIL, BT_TRAIL, BT_TRAIL, BT_TRAIL, -/* 0x94 */ BT_TRAIL, BT_TRAIL, BT_TRAIL, BT_TRAIL, -/* 0x98 */ BT_TRAIL, BT_TRAIL, BT_TRAIL, BT_TRAIL, -/* 0x9C */ BT_TRAIL, BT_TRAIL, BT_TRAIL, BT_TRAIL, -/* 0xA0 */ BT_TRAIL, BT_TRAIL, BT_TRAIL, BT_TRAIL, -/* 0xA4 */ BT_TRAIL, BT_TRAIL, BT_TRAIL, BT_TRAIL, -/* 0xA8 */ BT_TRAIL, BT_TRAIL, BT_TRAIL, BT_TRAIL, -/* 0xAC */ BT_TRAIL, BT_TRAIL, BT_TRAIL, BT_TRAIL, -/* 0xB0 */ BT_TRAIL, BT_TRAIL, BT_TRAIL, BT_TRAIL, -/* 0xB4 */ BT_TRAIL, BT_TRAIL, BT_TRAIL, BT_TRAIL, -/* 0xB8 */ BT_TRAIL, BT_TRAIL, BT_TRAIL, BT_TRAIL, -/* 0xBC */ BT_TRAIL, BT_TRAIL, BT_TRAIL, BT_TRAIL, -/* 0xC0 */ BT_LEAD2, BT_LEAD2, BT_LEAD2, BT_LEAD2, -/* 0xC4 */ BT_LEAD2, BT_LEAD2, BT_LEAD2, BT_LEAD2, -/* 0xC8 */ BT_LEAD2, BT_LEAD2, BT_LEAD2, BT_LEAD2, -/* 0xCC */ BT_LEAD2, BT_LEAD2, BT_LEAD2, BT_LEAD2, -/* 0xD0 */ BT_LEAD2, BT_LEAD2, BT_LEAD2, BT_LEAD2, -/* 0xD4 */ BT_LEAD2, BT_LEAD2, BT_LEAD2, BT_LEAD2, -/* 0xD8 */ BT_LEAD2, BT_LEAD2, BT_LEAD2, BT_LEAD2, -/* 0xDC */ BT_LEAD2, BT_LEAD2, BT_LEAD2, BT_LEAD2, -/* 0xE0 */ BT_LEAD3, BT_LEAD3, BT_LEAD3, BT_LEAD3, -/* 0xE4 */ BT_LEAD3, BT_LEAD3, BT_LEAD3, BT_LEAD3, -/* 0xE8 */ BT_LEAD3, BT_LEAD3, BT_LEAD3, BT_LEAD3, -/* 0xEC */ BT_LEAD3, BT_LEAD3, BT_LEAD3, BT_LEAD3, -/* 0xF0 */ BT_LEAD4, BT_LEAD4, BT_LEAD4, BT_LEAD4, -/* 0xF4 */ BT_LEAD4, BT_NONXML, BT_NONXML, BT_NONXML, -/* 0xF8 */ BT_NONXML, BT_NONXML, BT_NONXML, BT_NONXML, -/* 0xFC */ BT_NONXML, BT_NONXML, BT_MALFORM, BT_MALFORM, + /* 0x84 */ BT_TRAIL, BT_TRAIL, BT_TRAIL, BT_TRAIL, + /* 0x88 */ BT_TRAIL, BT_TRAIL, BT_TRAIL, BT_TRAIL, + /* 0x8C */ BT_TRAIL, BT_TRAIL, BT_TRAIL, BT_TRAIL, + /* 0x90 */ BT_TRAIL, BT_TRAIL, BT_TRAIL, BT_TRAIL, + /* 0x94 */ BT_TRAIL, BT_TRAIL, BT_TRAIL, BT_TRAIL, + /* 0x98 */ BT_TRAIL, BT_TRAIL, BT_TRAIL, BT_TRAIL, + /* 0x9C */ BT_TRAIL, BT_TRAIL, BT_TRAIL, BT_TRAIL, + /* 0xA0 */ BT_TRAIL, BT_TRAIL, BT_TRAIL, BT_TRAIL, + /* 0xA4 */ BT_TRAIL, BT_TRAIL, BT_TRAIL, BT_TRAIL, + /* 0xA8 */ BT_TRAIL, BT_TRAIL, BT_TRAIL, BT_TRAIL, + /* 0xAC */ BT_TRAIL, BT_TRAIL, BT_TRAIL, BT_TRAIL, + /* 0xB0 */ BT_TRAIL, BT_TRAIL, BT_TRAIL, BT_TRAIL, + /* 0xB4 */ BT_TRAIL, BT_TRAIL, BT_TRAIL, BT_TRAIL, + /* 0xB8 */ BT_TRAIL, BT_TRAIL, BT_TRAIL, BT_TRAIL, + /* 0xBC */ BT_TRAIL, BT_TRAIL, BT_TRAIL, BT_TRAIL, + /* 0xC0 */ BT_LEAD2, BT_LEAD2, BT_LEAD2, BT_LEAD2, + /* 0xC4 */ BT_LEAD2, BT_LEAD2, BT_LEAD2, BT_LEAD2, + /* 0xC8 */ BT_LEAD2, BT_LEAD2, BT_LEAD2, BT_LEAD2, + /* 0xCC */ BT_LEAD2, BT_LEAD2, BT_LEAD2, BT_LEAD2, + /* 0xD0 */ BT_LEAD2, BT_LEAD2, BT_LEAD2, BT_LEAD2, + /* 0xD4 */ BT_LEAD2, BT_LEAD2, BT_LEAD2, BT_LEAD2, + /* 0xD8 */ BT_LEAD2, BT_LEAD2, BT_LEAD2, BT_LEAD2, + /* 0xDC */ BT_LEAD2, BT_LEAD2, BT_LEAD2, BT_LEAD2, + /* 0xE0 */ BT_LEAD3, BT_LEAD3, BT_LEAD3, BT_LEAD3, + /* 0xE4 */ BT_LEAD3, BT_LEAD3, BT_LEAD3, BT_LEAD3, + /* 0xE8 */ BT_LEAD3, BT_LEAD3, BT_LEAD3, BT_LEAD3, + /* 0xEC */ BT_LEAD3, BT_LEAD3, BT_LEAD3, BT_LEAD3, + /* 0xF0 */ BT_LEAD4, BT_LEAD4, BT_LEAD4, BT_LEAD4, + /* 0xF4 */ BT_LEAD4, BT_NONXML, BT_NONXML, BT_NONXML, + /* 0xF8 */ BT_NONXML, BT_NONXML, BT_NONXML, BT_NONXML, + /* 0xFC */ BT_NONXML, BT_NONXML, BT_MALFORM, BT_MALFORM, diff --git a/chromium/third_party/expat/files/lib/winconfig.h b/chromium/third_party/expat/files/lib/winconfig.h index 0f16ba5b9cf..ce1a4b95321 100644 --- a/chromium/third_party/expat/files/lib/winconfig.h +++ b/chromium/third_party/expat/files/lib/winconfig.h @@ -1,10 +1,33 @@ -/*================================================================ -** Copyright 2000, Clark Cooper -** All rights reserved. -** -** This is free software. You are permitted to copy, distribute, or modify -** it under the terms of the MIT/X license (contained in the COPYING file -** with this distribution.) +/* + __ __ _ + ___\ \/ /_ __ __ _| |_ + / _ \\ /| '_ \ / _` | __| + | __// \| |_) | (_| | |_ + \___/_/\_\ .__/ \__,_|\__| + |_| XML parser + + Copyright (c) 1997-2000 Thai Open Source Software Center Ltd + Copyright (c) 2000-2017 Expat development team + Licensed under the MIT license: + + Permission is hereby granted, free of charge, to any person obtaining + a copy of this software and associated documentation files (the + "Software"), to deal in the Software without restriction, including + without limitation the rights to use, copy, modify, merge, publish, + distribute, sublicense, and/or sell copies of the Software, and to permit + persons to whom the Software is furnished to do so, subject to the + following conditions: + + The above copyright notice and this permission notice shall be included + in all copies or substantial portions of the Software. + + THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN + NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, + DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR + OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE + USE OR OTHER DEALINGS IN THE SOFTWARE. */ #ifndef WINCONFIG_H @@ -19,14 +42,17 @@ #include <memory.h> #include <string.h> -#define XML_NS 1 -#define XML_DTD 1 -#define XML_CONTEXT_BYTES 1024 +#if defined(HAVE_EXPAT_CONFIG_H) /* e.g. MinGW */ +# include <expat_config.h> +#else /* !defined(HAVE_EXPAT_CONFIG_H) */ + +# define XML_NS 1 +# define XML_DTD 1 +# define XML_CONTEXT_BYTES 1024 /* we will assume all Windows platforms are little endian */ -#define BYTEORDER 1234 +# define BYTEORDER 1234 -/* Windows has memmove() available. */ -#define HAVE_MEMMOVE +#endif /* !defined(HAVE_EXPAT_CONFIG_H) */ #endif /* ndef WINCONFIG_H */ diff --git a/chromium/third_party/expat/files/lib/winconfig.h.original b/chromium/third_party/expat/files/lib/winconfig.h.original deleted file mode 100644 index c1b791d62d0..00000000000 --- a/chromium/third_party/expat/files/lib/winconfig.h.original +++ /dev/null @@ -1,30 +0,0 @@ -/*================================================================ -** Copyright 2000, Clark Cooper -** All rights reserved. -** -** This is free software. You are permitted to copy, distribute, or modify -** it under the terms of the MIT/X license (contained in the COPYING file -** with this distribution.) -*/ - -#ifndef WINCONFIG_H -#define WINCONFIG_H - -#define WIN32_LEAN_AND_MEAN -#include <windows.h> -#undef WIN32_LEAN_AND_MEAN - -#include <memory.h> -#include <string.h> - -#define XML_NS 1 -#define XML_DTD 1 -#define XML_CONTEXT_BYTES 1024 - -/* we will assume all Windows platforms are little endian */ -#define BYTEORDER 1234 - -/* Windows has memmove() available. */ -#define HAVE_MEMMOVE - -#endif /* ndef WINCONFIG_H */ diff --git a/chromium/third_party/expat/files/lib/xmlparse.c b/chromium/third_party/expat/files/lib/xmlparse.c index 72b39fced49..08a04c65de6 100644 --- a/chromium/third_party/expat/files/lib/xmlparse.c +++ b/chromium/third_party/expat/files/lib/xmlparse.c @@ -1,95 +1,172 @@ -/* Copyright (c) 1998, 1999, 2000 Thai Open Source Software Center Ltd - See the file COPYING for copying permission. +/* f2d0ab6d1d4422a08cf1cf3bbdfba96b49dea42fb5ff4615e03a2a25c306e769 (2.2.8+) + __ __ _ + ___\ \/ /_ __ __ _| |_ + / _ \\ /| '_ \ / _` | __| + | __// \| |_) | (_| | |_ + \___/_/\_\ .__/ \__,_|\__| + |_| XML parser + + Copyright (c) 1997-2000 Thai Open Source Software Center Ltd + Copyright (c) 2000-2017 Expat development team + Licensed under the MIT license: + + Permission is hereby granted, free of charge, to any person obtaining + a copy of this software and associated documentation files (the + "Software"), to deal in the Software without restriction, including + without limitation the rights to use, copy, modify, merge, publish, + distribute, sublicense, and/or sell copies of the Software, and to permit + persons to whom the Software is furnished to do so, subject to the + following conditions: + + The above copyright notice and this permission notice shall be included + in all copies or substantial portions of the Software. + + THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN + NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, + DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR + OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE + USE OR OTHER DEALINGS IN THE SOFTWARE. */ +#if ! defined(_GNU_SOURCE) +# define _GNU_SOURCE 1 /* syscall prototype */ +#endif + +#ifdef _WIN32 +/* force stdlib to define rand_s() */ +# if ! defined(_CRT_RAND_S) +# define _CRT_RAND_S +# endif +#endif + #include <stddef.h> -#include <string.h> /* memset(), memcpy() */ +#include <string.h> /* memset(), memcpy() */ #include <assert.h> -#include <limits.h> /* UINT_MAX */ +#include <limits.h> /* UINT_MAX */ +#include <stdio.h> /* fprintf */ +#include <stdlib.h> /* getenv, rand_s */ -#ifdef WIN32 -#define getpid GetCurrentProcessId +#ifdef _WIN32 +# define getpid GetCurrentProcessId #else -#include <sys/time.h> /* gettimeofday() */ -#include <sys/types.h> /* getpid() */ -#include <unistd.h> /* getpid() */ +# include <sys/time.h> /* gettimeofday() */ +# include <sys/types.h> /* getpid() */ +# include <unistd.h> /* getpid() */ +# include <fcntl.h> /* O_RDONLY */ +# include <errno.h> #endif #define XML_BUILDING_EXPAT 1 -#ifdef WIN32 -#include "winconfig.h" -#elif defined(MACOS_CLASSIC) -#include "macconfig.h" -#elif defined(__amigaos__) -#include "amigaconfig.h" -#elif defined(__WATCOMC__) -#include "watcomconfig.h" +#ifdef _WIN32 +# include "winconfig.h" #elif defined(HAVE_EXPAT_CONFIG_H) -#include <expat_config.h> -#endif /* ndef WIN32 */ +# include <expat_config.h> +#endif /* ndef _WIN32 */ #include "ascii.h" #include "expat.h" +#include "siphash.h" + +#if defined(HAVE_GETRANDOM) || defined(HAVE_SYSCALL_GETRANDOM) +# if defined(HAVE_GETRANDOM) +# include <sys/random.h> /* getrandom */ +# else +# include <unistd.h> /* syscall */ +# include <sys/syscall.h> /* SYS_getrandom */ +# endif +# if ! defined(GRND_NONBLOCK) +# define GRND_NONBLOCK 0x0001 +# endif /* defined(GRND_NONBLOCK) */ +#endif /* defined(HAVE_GETRANDOM) || defined(HAVE_SYSCALL_GETRANDOM) */ + +#if defined(HAVE_LIBBSD) \ + && (defined(HAVE_ARC4RANDOM_BUF) || defined(HAVE_ARC4RANDOM)) +# include <bsd/stdlib.h> +#endif + +#if defined(_WIN32) && ! defined(LOAD_LIBRARY_SEARCH_SYSTEM32) +# define LOAD_LIBRARY_SEARCH_SYSTEM32 0x00000800 +#endif + +#if ! defined(HAVE_GETRANDOM) && ! defined(HAVE_SYSCALL_GETRANDOM) \ + && ! defined(HAVE_ARC4RANDOM_BUF) && ! defined(HAVE_ARC4RANDOM) \ + && ! defined(XML_DEV_URANDOM) && ! defined(_WIN32) \ + && ! defined(XML_POOR_ENTROPY) +# error You do not have support for any sources of high quality entropy \ + enabled. For end user security, that is probably not what you want. \ + \ + Your options include: \ + * Linux + glibc >=2.25 (getrandom): HAVE_GETRANDOM, \ + * Linux + glibc <2.25 (syscall SYS_getrandom): HAVE_SYSCALL_GETRANDOM, \ + * BSD / macOS >=10.7 (arc4random_buf): HAVE_ARC4RANDOM_BUF, \ + * BSD / macOS <10.7 (arc4random): HAVE_ARC4RANDOM, \ + * libbsd (arc4random_buf): HAVE_ARC4RANDOM_BUF + HAVE_LIBBSD, \ + * libbsd (arc4random): HAVE_ARC4RANDOM + HAVE_LIBBSD, \ + * Linux / BSD / macOS (/dev/urandom): XML_DEV_URANDOM \ + * Windows (rand_s): _WIN32. \ + \ + If insist on not using any of these, bypass this error by defining \ + XML_POOR_ENTROPY; you have been warned. \ + \ + If you have reasons to patch this detection code away or need changes \ + to the build system, please open a bug. Thank you! +#endif #ifdef XML_UNICODE -#define XML_ENCODE_MAX XML_UTF16_ENCODE_MAX -#define XmlConvert XmlUtf16Convert -#define XmlGetInternalEncoding XmlGetUtf16InternalEncoding -#define XmlGetInternalEncodingNS XmlGetUtf16InternalEncodingNS -#define XmlEncode XmlUtf16Encode +# define XML_ENCODE_MAX XML_UTF16_ENCODE_MAX +# define XmlConvert XmlUtf16Convert +# define XmlGetInternalEncoding XmlGetUtf16InternalEncoding +# define XmlGetInternalEncodingNS XmlGetUtf16InternalEncodingNS +# define XmlEncode XmlUtf16Encode /* Using pointer subtraction to convert to integer type. */ -#define MUST_CONVERT(enc, s) (!(enc)->isUtf16 || (((char *)(s) - (char *)NULL) & 1)) +# define MUST_CONVERT(enc, s) \ + (! (enc)->isUtf16 || (((char *)(s) - (char *)NULL) & 1)) typedef unsigned short ICHAR; #else -#define XML_ENCODE_MAX XML_UTF8_ENCODE_MAX -#define XmlConvert XmlUtf8Convert -#define XmlGetInternalEncoding XmlGetUtf8InternalEncoding -#define XmlGetInternalEncodingNS XmlGetUtf8InternalEncodingNS -#define XmlEncode XmlUtf8Encode -#define MUST_CONVERT(enc, s) (!(enc)->isUtf8) +# define XML_ENCODE_MAX XML_UTF8_ENCODE_MAX +# define XmlConvert XmlUtf8Convert +# define XmlGetInternalEncoding XmlGetUtf8InternalEncoding +# define XmlGetInternalEncodingNS XmlGetUtf8InternalEncodingNS +# define XmlEncode XmlUtf8Encode +# define MUST_CONVERT(enc, s) (! (enc)->isUtf8) typedef char ICHAR; #endif - #ifndef XML_NS -#define XmlInitEncodingNS XmlInitEncoding -#define XmlInitUnknownEncodingNS XmlInitUnknownEncoding -#undef XmlGetInternalEncodingNS -#define XmlGetInternalEncodingNS XmlGetInternalEncoding -#define XmlParseXmlDeclNS XmlParseXmlDecl +# define XmlInitEncodingNS XmlInitEncoding +# define XmlInitUnknownEncodingNS XmlInitUnknownEncoding +# undef XmlGetInternalEncodingNS +# define XmlGetInternalEncodingNS XmlGetInternalEncoding +# define XmlParseXmlDeclNS XmlParseXmlDecl #endif #ifdef XML_UNICODE -#ifdef XML_UNICODE_WCHAR_T -#define XML_T(x) (const wchar_t)x -#define XML_L(x) L ## x -#else -#define XML_T(x) (const unsigned short)x -#define XML_L(x) x -#endif +# ifdef XML_UNICODE_WCHAR_T +# define XML_T(x) (const wchar_t) x +# define XML_L(x) L##x +# else +# define XML_T(x) (const unsigned short)x +# define XML_L(x) x +# endif #else -#define XML_T(x) x -#define XML_L(x) x +# define XML_T(x) x +# define XML_L(x) x #endif /* Round up n to be a multiple of sz, where sz is a power of 2. */ -#define ROUND_UP(n, sz) (((n) + ((sz) - 1)) & ~((sz) - 1)) +#define ROUND_UP(n, sz) (((n) + ((sz)-1)) & ~((sz)-1)) -/* Handle the case where memmove() doesn't exist. */ -#ifndef HAVE_MEMMOVE -#ifdef HAVE_BCOPY -#define memmove(d,s,l) bcopy((s),(d),(l)) -#else -#error memmove does not exist on this platform, nor is a substitute available -#endif /* HAVE_BCOPY */ -#endif /* HAVE_MEMMOVE */ +/* Do safe (NULL-aware) pointer arithmetic */ +#define EXPAT_SAFE_PTR_DIFF(p, q) (((p) && (q)) ? ((p) - (q)) : 0) #include "internal.h" #include "xmltok.h" @@ -109,17 +186,9 @@ typedef struct { const XML_Memory_Handling_Suite *mem; } HASH_TABLE; -/* Basic character hash algorithm, taken from Python's string hash: - h = h * 1000003 ^ character, the constant being a prime number. +static size_t keylen(KEY s); -*/ -#ifdef XML_UNICODE -#define CHAR_HASH(h, c) \ - (((h) * 0xF4243) ^ (unsigned short)(c)) -#else -#define CHAR_HASH(h, c) \ - (((h) * 0xF4243) ^ (unsigned char)(c)) -#endif +static void copy_salt_to_sipkey(XML_Parser parser, struct sipkey *key); /* For probing (after a collision) we need a step size relative prime to the hash table size, which is a power of 2. We use double-hashing, @@ -129,9 +198,9 @@ typedef struct { We limit the maximum step size to table->size / 4 (mask >> 2) and make it odd, since odd numbers are always relative prime to a power of 2. */ -#define SECOND_HASH(hash, mask, power) \ - ((((hash) & ~(mask)) >> ((power) - 1)) & ((mask) >> 2)) -#define PROBE_STEP(hash, mask, power) \ +#define SECOND_HASH(hash, mask, power) \ + ((((hash) & ~(mask)) >> ((power)-1)) & ((mask) >> 2)) +#define PROBE_STEP(hash, mask, power) \ ((unsigned char)((SECOND_HASH(hash, mask, power)) | 1)) typedef struct { @@ -139,7 +208,7 @@ typedef struct { NAMED **end; } HASH_TABLE_ITER; -#define INIT_TAG_BUF_SIZE 32 /* must be a multiple of sizeof(XML_Char) */ +#define INIT_TAG_BUF_SIZE 32 /* must be a multiple of sizeof(XML_Char) */ #define INIT_DATA_BUF_SIZE 1024 #define INIT_ATTS_SIZE 16 #define INIT_ATTS_VERSION 0xFFFFFFFF @@ -186,20 +255,20 @@ typedef struct { TAG objects in a free list. */ typedef struct tag { - struct tag *parent; /* parent of this element */ - const char *rawName; /* tagName in the original encoding */ + struct tag *parent; /* parent of this element */ + const char *rawName; /* tagName in the original encoding */ int rawNameLength; - TAG_NAME name; /* tagName in the API encoding */ - char *buf; /* buffer for name components */ - char *bufEnd; /* end of the buffer */ + TAG_NAME name; /* tagName in the API encoding */ + char *buf; /* buffer for name components */ + char *bufEnd; /* end of the buffer */ BINDING *bindings; } TAG; typedef struct { const XML_Char *name; const XML_Char *textPtr; - int textLen; /* length in XML_Chars */ - int processed; /* # of processed bytes - when suspended */ + int textLen; /* length in XML_Chars */ + int processed; /* # of processed bytes - when suspended */ const XML_Char *systemId; const XML_Char *base; const XML_Char *publicId; @@ -210,13 +279,13 @@ typedef struct { } ENTITY; typedef struct { - enum XML_Content_Type type; - enum XML_Content_Quant quant; - const XML_Char * name; - int firstchild; - int lastchild; - int childcnt; - int nextsib; + enum XML_Content_Type type; + enum XML_Content_Quant quant; + const XML_Char *name; + int firstchild; + int lastchild; + int childcnt; + int nextsib; } CONTENT_SCAFFOLD; #define INIT_SCAFFOLD_ELEMENTS 32 @@ -304,10 +373,8 @@ typedef struct open_internal_entity { XML_Bool betweenDecl; /* WFC: PE Between Declarations */ } OPEN_INTERNAL_ENTITY; -typedef enum XML_Error PTRCALL Processor(XML_Parser parser, - const char *start, - const char *end, - const char **endPtr); +typedef enum XML_Error PTRCALL Processor(XML_Parser parser, const char *start, + const char *end, const char **endPtr); static Processor prologProcessor; static Processor prologInitProcessor; @@ -328,128 +395,113 @@ static Processor externalEntityInitProcessor3; static Processor externalEntityContentProcessor; static Processor internalEntityProcessor; -static enum XML_Error -handleUnknownEncoding(XML_Parser parser, const XML_Char *encodingName); -static enum XML_Error -processXmlDecl(XML_Parser parser, int isGeneralTextEntity, - const char *s, const char *next); -static enum XML_Error -initializeEncoding(XML_Parser parser); -static enum XML_Error -doProlog(XML_Parser parser, const ENCODING *enc, const char *s, - const char *end, int tok, const char *next, const char **nextPtr, - XML_Bool haveMore); -static enum XML_Error -processInternalEntity(XML_Parser parser, ENTITY *entity, - XML_Bool betweenDecl); -static enum XML_Error -doContent(XML_Parser parser, int startTagLevel, const ENCODING *enc, - const char *start, const char *end, const char **endPtr, - XML_Bool haveMore); -static enum XML_Error -doCdataSection(XML_Parser parser, const ENCODING *, const char **startPtr, - const char *end, const char **nextPtr, XML_Bool haveMore); +static enum XML_Error handleUnknownEncoding(XML_Parser parser, + const XML_Char *encodingName); +static enum XML_Error processXmlDecl(XML_Parser parser, int isGeneralTextEntity, + const char *s, const char *next); +static enum XML_Error initializeEncoding(XML_Parser parser); +static enum XML_Error doProlog(XML_Parser parser, const ENCODING *enc, + const char *s, const char *end, int tok, + const char *next, const char **nextPtr, + XML_Bool haveMore, XML_Bool allowClosingDoctype); +static enum XML_Error processInternalEntity(XML_Parser parser, ENTITY *entity, + XML_Bool betweenDecl); +static enum XML_Error doContent(XML_Parser parser, int startTagLevel, + const ENCODING *enc, const char *start, + const char *end, const char **endPtr, + XML_Bool haveMore); +static enum XML_Error doCdataSection(XML_Parser parser, const ENCODING *, + const char **startPtr, const char *end, + const char **nextPtr, XML_Bool haveMore); #ifdef XML_DTD -static enum XML_Error -doIgnoreSection(XML_Parser parser, const ENCODING *, const char **startPtr, - const char *end, const char **nextPtr, XML_Bool haveMore); +static enum XML_Error doIgnoreSection(XML_Parser parser, const ENCODING *, + const char **startPtr, const char *end, + const char **nextPtr, XML_Bool haveMore); #endif /* XML_DTD */ -static enum XML_Error -storeAtts(XML_Parser parser, const ENCODING *, const char *s, - TAG_NAME *tagNamePtr, BINDING **bindingsPtr); -static enum XML_Error -addBinding(XML_Parser parser, PREFIX *prefix, const ATTRIBUTE_ID *attId, - const XML_Char *uri, BINDING **bindingsPtr); -static int -defineAttribute(ELEMENT_TYPE *type, ATTRIBUTE_ID *, XML_Bool isCdata, - XML_Bool isId, const XML_Char *dfltValue, XML_Parser parser); -static enum XML_Error -storeAttributeValue(XML_Parser parser, const ENCODING *, XML_Bool isCdata, - const char *, const char *, STRING_POOL *); -static enum XML_Error -appendAttributeValue(XML_Parser parser, const ENCODING *, XML_Bool isCdata, - const char *, const char *, STRING_POOL *); -static ATTRIBUTE_ID * -getAttributeId(XML_Parser parser, const ENCODING *enc, const char *start, - const char *end); -static int -setElementTypePrefix(XML_Parser parser, ELEMENT_TYPE *); -static enum XML_Error -storeEntityValue(XML_Parser parser, const ENCODING *enc, const char *start, - const char *end); -static int -reportProcessingInstruction(XML_Parser parser, const ENCODING *enc, - const char *start, const char *end); -static int -reportComment(XML_Parser parser, const ENCODING *enc, const char *start, - const char *end); -static void -reportDefault(XML_Parser parser, const ENCODING *enc, const char *start, - const char *end); - -static const XML_Char * getContext(XML_Parser parser); -static XML_Bool -setContext(XML_Parser parser, const XML_Char *context); +static void freeBindings(XML_Parser parser, BINDING *bindings); +static enum XML_Error storeAtts(XML_Parser parser, const ENCODING *, + const char *s, TAG_NAME *tagNamePtr, + BINDING **bindingsPtr); +static enum XML_Error addBinding(XML_Parser parser, PREFIX *prefix, + const ATTRIBUTE_ID *attId, const XML_Char *uri, + BINDING **bindingsPtr); +static int defineAttribute(ELEMENT_TYPE *type, ATTRIBUTE_ID *, XML_Bool isCdata, + XML_Bool isId, const XML_Char *dfltValue, + XML_Parser parser); +static enum XML_Error storeAttributeValue(XML_Parser parser, const ENCODING *, + XML_Bool isCdata, const char *, + const char *, STRING_POOL *); +static enum XML_Error appendAttributeValue(XML_Parser parser, const ENCODING *, + XML_Bool isCdata, const char *, + const char *, STRING_POOL *); +static ATTRIBUTE_ID *getAttributeId(XML_Parser parser, const ENCODING *enc, + const char *start, const char *end); +static int setElementTypePrefix(XML_Parser parser, ELEMENT_TYPE *); +static enum XML_Error storeEntityValue(XML_Parser parser, const ENCODING *enc, + const char *start, const char *end); +static int reportProcessingInstruction(XML_Parser parser, const ENCODING *enc, + const char *start, const char *end); +static int reportComment(XML_Parser parser, const ENCODING *enc, + const char *start, const char *end); +static void reportDefault(XML_Parser parser, const ENCODING *enc, + const char *start, const char *end); + +static const XML_Char *getContext(XML_Parser parser); +static XML_Bool setContext(XML_Parser parser, const XML_Char *context); static void FASTCALL normalizePublicId(XML_Char *s); -static DTD * dtdCreate(const XML_Memory_Handling_Suite *ms); -/* do not call if parentParser != NULL */ +static DTD *dtdCreate(const XML_Memory_Handling_Suite *ms); +/* do not call if m_parentParser != NULL */ static void dtdReset(DTD *p, const XML_Memory_Handling_Suite *ms); -static void -dtdDestroy(DTD *p, XML_Bool isDocEntity, const XML_Memory_Handling_Suite *ms); -static int -dtdCopy(XML_Parser oldParser, - DTD *newDtd, const DTD *oldDtd, const XML_Memory_Handling_Suite *ms); -static int -copyEntityTable(XML_Parser oldParser, - HASH_TABLE *, STRING_POOL *, const HASH_TABLE *); -static NAMED * -lookup(XML_Parser parser, HASH_TABLE *table, KEY name, size_t createSize); -static void FASTCALL -hashTableInit(HASH_TABLE *, const XML_Memory_Handling_Suite *ms); +static void dtdDestroy(DTD *p, XML_Bool isDocEntity, + const XML_Memory_Handling_Suite *ms); +static int dtdCopy(XML_Parser oldParser, DTD *newDtd, const DTD *oldDtd, + const XML_Memory_Handling_Suite *ms); +static int copyEntityTable(XML_Parser oldParser, HASH_TABLE *, STRING_POOL *, + const HASH_TABLE *); +static NAMED *lookup(XML_Parser parser, HASH_TABLE *table, KEY name, + size_t createSize); +static void FASTCALL hashTableInit(HASH_TABLE *, + const XML_Memory_Handling_Suite *ms); static void FASTCALL hashTableClear(HASH_TABLE *); static void FASTCALL hashTableDestroy(HASH_TABLE *); -static void FASTCALL -hashTableIterInit(HASH_TABLE_ITER *, const HASH_TABLE *); -static NAMED * FASTCALL hashTableIterNext(HASH_TABLE_ITER *); +static void FASTCALL hashTableIterInit(HASH_TABLE_ITER *, const HASH_TABLE *); +static NAMED *FASTCALL hashTableIterNext(HASH_TABLE_ITER *); -static void FASTCALL -poolInit(STRING_POOL *, const XML_Memory_Handling_Suite *ms); +static void FASTCALL poolInit(STRING_POOL *, + const XML_Memory_Handling_Suite *ms); static void FASTCALL poolClear(STRING_POOL *); static void FASTCALL poolDestroy(STRING_POOL *); -static XML_Char * -poolAppend(STRING_POOL *pool, const ENCODING *enc, - const char *ptr, const char *end); -static XML_Char * -poolStoreString(STRING_POOL *pool, const ENCODING *enc, - const char *ptr, const char *end); +static XML_Char *poolAppend(STRING_POOL *pool, const ENCODING *enc, + const char *ptr, const char *end); +static XML_Char *poolStoreString(STRING_POOL *pool, const ENCODING *enc, + const char *ptr, const char *end); static XML_Bool FASTCALL poolGrow(STRING_POOL *pool); -static const XML_Char * FASTCALL -poolCopyString(STRING_POOL *pool, const XML_Char *s); -static const XML_Char * -poolCopyStringN(STRING_POOL *pool, const XML_Char *s, int n); -static const XML_Char * FASTCALL -poolAppendString(STRING_POOL *pool, const XML_Char *s); +static const XML_Char *FASTCALL poolCopyString(STRING_POOL *pool, + const XML_Char *s); +static const XML_Char *poolCopyStringN(STRING_POOL *pool, const XML_Char *s, + int n); +static const XML_Char *FASTCALL poolAppendString(STRING_POOL *pool, + const XML_Char *s); static int FASTCALL nextScaffoldPart(XML_Parser parser); -static XML_Content * build_model(XML_Parser parser); -static ELEMENT_TYPE * -getElementType(XML_Parser parser, const ENCODING *enc, - const char *ptr, const char *end); +static XML_Content *build_model(XML_Parser parser); +static ELEMENT_TYPE *getElementType(XML_Parser parser, const ENCODING *enc, + const char *ptr, const char *end); + +static XML_Char *copyString(const XML_Char *s, + const XML_Memory_Handling_Suite *memsuite); static unsigned long generate_hash_secret_salt(XML_Parser parser); static XML_Bool startParsing(XML_Parser parser); -static XML_Parser -parserCreate(const XML_Char *encodingName, - const XML_Memory_Handling_Suite *memsuite, - const XML_Char *nameSep, - DTD *dtd); +static XML_Parser parserCreate(const XML_Char *encodingName, + const XML_Memory_Handling_Suite *memsuite, + const XML_Char *nameSep, DTD *dtd); -static void -parserInit(XML_Parser parser, const XML_Char *encodingName); +static void parserInit(XML_Parser parser, const XML_Char *encodingName); #define poolStart(pool) ((pool)->start) #define poolEnd(pool) ((pool)->ptr) @@ -458,13 +510,13 @@ parserInit(XML_Parser parser, const XML_Char *encodingName); #define poolLastChar(pool) (((pool)->ptr)[-1]) #define poolDiscard(pool) ((pool)->ptr = (pool)->start) #define poolFinish(pool) ((pool)->start = (pool)->ptr) -#define poolAppendChar(pool, c) \ - (((pool)->ptr == (pool)->end && !poolGrow(pool)) \ - ? 0 \ - : ((*((pool)->ptr)++ = c), 1)) +#define poolAppendChar(pool, c) \ + (((pool)->ptr == (pool)->end && ! poolGrow(pool)) \ + ? 0 \ + : ((*((pool)->ptr)++ = c), 1)) struct XML_ParserStruct { - /* The first member must be userData so that the XML_GetUserData + /* The first member must be m_userData so that the XML_GetUserData macro works. */ void *m_userData; void *m_handlerArg; @@ -474,7 +526,7 @@ struct XML_ParserStruct { const char *m_bufferPtr; /* past last character to be parsed */ char *m_bufferEnd; - /* allocated end of buffer */ + /* allocated end of m_buffer */ const char *m_bufferLim; XML_Index m_parseEndByteIndex; const char *m_parseEndPtr; @@ -512,7 +564,7 @@ struct XML_ParserStruct { void *m_unknownEncodingMem; void *m_unknownEncodingData; void *m_unknownEncodingHandlerData; - void (XMLCALL *m_unknownEncodingRelease)(void *); + void(XMLCALL *m_unknownEncodingRelease)(void *); PROLOG_STATE m_prologState; Processor *m_processor; enum XML_Error m_errorCode; @@ -566,227 +618,274 @@ struct XML_ParserStruct { unsigned long m_hash_secret_salt; }; -#define MALLOC(s) (parser->m_mem.malloc_fcn((s))) -#define REALLOC(p,s) (parser->m_mem.realloc_fcn((p),(s))) -#define FREE(p) (parser->m_mem.free_fcn((p))) - -#define userData (parser->m_userData) -#define handlerArg (parser->m_handlerArg) -#define startElementHandler (parser->m_startElementHandler) -#define endElementHandler (parser->m_endElementHandler) -#define characterDataHandler (parser->m_characterDataHandler) -#define processingInstructionHandler \ - (parser->m_processingInstructionHandler) -#define commentHandler (parser->m_commentHandler) -#define startCdataSectionHandler \ - (parser->m_startCdataSectionHandler) -#define endCdataSectionHandler (parser->m_endCdataSectionHandler) -#define defaultHandler (parser->m_defaultHandler) -#define startDoctypeDeclHandler (parser->m_startDoctypeDeclHandler) -#define endDoctypeDeclHandler (parser->m_endDoctypeDeclHandler) -#define unparsedEntityDeclHandler \ - (parser->m_unparsedEntityDeclHandler) -#define notationDeclHandler (parser->m_notationDeclHandler) -#define startNamespaceDeclHandler \ - (parser->m_startNamespaceDeclHandler) -#define endNamespaceDeclHandler (parser->m_endNamespaceDeclHandler) -#define notStandaloneHandler (parser->m_notStandaloneHandler) -#define externalEntityRefHandler \ - (parser->m_externalEntityRefHandler) -#define externalEntityRefHandlerArg \ - (parser->m_externalEntityRefHandlerArg) -#define internalEntityRefHandler \ - (parser->m_internalEntityRefHandler) -#define skippedEntityHandler (parser->m_skippedEntityHandler) -#define unknownEncodingHandler (parser->m_unknownEncodingHandler) -#define elementDeclHandler (parser->m_elementDeclHandler) -#define attlistDeclHandler (parser->m_attlistDeclHandler) -#define entityDeclHandler (parser->m_entityDeclHandler) -#define xmlDeclHandler (parser->m_xmlDeclHandler) -#define encoding (parser->m_encoding) -#define initEncoding (parser->m_initEncoding) -#define internalEncoding (parser->m_internalEncoding) -#define unknownEncodingMem (parser->m_unknownEncodingMem) -#define unknownEncodingData (parser->m_unknownEncodingData) -#define unknownEncodingHandlerData \ - (parser->m_unknownEncodingHandlerData) -#define unknownEncodingRelease (parser->m_unknownEncodingRelease) -#define protocolEncodingName (parser->m_protocolEncodingName) -#define ns (parser->m_ns) -#define ns_triplets (parser->m_ns_triplets) -#define prologState (parser->m_prologState) -#define processor (parser->m_processor) -#define errorCode (parser->m_errorCode) -#define eventPtr (parser->m_eventPtr) -#define eventEndPtr (parser->m_eventEndPtr) -#define positionPtr (parser->m_positionPtr) -#define position (parser->m_position) -#define openInternalEntities (parser->m_openInternalEntities) -#define freeInternalEntities (parser->m_freeInternalEntities) -#define defaultExpandInternalEntities \ - (parser->m_defaultExpandInternalEntities) -#define tagLevel (parser->m_tagLevel) -#define buffer (parser->m_buffer) -#define bufferPtr (parser->m_bufferPtr) -#define bufferEnd (parser->m_bufferEnd) -#define parseEndByteIndex (parser->m_parseEndByteIndex) -#define parseEndPtr (parser->m_parseEndPtr) -#define bufferLim (parser->m_bufferLim) -#define dataBuf (parser->m_dataBuf) -#define dataBufEnd (parser->m_dataBufEnd) -#define _dtd (parser->m_dtd) -#define curBase (parser->m_curBase) -#define declEntity (parser->m_declEntity) -#define doctypeName (parser->m_doctypeName) -#define doctypeSysid (parser->m_doctypeSysid) -#define doctypePubid (parser->m_doctypePubid) -#define declAttributeType (parser->m_declAttributeType) -#define declNotationName (parser->m_declNotationName) -#define declNotationPublicId (parser->m_declNotationPublicId) -#define declElementType (parser->m_declElementType) -#define declAttributeId (parser->m_declAttributeId) -#define declAttributeIsCdata (parser->m_declAttributeIsCdata) -#define declAttributeIsId (parser->m_declAttributeIsId) -#define freeTagList (parser->m_freeTagList) -#define freeBindingList (parser->m_freeBindingList) -#define inheritedBindings (parser->m_inheritedBindings) -#define tagStack (parser->m_tagStack) -#define atts (parser->m_atts) -#define attsSize (parser->m_attsSize) -#define nSpecifiedAtts (parser->m_nSpecifiedAtts) -#define idAttIndex (parser->m_idAttIndex) -#define nsAtts (parser->m_nsAtts) -#define nsAttsVersion (parser->m_nsAttsVersion) -#define nsAttsPower (parser->m_nsAttsPower) -#define attInfo (parser->m_attInfo) -#define tempPool (parser->m_tempPool) -#define temp2Pool (parser->m_temp2Pool) -#define groupConnector (parser->m_groupConnector) -#define groupSize (parser->m_groupSize) -#define namespaceSeparator (parser->m_namespaceSeparator) -#define parentParser (parser->m_parentParser) -#define ps_parsing (parser->m_parsingStatus.parsing) -#define ps_finalBuffer (parser->m_parsingStatus.finalBuffer) -#ifdef XML_DTD -#define isParamEntity (parser->m_isParamEntity) -#define useForeignDTD (parser->m_useForeignDTD) -#define paramEntityParsing (parser->m_paramEntityParsing) -#endif /* XML_DTD */ -#define hash_secret_salt (parser->m_hash_secret_salt) +#define MALLOC(parser, s) (parser->m_mem.malloc_fcn((s))) +#define REALLOC(parser, p, s) (parser->m_mem.realloc_fcn((p), (s))) +#define FREE(parser, p) (parser->m_mem.free_fcn((p))) XML_Parser XMLCALL -XML_ParserCreate(const XML_Char *encodingName) -{ +XML_ParserCreate(const XML_Char *encodingName) { return XML_ParserCreate_MM(encodingName, NULL, NULL); } XML_Parser XMLCALL -XML_ParserCreateNS(const XML_Char *encodingName, XML_Char nsSep) -{ +XML_ParserCreateNS(const XML_Char *encodingName, XML_Char nsSep) { XML_Char tmp[2]; *tmp = nsSep; return XML_ParserCreate_MM(encodingName, NULL, tmp); } -static const XML_Char implicitContext[] = { - ASCII_x, ASCII_m, ASCII_l, ASCII_EQUALS, ASCII_h, ASCII_t, ASCII_t, ASCII_p, - ASCII_COLON, ASCII_SLASH, ASCII_SLASH, ASCII_w, ASCII_w, ASCII_w, - ASCII_PERIOD, ASCII_w, ASCII_3, ASCII_PERIOD, ASCII_o, ASCII_r, ASCII_g, - ASCII_SLASH, ASCII_X, ASCII_M, ASCII_L, ASCII_SLASH, ASCII_1, ASCII_9, - ASCII_9, ASCII_8, ASCII_SLASH, ASCII_n, ASCII_a, ASCII_m, ASCII_e, - ASCII_s, ASCII_p, ASCII_a, ASCII_c, ASCII_e, '\0' -}; +static const XML_Char implicitContext[] + = {ASCII_x, ASCII_m, ASCII_l, ASCII_EQUALS, ASCII_h, + ASCII_t, ASCII_t, ASCII_p, ASCII_COLON, ASCII_SLASH, + ASCII_SLASH, ASCII_w, ASCII_w, ASCII_w, ASCII_PERIOD, + ASCII_w, ASCII_3, ASCII_PERIOD, ASCII_o, ASCII_r, + ASCII_g, ASCII_SLASH, ASCII_X, ASCII_M, ASCII_L, + ASCII_SLASH, ASCII_1, ASCII_9, ASCII_9, ASCII_8, + ASCII_SLASH, ASCII_n, ASCII_a, ASCII_m, ASCII_e, + ASCII_s, ASCII_p, ASCII_a, ASCII_c, ASCII_e, + '\0'}; + +/* To avoid warnings about unused functions: */ +#if ! defined(HAVE_ARC4RANDOM_BUF) && ! defined(HAVE_ARC4RANDOM) + +# if defined(HAVE_GETRANDOM) || defined(HAVE_SYSCALL_GETRANDOM) + +/* Obtain entropy on Linux 3.17+ */ +static int +writeRandomBytes_getrandom_nonblock(void *target, size_t count) { + int success = 0; /* full count bytes written? */ + size_t bytesWrittenTotal = 0; + const unsigned int getrandomFlags = GRND_NONBLOCK; + + do { + void *const currentTarget = (void *)((char *)target + bytesWrittenTotal); + const size_t bytesToWrite = count - bytesWrittenTotal; + + const int bytesWrittenMore = +# if defined(HAVE_GETRANDOM) + getrandom(currentTarget, bytesToWrite, getrandomFlags); +# else + syscall(SYS_getrandom, currentTarget, bytesToWrite, getrandomFlags); +# endif + + if (bytesWrittenMore > 0) { + bytesWrittenTotal += bytesWrittenMore; + if (bytesWrittenTotal >= count) + success = 1; + } + } while (! success && (errno == EINTR)); + + return success; +} + +# endif /* defined(HAVE_GETRANDOM) || defined(HAVE_SYSCALL_GETRANDOM) */ + +# if ! defined(_WIN32) && defined(XML_DEV_URANDOM) + +/* Extract entropy from /dev/urandom */ +static int +writeRandomBytes_dev_urandom(void *target, size_t count) { + int success = 0; /* full count bytes written? */ + size_t bytesWrittenTotal = 0; + + const int fd = open("/dev/urandom", O_RDONLY); + if (fd < 0) { + return 0; + } + + do { + void *const currentTarget = (void *)((char *)target + bytesWrittenTotal); + const size_t bytesToWrite = count - bytesWrittenTotal; + + const ssize_t bytesWrittenMore = read(fd, currentTarget, bytesToWrite); + + if (bytesWrittenMore > 0) { + bytesWrittenTotal += bytesWrittenMore; + if (bytesWrittenTotal >= count) + success = 1; + } + } while (! success && (errno == EINTR)); + + close(fd); + return success; +} + +# endif /* ! defined(_WIN32) && defined(XML_DEV_URANDOM) */ + +#endif /* ! defined(HAVE_ARC4RANDOM_BUF) && ! defined(HAVE_ARC4RANDOM) */ + +#if defined(HAVE_ARC4RANDOM) && ! defined(HAVE_ARC4RANDOM_BUF) + +static void +writeRandomBytes_arc4random(void *target, size_t count) { + size_t bytesWrittenTotal = 0; + + while (bytesWrittenTotal < count) { + const uint32_t random32 = arc4random(); + size_t i = 0; + + for (; (i < sizeof(random32)) && (bytesWrittenTotal < count); + i++, bytesWrittenTotal++) { + const uint8_t random8 = (uint8_t)(random32 >> (i * 8)); + ((uint8_t *)target)[bytesWrittenTotal] = random8; + } + } +} + +#endif /* defined(HAVE_ARC4RANDOM) && ! defined(HAVE_ARC4RANDOM_BUF) */ + +#ifdef _WIN32 + +/* Obtain entropy on Windows using the rand_s() function which + * generates cryptographically secure random numbers. Internally it + * uses RtlGenRandom API which is present in Windows XP and later. + */ +static int +writeRandomBytes_rand_s(void *target, size_t count) { + size_t bytesWrittenTotal = 0; + + while (bytesWrittenTotal < count) { + unsigned int random32 = 0; + size_t i = 0; + + if (rand_s(&random32)) + return 0; /* failure */ + + for (; (i < sizeof(random32)) && (bytesWrittenTotal < count); + i++, bytesWrittenTotal++) { + const uint8_t random8 = (uint8_t)(random32 >> (i * 8)); + ((uint8_t *)target)[bytesWrittenTotal] = random8; + } + } + return 1; /* success */ +} + +#endif /* _WIN32 */ + +#if ! defined(HAVE_ARC4RANDOM_BUF) && ! defined(HAVE_ARC4RANDOM) static unsigned long -gather_time_entropy(void) -{ -#ifdef WIN32 +gather_time_entropy(void) { +# ifdef _WIN32 FILETIME ft; GetSystemTimeAsFileTime(&ft); /* never fails */ return ft.dwHighDateTime ^ ft.dwLowDateTime; -#else +# else struct timeval tv; int gettimeofday_res; gettimeofday_res = gettimeofday(&tv, NULL); - assert (gettimeofday_res == 0); + +# if defined(NDEBUG) (void)gettimeofday_res; +# else + assert(gettimeofday_res == 0); +# endif /* defined(NDEBUG) */ /* Microseconds time is <20 bits entropy */ return tv.tv_usec; -#endif +# endif } +#endif /* ! defined(HAVE_ARC4RANDOM_BUF) && ! defined(HAVE_ARC4RANDOM) */ + static unsigned long -generate_hash_secret_salt(XML_Parser parser) -{ -#if defined(__UINTPTR_TYPE__) -# define PARSER_CAST(p) (__UINTPTR_TYPE__)(p) -#elif defined(_WIN64) && defined(_MSC_VER) -# define PARSER_CAST(p) (unsigned __int64)(p) -#else -# define PARSER_CAST(p) (p) -#endif +ENTROPY_DEBUG(const char *label, unsigned long entropy) { + const char *const EXPAT_ENTROPY_DEBUG = getenv("EXPAT_ENTROPY_DEBUG"); + if (EXPAT_ENTROPY_DEBUG && ! strcmp(EXPAT_ENTROPY_DEBUG, "1")) { + fprintf(stderr, "Entropy: %s --> 0x%0*lx (%lu bytes)\n", label, + (int)sizeof(entropy) * 2, entropy, (unsigned long)sizeof(entropy)); + } + return entropy; +} - /* Factors are 2^31-1 and 2^61-1 (Mersenne primes M31 and M61) */ - unsigned long small_factory = 2147483647ul; - unsigned long long big_factory = 2305843009213693951ull; +static unsigned long +generate_hash_secret_salt(XML_Parser parser) { + unsigned long entropy; + (void)parser; + + /* "Failproof" high quality providers: */ +#if defined(HAVE_ARC4RANDOM_BUF) + arc4random_buf(&entropy, sizeof(entropy)); + return ENTROPY_DEBUG("arc4random_buf", entropy); +#elif defined(HAVE_ARC4RANDOM) + writeRandomBytes_arc4random((void *)&entropy, sizeof(entropy)); + return ENTROPY_DEBUG("arc4random", entropy); +#else + /* Try high quality providers first .. */ +# ifdef _WIN32 + if (writeRandomBytes_rand_s((void *)&entropy, sizeof(entropy))) { + return ENTROPY_DEBUG("rand_s", entropy); + } +# elif defined(HAVE_GETRANDOM) || defined(HAVE_SYSCALL_GETRANDOM) + if (writeRandomBytes_getrandom_nonblock((void *)&entropy, sizeof(entropy))) { + return ENTROPY_DEBUG("getrandom", entropy); + } +# endif +# if ! defined(_WIN32) && defined(XML_DEV_URANDOM) + if (writeRandomBytes_dev_urandom((void *)&entropy, sizeof(entropy))) { + return ENTROPY_DEBUG("/dev/urandom", entropy); + } +# endif /* ! defined(_WIN32) && defined(XML_DEV_URANDOM) */ + /* .. and self-made low quality for backup: */ - /* Process ID is 0 bits entropy if attacker has local access - * XML_Parser address is few bits of entropy if attacker has local access */ - const unsigned long entropy = - gather_time_entropy() ^ getpid() ^ (unsigned long)PARSER_CAST(parser); + /* Process ID is 0 bits entropy if attacker has local access */ + entropy = gather_time_entropy() ^ getpid(); + /* Factors are 2^31-1 and 2^61-1 (Mersenne primes M31 and M61) */ if (sizeof(unsigned long) == 4) { - return entropy * small_factory; + return ENTROPY_DEBUG("fallback(4)", entropy * 2147483647); } else { - return entropy * (unsigned long)big_factory; + return ENTROPY_DEBUG("fallback(8)", + entropy * (unsigned long)2305843009213693951ULL); } +#endif } -static XML_Bool /* only valid for root parser */ -startParsing(XML_Parser parser) -{ - /* hash functions must be initialized before setContext() is called */ - if (hash_secret_salt == 0) - hash_secret_salt = generate_hash_secret_salt(parser); - if (ns) { - /* implicit context only set for root parser, since child - parsers (i.e. external entity parsers) will inherit it - */ - return setContext(parser, implicitContext); - } - return XML_TRUE; +static unsigned long +get_hash_secret_salt(XML_Parser parser) { + if (parser->m_parentParser != NULL) + return get_hash_secret_salt(parser->m_parentParser); + return parser->m_hash_secret_salt; +} + +static XML_Bool /* only valid for root parser */ +startParsing(XML_Parser parser) { + /* hash functions must be initialized before setContext() is called */ + if (parser->m_hash_secret_salt == 0) + parser->m_hash_secret_salt = generate_hash_secret_salt(parser); + if (parser->m_ns) { + /* implicit context only set for root parser, since child + parsers (i.e. external entity parsers) will inherit it + */ + return setContext(parser, implicitContext); + } + return XML_TRUE; } XML_Parser XMLCALL XML_ParserCreate_MM(const XML_Char *encodingName, const XML_Memory_Handling_Suite *memsuite, - const XML_Char *nameSep) -{ + const XML_Char *nameSep) { return parserCreate(encodingName, memsuite, nameSep, NULL); } static XML_Parser parserCreate(const XML_Char *encodingName, - const XML_Memory_Handling_Suite *memsuite, - const XML_Char *nameSep, - DTD *dtd) -{ + const XML_Memory_Handling_Suite *memsuite, const XML_Char *nameSep, + DTD *dtd) { XML_Parser parser; if (memsuite) { XML_Memory_Handling_Suite *mtemp; - parser = (XML_Parser) - memsuite->malloc_fcn(sizeof(struct XML_ParserStruct)); + parser = (XML_Parser)memsuite->malloc_fcn(sizeof(struct XML_ParserStruct)); if (parser != NULL) { mtemp = (XML_Memory_Handling_Suite *)&(parser->m_mem); mtemp->malloc_fcn = memsuite->malloc_fcn; mtemp->realloc_fcn = memsuite->realloc_fcn; mtemp->free_fcn = memsuite->free_fcn; } - } - else { + } else { XML_Memory_Handling_Suite *mtemp; parser = (XML_Parser)malloc(sizeof(struct XML_ParserStruct)); if (parser != NULL) { @@ -797,287 +896,336 @@ parserCreate(const XML_Char *encodingName, } } - if (!parser) + if (! parser) return parser; - buffer = NULL; - bufferLim = NULL; + parser->m_buffer = NULL; + parser->m_bufferLim = NULL; - attsSize = INIT_ATTS_SIZE; - atts = (ATTRIBUTE *)MALLOC(attsSize * sizeof(ATTRIBUTE)); - if (atts == NULL) { - FREE(parser); + parser->m_attsSize = INIT_ATTS_SIZE; + parser->m_atts + = (ATTRIBUTE *)MALLOC(parser, parser->m_attsSize * sizeof(ATTRIBUTE)); + if (parser->m_atts == NULL) { + FREE(parser, parser); return NULL; } #ifdef XML_ATTR_INFO - attInfo = (XML_AttrInfo*)MALLOC(attsSize * sizeof(XML_AttrInfo)); - if (attInfo == NULL) { - FREE(atts); - FREE(parser); + parser->m_attInfo = (XML_AttrInfo *)MALLOC( + parser, parser->m_attsSize * sizeof(XML_AttrInfo)); + if (parser->m_attInfo == NULL) { + FREE(parser, parser->m_atts); + FREE(parser, parser); return NULL; } #endif - dataBuf = (XML_Char *)MALLOC(INIT_DATA_BUF_SIZE * sizeof(XML_Char)); - if (dataBuf == NULL) { - FREE(atts); + parser->m_dataBuf + = (XML_Char *)MALLOC(parser, INIT_DATA_BUF_SIZE * sizeof(XML_Char)); + if (parser->m_dataBuf == NULL) { + FREE(parser, parser->m_atts); #ifdef XML_ATTR_INFO - FREE(attInfo); + FREE(parser, parser->m_attInfo); #endif - FREE(parser); + FREE(parser, parser); return NULL; } - dataBufEnd = dataBuf + INIT_DATA_BUF_SIZE; + parser->m_dataBufEnd = parser->m_dataBuf + INIT_DATA_BUF_SIZE; if (dtd) - _dtd = dtd; + parser->m_dtd = dtd; else { - _dtd = dtdCreate(&parser->m_mem); - if (_dtd == NULL) { - FREE(dataBuf); - FREE(atts); + parser->m_dtd = dtdCreate(&parser->m_mem); + if (parser->m_dtd == NULL) { + FREE(parser, parser->m_dataBuf); + FREE(parser, parser->m_atts); #ifdef XML_ATTR_INFO - FREE(attInfo); + FREE(parser, parser->m_attInfo); #endif - FREE(parser); + FREE(parser, parser); return NULL; } } - freeBindingList = NULL; - freeTagList = NULL; - freeInternalEntities = NULL; + parser->m_freeBindingList = NULL; + parser->m_freeTagList = NULL; + parser->m_freeInternalEntities = NULL; + + parser->m_groupSize = 0; + parser->m_groupConnector = NULL; - groupSize = 0; - groupConnector = NULL; + parser->m_unknownEncodingHandler = NULL; + parser->m_unknownEncodingHandlerData = NULL; - unknownEncodingHandler = NULL; - unknownEncodingHandlerData = NULL; + parser->m_namespaceSeparator = ASCII_EXCL; + parser->m_ns = XML_FALSE; + parser->m_ns_triplets = XML_FALSE; - namespaceSeparator = ASCII_EXCL; - ns = XML_FALSE; - ns_triplets = XML_FALSE; + parser->m_nsAtts = NULL; + parser->m_nsAttsVersion = 0; + parser->m_nsAttsPower = 0; - nsAtts = NULL; - nsAttsVersion = 0; - nsAttsPower = 0; + parser->m_protocolEncodingName = NULL; - poolInit(&tempPool, &(parser->m_mem)); - poolInit(&temp2Pool, &(parser->m_mem)); + poolInit(&parser->m_tempPool, &(parser->m_mem)); + poolInit(&parser->m_temp2Pool, &(parser->m_mem)); parserInit(parser, encodingName); - if (encodingName && !protocolEncodingName) { + if (encodingName && ! parser->m_protocolEncodingName) { XML_ParserFree(parser); return NULL; } if (nameSep) { - ns = XML_TRUE; - internalEncoding = XmlGetInternalEncodingNS(); - namespaceSeparator = *nameSep; - } - else { - internalEncoding = XmlGetInternalEncoding(); + parser->m_ns = XML_TRUE; + parser->m_internalEncoding = XmlGetInternalEncodingNS(); + parser->m_namespaceSeparator = *nameSep; + } else { + parser->m_internalEncoding = XmlGetInternalEncoding(); } return parser; } static void -parserInit(XML_Parser parser, const XML_Char *encodingName) -{ - processor = prologInitProcessor; - XmlPrologStateInit(&prologState); - protocolEncodingName = (encodingName != NULL - ? poolCopyString(&tempPool, encodingName) - : NULL); - curBase = NULL; - XmlInitEncoding(&initEncoding, &encoding, 0); - userData = NULL; - handlerArg = NULL; - startElementHandler = NULL; - endElementHandler = NULL; - characterDataHandler = NULL; - processingInstructionHandler = NULL; - commentHandler = NULL; - startCdataSectionHandler = NULL; - endCdataSectionHandler = NULL; - defaultHandler = NULL; - startDoctypeDeclHandler = NULL; - endDoctypeDeclHandler = NULL; - unparsedEntityDeclHandler = NULL; - notationDeclHandler = NULL; - startNamespaceDeclHandler = NULL; - endNamespaceDeclHandler = NULL; - notStandaloneHandler = NULL; - externalEntityRefHandler = NULL; - externalEntityRefHandlerArg = parser; - skippedEntityHandler = NULL; - elementDeclHandler = NULL; - attlistDeclHandler = NULL; - entityDeclHandler = NULL; - xmlDeclHandler = NULL; - bufferPtr = buffer; - bufferEnd = buffer; - parseEndByteIndex = 0; - parseEndPtr = NULL; - declElementType = NULL; - declAttributeId = NULL; - declEntity = NULL; - doctypeName = NULL; - doctypeSysid = NULL; - doctypePubid = NULL; - declAttributeType = NULL; - declNotationName = NULL; - declNotationPublicId = NULL; - declAttributeIsCdata = XML_FALSE; - declAttributeIsId = XML_FALSE; - memset(&position, 0, sizeof(POSITION)); - errorCode = XML_ERROR_NONE; - eventPtr = NULL; - eventEndPtr = NULL; - positionPtr = NULL; - openInternalEntities = NULL; - defaultExpandInternalEntities = XML_TRUE; - tagLevel = 0; - tagStack = NULL; - inheritedBindings = NULL; - nSpecifiedAtts = 0; - unknownEncodingMem = NULL; - unknownEncodingRelease = NULL; - unknownEncodingData = NULL; - parentParser = NULL; - ps_parsing = XML_INITIALIZED; +parserInit(XML_Parser parser, const XML_Char *encodingName) { + parser->m_processor = prologInitProcessor; + XmlPrologStateInit(&parser->m_prologState); + if (encodingName != NULL) { + parser->m_protocolEncodingName = copyString(encodingName, &(parser->m_mem)); + } + parser->m_curBase = NULL; + XmlInitEncoding(&parser->m_initEncoding, &parser->m_encoding, 0); + parser->m_userData = NULL; + parser->m_handlerArg = NULL; + parser->m_startElementHandler = NULL; + parser->m_endElementHandler = NULL; + parser->m_characterDataHandler = NULL; + parser->m_processingInstructionHandler = NULL; + parser->m_commentHandler = NULL; + parser->m_startCdataSectionHandler = NULL; + parser->m_endCdataSectionHandler = NULL; + parser->m_defaultHandler = NULL; + parser->m_startDoctypeDeclHandler = NULL; + parser->m_endDoctypeDeclHandler = NULL; + parser->m_unparsedEntityDeclHandler = NULL; + parser->m_notationDeclHandler = NULL; + parser->m_startNamespaceDeclHandler = NULL; + parser->m_endNamespaceDeclHandler = NULL; + parser->m_notStandaloneHandler = NULL; + parser->m_externalEntityRefHandler = NULL; + parser->m_externalEntityRefHandlerArg = parser; + parser->m_skippedEntityHandler = NULL; + parser->m_elementDeclHandler = NULL; + parser->m_attlistDeclHandler = NULL; + parser->m_entityDeclHandler = NULL; + parser->m_xmlDeclHandler = NULL; + parser->m_bufferPtr = parser->m_buffer; + parser->m_bufferEnd = parser->m_buffer; + parser->m_parseEndByteIndex = 0; + parser->m_parseEndPtr = NULL; + parser->m_declElementType = NULL; + parser->m_declAttributeId = NULL; + parser->m_declEntity = NULL; + parser->m_doctypeName = NULL; + parser->m_doctypeSysid = NULL; + parser->m_doctypePubid = NULL; + parser->m_declAttributeType = NULL; + parser->m_declNotationName = NULL; + parser->m_declNotationPublicId = NULL; + parser->m_declAttributeIsCdata = XML_FALSE; + parser->m_declAttributeIsId = XML_FALSE; + memset(&parser->m_position, 0, sizeof(POSITION)); + parser->m_errorCode = XML_ERROR_NONE; + parser->m_eventPtr = NULL; + parser->m_eventEndPtr = NULL; + parser->m_positionPtr = NULL; + parser->m_openInternalEntities = NULL; + parser->m_defaultExpandInternalEntities = XML_TRUE; + parser->m_tagLevel = 0; + parser->m_tagStack = NULL; + parser->m_inheritedBindings = NULL; + parser->m_nSpecifiedAtts = 0; + parser->m_unknownEncodingMem = NULL; + parser->m_unknownEncodingRelease = NULL; + parser->m_unknownEncodingData = NULL; + parser->m_parentParser = NULL; + parser->m_parsingStatus.parsing = XML_INITIALIZED; #ifdef XML_DTD - isParamEntity = XML_FALSE; - useForeignDTD = XML_FALSE; - paramEntityParsing = XML_PARAM_ENTITY_PARSING_NEVER; + parser->m_isParamEntity = XML_FALSE; + parser->m_useForeignDTD = XML_FALSE; + parser->m_paramEntityParsing = XML_PARAM_ENTITY_PARSING_NEVER; #endif - hash_secret_salt = 0; + parser->m_hash_secret_salt = 0; } -/* moves list of bindings to freeBindingList */ +/* moves list of bindings to m_freeBindingList */ static void FASTCALL -moveToFreeBindingList(XML_Parser parser, BINDING *bindings) -{ +moveToFreeBindingList(XML_Parser parser, BINDING *bindings) { while (bindings) { BINDING *b = bindings; bindings = bindings->nextTagBinding; - b->nextTagBinding = freeBindingList; - freeBindingList = b; + b->nextTagBinding = parser->m_freeBindingList; + parser->m_freeBindingList = b; } } XML_Bool XMLCALL -XML_ParserReset(XML_Parser parser, const XML_Char *encodingName) -{ +XML_ParserReset(XML_Parser parser, const XML_Char *encodingName) { TAG *tStk; OPEN_INTERNAL_ENTITY *openEntityList; - if (parentParser) + + if (parser == NULL) + return XML_FALSE; + + if (parser->m_parentParser) return XML_FALSE; - /* move tagStack to freeTagList */ - tStk = tagStack; + /* move m_tagStack to m_freeTagList */ + tStk = parser->m_tagStack; while (tStk) { TAG *tag = tStk; tStk = tStk->parent; - tag->parent = freeTagList; + tag->parent = parser->m_freeTagList; moveToFreeBindingList(parser, tag->bindings); tag->bindings = NULL; - freeTagList = tag; + parser->m_freeTagList = tag; } - /* move openInternalEntities to freeInternalEntities */ - openEntityList = openInternalEntities; + /* move m_openInternalEntities to m_freeInternalEntities */ + openEntityList = parser->m_openInternalEntities; while (openEntityList) { OPEN_INTERNAL_ENTITY *openEntity = openEntityList; openEntityList = openEntity->next; - openEntity->next = freeInternalEntities; - freeInternalEntities = openEntity; - } - moveToFreeBindingList(parser, inheritedBindings); - FREE(unknownEncodingMem); - if (unknownEncodingRelease) - unknownEncodingRelease(unknownEncodingData); - poolClear(&tempPool); - poolClear(&temp2Pool); + openEntity->next = parser->m_freeInternalEntities; + parser->m_freeInternalEntities = openEntity; + } + moveToFreeBindingList(parser, parser->m_inheritedBindings); + FREE(parser, parser->m_unknownEncodingMem); + if (parser->m_unknownEncodingRelease) + parser->m_unknownEncodingRelease(parser->m_unknownEncodingData); + poolClear(&parser->m_tempPool); + poolClear(&parser->m_temp2Pool); + FREE(parser, (void *)parser->m_protocolEncodingName); + parser->m_protocolEncodingName = NULL; parserInit(parser, encodingName); - dtdReset(_dtd, &parser->m_mem); + dtdReset(parser->m_dtd, &parser->m_mem); return XML_TRUE; } enum XML_Status XMLCALL -XML_SetEncoding(XML_Parser parser, const XML_Char *encodingName) -{ +XML_SetEncoding(XML_Parser parser, const XML_Char *encodingName) { + if (parser == NULL) + return XML_STATUS_ERROR; /* Block after XML_Parse()/XML_ParseBuffer() has been called. XXX There's no way for the caller to determine which of the XXX possible error cases caused the XML_STATUS_ERROR return. */ - if (ps_parsing == XML_PARSING || ps_parsing == XML_SUSPENDED) + if (parser->m_parsingStatus.parsing == XML_PARSING + || parser->m_parsingStatus.parsing == XML_SUSPENDED) return XML_STATUS_ERROR; + + /* Get rid of any previous encoding name */ + FREE(parser, (void *)parser->m_protocolEncodingName); + if (encodingName == NULL) - protocolEncodingName = NULL; + /* No new encoding name */ + parser->m_protocolEncodingName = NULL; else { - protocolEncodingName = poolCopyString(&tempPool, encodingName); - if (!protocolEncodingName) + /* Copy the new encoding name into allocated memory */ + parser->m_protocolEncodingName = copyString(encodingName, &(parser->m_mem)); + if (! parser->m_protocolEncodingName) return XML_STATUS_ERROR; } return XML_STATUS_OK; } XML_Parser XMLCALL -XML_ExternalEntityParserCreate(XML_Parser oldParser, - const XML_Char *context, - const XML_Char *encodingName) -{ +XML_ExternalEntityParserCreate(XML_Parser oldParser, const XML_Char *context, + const XML_Char *encodingName) { XML_Parser parser = oldParser; DTD *newDtd = NULL; - DTD *oldDtd = _dtd; - XML_StartElementHandler oldStartElementHandler = startElementHandler; - XML_EndElementHandler oldEndElementHandler = endElementHandler; - XML_CharacterDataHandler oldCharacterDataHandler = characterDataHandler; - XML_ProcessingInstructionHandler oldProcessingInstructionHandler - = processingInstructionHandler; - XML_CommentHandler oldCommentHandler = commentHandler; - XML_StartCdataSectionHandler oldStartCdataSectionHandler - = startCdataSectionHandler; - XML_EndCdataSectionHandler oldEndCdataSectionHandler - = endCdataSectionHandler; - XML_DefaultHandler oldDefaultHandler = defaultHandler; - XML_UnparsedEntityDeclHandler oldUnparsedEntityDeclHandler - = unparsedEntityDeclHandler; - XML_NotationDeclHandler oldNotationDeclHandler = notationDeclHandler; - XML_StartNamespaceDeclHandler oldStartNamespaceDeclHandler - = startNamespaceDeclHandler; - XML_EndNamespaceDeclHandler oldEndNamespaceDeclHandler - = endNamespaceDeclHandler; - XML_NotStandaloneHandler oldNotStandaloneHandler = notStandaloneHandler; - XML_ExternalEntityRefHandler oldExternalEntityRefHandler - = externalEntityRefHandler; - XML_SkippedEntityHandler oldSkippedEntityHandler = skippedEntityHandler; - XML_UnknownEncodingHandler oldUnknownEncodingHandler - = unknownEncodingHandler; - XML_ElementDeclHandler oldElementDeclHandler = elementDeclHandler; - XML_AttlistDeclHandler oldAttlistDeclHandler = attlistDeclHandler; - XML_EntityDeclHandler oldEntityDeclHandler = entityDeclHandler; - XML_XmlDeclHandler oldXmlDeclHandler = xmlDeclHandler; - ELEMENT_TYPE * oldDeclElementType = declElementType; - - void *oldUserData = userData; - void *oldHandlerArg = handlerArg; - XML_Bool oldDefaultExpandInternalEntities = defaultExpandInternalEntities; - XML_Parser oldExternalEntityRefHandlerArg = externalEntityRefHandlerArg; + DTD *oldDtd; + XML_StartElementHandler oldStartElementHandler; + XML_EndElementHandler oldEndElementHandler; + XML_CharacterDataHandler oldCharacterDataHandler; + XML_ProcessingInstructionHandler oldProcessingInstructionHandler; + XML_CommentHandler oldCommentHandler; + XML_StartCdataSectionHandler oldStartCdataSectionHandler; + XML_EndCdataSectionHandler oldEndCdataSectionHandler; + XML_DefaultHandler oldDefaultHandler; + XML_UnparsedEntityDeclHandler oldUnparsedEntityDeclHandler; + XML_NotationDeclHandler oldNotationDeclHandler; + XML_StartNamespaceDeclHandler oldStartNamespaceDeclHandler; + XML_EndNamespaceDeclHandler oldEndNamespaceDeclHandler; + XML_NotStandaloneHandler oldNotStandaloneHandler; + XML_ExternalEntityRefHandler oldExternalEntityRefHandler; + XML_SkippedEntityHandler oldSkippedEntityHandler; + XML_UnknownEncodingHandler oldUnknownEncodingHandler; + XML_ElementDeclHandler oldElementDeclHandler; + XML_AttlistDeclHandler oldAttlistDeclHandler; + XML_EntityDeclHandler oldEntityDeclHandler; + XML_XmlDeclHandler oldXmlDeclHandler; + ELEMENT_TYPE *oldDeclElementType; + + void *oldUserData; + void *oldHandlerArg; + XML_Bool oldDefaultExpandInternalEntities; + XML_Parser oldExternalEntityRefHandlerArg; +#ifdef XML_DTD + enum XML_ParamEntityParsing oldParamEntityParsing; + int oldInEntityValue; +#endif + XML_Bool oldns_triplets; + /* Note that the new parser shares the same hash secret as the old + parser, so that dtdCopy and copyEntityTable can lookup values + from hash tables associated with either parser without us having + to worry which hash secrets each table has. + */ + unsigned long oldhash_secret_salt; + + /* Validate the oldParser parameter before we pull everything out of it */ + if (oldParser == NULL) + return NULL; + + /* Stash the original parser contents on the stack */ + oldDtd = parser->m_dtd; + oldStartElementHandler = parser->m_startElementHandler; + oldEndElementHandler = parser->m_endElementHandler; + oldCharacterDataHandler = parser->m_characterDataHandler; + oldProcessingInstructionHandler = parser->m_processingInstructionHandler; + oldCommentHandler = parser->m_commentHandler; + oldStartCdataSectionHandler = parser->m_startCdataSectionHandler; + oldEndCdataSectionHandler = parser->m_endCdataSectionHandler; + oldDefaultHandler = parser->m_defaultHandler; + oldUnparsedEntityDeclHandler = parser->m_unparsedEntityDeclHandler; + oldNotationDeclHandler = parser->m_notationDeclHandler; + oldStartNamespaceDeclHandler = parser->m_startNamespaceDeclHandler; + oldEndNamespaceDeclHandler = parser->m_endNamespaceDeclHandler; + oldNotStandaloneHandler = parser->m_notStandaloneHandler; + oldExternalEntityRefHandler = parser->m_externalEntityRefHandler; + oldSkippedEntityHandler = parser->m_skippedEntityHandler; + oldUnknownEncodingHandler = parser->m_unknownEncodingHandler; + oldElementDeclHandler = parser->m_elementDeclHandler; + oldAttlistDeclHandler = parser->m_attlistDeclHandler; + oldEntityDeclHandler = parser->m_entityDeclHandler; + oldXmlDeclHandler = parser->m_xmlDeclHandler; + oldDeclElementType = parser->m_declElementType; + + oldUserData = parser->m_userData; + oldHandlerArg = parser->m_handlerArg; + oldDefaultExpandInternalEntities = parser->m_defaultExpandInternalEntities; + oldExternalEntityRefHandlerArg = parser->m_externalEntityRefHandlerArg; #ifdef XML_DTD - enum XML_ParamEntityParsing oldParamEntityParsing = paramEntityParsing; - int oldInEntityValue = prologState.inEntityValue; + oldParamEntityParsing = parser->m_paramEntityParsing; + oldInEntityValue = parser->m_prologState.inEntityValue; #endif - XML_Bool oldns_triplets = ns_triplets; + oldns_triplets = parser->m_ns_triplets; /* Note that the new parser shares the same hash secret as the old parser, so that dtdCopy and copyEntityTable can lookup values from hash tables associated with either parser without us having to worry which hash secrets each table has. */ - unsigned long oldhash_secret_salt = hash_secret_salt; + oldhash_secret_salt = parser->m_hash_secret_salt; #ifdef XML_DTD - if (!context) + if (! context) newDtd = oldDtd; #endif /* XML_DTD */ @@ -1086,171 +1234,171 @@ XML_ExternalEntityParserCreate(XML_Parser oldParser, here. This makes this function more painful to follow than it would be otherwise. */ - if (ns) { + if (parser->m_ns) { XML_Char tmp[2]; - *tmp = namespaceSeparator; + *tmp = parser->m_namespaceSeparator; parser = parserCreate(encodingName, &parser->m_mem, tmp, newDtd); - } - else { + } else { parser = parserCreate(encodingName, &parser->m_mem, NULL, newDtd); } - if (!parser) + if (! parser) return NULL; - startElementHandler = oldStartElementHandler; - endElementHandler = oldEndElementHandler; - characterDataHandler = oldCharacterDataHandler; - processingInstructionHandler = oldProcessingInstructionHandler; - commentHandler = oldCommentHandler; - startCdataSectionHandler = oldStartCdataSectionHandler; - endCdataSectionHandler = oldEndCdataSectionHandler; - defaultHandler = oldDefaultHandler; - unparsedEntityDeclHandler = oldUnparsedEntityDeclHandler; - notationDeclHandler = oldNotationDeclHandler; - startNamespaceDeclHandler = oldStartNamespaceDeclHandler; - endNamespaceDeclHandler = oldEndNamespaceDeclHandler; - notStandaloneHandler = oldNotStandaloneHandler; - externalEntityRefHandler = oldExternalEntityRefHandler; - skippedEntityHandler = oldSkippedEntityHandler; - unknownEncodingHandler = oldUnknownEncodingHandler; - elementDeclHandler = oldElementDeclHandler; - attlistDeclHandler = oldAttlistDeclHandler; - entityDeclHandler = oldEntityDeclHandler; - xmlDeclHandler = oldXmlDeclHandler; - declElementType = oldDeclElementType; - userData = oldUserData; + parser->m_startElementHandler = oldStartElementHandler; + parser->m_endElementHandler = oldEndElementHandler; + parser->m_characterDataHandler = oldCharacterDataHandler; + parser->m_processingInstructionHandler = oldProcessingInstructionHandler; + parser->m_commentHandler = oldCommentHandler; + parser->m_startCdataSectionHandler = oldStartCdataSectionHandler; + parser->m_endCdataSectionHandler = oldEndCdataSectionHandler; + parser->m_defaultHandler = oldDefaultHandler; + parser->m_unparsedEntityDeclHandler = oldUnparsedEntityDeclHandler; + parser->m_notationDeclHandler = oldNotationDeclHandler; + parser->m_startNamespaceDeclHandler = oldStartNamespaceDeclHandler; + parser->m_endNamespaceDeclHandler = oldEndNamespaceDeclHandler; + parser->m_notStandaloneHandler = oldNotStandaloneHandler; + parser->m_externalEntityRefHandler = oldExternalEntityRefHandler; + parser->m_skippedEntityHandler = oldSkippedEntityHandler; + parser->m_unknownEncodingHandler = oldUnknownEncodingHandler; + parser->m_elementDeclHandler = oldElementDeclHandler; + parser->m_attlistDeclHandler = oldAttlistDeclHandler; + parser->m_entityDeclHandler = oldEntityDeclHandler; + parser->m_xmlDeclHandler = oldXmlDeclHandler; + parser->m_declElementType = oldDeclElementType; + parser->m_userData = oldUserData; if (oldUserData == oldHandlerArg) - handlerArg = userData; + parser->m_handlerArg = parser->m_userData; else - handlerArg = parser; + parser->m_handlerArg = parser; if (oldExternalEntityRefHandlerArg != oldParser) - externalEntityRefHandlerArg = oldExternalEntityRefHandlerArg; - defaultExpandInternalEntities = oldDefaultExpandInternalEntities; - ns_triplets = oldns_triplets; - hash_secret_salt = oldhash_secret_salt; - parentParser = oldParser; + parser->m_externalEntityRefHandlerArg = oldExternalEntityRefHandlerArg; + parser->m_defaultExpandInternalEntities = oldDefaultExpandInternalEntities; + parser->m_ns_triplets = oldns_triplets; + parser->m_hash_secret_salt = oldhash_secret_salt; + parser->m_parentParser = oldParser; #ifdef XML_DTD - paramEntityParsing = oldParamEntityParsing; - prologState.inEntityValue = oldInEntityValue; + parser->m_paramEntityParsing = oldParamEntityParsing; + parser->m_prologState.inEntityValue = oldInEntityValue; if (context) { #endif /* XML_DTD */ - if (!dtdCopy(oldParser, _dtd, oldDtd, &parser->m_mem) - || !setContext(parser, context)) { + if (! dtdCopy(oldParser, parser->m_dtd, oldDtd, &parser->m_mem) + || ! setContext(parser, context)) { XML_ParserFree(parser); return NULL; } - processor = externalEntityInitProcessor; + parser->m_processor = externalEntityInitProcessor; #ifdef XML_DTD - } - else { - /* The DTD instance referenced by _dtd is shared between the document's - root parser and external PE parsers, therefore one does not need to - call setContext. In addition, one also *must* not call setContext, - because this would overwrite existing prefix->binding pointers in - _dtd with ones that get destroyed with the external PE parser. - This would leave those prefixes with dangling pointers. + } else { + /* The DTD instance referenced by parser->m_dtd is shared between the + document's root parser and external PE parsers, therefore one does not + need to call setContext. In addition, one also *must* not call + setContext, because this would overwrite existing prefix->binding + pointers in parser->m_dtd with ones that get destroyed with the external + PE parser. This would leave those prefixes with dangling pointers. */ - isParamEntity = XML_TRUE; - XmlPrologStateInitExternalEntity(&prologState); - processor = externalParEntInitProcessor; + parser->m_isParamEntity = XML_TRUE; + XmlPrologStateInitExternalEntity(&parser->m_prologState); + parser->m_processor = externalParEntInitProcessor; } #endif /* XML_DTD */ return parser; } static void FASTCALL -destroyBindings(BINDING *bindings, XML_Parser parser) -{ +destroyBindings(BINDING *bindings, XML_Parser parser) { for (;;) { BINDING *b = bindings; - if (!b) + if (! b) break; bindings = b->nextTagBinding; - FREE(b->uri); - FREE(b); + FREE(parser, b->uri); + FREE(parser, b); } } void XMLCALL -XML_ParserFree(XML_Parser parser) -{ +XML_ParserFree(XML_Parser parser) { TAG *tagList; OPEN_INTERNAL_ENTITY *entityList; if (parser == NULL) return; - /* free tagStack and freeTagList */ - tagList = tagStack; + /* free m_tagStack and m_freeTagList */ + tagList = parser->m_tagStack; for (;;) { TAG *p; if (tagList == NULL) { - if (freeTagList == NULL) + if (parser->m_freeTagList == NULL) break; - tagList = freeTagList; - freeTagList = NULL; + tagList = parser->m_freeTagList; + parser->m_freeTagList = NULL; } p = tagList; tagList = tagList->parent; - FREE(p->buf); + FREE(parser, p->buf); destroyBindings(p->bindings, parser); - FREE(p); + FREE(parser, p); } - /* free openInternalEntities and freeInternalEntities */ - entityList = openInternalEntities; + /* free m_openInternalEntities and m_freeInternalEntities */ + entityList = parser->m_openInternalEntities; for (;;) { OPEN_INTERNAL_ENTITY *openEntity; if (entityList == NULL) { - if (freeInternalEntities == NULL) + if (parser->m_freeInternalEntities == NULL) break; - entityList = freeInternalEntities; - freeInternalEntities = NULL; + entityList = parser->m_freeInternalEntities; + parser->m_freeInternalEntities = NULL; } openEntity = entityList; entityList = entityList->next; - FREE(openEntity); + FREE(parser, openEntity); } - destroyBindings(freeBindingList, parser); - destroyBindings(inheritedBindings, parser); - poolDestroy(&tempPool); - poolDestroy(&temp2Pool); + destroyBindings(parser->m_freeBindingList, parser); + destroyBindings(parser->m_inheritedBindings, parser); + poolDestroy(&parser->m_tempPool); + poolDestroy(&parser->m_temp2Pool); + FREE(parser, (void *)parser->m_protocolEncodingName); #ifdef XML_DTD /* external parameter entity parsers share the DTD structure parser->m_dtd with the root parser, so we must not destroy it */ - if (!isParamEntity && _dtd) + if (! parser->m_isParamEntity && parser->m_dtd) #else - if (_dtd) + if (parser->m_dtd) #endif /* XML_DTD */ - dtdDestroy(_dtd, (XML_Bool)!parentParser, &parser->m_mem); - FREE((void *)atts); + dtdDestroy(parser->m_dtd, (XML_Bool)! parser->m_parentParser, + &parser->m_mem); + FREE(parser, (void *)parser->m_atts); #ifdef XML_ATTR_INFO - FREE((void *)attInfo); + FREE(parser, (void *)parser->m_attInfo); #endif - FREE(groupConnector); - FREE(buffer); - FREE(dataBuf); - FREE(nsAtts); - FREE(unknownEncodingMem); - if (unknownEncodingRelease) - unknownEncodingRelease(unknownEncodingData); - FREE(parser); + FREE(parser, parser->m_groupConnector); + FREE(parser, parser->m_buffer); + FREE(parser, parser->m_dataBuf); + FREE(parser, parser->m_nsAtts); + FREE(parser, parser->m_unknownEncodingMem); + if (parser->m_unknownEncodingRelease) + parser->m_unknownEncodingRelease(parser->m_unknownEncodingData); + FREE(parser, parser); } void XMLCALL -XML_UseParserAsHandlerArg(XML_Parser parser) -{ - handlerArg = parser; +XML_UseParserAsHandlerArg(XML_Parser parser) { + if (parser != NULL) + parser->m_handlerArg = parser; } enum XML_Error XMLCALL -XML_UseForeignDTD(XML_Parser parser, XML_Bool useDTD) -{ +XML_UseForeignDTD(XML_Parser parser, XML_Bool useDTD) { + if (parser == NULL) + return XML_ERROR_INVALID_ARGUMENT; #ifdef XML_DTD /* block after XML_Parse()/XML_ParseBuffer() has been called */ - if (ps_parsing == XML_PARSING || ps_parsing == XML_SUSPENDED) + if (parser->m_parsingStatus.parsing == XML_PARSING + || parser->m_parsingStatus.parsing == XML_SUSPENDED) return XML_ERROR_CANT_CHANGE_FEATURE_ONCE_PARSING; - useForeignDTD = useDTD; + parser->m_useForeignDTD = useDTD; return XML_ERROR_NONE; #else return XML_ERROR_FEATURE_REQUIRES_XML_DTD; @@ -1258,273 +1406,285 @@ XML_UseForeignDTD(XML_Parser parser, XML_Bool useDTD) } void XMLCALL -XML_SetReturnNSTriplet(XML_Parser parser, int do_nst) -{ +XML_SetReturnNSTriplet(XML_Parser parser, int do_nst) { + if (parser == NULL) + return; /* block after XML_Parse()/XML_ParseBuffer() has been called */ - if (ps_parsing == XML_PARSING || ps_parsing == XML_SUSPENDED) + if (parser->m_parsingStatus.parsing == XML_PARSING + || parser->m_parsingStatus.parsing == XML_SUSPENDED) return; - ns_triplets = do_nst ? XML_TRUE : XML_FALSE; + parser->m_ns_triplets = do_nst ? XML_TRUE : XML_FALSE; } void XMLCALL -XML_SetUserData(XML_Parser parser, void *p) -{ - if (handlerArg == userData) - handlerArg = userData = p; +XML_SetUserData(XML_Parser parser, void *p) { + if (parser == NULL) + return; + if (parser->m_handlerArg == parser->m_userData) + parser->m_handlerArg = parser->m_userData = p; else - userData = p; + parser->m_userData = p; } enum XML_Status XMLCALL -XML_SetBase(XML_Parser parser, const XML_Char *p) -{ +XML_SetBase(XML_Parser parser, const XML_Char *p) { + if (parser == NULL) + return XML_STATUS_ERROR; if (p) { - p = poolCopyString(&_dtd->pool, p); - if (!p) + p = poolCopyString(&parser->m_dtd->pool, p); + if (! p) return XML_STATUS_ERROR; - curBase = p; - } - else - curBase = NULL; + parser->m_curBase = p; + } else + parser->m_curBase = NULL; return XML_STATUS_OK; } -const XML_Char * XMLCALL -XML_GetBase(XML_Parser parser) -{ - return curBase; +const XML_Char *XMLCALL +XML_GetBase(XML_Parser parser) { + if (parser == NULL) + return NULL; + return parser->m_curBase; } int XMLCALL -XML_GetSpecifiedAttributeCount(XML_Parser parser) -{ - return nSpecifiedAtts; +XML_GetSpecifiedAttributeCount(XML_Parser parser) { + if (parser == NULL) + return -1; + return parser->m_nSpecifiedAtts; } int XMLCALL -XML_GetIdAttributeIndex(XML_Parser parser) -{ - return idAttIndex; +XML_GetIdAttributeIndex(XML_Parser parser) { + if (parser == NULL) + return -1; + return parser->m_idAttIndex; } #ifdef XML_ATTR_INFO -const XML_AttrInfo * XMLCALL -XML_GetAttributeInfo(XML_Parser parser) -{ - return attInfo; +const XML_AttrInfo *XMLCALL +XML_GetAttributeInfo(XML_Parser parser) { + if (parser == NULL) + return NULL; + return parser->m_attInfo; } #endif void XMLCALL -XML_SetElementHandler(XML_Parser parser, - XML_StartElementHandler start, - XML_EndElementHandler end) -{ - startElementHandler = start; - endElementHandler = end; +XML_SetElementHandler(XML_Parser parser, XML_StartElementHandler start, + XML_EndElementHandler end) { + if (parser == NULL) + return; + parser->m_startElementHandler = start; + parser->m_endElementHandler = end; } void XMLCALL -XML_SetStartElementHandler(XML_Parser parser, - XML_StartElementHandler start) { - startElementHandler = start; +XML_SetStartElementHandler(XML_Parser parser, XML_StartElementHandler start) { + if (parser != NULL) + parser->m_startElementHandler = start; } void XMLCALL -XML_SetEndElementHandler(XML_Parser parser, - XML_EndElementHandler end) { - endElementHandler = end; +XML_SetEndElementHandler(XML_Parser parser, XML_EndElementHandler end) { + if (parser != NULL) + parser->m_endElementHandler = end; } void XMLCALL XML_SetCharacterDataHandler(XML_Parser parser, - XML_CharacterDataHandler handler) -{ - characterDataHandler = handler; + XML_CharacterDataHandler handler) { + if (parser != NULL) + parser->m_characterDataHandler = handler; } void XMLCALL XML_SetProcessingInstructionHandler(XML_Parser parser, - XML_ProcessingInstructionHandler handler) -{ - processingInstructionHandler = handler; + XML_ProcessingInstructionHandler handler) { + if (parser != NULL) + parser->m_processingInstructionHandler = handler; } void XMLCALL -XML_SetCommentHandler(XML_Parser parser, - XML_CommentHandler handler) -{ - commentHandler = handler; +XML_SetCommentHandler(XML_Parser parser, XML_CommentHandler handler) { + if (parser != NULL) + parser->m_commentHandler = handler; } void XMLCALL XML_SetCdataSectionHandler(XML_Parser parser, XML_StartCdataSectionHandler start, - XML_EndCdataSectionHandler end) -{ - startCdataSectionHandler = start; - endCdataSectionHandler = end; + XML_EndCdataSectionHandler end) { + if (parser == NULL) + return; + parser->m_startCdataSectionHandler = start; + parser->m_endCdataSectionHandler = end; } void XMLCALL XML_SetStartCdataSectionHandler(XML_Parser parser, XML_StartCdataSectionHandler start) { - startCdataSectionHandler = start; + if (parser != NULL) + parser->m_startCdataSectionHandler = start; } void XMLCALL XML_SetEndCdataSectionHandler(XML_Parser parser, XML_EndCdataSectionHandler end) { - endCdataSectionHandler = end; + if (parser != NULL) + parser->m_endCdataSectionHandler = end; } void XMLCALL -XML_SetDefaultHandler(XML_Parser parser, - XML_DefaultHandler handler) -{ - defaultHandler = handler; - defaultExpandInternalEntities = XML_FALSE; +XML_SetDefaultHandler(XML_Parser parser, XML_DefaultHandler handler) { + if (parser == NULL) + return; + parser->m_defaultHandler = handler; + parser->m_defaultExpandInternalEntities = XML_FALSE; } void XMLCALL -XML_SetDefaultHandlerExpand(XML_Parser parser, - XML_DefaultHandler handler) -{ - defaultHandler = handler; - defaultExpandInternalEntities = XML_TRUE; +XML_SetDefaultHandlerExpand(XML_Parser parser, XML_DefaultHandler handler) { + if (parser == NULL) + return; + parser->m_defaultHandler = handler; + parser->m_defaultExpandInternalEntities = XML_TRUE; } void XMLCALL -XML_SetDoctypeDeclHandler(XML_Parser parser, - XML_StartDoctypeDeclHandler start, - XML_EndDoctypeDeclHandler end) -{ - startDoctypeDeclHandler = start; - endDoctypeDeclHandler = end; +XML_SetDoctypeDeclHandler(XML_Parser parser, XML_StartDoctypeDeclHandler start, + XML_EndDoctypeDeclHandler end) { + if (parser == NULL) + return; + parser->m_startDoctypeDeclHandler = start; + parser->m_endDoctypeDeclHandler = end; } void XMLCALL XML_SetStartDoctypeDeclHandler(XML_Parser parser, XML_StartDoctypeDeclHandler start) { - startDoctypeDeclHandler = start; + if (parser != NULL) + parser->m_startDoctypeDeclHandler = start; } void XMLCALL -XML_SetEndDoctypeDeclHandler(XML_Parser parser, - XML_EndDoctypeDeclHandler end) { - endDoctypeDeclHandler = end; +XML_SetEndDoctypeDeclHandler(XML_Parser parser, XML_EndDoctypeDeclHandler end) { + if (parser != NULL) + parser->m_endDoctypeDeclHandler = end; } void XMLCALL XML_SetUnparsedEntityDeclHandler(XML_Parser parser, - XML_UnparsedEntityDeclHandler handler) -{ - unparsedEntityDeclHandler = handler; + XML_UnparsedEntityDeclHandler handler) { + if (parser != NULL) + parser->m_unparsedEntityDeclHandler = handler; } void XMLCALL -XML_SetNotationDeclHandler(XML_Parser parser, - XML_NotationDeclHandler handler) -{ - notationDeclHandler = handler; +XML_SetNotationDeclHandler(XML_Parser parser, XML_NotationDeclHandler handler) { + if (parser != NULL) + parser->m_notationDeclHandler = handler; } void XMLCALL XML_SetNamespaceDeclHandler(XML_Parser parser, XML_StartNamespaceDeclHandler start, - XML_EndNamespaceDeclHandler end) -{ - startNamespaceDeclHandler = start; - endNamespaceDeclHandler = end; + XML_EndNamespaceDeclHandler end) { + if (parser == NULL) + return; + parser->m_startNamespaceDeclHandler = start; + parser->m_endNamespaceDeclHandler = end; } void XMLCALL XML_SetStartNamespaceDeclHandler(XML_Parser parser, XML_StartNamespaceDeclHandler start) { - startNamespaceDeclHandler = start; + if (parser != NULL) + parser->m_startNamespaceDeclHandler = start; } void XMLCALL XML_SetEndNamespaceDeclHandler(XML_Parser parser, XML_EndNamespaceDeclHandler end) { - endNamespaceDeclHandler = end; + if (parser != NULL) + parser->m_endNamespaceDeclHandler = end; } void XMLCALL XML_SetNotStandaloneHandler(XML_Parser parser, - XML_NotStandaloneHandler handler) -{ - notStandaloneHandler = handler; + XML_NotStandaloneHandler handler) { + if (parser != NULL) + parser->m_notStandaloneHandler = handler; } void XMLCALL XML_SetExternalEntityRefHandler(XML_Parser parser, - XML_ExternalEntityRefHandler handler) -{ - externalEntityRefHandler = handler; + XML_ExternalEntityRefHandler handler) { + if (parser != NULL) + parser->m_externalEntityRefHandler = handler; } void XMLCALL -XML_SetExternalEntityRefHandlerArg(XML_Parser parser, void *arg) -{ +XML_SetExternalEntityRefHandlerArg(XML_Parser parser, void *arg) { + if (parser == NULL) + return; if (arg) - externalEntityRefHandlerArg = (XML_Parser)arg; + parser->m_externalEntityRefHandlerArg = (XML_Parser)arg; else - externalEntityRefHandlerArg = parser; + parser->m_externalEntityRefHandlerArg = parser; } void XMLCALL XML_SetSkippedEntityHandler(XML_Parser parser, - XML_SkippedEntityHandler handler) -{ - skippedEntityHandler = handler; + XML_SkippedEntityHandler handler) { + if (parser != NULL) + parser->m_skippedEntityHandler = handler; } void XMLCALL XML_SetUnknownEncodingHandler(XML_Parser parser, - XML_UnknownEncodingHandler handler, - void *data) -{ - unknownEncodingHandler = handler; - unknownEncodingHandlerData = data; + XML_UnknownEncodingHandler handler, void *data) { + if (parser == NULL) + return; + parser->m_unknownEncodingHandler = handler; + parser->m_unknownEncodingHandlerData = data; } void XMLCALL -XML_SetElementDeclHandler(XML_Parser parser, - XML_ElementDeclHandler eldecl) -{ - elementDeclHandler = eldecl; +XML_SetElementDeclHandler(XML_Parser parser, XML_ElementDeclHandler eldecl) { + if (parser != NULL) + parser->m_elementDeclHandler = eldecl; } void XMLCALL -XML_SetAttlistDeclHandler(XML_Parser parser, - XML_AttlistDeclHandler attdecl) -{ - attlistDeclHandler = attdecl; +XML_SetAttlistDeclHandler(XML_Parser parser, XML_AttlistDeclHandler attdecl) { + if (parser != NULL) + parser->m_attlistDeclHandler = attdecl; } void XMLCALL -XML_SetEntityDeclHandler(XML_Parser parser, - XML_EntityDeclHandler handler) -{ - entityDeclHandler = handler; +XML_SetEntityDeclHandler(XML_Parser parser, XML_EntityDeclHandler handler) { + if (parser != NULL) + parser->m_entityDeclHandler = handler; } void XMLCALL -XML_SetXmlDeclHandler(XML_Parser parser, - XML_XmlDeclHandler handler) { - xmlDeclHandler = handler; +XML_SetXmlDeclHandler(XML_Parser parser, XML_XmlDeclHandler handler) { + if (parser != NULL) + parser->m_xmlDeclHandler = handler; } int XMLCALL XML_SetParamEntityParsing(XML_Parser parser, - enum XML_ParamEntityParsing peParsing) -{ + enum XML_ParamEntityParsing peParsing) { + if (parser == NULL) + return 0; /* block after XML_Parse()/XML_ParseBuffer() has been called */ - if (ps_parsing == XML_PARSING || ps_parsing == XML_SUSPENDED) + if (parser->m_parsingStatus.parsing == XML_PARSING + || parser->m_parsingStatus.parsing == XML_SUSPENDED) return 0; #ifdef XML_DTD - paramEntityParsing = peParsing; + parser->m_paramEntityParsing = peParsing; return 1; #else return peParsing == XML_PARAM_ENTITY_PARSING_NEVER; @@ -1532,91 +1692,122 @@ XML_SetParamEntityParsing(XML_Parser parser, } int XMLCALL -XML_SetHashSalt(XML_Parser parser, - unsigned long hash_salt) -{ +XML_SetHashSalt(XML_Parser parser, unsigned long hash_salt) { + if (parser == NULL) + return 0; + if (parser->m_parentParser) + return XML_SetHashSalt(parser->m_parentParser, hash_salt); /* block after XML_Parse()/XML_ParseBuffer() has been called */ - if (ps_parsing == XML_PARSING || ps_parsing == XML_SUSPENDED) + if (parser->m_parsingStatus.parsing == XML_PARSING + || parser->m_parsingStatus.parsing == XML_SUSPENDED) return 0; - hash_secret_salt = hash_salt; + parser->m_hash_secret_salt = hash_salt; return 1; } enum XML_Status XMLCALL -XML_Parse(XML_Parser parser, const char *s, int len, int isFinal) -{ - switch (ps_parsing) { +XML_Parse(XML_Parser parser, const char *s, int len, int isFinal) { + if ((parser == NULL) || (len < 0) || ((s == NULL) && (len != 0))) { + if (parser != NULL) + parser->m_errorCode = XML_ERROR_INVALID_ARGUMENT; + return XML_STATUS_ERROR; + } + switch (parser->m_parsingStatus.parsing) { case XML_SUSPENDED: - errorCode = XML_ERROR_SUSPENDED; + parser->m_errorCode = XML_ERROR_SUSPENDED; return XML_STATUS_ERROR; case XML_FINISHED: - errorCode = XML_ERROR_FINISHED; + parser->m_errorCode = XML_ERROR_FINISHED; return XML_STATUS_ERROR; case XML_INITIALIZED: - if (parentParser == NULL && !startParsing(parser)) { - errorCode = XML_ERROR_NO_MEMORY; + if (parser->m_parentParser == NULL && ! startParsing(parser)) { + parser->m_errorCode = XML_ERROR_NO_MEMORY; return XML_STATUS_ERROR; } + /* fall through */ default: - ps_parsing = XML_PARSING; + parser->m_parsingStatus.parsing = XML_PARSING; } if (len == 0) { - ps_finalBuffer = (XML_Bool)isFinal; - if (!isFinal) + parser->m_parsingStatus.finalBuffer = (XML_Bool)isFinal; + if (! isFinal) return XML_STATUS_OK; - positionPtr = bufferPtr; - parseEndPtr = bufferEnd; + parser->m_positionPtr = parser->m_bufferPtr; + parser->m_parseEndPtr = parser->m_bufferEnd; /* If data are left over from last buffer, and we now know that these data are the final chunk of input, then we have to check them again to detect errors based on that fact. */ - errorCode = processor(parser, bufferPtr, parseEndPtr, &bufferPtr); + parser->m_errorCode + = parser->m_processor(parser, parser->m_bufferPtr, + parser->m_parseEndPtr, &parser->m_bufferPtr); - if (errorCode == XML_ERROR_NONE) { - switch (ps_parsing) { + if (parser->m_errorCode == XML_ERROR_NONE) { + switch (parser->m_parsingStatus.parsing) { case XML_SUSPENDED: - XmlUpdatePosition(encoding, positionPtr, bufferPtr, &position); - positionPtr = bufferPtr; + /* It is hard to be certain, but it seems that this case + * cannot occur. This code is cleaning up a previous parse + * with no new data (since len == 0). Changing the parsing + * state requires getting to execute a handler function, and + * there doesn't seem to be an opportunity for that while in + * this circumstance. + * + * Given the uncertainty, we retain the code but exclude it + * from coverage tests. + * + * LCOV_EXCL_START + */ + XmlUpdatePosition(parser->m_encoding, parser->m_positionPtr, + parser->m_bufferPtr, &parser->m_position); + parser->m_positionPtr = parser->m_bufferPtr; return XML_STATUS_SUSPENDED; + /* LCOV_EXCL_STOP */ case XML_INITIALIZED: case XML_PARSING: - ps_parsing = XML_FINISHED; + parser->m_parsingStatus.parsing = XML_FINISHED; /* fall through */ default: return XML_STATUS_OK; } } - eventEndPtr = eventPtr; - processor = errorProcessor; + parser->m_eventEndPtr = parser->m_eventPtr; + parser->m_processor = errorProcessor; return XML_STATUS_ERROR; } #ifndef XML_CONTEXT_BYTES - else if (bufferPtr == bufferEnd) { + else if (parser->m_bufferPtr == parser->m_bufferEnd) { const char *end; int nLeftOver; enum XML_Status result; - parseEndByteIndex += len; - positionPtr = s; - ps_finalBuffer = (XML_Bool)isFinal; + /* Detect overflow (a+b > MAX <==> b > MAX-a) */ + if (len > ((XML_Size)-1) / 2 - parser->m_parseEndByteIndex) { + parser->m_errorCode = XML_ERROR_NO_MEMORY; + parser->m_eventPtr = parser->m_eventEndPtr = NULL; + parser->m_processor = errorProcessor; + return XML_STATUS_ERROR; + } + parser->m_parseEndByteIndex += len; + parser->m_positionPtr = s; + parser->m_parsingStatus.finalBuffer = (XML_Bool)isFinal; - errorCode = processor(parser, s, parseEndPtr = s + len, &end); + parser->m_errorCode + = parser->m_processor(parser, s, parser->m_parseEndPtr = s + len, &end); - if (errorCode != XML_ERROR_NONE) { - eventEndPtr = eventPtr; - processor = errorProcessor; + if (parser->m_errorCode != XML_ERROR_NONE) { + parser->m_eventEndPtr = parser->m_eventPtr; + parser->m_processor = errorProcessor; return XML_STATUS_ERROR; - } - else { - switch (ps_parsing) { + } else { + switch (parser->m_parsingStatus.parsing) { case XML_SUSPENDED: result = XML_STATUS_SUSPENDED; break; case XML_INITIALIZED: case XML_PARSING: if (isFinal) { - ps_parsing = XML_FINISHED; + parser->m_parsingStatus.parsing = XML_FINISHED; return XML_STATUS_OK; } /* fall through */ @@ -1625,35 +1816,38 @@ XML_Parse(XML_Parser parser, const char *s, int len, int isFinal) } } - XmlUpdatePosition(encoding, positionPtr, end, &position); + XmlUpdatePosition(parser->m_encoding, parser->m_positionPtr, end, + &parser->m_position); nLeftOver = s + len - end; if (nLeftOver) { - if (buffer == NULL || nLeftOver > bufferLim - buffer) { - /* FIXME avoid integer overflow */ - char *temp; - temp = (buffer == NULL - ? (char *)MALLOC(len * 2) - : (char *)REALLOC(buffer, len * 2)); + if (parser->m_buffer == NULL + || nLeftOver > parser->m_bufferLim - parser->m_buffer) { + /* avoid _signed_ integer overflow */ + char *temp = NULL; + const int bytesToAllocate = (int)((unsigned)len * 2U); + if (bytesToAllocate > 0) { + temp = (char *)REALLOC(parser, parser->m_buffer, bytesToAllocate); + } if (temp == NULL) { - errorCode = XML_ERROR_NO_MEMORY; - eventPtr = eventEndPtr = NULL; - processor = errorProcessor; + parser->m_errorCode = XML_ERROR_NO_MEMORY; + parser->m_eventPtr = parser->m_eventEndPtr = NULL; + parser->m_processor = errorProcessor; return XML_STATUS_ERROR; } - buffer = temp; - bufferLim = buffer + len * 2; + parser->m_buffer = temp; + parser->m_bufferLim = parser->m_buffer + bytesToAllocate; } - memcpy(buffer, end, nLeftOver); + memcpy(parser->m_buffer, end, nLeftOver); } - bufferPtr = buffer; - bufferEnd = buffer + nLeftOver; - positionPtr = bufferPtr; - parseEndPtr = bufferEnd; - eventPtr = bufferPtr; - eventEndPtr = bufferPtr; + parser->m_bufferPtr = parser->m_buffer; + parser->m_bufferEnd = parser->m_buffer + nLeftOver; + parser->m_positionPtr = parser->m_bufferPtr; + parser->m_parseEndPtr = parser->m_bufferEnd; + parser->m_eventPtr = parser->m_bufferPtr; + parser->m_eventEndPtr = parser->m_bufferPtr; return result; } -#endif /* not defined XML_CONTEXT_BYTES */ +#endif /* not defined XML_CONTEXT_BYTES */ else { void *buff = XML_GetBuffer(parser, len); if (buff == NULL) @@ -1666,379 +1860,470 @@ XML_Parse(XML_Parser parser, const char *s, int len, int isFinal) } enum XML_Status XMLCALL -XML_ParseBuffer(XML_Parser parser, int len, int isFinal) -{ +XML_ParseBuffer(XML_Parser parser, int len, int isFinal) { const char *start; enum XML_Status result = XML_STATUS_OK; - switch (ps_parsing) { + if (parser == NULL) + return XML_STATUS_ERROR; + switch (parser->m_parsingStatus.parsing) { case XML_SUSPENDED: - errorCode = XML_ERROR_SUSPENDED; + parser->m_errorCode = XML_ERROR_SUSPENDED; return XML_STATUS_ERROR; case XML_FINISHED: - errorCode = XML_ERROR_FINISHED; + parser->m_errorCode = XML_ERROR_FINISHED; return XML_STATUS_ERROR; case XML_INITIALIZED: - if (parentParser == NULL && !startParsing(parser)) { - errorCode = XML_ERROR_NO_MEMORY; + if (parser->m_parentParser == NULL && ! startParsing(parser)) { + parser->m_errorCode = XML_ERROR_NO_MEMORY; return XML_STATUS_ERROR; } + /* fall through */ default: - ps_parsing = XML_PARSING; + parser->m_parsingStatus.parsing = XML_PARSING; } - start = bufferPtr; - positionPtr = start; - bufferEnd += len; - parseEndPtr = bufferEnd; - parseEndByteIndex += len; - ps_finalBuffer = (XML_Bool)isFinal; + start = parser->m_bufferPtr; + parser->m_positionPtr = start; + parser->m_bufferEnd += len; + parser->m_parseEndPtr = parser->m_bufferEnd; + parser->m_parseEndByteIndex += len; + parser->m_parsingStatus.finalBuffer = (XML_Bool)isFinal; - errorCode = processor(parser, start, parseEndPtr, &bufferPtr); + parser->m_errorCode = parser->m_processor( + parser, start, parser->m_parseEndPtr, &parser->m_bufferPtr); - if (errorCode != XML_ERROR_NONE) { - eventEndPtr = eventPtr; - processor = errorProcessor; + if (parser->m_errorCode != XML_ERROR_NONE) { + parser->m_eventEndPtr = parser->m_eventPtr; + parser->m_processor = errorProcessor; return XML_STATUS_ERROR; - } - else { - switch (ps_parsing) { + } else { + switch (parser->m_parsingStatus.parsing) { case XML_SUSPENDED: result = XML_STATUS_SUSPENDED; break; case XML_INITIALIZED: case XML_PARSING: if (isFinal) { - ps_parsing = XML_FINISHED; + parser->m_parsingStatus.parsing = XML_FINISHED; return result; } - default: ; /* should not happen */ + default:; /* should not happen */ } } - XmlUpdatePosition(encoding, positionPtr, bufferPtr, &position); - positionPtr = bufferPtr; + XmlUpdatePosition(parser->m_encoding, parser->m_positionPtr, + parser->m_bufferPtr, &parser->m_position); + parser->m_positionPtr = parser->m_bufferPtr; return result; } -void * XMLCALL -XML_GetBuffer(XML_Parser parser, int len) -{ +void *XMLCALL +XML_GetBuffer(XML_Parser parser, int len) { + if (parser == NULL) + return NULL; if (len < 0) { - errorCode = XML_ERROR_NO_MEMORY; + parser->m_errorCode = XML_ERROR_NO_MEMORY; return NULL; } - switch (ps_parsing) { + switch (parser->m_parsingStatus.parsing) { case XML_SUSPENDED: - errorCode = XML_ERROR_SUSPENDED; + parser->m_errorCode = XML_ERROR_SUSPENDED; return NULL; case XML_FINISHED: - errorCode = XML_ERROR_FINISHED; + parser->m_errorCode = XML_ERROR_FINISHED; return NULL; - default: ; + default:; } - if (len > bufferLim - bufferEnd) { + if (len > EXPAT_SAFE_PTR_DIFF(parser->m_bufferLim, parser->m_bufferEnd)) { #ifdef XML_CONTEXT_BYTES int keep; -#endif /* defined XML_CONTEXT_BYTES */ +#endif /* defined XML_CONTEXT_BYTES */ /* Do not invoke signed arithmetic overflow: */ - int neededSize = (int) ((unsigned)len + (unsigned)(bufferEnd - bufferPtr)); + int neededSize = (int)((unsigned)len + + (unsigned)EXPAT_SAFE_PTR_DIFF( + parser->m_bufferEnd, parser->m_bufferPtr)); if (neededSize < 0) { - errorCode = XML_ERROR_NO_MEMORY; + parser->m_errorCode = XML_ERROR_NO_MEMORY; return NULL; } #ifdef XML_CONTEXT_BYTES - keep = (int)(bufferPtr - buffer); + keep = (int)EXPAT_SAFE_PTR_DIFF(parser->m_bufferPtr, parser->m_buffer); if (keep > XML_CONTEXT_BYTES) keep = XML_CONTEXT_BYTES; neededSize += keep; -#endif /* defined XML_CONTEXT_BYTES */ - if (neededSize <= bufferLim - buffer) { +#endif /* defined XML_CONTEXT_BYTES */ + if (neededSize + <= EXPAT_SAFE_PTR_DIFF(parser->m_bufferLim, parser->m_buffer)) { #ifdef XML_CONTEXT_BYTES - if (keep < bufferPtr - buffer) { - int offset = (int)(bufferPtr - buffer) - keep; - memmove(buffer, &buffer[offset], bufferEnd - bufferPtr + keep); - bufferEnd -= offset; - bufferPtr -= offset; + if (keep < EXPAT_SAFE_PTR_DIFF(parser->m_bufferPtr, parser->m_buffer)) { + int offset + = (int)EXPAT_SAFE_PTR_DIFF(parser->m_bufferPtr, parser->m_buffer) + - keep; + /* The buffer pointers cannot be NULL here; we have at least some bytes + * in the buffer */ + memmove(parser->m_buffer, &parser->m_buffer[offset], + parser->m_bufferEnd - parser->m_bufferPtr + keep); + parser->m_bufferEnd -= offset; + parser->m_bufferPtr -= offset; } #else - memmove(buffer, bufferPtr, bufferEnd - bufferPtr); - bufferEnd = buffer + (bufferEnd - bufferPtr); - bufferPtr = buffer; -#endif /* not defined XML_CONTEXT_BYTES */ - } - else { + if (parser->m_buffer && parser->m_bufferPtr) { + memmove(parser->m_buffer, parser->m_bufferPtr, + EXPAT_SAFE_PTR_DIFF(parser->m_bufferEnd, parser->m_bufferPtr)); + parser->m_bufferEnd + = parser->m_buffer + + EXPAT_SAFE_PTR_DIFF(parser->m_bufferEnd, parser->m_bufferPtr); + parser->m_bufferPtr = parser->m_buffer; + } +#endif /* not defined XML_CONTEXT_BYTES */ + } else { char *newBuf; - int bufferSize = (int)(bufferLim - bufferPtr); + int bufferSize + = (int)EXPAT_SAFE_PTR_DIFF(parser->m_bufferLim, parser->m_bufferPtr); if (bufferSize == 0) bufferSize = INIT_BUFFER_SIZE; do { /* Do not invoke signed arithmetic overflow: */ - bufferSize = (int) (2U * (unsigned) bufferSize); + bufferSize = (int)(2U * (unsigned)bufferSize); } while (bufferSize < neededSize && bufferSize > 0); if (bufferSize <= 0) { - errorCode = XML_ERROR_NO_MEMORY; + parser->m_errorCode = XML_ERROR_NO_MEMORY; return NULL; } - newBuf = (char *)MALLOC(bufferSize); + newBuf = (char *)MALLOC(parser, bufferSize); if (newBuf == 0) { - errorCode = XML_ERROR_NO_MEMORY; + parser->m_errorCode = XML_ERROR_NO_MEMORY; return NULL; } - bufferLim = newBuf + bufferSize; + parser->m_bufferLim = newBuf + bufferSize; #ifdef XML_CONTEXT_BYTES - if (bufferPtr) { - int keep = (int)(bufferPtr - buffer); - if (keep > XML_CONTEXT_BYTES) - keep = XML_CONTEXT_BYTES; - memcpy(newBuf, &bufferPtr[-keep], bufferEnd - bufferPtr + keep); - FREE(buffer); - buffer = newBuf; - bufferEnd = buffer + (bufferEnd - bufferPtr) + keep; - bufferPtr = buffer + keep; - } - else { - bufferEnd = newBuf + (bufferEnd - bufferPtr); - bufferPtr = buffer = newBuf; + if (parser->m_bufferPtr) { + memcpy(newBuf, &parser->m_bufferPtr[-keep], + EXPAT_SAFE_PTR_DIFF(parser->m_bufferEnd, parser->m_bufferPtr) + + keep); + FREE(parser, parser->m_buffer); + parser->m_buffer = newBuf; + parser->m_bufferEnd + = parser->m_buffer + + EXPAT_SAFE_PTR_DIFF(parser->m_bufferEnd, parser->m_bufferPtr) + + keep; + parser->m_bufferPtr = parser->m_buffer + keep; + } else { + /* This must be a brand new buffer with no data in it yet */ + parser->m_bufferEnd = newBuf; + parser->m_bufferPtr = parser->m_buffer = newBuf; } #else - if (bufferPtr) { - memcpy(newBuf, bufferPtr, bufferEnd - bufferPtr); - FREE(buffer); + if (parser->m_bufferPtr) { + memcpy(newBuf, parser->m_bufferPtr, + EXPAT_SAFE_PTR_DIFF(parser->m_bufferEnd, parser->m_bufferPtr)); + FREE(parser, parser->m_buffer); + parser->m_bufferEnd + = newBuf + + EXPAT_SAFE_PTR_DIFF(parser->m_bufferEnd, parser->m_bufferPtr); + } else { + /* This must be a brand new buffer with no data in it yet */ + parser->m_bufferEnd = newBuf; } - bufferEnd = newBuf + (bufferEnd - bufferPtr); - bufferPtr = buffer = newBuf; -#endif /* not defined XML_CONTEXT_BYTES */ + parser->m_bufferPtr = parser->m_buffer = newBuf; +#endif /* not defined XML_CONTEXT_BYTES */ } - eventPtr = eventEndPtr = NULL; - positionPtr = NULL; + parser->m_eventPtr = parser->m_eventEndPtr = NULL; + parser->m_positionPtr = NULL; } - return bufferEnd; + return parser->m_bufferEnd; } enum XML_Status XMLCALL -XML_StopParser(XML_Parser parser, XML_Bool resumable) -{ - switch (ps_parsing) { +XML_StopParser(XML_Parser parser, XML_Bool resumable) { + if (parser == NULL) + return XML_STATUS_ERROR; + switch (parser->m_parsingStatus.parsing) { case XML_SUSPENDED: if (resumable) { - errorCode = XML_ERROR_SUSPENDED; + parser->m_errorCode = XML_ERROR_SUSPENDED; return XML_STATUS_ERROR; } - ps_parsing = XML_FINISHED; + parser->m_parsingStatus.parsing = XML_FINISHED; break; case XML_FINISHED: - errorCode = XML_ERROR_FINISHED; + parser->m_errorCode = XML_ERROR_FINISHED; return XML_STATUS_ERROR; default: if (resumable) { #ifdef XML_DTD - if (isParamEntity) { - errorCode = XML_ERROR_SUSPEND_PE; + if (parser->m_isParamEntity) { + parser->m_errorCode = XML_ERROR_SUSPEND_PE; return XML_STATUS_ERROR; } #endif - ps_parsing = XML_SUSPENDED; - } - else - ps_parsing = XML_FINISHED; + parser->m_parsingStatus.parsing = XML_SUSPENDED; + } else + parser->m_parsingStatus.parsing = XML_FINISHED; } return XML_STATUS_OK; } enum XML_Status XMLCALL -XML_ResumeParser(XML_Parser parser) -{ +XML_ResumeParser(XML_Parser parser) { enum XML_Status result = XML_STATUS_OK; - if (ps_parsing != XML_SUSPENDED) { - errorCode = XML_ERROR_NOT_SUSPENDED; + if (parser == NULL) + return XML_STATUS_ERROR; + if (parser->m_parsingStatus.parsing != XML_SUSPENDED) { + parser->m_errorCode = XML_ERROR_NOT_SUSPENDED; return XML_STATUS_ERROR; } - ps_parsing = XML_PARSING; + parser->m_parsingStatus.parsing = XML_PARSING; - errorCode = processor(parser, bufferPtr, parseEndPtr, &bufferPtr); + parser->m_errorCode = parser->m_processor( + parser, parser->m_bufferPtr, parser->m_parseEndPtr, &parser->m_bufferPtr); - if (errorCode != XML_ERROR_NONE) { - eventEndPtr = eventPtr; - processor = errorProcessor; + if (parser->m_errorCode != XML_ERROR_NONE) { + parser->m_eventEndPtr = parser->m_eventPtr; + parser->m_processor = errorProcessor; return XML_STATUS_ERROR; - } - else { - switch (ps_parsing) { + } else { + switch (parser->m_parsingStatus.parsing) { case XML_SUSPENDED: result = XML_STATUS_SUSPENDED; break; case XML_INITIALIZED: case XML_PARSING: - if (ps_finalBuffer) { - ps_parsing = XML_FINISHED; + if (parser->m_parsingStatus.finalBuffer) { + parser->m_parsingStatus.parsing = XML_FINISHED; return result; } - default: ; + default:; } } - XmlUpdatePosition(encoding, positionPtr, bufferPtr, &position); - positionPtr = bufferPtr; + XmlUpdatePosition(parser->m_encoding, parser->m_positionPtr, + parser->m_bufferPtr, &parser->m_position); + parser->m_positionPtr = parser->m_bufferPtr; return result; } void XMLCALL -XML_GetParsingStatus(XML_Parser parser, XML_ParsingStatus *status) -{ +XML_GetParsingStatus(XML_Parser parser, XML_ParsingStatus *status) { + if (parser == NULL) + return; assert(status != NULL); *status = parser->m_parsingStatus; } enum XML_Error XMLCALL -XML_GetErrorCode(XML_Parser parser) -{ - return errorCode; +XML_GetErrorCode(XML_Parser parser) { + if (parser == NULL) + return XML_ERROR_INVALID_ARGUMENT; + return parser->m_errorCode; } XML_Index XMLCALL -XML_GetCurrentByteIndex(XML_Parser parser) -{ - if (eventPtr) - return (XML_Index)(parseEndByteIndex - (parseEndPtr - eventPtr)); +XML_GetCurrentByteIndex(XML_Parser parser) { + if (parser == NULL) + return -1; + if (parser->m_eventPtr) + return (XML_Index)(parser->m_parseEndByteIndex + - (parser->m_parseEndPtr - parser->m_eventPtr)); return -1; } int XMLCALL -XML_GetCurrentByteCount(XML_Parser parser) -{ - if (eventEndPtr && eventPtr) - return (int)(eventEndPtr - eventPtr); +XML_GetCurrentByteCount(XML_Parser parser) { + if (parser == NULL) + return 0; + if (parser->m_eventEndPtr && parser->m_eventPtr) + return (int)(parser->m_eventEndPtr - parser->m_eventPtr); return 0; } -const char * XMLCALL -XML_GetInputContext(XML_Parser parser, int *offset, int *size) -{ +const char *XMLCALL +XML_GetInputContext(XML_Parser parser, int *offset, int *size) { #ifdef XML_CONTEXT_BYTES - if (eventPtr && buffer) { - *offset = (int)(eventPtr - buffer); - *size = (int)(bufferEnd - buffer); - return buffer; + if (parser == NULL) + return NULL; + if (parser->m_eventPtr && parser->m_buffer) { + if (offset != NULL) + *offset = (int)(parser->m_eventPtr - parser->m_buffer); + if (size != NULL) + *size = (int)(parser->m_bufferEnd - parser->m_buffer); + return parser->m_buffer; } +#else + (void)parser; + (void)offset; + (void)size; #endif /* defined XML_CONTEXT_BYTES */ - return (char *) 0; + return (char *)0; } XML_Size XMLCALL -XML_GetCurrentLineNumber(XML_Parser parser) -{ - if (eventPtr && eventPtr >= positionPtr) { - XmlUpdatePosition(encoding, positionPtr, eventPtr, &position); - positionPtr = eventPtr; +XML_GetCurrentLineNumber(XML_Parser parser) { + if (parser == NULL) + return 0; + if (parser->m_eventPtr && parser->m_eventPtr >= parser->m_positionPtr) { + XmlUpdatePosition(parser->m_encoding, parser->m_positionPtr, + parser->m_eventPtr, &parser->m_position); + parser->m_positionPtr = parser->m_eventPtr; } - return position.lineNumber + 1; + return parser->m_position.lineNumber + 1; } XML_Size XMLCALL -XML_GetCurrentColumnNumber(XML_Parser parser) -{ - if (eventPtr && eventPtr >= positionPtr) { - XmlUpdatePosition(encoding, positionPtr, eventPtr, &position); - positionPtr = eventPtr; +XML_GetCurrentColumnNumber(XML_Parser parser) { + if (parser == NULL) + return 0; + if (parser->m_eventPtr && parser->m_eventPtr >= parser->m_positionPtr) { + XmlUpdatePosition(parser->m_encoding, parser->m_positionPtr, + parser->m_eventPtr, &parser->m_position); + parser->m_positionPtr = parser->m_eventPtr; } - return position.columnNumber; + return parser->m_position.columnNumber; } void XMLCALL -XML_FreeContentModel(XML_Parser parser, XML_Content *model) -{ - FREE(model); +XML_FreeContentModel(XML_Parser parser, XML_Content *model) { + if (parser != NULL) + FREE(parser, model); } -void * XMLCALL -XML_MemMalloc(XML_Parser parser, size_t size) -{ - return MALLOC(size); +void *XMLCALL +XML_MemMalloc(XML_Parser parser, size_t size) { + if (parser == NULL) + return NULL; + return MALLOC(parser, size); } -void * XMLCALL -XML_MemRealloc(XML_Parser parser, void *ptr, size_t size) -{ - return REALLOC(ptr, size); +void *XMLCALL +XML_MemRealloc(XML_Parser parser, void *ptr, size_t size) { + if (parser == NULL) + return NULL; + return REALLOC(parser, ptr, size); } void XMLCALL -XML_MemFree(XML_Parser parser, void *ptr) -{ - FREE(ptr); +XML_MemFree(XML_Parser parser, void *ptr) { + if (parser != NULL) + FREE(parser, ptr); } void XMLCALL -XML_DefaultCurrent(XML_Parser parser) -{ - if (defaultHandler) { - if (openInternalEntities) - reportDefault(parser, - internalEncoding, - openInternalEntities->internalEventPtr, - openInternalEntities->internalEventEndPtr); +XML_DefaultCurrent(XML_Parser parser) { + if (parser == NULL) + return; + if (parser->m_defaultHandler) { + if (parser->m_openInternalEntities) + reportDefault(parser, parser->m_internalEncoding, + parser->m_openInternalEntities->internalEventPtr, + parser->m_openInternalEntities->internalEventEndPtr); else - reportDefault(parser, encoding, eventPtr, eventEndPtr); + reportDefault(parser, parser->m_encoding, parser->m_eventPtr, + parser->m_eventEndPtr); } } -const XML_LChar * XMLCALL -XML_ErrorString(enum XML_Error code) -{ - static const XML_LChar* const message[] = { - 0, - XML_L("out of memory"), - XML_L("syntax error"), - XML_L("no element found"), - XML_L("not well-formed (invalid token)"), - XML_L("unclosed token"), - XML_L("partial character"), - XML_L("mismatched tag"), - XML_L("duplicate attribute"), - XML_L("junk after document element"), - XML_L("illegal parameter entity reference"), - XML_L("undefined entity"), - XML_L("recursive entity reference"), - XML_L("asynchronous entity"), - XML_L("reference to invalid character number"), - XML_L("reference to binary entity"), - XML_L("reference to external entity in attribute"), - XML_L("XML or text declaration not at start of entity"), - XML_L("unknown encoding"), - XML_L("encoding specified in XML declaration is incorrect"), - XML_L("unclosed CDATA section"), - XML_L("error in processing external entity reference"), - XML_L("document is not standalone"), - XML_L("unexpected parser state - please send a bug report"), - XML_L("entity declared in parameter entity"), - XML_L("requested feature requires XML_DTD support in Expat"), - XML_L("cannot change setting once parsing has begun"), - XML_L("unbound prefix"), - XML_L("must not undeclare prefix"), - XML_L("incomplete markup in parameter entity"), - XML_L("XML declaration not well-formed"), - XML_L("text declaration not well-formed"), - XML_L("illegal character(s) in public id"), - XML_L("parser suspended"), - XML_L("parser not suspended"), - XML_L("parsing aborted"), - XML_L("parsing finished"), - XML_L("cannot suspend in external parameter entity"), - XML_L("reserved prefix (xml) must not be undeclared or bound to another namespace name"), - XML_L("reserved prefix (xmlns) must not be declared or undeclared"), - XML_L("prefix must not be bound to one of the reserved namespace names") - }; - if (code > 0 && code < sizeof(message)/sizeof(message[0])) - return message[code]; +const XML_LChar *XMLCALL +XML_ErrorString(enum XML_Error code) { + switch (code) { + case XML_ERROR_NONE: + return NULL; + case XML_ERROR_NO_MEMORY: + return XML_L("out of memory"); + case XML_ERROR_SYNTAX: + return XML_L("syntax error"); + case XML_ERROR_NO_ELEMENTS: + return XML_L("no element found"); + case XML_ERROR_INVALID_TOKEN: + return XML_L("not well-formed (invalid token)"); + case XML_ERROR_UNCLOSED_TOKEN: + return XML_L("unclosed token"); + case XML_ERROR_PARTIAL_CHAR: + return XML_L("partial character"); + case XML_ERROR_TAG_MISMATCH: + return XML_L("mismatched tag"); + case XML_ERROR_DUPLICATE_ATTRIBUTE: + return XML_L("duplicate attribute"); + case XML_ERROR_JUNK_AFTER_DOC_ELEMENT: + return XML_L("junk after document element"); + case XML_ERROR_PARAM_ENTITY_REF: + return XML_L("illegal parameter entity reference"); + case XML_ERROR_UNDEFINED_ENTITY: + return XML_L("undefined entity"); + case XML_ERROR_RECURSIVE_ENTITY_REF: + return XML_L("recursive entity reference"); + case XML_ERROR_ASYNC_ENTITY: + return XML_L("asynchronous entity"); + case XML_ERROR_BAD_CHAR_REF: + return XML_L("reference to invalid character number"); + case XML_ERROR_BINARY_ENTITY_REF: + return XML_L("reference to binary entity"); + case XML_ERROR_ATTRIBUTE_EXTERNAL_ENTITY_REF: + return XML_L("reference to external entity in attribute"); + case XML_ERROR_MISPLACED_XML_PI: + return XML_L("XML or text declaration not at start of entity"); + case XML_ERROR_UNKNOWN_ENCODING: + return XML_L("unknown encoding"); + case XML_ERROR_INCORRECT_ENCODING: + return XML_L("encoding specified in XML declaration is incorrect"); + case XML_ERROR_UNCLOSED_CDATA_SECTION: + return XML_L("unclosed CDATA section"); + case XML_ERROR_EXTERNAL_ENTITY_HANDLING: + return XML_L("error in processing external entity reference"); + case XML_ERROR_NOT_STANDALONE: + return XML_L("document is not standalone"); + case XML_ERROR_UNEXPECTED_STATE: + return XML_L("unexpected parser state - please send a bug report"); + case XML_ERROR_ENTITY_DECLARED_IN_PE: + return XML_L("entity declared in parameter entity"); + case XML_ERROR_FEATURE_REQUIRES_XML_DTD: + return XML_L("requested feature requires XML_DTD support in Expat"); + case XML_ERROR_CANT_CHANGE_FEATURE_ONCE_PARSING: + return XML_L("cannot change setting once parsing has begun"); + /* Added in 1.95.7. */ + case XML_ERROR_UNBOUND_PREFIX: + return XML_L("unbound prefix"); + /* Added in 1.95.8. */ + case XML_ERROR_UNDECLARING_PREFIX: + return XML_L("must not undeclare prefix"); + case XML_ERROR_INCOMPLETE_PE: + return XML_L("incomplete markup in parameter entity"); + case XML_ERROR_XML_DECL: + return XML_L("XML declaration not well-formed"); + case XML_ERROR_TEXT_DECL: + return XML_L("text declaration not well-formed"); + case XML_ERROR_PUBLICID: + return XML_L("illegal character(s) in public id"); + case XML_ERROR_SUSPENDED: + return XML_L("parser suspended"); + case XML_ERROR_NOT_SUSPENDED: + return XML_L("parser not suspended"); + case XML_ERROR_ABORTED: + return XML_L("parsing aborted"); + case XML_ERROR_FINISHED: + return XML_L("parsing finished"); + case XML_ERROR_SUSPEND_PE: + return XML_L("cannot suspend in external parameter entity"); + /* Added in 2.0.0. */ + case XML_ERROR_RESERVED_PREFIX_XML: + return XML_L( + "reserved prefix (xml) must not be undeclared or bound to another namespace name"); + case XML_ERROR_RESERVED_PREFIX_XMLNS: + return XML_L("reserved prefix (xmlns) must not be declared or undeclared"); + case XML_ERROR_RESERVED_NAMESPACE_URI: + return XML_L( + "prefix must not be bound to one of the reserved namespace names"); + /* Added in 2.2.5. */ + case XML_ERROR_INVALID_ARGUMENT: /* Constant added in 2.2.1, already */ + return XML_L("invalid argument"); + } return NULL; } -const XML_LChar * XMLCALL +const XML_LChar *XMLCALL XML_ExpatVersion(void) { - /* V1 is used to string-ize the version number. However, it would string-ize the actual version macro *names* unless we get them substituted before being passed to V1. CPP is defined to expand @@ -2047,8 +2332,8 @@ XML_ExpatVersion(void) { with the correct numerals. */ /* ### I'm assuming cpp is portable in this respect... */ -#define V1(a,b,c) XML_L(#a)XML_L(".")XML_L(#b)XML_L(".")XML_L(#c) -#define V2(a,b,c) XML_L("expat_")V1(a,b,c) +#define V1(a, b, c) XML_L(#a) XML_L(".") XML_L(#b) XML_L(".") XML_L(#c) +#define V2(a, b, c) XML_L("expat_") V1(a, b, c) return V2(XML_MAJOR_VERSION, XML_MINOR_VERSION, XML_MICRO_VERSION); @@ -2057,8 +2342,7 @@ XML_ExpatVersion(void) { } XML_Expat_Version XMLCALL -XML_ExpatVersionInfo(void) -{ +XML_ExpatVersionInfo(void) { XML_Expat_Version version; version.major = XML_MAJOR_VERSION; @@ -2068,41 +2352,39 @@ XML_ExpatVersionInfo(void) return version; } -const XML_Feature * XMLCALL -XML_GetFeatureList(void) -{ - static const XML_Feature features[] = { - {XML_FEATURE_SIZEOF_XML_CHAR, XML_L("sizeof(XML_Char)"), - sizeof(XML_Char)}, - {XML_FEATURE_SIZEOF_XML_LCHAR, XML_L("sizeof(XML_LChar)"), - sizeof(XML_LChar)}, +const XML_Feature *XMLCALL +XML_GetFeatureList(void) { + static const XML_Feature features[] + = {{XML_FEATURE_SIZEOF_XML_CHAR, XML_L("sizeof(XML_Char)"), + sizeof(XML_Char)}, + {XML_FEATURE_SIZEOF_XML_LCHAR, XML_L("sizeof(XML_LChar)"), + sizeof(XML_LChar)}, #ifdef XML_UNICODE - {XML_FEATURE_UNICODE, XML_L("XML_UNICODE"), 0}, + {XML_FEATURE_UNICODE, XML_L("XML_UNICODE"), 0}, #endif #ifdef XML_UNICODE_WCHAR_T - {XML_FEATURE_UNICODE_WCHAR_T, XML_L("XML_UNICODE_WCHAR_T"), 0}, + {XML_FEATURE_UNICODE_WCHAR_T, XML_L("XML_UNICODE_WCHAR_T"), 0}, #endif #ifdef XML_DTD - {XML_FEATURE_DTD, XML_L("XML_DTD"), 0}, + {XML_FEATURE_DTD, XML_L("XML_DTD"), 0}, #endif #ifdef XML_CONTEXT_BYTES - {XML_FEATURE_CONTEXT_BYTES, XML_L("XML_CONTEXT_BYTES"), - XML_CONTEXT_BYTES}, + {XML_FEATURE_CONTEXT_BYTES, XML_L("XML_CONTEXT_BYTES"), + XML_CONTEXT_BYTES}, #endif #ifdef XML_MIN_SIZE - {XML_FEATURE_MIN_SIZE, XML_L("XML_MIN_SIZE"), 0}, + {XML_FEATURE_MIN_SIZE, XML_L("XML_MIN_SIZE"), 0}, #endif #ifdef XML_NS - {XML_FEATURE_NS, XML_L("XML_NS"), 0}, + {XML_FEATURE_NS, XML_L("XML_NS"), 0}, #endif #ifdef XML_LARGE_SIZE - {XML_FEATURE_LARGE_SIZE, XML_L("XML_LARGE_SIZE"), 0}, + {XML_FEATURE_LARGE_SIZE, XML_L("XML_LARGE_SIZE"), 0}, #endif #ifdef XML_ATTR_INFO - {XML_FEATURE_ATTR_INFO, XML_L("XML_ATTR_INFO"), 0}, + {XML_FEATURE_ATTR_INFO, XML_L("XML_ATTR_INFO"), 0}, #endif - {XML_FEATURE_END, NULL, 0} - }; + {XML_FEATURE_END, NULL, 0}}; return features; } @@ -2113,14 +2395,13 @@ XML_GetFeatureList(void) permanent location, since the parse buffer is about to be discarded. */ static XML_Bool -storeRawNames(XML_Parser parser) -{ - TAG *tag = tagStack; +storeRawNames(XML_Parser parser) { + TAG *tag = parser->m_tagStack; while (tag) { int bufSize; int nameLen = sizeof(XML_Char) * (tag->name.strLen + 1); char *rawNameBuf = tag->buf + nameLen; - /* Stop if already stored. Since tagStack is a stack, we can stop + /* Stop if already stored. Since m_tagStack is a stack, we can stop at the first entry that has already been copied; everything below it in the stack is already been accounted for in a previous call to this function. @@ -2132,7 +2413,7 @@ storeRawNames(XML_Parser parser) */ bufSize = nameLen + ROUND_UP(tag->rawNameLength, sizeof(XML_Char)); if (bufSize > tag->bufEnd - tag->buf) { - char *temp = (char *)REALLOC(tag->buf, bufSize); + char *temp = (char *)REALLOC(parser, tag->buf, bufSize); if (temp == NULL) return XML_FALSE; /* if tag->name.str points to tag->buf (only when namespace @@ -2144,8 +2425,8 @@ storeRawNames(XML_Parser parser) then update it as well, since it will always point into tag->buf */ if (tag->name.localPart) - tag->name.localPart = (XML_Char *)temp + (tag->name.localPart - - (XML_Char *)tag->buf); + tag->name.localPart + = (XML_Char *)temp + (tag->name.localPart - (XML_Char *)tag->buf); tag->buf = temp; tag->bufEnd = temp + bufSize; rawNameBuf = temp + nameLen; @@ -2158,41 +2439,33 @@ storeRawNames(XML_Parser parser) } static enum XML_Error PTRCALL -contentProcessor(XML_Parser parser, - const char *start, - const char *end, - const char **endPtr) -{ - enum XML_Error result = doContent(parser, 0, encoding, start, end, - endPtr, (XML_Bool)!ps_finalBuffer); +contentProcessor(XML_Parser parser, const char *start, const char *end, + const char **endPtr) { + enum XML_Error result + = doContent(parser, 0, parser->m_encoding, start, end, endPtr, + (XML_Bool)! parser->m_parsingStatus.finalBuffer); if (result == XML_ERROR_NONE) { - if (!storeRawNames(parser)) + if (! storeRawNames(parser)) return XML_ERROR_NO_MEMORY; } return result; } static enum XML_Error PTRCALL -externalEntityInitProcessor(XML_Parser parser, - const char *start, - const char *end, - const char **endPtr) -{ +externalEntityInitProcessor(XML_Parser parser, const char *start, + const char *end, const char **endPtr) { enum XML_Error result = initializeEncoding(parser); if (result != XML_ERROR_NONE) return result; - processor = externalEntityInitProcessor2; + parser->m_processor = externalEntityInitProcessor2; return externalEntityInitProcessor2(parser, start, end, endPtr); } static enum XML_Error PTRCALL -externalEntityInitProcessor2(XML_Parser parser, - const char *start, - const char *end, - const char **endPtr) -{ +externalEntityInitProcessor2(XML_Parser parser, const char *start, + const char *end, const char **endPtr) { const char *next = start; /* XmlContentTok doesn't always set the last arg */ - int tok = XmlContentTok(encoding, start, end, &next); + int tok = XmlContentTok(parser->m_encoding, start, end, &next); switch (tok) { case XML_TOK_BOM: /* If we are at the end of the buffer, this would cause the next stage, @@ -2200,115 +2473,102 @@ externalEntityInitProcessor2(XML_Parser parser, doContent (by detecting XML_TOK_NONE) without processing any xml text declaration - causing the error XML_ERROR_MISPLACED_XML_PI in doContent. */ - if (next == end && !ps_finalBuffer) { + if (next == end && ! parser->m_parsingStatus.finalBuffer) { *endPtr = next; return XML_ERROR_NONE; } start = next; break; case XML_TOK_PARTIAL: - if (!ps_finalBuffer) { + if (! parser->m_parsingStatus.finalBuffer) { *endPtr = start; return XML_ERROR_NONE; } - eventPtr = start; + parser->m_eventPtr = start; return XML_ERROR_UNCLOSED_TOKEN; case XML_TOK_PARTIAL_CHAR: - if (!ps_finalBuffer) { + if (! parser->m_parsingStatus.finalBuffer) { *endPtr = start; return XML_ERROR_NONE; } - eventPtr = start; + parser->m_eventPtr = start; return XML_ERROR_PARTIAL_CHAR; } - processor = externalEntityInitProcessor3; + parser->m_processor = externalEntityInitProcessor3; return externalEntityInitProcessor3(parser, start, end, endPtr); } static enum XML_Error PTRCALL -externalEntityInitProcessor3(XML_Parser parser, - const char *start, - const char *end, - const char **endPtr) -{ +externalEntityInitProcessor3(XML_Parser parser, const char *start, + const char *end, const char **endPtr) { int tok; const char *next = start; /* XmlContentTok doesn't always set the last arg */ - eventPtr = start; - tok = XmlContentTok(encoding, start, end, &next); - eventEndPtr = next; + parser->m_eventPtr = start; + tok = XmlContentTok(parser->m_encoding, start, end, &next); + parser->m_eventEndPtr = next; switch (tok) { - case XML_TOK_XML_DECL: - { - enum XML_Error result; - result = processXmlDecl(parser, 1, start, next); - if (result != XML_ERROR_NONE) - return result; - switch (ps_parsing) { - case XML_SUSPENDED: - *endPtr = next; - return XML_ERROR_NONE; - case XML_FINISHED: - return XML_ERROR_ABORTED; - default: - start = next; - } + case XML_TOK_XML_DECL: { + enum XML_Error result; + result = processXmlDecl(parser, 1, start, next); + if (result != XML_ERROR_NONE) + return result; + switch (parser->m_parsingStatus.parsing) { + case XML_SUSPENDED: + *endPtr = next; + return XML_ERROR_NONE; + case XML_FINISHED: + return XML_ERROR_ABORTED; + default: + start = next; } - break; + } break; case XML_TOK_PARTIAL: - if (!ps_finalBuffer) { + if (! parser->m_parsingStatus.finalBuffer) { *endPtr = start; return XML_ERROR_NONE; } return XML_ERROR_UNCLOSED_TOKEN; case XML_TOK_PARTIAL_CHAR: - if (!ps_finalBuffer) { + if (! parser->m_parsingStatus.finalBuffer) { *endPtr = start; return XML_ERROR_NONE; } return XML_ERROR_PARTIAL_CHAR; } - processor = externalEntityContentProcessor; - tagLevel = 1; + parser->m_processor = externalEntityContentProcessor; + parser->m_tagLevel = 1; return externalEntityContentProcessor(parser, start, end, endPtr); } static enum XML_Error PTRCALL -externalEntityContentProcessor(XML_Parser parser, - const char *start, - const char *end, - const char **endPtr) -{ - enum XML_Error result = doContent(parser, 1, encoding, start, end, - endPtr, (XML_Bool)!ps_finalBuffer); +externalEntityContentProcessor(XML_Parser parser, const char *start, + const char *end, const char **endPtr) { + enum XML_Error result + = doContent(parser, 1, parser->m_encoding, start, end, endPtr, + (XML_Bool)! parser->m_parsingStatus.finalBuffer); if (result == XML_ERROR_NONE) { - if (!storeRawNames(parser)) + if (! storeRawNames(parser)) return XML_ERROR_NO_MEMORY; } return result; } static enum XML_Error -doContent(XML_Parser parser, - int startTagLevel, - const ENCODING *enc, - const char *s, - const char *end, - const char **nextPtr, - XML_Bool haveMore) -{ +doContent(XML_Parser parser, int startTagLevel, const ENCODING *enc, + const char *s, const char *end, const char **nextPtr, + XML_Bool haveMore) { /* save one level of indirection */ - DTD * const dtd = _dtd; + DTD *const dtd = parser->m_dtd; const char **eventPP; const char **eventEndPP; - if (enc == encoding) { - eventPP = &eventPtr; - eventEndPP = &eventEndPtr; - } - else { - eventPP = &(openInternalEntities->internalEventPtr); - eventEndPP = &(openInternalEntities->internalEventEndPtr); + if (enc == parser->m_encoding) { + eventPP = &parser->m_eventPtr; + eventEndPP = &parser->m_eventEndPtr; + } else { + eventPP = &(parser->m_openInternalEntities->internalEventPtr); + eventEndPP = &(parser->m_openInternalEntities->internalEventEndPtr); } *eventPP = s; @@ -2323,18 +2583,17 @@ doContent(XML_Parser parser, return XML_ERROR_NONE; } *eventEndPP = end; - if (characterDataHandler) { + if (parser->m_characterDataHandler) { XML_Char c = 0xA; - characterDataHandler(handlerArg, &c, 1); - } - else if (defaultHandler) + parser->m_characterDataHandler(parser->m_handlerArg, &c, 1); + } else if (parser->m_defaultHandler) reportDefault(parser, enc, s, end); /* We are at the end of the final buffer, should we check for XML_SUSPENDED, XML_FINISHED? */ if (startTagLevel == 0) return XML_ERROR_NO_ELEMENTS; - if (tagLevel != startTagLevel) + if (parser->m_tagLevel != startTagLevel) return XML_ERROR_ASYNC_ENTITY; *nextPtr = end; return XML_ERROR_NONE; @@ -2344,7 +2603,7 @@ doContent(XML_Parser parser, return XML_ERROR_NONE; } if (startTagLevel > 0) { - if (tagLevel != startTagLevel) + if (parser->m_tagLevel != startTagLevel) return XML_ERROR_ASYNC_ENTITY; *nextPtr = s; return XML_ERROR_NONE; @@ -2365,321 +2624,314 @@ doContent(XML_Parser parser, return XML_ERROR_NONE; } return XML_ERROR_PARTIAL_CHAR; - case XML_TOK_ENTITY_REF: - { - const XML_Char *name; - ENTITY *entity; - XML_Char ch = (XML_Char) XmlPredefinedEntityName(enc, - s + enc->minBytesPerChar, - next - enc->minBytesPerChar); - if (ch) { - if (characterDataHandler) - characterDataHandler(handlerArg, &ch, 1); - else if (defaultHandler) + case XML_TOK_ENTITY_REF: { + const XML_Char *name; + ENTITY *entity; + XML_Char ch = (XML_Char)XmlPredefinedEntityName( + enc, s + enc->minBytesPerChar, next - enc->minBytesPerChar); + if (ch) { + if (parser->m_characterDataHandler) + parser->m_characterDataHandler(parser->m_handlerArg, &ch, 1); + else if (parser->m_defaultHandler) + reportDefault(parser, enc, s, next); + break; + } + name = poolStoreString(&dtd->pool, enc, s + enc->minBytesPerChar, + next - enc->minBytesPerChar); + if (! name) + return XML_ERROR_NO_MEMORY; + entity = (ENTITY *)lookup(parser, &dtd->generalEntities, name, 0); + poolDiscard(&dtd->pool); + /* First, determine if a check for an existing declaration is needed; + if yes, check that the entity exists, and that it is internal, + otherwise call the skipped entity or default handler. + */ + if (! dtd->hasParamEntityRefs || dtd->standalone) { + if (! entity) + return XML_ERROR_UNDEFINED_ENTITY; + else if (! entity->is_internal) + return XML_ERROR_ENTITY_DECLARED_IN_PE; + } else if (! entity) { + if (parser->m_skippedEntityHandler) + parser->m_skippedEntityHandler(parser->m_handlerArg, name, 0); + else if (parser->m_defaultHandler) + reportDefault(parser, enc, s, next); + break; + } + if (entity->open) + return XML_ERROR_RECURSIVE_ENTITY_REF; + if (entity->notation) + return XML_ERROR_BINARY_ENTITY_REF; + if (entity->textPtr) { + enum XML_Error result; + if (! parser->m_defaultExpandInternalEntities) { + if (parser->m_skippedEntityHandler) + parser->m_skippedEntityHandler(parser->m_handlerArg, entity->name, + 0); + else if (parser->m_defaultHandler) reportDefault(parser, enc, s, next); break; } - name = poolStoreString(&dtd->pool, enc, - s + enc->minBytesPerChar, - next - enc->minBytesPerChar); - if (!name) + result = processInternalEntity(parser, entity, XML_FALSE); + if (result != XML_ERROR_NONE) + return result; + } else if (parser->m_externalEntityRefHandler) { + const XML_Char *context; + entity->open = XML_TRUE; + context = getContext(parser); + entity->open = XML_FALSE; + if (! context) return XML_ERROR_NO_MEMORY; - entity = (ENTITY *)lookup(parser, &dtd->generalEntities, name, 0); - poolDiscard(&dtd->pool); - /* First, determine if a check for an existing declaration is needed; - if yes, check that the entity exists, and that it is internal, - otherwise call the skipped entity or default handler. - */ - if (!dtd->hasParamEntityRefs || dtd->standalone) { - if (!entity) - return XML_ERROR_UNDEFINED_ENTITY; - else if (!entity->is_internal) - return XML_ERROR_ENTITY_DECLARED_IN_PE; - } - else if (!entity) { - if (skippedEntityHandler) - skippedEntityHandler(handlerArg, name, 0); - else if (defaultHandler) - reportDefault(parser, enc, s, next); - break; - } - if (entity->open) - return XML_ERROR_RECURSIVE_ENTITY_REF; - if (entity->notation) - return XML_ERROR_BINARY_ENTITY_REF; - if (entity->textPtr) { - enum XML_Error result; - if (!defaultExpandInternalEntities) { - if (skippedEntityHandler) - skippedEntityHandler(handlerArg, entity->name, 0); - else if (defaultHandler) - reportDefault(parser, enc, s, next); - break; - } - result = processInternalEntity(parser, entity, XML_FALSE); - if (result != XML_ERROR_NONE) - return result; - } - else if (externalEntityRefHandler) { - const XML_Char *context; - entity->open = XML_TRUE; - context = getContext(parser); - entity->open = XML_FALSE; - if (!context) - return XML_ERROR_NO_MEMORY; - if (!externalEntityRefHandler(externalEntityRefHandlerArg, - context, - entity->base, - entity->systemId, - entity->publicId)) - return XML_ERROR_EXTERNAL_ENTITY_HANDLING; - poolDiscard(&tempPool); - } - else if (defaultHandler) - reportDefault(parser, enc, s, next); - break; - } + if (! parser->m_externalEntityRefHandler( + parser->m_externalEntityRefHandlerArg, context, entity->base, + entity->systemId, entity->publicId)) + return XML_ERROR_EXTERNAL_ENTITY_HANDLING; + poolDiscard(&parser->m_tempPool); + } else if (parser->m_defaultHandler) + reportDefault(parser, enc, s, next); + break; + } case XML_TOK_START_TAG_NO_ATTS: /* fall through */ - case XML_TOK_START_TAG_WITH_ATTS: - { - TAG *tag; - enum XML_Error result; - XML_Char *toPtr; - if (freeTagList) { - tag = freeTagList; - freeTagList = freeTagList->parent; + case XML_TOK_START_TAG_WITH_ATTS: { + TAG *tag; + enum XML_Error result; + XML_Char *toPtr; + if (parser->m_freeTagList) { + tag = parser->m_freeTagList; + parser->m_freeTagList = parser->m_freeTagList->parent; + } else { + tag = (TAG *)MALLOC(parser, sizeof(TAG)); + if (! tag) + return XML_ERROR_NO_MEMORY; + tag->buf = (char *)MALLOC(parser, INIT_TAG_BUF_SIZE); + if (! tag->buf) { + FREE(parser, tag); + return XML_ERROR_NO_MEMORY; } - else { - tag = (TAG *)MALLOC(sizeof(TAG)); - if (!tag) - return XML_ERROR_NO_MEMORY; - tag->buf = (char *)MALLOC(INIT_TAG_BUF_SIZE); - if (!tag->buf) { - FREE(tag); - return XML_ERROR_NO_MEMORY; + tag->bufEnd = tag->buf + INIT_TAG_BUF_SIZE; + } + tag->bindings = NULL; + tag->parent = parser->m_tagStack; + parser->m_tagStack = tag; + tag->name.localPart = NULL; + tag->name.prefix = NULL; + tag->rawName = s + enc->minBytesPerChar; + tag->rawNameLength = XmlNameLength(enc, tag->rawName); + ++parser->m_tagLevel; + { + const char *rawNameEnd = tag->rawName + tag->rawNameLength; + const char *fromPtr = tag->rawName; + toPtr = (XML_Char *)tag->buf; + for (;;) { + int bufSize; + int convLen; + const enum XML_Convert_Result convert_res + = XmlConvert(enc, &fromPtr, rawNameEnd, (ICHAR **)&toPtr, + (ICHAR *)tag->bufEnd - 1); + convLen = (int)(toPtr - (XML_Char *)tag->buf); + if ((fromPtr >= rawNameEnd) + || (convert_res == XML_CONVERT_INPUT_INCOMPLETE)) { + tag->name.strLen = convLen; + break; } - tag->bufEnd = tag->buf + INIT_TAG_BUF_SIZE; - } - tag->bindings = NULL; - tag->parent = tagStack; - tagStack = tag; - tag->name.localPart = NULL; - tag->name.prefix = NULL; - tag->rawName = s + enc->minBytesPerChar; - tag->rawNameLength = XmlNameLength(enc, tag->rawName); - ++tagLevel; - { - const char *rawNameEnd = tag->rawName + tag->rawNameLength; - const char *fromPtr = tag->rawName; - toPtr = (XML_Char *)tag->buf; - for (;;) { - int bufSize; - int convLen; - const enum XML_Convert_Result convert_res = XmlConvert(enc, - &fromPtr, rawNameEnd, - (ICHAR **)&toPtr, (ICHAR *)tag->bufEnd - 1); - convLen = (int)(toPtr - (XML_Char *)tag->buf); - if ((fromPtr >= rawNameEnd) || (convert_res == XML_CONVERT_INPUT_INCOMPLETE)) { - tag->name.strLen = convLen; - break; - } - bufSize = (int)(tag->bufEnd - tag->buf) << 1; - { - char *temp = (char *)REALLOC(tag->buf, bufSize); - if (temp == NULL) - return XML_ERROR_NO_MEMORY; - tag->buf = temp; - tag->bufEnd = temp + bufSize; - toPtr = (XML_Char *)temp + convLen; - } + bufSize = (int)(tag->bufEnd - tag->buf) << 1; + { + char *temp = (char *)REALLOC(parser, tag->buf, bufSize); + if (temp == NULL) + return XML_ERROR_NO_MEMORY; + tag->buf = temp; + tag->bufEnd = temp + bufSize; + toPtr = (XML_Char *)temp + convLen; } } - tag->name.str = (XML_Char *)tag->buf; - *toPtr = XML_T('\0'); - result = storeAtts(parser, enc, s, &(tag->name), &(tag->bindings)); - if (result) - return result; - if (startElementHandler) - startElementHandler(handlerArg, tag->name.str, - (const XML_Char **)atts); - else if (defaultHandler) - reportDefault(parser, enc, s, next); - poolClear(&tempPool); - break; } + tag->name.str = (XML_Char *)tag->buf; + *toPtr = XML_T('\0'); + result = storeAtts(parser, enc, s, &(tag->name), &(tag->bindings)); + if (result) + return result; + if (parser->m_startElementHandler) + parser->m_startElementHandler(parser->m_handlerArg, tag->name.str, + (const XML_Char **)parser->m_atts); + else if (parser->m_defaultHandler) + reportDefault(parser, enc, s, next); + poolClear(&parser->m_tempPool); + break; + } case XML_TOK_EMPTY_ELEMENT_NO_ATTS: /* fall through */ - case XML_TOK_EMPTY_ELEMENT_WITH_ATTS: - { - const char *rawName = s + enc->minBytesPerChar; - enum XML_Error result; - BINDING *bindings = NULL; - XML_Bool noElmHandlers = XML_TRUE; - TAG_NAME name; - name.str = poolStoreString(&tempPool, enc, rawName, - rawName + XmlNameLength(enc, rawName)); - if (!name.str) - return XML_ERROR_NO_MEMORY; - poolFinish(&tempPool); - result = storeAtts(parser, enc, s, &name, &bindings); - if (result) - return result; - poolFinish(&tempPool); - if (startElementHandler) { - startElementHandler(handlerArg, name.str, (const XML_Char **)atts); - noElmHandlers = XML_FALSE; - } - if (endElementHandler) { - if (startElementHandler) - *eventPP = *eventEndPP; - endElementHandler(handlerArg, name.str); - noElmHandlers = XML_FALSE; - } - if (noElmHandlers && defaultHandler) - reportDefault(parser, enc, s, next); - poolClear(&tempPool); - while (bindings) { - BINDING *b = bindings; - if (endNamespaceDeclHandler) - endNamespaceDeclHandler(handlerArg, b->prefix->name); - bindings = bindings->nextTagBinding; - b->nextTagBinding = freeBindingList; - freeBindingList = b; - b->prefix->binding = b->prevPrefixBinding; - } + case XML_TOK_EMPTY_ELEMENT_WITH_ATTS: { + const char *rawName = s + enc->minBytesPerChar; + enum XML_Error result; + BINDING *bindings = NULL; + XML_Bool noElmHandlers = XML_TRUE; + TAG_NAME name; + name.str = poolStoreString(&parser->m_tempPool, enc, rawName, + rawName + XmlNameLength(enc, rawName)); + if (! name.str) + return XML_ERROR_NO_MEMORY; + poolFinish(&parser->m_tempPool); + result = storeAtts(parser, enc, s, &name, &bindings); + if (result != XML_ERROR_NONE) { + freeBindings(parser, bindings); + return result; + } + poolFinish(&parser->m_tempPool); + if (parser->m_startElementHandler) { + parser->m_startElementHandler(parser->m_handlerArg, name.str, + (const XML_Char **)parser->m_atts); + noElmHandlers = XML_FALSE; + } + if (parser->m_endElementHandler) { + if (parser->m_startElementHandler) + *eventPP = *eventEndPP; + parser->m_endElementHandler(parser->m_handlerArg, name.str); + noElmHandlers = XML_FALSE; + } + if (noElmHandlers && parser->m_defaultHandler) + reportDefault(parser, enc, s, next); + poolClear(&parser->m_tempPool); + freeBindings(parser, bindings); + } + if ((parser->m_tagLevel == 0) + && (parser->m_parsingStatus.parsing != XML_FINISHED)) { + if (parser->m_parsingStatus.parsing == XML_SUSPENDED) + parser->m_processor = epilogProcessor; + else + return epilogProcessor(parser, next, end, nextPtr); } - if (tagLevel == 0) - return epilogProcessor(parser, next, end, nextPtr); break; case XML_TOK_END_TAG: - if (tagLevel == startTagLevel) + if (parser->m_tagLevel == startTagLevel) return XML_ERROR_ASYNC_ENTITY; else { int len; const char *rawName; - TAG *tag = tagStack; - tagStack = tag->parent; - tag->parent = freeTagList; - freeTagList = tag; - rawName = s + enc->minBytesPerChar*2; + TAG *tag = parser->m_tagStack; + parser->m_tagStack = tag->parent; + tag->parent = parser->m_freeTagList; + parser->m_freeTagList = tag; + rawName = s + enc->minBytesPerChar * 2; len = XmlNameLength(enc, rawName); if (len != tag->rawNameLength || memcmp(tag->rawName, rawName, len) != 0) { *eventPP = rawName; return XML_ERROR_TAG_MISMATCH; } - --tagLevel; - if (endElementHandler) { + --parser->m_tagLevel; + if (parser->m_endElementHandler) { const XML_Char *localPart; const XML_Char *prefix; XML_Char *uri; localPart = tag->name.localPart; - if (ns && localPart) { + if (parser->m_ns && localPart) { /* localPart and prefix may have been overwritten in tag->name.str, since this points to the binding->uri buffer which gets re-used; so we have to add them again */ uri = (XML_Char *)tag->name.str + tag->name.uriLen; /* don't need to check for space - already done in storeAtts() */ - while (*localPart) *uri++ = *localPart++; + while (*localPart) + *uri++ = *localPart++; prefix = (XML_Char *)tag->name.prefix; - if (ns_triplets && prefix) { - *uri++ = namespaceSeparator; - while (*prefix) *uri++ = *prefix++; - } + if (parser->m_ns_triplets && prefix) { + *uri++ = parser->m_namespaceSeparator; + while (*prefix) + *uri++ = *prefix++; + } *uri = XML_T('\0'); } - endElementHandler(handlerArg, tag->name.str); - } - else if (defaultHandler) + parser->m_endElementHandler(parser->m_handlerArg, tag->name.str); + } else if (parser->m_defaultHandler) reportDefault(parser, enc, s, next); while (tag->bindings) { BINDING *b = tag->bindings; - if (endNamespaceDeclHandler) - endNamespaceDeclHandler(handlerArg, b->prefix->name); + if (parser->m_endNamespaceDeclHandler) + parser->m_endNamespaceDeclHandler(parser->m_handlerArg, + b->prefix->name); tag->bindings = tag->bindings->nextTagBinding; - b->nextTagBinding = freeBindingList; - freeBindingList = b; + b->nextTagBinding = parser->m_freeBindingList; + parser->m_freeBindingList = b; b->prefix->binding = b->prevPrefixBinding; } - if (tagLevel == 0) - return epilogProcessor(parser, next, end, nextPtr); - } - break; - case XML_TOK_CHAR_REF: - { - int n = XmlCharRefNumber(enc, s); - if (n < 0) - return XML_ERROR_BAD_CHAR_REF; - if (characterDataHandler) { - XML_Char buf[XML_ENCODE_MAX]; - characterDataHandler(handlerArg, buf, XmlEncode(n, (ICHAR *)buf)); + if ((parser->m_tagLevel == 0) + && (parser->m_parsingStatus.parsing != XML_FINISHED)) { + if (parser->m_parsingStatus.parsing == XML_SUSPENDED) + parser->m_processor = epilogProcessor; + else + return epilogProcessor(parser, next, end, nextPtr); } - else if (defaultHandler) - reportDefault(parser, enc, s, next); } break; + case XML_TOK_CHAR_REF: { + int n = XmlCharRefNumber(enc, s); + if (n < 0) + return XML_ERROR_BAD_CHAR_REF; + if (parser->m_characterDataHandler) { + XML_Char buf[XML_ENCODE_MAX]; + parser->m_characterDataHandler(parser->m_handlerArg, buf, + XmlEncode(n, (ICHAR *)buf)); + } else if (parser->m_defaultHandler) + reportDefault(parser, enc, s, next); + } break; case XML_TOK_XML_DECL: return XML_ERROR_MISPLACED_XML_PI; case XML_TOK_DATA_NEWLINE: - if (characterDataHandler) { + if (parser->m_characterDataHandler) { XML_Char c = 0xA; - characterDataHandler(handlerArg, &c, 1); - } - else if (defaultHandler) + parser->m_characterDataHandler(parser->m_handlerArg, &c, 1); + } else if (parser->m_defaultHandler) reportDefault(parser, enc, s, next); break; - case XML_TOK_CDATA_SECT_OPEN: - { - enum XML_Error result; - if (startCdataSectionHandler) - startCdataSectionHandler(handlerArg); -#if 0 - /* Suppose you doing a transformation on a document that involves - changing only the character data. You set up a defaultHandler - and a characterDataHandler. The defaultHandler simply copies - characters through. The characterDataHandler does the - transformation and writes the characters out escaping them as - necessary. This case will fail to work if we leave out the - following two lines (because & and < inside CDATA sections will - be incorrectly escaped). - - However, now we have a start/endCdataSectionHandler, so it seems - easier to let the user deal with this. - */ - else if (characterDataHandler) - characterDataHandler(handlerArg, dataBuf, 0); -#endif - else if (defaultHandler) - reportDefault(parser, enc, s, next); - result = doCdataSection(parser, enc, &next, end, nextPtr, haveMore); - if (result != XML_ERROR_NONE) - return result; - else if (!next) { - processor = cdataSectionProcessor; - return result; - } + case XML_TOK_CDATA_SECT_OPEN: { + enum XML_Error result; + if (parser->m_startCdataSectionHandler) + parser->m_startCdataSectionHandler(parser->m_handlerArg); + /* BEGIN disabled code */ + /* Suppose you doing a transformation on a document that involves + changing only the character data. You set up a defaultHandler + and a characterDataHandler. The defaultHandler simply copies + characters through. The characterDataHandler does the + transformation and writes the characters out escaping them as + necessary. This case will fail to work if we leave out the + following two lines (because & and < inside CDATA sections will + be incorrectly escaped). + + However, now we have a start/endCdataSectionHandler, so it seems + easier to let the user deal with this. + */ + else if (0 && parser->m_characterDataHandler) + parser->m_characterDataHandler(parser->m_handlerArg, parser->m_dataBuf, + 0); + /* END disabled code */ + else if (parser->m_defaultHandler) + reportDefault(parser, enc, s, next); + result = doCdataSection(parser, enc, &next, end, nextPtr, haveMore); + if (result != XML_ERROR_NONE) + return result; + else if (! next) { + parser->m_processor = cdataSectionProcessor; + return result; } - break; + } break; case XML_TOK_TRAILING_RSQB: if (haveMore) { *nextPtr = s; return XML_ERROR_NONE; } - if (characterDataHandler) { + if (parser->m_characterDataHandler) { if (MUST_CONVERT(enc, s)) { - ICHAR *dataPtr = (ICHAR *)dataBuf; - XmlConvert(enc, &s, end, &dataPtr, (ICHAR *)dataBufEnd); - characterDataHandler(handlerArg, dataBuf, - (int)(dataPtr - (ICHAR *)dataBuf)); - } - else - characterDataHandler(handlerArg, - (XML_Char *)s, - (int)((XML_Char *)end - (XML_Char *)s)); - } - else if (defaultHandler) + ICHAR *dataPtr = (ICHAR *)parser->m_dataBuf; + XmlConvert(enc, &s, end, &dataPtr, (ICHAR *)parser->m_dataBufEnd); + parser->m_characterDataHandler( + parser->m_handlerArg, parser->m_dataBuf, + (int)(dataPtr - (ICHAR *)parser->m_dataBuf)); + } else + parser->m_characterDataHandler( + parser->m_handlerArg, (XML_Char *)s, + (int)((XML_Char *)end - (XML_Char *)s)); + } else if (parser->m_defaultHandler) reportDefault(parser, enc, s, end); /* We are at the end of the final buffer, should we check for XML_SUSPENDED, XML_FINISHED? @@ -2688,63 +2940,90 @@ doContent(XML_Parser parser, *eventPP = end; return XML_ERROR_NO_ELEMENTS; } - if (tagLevel != startTagLevel) { + if (parser->m_tagLevel != startTagLevel) { *eventPP = end; return XML_ERROR_ASYNC_ENTITY; } *nextPtr = end; return XML_ERROR_NONE; - case XML_TOK_DATA_CHARS: - { - XML_CharacterDataHandler charDataHandler = characterDataHandler; - if (charDataHandler) { - if (MUST_CONVERT(enc, s)) { - for (;;) { - ICHAR *dataPtr = (ICHAR *)dataBuf; - const enum XML_Convert_Result convert_res = XmlConvert(enc, &s, next, &dataPtr, (ICHAR *)dataBufEnd); - *eventEndPP = s; - charDataHandler(handlerArg, dataBuf, - (int)(dataPtr - (ICHAR *)dataBuf)); - if ((convert_res == XML_CONVERT_COMPLETED) || (convert_res == XML_CONVERT_INPUT_INCOMPLETE)) - break; - *eventPP = s; - } + case XML_TOK_DATA_CHARS: { + XML_CharacterDataHandler charDataHandler = parser->m_characterDataHandler; + if (charDataHandler) { + if (MUST_CONVERT(enc, s)) { + for (;;) { + ICHAR *dataPtr = (ICHAR *)parser->m_dataBuf; + const enum XML_Convert_Result convert_res = XmlConvert( + enc, &s, next, &dataPtr, (ICHAR *)parser->m_dataBufEnd); + *eventEndPP = s; + charDataHandler(parser->m_handlerArg, parser->m_dataBuf, + (int)(dataPtr - (ICHAR *)parser->m_dataBuf)); + if ((convert_res == XML_CONVERT_COMPLETED) + || (convert_res == XML_CONVERT_INPUT_INCOMPLETE)) + break; + *eventPP = s; } - else - charDataHandler(handlerArg, - (XML_Char *)s, - (int)((XML_Char *)next - (XML_Char *)s)); - } - else if (defaultHandler) - reportDefault(parser, enc, s, next); - } - break; + } else + charDataHandler(parser->m_handlerArg, (XML_Char *)s, + (int)((XML_Char *)next - (XML_Char *)s)); + } else if (parser->m_defaultHandler) + reportDefault(parser, enc, s, next); + } break; case XML_TOK_PI: - if (!reportProcessingInstruction(parser, enc, s, next)) + if (! reportProcessingInstruction(parser, enc, s, next)) return XML_ERROR_NO_MEMORY; break; case XML_TOK_COMMENT: - if (!reportComment(parser, enc, s, next)) + if (! reportComment(parser, enc, s, next)) return XML_ERROR_NO_MEMORY; break; default: - if (defaultHandler) + /* All of the tokens produced by XmlContentTok() have their own + * explicit cases, so this default is not strictly necessary. + * However it is a useful safety net, so we retain the code and + * simply exclude it from the coverage tests. + * + * LCOV_EXCL_START + */ + if (parser->m_defaultHandler) reportDefault(parser, enc, s, next); break; + /* LCOV_EXCL_STOP */ } *eventPP = s = next; - switch (ps_parsing) { + switch (parser->m_parsingStatus.parsing) { case XML_SUSPENDED: *nextPtr = next; return XML_ERROR_NONE; case XML_FINISHED: return XML_ERROR_ABORTED; - default: ; + default:; } } /* not reached */ } +/* This function does not call free() on the allocated memory, merely + * moving it to the parser's m_freeBindingList where it can be freed or + * reused as appropriate. + */ +static void +freeBindings(XML_Parser parser, BINDING *bindings) { + while (bindings) { + BINDING *b = bindings; + + /* m_startNamespaceDeclHandler will have been called for this + * binding in addBindings(), so call the end handler now. + */ + if (parser->m_endNamespaceDeclHandler) + parser->m_endNamespaceDeclHandler(parser->m_handlerArg, b->prefix->name); + + bindings = bindings->nextTagBinding; + b->nextTagBinding = parser->m_freeBindingList; + parser->m_freeBindingList = b; + b->prefix->binding = b->prevPrefixBinding; + } +} + /* Precondition: all arguments must be non-NULL; Purpose: - normalize attributes @@ -2756,14 +3035,12 @@ doContent(XML_Parser parser, - generate namespace aware element name (URI, prefix) */ static enum XML_Error -storeAtts(XML_Parser parser, const ENCODING *enc, - const char *attStr, TAG_NAME *tagNamePtr, - BINDING **bindingsPtr) -{ - DTD * const dtd = _dtd; /* save one level of indirection */ +storeAtts(XML_Parser parser, const ENCODING *enc, const char *attStr, + TAG_NAME *tagNamePtr, BINDING **bindingsPtr) { + DTD *const dtd = parser->m_dtd; /* save one level of indirection */ ELEMENT_TYPE *elementType; int nDefaultAtts; - const XML_Char **appAtts; /* the attribute list for the application */ + const XML_Char **appAtts; /* the attribute list for the application */ int attIndex = 0; int prefixLen; int i; @@ -2774,75 +3051,84 @@ storeAtts(XML_Parser parser, const ENCODING *enc, const XML_Char *localPart; /* lookup the element type name */ - elementType = (ELEMENT_TYPE *)lookup(parser, &dtd->elementTypes, tagNamePtr->str,0); - if (!elementType) { + elementType + = (ELEMENT_TYPE *)lookup(parser, &dtd->elementTypes, tagNamePtr->str, 0); + if (! elementType) { const XML_Char *name = poolCopyString(&dtd->pool, tagNamePtr->str); - if (!name) + if (! name) return XML_ERROR_NO_MEMORY; elementType = (ELEMENT_TYPE *)lookup(parser, &dtd->elementTypes, name, sizeof(ELEMENT_TYPE)); - if (!elementType) + if (! elementType) return XML_ERROR_NO_MEMORY; - if (ns && !setElementTypePrefix(parser, elementType)) + if (parser->m_ns && ! setElementTypePrefix(parser, elementType)) return XML_ERROR_NO_MEMORY; } nDefaultAtts = elementType->nDefaultAtts; /* get the attributes from the tokenizer */ - n = XmlGetAttributes(enc, attStr, attsSize, atts); - if (n + nDefaultAtts > attsSize) { - int oldAttsSize = attsSize; + n = XmlGetAttributes(enc, attStr, parser->m_attsSize, parser->m_atts); + if (n + nDefaultAtts > parser->m_attsSize) { + int oldAttsSize = parser->m_attsSize; ATTRIBUTE *temp; #ifdef XML_ATTR_INFO XML_AttrInfo *temp2; #endif - attsSize = n + nDefaultAtts + INIT_ATTS_SIZE; - temp = (ATTRIBUTE *)REALLOC((void *)atts, attsSize * sizeof(ATTRIBUTE)); - if (temp == NULL) + parser->m_attsSize = n + nDefaultAtts + INIT_ATTS_SIZE; + temp = (ATTRIBUTE *)REALLOC(parser, (void *)parser->m_atts, + parser->m_attsSize * sizeof(ATTRIBUTE)); + if (temp == NULL) { + parser->m_attsSize = oldAttsSize; return XML_ERROR_NO_MEMORY; - atts = temp; + } + parser->m_atts = temp; #ifdef XML_ATTR_INFO - temp2 = (XML_AttrInfo *)REALLOC((void *)attInfo, attsSize * sizeof(XML_AttrInfo)); - if (temp2 == NULL) + temp2 = (XML_AttrInfo *)REALLOC(parser, (void *)parser->m_attInfo, + parser->m_attsSize * sizeof(XML_AttrInfo)); + if (temp2 == NULL) { + parser->m_attsSize = oldAttsSize; return XML_ERROR_NO_MEMORY; - attInfo = temp2; + } + parser->m_attInfo = temp2; #endif if (n > oldAttsSize) - XmlGetAttributes(enc, attStr, n, atts); + XmlGetAttributes(enc, attStr, n, parser->m_atts); } - appAtts = (const XML_Char **)atts; + appAtts = (const XML_Char **)parser->m_atts; for (i = 0; i < n; i++) { - ATTRIBUTE *currAtt = &atts[i]; + ATTRIBUTE *currAtt = &parser->m_atts[i]; #ifdef XML_ATTR_INFO - XML_AttrInfo *currAttInfo = &attInfo[i]; + XML_AttrInfo *currAttInfo = &parser->m_attInfo[i]; #endif /* add the name and value to the attribute list */ - ATTRIBUTE_ID *attId = getAttributeId(parser, enc, currAtt->name, - currAtt->name - + XmlNameLength(enc, currAtt->name)); - if (!attId) + ATTRIBUTE_ID *attId + = getAttributeId(parser, enc, currAtt->name, + currAtt->name + XmlNameLength(enc, currAtt->name)); + if (! attId) return XML_ERROR_NO_MEMORY; #ifdef XML_ATTR_INFO - currAttInfo->nameStart = parseEndByteIndex - (parseEndPtr - currAtt->name); - currAttInfo->nameEnd = currAttInfo->nameStart + - XmlNameLength(enc, currAtt->name); - currAttInfo->valueStart = parseEndByteIndex - - (parseEndPtr - currAtt->valuePtr); - currAttInfo->valueEnd = parseEndByteIndex - (parseEndPtr - currAtt->valueEnd); + currAttInfo->nameStart + = parser->m_parseEndByteIndex - (parser->m_parseEndPtr - currAtt->name); + currAttInfo->nameEnd + = currAttInfo->nameStart + XmlNameLength(enc, currAtt->name); + currAttInfo->valueStart = parser->m_parseEndByteIndex + - (parser->m_parseEndPtr - currAtt->valuePtr); + currAttInfo->valueEnd = parser->m_parseEndByteIndex + - (parser->m_parseEndPtr - currAtt->valueEnd); #endif /* Detect duplicate attributes by their QNames. This does not work when namespace processing is turned on and different prefixes for the same namespace are used. For this case we have a check further down. */ if ((attId->name)[-1]) { - if (enc == encoding) - eventPtr = atts[i].name; + if (enc == parser->m_encoding) + parser->m_eventPtr = parser->m_atts[i].name; return XML_ERROR_DUPLICATE_ATTRIBUTE; } (attId->name)[-1] = 1; appAtts[attIndex++] = attId->name; - if (!atts[i].normalized) { + if (! parser->m_atts[i].normalized) { enum XML_Error result; XML_Bool isCdata = XML_TRUE; @@ -2858,21 +3144,21 @@ storeAtts(XML_Parser parser, const ENCODING *enc, } /* normalize the attribute value */ - result = storeAttributeValue(parser, enc, isCdata, - atts[i].valuePtr, atts[i].valueEnd, - &tempPool); + result = storeAttributeValue( + parser, enc, isCdata, parser->m_atts[i].valuePtr, + parser->m_atts[i].valueEnd, &parser->m_tempPool); if (result) return result; - appAtts[attIndex] = poolStart(&tempPool); - poolFinish(&tempPool); - } - else { + appAtts[attIndex] = poolStart(&parser->m_tempPool); + poolFinish(&parser->m_tempPool); + } else { /* the value did not need normalizing */ - appAtts[attIndex] = poolStoreString(&tempPool, enc, atts[i].valuePtr, - atts[i].valueEnd); + appAtts[attIndex] = poolStoreString(&parser->m_tempPool, enc, + parser->m_atts[i].valuePtr, + parser->m_atts[i].valueEnd); if (appAtts[attIndex] == 0) return XML_ERROR_NO_MEMORY; - poolFinish(&tempPool); + poolFinish(&parser->m_tempPool); } /* handle prefixed attribute names */ if (attId->prefix) { @@ -2883,49 +3169,44 @@ storeAtts(XML_Parser parser, const ENCODING *enc, if (result) return result; --attIndex; - } - else { + } else { /* deal with other prefixed names later */ attIndex++; nPrefixes++; (attId->name)[-1] = 2; } - } - else + } else attIndex++; } /* set-up for XML_GetSpecifiedAttributeCount and XML_GetIdAttributeIndex */ - nSpecifiedAtts = attIndex; + parser->m_nSpecifiedAtts = attIndex; if (elementType->idAtt && (elementType->idAtt->name)[-1]) { for (i = 0; i < attIndex; i += 2) if (appAtts[i] == elementType->idAtt->name) { - idAttIndex = i; + parser->m_idAttIndex = i; break; } - } - else - idAttIndex = -1; + } else + parser->m_idAttIndex = -1; /* do attribute defaulting */ for (i = 0; i < nDefaultAtts; i++) { const DEFAULT_ATTRIBUTE *da = elementType->defaultAtts + i; - if (!(da->id->name)[-1] && da->value) { + if (! (da->id->name)[-1] && da->value) { if (da->id->prefix) { if (da->id->xmlns) { enum XML_Error result = addBinding(parser, da->id->prefix, da->id, da->value, bindingsPtr); if (result) return result; - } - else { + } else { (da->id->name)[-1] = 2; nPrefixes++; appAtts[attIndex++] = da->id->name; appAtts[attIndex++] = da->value; } - } - else { + } else { (da->id->name)[-1] = 1; appAtts[attIndex++] = da->id->name; appAtts[attIndex++] = da->value; @@ -2938,110 +3219,142 @@ storeAtts(XML_Parser parser, const ENCODING *enc, and clear flags that say whether attributes were specified */ i = 0; if (nPrefixes) { - int j; /* hash table index */ - unsigned long version = nsAttsVersion; - int nsAttsSize = (int)1 << nsAttsPower; + int j; /* hash table index */ + unsigned long version = parser->m_nsAttsVersion; + int nsAttsSize = (int)1 << parser->m_nsAttsPower; + unsigned char oldNsAttsPower = parser->m_nsAttsPower; /* size of hash table must be at least 2 * (# of prefixed attributes) */ - if ((nPrefixes << 1) >> nsAttsPower) { /* true for nsAttsPower = 0 */ + if ((nPrefixes << 1) + >> parser->m_nsAttsPower) { /* true for m_nsAttsPower = 0 */ NS_ATT *temp; /* hash table size must also be a power of 2 and >= 8 */ - while (nPrefixes >> nsAttsPower++); - if (nsAttsPower < 3) - nsAttsPower = 3; - nsAttsSize = (int)1 << nsAttsPower; - temp = (NS_ATT *)REALLOC(nsAtts, nsAttsSize * sizeof(NS_ATT)); - if (!temp) + while (nPrefixes >> parser->m_nsAttsPower++) + ; + if (parser->m_nsAttsPower < 3) + parser->m_nsAttsPower = 3; + nsAttsSize = (int)1 << parser->m_nsAttsPower; + temp = (NS_ATT *)REALLOC(parser, parser->m_nsAtts, + nsAttsSize * sizeof(NS_ATT)); + if (! temp) { + /* Restore actual size of memory in m_nsAtts */ + parser->m_nsAttsPower = oldNsAttsPower; return XML_ERROR_NO_MEMORY; - nsAtts = temp; - version = 0; /* force re-initialization of nsAtts hash table */ + } + parser->m_nsAtts = temp; + version = 0; /* force re-initialization of m_nsAtts hash table */ } - /* using a version flag saves us from initializing nsAtts every time */ - if (!version) { /* initialize version flags when version wraps around */ + /* using a version flag saves us from initializing m_nsAtts every time */ + if (! version) { /* initialize version flags when version wraps around */ version = INIT_ATTS_VERSION; - for (j = nsAttsSize; j != 0; ) - nsAtts[--j].version = version; + for (j = nsAttsSize; j != 0;) + parser->m_nsAtts[--j].version = version; } - nsAttsVersion = --version; + parser->m_nsAttsVersion = --version; /* expand prefixed names and check for duplicates */ for (; i < attIndex; i += 2) { const XML_Char *s = appAtts[i]; - if (s[-1] == 2) { /* prefixed */ + if (s[-1] == 2) { /* prefixed */ ATTRIBUTE_ID *id; const BINDING *b; - unsigned long uriHash = hash_secret_salt; - ((XML_Char *)s)[-1] = 0; /* clear flag */ + unsigned long uriHash; + struct siphash sip_state; + struct sipkey sip_key; + + copy_salt_to_sipkey(parser, &sip_key); + sip24_init(&sip_state, &sip_key); + + ((XML_Char *)s)[-1] = 0; /* clear flag */ id = (ATTRIBUTE_ID *)lookup(parser, &dtd->attributeIds, s, 0); - if (!id || !id->prefix) - return XML_ERROR_NO_MEMORY; + if (! id || ! id->prefix) { + /* This code is walking through the appAtts array, dealing + * with (in this case) a prefixed attribute name. To be in + * the array, the attribute must have already been bound, so + * has to have passed through the hash table lookup once + * already. That implies that an entry for it already + * exists, so the lookup above will return a pointer to + * already allocated memory. There is no opportunaity for + * the allocator to fail, so the condition above cannot be + * fulfilled. + * + * Since it is difficult to be certain that the above + * analysis is complete, we retain the test and merely + * remove the code from coverage tests. + */ + return XML_ERROR_NO_MEMORY; /* LCOV_EXCL_LINE */ + } b = id->prefix->binding; - if (!b) + if (! b) return XML_ERROR_UNBOUND_PREFIX; - /* as we expand the name we also calculate its hash value */ for (j = 0; j < b->uriLen; j++) { const XML_Char c = b->uri[j]; - if (!poolAppendChar(&tempPool, c)) + if (! poolAppendChar(&parser->m_tempPool, c)) return XML_ERROR_NO_MEMORY; - uriHash = CHAR_HASH(uriHash, c); } + + sip24_update(&sip_state, b->uri, b->uriLen * sizeof(XML_Char)); + while (*s++ != XML_T(ASCII_COLON)) ; - do { /* copies null terminator */ - const XML_Char c = *s; - if (!poolAppendChar(&tempPool, *s)) + + sip24_update(&sip_state, s, keylen(s) * sizeof(XML_Char)); + + do { /* copies null terminator */ + if (! poolAppendChar(&parser->m_tempPool, *s)) return XML_ERROR_NO_MEMORY; - uriHash = CHAR_HASH(uriHash, c); } while (*s++); + uriHash = (unsigned long)sip24_final(&sip_state); + { /* Check hash table for duplicate of expanded name (uriName). Derived from code in lookup(parser, HASH_TABLE *table, ...). */ unsigned char step = 0; unsigned long mask = nsAttsSize - 1; - j = uriHash & mask; /* index into hash table */ - while (nsAtts[j].version == version) { + j = uriHash & mask; /* index into hash table */ + while (parser->m_nsAtts[j].version == version) { /* for speed we compare stored hash values first */ - if (uriHash == nsAtts[j].hash) { - const XML_Char *s1 = poolStart(&tempPool); - const XML_Char *s2 = nsAtts[j].uriName; + if (uriHash == parser->m_nsAtts[j].hash) { + const XML_Char *s1 = poolStart(&parser->m_tempPool); + const XML_Char *s2 = parser->m_nsAtts[j].uriName; /* s1 is null terminated, but not s2 */ - for (; *s1 == *s2 && *s1 != 0; s1++, s2++); + for (; *s1 == *s2 && *s1 != 0; s1++, s2++) + ; if (*s1 == 0) return XML_ERROR_DUPLICATE_ATTRIBUTE; } - if (!step) - step = PROBE_STEP(uriHash, mask, nsAttsPower); + if (! step) + step = PROBE_STEP(uriHash, mask, parser->m_nsAttsPower); j < step ? (j += nsAttsSize - step) : (j -= step); } } - if (ns_triplets) { /* append namespace separator and prefix */ - tempPool.ptr[-1] = namespaceSeparator; + if (parser->m_ns_triplets) { /* append namespace separator and prefix */ + parser->m_tempPool.ptr[-1] = parser->m_namespaceSeparator; s = b->prefix->name; do { - if (!poolAppendChar(&tempPool, *s)) + if (! poolAppendChar(&parser->m_tempPool, *s)) return XML_ERROR_NO_MEMORY; } while (*s++); } /* store expanded name in attribute list */ - s = poolStart(&tempPool); - poolFinish(&tempPool); + s = poolStart(&parser->m_tempPool); + poolFinish(&parser->m_tempPool); appAtts[i] = s; /* fill empty slot with new version, uriName and hash value */ - nsAtts[j].version = version; - nsAtts[j].hash = uriHash; - nsAtts[j].uriName = s; + parser->m_nsAtts[j].version = version; + parser->m_nsAtts[j].hash = uriHash; + parser->m_nsAtts[j].uriName = s; - if (!--nPrefixes) { + if (! --nPrefixes) { i += 2; break; } - } - else /* not prefixed */ - ((XML_Char *)s)[-1] = 0; /* clear flag */ + } else /* not prefixed */ + ((XML_Char *)s)[-1] = 0; /* clear flag */ } } /* clear flags for the remaining attributes */ @@ -3050,56 +3363,54 @@ storeAtts(XML_Parser parser, const ENCODING *enc, for (binding = *bindingsPtr; binding; binding = binding->nextTagBinding) binding->attId->name[-1] = 0; - if (!ns) + if (! parser->m_ns) return XML_ERROR_NONE; /* expand the element type name */ if (elementType->prefix) { binding = elementType->prefix->binding; - if (!binding) + if (! binding) return XML_ERROR_UNBOUND_PREFIX; localPart = tagNamePtr->str; while (*localPart++ != XML_T(ASCII_COLON)) ; - } - else if (dtd->defaultPrefix.binding) { + } else if (dtd->defaultPrefix.binding) { binding = dtd->defaultPrefix.binding; localPart = tagNamePtr->str; - } - else + } else return XML_ERROR_NONE; prefixLen = 0; - if (ns_triplets && binding->prefix->name) { + if (parser->m_ns_triplets && binding->prefix->name) { for (; binding->prefix->name[prefixLen++];) - ; /* prefixLen includes null terminator */ + ; /* prefixLen includes null terminator */ } tagNamePtr->localPart = localPart; tagNamePtr->uriLen = binding->uriLen; tagNamePtr->prefix = binding->prefix->name; tagNamePtr->prefixLen = prefixLen; for (i = 0; localPart[i++];) - ; /* i includes null terminator */ + ; /* i includes null terminator */ n = i + binding->uriLen + prefixLen; if (n > binding->uriAlloc) { TAG *p; - uri = (XML_Char *)MALLOC((n + EXPAND_SPARE) * sizeof(XML_Char)); - if (!uri) + uri = (XML_Char *)MALLOC(parser, (n + EXPAND_SPARE) * sizeof(XML_Char)); + if (! uri) return XML_ERROR_NO_MEMORY; binding->uriAlloc = n + EXPAND_SPARE; memcpy(uri, binding->uri, binding->uriLen * sizeof(XML_Char)); - for (p = tagStack; p; p = p->parent) + for (p = parser->m_tagStack; p; p = p->parent) if (p->name.str == binding->uri) p->name.str = uri; - FREE(binding->uri); + FREE(parser, binding->uri); binding->uri = uri; } - /* if namespaceSeparator != '\0' then uri includes it already */ + /* if m_namespaceSeparator != '\0' then uri includes it already */ uri = binding->uri + binding->uriLen; memcpy(uri, localPart, i * sizeof(XML_Char)); /* we always have a namespace separator between localPart and prefix */ if (prefixLen) { uri += i - 1; - *uri = namespaceSeparator; /* replace null terminator */ + *uri = parser->m_namespaceSeparator; /* replace null terminator */ memcpy(uri + 1, binding->prefix->name, prefixLen * sizeof(XML_Char)); } tagNamePtr->str = binding->uri; @@ -3111,27 +3422,25 @@ storeAtts(XML_Parser parser, const ENCODING *enc, */ static enum XML_Error addBinding(XML_Parser parser, PREFIX *prefix, const ATTRIBUTE_ID *attId, - const XML_Char *uri, BINDING **bindingsPtr) -{ - static const XML_Char xmlNamespace[] = { - ASCII_h, ASCII_t, ASCII_t, ASCII_p, ASCII_COLON, ASCII_SLASH, ASCII_SLASH, - ASCII_w, ASCII_w, ASCII_w, ASCII_PERIOD, ASCII_w, ASCII_3, ASCII_PERIOD, - ASCII_o, ASCII_r, ASCII_g, ASCII_SLASH, ASCII_X, ASCII_M, ASCII_L, - ASCII_SLASH, ASCII_1, ASCII_9, ASCII_9, ASCII_8, ASCII_SLASH, - ASCII_n, ASCII_a, ASCII_m, ASCII_e, ASCII_s, ASCII_p, ASCII_a, ASCII_c, - ASCII_e, '\0' - }; - static const int xmlLen = - (int)sizeof(xmlNamespace)/sizeof(XML_Char) - 1; - static const XML_Char xmlnsNamespace[] = { - ASCII_h, ASCII_t, ASCII_t, ASCII_p, ASCII_COLON, ASCII_SLASH, ASCII_SLASH, - ASCII_w, ASCII_w, ASCII_w, ASCII_PERIOD, ASCII_w, ASCII_3, ASCII_PERIOD, - ASCII_o, ASCII_r, ASCII_g, ASCII_SLASH, ASCII_2, ASCII_0, ASCII_0, - ASCII_0, ASCII_SLASH, ASCII_x, ASCII_m, ASCII_l, ASCII_n, ASCII_s, - ASCII_SLASH, '\0' - }; - static const int xmlnsLen = - (int)sizeof(xmlnsNamespace)/sizeof(XML_Char) - 1; + const XML_Char *uri, BINDING **bindingsPtr) { + static const XML_Char xmlNamespace[] + = {ASCII_h, ASCII_t, ASCII_t, ASCII_p, ASCII_COLON, + ASCII_SLASH, ASCII_SLASH, ASCII_w, ASCII_w, ASCII_w, + ASCII_PERIOD, ASCII_w, ASCII_3, ASCII_PERIOD, ASCII_o, + ASCII_r, ASCII_g, ASCII_SLASH, ASCII_X, ASCII_M, + ASCII_L, ASCII_SLASH, ASCII_1, ASCII_9, ASCII_9, + ASCII_8, ASCII_SLASH, ASCII_n, ASCII_a, ASCII_m, + ASCII_e, ASCII_s, ASCII_p, ASCII_a, ASCII_c, + ASCII_e, '\0'}; + static const int xmlLen = (int)sizeof(xmlNamespace) / sizeof(XML_Char) - 1; + static const XML_Char xmlnsNamespace[] + = {ASCII_h, ASCII_t, ASCII_t, ASCII_p, ASCII_COLON, ASCII_SLASH, + ASCII_SLASH, ASCII_w, ASCII_w, ASCII_w, ASCII_PERIOD, ASCII_w, + ASCII_3, ASCII_PERIOD, ASCII_o, ASCII_r, ASCII_g, ASCII_SLASH, + ASCII_2, ASCII_0, ASCII_0, ASCII_0, ASCII_SLASH, ASCII_x, + ASCII_m, ASCII_l, ASCII_n, ASCII_s, ASCII_SLASH, '\0'}; + static const int xmlnsLen + = (int)sizeof(xmlnsNamespace) / sizeof(XML_Char) - 1; XML_Bool mustBeXML = XML_FALSE; XML_Bool isXML = XML_TRUE; @@ -3144,14 +3453,11 @@ addBinding(XML_Parser parser, PREFIX *prefix, const ATTRIBUTE_ID *attId, if (*uri == XML_T('\0') && prefix->name) return XML_ERROR_UNDECLARING_PREFIX; - if (prefix->name - && prefix->name[0] == XML_T(ASCII_x) + if (prefix->name && prefix->name[0] == XML_T(ASCII_x) && prefix->name[1] == XML_T(ASCII_m) && prefix->name[2] == XML_T(ASCII_l)) { - /* Not allowed to bind xmlns */ - if (prefix->name[3] == XML_T(ASCII_n) - && prefix->name[4] == XML_T(ASCII_s) + if (prefix->name[3] == XML_T(ASCII_n) && prefix->name[4] == XML_T(ASCII_s) && prefix->name[5] == XML_T('\0')) return XML_ERROR_RESERVED_PREFIX_XMLNS; @@ -3163,7 +3469,7 @@ addBinding(XML_Parser parser, PREFIX *prefix, const ATTRIBUTE_ID *attId, if (isXML && (len > xmlLen || uri[len] != xmlNamespace[len])) isXML = XML_FALSE; - if (!mustBeXML && isXMLNS + if (! mustBeXML && isXMLNS && (len > xmlnsLen || uri[len] != xmlnsNamespace[len])) isXMLNS = XML_FALSE; } @@ -3177,49 +3483,49 @@ addBinding(XML_Parser parser, PREFIX *prefix, const ATTRIBUTE_ID *attId, if (isXMLNS) return XML_ERROR_RESERVED_NAMESPACE_URI; - if (namespaceSeparator) + if (parser->m_namespaceSeparator) len++; - if (freeBindingList) { - b = freeBindingList; + if (parser->m_freeBindingList) { + b = parser->m_freeBindingList; if (len > b->uriAlloc) { - XML_Char *temp = (XML_Char *)REALLOC(b->uri, - sizeof(XML_Char) * (len + EXPAND_SPARE)); + XML_Char *temp = (XML_Char *)REALLOC( + parser, b->uri, sizeof(XML_Char) * (len + EXPAND_SPARE)); if (temp == NULL) return XML_ERROR_NO_MEMORY; b->uri = temp; b->uriAlloc = len + EXPAND_SPARE; } - freeBindingList = b->nextTagBinding; - } - else { - b = (BINDING *)MALLOC(sizeof(BINDING)); - if (!b) + parser->m_freeBindingList = b->nextTagBinding; + } else { + b = (BINDING *)MALLOC(parser, sizeof(BINDING)); + if (! b) return XML_ERROR_NO_MEMORY; - b->uri = (XML_Char *)MALLOC(sizeof(XML_Char) * (len + EXPAND_SPARE)); - if (!b->uri) { - FREE(b); + b->uri + = (XML_Char *)MALLOC(parser, sizeof(XML_Char) * (len + EXPAND_SPARE)); + if (! b->uri) { + FREE(parser, b); return XML_ERROR_NO_MEMORY; } b->uriAlloc = len + EXPAND_SPARE; } b->uriLen = len; memcpy(b->uri, uri, len * sizeof(XML_Char)); - if (namespaceSeparator) - b->uri[len - 1] = namespaceSeparator; + if (parser->m_namespaceSeparator) + b->uri[len - 1] = parser->m_namespaceSeparator; b->prefix = prefix; b->attId = attId; b->prevPrefixBinding = prefix->binding; /* NULL binding when default namespace undeclared */ - if (*uri == XML_T('\0') && prefix == &_dtd->defaultPrefix) + if (*uri == XML_T('\0') && prefix == &parser->m_dtd->defaultPrefix) prefix->binding = NULL; else prefix->binding = b; b->nextTagBinding = *bindingsPtr; *bindingsPtr = b; /* if attId == NULL then we are not starting a namespace scope */ - if (attId && startNamespaceDeclHandler) - startNamespaceDeclHandler(handlerArg, prefix->name, - prefix->binding ? uri : 0); + if (attId && parser->m_startNamespaceDeclHandler) + parser->m_startNamespaceDeclHandler(parser->m_handlerArg, prefix->name, + prefix->binding ? uri : 0); return XML_ERROR_NONE; } @@ -3227,22 +3533,19 @@ addBinding(XML_Parser parser, PREFIX *prefix, const ATTRIBUTE_ID *attId, the whole file is parsed with one call. */ static enum XML_Error PTRCALL -cdataSectionProcessor(XML_Parser parser, - const char *start, - const char *end, - const char **endPtr) -{ - enum XML_Error result = doCdataSection(parser, encoding, &start, end, - endPtr, (XML_Bool)!ps_finalBuffer); +cdataSectionProcessor(XML_Parser parser, const char *start, const char *end, + const char **endPtr) { + enum XML_Error result + = doCdataSection(parser, parser->m_encoding, &start, end, endPtr, + (XML_Bool)! parser->m_parsingStatus.finalBuffer); if (result != XML_ERROR_NONE) return result; if (start) { - if (parentParser) { /* we are parsing an external entity */ - processor = externalEntityContentProcessor; + if (parser->m_parentParser) { /* we are parsing an external entity */ + parser->m_processor = externalEntityContentProcessor; return externalEntityContentProcessor(parser, start, end, endPtr); - } - else { - processor = contentProcessor; + } else { + parser->m_processor = contentProcessor; return contentProcessor(parser, start, end, endPtr); } } @@ -3253,24 +3556,18 @@ cdataSectionProcessor(XML_Parser parser, the section is not yet closed. */ static enum XML_Error -doCdataSection(XML_Parser parser, - const ENCODING *enc, - const char **startPtr, - const char *end, - const char **nextPtr, - XML_Bool haveMore) -{ +doCdataSection(XML_Parser parser, const ENCODING *enc, const char **startPtr, + const char *end, const char **nextPtr, XML_Bool haveMore) { const char *s = *startPtr; const char **eventPP; const char **eventEndPP; - if (enc == encoding) { - eventPP = &eventPtr; + if (enc == parser->m_encoding) { + eventPP = &parser->m_eventPtr; *eventPP = s; - eventEndPP = &eventEndPtr; - } - else { - eventPP = &(openInternalEntities->internalEventPtr); - eventEndPP = &(openInternalEntities->internalEventEndPtr); + eventEndPP = &parser->m_eventEndPtr; + } else { + eventPP = &(parser->m_openInternalEntities->internalEventPtr); + eventEndPP = &(parser->m_openInternalEntities->internalEventEndPtr); } *eventPP = s; *startPtr = NULL; @@ -3281,54 +3578,51 @@ doCdataSection(XML_Parser parser, *eventEndPP = next; switch (tok) { case XML_TOK_CDATA_SECT_CLOSE: - if (endCdataSectionHandler) - endCdataSectionHandler(handlerArg); -#if 0 + if (parser->m_endCdataSectionHandler) + parser->m_endCdataSectionHandler(parser->m_handlerArg); + /* BEGIN disabled code */ /* see comment under XML_TOK_CDATA_SECT_OPEN */ - else if (characterDataHandler) - characterDataHandler(handlerArg, dataBuf, 0); -#endif - else if (defaultHandler) + else if (0 && parser->m_characterDataHandler) + parser->m_characterDataHandler(parser->m_handlerArg, parser->m_dataBuf, + 0); + /* END disabled code */ + else if (parser->m_defaultHandler) reportDefault(parser, enc, s, next); *startPtr = next; *nextPtr = next; - if (ps_parsing == XML_FINISHED) + if (parser->m_parsingStatus.parsing == XML_FINISHED) return XML_ERROR_ABORTED; else return XML_ERROR_NONE; case XML_TOK_DATA_NEWLINE: - if (characterDataHandler) { + if (parser->m_characterDataHandler) { XML_Char c = 0xA; - characterDataHandler(handlerArg, &c, 1); - } - else if (defaultHandler) + parser->m_characterDataHandler(parser->m_handlerArg, &c, 1); + } else if (parser->m_defaultHandler) reportDefault(parser, enc, s, next); break; - case XML_TOK_DATA_CHARS: - { - XML_CharacterDataHandler charDataHandler = characterDataHandler; - if (charDataHandler) { - if (MUST_CONVERT(enc, s)) { - for (;;) { - ICHAR *dataPtr = (ICHAR *)dataBuf; - const enum XML_Convert_Result convert_res = XmlConvert(enc, &s, next, &dataPtr, (ICHAR *)dataBufEnd); - *eventEndPP = next; - charDataHandler(handlerArg, dataBuf, - (int)(dataPtr - (ICHAR *)dataBuf)); - if ((convert_res == XML_CONVERT_COMPLETED) || (convert_res == XML_CONVERT_INPUT_INCOMPLETE)) - break; - *eventPP = s; - } + case XML_TOK_DATA_CHARS: { + XML_CharacterDataHandler charDataHandler = parser->m_characterDataHandler; + if (charDataHandler) { + if (MUST_CONVERT(enc, s)) { + for (;;) { + ICHAR *dataPtr = (ICHAR *)parser->m_dataBuf; + const enum XML_Convert_Result convert_res = XmlConvert( + enc, &s, next, &dataPtr, (ICHAR *)parser->m_dataBufEnd); + *eventEndPP = next; + charDataHandler(parser->m_handlerArg, parser->m_dataBuf, + (int)(dataPtr - (ICHAR *)parser->m_dataBuf)); + if ((convert_res == XML_CONVERT_COMPLETED) + || (convert_res == XML_CONVERT_INPUT_INCOMPLETE)) + break; + *eventPP = s; } - else - charDataHandler(handlerArg, - (XML_Char *)s, - (int)((XML_Char *)next - (XML_Char *)s)); - } - else if (defaultHandler) - reportDefault(parser, enc, s, next); - } - break; + } else + charDataHandler(parser->m_handlerArg, (XML_Char *)s, + (int)((XML_Char *)next - (XML_Char *)s)); + } else if (parser->m_defaultHandler) + reportDefault(parser, enc, s, next); + } break; case XML_TOK_INVALID: *eventPP = next; return XML_ERROR_INVALID_TOKEN; @@ -3346,18 +3640,26 @@ doCdataSection(XML_Parser parser, } return XML_ERROR_UNCLOSED_CDATA_SECTION; default: + /* Every token returned by XmlCdataSectionTok() has its own + * explicit case, so this default case will never be executed. + * We retain it as a safety net and exclude it from the coverage + * statistics. + * + * LCOV_EXCL_START + */ *eventPP = next; return XML_ERROR_UNEXPECTED_STATE; + /* LCOV_EXCL_STOP */ } *eventPP = s = next; - switch (ps_parsing) { + switch (parser->m_parsingStatus.parsing) { case XML_SUSPENDED: *nextPtr = next; return XML_ERROR_NONE; case XML_FINISHED: return XML_ERROR_ABORTED; - default: ; + default:; } } /* not reached */ @@ -3369,17 +3671,15 @@ doCdataSection(XML_Parser parser, the whole file is parsed with one call. */ static enum XML_Error PTRCALL -ignoreSectionProcessor(XML_Parser parser, - const char *start, - const char *end, - const char **endPtr) -{ - enum XML_Error result = doIgnoreSection(parser, encoding, &start, end, - endPtr, (XML_Bool)!ps_finalBuffer); +ignoreSectionProcessor(XML_Parser parser, const char *start, const char *end, + const char **endPtr) { + enum XML_Error result + = doIgnoreSection(parser, parser->m_encoding, &start, end, endPtr, + (XML_Bool)! parser->m_parsingStatus.finalBuffer); if (result != XML_ERROR_NONE) return result; if (start) { - processor = prologProcessor; + parser->m_processor = prologProcessor; return prologProcessor(parser, start, end, endPtr); } return result; @@ -3389,26 +3689,32 @@ ignoreSectionProcessor(XML_Parser parser, if the section is not yet closed. */ static enum XML_Error -doIgnoreSection(XML_Parser parser, - const ENCODING *enc, - const char **startPtr, - const char *end, - const char **nextPtr, - XML_Bool haveMore) -{ +doIgnoreSection(XML_Parser parser, const ENCODING *enc, const char **startPtr, + const char *end, const char **nextPtr, XML_Bool haveMore) { const char *next; int tok; const char *s = *startPtr; const char **eventPP; const char **eventEndPP; - if (enc == encoding) { - eventPP = &eventPtr; + if (enc == parser->m_encoding) { + eventPP = &parser->m_eventPtr; *eventPP = s; - eventEndPP = &eventEndPtr; - } - else { - eventPP = &(openInternalEntities->internalEventPtr); - eventEndPP = &(openInternalEntities->internalEventEndPtr); + eventEndPP = &parser->m_eventEndPtr; + } else { + /* It's not entirely clear, but it seems the following two lines + * of code cannot be executed. The only occasions on which 'enc' + * is not 'encoding' are when this function is called + * from the internal entity processing, and IGNORE sections are an + * error in internal entities. + * + * Since it really isn't clear that this is true, we keep the code + * and just remove it from our coverage tests. + * + * LCOV_EXCL_START + */ + eventPP = &(parser->m_openInternalEntities->internalEventPtr); + eventEndPP = &(parser->m_openInternalEntities->internalEventEndPtr); + /* LCOV_EXCL_STOP */ } *eventPP = s; *startPtr = NULL; @@ -3416,11 +3722,11 @@ doIgnoreSection(XML_Parser parser, *eventEndPP = next; switch (tok) { case XML_TOK_IGNORE_SECT: - if (defaultHandler) + if (parser->m_defaultHandler) reportDefault(parser, enc, s, next); *startPtr = next; *nextPtr = next; - if (ps_parsing == XML_FINISHED) + if (parser->m_parsingStatus.parsing == XML_FINISHED) return XML_ERROR_ABORTED; else return XML_ERROR_NONE; @@ -3441,8 +3747,16 @@ doIgnoreSection(XML_Parser parser, } return XML_ERROR_SYNTAX; /* XML_ERROR_UNCLOSED_IGNORE_SECTION */ default: + /* All of the tokens that XmlIgnoreSectionTok() returns have + * explicit cases to handle them, so this default case is never + * executed. We keep it as a safety net anyway, and remove it + * from our test coverage statistics. + * + * LCOV_EXCL_START + */ *eventPP = next; return XML_ERROR_UNEXPECTED_STATE; + /* LCOV_EXCL_STOP */ } /* not reached */ } @@ -3450,38 +3764,38 @@ doIgnoreSection(XML_Parser parser, #endif /* XML_DTD */ static enum XML_Error -initializeEncoding(XML_Parser parser) -{ +initializeEncoding(XML_Parser parser) { const char *s; #ifdef XML_UNICODE char encodingBuf[128]; - if (!protocolEncodingName) + /* See comments abount `protoclEncodingName` in parserInit() */ + if (! parser->m_protocolEncodingName) s = NULL; else { int i; - for (i = 0; protocolEncodingName[i]; i++) { + for (i = 0; parser->m_protocolEncodingName[i]; i++) { if (i == sizeof(encodingBuf) - 1 - || (protocolEncodingName[i] & ~0x7f) != 0) { + || (parser->m_protocolEncodingName[i] & ~0x7f) != 0) { encodingBuf[0] = '\0'; break; } - encodingBuf[i] = (char)protocolEncodingName[i]; + encodingBuf[i] = (char)parser->m_protocolEncodingName[i]; } encodingBuf[i] = '\0'; s = encodingBuf; } #else - s = protocolEncodingName; + s = parser->m_protocolEncodingName; #endif - if ((ns ? XmlInitEncodingNS : XmlInitEncoding)(&initEncoding, &encoding, s)) + if ((parser->m_ns ? XmlInitEncodingNS : XmlInitEncoding)( + &parser->m_initEncoding, &parser->m_encoding, s)) return XML_ERROR_NONE; - return handleUnknownEncoding(parser, protocolEncodingName); + return handleUnknownEncoding(parser, parser->m_protocolEncodingName); } static enum XML_Error -processXmlDecl(XML_Parser parser, int isGeneralTextEntity, - const char *s, const char *next) -{ +processXmlDecl(XML_Parser parser, int isGeneralTextEntity, const char *s, + const char *next) { const char *encodingName = NULL; const XML_Char *storedEncName = NULL; const ENCODING *newEncoding = NULL; @@ -3489,88 +3803,82 @@ processXmlDecl(XML_Parser parser, int isGeneralTextEntity, const char *versionend; const XML_Char *storedversion = NULL; int standalone = -1; - if (!(ns - ? XmlParseXmlDeclNS - : XmlParseXmlDecl)(isGeneralTextEntity, - encoding, - s, - next, - &eventPtr, - &version, - &versionend, - &encodingName, - &newEncoding, - &standalone)) { + if (! (parser->m_ns ? XmlParseXmlDeclNS : XmlParseXmlDecl)( + isGeneralTextEntity, parser->m_encoding, s, next, &parser->m_eventPtr, + &version, &versionend, &encodingName, &newEncoding, &standalone)) { if (isGeneralTextEntity) return XML_ERROR_TEXT_DECL; else return XML_ERROR_XML_DECL; } - if (!isGeneralTextEntity && standalone == 1) { - _dtd->standalone = XML_TRUE; + if (! isGeneralTextEntity && standalone == 1) { + parser->m_dtd->standalone = XML_TRUE; #ifdef XML_DTD - if (paramEntityParsing == XML_PARAM_ENTITY_PARSING_UNLESS_STANDALONE) - paramEntityParsing = XML_PARAM_ENTITY_PARSING_NEVER; + if (parser->m_paramEntityParsing + == XML_PARAM_ENTITY_PARSING_UNLESS_STANDALONE) + parser->m_paramEntityParsing = XML_PARAM_ENTITY_PARSING_NEVER; #endif /* XML_DTD */ } - if (xmlDeclHandler) { + if (parser->m_xmlDeclHandler) { if (encodingName != NULL) { - storedEncName = poolStoreString(&temp2Pool, - encoding, - encodingName, - encodingName - + XmlNameLength(encoding, encodingName)); - if (!storedEncName) - return XML_ERROR_NO_MEMORY; - poolFinish(&temp2Pool); + storedEncName = poolStoreString( + &parser->m_temp2Pool, parser->m_encoding, encodingName, + encodingName + XmlNameLength(parser->m_encoding, encodingName)); + if (! storedEncName) + return XML_ERROR_NO_MEMORY; + poolFinish(&parser->m_temp2Pool); } if (version) { - storedversion = poolStoreString(&temp2Pool, - encoding, - version, - versionend - encoding->minBytesPerChar); - if (!storedversion) + storedversion + = poolStoreString(&parser->m_temp2Pool, parser->m_encoding, version, + versionend - parser->m_encoding->minBytesPerChar); + if (! storedversion) return XML_ERROR_NO_MEMORY; } - xmlDeclHandler(handlerArg, storedversion, storedEncName, standalone); - } - else if (defaultHandler) - reportDefault(parser, encoding, s, next); - if (protocolEncodingName == NULL) { + parser->m_xmlDeclHandler(parser->m_handlerArg, storedversion, storedEncName, + standalone); + } else if (parser->m_defaultHandler) + reportDefault(parser, parser->m_encoding, s, next); + if (parser->m_protocolEncodingName == NULL) { if (newEncoding) { - if (newEncoding->minBytesPerChar != encoding->minBytesPerChar) { - eventPtr = encodingName; + /* Check that the specified encoding does not conflict with what + * the parser has already deduced. Do we have the same number + * of bytes in the smallest representation of a character? If + * this is UTF-16, is it the same endianness? + */ + if (newEncoding->minBytesPerChar != parser->m_encoding->minBytesPerChar + || (newEncoding->minBytesPerChar == 2 + && newEncoding != parser->m_encoding)) { + parser->m_eventPtr = encodingName; return XML_ERROR_INCORRECT_ENCODING; } - encoding = newEncoding; - } - else if (encodingName) { + parser->m_encoding = newEncoding; + } else if (encodingName) { enum XML_Error result; - if (!storedEncName) { + if (! storedEncName) { storedEncName = poolStoreString( - &temp2Pool, encoding, encodingName, - encodingName + XmlNameLength(encoding, encodingName)); - if (!storedEncName) + &parser->m_temp2Pool, parser->m_encoding, encodingName, + encodingName + XmlNameLength(parser->m_encoding, encodingName)); + if (! storedEncName) return XML_ERROR_NO_MEMORY; } result = handleUnknownEncoding(parser, storedEncName); - poolClear(&temp2Pool); + poolClear(&parser->m_temp2Pool); if (result == XML_ERROR_UNKNOWN_ENCODING) - eventPtr = encodingName; + parser->m_eventPtr = encodingName; return result; } } if (storedEncName || storedversion) - poolClear(&temp2Pool); + poolClear(&parser->m_temp2Pool); return XML_ERROR_NONE; } static enum XML_Error -handleUnknownEncoding(XML_Parser parser, const XML_Char *encodingName) -{ - if (unknownEncodingHandler) { +handleUnknownEncoding(XML_Parser parser, const XML_Char *encodingName) { + if (parser->m_unknownEncodingHandler) { XML_Encoding info; int i; for (i = 0; i < 256; i++) @@ -3578,25 +3886,21 @@ handleUnknownEncoding(XML_Parser parser, const XML_Char *encodingName) info.convert = NULL; info.data = NULL; info.release = NULL; - if (unknownEncodingHandler(unknownEncodingHandlerData, encodingName, - &info)) { + if (parser->m_unknownEncodingHandler(parser->m_unknownEncodingHandlerData, + encodingName, &info)) { ENCODING *enc; - unknownEncodingMem = MALLOC(XmlSizeOfUnknownEncoding()); - if (!unknownEncodingMem) { + parser->m_unknownEncodingMem = MALLOC(parser, XmlSizeOfUnknownEncoding()); + if (! parser->m_unknownEncodingMem) { if (info.release) info.release(info.data); return XML_ERROR_NO_MEMORY; } - enc = (ns - ? XmlInitUnknownEncodingNS - : XmlInitUnknownEncoding)(unknownEncodingMem, - info.map, - info.convert, - info.data); + enc = (parser->m_ns ? XmlInitUnknownEncodingNS : XmlInitUnknownEncoding)( + parser->m_unknownEncodingMem, info.map, info.convert, info.data); if (enc) { - unknownEncodingData = info.data; - unknownEncodingRelease = info.release; - encoding = enc; + parser->m_unknownEncodingData = info.data; + parser->m_unknownEncodingRelease = info.release; + parser->m_encoding = enc; return XML_ERROR_NONE; } } @@ -3607,60 +3911,50 @@ handleUnknownEncoding(XML_Parser parser, const XML_Char *encodingName) } static enum XML_Error PTRCALL -prologInitProcessor(XML_Parser parser, - const char *s, - const char *end, - const char **nextPtr) -{ +prologInitProcessor(XML_Parser parser, const char *s, const char *end, + const char **nextPtr) { enum XML_Error result = initializeEncoding(parser); if (result != XML_ERROR_NONE) return result; - processor = prologProcessor; + parser->m_processor = prologProcessor; return prologProcessor(parser, s, end, nextPtr); } #ifdef XML_DTD static enum XML_Error PTRCALL -externalParEntInitProcessor(XML_Parser parser, - const char *s, - const char *end, - const char **nextPtr) -{ +externalParEntInitProcessor(XML_Parser parser, const char *s, const char *end, + const char **nextPtr) { enum XML_Error result = initializeEncoding(parser); if (result != XML_ERROR_NONE) return result; /* we know now that XML_Parse(Buffer) has been called, so we consider the external parameter entity read */ - _dtd->paramEntityRead = XML_TRUE; + parser->m_dtd->paramEntityRead = XML_TRUE; - if (prologState.inEntityValue) { - processor = entityValueInitProcessor; + if (parser->m_prologState.inEntityValue) { + parser->m_processor = entityValueInitProcessor; return entityValueInitProcessor(parser, s, end, nextPtr); - } - else { - processor = externalParEntProcessor; + } else { + parser->m_processor = externalParEntProcessor; return externalParEntProcessor(parser, s, end, nextPtr); } } static enum XML_Error PTRCALL -entityValueInitProcessor(XML_Parser parser, - const char *s, - const char *end, - const char **nextPtr) -{ +entityValueInitProcessor(XML_Parser parser, const char *s, const char *end, + const char **nextPtr) { int tok; const char *start = s; const char *next = start; - eventPtr = start; + parser->m_eventPtr = start; for (;;) { - tok = XmlPrologTok(encoding, start, end, &next); - eventEndPtr = next; + tok = XmlPrologTok(parser->m_encoding, start, end, &next); + parser->m_eventEndPtr = next; if (tok <= 0) { - if (!ps_finalBuffer && tok != XML_TOK_INVALID) { + if (! parser->m_parsingStatus.finalBuffer && tok != XML_TOK_INVALID) { *nextPtr = s; return XML_ERROR_NONE; } @@ -3671,29 +3965,27 @@ entityValueInitProcessor(XML_Parser parser, return XML_ERROR_UNCLOSED_TOKEN; case XML_TOK_PARTIAL_CHAR: return XML_ERROR_PARTIAL_CHAR; - case XML_TOK_NONE: /* start == end */ + case XML_TOK_NONE: /* start == end */ default: break; } /* found end of entity value - can store it now */ - return storeEntityValue(parser, encoding, s, end); - } - else if (tok == XML_TOK_XML_DECL) { + return storeEntityValue(parser, parser->m_encoding, s, end); + } else if (tok == XML_TOK_XML_DECL) { enum XML_Error result; result = processXmlDecl(parser, 0, start, next); if (result != XML_ERROR_NONE) return result; - switch (ps_parsing) { - case XML_SUSPENDED: - *nextPtr = next; - return XML_ERROR_NONE; - case XML_FINISHED: + /* At this point, m_parsingStatus.parsing cannot be XML_SUSPENDED. For + * that to happen, a parameter entity parsing handler must have attempted + * to suspend the parser, which fails and raises an error. The parser can + * be aborted, but can't be suspended. + */ + if (parser->m_parsingStatus.parsing == XML_FINISHED) return XML_ERROR_ABORTED; - default: - *nextPtr = next; - } + *nextPtr = next; /* stop scanning for text declaration - we found one */ - processor = entityValueProcessor; + parser->m_processor = entityValueProcessor; return entityValueProcessor(parser, next, end, nextPtr); } /* If we are at the end of the buffer, this would cause XmlPrologTok to @@ -3703,27 +3995,33 @@ entityValueInitProcessor(XML_Parser parser, then, when this routine is entered the next time, XmlPrologTok will return XML_TOK_INVALID, since the BOM is still in the buffer */ - else if (tok == XML_TOK_BOM && next == end && !ps_finalBuffer) { + else if (tok == XML_TOK_BOM && next == end + && ! parser->m_parsingStatus.finalBuffer) { *nextPtr = next; return XML_ERROR_NONE; } + /* If we get this token, we have the start of what might be a + normal tag, but not a declaration (i.e. it doesn't begin with + "<!"). In a DTD context, that isn't legal. + */ + else if (tok == XML_TOK_INSTANCE_START) { + *nextPtr = next; + return XML_ERROR_SYNTAX; + } start = next; - eventPtr = start; + parser->m_eventPtr = start; } } static enum XML_Error PTRCALL -externalParEntProcessor(XML_Parser parser, - const char *s, - const char *end, - const char **nextPtr) -{ +externalParEntProcessor(XML_Parser parser, const char *s, const char *end, + const char **nextPtr) { const char *next = s; int tok; - tok = XmlPrologTok(encoding, s, end, &next); + tok = XmlPrologTok(parser->m_encoding, s, end, &next); if (tok <= 0) { - if (!ps_finalBuffer && tok != XML_TOK_INVALID) { + if (! parser->m_parsingStatus.finalBuffer && tok != XML_TOK_INVALID) { *nextPtr = s; return XML_ERROR_NONE; } @@ -3734,7 +4032,7 @@ externalParEntProcessor(XML_Parser parser, return XML_ERROR_UNCLOSED_TOKEN; case XML_TOK_PARTIAL_CHAR: return XML_ERROR_PARTIAL_CHAR; - case XML_TOK_NONE: /* start == end */ + case XML_TOK_NONE: /* start == end */ default: break; } @@ -3745,29 +4043,26 @@ externalParEntProcessor(XML_Parser parser, */ else if (tok == XML_TOK_BOM) { s = next; - tok = XmlPrologTok(encoding, s, end, &next); + tok = XmlPrologTok(parser->m_encoding, s, end, &next); } - processor = prologProcessor; - return doProlog(parser, encoding, s, end, tok, next, - nextPtr, (XML_Bool)!ps_finalBuffer); + parser->m_processor = prologProcessor; + return doProlog(parser, parser->m_encoding, s, end, tok, next, nextPtr, + (XML_Bool)! parser->m_parsingStatus.finalBuffer, XML_TRUE); } static enum XML_Error PTRCALL -entityValueProcessor(XML_Parser parser, - const char *s, - const char *end, - const char **nextPtr) -{ +entityValueProcessor(XML_Parser parser, const char *s, const char *end, + const char **nextPtr) { const char *start = s; const char *next = s; - const ENCODING *enc = encoding; + const ENCODING *enc = parser->m_encoding; int tok; for (;;) { tok = XmlPrologTok(enc, start, end, &next); if (tok <= 0) { - if (!ps_finalBuffer && tok != XML_TOK_INVALID) { + if (! parser->m_parsingStatus.finalBuffer && tok != XML_TOK_INVALID) { *nextPtr = s; return XML_ERROR_NONE; } @@ -3778,7 +4073,7 @@ entityValueProcessor(XML_Parser parser, return XML_ERROR_UNCLOSED_TOKEN; case XML_TOK_PARTIAL_CHAR: return XML_ERROR_PARTIAL_CHAR; - case XML_TOK_NONE: /* start == end */ + case XML_TOK_NONE: /* start == end */ default: break; } @@ -3792,64 +4087,57 @@ entityValueProcessor(XML_Parser parser, #endif /* XML_DTD */ static enum XML_Error PTRCALL -prologProcessor(XML_Parser parser, - const char *s, - const char *end, - const char **nextPtr) -{ +prologProcessor(XML_Parser parser, const char *s, const char *end, + const char **nextPtr) { const char *next = s; - int tok = XmlPrologTok(encoding, s, end, &next); - return doProlog(parser, encoding, s, end, tok, next, - nextPtr, (XML_Bool)!ps_finalBuffer); + int tok = XmlPrologTok(parser->m_encoding, s, end, &next); + return doProlog(parser, parser->m_encoding, s, end, tok, next, nextPtr, + (XML_Bool)! parser->m_parsingStatus.finalBuffer, XML_TRUE); } static enum XML_Error -doProlog(XML_Parser parser, - const ENCODING *enc, - const char *s, - const char *end, - int tok, - const char *next, - const char **nextPtr, - XML_Bool haveMore) -{ +doProlog(XML_Parser parser, const ENCODING *enc, const char *s, const char *end, + int tok, const char *next, const char **nextPtr, XML_Bool haveMore, + XML_Bool allowClosingDoctype) { #ifdef XML_DTD - static const XML_Char externalSubsetName[] = { ASCII_HASH , '\0' }; + static const XML_Char externalSubsetName[] = {ASCII_HASH, '\0'}; #endif /* XML_DTD */ - static const XML_Char atypeCDATA[] = - { ASCII_C, ASCII_D, ASCII_A, ASCII_T, ASCII_A, '\0' }; - static const XML_Char atypeID[] = { ASCII_I, ASCII_D, '\0' }; - static const XML_Char atypeIDREF[] = - { ASCII_I, ASCII_D, ASCII_R, ASCII_E, ASCII_F, '\0' }; - static const XML_Char atypeIDREFS[] = - { ASCII_I, ASCII_D, ASCII_R, ASCII_E, ASCII_F, ASCII_S, '\0' }; - static const XML_Char atypeENTITY[] = - { ASCII_E, ASCII_N, ASCII_T, ASCII_I, ASCII_T, ASCII_Y, '\0' }; - static const XML_Char atypeENTITIES[] = { ASCII_E, ASCII_N, - ASCII_T, ASCII_I, ASCII_T, ASCII_I, ASCII_E, ASCII_S, '\0' }; - static const XML_Char atypeNMTOKEN[] = { - ASCII_N, ASCII_M, ASCII_T, ASCII_O, ASCII_K, ASCII_E, ASCII_N, '\0' }; - static const XML_Char atypeNMTOKENS[] = { ASCII_N, ASCII_M, ASCII_T, - ASCII_O, ASCII_K, ASCII_E, ASCII_N, ASCII_S, '\0' }; - static const XML_Char notationPrefix[] = { ASCII_N, ASCII_O, ASCII_T, - ASCII_A, ASCII_T, ASCII_I, ASCII_O, ASCII_N, ASCII_LPAREN, '\0' }; - static const XML_Char enumValueSep[] = { ASCII_PIPE, '\0' }; - static const XML_Char enumValueStart[] = { ASCII_LPAREN, '\0' }; + static const XML_Char atypeCDATA[] + = {ASCII_C, ASCII_D, ASCII_A, ASCII_T, ASCII_A, '\0'}; + static const XML_Char atypeID[] = {ASCII_I, ASCII_D, '\0'}; + static const XML_Char atypeIDREF[] + = {ASCII_I, ASCII_D, ASCII_R, ASCII_E, ASCII_F, '\0'}; + static const XML_Char atypeIDREFS[] + = {ASCII_I, ASCII_D, ASCII_R, ASCII_E, ASCII_F, ASCII_S, '\0'}; + static const XML_Char atypeENTITY[] + = {ASCII_E, ASCII_N, ASCII_T, ASCII_I, ASCII_T, ASCII_Y, '\0'}; + static const XML_Char atypeENTITIES[] + = {ASCII_E, ASCII_N, ASCII_T, ASCII_I, ASCII_T, + ASCII_I, ASCII_E, ASCII_S, '\0'}; + static const XML_Char atypeNMTOKEN[] + = {ASCII_N, ASCII_M, ASCII_T, ASCII_O, ASCII_K, ASCII_E, ASCII_N, '\0'}; + static const XML_Char atypeNMTOKENS[] + = {ASCII_N, ASCII_M, ASCII_T, ASCII_O, ASCII_K, + ASCII_E, ASCII_N, ASCII_S, '\0'}; + static const XML_Char notationPrefix[] + = {ASCII_N, ASCII_O, ASCII_T, ASCII_A, ASCII_T, + ASCII_I, ASCII_O, ASCII_N, ASCII_LPAREN, '\0'}; + static const XML_Char enumValueSep[] = {ASCII_PIPE, '\0'}; + static const XML_Char enumValueStart[] = {ASCII_LPAREN, '\0'}; /* save one level of indirection */ - DTD * const dtd = _dtd; + DTD *const dtd = parser->m_dtd; const char **eventPP; const char **eventEndPP; enum XML_Content_Quant quant; - if (enc == encoding) { - eventPP = &eventPtr; - eventEndPP = &eventEndPtr; - } - else { - eventPP = &(openInternalEntities->internalEventPtr); - eventEndPP = &(openInternalEntities->internalEventEndPtr); + if (enc == parser->m_encoding) { + eventPP = &parser->m_eventPtr; + eventEndPP = &parser->m_eventEndPtr; + } else { + eventPP = &(parser->m_openInternalEntities->internalEventPtr); + eventEndPP = &(parser->m_openInternalEntities->internalEventEndPtr); } for (;;) { @@ -3876,7 +4164,8 @@ doProlog(XML_Parser parser, case XML_TOK_NONE: #ifdef XML_DTD /* for internal PE NOT referenced between declarations */ - if (enc != encoding && !openInternalEntities->betweenDecl) { + if (enc != parser->m_encoding + && ! parser->m_openInternalEntities->betweenDecl) { *nextPtr = s; return XML_ERROR_NONE; } @@ -3884,8 +4173,8 @@ doProlog(XML_Parser parser, complete markup, not only for external PEs, but also for internal PEs if the reference occurs between declarations. */ - if (isParamEntity || enc != encoding) { - if (XmlTokenRole(&prologState, XML_TOK_NONE, end, end, enc) + if (parser->m_isParamEntity || enc != parser->m_encoding) { + if (XmlTokenRole(&parser->m_prologState, XML_TOK_NONE, end, end, enc) == XML_ROLE_ERROR) return XML_ERROR_INCOMPLETE_PE; *nextPtr = s; @@ -3899,142 +4188,148 @@ doProlog(XML_Parser parser, break; } } - role = XmlTokenRole(&prologState, tok, s, next, enc); + role = XmlTokenRole(&parser->m_prologState, tok, s, next, enc); switch (role) { - case XML_ROLE_XML_DECL: - { - enum XML_Error result = processXmlDecl(parser, 0, s, next); - if (result != XML_ERROR_NONE) - return result; - enc = encoding; - handleDefault = XML_FALSE; - } - break; + case XML_ROLE_XML_DECL: { + enum XML_Error result = processXmlDecl(parser, 0, s, next); + if (result != XML_ERROR_NONE) + return result; + enc = parser->m_encoding; + handleDefault = XML_FALSE; + } break; case XML_ROLE_DOCTYPE_NAME: - if (startDoctypeDeclHandler) { - doctypeName = poolStoreString(&tempPool, enc, s, next); - if (!doctypeName) + if (parser->m_startDoctypeDeclHandler) { + parser->m_doctypeName + = poolStoreString(&parser->m_tempPool, enc, s, next); + if (! parser->m_doctypeName) return XML_ERROR_NO_MEMORY; - poolFinish(&tempPool); - doctypePubid = NULL; + poolFinish(&parser->m_tempPool); + parser->m_doctypePubid = NULL; handleDefault = XML_FALSE; } - doctypeSysid = NULL; /* always initialize to NULL */ + parser->m_doctypeSysid = NULL; /* always initialize to NULL */ break; case XML_ROLE_DOCTYPE_INTERNAL_SUBSET: - if (startDoctypeDeclHandler) { - startDoctypeDeclHandler(handlerArg, doctypeName, doctypeSysid, - doctypePubid, 1); - doctypeName = NULL; - poolClear(&tempPool); + if (parser->m_startDoctypeDeclHandler) { + parser->m_startDoctypeDeclHandler( + parser->m_handlerArg, parser->m_doctypeName, parser->m_doctypeSysid, + parser->m_doctypePubid, 1); + parser->m_doctypeName = NULL; + poolClear(&parser->m_tempPool); handleDefault = XML_FALSE; } break; #ifdef XML_DTD - case XML_ROLE_TEXT_DECL: - { - enum XML_Error result = processXmlDecl(parser, 1, s, next); - if (result != XML_ERROR_NONE) - return result; - enc = encoding; - handleDefault = XML_FALSE; - } - break; + case XML_ROLE_TEXT_DECL: { + enum XML_Error result = processXmlDecl(parser, 1, s, next); + if (result != XML_ERROR_NONE) + return result; + enc = parser->m_encoding; + handleDefault = XML_FALSE; + } break; #endif /* XML_DTD */ case XML_ROLE_DOCTYPE_PUBLIC_ID: #ifdef XML_DTD - useForeignDTD = XML_FALSE; - declEntity = (ENTITY *)lookup(parser, - &dtd->paramEntities, - externalSubsetName, - sizeof(ENTITY)); - if (!declEntity) + parser->m_useForeignDTD = XML_FALSE; + parser->m_declEntity = (ENTITY *)lookup( + parser, &dtd->paramEntities, externalSubsetName, sizeof(ENTITY)); + if (! parser->m_declEntity) return XML_ERROR_NO_MEMORY; #endif /* XML_DTD */ dtd->hasParamEntityRefs = XML_TRUE; - if (startDoctypeDeclHandler) { + if (parser->m_startDoctypeDeclHandler) { XML_Char *pubId; - if (!XmlIsPublicId(enc, s, next, eventPP)) + if (! XmlIsPublicId(enc, s, next, eventPP)) return XML_ERROR_PUBLICID; - pubId = poolStoreString(&tempPool, enc, + pubId = poolStoreString(&parser->m_tempPool, enc, s + enc->minBytesPerChar, next - enc->minBytesPerChar); - if (!pubId) + if (! pubId) return XML_ERROR_NO_MEMORY; normalizePublicId(pubId); - poolFinish(&tempPool); - doctypePubid = pubId; + poolFinish(&parser->m_tempPool); + parser->m_doctypePubid = pubId; handleDefault = XML_FALSE; goto alreadyChecked; } /* fall through */ case XML_ROLE_ENTITY_PUBLIC_ID: - if (!XmlIsPublicId(enc, s, next, eventPP)) + if (! XmlIsPublicId(enc, s, next, eventPP)) return XML_ERROR_PUBLICID; alreadyChecked: - if (dtd->keepProcessing && declEntity) { - XML_Char *tem = poolStoreString(&dtd->pool, - enc, - s + enc->minBytesPerChar, - next - enc->minBytesPerChar); - if (!tem) + if (dtd->keepProcessing && parser->m_declEntity) { + XML_Char *tem + = poolStoreString(&dtd->pool, enc, s + enc->minBytesPerChar, + next - enc->minBytesPerChar); + if (! tem) return XML_ERROR_NO_MEMORY; normalizePublicId(tem); - declEntity->publicId = tem; + parser->m_declEntity->publicId = tem; poolFinish(&dtd->pool); - if (entityDeclHandler) + /* Don't suppress the default handler if we fell through from + * the XML_ROLE_DOCTYPE_PUBLIC_ID case. + */ + if (parser->m_entityDeclHandler && role == XML_ROLE_ENTITY_PUBLIC_ID) handleDefault = XML_FALSE; } break; case XML_ROLE_DOCTYPE_CLOSE: - if (doctypeName) { - startDoctypeDeclHandler(handlerArg, doctypeName, - doctypeSysid, doctypePubid, 0); - poolClear(&tempPool); + if (allowClosingDoctype != XML_TRUE) { + /* Must not close doctype from within expanded parameter entities */ + return XML_ERROR_INVALID_TOKEN; + } + + if (parser->m_doctypeName) { + parser->m_startDoctypeDeclHandler( + parser->m_handlerArg, parser->m_doctypeName, parser->m_doctypeSysid, + parser->m_doctypePubid, 0); + poolClear(&parser->m_tempPool); handleDefault = XML_FALSE; } - /* doctypeSysid will be non-NULL in the case of a previous - XML_ROLE_DOCTYPE_SYSTEM_ID, even if startDoctypeDeclHandler + /* parser->m_doctypeSysid will be non-NULL in the case of a previous + XML_ROLE_DOCTYPE_SYSTEM_ID, even if parser->m_startDoctypeDeclHandler was not set, indicating an external subset */ #ifdef XML_DTD - if (doctypeSysid || useForeignDTD) { + if (parser->m_doctypeSysid || parser->m_useForeignDTD) { XML_Bool hadParamEntityRefs = dtd->hasParamEntityRefs; dtd->hasParamEntityRefs = XML_TRUE; - if (paramEntityParsing && externalEntityRefHandler) { - ENTITY *entity = (ENTITY *)lookup(parser, - &dtd->paramEntities, - externalSubsetName, - sizeof(ENTITY)); - if (!entity) - return XML_ERROR_NO_MEMORY; - if (useForeignDTD) - entity->base = curBase; + if (parser->m_paramEntityParsing + && parser->m_externalEntityRefHandler) { + ENTITY *entity = (ENTITY *)lookup(parser, &dtd->paramEntities, + externalSubsetName, sizeof(ENTITY)); + if (! entity) { + /* The external subset name "#" will have already been + * inserted into the hash table at the start of the + * external entity parsing, so no allocation will happen + * and lookup() cannot fail. + */ + return XML_ERROR_NO_MEMORY; /* LCOV_EXCL_LINE */ + } + if (parser->m_useForeignDTD) + entity->base = parser->m_curBase; dtd->paramEntityRead = XML_FALSE; - if (!externalEntityRefHandler(externalEntityRefHandlerArg, - 0, - entity->base, - entity->systemId, - entity->publicId)) + if (! parser->m_externalEntityRefHandler( + parser->m_externalEntityRefHandlerArg, 0, entity->base, + entity->systemId, entity->publicId)) return XML_ERROR_EXTERNAL_ENTITY_HANDLING; if (dtd->paramEntityRead) { - if (!dtd->standalone && - notStandaloneHandler && - !notStandaloneHandler(handlerArg)) + if (! dtd->standalone && parser->m_notStandaloneHandler + && ! parser->m_notStandaloneHandler(parser->m_handlerArg)) return XML_ERROR_NOT_STANDALONE; } /* if we didn't read the foreign DTD then this means that there is no external subset and we must reset dtd->hasParamEntityRefs */ - else if (!doctypeSysid) + else if (! parser->m_doctypeSysid) dtd->hasParamEntityRefs = hadParamEntityRefs; /* end of DTD - no need to update dtd->keepProcessing */ } - useForeignDTD = XML_FALSE; + parser->m_useForeignDTD = XML_FALSE; } #endif /* XML_DTD */ - if (endDoctypeDeclHandler) { - endDoctypeDeclHandler(handlerArg); + if (parser->m_endDoctypeDeclHandler) { + parser->m_endDoctypeDeclHandler(parser->m_handlerArg); handleDefault = XML_FALSE; } break; @@ -4043,27 +4338,24 @@ doProlog(XML_Parser parser, /* if there is no DOCTYPE declaration then now is the last chance to read the foreign DTD */ - if (useForeignDTD) { + if (parser->m_useForeignDTD) { XML_Bool hadParamEntityRefs = dtd->hasParamEntityRefs; dtd->hasParamEntityRefs = XML_TRUE; - if (paramEntityParsing && externalEntityRefHandler) { + if (parser->m_paramEntityParsing + && parser->m_externalEntityRefHandler) { ENTITY *entity = (ENTITY *)lookup(parser, &dtd->paramEntities, - externalSubsetName, - sizeof(ENTITY)); - if (!entity) + externalSubsetName, sizeof(ENTITY)); + if (! entity) return XML_ERROR_NO_MEMORY; - entity->base = curBase; + entity->base = parser->m_curBase; dtd->paramEntityRead = XML_FALSE; - if (!externalEntityRefHandler(externalEntityRefHandlerArg, - 0, - entity->base, - entity->systemId, - entity->publicId)) + if (! parser->m_externalEntityRefHandler( + parser->m_externalEntityRefHandlerArg, 0, entity->base, + entity->systemId, entity->publicId)) return XML_ERROR_EXTERNAL_ENTITY_HANDLING; if (dtd->paramEntityRead) { - if (!dtd->standalone && - notStandaloneHandler && - !notStandaloneHandler(handlerArg)) + if (! dtd->standalone && parser->m_notStandaloneHandler + && ! parser->m_notStandaloneHandler(parser->m_handlerArg)) return XML_ERROR_NOT_STANDALONE; } /* if we didn't read the foreign DTD then this means that there @@ -4075,93 +4367,93 @@ doProlog(XML_Parser parser, } } #endif /* XML_DTD */ - processor = contentProcessor; + parser->m_processor = contentProcessor; return contentProcessor(parser, s, end, nextPtr); case XML_ROLE_ATTLIST_ELEMENT_NAME: - declElementType = getElementType(parser, enc, s, next); - if (!declElementType) + parser->m_declElementType = getElementType(parser, enc, s, next); + if (! parser->m_declElementType) return XML_ERROR_NO_MEMORY; goto checkAttListDeclHandler; case XML_ROLE_ATTRIBUTE_NAME: - declAttributeId = getAttributeId(parser, enc, s, next); - if (!declAttributeId) + parser->m_declAttributeId = getAttributeId(parser, enc, s, next); + if (! parser->m_declAttributeId) return XML_ERROR_NO_MEMORY; - declAttributeIsCdata = XML_FALSE; - declAttributeType = NULL; - declAttributeIsId = XML_FALSE; + parser->m_declAttributeIsCdata = XML_FALSE; + parser->m_declAttributeType = NULL; + parser->m_declAttributeIsId = XML_FALSE; goto checkAttListDeclHandler; case XML_ROLE_ATTRIBUTE_TYPE_CDATA: - declAttributeIsCdata = XML_TRUE; - declAttributeType = atypeCDATA; + parser->m_declAttributeIsCdata = XML_TRUE; + parser->m_declAttributeType = atypeCDATA; goto checkAttListDeclHandler; case XML_ROLE_ATTRIBUTE_TYPE_ID: - declAttributeIsId = XML_TRUE; - declAttributeType = atypeID; + parser->m_declAttributeIsId = XML_TRUE; + parser->m_declAttributeType = atypeID; goto checkAttListDeclHandler; case XML_ROLE_ATTRIBUTE_TYPE_IDREF: - declAttributeType = atypeIDREF; + parser->m_declAttributeType = atypeIDREF; goto checkAttListDeclHandler; case XML_ROLE_ATTRIBUTE_TYPE_IDREFS: - declAttributeType = atypeIDREFS; + parser->m_declAttributeType = atypeIDREFS; goto checkAttListDeclHandler; case XML_ROLE_ATTRIBUTE_TYPE_ENTITY: - declAttributeType = atypeENTITY; + parser->m_declAttributeType = atypeENTITY; goto checkAttListDeclHandler; case XML_ROLE_ATTRIBUTE_TYPE_ENTITIES: - declAttributeType = atypeENTITIES; + parser->m_declAttributeType = atypeENTITIES; goto checkAttListDeclHandler; case XML_ROLE_ATTRIBUTE_TYPE_NMTOKEN: - declAttributeType = atypeNMTOKEN; + parser->m_declAttributeType = atypeNMTOKEN; goto checkAttListDeclHandler; case XML_ROLE_ATTRIBUTE_TYPE_NMTOKENS: - declAttributeType = atypeNMTOKENS; + parser->m_declAttributeType = atypeNMTOKENS; checkAttListDeclHandler: - if (dtd->keepProcessing && attlistDeclHandler) + if (dtd->keepProcessing && parser->m_attlistDeclHandler) handleDefault = XML_FALSE; break; case XML_ROLE_ATTRIBUTE_ENUM_VALUE: case XML_ROLE_ATTRIBUTE_NOTATION_VALUE: - if (dtd->keepProcessing && attlistDeclHandler) { + if (dtd->keepProcessing && parser->m_attlistDeclHandler) { const XML_Char *prefix; - if (declAttributeType) { + if (parser->m_declAttributeType) { prefix = enumValueSep; + } else { + prefix = (role == XML_ROLE_ATTRIBUTE_NOTATION_VALUE ? notationPrefix + : enumValueStart); } - else { - prefix = (role == XML_ROLE_ATTRIBUTE_NOTATION_VALUE - ? notationPrefix - : enumValueStart); - } - if (!poolAppendString(&tempPool, prefix)) + if (! poolAppendString(&parser->m_tempPool, prefix)) return XML_ERROR_NO_MEMORY; - if (!poolAppend(&tempPool, enc, s, next)) + if (! poolAppend(&parser->m_tempPool, enc, s, next)) return XML_ERROR_NO_MEMORY; - declAttributeType = tempPool.start; + parser->m_declAttributeType = parser->m_tempPool.start; handleDefault = XML_FALSE; } break; case XML_ROLE_IMPLIED_ATTRIBUTE_VALUE: case XML_ROLE_REQUIRED_ATTRIBUTE_VALUE: if (dtd->keepProcessing) { - if (!defineAttribute(declElementType, declAttributeId, - declAttributeIsCdata, declAttributeIsId, - 0, parser)) + if (! defineAttribute(parser->m_declElementType, + parser->m_declAttributeId, + parser->m_declAttributeIsCdata, + parser->m_declAttributeIsId, 0, parser)) return XML_ERROR_NO_MEMORY; - if (attlistDeclHandler && declAttributeType) { - if (*declAttributeType == XML_T(ASCII_LPAREN) - || (*declAttributeType == XML_T(ASCII_N) - && declAttributeType[1] == XML_T(ASCII_O))) { + if (parser->m_attlistDeclHandler && parser->m_declAttributeType) { + if (*parser->m_declAttributeType == XML_T(ASCII_LPAREN) + || (*parser->m_declAttributeType == XML_T(ASCII_N) + && parser->m_declAttributeType[1] == XML_T(ASCII_O))) { /* Enumerated or Notation type */ - if (!poolAppendChar(&tempPool, XML_T(ASCII_RPAREN)) - || !poolAppendChar(&tempPool, XML_T('\0'))) + if (! poolAppendChar(&parser->m_tempPool, XML_T(ASCII_RPAREN)) + || ! poolAppendChar(&parser->m_tempPool, XML_T('\0'))) return XML_ERROR_NO_MEMORY; - declAttributeType = tempPool.start; - poolFinish(&tempPool); + parser->m_declAttributeType = parser->m_tempPool.start; + poolFinish(&parser->m_tempPool); } *eventEndPP = s; - attlistDeclHandler(handlerArg, declElementType->name, - declAttributeId->name, declAttributeType, - 0, role == XML_ROLE_REQUIRED_ATTRIBUTE_VALUE); - poolClear(&tempPool); + parser->m_attlistDeclHandler( + parser->m_handlerArg, parser->m_declElementType->name, + parser->m_declAttributeId->name, parser->m_declAttributeType, 0, + role == XML_ROLE_REQUIRED_ATTRIBUTE_VALUE); + poolClear(&parser->m_tempPool); handleDefault = XML_FALSE; } } @@ -4170,61 +4462,57 @@ doProlog(XML_Parser parser, case XML_ROLE_FIXED_ATTRIBUTE_VALUE: if (dtd->keepProcessing) { const XML_Char *attVal; - enum XML_Error result = - storeAttributeValue(parser, enc, declAttributeIsCdata, - s + enc->minBytesPerChar, - next - enc->minBytesPerChar, - &dtd->pool); + enum XML_Error result = storeAttributeValue( + parser, enc, parser->m_declAttributeIsCdata, + s + enc->minBytesPerChar, next - enc->minBytesPerChar, &dtd->pool); if (result) return result; attVal = poolStart(&dtd->pool); poolFinish(&dtd->pool); /* ID attributes aren't allowed to have a default */ - if (!defineAttribute(declElementType, declAttributeId, - declAttributeIsCdata, XML_FALSE, attVal, parser)) + if (! defineAttribute( + parser->m_declElementType, parser->m_declAttributeId, + parser->m_declAttributeIsCdata, XML_FALSE, attVal, parser)) return XML_ERROR_NO_MEMORY; - if (attlistDeclHandler && declAttributeType) { - if (*declAttributeType == XML_T(ASCII_LPAREN) - || (*declAttributeType == XML_T(ASCII_N) - && declAttributeType[1] == XML_T(ASCII_O))) { + if (parser->m_attlistDeclHandler && parser->m_declAttributeType) { + if (*parser->m_declAttributeType == XML_T(ASCII_LPAREN) + || (*parser->m_declAttributeType == XML_T(ASCII_N) + && parser->m_declAttributeType[1] == XML_T(ASCII_O))) { /* Enumerated or Notation type */ - if (!poolAppendChar(&tempPool, XML_T(ASCII_RPAREN)) - || !poolAppendChar(&tempPool, XML_T('\0'))) + if (! poolAppendChar(&parser->m_tempPool, XML_T(ASCII_RPAREN)) + || ! poolAppendChar(&parser->m_tempPool, XML_T('\0'))) return XML_ERROR_NO_MEMORY; - declAttributeType = tempPool.start; - poolFinish(&tempPool); + parser->m_declAttributeType = parser->m_tempPool.start; + poolFinish(&parser->m_tempPool); } *eventEndPP = s; - attlistDeclHandler(handlerArg, declElementType->name, - declAttributeId->name, declAttributeType, - attVal, - role == XML_ROLE_FIXED_ATTRIBUTE_VALUE); - poolClear(&tempPool); + parser->m_attlistDeclHandler( + parser->m_handlerArg, parser->m_declElementType->name, + parser->m_declAttributeId->name, parser->m_declAttributeType, + attVal, role == XML_ROLE_FIXED_ATTRIBUTE_VALUE); + poolClear(&parser->m_tempPool); handleDefault = XML_FALSE; } } break; case XML_ROLE_ENTITY_VALUE: if (dtd->keepProcessing) { - enum XML_Error result = storeEntityValue(parser, enc, - s + enc->minBytesPerChar, - next - enc->minBytesPerChar); - if (declEntity) { - declEntity->textPtr = poolStart(&dtd->entityValuePool); - declEntity->textLen = (int)(poolLength(&dtd->entityValuePool)); + enum XML_Error result = storeEntityValue( + parser, enc, s + enc->minBytesPerChar, next - enc->minBytesPerChar); + if (parser->m_declEntity) { + parser->m_declEntity->textPtr = poolStart(&dtd->entityValuePool); + parser->m_declEntity->textLen + = (int)(poolLength(&dtd->entityValuePool)); poolFinish(&dtd->entityValuePool); - if (entityDeclHandler) { + if (parser->m_entityDeclHandler) { *eventEndPP = s; - entityDeclHandler(handlerArg, - declEntity->name, - declEntity->is_param, - declEntity->textPtr, - declEntity->textLen, - curBase, 0, 0, 0); + parser->m_entityDeclHandler( + parser->m_handlerArg, parser->m_declEntity->name, + parser->m_declEntity->is_param, parser->m_declEntity->textPtr, + parser->m_declEntity->textLen, parser->m_curBase, 0, 0, 0); handleDefault = XML_FALSE; } - } - else + } else poolDiscard(&dtd->entityValuePool); if (result != XML_ERROR_NONE) return result; @@ -4232,227 +4520,212 @@ doProlog(XML_Parser parser, break; case XML_ROLE_DOCTYPE_SYSTEM_ID: #ifdef XML_DTD - useForeignDTD = XML_FALSE; + parser->m_useForeignDTD = XML_FALSE; #endif /* XML_DTD */ dtd->hasParamEntityRefs = XML_TRUE; - if (startDoctypeDeclHandler) { - doctypeSysid = poolStoreString(&tempPool, enc, - s + enc->minBytesPerChar, - next - enc->minBytesPerChar); - if (doctypeSysid == NULL) + if (parser->m_startDoctypeDeclHandler) { + parser->m_doctypeSysid = poolStoreString(&parser->m_tempPool, enc, + s + enc->minBytesPerChar, + next - enc->minBytesPerChar); + if (parser->m_doctypeSysid == NULL) return XML_ERROR_NO_MEMORY; - poolFinish(&tempPool); + poolFinish(&parser->m_tempPool); handleDefault = XML_FALSE; } #ifdef XML_DTD else - /* use externalSubsetName to make doctypeSysid non-NULL - for the case where no startDoctypeDeclHandler is set */ - doctypeSysid = externalSubsetName; + /* use externalSubsetName to make parser->m_doctypeSysid non-NULL + for the case where no parser->m_startDoctypeDeclHandler is set */ + parser->m_doctypeSysid = externalSubsetName; #endif /* XML_DTD */ - if (!dtd->standalone + if (! dtd->standalone #ifdef XML_DTD - && !paramEntityParsing + && ! parser->m_paramEntityParsing #endif /* XML_DTD */ - && notStandaloneHandler - && !notStandaloneHandler(handlerArg)) + && parser->m_notStandaloneHandler + && ! parser->m_notStandaloneHandler(parser->m_handlerArg)) return XML_ERROR_NOT_STANDALONE; #ifndef XML_DTD break; -#else /* XML_DTD */ - if (!declEntity) { - declEntity = (ENTITY *)lookup(parser, - &dtd->paramEntities, - externalSubsetName, - sizeof(ENTITY)); - if (!declEntity) +#else /* XML_DTD */ + if (! parser->m_declEntity) { + parser->m_declEntity = (ENTITY *)lookup( + parser, &dtd->paramEntities, externalSubsetName, sizeof(ENTITY)); + if (! parser->m_declEntity) return XML_ERROR_NO_MEMORY; - declEntity->publicId = NULL; + parser->m_declEntity->publicId = NULL; } - /* fall through */ #endif /* XML_DTD */ + /* fall through */ case XML_ROLE_ENTITY_SYSTEM_ID: - if (dtd->keepProcessing && declEntity) { - declEntity->systemId = poolStoreString(&dtd->pool, enc, - s + enc->minBytesPerChar, - next - enc->minBytesPerChar); - if (!declEntity->systemId) + if (dtd->keepProcessing && parser->m_declEntity) { + parser->m_declEntity->systemId + = poolStoreString(&dtd->pool, enc, s + enc->minBytesPerChar, + next - enc->minBytesPerChar); + if (! parser->m_declEntity->systemId) return XML_ERROR_NO_MEMORY; - declEntity->base = curBase; + parser->m_declEntity->base = parser->m_curBase; poolFinish(&dtd->pool); - if (entityDeclHandler) + /* Don't suppress the default handler if we fell through from + * the XML_ROLE_DOCTYPE_SYSTEM_ID case. + */ + if (parser->m_entityDeclHandler && role == XML_ROLE_ENTITY_SYSTEM_ID) handleDefault = XML_FALSE; } break; case XML_ROLE_ENTITY_COMPLETE: - if (dtd->keepProcessing && declEntity && entityDeclHandler) { + if (dtd->keepProcessing && parser->m_declEntity + && parser->m_entityDeclHandler) { *eventEndPP = s; - entityDeclHandler(handlerArg, - declEntity->name, - declEntity->is_param, - 0,0, - declEntity->base, - declEntity->systemId, - declEntity->publicId, - 0); + parser->m_entityDeclHandler( + parser->m_handlerArg, parser->m_declEntity->name, + parser->m_declEntity->is_param, 0, 0, parser->m_declEntity->base, + parser->m_declEntity->systemId, parser->m_declEntity->publicId, 0); handleDefault = XML_FALSE; } break; case XML_ROLE_ENTITY_NOTATION_NAME: - if (dtd->keepProcessing && declEntity) { - declEntity->notation = poolStoreString(&dtd->pool, enc, s, next); - if (!declEntity->notation) + if (dtd->keepProcessing && parser->m_declEntity) { + parser->m_declEntity->notation + = poolStoreString(&dtd->pool, enc, s, next); + if (! parser->m_declEntity->notation) return XML_ERROR_NO_MEMORY; poolFinish(&dtd->pool); - if (unparsedEntityDeclHandler) { + if (parser->m_unparsedEntityDeclHandler) { *eventEndPP = s; - unparsedEntityDeclHandler(handlerArg, - declEntity->name, - declEntity->base, - declEntity->systemId, - declEntity->publicId, - declEntity->notation); + parser->m_unparsedEntityDeclHandler( + parser->m_handlerArg, parser->m_declEntity->name, + parser->m_declEntity->base, parser->m_declEntity->systemId, + parser->m_declEntity->publicId, parser->m_declEntity->notation); handleDefault = XML_FALSE; - } - else if (entityDeclHandler) { + } else if (parser->m_entityDeclHandler) { *eventEndPP = s; - entityDeclHandler(handlerArg, - declEntity->name, - 0,0,0, - declEntity->base, - declEntity->systemId, - declEntity->publicId, - declEntity->notation); + parser->m_entityDeclHandler( + parser->m_handlerArg, parser->m_declEntity->name, 0, 0, 0, + parser->m_declEntity->base, parser->m_declEntity->systemId, + parser->m_declEntity->publicId, parser->m_declEntity->notation); handleDefault = XML_FALSE; } } break; - case XML_ROLE_GENERAL_ENTITY_NAME: - { - if (XmlPredefinedEntityName(enc, s, next)) { - declEntity = NULL; - break; - } - if (dtd->keepProcessing) { - const XML_Char *name = poolStoreString(&dtd->pool, enc, s, next); - if (!name) - return XML_ERROR_NO_MEMORY; - declEntity = (ENTITY *)lookup(parser, &dtd->generalEntities, name, - sizeof(ENTITY)); - if (!declEntity) - return XML_ERROR_NO_MEMORY; - if (declEntity->name != name) { - poolDiscard(&dtd->pool); - declEntity = NULL; - } - else { - poolFinish(&dtd->pool); - declEntity->publicId = NULL; - declEntity->is_param = XML_FALSE; - /* if we have a parent parser or are reading an internal parameter - entity, then the entity declaration is not considered "internal" - */ - declEntity->is_internal = !(parentParser || openInternalEntities); - if (entityDeclHandler) - handleDefault = XML_FALSE; - } - } - else { + case XML_ROLE_GENERAL_ENTITY_NAME: { + if (XmlPredefinedEntityName(enc, s, next)) { + parser->m_declEntity = NULL; + break; + } + if (dtd->keepProcessing) { + const XML_Char *name = poolStoreString(&dtd->pool, enc, s, next); + if (! name) + return XML_ERROR_NO_MEMORY; + parser->m_declEntity = (ENTITY *)lookup(parser, &dtd->generalEntities, + name, sizeof(ENTITY)); + if (! parser->m_declEntity) + return XML_ERROR_NO_MEMORY; + if (parser->m_declEntity->name != name) { poolDiscard(&dtd->pool); - declEntity = NULL; + parser->m_declEntity = NULL; + } else { + poolFinish(&dtd->pool); + parser->m_declEntity->publicId = NULL; + parser->m_declEntity->is_param = XML_FALSE; + /* if we have a parent parser or are reading an internal parameter + entity, then the entity declaration is not considered "internal" + */ + parser->m_declEntity->is_internal + = ! (parser->m_parentParser || parser->m_openInternalEntities); + if (parser->m_entityDeclHandler) + handleDefault = XML_FALSE; } + } else { + poolDiscard(&dtd->pool); + parser->m_declEntity = NULL; } - break; + } break; case XML_ROLE_PARAM_ENTITY_NAME: #ifdef XML_DTD if (dtd->keepProcessing) { const XML_Char *name = poolStoreString(&dtd->pool, enc, s, next); - if (!name) + if (! name) return XML_ERROR_NO_MEMORY; - declEntity = (ENTITY *)lookup(parser, &dtd->paramEntities, - name, sizeof(ENTITY)); - if (!declEntity) + parser->m_declEntity = (ENTITY *)lookup(parser, &dtd->paramEntities, + name, sizeof(ENTITY)); + if (! parser->m_declEntity) return XML_ERROR_NO_MEMORY; - if (declEntity->name != name) { + if (parser->m_declEntity->name != name) { poolDiscard(&dtd->pool); - declEntity = NULL; - } - else { + parser->m_declEntity = NULL; + } else { poolFinish(&dtd->pool); - declEntity->publicId = NULL; - declEntity->is_param = XML_TRUE; + parser->m_declEntity->publicId = NULL; + parser->m_declEntity->is_param = XML_TRUE; /* if we have a parent parser or are reading an internal parameter entity, then the entity declaration is not considered "internal" */ - declEntity->is_internal = !(parentParser || openInternalEntities); - if (entityDeclHandler) + parser->m_declEntity->is_internal + = ! (parser->m_parentParser || parser->m_openInternalEntities); + if (parser->m_entityDeclHandler) handleDefault = XML_FALSE; } - } - else { + } else { poolDiscard(&dtd->pool); - declEntity = NULL; + parser->m_declEntity = NULL; } -#else /* not XML_DTD */ - declEntity = NULL; +#else /* not XML_DTD */ + parser->m_declEntity = NULL; #endif /* XML_DTD */ break; case XML_ROLE_NOTATION_NAME: - declNotationPublicId = NULL; - declNotationName = NULL; - if (notationDeclHandler) { - declNotationName = poolStoreString(&tempPool, enc, s, next); - if (!declNotationName) + parser->m_declNotationPublicId = NULL; + parser->m_declNotationName = NULL; + if (parser->m_notationDeclHandler) { + parser->m_declNotationName + = poolStoreString(&parser->m_tempPool, enc, s, next); + if (! parser->m_declNotationName) return XML_ERROR_NO_MEMORY; - poolFinish(&tempPool); + poolFinish(&parser->m_tempPool); handleDefault = XML_FALSE; } break; case XML_ROLE_NOTATION_PUBLIC_ID: - if (!XmlIsPublicId(enc, s, next, eventPP)) + if (! XmlIsPublicId(enc, s, next, eventPP)) return XML_ERROR_PUBLICID; - if (declNotationName) { /* means notationDeclHandler != NULL */ - XML_Char *tem = poolStoreString(&tempPool, - enc, + if (parser + ->m_declNotationName) { /* means m_notationDeclHandler != NULL */ + XML_Char *tem = poolStoreString(&parser->m_tempPool, enc, s + enc->minBytesPerChar, next - enc->minBytesPerChar); - if (!tem) + if (! tem) return XML_ERROR_NO_MEMORY; normalizePublicId(tem); - declNotationPublicId = tem; - poolFinish(&tempPool); + parser->m_declNotationPublicId = tem; + poolFinish(&parser->m_tempPool); handleDefault = XML_FALSE; } break; case XML_ROLE_NOTATION_SYSTEM_ID: - if (declNotationName && notationDeclHandler) { - const XML_Char *systemId - = poolStoreString(&tempPool, enc, - s + enc->minBytesPerChar, - next - enc->minBytesPerChar); - if (!systemId) + if (parser->m_declNotationName && parser->m_notationDeclHandler) { + const XML_Char *systemId = poolStoreString(&parser->m_tempPool, enc, + s + enc->minBytesPerChar, + next - enc->minBytesPerChar); + if (! systemId) return XML_ERROR_NO_MEMORY; *eventEndPP = s; - notationDeclHandler(handlerArg, - declNotationName, - curBase, - systemId, - declNotationPublicId); + parser->m_notationDeclHandler( + parser->m_handlerArg, parser->m_declNotationName, parser->m_curBase, + systemId, parser->m_declNotationPublicId); handleDefault = XML_FALSE; } - poolClear(&tempPool); + poolClear(&parser->m_tempPool); break; case XML_ROLE_NOTATION_NO_SYSTEM_ID: - if (declNotationPublicId && notationDeclHandler) { + if (parser->m_declNotationPublicId && parser->m_notationDeclHandler) { *eventEndPP = s; - notationDeclHandler(handlerArg, - declNotationName, - curBase, - 0, - declNotationPublicId); + parser->m_notationDeclHandler( + parser->m_handlerArg, parser->m_declNotationName, parser->m_curBase, + 0, parser->m_declNotationPublicId); handleDefault = XML_FALSE; } - poolClear(&tempPool); + poolClear(&parser->m_tempPool); break; case XML_ROLE_ERROR: switch (tok) { @@ -4466,90 +4739,95 @@ doProlog(XML_Parser parser, return XML_ERROR_SYNTAX; } #ifdef XML_DTD - case XML_ROLE_IGNORE_SECT: - { - enum XML_Error result; - if (defaultHandler) - reportDefault(parser, enc, s, next); - handleDefault = XML_FALSE; - result = doIgnoreSection(parser, enc, &next, end, nextPtr, haveMore); - if (result != XML_ERROR_NONE) - return result; - else if (!next) { - processor = ignoreSectionProcessor; - return result; - } + case XML_ROLE_IGNORE_SECT: { + enum XML_Error result; + if (parser->m_defaultHandler) + reportDefault(parser, enc, s, next); + handleDefault = XML_FALSE; + result = doIgnoreSection(parser, enc, &next, end, nextPtr, haveMore); + if (result != XML_ERROR_NONE) + return result; + else if (! next) { + parser->m_processor = ignoreSectionProcessor; + return result; } - break; + } break; #endif /* XML_DTD */ case XML_ROLE_GROUP_OPEN: - if (prologState.level >= groupSize) { - if (groupSize) { - char *temp = (char *)REALLOC(groupConnector, groupSize *= 2); - if (temp == NULL) - return XML_ERROR_NO_MEMORY; - groupConnector = temp; + if (parser->m_prologState.level >= parser->m_groupSize) { + if (parser->m_groupSize) { + { + char *const new_connector = (char *)REALLOC( + parser, parser->m_groupConnector, parser->m_groupSize *= 2); + if (new_connector == NULL) { + parser->m_groupSize /= 2; + return XML_ERROR_NO_MEMORY; + } + parser->m_groupConnector = new_connector; + } + if (dtd->scaffIndex) { - int *temp = (int *)REALLOC(dtd->scaffIndex, - groupSize * sizeof(int)); - if (temp == NULL) + int *const new_scaff_index = (int *)REALLOC( + parser, dtd->scaffIndex, parser->m_groupSize * sizeof(int)); + if (new_scaff_index == NULL) return XML_ERROR_NO_MEMORY; - dtd->scaffIndex = temp; + dtd->scaffIndex = new_scaff_index; } - } - else { - groupConnector = (char *)MALLOC(groupSize = 32); - if (!groupConnector) + } else { + parser->m_groupConnector + = (char *)MALLOC(parser, parser->m_groupSize = 32); + if (! parser->m_groupConnector) { + parser->m_groupSize = 0; return XML_ERROR_NO_MEMORY; + } } } - groupConnector[prologState.level] = 0; + parser->m_groupConnector[parser->m_prologState.level] = 0; if (dtd->in_eldecl) { int myindex = nextScaffoldPart(parser); if (myindex < 0) return XML_ERROR_NO_MEMORY; + assert(dtd->scaffIndex != NULL); dtd->scaffIndex[dtd->scaffLevel] = myindex; dtd->scaffLevel++; dtd->scaffold[myindex].type = XML_CTYPE_SEQ; - if (elementDeclHandler) + if (parser->m_elementDeclHandler) handleDefault = XML_FALSE; } break; case XML_ROLE_GROUP_SEQUENCE: - if (groupConnector[prologState.level] == ASCII_PIPE) + if (parser->m_groupConnector[parser->m_prologState.level] == ASCII_PIPE) return XML_ERROR_SYNTAX; - groupConnector[prologState.level] = ASCII_COMMA; - if (dtd->in_eldecl && elementDeclHandler) + parser->m_groupConnector[parser->m_prologState.level] = ASCII_COMMA; + if (dtd->in_eldecl && parser->m_elementDeclHandler) handleDefault = XML_FALSE; break; case XML_ROLE_GROUP_CHOICE: - if (groupConnector[prologState.level] == ASCII_COMMA) + if (parser->m_groupConnector[parser->m_prologState.level] == ASCII_COMMA) return XML_ERROR_SYNTAX; if (dtd->in_eldecl - && !groupConnector[prologState.level] + && ! parser->m_groupConnector[parser->m_prologState.level] && (dtd->scaffold[dtd->scaffIndex[dtd->scaffLevel - 1]].type - != XML_CTYPE_MIXED) - ) { + != XML_CTYPE_MIXED)) { dtd->scaffold[dtd->scaffIndex[dtd->scaffLevel - 1]].type = XML_CTYPE_CHOICE; - if (elementDeclHandler) + if (parser->m_elementDeclHandler) handleDefault = XML_FALSE; } - groupConnector[prologState.level] = ASCII_PIPE; + parser->m_groupConnector[parser->m_prologState.level] = ASCII_PIPE; break; case XML_ROLE_PARAM_ENTITY_REF: #ifdef XML_DTD case XML_ROLE_INNER_PARAM_ENTITY_REF: dtd->hasParamEntityRefs = XML_TRUE; - if (!paramEntityParsing) + if (! parser->m_paramEntityParsing) dtd->keepProcessing = dtd->standalone; else { const XML_Char *name; ENTITY *entity; - name = poolStoreString(&dtd->pool, enc, - s + enc->minBytesPerChar, - next - enc->minBytesPerChar); - if (!name) + name = poolStoreString(&dtd->pool, enc, s + enc->minBytesPerChar, + next - enc->minBytesPerChar); + if (! name) return XML_ERROR_NO_MEMORY; entity = (ENTITY *)lookup(parser, &dtd->paramEntities, name, 0); poolDiscard(&dtd->pool); @@ -4557,20 +4835,40 @@ doProlog(XML_Parser parser, if yes, check that the entity exists, and that it is internal, otherwise call the skipped entity handler */ - if (prologState.documentEntity && - (dtd->standalone - ? !openInternalEntities - : !dtd->hasParamEntityRefs)) { - if (!entity) + if (parser->m_prologState.documentEntity + && (dtd->standalone ? ! parser->m_openInternalEntities + : ! dtd->hasParamEntityRefs)) { + if (! entity) return XML_ERROR_UNDEFINED_ENTITY; - else if (!entity->is_internal) - return XML_ERROR_ENTITY_DECLARED_IN_PE; - } - else if (!entity) { + else if (! entity->is_internal) { + /* It's hard to exhaustively search the code to be sure, + * but there doesn't seem to be a way of executing the + * following line. There are two cases: + * + * If 'standalone' is false, the DTD must have no + * parameter entities or we wouldn't have passed the outer + * 'if' statement. That measn the only entity in the hash + * table is the external subset name "#" which cannot be + * given as a parameter entity name in XML syntax, so the + * lookup must have returned NULL and we don't even reach + * the test for an internal entity. + * + * If 'standalone' is true, it does not seem to be + * possible to create entities taking this code path that + * are not internal entities, so fail the test above. + * + * Because this analysis is very uncertain, the code is + * being left in place and merely removed from the + * coverage test statistics. + */ + return XML_ERROR_ENTITY_DECLARED_IN_PE; /* LCOV_EXCL_LINE */ + } + } else if (! entity) { dtd->keepProcessing = dtd->standalone; /* cannot report skipped entities in declarations */ - if ((role == XML_ROLE_PARAM_ENTITY_REF) && skippedEntityHandler) { - skippedEntityHandler(handlerArg, name, 1); + if ((role == XML_ROLE_PARAM_ENTITY_REF) + && parser->m_skippedEntityHandler) { + parser->m_skippedEntityHandler(parser->m_handlerArg, name, 1); handleDefault = XML_FALSE; } break; @@ -4579,50 +4877,46 @@ doProlog(XML_Parser parser, return XML_ERROR_RECURSIVE_ENTITY_REF; if (entity->textPtr) { enum XML_Error result; - XML_Bool betweenDecl = - (role == XML_ROLE_PARAM_ENTITY_REF ? XML_TRUE : XML_FALSE); + XML_Bool betweenDecl + = (role == XML_ROLE_PARAM_ENTITY_REF ? XML_TRUE : XML_FALSE); result = processInternalEntity(parser, entity, betweenDecl); if (result != XML_ERROR_NONE) return result; handleDefault = XML_FALSE; break; } - if (externalEntityRefHandler) { + if (parser->m_externalEntityRefHandler) { dtd->paramEntityRead = XML_FALSE; entity->open = XML_TRUE; - if (!externalEntityRefHandler(externalEntityRefHandlerArg, - 0, - entity->base, - entity->systemId, - entity->publicId)) { + if (! parser->m_externalEntityRefHandler( + parser->m_externalEntityRefHandlerArg, 0, entity->base, + entity->systemId, entity->publicId)) { entity->open = XML_FALSE; return XML_ERROR_EXTERNAL_ENTITY_HANDLING; } entity->open = XML_FALSE; handleDefault = XML_FALSE; - if (!dtd->paramEntityRead) { + if (! dtd->paramEntityRead) { dtd->keepProcessing = dtd->standalone; break; } - } - else { + } else { dtd->keepProcessing = dtd->standalone; break; } } #endif /* XML_DTD */ - if (!dtd->standalone && - notStandaloneHandler && - !notStandaloneHandler(handlerArg)) + if (! dtd->standalone && parser->m_notStandaloneHandler + && ! parser->m_notStandaloneHandler(parser->m_handlerArg)) return XML_ERROR_NOT_STANDALONE; break; - /* Element declaration stuff */ + /* Element declaration stuff */ case XML_ROLE_ELEMENT_NAME: - if (elementDeclHandler) { - declElementType = getElementType(parser, enc, s, next); - if (!declElementType) + if (parser->m_elementDeclHandler) { + parser->m_declElementType = getElementType(parser, enc, s, next); + if (! parser->m_declElementType) return XML_ERROR_NO_MEMORY; dtd->scaffLevel = 0; dtd->scaffCount = 0; @@ -4634,19 +4928,20 @@ doProlog(XML_Parser parser, case XML_ROLE_CONTENT_ANY: case XML_ROLE_CONTENT_EMPTY: if (dtd->in_eldecl) { - if (elementDeclHandler) { - XML_Content * content = (XML_Content *) MALLOC(sizeof(XML_Content)); - if (!content) + if (parser->m_elementDeclHandler) { + XML_Content *content + = (XML_Content *)MALLOC(parser, sizeof(XML_Content)); + if (! content) return XML_ERROR_NO_MEMORY; content->quant = XML_CQUANT_NONE; content->name = NULL; content->numchildren = 0; content->children = NULL; - content->type = ((role == XML_ROLE_CONTENT_ANY) ? - XML_CTYPE_ANY : - XML_CTYPE_EMPTY); + content->type = ((role == XML_ROLE_CONTENT_ANY) ? XML_CTYPE_ANY + : XML_CTYPE_EMPTY); *eventEndPP = s; - elementDeclHandler(handlerArg, declElementType->name, content); + parser->m_elementDeclHandler( + parser->m_handlerArg, parser->m_declElementType->name, content); handleDefault = XML_FALSE; } dtd->in_eldecl = XML_FALSE; @@ -4657,7 +4952,7 @@ doProlog(XML_Parser parser, if (dtd->in_eldecl) { dtd->scaffold[dtd->scaffIndex[dtd->scaffLevel - 1]].type = XML_CTYPE_MIXED; - if (elementDeclHandler) + if (parser->m_elementDeclHandler) handleDefault = XML_FALSE; } break; @@ -4678,23 +4973,23 @@ doProlog(XML_Parser parser, ELEMENT_TYPE *el; const XML_Char *name; int nameLen; - const char *nxt = (quant == XML_CQUANT_NONE - ? next - : next - enc->minBytesPerChar); + const char *nxt + = (quant == XML_CQUANT_NONE ? next : next - enc->minBytesPerChar); int myindex = nextScaffoldPart(parser); if (myindex < 0) return XML_ERROR_NO_MEMORY; dtd->scaffold[myindex].type = XML_CTYPE_NAME; dtd->scaffold[myindex].quant = quant; el = getElementType(parser, enc, s, nxt); - if (!el) + if (! el) return XML_ERROR_NO_MEMORY; name = el->name; dtd->scaffold[myindex].name = name; nameLen = 0; - for (; name[nameLen++]; ); - dtd->contentStringLen += nameLen; - if (elementDeclHandler) + for (; name[nameLen++];) + ; + dtd->contentStringLen += nameLen; + if (parser->m_elementDeclHandler) handleDefault = XML_FALSE; } break; @@ -4712,17 +5007,18 @@ doProlog(XML_Parser parser, quant = XML_CQUANT_PLUS; closeGroup: if (dtd->in_eldecl) { - if (elementDeclHandler) + if (parser->m_elementDeclHandler) handleDefault = XML_FALSE; dtd->scaffLevel--; dtd->scaffold[dtd->scaffIndex[dtd->scaffLevel]].quant = quant; if (dtd->scaffLevel == 0) { - if (!handleDefault) { + if (! handleDefault) { XML_Content *model = build_model(parser); - if (!model) + if (! model) return XML_ERROR_NO_MEMORY; *eventEndPP = s; - elementDeclHandler(handlerArg, declElementType->name, model); + parser->m_elementDeclHandler( + parser->m_handlerArg, parser->m_declElementType->name, model); } dtd->in_eldecl = XML_FALSE; dtd->contentStringLen = 0; @@ -4732,12 +5028,12 @@ doProlog(XML_Parser parser, /* End element declaration stuff */ case XML_ROLE_PI: - if (!reportProcessingInstruction(parser, enc, s, next)) + if (! reportProcessingInstruction(parser, enc, s, next)) return XML_ERROR_NO_MEMORY; handleDefault = XML_FALSE; break; case XML_ROLE_COMMENT: - if (!reportComment(parser, enc, s, next)) + if (! reportComment(parser, enc, s, next)) return XML_ERROR_NO_MEMORY; handleDefault = XML_FALSE; break; @@ -4749,31 +5045,31 @@ doProlog(XML_Parser parser, } break; case XML_ROLE_DOCTYPE_NONE: - if (startDoctypeDeclHandler) + if (parser->m_startDoctypeDeclHandler) handleDefault = XML_FALSE; break; case XML_ROLE_ENTITY_NONE: - if (dtd->keepProcessing && entityDeclHandler) + if (dtd->keepProcessing && parser->m_entityDeclHandler) handleDefault = XML_FALSE; break; case XML_ROLE_NOTATION_NONE: - if (notationDeclHandler) + if (parser->m_notationDeclHandler) handleDefault = XML_FALSE; break; case XML_ROLE_ATTLIST_NONE: - if (dtd->keepProcessing && attlistDeclHandler) + if (dtd->keepProcessing && parser->m_attlistDeclHandler) handleDefault = XML_FALSE; break; case XML_ROLE_ELEMENT_NONE: - if (elementDeclHandler) + if (parser->m_elementDeclHandler) handleDefault = XML_FALSE; break; } /* end of big switch */ - if (handleDefault && defaultHandler) + if (handleDefault && parser->m_defaultHandler) reportDefault(parser, enc, s, next); - switch (ps_parsing) { + switch (parser->m_parsingStatus.parsing) { case XML_SUSPENDED: *nextPtr = next; return XML_ERROR_NONE; @@ -4788,23 +5084,20 @@ doProlog(XML_Parser parser, } static enum XML_Error PTRCALL -epilogProcessor(XML_Parser parser, - const char *s, - const char *end, - const char **nextPtr) -{ - processor = epilogProcessor; - eventPtr = s; +epilogProcessor(XML_Parser parser, const char *s, const char *end, + const char **nextPtr) { + parser->m_processor = epilogProcessor; + parser->m_eventPtr = s; for (;;) { const char *next = NULL; - int tok = XmlPrologTok(encoding, s, end, &next); - eventEndPtr = next; + int tok = XmlPrologTok(parser->m_encoding, s, end, &next); + parser->m_eventEndPtr = next; switch (tok) { /* report partial linebreak - it might be the last token */ case -XML_TOK_PROLOG_S: - if (defaultHandler) { - reportDefault(parser, encoding, s, next); - if (ps_parsing == XML_FINISHED) + if (parser->m_defaultHandler) { + reportDefault(parser, parser->m_encoding, s, next); + if (parser->m_parsingStatus.parsing == XML_FINISHED) return XML_ERROR_ABORTED; } *nextPtr = next; @@ -4813,28 +5106,28 @@ epilogProcessor(XML_Parser parser, *nextPtr = s; return XML_ERROR_NONE; case XML_TOK_PROLOG_S: - if (defaultHandler) - reportDefault(parser, encoding, s, next); + if (parser->m_defaultHandler) + reportDefault(parser, parser->m_encoding, s, next); break; case XML_TOK_PI: - if (!reportProcessingInstruction(parser, encoding, s, next)) + if (! reportProcessingInstruction(parser, parser->m_encoding, s, next)) return XML_ERROR_NO_MEMORY; break; case XML_TOK_COMMENT: - if (!reportComment(parser, encoding, s, next)) + if (! reportComment(parser, parser->m_encoding, s, next)) return XML_ERROR_NO_MEMORY; break; case XML_TOK_INVALID: - eventPtr = next; + parser->m_eventPtr = next; return XML_ERROR_INVALID_TOKEN; case XML_TOK_PARTIAL: - if (!ps_finalBuffer) { + if (! parser->m_parsingStatus.finalBuffer) { *nextPtr = s; return XML_ERROR_NONE; } return XML_ERROR_UNCLOSED_TOKEN; case XML_TOK_PARTIAL_CHAR: - if (!ps_finalBuffer) { + if (! parser->m_parsingStatus.finalBuffer) { *nextPtr = s; return XML_ERROR_NONE; } @@ -4842,167 +5135,162 @@ epilogProcessor(XML_Parser parser, default: return XML_ERROR_JUNK_AFTER_DOC_ELEMENT; } - eventPtr = s = next; - switch (ps_parsing) { + parser->m_eventPtr = s = next; + switch (parser->m_parsingStatus.parsing) { case XML_SUSPENDED: *nextPtr = next; return XML_ERROR_NONE; case XML_FINISHED: return XML_ERROR_ABORTED; - default: ; + default:; } } } static enum XML_Error -processInternalEntity(XML_Parser parser, ENTITY *entity, - XML_Bool betweenDecl) -{ +processInternalEntity(XML_Parser parser, ENTITY *entity, XML_Bool betweenDecl) { const char *textStart, *textEnd; const char *next; enum XML_Error result; OPEN_INTERNAL_ENTITY *openEntity; - if (freeInternalEntities) { - openEntity = freeInternalEntities; - freeInternalEntities = openEntity->next; - } - else { - openEntity = (OPEN_INTERNAL_ENTITY *)MALLOC(sizeof(OPEN_INTERNAL_ENTITY)); - if (!openEntity) + if (parser->m_freeInternalEntities) { + openEntity = parser->m_freeInternalEntities; + parser->m_freeInternalEntities = openEntity->next; + } else { + openEntity + = (OPEN_INTERNAL_ENTITY *)MALLOC(parser, sizeof(OPEN_INTERNAL_ENTITY)); + if (! openEntity) return XML_ERROR_NO_MEMORY; } entity->open = XML_TRUE; entity->processed = 0; - openEntity->next = openInternalEntities; - openInternalEntities = openEntity; + openEntity->next = parser->m_openInternalEntities; + parser->m_openInternalEntities = openEntity; openEntity->entity = entity; - openEntity->startTagLevel = tagLevel; + openEntity->startTagLevel = parser->m_tagLevel; openEntity->betweenDecl = betweenDecl; openEntity->internalEventPtr = NULL; openEntity->internalEventEndPtr = NULL; textStart = (char *)entity->textPtr; textEnd = (char *)(entity->textPtr + entity->textLen); + /* Set a safe default value in case 'next' does not get set */ + next = textStart; #ifdef XML_DTD if (entity->is_param) { - int tok = XmlPrologTok(internalEncoding, textStart, textEnd, &next); - result = doProlog(parser, internalEncoding, textStart, textEnd, tok, - next, &next, XML_FALSE); - } - else + int tok + = XmlPrologTok(parser->m_internalEncoding, textStart, textEnd, &next); + result = doProlog(parser, parser->m_internalEncoding, textStart, textEnd, + tok, next, &next, XML_FALSE, XML_FALSE); + } else #endif /* XML_DTD */ - result = doContent(parser, tagLevel, internalEncoding, textStart, - textEnd, &next, XML_FALSE); + result = doContent(parser, parser->m_tagLevel, parser->m_internalEncoding, + textStart, textEnd, &next, XML_FALSE); if (result == XML_ERROR_NONE) { - if (textEnd != next && ps_parsing == XML_SUSPENDED) { + if (textEnd != next && parser->m_parsingStatus.parsing == XML_SUSPENDED) { entity->processed = (int)(next - textStart); - processor = internalEntityProcessor; - } - else { + parser->m_processor = internalEntityProcessor; + } else { entity->open = XML_FALSE; - openInternalEntities = openEntity->next; + parser->m_openInternalEntities = openEntity->next; /* put openEntity back in list of free instances */ - openEntity->next = freeInternalEntities; - freeInternalEntities = openEntity; + openEntity->next = parser->m_freeInternalEntities; + parser->m_freeInternalEntities = openEntity; } } return result; } static enum XML_Error PTRCALL -internalEntityProcessor(XML_Parser parser, - const char *s, - const char *end, - const char **nextPtr) -{ +internalEntityProcessor(XML_Parser parser, const char *s, const char *end, + const char **nextPtr) { ENTITY *entity; const char *textStart, *textEnd; const char *next; enum XML_Error result; - OPEN_INTERNAL_ENTITY *openEntity = openInternalEntities; - if (!openEntity) + OPEN_INTERNAL_ENTITY *openEntity = parser->m_openInternalEntities; + if (! openEntity) return XML_ERROR_UNEXPECTED_STATE; entity = openEntity->entity; textStart = ((char *)entity->textPtr) + entity->processed; textEnd = (char *)(entity->textPtr + entity->textLen); + /* Set a safe default value in case 'next' does not get set */ + next = textStart; #ifdef XML_DTD if (entity->is_param) { - int tok = XmlPrologTok(internalEncoding, textStart, textEnd, &next); - result = doProlog(parser, internalEncoding, textStart, textEnd, tok, - next, &next, XML_FALSE); - } - else + int tok + = XmlPrologTok(parser->m_internalEncoding, textStart, textEnd, &next); + result = doProlog(parser, parser->m_internalEncoding, textStart, textEnd, + tok, next, &next, XML_FALSE, XML_TRUE); + } else #endif /* XML_DTD */ - result = doContent(parser, openEntity->startTagLevel, internalEncoding, - textStart, textEnd, &next, XML_FALSE); + result = doContent(parser, openEntity->startTagLevel, + parser->m_internalEncoding, textStart, textEnd, &next, + XML_FALSE); if (result != XML_ERROR_NONE) return result; - else if (textEnd != next && ps_parsing == XML_SUSPENDED) { + else if (textEnd != next + && parser->m_parsingStatus.parsing == XML_SUSPENDED) { entity->processed = (int)(next - (char *)entity->textPtr); return result; - } - else { + } else { entity->open = XML_FALSE; - openInternalEntities = openEntity->next; + parser->m_openInternalEntities = openEntity->next; /* put openEntity back in list of free instances */ - openEntity->next = freeInternalEntities; - freeInternalEntities = openEntity; + openEntity->next = parser->m_freeInternalEntities; + parser->m_freeInternalEntities = openEntity; } #ifdef XML_DTD if (entity->is_param) { int tok; - processor = prologProcessor; - tok = XmlPrologTok(encoding, s, end, &next); - return doProlog(parser, encoding, s, end, tok, next, nextPtr, - (XML_Bool)!ps_finalBuffer); - } - else + parser->m_processor = prologProcessor; + tok = XmlPrologTok(parser->m_encoding, s, end, &next); + return doProlog(parser, parser->m_encoding, s, end, tok, next, nextPtr, + (XML_Bool)! parser->m_parsingStatus.finalBuffer, XML_TRUE); + } else #endif /* XML_DTD */ { - processor = contentProcessor; + parser->m_processor = contentProcessor; /* see externalEntityContentProcessor vs contentProcessor */ - return doContent(parser, parentParser ? 1 : 0, encoding, s, end, - nextPtr, (XML_Bool)!ps_finalBuffer); + return doContent(parser, parser->m_parentParser ? 1 : 0, parser->m_encoding, + s, end, nextPtr, + (XML_Bool)! parser->m_parsingStatus.finalBuffer); } } static enum XML_Error PTRCALL -errorProcessor(XML_Parser parser, - const char *UNUSED_P(s), - const char *UNUSED_P(end), - const char **UNUSED_P(nextPtr)) -{ - return errorCode; +errorProcessor(XML_Parser parser, const char *s, const char *end, + const char **nextPtr) { + UNUSED_P(s); + UNUSED_P(end); + UNUSED_P(nextPtr); + return parser->m_errorCode; } static enum XML_Error storeAttributeValue(XML_Parser parser, const ENCODING *enc, XML_Bool isCdata, - const char *ptr, const char *end, - STRING_POOL *pool) -{ - enum XML_Error result = appendAttributeValue(parser, enc, isCdata, ptr, - end, pool); + const char *ptr, const char *end, STRING_POOL *pool) { + enum XML_Error result + = appendAttributeValue(parser, enc, isCdata, ptr, end, pool); if (result) return result; - if (!isCdata && poolLength(pool) && poolLastChar(pool) == 0x20) + if (! isCdata && poolLength(pool) && poolLastChar(pool) == 0x20) poolChop(pool); - if (!poolAppendChar(pool, XML_T('\0'))) + if (! poolAppendChar(pool, XML_T('\0'))) return XML_ERROR_NO_MEMORY; return XML_ERROR_NONE; } static enum XML_Error appendAttributeValue(XML_Parser parser, const ENCODING *enc, XML_Bool isCdata, - const char *ptr, const char *end, - STRING_POOL *pool) -{ - DTD * const dtd = _dtd; /* save one level of indirection */ + const char *ptr, const char *end, STRING_POOL *pool) { + DTD *const dtd = parser->m_dtd; /* save one level of indirection */ for (;;) { const char *next; int tok = XmlAttributeValueTok(enc, ptr, end, &next); @@ -5010,41 +5298,42 @@ appendAttributeValue(XML_Parser parser, const ENCODING *enc, XML_Bool isCdata, case XML_TOK_NONE: return XML_ERROR_NONE; case XML_TOK_INVALID: - if (enc == encoding) - eventPtr = next; + if (enc == parser->m_encoding) + parser->m_eventPtr = next; return XML_ERROR_INVALID_TOKEN; case XML_TOK_PARTIAL: - if (enc == encoding) - eventPtr = ptr; + if (enc == parser->m_encoding) + parser->m_eventPtr = ptr; return XML_ERROR_INVALID_TOKEN; - case XML_TOK_CHAR_REF: - { - XML_Char buf[XML_ENCODE_MAX]; - int i; - int n = XmlCharRefNumber(enc, ptr); - if (n < 0) { - if (enc == encoding) - eventPtr = ptr; - return XML_ERROR_BAD_CHAR_REF; - } - if (!isCdata - && n == 0x20 /* space */ - && (poolLength(pool) == 0 || poolLastChar(pool) == 0x20)) - break; - n = XmlEncode(n, (ICHAR *)buf); - if (!n) { - if (enc == encoding) - eventPtr = ptr; - return XML_ERROR_BAD_CHAR_REF; - } - for (i = 0; i < n; i++) { - if (!poolAppendChar(pool, buf[i])) - return XML_ERROR_NO_MEMORY; - } + case XML_TOK_CHAR_REF: { + XML_Char buf[XML_ENCODE_MAX]; + int i; + int n = XmlCharRefNumber(enc, ptr); + if (n < 0) { + if (enc == parser->m_encoding) + parser->m_eventPtr = ptr; + return XML_ERROR_BAD_CHAR_REF; } - break; + if (! isCdata && n == 0x20 /* space */ + && (poolLength(pool) == 0 || poolLastChar(pool) == 0x20)) + break; + n = XmlEncode(n, (ICHAR *)buf); + /* The XmlEncode() functions can never return 0 here. That + * error return happens if the code point passed in is either + * negative or greater than or equal to 0x110000. The + * XmlCharRefNumber() functions will all return a number + * strictly less than 0x110000 or a negative value if an error + * occurred. The negative value is intercepted above, so + * XmlEncode() is never passed a value it might return an + * error for. + */ + for (i = 0; i < n; i++) { + if (! poolAppendChar(pool, buf[i])) + return XML_ERROR_NO_MEMORY; + } + } break; case XML_TOK_DATA_CHARS: - if (!poolAppend(pool, enc, ptr, next)) + if (! poolAppend(pool, enc, ptr, next)) return XML_ERROR_NO_MEMORY; break; case XML_TOK_TRAILING_CR: @@ -5052,95 +5341,119 @@ appendAttributeValue(XML_Parser parser, const ENCODING *enc, XML_Bool isCdata, /* fall through */ case XML_TOK_ATTRIBUTE_VALUE_S: case XML_TOK_DATA_NEWLINE: - if (!isCdata && (poolLength(pool) == 0 || poolLastChar(pool) == 0x20)) + if (! isCdata && (poolLength(pool) == 0 || poolLastChar(pool) == 0x20)) break; - if (!poolAppendChar(pool, 0x20)) + if (! poolAppendChar(pool, 0x20)) return XML_ERROR_NO_MEMORY; break; - case XML_TOK_ENTITY_REF: - { - const XML_Char *name; - ENTITY *entity; - char checkEntityDecl; - XML_Char ch = (XML_Char) XmlPredefinedEntityName(enc, - ptr + enc->minBytesPerChar, - next - enc->minBytesPerChar); - if (ch) { - if (!poolAppendChar(pool, ch)) - return XML_ERROR_NO_MEMORY; - break; - } - name = poolStoreString(&temp2Pool, enc, - ptr + enc->minBytesPerChar, - next - enc->minBytesPerChar); - if (!name) + case XML_TOK_ENTITY_REF: { + const XML_Char *name; + ENTITY *entity; + char checkEntityDecl; + XML_Char ch = (XML_Char)XmlPredefinedEntityName( + enc, ptr + enc->minBytesPerChar, next - enc->minBytesPerChar); + if (ch) { + if (! poolAppendChar(pool, ch)) return XML_ERROR_NO_MEMORY; - entity = (ENTITY *)lookup(parser, &dtd->generalEntities, name, 0); - poolDiscard(&temp2Pool); - /* First, determine if a check for an existing declaration is needed; - if yes, check that the entity exists, and that it is internal. - */ - if (pool == &dtd->pool) /* are we called from prolog? */ - checkEntityDecl = + break; + } + name = poolStoreString(&parser->m_temp2Pool, enc, + ptr + enc->minBytesPerChar, + next - enc->minBytesPerChar); + if (! name) + return XML_ERROR_NO_MEMORY; + entity = (ENTITY *)lookup(parser, &dtd->generalEntities, name, 0); + poolDiscard(&parser->m_temp2Pool); + /* First, determine if a check for an existing declaration is needed; + if yes, check that the entity exists, and that it is internal. + */ + if (pool == &dtd->pool) /* are we called from prolog? */ + checkEntityDecl = #ifdef XML_DTD - prologState.documentEntity && + parser->m_prologState.documentEntity && #endif /* XML_DTD */ - (dtd->standalone - ? !openInternalEntities - : !dtd->hasParamEntityRefs); - else /* if (pool == &tempPool): we are called from content */ - checkEntityDecl = !dtd->hasParamEntityRefs || dtd->standalone; - if (checkEntityDecl) { - if (!entity) - return XML_ERROR_UNDEFINED_ENTITY; - else if (!entity->is_internal) - return XML_ERROR_ENTITY_DECLARED_IN_PE; - } - else if (!entity) { - /* Cannot report skipped entity here - see comments on - skippedEntityHandler. - if (skippedEntityHandler) - skippedEntityHandler(handlerArg, name, 0); - */ - /* Cannot call the default handler because this would be - out of sync with the call to the startElementHandler. - if ((pool == &tempPool) && defaultHandler) - reportDefault(parser, enc, ptr, next); - */ - break; - } - if (entity->open) { - if (enc == encoding) - eventPtr = ptr; - return XML_ERROR_RECURSIVE_ENTITY_REF; - } - if (entity->notation) { - if (enc == encoding) - eventPtr = ptr; - return XML_ERROR_BINARY_ENTITY_REF; - } - if (!entity->textPtr) { - if (enc == encoding) - eventPtr = ptr; - return XML_ERROR_ATTRIBUTE_EXTERNAL_ENTITY_REF; - } - else { - enum XML_Error result; - const XML_Char *textEnd = entity->textPtr + entity->textLen; - entity->open = XML_TRUE; - result = appendAttributeValue(parser, internalEncoding, isCdata, - (char *)entity->textPtr, - (char *)textEnd, pool); - entity->open = XML_FALSE; - if (result) - return result; + (dtd->standalone ? ! parser->m_openInternalEntities + : ! dtd->hasParamEntityRefs); + else /* if (pool == &parser->m_tempPool): we are called from content */ + checkEntityDecl = ! dtd->hasParamEntityRefs || dtd->standalone; + if (checkEntityDecl) { + if (! entity) + return XML_ERROR_UNDEFINED_ENTITY; + else if (! entity->is_internal) + return XML_ERROR_ENTITY_DECLARED_IN_PE; + } else if (! entity) { + /* Cannot report skipped entity here - see comments on + parser->m_skippedEntityHandler. + if (parser->m_skippedEntityHandler) + parser->m_skippedEntityHandler(parser->m_handlerArg, name, 0); + */ + /* Cannot call the default handler because this would be + out of sync with the call to the startElementHandler. + if ((pool == &parser->m_tempPool) && parser->m_defaultHandler) + reportDefault(parser, enc, ptr, next); + */ + break; + } + if (entity->open) { + if (enc == parser->m_encoding) { + /* It does not appear that this line can be executed. + * + * The "if (entity->open)" check catches recursive entity + * definitions. In order to be called with an open + * entity, it must have gone through this code before and + * been through the recursive call to + * appendAttributeValue() some lines below. That call + * sets the local encoding ("enc") to the parser's + * internal encoding (internal_utf8 or internal_utf16), + * which can never be the same as the principle encoding. + * It doesn't appear there is another code path that gets + * here with entity->open being TRUE. + * + * Since it is not certain that this logic is watertight, + * we keep the line and merely exclude it from coverage + * tests. + */ + parser->m_eventPtr = ptr; /* LCOV_EXCL_LINE */ } + return XML_ERROR_RECURSIVE_ENTITY_REF; } - break; + if (entity->notation) { + if (enc == parser->m_encoding) + parser->m_eventPtr = ptr; + return XML_ERROR_BINARY_ENTITY_REF; + } + if (! entity->textPtr) { + if (enc == parser->m_encoding) + parser->m_eventPtr = ptr; + return XML_ERROR_ATTRIBUTE_EXTERNAL_ENTITY_REF; + } else { + enum XML_Error result; + const XML_Char *textEnd = entity->textPtr + entity->textLen; + entity->open = XML_TRUE; + result = appendAttributeValue(parser, parser->m_internalEncoding, + isCdata, (char *)entity->textPtr, + (char *)textEnd, pool); + entity->open = XML_FALSE; + if (result) + return result; + } + } break; default: - if (enc == encoding) - eventPtr = ptr; + /* The only token returned by XmlAttributeValueTok() that does + * not have an explicit case here is XML_TOK_PARTIAL_CHAR. + * Getting that would require an entity name to contain an + * incomplete XML character (e.g. \xE2\x82); however previous + * tokenisers will have already recognised and rejected such + * names before XmlAttributeValueTok() gets a look-in. This + * default case should be retained as a safety net, but the code + * excluded from coverage tests. + * + * LCOV_EXCL_START + */ + if (enc == parser->m_encoding) + parser->m_eventPtr = ptr; return XML_ERROR_UNEXPECTED_STATE; + /* LCOV_EXCL_STOP */ } ptr = next; } @@ -5148,23 +5461,20 @@ appendAttributeValue(XML_Parser parser, const ENCODING *enc, XML_Bool isCdata, } static enum XML_Error -storeEntityValue(XML_Parser parser, - const ENCODING *enc, - const char *entityTextPtr, - const char *entityTextEnd) -{ - DTD * const dtd = _dtd; /* save one level of indirection */ +storeEntityValue(XML_Parser parser, const ENCODING *enc, + const char *entityTextPtr, const char *entityTextEnd) { + DTD *const dtd = parser->m_dtd; /* save one level of indirection */ STRING_POOL *pool = &(dtd->entityValuePool); enum XML_Error result = XML_ERROR_NONE; #ifdef XML_DTD - int oldInEntityValue = prologState.inEntityValue; - prologState.inEntityValue = 1; + int oldInEntityValue = parser->m_prologState.inEntityValue; + parser->m_prologState.inEntityValue = 1; #endif /* XML_DTD */ /* never return Null for the value argument in EntityDeclHandler, since this would indicate an external entity; therefore we have to make sure that entityValuePool.start is not null */ - if (!pool->blocks) { - if (!poolGrow(pool)) + if (! pool->blocks) { + if (! poolGrow(pool)) return XML_ERROR_NO_MEMORY; } @@ -5174,61 +5484,55 @@ storeEntityValue(XML_Parser parser, switch (tok) { case XML_TOK_PARAM_ENTITY_REF: #ifdef XML_DTD - if (isParamEntity || enc != encoding) { + if (parser->m_isParamEntity || enc != parser->m_encoding) { const XML_Char *name; ENTITY *entity; - name = poolStoreString(&tempPool, enc, + name = poolStoreString(&parser->m_tempPool, enc, entityTextPtr + enc->minBytesPerChar, next - enc->minBytesPerChar); - if (!name) { + if (! name) { result = XML_ERROR_NO_MEMORY; goto endEntityValue; } entity = (ENTITY *)lookup(parser, &dtd->paramEntities, name, 0); - poolDiscard(&tempPool); - if (!entity) { + poolDiscard(&parser->m_tempPool); + if (! entity) { /* not a well-formedness error - see XML 1.0: WFC Entity Declared */ /* cannot report skipped entity here - see comments on - skippedEntityHandler - if (skippedEntityHandler) - skippedEntityHandler(handlerArg, name, 0); + parser->m_skippedEntityHandler + if (parser->m_skippedEntityHandler) + parser->m_skippedEntityHandler(parser->m_handlerArg, name, 0); */ dtd->keepProcessing = dtd->standalone; goto endEntityValue; } if (entity->open) { - if (enc == encoding) - eventPtr = entityTextPtr; + if (enc == parser->m_encoding) + parser->m_eventPtr = entityTextPtr; result = XML_ERROR_RECURSIVE_ENTITY_REF; goto endEntityValue; } if (entity->systemId) { - if (externalEntityRefHandler) { + if (parser->m_externalEntityRefHandler) { dtd->paramEntityRead = XML_FALSE; entity->open = XML_TRUE; - if (!externalEntityRefHandler(externalEntityRefHandlerArg, - 0, - entity->base, - entity->systemId, - entity->publicId)) { + if (! parser->m_externalEntityRefHandler( + parser->m_externalEntityRefHandlerArg, 0, entity->base, + entity->systemId, entity->publicId)) { entity->open = XML_FALSE; result = XML_ERROR_EXTERNAL_ENTITY_HANDLING; goto endEntityValue; } entity->open = XML_FALSE; - if (!dtd->paramEntityRead) + if (! dtd->paramEntityRead) dtd->keepProcessing = dtd->standalone; - } - else + } else dtd->keepProcessing = dtd->standalone; - } - else { + } else { entity->open = XML_TRUE; - result = storeEntityValue(parser, - internalEncoding, - (char *)entity->textPtr, - (char *)(entity->textPtr - + entity->textLen)); + result = storeEntityValue( + parser, parser->m_internalEncoding, (char *)entity->textPtr, + (char *)(entity->textPtr + entity->textLen)); entity->open = XML_FALSE; if (result) goto endEntityValue; @@ -5238,7 +5542,7 @@ storeEntityValue(XML_Parser parser, #endif /* XML_DTD */ /* In the internal subset, PE references are not legal within markup declarations, e.g entity values in this case. */ - eventPtr = entityTextPtr; + parser->m_eventPtr = entityTextPtr; result = XML_ERROR_PARAM_ENTITY_REF; goto endEntityValue; case XML_TOK_NONE: @@ -5246,7 +5550,7 @@ storeEntityValue(XML_Parser parser, goto endEntityValue; case XML_TOK_ENTITY_REF: case XML_TOK_DATA_CHARS: - if (!poolAppend(pool, enc, entityTextPtr, next)) { + if (! poolAppend(pool, enc, entityTextPtr, next)) { result = XML_ERROR_NO_MEMORY; goto endEntityValue; } @@ -5255,67 +5559,75 @@ storeEntityValue(XML_Parser parser, next = entityTextPtr + enc->minBytesPerChar; /* fall through */ case XML_TOK_DATA_NEWLINE: - if (pool->end == pool->ptr && !poolGrow(pool)) { - result = XML_ERROR_NO_MEMORY; + if (pool->end == pool->ptr && ! poolGrow(pool)) { + result = XML_ERROR_NO_MEMORY; goto endEntityValue; } *(pool->ptr)++ = 0xA; break; - case XML_TOK_CHAR_REF: - { - XML_Char buf[XML_ENCODE_MAX]; - int i; - int n = XmlCharRefNumber(enc, entityTextPtr); - if (n < 0) { - if (enc == encoding) - eventPtr = entityTextPtr; - result = XML_ERROR_BAD_CHAR_REF; - goto endEntityValue; - } - n = XmlEncode(n, (ICHAR *)buf); - if (!n) { - if (enc == encoding) - eventPtr = entityTextPtr; - result = XML_ERROR_BAD_CHAR_REF; + case XML_TOK_CHAR_REF: { + XML_Char buf[XML_ENCODE_MAX]; + int i; + int n = XmlCharRefNumber(enc, entityTextPtr); + if (n < 0) { + if (enc == parser->m_encoding) + parser->m_eventPtr = entityTextPtr; + result = XML_ERROR_BAD_CHAR_REF; + goto endEntityValue; + } + n = XmlEncode(n, (ICHAR *)buf); + /* The XmlEncode() functions can never return 0 here. That + * error return happens if the code point passed in is either + * negative or greater than or equal to 0x110000. The + * XmlCharRefNumber() functions will all return a number + * strictly less than 0x110000 or a negative value if an error + * occurred. The negative value is intercepted above, so + * XmlEncode() is never passed a value it might return an + * error for. + */ + for (i = 0; i < n; i++) { + if (pool->end == pool->ptr && ! poolGrow(pool)) { + result = XML_ERROR_NO_MEMORY; goto endEntityValue; } - for (i = 0; i < n; i++) { - if (pool->end == pool->ptr && !poolGrow(pool)) { - result = XML_ERROR_NO_MEMORY; - goto endEntityValue; - } - *(pool->ptr)++ = buf[i]; - } + *(pool->ptr)++ = buf[i]; } - break; + } break; case XML_TOK_PARTIAL: - if (enc == encoding) - eventPtr = entityTextPtr; + if (enc == parser->m_encoding) + parser->m_eventPtr = entityTextPtr; result = XML_ERROR_INVALID_TOKEN; goto endEntityValue; case XML_TOK_INVALID: - if (enc == encoding) - eventPtr = next; + if (enc == parser->m_encoding) + parser->m_eventPtr = next; result = XML_ERROR_INVALID_TOKEN; goto endEntityValue; default: - if (enc == encoding) - eventPtr = entityTextPtr; + /* This default case should be unnecessary -- all the tokens + * that XmlEntityValueTok() can return have their own explicit + * cases -- but should be retained for safety. We do however + * exclude it from the coverage statistics. + * + * LCOV_EXCL_START + */ + if (enc == parser->m_encoding) + parser->m_eventPtr = entityTextPtr; result = XML_ERROR_UNEXPECTED_STATE; goto endEntityValue; + /* LCOV_EXCL_STOP */ } entityTextPtr = next; } endEntityValue: #ifdef XML_DTD - prologState.inEntityValue = oldInEntityValue; + parser->m_prologState.inEntityValue = oldInEntityValue; #endif /* XML_DTD */ return result; } static void FASTCALL -normalizeLines(XML_Char *s) -{ +normalizeLines(XML_Char *s) { XML_Char *p; for (;; s++) { if (*s == XML_T('\0')) @@ -5329,8 +5641,7 @@ normalizeLines(XML_Char *s) *p++ = 0xA; if (*++s == 0xA) s++; - } - else + } else *p++ = *s++; } while (*s); *p = XML_T('\0'); @@ -5338,88 +5649,100 @@ normalizeLines(XML_Char *s) static int reportProcessingInstruction(XML_Parser parser, const ENCODING *enc, - const char *start, const char *end) -{ + const char *start, const char *end) { const XML_Char *target; XML_Char *data; const char *tem; - if (!processingInstructionHandler) { - if (defaultHandler) + if (! parser->m_processingInstructionHandler) { + if (parser->m_defaultHandler) reportDefault(parser, enc, start, end); return 1; } start += enc->minBytesPerChar * 2; tem = start + XmlNameLength(enc, start); - target = poolStoreString(&tempPool, enc, start, tem); - if (!target) + target = poolStoreString(&parser->m_tempPool, enc, start, tem); + if (! target) return 0; - poolFinish(&tempPool); - data = poolStoreString(&tempPool, enc, - XmlSkipS(enc, tem), - end - enc->minBytesPerChar*2); - if (!data) + poolFinish(&parser->m_tempPool); + data = poolStoreString(&parser->m_tempPool, enc, XmlSkipS(enc, tem), + end - enc->minBytesPerChar * 2); + if (! data) return 0; normalizeLines(data); - processingInstructionHandler(handlerArg, target, data); - poolClear(&tempPool); + parser->m_processingInstructionHandler(parser->m_handlerArg, target, data); + poolClear(&parser->m_tempPool); return 1; } static int -reportComment(XML_Parser parser, const ENCODING *enc, - const char *start, const char *end) -{ +reportComment(XML_Parser parser, const ENCODING *enc, const char *start, + const char *end) { XML_Char *data; - if (!commentHandler) { - if (defaultHandler) + if (! parser->m_commentHandler) { + if (parser->m_defaultHandler) reportDefault(parser, enc, start, end); return 1; } - data = poolStoreString(&tempPool, - enc, + data = poolStoreString(&parser->m_tempPool, enc, start + enc->minBytesPerChar * 4, end - enc->minBytesPerChar * 3); - if (!data) + if (! data) return 0; normalizeLines(data); - commentHandler(handlerArg, data); - poolClear(&tempPool); + parser->m_commentHandler(parser->m_handlerArg, data); + poolClear(&parser->m_tempPool); return 1; } static void -reportDefault(XML_Parser parser, const ENCODING *enc, - const char *s, const char *end) -{ +reportDefault(XML_Parser parser, const ENCODING *enc, const char *s, + const char *end) { if (MUST_CONVERT(enc, s)) { enum XML_Convert_Result convert_res; const char **eventPP; const char **eventEndPP; - if (enc == encoding) { - eventPP = &eventPtr; - eventEndPP = &eventEndPtr; - } - else { - eventPP = &(openInternalEntities->internalEventPtr); - eventEndPP = &(openInternalEntities->internalEventEndPtr); + if (enc == parser->m_encoding) { + eventPP = &parser->m_eventPtr; + eventEndPP = &parser->m_eventEndPtr; + } else { + /* To get here, two things must be true; the parser must be + * using a character encoding that is not the same as the + * encoding passed in, and the encoding passed in must need + * conversion to the internal format (UTF-8 unless XML_UNICODE + * is defined). The only occasions on which the encoding passed + * in is not the same as the parser's encoding are when it is + * the internal encoding (e.g. a previously defined parameter + * entity, already converted to internal format). This by + * definition doesn't need conversion, so the whole branch never + * gets executed. + * + * For safety's sake we don't delete these lines and merely + * exclude them from coverage statistics. + * + * LCOV_EXCL_START + */ + eventPP = &(parser->m_openInternalEntities->internalEventPtr); + eventEndPP = &(parser->m_openInternalEntities->internalEventEndPtr); + /* LCOV_EXCL_STOP */ } do { - ICHAR *dataPtr = (ICHAR *)dataBuf; - convert_res = XmlConvert(enc, &s, end, &dataPtr, (ICHAR *)dataBufEnd); + ICHAR *dataPtr = (ICHAR *)parser->m_dataBuf; + convert_res + = XmlConvert(enc, &s, end, &dataPtr, (ICHAR *)parser->m_dataBufEnd); *eventEndPP = s; - defaultHandler(handlerArg, dataBuf, (int)(dataPtr - (ICHAR *)dataBuf)); + parser->m_defaultHandler(parser->m_handlerArg, parser->m_dataBuf, + (int)(dataPtr - (ICHAR *)parser->m_dataBuf)); *eventPP = s; - } while ((convert_res != XML_CONVERT_COMPLETED) && (convert_res != XML_CONVERT_INPUT_INCOMPLETE)); - } - else - defaultHandler(handlerArg, (XML_Char *)s, (int)((XML_Char *)end - (XML_Char *)s)); + } while ((convert_res != XML_CONVERT_COMPLETED) + && (convert_res != XML_CONVERT_INPUT_INCOMPLETE)); + } else + parser->m_defaultHandler(parser->m_handlerArg, (XML_Char *)s, + (int)((XML_Char *)end - (XML_Char *)s)); } - static int defineAttribute(ELEMENT_TYPE *type, ATTRIBUTE_ID *attId, XML_Bool isCdata, - XML_Bool isId, const XML_Char *value, XML_Parser parser) -{ + XML_Bool isId, const XML_Char *value, XML_Parser parser) { DEFAULT_ATTRIBUTE *att; if (value || isId) { /* The handling of default attributes gets messed up if we have @@ -5428,22 +5751,23 @@ defineAttribute(ELEMENT_TYPE *type, ATTRIBUTE_ID *attId, XML_Bool isCdata, for (i = 0; i < type->nDefaultAtts; i++) if (attId == type->defaultAtts[i].id) return 1; - if (isId && !type->idAtt && !attId->xmlns) + if (isId && ! type->idAtt && ! attId->xmlns) type->idAtt = attId; } if (type->nDefaultAtts == type->allocDefaultAtts) { if (type->allocDefaultAtts == 0) { type->allocDefaultAtts = 8; - type->defaultAtts = (DEFAULT_ATTRIBUTE *)MALLOC(type->allocDefaultAtts - * sizeof(DEFAULT_ATTRIBUTE)); - if (!type->defaultAtts) + type->defaultAtts = (DEFAULT_ATTRIBUTE *)MALLOC( + parser, type->allocDefaultAtts * sizeof(DEFAULT_ATTRIBUTE)); + if (! type->defaultAtts) { + type->allocDefaultAtts = 0; return 0; - } - else { + } + } else { DEFAULT_ATTRIBUTE *temp; int count = type->allocDefaultAtts * 2; - temp = (DEFAULT_ATTRIBUTE *) - REALLOC(type->defaultAtts, (count * sizeof(DEFAULT_ATTRIBUTE))); + temp = (DEFAULT_ATTRIBUTE *)REALLOC(parser, type->defaultAtts, + (count * sizeof(DEFAULT_ATTRIBUTE))); if (temp == NULL) return 0; type->allocDefaultAtts = count; @@ -5454,92 +5778,89 @@ defineAttribute(ELEMENT_TYPE *type, ATTRIBUTE_ID *attId, XML_Bool isCdata, att->id = attId; att->value = value; att->isCdata = isCdata; - if (!isCdata) + if (! isCdata) attId->maybeTokenized = XML_TRUE; type->nDefaultAtts += 1; return 1; } static int -setElementTypePrefix(XML_Parser parser, ELEMENT_TYPE *elementType) -{ - DTD * const dtd = _dtd; /* save one level of indirection */ +setElementTypePrefix(XML_Parser parser, ELEMENT_TYPE *elementType) { + DTD *const dtd = parser->m_dtd; /* save one level of indirection */ const XML_Char *name; for (name = elementType->name; *name; name++) { if (*name == XML_T(ASCII_COLON)) { PREFIX *prefix; const XML_Char *s; for (s = elementType->name; s != name; s++) { - if (!poolAppendChar(&dtd->pool, *s)) + if (! poolAppendChar(&dtd->pool, *s)) return 0; } - if (!poolAppendChar(&dtd->pool, XML_T('\0'))) + if (! poolAppendChar(&dtd->pool, XML_T('\0'))) return 0; prefix = (PREFIX *)lookup(parser, &dtd->prefixes, poolStart(&dtd->pool), sizeof(PREFIX)); - if (!prefix) + if (! prefix) return 0; if (prefix->name == poolStart(&dtd->pool)) poolFinish(&dtd->pool); else poolDiscard(&dtd->pool); elementType->prefix = prefix; - + break; } } return 1; } static ATTRIBUTE_ID * -getAttributeId(XML_Parser parser, const ENCODING *enc, - const char *start, const char *end) -{ - DTD * const dtd = _dtd; /* save one level of indirection */ +getAttributeId(XML_Parser parser, const ENCODING *enc, const char *start, + const char *end) { + DTD *const dtd = parser->m_dtd; /* save one level of indirection */ ATTRIBUTE_ID *id; const XML_Char *name; - if (!poolAppendChar(&dtd->pool, XML_T('\0'))) + if (! poolAppendChar(&dtd->pool, XML_T('\0'))) return NULL; name = poolStoreString(&dtd->pool, enc, start, end); - if (!name) + if (! name) return NULL; /* skip quotation mark - its storage will be re-used (like in name[-1]) */ ++name; - id = (ATTRIBUTE_ID *)lookup(parser, &dtd->attributeIds, name, sizeof(ATTRIBUTE_ID)); - if (!id) + id = (ATTRIBUTE_ID *)lookup(parser, &dtd->attributeIds, name, + sizeof(ATTRIBUTE_ID)); + if (! id) return NULL; if (id->name != name) poolDiscard(&dtd->pool); else { poolFinish(&dtd->pool); - if (!ns) + if (! parser->m_ns) ; - else if (name[0] == XML_T(ASCII_x) - && name[1] == XML_T(ASCII_m) - && name[2] == XML_T(ASCII_l) - && name[3] == XML_T(ASCII_n) - && name[4] == XML_T(ASCII_s) - && (name[5] == XML_T('\0') || name[5] == XML_T(ASCII_COLON))) { + else if (name[0] == XML_T(ASCII_x) && name[1] == XML_T(ASCII_m) + && name[2] == XML_T(ASCII_l) && name[3] == XML_T(ASCII_n) + && name[4] == XML_T(ASCII_s) + && (name[5] == XML_T('\0') || name[5] == XML_T(ASCII_COLON))) { if (name[5] == XML_T('\0')) id->prefix = &dtd->defaultPrefix; else - id->prefix = (PREFIX *)lookup(parser, &dtd->prefixes, name + 6, sizeof(PREFIX)); + id->prefix = (PREFIX *)lookup(parser, &dtd->prefixes, name + 6, + sizeof(PREFIX)); id->xmlns = XML_TRUE; - } - else { + } else { int i; for (i = 0; name[i]; i++) { /* attributes without prefix are *not* in the default namespace */ if (name[i] == XML_T(ASCII_COLON)) { int j; for (j = 0; j < i; j++) { - if (!poolAppendChar(&dtd->pool, name[j])) + if (! poolAppendChar(&dtd->pool, name[j])) return NULL; } - if (!poolAppendChar(&dtd->pool, XML_T('\0'))) + if (! poolAppendChar(&dtd->pool, XML_T('\0'))) return NULL; - id->prefix = (PREFIX *)lookup(parser, &dtd->prefixes, poolStart(&dtd->pool), - sizeof(PREFIX)); - if (!id->prefix) + id->prefix = (PREFIX *)lookup(parser, &dtd->prefixes, + poolStart(&dtd->pool), sizeof(PREFIX)); + if (! id->prefix) return NULL; if (id->prefix->name == poolStart(&dtd->pool)) poolFinish(&dtd->pool); @@ -5556,23 +5877,44 @@ getAttributeId(XML_Parser parser, const ENCODING *enc, #define CONTEXT_SEP XML_T(ASCII_FF) static const XML_Char * -getContext(XML_Parser parser) -{ - DTD * const dtd = _dtd; /* save one level of indirection */ +getContext(XML_Parser parser) { + DTD *const dtd = parser->m_dtd; /* save one level of indirection */ HASH_TABLE_ITER iter; XML_Bool needSep = XML_FALSE; if (dtd->defaultPrefix.binding) { int i; int len; - if (!poolAppendChar(&tempPool, XML_T(ASCII_EQUALS))) + if (! poolAppendChar(&parser->m_tempPool, XML_T(ASCII_EQUALS))) return NULL; len = dtd->defaultPrefix.binding->uriLen; - if (namespaceSeparator) + if (parser->m_namespaceSeparator) len--; - for (i = 0; i < len; i++) - if (!poolAppendChar(&tempPool, dtd->defaultPrefix.binding->uri[i])) - return NULL; + for (i = 0; i < len; i++) { + if (! poolAppendChar(&parser->m_tempPool, + dtd->defaultPrefix.binding->uri[i])) { + /* Because of memory caching, I don't believe this line can be + * executed. + * + * This is part of a loop copying the default prefix binding + * URI into the parser's temporary string pool. Previously, + * that URI was copied into the same string pool, with a + * terminating NUL character, as part of setContext(). When + * the pool was cleared, that leaves a block definitely big + * enough to hold the URI on the free block list of the pool. + * The URI copy in getContext() therefore cannot run out of + * memory. + * + * If the pool is used between the setContext() and + * getContext() calls, the worst it can do is leave a bigger + * block on the front of the free list. Given that this is + * all somewhat inobvious and program logic can be changed, we + * don't delete the line but we do exclude it from the test + * coverage statistics. + */ + return NULL; /* LCOV_EXCL_LINE */ + } + } needSep = XML_TRUE; } @@ -5582,102 +5924,107 @@ getContext(XML_Parser parser) int len; const XML_Char *s; PREFIX *prefix = (PREFIX *)hashTableIterNext(&iter); - if (!prefix) + if (! prefix) break; - if (!prefix->binding) - continue; - if (needSep && !poolAppendChar(&tempPool, CONTEXT_SEP)) + if (! prefix->binding) { + /* This test appears to be (justifiable) paranoia. There does + * not seem to be a way of injecting a prefix without a binding + * that doesn't get errored long before this function is called. + * The test should remain for safety's sake, so we instead + * exclude the following line from the coverage statistics. + */ + continue; /* LCOV_EXCL_LINE */ + } + if (needSep && ! poolAppendChar(&parser->m_tempPool, CONTEXT_SEP)) return NULL; for (s = prefix->name; *s; s++) - if (!poolAppendChar(&tempPool, *s)) + if (! poolAppendChar(&parser->m_tempPool, *s)) return NULL; - if (!poolAppendChar(&tempPool, XML_T(ASCII_EQUALS))) + if (! poolAppendChar(&parser->m_tempPool, XML_T(ASCII_EQUALS))) return NULL; len = prefix->binding->uriLen; - if (namespaceSeparator) + if (parser->m_namespaceSeparator) len--; for (i = 0; i < len; i++) - if (!poolAppendChar(&tempPool, prefix->binding->uri[i])) + if (! poolAppendChar(&parser->m_tempPool, prefix->binding->uri[i])) return NULL; needSep = XML_TRUE; } - hashTableIterInit(&iter, &(dtd->generalEntities)); for (;;) { const XML_Char *s; ENTITY *e = (ENTITY *)hashTableIterNext(&iter); - if (!e) + if (! e) break; - if (!e->open) + if (! e->open) continue; - if (needSep && !poolAppendChar(&tempPool, CONTEXT_SEP)) + if (needSep && ! poolAppendChar(&parser->m_tempPool, CONTEXT_SEP)) return NULL; for (s = e->name; *s; s++) - if (!poolAppendChar(&tempPool, *s)) + if (! poolAppendChar(&parser->m_tempPool, *s)) return 0; needSep = XML_TRUE; } - if (!poolAppendChar(&tempPool, XML_T('\0'))) + if (! poolAppendChar(&parser->m_tempPool, XML_T('\0'))) return NULL; - return tempPool.start; + return parser->m_tempPool.start; } static XML_Bool -setContext(XML_Parser parser, const XML_Char *context) -{ - DTD * const dtd = _dtd; /* save one level of indirection */ +setContext(XML_Parser parser, const XML_Char *context) { + DTD *const dtd = parser->m_dtd; /* save one level of indirection */ const XML_Char *s = context; while (*context != XML_T('\0')) { if (*s == CONTEXT_SEP || *s == XML_T('\0')) { ENTITY *e; - if (!poolAppendChar(&tempPool, XML_T('\0'))) + if (! poolAppendChar(&parser->m_tempPool, XML_T('\0'))) return XML_FALSE; - e = (ENTITY *)lookup(parser, &dtd->generalEntities, poolStart(&tempPool), 0); + e = (ENTITY *)lookup(parser, &dtd->generalEntities, + poolStart(&parser->m_tempPool), 0); if (e) e->open = XML_TRUE; if (*s != XML_T('\0')) s++; context = s; - poolDiscard(&tempPool); - } - else if (*s == XML_T(ASCII_EQUALS)) { + poolDiscard(&parser->m_tempPool); + } else if (*s == XML_T(ASCII_EQUALS)) { PREFIX *prefix; - if (poolLength(&tempPool) == 0) + if (poolLength(&parser->m_tempPool) == 0) prefix = &dtd->defaultPrefix; else { - if (!poolAppendChar(&tempPool, XML_T('\0'))) + if (! poolAppendChar(&parser->m_tempPool, XML_T('\0'))) return XML_FALSE; - prefix = (PREFIX *)lookup(parser, &dtd->prefixes, poolStart(&tempPool), - sizeof(PREFIX)); - if (!prefix) + prefix + = (PREFIX *)lookup(parser, &dtd->prefixes, + poolStart(&parser->m_tempPool), sizeof(PREFIX)); + if (! prefix) return XML_FALSE; - if (prefix->name == poolStart(&tempPool)) { + if (prefix->name == poolStart(&parser->m_tempPool)) { prefix->name = poolCopyString(&dtd->pool, prefix->name); - if (!prefix->name) + if (! prefix->name) return XML_FALSE; } - poolDiscard(&tempPool); + poolDiscard(&parser->m_tempPool); } - for (context = s + 1; - *context != CONTEXT_SEP && *context != XML_T('\0'); + for (context = s + 1; *context != CONTEXT_SEP && *context != XML_T('\0'); context++) - if (!poolAppendChar(&tempPool, *context)) + if (! poolAppendChar(&parser->m_tempPool, *context)) return XML_FALSE; - if (!poolAppendChar(&tempPool, XML_T('\0'))) + if (! poolAppendChar(&parser->m_tempPool, XML_T('\0'))) return XML_FALSE; - if (addBinding(parser, prefix, NULL, poolStart(&tempPool), - &inheritedBindings) != XML_ERROR_NONE) + if (addBinding(parser, prefix, NULL, poolStart(&parser->m_tempPool), + &parser->m_inheritedBindings) + != XML_ERROR_NONE) return XML_FALSE; - poolDiscard(&tempPool); + poolDiscard(&parser->m_tempPool); if (*context != XML_T('\0')) ++context; s = context; - } - else { - if (!poolAppendChar(&tempPool, *s)) + } else { + if (! poolAppendChar(&parser->m_tempPool, *s)) return XML_FALSE; s++; } @@ -5686,8 +6033,7 @@ setContext(XML_Parser parser, const XML_Char *context) } static void FASTCALL -normalizePublicId(XML_Char *publicId) -{ +normalizePublicId(XML_Char *publicId) { XML_Char *p = publicId; XML_Char *s; for (s = publicId; *s; s++) { @@ -5708,8 +6054,7 @@ normalizePublicId(XML_Char *publicId) } static DTD * -dtdCreate(const XML_Memory_Handling_Suite *ms) -{ +dtdCreate(const XML_Memory_Handling_Suite *ms) { DTD *p = (DTD *)ms->malloc_fcn(sizeof(DTD)); if (p == NULL) return p; @@ -5741,13 +6086,12 @@ dtdCreate(const XML_Memory_Handling_Suite *ms) } static void -dtdReset(DTD *p, const XML_Memory_Handling_Suite *ms) -{ +dtdReset(DTD *p, const XML_Memory_Handling_Suite *ms) { HASH_TABLE_ITER iter; hashTableIterInit(&iter, &(p->elementTypes)); for (;;) { ELEMENT_TYPE *e = (ELEMENT_TYPE *)hashTableIterNext(&iter); - if (!e) + if (! e) break; if (e->allocDefaultAtts != 0) ms->free_fcn(e->defaultAtts); @@ -5783,13 +6127,12 @@ dtdReset(DTD *p, const XML_Memory_Handling_Suite *ms) } static void -dtdDestroy(DTD *p, XML_Bool isDocEntity, const XML_Memory_Handling_Suite *ms) -{ +dtdDestroy(DTD *p, XML_Bool isDocEntity, const XML_Memory_Handling_Suite *ms) { HASH_TABLE_ITER iter; hashTableIterInit(&iter, &(p->elementTypes)); for (;;) { ELEMENT_TYPE *e = (ELEMENT_TYPE *)hashTableIterNext(&iter); - if (!e) + if (! e) break; if (e->allocDefaultAtts != 0) ms->free_fcn(e->defaultAtts); @@ -5814,8 +6157,8 @@ dtdDestroy(DTD *p, XML_Bool isDocEntity, const XML_Memory_Handling_Suite *ms) The new DTD has already been initialized. */ static int -dtdCopy(XML_Parser oldParser, DTD *newDtd, const DTD *oldDtd, const XML_Memory_Handling_Suite *ms) -{ +dtdCopy(XML_Parser oldParser, DTD *newDtd, const DTD *oldDtd, + const XML_Memory_Handling_Suite *ms) { HASH_TABLE_ITER iter; /* Copy the prefix table. */ @@ -5824,12 +6167,12 @@ dtdCopy(XML_Parser oldParser, DTD *newDtd, const DTD *oldDtd, const XML_Memory_H for (;;) { const XML_Char *name; const PREFIX *oldP = (PREFIX *)hashTableIterNext(&iter); - if (!oldP) + if (! oldP) break; name = poolCopyString(&(newDtd->pool), oldP->name); - if (!name) + if (! name) return 0; - if (!lookup(oldParser, &(newDtd->prefixes), name, sizeof(PREFIX))) + if (! lookup(oldParser, &(newDtd->prefixes), name, sizeof(PREFIX))) return 0; } @@ -5842,18 +6185,18 @@ dtdCopy(XML_Parser oldParser, DTD *newDtd, const DTD *oldDtd, const XML_Memory_H const XML_Char *name; const ATTRIBUTE_ID *oldA = (ATTRIBUTE_ID *)hashTableIterNext(&iter); - if (!oldA) + if (! oldA) break; /* Remember to allocate the scratch byte before the name. */ - if (!poolAppendChar(&(newDtd->pool), XML_T('\0'))) + if (! poolAppendChar(&(newDtd->pool), XML_T('\0'))) return 0; name = poolCopyString(&(newDtd->pool), oldA->name); - if (!name) + if (! name) return 0; ++name; newA = (ATTRIBUTE_ID *)lookup(oldParser, &(newDtd->attributeIds), name, sizeof(ATTRIBUTE_ID)); - if (!newA) + if (! newA) return 0; newA->maybeTokenized = oldA->maybeTokenized; if (oldA->prefix) { @@ -5875,57 +6218,52 @@ dtdCopy(XML_Parser oldParser, DTD *newDtd, const DTD *oldDtd, const XML_Memory_H ELEMENT_TYPE *newE; const XML_Char *name; const ELEMENT_TYPE *oldE = (ELEMENT_TYPE *)hashTableIterNext(&iter); - if (!oldE) + if (! oldE) break; name = poolCopyString(&(newDtd->pool), oldE->name); - if (!name) + if (! name) return 0; newE = (ELEMENT_TYPE *)lookup(oldParser, &(newDtd->elementTypes), name, sizeof(ELEMENT_TYPE)); - if (!newE) + if (! newE) return 0; if (oldE->nDefaultAtts) { - newE->defaultAtts = (DEFAULT_ATTRIBUTE *) - ms->malloc_fcn(oldE->nDefaultAtts * sizeof(DEFAULT_ATTRIBUTE)); - if (!newE->defaultAtts) { + newE->defaultAtts = (DEFAULT_ATTRIBUTE *)ms->malloc_fcn( + oldE->nDefaultAtts * sizeof(DEFAULT_ATTRIBUTE)); + if (! newE->defaultAtts) { return 0; } } if (oldE->idAtt) - newE->idAtt = (ATTRIBUTE_ID *) - lookup(oldParser, &(newDtd->attributeIds), oldE->idAtt->name, 0); + newE->idAtt = (ATTRIBUTE_ID *)lookup(oldParser, &(newDtd->attributeIds), + oldE->idAtt->name, 0); newE->allocDefaultAtts = newE->nDefaultAtts = oldE->nDefaultAtts; if (oldE->prefix) newE->prefix = (PREFIX *)lookup(oldParser, &(newDtd->prefixes), oldE->prefix->name, 0); for (i = 0; i < newE->nDefaultAtts; i++) { - newE->defaultAtts[i].id = (ATTRIBUTE_ID *) - lookup(oldParser, &(newDtd->attributeIds), oldE->defaultAtts[i].id->name, 0); + newE->defaultAtts[i].id = (ATTRIBUTE_ID *)lookup( + oldParser, &(newDtd->attributeIds), oldE->defaultAtts[i].id->name, 0); newE->defaultAtts[i].isCdata = oldE->defaultAtts[i].isCdata; if (oldE->defaultAtts[i].value) { newE->defaultAtts[i].value = poolCopyString(&(newDtd->pool), oldE->defaultAtts[i].value); - if (!newE->defaultAtts[i].value) + if (! newE->defaultAtts[i].value) return 0; - } - else + } else newE->defaultAtts[i].value = NULL; } } /* Copy the entity tables. */ - if (!copyEntityTable(oldParser, - &(newDtd->generalEntities), - &(newDtd->pool), - &(oldDtd->generalEntities))) - return 0; + if (! copyEntityTable(oldParser, &(newDtd->generalEntities), &(newDtd->pool), + &(oldDtd->generalEntities))) + return 0; #ifdef XML_DTD - if (!copyEntityTable(oldParser, - &(newDtd->paramEntities), - &(newDtd->pool), - &(oldDtd->paramEntities))) - return 0; + if (! copyEntityTable(oldParser, &(newDtd->paramEntities), &(newDtd->pool), + &(oldDtd->paramEntities))) + return 0; newDtd->paramEntityRead = oldDtd->paramEntityRead; #endif /* XML_DTD */ @@ -5942,14 +6280,11 @@ dtdCopy(XML_Parser oldParser, DTD *newDtd, const DTD *oldDtd, const XML_Memory_H newDtd->scaffIndex = oldDtd->scaffIndex; return 1; -} /* End dtdCopy */ +} /* End dtdCopy */ static int -copyEntityTable(XML_Parser oldParser, - HASH_TABLE *newTable, - STRING_POOL *newPool, - const HASH_TABLE *oldTable) -{ +copyEntityTable(XML_Parser oldParser, HASH_TABLE *newTable, + STRING_POOL *newPool, const HASH_TABLE *oldTable) { HASH_TABLE_ITER iter; const XML_Char *cachedOldBase = NULL; const XML_Char *cachedNewBase = NULL; @@ -5960,17 +6295,17 @@ copyEntityTable(XML_Parser oldParser, ENTITY *newE; const XML_Char *name; const ENTITY *oldE = (ENTITY *)hashTableIterNext(&iter); - if (!oldE) + if (! oldE) break; name = poolCopyString(newPool, oldE->name); - if (!name) + if (! name) return 0; newE = (ENTITY *)lookup(oldParser, newTable, name, sizeof(ENTITY)); - if (!newE) + if (! newE) return 0; if (oldE->systemId) { const XML_Char *tem = poolCopyString(newPool, oldE->systemId); - if (!tem) + if (! tem) return 0; newE->systemId = tem; if (oldE->base) { @@ -5979,29 +6314,28 @@ copyEntityTable(XML_Parser oldParser, else { cachedOldBase = oldE->base; tem = poolCopyString(newPool, cachedOldBase); - if (!tem) + if (! tem) return 0; cachedNewBase = newE->base = tem; } } if (oldE->publicId) { tem = poolCopyString(newPool, oldE->publicId); - if (!tem) + if (! tem) return 0; newE->publicId = tem; } - } - else { - const XML_Char *tem = poolCopyStringN(newPool, oldE->textPtr, - oldE->textLen); - if (!tem) + } else { + const XML_Char *tem + = poolCopyStringN(newPool, oldE->textPtr, oldE->textLen); + if (! tem) return 0; newE->textPtr = tem; newE->textLen = oldE->textLen; } if (oldE->notation) { const XML_Char *tem = poolCopyString(newPool, oldE->notation); - if (!tem) + if (! tem) return 0; newE->notation = tem; } @@ -6014,44 +6348,57 @@ copyEntityTable(XML_Parser oldParser, #define INIT_POWER 6 static XML_Bool FASTCALL -keyeq(KEY s1, KEY s2) -{ +keyeq(KEY s1, KEY s2) { for (; *s1 == *s2; s1++, s2++) if (*s1 == 0) return XML_TRUE; return XML_FALSE; } +static size_t +keylen(KEY s) { + size_t len = 0; + for (; *s; s++, len++) + ; + return len; +} + +static void +copy_salt_to_sipkey(XML_Parser parser, struct sipkey *key) { + key->k[0] = 0; + key->k[1] = get_hash_secret_salt(parser); +} + static unsigned long FASTCALL -hash(XML_Parser parser, KEY s) -{ - unsigned long h = hash_secret_salt; - while (*s) - h = CHAR_HASH(h, *s++); - return h; +hash(XML_Parser parser, KEY s) { + struct siphash state; + struct sipkey key; + (void)sip24_valid; + copy_salt_to_sipkey(parser, &key); + sip24_init(&state, &key); + sip24_update(&state, s, keylen(s) * sizeof(XML_Char)); + return (unsigned long)sip24_final(&state); } static NAMED * -lookup(XML_Parser parser, HASH_TABLE *table, KEY name, size_t createSize) -{ +lookup(XML_Parser parser, HASH_TABLE *table, KEY name, size_t createSize) { size_t i; if (table->size == 0) { size_t tsize; - if (!createSize) + if (! createSize) return NULL; table->power = INIT_POWER; /* table->size is a power of 2 */ table->size = (size_t)1 << INIT_POWER; tsize = table->size * sizeof(NAMED *); table->v = (NAMED **)table->mem->malloc_fcn(tsize); - if (!table->v) { + if (! table->v) { table->size = 0; return NULL; } memset(table->v, 0, tsize); i = hash(parser, name) & ((unsigned long)table->size - 1); - } - else { + } else { unsigned long h = hash(parser, name); unsigned long mask = (unsigned long)table->size - 1; unsigned char step = 0; @@ -6059,11 +6406,11 @@ lookup(XML_Parser parser, HASH_TABLE *table, KEY name, size_t createSize) while (table->v[i]) { if (keyeq(name, table->v[i]->name)) return table->v[i]; - if (!step) + if (! step) step = PROBE_STEP(h, mask, table->power); i < step ? (i += table->size - step) : (i -= step); } - if (!createSize) + if (! createSize) return NULL; /* check for overflow (table is half full) */ @@ -6073,7 +6420,7 @@ lookup(XML_Parser parser, HASH_TABLE *table, KEY name, size_t createSize) unsigned long newMask = (unsigned long)newSize - 1; size_t tsize = newSize * sizeof(NAMED *); NAMED **newV = (NAMED **)table->mem->malloc_fcn(tsize); - if (!newV) + if (! newV) return NULL; memset(newV, 0, tsize); for (i = 0; i < table->size; i++) @@ -6082,7 +6429,7 @@ lookup(XML_Parser parser, HASH_TABLE *table, KEY name, size_t createSize) size_t j = newHash & newMask; step = 0; while (newV[j]) { - if (!step) + if (! step) step = PROBE_STEP(newHash, newMask, newPower); j < step ? (j += newSize - step) : (j -= step); } @@ -6095,14 +6442,14 @@ lookup(XML_Parser parser, HASH_TABLE *table, KEY name, size_t createSize) i = h & newMask; step = 0; while (table->v[i]) { - if (!step) + if (! step) step = PROBE_STEP(h, newMask, newPower); i < step ? (i += newSize - step) : (i -= step); } } } table->v[i] = (NAMED *)table->mem->malloc_fcn(createSize); - if (!table->v[i]) + if (! table->v[i]) return NULL; memset(table->v[i], 0, createSize); table->v[i]->name = name; @@ -6111,8 +6458,7 @@ lookup(XML_Parser parser, HASH_TABLE *table, KEY name, size_t createSize) } static void FASTCALL -hashTableClear(HASH_TABLE *table) -{ +hashTableClear(HASH_TABLE *table) { size_t i; for (i = 0; i < table->size; i++) { table->mem->free_fcn(table->v[i]); @@ -6122,8 +6468,7 @@ hashTableClear(HASH_TABLE *table) } static void FASTCALL -hashTableDestroy(HASH_TABLE *table) -{ +hashTableDestroy(HASH_TABLE *table) { size_t i; for (i = 0; i < table->size; i++) table->mem->free_fcn(table->v[i]); @@ -6131,8 +6476,7 @@ hashTableDestroy(HASH_TABLE *table) } static void FASTCALL -hashTableInit(HASH_TABLE *p, const XML_Memory_Handling_Suite *ms) -{ +hashTableInit(HASH_TABLE *p, const XML_Memory_Handling_Suite *ms) { p->power = 0; p->size = 0; p->used = 0; @@ -6141,15 +6485,13 @@ hashTableInit(HASH_TABLE *p, const XML_Memory_Handling_Suite *ms) } static void FASTCALL -hashTableIterInit(HASH_TABLE_ITER *iter, const HASH_TABLE *table) -{ +hashTableIterInit(HASH_TABLE_ITER *iter, const HASH_TABLE *table) { iter->p = table->v; iter->end = iter->p + table->size; } -static NAMED * FASTCALL -hashTableIterNext(HASH_TABLE_ITER *iter) -{ +static NAMED *FASTCALL +hashTableIterNext(HASH_TABLE_ITER *iter) { while (iter->p != iter->end) { NAMED *tem = *(iter->p)++; if (tem) @@ -6159,8 +6501,7 @@ hashTableIterNext(HASH_TABLE_ITER *iter) } static void FASTCALL -poolInit(STRING_POOL *pool, const XML_Memory_Handling_Suite *ms) -{ +poolInit(STRING_POOL *pool, const XML_Memory_Handling_Suite *ms) { pool->blocks = NULL; pool->freeBlocks = NULL; pool->start = NULL; @@ -6170,9 +6511,8 @@ poolInit(STRING_POOL *pool, const XML_Memory_Handling_Suite *ms) } static void FASTCALL -poolClear(STRING_POOL *pool) -{ - if (!pool->freeBlocks) +poolClear(STRING_POOL *pool) { + if (! pool->freeBlocks) pool->freeBlocks = pool->blocks; else { BLOCK *p = pool->blocks; @@ -6190,8 +6530,7 @@ poolClear(STRING_POOL *pool) } static void FASTCALL -poolDestroy(STRING_POOL *pool) -{ +poolDestroy(STRING_POOL *pool) { BLOCK *p = pool->blocks; while (p) { BLOCK *tem = p->next; @@ -6207,26 +6546,26 @@ poolDestroy(STRING_POOL *pool) } static XML_Char * -poolAppend(STRING_POOL *pool, const ENCODING *enc, - const char *ptr, const char *end) -{ - if (!pool->ptr && !poolGrow(pool)) +poolAppend(STRING_POOL *pool, const ENCODING *enc, const char *ptr, + const char *end) { + if (! pool->ptr && ! poolGrow(pool)) return NULL; for (;;) { - const enum XML_Convert_Result convert_res = XmlConvert(enc, &ptr, end, (ICHAR **)&(pool->ptr), (ICHAR *)pool->end); - if ((convert_res == XML_CONVERT_COMPLETED) || (convert_res == XML_CONVERT_INPUT_INCOMPLETE)) + const enum XML_Convert_Result convert_res = XmlConvert( + enc, &ptr, end, (ICHAR **)&(pool->ptr), (ICHAR *)pool->end); + if ((convert_res == XML_CONVERT_COMPLETED) + || (convert_res == XML_CONVERT_INPUT_INCOMPLETE)) break; - if (!poolGrow(pool)) + if (! poolGrow(pool)) return NULL; } return pool->start; } -static const XML_Char * FASTCALL -poolCopyString(STRING_POOL *pool, const XML_Char *s) -{ +static const XML_Char *FASTCALL +poolCopyString(STRING_POOL *pool, const XML_Char *s) { do { - if (!poolAppendChar(pool, *s)) + if (! poolAppendChar(pool, *s)) return NULL; } while (*s++); s = pool->start; @@ -6235,12 +6574,23 @@ poolCopyString(STRING_POOL *pool, const XML_Char *s) } static const XML_Char * -poolCopyStringN(STRING_POOL *pool, const XML_Char *s, int n) -{ - if (!pool->ptr && !poolGrow(pool)) - return NULL; +poolCopyStringN(STRING_POOL *pool, const XML_Char *s, int n) { + if (! pool->ptr && ! poolGrow(pool)) { + /* The following line is unreachable given the current usage of + * poolCopyStringN(). Currently it is called from exactly one + * place to copy the text of a simple general entity. By that + * point, the name of the entity is already stored in the pool, so + * pool->ptr cannot be NULL. + * + * If poolCopyStringN() is used elsewhere as it well might be, + * this line may well become executable again. Regardless, this + * sort of check shouldn't be removed lightly, so we just exclude + * it from the coverage statistics. + */ + return NULL; /* LCOV_EXCL_LINE */ + } for (; n > 0; --n, s++) { - if (!poolAppendChar(pool, *s)) + if (! poolAppendChar(pool, *s)) return NULL; } s = pool->start; @@ -6248,11 +6598,10 @@ poolCopyStringN(STRING_POOL *pool, const XML_Char *s, int n) return s; } -static const XML_Char * FASTCALL -poolAppendString(STRING_POOL *pool, const XML_Char *s) -{ +static const XML_Char *FASTCALL +poolAppendString(STRING_POOL *pool, const XML_Char *s) { while (*s) { - if (!poolAppendChar(pool, *s)) + if (! poolAppendChar(pool, *s)) return NULL; s++; } @@ -6260,20 +6609,46 @@ poolAppendString(STRING_POOL *pool, const XML_Char *s) } static XML_Char * -poolStoreString(STRING_POOL *pool, const ENCODING *enc, - const char *ptr, const char *end) -{ - if (!poolAppend(pool, enc, ptr, end)) +poolStoreString(STRING_POOL *pool, const ENCODING *enc, const char *ptr, + const char *end) { + if (! poolAppend(pool, enc, ptr, end)) return NULL; - if (pool->ptr == pool->end && !poolGrow(pool)) + if (pool->ptr == pool->end && ! poolGrow(pool)) return NULL; *(pool->ptr)++ = 0; return pool->start; } +static size_t +poolBytesToAllocateFor(int blockSize) { + /* Unprotected math would be: + ** return offsetof(BLOCK, s) + blockSize * sizeof(XML_Char); + ** + ** Detect overflow, avoiding _signed_ overflow undefined behavior + ** For a + b * c we check b * c in isolation first, so that addition of a + ** on top has no chance of making us accept a small non-negative number + */ + const size_t stretch = sizeof(XML_Char); /* can be 4 bytes */ + + if (blockSize <= 0) + return 0; + + if (blockSize > (int)(INT_MAX / stretch)) + return 0; + + { + const int stretchedBlockSize = blockSize * (int)stretch; + const int bytesToAllocate + = (int)(offsetof(BLOCK, s) + (unsigned)stretchedBlockSize); + if (bytesToAllocate < 0) + return 0; + + return (size_t)bytesToAllocate; + } +} + static XML_Bool FASTCALL -poolGrow(STRING_POOL *pool) -{ +poolGrow(STRING_POOL *pool) { if (pool->freeBlocks) { if (pool->start == 0) { pool->blocks = pool->freeBlocks; @@ -6299,44 +6674,76 @@ poolGrow(STRING_POOL *pool) } if (pool->blocks && pool->start == pool->blocks->s) { BLOCK *temp; - int blockSize = (int)((unsigned)(pool->end - pool->start)*2U); + int blockSize = (int)((unsigned)(pool->end - pool->start) * 2U); + size_t bytesToAllocate; + + /* NOTE: Needs to be calculated prior to calling `realloc` + to avoid dangling pointers: */ + const ptrdiff_t offsetInsideBlock = pool->ptr - pool->start; + + if (blockSize < 0) { + /* This condition traps a situation where either more than + * INT_MAX/2 bytes have already been allocated. This isn't + * readily testable, since it is unlikely that an average + * machine will have that much memory, so we exclude it from the + * coverage statistics. + */ + return XML_FALSE; /* LCOV_EXCL_LINE */ + } - if (blockSize < 0) + bytesToAllocate = poolBytesToAllocateFor(blockSize); + if (bytesToAllocate == 0) return XML_FALSE; - temp = (BLOCK *) - pool->mem->realloc_fcn(pool->blocks, - (offsetof(BLOCK, s) - + blockSize * sizeof(XML_Char))); + temp = (BLOCK *)pool->mem->realloc_fcn(pool->blocks, + (unsigned)bytesToAllocate); if (temp == NULL) return XML_FALSE; pool->blocks = temp; pool->blocks->size = blockSize; - pool->ptr = pool->blocks->s + (pool->ptr - pool->start); + pool->ptr = pool->blocks->s + offsetInsideBlock; pool->start = pool->blocks->s; pool->end = pool->start + blockSize; - } - else { + } else { BLOCK *tem; int blockSize = (int)(pool->end - pool->start); - - if (blockSize < 0) - return XML_FALSE; + size_t bytesToAllocate; + + if (blockSize < 0) { + /* This condition traps a situation where either more than + * INT_MAX bytes have already been allocated (which is prevented + * by various pieces of program logic, not least this one, never + * mind the unlikelihood of actually having that much memory) or + * the pool control fields have been corrupted (which could + * conceivably happen in an extremely buggy user handler + * function). Either way it isn't readily testable, so we + * exclude it from the coverage statistics. + */ + return XML_FALSE; /* LCOV_EXCL_LINE */ + } if (blockSize < INIT_BLOCK_SIZE) blockSize = INIT_BLOCK_SIZE; - else + else { + /* Detect overflow, avoiding _signed_ overflow undefined behavior */ + if ((int)((unsigned)blockSize * 2U) < 0) { + return XML_FALSE; + } blockSize *= 2; - tem = (BLOCK *)pool->mem->malloc_fcn(offsetof(BLOCK, s) - + blockSize * sizeof(XML_Char)); - if (!tem) + } + + bytesToAllocate = poolBytesToAllocateFor(blockSize); + if (bytesToAllocate == 0) + return XML_FALSE; + + tem = (BLOCK *)pool->mem->malloc_fcn(bytesToAllocate); + if (! tem) return XML_FALSE; tem->size = blockSize; tem->next = pool->blocks; pool->blocks = tem; if (pool->ptr != pool->start) - memcpy(tem->s, pool->start, - (pool->ptr - pool->start) * sizeof(XML_Char)); + memcpy(tem->s, pool->start, (pool->ptr - pool->start) * sizeof(XML_Char)); pool->ptr = tem->s + (pool->ptr - pool->start); pool->start = tem->s; pool->end = tem->s + blockSize; @@ -6345,15 +6752,14 @@ poolGrow(STRING_POOL *pool) } static int FASTCALL -nextScaffoldPart(XML_Parser parser) -{ - DTD * const dtd = _dtd; /* save one level of indirection */ - CONTENT_SCAFFOLD * me; +nextScaffoldPart(XML_Parser parser) { + DTD *const dtd = parser->m_dtd; /* save one level of indirection */ + CONTENT_SCAFFOLD *me; int next; - if (!dtd->scaffIndex) { - dtd->scaffIndex = (int *)MALLOC(groupSize * sizeof(int)); - if (!dtd->scaffIndex) + if (! dtd->scaffIndex) { + dtd->scaffIndex = (int *)MALLOC(parser, parser->m_groupSize * sizeof(int)); + if (! dtd->scaffIndex) return -1; dtd->scaffIndex[0] = 0; } @@ -6361,15 +6767,14 @@ nextScaffoldPart(XML_Parser parser) if (dtd->scaffCount >= dtd->scaffSize) { CONTENT_SCAFFOLD *temp; if (dtd->scaffold) { - temp = (CONTENT_SCAFFOLD *) - REALLOC(dtd->scaffold, dtd->scaffSize * 2 * sizeof(CONTENT_SCAFFOLD)); + temp = (CONTENT_SCAFFOLD *)REALLOC( + parser, dtd->scaffold, dtd->scaffSize * 2 * sizeof(CONTENT_SCAFFOLD)); if (temp == NULL) return -1; dtd->scaffSize *= 2; - } - else { - temp = (CONTENT_SCAFFOLD *)MALLOC(INIT_SCAFFOLD_ELEMENTS - * sizeof(CONTENT_SCAFFOLD)); + } else { + temp = (CONTENT_SCAFFOLD *)MALLOC(parser, INIT_SCAFFOLD_ELEMENTS + * sizeof(CONTENT_SCAFFOLD)); if (temp == NULL) return -1; dtd->scaffSize = INIT_SCAFFOLD_ELEMENTS; @@ -6379,11 +6784,12 @@ nextScaffoldPart(XML_Parser parser) next = dtd->scaffCount++; me = &dtd->scaffold[next]; if (dtd->scaffLevel) { - CONTENT_SCAFFOLD *parent = &dtd->scaffold[dtd->scaffIndex[dtd->scaffLevel-1]]; + CONTENT_SCAFFOLD *parent + = &dtd->scaffold[dtd->scaffIndex[dtd->scaffLevel - 1]]; if (parent->lastchild) { dtd->scaffold[parent->lastchild].nextsib = next; } - if (!parent->childcnt) + if (! parent->childcnt) parent->firstchild = next; parent->lastchild = next; parent->childcnt++; @@ -6393,13 +6799,9 @@ nextScaffoldPart(XML_Parser parser) } static void -build_node(XML_Parser parser, - int src_node, - XML_Content *dest, - XML_Content **contpos, - XML_Char **strpos) -{ - DTD * const dtd = _dtd; /* save one level of indirection */ +build_node(XML_Parser parser, int src_node, XML_Content *dest, + XML_Content **contpos, XML_Char **strpos) { + DTD *const dtd = parser->m_dtd; /* save one level of indirection */ dest->type = dtd->scaffold[src_node].type; dest->quant = dtd->scaffold[src_node].quant; if (dest->type == XML_CTYPE_NAME) { @@ -6408,21 +6810,19 @@ build_node(XML_Parser parser, src = dtd->scaffold[src_node].name; for (;;) { *(*strpos)++ = *src; - if (!*src) + if (! *src) break; src++; } dest->numchildren = 0; dest->children = NULL; - } - else { + } else { unsigned int i; int cn; dest->numchildren = dtd->scaffold[src_node].childcnt; dest->children = *contpos; *contpos += dest->numchildren; - for (i = 0, cn = dtd->scaffold[src_node].firstchild; - i < dest->numchildren; + for (i = 0, cn = dtd->scaffold[src_node].firstchild; i < dest->numchildren; i++, cn = dtd->scaffold[cn].nextsib) { build_node(parser, cn, &(dest->children[i]), contpos, strpos); } @@ -6431,20 +6831,19 @@ build_node(XML_Parser parser, } static XML_Content * -build_model (XML_Parser parser) -{ - DTD * const dtd = _dtd; /* save one level of indirection */ +build_model(XML_Parser parser) { + DTD *const dtd = parser->m_dtd; /* save one level of indirection */ XML_Content *ret; XML_Content *cpos; - XML_Char * str; + XML_Char *str; int allocsize = (dtd->scaffCount * sizeof(XML_Content) + (dtd->contentStringLen * sizeof(XML_Char))); - ret = (XML_Content *)MALLOC(allocsize); - if (!ret) + ret = (XML_Content *)MALLOC(parser, allocsize); + if (! ret) return NULL; - str = (XML_Char *) (&ret[dtd->scaffCount]); + str = (XML_Char *)(&ret[dtd->scaffCount]); cpos = &ret[1]; build_node(parser, 0, ret, &cpos, &str); @@ -6452,26 +6851,45 @@ build_model (XML_Parser parser) } static ELEMENT_TYPE * -getElementType(XML_Parser parser, - const ENCODING *enc, - const char *ptr, - const char *end) -{ - DTD * const dtd = _dtd; /* save one level of indirection */ +getElementType(XML_Parser parser, const ENCODING *enc, const char *ptr, + const char *end) { + DTD *const dtd = parser->m_dtd; /* save one level of indirection */ const XML_Char *name = poolStoreString(&dtd->pool, enc, ptr, end); ELEMENT_TYPE *ret; - if (!name) + if (! name) return NULL; - ret = (ELEMENT_TYPE *) lookup(parser, &dtd->elementTypes, name, sizeof(ELEMENT_TYPE)); - if (!ret) + ret = (ELEMENT_TYPE *)lookup(parser, &dtd->elementTypes, name, + sizeof(ELEMENT_TYPE)); + if (! ret) return NULL; if (ret->name != name) poolDiscard(&dtd->pool); else { poolFinish(&dtd->pool); - if (!setElementTypePrefix(parser, ret)) + if (! setElementTypePrefix(parser, ret)) return NULL; } return ret; } + +static XML_Char * +copyString(const XML_Char *s, const XML_Memory_Handling_Suite *memsuite) { + int charsRequired = 0; + XML_Char *result; + + /* First determine how long the string is */ + while (s[charsRequired] != 0) { + charsRequired++; + } + /* Include the terminator */ + charsRequired++; + + /* Now allocate space for the copy */ + result = memsuite->malloc_fcn(charsRequired * sizeof(XML_Char)); + if (result == NULL) + return NULL; + /* Copy the original into place */ + memcpy(result, s, charsRequired * sizeof(XML_Char)); + return result; +} diff --git a/chromium/third_party/expat/files/lib/xmlparse.c.original b/chromium/third_party/expat/files/lib/xmlparse.c.original deleted file mode 100644 index b308e67e2d3..00000000000 --- a/chromium/third_party/expat/files/lib/xmlparse.c.original +++ /dev/null @@ -1,6466 +0,0 @@ -/* Copyright (c) 1998, 1999, 2000 Thai Open Source Software Center Ltd - See the file COPYING for copying permission. -*/ - -#include <stddef.h> -#include <string.h> /* memset(), memcpy() */ -#include <assert.h> -#include <limits.h> /* UINT_MAX */ - -#ifdef WIN32 -#define getpid GetCurrentProcessId -#else -#include <sys/time.h> /* gettimeofday() */ -#include <sys/types.h> /* getpid() */ -#include <unistd.h> /* getpid() */ -#endif - -#define XML_BUILDING_EXPAT 1 - -#ifdef WIN32 -#include "winconfig.h" -#elif defined(MACOS_CLASSIC) -#include "macconfig.h" -#elif defined(__amigaos__) -#include "amigaconfig.h" -#elif defined(__WATCOMC__) -#include "watcomconfig.h" -#elif defined(HAVE_EXPAT_CONFIG_H) -#include <expat_config.h> -#endif /* ndef WIN32 */ - -#include "ascii.h" -#include "expat.h" - -#ifdef XML_UNICODE -#define XML_ENCODE_MAX XML_UTF16_ENCODE_MAX -#define XmlConvert XmlUtf16Convert -#define XmlGetInternalEncoding XmlGetUtf16InternalEncoding -#define XmlGetInternalEncodingNS XmlGetUtf16InternalEncodingNS -#define XmlEncode XmlUtf16Encode -/* Using pointer subtraction to convert to integer type. */ -#define MUST_CONVERT(enc, s) (!(enc)->isUtf16 || (((char *)(s) - (char *)NULL) & 1)) -typedef unsigned short ICHAR; -#else -#define XML_ENCODE_MAX XML_UTF8_ENCODE_MAX -#define XmlConvert XmlUtf8Convert -#define XmlGetInternalEncoding XmlGetUtf8InternalEncoding -#define XmlGetInternalEncodingNS XmlGetUtf8InternalEncodingNS -#define XmlEncode XmlUtf8Encode -#define MUST_CONVERT(enc, s) (!(enc)->isUtf8) -typedef char ICHAR; -#endif - - -#ifndef XML_NS - -#define XmlInitEncodingNS XmlInitEncoding -#define XmlInitUnknownEncodingNS XmlInitUnknownEncoding -#undef XmlGetInternalEncodingNS -#define XmlGetInternalEncodingNS XmlGetInternalEncoding -#define XmlParseXmlDeclNS XmlParseXmlDecl - -#endif - -#ifdef XML_UNICODE - -#ifdef XML_UNICODE_WCHAR_T -#define XML_T(x) (const wchar_t)x -#define XML_L(x) L ## x -#else -#define XML_T(x) (const unsigned short)x -#define XML_L(x) x -#endif - -#else - -#define XML_T(x) x -#define XML_L(x) x - -#endif - -/* Round up n to be a multiple of sz, where sz is a power of 2. */ -#define ROUND_UP(n, sz) (((n) + ((sz) - 1)) & ~((sz) - 1)) - -/* Handle the case where memmove() doesn't exist. */ -#ifndef HAVE_MEMMOVE -#ifdef HAVE_BCOPY -#define memmove(d,s,l) bcopy((s),(d),(l)) -#else -#error memmove does not exist on this platform, nor is a substitute available -#endif /* HAVE_BCOPY */ -#endif /* HAVE_MEMMOVE */ - -#include "internal.h" -#include "xmltok.h" -#include "xmlrole.h" - -typedef const XML_Char *KEY; - -typedef struct { - KEY name; -} NAMED; - -typedef struct { - NAMED **v; - unsigned char power; - size_t size; - size_t used; - const XML_Memory_Handling_Suite *mem; -} HASH_TABLE; - -/* Basic character hash algorithm, taken from Python's string hash: - h = h * 1000003 ^ character, the constant being a prime number. - -*/ -#ifdef XML_UNICODE -#define CHAR_HASH(h, c) \ - (((h) * 0xF4243) ^ (unsigned short)(c)) -#else -#define CHAR_HASH(h, c) \ - (((h) * 0xF4243) ^ (unsigned char)(c)) -#endif - -/* For probing (after a collision) we need a step size relative prime - to the hash table size, which is a power of 2. We use double-hashing, - since we can calculate a second hash value cheaply by taking those bits - of the first hash value that were discarded (masked out) when the table - index was calculated: index = hash & mask, where mask = table->size - 1. - We limit the maximum step size to table->size / 4 (mask >> 2) and make - it odd, since odd numbers are always relative prime to a power of 2. -*/ -#define SECOND_HASH(hash, mask, power) \ - ((((hash) & ~(mask)) >> ((power) - 1)) & ((mask) >> 2)) -#define PROBE_STEP(hash, mask, power) \ - ((unsigned char)((SECOND_HASH(hash, mask, power)) | 1)) - -typedef struct { - NAMED **p; - NAMED **end; -} HASH_TABLE_ITER; - -#define INIT_TAG_BUF_SIZE 32 /* must be a multiple of sizeof(XML_Char) */ -#define INIT_DATA_BUF_SIZE 1024 -#define INIT_ATTS_SIZE 16 -#define INIT_ATTS_VERSION 0xFFFFFFFF -#define INIT_BLOCK_SIZE 1024 -#define INIT_BUFFER_SIZE 1024 - -#define EXPAND_SPARE 24 - -typedef struct binding { - struct prefix *prefix; - struct binding *nextTagBinding; - struct binding *prevPrefixBinding; - const struct attribute_id *attId; - XML_Char *uri; - int uriLen; - int uriAlloc; -} BINDING; - -typedef struct prefix { - const XML_Char *name; - BINDING *binding; -} PREFIX; - -typedef struct { - const XML_Char *str; - const XML_Char *localPart; - const XML_Char *prefix; - int strLen; - int uriLen; - int prefixLen; -} TAG_NAME; - -/* TAG represents an open element. - The name of the element is stored in both the document and API - encodings. The memory buffer 'buf' is a separately-allocated - memory area which stores the name. During the XML_Parse()/ - XMLParseBuffer() when the element is open, the memory for the 'raw' - version of the name (in the document encoding) is shared with the - document buffer. If the element is open across calls to - XML_Parse()/XML_ParseBuffer(), the buffer is re-allocated to - contain the 'raw' name as well. - - A parser re-uses these structures, maintaining a list of allocated - TAG objects in a free list. -*/ -typedef struct tag { - struct tag *parent; /* parent of this element */ - const char *rawName; /* tagName in the original encoding */ - int rawNameLength; - TAG_NAME name; /* tagName in the API encoding */ - char *buf; /* buffer for name components */ - char *bufEnd; /* end of the buffer */ - BINDING *bindings; -} TAG; - -typedef struct { - const XML_Char *name; - const XML_Char *textPtr; - int textLen; /* length in XML_Chars */ - int processed; /* # of processed bytes - when suspended */ - const XML_Char *systemId; - const XML_Char *base; - const XML_Char *publicId; - const XML_Char *notation; - XML_Bool open; - XML_Bool is_param; - XML_Bool is_internal; /* true if declared in internal subset outside PE */ -} ENTITY; - -typedef struct { - enum XML_Content_Type type; - enum XML_Content_Quant quant; - const XML_Char * name; - int firstchild; - int lastchild; - int childcnt; - int nextsib; -} CONTENT_SCAFFOLD; - -#define INIT_SCAFFOLD_ELEMENTS 32 - -typedef struct block { - struct block *next; - int size; - XML_Char s[1]; -} BLOCK; - -typedef struct { - BLOCK *blocks; - BLOCK *freeBlocks; - const XML_Char *end; - XML_Char *ptr; - XML_Char *start; - const XML_Memory_Handling_Suite *mem; -} STRING_POOL; - -/* The XML_Char before the name is used to determine whether - an attribute has been specified. */ -typedef struct attribute_id { - XML_Char *name; - PREFIX *prefix; - XML_Bool maybeTokenized; - XML_Bool xmlns; -} ATTRIBUTE_ID; - -typedef struct { - const ATTRIBUTE_ID *id; - XML_Bool isCdata; - const XML_Char *value; -} DEFAULT_ATTRIBUTE; - -typedef struct { - unsigned long version; - unsigned long hash; - const XML_Char *uriName; -} NS_ATT; - -typedef struct { - const XML_Char *name; - PREFIX *prefix; - const ATTRIBUTE_ID *idAtt; - int nDefaultAtts; - int allocDefaultAtts; - DEFAULT_ATTRIBUTE *defaultAtts; -} ELEMENT_TYPE; - -typedef struct { - HASH_TABLE generalEntities; - HASH_TABLE elementTypes; - HASH_TABLE attributeIds; - HASH_TABLE prefixes; - STRING_POOL pool; - STRING_POOL entityValuePool; - /* false once a parameter entity reference has been skipped */ - XML_Bool keepProcessing; - /* true once an internal or external PE reference has been encountered; - this includes the reference to an external subset */ - XML_Bool hasParamEntityRefs; - XML_Bool standalone; -#ifdef XML_DTD - /* indicates if external PE has been read */ - XML_Bool paramEntityRead; - HASH_TABLE paramEntities; -#endif /* XML_DTD */ - PREFIX defaultPrefix; - /* === scaffolding for building content model === */ - XML_Bool in_eldecl; - CONTENT_SCAFFOLD *scaffold; - unsigned contentStringLen; - unsigned scaffSize; - unsigned scaffCount; - int scaffLevel; - int *scaffIndex; -} DTD; - -typedef struct open_internal_entity { - const char *internalEventPtr; - const char *internalEventEndPtr; - struct open_internal_entity *next; - ENTITY *entity; - int startTagLevel; - XML_Bool betweenDecl; /* WFC: PE Between Declarations */ -} OPEN_INTERNAL_ENTITY; - -typedef enum XML_Error PTRCALL Processor(XML_Parser parser, - const char *start, - const char *end, - const char **endPtr); - -static Processor prologProcessor; -static Processor prologInitProcessor; -static Processor contentProcessor; -static Processor cdataSectionProcessor; -#ifdef XML_DTD -static Processor ignoreSectionProcessor; -static Processor externalParEntProcessor; -static Processor externalParEntInitProcessor; -static Processor entityValueProcessor; -static Processor entityValueInitProcessor; -#endif /* XML_DTD */ -static Processor epilogProcessor; -static Processor errorProcessor; -static Processor externalEntityInitProcessor; -static Processor externalEntityInitProcessor2; -static Processor externalEntityInitProcessor3; -static Processor externalEntityContentProcessor; -static Processor internalEntityProcessor; - -static enum XML_Error -handleUnknownEncoding(XML_Parser parser, const XML_Char *encodingName); -static enum XML_Error -processXmlDecl(XML_Parser parser, int isGeneralTextEntity, - const char *s, const char *next); -static enum XML_Error -initializeEncoding(XML_Parser parser); -static enum XML_Error -doProlog(XML_Parser parser, const ENCODING *enc, const char *s, - const char *end, int tok, const char *next, const char **nextPtr, - XML_Bool haveMore); -static enum XML_Error -processInternalEntity(XML_Parser parser, ENTITY *entity, - XML_Bool betweenDecl); -static enum XML_Error -doContent(XML_Parser parser, int startTagLevel, const ENCODING *enc, - const char *start, const char *end, const char **endPtr, - XML_Bool haveMore); -static enum XML_Error -doCdataSection(XML_Parser parser, const ENCODING *, const char **startPtr, - const char *end, const char **nextPtr, XML_Bool haveMore); -#ifdef XML_DTD -static enum XML_Error -doIgnoreSection(XML_Parser parser, const ENCODING *, const char **startPtr, - const char *end, const char **nextPtr, XML_Bool haveMore); -#endif /* XML_DTD */ - -static enum XML_Error -storeAtts(XML_Parser parser, const ENCODING *, const char *s, - TAG_NAME *tagNamePtr, BINDING **bindingsPtr); -static enum XML_Error -addBinding(XML_Parser parser, PREFIX *prefix, const ATTRIBUTE_ID *attId, - const XML_Char *uri, BINDING **bindingsPtr); -static int -defineAttribute(ELEMENT_TYPE *type, ATTRIBUTE_ID *, XML_Bool isCdata, - XML_Bool isId, const XML_Char *dfltValue, XML_Parser parser); -static enum XML_Error -storeAttributeValue(XML_Parser parser, const ENCODING *, XML_Bool isCdata, - const char *, const char *, STRING_POOL *); -static enum XML_Error -appendAttributeValue(XML_Parser parser, const ENCODING *, XML_Bool isCdata, - const char *, const char *, STRING_POOL *); -static ATTRIBUTE_ID * -getAttributeId(XML_Parser parser, const ENCODING *enc, const char *start, - const char *end); -static int -setElementTypePrefix(XML_Parser parser, ELEMENT_TYPE *); -static enum XML_Error -storeEntityValue(XML_Parser parser, const ENCODING *enc, const char *start, - const char *end); -static int -reportProcessingInstruction(XML_Parser parser, const ENCODING *enc, - const char *start, const char *end); -static int -reportComment(XML_Parser parser, const ENCODING *enc, const char *start, - const char *end); -static void -reportDefault(XML_Parser parser, const ENCODING *enc, const char *start, - const char *end); - -static const XML_Char * getContext(XML_Parser parser); -static XML_Bool -setContext(XML_Parser parser, const XML_Char *context); - -static void FASTCALL normalizePublicId(XML_Char *s); - -static DTD * dtdCreate(const XML_Memory_Handling_Suite *ms); -/* do not call if parentParser != NULL */ -static void dtdReset(DTD *p, const XML_Memory_Handling_Suite *ms); -static void -dtdDestroy(DTD *p, XML_Bool isDocEntity, const XML_Memory_Handling_Suite *ms); -static int -dtdCopy(XML_Parser oldParser, - DTD *newDtd, const DTD *oldDtd, const XML_Memory_Handling_Suite *ms); -static int -copyEntityTable(XML_Parser oldParser, - HASH_TABLE *, STRING_POOL *, const HASH_TABLE *); -static NAMED * -lookup(XML_Parser parser, HASH_TABLE *table, KEY name, size_t createSize); -static void FASTCALL -hashTableInit(HASH_TABLE *, const XML_Memory_Handling_Suite *ms); -static void FASTCALL hashTableClear(HASH_TABLE *); -static void FASTCALL hashTableDestroy(HASH_TABLE *); -static void FASTCALL -hashTableIterInit(HASH_TABLE_ITER *, const HASH_TABLE *); -static NAMED * FASTCALL hashTableIterNext(HASH_TABLE_ITER *); - -static void FASTCALL -poolInit(STRING_POOL *, const XML_Memory_Handling_Suite *ms); -static void FASTCALL poolClear(STRING_POOL *); -static void FASTCALL poolDestroy(STRING_POOL *); -static XML_Char * -poolAppend(STRING_POOL *pool, const ENCODING *enc, - const char *ptr, const char *end); -static XML_Char * -poolStoreString(STRING_POOL *pool, const ENCODING *enc, - const char *ptr, const char *end); -static XML_Bool FASTCALL poolGrow(STRING_POOL *pool); -static const XML_Char * FASTCALL -poolCopyString(STRING_POOL *pool, const XML_Char *s); -static const XML_Char * -poolCopyStringN(STRING_POOL *pool, const XML_Char *s, int n); -static const XML_Char * FASTCALL -poolAppendString(STRING_POOL *pool, const XML_Char *s); - -static int FASTCALL nextScaffoldPart(XML_Parser parser); -static XML_Content * build_model(XML_Parser parser); -static ELEMENT_TYPE * -getElementType(XML_Parser parser, const ENCODING *enc, - const char *ptr, const char *end); - -static unsigned long generate_hash_secret_salt(XML_Parser parser); -static XML_Bool startParsing(XML_Parser parser); - -static XML_Parser -parserCreate(const XML_Char *encodingName, - const XML_Memory_Handling_Suite *memsuite, - const XML_Char *nameSep, - DTD *dtd); - -static void -parserInit(XML_Parser parser, const XML_Char *encodingName); - -#define poolStart(pool) ((pool)->start) -#define poolEnd(pool) ((pool)->ptr) -#define poolLength(pool) ((pool)->ptr - (pool)->start) -#define poolChop(pool) ((void)--(pool->ptr)) -#define poolLastChar(pool) (((pool)->ptr)[-1]) -#define poolDiscard(pool) ((pool)->ptr = (pool)->start) -#define poolFinish(pool) ((pool)->start = (pool)->ptr) -#define poolAppendChar(pool, c) \ - (((pool)->ptr == (pool)->end && !poolGrow(pool)) \ - ? 0 \ - : ((*((pool)->ptr)++ = c), 1)) - -struct XML_ParserStruct { - /* The first member must be userData so that the XML_GetUserData - macro works. */ - void *m_userData; - void *m_handlerArg; - char *m_buffer; - const XML_Memory_Handling_Suite m_mem; - /* first character to be parsed */ - const char *m_bufferPtr; - /* past last character to be parsed */ - char *m_bufferEnd; - /* allocated end of buffer */ - const char *m_bufferLim; - XML_Index m_parseEndByteIndex; - const char *m_parseEndPtr; - XML_Char *m_dataBuf; - XML_Char *m_dataBufEnd; - XML_StartElementHandler m_startElementHandler; - XML_EndElementHandler m_endElementHandler; - XML_CharacterDataHandler m_characterDataHandler; - XML_ProcessingInstructionHandler m_processingInstructionHandler; - XML_CommentHandler m_commentHandler; - XML_StartCdataSectionHandler m_startCdataSectionHandler; - XML_EndCdataSectionHandler m_endCdataSectionHandler; - XML_DefaultHandler m_defaultHandler; - XML_StartDoctypeDeclHandler m_startDoctypeDeclHandler; - XML_EndDoctypeDeclHandler m_endDoctypeDeclHandler; - XML_UnparsedEntityDeclHandler m_unparsedEntityDeclHandler; - XML_NotationDeclHandler m_notationDeclHandler; - XML_StartNamespaceDeclHandler m_startNamespaceDeclHandler; - XML_EndNamespaceDeclHandler m_endNamespaceDeclHandler; - XML_NotStandaloneHandler m_notStandaloneHandler; - XML_ExternalEntityRefHandler m_externalEntityRefHandler; - XML_Parser m_externalEntityRefHandlerArg; - XML_SkippedEntityHandler m_skippedEntityHandler; - XML_UnknownEncodingHandler m_unknownEncodingHandler; - XML_ElementDeclHandler m_elementDeclHandler; - XML_AttlistDeclHandler m_attlistDeclHandler; - XML_EntityDeclHandler m_entityDeclHandler; - XML_XmlDeclHandler m_xmlDeclHandler; - const ENCODING *m_encoding; - INIT_ENCODING m_initEncoding; - const ENCODING *m_internalEncoding; - const XML_Char *m_protocolEncodingName; - XML_Bool m_ns; - XML_Bool m_ns_triplets; - void *m_unknownEncodingMem; - void *m_unknownEncodingData; - void *m_unknownEncodingHandlerData; - void (XMLCALL *m_unknownEncodingRelease)(void *); - PROLOG_STATE m_prologState; - Processor *m_processor; - enum XML_Error m_errorCode; - const char *m_eventPtr; - const char *m_eventEndPtr; - const char *m_positionPtr; - OPEN_INTERNAL_ENTITY *m_openInternalEntities; - OPEN_INTERNAL_ENTITY *m_freeInternalEntities; - XML_Bool m_defaultExpandInternalEntities; - int m_tagLevel; - ENTITY *m_declEntity; - const XML_Char *m_doctypeName; - const XML_Char *m_doctypeSysid; - const XML_Char *m_doctypePubid; - const XML_Char *m_declAttributeType; - const XML_Char *m_declNotationName; - const XML_Char *m_declNotationPublicId; - ELEMENT_TYPE *m_declElementType; - ATTRIBUTE_ID *m_declAttributeId; - XML_Bool m_declAttributeIsCdata; - XML_Bool m_declAttributeIsId; - DTD *m_dtd; - const XML_Char *m_curBase; - TAG *m_tagStack; - TAG *m_freeTagList; - BINDING *m_inheritedBindings; - BINDING *m_freeBindingList; - int m_attsSize; - int m_nSpecifiedAtts; - int m_idAttIndex; - ATTRIBUTE *m_atts; - NS_ATT *m_nsAtts; - unsigned long m_nsAttsVersion; - unsigned char m_nsAttsPower; -#ifdef XML_ATTR_INFO - XML_AttrInfo *m_attInfo; -#endif - POSITION m_position; - STRING_POOL m_tempPool; - STRING_POOL m_temp2Pool; - char *m_groupConnector; - unsigned int m_groupSize; - XML_Char m_namespaceSeparator; - XML_Parser m_parentParser; - XML_ParsingStatus m_parsingStatus; -#ifdef XML_DTD - XML_Bool m_isParamEntity; - XML_Bool m_useForeignDTD; - enum XML_ParamEntityParsing m_paramEntityParsing; -#endif - unsigned long m_hash_secret_salt; -}; - -#define MALLOC(s) (parser->m_mem.malloc_fcn((s))) -#define REALLOC(p,s) (parser->m_mem.realloc_fcn((p),(s))) -#define FREE(p) (parser->m_mem.free_fcn((p))) - -#define userData (parser->m_userData) -#define handlerArg (parser->m_handlerArg) -#define startElementHandler (parser->m_startElementHandler) -#define endElementHandler (parser->m_endElementHandler) -#define characterDataHandler (parser->m_characterDataHandler) -#define processingInstructionHandler \ - (parser->m_processingInstructionHandler) -#define commentHandler (parser->m_commentHandler) -#define startCdataSectionHandler \ - (parser->m_startCdataSectionHandler) -#define endCdataSectionHandler (parser->m_endCdataSectionHandler) -#define defaultHandler (parser->m_defaultHandler) -#define startDoctypeDeclHandler (parser->m_startDoctypeDeclHandler) -#define endDoctypeDeclHandler (parser->m_endDoctypeDeclHandler) -#define unparsedEntityDeclHandler \ - (parser->m_unparsedEntityDeclHandler) -#define notationDeclHandler (parser->m_notationDeclHandler) -#define startNamespaceDeclHandler \ - (parser->m_startNamespaceDeclHandler) -#define endNamespaceDeclHandler (parser->m_endNamespaceDeclHandler) -#define notStandaloneHandler (parser->m_notStandaloneHandler) -#define externalEntityRefHandler \ - (parser->m_externalEntityRefHandler) -#define externalEntityRefHandlerArg \ - (parser->m_externalEntityRefHandlerArg) -#define internalEntityRefHandler \ - (parser->m_internalEntityRefHandler) -#define skippedEntityHandler (parser->m_skippedEntityHandler) -#define unknownEncodingHandler (parser->m_unknownEncodingHandler) -#define elementDeclHandler (parser->m_elementDeclHandler) -#define attlistDeclHandler (parser->m_attlistDeclHandler) -#define entityDeclHandler (parser->m_entityDeclHandler) -#define xmlDeclHandler (parser->m_xmlDeclHandler) -#define encoding (parser->m_encoding) -#define initEncoding (parser->m_initEncoding) -#define internalEncoding (parser->m_internalEncoding) -#define unknownEncodingMem (parser->m_unknownEncodingMem) -#define unknownEncodingData (parser->m_unknownEncodingData) -#define unknownEncodingHandlerData \ - (parser->m_unknownEncodingHandlerData) -#define unknownEncodingRelease (parser->m_unknownEncodingRelease) -#define protocolEncodingName (parser->m_protocolEncodingName) -#define ns (parser->m_ns) -#define ns_triplets (parser->m_ns_triplets) -#define prologState (parser->m_prologState) -#define processor (parser->m_processor) -#define errorCode (parser->m_errorCode) -#define eventPtr (parser->m_eventPtr) -#define eventEndPtr (parser->m_eventEndPtr) -#define positionPtr (parser->m_positionPtr) -#define position (parser->m_position) -#define openInternalEntities (parser->m_openInternalEntities) -#define freeInternalEntities (parser->m_freeInternalEntities) -#define defaultExpandInternalEntities \ - (parser->m_defaultExpandInternalEntities) -#define tagLevel (parser->m_tagLevel) -#define buffer (parser->m_buffer) -#define bufferPtr (parser->m_bufferPtr) -#define bufferEnd (parser->m_bufferEnd) -#define parseEndByteIndex (parser->m_parseEndByteIndex) -#define parseEndPtr (parser->m_parseEndPtr) -#define bufferLim (parser->m_bufferLim) -#define dataBuf (parser->m_dataBuf) -#define dataBufEnd (parser->m_dataBufEnd) -#define _dtd (parser->m_dtd) -#define curBase (parser->m_curBase) -#define declEntity (parser->m_declEntity) -#define doctypeName (parser->m_doctypeName) -#define doctypeSysid (parser->m_doctypeSysid) -#define doctypePubid (parser->m_doctypePubid) -#define declAttributeType (parser->m_declAttributeType) -#define declNotationName (parser->m_declNotationName) -#define declNotationPublicId (parser->m_declNotationPublicId) -#define declElementType (parser->m_declElementType) -#define declAttributeId (parser->m_declAttributeId) -#define declAttributeIsCdata (parser->m_declAttributeIsCdata) -#define declAttributeIsId (parser->m_declAttributeIsId) -#define freeTagList (parser->m_freeTagList) -#define freeBindingList (parser->m_freeBindingList) -#define inheritedBindings (parser->m_inheritedBindings) -#define tagStack (parser->m_tagStack) -#define atts (parser->m_atts) -#define attsSize (parser->m_attsSize) -#define nSpecifiedAtts (parser->m_nSpecifiedAtts) -#define idAttIndex (parser->m_idAttIndex) -#define nsAtts (parser->m_nsAtts) -#define nsAttsVersion (parser->m_nsAttsVersion) -#define nsAttsPower (parser->m_nsAttsPower) -#define attInfo (parser->m_attInfo) -#define tempPool (parser->m_tempPool) -#define temp2Pool (parser->m_temp2Pool) -#define groupConnector (parser->m_groupConnector) -#define groupSize (parser->m_groupSize) -#define namespaceSeparator (parser->m_namespaceSeparator) -#define parentParser (parser->m_parentParser) -#define ps_parsing (parser->m_parsingStatus.parsing) -#define ps_finalBuffer (parser->m_parsingStatus.finalBuffer) -#ifdef XML_DTD -#define isParamEntity (parser->m_isParamEntity) -#define useForeignDTD (parser->m_useForeignDTD) -#define paramEntityParsing (parser->m_paramEntityParsing) -#endif /* XML_DTD */ -#define hash_secret_salt (parser->m_hash_secret_salt) - -XML_Parser XMLCALL -XML_ParserCreate(const XML_Char *encodingName) -{ - return XML_ParserCreate_MM(encodingName, NULL, NULL); -} - -XML_Parser XMLCALL -XML_ParserCreateNS(const XML_Char *encodingName, XML_Char nsSep) -{ - XML_Char tmp[2]; - *tmp = nsSep; - return XML_ParserCreate_MM(encodingName, NULL, tmp); -} - -static const XML_Char implicitContext[] = { - ASCII_x, ASCII_m, ASCII_l, ASCII_EQUALS, ASCII_h, ASCII_t, ASCII_t, ASCII_p, - ASCII_COLON, ASCII_SLASH, ASCII_SLASH, ASCII_w, ASCII_w, ASCII_w, - ASCII_PERIOD, ASCII_w, ASCII_3, ASCII_PERIOD, ASCII_o, ASCII_r, ASCII_g, - ASCII_SLASH, ASCII_X, ASCII_M, ASCII_L, ASCII_SLASH, ASCII_1, ASCII_9, - ASCII_9, ASCII_8, ASCII_SLASH, ASCII_n, ASCII_a, ASCII_m, ASCII_e, - ASCII_s, ASCII_p, ASCII_a, ASCII_c, ASCII_e, '\0' -}; - -static unsigned long -gather_time_entropy(void) -{ -#ifdef WIN32 - FILETIME ft; - GetSystemTimeAsFileTime(&ft); /* never fails */ - return ft.dwHighDateTime ^ ft.dwLowDateTime; -#else - struct timeval tv; - int gettimeofday_res; - - gettimeofday_res = gettimeofday(&tv, NULL); - assert (gettimeofday_res == 0); - - /* Microseconds time is <20 bits entropy */ - return tv.tv_usec; -#endif -} - -static unsigned long -generate_hash_secret_salt(XML_Parser parser) -{ - /* Process ID is 0 bits entropy if attacker has local access - * XML_Parser address is few bits of entropy if attacker has local access */ - const unsigned long entropy = - gather_time_entropy() ^ getpid() ^ (unsigned long)parser; - - /* Factors are 2^31-1 and 2^61-1 (Mersenne primes M31 and M61) */ - if (sizeof(unsigned long) == 4) { - return entropy * 2147483647; - } else { - return entropy * (unsigned long)2305843009213693951; - } -} - -static XML_Bool /* only valid for root parser */ -startParsing(XML_Parser parser) -{ - /* hash functions must be initialized before setContext() is called */ - if (hash_secret_salt == 0) - hash_secret_salt = generate_hash_secret_salt(parser); - if (ns) { - /* implicit context only set for root parser, since child - parsers (i.e. external entity parsers) will inherit it - */ - return setContext(parser, implicitContext); - } - return XML_TRUE; -} - -XML_Parser XMLCALL -XML_ParserCreate_MM(const XML_Char *encodingName, - const XML_Memory_Handling_Suite *memsuite, - const XML_Char *nameSep) -{ - return parserCreate(encodingName, memsuite, nameSep, NULL); -} - -static XML_Parser -parserCreate(const XML_Char *encodingName, - const XML_Memory_Handling_Suite *memsuite, - const XML_Char *nameSep, - DTD *dtd) -{ - XML_Parser parser; - - if (memsuite) { - XML_Memory_Handling_Suite *mtemp; - parser = (XML_Parser) - memsuite->malloc_fcn(sizeof(struct XML_ParserStruct)); - if (parser != NULL) { - mtemp = (XML_Memory_Handling_Suite *)&(parser->m_mem); - mtemp->malloc_fcn = memsuite->malloc_fcn; - mtemp->realloc_fcn = memsuite->realloc_fcn; - mtemp->free_fcn = memsuite->free_fcn; - } - } - else { - XML_Memory_Handling_Suite *mtemp; - parser = (XML_Parser)malloc(sizeof(struct XML_ParserStruct)); - if (parser != NULL) { - mtemp = (XML_Memory_Handling_Suite *)&(parser->m_mem); - mtemp->malloc_fcn = malloc; - mtemp->realloc_fcn = realloc; - mtemp->free_fcn = free; - } - } - - if (!parser) - return parser; - - buffer = NULL; - bufferLim = NULL; - - attsSize = INIT_ATTS_SIZE; - atts = (ATTRIBUTE *)MALLOC(attsSize * sizeof(ATTRIBUTE)); - if (atts == NULL) { - FREE(parser); - return NULL; - } -#ifdef XML_ATTR_INFO - attInfo = (XML_AttrInfo*)MALLOC(attsSize * sizeof(XML_AttrInfo)); - if (attInfo == NULL) { - FREE(atts); - FREE(parser); - return NULL; - } -#endif - dataBuf = (XML_Char *)MALLOC(INIT_DATA_BUF_SIZE * sizeof(XML_Char)); - if (dataBuf == NULL) { - FREE(atts); -#ifdef XML_ATTR_INFO - FREE(attInfo); -#endif - FREE(parser); - return NULL; - } - dataBufEnd = dataBuf + INIT_DATA_BUF_SIZE; - - if (dtd) - _dtd = dtd; - else { - _dtd = dtdCreate(&parser->m_mem); - if (_dtd == NULL) { - FREE(dataBuf); - FREE(atts); -#ifdef XML_ATTR_INFO - FREE(attInfo); -#endif - FREE(parser); - return NULL; - } - } - - freeBindingList = NULL; - freeTagList = NULL; - freeInternalEntities = NULL; - - groupSize = 0; - groupConnector = NULL; - - unknownEncodingHandler = NULL; - unknownEncodingHandlerData = NULL; - - namespaceSeparator = ASCII_EXCL; - ns = XML_FALSE; - ns_triplets = XML_FALSE; - - nsAtts = NULL; - nsAttsVersion = 0; - nsAttsPower = 0; - - poolInit(&tempPool, &(parser->m_mem)); - poolInit(&temp2Pool, &(parser->m_mem)); - parserInit(parser, encodingName); - - if (encodingName && !protocolEncodingName) { - XML_ParserFree(parser); - return NULL; - } - - if (nameSep) { - ns = XML_TRUE; - internalEncoding = XmlGetInternalEncodingNS(); - namespaceSeparator = *nameSep; - } - else { - internalEncoding = XmlGetInternalEncoding(); - } - - return parser; -} - -static void -parserInit(XML_Parser parser, const XML_Char *encodingName) -{ - processor = prologInitProcessor; - XmlPrologStateInit(&prologState); - protocolEncodingName = (encodingName != NULL - ? poolCopyString(&tempPool, encodingName) - : NULL); - curBase = NULL; - XmlInitEncoding(&initEncoding, &encoding, 0); - userData = NULL; - handlerArg = NULL; - startElementHandler = NULL; - endElementHandler = NULL; - characterDataHandler = NULL; - processingInstructionHandler = NULL; - commentHandler = NULL; - startCdataSectionHandler = NULL; - endCdataSectionHandler = NULL; - defaultHandler = NULL; - startDoctypeDeclHandler = NULL; - endDoctypeDeclHandler = NULL; - unparsedEntityDeclHandler = NULL; - notationDeclHandler = NULL; - startNamespaceDeclHandler = NULL; - endNamespaceDeclHandler = NULL; - notStandaloneHandler = NULL; - externalEntityRefHandler = NULL; - externalEntityRefHandlerArg = parser; - skippedEntityHandler = NULL; - elementDeclHandler = NULL; - attlistDeclHandler = NULL; - entityDeclHandler = NULL; - xmlDeclHandler = NULL; - bufferPtr = buffer; - bufferEnd = buffer; - parseEndByteIndex = 0; - parseEndPtr = NULL; - declElementType = NULL; - declAttributeId = NULL; - declEntity = NULL; - doctypeName = NULL; - doctypeSysid = NULL; - doctypePubid = NULL; - declAttributeType = NULL; - declNotationName = NULL; - declNotationPublicId = NULL; - declAttributeIsCdata = XML_FALSE; - declAttributeIsId = XML_FALSE; - memset(&position, 0, sizeof(POSITION)); - errorCode = XML_ERROR_NONE; - eventPtr = NULL; - eventEndPtr = NULL; - positionPtr = NULL; - openInternalEntities = NULL; - defaultExpandInternalEntities = XML_TRUE; - tagLevel = 0; - tagStack = NULL; - inheritedBindings = NULL; - nSpecifiedAtts = 0; - unknownEncodingMem = NULL; - unknownEncodingRelease = NULL; - unknownEncodingData = NULL; - parentParser = NULL; - ps_parsing = XML_INITIALIZED; -#ifdef XML_DTD - isParamEntity = XML_FALSE; - useForeignDTD = XML_FALSE; - paramEntityParsing = XML_PARAM_ENTITY_PARSING_NEVER; -#endif - hash_secret_salt = 0; -} - -/* moves list of bindings to freeBindingList */ -static void FASTCALL -moveToFreeBindingList(XML_Parser parser, BINDING *bindings) -{ - while (bindings) { - BINDING *b = bindings; - bindings = bindings->nextTagBinding; - b->nextTagBinding = freeBindingList; - freeBindingList = b; - } -} - -XML_Bool XMLCALL -XML_ParserReset(XML_Parser parser, const XML_Char *encodingName) -{ - TAG *tStk; - OPEN_INTERNAL_ENTITY *openEntityList; - if (parentParser) - return XML_FALSE; - /* move tagStack to freeTagList */ - tStk = tagStack; - while (tStk) { - TAG *tag = tStk; - tStk = tStk->parent; - tag->parent = freeTagList; - moveToFreeBindingList(parser, tag->bindings); - tag->bindings = NULL; - freeTagList = tag; - } - /* move openInternalEntities to freeInternalEntities */ - openEntityList = openInternalEntities; - while (openEntityList) { - OPEN_INTERNAL_ENTITY *openEntity = openEntityList; - openEntityList = openEntity->next; - openEntity->next = freeInternalEntities; - freeInternalEntities = openEntity; - } - moveToFreeBindingList(parser, inheritedBindings); - FREE(unknownEncodingMem); - if (unknownEncodingRelease) - unknownEncodingRelease(unknownEncodingData); - poolClear(&tempPool); - poolClear(&temp2Pool); - parserInit(parser, encodingName); - dtdReset(_dtd, &parser->m_mem); - return XML_TRUE; -} - -enum XML_Status XMLCALL -XML_SetEncoding(XML_Parser parser, const XML_Char *encodingName) -{ - /* Block after XML_Parse()/XML_ParseBuffer() has been called. - XXX There's no way for the caller to determine which of the - XXX possible error cases caused the XML_STATUS_ERROR return. - */ - if (ps_parsing == XML_PARSING || ps_parsing == XML_SUSPENDED) - return XML_STATUS_ERROR; - if (encodingName == NULL) - protocolEncodingName = NULL; - else { - protocolEncodingName = poolCopyString(&tempPool, encodingName); - if (!protocolEncodingName) - return XML_STATUS_ERROR; - } - return XML_STATUS_OK; -} - -XML_Parser XMLCALL -XML_ExternalEntityParserCreate(XML_Parser oldParser, - const XML_Char *context, - const XML_Char *encodingName) -{ - XML_Parser parser = oldParser; - DTD *newDtd = NULL; - DTD *oldDtd = _dtd; - XML_StartElementHandler oldStartElementHandler = startElementHandler; - XML_EndElementHandler oldEndElementHandler = endElementHandler; - XML_CharacterDataHandler oldCharacterDataHandler = characterDataHandler; - XML_ProcessingInstructionHandler oldProcessingInstructionHandler - = processingInstructionHandler; - XML_CommentHandler oldCommentHandler = commentHandler; - XML_StartCdataSectionHandler oldStartCdataSectionHandler - = startCdataSectionHandler; - XML_EndCdataSectionHandler oldEndCdataSectionHandler - = endCdataSectionHandler; - XML_DefaultHandler oldDefaultHandler = defaultHandler; - XML_UnparsedEntityDeclHandler oldUnparsedEntityDeclHandler - = unparsedEntityDeclHandler; - XML_NotationDeclHandler oldNotationDeclHandler = notationDeclHandler; - XML_StartNamespaceDeclHandler oldStartNamespaceDeclHandler - = startNamespaceDeclHandler; - XML_EndNamespaceDeclHandler oldEndNamespaceDeclHandler - = endNamespaceDeclHandler; - XML_NotStandaloneHandler oldNotStandaloneHandler = notStandaloneHandler; - XML_ExternalEntityRefHandler oldExternalEntityRefHandler - = externalEntityRefHandler; - XML_SkippedEntityHandler oldSkippedEntityHandler = skippedEntityHandler; - XML_UnknownEncodingHandler oldUnknownEncodingHandler - = unknownEncodingHandler; - XML_ElementDeclHandler oldElementDeclHandler = elementDeclHandler; - XML_AttlistDeclHandler oldAttlistDeclHandler = attlistDeclHandler; - XML_EntityDeclHandler oldEntityDeclHandler = entityDeclHandler; - XML_XmlDeclHandler oldXmlDeclHandler = xmlDeclHandler; - ELEMENT_TYPE * oldDeclElementType = declElementType; - - void *oldUserData = userData; - void *oldHandlerArg = handlerArg; - XML_Bool oldDefaultExpandInternalEntities = defaultExpandInternalEntities; - XML_Parser oldExternalEntityRefHandlerArg = externalEntityRefHandlerArg; -#ifdef XML_DTD - enum XML_ParamEntityParsing oldParamEntityParsing = paramEntityParsing; - int oldInEntityValue = prologState.inEntityValue; -#endif - XML_Bool oldns_triplets = ns_triplets; - /* Note that the new parser shares the same hash secret as the old - parser, so that dtdCopy and copyEntityTable can lookup values - from hash tables associated with either parser without us having - to worry which hash secrets each table has. - */ - unsigned long oldhash_secret_salt = hash_secret_salt; - -#ifdef XML_DTD - if (!context) - newDtd = oldDtd; -#endif /* XML_DTD */ - - /* Note that the magical uses of the pre-processor to make field - access look more like C++ require that `parser' be overwritten - here. This makes this function more painful to follow than it - would be otherwise. - */ - if (ns) { - XML_Char tmp[2]; - *tmp = namespaceSeparator; - parser = parserCreate(encodingName, &parser->m_mem, tmp, newDtd); - } - else { - parser = parserCreate(encodingName, &parser->m_mem, NULL, newDtd); - } - - if (!parser) - return NULL; - - startElementHandler = oldStartElementHandler; - endElementHandler = oldEndElementHandler; - characterDataHandler = oldCharacterDataHandler; - processingInstructionHandler = oldProcessingInstructionHandler; - commentHandler = oldCommentHandler; - startCdataSectionHandler = oldStartCdataSectionHandler; - endCdataSectionHandler = oldEndCdataSectionHandler; - defaultHandler = oldDefaultHandler; - unparsedEntityDeclHandler = oldUnparsedEntityDeclHandler; - notationDeclHandler = oldNotationDeclHandler; - startNamespaceDeclHandler = oldStartNamespaceDeclHandler; - endNamespaceDeclHandler = oldEndNamespaceDeclHandler; - notStandaloneHandler = oldNotStandaloneHandler; - externalEntityRefHandler = oldExternalEntityRefHandler; - skippedEntityHandler = oldSkippedEntityHandler; - unknownEncodingHandler = oldUnknownEncodingHandler; - elementDeclHandler = oldElementDeclHandler; - attlistDeclHandler = oldAttlistDeclHandler; - entityDeclHandler = oldEntityDeclHandler; - xmlDeclHandler = oldXmlDeclHandler; - declElementType = oldDeclElementType; - userData = oldUserData; - if (oldUserData == oldHandlerArg) - handlerArg = userData; - else - handlerArg = parser; - if (oldExternalEntityRefHandlerArg != oldParser) - externalEntityRefHandlerArg = oldExternalEntityRefHandlerArg; - defaultExpandInternalEntities = oldDefaultExpandInternalEntities; - ns_triplets = oldns_triplets; - hash_secret_salt = oldhash_secret_salt; - parentParser = oldParser; -#ifdef XML_DTD - paramEntityParsing = oldParamEntityParsing; - prologState.inEntityValue = oldInEntityValue; - if (context) { -#endif /* XML_DTD */ - if (!dtdCopy(oldParser, _dtd, oldDtd, &parser->m_mem) - || !setContext(parser, context)) { - XML_ParserFree(parser); - return NULL; - } - processor = externalEntityInitProcessor; -#ifdef XML_DTD - } - else { - /* The DTD instance referenced by _dtd is shared between the document's - root parser and external PE parsers, therefore one does not need to - call setContext. In addition, one also *must* not call setContext, - because this would overwrite existing prefix->binding pointers in - _dtd with ones that get destroyed with the external PE parser. - This would leave those prefixes with dangling pointers. - */ - isParamEntity = XML_TRUE; - XmlPrologStateInitExternalEntity(&prologState); - processor = externalParEntInitProcessor; - } -#endif /* XML_DTD */ - return parser; -} - -static void FASTCALL -destroyBindings(BINDING *bindings, XML_Parser parser) -{ - for (;;) { - BINDING *b = bindings; - if (!b) - break; - bindings = b->nextTagBinding; - FREE(b->uri); - FREE(b); - } -} - -void XMLCALL -XML_ParserFree(XML_Parser parser) -{ - TAG *tagList; - OPEN_INTERNAL_ENTITY *entityList; - if (parser == NULL) - return; - /* free tagStack and freeTagList */ - tagList = tagStack; - for (;;) { - TAG *p; - if (tagList == NULL) { - if (freeTagList == NULL) - break; - tagList = freeTagList; - freeTagList = NULL; - } - p = tagList; - tagList = tagList->parent; - FREE(p->buf); - destroyBindings(p->bindings, parser); - FREE(p); - } - /* free openInternalEntities and freeInternalEntities */ - entityList = openInternalEntities; - for (;;) { - OPEN_INTERNAL_ENTITY *openEntity; - if (entityList == NULL) { - if (freeInternalEntities == NULL) - break; - entityList = freeInternalEntities; - freeInternalEntities = NULL; - } - openEntity = entityList; - entityList = entityList->next; - FREE(openEntity); - } - - destroyBindings(freeBindingList, parser); - destroyBindings(inheritedBindings, parser); - poolDestroy(&tempPool); - poolDestroy(&temp2Pool); -#ifdef XML_DTD - /* external parameter entity parsers share the DTD structure - parser->m_dtd with the root parser, so we must not destroy it - */ - if (!isParamEntity && _dtd) -#else - if (_dtd) -#endif /* XML_DTD */ - dtdDestroy(_dtd, (XML_Bool)!parentParser, &parser->m_mem); - FREE((void *)atts); -#ifdef XML_ATTR_INFO - FREE((void *)attInfo); -#endif - FREE(groupConnector); - FREE(buffer); - FREE(dataBuf); - FREE(nsAtts); - FREE(unknownEncodingMem); - if (unknownEncodingRelease) - unknownEncodingRelease(unknownEncodingData); - FREE(parser); -} - -void XMLCALL -XML_UseParserAsHandlerArg(XML_Parser parser) -{ - handlerArg = parser; -} - -enum XML_Error XMLCALL -XML_UseForeignDTD(XML_Parser parser, XML_Bool useDTD) -{ -#ifdef XML_DTD - /* block after XML_Parse()/XML_ParseBuffer() has been called */ - if (ps_parsing == XML_PARSING || ps_parsing == XML_SUSPENDED) - return XML_ERROR_CANT_CHANGE_FEATURE_ONCE_PARSING; - useForeignDTD = useDTD; - return XML_ERROR_NONE; -#else - return XML_ERROR_FEATURE_REQUIRES_XML_DTD; -#endif -} - -void XMLCALL -XML_SetReturnNSTriplet(XML_Parser parser, int do_nst) -{ - /* block after XML_Parse()/XML_ParseBuffer() has been called */ - if (ps_parsing == XML_PARSING || ps_parsing == XML_SUSPENDED) - return; - ns_triplets = do_nst ? XML_TRUE : XML_FALSE; -} - -void XMLCALL -XML_SetUserData(XML_Parser parser, void *p) -{ - if (handlerArg == userData) - handlerArg = userData = p; - else - userData = p; -} - -enum XML_Status XMLCALL -XML_SetBase(XML_Parser parser, const XML_Char *p) -{ - if (p) { - p = poolCopyString(&_dtd->pool, p); - if (!p) - return XML_STATUS_ERROR; - curBase = p; - } - else - curBase = NULL; - return XML_STATUS_OK; -} - -const XML_Char * XMLCALL -XML_GetBase(XML_Parser parser) -{ - return curBase; -} - -int XMLCALL -XML_GetSpecifiedAttributeCount(XML_Parser parser) -{ - return nSpecifiedAtts; -} - -int XMLCALL -XML_GetIdAttributeIndex(XML_Parser parser) -{ - return idAttIndex; -} - -#ifdef XML_ATTR_INFO -const XML_AttrInfo * XMLCALL -XML_GetAttributeInfo(XML_Parser parser) -{ - return attInfo; -} -#endif - -void XMLCALL -XML_SetElementHandler(XML_Parser parser, - XML_StartElementHandler start, - XML_EndElementHandler end) -{ - startElementHandler = start; - endElementHandler = end; -} - -void XMLCALL -XML_SetStartElementHandler(XML_Parser parser, - XML_StartElementHandler start) { - startElementHandler = start; -} - -void XMLCALL -XML_SetEndElementHandler(XML_Parser parser, - XML_EndElementHandler end) { - endElementHandler = end; -} - -void XMLCALL -XML_SetCharacterDataHandler(XML_Parser parser, - XML_CharacterDataHandler handler) -{ - characterDataHandler = handler; -} - -void XMLCALL -XML_SetProcessingInstructionHandler(XML_Parser parser, - XML_ProcessingInstructionHandler handler) -{ - processingInstructionHandler = handler; -} - -void XMLCALL -XML_SetCommentHandler(XML_Parser parser, - XML_CommentHandler handler) -{ - commentHandler = handler; -} - -void XMLCALL -XML_SetCdataSectionHandler(XML_Parser parser, - XML_StartCdataSectionHandler start, - XML_EndCdataSectionHandler end) -{ - startCdataSectionHandler = start; - endCdataSectionHandler = end; -} - -void XMLCALL -XML_SetStartCdataSectionHandler(XML_Parser parser, - XML_StartCdataSectionHandler start) { - startCdataSectionHandler = start; -} - -void XMLCALL -XML_SetEndCdataSectionHandler(XML_Parser parser, - XML_EndCdataSectionHandler end) { - endCdataSectionHandler = end; -} - -void XMLCALL -XML_SetDefaultHandler(XML_Parser parser, - XML_DefaultHandler handler) -{ - defaultHandler = handler; - defaultExpandInternalEntities = XML_FALSE; -} - -void XMLCALL -XML_SetDefaultHandlerExpand(XML_Parser parser, - XML_DefaultHandler handler) -{ - defaultHandler = handler; - defaultExpandInternalEntities = XML_TRUE; -} - -void XMLCALL -XML_SetDoctypeDeclHandler(XML_Parser parser, - XML_StartDoctypeDeclHandler start, - XML_EndDoctypeDeclHandler end) -{ - startDoctypeDeclHandler = start; - endDoctypeDeclHandler = end; -} - -void XMLCALL -XML_SetStartDoctypeDeclHandler(XML_Parser parser, - XML_StartDoctypeDeclHandler start) { - startDoctypeDeclHandler = start; -} - -void XMLCALL -XML_SetEndDoctypeDeclHandler(XML_Parser parser, - XML_EndDoctypeDeclHandler end) { - endDoctypeDeclHandler = end; -} - -void XMLCALL -XML_SetUnparsedEntityDeclHandler(XML_Parser parser, - XML_UnparsedEntityDeclHandler handler) -{ - unparsedEntityDeclHandler = handler; -} - -void XMLCALL -XML_SetNotationDeclHandler(XML_Parser parser, - XML_NotationDeclHandler handler) -{ - notationDeclHandler = handler; -} - -void XMLCALL -XML_SetNamespaceDeclHandler(XML_Parser parser, - XML_StartNamespaceDeclHandler start, - XML_EndNamespaceDeclHandler end) -{ - startNamespaceDeclHandler = start; - endNamespaceDeclHandler = end; -} - -void XMLCALL -XML_SetStartNamespaceDeclHandler(XML_Parser parser, - XML_StartNamespaceDeclHandler start) { - startNamespaceDeclHandler = start; -} - -void XMLCALL -XML_SetEndNamespaceDeclHandler(XML_Parser parser, - XML_EndNamespaceDeclHandler end) { - endNamespaceDeclHandler = end; -} - -void XMLCALL -XML_SetNotStandaloneHandler(XML_Parser parser, - XML_NotStandaloneHandler handler) -{ - notStandaloneHandler = handler; -} - -void XMLCALL -XML_SetExternalEntityRefHandler(XML_Parser parser, - XML_ExternalEntityRefHandler handler) -{ - externalEntityRefHandler = handler; -} - -void XMLCALL -XML_SetExternalEntityRefHandlerArg(XML_Parser parser, void *arg) -{ - if (arg) - externalEntityRefHandlerArg = (XML_Parser)arg; - else - externalEntityRefHandlerArg = parser; -} - -void XMLCALL -XML_SetSkippedEntityHandler(XML_Parser parser, - XML_SkippedEntityHandler handler) -{ - skippedEntityHandler = handler; -} - -void XMLCALL -XML_SetUnknownEncodingHandler(XML_Parser parser, - XML_UnknownEncodingHandler handler, - void *data) -{ - unknownEncodingHandler = handler; - unknownEncodingHandlerData = data; -} - -void XMLCALL -XML_SetElementDeclHandler(XML_Parser parser, - XML_ElementDeclHandler eldecl) -{ - elementDeclHandler = eldecl; -} - -void XMLCALL -XML_SetAttlistDeclHandler(XML_Parser parser, - XML_AttlistDeclHandler attdecl) -{ - attlistDeclHandler = attdecl; -} - -void XMLCALL -XML_SetEntityDeclHandler(XML_Parser parser, - XML_EntityDeclHandler handler) -{ - entityDeclHandler = handler; -} - -void XMLCALL -XML_SetXmlDeclHandler(XML_Parser parser, - XML_XmlDeclHandler handler) { - xmlDeclHandler = handler; -} - -int XMLCALL -XML_SetParamEntityParsing(XML_Parser parser, - enum XML_ParamEntityParsing peParsing) -{ - /* block after XML_Parse()/XML_ParseBuffer() has been called */ - if (ps_parsing == XML_PARSING || ps_parsing == XML_SUSPENDED) - return 0; -#ifdef XML_DTD - paramEntityParsing = peParsing; - return 1; -#else - return peParsing == XML_PARAM_ENTITY_PARSING_NEVER; -#endif -} - -int XMLCALL -XML_SetHashSalt(XML_Parser parser, - unsigned long hash_salt) -{ - /* block after XML_Parse()/XML_ParseBuffer() has been called */ - if (ps_parsing == XML_PARSING || ps_parsing == XML_SUSPENDED) - return 0; - hash_secret_salt = hash_salt; - return 1; -} - -enum XML_Status XMLCALL -XML_Parse(XML_Parser parser, const char *s, int len, int isFinal) -{ - switch (ps_parsing) { - case XML_SUSPENDED: - errorCode = XML_ERROR_SUSPENDED; - return XML_STATUS_ERROR; - case XML_FINISHED: - errorCode = XML_ERROR_FINISHED; - return XML_STATUS_ERROR; - case XML_INITIALIZED: - if (parentParser == NULL && !startParsing(parser)) { - errorCode = XML_ERROR_NO_MEMORY; - return XML_STATUS_ERROR; - } - default: - ps_parsing = XML_PARSING; - } - - if (len == 0) { - ps_finalBuffer = (XML_Bool)isFinal; - if (!isFinal) - return XML_STATUS_OK; - positionPtr = bufferPtr; - parseEndPtr = bufferEnd; - - /* If data are left over from last buffer, and we now know that these - data are the final chunk of input, then we have to check them again - to detect errors based on that fact. - */ - errorCode = processor(parser, bufferPtr, parseEndPtr, &bufferPtr); - - if (errorCode == XML_ERROR_NONE) { - switch (ps_parsing) { - case XML_SUSPENDED: - XmlUpdatePosition(encoding, positionPtr, bufferPtr, &position); - positionPtr = bufferPtr; - return XML_STATUS_SUSPENDED; - case XML_INITIALIZED: - case XML_PARSING: - ps_parsing = XML_FINISHED; - /* fall through */ - default: - return XML_STATUS_OK; - } - } - eventEndPtr = eventPtr; - processor = errorProcessor; - return XML_STATUS_ERROR; - } -#ifndef XML_CONTEXT_BYTES - else if (bufferPtr == bufferEnd) { - const char *end; - int nLeftOver; - enum XML_Status result; - parseEndByteIndex += len; - positionPtr = s; - ps_finalBuffer = (XML_Bool)isFinal; - - errorCode = processor(parser, s, parseEndPtr = s + len, &end); - - if (errorCode != XML_ERROR_NONE) { - eventEndPtr = eventPtr; - processor = errorProcessor; - return XML_STATUS_ERROR; - } - else { - switch (ps_parsing) { - case XML_SUSPENDED: - result = XML_STATUS_SUSPENDED; - break; - case XML_INITIALIZED: - case XML_PARSING: - if (isFinal) { - ps_parsing = XML_FINISHED; - return XML_STATUS_OK; - } - /* fall through */ - default: - result = XML_STATUS_OK; - } - } - - XmlUpdatePosition(encoding, positionPtr, end, &position); - nLeftOver = s + len - end; - if (nLeftOver) { - if (buffer == NULL || nLeftOver > bufferLim - buffer) { - /* FIXME avoid integer overflow */ - char *temp; - temp = (buffer == NULL - ? (char *)MALLOC(len * 2) - : (char *)REALLOC(buffer, len * 2)); - if (temp == NULL) { - errorCode = XML_ERROR_NO_MEMORY; - eventPtr = eventEndPtr = NULL; - processor = errorProcessor; - return XML_STATUS_ERROR; - } - buffer = temp; - bufferLim = buffer + len * 2; - } - memcpy(buffer, end, nLeftOver); - } - bufferPtr = buffer; - bufferEnd = buffer + nLeftOver; - positionPtr = bufferPtr; - parseEndPtr = bufferEnd; - eventPtr = bufferPtr; - eventEndPtr = bufferPtr; - return result; - } -#endif /* not defined XML_CONTEXT_BYTES */ - else { - void *buff = XML_GetBuffer(parser, len); - if (buff == NULL) - return XML_STATUS_ERROR; - else { - memcpy(buff, s, len); - return XML_ParseBuffer(parser, len, isFinal); - } - } -} - -enum XML_Status XMLCALL -XML_ParseBuffer(XML_Parser parser, int len, int isFinal) -{ - const char *start; - enum XML_Status result = XML_STATUS_OK; - - switch (ps_parsing) { - case XML_SUSPENDED: - errorCode = XML_ERROR_SUSPENDED; - return XML_STATUS_ERROR; - case XML_FINISHED: - errorCode = XML_ERROR_FINISHED; - return XML_STATUS_ERROR; - case XML_INITIALIZED: - if (parentParser == NULL && !startParsing(parser)) { - errorCode = XML_ERROR_NO_MEMORY; - return XML_STATUS_ERROR; - } - default: - ps_parsing = XML_PARSING; - } - - start = bufferPtr; - positionPtr = start; - bufferEnd += len; - parseEndPtr = bufferEnd; - parseEndByteIndex += len; - ps_finalBuffer = (XML_Bool)isFinal; - - errorCode = processor(parser, start, parseEndPtr, &bufferPtr); - - if (errorCode != XML_ERROR_NONE) { - eventEndPtr = eventPtr; - processor = errorProcessor; - return XML_STATUS_ERROR; - } - else { - switch (ps_parsing) { - case XML_SUSPENDED: - result = XML_STATUS_SUSPENDED; - break; - case XML_INITIALIZED: - case XML_PARSING: - if (isFinal) { - ps_parsing = XML_FINISHED; - return result; - } - default: ; /* should not happen */ - } - } - - XmlUpdatePosition(encoding, positionPtr, bufferPtr, &position); - positionPtr = bufferPtr; - return result; -} - -void * XMLCALL -XML_GetBuffer(XML_Parser parser, int len) -{ - if (len < 0) { - errorCode = XML_ERROR_NO_MEMORY; - return NULL; - } - switch (ps_parsing) { - case XML_SUSPENDED: - errorCode = XML_ERROR_SUSPENDED; - return NULL; - case XML_FINISHED: - errorCode = XML_ERROR_FINISHED; - return NULL; - default: ; - } - - if (len > bufferLim - bufferEnd) { -#ifdef XML_CONTEXT_BYTES - int keep; -#endif /* defined XML_CONTEXT_BYTES */ - /* Do not invoke signed arithmetic overflow: */ - int neededSize = (int) ((unsigned)len + (unsigned)(bufferEnd - bufferPtr)); - if (neededSize < 0) { - errorCode = XML_ERROR_NO_MEMORY; - return NULL; - } -#ifdef XML_CONTEXT_BYTES - keep = (int)(bufferPtr - buffer); - if (keep > XML_CONTEXT_BYTES) - keep = XML_CONTEXT_BYTES; - neededSize += keep; -#endif /* defined XML_CONTEXT_BYTES */ - if (neededSize <= bufferLim - buffer) { -#ifdef XML_CONTEXT_BYTES - if (keep < bufferPtr - buffer) { - int offset = (int)(bufferPtr - buffer) - keep; - memmove(buffer, &buffer[offset], bufferEnd - bufferPtr + keep); - bufferEnd -= offset; - bufferPtr -= offset; - } -#else - memmove(buffer, bufferPtr, bufferEnd - bufferPtr); - bufferEnd = buffer + (bufferEnd - bufferPtr); - bufferPtr = buffer; -#endif /* not defined XML_CONTEXT_BYTES */ - } - else { - char *newBuf; - int bufferSize = (int)(bufferLim - bufferPtr); - if (bufferSize == 0) - bufferSize = INIT_BUFFER_SIZE; - do { - /* Do not invoke signed arithmetic overflow: */ - bufferSize = (int) (2U * (unsigned) bufferSize); - } while (bufferSize < neededSize && bufferSize > 0); - if (bufferSize <= 0) { - errorCode = XML_ERROR_NO_MEMORY; - return NULL; - } - newBuf = (char *)MALLOC(bufferSize); - if (newBuf == 0) { - errorCode = XML_ERROR_NO_MEMORY; - return NULL; - } - bufferLim = newBuf + bufferSize; -#ifdef XML_CONTEXT_BYTES - if (bufferPtr) { - int keep = (int)(bufferPtr - buffer); - if (keep > XML_CONTEXT_BYTES) - keep = XML_CONTEXT_BYTES; - memcpy(newBuf, &bufferPtr[-keep], bufferEnd - bufferPtr + keep); - FREE(buffer); - buffer = newBuf; - bufferEnd = buffer + (bufferEnd - bufferPtr) + keep; - bufferPtr = buffer + keep; - } - else { - bufferEnd = newBuf + (bufferEnd - bufferPtr); - bufferPtr = buffer = newBuf; - } -#else - if (bufferPtr) { - memcpy(newBuf, bufferPtr, bufferEnd - bufferPtr); - FREE(buffer); - } - bufferEnd = newBuf + (bufferEnd - bufferPtr); - bufferPtr = buffer = newBuf; -#endif /* not defined XML_CONTEXT_BYTES */ - } - eventPtr = eventEndPtr = NULL; - positionPtr = NULL; - } - return bufferEnd; -} - -enum XML_Status XMLCALL -XML_StopParser(XML_Parser parser, XML_Bool resumable) -{ - switch (ps_parsing) { - case XML_SUSPENDED: - if (resumable) { - errorCode = XML_ERROR_SUSPENDED; - return XML_STATUS_ERROR; - } - ps_parsing = XML_FINISHED; - break; - case XML_FINISHED: - errorCode = XML_ERROR_FINISHED; - return XML_STATUS_ERROR; - default: - if (resumable) { -#ifdef XML_DTD - if (isParamEntity) { - errorCode = XML_ERROR_SUSPEND_PE; - return XML_STATUS_ERROR; - } -#endif - ps_parsing = XML_SUSPENDED; - } - else - ps_parsing = XML_FINISHED; - } - return XML_STATUS_OK; -} - -enum XML_Status XMLCALL -XML_ResumeParser(XML_Parser parser) -{ - enum XML_Status result = XML_STATUS_OK; - - if (ps_parsing != XML_SUSPENDED) { - errorCode = XML_ERROR_NOT_SUSPENDED; - return XML_STATUS_ERROR; - } - ps_parsing = XML_PARSING; - - errorCode = processor(parser, bufferPtr, parseEndPtr, &bufferPtr); - - if (errorCode != XML_ERROR_NONE) { - eventEndPtr = eventPtr; - processor = errorProcessor; - return XML_STATUS_ERROR; - } - else { - switch (ps_parsing) { - case XML_SUSPENDED: - result = XML_STATUS_SUSPENDED; - break; - case XML_INITIALIZED: - case XML_PARSING: - if (ps_finalBuffer) { - ps_parsing = XML_FINISHED; - return result; - } - default: ; - } - } - - XmlUpdatePosition(encoding, positionPtr, bufferPtr, &position); - positionPtr = bufferPtr; - return result; -} - -void XMLCALL -XML_GetParsingStatus(XML_Parser parser, XML_ParsingStatus *status) -{ - assert(status != NULL); - *status = parser->m_parsingStatus; -} - -enum XML_Error XMLCALL -XML_GetErrorCode(XML_Parser parser) -{ - return errorCode; -} - -XML_Index XMLCALL -XML_GetCurrentByteIndex(XML_Parser parser) -{ - if (eventPtr) - return (XML_Index)(parseEndByteIndex - (parseEndPtr - eventPtr)); - return -1; -} - -int XMLCALL -XML_GetCurrentByteCount(XML_Parser parser) -{ - if (eventEndPtr && eventPtr) - return (int)(eventEndPtr - eventPtr); - return 0; -} - -const char * XMLCALL -XML_GetInputContext(XML_Parser parser, int *offset, int *size) -{ -#ifdef XML_CONTEXT_BYTES - if (eventPtr && buffer) { - *offset = (int)(eventPtr - buffer); - *size = (int)(bufferEnd - buffer); - return buffer; - } -#endif /* defined XML_CONTEXT_BYTES */ - return (char *) 0; -} - -XML_Size XMLCALL -XML_GetCurrentLineNumber(XML_Parser parser) -{ - if (eventPtr && eventPtr >= positionPtr) { - XmlUpdatePosition(encoding, positionPtr, eventPtr, &position); - positionPtr = eventPtr; - } - return position.lineNumber + 1; -} - -XML_Size XMLCALL -XML_GetCurrentColumnNumber(XML_Parser parser) -{ - if (eventPtr && eventPtr >= positionPtr) { - XmlUpdatePosition(encoding, positionPtr, eventPtr, &position); - positionPtr = eventPtr; - } - return position.columnNumber; -} - -void XMLCALL -XML_FreeContentModel(XML_Parser parser, XML_Content *model) -{ - FREE(model); -} - -void * XMLCALL -XML_MemMalloc(XML_Parser parser, size_t size) -{ - return MALLOC(size); -} - -void * XMLCALL -XML_MemRealloc(XML_Parser parser, void *ptr, size_t size) -{ - return REALLOC(ptr, size); -} - -void XMLCALL -XML_MemFree(XML_Parser parser, void *ptr) -{ - FREE(ptr); -} - -void XMLCALL -XML_DefaultCurrent(XML_Parser parser) -{ - if (defaultHandler) { - if (openInternalEntities) - reportDefault(parser, - internalEncoding, - openInternalEntities->internalEventPtr, - openInternalEntities->internalEventEndPtr); - else - reportDefault(parser, encoding, eventPtr, eventEndPtr); - } -} - -const XML_LChar * XMLCALL -XML_ErrorString(enum XML_Error code) -{ - static const XML_LChar* const message[] = { - 0, - XML_L("out of memory"), - XML_L("syntax error"), - XML_L("no element found"), - XML_L("not well-formed (invalid token)"), - XML_L("unclosed token"), - XML_L("partial character"), - XML_L("mismatched tag"), - XML_L("duplicate attribute"), - XML_L("junk after document element"), - XML_L("illegal parameter entity reference"), - XML_L("undefined entity"), - XML_L("recursive entity reference"), - XML_L("asynchronous entity"), - XML_L("reference to invalid character number"), - XML_L("reference to binary entity"), - XML_L("reference to external entity in attribute"), - XML_L("XML or text declaration not at start of entity"), - XML_L("unknown encoding"), - XML_L("encoding specified in XML declaration is incorrect"), - XML_L("unclosed CDATA section"), - XML_L("error in processing external entity reference"), - XML_L("document is not standalone"), - XML_L("unexpected parser state - please send a bug report"), - XML_L("entity declared in parameter entity"), - XML_L("requested feature requires XML_DTD support in Expat"), - XML_L("cannot change setting once parsing has begun"), - XML_L("unbound prefix"), - XML_L("must not undeclare prefix"), - XML_L("incomplete markup in parameter entity"), - XML_L("XML declaration not well-formed"), - XML_L("text declaration not well-formed"), - XML_L("illegal character(s) in public id"), - XML_L("parser suspended"), - XML_L("parser not suspended"), - XML_L("parsing aborted"), - XML_L("parsing finished"), - XML_L("cannot suspend in external parameter entity"), - XML_L("reserved prefix (xml) must not be undeclared or bound to another namespace name"), - XML_L("reserved prefix (xmlns) must not be declared or undeclared"), - XML_L("prefix must not be bound to one of the reserved namespace names") - }; - if (code > 0 && code < sizeof(message)/sizeof(message[0])) - return message[code]; - return NULL; -} - -const XML_LChar * XMLCALL -XML_ExpatVersion(void) { - - /* V1 is used to string-ize the version number. However, it would - string-ize the actual version macro *names* unless we get them - substituted before being passed to V1. CPP is defined to expand - a macro, then rescan for more expansions. Thus, we use V2 to expand - the version macros, then CPP will expand the resulting V1() macro - with the correct numerals. */ - /* ### I'm assuming cpp is portable in this respect... */ - -#define V1(a,b,c) XML_L(#a)XML_L(".")XML_L(#b)XML_L(".")XML_L(#c) -#define V2(a,b,c) XML_L("expat_")V1(a,b,c) - - return V2(XML_MAJOR_VERSION, XML_MINOR_VERSION, XML_MICRO_VERSION); - -#undef V1 -#undef V2 -} - -XML_Expat_Version XMLCALL -XML_ExpatVersionInfo(void) -{ - XML_Expat_Version version; - - version.major = XML_MAJOR_VERSION; - version.minor = XML_MINOR_VERSION; - version.micro = XML_MICRO_VERSION; - - return version; -} - -const XML_Feature * XMLCALL -XML_GetFeatureList(void) -{ - static const XML_Feature features[] = { - {XML_FEATURE_SIZEOF_XML_CHAR, XML_L("sizeof(XML_Char)"), - sizeof(XML_Char)}, - {XML_FEATURE_SIZEOF_XML_LCHAR, XML_L("sizeof(XML_LChar)"), - sizeof(XML_LChar)}, -#ifdef XML_UNICODE - {XML_FEATURE_UNICODE, XML_L("XML_UNICODE"), 0}, -#endif -#ifdef XML_UNICODE_WCHAR_T - {XML_FEATURE_UNICODE_WCHAR_T, XML_L("XML_UNICODE_WCHAR_T"), 0}, -#endif -#ifdef XML_DTD - {XML_FEATURE_DTD, XML_L("XML_DTD"), 0}, -#endif -#ifdef XML_CONTEXT_BYTES - {XML_FEATURE_CONTEXT_BYTES, XML_L("XML_CONTEXT_BYTES"), - XML_CONTEXT_BYTES}, -#endif -#ifdef XML_MIN_SIZE - {XML_FEATURE_MIN_SIZE, XML_L("XML_MIN_SIZE"), 0}, -#endif -#ifdef XML_NS - {XML_FEATURE_NS, XML_L("XML_NS"), 0}, -#endif -#ifdef XML_LARGE_SIZE - {XML_FEATURE_LARGE_SIZE, XML_L("XML_LARGE_SIZE"), 0}, -#endif -#ifdef XML_ATTR_INFO - {XML_FEATURE_ATTR_INFO, XML_L("XML_ATTR_INFO"), 0}, -#endif - {XML_FEATURE_END, NULL, 0} - }; - - return features; -} - -/* Initially tag->rawName always points into the parse buffer; - for those TAG instances opened while the current parse buffer was - processed, and not yet closed, we need to store tag->rawName in a more - permanent location, since the parse buffer is about to be discarded. -*/ -static XML_Bool -storeRawNames(XML_Parser parser) -{ - TAG *tag = tagStack; - while (tag) { - int bufSize; - int nameLen = sizeof(XML_Char) * (tag->name.strLen + 1); - char *rawNameBuf = tag->buf + nameLen; - /* Stop if already stored. Since tagStack is a stack, we can stop - at the first entry that has already been copied; everything - below it in the stack is already been accounted for in a - previous call to this function. - */ - if (tag->rawName == rawNameBuf) - break; - /* For re-use purposes we need to ensure that the - size of tag->buf is a multiple of sizeof(XML_Char). - */ - bufSize = nameLen + ROUND_UP(tag->rawNameLength, sizeof(XML_Char)); - if (bufSize > tag->bufEnd - tag->buf) { - char *temp = (char *)REALLOC(tag->buf, bufSize); - if (temp == NULL) - return XML_FALSE; - /* if tag->name.str points to tag->buf (only when namespace - processing is off) then we have to update it - */ - if (tag->name.str == (XML_Char *)tag->buf) - tag->name.str = (XML_Char *)temp; - /* if tag->name.localPart is set (when namespace processing is on) - then update it as well, since it will always point into tag->buf - */ - if (tag->name.localPart) - tag->name.localPart = (XML_Char *)temp + (tag->name.localPart - - (XML_Char *)tag->buf); - tag->buf = temp; - tag->bufEnd = temp + bufSize; - rawNameBuf = temp + nameLen; - } - memcpy(rawNameBuf, tag->rawName, tag->rawNameLength); - tag->rawName = rawNameBuf; - tag = tag->parent; - } - return XML_TRUE; -} - -static enum XML_Error PTRCALL -contentProcessor(XML_Parser parser, - const char *start, - const char *end, - const char **endPtr) -{ - enum XML_Error result = doContent(parser, 0, encoding, start, end, - endPtr, (XML_Bool)!ps_finalBuffer); - if (result == XML_ERROR_NONE) { - if (!storeRawNames(parser)) - return XML_ERROR_NO_MEMORY; - } - return result; -} - -static enum XML_Error PTRCALL -externalEntityInitProcessor(XML_Parser parser, - const char *start, - const char *end, - const char **endPtr) -{ - enum XML_Error result = initializeEncoding(parser); - if (result != XML_ERROR_NONE) - return result; - processor = externalEntityInitProcessor2; - return externalEntityInitProcessor2(parser, start, end, endPtr); -} - -static enum XML_Error PTRCALL -externalEntityInitProcessor2(XML_Parser parser, - const char *start, - const char *end, - const char **endPtr) -{ - const char *next = start; /* XmlContentTok doesn't always set the last arg */ - int tok = XmlContentTok(encoding, start, end, &next); - switch (tok) { - case XML_TOK_BOM: - /* If we are at the end of the buffer, this would cause the next stage, - i.e. externalEntityInitProcessor3, to pass control directly to - doContent (by detecting XML_TOK_NONE) without processing any xml text - declaration - causing the error XML_ERROR_MISPLACED_XML_PI in doContent. - */ - if (next == end && !ps_finalBuffer) { - *endPtr = next; - return XML_ERROR_NONE; - } - start = next; - break; - case XML_TOK_PARTIAL: - if (!ps_finalBuffer) { - *endPtr = start; - return XML_ERROR_NONE; - } - eventPtr = start; - return XML_ERROR_UNCLOSED_TOKEN; - case XML_TOK_PARTIAL_CHAR: - if (!ps_finalBuffer) { - *endPtr = start; - return XML_ERROR_NONE; - } - eventPtr = start; - return XML_ERROR_PARTIAL_CHAR; - } - processor = externalEntityInitProcessor3; - return externalEntityInitProcessor3(parser, start, end, endPtr); -} - -static enum XML_Error PTRCALL -externalEntityInitProcessor3(XML_Parser parser, - const char *start, - const char *end, - const char **endPtr) -{ - int tok; - const char *next = start; /* XmlContentTok doesn't always set the last arg */ - eventPtr = start; - tok = XmlContentTok(encoding, start, end, &next); - eventEndPtr = next; - - switch (tok) { - case XML_TOK_XML_DECL: - { - enum XML_Error result; - result = processXmlDecl(parser, 1, start, next); - if (result != XML_ERROR_NONE) - return result; - switch (ps_parsing) { - case XML_SUSPENDED: - *endPtr = next; - return XML_ERROR_NONE; - case XML_FINISHED: - return XML_ERROR_ABORTED; - default: - start = next; - } - } - break; - case XML_TOK_PARTIAL: - if (!ps_finalBuffer) { - *endPtr = start; - return XML_ERROR_NONE; - } - return XML_ERROR_UNCLOSED_TOKEN; - case XML_TOK_PARTIAL_CHAR: - if (!ps_finalBuffer) { - *endPtr = start; - return XML_ERROR_NONE; - } - return XML_ERROR_PARTIAL_CHAR; - } - processor = externalEntityContentProcessor; - tagLevel = 1; - return externalEntityContentProcessor(parser, start, end, endPtr); -} - -static enum XML_Error PTRCALL -externalEntityContentProcessor(XML_Parser parser, - const char *start, - const char *end, - const char **endPtr) -{ - enum XML_Error result = doContent(parser, 1, encoding, start, end, - endPtr, (XML_Bool)!ps_finalBuffer); - if (result == XML_ERROR_NONE) { - if (!storeRawNames(parser)) - return XML_ERROR_NO_MEMORY; - } - return result; -} - -static enum XML_Error -doContent(XML_Parser parser, - int startTagLevel, - const ENCODING *enc, - const char *s, - const char *end, - const char **nextPtr, - XML_Bool haveMore) -{ - /* save one level of indirection */ - DTD * const dtd = _dtd; - - const char **eventPP; - const char **eventEndPP; - if (enc == encoding) { - eventPP = &eventPtr; - eventEndPP = &eventEndPtr; - } - else { - eventPP = &(openInternalEntities->internalEventPtr); - eventEndPP = &(openInternalEntities->internalEventEndPtr); - } - *eventPP = s; - - for (;;) { - const char *next = s; /* XmlContentTok doesn't always set the last arg */ - int tok = XmlContentTok(enc, s, end, &next); - *eventEndPP = next; - switch (tok) { - case XML_TOK_TRAILING_CR: - if (haveMore) { - *nextPtr = s; - return XML_ERROR_NONE; - } - *eventEndPP = end; - if (characterDataHandler) { - XML_Char c = 0xA; - characterDataHandler(handlerArg, &c, 1); - } - else if (defaultHandler) - reportDefault(parser, enc, s, end); - /* We are at the end of the final buffer, should we check for - XML_SUSPENDED, XML_FINISHED? - */ - if (startTagLevel == 0) - return XML_ERROR_NO_ELEMENTS; - if (tagLevel != startTagLevel) - return XML_ERROR_ASYNC_ENTITY; - *nextPtr = end; - return XML_ERROR_NONE; - case XML_TOK_NONE: - if (haveMore) { - *nextPtr = s; - return XML_ERROR_NONE; - } - if (startTagLevel > 0) { - if (tagLevel != startTagLevel) - return XML_ERROR_ASYNC_ENTITY; - *nextPtr = s; - return XML_ERROR_NONE; - } - return XML_ERROR_NO_ELEMENTS; - case XML_TOK_INVALID: - *eventPP = next; - return XML_ERROR_INVALID_TOKEN; - case XML_TOK_PARTIAL: - if (haveMore) { - *nextPtr = s; - return XML_ERROR_NONE; - } - return XML_ERROR_UNCLOSED_TOKEN; - case XML_TOK_PARTIAL_CHAR: - if (haveMore) { - *nextPtr = s; - return XML_ERROR_NONE; - } - return XML_ERROR_PARTIAL_CHAR; - case XML_TOK_ENTITY_REF: - { - const XML_Char *name; - ENTITY *entity; - XML_Char ch = (XML_Char) XmlPredefinedEntityName(enc, - s + enc->minBytesPerChar, - next - enc->minBytesPerChar); - if (ch) { - if (characterDataHandler) - characterDataHandler(handlerArg, &ch, 1); - else if (defaultHandler) - reportDefault(parser, enc, s, next); - break; - } - name = poolStoreString(&dtd->pool, enc, - s + enc->minBytesPerChar, - next - enc->minBytesPerChar); - if (!name) - return XML_ERROR_NO_MEMORY; - entity = (ENTITY *)lookup(parser, &dtd->generalEntities, name, 0); - poolDiscard(&dtd->pool); - /* First, determine if a check for an existing declaration is needed; - if yes, check that the entity exists, and that it is internal, - otherwise call the skipped entity or default handler. - */ - if (!dtd->hasParamEntityRefs || dtd->standalone) { - if (!entity) - return XML_ERROR_UNDEFINED_ENTITY; - else if (!entity->is_internal) - return XML_ERROR_ENTITY_DECLARED_IN_PE; - } - else if (!entity) { - if (skippedEntityHandler) - skippedEntityHandler(handlerArg, name, 0); - else if (defaultHandler) - reportDefault(parser, enc, s, next); - break; - } - if (entity->open) - return XML_ERROR_RECURSIVE_ENTITY_REF; - if (entity->notation) - return XML_ERROR_BINARY_ENTITY_REF; - if (entity->textPtr) { - enum XML_Error result; - if (!defaultExpandInternalEntities) { - if (skippedEntityHandler) - skippedEntityHandler(handlerArg, entity->name, 0); - else if (defaultHandler) - reportDefault(parser, enc, s, next); - break; - } - result = processInternalEntity(parser, entity, XML_FALSE); - if (result != XML_ERROR_NONE) - return result; - } - else if (externalEntityRefHandler) { - const XML_Char *context; - entity->open = XML_TRUE; - context = getContext(parser); - entity->open = XML_FALSE; - if (!context) - return XML_ERROR_NO_MEMORY; - if (!externalEntityRefHandler(externalEntityRefHandlerArg, - context, - entity->base, - entity->systemId, - entity->publicId)) - return XML_ERROR_EXTERNAL_ENTITY_HANDLING; - poolDiscard(&tempPool); - } - else if (defaultHandler) - reportDefault(parser, enc, s, next); - break; - } - case XML_TOK_START_TAG_NO_ATTS: - /* fall through */ - case XML_TOK_START_TAG_WITH_ATTS: - { - TAG *tag; - enum XML_Error result; - XML_Char *toPtr; - if (freeTagList) { - tag = freeTagList; - freeTagList = freeTagList->parent; - } - else { - tag = (TAG *)MALLOC(sizeof(TAG)); - if (!tag) - return XML_ERROR_NO_MEMORY; - tag->buf = (char *)MALLOC(INIT_TAG_BUF_SIZE); - if (!tag->buf) { - FREE(tag); - return XML_ERROR_NO_MEMORY; - } - tag->bufEnd = tag->buf + INIT_TAG_BUF_SIZE; - } - tag->bindings = NULL; - tag->parent = tagStack; - tagStack = tag; - tag->name.localPart = NULL; - tag->name.prefix = NULL; - tag->rawName = s + enc->minBytesPerChar; - tag->rawNameLength = XmlNameLength(enc, tag->rawName); - ++tagLevel; - { - const char *rawNameEnd = tag->rawName + tag->rawNameLength; - const char *fromPtr = tag->rawName; - toPtr = (XML_Char *)tag->buf; - for (;;) { - int bufSize; - int convLen; - const enum XML_Convert_Result convert_res = XmlConvert(enc, - &fromPtr, rawNameEnd, - (ICHAR **)&toPtr, (ICHAR *)tag->bufEnd - 1); - convLen = (int)(toPtr - (XML_Char *)tag->buf); - if ((convert_res == XML_CONVERT_COMPLETED) || (convert_res == XML_CONVERT_INPUT_INCOMPLETE)) { - tag->name.strLen = convLen; - break; - } - bufSize = (int)(tag->bufEnd - tag->buf) << 1; - { - char *temp = (char *)REALLOC(tag->buf, bufSize); - if (temp == NULL) - return XML_ERROR_NO_MEMORY; - tag->buf = temp; - tag->bufEnd = temp + bufSize; - toPtr = (XML_Char *)temp + convLen; - } - } - } - tag->name.str = (XML_Char *)tag->buf; - *toPtr = XML_T('\0'); - result = storeAtts(parser, enc, s, &(tag->name), &(tag->bindings)); - if (result) - return result; - if (startElementHandler) - startElementHandler(handlerArg, tag->name.str, - (const XML_Char **)atts); - else if (defaultHandler) - reportDefault(parser, enc, s, next); - poolClear(&tempPool); - break; - } - case XML_TOK_EMPTY_ELEMENT_NO_ATTS: - /* fall through */ - case XML_TOK_EMPTY_ELEMENT_WITH_ATTS: - { - const char *rawName = s + enc->minBytesPerChar; - enum XML_Error result; - BINDING *bindings = NULL; - XML_Bool noElmHandlers = XML_TRUE; - TAG_NAME name; - name.str = poolStoreString(&tempPool, enc, rawName, - rawName + XmlNameLength(enc, rawName)); - if (!name.str) - return XML_ERROR_NO_MEMORY; - poolFinish(&tempPool); - result = storeAtts(parser, enc, s, &name, &bindings); - if (result) - return result; - poolFinish(&tempPool); - if (startElementHandler) { - startElementHandler(handlerArg, name.str, (const XML_Char **)atts); - noElmHandlers = XML_FALSE; - } - if (endElementHandler) { - if (startElementHandler) - *eventPP = *eventEndPP; - endElementHandler(handlerArg, name.str); - noElmHandlers = XML_FALSE; - } - if (noElmHandlers && defaultHandler) - reportDefault(parser, enc, s, next); - poolClear(&tempPool); - while (bindings) { - BINDING *b = bindings; - if (endNamespaceDeclHandler) - endNamespaceDeclHandler(handlerArg, b->prefix->name); - bindings = bindings->nextTagBinding; - b->nextTagBinding = freeBindingList; - freeBindingList = b; - b->prefix->binding = b->prevPrefixBinding; - } - } - if (tagLevel == 0) - return epilogProcessor(parser, next, end, nextPtr); - break; - case XML_TOK_END_TAG: - if (tagLevel == startTagLevel) - return XML_ERROR_ASYNC_ENTITY; - else { - int len; - const char *rawName; - TAG *tag = tagStack; - tagStack = tag->parent; - tag->parent = freeTagList; - freeTagList = tag; - rawName = s + enc->minBytesPerChar*2; - len = XmlNameLength(enc, rawName); - if (len != tag->rawNameLength - || memcmp(tag->rawName, rawName, len) != 0) { - *eventPP = rawName; - return XML_ERROR_TAG_MISMATCH; - } - --tagLevel; - if (endElementHandler) { - const XML_Char *localPart; - const XML_Char *prefix; - XML_Char *uri; - localPart = tag->name.localPart; - if (ns && localPart) { - /* localPart and prefix may have been overwritten in - tag->name.str, since this points to the binding->uri - buffer which gets re-used; so we have to add them again - */ - uri = (XML_Char *)tag->name.str + tag->name.uriLen; - /* don't need to check for space - already done in storeAtts() */ - while (*localPart) *uri++ = *localPart++; - prefix = (XML_Char *)tag->name.prefix; - if (ns_triplets && prefix) { - *uri++ = namespaceSeparator; - while (*prefix) *uri++ = *prefix++; - } - *uri = XML_T('\0'); - } - endElementHandler(handlerArg, tag->name.str); - } - else if (defaultHandler) - reportDefault(parser, enc, s, next); - while (tag->bindings) { - BINDING *b = tag->bindings; - if (endNamespaceDeclHandler) - endNamespaceDeclHandler(handlerArg, b->prefix->name); - tag->bindings = tag->bindings->nextTagBinding; - b->nextTagBinding = freeBindingList; - freeBindingList = b; - b->prefix->binding = b->prevPrefixBinding; - } - if (tagLevel == 0) - return epilogProcessor(parser, next, end, nextPtr); - } - break; - case XML_TOK_CHAR_REF: - { - int n = XmlCharRefNumber(enc, s); - if (n < 0) - return XML_ERROR_BAD_CHAR_REF; - if (characterDataHandler) { - XML_Char buf[XML_ENCODE_MAX]; - characterDataHandler(handlerArg, buf, XmlEncode(n, (ICHAR *)buf)); - } - else if (defaultHandler) - reportDefault(parser, enc, s, next); - } - break; - case XML_TOK_XML_DECL: - return XML_ERROR_MISPLACED_XML_PI; - case XML_TOK_DATA_NEWLINE: - if (characterDataHandler) { - XML_Char c = 0xA; - characterDataHandler(handlerArg, &c, 1); - } - else if (defaultHandler) - reportDefault(parser, enc, s, next); - break; - case XML_TOK_CDATA_SECT_OPEN: - { - enum XML_Error result; - if (startCdataSectionHandler) - startCdataSectionHandler(handlerArg); -#if 0 - /* Suppose you doing a transformation on a document that involves - changing only the character data. You set up a defaultHandler - and a characterDataHandler. The defaultHandler simply copies - characters through. The characterDataHandler does the - transformation and writes the characters out escaping them as - necessary. This case will fail to work if we leave out the - following two lines (because & and < inside CDATA sections will - be incorrectly escaped). - - However, now we have a start/endCdataSectionHandler, so it seems - easier to let the user deal with this. - */ - else if (characterDataHandler) - characterDataHandler(handlerArg, dataBuf, 0); -#endif - else if (defaultHandler) - reportDefault(parser, enc, s, next); - result = doCdataSection(parser, enc, &next, end, nextPtr, haveMore); - if (result != XML_ERROR_NONE) - return result; - else if (!next) { - processor = cdataSectionProcessor; - return result; - } - } - break; - case XML_TOK_TRAILING_RSQB: - if (haveMore) { - *nextPtr = s; - return XML_ERROR_NONE; - } - if (characterDataHandler) { - if (MUST_CONVERT(enc, s)) { - ICHAR *dataPtr = (ICHAR *)dataBuf; - XmlConvert(enc, &s, end, &dataPtr, (ICHAR *)dataBufEnd); - characterDataHandler(handlerArg, dataBuf, - (int)(dataPtr - (ICHAR *)dataBuf)); - } - else - characterDataHandler(handlerArg, - (XML_Char *)s, - (int)((XML_Char *)end - (XML_Char *)s)); - } - else if (defaultHandler) - reportDefault(parser, enc, s, end); - /* We are at the end of the final buffer, should we check for - XML_SUSPENDED, XML_FINISHED? - */ - if (startTagLevel == 0) { - *eventPP = end; - return XML_ERROR_NO_ELEMENTS; - } - if (tagLevel != startTagLevel) { - *eventPP = end; - return XML_ERROR_ASYNC_ENTITY; - } - *nextPtr = end; - return XML_ERROR_NONE; - case XML_TOK_DATA_CHARS: - { - XML_CharacterDataHandler charDataHandler = characterDataHandler; - if (charDataHandler) { - if (MUST_CONVERT(enc, s)) { - for (;;) { - ICHAR *dataPtr = (ICHAR *)dataBuf; - const enum XML_Convert_Result convert_res = XmlConvert(enc, &s, next, &dataPtr, (ICHAR *)dataBufEnd); - *eventEndPP = s; - charDataHandler(handlerArg, dataBuf, - (int)(dataPtr - (ICHAR *)dataBuf)); - if ((convert_res == XML_CONVERT_COMPLETED) || (convert_res == XML_CONVERT_INPUT_INCOMPLETE)) - break; - *eventPP = s; - } - } - else - charDataHandler(handlerArg, - (XML_Char *)s, - (int)((XML_Char *)next - (XML_Char *)s)); - } - else if (defaultHandler) - reportDefault(parser, enc, s, next); - } - break; - case XML_TOK_PI: - if (!reportProcessingInstruction(parser, enc, s, next)) - return XML_ERROR_NO_MEMORY; - break; - case XML_TOK_COMMENT: - if (!reportComment(parser, enc, s, next)) - return XML_ERROR_NO_MEMORY; - break; - default: - if (defaultHandler) - reportDefault(parser, enc, s, next); - break; - } - *eventPP = s = next; - switch (ps_parsing) { - case XML_SUSPENDED: - *nextPtr = next; - return XML_ERROR_NONE; - case XML_FINISHED: - return XML_ERROR_ABORTED; - default: ; - } - } - /* not reached */ -} - -/* Precondition: all arguments must be non-NULL; - Purpose: - - normalize attributes - - check attributes for well-formedness - - generate namespace aware attribute names (URI, prefix) - - build list of attributes for startElementHandler - - default attributes - - process namespace declarations (check and report them) - - generate namespace aware element name (URI, prefix) -*/ -static enum XML_Error -storeAtts(XML_Parser parser, const ENCODING *enc, - const char *attStr, TAG_NAME *tagNamePtr, - BINDING **bindingsPtr) -{ - DTD * const dtd = _dtd; /* save one level of indirection */ - ELEMENT_TYPE *elementType; - int nDefaultAtts; - const XML_Char **appAtts; /* the attribute list for the application */ - int attIndex = 0; - int prefixLen; - int i; - int n; - XML_Char *uri; - int nPrefixes = 0; - BINDING *binding; - const XML_Char *localPart; - - /* lookup the element type name */ - elementType = (ELEMENT_TYPE *)lookup(parser, &dtd->elementTypes, tagNamePtr->str,0); - if (!elementType) { - const XML_Char *name = poolCopyString(&dtd->pool, tagNamePtr->str); - if (!name) - return XML_ERROR_NO_MEMORY; - elementType = (ELEMENT_TYPE *)lookup(parser, &dtd->elementTypes, name, - sizeof(ELEMENT_TYPE)); - if (!elementType) - return XML_ERROR_NO_MEMORY; - if (ns && !setElementTypePrefix(parser, elementType)) - return XML_ERROR_NO_MEMORY; - } - nDefaultAtts = elementType->nDefaultAtts; - - /* get the attributes from the tokenizer */ - n = XmlGetAttributes(enc, attStr, attsSize, atts); - if (n + nDefaultAtts > attsSize) { - int oldAttsSize = attsSize; - ATTRIBUTE *temp; -#ifdef XML_ATTR_INFO - XML_AttrInfo *temp2; -#endif - attsSize = n + nDefaultAtts + INIT_ATTS_SIZE; - temp = (ATTRIBUTE *)REALLOC((void *)atts, attsSize * sizeof(ATTRIBUTE)); - if (temp == NULL) - return XML_ERROR_NO_MEMORY; - atts = temp; -#ifdef XML_ATTR_INFO - temp2 = (XML_AttrInfo *)REALLOC((void *)attInfo, attsSize * sizeof(XML_AttrInfo)); - if (temp2 == NULL) - return XML_ERROR_NO_MEMORY; - attInfo = temp2; -#endif - if (n > oldAttsSize) - XmlGetAttributes(enc, attStr, n, atts); - } - - appAtts = (const XML_Char **)atts; - for (i = 0; i < n; i++) { - ATTRIBUTE *currAtt = &atts[i]; -#ifdef XML_ATTR_INFO - XML_AttrInfo *currAttInfo = &attInfo[i]; -#endif - /* add the name and value to the attribute list */ - ATTRIBUTE_ID *attId = getAttributeId(parser, enc, currAtt->name, - currAtt->name - + XmlNameLength(enc, currAtt->name)); - if (!attId) - return XML_ERROR_NO_MEMORY; -#ifdef XML_ATTR_INFO - currAttInfo->nameStart = parseEndByteIndex - (parseEndPtr - currAtt->name); - currAttInfo->nameEnd = currAttInfo->nameStart + - XmlNameLength(enc, currAtt->name); - currAttInfo->valueStart = parseEndByteIndex - - (parseEndPtr - currAtt->valuePtr); - currAttInfo->valueEnd = parseEndByteIndex - (parseEndPtr - currAtt->valueEnd); -#endif - /* Detect duplicate attributes by their QNames. This does not work when - namespace processing is turned on and different prefixes for the same - namespace are used. For this case we have a check further down. - */ - if ((attId->name)[-1]) { - if (enc == encoding) - eventPtr = atts[i].name; - return XML_ERROR_DUPLICATE_ATTRIBUTE; - } - (attId->name)[-1] = 1; - appAtts[attIndex++] = attId->name; - if (!atts[i].normalized) { - enum XML_Error result; - XML_Bool isCdata = XML_TRUE; - - /* figure out whether declared as other than CDATA */ - if (attId->maybeTokenized) { - int j; - for (j = 0; j < nDefaultAtts; j++) { - if (attId == elementType->defaultAtts[j].id) { - isCdata = elementType->defaultAtts[j].isCdata; - break; - } - } - } - - /* normalize the attribute value */ - result = storeAttributeValue(parser, enc, isCdata, - atts[i].valuePtr, atts[i].valueEnd, - &tempPool); - if (result) - return result; - appAtts[attIndex] = poolStart(&tempPool); - poolFinish(&tempPool); - } - else { - /* the value did not need normalizing */ - appAtts[attIndex] = poolStoreString(&tempPool, enc, atts[i].valuePtr, - atts[i].valueEnd); - if (appAtts[attIndex] == 0) - return XML_ERROR_NO_MEMORY; - poolFinish(&tempPool); - } - /* handle prefixed attribute names */ - if (attId->prefix) { - if (attId->xmlns) { - /* deal with namespace declarations here */ - enum XML_Error result = addBinding(parser, attId->prefix, attId, - appAtts[attIndex], bindingsPtr); - if (result) - return result; - --attIndex; - } - else { - /* deal with other prefixed names later */ - attIndex++; - nPrefixes++; - (attId->name)[-1] = 2; - } - } - else - attIndex++; - } - - /* set-up for XML_GetSpecifiedAttributeCount and XML_GetIdAttributeIndex */ - nSpecifiedAtts = attIndex; - if (elementType->idAtt && (elementType->idAtt->name)[-1]) { - for (i = 0; i < attIndex; i += 2) - if (appAtts[i] == elementType->idAtt->name) { - idAttIndex = i; - break; - } - } - else - idAttIndex = -1; - - /* do attribute defaulting */ - for (i = 0; i < nDefaultAtts; i++) { - const DEFAULT_ATTRIBUTE *da = elementType->defaultAtts + i; - if (!(da->id->name)[-1] && da->value) { - if (da->id->prefix) { - if (da->id->xmlns) { - enum XML_Error result = addBinding(parser, da->id->prefix, da->id, - da->value, bindingsPtr); - if (result) - return result; - } - else { - (da->id->name)[-1] = 2; - nPrefixes++; - appAtts[attIndex++] = da->id->name; - appAtts[attIndex++] = da->value; - } - } - else { - (da->id->name)[-1] = 1; - appAtts[attIndex++] = da->id->name; - appAtts[attIndex++] = da->value; - } - } - } - appAtts[attIndex] = 0; - - /* expand prefixed attribute names, check for duplicates, - and clear flags that say whether attributes were specified */ - i = 0; - if (nPrefixes) { - int j; /* hash table index */ - unsigned long version = nsAttsVersion; - int nsAttsSize = (int)1 << nsAttsPower; - /* size of hash table must be at least 2 * (# of prefixed attributes) */ - if ((nPrefixes << 1) >> nsAttsPower) { /* true for nsAttsPower = 0 */ - NS_ATT *temp; - /* hash table size must also be a power of 2 and >= 8 */ - while (nPrefixes >> nsAttsPower++); - if (nsAttsPower < 3) - nsAttsPower = 3; - nsAttsSize = (int)1 << nsAttsPower; - temp = (NS_ATT *)REALLOC(nsAtts, nsAttsSize * sizeof(NS_ATT)); - if (!temp) - return XML_ERROR_NO_MEMORY; - nsAtts = temp; - version = 0; /* force re-initialization of nsAtts hash table */ - } - /* using a version flag saves us from initializing nsAtts every time */ - if (!version) { /* initialize version flags when version wraps around */ - version = INIT_ATTS_VERSION; - for (j = nsAttsSize; j != 0; ) - nsAtts[--j].version = version; - } - nsAttsVersion = --version; - - /* expand prefixed names and check for duplicates */ - for (; i < attIndex; i += 2) { - const XML_Char *s = appAtts[i]; - if (s[-1] == 2) { /* prefixed */ - ATTRIBUTE_ID *id; - const BINDING *b; - unsigned long uriHash = hash_secret_salt; - ((XML_Char *)s)[-1] = 0; /* clear flag */ - id = (ATTRIBUTE_ID *)lookup(parser, &dtd->attributeIds, s, 0); - if (!id || !id->prefix) - return XML_ERROR_NO_MEMORY; - b = id->prefix->binding; - if (!b) - return XML_ERROR_UNBOUND_PREFIX; - - /* as we expand the name we also calculate its hash value */ - for (j = 0; j < b->uriLen; j++) { - const XML_Char c = b->uri[j]; - if (!poolAppendChar(&tempPool, c)) - return XML_ERROR_NO_MEMORY; - uriHash = CHAR_HASH(uriHash, c); - } - while (*s++ != XML_T(ASCII_COLON)) - ; - do { /* copies null terminator */ - const XML_Char c = *s; - if (!poolAppendChar(&tempPool, *s)) - return XML_ERROR_NO_MEMORY; - uriHash = CHAR_HASH(uriHash, c); - } while (*s++); - - { /* Check hash table for duplicate of expanded name (uriName). - Derived from code in lookup(parser, HASH_TABLE *table, ...). - */ - unsigned char step = 0; - unsigned long mask = nsAttsSize - 1; - j = uriHash & mask; /* index into hash table */ - while (nsAtts[j].version == version) { - /* for speed we compare stored hash values first */ - if (uriHash == nsAtts[j].hash) { - const XML_Char *s1 = poolStart(&tempPool); - const XML_Char *s2 = nsAtts[j].uriName; - /* s1 is null terminated, but not s2 */ - for (; *s1 == *s2 && *s1 != 0; s1++, s2++); - if (*s1 == 0) - return XML_ERROR_DUPLICATE_ATTRIBUTE; - } - if (!step) - step = PROBE_STEP(uriHash, mask, nsAttsPower); - j < step ? (j += nsAttsSize - step) : (j -= step); - } - } - - if (ns_triplets) { /* append namespace separator and prefix */ - tempPool.ptr[-1] = namespaceSeparator; - s = b->prefix->name; - do { - if (!poolAppendChar(&tempPool, *s)) - return XML_ERROR_NO_MEMORY; - } while (*s++); - } - - /* store expanded name in attribute list */ - s = poolStart(&tempPool); - poolFinish(&tempPool); - appAtts[i] = s; - - /* fill empty slot with new version, uriName and hash value */ - nsAtts[j].version = version; - nsAtts[j].hash = uriHash; - nsAtts[j].uriName = s; - - if (!--nPrefixes) { - i += 2; - break; - } - } - else /* not prefixed */ - ((XML_Char *)s)[-1] = 0; /* clear flag */ - } - } - /* clear flags for the remaining attributes */ - for (; i < attIndex; i += 2) - ((XML_Char *)(appAtts[i]))[-1] = 0; - for (binding = *bindingsPtr; binding; binding = binding->nextTagBinding) - binding->attId->name[-1] = 0; - - if (!ns) - return XML_ERROR_NONE; - - /* expand the element type name */ - if (elementType->prefix) { - binding = elementType->prefix->binding; - if (!binding) - return XML_ERROR_UNBOUND_PREFIX; - localPart = tagNamePtr->str; - while (*localPart++ != XML_T(ASCII_COLON)) - ; - } - else if (dtd->defaultPrefix.binding) { - binding = dtd->defaultPrefix.binding; - localPart = tagNamePtr->str; - } - else - return XML_ERROR_NONE; - prefixLen = 0; - if (ns_triplets && binding->prefix->name) { - for (; binding->prefix->name[prefixLen++];) - ; /* prefixLen includes null terminator */ - } - tagNamePtr->localPart = localPart; - tagNamePtr->uriLen = binding->uriLen; - tagNamePtr->prefix = binding->prefix->name; - tagNamePtr->prefixLen = prefixLen; - for (i = 0; localPart[i++];) - ; /* i includes null terminator */ - n = i + binding->uriLen + prefixLen; - if (n > binding->uriAlloc) { - TAG *p; - uri = (XML_Char *)MALLOC((n + EXPAND_SPARE) * sizeof(XML_Char)); - if (!uri) - return XML_ERROR_NO_MEMORY; - binding->uriAlloc = n + EXPAND_SPARE; - memcpy(uri, binding->uri, binding->uriLen * sizeof(XML_Char)); - for (p = tagStack; p; p = p->parent) - if (p->name.str == binding->uri) - p->name.str = uri; - FREE(binding->uri); - binding->uri = uri; - } - /* if namespaceSeparator != '\0' then uri includes it already */ - uri = binding->uri + binding->uriLen; - memcpy(uri, localPart, i * sizeof(XML_Char)); - /* we always have a namespace separator between localPart and prefix */ - if (prefixLen) { - uri += i - 1; - *uri = namespaceSeparator; /* replace null terminator */ - memcpy(uri + 1, binding->prefix->name, prefixLen * sizeof(XML_Char)); - } - tagNamePtr->str = binding->uri; - return XML_ERROR_NONE; -} - -/* addBinding() overwrites the value of prefix->binding without checking. - Therefore one must keep track of the old value outside of addBinding(). -*/ -static enum XML_Error -addBinding(XML_Parser parser, PREFIX *prefix, const ATTRIBUTE_ID *attId, - const XML_Char *uri, BINDING **bindingsPtr) -{ - static const XML_Char xmlNamespace[] = { - ASCII_h, ASCII_t, ASCII_t, ASCII_p, ASCII_COLON, ASCII_SLASH, ASCII_SLASH, - ASCII_w, ASCII_w, ASCII_w, ASCII_PERIOD, ASCII_w, ASCII_3, ASCII_PERIOD, - ASCII_o, ASCII_r, ASCII_g, ASCII_SLASH, ASCII_X, ASCII_M, ASCII_L, - ASCII_SLASH, ASCII_1, ASCII_9, ASCII_9, ASCII_8, ASCII_SLASH, - ASCII_n, ASCII_a, ASCII_m, ASCII_e, ASCII_s, ASCII_p, ASCII_a, ASCII_c, - ASCII_e, '\0' - }; - static const int xmlLen = - (int)sizeof(xmlNamespace)/sizeof(XML_Char) - 1; - static const XML_Char xmlnsNamespace[] = { - ASCII_h, ASCII_t, ASCII_t, ASCII_p, ASCII_COLON, ASCII_SLASH, ASCII_SLASH, - ASCII_w, ASCII_w, ASCII_w, ASCII_PERIOD, ASCII_w, ASCII_3, ASCII_PERIOD, - ASCII_o, ASCII_r, ASCII_g, ASCII_SLASH, ASCII_2, ASCII_0, ASCII_0, - ASCII_0, ASCII_SLASH, ASCII_x, ASCII_m, ASCII_l, ASCII_n, ASCII_s, - ASCII_SLASH, '\0' - }; - static const int xmlnsLen = - (int)sizeof(xmlnsNamespace)/sizeof(XML_Char) - 1; - - XML_Bool mustBeXML = XML_FALSE; - XML_Bool isXML = XML_TRUE; - XML_Bool isXMLNS = XML_TRUE; - - BINDING *b; - int len; - - /* empty URI is only valid for default namespace per XML NS 1.0 (not 1.1) */ - if (*uri == XML_T('\0') && prefix->name) - return XML_ERROR_UNDECLARING_PREFIX; - - if (prefix->name - && prefix->name[0] == XML_T(ASCII_x) - && prefix->name[1] == XML_T(ASCII_m) - && prefix->name[2] == XML_T(ASCII_l)) { - - /* Not allowed to bind xmlns */ - if (prefix->name[3] == XML_T(ASCII_n) - && prefix->name[4] == XML_T(ASCII_s) - && prefix->name[5] == XML_T('\0')) - return XML_ERROR_RESERVED_PREFIX_XMLNS; - - if (prefix->name[3] == XML_T('\0')) - mustBeXML = XML_TRUE; - } - - for (len = 0; uri[len]; len++) { - if (isXML && (len > xmlLen || uri[len] != xmlNamespace[len])) - isXML = XML_FALSE; - - if (!mustBeXML && isXMLNS - && (len > xmlnsLen || uri[len] != xmlnsNamespace[len])) - isXMLNS = XML_FALSE; - } - isXML = isXML && len == xmlLen; - isXMLNS = isXMLNS && len == xmlnsLen; - - if (mustBeXML != isXML) - return mustBeXML ? XML_ERROR_RESERVED_PREFIX_XML - : XML_ERROR_RESERVED_NAMESPACE_URI; - - if (isXMLNS) - return XML_ERROR_RESERVED_NAMESPACE_URI; - - if (namespaceSeparator) - len++; - if (freeBindingList) { - b = freeBindingList; - if (len > b->uriAlloc) { - XML_Char *temp = (XML_Char *)REALLOC(b->uri, - sizeof(XML_Char) * (len + EXPAND_SPARE)); - if (temp == NULL) - return XML_ERROR_NO_MEMORY; - b->uri = temp; - b->uriAlloc = len + EXPAND_SPARE; - } - freeBindingList = b->nextTagBinding; - } - else { - b = (BINDING *)MALLOC(sizeof(BINDING)); - if (!b) - return XML_ERROR_NO_MEMORY; - b->uri = (XML_Char *)MALLOC(sizeof(XML_Char) * (len + EXPAND_SPARE)); - if (!b->uri) { - FREE(b); - return XML_ERROR_NO_MEMORY; - } - b->uriAlloc = len + EXPAND_SPARE; - } - b->uriLen = len; - memcpy(b->uri, uri, len * sizeof(XML_Char)); - if (namespaceSeparator) - b->uri[len - 1] = namespaceSeparator; - b->prefix = prefix; - b->attId = attId; - b->prevPrefixBinding = prefix->binding; - /* NULL binding when default namespace undeclared */ - if (*uri == XML_T('\0') && prefix == &_dtd->defaultPrefix) - prefix->binding = NULL; - else - prefix->binding = b; - b->nextTagBinding = *bindingsPtr; - *bindingsPtr = b; - /* if attId == NULL then we are not starting a namespace scope */ - if (attId && startNamespaceDeclHandler) - startNamespaceDeclHandler(handlerArg, prefix->name, - prefix->binding ? uri : 0); - return XML_ERROR_NONE; -} - -/* The idea here is to avoid using stack for each CDATA section when - the whole file is parsed with one call. -*/ -static enum XML_Error PTRCALL -cdataSectionProcessor(XML_Parser parser, - const char *start, - const char *end, - const char **endPtr) -{ - enum XML_Error result = doCdataSection(parser, encoding, &start, end, - endPtr, (XML_Bool)!ps_finalBuffer); - if (result != XML_ERROR_NONE) - return result; - if (start) { - if (parentParser) { /* we are parsing an external entity */ - processor = externalEntityContentProcessor; - return externalEntityContentProcessor(parser, start, end, endPtr); - } - else { - processor = contentProcessor; - return contentProcessor(parser, start, end, endPtr); - } - } - return result; -} - -/* startPtr gets set to non-null if the section is closed, and to null if - the section is not yet closed. -*/ -static enum XML_Error -doCdataSection(XML_Parser parser, - const ENCODING *enc, - const char **startPtr, - const char *end, - const char **nextPtr, - XML_Bool haveMore) -{ - const char *s = *startPtr; - const char **eventPP; - const char **eventEndPP; - if (enc == encoding) { - eventPP = &eventPtr; - *eventPP = s; - eventEndPP = &eventEndPtr; - } - else { - eventPP = &(openInternalEntities->internalEventPtr); - eventEndPP = &(openInternalEntities->internalEventEndPtr); - } - *eventPP = s; - *startPtr = NULL; - - for (;;) { - const char *next; - int tok = XmlCdataSectionTok(enc, s, end, &next); - *eventEndPP = next; - switch (tok) { - case XML_TOK_CDATA_SECT_CLOSE: - if (endCdataSectionHandler) - endCdataSectionHandler(handlerArg); -#if 0 - /* see comment under XML_TOK_CDATA_SECT_OPEN */ - else if (characterDataHandler) - characterDataHandler(handlerArg, dataBuf, 0); -#endif - else if (defaultHandler) - reportDefault(parser, enc, s, next); - *startPtr = next; - *nextPtr = next; - if (ps_parsing == XML_FINISHED) - return XML_ERROR_ABORTED; - else - return XML_ERROR_NONE; - case XML_TOK_DATA_NEWLINE: - if (characterDataHandler) { - XML_Char c = 0xA; - characterDataHandler(handlerArg, &c, 1); - } - else if (defaultHandler) - reportDefault(parser, enc, s, next); - break; - case XML_TOK_DATA_CHARS: - { - XML_CharacterDataHandler charDataHandler = characterDataHandler; - if (charDataHandler) { - if (MUST_CONVERT(enc, s)) { - for (;;) { - ICHAR *dataPtr = (ICHAR *)dataBuf; - const enum XML_Convert_Result convert_res = XmlConvert(enc, &s, next, &dataPtr, (ICHAR *)dataBufEnd); - *eventEndPP = next; - charDataHandler(handlerArg, dataBuf, - (int)(dataPtr - (ICHAR *)dataBuf)); - if ((convert_res == XML_CONVERT_COMPLETED) || (convert_res == XML_CONVERT_INPUT_INCOMPLETE)) - break; - *eventPP = s; - } - } - else - charDataHandler(handlerArg, - (XML_Char *)s, - (int)((XML_Char *)next - (XML_Char *)s)); - } - else if (defaultHandler) - reportDefault(parser, enc, s, next); - } - break; - case XML_TOK_INVALID: - *eventPP = next; - return XML_ERROR_INVALID_TOKEN; - case XML_TOK_PARTIAL_CHAR: - if (haveMore) { - *nextPtr = s; - return XML_ERROR_NONE; - } - return XML_ERROR_PARTIAL_CHAR; - case XML_TOK_PARTIAL: - case XML_TOK_NONE: - if (haveMore) { - *nextPtr = s; - return XML_ERROR_NONE; - } - return XML_ERROR_UNCLOSED_CDATA_SECTION; - default: - *eventPP = next; - return XML_ERROR_UNEXPECTED_STATE; - } - - *eventPP = s = next; - switch (ps_parsing) { - case XML_SUSPENDED: - *nextPtr = next; - return XML_ERROR_NONE; - case XML_FINISHED: - return XML_ERROR_ABORTED; - default: ; - } - } - /* not reached */ -} - -#ifdef XML_DTD - -/* The idea here is to avoid using stack for each IGNORE section when - the whole file is parsed with one call. -*/ -static enum XML_Error PTRCALL -ignoreSectionProcessor(XML_Parser parser, - const char *start, - const char *end, - const char **endPtr) -{ - enum XML_Error result = doIgnoreSection(parser, encoding, &start, end, - endPtr, (XML_Bool)!ps_finalBuffer); - if (result != XML_ERROR_NONE) - return result; - if (start) { - processor = prologProcessor; - return prologProcessor(parser, start, end, endPtr); - } - return result; -} - -/* startPtr gets set to non-null is the section is closed, and to null - if the section is not yet closed. -*/ -static enum XML_Error -doIgnoreSection(XML_Parser parser, - const ENCODING *enc, - const char **startPtr, - const char *end, - const char **nextPtr, - XML_Bool haveMore) -{ - const char *next; - int tok; - const char *s = *startPtr; - const char **eventPP; - const char **eventEndPP; - if (enc == encoding) { - eventPP = &eventPtr; - *eventPP = s; - eventEndPP = &eventEndPtr; - } - else { - eventPP = &(openInternalEntities->internalEventPtr); - eventEndPP = &(openInternalEntities->internalEventEndPtr); - } - *eventPP = s; - *startPtr = NULL; - tok = XmlIgnoreSectionTok(enc, s, end, &next); - *eventEndPP = next; - switch (tok) { - case XML_TOK_IGNORE_SECT: - if (defaultHandler) - reportDefault(parser, enc, s, next); - *startPtr = next; - *nextPtr = next; - if (ps_parsing == XML_FINISHED) - return XML_ERROR_ABORTED; - else - return XML_ERROR_NONE; - case XML_TOK_INVALID: - *eventPP = next; - return XML_ERROR_INVALID_TOKEN; - case XML_TOK_PARTIAL_CHAR: - if (haveMore) { - *nextPtr = s; - return XML_ERROR_NONE; - } - return XML_ERROR_PARTIAL_CHAR; - case XML_TOK_PARTIAL: - case XML_TOK_NONE: - if (haveMore) { - *nextPtr = s; - return XML_ERROR_NONE; - } - return XML_ERROR_SYNTAX; /* XML_ERROR_UNCLOSED_IGNORE_SECTION */ - default: - *eventPP = next; - return XML_ERROR_UNEXPECTED_STATE; - } - /* not reached */ -} - -#endif /* XML_DTD */ - -static enum XML_Error -initializeEncoding(XML_Parser parser) -{ - const char *s; -#ifdef XML_UNICODE - char encodingBuf[128]; - if (!protocolEncodingName) - s = NULL; - else { - int i; - for (i = 0; protocolEncodingName[i]; i++) { - if (i == sizeof(encodingBuf) - 1 - || (protocolEncodingName[i] & ~0x7f) != 0) { - encodingBuf[0] = '\0'; - break; - } - encodingBuf[i] = (char)protocolEncodingName[i]; - } - encodingBuf[i] = '\0'; - s = encodingBuf; - } -#else - s = protocolEncodingName; -#endif - if ((ns ? XmlInitEncodingNS : XmlInitEncoding)(&initEncoding, &encoding, s)) - return XML_ERROR_NONE; - return handleUnknownEncoding(parser, protocolEncodingName); -} - -static enum XML_Error -processXmlDecl(XML_Parser parser, int isGeneralTextEntity, - const char *s, const char *next) -{ - const char *encodingName = NULL; - const XML_Char *storedEncName = NULL; - const ENCODING *newEncoding = NULL; - const char *version = NULL; - const char *versionend; - const XML_Char *storedversion = NULL; - int standalone = -1; - if (!(ns - ? XmlParseXmlDeclNS - : XmlParseXmlDecl)(isGeneralTextEntity, - encoding, - s, - next, - &eventPtr, - &version, - &versionend, - &encodingName, - &newEncoding, - &standalone)) { - if (isGeneralTextEntity) - return XML_ERROR_TEXT_DECL; - else - return XML_ERROR_XML_DECL; - } - if (!isGeneralTextEntity && standalone == 1) { - _dtd->standalone = XML_TRUE; -#ifdef XML_DTD - if (paramEntityParsing == XML_PARAM_ENTITY_PARSING_UNLESS_STANDALONE) - paramEntityParsing = XML_PARAM_ENTITY_PARSING_NEVER; -#endif /* XML_DTD */ - } - if (xmlDeclHandler) { - if (encodingName != NULL) { - storedEncName = poolStoreString(&temp2Pool, - encoding, - encodingName, - encodingName - + XmlNameLength(encoding, encodingName)); - if (!storedEncName) - return XML_ERROR_NO_MEMORY; - poolFinish(&temp2Pool); - } - if (version) { - storedversion = poolStoreString(&temp2Pool, - encoding, - version, - versionend - encoding->minBytesPerChar); - if (!storedversion) - return XML_ERROR_NO_MEMORY; - } - xmlDeclHandler(handlerArg, storedversion, storedEncName, standalone); - } - else if (defaultHandler) - reportDefault(parser, encoding, s, next); - if (protocolEncodingName == NULL) { - if (newEncoding) { - if (newEncoding->minBytesPerChar != encoding->minBytesPerChar) { - eventPtr = encodingName; - return XML_ERROR_INCORRECT_ENCODING; - } - encoding = newEncoding; - } - else if (encodingName) { - enum XML_Error result; - if (!storedEncName) { - storedEncName = poolStoreString( - &temp2Pool, encoding, encodingName, - encodingName + XmlNameLength(encoding, encodingName)); - if (!storedEncName) - return XML_ERROR_NO_MEMORY; - } - result = handleUnknownEncoding(parser, storedEncName); - poolClear(&temp2Pool); - if (result == XML_ERROR_UNKNOWN_ENCODING) - eventPtr = encodingName; - return result; - } - } - - if (storedEncName || storedversion) - poolClear(&temp2Pool); - - return XML_ERROR_NONE; -} - -static enum XML_Error -handleUnknownEncoding(XML_Parser parser, const XML_Char *encodingName) -{ - if (unknownEncodingHandler) { - XML_Encoding info; - int i; - for (i = 0; i < 256; i++) - info.map[i] = -1; - info.convert = NULL; - info.data = NULL; - info.release = NULL; - if (unknownEncodingHandler(unknownEncodingHandlerData, encodingName, - &info)) { - ENCODING *enc; - unknownEncodingMem = MALLOC(XmlSizeOfUnknownEncoding()); - if (!unknownEncodingMem) { - if (info.release) - info.release(info.data); - return XML_ERROR_NO_MEMORY; - } - enc = (ns - ? XmlInitUnknownEncodingNS - : XmlInitUnknownEncoding)(unknownEncodingMem, - info.map, - info.convert, - info.data); - if (enc) { - unknownEncodingData = info.data; - unknownEncodingRelease = info.release; - encoding = enc; - return XML_ERROR_NONE; - } - } - if (info.release != NULL) - info.release(info.data); - } - return XML_ERROR_UNKNOWN_ENCODING; -} - -static enum XML_Error PTRCALL -prologInitProcessor(XML_Parser parser, - const char *s, - const char *end, - const char **nextPtr) -{ - enum XML_Error result = initializeEncoding(parser); - if (result != XML_ERROR_NONE) - return result; - processor = prologProcessor; - return prologProcessor(parser, s, end, nextPtr); -} - -#ifdef XML_DTD - -static enum XML_Error PTRCALL -externalParEntInitProcessor(XML_Parser parser, - const char *s, - const char *end, - const char **nextPtr) -{ - enum XML_Error result = initializeEncoding(parser); - if (result != XML_ERROR_NONE) - return result; - - /* we know now that XML_Parse(Buffer) has been called, - so we consider the external parameter entity read */ - _dtd->paramEntityRead = XML_TRUE; - - if (prologState.inEntityValue) { - processor = entityValueInitProcessor; - return entityValueInitProcessor(parser, s, end, nextPtr); - } - else { - processor = externalParEntProcessor; - return externalParEntProcessor(parser, s, end, nextPtr); - } -} - -static enum XML_Error PTRCALL -entityValueInitProcessor(XML_Parser parser, - const char *s, - const char *end, - const char **nextPtr) -{ - int tok; - const char *start = s; - const char *next = start; - eventPtr = start; - - for (;;) { - tok = XmlPrologTok(encoding, start, end, &next); - eventEndPtr = next; - if (tok <= 0) { - if (!ps_finalBuffer && tok != XML_TOK_INVALID) { - *nextPtr = s; - return XML_ERROR_NONE; - } - switch (tok) { - case XML_TOK_INVALID: - return XML_ERROR_INVALID_TOKEN; - case XML_TOK_PARTIAL: - return XML_ERROR_UNCLOSED_TOKEN; - case XML_TOK_PARTIAL_CHAR: - return XML_ERROR_PARTIAL_CHAR; - case XML_TOK_NONE: /* start == end */ - default: - break; - } - /* found end of entity value - can store it now */ - return storeEntityValue(parser, encoding, s, end); - } - else if (tok == XML_TOK_XML_DECL) { - enum XML_Error result; - result = processXmlDecl(parser, 0, start, next); - if (result != XML_ERROR_NONE) - return result; - switch (ps_parsing) { - case XML_SUSPENDED: - *nextPtr = next; - return XML_ERROR_NONE; - case XML_FINISHED: - return XML_ERROR_ABORTED; - default: - *nextPtr = next; - } - /* stop scanning for text declaration - we found one */ - processor = entityValueProcessor; - return entityValueProcessor(parser, next, end, nextPtr); - } - /* If we are at the end of the buffer, this would cause XmlPrologTok to - return XML_TOK_NONE on the next call, which would then cause the - function to exit with *nextPtr set to s - that is what we want for other - tokens, but not for the BOM - we would rather like to skip it; - then, when this routine is entered the next time, XmlPrologTok will - return XML_TOK_INVALID, since the BOM is still in the buffer - */ - else if (tok == XML_TOK_BOM && next == end && !ps_finalBuffer) { - *nextPtr = next; - return XML_ERROR_NONE; - } - start = next; - eventPtr = start; - } -} - -static enum XML_Error PTRCALL -externalParEntProcessor(XML_Parser parser, - const char *s, - const char *end, - const char **nextPtr) -{ - const char *next = s; - int tok; - - tok = XmlPrologTok(encoding, s, end, &next); - if (tok <= 0) { - if (!ps_finalBuffer && tok != XML_TOK_INVALID) { - *nextPtr = s; - return XML_ERROR_NONE; - } - switch (tok) { - case XML_TOK_INVALID: - return XML_ERROR_INVALID_TOKEN; - case XML_TOK_PARTIAL: - return XML_ERROR_UNCLOSED_TOKEN; - case XML_TOK_PARTIAL_CHAR: - return XML_ERROR_PARTIAL_CHAR; - case XML_TOK_NONE: /* start == end */ - default: - break; - } - } - /* This would cause the next stage, i.e. doProlog to be passed XML_TOK_BOM. - However, when parsing an external subset, doProlog will not accept a BOM - as valid, and report a syntax error, so we have to skip the BOM - */ - else if (tok == XML_TOK_BOM) { - s = next; - tok = XmlPrologTok(encoding, s, end, &next); - } - - processor = prologProcessor; - return doProlog(parser, encoding, s, end, tok, next, - nextPtr, (XML_Bool)!ps_finalBuffer); -} - -static enum XML_Error PTRCALL -entityValueProcessor(XML_Parser parser, - const char *s, - const char *end, - const char **nextPtr) -{ - const char *start = s; - const char *next = s; - const ENCODING *enc = encoding; - int tok; - - for (;;) { - tok = XmlPrologTok(enc, start, end, &next); - if (tok <= 0) { - if (!ps_finalBuffer && tok != XML_TOK_INVALID) { - *nextPtr = s; - return XML_ERROR_NONE; - } - switch (tok) { - case XML_TOK_INVALID: - return XML_ERROR_INVALID_TOKEN; - case XML_TOK_PARTIAL: - return XML_ERROR_UNCLOSED_TOKEN; - case XML_TOK_PARTIAL_CHAR: - return XML_ERROR_PARTIAL_CHAR; - case XML_TOK_NONE: /* start == end */ - default: - break; - } - /* found end of entity value - can store it now */ - return storeEntityValue(parser, enc, s, end); - } - start = next; - } -} - -#endif /* XML_DTD */ - -static enum XML_Error PTRCALL -prologProcessor(XML_Parser parser, - const char *s, - const char *end, - const char **nextPtr) -{ - const char *next = s; - int tok = XmlPrologTok(encoding, s, end, &next); - return doProlog(parser, encoding, s, end, tok, next, - nextPtr, (XML_Bool)!ps_finalBuffer); -} - -static enum XML_Error -doProlog(XML_Parser parser, - const ENCODING *enc, - const char *s, - const char *end, - int tok, - const char *next, - const char **nextPtr, - XML_Bool haveMore) -{ -#ifdef XML_DTD - static const XML_Char externalSubsetName[] = { ASCII_HASH , '\0' }; -#endif /* XML_DTD */ - static const XML_Char atypeCDATA[] = - { ASCII_C, ASCII_D, ASCII_A, ASCII_T, ASCII_A, '\0' }; - static const XML_Char atypeID[] = { ASCII_I, ASCII_D, '\0' }; - static const XML_Char atypeIDREF[] = - { ASCII_I, ASCII_D, ASCII_R, ASCII_E, ASCII_F, '\0' }; - static const XML_Char atypeIDREFS[] = - { ASCII_I, ASCII_D, ASCII_R, ASCII_E, ASCII_F, ASCII_S, '\0' }; - static const XML_Char atypeENTITY[] = - { ASCII_E, ASCII_N, ASCII_T, ASCII_I, ASCII_T, ASCII_Y, '\0' }; - static const XML_Char atypeENTITIES[] = { ASCII_E, ASCII_N, - ASCII_T, ASCII_I, ASCII_T, ASCII_I, ASCII_E, ASCII_S, '\0' }; - static const XML_Char atypeNMTOKEN[] = { - ASCII_N, ASCII_M, ASCII_T, ASCII_O, ASCII_K, ASCII_E, ASCII_N, '\0' }; - static const XML_Char atypeNMTOKENS[] = { ASCII_N, ASCII_M, ASCII_T, - ASCII_O, ASCII_K, ASCII_E, ASCII_N, ASCII_S, '\0' }; - static const XML_Char notationPrefix[] = { ASCII_N, ASCII_O, ASCII_T, - ASCII_A, ASCII_T, ASCII_I, ASCII_O, ASCII_N, ASCII_LPAREN, '\0' }; - static const XML_Char enumValueSep[] = { ASCII_PIPE, '\0' }; - static const XML_Char enumValueStart[] = { ASCII_LPAREN, '\0' }; - - /* save one level of indirection */ - DTD * const dtd = _dtd; - - const char **eventPP; - const char **eventEndPP; - enum XML_Content_Quant quant; - - if (enc == encoding) { - eventPP = &eventPtr; - eventEndPP = &eventEndPtr; - } - else { - eventPP = &(openInternalEntities->internalEventPtr); - eventEndPP = &(openInternalEntities->internalEventEndPtr); - } - - for (;;) { - int role; - XML_Bool handleDefault = XML_TRUE; - *eventPP = s; - *eventEndPP = next; - if (tok <= 0) { - if (haveMore && tok != XML_TOK_INVALID) { - *nextPtr = s; - return XML_ERROR_NONE; - } - switch (tok) { - case XML_TOK_INVALID: - *eventPP = next; - return XML_ERROR_INVALID_TOKEN; - case XML_TOK_PARTIAL: - return XML_ERROR_UNCLOSED_TOKEN; - case XML_TOK_PARTIAL_CHAR: - return XML_ERROR_PARTIAL_CHAR; - case -XML_TOK_PROLOG_S: - tok = -tok; - break; - case XML_TOK_NONE: -#ifdef XML_DTD - /* for internal PE NOT referenced between declarations */ - if (enc != encoding && !openInternalEntities->betweenDecl) { - *nextPtr = s; - return XML_ERROR_NONE; - } - /* WFC: PE Between Declarations - must check that PE contains - complete markup, not only for external PEs, but also for - internal PEs if the reference occurs between declarations. - */ - if (isParamEntity || enc != encoding) { - if (XmlTokenRole(&prologState, XML_TOK_NONE, end, end, enc) - == XML_ROLE_ERROR) - return XML_ERROR_INCOMPLETE_PE; - *nextPtr = s; - return XML_ERROR_NONE; - } -#endif /* XML_DTD */ - return XML_ERROR_NO_ELEMENTS; - default: - tok = -tok; - next = end; - break; - } - } - role = XmlTokenRole(&prologState, tok, s, next, enc); - switch (role) { - case XML_ROLE_XML_DECL: - { - enum XML_Error result = processXmlDecl(parser, 0, s, next); - if (result != XML_ERROR_NONE) - return result; - enc = encoding; - handleDefault = XML_FALSE; - } - break; - case XML_ROLE_DOCTYPE_NAME: - if (startDoctypeDeclHandler) { - doctypeName = poolStoreString(&tempPool, enc, s, next); - if (!doctypeName) - return XML_ERROR_NO_MEMORY; - poolFinish(&tempPool); - doctypePubid = NULL; - handleDefault = XML_FALSE; - } - doctypeSysid = NULL; /* always initialize to NULL */ - break; - case XML_ROLE_DOCTYPE_INTERNAL_SUBSET: - if (startDoctypeDeclHandler) { - startDoctypeDeclHandler(handlerArg, doctypeName, doctypeSysid, - doctypePubid, 1); - doctypeName = NULL; - poolClear(&tempPool); - handleDefault = XML_FALSE; - } - break; -#ifdef XML_DTD - case XML_ROLE_TEXT_DECL: - { - enum XML_Error result = processXmlDecl(parser, 1, s, next); - if (result != XML_ERROR_NONE) - return result; - enc = encoding; - handleDefault = XML_FALSE; - } - break; -#endif /* XML_DTD */ - case XML_ROLE_DOCTYPE_PUBLIC_ID: -#ifdef XML_DTD - useForeignDTD = XML_FALSE; - declEntity = (ENTITY *)lookup(parser, - &dtd->paramEntities, - externalSubsetName, - sizeof(ENTITY)); - if (!declEntity) - return XML_ERROR_NO_MEMORY; -#endif /* XML_DTD */ - dtd->hasParamEntityRefs = XML_TRUE; - if (startDoctypeDeclHandler) { - XML_Char *pubId; - if (!XmlIsPublicId(enc, s, next, eventPP)) - return XML_ERROR_PUBLICID; - pubId = poolStoreString(&tempPool, enc, - s + enc->minBytesPerChar, - next - enc->minBytesPerChar); - if (!pubId) - return XML_ERROR_NO_MEMORY; - normalizePublicId(pubId); - poolFinish(&tempPool); - doctypePubid = pubId; - handleDefault = XML_FALSE; - goto alreadyChecked; - } - /* fall through */ - case XML_ROLE_ENTITY_PUBLIC_ID: - if (!XmlIsPublicId(enc, s, next, eventPP)) - return XML_ERROR_PUBLICID; - alreadyChecked: - if (dtd->keepProcessing && declEntity) { - XML_Char *tem = poolStoreString(&dtd->pool, - enc, - s + enc->minBytesPerChar, - next - enc->minBytesPerChar); - if (!tem) - return XML_ERROR_NO_MEMORY; - normalizePublicId(tem); - declEntity->publicId = tem; - poolFinish(&dtd->pool); - if (entityDeclHandler) - handleDefault = XML_FALSE; - } - break; - case XML_ROLE_DOCTYPE_CLOSE: - if (doctypeName) { - startDoctypeDeclHandler(handlerArg, doctypeName, - doctypeSysid, doctypePubid, 0); - poolClear(&tempPool); - handleDefault = XML_FALSE; - } - /* doctypeSysid will be non-NULL in the case of a previous - XML_ROLE_DOCTYPE_SYSTEM_ID, even if startDoctypeDeclHandler - was not set, indicating an external subset - */ -#ifdef XML_DTD - if (doctypeSysid || useForeignDTD) { - XML_Bool hadParamEntityRefs = dtd->hasParamEntityRefs; - dtd->hasParamEntityRefs = XML_TRUE; - if (paramEntityParsing && externalEntityRefHandler) { - ENTITY *entity = (ENTITY *)lookup(parser, - &dtd->paramEntities, - externalSubsetName, - sizeof(ENTITY)); - if (!entity) - return XML_ERROR_NO_MEMORY; - if (useForeignDTD) - entity->base = curBase; - dtd->paramEntityRead = XML_FALSE; - if (!externalEntityRefHandler(externalEntityRefHandlerArg, - 0, - entity->base, - entity->systemId, - entity->publicId)) - return XML_ERROR_EXTERNAL_ENTITY_HANDLING; - if (dtd->paramEntityRead) { - if (!dtd->standalone && - notStandaloneHandler && - !notStandaloneHandler(handlerArg)) - return XML_ERROR_NOT_STANDALONE; - } - /* if we didn't read the foreign DTD then this means that there - is no external subset and we must reset dtd->hasParamEntityRefs - */ - else if (!doctypeSysid) - dtd->hasParamEntityRefs = hadParamEntityRefs; - /* end of DTD - no need to update dtd->keepProcessing */ - } - useForeignDTD = XML_FALSE; - } -#endif /* XML_DTD */ - if (endDoctypeDeclHandler) { - endDoctypeDeclHandler(handlerArg); - handleDefault = XML_FALSE; - } - break; - case XML_ROLE_INSTANCE_START: -#ifdef XML_DTD - /* if there is no DOCTYPE declaration then now is the - last chance to read the foreign DTD - */ - if (useForeignDTD) { - XML_Bool hadParamEntityRefs = dtd->hasParamEntityRefs; - dtd->hasParamEntityRefs = XML_TRUE; - if (paramEntityParsing && externalEntityRefHandler) { - ENTITY *entity = (ENTITY *)lookup(parser, &dtd->paramEntities, - externalSubsetName, - sizeof(ENTITY)); - if (!entity) - return XML_ERROR_NO_MEMORY; - entity->base = curBase; - dtd->paramEntityRead = XML_FALSE; - if (!externalEntityRefHandler(externalEntityRefHandlerArg, - 0, - entity->base, - entity->systemId, - entity->publicId)) - return XML_ERROR_EXTERNAL_ENTITY_HANDLING; - if (dtd->paramEntityRead) { - if (!dtd->standalone && - notStandaloneHandler && - !notStandaloneHandler(handlerArg)) - return XML_ERROR_NOT_STANDALONE; - } - /* if we didn't read the foreign DTD then this means that there - is no external subset and we must reset dtd->hasParamEntityRefs - */ - else - dtd->hasParamEntityRefs = hadParamEntityRefs; - /* end of DTD - no need to update dtd->keepProcessing */ - } - } -#endif /* XML_DTD */ - processor = contentProcessor; - return contentProcessor(parser, s, end, nextPtr); - case XML_ROLE_ATTLIST_ELEMENT_NAME: - declElementType = getElementType(parser, enc, s, next); - if (!declElementType) - return XML_ERROR_NO_MEMORY; - goto checkAttListDeclHandler; - case XML_ROLE_ATTRIBUTE_NAME: - declAttributeId = getAttributeId(parser, enc, s, next); - if (!declAttributeId) - return XML_ERROR_NO_MEMORY; - declAttributeIsCdata = XML_FALSE; - declAttributeType = NULL; - declAttributeIsId = XML_FALSE; - goto checkAttListDeclHandler; - case XML_ROLE_ATTRIBUTE_TYPE_CDATA: - declAttributeIsCdata = XML_TRUE; - declAttributeType = atypeCDATA; - goto checkAttListDeclHandler; - case XML_ROLE_ATTRIBUTE_TYPE_ID: - declAttributeIsId = XML_TRUE; - declAttributeType = atypeID; - goto checkAttListDeclHandler; - case XML_ROLE_ATTRIBUTE_TYPE_IDREF: - declAttributeType = atypeIDREF; - goto checkAttListDeclHandler; - case XML_ROLE_ATTRIBUTE_TYPE_IDREFS: - declAttributeType = atypeIDREFS; - goto checkAttListDeclHandler; - case XML_ROLE_ATTRIBUTE_TYPE_ENTITY: - declAttributeType = atypeENTITY; - goto checkAttListDeclHandler; - case XML_ROLE_ATTRIBUTE_TYPE_ENTITIES: - declAttributeType = atypeENTITIES; - goto checkAttListDeclHandler; - case XML_ROLE_ATTRIBUTE_TYPE_NMTOKEN: - declAttributeType = atypeNMTOKEN; - goto checkAttListDeclHandler; - case XML_ROLE_ATTRIBUTE_TYPE_NMTOKENS: - declAttributeType = atypeNMTOKENS; - checkAttListDeclHandler: - if (dtd->keepProcessing && attlistDeclHandler) - handleDefault = XML_FALSE; - break; - case XML_ROLE_ATTRIBUTE_ENUM_VALUE: - case XML_ROLE_ATTRIBUTE_NOTATION_VALUE: - if (dtd->keepProcessing && attlistDeclHandler) { - const XML_Char *prefix; - if (declAttributeType) { - prefix = enumValueSep; - } - else { - prefix = (role == XML_ROLE_ATTRIBUTE_NOTATION_VALUE - ? notationPrefix - : enumValueStart); - } - if (!poolAppendString(&tempPool, prefix)) - return XML_ERROR_NO_MEMORY; - if (!poolAppend(&tempPool, enc, s, next)) - return XML_ERROR_NO_MEMORY; - declAttributeType = tempPool.start; - handleDefault = XML_FALSE; - } - break; - case XML_ROLE_IMPLIED_ATTRIBUTE_VALUE: - case XML_ROLE_REQUIRED_ATTRIBUTE_VALUE: - if (dtd->keepProcessing) { - if (!defineAttribute(declElementType, declAttributeId, - declAttributeIsCdata, declAttributeIsId, - 0, parser)) - return XML_ERROR_NO_MEMORY; - if (attlistDeclHandler && declAttributeType) { - if (*declAttributeType == XML_T(ASCII_LPAREN) - || (*declAttributeType == XML_T(ASCII_N) - && declAttributeType[1] == XML_T(ASCII_O))) { - /* Enumerated or Notation type */ - if (!poolAppendChar(&tempPool, XML_T(ASCII_RPAREN)) - || !poolAppendChar(&tempPool, XML_T('\0'))) - return XML_ERROR_NO_MEMORY; - declAttributeType = tempPool.start; - poolFinish(&tempPool); - } - *eventEndPP = s; - attlistDeclHandler(handlerArg, declElementType->name, - declAttributeId->name, declAttributeType, - 0, role == XML_ROLE_REQUIRED_ATTRIBUTE_VALUE); - poolClear(&tempPool); - handleDefault = XML_FALSE; - } - } - break; - case XML_ROLE_DEFAULT_ATTRIBUTE_VALUE: - case XML_ROLE_FIXED_ATTRIBUTE_VALUE: - if (dtd->keepProcessing) { - const XML_Char *attVal; - enum XML_Error result = - storeAttributeValue(parser, enc, declAttributeIsCdata, - s + enc->minBytesPerChar, - next - enc->minBytesPerChar, - &dtd->pool); - if (result) - return result; - attVal = poolStart(&dtd->pool); - poolFinish(&dtd->pool); - /* ID attributes aren't allowed to have a default */ - if (!defineAttribute(declElementType, declAttributeId, - declAttributeIsCdata, XML_FALSE, attVal, parser)) - return XML_ERROR_NO_MEMORY; - if (attlistDeclHandler && declAttributeType) { - if (*declAttributeType == XML_T(ASCII_LPAREN) - || (*declAttributeType == XML_T(ASCII_N) - && declAttributeType[1] == XML_T(ASCII_O))) { - /* Enumerated or Notation type */ - if (!poolAppendChar(&tempPool, XML_T(ASCII_RPAREN)) - || !poolAppendChar(&tempPool, XML_T('\0'))) - return XML_ERROR_NO_MEMORY; - declAttributeType = tempPool.start; - poolFinish(&tempPool); - } - *eventEndPP = s; - attlistDeclHandler(handlerArg, declElementType->name, - declAttributeId->name, declAttributeType, - attVal, - role == XML_ROLE_FIXED_ATTRIBUTE_VALUE); - poolClear(&tempPool); - handleDefault = XML_FALSE; - } - } - break; - case XML_ROLE_ENTITY_VALUE: - if (dtd->keepProcessing) { - enum XML_Error result = storeEntityValue(parser, enc, - s + enc->minBytesPerChar, - next - enc->minBytesPerChar); - if (declEntity) { - declEntity->textPtr = poolStart(&dtd->entityValuePool); - declEntity->textLen = (int)(poolLength(&dtd->entityValuePool)); - poolFinish(&dtd->entityValuePool); - if (entityDeclHandler) { - *eventEndPP = s; - entityDeclHandler(handlerArg, - declEntity->name, - declEntity->is_param, - declEntity->textPtr, - declEntity->textLen, - curBase, 0, 0, 0); - handleDefault = XML_FALSE; - } - } - else - poolDiscard(&dtd->entityValuePool); - if (result != XML_ERROR_NONE) - return result; - } - break; - case XML_ROLE_DOCTYPE_SYSTEM_ID: -#ifdef XML_DTD - useForeignDTD = XML_FALSE; -#endif /* XML_DTD */ - dtd->hasParamEntityRefs = XML_TRUE; - if (startDoctypeDeclHandler) { - doctypeSysid = poolStoreString(&tempPool, enc, - s + enc->minBytesPerChar, - next - enc->minBytesPerChar); - if (doctypeSysid == NULL) - return XML_ERROR_NO_MEMORY; - poolFinish(&tempPool); - handleDefault = XML_FALSE; - } -#ifdef XML_DTD - else - /* use externalSubsetName to make doctypeSysid non-NULL - for the case where no startDoctypeDeclHandler is set */ - doctypeSysid = externalSubsetName; -#endif /* XML_DTD */ - if (!dtd->standalone -#ifdef XML_DTD - && !paramEntityParsing -#endif /* XML_DTD */ - && notStandaloneHandler - && !notStandaloneHandler(handlerArg)) - return XML_ERROR_NOT_STANDALONE; -#ifndef XML_DTD - break; -#else /* XML_DTD */ - if (!declEntity) { - declEntity = (ENTITY *)lookup(parser, - &dtd->paramEntities, - externalSubsetName, - sizeof(ENTITY)); - if (!declEntity) - return XML_ERROR_NO_MEMORY; - declEntity->publicId = NULL; - } - /* fall through */ -#endif /* XML_DTD */ - case XML_ROLE_ENTITY_SYSTEM_ID: - if (dtd->keepProcessing && declEntity) { - declEntity->systemId = poolStoreString(&dtd->pool, enc, - s + enc->minBytesPerChar, - next - enc->minBytesPerChar); - if (!declEntity->systemId) - return XML_ERROR_NO_MEMORY; - declEntity->base = curBase; - poolFinish(&dtd->pool); - if (entityDeclHandler) - handleDefault = XML_FALSE; - } - break; - case XML_ROLE_ENTITY_COMPLETE: - if (dtd->keepProcessing && declEntity && entityDeclHandler) { - *eventEndPP = s; - entityDeclHandler(handlerArg, - declEntity->name, - declEntity->is_param, - 0,0, - declEntity->base, - declEntity->systemId, - declEntity->publicId, - 0); - handleDefault = XML_FALSE; - } - break; - case XML_ROLE_ENTITY_NOTATION_NAME: - if (dtd->keepProcessing && declEntity) { - declEntity->notation = poolStoreString(&dtd->pool, enc, s, next); - if (!declEntity->notation) - return XML_ERROR_NO_MEMORY; - poolFinish(&dtd->pool); - if (unparsedEntityDeclHandler) { - *eventEndPP = s; - unparsedEntityDeclHandler(handlerArg, - declEntity->name, - declEntity->base, - declEntity->systemId, - declEntity->publicId, - declEntity->notation); - handleDefault = XML_FALSE; - } - else if (entityDeclHandler) { - *eventEndPP = s; - entityDeclHandler(handlerArg, - declEntity->name, - 0,0,0, - declEntity->base, - declEntity->systemId, - declEntity->publicId, - declEntity->notation); - handleDefault = XML_FALSE; - } - } - break; - case XML_ROLE_GENERAL_ENTITY_NAME: - { - if (XmlPredefinedEntityName(enc, s, next)) { - declEntity = NULL; - break; - } - if (dtd->keepProcessing) { - const XML_Char *name = poolStoreString(&dtd->pool, enc, s, next); - if (!name) - return XML_ERROR_NO_MEMORY; - declEntity = (ENTITY *)lookup(parser, &dtd->generalEntities, name, - sizeof(ENTITY)); - if (!declEntity) - return XML_ERROR_NO_MEMORY; - if (declEntity->name != name) { - poolDiscard(&dtd->pool); - declEntity = NULL; - } - else { - poolFinish(&dtd->pool); - declEntity->publicId = NULL; - declEntity->is_param = XML_FALSE; - /* if we have a parent parser or are reading an internal parameter - entity, then the entity declaration is not considered "internal" - */ - declEntity->is_internal = !(parentParser || openInternalEntities); - if (entityDeclHandler) - handleDefault = XML_FALSE; - } - } - else { - poolDiscard(&dtd->pool); - declEntity = NULL; - } - } - break; - case XML_ROLE_PARAM_ENTITY_NAME: -#ifdef XML_DTD - if (dtd->keepProcessing) { - const XML_Char *name = poolStoreString(&dtd->pool, enc, s, next); - if (!name) - return XML_ERROR_NO_MEMORY; - declEntity = (ENTITY *)lookup(parser, &dtd->paramEntities, - name, sizeof(ENTITY)); - if (!declEntity) - return XML_ERROR_NO_MEMORY; - if (declEntity->name != name) { - poolDiscard(&dtd->pool); - declEntity = NULL; - } - else { - poolFinish(&dtd->pool); - declEntity->publicId = NULL; - declEntity->is_param = XML_TRUE; - /* if we have a parent parser or are reading an internal parameter - entity, then the entity declaration is not considered "internal" - */ - declEntity->is_internal = !(parentParser || openInternalEntities); - if (entityDeclHandler) - handleDefault = XML_FALSE; - } - } - else { - poolDiscard(&dtd->pool); - declEntity = NULL; - } -#else /* not XML_DTD */ - declEntity = NULL; -#endif /* XML_DTD */ - break; - case XML_ROLE_NOTATION_NAME: - declNotationPublicId = NULL; - declNotationName = NULL; - if (notationDeclHandler) { - declNotationName = poolStoreString(&tempPool, enc, s, next); - if (!declNotationName) - return XML_ERROR_NO_MEMORY; - poolFinish(&tempPool); - handleDefault = XML_FALSE; - } - break; - case XML_ROLE_NOTATION_PUBLIC_ID: - if (!XmlIsPublicId(enc, s, next, eventPP)) - return XML_ERROR_PUBLICID; - if (declNotationName) { /* means notationDeclHandler != NULL */ - XML_Char *tem = poolStoreString(&tempPool, - enc, - s + enc->minBytesPerChar, - next - enc->minBytesPerChar); - if (!tem) - return XML_ERROR_NO_MEMORY; - normalizePublicId(tem); - declNotationPublicId = tem; - poolFinish(&tempPool); - handleDefault = XML_FALSE; - } - break; - case XML_ROLE_NOTATION_SYSTEM_ID: - if (declNotationName && notationDeclHandler) { - const XML_Char *systemId - = poolStoreString(&tempPool, enc, - s + enc->minBytesPerChar, - next - enc->minBytesPerChar); - if (!systemId) - return XML_ERROR_NO_MEMORY; - *eventEndPP = s; - notationDeclHandler(handlerArg, - declNotationName, - curBase, - systemId, - declNotationPublicId); - handleDefault = XML_FALSE; - } - poolClear(&tempPool); - break; - case XML_ROLE_NOTATION_NO_SYSTEM_ID: - if (declNotationPublicId && notationDeclHandler) { - *eventEndPP = s; - notationDeclHandler(handlerArg, - declNotationName, - curBase, - 0, - declNotationPublicId); - handleDefault = XML_FALSE; - } - poolClear(&tempPool); - break; - case XML_ROLE_ERROR: - switch (tok) { - case XML_TOK_PARAM_ENTITY_REF: - /* PE references in internal subset are - not allowed within declarations. */ - return XML_ERROR_PARAM_ENTITY_REF; - case XML_TOK_XML_DECL: - return XML_ERROR_MISPLACED_XML_PI; - default: - return XML_ERROR_SYNTAX; - } -#ifdef XML_DTD - case XML_ROLE_IGNORE_SECT: - { - enum XML_Error result; - if (defaultHandler) - reportDefault(parser, enc, s, next); - handleDefault = XML_FALSE; - result = doIgnoreSection(parser, enc, &next, end, nextPtr, haveMore); - if (result != XML_ERROR_NONE) - return result; - else if (!next) { - processor = ignoreSectionProcessor; - return result; - } - } - break; -#endif /* XML_DTD */ - case XML_ROLE_GROUP_OPEN: - if (prologState.level >= groupSize) { - if (groupSize) { - char *temp = (char *)REALLOC(groupConnector, groupSize *= 2); - if (temp == NULL) - return XML_ERROR_NO_MEMORY; - groupConnector = temp; - if (dtd->scaffIndex) { - int *temp = (int *)REALLOC(dtd->scaffIndex, - groupSize * sizeof(int)); - if (temp == NULL) - return XML_ERROR_NO_MEMORY; - dtd->scaffIndex = temp; - } - } - else { - groupConnector = (char *)MALLOC(groupSize = 32); - if (!groupConnector) - return XML_ERROR_NO_MEMORY; - } - } - groupConnector[prologState.level] = 0; - if (dtd->in_eldecl) { - int myindex = nextScaffoldPart(parser); - if (myindex < 0) - return XML_ERROR_NO_MEMORY; - dtd->scaffIndex[dtd->scaffLevel] = myindex; - dtd->scaffLevel++; - dtd->scaffold[myindex].type = XML_CTYPE_SEQ; - if (elementDeclHandler) - handleDefault = XML_FALSE; - } - break; - case XML_ROLE_GROUP_SEQUENCE: - if (groupConnector[prologState.level] == ASCII_PIPE) - return XML_ERROR_SYNTAX; - groupConnector[prologState.level] = ASCII_COMMA; - if (dtd->in_eldecl && elementDeclHandler) - handleDefault = XML_FALSE; - break; - case XML_ROLE_GROUP_CHOICE: - if (groupConnector[prologState.level] == ASCII_COMMA) - return XML_ERROR_SYNTAX; - if (dtd->in_eldecl - && !groupConnector[prologState.level] - && (dtd->scaffold[dtd->scaffIndex[dtd->scaffLevel - 1]].type - != XML_CTYPE_MIXED) - ) { - dtd->scaffold[dtd->scaffIndex[dtd->scaffLevel - 1]].type - = XML_CTYPE_CHOICE; - if (elementDeclHandler) - handleDefault = XML_FALSE; - } - groupConnector[prologState.level] = ASCII_PIPE; - break; - case XML_ROLE_PARAM_ENTITY_REF: -#ifdef XML_DTD - case XML_ROLE_INNER_PARAM_ENTITY_REF: - dtd->hasParamEntityRefs = XML_TRUE; - if (!paramEntityParsing) - dtd->keepProcessing = dtd->standalone; - else { - const XML_Char *name; - ENTITY *entity; - name = poolStoreString(&dtd->pool, enc, - s + enc->minBytesPerChar, - next - enc->minBytesPerChar); - if (!name) - return XML_ERROR_NO_MEMORY; - entity = (ENTITY *)lookup(parser, &dtd->paramEntities, name, 0); - poolDiscard(&dtd->pool); - /* first, determine if a check for an existing declaration is needed; - if yes, check that the entity exists, and that it is internal, - otherwise call the skipped entity handler - */ - if (prologState.documentEntity && - (dtd->standalone - ? !openInternalEntities - : !dtd->hasParamEntityRefs)) { - if (!entity) - return XML_ERROR_UNDEFINED_ENTITY; - else if (!entity->is_internal) - return XML_ERROR_ENTITY_DECLARED_IN_PE; - } - else if (!entity) { - dtd->keepProcessing = dtd->standalone; - /* cannot report skipped entities in declarations */ - if ((role == XML_ROLE_PARAM_ENTITY_REF) && skippedEntityHandler) { - skippedEntityHandler(handlerArg, name, 1); - handleDefault = XML_FALSE; - } - break; - } - if (entity->open) - return XML_ERROR_RECURSIVE_ENTITY_REF; - if (entity->textPtr) { - enum XML_Error result; - XML_Bool betweenDecl = - (role == XML_ROLE_PARAM_ENTITY_REF ? XML_TRUE : XML_FALSE); - result = processInternalEntity(parser, entity, betweenDecl); - if (result != XML_ERROR_NONE) - return result; - handleDefault = XML_FALSE; - break; - } - if (externalEntityRefHandler) { - dtd->paramEntityRead = XML_FALSE; - entity->open = XML_TRUE; - if (!externalEntityRefHandler(externalEntityRefHandlerArg, - 0, - entity->base, - entity->systemId, - entity->publicId)) { - entity->open = XML_FALSE; - return XML_ERROR_EXTERNAL_ENTITY_HANDLING; - } - entity->open = XML_FALSE; - handleDefault = XML_FALSE; - if (!dtd->paramEntityRead) { - dtd->keepProcessing = dtd->standalone; - break; - } - } - else { - dtd->keepProcessing = dtd->standalone; - break; - } - } -#endif /* XML_DTD */ - if (!dtd->standalone && - notStandaloneHandler && - !notStandaloneHandler(handlerArg)) - return XML_ERROR_NOT_STANDALONE; - break; - - /* Element declaration stuff */ - - case XML_ROLE_ELEMENT_NAME: - if (elementDeclHandler) { - declElementType = getElementType(parser, enc, s, next); - if (!declElementType) - return XML_ERROR_NO_MEMORY; - dtd->scaffLevel = 0; - dtd->scaffCount = 0; - dtd->in_eldecl = XML_TRUE; - handleDefault = XML_FALSE; - } - break; - - case XML_ROLE_CONTENT_ANY: - case XML_ROLE_CONTENT_EMPTY: - if (dtd->in_eldecl) { - if (elementDeclHandler) { - XML_Content * content = (XML_Content *) MALLOC(sizeof(XML_Content)); - if (!content) - return XML_ERROR_NO_MEMORY; - content->quant = XML_CQUANT_NONE; - content->name = NULL; - content->numchildren = 0; - content->children = NULL; - content->type = ((role == XML_ROLE_CONTENT_ANY) ? - XML_CTYPE_ANY : - XML_CTYPE_EMPTY); - *eventEndPP = s; - elementDeclHandler(handlerArg, declElementType->name, content); - handleDefault = XML_FALSE; - } - dtd->in_eldecl = XML_FALSE; - } - break; - - case XML_ROLE_CONTENT_PCDATA: - if (dtd->in_eldecl) { - dtd->scaffold[dtd->scaffIndex[dtd->scaffLevel - 1]].type - = XML_CTYPE_MIXED; - if (elementDeclHandler) - handleDefault = XML_FALSE; - } - break; - - case XML_ROLE_CONTENT_ELEMENT: - quant = XML_CQUANT_NONE; - goto elementContent; - case XML_ROLE_CONTENT_ELEMENT_OPT: - quant = XML_CQUANT_OPT; - goto elementContent; - case XML_ROLE_CONTENT_ELEMENT_REP: - quant = XML_CQUANT_REP; - goto elementContent; - case XML_ROLE_CONTENT_ELEMENT_PLUS: - quant = XML_CQUANT_PLUS; - elementContent: - if (dtd->in_eldecl) { - ELEMENT_TYPE *el; - const XML_Char *name; - int nameLen; - const char *nxt = (quant == XML_CQUANT_NONE - ? next - : next - enc->minBytesPerChar); - int myindex = nextScaffoldPart(parser); - if (myindex < 0) - return XML_ERROR_NO_MEMORY; - dtd->scaffold[myindex].type = XML_CTYPE_NAME; - dtd->scaffold[myindex].quant = quant; - el = getElementType(parser, enc, s, nxt); - if (!el) - return XML_ERROR_NO_MEMORY; - name = el->name; - dtd->scaffold[myindex].name = name; - nameLen = 0; - for (; name[nameLen++]; ); - dtd->contentStringLen += nameLen; - if (elementDeclHandler) - handleDefault = XML_FALSE; - } - break; - - case XML_ROLE_GROUP_CLOSE: - quant = XML_CQUANT_NONE; - goto closeGroup; - case XML_ROLE_GROUP_CLOSE_OPT: - quant = XML_CQUANT_OPT; - goto closeGroup; - case XML_ROLE_GROUP_CLOSE_REP: - quant = XML_CQUANT_REP; - goto closeGroup; - case XML_ROLE_GROUP_CLOSE_PLUS: - quant = XML_CQUANT_PLUS; - closeGroup: - if (dtd->in_eldecl) { - if (elementDeclHandler) - handleDefault = XML_FALSE; - dtd->scaffLevel--; - dtd->scaffold[dtd->scaffIndex[dtd->scaffLevel]].quant = quant; - if (dtd->scaffLevel == 0) { - if (!handleDefault) { - XML_Content *model = build_model(parser); - if (!model) - return XML_ERROR_NO_MEMORY; - *eventEndPP = s; - elementDeclHandler(handlerArg, declElementType->name, model); - } - dtd->in_eldecl = XML_FALSE; - dtd->contentStringLen = 0; - } - } - break; - /* End element declaration stuff */ - - case XML_ROLE_PI: - if (!reportProcessingInstruction(parser, enc, s, next)) - return XML_ERROR_NO_MEMORY; - handleDefault = XML_FALSE; - break; - case XML_ROLE_COMMENT: - if (!reportComment(parser, enc, s, next)) - return XML_ERROR_NO_MEMORY; - handleDefault = XML_FALSE; - break; - case XML_ROLE_NONE: - switch (tok) { - case XML_TOK_BOM: - handleDefault = XML_FALSE; - break; - } - break; - case XML_ROLE_DOCTYPE_NONE: - if (startDoctypeDeclHandler) - handleDefault = XML_FALSE; - break; - case XML_ROLE_ENTITY_NONE: - if (dtd->keepProcessing && entityDeclHandler) - handleDefault = XML_FALSE; - break; - case XML_ROLE_NOTATION_NONE: - if (notationDeclHandler) - handleDefault = XML_FALSE; - break; - case XML_ROLE_ATTLIST_NONE: - if (dtd->keepProcessing && attlistDeclHandler) - handleDefault = XML_FALSE; - break; - case XML_ROLE_ELEMENT_NONE: - if (elementDeclHandler) - handleDefault = XML_FALSE; - break; - } /* end of big switch */ - - if (handleDefault && defaultHandler) - reportDefault(parser, enc, s, next); - - switch (ps_parsing) { - case XML_SUSPENDED: - *nextPtr = next; - return XML_ERROR_NONE; - case XML_FINISHED: - return XML_ERROR_ABORTED; - default: - s = next; - tok = XmlPrologTok(enc, s, end, &next); - } - } - /* not reached */ -} - -static enum XML_Error PTRCALL -epilogProcessor(XML_Parser parser, - const char *s, - const char *end, - const char **nextPtr) -{ - processor = epilogProcessor; - eventPtr = s; - for (;;) { - const char *next = NULL; - int tok = XmlPrologTok(encoding, s, end, &next); - eventEndPtr = next; - switch (tok) { - /* report partial linebreak - it might be the last token */ - case -XML_TOK_PROLOG_S: - if (defaultHandler) { - reportDefault(parser, encoding, s, next); - if (ps_parsing == XML_FINISHED) - return XML_ERROR_ABORTED; - } - *nextPtr = next; - return XML_ERROR_NONE; - case XML_TOK_NONE: - *nextPtr = s; - return XML_ERROR_NONE; - case XML_TOK_PROLOG_S: - if (defaultHandler) - reportDefault(parser, encoding, s, next); - break; - case XML_TOK_PI: - if (!reportProcessingInstruction(parser, encoding, s, next)) - return XML_ERROR_NO_MEMORY; - break; - case XML_TOK_COMMENT: - if (!reportComment(parser, encoding, s, next)) - return XML_ERROR_NO_MEMORY; - break; - case XML_TOK_INVALID: - eventPtr = next; - return XML_ERROR_INVALID_TOKEN; - case XML_TOK_PARTIAL: - if (!ps_finalBuffer) { - *nextPtr = s; - return XML_ERROR_NONE; - } - return XML_ERROR_UNCLOSED_TOKEN; - case XML_TOK_PARTIAL_CHAR: - if (!ps_finalBuffer) { - *nextPtr = s; - return XML_ERROR_NONE; - } - return XML_ERROR_PARTIAL_CHAR; - default: - return XML_ERROR_JUNK_AFTER_DOC_ELEMENT; - } - eventPtr = s = next; - switch (ps_parsing) { - case XML_SUSPENDED: - *nextPtr = next; - return XML_ERROR_NONE; - case XML_FINISHED: - return XML_ERROR_ABORTED; - default: ; - } - } -} - -static enum XML_Error -processInternalEntity(XML_Parser parser, ENTITY *entity, - XML_Bool betweenDecl) -{ - const char *textStart, *textEnd; - const char *next; - enum XML_Error result; - OPEN_INTERNAL_ENTITY *openEntity; - - if (freeInternalEntities) { - openEntity = freeInternalEntities; - freeInternalEntities = openEntity->next; - } - else { - openEntity = (OPEN_INTERNAL_ENTITY *)MALLOC(sizeof(OPEN_INTERNAL_ENTITY)); - if (!openEntity) - return XML_ERROR_NO_MEMORY; - } - entity->open = XML_TRUE; - entity->processed = 0; - openEntity->next = openInternalEntities; - openInternalEntities = openEntity; - openEntity->entity = entity; - openEntity->startTagLevel = tagLevel; - openEntity->betweenDecl = betweenDecl; - openEntity->internalEventPtr = NULL; - openEntity->internalEventEndPtr = NULL; - textStart = (char *)entity->textPtr; - textEnd = (char *)(entity->textPtr + entity->textLen); - -#ifdef XML_DTD - if (entity->is_param) { - int tok = XmlPrologTok(internalEncoding, textStart, textEnd, &next); - result = doProlog(parser, internalEncoding, textStart, textEnd, tok, - next, &next, XML_FALSE); - } - else -#endif /* XML_DTD */ - result = doContent(parser, tagLevel, internalEncoding, textStart, - textEnd, &next, XML_FALSE); - - if (result == XML_ERROR_NONE) { - if (textEnd != next && ps_parsing == XML_SUSPENDED) { - entity->processed = (int)(next - textStart); - processor = internalEntityProcessor; - } - else { - entity->open = XML_FALSE; - openInternalEntities = openEntity->next; - /* put openEntity back in list of free instances */ - openEntity->next = freeInternalEntities; - freeInternalEntities = openEntity; - } - } - return result; -} - -static enum XML_Error PTRCALL -internalEntityProcessor(XML_Parser parser, - const char *s, - const char *end, - const char **nextPtr) -{ - ENTITY *entity; - const char *textStart, *textEnd; - const char *next; - enum XML_Error result; - OPEN_INTERNAL_ENTITY *openEntity = openInternalEntities; - if (!openEntity) - return XML_ERROR_UNEXPECTED_STATE; - - entity = openEntity->entity; - textStart = ((char *)entity->textPtr) + entity->processed; - textEnd = (char *)(entity->textPtr + entity->textLen); - -#ifdef XML_DTD - if (entity->is_param) { - int tok = XmlPrologTok(internalEncoding, textStart, textEnd, &next); - result = doProlog(parser, internalEncoding, textStart, textEnd, tok, - next, &next, XML_FALSE); - } - else -#endif /* XML_DTD */ - result = doContent(parser, openEntity->startTagLevel, internalEncoding, - textStart, textEnd, &next, XML_FALSE); - - if (result != XML_ERROR_NONE) - return result; - else if (textEnd != next && ps_parsing == XML_SUSPENDED) { - entity->processed = (int)(next - (char *)entity->textPtr); - return result; - } - else { - entity->open = XML_FALSE; - openInternalEntities = openEntity->next; - /* put openEntity back in list of free instances */ - openEntity->next = freeInternalEntities; - freeInternalEntities = openEntity; - } - -#ifdef XML_DTD - if (entity->is_param) { - int tok; - processor = prologProcessor; - tok = XmlPrologTok(encoding, s, end, &next); - return doProlog(parser, encoding, s, end, tok, next, nextPtr, - (XML_Bool)!ps_finalBuffer); - } - else -#endif /* XML_DTD */ - { - processor = contentProcessor; - /* see externalEntityContentProcessor vs contentProcessor */ - return doContent(parser, parentParser ? 1 : 0, encoding, s, end, - nextPtr, (XML_Bool)!ps_finalBuffer); - } -} - -static enum XML_Error PTRCALL -errorProcessor(XML_Parser parser, - const char *UNUSED_P(s), - const char *UNUSED_P(end), - const char **UNUSED_P(nextPtr)) -{ - return errorCode; -} - -static enum XML_Error -storeAttributeValue(XML_Parser parser, const ENCODING *enc, XML_Bool isCdata, - const char *ptr, const char *end, - STRING_POOL *pool) -{ - enum XML_Error result = appendAttributeValue(parser, enc, isCdata, ptr, - end, pool); - if (result) - return result; - if (!isCdata && poolLength(pool) && poolLastChar(pool) == 0x20) - poolChop(pool); - if (!poolAppendChar(pool, XML_T('\0'))) - return XML_ERROR_NO_MEMORY; - return XML_ERROR_NONE; -} - -static enum XML_Error -appendAttributeValue(XML_Parser parser, const ENCODING *enc, XML_Bool isCdata, - const char *ptr, const char *end, - STRING_POOL *pool) -{ - DTD * const dtd = _dtd; /* save one level of indirection */ - for (;;) { - const char *next; - int tok = XmlAttributeValueTok(enc, ptr, end, &next); - switch (tok) { - case XML_TOK_NONE: - return XML_ERROR_NONE; - case XML_TOK_INVALID: - if (enc == encoding) - eventPtr = next; - return XML_ERROR_INVALID_TOKEN; - case XML_TOK_PARTIAL: - if (enc == encoding) - eventPtr = ptr; - return XML_ERROR_INVALID_TOKEN; - case XML_TOK_CHAR_REF: - { - XML_Char buf[XML_ENCODE_MAX]; - int i; - int n = XmlCharRefNumber(enc, ptr); - if (n < 0) { - if (enc == encoding) - eventPtr = ptr; - return XML_ERROR_BAD_CHAR_REF; - } - if (!isCdata - && n == 0x20 /* space */ - && (poolLength(pool) == 0 || poolLastChar(pool) == 0x20)) - break; - n = XmlEncode(n, (ICHAR *)buf); - if (!n) { - if (enc == encoding) - eventPtr = ptr; - return XML_ERROR_BAD_CHAR_REF; - } - for (i = 0; i < n; i++) { - if (!poolAppendChar(pool, buf[i])) - return XML_ERROR_NO_MEMORY; - } - } - break; - case XML_TOK_DATA_CHARS: - if (!poolAppend(pool, enc, ptr, next)) - return XML_ERROR_NO_MEMORY; - break; - case XML_TOK_TRAILING_CR: - next = ptr + enc->minBytesPerChar; - /* fall through */ - case XML_TOK_ATTRIBUTE_VALUE_S: - case XML_TOK_DATA_NEWLINE: - if (!isCdata && (poolLength(pool) == 0 || poolLastChar(pool) == 0x20)) - break; - if (!poolAppendChar(pool, 0x20)) - return XML_ERROR_NO_MEMORY; - break; - case XML_TOK_ENTITY_REF: - { - const XML_Char *name; - ENTITY *entity; - char checkEntityDecl; - XML_Char ch = (XML_Char) XmlPredefinedEntityName(enc, - ptr + enc->minBytesPerChar, - next - enc->minBytesPerChar); - if (ch) { - if (!poolAppendChar(pool, ch)) - return XML_ERROR_NO_MEMORY; - break; - } - name = poolStoreString(&temp2Pool, enc, - ptr + enc->minBytesPerChar, - next - enc->minBytesPerChar); - if (!name) - return XML_ERROR_NO_MEMORY; - entity = (ENTITY *)lookup(parser, &dtd->generalEntities, name, 0); - poolDiscard(&temp2Pool); - /* First, determine if a check for an existing declaration is needed; - if yes, check that the entity exists, and that it is internal. - */ - if (pool == &dtd->pool) /* are we called from prolog? */ - checkEntityDecl = -#ifdef XML_DTD - prologState.documentEntity && -#endif /* XML_DTD */ - (dtd->standalone - ? !openInternalEntities - : !dtd->hasParamEntityRefs); - else /* if (pool == &tempPool): we are called from content */ - checkEntityDecl = !dtd->hasParamEntityRefs || dtd->standalone; - if (checkEntityDecl) { - if (!entity) - return XML_ERROR_UNDEFINED_ENTITY; - else if (!entity->is_internal) - return XML_ERROR_ENTITY_DECLARED_IN_PE; - } - else if (!entity) { - /* Cannot report skipped entity here - see comments on - skippedEntityHandler. - if (skippedEntityHandler) - skippedEntityHandler(handlerArg, name, 0); - */ - /* Cannot call the default handler because this would be - out of sync with the call to the startElementHandler. - if ((pool == &tempPool) && defaultHandler) - reportDefault(parser, enc, ptr, next); - */ - break; - } - if (entity->open) { - if (enc == encoding) - eventPtr = ptr; - return XML_ERROR_RECURSIVE_ENTITY_REF; - } - if (entity->notation) { - if (enc == encoding) - eventPtr = ptr; - return XML_ERROR_BINARY_ENTITY_REF; - } - if (!entity->textPtr) { - if (enc == encoding) - eventPtr = ptr; - return XML_ERROR_ATTRIBUTE_EXTERNAL_ENTITY_REF; - } - else { - enum XML_Error result; - const XML_Char *textEnd = entity->textPtr + entity->textLen; - entity->open = XML_TRUE; - result = appendAttributeValue(parser, internalEncoding, isCdata, - (char *)entity->textPtr, - (char *)textEnd, pool); - entity->open = XML_FALSE; - if (result) - return result; - } - } - break; - default: - if (enc == encoding) - eventPtr = ptr; - return XML_ERROR_UNEXPECTED_STATE; - } - ptr = next; - } - /* not reached */ -} - -static enum XML_Error -storeEntityValue(XML_Parser parser, - const ENCODING *enc, - const char *entityTextPtr, - const char *entityTextEnd) -{ - DTD * const dtd = _dtd; /* save one level of indirection */ - STRING_POOL *pool = &(dtd->entityValuePool); - enum XML_Error result = XML_ERROR_NONE; -#ifdef XML_DTD - int oldInEntityValue = prologState.inEntityValue; - prologState.inEntityValue = 1; -#endif /* XML_DTD */ - /* never return Null for the value argument in EntityDeclHandler, - since this would indicate an external entity; therefore we - have to make sure that entityValuePool.start is not null */ - if (!pool->blocks) { - if (!poolGrow(pool)) - return XML_ERROR_NO_MEMORY; - } - - for (;;) { - const char *next; - int tok = XmlEntityValueTok(enc, entityTextPtr, entityTextEnd, &next); - switch (tok) { - case XML_TOK_PARAM_ENTITY_REF: -#ifdef XML_DTD - if (isParamEntity || enc != encoding) { - const XML_Char *name; - ENTITY *entity; - name = poolStoreString(&tempPool, enc, - entityTextPtr + enc->minBytesPerChar, - next - enc->minBytesPerChar); - if (!name) { - result = XML_ERROR_NO_MEMORY; - goto endEntityValue; - } - entity = (ENTITY *)lookup(parser, &dtd->paramEntities, name, 0); - poolDiscard(&tempPool); - if (!entity) { - /* not a well-formedness error - see XML 1.0: WFC Entity Declared */ - /* cannot report skipped entity here - see comments on - skippedEntityHandler - if (skippedEntityHandler) - skippedEntityHandler(handlerArg, name, 0); - */ - dtd->keepProcessing = dtd->standalone; - goto endEntityValue; - } - if (entity->open) { - if (enc == encoding) - eventPtr = entityTextPtr; - result = XML_ERROR_RECURSIVE_ENTITY_REF; - goto endEntityValue; - } - if (entity->systemId) { - if (externalEntityRefHandler) { - dtd->paramEntityRead = XML_FALSE; - entity->open = XML_TRUE; - if (!externalEntityRefHandler(externalEntityRefHandlerArg, - 0, - entity->base, - entity->systemId, - entity->publicId)) { - entity->open = XML_FALSE; - result = XML_ERROR_EXTERNAL_ENTITY_HANDLING; - goto endEntityValue; - } - entity->open = XML_FALSE; - if (!dtd->paramEntityRead) - dtd->keepProcessing = dtd->standalone; - } - else - dtd->keepProcessing = dtd->standalone; - } - else { - entity->open = XML_TRUE; - result = storeEntityValue(parser, - internalEncoding, - (char *)entity->textPtr, - (char *)(entity->textPtr - + entity->textLen)); - entity->open = XML_FALSE; - if (result) - goto endEntityValue; - } - break; - } -#endif /* XML_DTD */ - /* In the internal subset, PE references are not legal - within markup declarations, e.g entity values in this case. */ - eventPtr = entityTextPtr; - result = XML_ERROR_PARAM_ENTITY_REF; - goto endEntityValue; - case XML_TOK_NONE: - result = XML_ERROR_NONE; - goto endEntityValue; - case XML_TOK_ENTITY_REF: - case XML_TOK_DATA_CHARS: - if (!poolAppend(pool, enc, entityTextPtr, next)) { - result = XML_ERROR_NO_MEMORY; - goto endEntityValue; - } - break; - case XML_TOK_TRAILING_CR: - next = entityTextPtr + enc->minBytesPerChar; - /* fall through */ - case XML_TOK_DATA_NEWLINE: - if (pool->end == pool->ptr && !poolGrow(pool)) { - result = XML_ERROR_NO_MEMORY; - goto endEntityValue; - } - *(pool->ptr)++ = 0xA; - break; - case XML_TOK_CHAR_REF: - { - XML_Char buf[XML_ENCODE_MAX]; - int i; - int n = XmlCharRefNumber(enc, entityTextPtr); - if (n < 0) { - if (enc == encoding) - eventPtr = entityTextPtr; - result = XML_ERROR_BAD_CHAR_REF; - goto endEntityValue; - } - n = XmlEncode(n, (ICHAR *)buf); - if (!n) { - if (enc == encoding) - eventPtr = entityTextPtr; - result = XML_ERROR_BAD_CHAR_REF; - goto endEntityValue; - } - for (i = 0; i < n; i++) { - if (pool->end == pool->ptr && !poolGrow(pool)) { - result = XML_ERROR_NO_MEMORY; - goto endEntityValue; - } - *(pool->ptr)++ = buf[i]; - } - } - break; - case XML_TOK_PARTIAL: - if (enc == encoding) - eventPtr = entityTextPtr; - result = XML_ERROR_INVALID_TOKEN; - goto endEntityValue; - case XML_TOK_INVALID: - if (enc == encoding) - eventPtr = next; - result = XML_ERROR_INVALID_TOKEN; - goto endEntityValue; - default: - if (enc == encoding) - eventPtr = entityTextPtr; - result = XML_ERROR_UNEXPECTED_STATE; - goto endEntityValue; - } - entityTextPtr = next; - } -endEntityValue: -#ifdef XML_DTD - prologState.inEntityValue = oldInEntityValue; -#endif /* XML_DTD */ - return result; -} - -static void FASTCALL -normalizeLines(XML_Char *s) -{ - XML_Char *p; - for (;; s++) { - if (*s == XML_T('\0')) - return; - if (*s == 0xD) - break; - } - p = s; - do { - if (*s == 0xD) { - *p++ = 0xA; - if (*++s == 0xA) - s++; - } - else - *p++ = *s++; - } while (*s); - *p = XML_T('\0'); -} - -static int -reportProcessingInstruction(XML_Parser parser, const ENCODING *enc, - const char *start, const char *end) -{ - const XML_Char *target; - XML_Char *data; - const char *tem; - if (!processingInstructionHandler) { - if (defaultHandler) - reportDefault(parser, enc, start, end); - return 1; - } - start += enc->minBytesPerChar * 2; - tem = start + XmlNameLength(enc, start); - target = poolStoreString(&tempPool, enc, start, tem); - if (!target) - return 0; - poolFinish(&tempPool); - data = poolStoreString(&tempPool, enc, - XmlSkipS(enc, tem), - end - enc->minBytesPerChar*2); - if (!data) - return 0; - normalizeLines(data); - processingInstructionHandler(handlerArg, target, data); - poolClear(&tempPool); - return 1; -} - -static int -reportComment(XML_Parser parser, const ENCODING *enc, - const char *start, const char *end) -{ - XML_Char *data; - if (!commentHandler) { - if (defaultHandler) - reportDefault(parser, enc, start, end); - return 1; - } - data = poolStoreString(&tempPool, - enc, - start + enc->minBytesPerChar * 4, - end - enc->minBytesPerChar * 3); - if (!data) - return 0; - normalizeLines(data); - commentHandler(handlerArg, data); - poolClear(&tempPool); - return 1; -} - -static void -reportDefault(XML_Parser parser, const ENCODING *enc, - const char *s, const char *end) -{ - if (MUST_CONVERT(enc, s)) { - enum XML_Convert_Result convert_res; - const char **eventPP; - const char **eventEndPP; - if (enc == encoding) { - eventPP = &eventPtr; - eventEndPP = &eventEndPtr; - } - else { - eventPP = &(openInternalEntities->internalEventPtr); - eventEndPP = &(openInternalEntities->internalEventEndPtr); - } - do { - ICHAR *dataPtr = (ICHAR *)dataBuf; - convert_res = XmlConvert(enc, &s, end, &dataPtr, (ICHAR *)dataBufEnd); - *eventEndPP = s; - defaultHandler(handlerArg, dataBuf, (int)(dataPtr - (ICHAR *)dataBuf)); - *eventPP = s; - } while ((convert_res != XML_CONVERT_COMPLETED) && (convert_res != XML_CONVERT_INPUT_INCOMPLETE)); - } - else - defaultHandler(handlerArg, (XML_Char *)s, (int)((XML_Char *)end - (XML_Char *)s)); -} - - -static int -defineAttribute(ELEMENT_TYPE *type, ATTRIBUTE_ID *attId, XML_Bool isCdata, - XML_Bool isId, const XML_Char *value, XML_Parser parser) -{ - DEFAULT_ATTRIBUTE *att; - if (value || isId) { - /* The handling of default attributes gets messed up if we have - a default which duplicates a non-default. */ - int i; - for (i = 0; i < type->nDefaultAtts; i++) - if (attId == type->defaultAtts[i].id) - return 1; - if (isId && !type->idAtt && !attId->xmlns) - type->idAtt = attId; - } - if (type->nDefaultAtts == type->allocDefaultAtts) { - if (type->allocDefaultAtts == 0) { - type->allocDefaultAtts = 8; - type->defaultAtts = (DEFAULT_ATTRIBUTE *)MALLOC(type->allocDefaultAtts - * sizeof(DEFAULT_ATTRIBUTE)); - if (!type->defaultAtts) - return 0; - } - else { - DEFAULT_ATTRIBUTE *temp; - int count = type->allocDefaultAtts * 2; - temp = (DEFAULT_ATTRIBUTE *) - REALLOC(type->defaultAtts, (count * sizeof(DEFAULT_ATTRIBUTE))); - if (temp == NULL) - return 0; - type->allocDefaultAtts = count; - type->defaultAtts = temp; - } - } - att = type->defaultAtts + type->nDefaultAtts; - att->id = attId; - att->value = value; - att->isCdata = isCdata; - if (!isCdata) - attId->maybeTokenized = XML_TRUE; - type->nDefaultAtts += 1; - return 1; -} - -static int -setElementTypePrefix(XML_Parser parser, ELEMENT_TYPE *elementType) -{ - DTD * const dtd = _dtd; /* save one level of indirection */ - const XML_Char *name; - for (name = elementType->name; *name; name++) { - if (*name == XML_T(ASCII_COLON)) { - PREFIX *prefix; - const XML_Char *s; - for (s = elementType->name; s != name; s++) { - if (!poolAppendChar(&dtd->pool, *s)) - return 0; - } - if (!poolAppendChar(&dtd->pool, XML_T('\0'))) - return 0; - prefix = (PREFIX *)lookup(parser, &dtd->prefixes, poolStart(&dtd->pool), - sizeof(PREFIX)); - if (!prefix) - return 0; - if (prefix->name == poolStart(&dtd->pool)) - poolFinish(&dtd->pool); - else - poolDiscard(&dtd->pool); - elementType->prefix = prefix; - - } - } - return 1; -} - -static ATTRIBUTE_ID * -getAttributeId(XML_Parser parser, const ENCODING *enc, - const char *start, const char *end) -{ - DTD * const dtd = _dtd; /* save one level of indirection */ - ATTRIBUTE_ID *id; - const XML_Char *name; - if (!poolAppendChar(&dtd->pool, XML_T('\0'))) - return NULL; - name = poolStoreString(&dtd->pool, enc, start, end); - if (!name) - return NULL; - /* skip quotation mark - its storage will be re-used (like in name[-1]) */ - ++name; - id = (ATTRIBUTE_ID *)lookup(parser, &dtd->attributeIds, name, sizeof(ATTRIBUTE_ID)); - if (!id) - return NULL; - if (id->name != name) - poolDiscard(&dtd->pool); - else { - poolFinish(&dtd->pool); - if (!ns) - ; - else if (name[0] == XML_T(ASCII_x) - && name[1] == XML_T(ASCII_m) - && name[2] == XML_T(ASCII_l) - && name[3] == XML_T(ASCII_n) - && name[4] == XML_T(ASCII_s) - && (name[5] == XML_T('\0') || name[5] == XML_T(ASCII_COLON))) { - if (name[5] == XML_T('\0')) - id->prefix = &dtd->defaultPrefix; - else - id->prefix = (PREFIX *)lookup(parser, &dtd->prefixes, name + 6, sizeof(PREFIX)); - id->xmlns = XML_TRUE; - } - else { - int i; - for (i = 0; name[i]; i++) { - /* attributes without prefix are *not* in the default namespace */ - if (name[i] == XML_T(ASCII_COLON)) { - int j; - for (j = 0; j < i; j++) { - if (!poolAppendChar(&dtd->pool, name[j])) - return NULL; - } - if (!poolAppendChar(&dtd->pool, XML_T('\0'))) - return NULL; - id->prefix = (PREFIX *)lookup(parser, &dtd->prefixes, poolStart(&dtd->pool), - sizeof(PREFIX)); - if (!id->prefix) - return NULL; - if (id->prefix->name == poolStart(&dtd->pool)) - poolFinish(&dtd->pool); - else - poolDiscard(&dtd->pool); - break; - } - } - } - } - return id; -} - -#define CONTEXT_SEP XML_T(ASCII_FF) - -static const XML_Char * -getContext(XML_Parser parser) -{ - DTD * const dtd = _dtd; /* save one level of indirection */ - HASH_TABLE_ITER iter; - XML_Bool needSep = XML_FALSE; - - if (dtd->defaultPrefix.binding) { - int i; - int len; - if (!poolAppendChar(&tempPool, XML_T(ASCII_EQUALS))) - return NULL; - len = dtd->defaultPrefix.binding->uriLen; - if (namespaceSeparator) - len--; - for (i = 0; i < len; i++) - if (!poolAppendChar(&tempPool, dtd->defaultPrefix.binding->uri[i])) - return NULL; - needSep = XML_TRUE; - } - - hashTableIterInit(&iter, &(dtd->prefixes)); - for (;;) { - int i; - int len; - const XML_Char *s; - PREFIX *prefix = (PREFIX *)hashTableIterNext(&iter); - if (!prefix) - break; - if (!prefix->binding) - continue; - if (needSep && !poolAppendChar(&tempPool, CONTEXT_SEP)) - return NULL; - for (s = prefix->name; *s; s++) - if (!poolAppendChar(&tempPool, *s)) - return NULL; - if (!poolAppendChar(&tempPool, XML_T(ASCII_EQUALS))) - return NULL; - len = prefix->binding->uriLen; - if (namespaceSeparator) - len--; - for (i = 0; i < len; i++) - if (!poolAppendChar(&tempPool, prefix->binding->uri[i])) - return NULL; - needSep = XML_TRUE; - } - - - hashTableIterInit(&iter, &(dtd->generalEntities)); - for (;;) { - const XML_Char *s; - ENTITY *e = (ENTITY *)hashTableIterNext(&iter); - if (!e) - break; - if (!e->open) - continue; - if (needSep && !poolAppendChar(&tempPool, CONTEXT_SEP)) - return NULL; - for (s = e->name; *s; s++) - if (!poolAppendChar(&tempPool, *s)) - return 0; - needSep = XML_TRUE; - } - - if (!poolAppendChar(&tempPool, XML_T('\0'))) - return NULL; - return tempPool.start; -} - -static XML_Bool -setContext(XML_Parser parser, const XML_Char *context) -{ - DTD * const dtd = _dtd; /* save one level of indirection */ - const XML_Char *s = context; - - while (*context != XML_T('\0')) { - if (*s == CONTEXT_SEP || *s == XML_T('\0')) { - ENTITY *e; - if (!poolAppendChar(&tempPool, XML_T('\0'))) - return XML_FALSE; - e = (ENTITY *)lookup(parser, &dtd->generalEntities, poolStart(&tempPool), 0); - if (e) - e->open = XML_TRUE; - if (*s != XML_T('\0')) - s++; - context = s; - poolDiscard(&tempPool); - } - else if (*s == XML_T(ASCII_EQUALS)) { - PREFIX *prefix; - if (poolLength(&tempPool) == 0) - prefix = &dtd->defaultPrefix; - else { - if (!poolAppendChar(&tempPool, XML_T('\0'))) - return XML_FALSE; - prefix = (PREFIX *)lookup(parser, &dtd->prefixes, poolStart(&tempPool), - sizeof(PREFIX)); - if (!prefix) - return XML_FALSE; - if (prefix->name == poolStart(&tempPool)) { - prefix->name = poolCopyString(&dtd->pool, prefix->name); - if (!prefix->name) - return XML_FALSE; - } - poolDiscard(&tempPool); - } - for (context = s + 1; - *context != CONTEXT_SEP && *context != XML_T('\0'); - context++) - if (!poolAppendChar(&tempPool, *context)) - return XML_FALSE; - if (!poolAppendChar(&tempPool, XML_T('\0'))) - return XML_FALSE; - if (addBinding(parser, prefix, NULL, poolStart(&tempPool), - &inheritedBindings) != XML_ERROR_NONE) - return XML_FALSE; - poolDiscard(&tempPool); - if (*context != XML_T('\0')) - ++context; - s = context; - } - else { - if (!poolAppendChar(&tempPool, *s)) - return XML_FALSE; - s++; - } - } - return XML_TRUE; -} - -static void FASTCALL -normalizePublicId(XML_Char *publicId) -{ - XML_Char *p = publicId; - XML_Char *s; - for (s = publicId; *s; s++) { - switch (*s) { - case 0x20: - case 0xD: - case 0xA: - if (p != publicId && p[-1] != 0x20) - *p++ = 0x20; - break; - default: - *p++ = *s; - } - } - if (p != publicId && p[-1] == 0x20) - --p; - *p = XML_T('\0'); -} - -static DTD * -dtdCreate(const XML_Memory_Handling_Suite *ms) -{ - DTD *p = (DTD *)ms->malloc_fcn(sizeof(DTD)); - if (p == NULL) - return p; - poolInit(&(p->pool), ms); - poolInit(&(p->entityValuePool), ms); - hashTableInit(&(p->generalEntities), ms); - hashTableInit(&(p->elementTypes), ms); - hashTableInit(&(p->attributeIds), ms); - hashTableInit(&(p->prefixes), ms); -#ifdef XML_DTD - p->paramEntityRead = XML_FALSE; - hashTableInit(&(p->paramEntities), ms); -#endif /* XML_DTD */ - p->defaultPrefix.name = NULL; - p->defaultPrefix.binding = NULL; - - p->in_eldecl = XML_FALSE; - p->scaffIndex = NULL; - p->scaffold = NULL; - p->scaffLevel = 0; - p->scaffSize = 0; - p->scaffCount = 0; - p->contentStringLen = 0; - - p->keepProcessing = XML_TRUE; - p->hasParamEntityRefs = XML_FALSE; - p->standalone = XML_FALSE; - return p; -} - -static void -dtdReset(DTD *p, const XML_Memory_Handling_Suite *ms) -{ - HASH_TABLE_ITER iter; - hashTableIterInit(&iter, &(p->elementTypes)); - for (;;) { - ELEMENT_TYPE *e = (ELEMENT_TYPE *)hashTableIterNext(&iter); - if (!e) - break; - if (e->allocDefaultAtts != 0) - ms->free_fcn(e->defaultAtts); - } - hashTableClear(&(p->generalEntities)); -#ifdef XML_DTD - p->paramEntityRead = XML_FALSE; - hashTableClear(&(p->paramEntities)); -#endif /* XML_DTD */ - hashTableClear(&(p->elementTypes)); - hashTableClear(&(p->attributeIds)); - hashTableClear(&(p->prefixes)); - poolClear(&(p->pool)); - poolClear(&(p->entityValuePool)); - p->defaultPrefix.name = NULL; - p->defaultPrefix.binding = NULL; - - p->in_eldecl = XML_FALSE; - - ms->free_fcn(p->scaffIndex); - p->scaffIndex = NULL; - ms->free_fcn(p->scaffold); - p->scaffold = NULL; - - p->scaffLevel = 0; - p->scaffSize = 0; - p->scaffCount = 0; - p->contentStringLen = 0; - - p->keepProcessing = XML_TRUE; - p->hasParamEntityRefs = XML_FALSE; - p->standalone = XML_FALSE; -} - -static void -dtdDestroy(DTD *p, XML_Bool isDocEntity, const XML_Memory_Handling_Suite *ms) -{ - HASH_TABLE_ITER iter; - hashTableIterInit(&iter, &(p->elementTypes)); - for (;;) { - ELEMENT_TYPE *e = (ELEMENT_TYPE *)hashTableIterNext(&iter); - if (!e) - break; - if (e->allocDefaultAtts != 0) - ms->free_fcn(e->defaultAtts); - } - hashTableDestroy(&(p->generalEntities)); -#ifdef XML_DTD - hashTableDestroy(&(p->paramEntities)); -#endif /* XML_DTD */ - hashTableDestroy(&(p->elementTypes)); - hashTableDestroy(&(p->attributeIds)); - hashTableDestroy(&(p->prefixes)); - poolDestroy(&(p->pool)); - poolDestroy(&(p->entityValuePool)); - if (isDocEntity) { - ms->free_fcn(p->scaffIndex); - ms->free_fcn(p->scaffold); - } - ms->free_fcn(p); -} - -/* Do a deep copy of the DTD. Return 0 for out of memory, non-zero otherwise. - The new DTD has already been initialized. -*/ -static int -dtdCopy(XML_Parser oldParser, DTD *newDtd, const DTD *oldDtd, const XML_Memory_Handling_Suite *ms) -{ - HASH_TABLE_ITER iter; - - /* Copy the prefix table. */ - - hashTableIterInit(&iter, &(oldDtd->prefixes)); - for (;;) { - const XML_Char *name; - const PREFIX *oldP = (PREFIX *)hashTableIterNext(&iter); - if (!oldP) - break; - name = poolCopyString(&(newDtd->pool), oldP->name); - if (!name) - return 0; - if (!lookup(oldParser, &(newDtd->prefixes), name, sizeof(PREFIX))) - return 0; - } - - hashTableIterInit(&iter, &(oldDtd->attributeIds)); - - /* Copy the attribute id table. */ - - for (;;) { - ATTRIBUTE_ID *newA; - const XML_Char *name; - const ATTRIBUTE_ID *oldA = (ATTRIBUTE_ID *)hashTableIterNext(&iter); - - if (!oldA) - break; - /* Remember to allocate the scratch byte before the name. */ - if (!poolAppendChar(&(newDtd->pool), XML_T('\0'))) - return 0; - name = poolCopyString(&(newDtd->pool), oldA->name); - if (!name) - return 0; - ++name; - newA = (ATTRIBUTE_ID *)lookup(oldParser, &(newDtd->attributeIds), name, - sizeof(ATTRIBUTE_ID)); - if (!newA) - return 0; - newA->maybeTokenized = oldA->maybeTokenized; - if (oldA->prefix) { - newA->xmlns = oldA->xmlns; - if (oldA->prefix == &oldDtd->defaultPrefix) - newA->prefix = &newDtd->defaultPrefix; - else - newA->prefix = (PREFIX *)lookup(oldParser, &(newDtd->prefixes), - oldA->prefix->name, 0); - } - } - - /* Copy the element type table. */ - - hashTableIterInit(&iter, &(oldDtd->elementTypes)); - - for (;;) { - int i; - ELEMENT_TYPE *newE; - const XML_Char *name; - const ELEMENT_TYPE *oldE = (ELEMENT_TYPE *)hashTableIterNext(&iter); - if (!oldE) - break; - name = poolCopyString(&(newDtd->pool), oldE->name); - if (!name) - return 0; - newE = (ELEMENT_TYPE *)lookup(oldParser, &(newDtd->elementTypes), name, - sizeof(ELEMENT_TYPE)); - if (!newE) - return 0; - if (oldE->nDefaultAtts) { - newE->defaultAtts = (DEFAULT_ATTRIBUTE *) - ms->malloc_fcn(oldE->nDefaultAtts * sizeof(DEFAULT_ATTRIBUTE)); - if (!newE->defaultAtts) { - ms->free_fcn(newE); - return 0; - } - } - if (oldE->idAtt) - newE->idAtt = (ATTRIBUTE_ID *) - lookup(oldParser, &(newDtd->attributeIds), oldE->idAtt->name, 0); - newE->allocDefaultAtts = newE->nDefaultAtts = oldE->nDefaultAtts; - if (oldE->prefix) - newE->prefix = (PREFIX *)lookup(oldParser, &(newDtd->prefixes), - oldE->prefix->name, 0); - for (i = 0; i < newE->nDefaultAtts; i++) { - newE->defaultAtts[i].id = (ATTRIBUTE_ID *) - lookup(oldParser, &(newDtd->attributeIds), oldE->defaultAtts[i].id->name, 0); - newE->defaultAtts[i].isCdata = oldE->defaultAtts[i].isCdata; - if (oldE->defaultAtts[i].value) { - newE->defaultAtts[i].value - = poolCopyString(&(newDtd->pool), oldE->defaultAtts[i].value); - if (!newE->defaultAtts[i].value) - return 0; - } - else - newE->defaultAtts[i].value = NULL; - } - } - - /* Copy the entity tables. */ - if (!copyEntityTable(oldParser, - &(newDtd->generalEntities), - &(newDtd->pool), - &(oldDtd->generalEntities))) - return 0; - -#ifdef XML_DTD - if (!copyEntityTable(oldParser, - &(newDtd->paramEntities), - &(newDtd->pool), - &(oldDtd->paramEntities))) - return 0; - newDtd->paramEntityRead = oldDtd->paramEntityRead; -#endif /* XML_DTD */ - - newDtd->keepProcessing = oldDtd->keepProcessing; - newDtd->hasParamEntityRefs = oldDtd->hasParamEntityRefs; - newDtd->standalone = oldDtd->standalone; - - /* Don't want deep copying for scaffolding */ - newDtd->in_eldecl = oldDtd->in_eldecl; - newDtd->scaffold = oldDtd->scaffold; - newDtd->contentStringLen = oldDtd->contentStringLen; - newDtd->scaffSize = oldDtd->scaffSize; - newDtd->scaffLevel = oldDtd->scaffLevel; - newDtd->scaffIndex = oldDtd->scaffIndex; - - return 1; -} /* End dtdCopy */ - -static int -copyEntityTable(XML_Parser oldParser, - HASH_TABLE *newTable, - STRING_POOL *newPool, - const HASH_TABLE *oldTable) -{ - HASH_TABLE_ITER iter; - const XML_Char *cachedOldBase = NULL; - const XML_Char *cachedNewBase = NULL; - - hashTableIterInit(&iter, oldTable); - - for (;;) { - ENTITY *newE; - const XML_Char *name; - const ENTITY *oldE = (ENTITY *)hashTableIterNext(&iter); - if (!oldE) - break; - name = poolCopyString(newPool, oldE->name); - if (!name) - return 0; - newE = (ENTITY *)lookup(oldParser, newTable, name, sizeof(ENTITY)); - if (!newE) - return 0; - if (oldE->systemId) { - const XML_Char *tem = poolCopyString(newPool, oldE->systemId); - if (!tem) - return 0; - newE->systemId = tem; - if (oldE->base) { - if (oldE->base == cachedOldBase) - newE->base = cachedNewBase; - else { - cachedOldBase = oldE->base; - tem = poolCopyString(newPool, cachedOldBase); - if (!tem) - return 0; - cachedNewBase = newE->base = tem; - } - } - if (oldE->publicId) { - tem = poolCopyString(newPool, oldE->publicId); - if (!tem) - return 0; - newE->publicId = tem; - } - } - else { - const XML_Char *tem = poolCopyStringN(newPool, oldE->textPtr, - oldE->textLen); - if (!tem) - return 0; - newE->textPtr = tem; - newE->textLen = oldE->textLen; - } - if (oldE->notation) { - const XML_Char *tem = poolCopyString(newPool, oldE->notation); - if (!tem) - return 0; - newE->notation = tem; - } - newE->is_param = oldE->is_param; - newE->is_internal = oldE->is_internal; - } - return 1; -} - -#define INIT_POWER 6 - -static XML_Bool FASTCALL -keyeq(KEY s1, KEY s2) -{ - for (; *s1 == *s2; s1++, s2++) - if (*s1 == 0) - return XML_TRUE; - return XML_FALSE; -} - -static unsigned long FASTCALL -hash(XML_Parser parser, KEY s) -{ - unsigned long h = hash_secret_salt; - while (*s) - h = CHAR_HASH(h, *s++); - return h; -} - -static NAMED * -lookup(XML_Parser parser, HASH_TABLE *table, KEY name, size_t createSize) -{ - size_t i; - if (table->size == 0) { - size_t tsize; - if (!createSize) - return NULL; - table->power = INIT_POWER; - /* table->size is a power of 2 */ - table->size = (size_t)1 << INIT_POWER; - tsize = table->size * sizeof(NAMED *); - table->v = (NAMED **)table->mem->malloc_fcn(tsize); - if (!table->v) { - table->size = 0; - return NULL; - } - memset(table->v, 0, tsize); - i = hash(parser, name) & ((unsigned long)table->size - 1); - } - else { - unsigned long h = hash(parser, name); - unsigned long mask = (unsigned long)table->size - 1; - unsigned char step = 0; - i = h & mask; - while (table->v[i]) { - if (keyeq(name, table->v[i]->name)) - return table->v[i]; - if (!step) - step = PROBE_STEP(h, mask, table->power); - i < step ? (i += table->size - step) : (i -= step); - } - if (!createSize) - return NULL; - - /* check for overflow (table is half full) */ - if (table->used >> (table->power - 1)) { - unsigned char newPower = table->power + 1; - size_t newSize = (size_t)1 << newPower; - unsigned long newMask = (unsigned long)newSize - 1; - size_t tsize = newSize * sizeof(NAMED *); - NAMED **newV = (NAMED **)table->mem->malloc_fcn(tsize); - if (!newV) - return NULL; - memset(newV, 0, tsize); - for (i = 0; i < table->size; i++) - if (table->v[i]) { - unsigned long newHash = hash(parser, table->v[i]->name); - size_t j = newHash & newMask; - step = 0; - while (newV[j]) { - if (!step) - step = PROBE_STEP(newHash, newMask, newPower); - j < step ? (j += newSize - step) : (j -= step); - } - newV[j] = table->v[i]; - } - table->mem->free_fcn(table->v); - table->v = newV; - table->power = newPower; - table->size = newSize; - i = h & newMask; - step = 0; - while (table->v[i]) { - if (!step) - step = PROBE_STEP(h, newMask, newPower); - i < step ? (i += newSize - step) : (i -= step); - } - } - } - table->v[i] = (NAMED *)table->mem->malloc_fcn(createSize); - if (!table->v[i]) - return NULL; - memset(table->v[i], 0, createSize); - table->v[i]->name = name; - (table->used)++; - return table->v[i]; -} - -static void FASTCALL -hashTableClear(HASH_TABLE *table) -{ - size_t i; - for (i = 0; i < table->size; i++) { - table->mem->free_fcn(table->v[i]); - table->v[i] = NULL; - } - table->used = 0; -} - -static void FASTCALL -hashTableDestroy(HASH_TABLE *table) -{ - size_t i; - for (i = 0; i < table->size; i++) - table->mem->free_fcn(table->v[i]); - table->mem->free_fcn(table->v); -} - -static void FASTCALL -hashTableInit(HASH_TABLE *p, const XML_Memory_Handling_Suite *ms) -{ - p->power = 0; - p->size = 0; - p->used = 0; - p->v = NULL; - p->mem = ms; -} - -static void FASTCALL -hashTableIterInit(HASH_TABLE_ITER *iter, const HASH_TABLE *table) -{ - iter->p = table->v; - iter->end = iter->p + table->size; -} - -static NAMED * FASTCALL -hashTableIterNext(HASH_TABLE_ITER *iter) -{ - while (iter->p != iter->end) { - NAMED *tem = *(iter->p)++; - if (tem) - return tem; - } - return NULL; -} - -static void FASTCALL -poolInit(STRING_POOL *pool, const XML_Memory_Handling_Suite *ms) -{ - pool->blocks = NULL; - pool->freeBlocks = NULL; - pool->start = NULL; - pool->ptr = NULL; - pool->end = NULL; - pool->mem = ms; -} - -static void FASTCALL -poolClear(STRING_POOL *pool) -{ - if (!pool->freeBlocks) - pool->freeBlocks = pool->blocks; - else { - BLOCK *p = pool->blocks; - while (p) { - BLOCK *tem = p->next; - p->next = pool->freeBlocks; - pool->freeBlocks = p; - p = tem; - } - } - pool->blocks = NULL; - pool->start = NULL; - pool->ptr = NULL; - pool->end = NULL; -} - -static void FASTCALL -poolDestroy(STRING_POOL *pool) -{ - BLOCK *p = pool->blocks; - while (p) { - BLOCK *tem = p->next; - pool->mem->free_fcn(p); - p = tem; - } - p = pool->freeBlocks; - while (p) { - BLOCK *tem = p->next; - pool->mem->free_fcn(p); - p = tem; - } -} - -static XML_Char * -poolAppend(STRING_POOL *pool, const ENCODING *enc, - const char *ptr, const char *end) -{ - if (!pool->ptr && !poolGrow(pool)) - return NULL; - for (;;) { - const enum XML_Convert_Result convert_res = XmlConvert(enc, &ptr, end, (ICHAR **)&(pool->ptr), (ICHAR *)pool->end); - if ((convert_res == XML_CONVERT_COMPLETED) || (convert_res == XML_CONVERT_INPUT_INCOMPLETE)) - break; - if (!poolGrow(pool)) - return NULL; - } - return pool->start; -} - -static const XML_Char * FASTCALL -poolCopyString(STRING_POOL *pool, const XML_Char *s) -{ - do { - if (!poolAppendChar(pool, *s)) - return NULL; - } while (*s++); - s = pool->start; - poolFinish(pool); - return s; -} - -static const XML_Char * -poolCopyStringN(STRING_POOL *pool, const XML_Char *s, int n) -{ - if (!pool->ptr && !poolGrow(pool)) - return NULL; - for (; n > 0; --n, s++) { - if (!poolAppendChar(pool, *s)) - return NULL; - } - s = pool->start; - poolFinish(pool); - return s; -} - -static const XML_Char * FASTCALL -poolAppendString(STRING_POOL *pool, const XML_Char *s) -{ - while (*s) { - if (!poolAppendChar(pool, *s)) - return NULL; - s++; - } - return pool->start; -} - -static XML_Char * -poolStoreString(STRING_POOL *pool, const ENCODING *enc, - const char *ptr, const char *end) -{ - if (!poolAppend(pool, enc, ptr, end)) - return NULL; - if (pool->ptr == pool->end && !poolGrow(pool)) - return NULL; - *(pool->ptr)++ = 0; - return pool->start; -} - -static XML_Bool FASTCALL -poolGrow(STRING_POOL *pool) -{ - if (pool->freeBlocks) { - if (pool->start == 0) { - pool->blocks = pool->freeBlocks; - pool->freeBlocks = pool->freeBlocks->next; - pool->blocks->next = NULL; - pool->start = pool->blocks->s; - pool->end = pool->start + pool->blocks->size; - pool->ptr = pool->start; - return XML_TRUE; - } - if (pool->end - pool->start < pool->freeBlocks->size) { - BLOCK *tem = pool->freeBlocks->next; - pool->freeBlocks->next = pool->blocks; - pool->blocks = pool->freeBlocks; - pool->freeBlocks = tem; - memcpy(pool->blocks->s, pool->start, - (pool->end - pool->start) * sizeof(XML_Char)); - pool->ptr = pool->blocks->s + (pool->ptr - pool->start); - pool->start = pool->blocks->s; - pool->end = pool->start + pool->blocks->size; - return XML_TRUE; - } - } - if (pool->blocks && pool->start == pool->blocks->s) { - BLOCK *temp; - int blockSize = (int)((unsigned)(pool->end - pool->start)*2U); - - if (blockSize < 0) - return XML_FALSE; - - temp = (BLOCK *) - pool->mem->realloc_fcn(pool->blocks, - (offsetof(BLOCK, s) - + blockSize * sizeof(XML_Char))); - if (temp == NULL) - return XML_FALSE; - pool->blocks = temp; - pool->blocks->size = blockSize; - pool->ptr = pool->blocks->s + (pool->ptr - pool->start); - pool->start = pool->blocks->s; - pool->end = pool->start + blockSize; - } - else { - BLOCK *tem; - int blockSize = (int)(pool->end - pool->start); - - if (blockSize < 0) - return XML_FALSE; - - if (blockSize < INIT_BLOCK_SIZE) - blockSize = INIT_BLOCK_SIZE; - else - blockSize *= 2; - tem = (BLOCK *)pool->mem->malloc_fcn(offsetof(BLOCK, s) - + blockSize * sizeof(XML_Char)); - if (!tem) - return XML_FALSE; - tem->size = blockSize; - tem->next = pool->blocks; - pool->blocks = tem; - if (pool->ptr != pool->start) - memcpy(tem->s, pool->start, - (pool->ptr - pool->start) * sizeof(XML_Char)); - pool->ptr = tem->s + (pool->ptr - pool->start); - pool->start = tem->s; - pool->end = tem->s + blockSize; - } - return XML_TRUE; -} - -static int FASTCALL -nextScaffoldPart(XML_Parser parser) -{ - DTD * const dtd = _dtd; /* save one level of indirection */ - CONTENT_SCAFFOLD * me; - int next; - - if (!dtd->scaffIndex) { - dtd->scaffIndex = (int *)MALLOC(groupSize * sizeof(int)); - if (!dtd->scaffIndex) - return -1; - dtd->scaffIndex[0] = 0; - } - - if (dtd->scaffCount >= dtd->scaffSize) { - CONTENT_SCAFFOLD *temp; - if (dtd->scaffold) { - temp = (CONTENT_SCAFFOLD *) - REALLOC(dtd->scaffold, dtd->scaffSize * 2 * sizeof(CONTENT_SCAFFOLD)); - if (temp == NULL) - return -1; - dtd->scaffSize *= 2; - } - else { - temp = (CONTENT_SCAFFOLD *)MALLOC(INIT_SCAFFOLD_ELEMENTS - * sizeof(CONTENT_SCAFFOLD)); - if (temp == NULL) - return -1; - dtd->scaffSize = INIT_SCAFFOLD_ELEMENTS; - } - dtd->scaffold = temp; - } - next = dtd->scaffCount++; - me = &dtd->scaffold[next]; - if (dtd->scaffLevel) { - CONTENT_SCAFFOLD *parent = &dtd->scaffold[dtd->scaffIndex[dtd->scaffLevel-1]]; - if (parent->lastchild) { - dtd->scaffold[parent->lastchild].nextsib = next; - } - if (!parent->childcnt) - parent->firstchild = next; - parent->lastchild = next; - parent->childcnt++; - } - me->firstchild = me->lastchild = me->childcnt = me->nextsib = 0; - return next; -} - -static void -build_node(XML_Parser parser, - int src_node, - XML_Content *dest, - XML_Content **contpos, - XML_Char **strpos) -{ - DTD * const dtd = _dtd; /* save one level of indirection */ - dest->type = dtd->scaffold[src_node].type; - dest->quant = dtd->scaffold[src_node].quant; - if (dest->type == XML_CTYPE_NAME) { - const XML_Char *src; - dest->name = *strpos; - src = dtd->scaffold[src_node].name; - for (;;) { - *(*strpos)++ = *src; - if (!*src) - break; - src++; - } - dest->numchildren = 0; - dest->children = NULL; - } - else { - unsigned int i; - int cn; - dest->numchildren = dtd->scaffold[src_node].childcnt; - dest->children = *contpos; - *contpos += dest->numchildren; - for (i = 0, cn = dtd->scaffold[src_node].firstchild; - i < dest->numchildren; - i++, cn = dtd->scaffold[cn].nextsib) { - build_node(parser, cn, &(dest->children[i]), contpos, strpos); - } - dest->name = NULL; - } -} - -static XML_Content * -build_model (XML_Parser parser) -{ - DTD * const dtd = _dtd; /* save one level of indirection */ - XML_Content *ret; - XML_Content *cpos; - XML_Char * str; - int allocsize = (dtd->scaffCount * sizeof(XML_Content) - + (dtd->contentStringLen * sizeof(XML_Char))); - - ret = (XML_Content *)MALLOC(allocsize); - if (!ret) - return NULL; - - str = (XML_Char *) (&ret[dtd->scaffCount]); - cpos = &ret[1]; - - build_node(parser, 0, ret, &cpos, &str); - return ret; -} - -static ELEMENT_TYPE * -getElementType(XML_Parser parser, - const ENCODING *enc, - const char *ptr, - const char *end) -{ - DTD * const dtd = _dtd; /* save one level of indirection */ - const XML_Char *name = poolStoreString(&dtd->pool, enc, ptr, end); - ELEMENT_TYPE *ret; - - if (!name) - return NULL; - ret = (ELEMENT_TYPE *) lookup(parser, &dtd->elementTypes, name, sizeof(ELEMENT_TYPE)); - if (!ret) - return NULL; - if (ret->name != name) - poolDiscard(&dtd->pool); - else { - poolFinish(&dtd->pool); - if (!setElementTypePrefix(parser, ret)) - return NULL; - } - return ret; -} diff --git a/chromium/third_party/expat/files/lib/xmlrole.c b/chromium/third_party/expat/files/lib/xmlrole.c index fcd0dc6948f..4d3e3e86e9e 100644 --- a/chromium/third_party/expat/files/lib/xmlrole.c +++ b/chromium/third_party/expat/files/lib/xmlrole.c @@ -1,22 +1,44 @@ -/* Copyright (c) 1998, 1999 Thai Open Source Software Center Ltd - See the file COPYING for copying permission. +/* + __ __ _ + ___\ \/ /_ __ __ _| |_ + / _ \\ /| '_ \ / _` | __| + | __// \| |_) | (_| | |_ + \___/_/\_\ .__/ \__,_|\__| + |_| XML parser + + Copyright (c) 1997-2000 Thai Open Source Software Center Ltd + Copyright (c) 2000-2017 Expat development team + Licensed under the MIT license: + + Permission is hereby granted, free of charge, to any person obtaining + a copy of this software and associated documentation files (the + "Software"), to deal in the Software without restriction, including + without limitation the rights to use, copy, modify, merge, publish, + distribute, sublicense, and/or sell copies of the Software, and to permit + persons to whom the Software is furnished to do so, subject to the + following conditions: + + The above copyright notice and this permission notice shall be included + in all copies or substantial portions of the Software. + + THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN + NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, + DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR + OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE + USE OR OTHER DEALINGS IN THE SOFTWARE. */ #include <stddef.h> -#ifdef WIN32 -#include "winconfig.h" -#elif defined(MACOS_CLASSIC) -#include "macconfig.h" -#elif defined(__amigaos__) -#include "amigaconfig.h" -#elif defined(__WATCOMC__) -#include "watcomconfig.h" +#ifdef _WIN32 +# include "winconfig.h" #else -#ifdef HAVE_EXPAT_CONFIG_H -#include <expat_config.h> -#endif -#endif /* ndef WIN32 */ +# ifdef HAVE_EXPAT_CONFIG_H +# include <expat_config.h> +# endif +#endif /* ndef _WIN32 */ #include "expat_external.h" #include "internal.h" @@ -30,107 +52,88 @@ */ -static const char KW_ANY[] = { - ASCII_A, ASCII_N, ASCII_Y, '\0' }; -static const char KW_ATTLIST[] = { - ASCII_A, ASCII_T, ASCII_T, ASCII_L, ASCII_I, ASCII_S, ASCII_T, '\0' }; -static const char KW_CDATA[] = { - ASCII_C, ASCII_D, ASCII_A, ASCII_T, ASCII_A, '\0' }; -static const char KW_DOCTYPE[] = { - ASCII_D, ASCII_O, ASCII_C, ASCII_T, ASCII_Y, ASCII_P, ASCII_E, '\0' }; -static const char KW_ELEMENT[] = { - ASCII_E, ASCII_L, ASCII_E, ASCII_M, ASCII_E, ASCII_N, ASCII_T, '\0' }; -static const char KW_EMPTY[] = { - ASCII_E, ASCII_M, ASCII_P, ASCII_T, ASCII_Y, '\0' }; -static const char KW_ENTITIES[] = { - ASCII_E, ASCII_N, ASCII_T, ASCII_I, ASCII_T, ASCII_I, ASCII_E, ASCII_S, - '\0' }; -static const char KW_ENTITY[] = { - ASCII_E, ASCII_N, ASCII_T, ASCII_I, ASCII_T, ASCII_Y, '\0' }; -static const char KW_FIXED[] = { - ASCII_F, ASCII_I, ASCII_X, ASCII_E, ASCII_D, '\0' }; -static const char KW_ID[] = { - ASCII_I, ASCII_D, '\0' }; -static const char KW_IDREF[] = { - ASCII_I, ASCII_D, ASCII_R, ASCII_E, ASCII_F, '\0' }; -static const char KW_IDREFS[] = { - ASCII_I, ASCII_D, ASCII_R, ASCII_E, ASCII_F, ASCII_S, '\0' }; +static const char KW_ANY[] = {ASCII_A, ASCII_N, ASCII_Y, '\0'}; +static const char KW_ATTLIST[] + = {ASCII_A, ASCII_T, ASCII_T, ASCII_L, ASCII_I, ASCII_S, ASCII_T, '\0'}; +static const char KW_CDATA[] + = {ASCII_C, ASCII_D, ASCII_A, ASCII_T, ASCII_A, '\0'}; +static const char KW_DOCTYPE[] + = {ASCII_D, ASCII_O, ASCII_C, ASCII_T, ASCII_Y, ASCII_P, ASCII_E, '\0'}; +static const char KW_ELEMENT[] + = {ASCII_E, ASCII_L, ASCII_E, ASCII_M, ASCII_E, ASCII_N, ASCII_T, '\0'}; +static const char KW_EMPTY[] + = {ASCII_E, ASCII_M, ASCII_P, ASCII_T, ASCII_Y, '\0'}; +static const char KW_ENTITIES[] = {ASCII_E, ASCII_N, ASCII_T, ASCII_I, ASCII_T, + ASCII_I, ASCII_E, ASCII_S, '\0'}; +static const char KW_ENTITY[] + = {ASCII_E, ASCII_N, ASCII_T, ASCII_I, ASCII_T, ASCII_Y, '\0'}; +static const char KW_FIXED[] + = {ASCII_F, ASCII_I, ASCII_X, ASCII_E, ASCII_D, '\0'}; +static const char KW_ID[] = {ASCII_I, ASCII_D, '\0'}; +static const char KW_IDREF[] + = {ASCII_I, ASCII_D, ASCII_R, ASCII_E, ASCII_F, '\0'}; +static const char KW_IDREFS[] + = {ASCII_I, ASCII_D, ASCII_R, ASCII_E, ASCII_F, ASCII_S, '\0'}; #ifdef XML_DTD -static const char KW_IGNORE[] = { - ASCII_I, ASCII_G, ASCII_N, ASCII_O, ASCII_R, ASCII_E, '\0' }; +static const char KW_IGNORE[] + = {ASCII_I, ASCII_G, ASCII_N, ASCII_O, ASCII_R, ASCII_E, '\0'}; #endif -static const char KW_IMPLIED[] = { - ASCII_I, ASCII_M, ASCII_P, ASCII_L, ASCII_I, ASCII_E, ASCII_D, '\0' }; +static const char KW_IMPLIED[] + = {ASCII_I, ASCII_M, ASCII_P, ASCII_L, ASCII_I, ASCII_E, ASCII_D, '\0'}; #ifdef XML_DTD -static const char KW_INCLUDE[] = { - ASCII_I, ASCII_N, ASCII_C, ASCII_L, ASCII_U, ASCII_D, ASCII_E, '\0' }; +static const char KW_INCLUDE[] + = {ASCII_I, ASCII_N, ASCII_C, ASCII_L, ASCII_U, ASCII_D, ASCII_E, '\0'}; #endif -static const char KW_NDATA[] = { - ASCII_N, ASCII_D, ASCII_A, ASCII_T, ASCII_A, '\0' }; -static const char KW_NMTOKEN[] = { - ASCII_N, ASCII_M, ASCII_T, ASCII_O, ASCII_K, ASCII_E, ASCII_N, '\0' }; -static const char KW_NMTOKENS[] = { - ASCII_N, ASCII_M, ASCII_T, ASCII_O, ASCII_K, ASCII_E, ASCII_N, ASCII_S, - '\0' }; -static const char KW_NOTATION[] = - { ASCII_N, ASCII_O, ASCII_T, ASCII_A, ASCII_T, ASCII_I, ASCII_O, ASCII_N, - '\0' }; -static const char KW_PCDATA[] = { - ASCII_P, ASCII_C, ASCII_D, ASCII_A, ASCII_T, ASCII_A, '\0' }; -static const char KW_PUBLIC[] = { - ASCII_P, ASCII_U, ASCII_B, ASCII_L, ASCII_I, ASCII_C, '\0' }; -static const char KW_REQUIRED[] = { - ASCII_R, ASCII_E, ASCII_Q, ASCII_U, ASCII_I, ASCII_R, ASCII_E, ASCII_D, - '\0' }; -static const char KW_SYSTEM[] = { - ASCII_S, ASCII_Y, ASCII_S, ASCII_T, ASCII_E, ASCII_M, '\0' }; +static const char KW_NDATA[] + = {ASCII_N, ASCII_D, ASCII_A, ASCII_T, ASCII_A, '\0'}; +static const char KW_NMTOKEN[] + = {ASCII_N, ASCII_M, ASCII_T, ASCII_O, ASCII_K, ASCII_E, ASCII_N, '\0'}; +static const char KW_NMTOKENS[] = {ASCII_N, ASCII_M, ASCII_T, ASCII_O, ASCII_K, + ASCII_E, ASCII_N, ASCII_S, '\0'}; +static const char KW_NOTATION[] = {ASCII_N, ASCII_O, ASCII_T, ASCII_A, ASCII_T, + ASCII_I, ASCII_O, ASCII_N, '\0'}; +static const char KW_PCDATA[] + = {ASCII_P, ASCII_C, ASCII_D, ASCII_A, ASCII_T, ASCII_A, '\0'}; +static const char KW_PUBLIC[] + = {ASCII_P, ASCII_U, ASCII_B, ASCII_L, ASCII_I, ASCII_C, '\0'}; +static const char KW_REQUIRED[] = {ASCII_R, ASCII_E, ASCII_Q, ASCII_U, ASCII_I, + ASCII_R, ASCII_E, ASCII_D, '\0'}; +static const char KW_SYSTEM[] + = {ASCII_S, ASCII_Y, ASCII_S, ASCII_T, ASCII_E, ASCII_M, '\0'}; #ifndef MIN_BYTES_PER_CHAR -#define MIN_BYTES_PER_CHAR(enc) ((enc)->minBytesPerChar) +# define MIN_BYTES_PER_CHAR(enc) ((enc)->minBytesPerChar) #endif #ifdef XML_DTD -#define setTopLevel(state) \ - ((state)->handler = ((state)->documentEntity \ - ? internalSubset \ - : externalSubset1)) +# define setTopLevel(state) \ + ((state)->handler \ + = ((state)->documentEntity ? internalSubset : externalSubset1)) #else /* not XML_DTD */ -#define setTopLevel(state) ((state)->handler = internalSubset) +# define setTopLevel(state) ((state)->handler = internalSubset) #endif /* not XML_DTD */ -typedef int PTRCALL PROLOG_HANDLER(PROLOG_STATE *state, - int tok, - const char *ptr, - const char *end, +typedef int PTRCALL PROLOG_HANDLER(PROLOG_STATE *state, int tok, + const char *ptr, const char *end, const ENCODING *enc); -static PROLOG_HANDLER - prolog0, prolog1, prolog2, - doctype0, doctype1, doctype2, doctype3, doctype4, doctype5, - internalSubset, - entity0, entity1, entity2, entity3, entity4, entity5, entity6, - entity7, entity8, entity9, entity10, - notation0, notation1, notation2, notation3, notation4, - attlist0, attlist1, attlist2, attlist3, attlist4, attlist5, attlist6, - attlist7, attlist8, attlist9, - element0, element1, element2, element3, element4, element5, element6, - element7, +static PROLOG_HANDLER prolog0, prolog1, prolog2, doctype0, doctype1, doctype2, + doctype3, doctype4, doctype5, internalSubset, entity0, entity1, entity2, + entity3, entity4, entity5, entity6, entity7, entity8, entity9, entity10, + notation0, notation1, notation2, notation3, notation4, attlist0, attlist1, + attlist2, attlist3, attlist4, attlist5, attlist6, attlist7, attlist8, + attlist9, element0, element1, element2, element3, element4, element5, + element6, element7, #ifdef XML_DTD - externalSubset0, externalSubset1, - condSect0, condSect1, condSect2, + externalSubset0, externalSubset1, condSect0, condSect1, condSect2, #endif /* XML_DTD */ - declClose, - error; + declClose, error; static int FASTCALL common(PROLOG_STATE *state, int tok); static int PTRCALL -prolog0(PROLOG_STATE *state, - int tok, - const char *ptr, - const char *end, - const ENCODING *enc) -{ +prolog0(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { switch (tok) { case XML_TOK_PROLOG_S: state->handler = prolog1; @@ -147,10 +150,8 @@ prolog0(PROLOG_STATE *state, case XML_TOK_BOM: return XML_ROLE_NONE; case XML_TOK_DECL_OPEN: - if (!XmlNameMatchesAscii(enc, - ptr + 2 * MIN_BYTES_PER_CHAR(enc), - end, - KW_DOCTYPE)) + if (! XmlNameMatchesAscii(enc, ptr + 2 * MIN_BYTES_PER_CHAR(enc), end, + KW_DOCTYPE)) break; state->handler = doctype0; return XML_ROLE_DOCTYPE_NONE; @@ -162,12 +163,8 @@ prolog0(PROLOG_STATE *state, } static int PTRCALL -prolog1(PROLOG_STATE *state, - int tok, - const char *ptr, - const char *end, - const ENCODING *enc) -{ +prolog1(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { switch (tok) { case XML_TOK_PROLOG_S: return XML_ROLE_NONE; @@ -176,12 +173,17 @@ prolog1(PROLOG_STATE *state, case XML_TOK_COMMENT: return XML_ROLE_COMMENT; case XML_TOK_BOM: - return XML_ROLE_NONE; + /* This case can never arise. To reach this role function, the + * parse must have passed through prolog0 and therefore have had + * some form of input, even if only a space. At that point, a + * byte order mark is no longer a valid character (though + * technically it should be interpreted as a non-breaking space), + * so will be rejected by the tokenizing stages. + */ + return XML_ROLE_NONE; /* LCOV_EXCL_LINE */ case XML_TOK_DECL_OPEN: - if (!XmlNameMatchesAscii(enc, - ptr + 2 * MIN_BYTES_PER_CHAR(enc), - end, - KW_DOCTYPE)) + if (! XmlNameMatchesAscii(enc, ptr + 2 * MIN_BYTES_PER_CHAR(enc), end, + KW_DOCTYPE)) break; state->handler = doctype0; return XML_ROLE_DOCTYPE_NONE; @@ -193,12 +195,11 @@ prolog1(PROLOG_STATE *state, } static int PTRCALL -prolog2(PROLOG_STATE *state, - int tok, - const char *UNUSED_P(ptr), - const char *UNUSED_P(end), - const ENCODING *UNUSED_P(enc)) -{ +prolog2(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { + UNUSED_P(ptr); + UNUSED_P(end); + UNUSED_P(enc); switch (tok) { case XML_TOK_PROLOG_S: return XML_ROLE_NONE; @@ -214,12 +215,11 @@ prolog2(PROLOG_STATE *state, } static int PTRCALL -doctype0(PROLOG_STATE *state, - int tok, - const char *UNUSED_P(ptr), - const char *UNUSED_P(end), - const ENCODING *UNUSED_P(enc)) -{ +doctype0(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { + UNUSED_P(ptr); + UNUSED_P(end); + UNUSED_P(enc); switch (tok) { case XML_TOK_PROLOG_S: return XML_ROLE_DOCTYPE_NONE; @@ -232,12 +232,8 @@ doctype0(PROLOG_STATE *state, } static int PTRCALL -doctype1(PROLOG_STATE *state, - int tok, - const char *ptr, - const char *end, - const ENCODING *enc) -{ +doctype1(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { switch (tok) { case XML_TOK_PROLOG_S: return XML_ROLE_DOCTYPE_NONE; @@ -262,12 +258,11 @@ doctype1(PROLOG_STATE *state, } static int PTRCALL -doctype2(PROLOG_STATE *state, - int tok, - const char *UNUSED_P(ptr), - const char *UNUSED_P(end), - const ENCODING *UNUSED_P(enc)) -{ +doctype2(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { + UNUSED_P(ptr); + UNUSED_P(end); + UNUSED_P(enc); switch (tok) { case XML_TOK_PROLOG_S: return XML_ROLE_DOCTYPE_NONE; @@ -279,12 +274,11 @@ doctype2(PROLOG_STATE *state, } static int PTRCALL -doctype3(PROLOG_STATE *state, - int tok, - const char *UNUSED_P(ptr), - const char *UNUSED_P(end), - const ENCODING *UNUSED_P(enc)) -{ +doctype3(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { + UNUSED_P(ptr); + UNUSED_P(end); + UNUSED_P(enc); switch (tok) { case XML_TOK_PROLOG_S: return XML_ROLE_DOCTYPE_NONE; @@ -296,12 +290,11 @@ doctype3(PROLOG_STATE *state, } static int PTRCALL -doctype4(PROLOG_STATE *state, - int tok, - const char *UNUSED_P(ptr), - const char *UNUSED_P(end), - const ENCODING *UNUSED_P(enc)) -{ +doctype4(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { + UNUSED_P(ptr); + UNUSED_P(end); + UNUSED_P(enc); switch (tok) { case XML_TOK_PROLOG_S: return XML_ROLE_DOCTYPE_NONE; @@ -316,12 +309,11 @@ doctype4(PROLOG_STATE *state, } static int PTRCALL -doctype5(PROLOG_STATE *state, - int tok, - const char *UNUSED_P(ptr), - const char *UNUSED_P(end), - const ENCODING *UNUSED_P(enc)) -{ +doctype5(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { + UNUSED_P(ptr); + UNUSED_P(end); + UNUSED_P(enc); switch (tok) { case XML_TOK_PROLOG_S: return XML_ROLE_DOCTYPE_NONE; @@ -333,40 +325,28 @@ doctype5(PROLOG_STATE *state, } static int PTRCALL -internalSubset(PROLOG_STATE *state, - int tok, - const char *ptr, - const char *end, - const ENCODING *enc) -{ +internalSubset(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { switch (tok) { case XML_TOK_PROLOG_S: return XML_ROLE_NONE; case XML_TOK_DECL_OPEN: - if (XmlNameMatchesAscii(enc, - ptr + 2 * MIN_BYTES_PER_CHAR(enc), - end, + if (XmlNameMatchesAscii(enc, ptr + 2 * MIN_BYTES_PER_CHAR(enc), end, KW_ENTITY)) { state->handler = entity0; return XML_ROLE_ENTITY_NONE; } - if (XmlNameMatchesAscii(enc, - ptr + 2 * MIN_BYTES_PER_CHAR(enc), - end, + if (XmlNameMatchesAscii(enc, ptr + 2 * MIN_BYTES_PER_CHAR(enc), end, KW_ATTLIST)) { state->handler = attlist0; return XML_ROLE_ATTLIST_NONE; } - if (XmlNameMatchesAscii(enc, - ptr + 2 * MIN_BYTES_PER_CHAR(enc), - end, + if (XmlNameMatchesAscii(enc, ptr + 2 * MIN_BYTES_PER_CHAR(enc), end, KW_ELEMENT)) { state->handler = element0; return XML_ROLE_ELEMENT_NONE; } - if (XmlNameMatchesAscii(enc, - ptr + 2 * MIN_BYTES_PER_CHAR(enc), - end, + if (XmlNameMatchesAscii(enc, ptr + 2 * MIN_BYTES_PER_CHAR(enc), end, KW_NOTATION)) { state->handler = notation0; return XML_ROLE_NOTATION_NONE; @@ -390,12 +370,8 @@ internalSubset(PROLOG_STATE *state, #ifdef XML_DTD static int PTRCALL -externalSubset0(PROLOG_STATE *state, - int tok, - const char *ptr, - const char *end, - const ENCODING *enc) -{ +externalSubset0(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { state->handler = externalSubset1; if (tok == XML_TOK_XML_DECL) return XML_ROLE_TEXT_DECL; @@ -403,12 +379,8 @@ externalSubset0(PROLOG_STATE *state, } static int PTRCALL -externalSubset1(PROLOG_STATE *state, - int tok, - const char *ptr, - const char *end, - const ENCODING *enc) -{ +externalSubset1(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { switch (tok) { case XML_TOK_COND_SECT_OPEN: state->handler = condSect0; @@ -435,12 +407,11 @@ externalSubset1(PROLOG_STATE *state, #endif /* XML_DTD */ static int PTRCALL -entity0(PROLOG_STATE *state, - int tok, - const char *UNUSED_P(ptr), - const char *UNUSED_P(end), - const ENCODING *UNUSED_P(enc)) -{ +entity0(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { + UNUSED_P(ptr); + UNUSED_P(end); + UNUSED_P(enc); switch (tok) { case XML_TOK_PROLOG_S: return XML_ROLE_ENTITY_NONE; @@ -455,12 +426,11 @@ entity0(PROLOG_STATE *state, } static int PTRCALL -entity1(PROLOG_STATE *state, - int tok, - const char *UNUSED_P(ptr), - const char *UNUSED_P(end), - const ENCODING *UNUSED_P(enc)) -{ +entity1(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { + UNUSED_P(ptr); + UNUSED_P(end); + UNUSED_P(enc); switch (tok) { case XML_TOK_PROLOG_S: return XML_ROLE_ENTITY_NONE; @@ -472,12 +442,8 @@ entity1(PROLOG_STATE *state, } static int PTRCALL -entity2(PROLOG_STATE *state, - int tok, - const char *ptr, - const char *end, - const ENCODING *enc) -{ +entity2(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { switch (tok) { case XML_TOK_PROLOG_S: return XML_ROLE_ENTITY_NONE; @@ -500,12 +466,11 @@ entity2(PROLOG_STATE *state, } static int PTRCALL -entity3(PROLOG_STATE *state, - int tok, - const char *UNUSED_P(ptr), - const char *UNUSED_P(end), - const ENCODING *UNUSED_P(enc)) -{ +entity3(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { + UNUSED_P(ptr); + UNUSED_P(end); + UNUSED_P(enc); switch (tok) { case XML_TOK_PROLOG_S: return XML_ROLE_ENTITY_NONE; @@ -517,12 +482,11 @@ entity3(PROLOG_STATE *state, } static int PTRCALL -entity4(PROLOG_STATE *state, - int tok, - const char *UNUSED_P(ptr), - const char *UNUSED_P(end), - const ENCODING *UNUSED_P(enc)) -{ +entity4(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { + UNUSED_P(ptr); + UNUSED_P(end); + UNUSED_P(enc); switch (tok) { case XML_TOK_PROLOG_S: return XML_ROLE_ENTITY_NONE; @@ -534,12 +498,8 @@ entity4(PROLOG_STATE *state, } static int PTRCALL -entity5(PROLOG_STATE *state, - int tok, - const char *ptr, - const char *end, - const ENCODING *enc) -{ +entity5(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { switch (tok) { case XML_TOK_PROLOG_S: return XML_ROLE_ENTITY_NONE; @@ -557,12 +517,11 @@ entity5(PROLOG_STATE *state, } static int PTRCALL -entity6(PROLOG_STATE *state, - int tok, - const char *UNUSED_P(ptr), - const char *UNUSED_P(end), - const ENCODING *UNUSED_P(enc)) -{ +entity6(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { + UNUSED_P(ptr); + UNUSED_P(end); + UNUSED_P(enc); switch (tok) { case XML_TOK_PROLOG_S: return XML_ROLE_ENTITY_NONE; @@ -575,12 +534,8 @@ entity6(PROLOG_STATE *state, } static int PTRCALL -entity7(PROLOG_STATE *state, - int tok, - const char *ptr, - const char *end, - const ENCODING *enc) -{ +entity7(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { switch (tok) { case XML_TOK_PROLOG_S: return XML_ROLE_ENTITY_NONE; @@ -603,12 +558,11 @@ entity7(PROLOG_STATE *state, } static int PTRCALL -entity8(PROLOG_STATE *state, - int tok, - const char *UNUSED_P(ptr), - const char *UNUSED_P(end), - const ENCODING *UNUSED_P(enc)) -{ +entity8(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { + UNUSED_P(ptr); + UNUSED_P(end); + UNUSED_P(enc); switch (tok) { case XML_TOK_PROLOG_S: return XML_ROLE_ENTITY_NONE; @@ -620,12 +574,11 @@ entity8(PROLOG_STATE *state, } static int PTRCALL -entity9(PROLOG_STATE *state, - int tok, - const char *UNUSED_P(ptr), - const char *UNUSED_P(end), - const ENCODING *UNUSED_P(enc)) -{ +entity9(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { + UNUSED_P(ptr); + UNUSED_P(end); + UNUSED_P(enc); switch (tok) { case XML_TOK_PROLOG_S: return XML_ROLE_ENTITY_NONE; @@ -637,12 +590,11 @@ entity9(PROLOG_STATE *state, } static int PTRCALL -entity10(PROLOG_STATE *state, - int tok, - const char *UNUSED_P(ptr), - const char *UNUSED_P(end), - const ENCODING *UNUSED_P(enc)) -{ +entity10(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { + UNUSED_P(ptr); + UNUSED_P(end); + UNUSED_P(enc); switch (tok) { case XML_TOK_PROLOG_S: return XML_ROLE_ENTITY_NONE; @@ -654,12 +606,11 @@ entity10(PROLOG_STATE *state, } static int PTRCALL -notation0(PROLOG_STATE *state, - int tok, - const char *UNUSED_P(ptr), - const char *UNUSED_P(end), - const ENCODING *UNUSED_P(enc)) -{ +notation0(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { + UNUSED_P(ptr); + UNUSED_P(end); + UNUSED_P(enc); switch (tok) { case XML_TOK_PROLOG_S: return XML_ROLE_NOTATION_NONE; @@ -671,12 +622,8 @@ notation0(PROLOG_STATE *state, } static int PTRCALL -notation1(PROLOG_STATE *state, - int tok, - const char *ptr, - const char *end, - const ENCODING *enc) -{ +notation1(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { switch (tok) { case XML_TOK_PROLOG_S: return XML_ROLE_NOTATION_NONE; @@ -695,12 +642,11 @@ notation1(PROLOG_STATE *state, } static int PTRCALL -notation2(PROLOG_STATE *state, - int tok, - const char *UNUSED_P(ptr), - const char *UNUSED_P(end), - const ENCODING *UNUSED_P(enc)) -{ +notation2(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { + UNUSED_P(ptr); + UNUSED_P(end); + UNUSED_P(enc); switch (tok) { case XML_TOK_PROLOG_S: return XML_ROLE_NOTATION_NONE; @@ -712,12 +658,11 @@ notation2(PROLOG_STATE *state, } static int PTRCALL -notation3(PROLOG_STATE *state, - int tok, - const char *UNUSED_P(ptr), - const char *UNUSED_P(end), - const ENCODING *UNUSED_P(enc)) -{ +notation3(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { + UNUSED_P(ptr); + UNUSED_P(end); + UNUSED_P(enc); switch (tok) { case XML_TOK_PROLOG_S: return XML_ROLE_NOTATION_NONE; @@ -730,12 +675,11 @@ notation3(PROLOG_STATE *state, } static int PTRCALL -notation4(PROLOG_STATE *state, - int tok, - const char *UNUSED_P(ptr), - const char *UNUSED_P(end), - const ENCODING *UNUSED_P(enc)) -{ +notation4(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { + UNUSED_P(ptr); + UNUSED_P(end); + UNUSED_P(enc); switch (tok) { case XML_TOK_PROLOG_S: return XML_ROLE_NOTATION_NONE; @@ -751,12 +695,11 @@ notation4(PROLOG_STATE *state, } static int PTRCALL -attlist0(PROLOG_STATE *state, - int tok, - const char *UNUSED_P(ptr), - const char *UNUSED_P(end), - const ENCODING *UNUSED_P(enc)) -{ +attlist0(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { + UNUSED_P(ptr); + UNUSED_P(end); + UNUSED_P(enc); switch (tok) { case XML_TOK_PROLOG_S: return XML_ROLE_ATTLIST_NONE; @@ -769,12 +712,11 @@ attlist0(PROLOG_STATE *state, } static int PTRCALL -attlist1(PROLOG_STATE *state, - int tok, - const char *UNUSED_P(ptr), - const char *UNUSED_P(end), - const ENCODING *UNUSED_P(enc)) -{ +attlist1(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { + UNUSED_P(ptr); + UNUSED_P(end); + UNUSED_P(enc); switch (tok) { case XML_TOK_PROLOG_S: return XML_ROLE_ATTLIST_NONE; @@ -790,34 +732,23 @@ attlist1(PROLOG_STATE *state, } static int PTRCALL -attlist2(PROLOG_STATE *state, - int tok, - const char *ptr, - const char *end, - const ENCODING *enc) -{ +attlist2(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { switch (tok) { case XML_TOK_PROLOG_S: return XML_ROLE_ATTLIST_NONE; - case XML_TOK_NAME: - { - static const char * const types[] = { - KW_CDATA, - KW_ID, - KW_IDREF, - KW_IDREFS, - KW_ENTITY, - KW_ENTITIES, - KW_NMTOKEN, - KW_NMTOKENS, - }; - int i; - for (i = 0; i < (int)(sizeof(types)/sizeof(types[0])); i++) - if (XmlNameMatchesAscii(enc, ptr, end, types[i])) { - state->handler = attlist8; - return XML_ROLE_ATTRIBUTE_TYPE_CDATA + i; - } - } + case XML_TOK_NAME: { + static const char *const types[] = { + KW_CDATA, KW_ID, KW_IDREF, KW_IDREFS, + KW_ENTITY, KW_ENTITIES, KW_NMTOKEN, KW_NMTOKENS, + }; + int i; + for (i = 0; i < (int)(sizeof(types) / sizeof(types[0])); i++) + if (XmlNameMatchesAscii(enc, ptr, end, types[i])) { + state->handler = attlist8; + return XML_ROLE_ATTRIBUTE_TYPE_CDATA + i; + } + } if (XmlNameMatchesAscii(enc, ptr, end, KW_NOTATION)) { state->handler = attlist5; return XML_ROLE_ATTLIST_NONE; @@ -831,12 +762,11 @@ attlist2(PROLOG_STATE *state, } static int PTRCALL -attlist3(PROLOG_STATE *state, - int tok, - const char *UNUSED_P(ptr), - const char *UNUSED_P(end), - const ENCODING *UNUSED_P(enc)) -{ +attlist3(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { + UNUSED_P(ptr); + UNUSED_P(end); + UNUSED_P(enc); switch (tok) { case XML_TOK_PROLOG_S: return XML_ROLE_ATTLIST_NONE; @@ -850,12 +780,11 @@ attlist3(PROLOG_STATE *state, } static int PTRCALL -attlist4(PROLOG_STATE *state, - int tok, - const char *UNUSED_P(ptr), - const char *UNUSED_P(end), - const ENCODING *UNUSED_P(enc)) -{ +attlist4(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { + UNUSED_P(ptr); + UNUSED_P(end); + UNUSED_P(enc); switch (tok) { case XML_TOK_PROLOG_S: return XML_ROLE_ATTLIST_NONE; @@ -870,12 +799,11 @@ attlist4(PROLOG_STATE *state, } static int PTRCALL -attlist5(PROLOG_STATE *state, - int tok, - const char *UNUSED_P(ptr), - const char *UNUSED_P(end), - const ENCODING *UNUSED_P(enc)) -{ +attlist5(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { + UNUSED_P(ptr); + UNUSED_P(end); + UNUSED_P(enc); switch (tok) { case XML_TOK_PROLOG_S: return XML_ROLE_ATTLIST_NONE; @@ -887,12 +815,11 @@ attlist5(PROLOG_STATE *state, } static int PTRCALL -attlist6(PROLOG_STATE *state, - int tok, - const char *UNUSED_P(ptr), - const char *UNUSED_P(end), - const ENCODING *UNUSED_P(enc)) -{ +attlist6(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { + UNUSED_P(ptr); + UNUSED_P(end); + UNUSED_P(enc); switch (tok) { case XML_TOK_PROLOG_S: return XML_ROLE_ATTLIST_NONE; @@ -904,12 +831,11 @@ attlist6(PROLOG_STATE *state, } static int PTRCALL -attlist7(PROLOG_STATE *state, - int tok, - const char *UNUSED_P(ptr), - const char *UNUSED_P(end), - const ENCODING *UNUSED_P(enc)) -{ +attlist7(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { + UNUSED_P(ptr); + UNUSED_P(end); + UNUSED_P(enc); switch (tok) { case XML_TOK_PROLOG_S: return XML_ROLE_ATTLIST_NONE; @@ -925,33 +851,23 @@ attlist7(PROLOG_STATE *state, /* default value */ static int PTRCALL -attlist8(PROLOG_STATE *state, - int tok, - const char *ptr, - const char *end, - const ENCODING *enc) -{ +attlist8(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { switch (tok) { case XML_TOK_PROLOG_S: return XML_ROLE_ATTLIST_NONE; case XML_TOK_POUND_NAME: - if (XmlNameMatchesAscii(enc, - ptr + MIN_BYTES_PER_CHAR(enc), - end, + if (XmlNameMatchesAscii(enc, ptr + MIN_BYTES_PER_CHAR(enc), end, KW_IMPLIED)) { state->handler = attlist1; return XML_ROLE_IMPLIED_ATTRIBUTE_VALUE; } - if (XmlNameMatchesAscii(enc, - ptr + MIN_BYTES_PER_CHAR(enc), - end, + if (XmlNameMatchesAscii(enc, ptr + MIN_BYTES_PER_CHAR(enc), end, KW_REQUIRED)) { state->handler = attlist1; return XML_ROLE_REQUIRED_ATTRIBUTE_VALUE; } - if (XmlNameMatchesAscii(enc, - ptr + MIN_BYTES_PER_CHAR(enc), - end, + if (XmlNameMatchesAscii(enc, ptr + MIN_BYTES_PER_CHAR(enc), end, KW_FIXED)) { state->handler = attlist9; return XML_ROLE_ATTLIST_NONE; @@ -965,12 +881,11 @@ attlist8(PROLOG_STATE *state, } static int PTRCALL -attlist9(PROLOG_STATE *state, - int tok, - const char *UNUSED_P(ptr), - const char *UNUSED_P(end), - const ENCODING *UNUSED_P(enc)) -{ +attlist9(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { + UNUSED_P(ptr); + UNUSED_P(end); + UNUSED_P(enc); switch (tok) { case XML_TOK_PROLOG_S: return XML_ROLE_ATTLIST_NONE; @@ -982,12 +897,11 @@ attlist9(PROLOG_STATE *state, } static int PTRCALL -element0(PROLOG_STATE *state, - int tok, - const char *UNUSED_P(ptr), - const char *UNUSED_P(end), - const ENCODING *UNUSED_P(enc)) -{ +element0(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { + UNUSED_P(ptr); + UNUSED_P(end); + UNUSED_P(enc); switch (tok) { case XML_TOK_PROLOG_S: return XML_ROLE_ELEMENT_NONE; @@ -1000,12 +914,8 @@ element0(PROLOG_STATE *state, } static int PTRCALL -element1(PROLOG_STATE *state, - int tok, - const char *ptr, - const char *end, - const ENCODING *enc) -{ +element1(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { switch (tok) { case XML_TOK_PROLOG_S: return XML_ROLE_ELEMENT_NONE; @@ -1030,19 +940,13 @@ element1(PROLOG_STATE *state, } static int PTRCALL -element2(PROLOG_STATE *state, - int tok, - const char *ptr, - const char *end, - const ENCODING *enc) -{ +element2(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { switch (tok) { case XML_TOK_PROLOG_S: return XML_ROLE_ELEMENT_NONE; case XML_TOK_POUND_NAME: - if (XmlNameMatchesAscii(enc, - ptr + MIN_BYTES_PER_CHAR(enc), - end, + if (XmlNameMatchesAscii(enc, ptr + MIN_BYTES_PER_CHAR(enc), end, KW_PCDATA)) { state->handler = element3; return XML_ROLE_CONTENT_PCDATA; @@ -1070,12 +974,11 @@ element2(PROLOG_STATE *state, } static int PTRCALL -element3(PROLOG_STATE *state, - int tok, - const char *UNUSED_P(ptr), - const char *UNUSED_P(end), - const ENCODING *UNUSED_P(enc)) -{ +element3(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { + UNUSED_P(ptr); + UNUSED_P(end); + UNUSED_P(enc); switch (tok) { case XML_TOK_PROLOG_S: return XML_ROLE_ELEMENT_NONE; @@ -1095,12 +998,11 @@ element3(PROLOG_STATE *state, } static int PTRCALL -element4(PROLOG_STATE *state, - int tok, - const char *UNUSED_P(ptr), - const char *UNUSED_P(end), - const ENCODING *UNUSED_P(enc)) -{ +element4(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { + UNUSED_P(ptr); + UNUSED_P(end); + UNUSED_P(enc); switch (tok) { case XML_TOK_PROLOG_S: return XML_ROLE_ELEMENT_NONE; @@ -1113,12 +1015,11 @@ element4(PROLOG_STATE *state, } static int PTRCALL -element5(PROLOG_STATE *state, - int tok, - const char *UNUSED_P(ptr), - const char *UNUSED_P(end), - const ENCODING *UNUSED_P(enc)) -{ +element5(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { + UNUSED_P(ptr); + UNUSED_P(end); + UNUSED_P(enc); switch (tok) { case XML_TOK_PROLOG_S: return XML_ROLE_ELEMENT_NONE; @@ -1134,12 +1035,11 @@ element5(PROLOG_STATE *state, } static int PTRCALL -element6(PROLOG_STATE *state, - int tok, - const char *UNUSED_P(ptr), - const char *UNUSED_P(end), - const ENCODING *UNUSED_P(enc)) -{ +element6(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { + UNUSED_P(ptr); + UNUSED_P(end); + UNUSED_P(enc); switch (tok) { case XML_TOK_PROLOG_S: return XML_ROLE_ELEMENT_NONE; @@ -1164,12 +1064,11 @@ element6(PROLOG_STATE *state, } static int PTRCALL -element7(PROLOG_STATE *state, - int tok, - const char *UNUSED_P(ptr), - const char *UNUSED_P(end), - const ENCODING *UNUSED_P(enc)) -{ +element7(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { + UNUSED_P(ptr); + UNUSED_P(end); + UNUSED_P(enc); switch (tok) { case XML_TOK_PROLOG_S: return XML_ROLE_ELEMENT_NONE; @@ -1214,12 +1113,8 @@ element7(PROLOG_STATE *state, #ifdef XML_DTD static int PTRCALL -condSect0(PROLOG_STATE *state, - int tok, - const char *ptr, - const char *end, - const ENCODING *enc) -{ +condSect0(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { switch (tok) { case XML_TOK_PROLOG_S: return XML_ROLE_NONE; @@ -1238,12 +1133,11 @@ condSect0(PROLOG_STATE *state, } static int PTRCALL -condSect1(PROLOG_STATE *state, - int tok, - const char *UNUSED_P(ptr), - const char *UNUSED_P(end), - const ENCODING *UNUSED_P(enc)) -{ +condSect1(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { + UNUSED_P(ptr); + UNUSED_P(end); + UNUSED_P(enc); switch (tok) { case XML_TOK_PROLOG_S: return XML_ROLE_NONE; @@ -1256,12 +1150,11 @@ condSect1(PROLOG_STATE *state, } static int PTRCALL -condSect2(PROLOG_STATE *state, - int tok, - const char *UNUSED_P(ptr), - const char *UNUSED_P(end), - const ENCODING *UNUSED_P(enc)) -{ +condSect2(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { + UNUSED_P(ptr); + UNUSED_P(end); + UNUSED_P(enc); switch (tok) { case XML_TOK_PROLOG_S: return XML_ROLE_NONE; @@ -1275,12 +1168,11 @@ condSect2(PROLOG_STATE *state, #endif /* XML_DTD */ static int PTRCALL -declClose(PROLOG_STATE *state, - int tok, - const char *UNUSED_P(ptr), - const char *UNUSED_P(end), - const ENCODING *UNUSED_P(enc)) -{ +declClose(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { + UNUSED_P(ptr); + UNUSED_P(end); + UNUSED_P(enc); switch (tok) { case XML_TOK_PROLOG_S: return state->role_none; @@ -1291,21 +1183,42 @@ declClose(PROLOG_STATE *state, return common(state, tok); } +/* This function will only be invoked if the internal logic of the + * parser has broken down. It is used in two cases: + * + * 1: When the XML prolog has been finished. At this point the + * processor (the parser level above these role handlers) should + * switch from prologProcessor to contentProcessor and reinitialise + * the handler function. + * + * 2: When an error has been detected (via common() below). At this + * point again the processor should be switched to errorProcessor, + * which will never call a handler. + * + * The result of this is that error() can only be called if the + * processor switch failed to happen, which is an internal error and + * therefore we shouldn't be able to provoke it simply by using the + * library. It is a necessary backstop, however, so we merely exclude + * it from the coverage statistics. + * + * LCOV_EXCL_START + */ static int PTRCALL -error(PROLOG_STATE *UNUSED_P(state), - int UNUSED_P(tok), - const char *UNUSED_P(ptr), - const char *UNUSED_P(end), - const ENCODING *UNUSED_P(enc)) -{ +error(PROLOG_STATE *state, int tok, const char *ptr, const char *end, + const ENCODING *enc) { + UNUSED_P(state); + UNUSED_P(tok); + UNUSED_P(ptr); + UNUSED_P(end); + UNUSED_P(enc); return XML_ROLE_NONE; } +/* LCOV_EXCL_STOP */ static int FASTCALL -common(PROLOG_STATE *state, int tok) -{ +common(PROLOG_STATE *state, int tok) { #ifdef XML_DTD - if (!state->documentEntity && tok == XML_TOK_PARAM_ENTITY_REF) + if (! state->documentEntity && tok == XML_TOK_PARAM_ENTITY_REF) return XML_ROLE_INNER_PARAM_ENTITY_REF; #endif state->handler = error; @@ -1313,8 +1226,7 @@ common(PROLOG_STATE *state, int tok) } void -XmlPrologStateInit(PROLOG_STATE *state) -{ +XmlPrologStateInit(PROLOG_STATE *state) { state->handler = prolog0; #ifdef XML_DTD state->documentEntity = 1; @@ -1326,8 +1238,7 @@ XmlPrologStateInit(PROLOG_STATE *state) #ifdef XML_DTD void -XmlPrologStateInitExternalEntity(PROLOG_STATE *state) -{ +XmlPrologStateInitExternalEntity(PROLOG_STATE *state) { state->handler = externalSubset0; state->documentEntity = 0; state->includeLevel = 0; diff --git a/chromium/third_party/expat/files/lib/xmlrole.h b/chromium/third_party/expat/files/lib/xmlrole.h index 4dd9f06f976..036aba64fd2 100644 --- a/chromium/third_party/expat/files/lib/xmlrole.h +++ b/chromium/third_party/expat/files/lib/xmlrole.h @@ -1,5 +1,33 @@ -/* Copyright (c) 1998, 1999 Thai Open Source Software Center Ltd - See the file COPYING for copying permission. +/* + __ __ _ + ___\ \/ /_ __ __ _| |_ + / _ \\ /| '_ \ / _` | __| + | __// \| |_) | (_| | |_ + \___/_/\_\ .__/ \__,_|\__| + |_| XML parser + + Copyright (c) 1997-2000 Thai Open Source Software Center Ltd + Copyright (c) 2000-2017 Expat development team + Licensed under the MIT license: + + Permission is hereby granted, free of charge, to any person obtaining + a copy of this software and associated documentation files (the + "Software"), to deal in the Software without restriction, including + without limitation the rights to use, copy, modify, merge, publish, + distribute, sublicense, and/or sell copies of the Software, and to permit + persons to whom the Software is furnished to do so, subject to the + following conditions: + + The above copyright notice and this permission notice shall be included + in all copies or substantial portions of the Software. + + THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN + NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, + DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR + OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE + USE OR OTHER DEALINGS IN THE SOFTWARE. */ #ifndef XmlRole_INCLUDED @@ -8,7 +36,7 @@ #ifdef __VMS /* 0 1 2 3 0 1 2 3 1234567890123456789012345678901 1234567890123456789012345678901 */ -#define XmlPrologStateInitExternalEntity XmlPrologStateInitExternalEnt +# define XmlPrologStateInitExternalEntity XmlPrologStateInitExternalEnt #endif #include "xmltok.h" @@ -85,11 +113,8 @@ enum { }; typedef struct prolog_state { - int (PTRCALL *handler) (struct prolog_state *state, - int tok, - const char *ptr, - const char *end, - const ENCODING *enc); + int(PTRCALL *handler)(struct prolog_state *state, int tok, const char *ptr, + const char *end, const ENCODING *enc); unsigned level; int role_none; #ifdef XML_DTD @@ -104,8 +129,8 @@ void XmlPrologStateInit(PROLOG_STATE *); void XmlPrologStateInitExternalEntity(PROLOG_STATE *); #endif /* XML_DTD */ -#define XmlTokenRole(state, tok, ptr, end, enc) \ - (((state)->handler)(state, tok, ptr, end, enc)) +#define XmlTokenRole(state, tok, ptr, end, enc) \ + (((state)->handler)(state, tok, ptr, end, enc)) #ifdef __cplusplus } diff --git a/chromium/third_party/expat/files/lib/xmltok.c b/chromium/third_party/expat/files/lib/xmltok.c index b014e72ce16..11e9d1ccdad 100644 --- a/chromium/third_party/expat/files/lib/xmltok.c +++ b/chromium/third_party/expat/files/lib/xmltok.c @@ -1,22 +1,54 @@ -/* Copyright (c) 1998, 1999 Thai Open Source Software Center Ltd - See the file COPYING for copying permission. +/* + __ __ _ + ___\ \/ /_ __ __ _| |_ + / _ \\ /| '_ \ / _` | __| + | __// \| |_) | (_| | |_ + \___/_/\_\ .__/ \__,_|\__| + |_| XML parser + + Copyright (c) 1997-2000 Thai Open Source Software Center Ltd + Copyright (c) 2000-2017 Expat development team + Licensed under the MIT license: + + Permission is hereby granted, free of charge, to any person obtaining + a copy of this software and associated documentation files (the + "Software"), to deal in the Software without restriction, including + without limitation the rights to use, copy, modify, merge, publish, + distribute, sublicense, and/or sell copies of the Software, and to permit + persons to whom the Software is furnished to do so, subject to the + following conditions: + + The above copyright notice and this permission notice shall be included + in all copies or substantial portions of the Software. + + THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN + NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, + DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR + OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE + USE OR OTHER DEALINGS IN THE SOFTWARE. */ #include <stddef.h> +#include <string.h> /* memcpy */ -#ifdef WIN32 -#include "winconfig.h" -#elif defined(MACOS_CLASSIC) -#include "macconfig.h" -#elif defined(__amigaos__) -#include "amigaconfig.h" -#elif defined(__WATCOMC__) -#include "watcomconfig.h" +#if defined(_MSC_VER) && (_MSC_VER <= 1700) +/* for vs2012/11.0/1700 and earlier Visual Studio compilers */ +# define bool int +# define false 0 +# define true 1 #else -#ifdef HAVE_EXPAT_CONFIG_H -#include <expat_config.h> +# include <stdbool.h> #endif -#endif /* ndef WIN32 */ + +#ifdef _WIN32 +# include "winconfig.h" +#else +# ifdef HAVE_EXPAT_CONFIG_H +# include <expat_config.h> +# endif +#endif /* ndef _WIN32 */ #include "expat_external.h" #include "internal.h" @@ -24,59 +56,49 @@ #include "nametab.h" #ifdef XML_DTD -#define IGNORE_SECTION_TOK_VTABLE , PREFIX(ignoreSectionTok) +# define IGNORE_SECTION_TOK_VTABLE , PREFIX(ignoreSectionTok) #else -#define IGNORE_SECTION_TOK_VTABLE /* as nothing */ +# define IGNORE_SECTION_TOK_VTABLE /* as nothing */ #endif -#define VTABLE1 \ - { PREFIX(prologTok), PREFIX(contentTok), \ - PREFIX(cdataSectionTok) IGNORE_SECTION_TOK_VTABLE }, \ - { PREFIX(attributeValueTok), PREFIX(entityValueTok) }, \ - PREFIX(sameName), \ - PREFIX(nameMatchesAscii), \ - PREFIX(nameLength), \ - PREFIX(skipS), \ - PREFIX(getAtts), \ - PREFIX(charRefNumber), \ - PREFIX(predefinedEntityName), \ - PREFIX(updatePosition), \ - PREFIX(isPublicId) +#define VTABLE1 \ + {PREFIX(prologTok), PREFIX(contentTok), \ + PREFIX(cdataSectionTok) IGNORE_SECTION_TOK_VTABLE}, \ + {PREFIX(attributeValueTok), PREFIX(entityValueTok)}, \ + PREFIX(nameMatchesAscii), PREFIX(nameLength), PREFIX(skipS), \ + PREFIX(getAtts), PREFIX(charRefNumber), PREFIX(predefinedEntityName), \ + PREFIX(updatePosition), PREFIX(isPublicId) #define VTABLE VTABLE1, PREFIX(toUtf8), PREFIX(toUtf16) -#define UCS2_GET_NAMING(pages, hi, lo) \ - (namingBitmap[(pages[hi] << 3) + ((lo) >> 5)] & (1u << ((lo) & 0x1F))) +#define UCS2_GET_NAMING(pages, hi, lo) \ + (namingBitmap[(pages[hi] << 3) + ((lo) >> 5)] & (1u << ((lo)&0x1F))) /* A 2 byte UTF-8 representation splits the characters 11 bits between the bottom 5 and 6 bits of the bytes. We need 8 bits to index into pages, 3 bits to add to that index and 5 bits to generate the mask. */ -#define UTF8_GET_NAMING2(pages, byte) \ - (namingBitmap[((pages)[(((byte)[0]) >> 2) & 7] << 3) \ - + ((((byte)[0]) & 3) << 1) \ - + ((((byte)[1]) >> 5) & 1)] \ - & (1u << (((byte)[1]) & 0x1F))) +#define UTF8_GET_NAMING2(pages, byte) \ + (namingBitmap[((pages)[(((byte)[0]) >> 2) & 7] << 3) \ + + ((((byte)[0]) & 3) << 1) + ((((byte)[1]) >> 5) & 1)] \ + & (1u << (((byte)[1]) & 0x1F))) /* A 3 byte UTF-8 representation splits the characters 16 bits between the bottom 4, 6 and 6 bits of the bytes. We need 8 bits to index into pages, 3 bits to add to that index and 5 bits to generate the mask. */ -#define UTF8_GET_NAMING3(pages, byte) \ - (namingBitmap[((pages)[((((byte)[0]) & 0xF) << 4) \ - + ((((byte)[1]) >> 2) & 0xF)] \ - << 3) \ - + ((((byte)[1]) & 3) << 1) \ - + ((((byte)[2]) >> 5) & 1)] \ - & (1u << (((byte)[2]) & 0x1F))) - -#define UTF8_GET_NAMING(pages, p, n) \ - ((n) == 2 \ - ? UTF8_GET_NAMING2(pages, (const unsigned char *)(p)) \ - : ((n) == 3 \ - ? UTF8_GET_NAMING3(pages, (const unsigned char *)(p)) \ - : 0)) +#define UTF8_GET_NAMING3(pages, byte) \ + (namingBitmap \ + [((pages)[((((byte)[0]) & 0xF) << 4) + ((((byte)[1]) >> 2) & 0xF)] \ + << 3) \ + + ((((byte)[1]) & 3) << 1) + ((((byte)[2]) >> 5) & 1)] \ + & (1u << (((byte)[2]) & 0x1F))) + +#define UTF8_GET_NAMING(pages, p, n) \ + ((n) == 2 \ + ? UTF8_GET_NAMING2(pages, (const unsigned char *)(p)) \ + : ((n) == 3 ? UTF8_GET_NAMING3(pages, (const unsigned char *)(p)) : 0)) /* Detection of invalid UTF-8 sequences is based on Table 3.1B of Unicode 3.2: http://www.unicode.org/unicode/reports/tr28/ @@ -88,88 +110,76 @@ (A & 0xC0) == 0xC0 means A > 0xBF */ -#define UTF8_INVALID2(p) \ +#define UTF8_INVALID2(p) \ ((*p) < 0xC2 || ((p)[1] & 0x80) == 0 || ((p)[1] & 0xC0) == 0xC0) -#define UTF8_INVALID3(p) \ - (((p)[2] & 0x80) == 0 \ - || \ - ((*p) == 0xEF && (p)[1] == 0xBF \ - ? \ - (p)[2] > 0xBD \ - : \ - ((p)[2] & 0xC0) == 0xC0) \ - || \ - ((*p) == 0xE0 \ - ? \ - (p)[1] < 0xA0 || ((p)[1] & 0xC0) == 0xC0 \ - : \ - ((p)[1] & 0x80) == 0 \ - || \ - ((*p) == 0xED ? (p)[1] > 0x9F : ((p)[1] & 0xC0) == 0xC0))) - -#define UTF8_INVALID4(p) \ - (((p)[3] & 0x80) == 0 || ((p)[3] & 0xC0) == 0xC0 \ - || \ - ((p)[2] & 0x80) == 0 || ((p)[2] & 0xC0) == 0xC0 \ - || \ - ((*p) == 0xF0 \ - ? \ - (p)[1] < 0x90 || ((p)[1] & 0xC0) == 0xC0 \ - : \ - ((p)[1] & 0x80) == 0 \ - || \ - ((*p) == 0xF4 ? (p)[1] > 0x8F : ((p)[1] & 0xC0) == 0xC0))) +#define UTF8_INVALID3(p) \ + (((p)[2] & 0x80) == 0 \ + || ((*p) == 0xEF && (p)[1] == 0xBF ? (p)[2] > 0xBD \ + : ((p)[2] & 0xC0) == 0xC0) \ + || ((*p) == 0xE0 \ + ? (p)[1] < 0xA0 || ((p)[1] & 0xC0) == 0xC0 \ + : ((p)[1] & 0x80) == 0 \ + || ((*p) == 0xED ? (p)[1] > 0x9F : ((p)[1] & 0xC0) == 0xC0))) + +#define UTF8_INVALID4(p) \ + (((p)[3] & 0x80) == 0 || ((p)[3] & 0xC0) == 0xC0 || ((p)[2] & 0x80) == 0 \ + || ((p)[2] & 0xC0) == 0xC0 \ + || ((*p) == 0xF0 \ + ? (p)[1] < 0x90 || ((p)[1] & 0xC0) == 0xC0 \ + : ((p)[1] & 0x80) == 0 \ + || ((*p) == 0xF4 ? (p)[1] > 0x8F : ((p)[1] & 0xC0) == 0xC0))) static int PTRFASTCALL -isNever(const ENCODING *UNUSED_P(enc), const char *UNUSED_P(p)) -{ +isNever(const ENCODING *enc, const char *p) { + UNUSED_P(enc); + UNUSED_P(p); return 0; } static int PTRFASTCALL -utf8_isName2(const ENCODING *UNUSED_P(enc), const char *p) -{ +utf8_isName2(const ENCODING *enc, const char *p) { + UNUSED_P(enc); return UTF8_GET_NAMING2(namePages, (const unsigned char *)p); } static int PTRFASTCALL -utf8_isName3(const ENCODING *UNUSED_P(enc), const char *p) -{ +utf8_isName3(const ENCODING *enc, const char *p) { + UNUSED_P(enc); return UTF8_GET_NAMING3(namePages, (const unsigned char *)p); } #define utf8_isName4 isNever static int PTRFASTCALL -utf8_isNmstrt2(const ENCODING *UNUSED_P(enc), const char *p) -{ +utf8_isNmstrt2(const ENCODING *enc, const char *p) { + UNUSED_P(enc); return UTF8_GET_NAMING2(nmstrtPages, (const unsigned char *)p); } static int PTRFASTCALL -utf8_isNmstrt3(const ENCODING *UNUSED_P(enc), const char *p) -{ +utf8_isNmstrt3(const ENCODING *enc, const char *p) { + UNUSED_P(enc); return UTF8_GET_NAMING3(nmstrtPages, (const unsigned char *)p); } #define utf8_isNmstrt4 isNever static int PTRFASTCALL -utf8_isInvalid2(const ENCODING *UNUSED_P(enc), const char *p) -{ +utf8_isInvalid2(const ENCODING *enc, const char *p) { + UNUSED_P(enc); return UTF8_INVALID2((const unsigned char *)p); } static int PTRFASTCALL -utf8_isInvalid3(const ENCODING *UNUSED_P(enc), const char *p) -{ +utf8_isInvalid3(const ENCODING *enc, const char *p) { + UNUSED_P(enc); return UTF8_INVALID3((const unsigned char *)p); } static int PTRFASTCALL -utf8_isInvalid4(const ENCODING *UNUSED_P(enc), const char *p) -{ +utf8_isInvalid4(const ENCODING *enc, const char *p) { + UNUSED_P(enc); return UTF8_INVALID4((const unsigned char *)p); } @@ -177,61 +187,44 @@ struct normal_encoding { ENCODING enc; unsigned char type[256]; #ifdef XML_MIN_SIZE - int (PTRFASTCALL *byteType)(const ENCODING *, const char *); - int (PTRFASTCALL *isNameMin)(const ENCODING *, const char *); - int (PTRFASTCALL *isNmstrtMin)(const ENCODING *, const char *); - int (PTRFASTCALL *byteToAscii)(const ENCODING *, const char *); - int (PTRCALL *charMatches)(const ENCODING *, const char *, int); + int(PTRFASTCALL *byteType)(const ENCODING *, const char *); + int(PTRFASTCALL *isNameMin)(const ENCODING *, const char *); + int(PTRFASTCALL *isNmstrtMin)(const ENCODING *, const char *); + int(PTRFASTCALL *byteToAscii)(const ENCODING *, const char *); + int(PTRCALL *charMatches)(const ENCODING *, const char *, int); #endif /* XML_MIN_SIZE */ - int (PTRFASTCALL *isName2)(const ENCODING *, const char *); - int (PTRFASTCALL *isName3)(const ENCODING *, const char *); - int (PTRFASTCALL *isName4)(const ENCODING *, const char *); - int (PTRFASTCALL *isNmstrt2)(const ENCODING *, const char *); - int (PTRFASTCALL *isNmstrt3)(const ENCODING *, const char *); - int (PTRFASTCALL *isNmstrt4)(const ENCODING *, const char *); - int (PTRFASTCALL *isInvalid2)(const ENCODING *, const char *); - int (PTRFASTCALL *isInvalid3)(const ENCODING *, const char *); - int (PTRFASTCALL *isInvalid4)(const ENCODING *, const char *); + int(PTRFASTCALL *isName2)(const ENCODING *, const char *); + int(PTRFASTCALL *isName3)(const ENCODING *, const char *); + int(PTRFASTCALL *isName4)(const ENCODING *, const char *); + int(PTRFASTCALL *isNmstrt2)(const ENCODING *, const char *); + int(PTRFASTCALL *isNmstrt3)(const ENCODING *, const char *); + int(PTRFASTCALL *isNmstrt4)(const ENCODING *, const char *); + int(PTRFASTCALL *isInvalid2)(const ENCODING *, const char *); + int(PTRFASTCALL *isInvalid3)(const ENCODING *, const char *); + int(PTRFASTCALL *isInvalid4)(const ENCODING *, const char *); }; -#define AS_NORMAL_ENCODING(enc) ((const struct normal_encoding *) (enc)) +#define AS_NORMAL_ENCODING(enc) ((const struct normal_encoding *)(enc)) #ifdef XML_MIN_SIZE -#define STANDARD_VTABLE(E) \ - E ## byteType, \ - E ## isNameMin, \ - E ## isNmstrtMin, \ - E ## byteToAscii, \ - E ## charMatches, +# define STANDARD_VTABLE(E) \ + E##byteType, E##isNameMin, E##isNmstrtMin, E##byteToAscii, E##charMatches, #else -#define STANDARD_VTABLE(E) /* as nothing */ +# define STANDARD_VTABLE(E) /* as nothing */ #endif -#define NORMAL_VTABLE(E) \ - E ## isName2, \ - E ## isName3, \ - E ## isName4, \ - E ## isNmstrt2, \ - E ## isNmstrt3, \ - E ## isNmstrt4, \ - E ## isInvalid2, \ - E ## isInvalid3, \ - E ## isInvalid4 - -#define NULL_VTABLE \ - /* isName2 */ NULL, \ - /* isName3 */ NULL, \ - /* isName4 */ NULL, \ - /* isNmstrt2 */ NULL, \ - /* isNmstrt3 */ NULL, \ - /* isNmstrt4 */ NULL, \ - /* isInvalid2 */ NULL, \ - /* isInvalid3 */ NULL, \ - /* isInvalid4 */ NULL +#define NORMAL_VTABLE(E) \ + E##isName2, E##isName3, E##isName4, E##isNmstrt2, E##isNmstrt3, \ + E##isNmstrt4, E##isInvalid2, E##isInvalid3, E##isInvalid4 + +#define NULL_VTABLE \ + /* isName2 */ NULL, /* isName3 */ NULL, /* isName4 */ NULL, \ + /* isNmstrt2 */ NULL, /* isNmstrt3 */ NULL, /* isNmstrt4 */ NULL, \ + /* isInvalid2 */ NULL, /* isInvalid3 */ NULL, /* isInvalid4 */ NULL static int FASTCALL checkCharRefNumber(int); @@ -239,75 +232,70 @@ static int FASTCALL checkCharRefNumber(int); #include "ascii.h" #ifdef XML_MIN_SIZE -#define sb_isNameMin isNever -#define sb_isNmstrtMin isNever +# define sb_isNameMin isNever +# define sb_isNmstrtMin isNever #endif #ifdef XML_MIN_SIZE -#define MINBPC(enc) ((enc)->minBytesPerChar) +# define MINBPC(enc) ((enc)->minBytesPerChar) #else /* minimum bytes per character */ -#define MINBPC(enc) 1 +# define MINBPC(enc) 1 #endif -#define SB_BYTE_TYPE(enc, p) \ +#define SB_BYTE_TYPE(enc, p) \ (((struct normal_encoding *)(enc))->type[(unsigned char)*(p)]) #ifdef XML_MIN_SIZE static int PTRFASTCALL -sb_byteType(const ENCODING *enc, const char *p) -{ +sb_byteType(const ENCODING *enc, const char *p) { return SB_BYTE_TYPE(enc, p); } -#define BYTE_TYPE(enc, p) \ - (AS_NORMAL_ENCODING(enc)->byteType(enc, p)) +# define BYTE_TYPE(enc, p) (AS_NORMAL_ENCODING(enc)->byteType(enc, p)) #else -#define BYTE_TYPE(enc, p) SB_BYTE_TYPE(enc, p) +# define BYTE_TYPE(enc, p) SB_BYTE_TYPE(enc, p) #endif #ifdef XML_MIN_SIZE -#define BYTE_TO_ASCII(enc, p) \ - (AS_NORMAL_ENCODING(enc)->byteToAscii(enc, p)) +# define BYTE_TO_ASCII(enc, p) (AS_NORMAL_ENCODING(enc)->byteToAscii(enc, p)) static int PTRFASTCALL -sb_byteToAscii(const ENCODING *enc, const char *p) -{ +sb_byteToAscii(const ENCODING *enc, const char *p) { + UNUSED_P(enc); return *p; } #else -#define BYTE_TO_ASCII(enc, p) (*(p)) +# define BYTE_TO_ASCII(enc, p) (*(p)) #endif -#define IS_NAME_CHAR(enc, p, n) \ - (AS_NORMAL_ENCODING(enc)->isName ## n(enc, p)) -#define IS_NMSTRT_CHAR(enc, p, n) \ - (AS_NORMAL_ENCODING(enc)->isNmstrt ## n(enc, p)) -#define IS_INVALID_CHAR(enc, p, n) \ - (AS_NORMAL_ENCODING(enc)->isInvalid ## n(enc, p)) +#define IS_NAME_CHAR(enc, p, n) (AS_NORMAL_ENCODING(enc)->isName##n(enc, p)) +#define IS_NMSTRT_CHAR(enc, p, n) (AS_NORMAL_ENCODING(enc)->isNmstrt##n(enc, p)) +#define IS_INVALID_CHAR(enc, p, n) \ + (AS_NORMAL_ENCODING(enc)->isInvalid##n(enc, p)) #ifdef XML_MIN_SIZE -#define IS_NAME_CHAR_MINBPC(enc, p) \ - (AS_NORMAL_ENCODING(enc)->isNameMin(enc, p)) -#define IS_NMSTRT_CHAR_MINBPC(enc, p) \ - (AS_NORMAL_ENCODING(enc)->isNmstrtMin(enc, p)) +# define IS_NAME_CHAR_MINBPC(enc, p) \ + (AS_NORMAL_ENCODING(enc)->isNameMin(enc, p)) +# define IS_NMSTRT_CHAR_MINBPC(enc, p) \ + (AS_NORMAL_ENCODING(enc)->isNmstrtMin(enc, p)) #else -#define IS_NAME_CHAR_MINBPC(enc, p) (0) -#define IS_NMSTRT_CHAR_MINBPC(enc, p) (0) +# define IS_NAME_CHAR_MINBPC(enc, p) (0) +# define IS_NMSTRT_CHAR_MINBPC(enc, p) (0) #endif #ifdef XML_MIN_SIZE -#define CHAR_MATCHES(enc, p, c) \ - (AS_NORMAL_ENCODING(enc)->charMatches(enc, p, c)) +# define CHAR_MATCHES(enc, p, c) \ + (AS_NORMAL_ENCODING(enc)->charMatches(enc, p, c)) static int PTRCALL -sb_charMatches(const ENCODING *enc, const char *p, int c) -{ +sb_charMatches(const ENCODING *enc, const char *p, int c) { + UNUSED_P(enc); return *p == c; } #else /* c is an ASCII character */ -#define CHAR_MATCHES(enc, p, c) (*(p) == c) +# define CHAR_MATCHES(enc, p, c) (*(p) == c) #endif -#define PREFIX(ident) normal_ ## ident +#define PREFIX(ident) normal_##ident #define XML_TOK_IMPL_C #include "xmltok_impl.c" #undef XML_TOK_IMPL_C @@ -322,42 +310,46 @@ sb_charMatches(const ENCODING *enc, const char *p, int c) #undef IS_NMSTRT_CHAR_MINBPC #undef IS_INVALID_CHAR -enum { /* UTF8_cvalN is value of masked first byte of N byte sequence */ - UTF8_cval1 = 0x00, - UTF8_cval2 = 0xc0, - UTF8_cval3 = 0xe0, - UTF8_cval4 = 0xf0 +enum { /* UTF8_cvalN is value of masked first byte of N byte sequence */ + UTF8_cval1 = 0x00, + UTF8_cval2 = 0xc0, + UTF8_cval3 = 0xe0, + UTF8_cval4 = 0xf0 }; void -align_limit_to_full_utf8_characters(const char * from, const char ** fromLimRef) -{ - const char * fromLim = *fromLimRef; +_INTERNAL_trim_to_complete_utf8_characters(const char *from, + const char **fromLimRef) { + const char *fromLim = *fromLimRef; size_t walked = 0; for (; fromLim > from; fromLim--, walked++) { const unsigned char prev = (unsigned char)fromLim[-1]; - if ((prev & 0xf8u) == 0xf0u) { /* 4-byte character, lead by 0b11110xxx byte */ + if ((prev & 0xf8u) + == 0xf0u) { /* 4-byte character, lead by 0b11110xxx byte */ if (walked + 1 >= 4) { fromLim += 4 - 1; break; } else { walked = 0; } - } else if ((prev & 0xf0u) == 0xe0u) { /* 3-byte character, lead by 0b1110xxxx byte */ + } else if ((prev & 0xf0u) + == 0xe0u) { /* 3-byte character, lead by 0b1110xxxx byte */ if (walked + 1 >= 3) { fromLim += 3 - 1; break; } else { walked = 0; } - } else if ((prev & 0xe0u) == 0xc0u) { /* 2-byte character, lead by 0b110xxxxx byte */ + } else if ((prev & 0xe0u) + == 0xc0u) { /* 2-byte character, lead by 0b110xxxxx byte */ if (walked + 1 >= 2) { fromLim += 2 - 1; break; } else { walked = 0; } - } else if ((prev & 0x80u) == 0x00u) { /* 1-byte character, matching 0b0xxxxxxx */ + } else if ((prev & 0x80u) + == 0x00u) { /* 1-byte character, matching 0b0xxxxxxx */ break; } } @@ -365,35 +357,47 @@ align_limit_to_full_utf8_characters(const char * from, const char ** fromLimRef) } static enum XML_Convert_Result PTRCALL -utf8_toUtf8(const ENCODING *UNUSED_P(enc), - const char **fromP, const char *fromLim, - char **toP, const char *toLim) -{ - enum XML_Convert_Result res = XML_CONVERT_COMPLETED; - char *to; - const char *from; - if (fromLim - *fromP > toLim - *toP) { - /* Avoid copying partial characters. */ - res = XML_CONVERT_OUTPUT_EXHAUSTED; - fromLim = *fromP + (toLim - *toP); - align_limit_to_full_utf8_characters(*fromP, &fromLim); +utf8_toUtf8(const ENCODING *enc, const char **fromP, const char *fromLim, + char **toP, const char *toLim) { + bool input_incomplete = false; + bool output_exhausted = false; + + /* Avoid copying partial characters (due to limited space). */ + const ptrdiff_t bytesAvailable = fromLim - *fromP; + const ptrdiff_t bytesStorable = toLim - *toP; + UNUSED_P(enc); + if (bytesAvailable > bytesStorable) { + fromLim = *fromP + bytesStorable; + output_exhausted = true; + } + + /* Avoid copying partial characters (from incomplete input). */ + { + const char *const fromLimBefore = fromLim; + _INTERNAL_trim_to_complete_utf8_characters(*fromP, &fromLim); + if (fromLim < fromLimBefore) { + input_incomplete = true; + } } - for (to = *toP, from = *fromP; (from < fromLim) && (to < toLim); from++, to++) - *to = *from; - *fromP = from; - *toP = to; - if ((to == toLim) && (from < fromLim)) + { + const ptrdiff_t bytesToCopy = fromLim - *fromP; + memcpy(*toP, *fromP, bytesToCopy); + *fromP += bytesToCopy; + *toP += bytesToCopy; + } + + if (output_exhausted) /* needs to go first */ return XML_CONVERT_OUTPUT_EXHAUSTED; + else if (input_incomplete) + return XML_CONVERT_INPUT_INCOMPLETE; else - return res; + return XML_CONVERT_COMPLETED; } static enum XML_Convert_Result PTRCALL -utf8_toUtf16(const ENCODING *enc, - const char **fromP, const char *fromLim, - unsigned short **toP, const unsigned short *toLim) -{ +utf8_toUtf16(const ENCODING *enc, const char **fromP, const char *fromLim, + unsigned short **toP, const unsigned short *toLim) { enum XML_Convert_Result res = XML_CONVERT_COMPLETED; unsigned short *to = *toP; const char *from = *fromP; @@ -412,30 +416,28 @@ utf8_toUtf16(const ENCODING *enc, res = XML_CONVERT_INPUT_INCOMPLETE; goto after; } - *to++ = (unsigned short)(((from[0] & 0xf) << 12) - | ((from[1] & 0x3f) << 6) | (from[2] & 0x3f)); + *to++ = (unsigned short)(((from[0] & 0xf) << 12) | ((from[1] & 0x3f) << 6) + | (from[2] & 0x3f)); from += 3; break; - case BT_LEAD4: - { - unsigned long n; - if (toLim - to < 2) { - res = XML_CONVERT_OUTPUT_EXHAUSTED; - goto after; - } - if (fromLim - from < 4) { - res = XML_CONVERT_INPUT_INCOMPLETE; - goto after; - } - n = ((from[0] & 0x7) << 18) | ((from[1] & 0x3f) << 12) - | ((from[2] & 0x3f) << 6) | (from[3] & 0x3f); - n -= 0x10000; - to[0] = (unsigned short)((n >> 10) | 0xD800); - to[1] = (unsigned short)((n & 0x3FF) | 0xDC00); - to += 2; - from += 4; + case BT_LEAD4: { + unsigned long n; + if (toLim - to < 2) { + res = XML_CONVERT_OUTPUT_EXHAUSTED; + goto after; } - break; + if (fromLim - from < 4) { + res = XML_CONVERT_INPUT_INCOMPLETE; + goto after; + } + n = ((from[0] & 0x7) << 18) | ((from[1] & 0x3f) << 12) + | ((from[2] & 0x3f) << 6) | (from[3] & 0x3f); + n -= 0x10000; + to[0] = (unsigned short)((n >> 10) | 0xD800); + to[1] = (unsigned short)((n & 0x3FF) | 0xDC00); + to += 2; + from += 4; + } break; default: *to++ = *from++; break; @@ -450,56 +452,51 @@ after: } #ifdef XML_NS -static const struct normal_encoding utf8_encoding_ns = { - { VTABLE1, utf8_toUtf8, utf8_toUtf16, 1, 1, 0 }, - { -#include "asciitab.h" -#include "utf8tab.h" - }, - STANDARD_VTABLE(sb_) NORMAL_VTABLE(utf8_) -}; +static const struct normal_encoding utf8_encoding_ns + = {{VTABLE1, utf8_toUtf8, utf8_toUtf16, 1, 1, 0}, + { +# include "asciitab.h" +# include "utf8tab.h" + }, + STANDARD_VTABLE(sb_) NORMAL_VTABLE(utf8_)}; #endif -static const struct normal_encoding utf8_encoding = { - { VTABLE1, utf8_toUtf8, utf8_toUtf16, 1, 1, 0 }, - { +static const struct normal_encoding utf8_encoding + = {{VTABLE1, utf8_toUtf8, utf8_toUtf16, 1, 1, 0}, + { #define BT_COLON BT_NMSTRT #include "asciitab.h" #undef BT_COLON #include "utf8tab.h" - }, - STANDARD_VTABLE(sb_) NORMAL_VTABLE(utf8_) -}; + }, + STANDARD_VTABLE(sb_) NORMAL_VTABLE(utf8_)}; #ifdef XML_NS -static const struct normal_encoding internal_utf8_encoding_ns = { - { VTABLE1, utf8_toUtf8, utf8_toUtf16, 1, 1, 0 }, - { -#include "iasciitab.h" -#include "utf8tab.h" - }, - STANDARD_VTABLE(sb_) NORMAL_VTABLE(utf8_) -}; +static const struct normal_encoding internal_utf8_encoding_ns + = {{VTABLE1, utf8_toUtf8, utf8_toUtf16, 1, 1, 0}, + { +# include "iasciitab.h" +# include "utf8tab.h" + }, + STANDARD_VTABLE(sb_) NORMAL_VTABLE(utf8_)}; #endif -static const struct normal_encoding internal_utf8_encoding = { - { VTABLE1, utf8_toUtf8, utf8_toUtf16, 1, 1, 0 }, - { +static const struct normal_encoding internal_utf8_encoding + = {{VTABLE1, utf8_toUtf8, utf8_toUtf16, 1, 1, 0}, + { #define BT_COLON BT_NMSTRT #include "iasciitab.h" #undef BT_COLON #include "utf8tab.h" - }, - STANDARD_VTABLE(sb_) NORMAL_VTABLE(utf8_) -}; + }, + STANDARD_VTABLE(sb_) NORMAL_VTABLE(utf8_)}; static enum XML_Convert_Result PTRCALL -latin1_toUtf8(const ENCODING *UNUSED_P(enc), - const char **fromP, const char *fromLim, - char **toP, const char *toLim) -{ +latin1_toUtf8(const ENCODING *enc, const char **fromP, const char *fromLim, + char **toP, const char *toLim) { + UNUSED_P(enc); for (;;) { unsigned char c; if (*fromP == fromLim) @@ -511,8 +508,7 @@ latin1_toUtf8(const ENCODING *UNUSED_P(enc), *(*toP)++ = (char)((c >> 6) | UTF8_cval2); *(*toP)++ = (char)((c & 0x3f) | 0x80); (*fromP)++; - } - else { + } else { if (*toP == toLim) return XML_CONVERT_OUTPUT_EXHAUSTED; *(*toP)++ = *(*fromP)++; @@ -521,10 +517,9 @@ latin1_toUtf8(const ENCODING *UNUSED_P(enc), } static enum XML_Convert_Result PTRCALL -latin1_toUtf16(const ENCODING *UNUSED_P(enc), - const char **fromP, const char *fromLim, - unsigned short **toP, const unsigned short *toLim) -{ +latin1_toUtf16(const ENCODING *enc, const char **fromP, const char *fromLim, + unsigned short **toP, const unsigned short *toLim) { + UNUSED_P(enc); while (*fromP < fromLim && *toP < toLim) *(*toP)++ = (unsigned char)*(*fromP)++; @@ -536,33 +531,30 @@ latin1_toUtf16(const ENCODING *UNUSED_P(enc), #ifdef XML_NS -static const struct normal_encoding latin1_encoding_ns = { - { VTABLE1, latin1_toUtf8, latin1_toUtf16, 1, 0, 0 }, - { -#include "asciitab.h" -#include "latin1tab.h" - }, - STANDARD_VTABLE(sb_) NULL_VTABLE -}; +static const struct normal_encoding latin1_encoding_ns + = {{VTABLE1, latin1_toUtf8, latin1_toUtf16, 1, 0, 0}, + { +# include "asciitab.h" +# include "latin1tab.h" + }, + STANDARD_VTABLE(sb_) NULL_VTABLE}; #endif -static const struct normal_encoding latin1_encoding = { - { VTABLE1, latin1_toUtf8, latin1_toUtf16, 1, 0, 0 }, - { +static const struct normal_encoding latin1_encoding + = {{VTABLE1, latin1_toUtf8, latin1_toUtf16, 1, 0, 0}, + { #define BT_COLON BT_NMSTRT #include "asciitab.h" #undef BT_COLON #include "latin1tab.h" - }, - STANDARD_VTABLE(sb_) NULL_VTABLE -}; + }, + STANDARD_VTABLE(sb_) NULL_VTABLE}; static enum XML_Convert_Result PTRCALL -ascii_toUtf8(const ENCODING *UNUSED_P(enc), - const char **fromP, const char *fromLim, - char **toP, const char *toLim) -{ +ascii_toUtf8(const ENCODING *enc, const char **fromP, const char *fromLim, + char **toP, const char *toLim) { + UNUSED_P(enc); while (*fromP < fromLim && *toP < toLim) *(*toP)++ = *(*fromP)++; @@ -574,40 +566,45 @@ ascii_toUtf8(const ENCODING *UNUSED_P(enc), #ifdef XML_NS -static const struct normal_encoding ascii_encoding_ns = { - { VTABLE1, ascii_toUtf8, latin1_toUtf16, 1, 1, 0 }, - { -#include "asciitab.h" -/* BT_NONXML == 0 */ - }, - STANDARD_VTABLE(sb_) NULL_VTABLE -}; +static const struct normal_encoding ascii_encoding_ns + = {{VTABLE1, ascii_toUtf8, latin1_toUtf16, 1, 1, 0}, + { +# include "asciitab.h" + /* BT_NONXML == 0 */ + }, + STANDARD_VTABLE(sb_) NULL_VTABLE}; #endif -static const struct normal_encoding ascii_encoding = { - { VTABLE1, ascii_toUtf8, latin1_toUtf16, 1, 1, 0 }, - { +static const struct normal_encoding ascii_encoding + = {{VTABLE1, ascii_toUtf8, latin1_toUtf16, 1, 1, 0}, + { #define BT_COLON BT_NMSTRT #include "asciitab.h" #undef BT_COLON -/* BT_NONXML == 0 */ - }, - STANDARD_VTABLE(sb_) NULL_VTABLE -}; + /* BT_NONXML == 0 */ + }, + STANDARD_VTABLE(sb_) NULL_VTABLE}; static int PTRFASTCALL -unicode_byte_type(char hi, char lo) -{ +unicode_byte_type(char hi, char lo) { switch ((unsigned char)hi) { - case 0xD8: case 0xD9: case 0xDA: case 0xDB: + /* 0xD800–0xDBFF first 16-bit code unit or high surrogate (W1) */ + case 0xD8: + case 0xD9: + case 0xDA: + case 0xDB: return BT_LEAD4; - case 0xDC: case 0xDD: case 0xDE: case 0xDF: + /* 0xDC00–0xDFFF second 16-bit code unit or low surrogate (W2) */ + case 0xDC: + case 0xDD: + case 0xDE: + case 0xDF: return BT_TRAIL; case 0xFF: switch ((unsigned char)lo) { - case 0xFF: - case 0xFE: + case 0xFF: /* noncharacter-FFFF */ + case 0xFE: /* noncharacter-FFFE */ return BT_NONXML; } break; @@ -615,102 +612,105 @@ unicode_byte_type(char hi, char lo) return BT_NONASCII; } -#define DEFINE_UTF16_TO_UTF8(E) \ -static enum XML_Convert_Result PTRCALL \ -E ## toUtf8(const ENCODING *UNUSED_P(enc), \ - const char **fromP, const char *fromLim, \ - char **toP, const char *toLim) \ -{ \ - const char *from = *fromP; \ - fromLim = from + (((fromLim - from) >> 1) << 1); /* shrink to even */ \ - for (; from < fromLim; from += 2) { \ - int plane; \ - unsigned char lo2; \ - unsigned char lo = GET_LO(from); \ - unsigned char hi = GET_HI(from); \ - switch (hi) { \ - case 0: \ - if (lo < 0x80) { \ - if (*toP == toLim) { \ - *fromP = from; \ - return XML_CONVERT_OUTPUT_EXHAUSTED; \ - } \ - *(*toP)++ = lo; \ - break; \ - } \ - /* fall through */ \ - case 0x1: case 0x2: case 0x3: \ - case 0x4: case 0x5: case 0x6: case 0x7: \ - if (toLim - *toP < 2) { \ - *fromP = from; \ - return XML_CONVERT_OUTPUT_EXHAUSTED; \ - } \ - *(*toP)++ = ((lo >> 6) | (hi << 2) | UTF8_cval2); \ - *(*toP)++ = ((lo & 0x3f) | 0x80); \ - break; \ - default: \ - if (toLim - *toP < 3) { \ - *fromP = from; \ - return XML_CONVERT_OUTPUT_EXHAUSTED; \ - } \ - /* 16 bits divided 4, 6, 6 amongst 3 bytes */ \ - *(*toP)++ = ((hi >> 4) | UTF8_cval3); \ - *(*toP)++ = (((hi & 0xf) << 2) | (lo >> 6) | 0x80); \ - *(*toP)++ = ((lo & 0x3f) | 0x80); \ - break; \ - case 0xD8: case 0xD9: case 0xDA: case 0xDB: \ - if (toLim - *toP < 4) { \ - *fromP = from; \ - return XML_CONVERT_OUTPUT_EXHAUSTED; \ - } \ - if (fromLim - from < 4) { \ - *fromP = from; \ - return XML_CONVERT_INPUT_INCOMPLETE; \ - } \ - plane = (((hi & 0x3) << 2) | ((lo >> 6) & 0x3)) + 1; \ - *(*toP)++ = ((plane >> 2) | UTF8_cval4); \ - *(*toP)++ = (((lo >> 2) & 0xF) | ((plane & 0x3) << 4) | 0x80); \ - from += 2; \ - lo2 = GET_LO(from); \ - *(*toP)++ = (((lo & 0x3) << 4) \ - | ((GET_HI(from) & 0x3) << 2) \ - | (lo2 >> 6) \ - | 0x80); \ - *(*toP)++ = ((lo2 & 0x3f) | 0x80); \ - break; \ - } \ - } \ - *fromP = from; \ - if (from < fromLim) \ - return XML_CONVERT_INPUT_INCOMPLETE; \ - else \ - return XML_CONVERT_COMPLETED; \ -} +#define DEFINE_UTF16_TO_UTF8(E) \ + static enum XML_Convert_Result PTRCALL E##toUtf8( \ + const ENCODING *enc, const char **fromP, const char *fromLim, \ + char **toP, const char *toLim) { \ + const char *from = *fromP; \ + UNUSED_P(enc); \ + fromLim = from + (((fromLim - from) >> 1) << 1); /* shrink to even */ \ + for (; from < fromLim; from += 2) { \ + int plane; \ + unsigned char lo2; \ + unsigned char lo = GET_LO(from); \ + unsigned char hi = GET_HI(from); \ + switch (hi) { \ + case 0: \ + if (lo < 0x80) { \ + if (*toP == toLim) { \ + *fromP = from; \ + return XML_CONVERT_OUTPUT_EXHAUSTED; \ + } \ + *(*toP)++ = lo; \ + break; \ + } \ + /* fall through */ \ + case 0x1: \ + case 0x2: \ + case 0x3: \ + case 0x4: \ + case 0x5: \ + case 0x6: \ + case 0x7: \ + if (toLim - *toP < 2) { \ + *fromP = from; \ + return XML_CONVERT_OUTPUT_EXHAUSTED; \ + } \ + *(*toP)++ = ((lo >> 6) | (hi << 2) | UTF8_cval2); \ + *(*toP)++ = ((lo & 0x3f) | 0x80); \ + break; \ + default: \ + if (toLim - *toP < 3) { \ + *fromP = from; \ + return XML_CONVERT_OUTPUT_EXHAUSTED; \ + } \ + /* 16 bits divided 4, 6, 6 amongst 3 bytes */ \ + *(*toP)++ = ((hi >> 4) | UTF8_cval3); \ + *(*toP)++ = (((hi & 0xf) << 2) | (lo >> 6) | 0x80); \ + *(*toP)++ = ((lo & 0x3f) | 0x80); \ + break; \ + case 0xD8: \ + case 0xD9: \ + case 0xDA: \ + case 0xDB: \ + if (toLim - *toP < 4) { \ + *fromP = from; \ + return XML_CONVERT_OUTPUT_EXHAUSTED; \ + } \ + if (fromLim - from < 4) { \ + *fromP = from; \ + return XML_CONVERT_INPUT_INCOMPLETE; \ + } \ + plane = (((hi & 0x3) << 2) | ((lo >> 6) & 0x3)) + 1; \ + *(*toP)++ = (char)((plane >> 2) | UTF8_cval4); \ + *(*toP)++ = (((lo >> 2) & 0xF) | ((plane & 0x3) << 4) | 0x80); \ + from += 2; \ + lo2 = GET_LO(from); \ + *(*toP)++ = (((lo & 0x3) << 4) | ((GET_HI(from) & 0x3) << 2) \ + | (lo2 >> 6) | 0x80); \ + *(*toP)++ = ((lo2 & 0x3f) | 0x80); \ + break; \ + } \ + } \ + *fromP = from; \ + if (from < fromLim) \ + return XML_CONVERT_INPUT_INCOMPLETE; \ + else \ + return XML_CONVERT_COMPLETED; \ + } -#define DEFINE_UTF16_TO_UTF16(E) \ -static enum XML_Convert_Result PTRCALL \ -E ## toUtf16(const ENCODING *UNUSED_P(enc), \ - const char **fromP, const char *fromLim, \ - unsigned short **toP, const unsigned short *toLim) \ -{ \ - enum XML_Convert_Result res = XML_CONVERT_COMPLETED; \ - fromLim = *fromP + (((fromLim - *fromP) >> 1) << 1); /* shrink to even */ \ - /* Avoid copying first half only of surrogate */ \ - if (fromLim - *fromP > ((toLim - *toP) << 1) \ - && (GET_HI(fromLim - 2) & 0xF8) == 0xD8) { \ - fromLim -= 2; \ - res = XML_CONVERT_INPUT_INCOMPLETE; \ - } \ - for (; *fromP < fromLim && *toP < toLim; *fromP += 2) \ - *(*toP)++ = (GET_HI(*fromP) << 8) | GET_LO(*fromP); \ - if ((*toP == toLim) && (*fromP < fromLim)) \ - return XML_CONVERT_OUTPUT_EXHAUSTED; \ - else \ - return res; \ -} +#define DEFINE_UTF16_TO_UTF16(E) \ + static enum XML_Convert_Result PTRCALL E##toUtf16( \ + const ENCODING *enc, const char **fromP, const char *fromLim, \ + unsigned short **toP, const unsigned short *toLim) { \ + enum XML_Convert_Result res = XML_CONVERT_COMPLETED; \ + UNUSED_P(enc); \ + fromLim = *fromP + (((fromLim - *fromP) >> 1) << 1); /* shrink to even */ \ + /* Avoid copying first half only of surrogate */ \ + if (fromLim - *fromP > ((toLim - *toP) << 1) \ + && (GET_HI(fromLim - 2) & 0xF8) == 0xD8) { \ + fromLim -= 2; \ + res = XML_CONVERT_INPUT_INCOMPLETE; \ + } \ + for (; *fromP < fromLim && *toP < toLim; *fromP += 2) \ + *(*toP)++ = (GET_HI(*fromP) << 8) | GET_LO(*fromP); \ + if ((*toP == toLim) && (*fromP < fromLim)) \ + return XML_CONVERT_OUTPUT_EXHAUSTED; \ + else \ + return res; \ + } -#define SET2(ptr, ch) \ - (((ptr)[0] = ((ch) & 0xff)), ((ptr)[1] = ((ch) >> 8))) +#define SET2(ptr, ch) (((ptr)[0] = ((ch)&0xff)), ((ptr)[1] = ((ch) >> 8))) #define GET_LO(ptr) ((unsigned char)(ptr)[0]) #define GET_HI(ptr) ((unsigned char)(ptr)[1]) @@ -721,8 +721,7 @@ DEFINE_UTF16_TO_UTF16(little2_) #undef GET_LO #undef GET_HI -#define SET2(ptr, ch) \ - (((ptr)[0] = ((ch) >> 8)), ((ptr)[1] = ((ch) & 0xFF))) +#define SET2(ptr, ch) (((ptr)[0] = ((ch) >> 8)), ((ptr)[1] = ((ch)&0xFF))) #define GET_LO(ptr) ((unsigned char)(ptr)[1]) #define GET_HI(ptr) ((unsigned char)(ptr)[0]) @@ -733,317 +732,307 @@ DEFINE_UTF16_TO_UTF16(big2_) #undef GET_LO #undef GET_HI -#define LITTLE2_BYTE_TYPE(enc, p) \ - ((p)[1] == 0 \ - ? ((struct normal_encoding *)(enc))->type[(unsigned char)*(p)] \ - : unicode_byte_type((p)[1], (p)[0])) -#define LITTLE2_BYTE_TO_ASCII(enc, p) ((p)[1] == 0 ? (p)[0] : -1) -#define LITTLE2_CHAR_MATCHES(enc, p, c) ((p)[1] == 0 && (p)[0] == c) -#define LITTLE2_IS_NAME_CHAR_MINBPC(enc, p) \ +#define LITTLE2_BYTE_TYPE(enc, p) \ + ((p)[1] == 0 ? ((struct normal_encoding *)(enc))->type[(unsigned char)*(p)] \ + : unicode_byte_type((p)[1], (p)[0])) +#define LITTLE2_BYTE_TO_ASCII(p) ((p)[1] == 0 ? (p)[0] : -1) +#define LITTLE2_CHAR_MATCHES(p, c) ((p)[1] == 0 && (p)[0] == c) +#define LITTLE2_IS_NAME_CHAR_MINBPC(p) \ UCS2_GET_NAMING(namePages, (unsigned char)p[1], (unsigned char)p[0]) -#define LITTLE2_IS_NMSTRT_CHAR_MINBPC(enc, p) \ +#define LITTLE2_IS_NMSTRT_CHAR_MINBPC(p) \ UCS2_GET_NAMING(nmstrtPages, (unsigned char)p[1], (unsigned char)p[0]) #ifdef XML_MIN_SIZE static int PTRFASTCALL -little2_byteType(const ENCODING *enc, const char *p) -{ +little2_byteType(const ENCODING *enc, const char *p) { return LITTLE2_BYTE_TYPE(enc, p); } static int PTRFASTCALL -little2_byteToAscii(const ENCODING *enc, const char *p) -{ - return LITTLE2_BYTE_TO_ASCII(enc, p); +little2_byteToAscii(const ENCODING *enc, const char *p) { + UNUSED_P(enc); + return LITTLE2_BYTE_TO_ASCII(p); } static int PTRCALL -little2_charMatches(const ENCODING *enc, const char *p, int c) -{ - return LITTLE2_CHAR_MATCHES(enc, p, c); +little2_charMatches(const ENCODING *enc, const char *p, int c) { + UNUSED_P(enc); + return LITTLE2_CHAR_MATCHES(p, c); } static int PTRFASTCALL -little2_isNameMin(const ENCODING *enc, const char *p) -{ - return LITTLE2_IS_NAME_CHAR_MINBPC(enc, p); +little2_isNameMin(const ENCODING *enc, const char *p) { + UNUSED_P(enc); + return LITTLE2_IS_NAME_CHAR_MINBPC(p); } static int PTRFASTCALL -little2_isNmstrtMin(const ENCODING *enc, const char *p) -{ - return LITTLE2_IS_NMSTRT_CHAR_MINBPC(enc, p); +little2_isNmstrtMin(const ENCODING *enc, const char *p) { + UNUSED_P(enc); + return LITTLE2_IS_NMSTRT_CHAR_MINBPC(p); } -#undef VTABLE -#define VTABLE VTABLE1, little2_toUtf8, little2_toUtf16 +# undef VTABLE +# define VTABLE VTABLE1, little2_toUtf8, little2_toUtf16 #else /* not XML_MIN_SIZE */ -#undef PREFIX -#define PREFIX(ident) little2_ ## ident -#define MINBPC(enc) 2 +# undef PREFIX +# define PREFIX(ident) little2_##ident +# define MINBPC(enc) 2 /* CHAR_MATCHES is guaranteed to have MINBPC bytes available. */ -#define BYTE_TYPE(enc, p) LITTLE2_BYTE_TYPE(enc, p) -#define BYTE_TO_ASCII(enc, p) LITTLE2_BYTE_TO_ASCII(enc, p) -#define CHAR_MATCHES(enc, p, c) LITTLE2_CHAR_MATCHES(enc, p, c) -#define IS_NAME_CHAR(enc, p, n) 0 -#define IS_NAME_CHAR_MINBPC(enc, p) LITTLE2_IS_NAME_CHAR_MINBPC(enc, p) -#define IS_NMSTRT_CHAR(enc, p, n) (0) -#define IS_NMSTRT_CHAR_MINBPC(enc, p) LITTLE2_IS_NMSTRT_CHAR_MINBPC(enc, p) - -#define XML_TOK_IMPL_C -#include "xmltok_impl.c" -#undef XML_TOK_IMPL_C - -#undef MINBPC -#undef BYTE_TYPE -#undef BYTE_TO_ASCII -#undef CHAR_MATCHES -#undef IS_NAME_CHAR -#undef IS_NAME_CHAR_MINBPC -#undef IS_NMSTRT_CHAR -#undef IS_NMSTRT_CHAR_MINBPC -#undef IS_INVALID_CHAR +# define BYTE_TYPE(enc, p) LITTLE2_BYTE_TYPE(enc, p) +# define BYTE_TO_ASCII(enc, p) LITTLE2_BYTE_TO_ASCII(p) +# define CHAR_MATCHES(enc, p, c) LITTLE2_CHAR_MATCHES(p, c) +# define IS_NAME_CHAR(enc, p, n) 0 +# define IS_NAME_CHAR_MINBPC(enc, p) LITTLE2_IS_NAME_CHAR_MINBPC(p) +# define IS_NMSTRT_CHAR(enc, p, n) (0) +# define IS_NMSTRT_CHAR_MINBPC(enc, p) LITTLE2_IS_NMSTRT_CHAR_MINBPC(p) + +# define XML_TOK_IMPL_C +# include "xmltok_impl.c" +# undef XML_TOK_IMPL_C + +# undef MINBPC +# undef BYTE_TYPE +# undef BYTE_TO_ASCII +# undef CHAR_MATCHES +# undef IS_NAME_CHAR +# undef IS_NAME_CHAR_MINBPC +# undef IS_NMSTRT_CHAR +# undef IS_NMSTRT_CHAR_MINBPC +# undef IS_INVALID_CHAR #endif /* not XML_MIN_SIZE */ #ifdef XML_NS -static const struct normal_encoding little2_encoding_ns = { - { VTABLE, 2, 0, -#if BYTEORDER == 1234 - 1 -#else - 0 -#endif - }, - { -#include "asciitab.h" -#include "latin1tab.h" - }, - STANDARD_VTABLE(little2_) NULL_VTABLE -}; +static const struct normal_encoding little2_encoding_ns + = {{VTABLE, 2, 0, +# if BYTEORDER == 1234 + 1 +# else + 0 +# endif + }, + { +# include "asciitab.h" +# include "latin1tab.h" + }, + STANDARD_VTABLE(little2_) NULL_VTABLE}; #endif -static const struct normal_encoding little2_encoding = { - { VTABLE, 2, 0, +static const struct normal_encoding little2_encoding + = {{VTABLE, 2, 0, #if BYTEORDER == 1234 - 1 + 1 #else - 0 + 0 #endif - }, - { + }, + { #define BT_COLON BT_NMSTRT #include "asciitab.h" #undef BT_COLON #include "latin1tab.h" - }, - STANDARD_VTABLE(little2_) NULL_VTABLE -}; + }, + STANDARD_VTABLE(little2_) NULL_VTABLE}; #if BYTEORDER != 4321 -#ifdef XML_NS +# ifdef XML_NS -static const struct normal_encoding internal_little2_encoding_ns = { - { VTABLE, 2, 0, 1 }, - { -#include "iasciitab.h" -#include "latin1tab.h" - }, - STANDARD_VTABLE(little2_) NULL_VTABLE -}; +static const struct normal_encoding internal_little2_encoding_ns + = {{VTABLE, 2, 0, 1}, + { +# include "iasciitab.h" +# include "latin1tab.h" + }, + STANDARD_VTABLE(little2_) NULL_VTABLE}; -#endif +# endif -static const struct normal_encoding internal_little2_encoding = { - { VTABLE, 2, 0, 1 }, - { -#define BT_COLON BT_NMSTRT -#include "iasciitab.h" -#undef BT_COLON -#include "latin1tab.h" - }, - STANDARD_VTABLE(little2_) NULL_VTABLE -}; +static const struct normal_encoding internal_little2_encoding + = {{VTABLE, 2, 0, 1}, + { +# define BT_COLON BT_NMSTRT +# include "iasciitab.h" +# undef BT_COLON +# include "latin1tab.h" + }, + STANDARD_VTABLE(little2_) NULL_VTABLE}; #endif - -#define BIG2_BYTE_TYPE(enc, p) \ - ((p)[0] == 0 \ - ? ((struct normal_encoding *)(enc))->type[(unsigned char)(p)[1]] \ - : unicode_byte_type((p)[0], (p)[1])) -#define BIG2_BYTE_TO_ASCII(enc, p) ((p)[0] == 0 ? (p)[1] : -1) -#define BIG2_CHAR_MATCHES(enc, p, c) ((p)[0] == 0 && (p)[1] == c) -#define BIG2_IS_NAME_CHAR_MINBPC(enc, p) \ +#define BIG2_BYTE_TYPE(enc, p) \ + ((p)[0] == 0 \ + ? ((struct normal_encoding *)(enc))->type[(unsigned char)(p)[1]] \ + : unicode_byte_type((p)[0], (p)[1])) +#define BIG2_BYTE_TO_ASCII(p) ((p)[0] == 0 ? (p)[1] : -1) +#define BIG2_CHAR_MATCHES(p, c) ((p)[0] == 0 && (p)[1] == c) +#define BIG2_IS_NAME_CHAR_MINBPC(p) \ UCS2_GET_NAMING(namePages, (unsigned char)p[0], (unsigned char)p[1]) -#define BIG2_IS_NMSTRT_CHAR_MINBPC(enc, p) \ +#define BIG2_IS_NMSTRT_CHAR_MINBPC(p) \ UCS2_GET_NAMING(nmstrtPages, (unsigned char)p[0], (unsigned char)p[1]) #ifdef XML_MIN_SIZE static int PTRFASTCALL -big2_byteType(const ENCODING *enc, const char *p) -{ +big2_byteType(const ENCODING *enc, const char *p) { return BIG2_BYTE_TYPE(enc, p); } static int PTRFASTCALL -big2_byteToAscii(const ENCODING *enc, const char *p) -{ - return BIG2_BYTE_TO_ASCII(enc, p); +big2_byteToAscii(const ENCODING *enc, const char *p) { + UNUSED_P(enc); + return BIG2_BYTE_TO_ASCII(p); } static int PTRCALL -big2_charMatches(const ENCODING *enc, const char *p, int c) -{ - return BIG2_CHAR_MATCHES(enc, p, c); +big2_charMatches(const ENCODING *enc, const char *p, int c) { + UNUSED_P(enc); + return BIG2_CHAR_MATCHES(p, c); } static int PTRFASTCALL -big2_isNameMin(const ENCODING *enc, const char *p) -{ - return BIG2_IS_NAME_CHAR_MINBPC(enc, p); +big2_isNameMin(const ENCODING *enc, const char *p) { + UNUSED_P(enc); + return BIG2_IS_NAME_CHAR_MINBPC(p); } static int PTRFASTCALL -big2_isNmstrtMin(const ENCODING *enc, const char *p) -{ - return BIG2_IS_NMSTRT_CHAR_MINBPC(enc, p); +big2_isNmstrtMin(const ENCODING *enc, const char *p) { + UNUSED_P(enc); + return BIG2_IS_NMSTRT_CHAR_MINBPC(p); } -#undef VTABLE -#define VTABLE VTABLE1, big2_toUtf8, big2_toUtf16 +# undef VTABLE +# define VTABLE VTABLE1, big2_toUtf8, big2_toUtf16 #else /* not XML_MIN_SIZE */ -#undef PREFIX -#define PREFIX(ident) big2_ ## ident -#define MINBPC(enc) 2 +# undef PREFIX +# define PREFIX(ident) big2_##ident +# define MINBPC(enc) 2 /* CHAR_MATCHES is guaranteed to have MINBPC bytes available. */ -#define BYTE_TYPE(enc, p) BIG2_BYTE_TYPE(enc, p) -#define BYTE_TO_ASCII(enc, p) BIG2_BYTE_TO_ASCII(enc, p) -#define CHAR_MATCHES(enc, p, c) BIG2_CHAR_MATCHES(enc, p, c) -#define IS_NAME_CHAR(enc, p, n) 0 -#define IS_NAME_CHAR_MINBPC(enc, p) BIG2_IS_NAME_CHAR_MINBPC(enc, p) -#define IS_NMSTRT_CHAR(enc, p, n) (0) -#define IS_NMSTRT_CHAR_MINBPC(enc, p) BIG2_IS_NMSTRT_CHAR_MINBPC(enc, p) - -#define XML_TOK_IMPL_C -#include "xmltok_impl.c" -#undef XML_TOK_IMPL_C - -#undef MINBPC -#undef BYTE_TYPE -#undef BYTE_TO_ASCII -#undef CHAR_MATCHES -#undef IS_NAME_CHAR -#undef IS_NAME_CHAR_MINBPC -#undef IS_NMSTRT_CHAR -#undef IS_NMSTRT_CHAR_MINBPC -#undef IS_INVALID_CHAR +# define BYTE_TYPE(enc, p) BIG2_BYTE_TYPE(enc, p) +# define BYTE_TO_ASCII(enc, p) BIG2_BYTE_TO_ASCII(p) +# define CHAR_MATCHES(enc, p, c) BIG2_CHAR_MATCHES(p, c) +# define IS_NAME_CHAR(enc, p, n) 0 +# define IS_NAME_CHAR_MINBPC(enc, p) BIG2_IS_NAME_CHAR_MINBPC(p) +# define IS_NMSTRT_CHAR(enc, p, n) (0) +# define IS_NMSTRT_CHAR_MINBPC(enc, p) BIG2_IS_NMSTRT_CHAR_MINBPC(p) + +# define XML_TOK_IMPL_C +# include "xmltok_impl.c" +# undef XML_TOK_IMPL_C + +# undef MINBPC +# undef BYTE_TYPE +# undef BYTE_TO_ASCII +# undef CHAR_MATCHES +# undef IS_NAME_CHAR +# undef IS_NAME_CHAR_MINBPC +# undef IS_NMSTRT_CHAR +# undef IS_NMSTRT_CHAR_MINBPC +# undef IS_INVALID_CHAR #endif /* not XML_MIN_SIZE */ #ifdef XML_NS -static const struct normal_encoding big2_encoding_ns = { - { VTABLE, 2, 0, -#if BYTEORDER == 4321 - 1 -#else - 0 -#endif - }, - { -#include "asciitab.h" -#include "latin1tab.h" - }, - STANDARD_VTABLE(big2_) NULL_VTABLE -}; +static const struct normal_encoding big2_encoding_ns + = {{VTABLE, 2, 0, +# if BYTEORDER == 4321 + 1 +# else + 0 +# endif + }, + { +# include "asciitab.h" +# include "latin1tab.h" + }, + STANDARD_VTABLE(big2_) NULL_VTABLE}; #endif -static const struct normal_encoding big2_encoding = { - { VTABLE, 2, 0, +static const struct normal_encoding big2_encoding + = {{VTABLE, 2, 0, #if BYTEORDER == 4321 - 1 + 1 #else - 0 + 0 #endif - }, - { + }, + { #define BT_COLON BT_NMSTRT #include "asciitab.h" #undef BT_COLON #include "latin1tab.h" - }, - STANDARD_VTABLE(big2_) NULL_VTABLE -}; + }, + STANDARD_VTABLE(big2_) NULL_VTABLE}; #if BYTEORDER != 1234 -#ifdef XML_NS +# ifdef XML_NS -static const struct normal_encoding internal_big2_encoding_ns = { - { VTABLE, 2, 0, 1 }, - { -#include "iasciitab.h" -#include "latin1tab.h" - }, - STANDARD_VTABLE(big2_) NULL_VTABLE -}; +static const struct normal_encoding internal_big2_encoding_ns + = {{VTABLE, 2, 0, 1}, + { +# include "iasciitab.h" +# include "latin1tab.h" + }, + STANDARD_VTABLE(big2_) NULL_VTABLE}; -#endif +# endif -static const struct normal_encoding internal_big2_encoding = { - { VTABLE, 2, 0, 1 }, - { -#define BT_COLON BT_NMSTRT -#include "iasciitab.h" -#undef BT_COLON -#include "latin1tab.h" - }, - STANDARD_VTABLE(big2_) NULL_VTABLE -}; +static const struct normal_encoding internal_big2_encoding + = {{VTABLE, 2, 0, 1}, + { +# define BT_COLON BT_NMSTRT +# include "iasciitab.h" +# undef BT_COLON +# include "latin1tab.h" + }, + STANDARD_VTABLE(big2_) NULL_VTABLE}; #endif #undef PREFIX static int FASTCALL -streqci(const char *s1, const char *s2) -{ +streqci(const char *s1, const char *s2) { for (;;) { char c1 = *s1++; char c2 = *s2++; if (ASCII_a <= c1 && c1 <= ASCII_z) c1 += ASCII_A - ASCII_a; if (ASCII_a <= c2 && c2 <= ASCII_z) - c2 += ASCII_A - ASCII_a; + /* The following line will never get executed. streqci() is + * only called from two places, both of which guarantee to put + * upper-case strings into s2. + */ + c2 += ASCII_A - ASCII_a; /* LCOV_EXCL_LINE */ if (c1 != c2) return 0; - if (!c1) + if (! c1) break; } return 1; } static void PTRCALL -initUpdatePosition(const ENCODING *UNUSED_P(enc), const char *ptr, - const char *end, POSITION *pos) -{ +initUpdatePosition(const ENCODING *enc, const char *ptr, const char *end, + POSITION *pos) { + UNUSED_P(enc); normal_updatePosition(&utf8_encoding.enc, ptr, end, pos); } static int -toAscii(const ENCODING *enc, const char *ptr, const char *end) -{ +toAscii(const ENCODING *enc, const char *ptr, const char *end) { char buf[1]; char *p = buf; XmlUtf8Convert(enc, &ptr, end, &p, p + 1); @@ -1054,8 +1043,7 @@ toAscii(const ENCODING *enc, const char *ptr, const char *end) } static int FASTCALL -isSpace(int c) -{ +isSpace(int c) { switch (c) { case 0x20: case 0xD: @@ -1070,21 +1058,16 @@ isSpace(int c) followed by name=val. */ static int -parsePseudoAttribute(const ENCODING *enc, - const char *ptr, - const char *end, - const char **namePtr, - const char **nameEndPtr, - const char **valPtr, - const char **nextTokPtr) -{ +parsePseudoAttribute(const ENCODING *enc, const char *ptr, const char *end, + const char **namePtr, const char **nameEndPtr, + const char **valPtr, const char **nextTokPtr) { int c; char open; if (ptr == end) { *namePtr = NULL; return 1; } - if (!isSpace(toAscii(enc, ptr, end))) { + if (! isSpace(toAscii(enc, ptr, end))) { *nextTokPtr = ptr; return 0; } @@ -1140,12 +1123,9 @@ parsePseudoAttribute(const ENCODING *enc, c = toAscii(enc, ptr, end); if (c == open) break; - if (!(ASCII_a <= c && c <= ASCII_z) - && !(ASCII_A <= c && c <= ASCII_Z) - && !(ASCII_0 <= c && c <= ASCII_9) - && c != ASCII_PERIOD - && c != ASCII_MINUS - && c != ASCII_UNDERSCORE) { + if (! (ASCII_a <= c && c <= ASCII_z) && ! (ASCII_A <= c && c <= ASCII_Z) + && ! (ASCII_0 <= c && c <= ASCII_9) && c != ASCII_PERIOD + && c != ASCII_MINUS && c != ASCII_UNDERSCORE) { *nextTokPtr = ptr; return 0; } @@ -1154,68 +1134,52 @@ parsePseudoAttribute(const ENCODING *enc, return 1; } -static const char KW_version[] = { - ASCII_v, ASCII_e, ASCII_r, ASCII_s, ASCII_i, ASCII_o, ASCII_n, '\0' -}; +static const char KW_version[] + = {ASCII_v, ASCII_e, ASCII_r, ASCII_s, ASCII_i, ASCII_o, ASCII_n, '\0'}; -static const char KW_encoding[] = { - ASCII_e, ASCII_n, ASCII_c, ASCII_o, ASCII_d, ASCII_i, ASCII_n, ASCII_g, '\0' -}; +static const char KW_encoding[] = {ASCII_e, ASCII_n, ASCII_c, ASCII_o, ASCII_d, + ASCII_i, ASCII_n, ASCII_g, '\0'}; -static const char KW_standalone[] = { - ASCII_s, ASCII_t, ASCII_a, ASCII_n, ASCII_d, ASCII_a, ASCII_l, ASCII_o, - ASCII_n, ASCII_e, '\0' -}; +static const char KW_standalone[] + = {ASCII_s, ASCII_t, ASCII_a, ASCII_n, ASCII_d, ASCII_a, + ASCII_l, ASCII_o, ASCII_n, ASCII_e, '\0'}; -static const char KW_yes[] = { - ASCII_y, ASCII_e, ASCII_s, '\0' -}; +static const char KW_yes[] = {ASCII_y, ASCII_e, ASCII_s, '\0'}; -static const char KW_no[] = { - ASCII_n, ASCII_o, '\0' -}; +static const char KW_no[] = {ASCII_n, ASCII_o, '\0'}; static int -doParseXmlDecl(const ENCODING *(*encodingFinder)(const ENCODING *, - const char *, +doParseXmlDecl(const ENCODING *(*encodingFinder)(const ENCODING *, const char *, const char *), - int isGeneralTextEntity, - const ENCODING *enc, - const char *ptr, - const char *end, - const char **badPtr, - const char **versionPtr, - const char **versionEndPtr, - const char **encodingName, - const ENCODING **encoding, - int *standalone) -{ + int isGeneralTextEntity, const ENCODING *enc, const char *ptr, + const char *end, const char **badPtr, const char **versionPtr, + const char **versionEndPtr, const char **encodingName, + const ENCODING **encoding, int *standalone) { const char *val = NULL; const char *name = NULL; const char *nameEnd = NULL; ptr += 5 * enc->minBytesPerChar; end -= 2 * enc->minBytesPerChar; - if (!parsePseudoAttribute(enc, ptr, end, &name, &nameEnd, &val, &ptr) - || !name) { + if (! parsePseudoAttribute(enc, ptr, end, &name, &nameEnd, &val, &ptr) + || ! name) { *badPtr = ptr; return 0; } - if (!XmlNameMatchesAscii(enc, name, nameEnd, KW_version)) { - if (!isGeneralTextEntity) { + if (! XmlNameMatchesAscii(enc, name, nameEnd, KW_version)) { + if (! isGeneralTextEntity) { *badPtr = name; return 0; } - } - else { + } else { if (versionPtr) *versionPtr = val; if (versionEndPtr) *versionEndPtr = ptr; - if (!parsePseudoAttribute(enc, ptr, end, &name, &nameEnd, &val, &ptr)) { + if (! parsePseudoAttribute(enc, ptr, end, &name, &nameEnd, &val, &ptr)) { *badPtr = ptr; return 0; } - if (!name) { + if (! name) { if (isGeneralTextEntity) { /* a TextDecl must have an EncodingDecl */ *badPtr = ptr; @@ -1226,7 +1190,7 @@ doParseXmlDecl(const ENCODING *(*encodingFinder)(const ENCODING *, } if (XmlNameMatchesAscii(enc, name, nameEnd, KW_encoding)) { int c = toAscii(enc, val, end); - if (!(ASCII_a <= c && c <= ASCII_z) && !(ASCII_A <= c && c <= ASCII_Z)) { + if (! (ASCII_a <= c && c <= ASCII_z) && ! (ASCII_A <= c && c <= ASCII_Z)) { *badPtr = val; return 0; } @@ -1234,14 +1198,14 @@ doParseXmlDecl(const ENCODING *(*encodingFinder)(const ENCODING *, *encodingName = val; if (encoding) *encoding = encodingFinder(enc, val, ptr - enc->minBytesPerChar); - if (!parsePseudoAttribute(enc, ptr, end, &name, &nameEnd, &val, &ptr)) { + if (! parsePseudoAttribute(enc, ptr, end, &name, &nameEnd, &val, &ptr)) { *badPtr = ptr; return 0; } - if (!name) + if (! name) return 1; } - if (!XmlNameMatchesAscii(enc, name, nameEnd, KW_standalone) + if (! XmlNameMatchesAscii(enc, name, nameEnd, KW_standalone) || isGeneralTextEntity) { *badPtr = name; return 0; @@ -1249,12 +1213,10 @@ doParseXmlDecl(const ENCODING *(*encodingFinder)(const ENCODING *, if (XmlNameMatchesAscii(enc, val, ptr - enc->minBytesPerChar, KW_yes)) { if (standalone) *standalone = 1; - } - else if (XmlNameMatchesAscii(enc, val, ptr - enc->minBytesPerChar, KW_no)) { + } else if (XmlNameMatchesAscii(enc, val, ptr - enc->minBytesPerChar, KW_no)) { if (standalone) *standalone = 0; - } - else { + } else { *badPtr = val; return 0; } @@ -1268,11 +1230,16 @@ doParseXmlDecl(const ENCODING *(*encodingFinder)(const ENCODING *, } static int FASTCALL -checkCharRefNumber(int result) -{ +checkCharRefNumber(int result) { switch (result >> 8) { - case 0xD8: case 0xD9: case 0xDA: case 0xDB: - case 0xDC: case 0xDD: case 0xDE: case 0xDF: + case 0xD8: + case 0xD9: + case 0xDA: + case 0xDB: + case 0xDC: + case 0xDD: + case 0xDE: + case 0xDF: return -1; case 0: if (latin1_encoding.type[result] == BT_NONXML) @@ -1287,8 +1254,7 @@ checkCharRefNumber(int result) } int FASTCALL -XmlUtf8Encode(int c, char *buf) -{ +XmlUtf8Encode(int c, char *buf) { enum { /* minN is minimum legal resulting value for N byte sequence */ min2 = 0x80, @@ -1297,7 +1263,7 @@ XmlUtf8Encode(int c, char *buf) }; if (c < 0) - return 0; + return 0; /* LCOV_EXCL_LINE: this case is always eliminated beforehand */ if (c < min2) { buf[0] = (char)(c | UTF8_cval1); return 1; @@ -1320,12 +1286,11 @@ XmlUtf8Encode(int c, char *buf) buf[3] = (char)((c & 0x3f) | 0x80); return 4; } - return 0; + return 0; /* LCOV_EXCL_LINE: this case too is eliminated before calling */ } int FASTCALL -XmlUtf16Encode(int charNum, unsigned short *buf) -{ +XmlUtf16Encode(int charNum, unsigned short *buf) { if (charNum < 0) return 0; if (charNum < 0x10000) { @@ -1349,17 +1314,15 @@ struct unknown_encoding { char utf8[256][4]; }; -#define AS_UNKNOWN_ENCODING(enc) ((const struct unknown_encoding *) (enc)) +#define AS_UNKNOWN_ENCODING(enc) ((const struct unknown_encoding *)(enc)) int -XmlSizeOfUnknownEncoding(void) -{ +XmlSizeOfUnknownEncoding(void) { return sizeof(struct unknown_encoding); } static int PTRFASTCALL -unknown_isName(const ENCODING *enc, const char *p) -{ +unknown_isName(const ENCODING *enc, const char *p) { const struct unknown_encoding *uenc = AS_UNKNOWN_ENCODING(enc); int c = uenc->convert(uenc->userData, p); if (c & ~0xFFFF) @@ -1368,8 +1331,7 @@ unknown_isName(const ENCODING *enc, const char *p) } static int PTRFASTCALL -unknown_isNmstrt(const ENCODING *enc, const char *p) -{ +unknown_isNmstrt(const ENCODING *enc, const char *p) { const struct unknown_encoding *uenc = AS_UNKNOWN_ENCODING(enc); int c = uenc->convert(uenc->userData, p); if (c & ~0xFFFF) @@ -1378,18 +1340,15 @@ unknown_isNmstrt(const ENCODING *enc, const char *p) } static int PTRFASTCALL -unknown_isInvalid(const ENCODING *enc, const char *p) -{ +unknown_isInvalid(const ENCODING *enc, const char *p) { const struct unknown_encoding *uenc = AS_UNKNOWN_ENCODING(enc); int c = uenc->convert(uenc->userData, p); return (c & ~0xFFFF) || checkCharRefNumber(c) < 0; } static enum XML_Convert_Result PTRCALL -unknown_toUtf8(const ENCODING *enc, - const char **fromP, const char *fromLim, - char **toP, const char *toLim) -{ +unknown_toUtf8(const ENCODING *enc, const char **fromP, const char *fromLim, + char **toP, const char *toLim) { const struct unknown_encoding *uenc = AS_UNKNOWN_ENCODING(enc); char buf[XML_UTF8_ENCODE_MAX]; for (;;) { @@ -1407,33 +1366,27 @@ unknown_toUtf8(const ENCODING *enc, utf8 = buf; *fromP += (AS_NORMAL_ENCODING(enc)->type[(unsigned char)**fromP] - (BT_LEAD2 - 2)); - } - else { + } else { if (n > toLim - *toP) return XML_CONVERT_OUTPUT_EXHAUSTED; (*fromP)++; } - do { - *(*toP)++ = *utf8++; - } while (--n != 0); + memcpy(*toP, utf8, n); + *toP += n; } } static enum XML_Convert_Result PTRCALL -unknown_toUtf16(const ENCODING *enc, - const char **fromP, const char *fromLim, - unsigned short **toP, const unsigned short *toLim) -{ +unknown_toUtf16(const ENCODING *enc, const char **fromP, const char *fromLim, + unsigned short **toP, const unsigned short *toLim) { const struct unknown_encoding *uenc = AS_UNKNOWN_ENCODING(enc); while (*fromP < fromLim && *toP < toLim) { unsigned short c = uenc->utf16[(unsigned char)**fromP]; if (c == 0) { - c = (unsigned short) - uenc->convert(uenc->userData, *fromP); + c = (unsigned short)uenc->convert(uenc->userData, *fromP); *fromP += (AS_NORMAL_ENCODING(enc)->type[(unsigned char)**fromP] - (BT_LEAD2 - 2)); - } - else + } else (*fromP)++; *(*toP)++ = c; } @@ -1445,19 +1398,14 @@ unknown_toUtf16(const ENCODING *enc, } ENCODING * -XmlInitUnknownEncoding(void *mem, - int *table, - CONVERTER convert, - void *userData) -{ +XmlInitUnknownEncoding(void *mem, int *table, CONVERTER convert, + void *userData) { int i; struct unknown_encoding *e = (struct unknown_encoding *)mem; - for (i = 0; i < (int)sizeof(struct normal_encoding); i++) - ((char *)mem)[i] = ((char *)&latin1_encoding)[i]; + memcpy(mem, &latin1_encoding, sizeof(struct normal_encoding)); for (i = 0; i < 128; i++) if (latin1_encoding.type[i] != BT_OTHER - && latin1_encoding.type[i] != BT_NONXML - && table[i] != i) + && latin1_encoding.type[i] != BT_NONXML && table[i] != i) return 0; for (i = 0; i < 256; i++) { int c = table[i]; @@ -1467,32 +1415,30 @@ XmlInitUnknownEncoding(void *mem, e->utf16[i] = 0xFFFF; e->utf8[i][0] = 1; e->utf8[i][1] = 0; - } - else if (c < 0) { + } else if (c < 0) { if (c < -4) return 0; + /* Multi-byte sequences need a converter function */ + if (! convert) + return 0; e->normal.type[i] = (unsigned char)(BT_LEAD2 - (c + 2)); e->utf8[i][0] = 0; e->utf16[i] = 0; - } - else if (c < 0x80) { + } else if (c < 0x80) { if (latin1_encoding.type[c] != BT_OTHER - && latin1_encoding.type[c] != BT_NONXML - && c != i) + && latin1_encoding.type[c] != BT_NONXML && c != i) return 0; e->normal.type[i] = latin1_encoding.type[c]; e->utf8[i][0] = 1; e->utf8[i][1] = (char)c; e->utf16[i] = (unsigned short)(c == 0 ? 0xFFFF : c); - } - else if (checkCharRefNumber(c) < 0) { + } else if (checkCharRefNumber(c) < 0) { e->normal.type[i] = BT_NONXML; /* This shouldn't really get used. */ e->utf16[i] = 0xFFFF; e->utf8[i][0] = 1; e->utf8[i][1] = 0; - } - else { + } else { if (c > 0xFFFF) return 0; if (UCS2_GET_NAMING(nmstrtPages, c >> 8, c & 0xff)) @@ -1537,44 +1483,32 @@ enum { NO_ENC }; -static const char KW_ISO_8859_1[] = { - ASCII_I, ASCII_S, ASCII_O, ASCII_MINUS, ASCII_8, ASCII_8, ASCII_5, ASCII_9, - ASCII_MINUS, ASCII_1, '\0' -}; -static const char KW_US_ASCII[] = { - ASCII_U, ASCII_S, ASCII_MINUS, ASCII_A, ASCII_S, ASCII_C, ASCII_I, ASCII_I, - '\0' -}; -static const char KW_UTF_8[] = { - ASCII_U, ASCII_T, ASCII_F, ASCII_MINUS, ASCII_8, '\0' -}; -static const char KW_UTF_16[] = { - ASCII_U, ASCII_T, ASCII_F, ASCII_MINUS, ASCII_1, ASCII_6, '\0' -}; -static const char KW_UTF_16BE[] = { - ASCII_U, ASCII_T, ASCII_F, ASCII_MINUS, ASCII_1, ASCII_6, ASCII_B, ASCII_E, - '\0' -}; -static const char KW_UTF_16LE[] = { - ASCII_U, ASCII_T, ASCII_F, ASCII_MINUS, ASCII_1, ASCII_6, ASCII_L, ASCII_E, - '\0' -}; +static const char KW_ISO_8859_1[] + = {ASCII_I, ASCII_S, ASCII_O, ASCII_MINUS, ASCII_8, ASCII_8, + ASCII_5, ASCII_9, ASCII_MINUS, ASCII_1, '\0'}; +static const char KW_US_ASCII[] + = {ASCII_U, ASCII_S, ASCII_MINUS, ASCII_A, ASCII_S, + ASCII_C, ASCII_I, ASCII_I, '\0'}; +static const char KW_UTF_8[] + = {ASCII_U, ASCII_T, ASCII_F, ASCII_MINUS, ASCII_8, '\0'}; +static const char KW_UTF_16[] + = {ASCII_U, ASCII_T, ASCII_F, ASCII_MINUS, ASCII_1, ASCII_6, '\0'}; +static const char KW_UTF_16BE[] + = {ASCII_U, ASCII_T, ASCII_F, ASCII_MINUS, ASCII_1, + ASCII_6, ASCII_B, ASCII_E, '\0'}; +static const char KW_UTF_16LE[] + = {ASCII_U, ASCII_T, ASCII_F, ASCII_MINUS, ASCII_1, + ASCII_6, ASCII_L, ASCII_E, '\0'}; static int FASTCALL -getEncodingIndex(const char *name) -{ - static const char * const encodingNames[] = { - KW_ISO_8859_1, - KW_US_ASCII, - KW_UTF_8, - KW_UTF_16, - KW_UTF_16BE, - KW_UTF_16LE, +getEncodingIndex(const char *name) { + static const char *const encodingNames[] = { + KW_ISO_8859_1, KW_US_ASCII, KW_UTF_8, KW_UTF_16, KW_UTF_16BE, KW_UTF_16LE, }; int i; if (name == NULL) return NO_ENC; - for (i = 0; i < (int)(sizeof(encodingNames)/sizeof(encodingNames[0])); i++) + for (i = 0; i < (int)(sizeof(encodingNames) / sizeof(encodingNames[0])); i++) if (streqci(name, encodingNames[i])) return i; return UNKNOWN_ENC; @@ -1594,15 +1528,9 @@ getEncodingIndex(const char *name) XML_PROLOG_STATE otherwise. */ - static int -initScan(const ENCODING * const *encodingTable, - const INIT_ENCODING *enc, - int state, - const char *ptr, - const char *end, - const char **nextTokPtr) -{ +initScan(const ENCODING *const *encodingTable, const INIT_ENCODING *enc, + int state, const char *ptr, const char *end, const char **nextTokPtr) { const ENCODING **encPtr; if (ptr >= end) @@ -1627,20 +1555,17 @@ initScan(const ENCODING * const *encodingTable, case 0xFE: case 0xFF: case 0xEF: /* possibly first byte of UTF-8 BOM */ - if (INIT_ENC_INDEX(enc) == ISO_8859_1_ENC - && state == XML_CONTENT_STATE) + if (INIT_ENC_INDEX(enc) == ISO_8859_1_ENC && state == XML_CONTENT_STATE) break; /* fall through */ case 0x00: case 0x3C: return XML_TOK_PARTIAL; } - } - else { + } else { switch (((unsigned char)ptr[0] << 8) | (unsigned char)ptr[1]) { case 0xFEFF: - if (INIT_ENC_INDEX(enc) == ISO_8859_1_ENC - && state == XML_CONTENT_STATE) + if (INIT_ENC_INDEX(enc) == ISO_8859_1_ENC && state == XML_CONTENT_STATE) break; *nextTokPtr = ptr + 2; *encPtr = encodingTable[UTF_16BE_ENC]; @@ -1654,8 +1579,7 @@ initScan(const ENCODING * const *encodingTable, *encPtr = encodingTable[UTF_16LE_ENC]; return XmlTok(*encPtr, state, ptr, end, nextTokPtr); case 0xFFFE: - if (INIT_ENC_INDEX(enc) == ISO_8859_1_ENC - && state == XML_CONTENT_STATE) + if (INIT_ENC_INDEX(enc) == ISO_8859_1_ENC && state == XML_CONTENT_STATE) break; *nextTokPtr = ptr + 2; *encPtr = encodingTable[UTF_16LE_ENC]; @@ -1670,8 +1594,8 @@ initScan(const ENCODING * const *encodingTable, */ if (state == XML_CONTENT_STATE) { int e = INIT_ENC_INDEX(enc); - if (e == ISO_8859_1_ENC || e == UTF_16BE_ENC - || e == UTF_16LE_ENC || e == UTF_16_ENC) + if (e == ISO_8859_1_ENC || e == UTF_16BE_ENC || e == UTF_16LE_ENC + || e == UTF_16_ENC) break; } if (ptr + 2 == end) @@ -1694,8 +1618,7 @@ initScan(const ENCODING * const *encodingTable, break; *encPtr = encodingTable[UTF_16BE_ENC]; return XmlTok(*encPtr, state, ptr, end, nextTokPtr); - } - else if (ptr[1] == '\0') { + } else if (ptr[1] == '\0') { /* We could recover here in the case: - parsing an external entity - second byte is 0 @@ -1717,7 +1640,6 @@ initScan(const ENCODING * const *encodingTable, return XmlTok(*encPtr, state, ptr, end, nextTokPtr); } - #define NS(x) x #define ns(x) x #define XML_TOK_NS_C @@ -1728,22 +1650,19 @@ initScan(const ENCODING * const *encodingTable, #ifdef XML_NS -#define NS(x) x ## NS -#define ns(x) x ## _ns +# define NS(x) x##NS +# define ns(x) x##_ns -#define XML_TOK_NS_C -#include "xmltok_ns.c" -#undef XML_TOK_NS_C +# define XML_TOK_NS_C +# include "xmltok_ns.c" +# undef XML_TOK_NS_C -#undef NS -#undef ns +# undef NS +# undef ns ENCODING * -XmlInitUnknownEncodingNS(void *mem, - int *table, - CONVERTER convert, - void *userData) -{ +XmlInitUnknownEncodingNS(void *mem, int *table, CONVERTER convert, + void *userData) { ENCODING *enc = XmlInitUnknownEncoding(mem, table, convert, userData); if (enc) ((struct normal_encoding *)enc)->type[ASCII_COLON] = BT_COLON; diff --git a/chromium/third_party/expat/files/lib/xmltok.h b/chromium/third_party/expat/files/lib/xmltok.h index 752007e8b9e..2adbf5307be 100644 --- a/chromium/third_party/expat/files/lib/xmltok.h +++ b/chromium/third_party/expat/files/lib/xmltok.h @@ -1,5 +1,33 @@ -/* Copyright (c) 1998, 1999 Thai Open Source Software Center Ltd - See the file COPYING for copying permission. +/* + __ __ _ + ___\ \/ /_ __ __ _| |_ + / _ \\ /| '_ \ / _` | __| + | __// \| |_) | (_| | |_ + \___/_/\_\ .__/ \__,_|\__| + |_| XML parser + + Copyright (c) 1997-2000 Thai Open Source Software Center Ltd + Copyright (c) 2000-2017 Expat development team + Licensed under the MIT license: + + Permission is hereby granted, free of charge, to any person obtaining + a copy of this software and associated documentation files (the + "Software"), to deal in the Software without restriction, including + without limitation the rights to use, copy, modify, merge, publish, + distribute, sublicense, and/or sell copies of the Software, and to permit + persons to whom the Software is furnished to do so, subject to the + following conditions: + + The above copyright notice and this permission notice shall be included + in all copies or substantial portions of the Software. + + THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN + NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, + DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR + OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE + USE OR OTHER DEALINGS IN THE SOFTWARE. */ #ifndef XmlTok_INCLUDED @@ -10,16 +38,18 @@ extern "C" { #endif /* The following token may be returned by XmlContentTok */ -#define XML_TOK_TRAILING_RSQB -5 /* ] or ]] at the end of the scan; might be - start of illegal ]]> sequence */ +#define XML_TOK_TRAILING_RSQB \ + -5 /* ] or ]] at the end of the scan; might be \ + start of illegal ]]> sequence */ /* The following tokens may be returned by both XmlPrologTok and XmlContentTok. */ -#define XML_TOK_NONE -4 /* The string to be scanned is empty */ -#define XML_TOK_TRAILING_CR -3 /* A CR at the end of the scan; - might be part of CRLF sequence */ -#define XML_TOK_PARTIAL_CHAR -2 /* only part of a multibyte sequence */ -#define XML_TOK_PARTIAL -1 /* only part of a token */ +#define XML_TOK_NONE -4 /* The string to be scanned is empty */ +#define XML_TOK_TRAILING_CR \ + -3 /* A CR at the end of the scan; \ + might be part of CRLF sequence */ +#define XML_TOK_PARTIAL_CHAR -2 /* only part of a multibyte sequence */ +#define XML_TOK_PARTIAL -1 /* only part of a token */ #define XML_TOK_INVALID 0 /* The following tokens are returned by XmlContentTok; some are also @@ -34,24 +64,24 @@ extern "C" { #define XML_TOK_DATA_NEWLINE 7 #define XML_TOK_CDATA_SECT_OPEN 8 #define XML_TOK_ENTITY_REF 9 -#define XML_TOK_CHAR_REF 10 /* numeric character reference */ +#define XML_TOK_CHAR_REF 10 /* numeric character reference */ /* The following tokens may be returned by both XmlPrologTok and XmlContentTok. */ -#define XML_TOK_PI 11 /* processing instruction */ -#define XML_TOK_XML_DECL 12 /* XML decl or text decl */ +#define XML_TOK_PI 11 /* processing instruction */ +#define XML_TOK_XML_DECL 12 /* XML decl or text decl */ #define XML_TOK_COMMENT 13 -#define XML_TOK_BOM 14 /* Byte order mark */ +#define XML_TOK_BOM 14 /* Byte order mark */ /* The following tokens are returned only by XmlPrologTok */ #define XML_TOK_PROLOG_S 15 -#define XML_TOK_DECL_OPEN 16 /* <!foo */ -#define XML_TOK_DECL_CLOSE 17 /* > */ +#define XML_TOK_DECL_OPEN 16 /* <!foo */ +#define XML_TOK_DECL_CLOSE 17 /* > */ #define XML_TOK_NAME 18 #define XML_TOK_NMTOKEN 19 -#define XML_TOK_POUND_NAME 20 /* #name */ -#define XML_TOK_OR 21 /* | */ +#define XML_TOK_POUND_NAME 20 /* #name */ +#define XML_TOK_OR 21 /* | */ #define XML_TOK_PERCENT 22 #define XML_TOK_OPEN_PAREN 23 #define XML_TOK_CLOSE_PAREN 24 @@ -62,14 +92,14 @@ extern "C" { #define XML_TOK_INSTANCE_START 29 /* The following occur only in element type declarations */ -#define XML_TOK_NAME_QUESTION 30 /* name? */ -#define XML_TOK_NAME_ASTERISK 31 /* name* */ -#define XML_TOK_NAME_PLUS 32 /* name+ */ -#define XML_TOK_COND_SECT_OPEN 33 /* <![ */ -#define XML_TOK_COND_SECT_CLOSE 34 /* ]]> */ -#define XML_TOK_CLOSE_PAREN_QUESTION 35 /* )? */ -#define XML_TOK_CLOSE_PAREN_ASTERISK 36 /* )* */ -#define XML_TOK_CLOSE_PAREN_PLUS 37 /* )+ */ +#define XML_TOK_NAME_QUESTION 30 /* name? */ +#define XML_TOK_NAME_ASTERISK 31 /* name* */ +#define XML_TOK_NAME_PLUS 32 /* name+ */ +#define XML_TOK_COND_SECT_OPEN 33 /* <![ */ +#define XML_TOK_COND_SECT_CLOSE 34 /* ]]> */ +#define XML_TOK_CLOSE_PAREN_QUESTION 35 /* )? */ +#define XML_TOK_CLOSE_PAREN_ASTERISK 36 /* )* */ +#define XML_TOK_CLOSE_PAREN_PLUS 37 /* )+ */ #define XML_TOK_COMMA 38 /* The following token is returned only by XmlAttributeValueTok */ @@ -84,20 +114,20 @@ extern "C" { #define XML_TOK_PREFIXED_NAME 41 #ifdef XML_DTD -#define XML_TOK_IGNORE_SECT 42 +# define XML_TOK_IGNORE_SECT 42 #endif /* XML_DTD */ #ifdef XML_DTD -#define XML_N_STATES 4 +# define XML_N_STATES 4 #else /* not XML_DTD */ -#define XML_N_STATES 3 +# define XML_N_STATES 3 #endif /* not XML_DTD */ #define XML_PROLOG_STATE 0 #define XML_CONTENT_STATE 1 #define XML_CDATA_SECTION_STATE 2 #ifdef XML_DTD -#define XML_IGNORE_SECTION_STATE 3 +# define XML_IGNORE_SECTION_STATE 3 #endif /* XML_DTD */ #define XML_N_LITERAL_TYPES 2 @@ -125,55 +155,41 @@ typedef struct { struct encoding; typedef struct encoding ENCODING; -typedef int (PTRCALL *SCANNER)(const ENCODING *, - const char *, - const char *, - const char **); +typedef int(PTRCALL *SCANNER)(const ENCODING *, const char *, const char *, + const char **); enum XML_Convert_Result { XML_CONVERT_COMPLETED = 0, XML_CONVERT_INPUT_INCOMPLETE = 1, - XML_CONVERT_OUTPUT_EXHAUSTED = 2 /* and therefore potentially input remaining as well */ + XML_CONVERT_OUTPUT_EXHAUSTED + = 2 /* and therefore potentially input remaining as well */ }; struct encoding { SCANNER scanners[XML_N_STATES]; SCANNER literalScanners[XML_N_LITERAL_TYPES]; - int (PTRCALL *sameName)(const ENCODING *, - const char *, - const char *); - int (PTRCALL *nameMatchesAscii)(const ENCODING *, - const char *, - const char *, - const char *); - int (PTRFASTCALL *nameLength)(const ENCODING *, const char *); + int(PTRCALL *nameMatchesAscii)(const ENCODING *, const char *, const char *, + const char *); + int(PTRFASTCALL *nameLength)(const ENCODING *, const char *); const char *(PTRFASTCALL *skipS)(const ENCODING *, const char *); - int (PTRCALL *getAtts)(const ENCODING *enc, - const char *ptr, - int attsMax, - ATTRIBUTE *atts); - int (PTRFASTCALL *charRefNumber)(const ENCODING *enc, const char *ptr); - int (PTRCALL *predefinedEntityName)(const ENCODING *, - const char *, - const char *); - void (PTRCALL *updatePosition)(const ENCODING *, - const char *ptr, - const char *end, - POSITION *); - int (PTRCALL *isPublicId)(const ENCODING *enc, - const char *ptr, - const char *end, - const char **badPtr); - enum XML_Convert_Result (PTRCALL *utf8Convert)(const ENCODING *enc, - const char **fromP, - const char *fromLim, - char **toP, - const char *toLim); - enum XML_Convert_Result (PTRCALL *utf16Convert)(const ENCODING *enc, - const char **fromP, - const char *fromLim, - unsigned short **toP, - const unsigned short *toLim); + int(PTRCALL *getAtts)(const ENCODING *enc, const char *ptr, int attsMax, + ATTRIBUTE *atts); + int(PTRFASTCALL *charRefNumber)(const ENCODING *enc, const char *ptr); + int(PTRCALL *predefinedEntityName)(const ENCODING *, const char *, + const char *); + void(PTRCALL *updatePosition)(const ENCODING *, const char *ptr, + const char *end, POSITION *); + int(PTRCALL *isPublicId)(const ENCODING *enc, const char *ptr, + const char *end, const char **badPtr); + enum XML_Convert_Result(PTRCALL *utf8Convert)(const ENCODING *enc, + const char **fromP, + const char *fromLim, char **toP, + const char *toLim); + enum XML_Convert_Result(PTRCALL *utf16Convert)(const ENCODING *enc, + const char **fromP, + const char *fromLim, + unsigned short **toP, + const unsigned short *toLim); int minBytesPerChar; char isUtf8; char isUtf16; @@ -200,68 +216,62 @@ struct encoding { the prolog outside literals, comments and processing instructions. */ - -#define XmlTok(enc, state, ptr, end, nextTokPtr) \ +#define XmlTok(enc, state, ptr, end, nextTokPtr) \ (((enc)->scanners[state])(enc, ptr, end, nextTokPtr)) -#define XmlPrologTok(enc, ptr, end, nextTokPtr) \ - XmlTok(enc, XML_PROLOG_STATE, ptr, end, nextTokPtr) +#define XmlPrologTok(enc, ptr, end, nextTokPtr) \ + XmlTok(enc, XML_PROLOG_STATE, ptr, end, nextTokPtr) -#define XmlContentTok(enc, ptr, end, nextTokPtr) \ - XmlTok(enc, XML_CONTENT_STATE, ptr, end, nextTokPtr) +#define XmlContentTok(enc, ptr, end, nextTokPtr) \ + XmlTok(enc, XML_CONTENT_STATE, ptr, end, nextTokPtr) -#define XmlCdataSectionTok(enc, ptr, end, nextTokPtr) \ - XmlTok(enc, XML_CDATA_SECTION_STATE, ptr, end, nextTokPtr) +#define XmlCdataSectionTok(enc, ptr, end, nextTokPtr) \ + XmlTok(enc, XML_CDATA_SECTION_STATE, ptr, end, nextTokPtr) #ifdef XML_DTD -#define XmlIgnoreSectionTok(enc, ptr, end, nextTokPtr) \ - XmlTok(enc, XML_IGNORE_SECTION_STATE, ptr, end, nextTokPtr) +# define XmlIgnoreSectionTok(enc, ptr, end, nextTokPtr) \ + XmlTok(enc, XML_IGNORE_SECTION_STATE, ptr, end, nextTokPtr) #endif /* XML_DTD */ /* This is used for performing a 2nd-level tokenization on the content of a literal that has already been returned by XmlTok. */ -#define XmlLiteralTok(enc, literalType, ptr, end, nextTokPtr) \ +#define XmlLiteralTok(enc, literalType, ptr, end, nextTokPtr) \ (((enc)->literalScanners[literalType])(enc, ptr, end, nextTokPtr)) -#define XmlAttributeValueTok(enc, ptr, end, nextTokPtr) \ - XmlLiteralTok(enc, XML_ATTRIBUTE_VALUE_LITERAL, ptr, end, nextTokPtr) - -#define XmlEntityValueTok(enc, ptr, end, nextTokPtr) \ - XmlLiteralTok(enc, XML_ENTITY_VALUE_LITERAL, ptr, end, nextTokPtr) +#define XmlAttributeValueTok(enc, ptr, end, nextTokPtr) \ + XmlLiteralTok(enc, XML_ATTRIBUTE_VALUE_LITERAL, ptr, end, nextTokPtr) -#define XmlSameName(enc, ptr1, ptr2) (((enc)->sameName)(enc, ptr1, ptr2)) +#define XmlEntityValueTok(enc, ptr, end, nextTokPtr) \ + XmlLiteralTok(enc, XML_ENTITY_VALUE_LITERAL, ptr, end, nextTokPtr) -#define XmlNameMatchesAscii(enc, ptr1, end1, ptr2) \ +#define XmlNameMatchesAscii(enc, ptr1, end1, ptr2) \ (((enc)->nameMatchesAscii)(enc, ptr1, end1, ptr2)) -#define XmlNameLength(enc, ptr) \ - (((enc)->nameLength)(enc, ptr)) +#define XmlNameLength(enc, ptr) (((enc)->nameLength)(enc, ptr)) -#define XmlSkipS(enc, ptr) \ - (((enc)->skipS)(enc, ptr)) +#define XmlSkipS(enc, ptr) (((enc)->skipS)(enc, ptr)) -#define XmlGetAttributes(enc, ptr, attsMax, atts) \ +#define XmlGetAttributes(enc, ptr, attsMax, atts) \ (((enc)->getAtts)(enc, ptr, attsMax, atts)) -#define XmlCharRefNumber(enc, ptr) \ - (((enc)->charRefNumber)(enc, ptr)) +#define XmlCharRefNumber(enc, ptr) (((enc)->charRefNumber)(enc, ptr)) -#define XmlPredefinedEntityName(enc, ptr, end) \ +#define XmlPredefinedEntityName(enc, ptr, end) \ (((enc)->predefinedEntityName)(enc, ptr, end)) -#define XmlUpdatePosition(enc, ptr, end, pos) \ +#define XmlUpdatePosition(enc, ptr, end, pos) \ (((enc)->updatePosition)(enc, ptr, end, pos)) -#define XmlIsPublicId(enc, ptr, end, badPtr) \ +#define XmlIsPublicId(enc, ptr, end, badPtr) \ (((enc)->isPublicId)(enc, ptr, end, badPtr)) -#define XmlUtf8Convert(enc, fromP, fromLim, toP, toLim) \ +#define XmlUtf8Convert(enc, fromP, fromLim, toP, toLim) \ (((enc)->utf8Convert)(enc, fromP, fromLim, toP, toLim)) -#define XmlUtf16Convert(enc, fromP, fromLim, toP, toLim) \ +#define XmlUtf16Convert(enc, fromP, fromLim, toP, toLim) \ (((enc)->utf16Convert)(enc, fromP, fromLim, toP, toLim)) typedef struct { @@ -269,16 +279,11 @@ typedef struct { const ENCODING **encPtr; } INIT_ENCODING; -int XmlParseXmlDecl(int isGeneralTextEntity, - const ENCODING *enc, - const char *ptr, - const char *end, - const char **badPtr, - const char **versionPtr, - const char **versionEndPtr, +int XmlParseXmlDecl(int isGeneralTextEntity, const ENCODING *enc, + const char *ptr, const char *end, const char **badPtr, + const char **versionPtr, const char **versionEndPtr, const char **encodingNamePtr, - const ENCODING **namedEncodingPtr, - int *standalonePtr); + const ENCODING **namedEncodingPtr, int *standalonePtr); int XmlInitEncoding(INIT_ENCODING *, const ENCODING **, const char *name); const ENCODING *XmlGetUtf8InternalEncoding(void); @@ -287,34 +292,22 @@ int FASTCALL XmlUtf8Encode(int charNumber, char *buf); int FASTCALL XmlUtf16Encode(int charNumber, unsigned short *buf); int XmlSizeOfUnknownEncoding(void); +typedef int(XMLCALL *CONVERTER)(void *userData, const char *p); -typedef int (XMLCALL *CONVERTER) (void *userData, const char *p); - -ENCODING * -XmlInitUnknownEncoding(void *mem, - int *table, - CONVERTER convert, - void *userData); +ENCODING *XmlInitUnknownEncoding(void *mem, int *table, CONVERTER convert, + void *userData); -int XmlParseXmlDeclNS(int isGeneralTextEntity, - const ENCODING *enc, - const char *ptr, - const char *end, - const char **badPtr, - const char **versionPtr, - const char **versionEndPtr, +int XmlParseXmlDeclNS(int isGeneralTextEntity, const ENCODING *enc, + const char *ptr, const char *end, const char **badPtr, + const char **versionPtr, const char **versionEndPtr, const char **encodingNamePtr, - const ENCODING **namedEncodingPtr, - int *standalonePtr); + const ENCODING **namedEncodingPtr, int *standalonePtr); int XmlInitEncodingNS(INIT_ENCODING *, const ENCODING **, const char *name); const ENCODING *XmlGetUtf8InternalEncodingNS(void); const ENCODING *XmlGetUtf16InternalEncodingNS(void); -ENCODING * -XmlInitUnknownEncodingNS(void *mem, - int *table, - CONVERTER convert, - void *userData); +ENCODING *XmlInitUnknownEncodingNS(void *mem, int *table, CONVERTER convert, + void *userData); #ifdef __cplusplus } #endif diff --git a/chromium/third_party/expat/files/lib/xmltok_impl.c b/chromium/third_party/expat/files/lib/xmltok_impl.c index 5f779c0571b..c209221cd79 100644 --- a/chromium/third_party/expat/files/lib/xmltok_impl.c +++ b/chromium/third_party/expat/files/lib/xmltok_impl.c @@ -1,132 +1,155 @@ -/* Copyright (c) 1998, 1999 Thai Open Source Software Center Ltd - See the file COPYING for copying permission. +/* This file is included! + __ __ _ + ___\ \/ /_ __ __ _| |_ + / _ \\ /| '_ \ / _` | __| + | __// \| |_) | (_| | |_ + \___/_/\_\ .__/ \__,_|\__| + |_| XML parser + + Copyright (c) 1997-2000 Thai Open Source Software Center Ltd + Copyright (c) 2000-2017 Expat development team + Licensed under the MIT license: + + Permission is hereby granted, free of charge, to any person obtaining + a copy of this software and associated documentation files (the + "Software"), to deal in the Software without restriction, including + without limitation the rights to use, copy, modify, merge, publish, + distribute, sublicense, and/or sell copies of the Software, and to permit + persons to whom the Software is furnished to do so, subject to the + following conditions: + + The above copyright notice and this permission notice shall be included + in all copies or substantial portions of the Software. + + THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN + NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, + DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR + OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE + USE OR OTHER DEALINGS IN THE SOFTWARE. */ -/* This file is included! */ #ifdef XML_TOK_IMPL_C -#ifndef IS_INVALID_CHAR -#define IS_INVALID_CHAR(enc, ptr, n) (0) -#endif +# ifndef IS_INVALID_CHAR +# define IS_INVALID_CHAR(enc, ptr, n) (0) +# endif -#define INVALID_LEAD_CASE(n, ptr, nextTokPtr) \ - case BT_LEAD ## n: \ - if (end - ptr < n) \ - return XML_TOK_PARTIAL_CHAR; \ - if (IS_INVALID_CHAR(enc, ptr, n)) { \ - *(nextTokPtr) = (ptr); \ - return XML_TOK_INVALID; \ - } \ - ptr += n; \ - break; +# define INVALID_LEAD_CASE(n, ptr, nextTokPtr) \ + case BT_LEAD##n: \ + if (end - ptr < n) \ + return XML_TOK_PARTIAL_CHAR; \ + if (IS_INVALID_CHAR(enc, ptr, n)) { \ + *(nextTokPtr) = (ptr); \ + return XML_TOK_INVALID; \ + } \ + ptr += n; \ + break; -#define INVALID_CASES(ptr, nextTokPtr) \ - INVALID_LEAD_CASE(2, ptr, nextTokPtr) \ - INVALID_LEAD_CASE(3, ptr, nextTokPtr) \ - INVALID_LEAD_CASE(4, ptr, nextTokPtr) \ - case BT_NONXML: \ - case BT_MALFORM: \ - case BT_TRAIL: \ - *(nextTokPtr) = (ptr); \ +# define INVALID_CASES(ptr, nextTokPtr) \ + INVALID_LEAD_CASE(2, ptr, nextTokPtr) \ + INVALID_LEAD_CASE(3, ptr, nextTokPtr) \ + INVALID_LEAD_CASE(4, ptr, nextTokPtr) \ + case BT_NONXML: \ + case BT_MALFORM: \ + case BT_TRAIL: \ + *(nextTokPtr) = (ptr); \ return XML_TOK_INVALID; -#define CHECK_NAME_CASE(n, enc, ptr, end, nextTokPtr) \ - case BT_LEAD ## n: \ - if (end - ptr < n) \ - return XML_TOK_PARTIAL_CHAR; \ - if (!IS_NAME_CHAR(enc, ptr, n)) { \ - *nextTokPtr = ptr; \ - return XML_TOK_INVALID; \ - } \ - ptr += n; \ - break; - -#define CHECK_NAME_CASES(enc, ptr, end, nextTokPtr) \ - case BT_NONASCII: \ - if (!IS_NAME_CHAR_MINBPC(enc, ptr)) { \ - *nextTokPtr = ptr; \ - return XML_TOK_INVALID; \ - } \ - case BT_NMSTRT: \ - case BT_HEX: \ - case BT_DIGIT: \ - case BT_NAME: \ - case BT_MINUS: \ - ptr += MINBPC(enc); \ - break; \ - CHECK_NAME_CASE(2, enc, ptr, end, nextTokPtr) \ - CHECK_NAME_CASE(3, enc, ptr, end, nextTokPtr) \ - CHECK_NAME_CASE(4, enc, ptr, end, nextTokPtr) +# define CHECK_NAME_CASE(n, enc, ptr, end, nextTokPtr) \ + case BT_LEAD##n: \ + if (end - ptr < n) \ + return XML_TOK_PARTIAL_CHAR; \ + if (! IS_NAME_CHAR(enc, ptr, n)) { \ + *nextTokPtr = ptr; \ + return XML_TOK_INVALID; \ + } \ + ptr += n; \ + break; -#define CHECK_NMSTRT_CASE(n, enc, ptr, end, nextTokPtr) \ - case BT_LEAD ## n: \ - if (end - ptr < n) \ - return XML_TOK_PARTIAL_CHAR; \ - if (!IS_NMSTRT_CHAR(enc, ptr, n)) { \ - *nextTokPtr = ptr; \ - return XML_TOK_INVALID; \ - } \ - ptr += n; \ - break; +# define CHECK_NAME_CASES(enc, ptr, end, nextTokPtr) \ + case BT_NONASCII: \ + if (! IS_NAME_CHAR_MINBPC(enc, ptr)) { \ + *nextTokPtr = ptr; \ + return XML_TOK_INVALID; \ + } \ + /* fall through */ \ + case BT_NMSTRT: \ + case BT_HEX: \ + case BT_DIGIT: \ + case BT_NAME: \ + case BT_MINUS: \ + ptr += MINBPC(enc); \ + break; \ + CHECK_NAME_CASE(2, enc, ptr, end, nextTokPtr) \ + CHECK_NAME_CASE(3, enc, ptr, end, nextTokPtr) \ + CHECK_NAME_CASE(4, enc, ptr, end, nextTokPtr) -#define CHECK_NMSTRT_CASES(enc, ptr, end, nextTokPtr) \ - case BT_NONASCII: \ - if (!IS_NMSTRT_CHAR_MINBPC(enc, ptr)) { \ - *nextTokPtr = ptr; \ - return XML_TOK_INVALID; \ - } \ - case BT_NMSTRT: \ - case BT_HEX: \ - ptr += MINBPC(enc); \ - break; \ - CHECK_NMSTRT_CASE(2, enc, ptr, end, nextTokPtr) \ - CHECK_NMSTRT_CASE(3, enc, ptr, end, nextTokPtr) \ - CHECK_NMSTRT_CASE(4, enc, ptr, end, nextTokPtr) +# define CHECK_NMSTRT_CASE(n, enc, ptr, end, nextTokPtr) \ + case BT_LEAD##n: \ + if (end - ptr < n) \ + return XML_TOK_PARTIAL_CHAR; \ + if (! IS_NMSTRT_CHAR(enc, ptr, n)) { \ + *nextTokPtr = ptr; \ + return XML_TOK_INVALID; \ + } \ + ptr += n; \ + break; -#ifndef PREFIX -#define PREFIX(ident) ident -#endif +# define CHECK_NMSTRT_CASES(enc, ptr, end, nextTokPtr) \ + case BT_NONASCII: \ + if (! IS_NMSTRT_CHAR_MINBPC(enc, ptr)) { \ + *nextTokPtr = ptr; \ + return XML_TOK_INVALID; \ + } \ + /* fall through */ \ + case BT_NMSTRT: \ + case BT_HEX: \ + ptr += MINBPC(enc); \ + break; \ + CHECK_NMSTRT_CASE(2, enc, ptr, end, nextTokPtr) \ + CHECK_NMSTRT_CASE(3, enc, ptr, end, nextTokPtr) \ + CHECK_NMSTRT_CASE(4, enc, ptr, end, nextTokPtr) +# ifndef PREFIX +# define PREFIX(ident) ident +# endif -#define HAS_CHARS(enc, ptr, end, count) \ - (end - ptr >= count * MINBPC(enc)) +# define HAS_CHARS(enc, ptr, end, count) (end - ptr >= count * MINBPC(enc)) -#define HAS_CHAR(enc, ptr, end) \ - HAS_CHARS(enc, ptr, end, 1) +# define HAS_CHAR(enc, ptr, end) HAS_CHARS(enc, ptr, end, 1) -#define REQUIRE_CHARS(enc, ptr, end, count) \ - { \ - if (! HAS_CHARS(enc, ptr, end, count)) { \ - return XML_TOK_PARTIAL; \ - } \ +# define REQUIRE_CHARS(enc, ptr, end, count) \ + { \ + if (! HAS_CHARS(enc, ptr, end, count)) { \ + return XML_TOK_PARTIAL; \ + } \ } -#define REQUIRE_CHAR(enc, ptr, end) \ - REQUIRE_CHARS(enc, ptr, end, 1) - +# define REQUIRE_CHAR(enc, ptr, end) REQUIRE_CHARS(enc, ptr, end, 1) /* ptr points to character following "<!-" */ static int PTRCALL -PREFIX(scanComment)(const ENCODING *enc, const char *ptr, - const char *end, const char **nextTokPtr) -{ +PREFIX(scanComment)(const ENCODING *enc, const char *ptr, const char *end, + const char **nextTokPtr) { if (HAS_CHAR(enc, ptr, end)) { - if (!CHAR_MATCHES(enc, ptr, ASCII_MINUS)) { + if (! CHAR_MATCHES(enc, ptr, ASCII_MINUS)) { *nextTokPtr = ptr; return XML_TOK_INVALID; } ptr += MINBPC(enc); while (HAS_CHAR(enc, ptr, end)) { switch (BYTE_TYPE(enc, ptr)) { - INVALID_CASES(ptr, nextTokPtr) + INVALID_CASES(ptr, nextTokPtr) case BT_MINUS: ptr += MINBPC(enc); REQUIRE_CHAR(enc, ptr, end); if (CHAR_MATCHES(enc, ptr, ASCII_MINUS)) { ptr += MINBPC(enc); REQUIRE_CHAR(enc, ptr, end); - if (!CHAR_MATCHES(enc, ptr, ASCII_GT)) { + if (! CHAR_MATCHES(enc, ptr, ASCII_GT)) { *nextTokPtr = ptr; return XML_TOK_INVALID; } @@ -146,9 +169,8 @@ PREFIX(scanComment)(const ENCODING *enc, const char *ptr, /* ptr points to character following "<!" */ static int PTRCALL -PREFIX(scanDecl)(const ENCODING *enc, const char *ptr, - const char *end, const char **nextTokPtr) -{ +PREFIX(scanDecl)(const ENCODING *enc, const char *ptr, const char *end, + const char **nextTokPtr) { REQUIRE_CHAR(enc, ptr, end); switch (BYTE_TYPE(enc, ptr)) { case BT_MINUS: @@ -170,12 +192,17 @@ PREFIX(scanDecl)(const ENCODING *enc, const char *ptr, REQUIRE_CHARS(enc, ptr, end, 2); /* don't allow <!ENTITY% foo "whatever"> */ switch (BYTE_TYPE(enc, ptr + MINBPC(enc))) { - case BT_S: case BT_CR: case BT_LF: case BT_PERCNT: + case BT_S: + case BT_CR: + case BT_LF: + case BT_PERCNT: *nextTokPtr = ptr; return XML_TOK_INVALID; } /* fall through */ - case BT_S: case BT_CR: case BT_LF: + case BT_S: + case BT_CR: + case BT_LF: *nextTokPtr = ptr; return XML_TOK_DECL_OPEN; case BT_NMSTRT: @@ -191,12 +218,12 @@ PREFIX(scanDecl)(const ENCODING *enc, const char *ptr, } static int PTRCALL -PREFIX(checkPiTarget)(const ENCODING *UNUSED_P(enc), const char *ptr, - const char *end, int *tokPtr) -{ +PREFIX(checkPiTarget)(const ENCODING *enc, const char *ptr, const char *end, + int *tokPtr) { int upper = 0; + UNUSED_P(enc); *tokPtr = XML_TOK_PI; - if (end - ptr != MINBPC(enc)*3) + if (end - ptr != MINBPC(enc) * 3) return 1; switch (BYTE_TO_ASCII(enc, ptr)) { case ASCII_x: @@ -236,30 +263,31 @@ PREFIX(checkPiTarget)(const ENCODING *UNUSED_P(enc), const char *ptr, /* ptr points to character following "<?" */ static int PTRCALL -PREFIX(scanPi)(const ENCODING *enc, const char *ptr, - const char *end, const char **nextTokPtr) -{ +PREFIX(scanPi)(const ENCODING *enc, const char *ptr, const char *end, + const char **nextTokPtr) { int tok; const char *target = ptr; REQUIRE_CHAR(enc, ptr, end); switch (BYTE_TYPE(enc, ptr)) { - CHECK_NMSTRT_CASES(enc, ptr, end, nextTokPtr) + CHECK_NMSTRT_CASES(enc, ptr, end, nextTokPtr) default: *nextTokPtr = ptr; return XML_TOK_INVALID; } while (HAS_CHAR(enc, ptr, end)) { switch (BYTE_TYPE(enc, ptr)) { - CHECK_NAME_CASES(enc, ptr, end, nextTokPtr) - case BT_S: case BT_CR: case BT_LF: - if (!PREFIX(checkPiTarget)(enc, target, ptr, &tok)) { + CHECK_NAME_CASES(enc, ptr, end, nextTokPtr) + case BT_S: + case BT_CR: + case BT_LF: + if (! PREFIX(checkPiTarget)(enc, target, ptr, &tok)) { *nextTokPtr = ptr; return XML_TOK_INVALID; } ptr += MINBPC(enc); while (HAS_CHAR(enc, ptr, end)) { switch (BYTE_TYPE(enc, ptr)) { - INVALID_CASES(ptr, nextTokPtr) + INVALID_CASES(ptr, nextTokPtr) case BT_QUEST: ptr += MINBPC(enc); REQUIRE_CHAR(enc, ptr, end); @@ -275,7 +303,7 @@ PREFIX(scanPi)(const ENCODING *enc, const char *ptr, } return XML_TOK_PARTIAL; case BT_QUEST: - if (!PREFIX(checkPiTarget)(enc, target, ptr, &tok)) { + if (! PREFIX(checkPiTarget)(enc, target, ptr, &tok)) { *nextTokPtr = ptr; return XML_TOK_INVALID; } @@ -295,16 +323,16 @@ PREFIX(scanPi)(const ENCODING *enc, const char *ptr, } static int PTRCALL -PREFIX(scanCdataSection)(const ENCODING *UNUSED_P(enc), const char *ptr, - const char *end, const char **nextTokPtr) -{ - static const char CDATA_LSQB[] = { ASCII_C, ASCII_D, ASCII_A, - ASCII_T, ASCII_A, ASCII_LSQB }; +PREFIX(scanCdataSection)(const ENCODING *enc, const char *ptr, const char *end, + const char **nextTokPtr) { + static const char CDATA_LSQB[] + = {ASCII_C, ASCII_D, ASCII_A, ASCII_T, ASCII_A, ASCII_LSQB}; int i; + UNUSED_P(enc); /* CDATA[ */ REQUIRE_CHARS(enc, ptr, end, 6); for (i = 0; i < 6; i++, ptr += MINBPC(enc)) { - if (!CHAR_MATCHES(enc, ptr, CDATA_LSQB[i])) { + if (! CHAR_MATCHES(enc, ptr, CDATA_LSQB[i])) { *nextTokPtr = ptr; return XML_TOK_INVALID; } @@ -314,9 +342,8 @@ PREFIX(scanCdataSection)(const ENCODING *UNUSED_P(enc), const char *ptr, } static int PTRCALL -PREFIX(cdataSectionTok)(const ENCODING *enc, const char *ptr, - const char *end, const char **nextTokPtr) -{ +PREFIX(cdataSectionTok)(const ENCODING *enc, const char *ptr, const char *end, + const char **nextTokPtr) { if (ptr >= end) return XML_TOK_NONE; if (MINBPC(enc) > 1) { @@ -332,11 +359,11 @@ PREFIX(cdataSectionTok)(const ENCODING *enc, const char *ptr, case BT_RSQB: ptr += MINBPC(enc); REQUIRE_CHAR(enc, ptr, end); - if (!CHAR_MATCHES(enc, ptr, ASCII_RSQB)) + if (! CHAR_MATCHES(enc, ptr, ASCII_RSQB)) break; ptr += MINBPC(enc); REQUIRE_CHAR(enc, ptr, end); - if (!CHAR_MATCHES(enc, ptr, ASCII_GT)) { + if (! CHAR_MATCHES(enc, ptr, ASCII_GT)) { ptr -= MINBPC(enc); break; } @@ -352,23 +379,25 @@ PREFIX(cdataSectionTok)(const ENCODING *enc, const char *ptr, case BT_LF: *nextTokPtr = ptr + MINBPC(enc); return XML_TOK_DATA_NEWLINE; - INVALID_CASES(ptr, nextTokPtr) + INVALID_CASES(ptr, nextTokPtr) default: ptr += MINBPC(enc); break; } while (HAS_CHAR(enc, ptr, end)) { switch (BYTE_TYPE(enc, ptr)) { -#define LEAD_CASE(n) \ - case BT_LEAD ## n: \ - if (end - ptr < n || IS_INVALID_CHAR(enc, ptr, n)) { \ - *nextTokPtr = ptr; \ - return XML_TOK_DATA_CHARS; \ - } \ - ptr += n; \ - break; - LEAD_CASE(2) LEAD_CASE(3) LEAD_CASE(4) -#undef LEAD_CASE +# define LEAD_CASE(n) \ + case BT_LEAD##n: \ + if (end - ptr < n || IS_INVALID_CHAR(enc, ptr, n)) { \ + *nextTokPtr = ptr; \ + return XML_TOK_DATA_CHARS; \ + } \ + ptr += n; \ + break; + LEAD_CASE(2) + LEAD_CASE(3) + LEAD_CASE(4) +# undef LEAD_CASE case BT_NONXML: case BT_MALFORM: case BT_TRAIL: @@ -389,23 +418,26 @@ PREFIX(cdataSectionTok)(const ENCODING *enc, const char *ptr, /* ptr points to character following "</" */ static int PTRCALL -PREFIX(scanEndTag)(const ENCODING *enc, const char *ptr, - const char *end, const char **nextTokPtr) -{ +PREFIX(scanEndTag)(const ENCODING *enc, const char *ptr, const char *end, + const char **nextTokPtr) { REQUIRE_CHAR(enc, ptr, end); switch (BYTE_TYPE(enc, ptr)) { - CHECK_NMSTRT_CASES(enc, ptr, end, nextTokPtr) + CHECK_NMSTRT_CASES(enc, ptr, end, nextTokPtr) default: *nextTokPtr = ptr; return XML_TOK_INVALID; } while (HAS_CHAR(enc, ptr, end)) { switch (BYTE_TYPE(enc, ptr)) { - CHECK_NAME_CASES(enc, ptr, end, nextTokPtr) - case BT_S: case BT_CR: case BT_LF: + CHECK_NAME_CASES(enc, ptr, end, nextTokPtr) + case BT_S: + case BT_CR: + case BT_LF: for (ptr += MINBPC(enc); HAS_CHAR(enc, ptr, end); ptr += MINBPC(enc)) { switch (BYTE_TYPE(enc, ptr)) { - case BT_S: case BT_CR: case BT_LF: + case BT_S: + case BT_CR: + case BT_LF: break; case BT_GT: *nextTokPtr = ptr + MINBPC(enc); @@ -416,13 +448,13 @@ PREFIX(scanEndTag)(const ENCODING *enc, const char *ptr, } } return XML_TOK_PARTIAL; -#ifdef XML_NS +# ifdef XML_NS case BT_COLON: /* no need to check qname syntax here, since end-tag must match exactly */ ptr += MINBPC(enc); break; -#endif +# endif case BT_GT: *nextTokPtr = ptr + MINBPC(enc); return XML_TOK_END_TAG; @@ -437,9 +469,8 @@ PREFIX(scanEndTag)(const ENCODING *enc, const char *ptr, /* ptr points to character following "&#X" */ static int PTRCALL -PREFIX(scanHexCharRef)(const ENCODING *enc, const char *ptr, - const char *end, const char **nextTokPtr) -{ +PREFIX(scanHexCharRef)(const ENCODING *enc, const char *ptr, const char *end, + const char **nextTokPtr) { if (HAS_CHAR(enc, ptr, end)) { switch (BYTE_TYPE(enc, ptr)) { case BT_DIGIT: @@ -469,9 +500,8 @@ PREFIX(scanHexCharRef)(const ENCODING *enc, const char *ptr, /* ptr points to character following "&#" */ static int PTRCALL -PREFIX(scanCharRef)(const ENCODING *enc, const char *ptr, - const char *end, const char **nextTokPtr) -{ +PREFIX(scanCharRef)(const ENCODING *enc, const char *ptr, const char *end, + const char **nextTokPtr) { if (HAS_CHAR(enc, ptr, end)) { if (CHAR_MATCHES(enc, ptr, ASCII_x)) return PREFIX(scanHexCharRef)(enc, ptr + MINBPC(enc), end, nextTokPtr); @@ -502,11 +532,10 @@ PREFIX(scanCharRef)(const ENCODING *enc, const char *ptr, static int PTRCALL PREFIX(scanRef)(const ENCODING *enc, const char *ptr, const char *end, - const char **nextTokPtr) -{ + const char **nextTokPtr) { REQUIRE_CHAR(enc, ptr, end); switch (BYTE_TYPE(enc, ptr)) { - CHECK_NMSTRT_CASES(enc, ptr, end, nextTokPtr) + CHECK_NMSTRT_CASES(enc, ptr, end, nextTokPtr) case BT_NUM: return PREFIX(scanCharRef)(enc, ptr + MINBPC(enc), end, nextTokPtr); default: @@ -515,7 +544,7 @@ PREFIX(scanRef)(const ENCODING *enc, const char *ptr, const char *end, } while (HAS_CHAR(enc, ptr, end)) { switch (BYTE_TYPE(enc, ptr)) { - CHECK_NAME_CASES(enc, ptr, end, nextTokPtr) + CHECK_NAME_CASES(enc, ptr, end, nextTokPtr) case BT_SEMI: *nextTokPtr = ptr + MINBPC(enc); return XML_TOK_ENTITY_REF; @@ -531,15 +560,14 @@ PREFIX(scanRef)(const ENCODING *enc, const char *ptr, const char *end, static int PTRCALL PREFIX(scanAtts)(const ENCODING *enc, const char *ptr, const char *end, - const char **nextTokPtr) -{ -#ifdef XML_NS + const char **nextTokPtr) { +# ifdef XML_NS int hadColon = 0; -#endif +# endif while (HAS_CHAR(enc, ptr, end)) { switch (BYTE_TYPE(enc, ptr)) { - CHECK_NAME_CASES(enc, ptr, end, nextTokPtr) -#ifdef XML_NS + CHECK_NAME_CASES(enc, ptr, end, nextTokPtr) +# ifdef XML_NS case BT_COLON: if (hadColon) { *nextTokPtr = ptr; @@ -549,14 +577,16 @@ PREFIX(scanAtts)(const ENCODING *enc, const char *ptr, const char *end, ptr += MINBPC(enc); REQUIRE_CHAR(enc, ptr, end); switch (BYTE_TYPE(enc, ptr)) { - CHECK_NMSTRT_CASES(enc, ptr, end, nextTokPtr) + CHECK_NMSTRT_CASES(enc, ptr, end, nextTokPtr) default: *nextTokPtr = ptr; return XML_TOK_INVALID; } break; -#endif - case BT_S: case BT_CR: case BT_LF: +# endif + case BT_S: + case BT_CR: + case BT_LF: for (;;) { int t; @@ -575,102 +605,102 @@ PREFIX(scanAtts)(const ENCODING *enc, const char *ptr, const char *end, return XML_TOK_INVALID; } } - /* fall through */ - case BT_EQUALS: - { - int open; -#ifdef XML_NS - hadColon = 0; -#endif - for (;;) { - ptr += MINBPC(enc); - REQUIRE_CHAR(enc, ptr, end); - open = BYTE_TYPE(enc, ptr); - if (open == BT_QUOT || open == BT_APOS) - break; - switch (open) { - case BT_S: - case BT_LF: - case BT_CR: - break; - default: - *nextTokPtr = ptr; - return XML_TOK_INVALID; - } - } + /* fall through */ + case BT_EQUALS: { + int open; +# ifdef XML_NS + hadColon = 0; +# endif + for (;;) { ptr += MINBPC(enc); - /* in attribute value */ - for (;;) { - int t; - REQUIRE_CHAR(enc, ptr, end); - t = BYTE_TYPE(enc, ptr); - if (t == open) - break; - switch (t) { + REQUIRE_CHAR(enc, ptr, end); + open = BYTE_TYPE(enc, ptr); + if (open == BT_QUOT || open == BT_APOS) + break; + switch (open) { + case BT_S: + case BT_LF: + case BT_CR: + break; + default: + *nextTokPtr = ptr; + return XML_TOK_INVALID; + } + } + ptr += MINBPC(enc); + /* in attribute value */ + for (;;) { + int t; + REQUIRE_CHAR(enc, ptr, end); + t = BYTE_TYPE(enc, ptr); + if (t == open) + break; + switch (t) { INVALID_CASES(ptr, nextTokPtr) - case BT_AMP: - { - int tok = PREFIX(scanRef)(enc, ptr + MINBPC(enc), end, &ptr); - if (tok <= 0) { - if (tok == XML_TOK_INVALID) - *nextTokPtr = ptr; - return tok; - } - break; - } - case BT_LT: - *nextTokPtr = ptr; - return XML_TOK_INVALID; - default: - ptr += MINBPC(enc); - break; + case BT_AMP: { + int tok = PREFIX(scanRef)(enc, ptr + MINBPC(enc), end, &ptr); + if (tok <= 0) { + if (tok == XML_TOK_INVALID) + *nextTokPtr = ptr; + return tok; } + break; + } + case BT_LT: + *nextTokPtr = ptr; + return XML_TOK_INVALID; + default: + ptr += MINBPC(enc); + break; } + } + ptr += MINBPC(enc); + REQUIRE_CHAR(enc, ptr, end); + switch (BYTE_TYPE(enc, ptr)) { + case BT_S: + case BT_CR: + case BT_LF: + break; + case BT_SOL: + goto sol; + case BT_GT: + goto gt; + default: + *nextTokPtr = ptr; + return XML_TOK_INVALID; + } + /* ptr points to closing quote */ + for (;;) { ptr += MINBPC(enc); REQUIRE_CHAR(enc, ptr, end); switch (BYTE_TYPE(enc, ptr)) { + CHECK_NMSTRT_CASES(enc, ptr, end, nextTokPtr) case BT_S: case BT_CR: case BT_LF: - break; - case BT_SOL: - goto sol; + continue; case BT_GT: - goto gt; - default: - *nextTokPtr = ptr; - return XML_TOK_INVALID; - } - /* ptr points to closing quote */ - for (;;) { + gt: + *nextTokPtr = ptr + MINBPC(enc); + return XML_TOK_START_TAG_WITH_ATTS; + case BT_SOL: + sol: ptr += MINBPC(enc); REQUIRE_CHAR(enc, ptr, end); - switch (BYTE_TYPE(enc, ptr)) { - CHECK_NMSTRT_CASES(enc, ptr, end, nextTokPtr) - case BT_S: case BT_CR: case BT_LF: - continue; - case BT_GT: - gt: - *nextTokPtr = ptr + MINBPC(enc); - return XML_TOK_START_TAG_WITH_ATTS; - case BT_SOL: - sol: - ptr += MINBPC(enc); - REQUIRE_CHAR(enc, ptr, end); - if (!CHAR_MATCHES(enc, ptr, ASCII_GT)) { - *nextTokPtr = ptr; - return XML_TOK_INVALID; - } - *nextTokPtr = ptr + MINBPC(enc); - return XML_TOK_EMPTY_ELEMENT_WITH_ATTS; - default: + if (! CHAR_MATCHES(enc, ptr, ASCII_GT)) { *nextTokPtr = ptr; return XML_TOK_INVALID; } - break; + *nextTokPtr = ptr + MINBPC(enc); + return XML_TOK_EMPTY_ELEMENT_WITH_ATTS; + default: + *nextTokPtr = ptr; + return XML_TOK_INVALID; } break; } + break; + } default: *nextTokPtr = ptr; return XML_TOK_INVALID; @@ -683,14 +713,13 @@ PREFIX(scanAtts)(const ENCODING *enc, const char *ptr, const char *end, static int PTRCALL PREFIX(scanLt)(const ENCODING *enc, const char *ptr, const char *end, - const char **nextTokPtr) -{ -#ifdef XML_NS + const char **nextTokPtr) { +# ifdef XML_NS int hadColon; -#endif +# endif REQUIRE_CHAR(enc, ptr, end); switch (BYTE_TYPE(enc, ptr)) { - CHECK_NMSTRT_CASES(enc, ptr, end, nextTokPtr) + CHECK_NMSTRT_CASES(enc, ptr, end, nextTokPtr) case BT_EXCL: ptr += MINBPC(enc); REQUIRE_CHAR(enc, ptr, end); @@ -698,8 +727,7 @@ PREFIX(scanLt)(const ENCODING *enc, const char *ptr, const char *end, case BT_MINUS: return PREFIX(scanComment)(enc, ptr + MINBPC(enc), end, nextTokPtr); case BT_LSQB: - return PREFIX(scanCdataSection)(enc, ptr + MINBPC(enc), - end, nextTokPtr); + return PREFIX(scanCdataSection)(enc, ptr + MINBPC(enc), end, nextTokPtr); } *nextTokPtr = ptr; return XML_TOK_INVALID; @@ -711,14 +739,14 @@ PREFIX(scanLt)(const ENCODING *enc, const char *ptr, const char *end, *nextTokPtr = ptr; return XML_TOK_INVALID; } -#ifdef XML_NS +# ifdef XML_NS hadColon = 0; -#endif +# endif /* we have a start-tag */ while (HAS_CHAR(enc, ptr, end)) { switch (BYTE_TYPE(enc, ptr)) { - CHECK_NAME_CASES(enc, ptr, end, nextTokPtr) -#ifdef XML_NS + CHECK_NAME_CASES(enc, ptr, end, nextTokPtr) +# ifdef XML_NS case BT_COLON: if (hadColon) { *nextTokPtr = ptr; @@ -728,34 +756,37 @@ PREFIX(scanLt)(const ENCODING *enc, const char *ptr, const char *end, ptr += MINBPC(enc); REQUIRE_CHAR(enc, ptr, end); switch (BYTE_TYPE(enc, ptr)) { - CHECK_NMSTRT_CASES(enc, ptr, end, nextTokPtr) + CHECK_NMSTRT_CASES(enc, ptr, end, nextTokPtr) default: *nextTokPtr = ptr; return XML_TOK_INVALID; } break; -#endif - case BT_S: case BT_CR: case BT_LF: - { - ptr += MINBPC(enc); - while (HAS_CHAR(enc, ptr, end)) { - switch (BYTE_TYPE(enc, ptr)) { +# endif + case BT_S: + case BT_CR: + case BT_LF: { + ptr += MINBPC(enc); + while (HAS_CHAR(enc, ptr, end)) { + switch (BYTE_TYPE(enc, ptr)) { CHECK_NMSTRT_CASES(enc, ptr, end, nextTokPtr) - case BT_GT: - goto gt; - case BT_SOL: - goto sol; - case BT_S: case BT_CR: case BT_LF: - ptr += MINBPC(enc); - continue; - default: - *nextTokPtr = ptr; - return XML_TOK_INVALID; - } - return PREFIX(scanAtts)(enc, ptr, end, nextTokPtr); + case BT_GT: + goto gt; + case BT_SOL: + goto sol; + case BT_S: + case BT_CR: + case BT_LF: + ptr += MINBPC(enc); + continue; + default: + *nextTokPtr = ptr; + return XML_TOK_INVALID; } - return XML_TOK_PARTIAL; + return PREFIX(scanAtts)(enc, ptr, end, nextTokPtr); } + return XML_TOK_PARTIAL; + } case BT_GT: gt: *nextTokPtr = ptr + MINBPC(enc); @@ -764,7 +795,7 @@ PREFIX(scanLt)(const ENCODING *enc, const char *ptr, const char *end, sol: ptr += MINBPC(enc); REQUIRE_CHAR(enc, ptr, end); - if (!CHAR_MATCHES(enc, ptr, ASCII_GT)) { + if (! CHAR_MATCHES(enc, ptr, ASCII_GT)) { *nextTokPtr = ptr; return XML_TOK_INVALID; } @@ -780,8 +811,7 @@ PREFIX(scanLt)(const ENCODING *enc, const char *ptr, const char *end, static int PTRCALL PREFIX(contentTok)(const ENCODING *enc, const char *ptr, const char *end, - const char **nextTokPtr) -{ + const char **nextTokPtr) { if (ptr >= end) return XML_TOK_NONE; if (MINBPC(enc) > 1) { @@ -813,48 +843,50 @@ PREFIX(contentTok)(const ENCODING *enc, const char *ptr, const char *end, ptr += MINBPC(enc); if (! HAS_CHAR(enc, ptr, end)) return XML_TOK_TRAILING_RSQB; - if (!CHAR_MATCHES(enc, ptr, ASCII_RSQB)) + if (! CHAR_MATCHES(enc, ptr, ASCII_RSQB)) break; ptr += MINBPC(enc); if (! HAS_CHAR(enc, ptr, end)) return XML_TOK_TRAILING_RSQB; - if (!CHAR_MATCHES(enc, ptr, ASCII_GT)) { + if (! CHAR_MATCHES(enc, ptr, ASCII_GT)) { ptr -= MINBPC(enc); break; } *nextTokPtr = ptr; return XML_TOK_INVALID; - INVALID_CASES(ptr, nextTokPtr) + INVALID_CASES(ptr, nextTokPtr) default: ptr += MINBPC(enc); break; } while (HAS_CHAR(enc, ptr, end)) { switch (BYTE_TYPE(enc, ptr)) { -#define LEAD_CASE(n) \ - case BT_LEAD ## n: \ - if (end - ptr < n || IS_INVALID_CHAR(enc, ptr, n)) { \ - *nextTokPtr = ptr; \ - return XML_TOK_DATA_CHARS; \ - } \ - ptr += n; \ - break; - LEAD_CASE(2) LEAD_CASE(3) LEAD_CASE(4) -#undef LEAD_CASE +# define LEAD_CASE(n) \ + case BT_LEAD##n: \ + if (end - ptr < n || IS_INVALID_CHAR(enc, ptr, n)) { \ + *nextTokPtr = ptr; \ + return XML_TOK_DATA_CHARS; \ + } \ + ptr += n; \ + break; + LEAD_CASE(2) + LEAD_CASE(3) + LEAD_CASE(4) +# undef LEAD_CASE case BT_RSQB: if (HAS_CHARS(enc, ptr, end, 2)) { - if (!CHAR_MATCHES(enc, ptr + MINBPC(enc), ASCII_RSQB)) { - ptr += MINBPC(enc); - break; - } - if (HAS_CHARS(enc, ptr, end, 3)) { - if (!CHAR_MATCHES(enc, ptr + 2*MINBPC(enc), ASCII_GT)) { - ptr += MINBPC(enc); - break; - } - *nextTokPtr = ptr + 2*MINBPC(enc); - return XML_TOK_INVALID; - } + if (! CHAR_MATCHES(enc, ptr + MINBPC(enc), ASCII_RSQB)) { + ptr += MINBPC(enc); + break; + } + if (HAS_CHARS(enc, ptr, end, 3)) { + if (! CHAR_MATCHES(enc, ptr + 2 * MINBPC(enc), ASCII_GT)) { + ptr += MINBPC(enc); + break; + } + *nextTokPtr = ptr + 2 * MINBPC(enc); + return XML_TOK_INVALID; + } } /* fall through */ case BT_AMP: @@ -879,12 +911,14 @@ PREFIX(contentTok)(const ENCODING *enc, const char *ptr, const char *end, static int PTRCALL PREFIX(scanPercent)(const ENCODING *enc, const char *ptr, const char *end, - const char **nextTokPtr) -{ + const char **nextTokPtr) { REQUIRE_CHAR(enc, ptr, end); switch (BYTE_TYPE(enc, ptr)) { - CHECK_NMSTRT_CASES(enc, ptr, end, nextTokPtr) - case BT_S: case BT_LF: case BT_CR: case BT_PERCNT: + CHECK_NMSTRT_CASES(enc, ptr, end, nextTokPtr) + case BT_S: + case BT_LF: + case BT_CR: + case BT_PERCNT: *nextTokPtr = ptr; return XML_TOK_PERCENT; default: @@ -893,7 +927,7 @@ PREFIX(scanPercent)(const ENCODING *enc, const char *ptr, const char *end, } while (HAS_CHAR(enc, ptr, end)) { switch (BYTE_TYPE(enc, ptr)) { - CHECK_NAME_CASES(enc, ptr, end, nextTokPtr) + CHECK_NAME_CASES(enc, ptr, end, nextTokPtr) case BT_SEMI: *nextTokPtr = ptr + MINBPC(enc); return XML_TOK_PARAM_ENTITY_REF; @@ -907,20 +941,24 @@ PREFIX(scanPercent)(const ENCODING *enc, const char *ptr, const char *end, static int PTRCALL PREFIX(scanPoundName)(const ENCODING *enc, const char *ptr, const char *end, - const char **nextTokPtr) -{ + const char **nextTokPtr) { REQUIRE_CHAR(enc, ptr, end); switch (BYTE_TYPE(enc, ptr)) { - CHECK_NMSTRT_CASES(enc, ptr, end, nextTokPtr) + CHECK_NMSTRT_CASES(enc, ptr, end, nextTokPtr) default: *nextTokPtr = ptr; return XML_TOK_INVALID; } while (HAS_CHAR(enc, ptr, end)) { switch (BYTE_TYPE(enc, ptr)) { - CHECK_NAME_CASES(enc, ptr, end, nextTokPtr) - case BT_CR: case BT_LF: case BT_S: - case BT_RPAR: case BT_GT: case BT_PERCNT: case BT_VERBAR: + CHECK_NAME_CASES(enc, ptr, end, nextTokPtr) + case BT_CR: + case BT_LF: + case BT_S: + case BT_RPAR: + case BT_GT: + case BT_PERCNT: + case BT_VERBAR: *nextTokPtr = ptr; return XML_TOK_POUND_NAME; default: @@ -932,14 +970,12 @@ PREFIX(scanPoundName)(const ENCODING *enc, const char *ptr, const char *end, } static int PTRCALL -PREFIX(scanLit)(int open, const ENCODING *enc, - const char *ptr, const char *end, - const char **nextTokPtr) -{ +PREFIX(scanLit)(int open, const ENCODING *enc, const char *ptr, const char *end, + const char **nextTokPtr) { while (HAS_CHAR(enc, ptr, end)) { int t = BYTE_TYPE(enc, ptr); switch (t) { - INVALID_CASES(ptr, nextTokPtr) + INVALID_CASES(ptr, nextTokPtr) case BT_QUOT: case BT_APOS: ptr += MINBPC(enc); @@ -949,8 +985,12 @@ PREFIX(scanLit)(int open, const ENCODING *enc, return -XML_TOK_LITERAL; *nextTokPtr = ptr; switch (BYTE_TYPE(enc, ptr)) { - case BT_S: case BT_CR: case BT_LF: - case BT_GT: case BT_PERCNT: case BT_LSQB: + case BT_S: + case BT_CR: + case BT_LF: + case BT_GT: + case BT_PERCNT: + case BT_LSQB: return XML_TOK_LITERAL; default: return XML_TOK_INVALID; @@ -965,8 +1005,7 @@ PREFIX(scanLit)(int open, const ENCODING *enc, static int PTRCALL PREFIX(prologTok)(const ENCODING *enc, const char *ptr, const char *end, - const char **nextTokPtr) -{ + const char **nextTokPtr) { int tok; if (ptr >= end) return XML_TOK_NONE; @@ -984,27 +1023,26 @@ PREFIX(prologTok)(const ENCODING *enc, const char *ptr, const char *end, return PREFIX(scanLit)(BT_QUOT, enc, ptr + MINBPC(enc), end, nextTokPtr); case BT_APOS: return PREFIX(scanLit)(BT_APOS, enc, ptr + MINBPC(enc), end, nextTokPtr); - case BT_LT: - { - ptr += MINBPC(enc); - REQUIRE_CHAR(enc, ptr, end); - switch (BYTE_TYPE(enc, ptr)) { - case BT_EXCL: - return PREFIX(scanDecl)(enc, ptr + MINBPC(enc), end, nextTokPtr); - case BT_QUEST: - return PREFIX(scanPi)(enc, ptr + MINBPC(enc), end, nextTokPtr); - case BT_NMSTRT: - case BT_HEX: - case BT_NONASCII: - case BT_LEAD2: - case BT_LEAD3: - case BT_LEAD4: - *nextTokPtr = ptr - MINBPC(enc); - return XML_TOK_INSTANCE_START; - } - *nextTokPtr = ptr; - return XML_TOK_INVALID; + case BT_LT: { + ptr += MINBPC(enc); + REQUIRE_CHAR(enc, ptr, end); + switch (BYTE_TYPE(enc, ptr)) { + case BT_EXCL: + return PREFIX(scanDecl)(enc, ptr + MINBPC(enc), end, nextTokPtr); + case BT_QUEST: + return PREFIX(scanPi)(enc, ptr + MINBPC(enc), end, nextTokPtr); + case BT_NMSTRT: + case BT_HEX: + case BT_NONASCII: + case BT_LEAD2: + case BT_LEAD3: + case BT_LEAD4: + *nextTokPtr = ptr - MINBPC(enc); + return XML_TOK_INSTANCE_START; } + *nextTokPtr = ptr; + return XML_TOK_INVALID; + } case BT_CR: if (ptr + MINBPC(enc) == end) { *nextTokPtr = end; @@ -1012,13 +1050,15 @@ PREFIX(prologTok)(const ENCODING *enc, const char *ptr, const char *end, return -XML_TOK_PROLOG_S; } /* fall through */ - case BT_S: case BT_LF: + case BT_S: + case BT_LF: for (;;) { ptr += MINBPC(enc); if (! HAS_CHAR(enc, ptr, end)) break; switch (BYTE_TYPE(enc, ptr)) { - case BT_S: case BT_LF: + case BT_S: + case BT_LF: break; case BT_CR: /* don't split CR/LF pair */ @@ -1047,7 +1087,7 @@ PREFIX(prologTok)(const ENCODING *enc, const char *ptr, const char *end, if (CHAR_MATCHES(enc, ptr, ASCII_RSQB)) { REQUIRE_CHARS(enc, ptr, end, 2); if (CHAR_MATCHES(enc, ptr + MINBPC(enc), ASCII_GT)) { - *nextTokPtr = ptr + 2*MINBPC(enc); + *nextTokPtr = ptr + 2 * MINBPC(enc); return XML_TOK_COND_SECT_CLOSE; } } @@ -1070,8 +1110,12 @@ PREFIX(prologTok)(const ENCODING *enc, const char *ptr, const char *end, case BT_PLUS: *nextTokPtr = ptr + MINBPC(enc); return XML_TOK_CLOSE_PAREN_PLUS; - case BT_CR: case BT_LF: case BT_S: - case BT_GT: case BT_COMMA: case BT_VERBAR: + case BT_CR: + case BT_LF: + case BT_S: + case BT_GT: + case BT_COMMA: + case BT_VERBAR: case BT_RPAR: *nextTokPtr = ptr; return XML_TOK_CLOSE_PAREN; @@ -1086,24 +1130,26 @@ PREFIX(prologTok)(const ENCODING *enc, const char *ptr, const char *end, return XML_TOK_DECL_CLOSE; case BT_NUM: return PREFIX(scanPoundName)(enc, ptr + MINBPC(enc), end, nextTokPtr); -#define LEAD_CASE(n) \ - case BT_LEAD ## n: \ - if (end - ptr < n) \ - return XML_TOK_PARTIAL_CHAR; \ - if (IS_NMSTRT_CHAR(enc, ptr, n)) { \ - ptr += n; \ - tok = XML_TOK_NAME; \ - break; \ - } \ - if (IS_NAME_CHAR(enc, ptr, n)) { \ - ptr += n; \ - tok = XML_TOK_NMTOKEN; \ - break; \ - } \ - *nextTokPtr = ptr; \ +# define LEAD_CASE(n) \ + case BT_LEAD##n: \ + if (end - ptr < n) \ + return XML_TOK_PARTIAL_CHAR; \ + if (IS_NMSTRT_CHAR(enc, ptr, n)) { \ + ptr += n; \ + tok = XML_TOK_NAME; \ + break; \ + } \ + if (IS_NAME_CHAR(enc, ptr, n)) { \ + ptr += n; \ + tok = XML_TOK_NMTOKEN; \ + break; \ + } \ + *nextTokPtr = ptr; \ return XML_TOK_INVALID; - LEAD_CASE(2) LEAD_CASE(3) LEAD_CASE(4) -#undef LEAD_CASE + LEAD_CASE(2) + LEAD_CASE(3) + LEAD_CASE(4) +# undef LEAD_CASE case BT_NMSTRT: case BT_HEX: tok = XML_TOK_NAME; @@ -1112,9 +1158,9 @@ PREFIX(prologTok)(const ENCODING *enc, const char *ptr, const char *end, case BT_DIGIT: case BT_NAME: case BT_MINUS: -#ifdef XML_NS +# ifdef XML_NS case BT_COLON: -#endif +# endif tok = XML_TOK_NMTOKEN; ptr += MINBPC(enc); break; @@ -1136,13 +1182,19 @@ PREFIX(prologTok)(const ENCODING *enc, const char *ptr, const char *end, } while (HAS_CHAR(enc, ptr, end)) { switch (BYTE_TYPE(enc, ptr)) { - CHECK_NAME_CASES(enc, ptr, end, nextTokPtr) - case BT_GT: case BT_RPAR: case BT_COMMA: - case BT_VERBAR: case BT_LSQB: case BT_PERCNT: - case BT_S: case BT_CR: case BT_LF: + CHECK_NAME_CASES(enc, ptr, end, nextTokPtr) + case BT_GT: + case BT_RPAR: + case BT_COMMA: + case BT_VERBAR: + case BT_LSQB: + case BT_PERCNT: + case BT_S: + case BT_CR: + case BT_LF: *nextTokPtr = ptr; return tok; -#ifdef XML_NS +# ifdef XML_NS case BT_COLON: ptr += MINBPC(enc); switch (tok) { @@ -1150,7 +1202,7 @@ PREFIX(prologTok)(const ENCODING *enc, const char *ptr, const char *end, REQUIRE_CHAR(enc, ptr, end); tok = XML_TOK_PREFIXED_NAME; switch (BYTE_TYPE(enc, ptr)) { - CHECK_NAME_CASES(enc, ptr, end, nextTokPtr) + CHECK_NAME_CASES(enc, ptr, end, nextTokPtr) default: tok = XML_TOK_NMTOKEN; break; @@ -1161,23 +1213,23 @@ PREFIX(prologTok)(const ENCODING *enc, const char *ptr, const char *end, break; } break; -#endif +# endif case BT_PLUS: - if (tok == XML_TOK_NMTOKEN) { + if (tok == XML_TOK_NMTOKEN) { *nextTokPtr = ptr; return XML_TOK_INVALID; } *nextTokPtr = ptr + MINBPC(enc); return XML_TOK_NAME_PLUS; case BT_AST: - if (tok == XML_TOK_NMTOKEN) { + if (tok == XML_TOK_NMTOKEN) { *nextTokPtr = ptr; return XML_TOK_INVALID; } *nextTokPtr = ptr + MINBPC(enc); return XML_TOK_NAME_ASTERISK; case BT_QUEST: - if (tok == XML_TOK_NMTOKEN) { + if (tok == XML_TOK_NMTOKEN) { *nextTokPtr = ptr; return XML_TOK_INVALID; } @@ -1192,21 +1244,30 @@ PREFIX(prologTok)(const ENCODING *enc, const char *ptr, const char *end, } static int PTRCALL -PREFIX(attributeValueTok)(const ENCODING *enc, const char *ptr, - const char *end, const char **nextTokPtr) -{ +PREFIX(attributeValueTok)(const ENCODING *enc, const char *ptr, const char *end, + const char **nextTokPtr) { const char *start; if (ptr >= end) return XML_TOK_NONE; - else if (! HAS_CHAR(enc, ptr, end)) - return XML_TOK_PARTIAL; + else if (! HAS_CHAR(enc, ptr, end)) { + /* This line cannot be executed. The incoming data has already + * been tokenized once, so incomplete characters like this have + * already been eliminated from the input. Retaining the paranoia + * check is still valuable, however. + */ + return XML_TOK_PARTIAL; /* LCOV_EXCL_LINE */ + } start = ptr; while (HAS_CHAR(enc, ptr, end)) { switch (BYTE_TYPE(enc, ptr)) { -#define LEAD_CASE(n) \ - case BT_LEAD ## n: ptr += n; break; - LEAD_CASE(2) LEAD_CASE(3) LEAD_CASE(4) -#undef LEAD_CASE +# define LEAD_CASE(n) \ + case BT_LEAD##n: \ + ptr += n; \ + break; + LEAD_CASE(2) + LEAD_CASE(3) + LEAD_CASE(4) +# undef LEAD_CASE case BT_AMP: if (ptr == start) return PREFIX(scanRef)(enc, ptr + MINBPC(enc), end, nextTokPtr); @@ -1252,21 +1313,30 @@ PREFIX(attributeValueTok)(const ENCODING *enc, const char *ptr, } static int PTRCALL -PREFIX(entityValueTok)(const ENCODING *enc, const char *ptr, - const char *end, const char **nextTokPtr) -{ +PREFIX(entityValueTok)(const ENCODING *enc, const char *ptr, const char *end, + const char **nextTokPtr) { const char *start; if (ptr >= end) return XML_TOK_NONE; - else if (! HAS_CHAR(enc, ptr, end)) - return XML_TOK_PARTIAL; + else if (! HAS_CHAR(enc, ptr, end)) { + /* This line cannot be executed. The incoming data has already + * been tokenized once, so incomplete characters like this have + * already been eliminated from the input. Retaining the paranoia + * check is still valuable, however. + */ + return XML_TOK_PARTIAL; /* LCOV_EXCL_LINE */ + } start = ptr; while (HAS_CHAR(enc, ptr, end)) { switch (BYTE_TYPE(enc, ptr)) { -#define LEAD_CASE(n) \ - case BT_LEAD ## n: ptr += n; break; - LEAD_CASE(2) LEAD_CASE(3) LEAD_CASE(4) -#undef LEAD_CASE +# define LEAD_CASE(n) \ + case BT_LEAD##n: \ + ptr += n; \ + break; + LEAD_CASE(2) + LEAD_CASE(3) + LEAD_CASE(4) +# undef LEAD_CASE case BT_AMP: if (ptr == start) return PREFIX(scanRef)(enc, ptr + MINBPC(enc), end, nextTokPtr); @@ -1274,8 +1344,7 @@ PREFIX(entityValueTok)(const ENCODING *enc, const char *ptr, return XML_TOK_DATA_CHARS; case BT_PERCNT: if (ptr == start) { - int tok = PREFIX(scanPercent)(enc, ptr + MINBPC(enc), - end, nextTokPtr); + int tok = PREFIX(scanPercent)(enc, ptr + MINBPC(enc), end, nextTokPtr); return (tok == XML_TOK_PERCENT) ? XML_TOK_INVALID : tok; } *nextTokPtr = ptr; @@ -1308,12 +1377,11 @@ PREFIX(entityValueTok)(const ENCODING *enc, const char *ptr, return XML_TOK_DATA_CHARS; } -#ifdef XML_DTD +# ifdef XML_DTD static int PTRCALL -PREFIX(ignoreSectionTok)(const ENCODING *enc, const char *ptr, - const char *end, const char **nextTokPtr) -{ +PREFIX(ignoreSectionTok)(const ENCODING *enc, const char *ptr, const char *end, + const char **nextTokPtr) { int level = 0; if (MINBPC(enc) > 1) { size_t n = end - ptr; @@ -1324,7 +1392,7 @@ PREFIX(ignoreSectionTok)(const ENCODING *enc, const char *ptr, } while (HAS_CHAR(enc, ptr, end)) { switch (BYTE_TYPE(enc, ptr)) { - INVALID_CASES(ptr, nextTokPtr) + INVALID_CASES(ptr, nextTokPtr) case BT_LT: ptr += MINBPC(enc); REQUIRE_CHAR(enc, ptr, end); @@ -1361,12 +1429,11 @@ PREFIX(ignoreSectionTok)(const ENCODING *enc, const char *ptr, return XML_TOK_PARTIAL; } -#endif /* XML_DTD */ +# endif /* XML_DTD */ static int PTRCALL PREFIX(isPublicId)(const ENCODING *enc, const char *ptr, const char *end, - const char **badPtr) -{ + const char **badPtr) { ptr += MINBPC(enc); end -= MINBPC(enc); for (; HAS_CHAR(enc, ptr, end); ptr += MINBPC(enc)) { @@ -1389,9 +1456,9 @@ PREFIX(isPublicId)(const ENCODING *enc, const char *ptr, const char *end, case BT_AST: case BT_PERCNT: case BT_NUM: -#ifdef XML_NS +# ifdef XML_NS case BT_COLON: -#endif +# endif break; case BT_S: if (CHAR_MATCHES(enc, ptr, ASCII_TAB)) { @@ -1401,8 +1468,9 @@ PREFIX(isPublicId)(const ENCODING *enc, const char *ptr, const char *end, break; case BT_NAME: case BT_NMSTRT: - if (!(BYTE_TO_ASCII(enc, ptr) & ~0x7f)) + if (! (BYTE_TO_ASCII(enc, ptr) & ~0x7f)) break; + /* fall through */ default: switch (BYTE_TO_ASCII(enc, ptr)) { case 0x24: /* $ */ @@ -1424,9 +1492,8 @@ PREFIX(isPublicId)(const ENCODING *enc, const char *ptr, const char *end, */ static int PTRCALL -PREFIX(getAtts)(const ENCODING *enc, const char *ptr, - int attsMax, ATTRIBUTE *atts) -{ +PREFIX(getAtts)(const ENCODING *enc, const char *ptr, int attsMax, + ATTRIBUTE *atts) { enum { other, inName, inValue } state = inName; int nAtts = 0; int open = 0; /* defined when state == inValue; @@ -1434,32 +1501,35 @@ PREFIX(getAtts)(const ENCODING *enc, const char *ptr, for (ptr += MINBPC(enc);; ptr += MINBPC(enc)) { switch (BYTE_TYPE(enc, ptr)) { -#define START_NAME \ - if (state == other) { \ - if (nAtts < attsMax) { \ - atts[nAtts].name = ptr; \ - atts[nAtts].normalized = 1; \ - } \ - state = inName; \ - } -#define LEAD_CASE(n) \ - case BT_LEAD ## n: START_NAME ptr += (n - MINBPC(enc)); break; - LEAD_CASE(2) LEAD_CASE(3) LEAD_CASE(4) -#undef LEAD_CASE +# define START_NAME \ + if (state == other) { \ + if (nAtts < attsMax) { \ + atts[nAtts].name = ptr; \ + atts[nAtts].normalized = 1; \ + } \ + state = inName; \ + } +# define LEAD_CASE(n) \ + case BT_LEAD##n: \ + START_NAME ptr += (n - MINBPC(enc)); \ + break; + LEAD_CASE(2) + LEAD_CASE(3) + LEAD_CASE(4) +# undef LEAD_CASE case BT_NONASCII: case BT_NMSTRT: case BT_HEX: START_NAME break; -#undef START_NAME +# undef START_NAME case BT_QUOT: if (state != inValue) { if (nAtts < attsMax) atts[nAtts].valuePtr = ptr + MINBPC(enc); state = inValue; open = BT_QUOT; - } - else if (open == BT_QUOT) { + } else if (open == BT_QUOT) { state = other; if (nAtts < attsMax) atts[nAtts].valueEnd = ptr; @@ -1472,8 +1542,7 @@ PREFIX(getAtts)(const ENCODING *enc, const char *ptr, atts[nAtts].valuePtr = ptr + MINBPC(enc); state = inValue; open = BT_APOS; - } - else if (open == BT_APOS) { + } else if (open == BT_APOS) { state = other; if (nAtts < attsMax) atts[nAtts].valueEnd = ptr; @@ -1487,16 +1556,15 @@ PREFIX(getAtts)(const ENCODING *enc, const char *ptr, case BT_S: if (state == inName) state = other; - else if (state == inValue - && nAtts < attsMax - && atts[nAtts].normalized + else if (state == inValue && nAtts < attsMax && atts[nAtts].normalized && (ptr == atts[nAtts].valuePtr || BYTE_TO_ASCII(enc, ptr) != ASCII_SPACE || BYTE_TO_ASCII(enc, ptr + MINBPC(enc)) == ASCII_SPACE || BYTE_TYPE(enc, ptr + MINBPC(enc)) == open)) atts[nAtts].normalized = 0; break; - case BT_CR: case BT_LF: + case BT_CR: + case BT_LF: /* This case ensures that the first attribute name is counted Apart from that we could just change state on the quote. */ if (state == inName) @@ -1517,29 +1585,44 @@ PREFIX(getAtts)(const ENCODING *enc, const char *ptr, } static int PTRFASTCALL -PREFIX(charRefNumber)(const ENCODING *UNUSED_P(enc), const char *ptr) -{ +PREFIX(charRefNumber)(const ENCODING *enc, const char *ptr) { int result = 0; /* skip &# */ - ptr += 2*MINBPC(enc); + UNUSED_P(enc); + ptr += 2 * MINBPC(enc); if (CHAR_MATCHES(enc, ptr, ASCII_x)) { - for (ptr += MINBPC(enc); - !CHAR_MATCHES(enc, ptr, ASCII_SEMI); + for (ptr += MINBPC(enc); ! CHAR_MATCHES(enc, ptr, ASCII_SEMI); ptr += MINBPC(enc)) { int c = BYTE_TO_ASCII(enc, ptr); switch (c) { - case ASCII_0: case ASCII_1: case ASCII_2: case ASCII_3: case ASCII_4: - case ASCII_5: case ASCII_6: case ASCII_7: case ASCII_8: case ASCII_9: + case ASCII_0: + case ASCII_1: + case ASCII_2: + case ASCII_3: + case ASCII_4: + case ASCII_5: + case ASCII_6: + case ASCII_7: + case ASCII_8: + case ASCII_9: result <<= 4; result |= (c - ASCII_0); break; - case ASCII_A: case ASCII_B: case ASCII_C: - case ASCII_D: case ASCII_E: case ASCII_F: + case ASCII_A: + case ASCII_B: + case ASCII_C: + case ASCII_D: + case ASCII_E: + case ASCII_F: result <<= 4; result += 10 + (c - ASCII_A); break; - case ASCII_a: case ASCII_b: case ASCII_c: - case ASCII_d: case ASCII_e: case ASCII_f: + case ASCII_a: + case ASCII_b: + case ASCII_c: + case ASCII_d: + case ASCII_e: + case ASCII_f: result <<= 4; result += 10 + (c - ASCII_a); break; @@ -1547,9 +1630,8 @@ PREFIX(charRefNumber)(const ENCODING *UNUSED_P(enc), const char *ptr) if (result >= 0x110000) return -1; } - } - else { - for (; !CHAR_MATCHES(enc, ptr, ASCII_SEMI); ptr += MINBPC(enc)) { + } else { + for (; ! CHAR_MATCHES(enc, ptr, ASCII_SEMI); ptr += MINBPC(enc)) { int c = BYTE_TO_ASCII(enc, ptr); result *= 10; result += (c - ASCII_0); @@ -1561,10 +1643,10 @@ PREFIX(charRefNumber)(const ENCODING *UNUSED_P(enc), const char *ptr) } static int PTRCALL -PREFIX(predefinedEntityName)(const ENCODING *UNUSED_P(enc), const char *ptr, - const char *end) -{ - switch ((end - ptr)/MINBPC(enc)) { +PREFIX(predefinedEntityName)(const ENCODING *enc, const char *ptr, + const char *end) { + UNUSED_P(enc); + switch ((end - ptr) / MINBPC(enc)) { case 2: if (CHAR_MATCHES(enc, ptr + MINBPC(enc), ASCII_t)) { switch (BYTE_TO_ASCII(enc, ptr)) { @@ -1615,97 +1697,42 @@ PREFIX(predefinedEntityName)(const ENCODING *UNUSED_P(enc), const char *ptr, } static int PTRCALL -PREFIX(sameName)(const ENCODING *enc, const char *ptr1, const char *ptr2) -{ - for (;;) { - switch (BYTE_TYPE(enc, ptr1)) { -#define LEAD_CASE(n) \ - case BT_LEAD ## n: \ - if (*ptr1++ != *ptr2++) \ - return 0; - LEAD_CASE(4) LEAD_CASE(3) LEAD_CASE(2) -#undef LEAD_CASE - /* fall through */ - if (*ptr1++ != *ptr2++) - return 0; - break; - case BT_NONASCII: - case BT_NMSTRT: -#ifdef XML_NS - case BT_COLON: -#endif - case BT_HEX: - case BT_DIGIT: - case BT_NAME: - case BT_MINUS: - if (*ptr2++ != *ptr1++) - return 0; - if (MINBPC(enc) > 1) { - if (*ptr2++ != *ptr1++) - return 0; - if (MINBPC(enc) > 2) { - if (*ptr2++ != *ptr1++) - return 0; - if (MINBPC(enc) > 3) { - if (*ptr2++ != *ptr1++) - return 0; - } - } - } - break; - default: - if (MINBPC(enc) == 1 && *ptr1 == *ptr2) - return 1; - switch (BYTE_TYPE(enc, ptr2)) { - case BT_LEAD2: - case BT_LEAD3: - case BT_LEAD4: - case BT_NONASCII: - case BT_NMSTRT: -#ifdef XML_NS - case BT_COLON: -#endif - case BT_HEX: - case BT_DIGIT: - case BT_NAME: - case BT_MINUS: - return 0; - default: - return 1; - } - } - } - /* not reached */ -} - -static int PTRCALL -PREFIX(nameMatchesAscii)(const ENCODING *UNUSED_P(enc), const char *ptr1, - const char *end1, const char *ptr2) -{ +PREFIX(nameMatchesAscii)(const ENCODING *enc, const char *ptr1, + const char *end1, const char *ptr2) { + UNUSED_P(enc); for (; *ptr2; ptr1 += MINBPC(enc), ptr2++) { - if (end1 - ptr1 < MINBPC(enc)) - return 0; - if (!CHAR_MATCHES(enc, ptr1, *ptr2)) + if (end1 - ptr1 < MINBPC(enc)) { + /* This line cannot be executed. The incoming data has already + * been tokenized once, so incomplete characters like this have + * already been eliminated from the input. Retaining the + * paranoia check is still valuable, however. + */ + return 0; /* LCOV_EXCL_LINE */ + } + if (! CHAR_MATCHES(enc, ptr1, *ptr2)) return 0; } return ptr1 == end1; } static int PTRFASTCALL -PREFIX(nameLength)(const ENCODING *enc, const char *ptr) -{ +PREFIX(nameLength)(const ENCODING *enc, const char *ptr) { const char *start = ptr; for (;;) { switch (BYTE_TYPE(enc, ptr)) { -#define LEAD_CASE(n) \ - case BT_LEAD ## n: ptr += n; break; - LEAD_CASE(2) LEAD_CASE(3) LEAD_CASE(4) -#undef LEAD_CASE +# define LEAD_CASE(n) \ + case BT_LEAD##n: \ + ptr += n; \ + break; + LEAD_CASE(2) + LEAD_CASE(3) + LEAD_CASE(4) +# undef LEAD_CASE case BT_NONASCII: case BT_NMSTRT: -#ifdef XML_NS +# ifdef XML_NS case BT_COLON: -#endif +# endif case BT_HEX: case BT_DIGIT: case BT_NAME: @@ -1718,9 +1745,8 @@ PREFIX(nameLength)(const ENCODING *enc, const char *ptr) } } -static const char * PTRFASTCALL -PREFIX(skipS)(const ENCODING *enc, const char *ptr) -{ +static const char *PTRFASTCALL +PREFIX(skipS)(const ENCODING *enc, const char *ptr) { for (;;) { switch (BYTE_TYPE(enc, ptr)) { case BT_LF: @@ -1735,19 +1761,18 @@ PREFIX(skipS)(const ENCODING *enc, const char *ptr) } static void PTRCALL -PREFIX(updatePosition)(const ENCODING *enc, - const char *ptr, - const char *end, - POSITION *pos) -{ +PREFIX(updatePosition)(const ENCODING *enc, const char *ptr, const char *end, + POSITION *pos) { while (HAS_CHAR(enc, ptr, end)) { switch (BYTE_TYPE(enc, ptr)) { -#define LEAD_CASE(n) \ - case BT_LEAD ## n: \ - ptr += n; \ - break; - LEAD_CASE(2) LEAD_CASE(3) LEAD_CASE(4) -#undef LEAD_CASE +# define LEAD_CASE(n) \ + case BT_LEAD##n: \ + ptr += n; \ + break; + LEAD_CASE(2) + LEAD_CASE(3) + LEAD_CASE(4) +# undef LEAD_CASE case BT_LF: pos->columnNumber = (XML_Size)-1; pos->lineNumber++; @@ -1768,12 +1793,12 @@ PREFIX(updatePosition)(const ENCODING *enc, } } -#undef DO_LEAD_CASE -#undef MULTIBYTE_CASES -#undef INVALID_CASES -#undef CHECK_NAME_CASE -#undef CHECK_NAME_CASES -#undef CHECK_NMSTRT_CASE -#undef CHECK_NMSTRT_CASES +# undef DO_LEAD_CASE +# undef MULTIBYTE_CASES +# undef INVALID_CASES +# undef CHECK_NAME_CASE +# undef CHECK_NAME_CASES +# undef CHECK_NMSTRT_CASE +# undef CHECK_NMSTRT_CASES #endif /* XML_TOK_IMPL_C */ diff --git a/chromium/third_party/expat/files/lib/xmltok_impl.h b/chromium/third_party/expat/files/lib/xmltok_impl.h index da0ea60a657..e925dbc7e2c 100644 --- a/chromium/third_party/expat/files/lib/xmltok_impl.h +++ b/chromium/third_party/expat/files/lib/xmltok_impl.h @@ -1,46 +1,73 @@ /* -Copyright (c) 1998, 1999 Thai Open Source Software Center Ltd -See the file COPYING for copying permission. + __ __ _ + ___\ \/ /_ __ __ _| |_ + / _ \\ /| '_ \ / _` | __| + | __// \| |_) | (_| | |_ + \___/_/\_\ .__/ \__,_|\__| + |_| XML parser + + Copyright (c) 1997-2000 Thai Open Source Software Center Ltd + Copyright (c) 2000-2017 Expat development team + Licensed under the MIT license: + + Permission is hereby granted, free of charge, to any person obtaining + a copy of this software and associated documentation files (the + "Software"), to deal in the Software without restriction, including + without limitation the rights to use, copy, modify, merge, publish, + distribute, sublicense, and/or sell copies of the Software, and to permit + persons to whom the Software is furnished to do so, subject to the + following conditions: + + The above copyright notice and this permission notice shall be included + in all copies or substantial portions of the Software. + + THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN + NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, + DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR + OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE + USE OR OTHER DEALINGS IN THE SOFTWARE. */ enum { - BT_NONXML, - BT_MALFORM, - BT_LT, - BT_AMP, - BT_RSQB, - BT_LEAD2, - BT_LEAD3, - BT_LEAD4, - BT_TRAIL, - BT_CR, - BT_LF, - BT_GT, - BT_QUOT, - BT_APOS, - BT_EQUALS, - BT_QUEST, - BT_EXCL, - BT_SOL, - BT_SEMI, - BT_NUM, - BT_LSQB, - BT_S, - BT_NMSTRT, - BT_COLON, - BT_HEX, - BT_DIGIT, - BT_NAME, - BT_MINUS, - BT_OTHER, /* known not to be a name or name start character */ + BT_NONXML, /* e.g. noncharacter-FFFF */ + BT_MALFORM, /* illegal, with regard to encoding */ + BT_LT, /* less than = "<" */ + BT_AMP, /* ampersand = "&" */ + BT_RSQB, /* right square bracket = "[" */ + BT_LEAD2, /* lead byte of a 2-byte UTF-8 character */ + BT_LEAD3, /* lead byte of a 3-byte UTF-8 character */ + BT_LEAD4, /* lead byte of a 4-byte UTF-8 character */ + BT_TRAIL, /* trailing unit, e.g. second 16-bit unit of a 4-byte char. */ + BT_CR, /* carriage return = "\r" */ + BT_LF, /* line feed = "\n" */ + BT_GT, /* greater than = ">" */ + BT_QUOT, /* quotation character = "\"" */ + BT_APOS, /* aposthrophe = "'" */ + BT_EQUALS, /* equal sign = "=" */ + BT_QUEST, /* question mark = "?" */ + BT_EXCL, /* exclamation mark = "!" */ + BT_SOL, /* solidus, slash = "/" */ + BT_SEMI, /* semicolon = ";" */ + BT_NUM, /* number sign = "#" */ + BT_LSQB, /* left square bracket = "[" */ + BT_S, /* white space, e.g. "\t", " "[, "\r"] */ + BT_NMSTRT, /* non-hex name start letter = "G".."Z" + "g".."z" + "_" */ + BT_COLON, /* colon = ":" */ + BT_HEX, /* hex letter = "A".."F" + "a".."f" */ + BT_DIGIT, /* digit = "0".."9" */ + BT_NAME, /* dot and middle dot = "." + chr(0xb7) */ + BT_MINUS, /* minus = "-" */ + BT_OTHER, /* known not to be a name or name start character */ BT_NONASCII, /* might be a name or name start character */ - BT_PERCNT, - BT_LPAR, - BT_RPAR, - BT_AST, - BT_PLUS, - BT_COMMA, - BT_VERBAR + BT_PERCNT, /* percent sign = "%" */ + BT_LPAR, /* left parenthesis = "(" */ + BT_RPAR, /* right parenthesis = "(" */ + BT_AST, /* asterisk = "*" */ + BT_PLUS, /* plus sign = "+" */ + BT_COMMA, /* comma = "," */ + BT_VERBAR /* vertical bar = "|" */ }; #include <stddef.h> diff --git a/chromium/third_party/expat/files/lib/xmltok_ns.c b/chromium/third_party/expat/files/lib/xmltok_ns.c index c3b88fdf4e3..919c74e9f97 100644 --- a/chromium/third_party/expat/files/lib/xmltok_ns.c +++ b/chromium/third_party/expat/files/lib/xmltok_ns.c @@ -1,61 +1,79 @@ -/* Copyright (c) 1998, 1999 Thai Open Source Software Center Ltd - See the file COPYING for copying permission. +/* This file is included! + __ __ _ + ___\ \/ /_ __ __ _| |_ + / _ \\ /| '_ \ / _` | __| + | __// \| |_) | (_| | |_ + \___/_/\_\ .__/ \__,_|\__| + |_| XML parser + + Copyright (c) 1997-2000 Thai Open Source Software Center Ltd + Copyright (c) 2000-2017 Expat development team + Licensed under the MIT license: + + Permission is hereby granted, free of charge, to any person obtaining + a copy of this software and associated documentation files (the + "Software"), to deal in the Software without restriction, including + without limitation the rights to use, copy, modify, merge, publish, + distribute, sublicense, and/or sell copies of the Software, and to permit + persons to whom the Software is furnished to do so, subject to the + following conditions: + + The above copyright notice and this permission notice shall be included + in all copies or substantial portions of the Software. + + THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN + NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, + DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR + OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE + USE OR OTHER DEALINGS IN THE SOFTWARE. */ -/* This file is included! */ #ifdef XML_TOK_NS_C const ENCODING * -NS(XmlGetUtf8InternalEncoding)(void) -{ +NS(XmlGetUtf8InternalEncoding)(void) { return &ns(internal_utf8_encoding).enc; } const ENCODING * -NS(XmlGetUtf16InternalEncoding)(void) -{ -#if BYTEORDER == 1234 +NS(XmlGetUtf16InternalEncoding)(void) { +# if BYTEORDER == 1234 return &ns(internal_little2_encoding).enc; -#elif BYTEORDER == 4321 +# elif BYTEORDER == 4321 return &ns(internal_big2_encoding).enc; -#else +# else const short n = 1; - return (*(const char *)&n - ? &ns(internal_little2_encoding).enc - : &ns(internal_big2_encoding).enc); -#endif + return (*(const char *)&n ? &ns(internal_little2_encoding).enc + : &ns(internal_big2_encoding).enc); +# endif } -static const ENCODING * const NS(encodings)[] = { - &ns(latin1_encoding).enc, - &ns(ascii_encoding).enc, - &ns(utf8_encoding).enc, - &ns(big2_encoding).enc, - &ns(big2_encoding).enc, - &ns(little2_encoding).enc, - &ns(utf8_encoding).enc /* NO_ENC */ +static const ENCODING *const NS(encodings)[] = { + &ns(latin1_encoding).enc, &ns(ascii_encoding).enc, + &ns(utf8_encoding).enc, &ns(big2_encoding).enc, + &ns(big2_encoding).enc, &ns(little2_encoding).enc, + &ns(utf8_encoding).enc /* NO_ENC */ }; static int PTRCALL NS(initScanProlog)(const ENCODING *enc, const char *ptr, const char *end, - const char **nextTokPtr) -{ - return initScan(NS(encodings), (const INIT_ENCODING *)enc, - XML_PROLOG_STATE, ptr, end, nextTokPtr); + const char **nextTokPtr) { + return initScan(NS(encodings), (const INIT_ENCODING *)enc, XML_PROLOG_STATE, + ptr, end, nextTokPtr); } static int PTRCALL NS(initScanContent)(const ENCODING *enc, const char *ptr, const char *end, - const char **nextTokPtr) -{ - return initScan(NS(encodings), (const INIT_ENCODING *)enc, - XML_CONTENT_STATE, ptr, end, nextTokPtr); + const char **nextTokPtr) { + return initScan(NS(encodings), (const INIT_ENCODING *)enc, XML_CONTENT_STATE, + ptr, end, nextTokPtr); } int NS(XmlInitEncoding)(INIT_ENCODING *p, const ENCODING **encPtr, - const char *name) -{ + const char *name) { int i = getEncodingIndex(name); if (i == UNKNOWN_ENC) return 0; @@ -69,9 +87,8 @@ NS(XmlInitEncoding)(INIT_ENCODING *p, const ENCODING **encPtr, } static const ENCODING * -NS(findEncoding)(const ENCODING *enc, const char *ptr, const char *end) -{ -#define ENCODING_MAX 128 +NS(findEncoding)(const ENCODING *enc, const char *ptr, const char *end) { +# define ENCODING_MAX 128 char buf[ENCODING_MAX]; char *p = buf; int i; @@ -88,28 +105,14 @@ NS(findEncoding)(const ENCODING *enc, const char *ptr, const char *end) } int -NS(XmlParseXmlDecl)(int isGeneralTextEntity, - const ENCODING *enc, - const char *ptr, - const char *end, - const char **badPtr, - const char **versionPtr, - const char **versionEndPtr, - const char **encodingName, - const ENCODING **encoding, - int *standalone) -{ - return doParseXmlDecl(NS(findEncoding), - isGeneralTextEntity, - enc, - ptr, - end, - badPtr, - versionPtr, - versionEndPtr, - encodingName, - encoding, - standalone); +NS(XmlParseXmlDecl)(int isGeneralTextEntity, const ENCODING *enc, + const char *ptr, const char *end, const char **badPtr, + const char **versionPtr, const char **versionEndPtr, + const char **encodingName, const ENCODING **encoding, + int *standalone) { + return doParseXmlDecl(NS(findEncoding), isGeneralTextEntity, enc, ptr, end, + badPtr, versionPtr, versionEndPtr, encodingName, + encoding, standalone); } #endif /* XML_TOK_NS_C */ diff --git a/chromium/third_party/expat/fuzz/OWNERS b/chromium/third_party/expat/fuzz/OWNERS deleted file mode 100644 index 0230f7d8bf1..00000000000 --- a/chromium/third_party/expat/fuzz/OWNERS +++ /dev/null @@ -1,2 +0,0 @@ -aizatsky@chromium.org -mmoroz@chromium.org diff --git a/chromium/third_party/expat/fuzz/expat_xml_parse_fuzzer.cc b/chromium/third_party/expat/fuzz/expat_xml_parse_fuzzer.cc deleted file mode 100644 index b4120713633..00000000000 --- a/chromium/third_party/expat/fuzz/expat_xml_parse_fuzzer.cc +++ /dev/null @@ -1,30 +0,0 @@ -// Copyright 2016 The Chromium Authors. All rights reserved. -// Use of this source code is governed by a BSD-style license that can be -// found in the LICENSE file. - -#include <stddef.h> -#include <stdint.h> - -#include "third_party/expat/files/lib/expat.h" - -#include <vector> - -std::vector<const char*> kEncodings = {{"UTF-16", "UTF-8", "ISO-8859-1", - "US-ASCII", "UTF-16BE", "UTF-16LE", - "INVALIDENCODING"}}; - -// Entry point for LibFuzzer. -extern "C" int LLVMFuzzerTestOneInput(const uint8_t* data, size_t size) { - const char* dataPtr = reinterpret_cast<const char*>(data); - - for (int use_ns = 0; use_ns <= 1; ++use_ns) { - for (auto enc : kEncodings) { - XML_Parser parser = - use_ns ? XML_ParserCreateNS(enc, '\n') : XML_ParserCreate(enc); - XML_Parse(parser, dataPtr, size, true); - XML_ParserFree(parser); - } - } - - return 0; -} |