diff options
| author | ph10 <ph10@2f5784b3-3f2a-0410-8824-cb99058d5e15> | 2012-11-11 20:27:03 +0000 |
|---|---|---|
| committer | ph10 <ph10@2f5784b3-3f2a-0410-8824-cb99058d5e15> | 2012-11-11 20:27:03 +0000 |
| commit | fd5db157a2356f859e77744c4ea82fbe8aa17183 (patch) | |
| tree | 8211fa9eb9550cb1a93b36fe77f6b91426dae79f | |
| parent | b330e2d8210c08dfc4c99e71b477a020cb7e29fe (diff) | |
| download | pcre-fd5db157a2356f859e77744c4ea82fbe8aa17183.tar.gz | |
File tidies, preparing for 8.32-RC1.
git-svn-id: svn://vcs.exim.org/pcre/code/trunk@1221 2f5784b3-3f2a-0410-8824-cb99058d5e15
49 files changed, 2507 insertions, 2545 deletions
diff --git a/CMakeLists.txt b/CMakeLists.txt index 1b4f856..17d50b7 100644 --- a/CMakeLists.txt +++ b/CMakeLists.txt @@ -163,9 +163,9 @@ SET(PCRE_SUPPORT_BSR_ANYCRLF OFF CACHE BOOL SET(PCRE_SUPPORT_VALGRIND OFF CACHE BOOL "Enable Valgrind support.") - + SET(PCRE_SUPPORT_COVERAGE OFF CACHE BOOL - "Enable code coverage support using gcov.") + "Enable code coverage support using gcov.") OPTION(PCRE_SHOW_REPORT "Show the final configuration report" ON) OPTION(PCRE_BUILD_PCREGREP "Build pcregrep" ON) @@ -299,9 +299,9 @@ ENDIF(PCRE_SUPPORT_VALGRIND) IF(PCRE_SUPPORT_COVERAGE) SET(SUPPORT_GCOV 1) IF(NOT CMAKE_COMPILER_IS_GNUCC) - MESSAGE(FATAL_ERROR "Code coverage reports can only be generated when using GCC") - ENDIF(NOT CMAKE_COMPILER_IS_GNUCC) -ENDIF(PCRE_SUPPORT_COVERAGE) + MESSAGE(FATAL_ERROR "Code coverage reports can only be generated when using GCC") + ENDIF(NOT CMAKE_COMPILER_IS_GNUCC) +ENDIF(PCRE_SUPPORT_COVERAGE) # This next one used to contain # SET(PCRETEST_LIBS ${READLINE_LIBRARY}) @@ -372,7 +372,7 @@ ENDIF(PCRE_NEWLINE STREQUAL "LF") IF(PCRE_NEWLINE STREQUAL "CRLF") SET(NEWLINE "3365") ENDIF(PCRE_NEWLINE STREQUAL "CRLF") -ENDIF(PCRE_EBCDIC_NL25) +ENDIF(PCRE_EBCDIC_NL25) IF(PCRE_NO_RECURSE) SET(NO_RECURSE 1) @@ -947,7 +947,7 @@ IF(PCRE_SHOW_REPORT) MESSAGE(STATUS " Link pcretest with libreadline .. : Library not found" ) ENDIF(READLINE_FOUND) MESSAGE(STATUS " Support Valgrind .................: ${PCRE_SUPPORT_VALGRIND}") - MESSAGE(STATUS " Support coverage .................: ${PCRE_SUPPORT_COVERAGE}") + MESSAGE(STATUS " Support coverage .................: ${PCRE_SUPPORT_COVERAGE}") IF(MINGW AND NOT PCRE_STATIC) MESSAGE(STATUS " Non-standard dll names (prefix) . : ${NON_STANDARD_LIB_PREFIX}") @@ -16,104 +16,104 @@ Version 8.32 11-November-2012 5. Rename the "leave" variable names to "quit" to improve WinCE compatibility. Reported by Giuseppe D'Angelo. - -6. The PCRE_STARTLINE bit, indicating that a match can occur only at the start - of a line, was being set incorrectly in cases where .* appeared inside - atomic brackets at the start of a pattern, or where there was a subsequent + +6. The PCRE_STARTLINE bit, indicating that a match can occur only at the start + of a line, was being set incorrectly in cases where .* appeared inside + atomic brackets at the start of a pattern, or where there was a subsequent *PRUNE or *SKIP. 7. Improved instruction cache flush for POWER/PowerPC. Patch by Daniel Richard G. - + 8. Fixed a number of issues in pcregrep, making it more compatible with GNU grep: - + (a) There is now no limit to the number of patterns to be matched. - + (b) An error is given if a pattern is too long. - + (c) Multiple uses of --exclude, --exclude-dir, --include, and --include-dir are now supported. - + (d) --exclude-from and --include-from (multiple use) have been added. - + (e) Exclusions and inclusions now apply to all files and directories, not - just to those obtained from scanning a directory recursively. - + just to those obtained from scanning a directory recursively. + (f) Multiple uses of -f and --file-list are now supported. - - (g) In a Windows environment, the default for -d has been changed from - "read" (the GNU grep default) to "skip", because otherwise the presence + + (g) In a Windows environment, the default for -d has been changed from + "read" (the GNU grep default) to "skip", because otherwise the presence of a directory in the file list provokes an error. - - (h) The documentation has been revised and clarified in places. - + + (h) The documentation has been revised and clarified in places. + 9. Improve the matching speed of capturing brackets. 10. Changed the meaning of \X so that it now matches a Unicode extended grapheme cluster. - + 11. Patch by Daniel Richard G to the autoconf files to add a macro for sorting - out POSIX threads when JIT support is configured. - -12. Added support for PCRE_STUDY_EXTRA_NEEDED. + out POSIX threads when JIT support is configured. -13. In the POSIX wrapper regcomp() function, setting re_nsub field in the preg - structure could go wrong in environments where size_t is not the same size +12. Added support for PCRE_STUDY_EXTRA_NEEDED. + +13. In the POSIX wrapper regcomp() function, setting re_nsub field in the preg + structure could go wrong in environments where size_t is not the same size as int. - -14. Applied user-supplied patch to pcrecpp.cc to allow PCRE_NO_UTF8_CHECK to be + +14. Applied user-supplied patch to pcrecpp.cc to allow PCRE_NO_UTF8_CHECK to be set. - -15. The EBCDIC support had decayed; later updates to the code had included + +15. The EBCDIC support had decayed; later updates to the code had included explicit references to (e.g.) \x0a instead of CHAR_LF. There has been a - general tidy up of EBCDIC-related issues, and the documentation was also - not quite right. There is now a test that can be run on ASCII systems to - check some of the EBCDIC-related things (but is it not a full test). - -16. The new PCRE_STUDY_EXTRA_NEEDED option is now used by pcregrep, resulting + general tidy up of EBCDIC-related issues, and the documentation was also + not quite right. There is now a test that can be run on ASCII systems to + check some of the EBCDIC-related things (but is it not a full test). + +16. The new PCRE_STUDY_EXTRA_NEEDED option is now used by pcregrep, resulting in a small tidy to the code. 17. Fix JIT tests when UTF is disabled and both 8 and 16 bit mode are enabled. 18. If the --only-matching (-o) option in pcregrep is specified multiple - times, each one causes appropriate output. For example, -o1 -o2 outputs the - substrings matched by the 1st and 2nd capturing parentheses. A separating - string can be specified by --om-separator (default empty). + times, each one causes appropriate output. For example, -o1 -o2 outputs the + substrings matched by the 1st and 2nd capturing parentheses. A separating + string can be specified by --om-separator (default empty). 19. Improving the first n character searches. 20. Turn case lists for horizontal and vertical white space into macros so that they are defined only once. - + 21. This set of changes together give more compatible Unicode case-folding - behaviour for characters that have more than one other case when UCP + behaviour for characters that have more than one other case when UCP support is available. - + (a) The Unicode property table now has offsets into a new table of sets of - three or more characters that are case-equivalent. The MultiStage2.py - script that generates these tables (the pcre_ucd.c file) now scans - CaseFolding.txt instead of UnicodeData.txt for character case + three or more characters that are case-equivalent. The MultiStage2.py + script that generates these tables (the pcre_ucd.c file) now scans + CaseFolding.txt instead of UnicodeData.txt for character case information. - + (b) The code for adding characters or ranges of characters to a character class has been abstracted into a generalized function that also handles case-independence. In UTF-mode with UCP support, this uses the new data to handle characters with more than one other case. - + (c) A bug that is fixed as a result of (b) is that codepoints less than 256 whose other case is greater than 256 are now correctly matched - caselessly. Previously, the high codepoint matched the low one, but not - vice versa. - + caselessly. Previously, the high codepoint matched the low one, but not + vice versa. + (d) The processing of \h, \H, \v, and \ in character classes now makes use of the new class addition function, using character lists defined as macros alongside the case definitions of 20 above. - - (e) Caseless back references now work with characters that have more than + + (e) Caseless back references now work with characters that have more than one other case. - - (f) General caseless matching of characters with more than one other case + + (f) General caseless matching of characters with more than one other case is supported. 22. Unicode character properties were updated from Unicode 6.2.0 @@ -124,12 +124,12 @@ Version 8.32 11-November-2012 25. Major JIT compiler update (code refactoring and bugfixing). Experimental Sparc 32 support is added. - -26. Applied a modified version of Daniel Richard G's patch to create - pcre.h.generic and config.h.generic by "make" instead of in the + +26. Applied a modified version of Daniel Richard G's patch to create + pcre.h.generic and config.h.generic by "make" instead of in the PrepareRelease script. - -27. Added a definition for CHAR_NULL (helpful for the z/OS port), and use it in + +27. Added a definition for CHAR_NULL (helpful for the z/OS port), and use it in pcre_compile.c when checking for a zero character. 28. Introducing a native interface for JIT. Through this interface, the compiled @@ -137,30 +137,30 @@ Version 8.32 11-November-2012 provide fast pattern matching, so several sanity checks are not performed. However, feature tests are still performed. The new interface provides 1.4x speedup compared to the old one. - + 29. If pcre_exec() or pcre_dfa_exec() was called with a negative value for - the subject string length, the error given was PCRE_ERROR_BADOFFSET, which + the subject string length, the error given was PCRE_ERROR_BADOFFSET, which was confusing. There is now a new error PCRE_ERROR_BADLENGTH for this case. - + 30. In 8-bit UTF-8 mode, pcretest failed to give an error for data codepoints greater than 0x7fffffff (which cannot be represented in UTF-8, even under - the "old" RFC 2279). Instead, it ended up passing a negative length to + the "old" RFC 2279). Instead, it ended up passing a negative length to pcre_exec(). - + 31. Add support for GCC's visibility feature to hide internal functions. 32. Running "pcretest -C pcre8" or "pcretest -C pcre16" gave a spurious error "unknown -C option" after outputting 0 or 1. - + 33. There is now support for generating a code coverage report for the test - suite in environments where gcc is the compiler and lcov is installed. This - is mainly for the benefit of the developers. - + suite in environments where gcc is the compiler and lcov is installed. This + is mainly for the benefit of the developers. + 34. If PCRE is built with --enable-valgrind, certain memory regions are marked - unaddressable using valgrind annotations, allowing valgrind to detect + unaddressable using valgrind annotations, allowing valgrind to detect invalid memory accesses. This is mainly for the benefit of the developers. - -25. (*UTF) can now be used to start a pattern in any of the three libraries. + +25. (*UTF) can now be used to start a pattern in any of the three libraries. Version 8.31 06-July-2012 @@ -7,39 +7,39 @@ Release 8.32 12-November-2012 This release fixes a number of bugs, but also has some new features. These are the highlights: -. There is now support for 32-bit character strings and UTF-32. Like the +. There is now support for 32-bit character strings and UTF-32. Like the 16-bit support, this is done by compiling a separate 32-bit library. -. \X now matches a Unicode extended grapheme cluster. +. \X now matches a Unicode extended grapheme cluster. . Case-independent matching of Unicode characters that have more than one - "other case" now makes all three (or more) characters equivalent. This + "other case" now makes all three (or more) characters equivalent. This applies, for example, to Greek Sigma, which has two lowercase versions. - -. Unicode character properties are updated to Unicode 6.2.0. + +. Unicode character properties are updated to Unicode 6.2.0. . The EBCDIC support, which had decayed, has had a spring clean. -. A number of JIT optimizations have been added, which give faster JIT +. A number of JIT optimizations have been added, which give faster JIT execution speed. In addition, a new direct interface to JIT execution is - available. This bypasses some of the sanity checks of pcre_exec() to give a + available. This bypasses some of the sanity checks of pcre_exec() to give a noticeable speed-up. . A number of issues in pcregrep have been fixed, making it more compatible - with GNU grep. In particular, --exclude and --include (and variants) apply - to all files now, not just those obtained from scanning a directory + with GNU grep. In particular, --exclude and --include (and variants) apply + to all files now, not just those obtained from scanning a directory recursively. In Windows environments, the default action for directories is now "skip" instead of "read" (which provokes an error). - + . If the --only-matching (-o) option in pcregrep is specified multiple - times, each one causes appropriate output. For example, -o1 -o2 outputs the - substrings matched by the 1st and 2nd capturing parentheses. A separating - string can be specified by --om-separator (default empty). - -. When PCRE is built via Autotools using a version of gcc that has the + times, each one causes appropriate output. For example, -o1 -o2 outputs the + substrings matched by the 1st and 2nd capturing parentheses. A separating + string can be specified by --om-separator (default empty). + +. When PCRE is built via Autotools using a version of gcc that has the "visibility" feature, it is used to hide internal library functions that are not part of the public API. - + Release 8.31 06-July-2012 ------------------------- diff --git a/NON-AUTOTOOLS-BUILD b/NON-AUTOTOOLS-BUILD index 671c3f4..7ef5abb 100644 --- a/NON-AUTOTOOLS-BUILD +++ b/NON-AUTOTOOLS-BUILD @@ -56,12 +56,12 @@ can skip ahead to the CMake section. (1) Copy or rename the file config.h.generic as config.h, and edit the macro settings that it contains to whatever is appropriate for your environment. - In particular, you can alter the definition of the NEWLINE macro to + In particular, you can alter the definition of the NEWLINE macro to specify what character(s) you want to be interpreted as line terminators. In an EBCDIC environment, you MUST change NEWLINE, because its default value is 10, an ASCII LF. The usual EBCDIC newline character is 21 (0x15, NL), though in some cases it may be 37 (0x25). - + When you compile any of the PCRE modules, you must specify -DHAVE_CONFIG_H to your compiler so that config.h is included in the sources. @@ -392,7 +392,7 @@ CMake build process. In the CMake GUI, the cache can be deleted by selecting 4. Run cmake-gui from the Shell envirornment of your build tool, for example, Msys for Msys/MinGW or Visual Studio Command Prompt for VC/VC++. Do not try - to start Cmake from the Windows Start menu, as this can lead to errors. + to start Cmake from the Windows Start menu, as this can lead to errors. 5. Enter C:\pcre\pcre-xx and C:\pcre\pcre-xx\build for the source and build directories, respectively. diff --git a/PrepareRelease b/PrepareRelease index 1486c02..4ec803e 100755 --- a/PrepareRelease +++ b/PrepareRelease @@ -59,7 +59,7 @@ End echo "Making pcre.txt" for file in pcre pcre16 pcre32 pcrebuild pcrematching pcreapi pcrecallout \ - pcrecompat \ pcrepattern pcresyntax pcreunicode pcrejit pcrepartial \ + pcrecompat pcrepattern pcresyntax pcreunicode pcrejit pcrepartial \ pcreprecompile pcreperform pcreposix pcrecpp pcresample \ pcrelimits pcrestack ; do echo " Processing $file.3" @@ -322,28 +322,28 @@ library. They are also documented in the pcrebuild man page. This automatically implies --enable-rebuild-chartables (see above). However, when PCRE is built this way, it always operates in EBCDIC. It cannot support both EBCDIC and UTF-8/16/32. There is a second option, --enable-ebcdic-nl25, - which specifies that the code value for the EBCDIC NL character is 0x25 - instead of the default 0x15. - + which specifies that the code value for the EBCDIC NL character is 0x25 + instead of the default 0x15. + . In environments where valgrind is installed, if you specify --enable-valgrind - + PCRE will use valgrind annotations to mark certain memory regions as unaddressable. This allows it to detect invalid memory accesses, and is mostly useful for debugging PCRE itself. -. In environments where the gcc compiler is used and lcov version 1.6 or above +. In environments where the gcc compiler is used and lcov version 1.6 or above is installed, if you specify --enable-coverage - + the build process implements a code coverage report for the test suite. The - report is generated by running "make coverage". If ccache is installed on + report is generated by running "make coverage". If ccache is installed on your system, it must be disabled when building PCRE for coverage reporting. - You can do this by setting the environment variable CCACHE_DISABLE=1 before - running "make" to build PCRE. - + You can do this by setting the environment variable CCACHE_DISABLE=1 before + running "make" to build PCRE. + . The pcregrep program currently supports only 8-bit data files, and so requires the 8-bit PCRE library. It is possible to compile pcregrep to use libz and/or libbz2, in order to read .gz and .bz2 files (respectively), by @@ -127,7 +127,7 @@ if [ $# -eq 1 -a "$1" = "ebcdic" ]; then if [ $ebcdic -ne 1 ] ; then echo "Cannot run EBCDIC tests: EBCDIC support not compiled" exit 1 - fi + fi for opt in "" "-s" "-dfa" "-s -dfa"; do ./pcretest -q $opt $testdata/testinputEBC >testtry @@ -138,7 +138,7 @@ if [ $# -eq 1 -a "$1" = "ebcdic" ]; then fi if [ "$opt" = "-s" ] ; then echo " OK with study" elif [ "$opt" = "-dfa" ] ; then echo " OK using DFA" - elif [ "$opt" = "-s -dfa" ] ; then echo " OK using DFA with study" + elif [ "$opt" = "-s -dfa" ] ; then echo " OK using DFA with study" else echo " OK" fi done @@ -147,7 +147,7 @@ exit 0 fi -# ------ Normal Tests ------ +# ------ Normal Tests ------ # Default values @@ -229,7 +229,7 @@ while [ $# -gt 0 ] ; do shift done -# Find which optional facilities are available. +# Find which optional facilities are available. $sim ./pcretest -C linksize >/dev/null link_size=$? @@ -263,13 +263,13 @@ test32=skip if [ "$arg8$arg16$arg32" = "" ] ; then if [ $support8 -ne 0 ] ; then test8= - fi + fi if [ $support16 -ne 0 ] ; then test16=-16 - fi + fi if [ $support32 -ne 0 ] ; then test32=-32 - fi + fi # Select requested bit sizes @@ -280,21 +280,21 @@ else exit 1 fi test8= - fi + fi if [ "$arg16" = yes ] ; then if [ $support16 -eq 0 ] ; then echo "Cannot run 16-bit library tests: 16-bit library not compiled" exit 1 fi test16=-16 - fi + fi if [ "$arg32" = yes ] ; then if [ $support32 -eq 0 ] ; then echo "Cannot run 32-bit library tests: 32-bit library not compiled" exit 1 fi test32=-32 - fi + fi fi # UTF support always applies to all bit sizes if both are supported; we can't diff --git a/configure.ac b/configure.ac index 6f991b2..2cfab75 100644 --- a/configure.ac +++ b/configure.ac @@ -368,7 +368,7 @@ then fi fi -# Convert the newline identifier into the appropriate integer value. The first +# Convert the newline identifier into the appropriate integer value. The first # three are ASCII values 0x0a, 0x0d, and 0x0d0a, but if EBCDIC is enabled, they # are changed below. @@ -386,7 +386,7 @@ esac # --enable-ebcdic-nl25 implies --enable-ebcdic if test "x$enable_ebcdic_nl25" = "xyes"; then enable_ebcdic=yes -fi +fi # Make sure that if enable_ebcdic is set, rebuild_chartables is also enabled, # and the newline value is adjusted appropriately (CR is still 13, but LF is @@ -405,13 +405,13 @@ if test "x$enable_ebcdic" = "xyes"; then case "$ac_pcre_newline_value" in 10) ac_pcre_newline_value=21 ;; 3338) ac_pcre_newline_value=3349 ;; - esac - else + esac + else case "$ac_pcre_newline_value" in 10) ac_pcre_newline_value=37 ;; 3338) ac_pcre_newline_value=3365 ;; - esac - fi + esac + fi fi # Check argument to --with-link-size @@ -697,8 +697,8 @@ if test "$enable_stack_for_recursion" = "no"; then AC_DEFINE([NO_RECURSE], [], [ PCRE uses recursive function calls to handle backtracking while matching. This can sometimes be a problem on systems that have - stacks of limited size. Define NO_RECURSE to any value to get a - version that doesn't use recursion in the match() function; instead + stacks of limited size. Define NO_RECURSE to any value to get a + version that doesn't use recursion in the match() function; instead it creates its own stack by steam using pcre_recurse_malloc() to obtain memory from the heap. For more detail, see the comments and other stuff just above the match() function.]) @@ -748,7 +748,7 @@ if test "$enable_bsr_anycrlf" = "yes"; then AC_DEFINE([BSR_ANYCRLF], [], [ By default, the \R escape sequence matches any Unicode line ending character or sequence of characters. If BSR_ANYCRLF is defined (to any - value), this is changed so that backslash-R matches only CR, LF, or CRLF. + value), this is changed so that backslash-R matches only CR, LF, or CRLF. The build-time default can be overridden by the user of PCRE at runtime.]) fi @@ -803,10 +803,10 @@ AH_VERBATIM([PCRE_EXP_DEFN], [ Win32, and it needs some magic to be inserted before the definition of a function that is exported by the library, define this macro to contain the relevant magic. If you do not define this macro, a suitable - __declspec value is used for Windows systems; in other environments - "extern" is used for a C compiler and "extern C" for a C++ compiler. - This macro apears at the start of every exported function that is part - of the external API. It does not appear on functions that are "external" + __declspec value is used for Windows systems; in other environments + "extern" is used for a C compiler and "extern C" for a C++ compiler. + This macro apears at the start of every exported function that is part + of the external API. It does not appear on functions that are "external" in the C sense, but which are internal to the library. */ #undef PCRE_EXP_DEFN]) @@ -829,7 +829,7 @@ if test "$enable_ebcdic_nl25" = "yes"; then that LF does in an ASCII/Unicode environment. The value must also be set in the NEWLINE macro below. On systems that can use "configure" or CMake to set EBCDIC_NL25, the adjustment of NEWLINE is automatic.]) -fi +fi if test "$enable_valgrind" = "yes"; then AC_DEFINE_UNQUOTED([SUPPORT_VALGRIND], [], [ @@ -981,7 +981,7 @@ if test "$enable_coverage" = "yes"; then fi AC_DEFINE([SUPPORT_GCOV],[1], [ - Define to allow pcretest and pcregrep to be linked with gcov, so that they + Define to allow pcretest and pcregrep to be linked with gcov, so that they are able to generate code coverage reports.]) # And add flags needed for gcov @@ -1026,7 +1026,7 @@ if test "$enable_ebcdic_nl25" = "yes"; then ebcdic_nl_code=0x25 elif test "$enable_ebcdic" = "yes"; then ebcdic_nl_code=0x15 -fi +fi cat <<EOF @@ -1054,7 +1054,7 @@ $PACKAGE-$VERSION configuration summary: Newline char/sequence ........... : ${enable_newline} \R matches only ANYCRLF ......... : ${enable_bsr_anycrlf} EBCDIC coding ................... : ${enable_ebcdic} - EBCDIC code for NL .............. : ${ebcdic_nl_code} + EBCDIC code for NL .............. : ${ebcdic_nl_code} Rebuild char tables ............. : ${enable_rebuild_chartables} Use stack recursion ............. : ${enable_stack_for_recursion} POSIX mem threshold ............. : ${with_posix_malloc_threshold} @@ -125,7 +125,7 @@ fprintf(f, "#include \"config.h\"\n" "#endif\n\n" "#include \"pcre_internal.h\"\n\n"); - + fprintf(f, "const pcre_uint8 PRIV(default_tables)[] = {\n\n" "/* This table is a lower casing table. */\n\n"); diff --git a/doc/html/index.html b/doc/html/index.html index c7bc196..21e11ea 100644 --- a/doc/html/index.html +++ b/doc/html/index.html @@ -1,10 +1,10 @@ <html> -<!-- This is a manually maintained file that is the root of the HTML version of - the PCRE documentation. When the HTML documents are built from the man - page versions, the entire doc/html directory is emptied, this file is then - copied into doc/html/index.html, and the remaining files therein are +<!-- This is a manually maintained file that is the root of the HTML version of + the PCRE documentation. When the HTML documents are built from the man + page versions, the entire doc/html directory is emptied, this file is then + copied into doc/html/index.html, and the remaining files therein are created by the 132html script. ---> +--> <head> <title>PCRE specification</title> </head> @@ -94,7 +94,7 @@ in the library. There is a single page for each triple of 8-bit/16-bit/32-bit functions. </p> -<table> +<table> <tr><td><a href="pcre_assign_jit_stack.html">pcre_assign_jit_stack</a></td> <td> Assign stack for JIT matching</td></tr> @@ -157,7 +157,7 @@ functions. <tr><td><a href="pcre_maketables.html">pcre_maketables</a></td> <td> Build character tables in current locale</td></tr> - + <tr><td><a href="pcre_pattern_to_host_byte_order.html">pcre_pattern_to_host_byte_order</a></td> <td> Convert compiled pattern to host byte order if necessary</td></tr> diff --git a/doc/html/pcre-config.html b/doc/html/pcre-config.html index 3df7ff4..c2e3ba2 100644 --- a/doc/html/pcre-config.html +++ b/doc/html/pcre-config.html @@ -31,7 +31,7 @@ man page, in case the conversion went wrong. <b>pcre-config</b> returns the configuration of the installed PCRE libraries and the options required to compile a program to use them. Some of the options apply only to the 8-bit, or 16-bit, or 32-bit libraries, -respectively, and are +respectively, and are not available if only one of those libraries has been built. If an unavailable option is encountered, the "usage" information is output. </P> diff --git a/doc/html/pcre.html b/doc/html/pcre.html index f05e08c..edb7479 100644 --- a/doc/html/pcre.html +++ b/doc/html/pcre.html @@ -118,10 +118,12 @@ If you are using PCRE in a non-UTF application that permits users to supply arbitrary patterns for compilation, you should be aware of a feature that allows users to turn on UTF support from within a pattern, provided that PCRE was built with UTF support. For example, an 8-bit pattern that begins with -"(*UTF8)" turns on UTF-8 mode. This causes both the pattern and any data -against which it is matched to be checked for UTF-8 validity. If the data -string is very long, such a check might use sufficiently many resources as to -cause your application to lose performance. +"(*UTF8)" or "(*UTF)" turns on UTF-8 mode, which interprets patterns and +subjects as strings of UTF-8 characters instead of individual 8-bit characters. +This causes both the pattern and any data against which it is matched to be +checked for UTF-8 validity. If the data string is very long, such a check might +use sufficiently many resources as to cause your application to lose +performance. </P> <P> The best way of guarding against this possibility is to use the @@ -130,13 +132,13 @@ The best way of guarding against this possibility is to use the <P> If your application is one that supports UTF, be aware that validity checking can take time. If the same data string is to be matched many times, you can use -the PCRE_NO_UTF[8|16|32]_CHECK option for the second and subsequent matches to +the PCRE_NO_UTF[8|16|32]_CHECK option for the second and subsequent matches to save redundant checks. </P> <P> -Another way that performance can be hit is by running a pattern that has a very -large search tree against a string that will never match. Nested unlimited -repeats in a pattern are a common example. PCRE provides some protection +Another way that performance can be hit is by running a pattern that has a very +large search tree against a string that will never match. Nested unlimited +repeats in a pattern are a common example. PCRE provides some protection against this: see the PCRE_EXTRA_MATCH_LIMIT feature in the <a href="pcreapi.html"><b>pcreapi</b></a> page. @@ -193,7 +195,7 @@ two digits 10, at the domain cam.ac.uk. </P> <br><a name="SEC5" href="#TOC1">REVISION</a><br> <P> -Last updated: 30 October 2012 +Last updated: 11 November 2012 <br> Copyright © 1997-2012 University of Cambridge. <br> diff --git a/doc/html/pcre16.html b/doc/html/pcre16.html index 06388ed..179b2ad 100644 --- a/doc/html/pcre16.html +++ b/doc/html/pcre16.html @@ -187,7 +187,7 @@ library. For example, if you want to study a pattern that was compiled with <br><a name="SEC7" href="#TOC1">THE HEADER FILE</a><br> <P> There is only one header file, <b>pcre.h</b>. It contains prototypes for all the -functions in both libraries, as well as definitions of flags, structures, error +functions in all libraries, as well as definitions of flags, structures, error codes, etc. </P> <br><a name="SEC8" href="#TOC1">THE LIBRARY NAME</a><br> @@ -203,9 +203,9 @@ of bytes with the C type "char *". In the 16-bit library, strings are passed as vectors of unsigned 16-bit quantities. The macro PCRE_UCHAR16 specifies an appropriate data type, and PCRE_SPTR16 is defined as "const PCRE_UCHAR16 *". In very many environments, "short int" is a 16-bit data type. When PCRE is built, -it defines PCRE_UCHAR16 as "short int", but checks that it really is a 16-bit -data type. If it is not, the build fails with an error message telling the -maintainer to modify the definition appropriately. +it defines PCRE_UCHAR16 as "unsigned short int", but checks that it really is a +16-bit data type. If it is not, the build fails with an error message telling +the maintainer to modify the definition appropriately. </P> <br><a name="SEC10" href="#TOC1">STRUCTURE TYPES</a><br> <P> @@ -374,7 +374,7 @@ Cambridge CB2 3QH, England. </P> <br><a name="SEC22" href="#TOC1">REVISION</a><br> <P> -Last updated: 14 April 2012 +Last updated: 08 November 2012 <br> Copyright © 1997-2012 University of Cambridge. <br> diff --git a/doc/html/pcre32.html b/doc/html/pcre32.html index f170adf..629cf7c 100644 --- a/doc/html/pcre32.html +++ b/doc/html/pcre32.html @@ -168,7 +168,7 @@ man page, in case the conversion went wrong. Starting with release 8.32, it is possible to compile a PCRE library that supports 32-bit character strings, including UTF-32 strings, as well as or instead of the original 8-bit library. This work was done by Christian Persch, -based on the work done by Zoltan Herczeg for the 16-bit library. All three +based on the work done by Zoltan Herczeg for the 16-bit library. All three libraries contain identical sets of functions, used in exactly the same way. Only the names of the functions and the data types of their arguments and results are different. To avoid over-complication and reduce the documentation @@ -187,7 +187,7 @@ study data with <b>pcre32_free_study()</b>. <br><a name="SEC7" href="#TOC1">THE HEADER FILE</a><br> <P> There is only one header file, <b>pcre.h</b>. It contains prototypes for all the -functions in both libraries, as well as definitions of flags, structures, error +functions in all libraries, as well as definitions of flags, structures, error codes, etc. </P> <br><a name="SEC8" href="#TOC1">THE LIBRARY NAME</a><br> @@ -202,10 +202,10 @@ In the 8-bit library, strings are passed to PCRE library functions as vectors of bytes with the C type "char *". In the 32-bit library, strings are passed as vectors of unsigned 32-bit quantities. The macro PCRE_UCHAR32 specifies an appropriate data type, and PCRE_SPTR32 is defined as "const PCRE_UCHAR32 *". In -very many environments, "unsigned int" is a 32-bit data type. When PCRE is built, -it defines PCRE_UCHAR32 as "unsigned int", but checks that it really is a 32-bit -data type. If it is not, the build fails with an error message telling the -maintainer to modify the definition appropriately. +very many environments, "unsigned int" is a 32-bit data type. When PCRE is +built, it defines PCRE_UCHAR32 as "unsigned int", but checks that it really is +a 32-bit data type. If it is not, the build fails with an error message telling +the maintainer to modify the definition appropriately. </P> <br><a name="SEC10" href="#TOC1">STRUCTURE TYPES</a><br> <P> @@ -373,7 +373,7 @@ Cambridge CB2 3QH, England. </P> <br><a name="SEC22" href="#TOC1">REVISION</a><br> <P> -Last updated: 24 June 2012 +Last updated: 08 November 2012 <br> Copyright © 1997-2012 University of Cambridge. <br> diff --git a/doc/html/pcre_jit_exec.html b/doc/html/pcre_jit_exec.html index 4f6dfbb..0c63503 100644 --- a/doc/html/pcre_jit_exec.html +++ b/doc/html/pcre_jit_exec.html @@ -56,7 +56,7 @@ It returns offsets to captured substrings. Its arguments are: <i>options</i> Option bits <i>ovector</i> Points to a vector of ints for result offsets <i>ovecsize</i> Number of elements in the vector (a multiple of 3) - <i>jstack</i> Pointer to a JIT stack + <i>jstack</i> Pointer to a JIT stack </pre> The allowed options are: <pre> @@ -79,7 +79,7 @@ The allowed options are: PCRE_PARTIAL_HARD Return PCRE_ERROR_PARTIAL for a partial match if that is found before a full match </pre> -However, the PCRE_NO_UTF[8|16|32]_CHECK options have no effect, as this check +However, the PCRE_NO_UTF[8|16|32]_CHECK options have no effect, as this check is never applied. For details of partial matching, see the <a href="pcrepartial.html"><b>pcrepartial</b></a> page. A <b>pcre_extra</b> structure contains the following fields: diff --git a/doc/html/pcreapi.html b/doc/html/pcreapi.html index 742f61a..59398df 100644 --- a/doc/html/pcreapi.html +++ b/doc/html/pcreapi.html @@ -17,7 +17,7 @@ man page, in case the conversion went wrong. <li><a name="TOC2" href="#SEC2">PCRE NATIVE API STRING EXTRACTION FUNCTIONS</a> <li><a name="TOC3" href="#SEC3">PCRE NATIVE API AUXILIARY FUNCTIONS</a> <li><a name="TOC4" href="#SEC4">PCRE NATIVE API INDIRECTED FUNCTIONS</a> -<li><a name="TOC5" href="#SEC5">PCRE 8-BIT, 16-BIT AND 32-BIT LIBRARIES</a> +<li><a name="TOC5" href="#SEC5">PCRE 8-BIT, 16-BIT, AND 32-BIT LIBRARIES</a> <li><a name="TOC6" href="#SEC6">PCRE API OVERVIEW</a> <li><a name="TOC7" href="#SEC7">NEWLINES</a> <li><a name="TOC8" href="#SEC8">MULTITHREADING</a> @@ -167,14 +167,14 @@ man page, in case the conversion went wrong. <P> <b>int (*pcre_callout)(pcre_callout_block *);</b> </P> -<br><a name="SEC5" href="#TOC1">PCRE 8-BIT, 16-BIT AND 32-BIT LIBRARIES</a><br> +<br><a name="SEC5" href="#TOC1">PCRE 8-BIT, 16-BIT, AND 32-BIT LIBRARIES</a><br> <P> -From release 8.30, PCRE can be compiled as a library for handling 16-bit -character strings as well as, or instead of, the original library that handles -8-bit character strings. From release 8.32, PCRE can also be compiled as a -library for handling 32-bit character strings. To avoid too much complication, -this document describes the 8-bit versions of the functions, with only -occasional references to the 16-bit and 32-bit libraries. +As well as support for 8-bit character strings, PCRE also supports 16-bit +strings (from release 8.30) and 32-bit strings (from release 8.32), by means of +two additional libraries. They can be built as well as, or instead of, the +8-bit library. To avoid too much complication, this document describes the +8-bit versions of the functions, with only occasional references to the 16-bit +and 32-bit libraries. </P> <P> The 16-bit and 32-bit functions operate in the same way as their 8-bit @@ -187,7 +187,7 @@ by UTF16 or UTF32, respectively. This facility is in fact just cosmetic; the </P> <P> References to bytes and UTF-8 in this document should be read as references to -16-bit data quantities and UTF-16 when using the 16-bit library, or 32-bit data +16-bit data quantities and UTF-16 when using the 16-bit library, or 32-bit data quantities and UTF-32 when using the 32-bit library, unless specified otherwise. More details of the specific differences for the 16-bit and 32-bit libraries are given in the @@ -450,7 +450,7 @@ unaligned)". If JIT support is not available, the result is NULL. PCRE_CONFIG_NEWLINE </pre> The output is an integer whose value specifies the default character sequence -that is recognized as meaning "newline". The values that are supported in +that is recognized as meaning "newline". The values that are supported in ASCII/Unicode environments are: 10 for LF, 13 for CR, 3338 for CRLF, -2 for ANYCRLF, and -1 for ANY. In EBCDIC environments, CR, ANYCRLF, and ANY yield the same values. However, the value for LF is normally 21, though some EBCDIC @@ -768,7 +768,7 @@ indicated by a single character (CR or LF, respectively). Setting PCRE_NEWLINE_CRLF specifies that a newline is indicated by the two-character CRLF sequence. Setting PCRE_NEWLINE_ANYCRLF specifies that any of the three preceding sequences should be recognized. Setting PCRE_NEWLINE_ANY specifies -that any Unicode newline sequence should be recognized. +that any Unicode newline sequence should be recognized. </P> <P> In an ASCII/Unicode environment, the Unicode newline sequences are the three @@ -780,8 +780,8 @@ recognized only in UTF-8 mode. <P> When PCRE is compiled to run in an EBCDIC (mainframe) environment, the code for CR is 0x0d, the same as ASCII. However, the character code for LF is normally -0x15, though in some EBCDIC environments 0x25 is used. Whichever of these is -not LF is made to correspond to Unicode's NEL character. EBCDIC codes are all +0x15, though in some EBCDIC environments 0x25 is used. Whichever of these is +not LF is made to correspond to Unicode's NEL character. EBCDIC codes are all less than 256. For more details, see the <a href="pcrebuild.html"><b>pcrebuild</b></a> documentation. @@ -864,8 +864,8 @@ this check for performance reasons, you can set the PCRE_NO_UTF8_CHECK option. When it is set, the effect of passing an invalid UTF-8 string as a pattern is undefined. It may cause your program to crash. Note that this option can also be passed to <b>pcre_exec()</b> and <b>pcre_dfa_exec()</b>, to suppress the -validity checking of subject strings only. If the same string is being matched -many times, the option can be safely set for the second and subsequent +validity checking of subject strings only. If the same string is being matched +many times, the option can be safely set for the second and subsequent matchings to improve performance. </P> <br><a name="SEC12" href="#TOC1">COMPILATION ERROR CODES</a><br> @@ -988,7 +988,7 @@ in the section on matching a pattern. If studying the pattern does not produce any useful information, <b>pcre_study()</b> returns NULL by default. In that circumstance, if the calling program wants to pass any of the other fields to <b>pcre_exec()</b> or -<b>pcre_dfa_exec()</b>, it must set up its own <b>pcre_extra</b> block. However, +<b>pcre_dfa_exec()</b>, it must set up its own <b>pcre_extra</b> block. However, if <b>pcre_study()</b> is called with the PCRE_STUDY_EXTRA_NEEDED option, it returns a <b>pcre_extra</b> block even if studying did not find any additional information. It may still return NULL, however, if an error occurs in @@ -2238,15 +2238,15 @@ so that it runs on the new host. </pre> This error is returned when a pattern that was successfully studied using a JIT compile option is being matched, but the matching mode (partial or complete -match) does not correspond to any JIT compilation mode. When the JIT fast path +match) does not correspond to any JIT compilation mode. When the JIT fast path function is used, this error may be also given for invalid options. See the <a href="pcrejit.html"><b>pcrejit</b></a> documentation for more details. <pre> PCRE_ERROR_BADLENGTH (-32) </pre> -This error is given if <b>pcre_exec()</b> is called with a negative value for -the <i>length</i> argument. +This error is given if <b>pcre_exec()</b> is called with a negative value for +the <i>length</i> argument. </P> <P> Error numbers -16 to -20, -22, and 30 are not used by <b>pcre_exec()</b>. @@ -2256,11 +2256,11 @@ Reason codes for invalid UTF-8 strings </b><br> <P> This section applies only to the 8-bit library. The corresponding information -for the 16-bit library is given in the +for the 16-bit and 32-bit libraries is given in the <a href="pcre16.html"><b>pcre16</b></a> -page. The corresponding information for the 32-bit library is given in the +and <a href="pcre32.html"><b>pcre32</b></a> -page. +pages. </P> <P> When <b>pcre_exec()</b> returns either PCRE_ERROR_BADUTF8 or @@ -2777,7 +2777,7 @@ Cambridge CB2 3QH, England. </P> <br><a name="SEC26" href="#TOC1">REVISION</a><br> <P> -Last updated: 31 October 2012 +Last updated: 08 November 2012 <br> Copyright © 1997-2012 University of Cambridge. <br> diff --git a/doc/html/pcrebuild.html b/doc/html/pcrebuild.html index d6fa8f4..6eb169b 100644 --- a/doc/html/pcrebuild.html +++ b/doc/html/pcrebuild.html @@ -48,8 +48,8 @@ the GUI facility of <b>cmake-gui</b> if you are using <b>CMake</b> instead of <b>configure</b> to build PCRE. </P> <P> -There is a lot more information about building PCRE without using -<b>configure</b> (including information about using <b>CMake</b> or building "by +There is a lot more information about building PCRE without using +<b>configure</b> (including information about using <b>CMake</b> or building "by hand") in the file called <i>NON-AUTOTOOLS-BUILD</i>, which is part of the PCRE distribution. You should consult this file as well as the <i>README</i> file if you are building in a non-Unix-like environment. @@ -351,19 +351,19 @@ an EBCDIC environment (for example, an IBM mainframe operating system). The --enable-ebcdic option is incompatible with --enable-utf. </P> <P> -The EBCDIC character that corresponds to an ASCII LF is assumed to have the -value 0x15 by default. However, in some EBCDIC environments, 0x25 is used. In +The EBCDIC character that corresponds to an ASCII LF is assumed to have the +value 0x15 by default. However, in some EBCDIC environments, 0x25 is used. In such an environment you should use <pre> --enable-ebcdic-nl25 </pre> -as well as, or instead of, --enable-ebcdic. The EBCDIC character for CR has the -same value as in ASCII, namely, 0x0d. Whichever of 0x15 and 0x25 is <i>not</i> -chosen as LF is made to correspond to the Unicode NEL character (which, in +as well as, or instead of, --enable-ebcdic. The EBCDIC character for CR has the +same value as in ASCII, namely, 0x0d. Whichever of 0x15 and 0x25 is <i>not</i> +chosen as LF is made to correspond to the Unicode NEL character (which, in Unicode, is 0x85). </P> <P> -The options that select newline behaviour, such as --enable-newline-is-cr, +The options that select newline behaviour, such as --enable-newline-is-cr, and equivalent run-time options, refer to these character values in an EBCDIC environment. </P> @@ -444,7 +444,7 @@ code coverage report for its test suite. To enable this, you must install <pre> --enable-coverage </pre> -to the <b>configure</b> command and build PCRE in the usual way. +to the <b>configure</b> command and build PCRE in the usual way. </P> <P> Note that using <b>ccache</b> (a caching C compiler) is incompatible with code @@ -489,9 +489,9 @@ created at compile time (*.gcno). <pre> make coverage-clean </pre> -This cleans all coverage data including the generated coverage report. For more -information about code coverage, see the <b>gcov</b> and <b>lcov</b> -documentation. +This cleans all coverage data including the generated coverage report. For more +information about code coverage, see the <b>gcov</b> and <b>lcov</b> +documentation. </P> <br><a name="SEC21" href="#TOC1">SEE ALSO</a><br> <P> diff --git a/doc/html/pcrejit.html b/doc/html/pcrejit.html index 7161e71..6286fcc 100644 --- a/doc/html/pcrejit.html +++ b/doc/html/pcrejit.html @@ -64,7 +64,7 @@ JIT. The support is limited to the following hardware platforms: Intel x86 32-bit and 64-bit MIPS 32-bit Power PC 32-bit and 64-bit - SPARC 32-bit (experimental) + SPARC 32-bit (experimental) </pre> If --enable-jit is set on an unsupported platform, compilation fails. </P> @@ -73,8 +73,8 @@ A program that is linked with PCRE 8.20 or later can tell if JIT support is available by calling <b>pcre_config()</b> with the PCRE_CONFIG_JIT option. The result is 1 when JIT is available, and 0 otherwise. However, a simple program does not need to check this in order to use JIT. The normal API is implemented -in a way that falls back to the interpretive code if JIT is not available. For -programs that need the best possible performance, there is also a "fast path" +in a way that falls back to the interpretive code if JIT is not available. For +programs that need the best possible performance, there is also a "fast path" API that is JIT-specific. </P> <P> @@ -407,18 +407,18 @@ callback. </P> <br><a name="SEC11" href="#TOC1">JIT FAST PATH API</a><br> <P> -Because the API described above falls back to interpreted execution when JIT is -not available, it is convenient for programs that are written for general use -in many environments. However, calling JIT via <b>pcre_exec()</b> does have a -performance impact. Programs that are written for use where JIT is known to be +Because the API described above falls back to interpreted execution when JIT is +not available, it is convenient for programs that are written for general use +in many environments. However, calling JIT via <b>pcre_exec()</b> does have a +performance impact. Programs that are written for use where JIT is known to be available, and which need the best possible performance, can instead use a "fast path" API to call JIT execution directly instead of calling -<b>pcre_exec()</b> (obviously only for patterns that have been successfully +<b>pcre_exec()</b> (obviously only for patterns that have been successfully studied by JIT). </P> <P> -The fast path function is called <b>pcre_jit_exec()</b>, and it takes exactly -the same arguments as <b>pcre_exec()</b>, plus one additional argument that +The fast path function is called <b>pcre_jit_exec()</b>, and it takes exactly +the same arguments as <b>pcre_exec()</b>, plus one additional argument that must point to a JIT stack. The JIT stack arrangements described above do not apply. The return values are the same as for <b>pcre_exec()</b>. </P> @@ -431,7 +431,7 @@ for validity. In the interests of speed, these checks do not happen on the JIT fast path, and if invalid data is passed, the result is undefined. </P> <P> -Bypassing the sanity checks and the <b>pcre_exec()</b> wrapping can give +Bypassing the sanity checks and the <b>pcre_exec()</b> wrapping can give speedups of more than 10%. </P> <br><a name="SEC12" href="#TOC1">SEE ALSO</a><br> diff --git a/doc/html/pcrepattern.html b/doc/html/pcrepattern.html index 93c3e1f..ee55d06 100644 --- a/doc/html/pcrepattern.html +++ b/doc/html/pcrepattern.html @@ -63,17 +63,19 @@ description of PCRE's regular expressions is intended as reference material. <P> The original operation of PCRE was on strings of one-byte characters. However, there is now also support for UTF-8 strings in the original library, an -extra library that supports 16-bit and UTF-16 character strings, and an -extra library that supports 32-bit and UTF-32 character strings. To use these +extra library that supports 16-bit and UTF-16 character strings, and a +third library that supports 32-bit and UTF-32 character strings. To use these features, PCRE must be built to include appropriate support. When using UTF strings you must either call the compiling function with the PCRE_UTF8, -PCRE_UTF16 or PCRE_UTF32 option, or the pattern must start with one of +PCRE_UTF16, or PCRE_UTF32 option, or the pattern must start with one of these special sequences: <pre> (*UTF8) (*UTF16) (*UTF32) + (*UTF) </pre> +(*UTF) is a generic sequence that can be used with any of the libraries. Starting a pattern with such a sequence is equivalent to setting the relevant option. This feature is not Perl-compatible. How setting a UTF mode affects pattern matching is mentioned in several places below. There is also a summary @@ -83,7 +85,7 @@ page. </P> <P> Another special sequence that may appear at the start of a pattern or in -combination with (*UTF8) or (*UTF16) or (*UTF32) is: +combination with (*UTF8), (*UTF16), (*UTF32) or (*UTF) is: <pre> (*UCP) </pre> @@ -112,10 +114,10 @@ page. </P> <br><a name="SEC2" href="#TOC1">EBCDIC CHARACTER CODES</a><br> <P> -PCRE can be compiled to run in an environment that uses EBCDIC as its character -code rather than ASCII or Unicode (typically a mainframe system). In the -sections below, character code values are ASCII or Unicode; in an EBCDIC -environment these characters may have different code values, and there are no +PCRE can be compiled to run in an environment that uses EBCDIC as its character +code rather than ASCII or Unicode (typically a mainframe system). In the +sections below, character code values are ASCII or Unicode; in an EBCDIC +environment these characters may have different code values, and there are no code points greater than 255. <a name="newlines"></a></P> <br><a name="SEC3" href="#TOC1">NEWLINE CONVENTIONS</a><br> @@ -152,10 +154,11 @@ they must be in upper case. If more than one of them is present, the last one is used. </P> <P> -The newline convention affects the interpretation of the dot metacharacter when -PCRE_DOTALL is not set, and also the behaviour of \N. However, it does not -affect what the \R escape sequence matches. By default, this is any Unicode -newline sequence, for Perl compatibility. However, this can be changed; see the +The newline convention affects where the circumflex and dollar assertions are +true. It also affects the interpretation of the dot metacharacter when +PCRE_DOTALL is not set, and the behaviour of \N. However, it does not affect +what the \R escape sequence matches. By default, this is any Unicode newline +sequence, for Perl compatibility. However, this can be changed; see the description of \R in the section entitled <a href="#newlineseq">"Newline sequences"</a> below. A change of \R setting can be combined with a change of newline @@ -298,7 +301,7 @@ recognized when PCRE is compiled in EBCDIC mode, where data items are always bytes. In this mode, all values are valid after \c. If the next character is a lower case letter, it is converted to upper case. Then the 0xc0 bits of the byte are inverted. Thus \cA becomes hex 01, as in ASCII (A is C1), but because -the EBCDIC letters are disjoint, \cZ becomes hex 29 (Z is E9), and other +the EBCDIC letters are disjoint, \cZ becomes hex 29 (Z is E9), and other characters also generate different values. </P> <P> @@ -574,10 +577,10 @@ change of newline convention; for example, a pattern can start with: <pre> (*ANY)(*BSR_ANYCRLF) </pre> -They can also be combined with the (*UTF8), (*UTF16), (*UTF32) or (*UCP) special -sequences. Inside a character class, \R is treated as an unrecognized escape -sequence, and so matches the letter "R" by default, but causes an error if -PCRE_EXTRA is set. +They can also be combined with the (*UTF8), (*UTF16), (*UTF32), (*UTF) or +(*UCP) special sequences. Inside a character class, \R is treated as an +unrecognized escape sequence, and so matches the letter "R" by default, but +causes an error if PCRE_EXTRA is set. <a name="uniextseq"></a></P> <br><b> Unicode character properties @@ -836,7 +839,7 @@ of extended grapheme clusters. In releases of PCRE later than 8.31, \X matches one of these clusters. </P> <P> -\X always matches at least one character. Then it decides whether to add +\X always matches at least one character. Then it decides whether to add additional characters according to the following rules for ending a cluster: </P> <P> @@ -846,9 +849,9 @@ additional characters according to the following rules for ending a cluster: 2. Do not end between CR and LF; otherwise end after any control character. </P> <P> -3. Do not break Hangul (a Korean script) syllable sequences. Hangul characters +3. Do not break Hangul (a Korean script) syllable sequences. Hangul characters are of five types: L, V, T, LV, and LVT. An L character may be followed by an -L, V, LV, or LVT character; an LV or V character may be followed by a V or T +L, V, LV, or LVT character; an LV or V character may be followed by a V or T character; an LVT or T character may be follwed only by a T character. </P> <P> @@ -978,9 +981,14 @@ regular expression. </P> <br><a name="SEC6" href="#TOC1">CIRCUMFLEX AND DOLLAR</a><br> <P> +The circumflex and dollar metacharacters are zero-width assertions. That is, +they test for a particular condition being true without consuming any +characters from the subject string. +</P> +<P> Outside a character class, in the default matching mode, the circumflex -character is an assertion that is true only if the current matching point is -at the start of the subject string. If the <i>startoffset</i> argument of +character is an assertion that is true only if the current matching point is at +the start of the subject string. If the <i>startoffset</i> argument of <b>pcre_exec()</b> is non-zero, circumflex can never match if the PCRE_MULTILINE option is unset. Inside a character class, circumflex has an entirely different meaning @@ -996,12 +1004,12 @@ constrained to match only at the start of the subject, it is said to be an to be anchored.) </P> <P> -A dollar character is an assertion that is true only if the current matching -point is at the end of the subject string, or immediately before a newline -at the end of the string (by default). Dollar need not be the last character of -the pattern if a number of alternatives are involved, but it should be the last -item in any branch in which it appears. Dollar has no special meaning in a -character class. +The dollar character is an assertion that is true only if the current matching +point is at the end of the subject string, or immediately before a newline at +the end of the string (by default). Note, however, that it does not actually +match the newline. Dollar need not be the last character of the pattern if a +number of alternatives are involved, but it should be the last item in any +branch in which it appears. Dollar has no special meaning in a character class. </P> <P> The meaning of dollar can be changed so that it matches only at the very end of @@ -1344,10 +1352,11 @@ the pattern can contain special leading sequences such as (*CRLF) to override what the application has set or what has been defaulted. Details are given in the section entitled <a href="#newlineseq">"Newline sequences"</a> -above. There are also the (*UTF8), (*UTF16),(*UTF32) and (*UCP) leading +above. There are also the (*UTF8), (*UTF16),(*UTF32), and (*UCP) leading sequences that can be used to set UTF and Unicode property modes; they are equivalent to setting the PCRE_UTF8, PCRE_UTF16, PCRE_UTF32 and the PCRE_UCP -options, respectively. +options, respectively. The (*UTF) sequence is a generic version that can be +used with any of the libraries. <a name="subpattern"></a></P> <br><a name="SEC13" href="#TOC1">SUBPATTERNS</a><br> <P> @@ -1674,7 +1683,7 @@ one succeeds. Consider this pattern: <pre> (?>.*?a)b </pre> -It matches "ab" in the subject "aab". The use of the backtracking control verbs +It matches "ab" in the subject "aab". The use of the backtracking control verbs (*PRUNE) and (*SKIP) also disable this optimization. </P> <P> @@ -2935,7 +2944,7 @@ Cambridge CB2 3QH, England. </P> <br><a name="SEC29" href="#TOC1">REVISION</a><br> <P> -Last updated: 10 September 2012 +Last updated: 11 November 2012 <br> Copyright © 1997-2012 University of Cambridge. <br> diff --git a/doc/html/pcresyntax.html b/doc/html/pcresyntax.html index 09fe80a..22a253e 100644 --- a/doc/html/pcresyntax.html +++ b/doc/html/pcresyntax.html @@ -379,6 +379,7 @@ newline-setting options with similar syntax: (*UTF8) set UTF-8 mode: 8-bit library (PCRE_UTF8) (*UTF16) set UTF-16 mode: 16-bit library (PCRE_UTF16) (*UTF32) set UTF-32 mode: 32-bit library (PCRE_UTF32) + (*UTF) set appropriate UTF mode for the library in use (*UCP) set PCRE_UCP (use Unicode properties for \d etc) </PRE> </P> @@ -511,7 +512,7 @@ Cambridge CB2 3QH, England. </P> <br><a name="SEC27" href="#TOC1">REVISION</a><br> <P> -Last updated: 25 August 2012 +Last updated: 11 November 2012 <br> Copyright © 1997-2012 University of Cambridge. <br> diff --git a/doc/html/pcretest.html b/doc/html/pcretest.html index 905d7ff..8423ba5 100644 --- a/doc/html/pcretest.html +++ b/doc/html/pcretest.html @@ -47,7 +47,7 @@ options, see the <a href="pcre16.html"><b>pcre16</b></a> and <a href="pcre32.html"><b>pcre32</b></a> -documentation. +documentation. </P> <P> The input for <b>pcretest</b> is a sequence of regular expression patterns and @@ -60,7 +60,7 @@ As PCRE has evolved, it has acquired many different features, and as a result, <b>pcretest</b> now has rather a lot of obscure options for testing every possible feature. Some of these options are specifically designed for use in conjunction with the test script and data files that are distributed as part of -PCRE, and are unlikely to be of use otherwise. They are all documented here, +PCRE, and are unlikely to be of use otherwise. They are all documented here, but without much justification. </P> <br><a name="SEC2" href="#TOC1">PCRE's 8-BIT, 16-BIT AND 32-BIT LIBRARIES</a><br> @@ -120,7 +120,7 @@ functionality is intended for use in scripts such as <b>RunTest</b>. The following options output the value indicated: <pre> ebcdic-nl the code for LF (= NL) in an EBCDIC environment: - 0x15 or 0x25 + 0x15 or 0x25 0 if used in an ASCII environment linksize the internal link size (2, 3, or 4) newline the default newline setting: @@ -216,7 +216,7 @@ the text "(JIT)" is added to the first output line after a match or no match when JIT-compiled code was actually used. <br> <br> -Note that there are pattern options that can override <b>-s</b>, either +Note that there are pattern options that can override <b>-s</b>, either specifying no studying at all, or suppressing JIT compilation. <br> <br> @@ -353,7 +353,7 @@ sections. <b>/X</b> set PCRE_EXTRA <b>/x</b> set PCRE_EXTENDED <b>/Y</b> set PCRE_NO_START_OPTIMIZE - <b>/Z</b> don't show lengths in <b>/B</b> output + <b>/Z</b> don't show lengths in <b>/B</b> output <b>/<any></b> set PCRE_NEWLINE_ANY <b>/<anycrlf></b> set PCRE_NEWLINE_ANYCRLF @@ -540,12 +540,12 @@ JIT compiled code is also output. <P> The <b>/S</b> modifier causes <b>pcre[16|32]_study()</b> to be called after the expression has been compiled, and the results used when the expression is -matched. There are a number of qualifying characters that may follow <b>/S</b>. +matched. There are a number of qualifying characters that may follow <b>/S</b>. They may appear in any order. </P> <P> -If <b>S</b> is followed by an exclamation mark, <b>pcre[16|32]_study()</b> is called -with the PCRE_STUDY_EXTRA_NEEDED option, causing it always to return a +If <b>S</b> is followed by an exclamation mark, <b>pcre[16|32]_study()</b> is called +with the PCRE_STUDY_EXTRA_NEEDED option, causing it always to return a <b>pcre_extra</b> block, even when studying discovers no useful information. </P> <P> diff --git a/doc/html/pcreunicode.html b/doc/html/pcreunicode.html index 63b8746..c3c51ea 100644 --- a/doc/html/pcreunicode.html +++ b/doc/html/pcreunicode.html @@ -13,17 +13,12 @@ from the original man page. If there is any nonsense in it, please consult the man page, in case the conversion went wrong. <br> <br><b> -UTF-8, UTF-16, AND UNICODE PROPERTY SUPPORT +UTF-8, UTF-16, UTF-32, AND UNICODE PROPERTY SUPPORT </b><br> <P> -From Release 8.30, in addition to its previous UTF-8 support, PCRE also -supports UTF-16 by means of a separate 16-bit library. This can be built as -well as, or instead of, the 8-bit library. -</P> -<P> -From Release 8.32, in addition to its previous UTF-8 and UTF-16 support, -PCRE also supports UTF-32 by means of a separate 32-bit library. This can be -built as well as, or instead of, the 8-bit and 16-bit libraries. +As well as UTF-8 support, PCRE also supports UTF-16 (from release 8.30) and +UTF-32 (from release 8.32), by means of two additional libraries. They can be +built as well as, or instead of, the 8-bit library. </P> <br><b> UTF-8 SUPPORT @@ -33,33 +28,25 @@ In order process UTF-8 strings, you must build PCRE's 8-bit library with UTF support, and, in addition, you must call <a href="pcre_compile.html"><b>pcre_compile()</b></a> with the PCRE_UTF8 option flag, or the pattern must start with the sequence -(*UTF8). When either of these is the case, both the pattern and any subject -strings that are matched against it are treated as UTF-8 strings instead of -strings of 1-byte characters. -</P> -<br><b> -UTF-16 SUPPORT -</b><br> -<P> -In order process UTF-16 strings, you must build PCRE's 16-bit library with UTF -support, and, in addition, you must call -<a href="pcre_compile.html"><b>pcre16_compile()</b></a> -with the PCRE_UTF16 option flag, or the pattern must start with the sequence -(*UTF16). When either of these is the case, both the pattern and any subject -strings that are matched against it are treated as UTF-16 strings instead of -strings of 16-bit characters. +(*UTF8) or (*UTF). When either of these is the case, both the pattern and any +subject strings that are matched against it are treated as UTF-8 strings +instead of strings of individual 1-byte characters. </P> <br><b> -UTF-32 SUPPORT +UTF-16 AND UTF-32 SUPPORT </b><br> <P> -In order process UTF-32 strings, you must build PCRE's 32-bit library with UTF -support, and, in addition, you must call -<a href="pcre_compile.html"><b>pcre32_compile()</b></a> -with the PCRE_UTF32 option flag, or the pattern must start with the sequence -(*UTF32). When either of these is the case, both the pattern and any subject -strings that are matched against it are treated as UTF-32 strings instead of -strings of 32-bit characters. +In order process UTF-16 or UTF-32 strings, you must build PCRE's 16-bit or +32-bit library with UTF support, and, in addition, you must call +<a href="pcre16_compile.html"><b>pcre16_compile()</b></a> +or +<a href="pcre32_compile.html"><b>pcre32_compile()</b></a> +with the PCRE_UTF16 or PCRE_UTF32 option flag, as appropriate. Alternatively, +the pattern must start with the sequence (*UTF16), (*UTF32), as appropriate, or +(*UTF), which can be used with either library. When UTF mode is set, both the +pattern and any subject strings that are matched against it are treated as +UTF-16 or UTF-32 strings instead of strings of individual 16-bit or 32-bit +characters. </P> <br><b> UTF SUPPORT OVERHEAD @@ -78,8 +65,10 @@ support), the escape sequences \p{..}, \P{..}, and \X can be used. The available properties that can be tested are limited to the general category properties such as Lu for an upper case letter or Nd for a decimal number, the Unicode script names such as Arabic or Han, and the derived -properties Any and L&. A full list is given in the +properties Any and L&. Full lists is given in the <a href="pcrepattern.html"><b>pcrepattern</b></a> +and +<a href="pcresyntax.html"><b>pcresyntax</b></a> documentation. Only the short names for properties are supported. For example, \p{L} matches a letter. Its Perl synonym, \p{Letter}, is not supported. Furthermore, in Perl, many properties may optionally be prefixed by "Is", for @@ -96,17 +85,18 @@ place. From release 7.3 of PCRE, the check is according the rules of RFC 3629, which are themselves derived from the Unicode specification. Earlier releases of PCRE followed the rules of RFC 2279, which allows the full range of 31-bit values (0 to 0x7FFFFFFF). The current check allows only values in the range U+0 -to U+10FFFF, excluding the surrogate area, and the non-characters. +to U+10FFFF, excluding the surrogate area and the non-characters. </P> <P> -Excluded code points are the "Surrogate Area" of Unicode. They are reserved -for use by UTF-16, where they are used in pairs to encode codepoints with -values greater than 0xFFFF. The code points that are encoded by UTF-16 pairs -are available independently in the UTF-8 encoding. (In other words, the whole -surrogate thing is a fudge for UTF-16 which unfortunately messes up UTF-8.) +Characters in the "Surrogate Area" of Unicode are reserved for use by UTF-16, +where they are used in pairs to encode codepoints with values greater than +0xFFFF. The code points that are encoded by UTF-16 pairs are available +independently in the UTF-8 and UTF-32 encodings. (In other words, the whole +surrogate thing is a fudge for UTF-16 which unfortunately messes up UTF-8 and +UTF-32.) </P> <P> -Also excluded are the "Non-Characters" code points, which are U+FDD0 to U+FDEF +Also excluded are the "Non-Character" code points, which are U+FDD0 to U+FDEF and the last two code points in each plane, U+??FFFE and U+??FFFF. </P> <P> @@ -119,30 +109,20 @@ detailed reason code if the caller has provided memory in which to do this. <P> In some situations, you may already know that your strings are valid, and therefore want to skip these checks in order to improve performance, for -example in the case of a long subject string that is being scanned repeatedly -with different patterns. If you set the PCRE_NO_UTF8_CHECK flag at compile time -or at run time, PCRE assumes that the pattern or subject it is given -(respectively) contains only valid UTF-8 codes. In this case, it does not -diagnose an invalid UTF-8 string. +example in the case of a long subject string that is being scanned repeatedly. +If you set the PCRE_NO_UTF8_CHECK flag at compile time or at run time, PCRE +assumes that the pattern or subject it is given (respectively) contains only +valid UTF-8 codes. In this case, it does not diagnose an invalid UTF-8 string. </P> <P> -If you pass an invalid UTF-8 string when PCRE_NO_UTF8_CHECK is set, what -happens depends on why the string is invalid. If the string conforms to the -"old" definition of UTF-8 (RFC 2279), it is processed as a string of characters -in the range 0 to 0x7FFFFFFF by <b>pcre_dfa_exec()</b> and the interpreted -version of <b>pcre_exec()</b>. In other words, apart from the initial validity -test, these functions (when in UTF-8 mode) handle strings according to the more -liberal rules of RFC 2279. However, the just-in-time (JIT) optimization for -<b>pcre_exec()</b> supports only RFC 3629. If you are using JIT optimization, or -if the string does not even conform to RFC 2279, the result is undefined. Your -program may crash. +Note that passing PCRE_NO_UTF8_CHECK to <b>pcre_compile()</b> just disables the +check for the pattern; it does not also apply to subject strings. If you want +to disable the check for a subject string you must pass this option to +<b>pcre_exec()</b> or <b>pcre_dfa_exec()</b>. </P> <P> -If you want to process strings of values in the full range 0 to 0x7FFFFFFF, -encoded in a UTF-8-like manner as per the old RFC, you can set -PCRE_NO_UTF8_CHECK to bypass the more restrictive test. However, in this -situation, you will have to apply your own validity check, and avoid the use of -JIT optimization. +If you pass an invalid UTF-8 string when PCRE_NO_UTF8_CHECK is set, the result +is undefined and your program may crash. <a name="utf16strings"></a></P> <br><b> Validity of UTF-16 strings @@ -155,7 +135,7 @@ U+D800 to U+DFFF are independent code points. Values in the surrogate range must be used in pairs in the correct manner. </P> <P> -Excluded are the "Non-Characters" code points, which are U+FDD0 to U+FDEF +Excluded are the "Non-Character" code points, which are U+FDD0 to U+FDEF and the last two code points in each plane, U+??FFFE and U+??FFFF. </P> <P> @@ -171,6 +151,7 @@ therefore want to skip these checks in order to improve performance. If you set the PCRE_NO_UTF16_CHECK flag at compile time or at run time, PCRE assumes that the pattern or subject it is given (respectively) contains only valid UTF-16 sequences. In this case, it does not diagnose an invalid UTF-16 string. +However, if an invalid string is passed, the result is undefined. <a name="utf32strings"></a></P> <br><b> Validity of UTF-32 strings @@ -180,7 +161,7 @@ When you set the PCRE_UTF32 flag, the strings of 32-bit data units that are passed as patterns and subjects are (by default) checked for validity on entry to the relevant functions. This check allows only values in the range U+0 to U+10FFFF, excluding the surrogate area U+D800 to U+DFFF, and the -"Non-Characters" code points, which are U+FDD0 to U+FDEF and the last two +"Non-Character" code points, which are U+FDD0 to U+FDEF and the last two characters in each plane, U+??FFFE and U+??FFFF. </P> <P> @@ -196,28 +177,18 @@ therefore want to skip these checks in order to improve performance. If you set the PCRE_NO_UTF32_CHECK flag at compile time or at run time, PCRE assumes that the pattern or subject it is given (respectively) contains only valid UTF-32 sequences. In this case, it does not diagnose an invalid UTF-32 string. -</P> -<P> -UTF-32 only uses the lowest 21 bits of the 32 bit characters, and the -application may use the upper bits for internal purposes. To allow you to -pass these strings to PCRE unmodified (thus avoiding the costly operation of -creating a copy of the string with the upper bits masked), PCRE accepts -these 32-bit character strings as-is, but only uses the lowest 21 bits for -matching, if you pass the PCRE_NO_UTF32_CHECK flag to <b>pcre32_exec()</b> and -<b>pcre32_dfa_exec()</b>. However, in this situation, you will have to apply -your own validity check, and avoid the use of JIT optimization. -(The latter restriction may be lifter in a later version of PCRE.) +However, if an invalid string is passed, the result is undefined. </P> <br><b> General comments about UTF modes </b><br> <P> -1. Codepoints less than 256 can be specified by either braced or unbraced -hexadecimal escape sequences (for example, \x{b3} or \xb3). Larger values -have to use braced sequences. +1. Codepoints less than 256 can be specified in patterns by either braced or +unbraced hexadecimal escape sequences (for example, \x{b3} or \xb3). Larger +values have to use braced sequences. </P> <P> -2. Octal numbers up to \777 are recognized, and in UTF-8 mode, they match +2. Octal numbers up to \777 are recognized, and in UTF-8 mode they match two-byte characters for values greater than \177. </P> <P> @@ -235,10 +206,10 @@ UTF-32 mode, but its use can lead to some strange effects because it breaks up multi-unit characters (see the description of \C in the <a href="pcrepattern.html"><b>pcrepattern</b></a> documentation). The use of \C is not supported in the alternative matching -function <b>pcre[16|32]_dfa_exec()</b>, nor is it supported in UTF mode by the JIT -optimization of <b>pcre[16|32]_exec()</b>. If JIT optimization is requested for a -UTF pattern that contains \C, it will not succeed, and so the matching will -be carried out by the normal interpretive function. +function <b>pcre[16|32]_dfa_exec()</b>, nor is it supported in UTF mode by the +JIT optimization of <b>pcre[16|32]_exec()</b>. If JIT optimization is requested +for a UTF pattern that contains \C, it will not succeed, and so the matching +will be carried out by the normal interpretive function. </P> <P> 6. The character escapes \b, \B, \d, \D, \s, \S, \w, and \W correctly @@ -290,7 +261,7 @@ Cambridge CB2 3QH, England. REVISION </b><br> <P> -Last updated: 25 September 2012 +Last updated: 11 November 2012 <br> Copyright © 1997-2012 University of Cambridge. <br> diff --git a/doc/pcre-config.1 b/doc/pcre-config.1 index 0430904..92a4b58 100644 --- a/doc/pcre-config.1 +++ b/doc/pcre-config.1 @@ -17,7 +17,7 @@ pcre-config - program to return PCRE configuration \fBpcre-config\fP returns the configuration of the installed PCRE libraries and the options required to compile a program to use them. Some of the options apply only to the 8-bit, or 16-bit, or 32-bit libraries, -respectively, and are +respectively, and are not available if only one of those libraries has been built. If an unavailable option is encountered, the "usage" information is output. . @@ -114,7 +114,7 @@ If you are using PCRE in a non-UTF application that permits users to supply arbitrary patterns for compilation, you should be aware of a feature that allows users to turn on UTF support from within a pattern, provided that PCRE was built with UTF support. For example, an 8-bit pattern that begins with -"(*UTF8)" or "(*UTF)" turns on UTF-8 mode, which interprets patterns and +"(*UTF8)" or "(*UTF)" turns on UTF-8 mode, which interprets patterns and subjects as strings of UTF-8 characters instead of individual 8-bit characters. This causes both the pattern and any data against which it is matched to be checked for UTF-8 validity. If the data string is very long, such a check might @@ -126,12 +126,12 @@ The best way of guarding against this possibility is to use the .P If your application is one that supports UTF, be aware that validity checking can take time. If the same data string is to be matched many times, you can use -the PCRE_NO_UTF[8|16|32]_CHECK option for the second and subsequent matches to +the PCRE_NO_UTF[8|16|32]_CHECK option for the second and subsequent matches to save redundant checks. .P -Another way that performance can be hit is by running a pattern that has a very -large search tree against a string that will never match. Nested unlimited -repeats in a pattern are a common example. PCRE provides some protection +Another way that performance can be hit is by running a pattern that has a very +large search tree against a string that will never match. Nested unlimited +repeats in a pattern are a common example. PCRE provides some protection against this: see the PCRE_EXTRA_MATCH_LIMIT feature in the .\" HREF \fBpcreapi\fP diff --git a/doc/pcre.txt b/doc/pcre.txt index de5dfab..2a2a82c 100644 --- a/doc/pcre.txt +++ b/doc/pcre.txt @@ -98,11 +98,13 @@ SECURITY CONSIDERATIONS supply arbitrary patterns for compilation, you should be aware of a feature that allows users to turn on UTF support from within a pattern, provided that PCRE was built with UTF support. For example, an 8-bit - pattern that begins with "(*UTF8)" turns on UTF-8 mode. This causes - both the pattern and any data against which it is matched to be checked - for UTF-8 validity. If the data string is very long, such a check might - use sufficiently many resources as to cause your application to lose - performance. + pattern that begins with "(*UTF8)" or "(*UTF)" turns on UTF-8 mode, + which interprets patterns and subjects as strings of UTF-8 characters + instead of individual 8-bit characters. This causes both the pattern + and any data against which it is matched to be checked for UTF-8 valid- + ity. If the data string is very long, such a check might use suffi- + ciently many resources as to cause your application to lose perfor- + mance. The best way of guarding against this possibility is to use the pcre_fullinfo() function to check the compiled pattern's options for @@ -172,11 +174,11 @@ AUTHOR REVISION - Last updated: 30 October 2012 + Last updated: 11 November 2012 Copyright (c) 1997-2012 University of Cambridge. ------------------------------------------------------------------------------ - - + + PCRE(3) PCRE(3) @@ -315,8 +317,8 @@ THE PCRE 16-BIT LIBRARY THE HEADER FILE There is only one header file, pcre.h. It contains prototypes for all - the functions in both libraries, as well as definitions of flags, - structures, error codes, etc. + the functions in all libraries, as well as definitions of flags, struc- + tures, error codes, etc. THE LIBRARY NAME @@ -334,9 +336,9 @@ STRING TYPES PCRE_UCHAR16 specifies an appropriate data type, and PCRE_SPTR16 is defined as "const PCRE_UCHAR16 *". In very many environments, "short int" is a 16-bit data type. When PCRE is built, it defines PCRE_UCHAR16 - as "short int", but checks that it really is a 16-bit data type. If it - is not, the build fails with an error message telling the maintainer to - modify the definition appropriately. + as "unsigned short int", but checks that it really is a 16-bit data + type. If it is not, the build fails with an error message telling the + maintainer to modify the definition appropriately. STRUCTURE TYPES @@ -501,11 +503,11 @@ AUTHOR REVISION - Last updated: 14 April 2012 + Last updated: 08 November 2012 Copyright (c) 1997-2012 University of Cambridge. ------------------------------------------------------------------------------ - - + + PCRE(3) PCRE(3) @@ -644,8 +646,8 @@ THE PCRE 32-BIT LIBRARY THE HEADER FILE There is only one header file, pcre.h. It contains prototypes for all - the functions in both libraries, as well as definitions of flags, - structures, error codes, etc. + the functions in all libraries, as well as definitions of flags, struc- + tures, error codes, etc. THE LIBRARY NAME @@ -827,11 +829,11 @@ AUTHOR REVISION - Last updated: 24 June 2012 + Last updated: 08 November 2012 Copyright (c) 1997-2012 University of Cambridge. ------------------------------------------------------------------------------ - - + + PCREBUILD(3) PCREBUILD(3) @@ -1320,8 +1322,8 @@ REVISION Last updated: 30 October 2012 Copyright (c) 1997-2012 University of Cambridge. ------------------------------------------------------------------------------ - - + + PCREMATCHING(3) PCREMATCHING(3) @@ -1529,8 +1531,8 @@ REVISION Last updated: 08 January 2012 Copyright (c) 1997-2012 University of Cambridge. ------------------------------------------------------------------------------ - - + + PCREAPI(3) PCREAPI(3) @@ -1642,88 +1644,87 @@ PCRE NATIVE API INDIRECTED FUNCTIONS int (*pcre_callout)(pcre_callout_block *); -PCRE 8-BIT, 16-BIT AND 32-BIT LIBRARIES +PCRE 8-BIT, 16-BIT, AND 32-BIT LIBRARIES - From release 8.30, PCRE can be compiled as a library for handling - 16-bit character strings as well as, or instead of, the original - library that handles 8-bit character strings. From release 8.32, PCRE - can also be compiled as a library for handling 32-bit character - strings. To avoid too much complication, this document describes the - 8-bit versions of the functions, with only occasional references to the - 16-bit and 32-bit libraries. + As well as support for 8-bit character strings, PCRE also supports + 16-bit strings (from release 8.30) and 32-bit strings (from release + 8.32), by means of two additional libraries. They can be built as well + as, or instead of, the 8-bit library. To avoid too much complication, + this document describes the 8-bit versions of the functions, with only + occasional references to the 16-bit and 32-bit libraries. - The 16-bit and 32-bit functions operate in the same way as their 8-bit - counterparts; they just use different data types for their arguments - and results, and their names start with pcre16_ or pcre32_ instead of - pcre_. For every option that has UTF8 in its name (for example, - PCRE_UTF8), there are corresponding 16-bit and 32-bit names with UTF8 + The 16-bit and 32-bit functions operate in the same way as their 8-bit + counterparts; they just use different data types for their arguments + and results, and their names start with pcre16_ or pcre32_ instead of + pcre_. For every option that has UTF8 in its name (for example, + PCRE_UTF8), there are corresponding 16-bit and 32-bit names with UTF8 replaced by UTF16 or UTF32, respectively. This facility is in fact just - cosmetic; the 16-bit and 32-bit option names define the same bit val- + cosmetic; the 16-bit and 32-bit option names define the same bit val- ues. References to bytes and UTF-8 in this document should be read as refer- - ences to 16-bit data quantities and UTF-16 when using the 16-bit - library, or 32-bit data quantities and UTF-32 when using the 32-bit - library, unless specified otherwise. More details of the specific dif- - ferences for the 16-bit and 32-bit libraries are given in the pcre16 + ences to 16-bit data quantities and UTF-16 when using the 16-bit + library, or 32-bit data quantities and UTF-32 when using the 32-bit + library, unless specified otherwise. More details of the specific dif- + ferences for the 16-bit and 32-bit libraries are given in the pcre16 and pcre32 pages. PCRE API OVERVIEW PCRE has its own native API, which is described in this document. There - are also some wrapper functions (for the 8-bit library only) that cor- - respond to the POSIX regular expression API, but they do not give - access to all the functionality. They are described in the pcreposix - documentation. Both of these APIs define a set of C function calls. A + are also some wrapper functions (for the 8-bit library only) that cor- + respond to the POSIX regular expression API, but they do not give + access to all the functionality. They are described in the pcreposix + documentation. Both of these APIs define a set of C function calls. A C++ wrapper (again for the 8-bit library only) is also distributed with PCRE. It is documented in the pcrecpp page. - The native API C function prototypes are defined in the header file - pcre.h, and on Unix-like systems the (8-bit) library itself is called - libpcre. It can normally be accessed by adding -lpcre to the command - for linking an application that uses PCRE. The header file defines the + The native API C function prototypes are defined in the header file + pcre.h, and on Unix-like systems the (8-bit) library itself is called + libpcre. It can normally be accessed by adding -lpcre to the command + for linking an application that uses PCRE. The header file defines the macros PCRE_MAJOR and PCRE_MINOR to contain the major and minor release - numbers for the library. Applications can use these to include support + numbers for the library. Applications can use these to include support for different releases of PCRE. In a Windows environment, if you want to statically link an application - program against a non-dll pcre.a file, you must define PCRE_STATIC - before including pcre.h or pcrecpp.h, because otherwise the pcre_mal- + program against a non-dll pcre.a file, you must define PCRE_STATIC + before including pcre.h or pcrecpp.h, because otherwise the pcre_mal- loc() and pcre_free() exported functions will be declared __declspec(dllimport), with unwanted results. - The functions pcre_compile(), pcre_compile2(), pcre_study(), and - pcre_exec() are used for compiling and matching regular expressions in - a Perl-compatible manner. A sample program that demonstrates the sim- - plest way of using them is provided in the file called pcredemo.c in + The functions pcre_compile(), pcre_compile2(), pcre_study(), and + pcre_exec() are used for compiling and matching regular expressions in + a Perl-compatible manner. A sample program that demonstrates the sim- + plest way of using them is provided in the file called pcredemo.c in the PCRE source distribution. A listing of this program is given in the - pcredemo documentation, and the pcresample documentation describes how + pcredemo documentation, and the pcresample documentation describes how to compile and run it. - Just-in-time compiler support is an optional feature of PCRE that can + Just-in-time compiler support is an optional feature of PCRE that can be built in appropriate hardware environments. It greatly speeds up the - matching performance of many patterns. Simple programs can easily - request that it be used if available, by setting an option that is - ignored when it is not relevant. More complicated programs might need - to make use of the functions pcre_jit_stack_alloc(), - pcre_jit_stack_free(), and pcre_assign_jit_stack() in order to control + matching performance of many patterns. Simple programs can easily + request that it be used if available, by setting an option that is + ignored when it is not relevant. More complicated programs might need + to make use of the functions pcre_jit_stack_alloc(), + pcre_jit_stack_free(), and pcre_assign_jit_stack() in order to control the JIT code's memory usage. - From release 8.32 there is also a direct interface for JIT execution, - which gives improved performance. The JIT-specific functions are dis- + From release 8.32 there is also a direct interface for JIT execution, + which gives improved performance. The JIT-specific functions are dis- cussed in the pcrejit documentation. A second matching function, pcre_dfa_exec(), which is not Perl-compati- - ble, is also provided. This uses a different algorithm for the match- - ing. The alternative algorithm finds all possible matches (at a given - point in the subject), and scans the subject just once (unless there - are lookbehind assertions). However, this algorithm does not return - captured substrings. A description of the two matching algorithms and - their advantages and disadvantages is given in the pcrematching docu- + ble, is also provided. This uses a different algorithm for the match- + ing. The alternative algorithm finds all possible matches (at a given + point in the subject), and scans the subject just once (unless there + are lookbehind assertions). However, this algorithm does not return + captured substrings. A description of the two matching algorithms and + their advantages and disadvantages is given in the pcrematching docu- mentation. - In addition to the main compiling and matching functions, there are + In addition to the main compiling and matching functions, there are convenience functions for extracting captured substrings from a subject string that is matched by pcre_exec(). They are: @@ -1738,105 +1739,105 @@ PCRE API OVERVIEW pcre_free_substring() and pcre_free_substring_list() are also provided, to free the memory used for extracted strings. - The function pcre_maketables() is used to build a set of character - tables in the current locale for passing to pcre_compile(), - pcre_exec(), or pcre_dfa_exec(). This is an optional facility that is - provided for specialist use. Most commonly, no special tables are - passed, in which case internal tables that are generated when PCRE is + The function pcre_maketables() is used to build a set of character + tables in the current locale for passing to pcre_compile(), + pcre_exec(), or pcre_dfa_exec(). This is an optional facility that is + provided for specialist use. Most commonly, no special tables are + passed, in which case internal tables that are generated when PCRE is built are used. - The function pcre_fullinfo() is used to find out information about a - compiled pattern. The function pcre_version() returns a pointer to a + The function pcre_fullinfo() is used to find out information about a + compiled pattern. The function pcre_version() returns a pointer to a string containing the version of PCRE and its date of release. - The function pcre_refcount() maintains a reference count in a data - block containing a compiled pattern. This is provided for the benefit + The function pcre_refcount() maintains a reference count in a data + block containing a compiled pattern. This is provided for the benefit of object-oriented applications. - The global variables pcre_malloc and pcre_free initially contain the - entry points of the standard malloc() and free() functions, respec- + The global variables pcre_malloc and pcre_free initially contain the + entry points of the standard malloc() and free() functions, respec- tively. PCRE calls the memory management functions via these variables, - so a calling program can replace them if it wishes to intercept the + so a calling program can replace them if it wishes to intercept the calls. This should be done before calling any PCRE functions. - The global variables pcre_stack_malloc and pcre_stack_free are also - indirections to memory management functions. These special functions - are used only when PCRE is compiled to use the heap for remembering + The global variables pcre_stack_malloc and pcre_stack_free are also + indirections to memory management functions. These special functions + are used only when PCRE is compiled to use the heap for remembering data, instead of recursive function calls, when running the pcre_exec() - function. See the pcrebuild documentation for details of how to do - this. It is a non-standard way of building PCRE, for use in environ- - ments that have limited stacks. Because of the greater use of memory - management, it runs more slowly. Separate functions are provided so - that special-purpose external code can be used for this case. When - used, these functions are always called in a stack-like manner (last - obtained, first freed), and always for memory blocks of the same size. - There is a discussion about PCRE's stack usage in the pcrestack docu- + function. See the pcrebuild documentation for details of how to do + this. It is a non-standard way of building PCRE, for use in environ- + ments that have limited stacks. Because of the greater use of memory + management, it runs more slowly. Separate functions are provided so + that special-purpose external code can be used for this case. When + used, these functions are always called in a stack-like manner (last + obtained, first freed), and always for memory blocks of the same size. + There is a discussion about PCRE's stack usage in the pcrestack docu- mentation. The global variable pcre_callout initially contains NULL. It can be set - by the caller to a "callout" function, which PCRE will then call at - specified points during a matching operation. Details are given in the + by the caller to a "callout" function, which PCRE will then call at + specified points during a matching operation. Details are given in the pcrecallout documentation. NEWLINES - PCRE supports five different conventions for indicating line breaks in - strings: a single CR (carriage return) character, a single LF (line- + PCRE supports five different conventions for indicating line breaks in + strings: a single CR (carriage return) character, a single LF (line- feed) character, the two-character sequence CRLF, any of the three pre- - ceding, or any Unicode newline sequence. The Unicode newline sequences - are the three just mentioned, plus the single characters VT (vertical + ceding, or any Unicode newline sequence. The Unicode newline sequences + are the three just mentioned, plus the single characters VT (vertical tab, U+000B), FF (form feed, U+000C), NEL (next line, U+0085), LS (line separator, U+2028), and PS (paragraph separator, U+2029). - Each of the first three conventions is used by at least one operating - system as its standard newline sequence. When PCRE is built, a default - can be specified. The default default is LF, which is the Unix stan- - dard. When PCRE is run, the default can be overridden, either when a + Each of the first three conventions is used by at least one operating + system as its standard newline sequence. When PCRE is built, a default + can be specified. The default default is LF, which is the Unix stan- + dard. When PCRE is run, the default can be overridden, either when a pattern is compiled, or when it is matched. At compile time, the newline convention can be specified by the options - argument of pcre_compile(), or it can be specified by special text at + argument of pcre_compile(), or it can be specified by special text at the start of the pattern itself; this overrides any other settings. See the pcrepattern page for details of the special character sequences. In the PCRE documentation the word "newline" is used to mean "the char- - acter or pair of characters that indicate a line break". The choice of - newline convention affects the handling of the dot, circumflex, and + acter or pair of characters that indicate a line break". The choice of + newline convention affects the handling of the dot, circumflex, and dollar metacharacters, the handling of #-comments in /x mode, and, when - CRLF is a recognized line ending sequence, the match position advance- + CRLF is a recognized line ending sequence, the match position advance- ment for a non-anchored pattern. There is more detail about this in the section on pcre_exec() options below. - The choice of newline convention does not affect the interpretation of - the \n or \r escape sequences, nor does it affect what \R matches, + The choice of newline convention does not affect the interpretation of + the \n or \r escape sequences, nor does it affect what \R matches, which is controlled in a similar way, but by separate options. MULTITHREADING - The PCRE functions can be used in multi-threading applications, with + The PCRE functions can be used in multi-threading applications, with the proviso that the memory management functions pointed to by pcre_malloc, pcre_free, pcre_stack_malloc, and pcre_stack_free, and the callout function pointed to by pcre_callout, are shared by all threads. - The compiled form of a regular expression is not altered during match- + The compiled form of a regular expression is not altered during match- ing, so the same compiled pattern can safely be used by several threads at once. - If the just-in-time optimization feature is being used, it needs sepa- - rate memory stack areas for each thread. See the pcrejit documentation + If the just-in-time optimization feature is being used, it needs sepa- + rate memory stack areas for each thread. See the pcrejit documentation for more details. SAVING PRECOMPILED PATTERNS FOR LATER USE The compiled form of a regular expression can be saved and re-used at a - later time, possibly by a different program, and even on a host other - than the one on which it was compiled. Details are given in the - pcreprecompile documentation, which includes a description of the - pcre_pattern_to_host_byte_order() function. However, compiling a regu- - lar expression with one version of PCRE for use with a different ver- + later time, possibly by a different program, and even on a host other + than the one on which it was compiled. Details are given in the + pcreprecompile documentation, which includes a description of the + pcre_pattern_to_host_byte_order() function. However, compiling a regu- + lar expression with one version of PCRE for use with a different ver- sion is not guaranteed to work and may cause crashes. @@ -1844,45 +1845,45 @@ CHECKING BUILD-TIME OPTIONS int pcre_config(int what, void *where); - The function pcre_config() makes it possible for a PCRE client to dis- + The function pcre_config() makes it possible for a PCRE client to dis- cover which optional features have been compiled into the PCRE library. - The pcrebuild documentation has more details about these optional fea- + The pcrebuild documentation has more details about these optional fea- tures. - The first argument for pcre_config() is an integer, specifying which + The first argument for pcre_config() is an integer, specifying which information is required; the second argument is a pointer to a variable - into which the information is placed. The returned value is zero on - success, or the negative error code PCRE_ERROR_BADOPTION if the value - in the first argument is not recognized. The following information is + into which the information is placed. The returned value is zero on + success, or the negative error code PCRE_ERROR_BADOPTION if the value + in the first argument is not recognized. The following information is available: PCRE_CONFIG_UTF8 - The output is an integer that is set to one if UTF-8 support is avail- - able; otherwise it is set to zero. This value should normally be given + The output is an integer that is set to one if UTF-8 support is avail- + able; otherwise it is set to zero. This value should normally be given to the 8-bit version of this function, pcre_config(). If it is given to - the 16-bit or 32-bit version of this function, the result is + the 16-bit or 32-bit version of this function, the result is PCRE_ERROR_BADOPTION. PCRE_CONFIG_UTF16 The output is an integer that is set to one if UTF-16 support is avail- - able; otherwise it is set to zero. This value should normally be given + able; otherwise it is set to zero. This value should normally be given to the 16-bit version of this function, pcre16_config(). If it is given - to the 8-bit or 32-bit version of this function, the result is + to the 8-bit or 32-bit version of this function, the result is PCRE_ERROR_BADOPTION. PCRE_CONFIG_UTF32 The output is an integer that is set to one if UTF-32 support is avail- - able; otherwise it is set to zero. This value should normally be given + able; otherwise it is set to zero. This value should normally be given to the 32-bit version of this function, pcre32_config(). If it is given - to the 8-bit or 16-bit version of this function, the result is + to the 8-bit or 16-bit version of this function, the result is PCRE_ERROR_BADOPTION. PCRE_CONFIG_UNICODE_PROPERTIES - The output is an integer that is set to one if support for Unicode + The output is an integer that is set to one if support for Unicode character properties is available; otherwise it is set to zero. PCRE_CONFIG_JIT @@ -1892,70 +1893,70 @@ CHECKING BUILD-TIME OPTIONS PCRE_CONFIG_JITTARGET - The output is a pointer to a zero-terminated "const char *" string. If + The output is a pointer to a zero-terminated "const char *" string. If JIT support is available, the string contains the name of the architec- - ture for which the JIT compiler is configured, for example "x86 32bit - (little endian + unaligned)". If JIT support is not available, the + ture for which the JIT compiler is configured, for example "x86 32bit + (little endian + unaligned)". If JIT support is not available, the result is NULL. PCRE_CONFIG_NEWLINE - The output is an integer whose value specifies the default character - sequence that is recognized as meaning "newline". The values that are + The output is an integer whose value specifies the default character + sequence that is recognized as meaning "newline". The values that are supported in ASCII/Unicode environments are: 10 for LF, 13 for CR, 3338 - for CRLF, -2 for ANYCRLF, and -1 for ANY. In EBCDIC environments, CR, - ANYCRLF, and ANY yield the same values. However, the value for LF is - normally 21, though some EBCDIC environments use 37. The corresponding - values for CRLF are 3349 and 3365. The default should normally corre- + for CRLF, -2 for ANYCRLF, and -1 for ANY. In EBCDIC environments, CR, + ANYCRLF, and ANY yield the same values. However, the value for LF is + normally 21, though some EBCDIC environments use 37. The corresponding + values for CRLF are 3349 and 3365. The default should normally corre- spond to the standard sequence for your operating system. PCRE_CONFIG_BSR The output is an integer whose value indicates what character sequences - the \R escape sequence matches by default. A value of 0 means that \R - matches any Unicode line ending sequence; a value of 1 means that \R + the \R escape sequence matches by default. A value of 0 means that \R + matches any Unicode line ending sequence; a value of 1 means that \R matches only CR, LF, or CRLF. The default can be overridden when a pat- tern is compiled or matched. PCRE_CONFIG_LINK_SIZE - The output is an integer that contains the number of bytes used for + The output is an integer that contains the number of bytes used for internal linkage in compiled regular expressions. For the 8-bit library, the value can be 2, 3, or 4. For the 16-bit library, the value - is either 2 or 4 and is still a number of bytes. For the 32-bit + is either 2 or 4 and is still a number of bytes. For the 32-bit library, the value is either 2 or 4 and is still a number of bytes. The default value of 2 is sufficient for all but the most massive patterns, - since it allows the compiled pattern to be up to 64K in size. Larger - values allow larger regular expressions to be compiled, at the expense + since it allows the compiled pattern to be up to 64K in size. Larger + values allow larger regular expressions to be compiled, at the expense of slower matching. PCRE_CONFIG_POSIX_MALLOC_THRESHOLD - The output is an integer that contains the threshold above which the - POSIX interface uses malloc() for output vectors. Further details are + The output is an integer that contains the threshold above which the + POSIX interface uses malloc() for output vectors. Further details are given in the pcreposix documentation. PCRE_CONFIG_MATCH_LIMIT - The output is a long integer that gives the default limit for the num- - ber of internal matching function calls in a pcre_exec() execution. + The output is a long integer that gives the default limit for the num- + ber of internal matching function calls in a pcre_exec() execution. Further details are given with pcre_exec() below. PCRE_CONFIG_MATCH_LIMIT_RECURSION The output is a long integer that gives the default limit for the depth - of recursion when calling the internal matching function in a - pcre_exec() execution. Further details are given with pcre_exec() + of recursion when calling the internal matching function in a + pcre_exec() execution. Further details are given with pcre_exec() below. PCRE_CONFIG_STACKRECURSE - The output is an integer that is set to one if internal recursion when + The output is an integer that is set to one if internal recursion when running pcre_exec() is implemented by recursive function calls that use - the stack to remember their state. This is the usual way that PCRE is + the stack to remember their state. This is the usual way that PCRE is compiled. The output is zero if PCRE was compiled to use blocks of data - on the heap instead of recursive function calls. In this case, - pcre_stack_malloc and pcre_stack_free are called to manage memory + on the heap instead of recursive function calls. In this case, + pcre_stack_malloc and pcre_stack_free are called to manage memory blocks on the heap, thus avoiding the use of the stack. @@ -1972,65 +1973,65 @@ COMPILING A PATTERN Either of the functions pcre_compile() or pcre_compile2() can be called to compile a pattern into an internal form. The only difference between - the two interfaces is that pcre_compile2() has an additional argument, - errorcodeptr, via which a numerical error code can be returned. To - avoid too much repetition, we refer just to pcre_compile() below, but + the two interfaces is that pcre_compile2() has an additional argument, + errorcodeptr, via which a numerical error code can be returned. To + avoid too much repetition, we refer just to pcre_compile() below, but the information applies equally to pcre_compile2(). The pattern is a C string terminated by a binary zero, and is passed in - the pattern argument. A pointer to a single block of memory that is - obtained via pcre_malloc is returned. This contains the compiled code + the pattern argument. A pointer to a single block of memory that is + obtained via pcre_malloc is returned. This contains the compiled code and related data. The pcre type is defined for the returned block; this is a typedef for a structure whose contents are not externally defined. It is up to the caller to free the memory (via pcre_free) when it is no longer required. - Although the compiled code of a PCRE regex is relocatable, that is, it + Although the compiled code of a PCRE regex is relocatable, that is, it does not depend on memory location, the complete pcre data block is not - fully relocatable, because it may contain a copy of the tableptr argu- + fully relocatable, because it may contain a copy of the tableptr argu- ment, which is an address (see below). The options argument contains various bit settings that affect the com- - pilation. It should be zero if no options are required. The available - options are described below. Some of them (in particular, those that - are compatible with Perl, but some others as well) can also be set and - unset from within the pattern (see the detailed description in the - pcrepattern documentation). For those options that can be different in - different parts of the pattern, the contents of the options argument + pilation. It should be zero if no options are required. The available + options are described below. Some of them (in particular, those that + are compatible with Perl, but some others as well) can also be set and + unset from within the pattern (see the detailed description in the + pcrepattern documentation). For those options that can be different in + different parts of the pattern, the contents of the options argument specifies their settings at the start of compilation and execution. The - PCRE_ANCHORED, PCRE_BSR_xxx, PCRE_NEWLINE_xxx, PCRE_NO_UTF8_CHECK, and - PCRE_NO_START_OPTIMIZE options can be set at the time of matching as + PCRE_ANCHORED, PCRE_BSR_xxx, PCRE_NEWLINE_xxx, PCRE_NO_UTF8_CHECK, and + PCRE_NO_START_OPTIMIZE options can be set at the time of matching as well as at compile time. If errptr is NULL, pcre_compile() returns NULL immediately. Otherwise, - if compilation of a pattern fails, pcre_compile() returns NULL, and + if compilation of a pattern fails, pcre_compile() returns NULL, and sets the variable pointed to by errptr to point to a textual error mes- sage. This is a static string that is part of the library. You must not - try to free it. Normally, the offset from the start of the pattern to - the byte that was being processed when the error was discovered is - placed in the variable pointed to by erroffset, which must not be NULL - (if it is, an immediate error is given). However, for an invalid UTF-8 + try to free it. Normally, the offset from the start of the pattern to + the byte that was being processed when the error was discovered is + placed in the variable pointed to by erroffset, which must not be NULL + (if it is, an immediate error is given). However, for an invalid UTF-8 string, the offset is that of the first byte of the failing character. - Some errors are not detected until the whole pattern has been scanned; - in these cases, the offset passed back is the length of the pattern. - Note that the offset is in bytes, not characters, even in UTF-8 mode. + Some errors are not detected until the whole pattern has been scanned; + in these cases, the offset passed back is the length of the pattern. + Note that the offset is in bytes, not characters, even in UTF-8 mode. It may sometimes point into the middle of a UTF-8 character. - If pcre_compile2() is used instead of pcre_compile(), and the error- - codeptr argument is not NULL, a non-zero error code number is returned - via this argument in the event of an error. This is in addition to the + If pcre_compile2() is used instead of pcre_compile(), and the error- + codeptr argument is not NULL, a non-zero error code number is returned + via this argument in the event of an error. This is in addition to the textual error message. Error codes and messages are listed below. - If the final argument, tableptr, is NULL, PCRE uses a default set of - character tables that are built when PCRE is compiled, using the - default C locale. Otherwise, tableptr must be an address that is the - result of a call to pcre_maketables(). This value is stored with the - compiled pattern, and used again by pcre_exec(), unless another table + If the final argument, tableptr, is NULL, PCRE uses a default set of + character tables that are built when PCRE is compiled, using the + default C locale. Otherwise, tableptr must be an address that is the + result of a call to pcre_maketables(). This value is stored with the + compiled pattern, and used again by pcre_exec(), unless another table pointer is passed to it. For more discussion, see the section on locale support below. - This code fragment shows a typical straightforward call to pcre_com- + This code fragment shows a typical straightforward call to pcre_com- pile(): pcre *re; @@ -2043,161 +2044,161 @@ COMPILING A PATTERN &erroffset, /* for error offset */ NULL); /* use default character tables */ - The following names for option bits are defined in the pcre.h header + The following names for option bits are defined in the pcre.h header file: PCRE_ANCHORED If this bit is set, the pattern is forced to be "anchored", that is, it - is constrained to match only at the first matching point in the string - that is being searched (the "subject string"). This effect can also be - achieved by appropriate constructs in the pattern itself, which is the + is constrained to match only at the first matching point in the string + that is being searched (the "subject string"). This effect can also be + achieved by appropriate constructs in the pattern itself, which is the only way to do it in Perl. PCRE_AUTO_CALLOUT If this bit is set, pcre_compile() automatically inserts callout items, - all with number 255, before each pattern item. For discussion of the + all with number 255, before each pattern item. For discussion of the callout facility, see the pcrecallout documentation. PCRE_BSR_ANYCRLF PCRE_BSR_UNICODE These options (which are mutually exclusive) control what the \R escape - sequence matches. The choice is either to match only CR, LF, or CRLF, + sequence matches. The choice is either to match only CR, LF, or CRLF, or to match any Unicode newline sequence. The default is specified when PCRE is built. It can be overridden from within the pattern, or by set- ting an option when a compiled pattern is matched. PCRE_CASELESS - If this bit is set, letters in the pattern match both upper and lower - case letters. It is equivalent to Perl's /i option, and it can be - changed within a pattern by a (?i) option setting. In UTF-8 mode, PCRE - always understands the concept of case for characters whose values are - less than 128, so caseless matching is always possible. For characters - with higher values, the concept of case is supported if PCRE is com- - piled with Unicode property support, but not otherwise. If you want to - use caseless matching for characters 128 and above, you must ensure - that PCRE is compiled with Unicode property support as well as with + If this bit is set, letters in the pattern match both upper and lower + case letters. It is equivalent to Perl's /i option, and it can be + changed within a pattern by a (?i) option setting. In UTF-8 mode, PCRE + always understands the concept of case for characters whose values are + less than 128, so caseless matching is always possible. For characters + with higher values, the concept of case is supported if PCRE is com- + piled with Unicode property support, but not otherwise. If you want to + use caseless matching for characters 128 and above, you must ensure + that PCRE is compiled with Unicode property support as well as with UTF-8 support. PCRE_DOLLAR_ENDONLY - If this bit is set, a dollar metacharacter in the pattern matches only - at the end of the subject string. Without this option, a dollar also - matches immediately before a newline at the end of the string (but not - before any other newlines). The PCRE_DOLLAR_ENDONLY option is ignored - if PCRE_MULTILINE is set. There is no equivalent to this option in + If this bit is set, a dollar metacharacter in the pattern matches only + at the end of the subject string. Without this option, a dollar also + matches immediately before a newline at the end of the string (but not + before any other newlines). The PCRE_DOLLAR_ENDONLY option is ignored + if PCRE_MULTILINE is set. There is no equivalent to this option in Perl, and no way to set it within a pattern. PCRE_DOTALL - If this bit is set, a dot metacharacter in the pattern matches a char- + If this bit is set, a dot metacharacter in the pattern matches a char- acter of any value, including one that indicates a newline. However, it - only ever matches one character, even if newlines are coded as CRLF. - Without this option, a dot does not match when the current position is + only ever matches one character, even if newlines are coded as CRLF. + Without this option, a dot does not match when the current position is at a newline. This option is equivalent to Perl's /s option, and it can - be changed within a pattern by a (?s) option setting. A negative class + be changed within a pattern by a (?s) option setting. A negative class such as [^a] always matches newline characters, independent of the set- ting of this option. PCRE_DUPNAMES - If this bit is set, names used to identify capturing subpatterns need + If this bit is set, names used to identify capturing subpatterns need not be unique. This can be helpful for certain types of pattern when it - is known that only one instance of the named subpattern can ever be - matched. There are more details of named subpatterns below; see also + is known that only one instance of the named subpattern can ever be + matched. There are more details of named subpatterns below; see also the pcrepattern documentation. PCRE_EXTENDED - If this bit is set, white space data characters in the pattern are - totally ignored except when escaped or inside a character class. White + If this bit is set, white space data characters in the pattern are + totally ignored except when escaped or inside a character class. White space does not include the VT character (code 11). In addition, charac- ters between an unescaped # outside a character class and the next new- - line, inclusive, are also ignored. This is equivalent to Perl's /x - option, and it can be changed within a pattern by a (?x) option set- + line, inclusive, are also ignored. This is equivalent to Perl's /x + option, and it can be changed within a pattern by a (?x) option set- ting. - Which characters are interpreted as newlines is controlled by the - options passed to pcre_compile() or by a special sequence at the start - of the pattern, as described in the section entitled "Newline conven- + Which characters are interpreted as newlines is controlled by the + options passed to pcre_compile() or by a special sequence at the start + of the pattern, as described in the section entitled "Newline conven- tions" in the pcrepattern documentation. Note that the end of this type - of comment is a literal newline sequence in the pattern; escape + of comment is a literal newline sequence in the pattern; escape sequences that happen to represent a newline do not count. - This option makes it possible to include comments inside complicated - patterns. Note, however, that this applies only to data characters. - White space characters may never appear within special character + This option makes it possible to include comments inside complicated + patterns. Note, however, that this applies only to data characters. + White space characters may never appear within special character sequences in a pattern, for example within the sequence (?( that intro- duces a conditional subpattern. PCRE_EXTRA - This option was invented in order to turn on additional functionality - of PCRE that is incompatible with Perl, but it is currently of very - little use. When set, any backslash in a pattern that is followed by a - letter that has no special meaning causes an error, thus reserving - these combinations for future expansion. By default, as in Perl, a - backslash followed by a letter with no special meaning is treated as a + This option was invented in order to turn on additional functionality + of PCRE that is incompatible with Perl, but it is currently of very + little use. When set, any backslash in a pattern that is followed by a + letter that has no special meaning causes an error, thus reserving + these combinations for future expansion. By default, as in Perl, a + backslash followed by a letter with no special meaning is treated as a literal. (Perl can, however, be persuaded to give an error for this, by - running it with the -w option.) There are at present no other features - controlled by this option. It can also be set by a (?X) option setting + running it with the -w option.) There are at present no other features + controlled by this option. It can also be set by a (?X) option setting within a pattern. PCRE_FIRSTLINE - If this option is set, an unanchored pattern is required to match - before or at the first newline in the subject string, though the + If this option is set, an unanchored pattern is required to match + before or at the first newline in the subject string, though the matched text may continue over the newline. PCRE_JAVASCRIPT_COMPAT If this option is set, PCRE's behaviour is changed in some ways so that - it is compatible with JavaScript rather than Perl. The changes are as + it is compatible with JavaScript rather than Perl. The changes are as follows: - (1) A lone closing square bracket in a pattern causes a compile-time - error, because this is illegal in JavaScript (by default it is treated + (1) A lone closing square bracket in a pattern causes a compile-time + error, because this is illegal in JavaScript (by default it is treated as a data character). Thus, the pattern AB]CD becomes illegal when this option is set. - (2) At run time, a back reference to an unset subpattern group matches - an empty string (by default this causes the current matching alterna- - tive to fail). A pattern such as (\1)(a) succeeds when this option is - set (assuming it can find an "a" in the subject), whereas it fails by + (2) At run time, a back reference to an unset subpattern group matches + an empty string (by default this causes the current matching alterna- + tive to fail). A pattern such as (\1)(a) succeeds when this option is + set (assuming it can find an "a" in the subject), whereas it fails by default, for Perl compatibility. (3) \U matches an upper case "U" character; by default \U causes a com- pile time error (Perl uses \U to upper case subsequent characters). (4) \u matches a lower case "u" character unless it is followed by four - hexadecimal digits, in which case the hexadecimal number defines the - code point to match. By default, \u causes a compile time error (Perl + hexadecimal digits, in which case the hexadecimal number defines the + code point to match. By default, \u causes a compile time error (Perl uses it to upper case the following character). - (5) \x matches a lower case "x" character unless it is followed by two - hexadecimal digits, in which case the hexadecimal number defines the - code point to match. By default, as in Perl, a hexadecimal number is + (5) \x matches a lower case "x" character unless it is followed by two + hexadecimal digits, in which case the hexadecimal number defines the + code point to match. By default, as in Perl, a hexadecimal number is always expected after \x, but it may have zero, one, or two digits (so, for example, \xz matches a binary zero character followed by z). PCRE_MULTILINE - By default, PCRE treats the subject string as consisting of a single - line of characters (even if it actually contains newlines). The "start - of line" metacharacter (^) matches only at the start of the string, - while the "end of line" metacharacter ($) matches only at the end of + By default, PCRE treats the subject string as consisting of a single + line of characters (even if it actually contains newlines). The "start + of line" metacharacter (^) matches only at the start of the string, + while the "end of line" metacharacter ($) matches only at the end of the string, or before a terminating newline (unless PCRE_DOLLAR_ENDONLY is set). This is the same as Perl. - When PCRE_MULTILINE it is set, the "start of line" and "end of line" - constructs match immediately following or immediately before internal - newlines in the subject string, respectively, as well as at the very - start and end. This is equivalent to Perl's /m option, and it can be + When PCRE_MULTILINE it is set, the "start of line" and "end of line" + constructs match immediately following or immediately before internal + newlines in the subject string, respectively, as well as at the very + start and end. This is equivalent to Perl's /m option, and it can be changed within a pattern by a (?m) option setting. If there are no new- - lines in a subject string, or no occurrences of ^ or $ in a pattern, + lines in a subject string, or no occurrences of ^ or $ in a pattern, setting PCRE_MULTILINE has no effect. PCRE_NEWLINE_CR @@ -2206,41 +2207,41 @@ COMPILING A PATTERN PCRE_NEWLINE_ANYCRLF PCRE_NEWLINE_ANY - These options override the default newline definition that was chosen - when PCRE was built. Setting the first or the second specifies that a - newline is indicated by a single character (CR or LF, respectively). - Setting PCRE_NEWLINE_CRLF specifies that a newline is indicated by the - two-character CRLF sequence. Setting PCRE_NEWLINE_ANYCRLF specifies + These options override the default newline definition that was chosen + when PCRE was built. Setting the first or the second specifies that a + newline is indicated by a single character (CR or LF, respectively). + Setting PCRE_NEWLINE_CRLF specifies that a newline is indicated by the + two-character CRLF sequence. Setting PCRE_NEWLINE_ANYCRLF specifies that any of the three preceding sequences should be recognized. Setting - PCRE_NEWLINE_ANY specifies that any Unicode newline sequence should be + PCRE_NEWLINE_ANY specifies that any Unicode newline sequence should be recognized. - In an ASCII/Unicode environment, the Unicode newline sequences are the - three just mentioned, plus the single characters VT (vertical tab, + In an ASCII/Unicode environment, the Unicode newline sequences are the + three just mentioned, plus the single characters VT (vertical tab, U+000B), FF (form feed, U+000C), NEL (next line, U+0085), LS (line sep- - arator, U+2028), and PS (paragraph separator, U+2029). For the 8-bit + arator, U+2028), and PS (paragraph separator, U+2029). For the 8-bit library, the last two are recognized only in UTF-8 mode. - When PCRE is compiled to run in an EBCDIC (mainframe) environment, the + When PCRE is compiled to run in an EBCDIC (mainframe) environment, the code for CR is 0x0d, the same as ASCII. However, the character code for - LF is normally 0x15, though in some EBCDIC environments 0x25 is used. - Whichever of these is not LF is made to correspond to Unicode's NEL - character. EBCDIC codes are all less than 256. For more details, see + LF is normally 0x15, though in some EBCDIC environments 0x25 is used. + Whichever of these is not LF is made to correspond to Unicode's NEL + character. EBCDIC codes are all less than 256. For more details, see the pcrebuild documentation. - The newline setting in the options word uses three bits that are + The newline setting in the options word uses three bits that are treated as a number, giving eight possibilities. Currently only six are - used (default plus the five values above). This means that if you set - more than one newline option, the combination may or may not be sensi- + used (default plus the five values above). This means that if you set + more than one newline option, the combination may or may not be sensi- ble. For example, PCRE_NEWLINE_CR with PCRE_NEWLINE_LF is equivalent to - PCRE_NEWLINE_CRLF, but other combinations may yield unused numbers and + PCRE_NEWLINE_CRLF, but other combinations may yield unused numbers and cause an error. - The only time that a line break in a pattern is specially recognized - when compiling is when PCRE_EXTENDED is set. CR and LF are white space - characters, and so are ignored in this mode. Also, an unescaped # out- - side a character class indicates a comment that lasts until after the - next line break sequence. In other circumstances, line break sequences + The only time that a line break in a pattern is specially recognized + when compiling is when PCRE_EXTENDED is set. CR and LF are white space + characters, and so are ignored in this mode. Also, an unescaped # out- + side a character class indicates a comment that lasts until after the + next line break sequence. In other circumstances, line break sequences in patterns are treated as literal data. The newline option that is set at compile time becomes the default that @@ -2249,68 +2250,68 @@ COMPILING A PATTERN PCRE_NO_AUTO_CAPTURE If this option is set, it disables the use of numbered capturing paren- - theses in the pattern. Any opening parenthesis that is not followed by - ? behaves as if it were followed by ?: but named parentheses can still - be used for capturing (and they acquire numbers in the usual way). + theses in the pattern. Any opening parenthesis that is not followed by + ? behaves as if it were followed by ?: but named parentheses can still + be used for capturing (and they acquire numbers in the usual way). There is no equivalent of this option in Perl. NO_START_OPTIMIZE - This is an option that acts at matching time; that is, it is really an - option for pcre_exec() or pcre_dfa_exec(). If it is set at compile - time, it is remembered with the compiled pattern and assumed at match- - ing time. For details see the discussion of PCRE_NO_START_OPTIMIZE + This is an option that acts at matching time; that is, it is really an + option for pcre_exec() or pcre_dfa_exec(). If it is set at compile + time, it is remembered with the compiled pattern and assumed at match- + ing time. For details see the discussion of PCRE_NO_START_OPTIMIZE below. PCRE_UCP - This option changes the way PCRE processes \B, \b, \D, \d, \S, \s, \W, - \w, and some of the POSIX character classes. By default, only ASCII - characters are recognized, but if PCRE_UCP is set, Unicode properties - are used instead to classify characters. More details are given in the - section on generic character types in the pcrepattern page. If you set - PCRE_UCP, matching one of the items it affects takes much longer. The - option is available only if PCRE has been compiled with Unicode prop- + This option changes the way PCRE processes \B, \b, \D, \d, \S, \s, \W, + \w, and some of the POSIX character classes. By default, only ASCII + characters are recognized, but if PCRE_UCP is set, Unicode properties + are used instead to classify characters. More details are given in the + section on generic character types in the pcrepattern page. If you set + PCRE_UCP, matching one of the items it affects takes much longer. The + option is available only if PCRE has been compiled with Unicode prop- erty support. PCRE_UNGREEDY - This option inverts the "greediness" of the quantifiers so that they - are not greedy by default, but become greedy if followed by "?". It is - not compatible with Perl. It can also be set by a (?U) option setting + This option inverts the "greediness" of the quantifiers so that they + are not greedy by default, but become greedy if followed by "?". It is + not compatible with Perl. It can also be set by a (?U) option setting within the pattern. PCRE_UTF8 - This option causes PCRE to regard both the pattern and the subject as + This option causes PCRE to regard both the pattern and the subject as strings of UTF-8 characters instead of single-byte strings. However, it - is available only when PCRE is built to include UTF support. If not, - the use of this option provokes an error. Details of how this option + is available only when PCRE is built to include UTF support. If not, + the use of this option provokes an error. Details of how this option changes the behaviour of PCRE are given in the pcreunicode page. PCRE_NO_UTF8_CHECK When PCRE_UTF8 is set, the validity of the pattern as a UTF-8 string is - automatically checked. There is a discussion about the validity of - UTF-8 strings in the pcreunicode page. If an invalid UTF-8 sequence is - found, pcre_compile() returns an error. If you already know that your - pattern is valid, and you want to skip this check for performance rea- - sons, you can set the PCRE_NO_UTF8_CHECK option. When it is set, the + automatically checked. There is a discussion about the validity of + UTF-8 strings in the pcreunicode page. If an invalid UTF-8 sequence is + found, pcre_compile() returns an error. If you already know that your + pattern is valid, and you want to skip this check for performance rea- + sons, you can set the PCRE_NO_UTF8_CHECK option. When it is set, the effect of passing an invalid UTF-8 string as a pattern is undefined. It - may cause your program to crash. Note that this option can also be - passed to pcre_exec() and pcre_dfa_exec(), to suppress the validity - checking of subject strings only. If the same string is being matched - many times, the option can be safely set for the second and subsequent + may cause your program to crash. Note that this option can also be + passed to pcre_exec() and pcre_dfa_exec(), to suppress the validity + checking of subject strings only. If the same string is being matched + many times, the option can be safely set for the second and subsequent matchings to improve performance. COMPILATION ERROR CODES - The following table lists the error codes than may be returned by - pcre_compile2(), along with the error messages that may be returned by - both compiling functions. Note that error messages are always 8-bit - ASCII strings, even in 16-bit or 32-bit mode. As PCRE has developed, - some error codes have fallen out of use. To avoid confusion, they have + The following table lists the error codes than may be returned by + pcre_compile2(), along with the error messages that may be returned by + both compiling functions. Note that error messages are always 8-bit + ASCII strings, even in 16-bit or 32-bit mode. As PCRE has developed, + some error codes have fallen out of use. To avoid confusion, they have not been re-used. 0 no error @@ -2396,7 +2397,7 @@ COMPILATION ERROR CODES 76 character value in \u.... sequence is too large 77 invalid UTF-32 string (specifically UTF-32) - The numbers 32 and 10000 in errors 48 and 49 are defaults; different + The numbers 32 and 10000 in errors 48 and 49 are defaults; different values may be used if the limits were changed when PCRE was built. @@ -2405,64 +2406,64 @@ STUDYING A PATTERN pcre_extra *pcre_study(const pcre *code, int options const char **errptr); - If a compiled pattern is going to be used several times, it is worth + If a compiled pattern is going to be used several times, it is worth spending more time analyzing it in order to speed up the time taken for - matching. The function pcre_study() takes a pointer to a compiled pat- + matching. The function pcre_study() takes a pointer to a compiled pat- tern as its first argument. If studying the pattern produces additional - information that will help speed up matching, pcre_study() returns a - pointer to a pcre_extra block, in which the study_data field points to + information that will help speed up matching, pcre_study() returns a + pointer to a pcre_extra block, in which the study_data field points to the results of the study. The returned value from pcre_study() can be passed directly to - pcre_exec() or pcre_dfa_exec(). However, a pcre_extra block also con- - tains other fields that can be set by the caller before the block is + pcre_exec() or pcre_dfa_exec(). However, a pcre_extra block also con- + tains other fields that can be set by the caller before the block is passed; these are described below in the section on matching a pattern. - If studying the pattern does not produce any useful information, - pcre_study() returns NULL by default. In that circumstance, if the + If studying the pattern does not produce any useful information, + pcre_study() returns NULL by default. In that circumstance, if the calling program wants to pass any of the other fields to pcre_exec() or - pcre_dfa_exec(), it must set up its own pcre_extra block. However, if - pcre_study() is called with the PCRE_STUDY_EXTRA_NEEDED option, it + pcre_dfa_exec(), it must set up its own pcre_extra block. However, if + pcre_study() is called with the PCRE_STUDY_EXTRA_NEEDED option, it returns a pcre_extra block even if studying did not find any additional - information. It may still return NULL, however, if an error occurs in + information. It may still return NULL, however, if an error occurs in pcre_study(). - The second argument of pcre_study() contains option bits. There are + The second argument of pcre_study() contains option bits. There are three further options in addition to PCRE_STUDY_EXTRA_NEEDED: PCRE_STUDY_JIT_COMPILE PCRE_STUDY_JIT_PARTIAL_HARD_COMPILE PCRE_STUDY_JIT_PARTIAL_SOFT_COMPILE - If any of these are set, and the just-in-time compiler is available, - the pattern is further compiled into machine code that executes much - faster than the pcre_exec() interpretive matching function. If the - just-in-time compiler is not available, these options are ignored. All + If any of these are set, and the just-in-time compiler is available, + the pattern is further compiled into machine code that executes much + faster than the pcre_exec() interpretive matching function. If the + just-in-time compiler is not available, these options are ignored. All undefined bits in the options argument must be zero. - JIT compilation is a heavyweight optimization. It can take some time - for patterns to be analyzed, and for one-off matches and simple pat- - terns the benefit of faster execution might be offset by a much slower + JIT compilation is a heavyweight optimization. It can take some time + for patterns to be analyzed, and for one-off matches and simple pat- + terns the benefit of faster execution might be offset by a much slower study time. Not all patterns can be optimized by the JIT compiler. For - those that cannot be handled, matching automatically falls back to the - pcre_exec() interpreter. For more details, see the pcrejit documenta- + those that cannot be handled, matching automatically falls back to the + pcre_exec() interpreter. For more details, see the pcrejit documenta- tion. - The third argument for pcre_study() is a pointer for an error message. - If studying succeeds (even if no data is returned), the variable it - points to is set to NULL. Otherwise it is set to point to a textual + The third argument for pcre_study() is a pointer for an error message. + If studying succeeds (even if no data is returned), the variable it + points to is set to NULL. Otherwise it is set to point to a textual error message. This is a static string that is part of the library. You - must not try to free it. You should test the error pointer for NULL + must not try to free it. You should test the error pointer for NULL after calling pcre_study(), to be sure that it has run successfully. - When you are finished with a pattern, you can free the memory used for + When you are finished with a pattern, you can free the memory used for the study data by calling pcre_free_study(). This function was added to - the API for release 8.20. For earlier versions, the memory could be - freed with pcre_free(), just like the pattern itself. This will still - work in cases where JIT optimization is not used, but it is advisable + the API for release 8.20. For earlier versions, the memory could be + freed with pcre_free(), just like the pattern itself. This will still + work in cases where JIT optimization is not used, but it is advisable to change to the new function when convenient. - This is a typical way in which pcre_study() is used (except that in a + This is a typical way in which pcre_study() is used (except that in a real application there should be tests for errors): int rc; @@ -2482,82 +2483,82 @@ STUDYING A PATTERN Studying a pattern does two things: first, a lower bound for the length of subject string that is needed to match the pattern is computed. This does not mean that there are any strings of that length that match, but - it does guarantee that no shorter strings match. The value is used to + it does guarantee that no shorter strings match. The value is used to avoid wasting time by trying to match strings that are shorter than the - lower bound. You can find out the value in a calling program via the + lower bound. You can find out the value in a calling program via the pcre_fullinfo() function. Studying a pattern is also useful for non-anchored patterns that do not - have a single fixed starting character. A bitmap of possible starting - bytes is created. This speeds up finding a position in the subject at + have a single fixed starting character. A bitmap of possible starting + bytes is created. This speeds up finding a position in the subject at which to start matching. (In 16-bit mode, the bitmap is used for 16-bit - values less than 256. In 32-bit mode, the bitmap is used for 32-bit + values less than 256. In 32-bit mode, the bitmap is used for 32-bit values less than 256.) - These two optimizations apply to both pcre_exec() and pcre_dfa_exec(), - and the information is also used by the JIT compiler. The optimiza- + These two optimizations apply to both pcre_exec() and pcre_dfa_exec(), + and the information is also used by the JIT compiler. The optimiza- tions can be disabled by setting the PCRE_NO_START_OPTIMIZE option when calling pcre_exec() or pcre_dfa_exec(), but if this is done, JIT execu- - tion is also disabled. You might want to do this if your pattern con- - tains callouts or (*MARK) and you want to make use of these facilities - in cases where matching fails. See the discussion of + tion is also disabled. You might want to do this if your pattern con- + tains callouts or (*MARK) and you want to make use of these facilities + in cases where matching fails. See the discussion of PCRE_NO_START_OPTIMIZE below. LOCALE SUPPORT - PCRE handles caseless matching, and determines whether characters are - letters, digits, or whatever, by reference to a set of tables, indexed - by character value. When running in UTF-8 mode, this applies only to - characters with codes less than 128. By default, higher-valued codes + PCRE handles caseless matching, and determines whether characters are + letters, digits, or whatever, by reference to a set of tables, indexed + by character value. When running in UTF-8 mode, this applies only to + characters with codes less than 128. By default, higher-valued codes never match escapes such as \w or \d, but they can be tested with \p if - PCRE is built with Unicode character property support. Alternatively, - the PCRE_UCP option can be set at compile time; this causes \w and + PCRE is built with Unicode character property support. Alternatively, + the PCRE_UCP option can be set at compile time; this causes \w and friends to use Unicode property support instead of built-in tables. The use of locales with Unicode is discouraged. If you are handling charac- - ters with codes greater than 128, you should either use UTF-8 and Uni- + ters with codes greater than 128, you should either use UTF-8 and Uni- code, or use locales, but not try to mix the two. - PCRE contains an internal set of tables that are used when the final - argument of pcre_compile() is NULL. These are sufficient for many + PCRE contains an internal set of tables that are used when the final + argument of pcre_compile() is NULL. These are sufficient for many applications. Normally, the internal tables recognize only ASCII char- acters. However, when PCRE is built, it is possible to cause the inter- nal tables to be rebuilt in the default "C" locale of the local system, which may cause them to be different. - The internal tables can always be overridden by tables supplied by the + The internal tables can always be overridden by tables supplied by the application that calls PCRE. These may be created in a different locale - from the default. As more and more applications change to using Uni- + from the default. As more and more applications change to using Uni- code, the need for this locale support is expected to die away. - External tables are built by calling the pcre_maketables() function, - which has no arguments, in the relevant locale. The result can then be - passed to pcre_compile() or pcre_exec() as often as necessary. For - example, to build and use tables that are appropriate for the French - locale (where accented characters with values greater than 128 are + External tables are built by calling the pcre_maketables() function, + which has no arguments, in the relevant locale. The result can then be + passed to pcre_compile() or pcre_exec() as often as necessary. For + example, to build and use tables that are appropriate for the French + locale (where accented characters with values greater than 128 are treated as letters), the following code could be used: setlocale(LC_CTYPE, "fr_FR"); tables = pcre_maketables(); re = pcre_compile(..., tables); - The locale name "fr_FR" is used on Linux and other Unix-like systems; + The locale name "fr_FR" is used on Linux and other Unix-like systems; if you are using Windows, the name for the French locale is "french". - When pcre_maketables() runs, the tables are built in memory that is - obtained via pcre_malloc. It is the caller's responsibility to ensure - that the memory containing the tables remains available for as long as + When pcre_maketables() runs, the tables are built in memory that is + obtained via pcre_malloc. It is the caller's responsibility to ensure + that the memory containing the tables remains available for as long as it is needed. The pointer that is passed to pcre_compile() is saved with the compiled - pattern, and the same tables are used via this pointer by pcre_study() + pattern, and the same tables are used via this pointer by pcre_study() and normally also by pcre_exec(). Thus, by default, for any single pat- tern, compilation, studying and matching all happen in the same locale, but different patterns can be compiled in different locales. - It is possible to pass a table pointer or NULL (indicating the use of - the internal tables) to pcre_exec(). Although not intended for this - purpose, this facility could be used to match a pattern in a different + It is possible to pass a table pointer or NULL (indicating the use of + the internal tables) to pcre_exec(). Although not intended for this + purpose, this facility could be used to match a pattern in a different locale from the one in which it was compiled. Passing table pointers at run time is discussed below in the section on matching a pattern. @@ -2567,15 +2568,15 @@ INFORMATION ABOUT A PATTERN int pcre_fullinfo(const pcre *code, const pcre_extra *extra, int what, void *where); - The pcre_fullinfo() function returns information about a compiled pat- - tern. It replaces the pcre_info() function, which was removed from the + The pcre_fullinfo() function returns information about a compiled pat- + tern. It replaces the pcre_info() function, which was removed from the library at version 8.30, after more than 10 years of obsolescence. - The first argument for pcre_fullinfo() is a pointer to the compiled - pattern. The second argument is the result of pcre_study(), or NULL if - the pattern was not studied. The third argument specifies which piece - of information is required, and the fourth argument is a pointer to a - variable to receive the data. The yield of the function is zero for + The first argument for pcre_fullinfo() is a pointer to the compiled + pattern. The second argument is the result of pcre_study(), or NULL if + the pattern was not studied. The third argument specifies which piece + of information is required, and the fourth argument is a pointer to a + variable to receive the data. The yield of the function is zero for success, or one of the following negative numbers: PCRE_ERROR_NULL the argument code was NULL @@ -2585,10 +2586,10 @@ INFORMATION ABOUT A PATTERN endianness PCRE_ERROR_BADOPTION the value of what was invalid - The "magic number" is placed at the start of each compiled pattern as - an simple check against passing an arbitrary memory pointer. The endi- + The "magic number" is placed at the start of each compiled pattern as + an simple check against passing an arbitrary memory pointer. The endi- anness error can occur if a compiled pattern is saved and reloaded on a - different host. Here is a typical call of pcre_fullinfo(), to obtain + different host. Here is a typical call of pcre_fullinfo(), to obtain the length of the compiled pattern: int rc; @@ -2599,174 +2600,174 @@ INFORMATION ABOUT A PATTERN PCRE_INFO_SIZE, /* what is required */ &length); /* where to put the data */ - The possible values for the third argument are defined in pcre.h, and + The possible values for the third argument are defined in pcre.h, and are as follows: PCRE_INFO_BACKREFMAX - Return the number of the highest back reference in the pattern. The - fourth argument should point to an int variable. Zero is returned if + Return the number of the highest back reference in the pattern. The + fourth argument should point to an int variable. Zero is returned if there are no back references. PCRE_INFO_CAPTURECOUNT - Return the number of capturing subpatterns in the pattern. The fourth + Return the number of capturing subpatterns in the pattern. The fourth argument should point to an int variable. PCRE_INFO_DEFAULT_TABLES - Return a pointer to the internal default character tables within PCRE. - The fourth argument should point to an unsigned char * variable. This + Return a pointer to the internal default character tables within PCRE. + The fourth argument should point to an unsigned char * variable. This information call is provided for internal use by the pcre_study() func- - tion. External callers can cause PCRE to use its internal tables by + tion. External callers can cause PCRE to use its internal tables by passing a NULL table pointer. PCRE_INFO_FIRSTBYTE Return information about the first data unit of any matched string, for - a non-anchored pattern. (The name of this option refers to the 8-bit - library, where data units are bytes.) The fourth argument should point + a non-anchored pattern. (The name of this option refers to the 8-bit + library, where data units are bytes.) The fourth argument should point to an int variable. - If there is a fixed first value, for example, the letter "c" from a - pattern such as (cat|cow|coyote), its value is returned. In the 8-bit - library, the value is always less than 256. In the 16-bit library the + If there is a fixed first value, for example, the letter "c" from a + pattern such as (cat|cow|coyote), its value is returned. In the 8-bit + library, the value is always less than 256. In the 16-bit library the value can be up to 0xffff. In the 32-bit library the value can be up to 0x10ffff. If there is no fixed first value, and if either - (a) the pattern was compiled with the PCRE_MULTILINE option, and every + (a) the pattern was compiled with the PCRE_MULTILINE option, and every branch starts with "^", or (b) every branch of the pattern starts with ".*" and PCRE_DOTALL is not set (if it were set, the pattern would be anchored), - -1 is returned, indicating that the pattern matches only at the start - of a subject string or after any newline within the string. Otherwise + -1 is returned, indicating that the pattern matches only at the start + of a subject string or after any newline within the string. Otherwise -2 is returned. For anchored patterns, -2 is returned. - Since for the 32-bit library using the non-UTF-32 mode, this function - is unable to return the full 32-bit range of the character, this value - is deprecated; instead the PCRE_INFO_FIRSTCHARACTERFLAGS and + Since for the 32-bit library using the non-UTF-32 mode, this function + is unable to return the full 32-bit range of the character, this value + is deprecated; instead the PCRE_INFO_FIRSTCHARACTERFLAGS and PCRE_INFO_FIRSTCHARACTER values should be used. PCRE_INFO_FIRSTTABLE - If the pattern was studied, and this resulted in the construction of a - 256-bit table indicating a fixed set of values for the first data unit - in any matching string, a pointer to the table is returned. Otherwise - NULL is returned. The fourth argument should point to an unsigned char + If the pattern was studied, and this resulted in the construction of a + 256-bit table indicating a fixed set of values for the first data unit + in any matching string, a pointer to the table is returned. Otherwise + NULL is returned. The fourth argument should point to an unsigned char * variable. PCRE_INFO_HASCRORLF - Return 1 if the pattern contains any explicit matches for CR or LF - characters, otherwise 0. The fourth argument should point to an int - variable. An explicit match is either a literal CR or LF character, or + Return 1 if the pattern contains any explicit matches for CR or LF + characters, otherwise 0. The fourth argument should point to an int + variable. An explicit match is either a literal CR or LF character, or \r or \n. PCRE_INFO_JCHANGED - Return 1 if the (?J) or (?-J) option setting is used in the pattern, - otherwise 0. The fourth argument should point to an int variable. (?J) + Return 1 if the (?J) or (?-J) option setting is used in the pattern, + otherwise 0. The fourth argument should point to an int variable. (?J) and (?-J) set and unset the local PCRE_DUPNAMES option, respectively. PCRE_INFO_JIT - Return 1 if the pattern was studied with one of the JIT options, and + Return 1 if the pattern was studied with one of the JIT options, and just-in-time compiling was successful. The fourth argument should point - to an int variable. A return value of 0 means that JIT support is not - available in this version of PCRE, or that the pattern was not studied - with a JIT option, or that the JIT compiler could not handle this par- - ticular pattern. See the pcrejit documentation for details of what can + to an int variable. A return value of 0 means that JIT support is not + available in this version of PCRE, or that the pattern was not studied + with a JIT option, or that the JIT compiler could not handle this par- + ticular pattern. See the pcrejit documentation for details of what can and cannot be handled. PCRE_INFO_JITSIZE - If the pattern was successfully studied with a JIT option, return the - size of the JIT compiled code, otherwise return zero. The fourth argu- + If the pattern was successfully studied with a JIT option, return the + size of the JIT compiled code, otherwise return zero. The fourth argu- ment should point to a size_t variable. PCRE_INFO_LASTLITERAL - Return the value of the rightmost literal data unit that must exist in - any matched string, other than at its start, if such a value has been + Return the value of the rightmost literal data unit that must exist in + any matched string, other than at its start, if such a value has been recorded. The fourth argument should point to an int variable. If there is no such value, -1 is returned. For anchored patterns, a last literal - value is recorded only if it follows something of variable length. For + value is recorded only if it follows something of variable length. For example, for the pattern /^a\d+z\d+/ the returned value is "z", but for /^a\dz\d/ the returned value is -1. - Since for the 32-bit library using the non-UTF-32 mode, this function - is unable to return the full 32-bit range of the character, this value - is deprecated; instead the PCRE_INFO_REQUIREDCHARFLAGS and + Since for the 32-bit library using the non-UTF-32 mode, this function + is unable to return the full 32-bit range of the character, this value + is deprecated; instead the PCRE_INFO_REQUIREDCHARFLAGS and PCRE_INFO_REQUIREDCHAR values should be used. PCRE_INFO_MAXLOOKBEHIND - Return the number of characters (NB not bytes) in the longest lookbe- - hind assertion in the pattern. Note that the simple assertions \b and - \B require a one-character lookbehind. This information is useful when + Return the number of characters (NB not bytes) in the longest lookbe- + hind assertion in the pattern. Note that the simple assertions \b and + \B require a one-character lookbehind. This information is useful when doing multi-segment matching using the partial matching facilities. PCRE_INFO_MINLENGTH - If the pattern was studied and a minimum length for matching subject - strings was computed, its value is returned. Otherwise the returned - value is -1. The value is a number of characters, which in UTF-8 mode - may be different from the number of bytes. The fourth argument should - point to an int variable. A non-negative value is a lower bound to the - length of any matching string. There may not be any strings of that - length that do actually match, but every string that does match is at + If the pattern was studied and a minimum length for matching subject + strings was computed, its value is returned. Otherwise the returned + value is -1. The value is a number of characters, which in UTF-8 mode + may be different from the number of bytes. The fourth argument should + point to an int variable. A non-negative value is a lower bound to the + length of any matching string. There may not be any strings of that + length that do actually match, but every string that does match is at least that long. PCRE_INFO_NAMECOUNT PCRE_INFO_NAMEENTRYSIZE PCRE_INFO_NAMETABLE - PCRE supports the use of named as well as numbered capturing parenthe- - ses. The names are just an additional way of identifying the parenthe- + PCRE supports the use of named as well as numbered capturing parenthe- + ses. The names are just an additional way of identifying the parenthe- ses, which still acquire numbers. Several convenience functions such as - pcre_get_named_substring() are provided for extracting captured sub- - strings by name. It is also possible to extract the data directly, by - first converting the name to a number in order to access the correct + pcre_get_named_substring() are provided for extracting captured sub- + strings by name. It is also possible to extract the data directly, by + first converting the name to a number in order to access the correct pointers in the output vector (described with pcre_exec() below). To do - the conversion, you need to use the name-to-number map, which is + the conversion, you need to use the name-to-number map, which is described by these three values. The map consists of a number of fixed-size entries. PCRE_INFO_NAMECOUNT gives the number of entries, and PCRE_INFO_NAMEENTRYSIZE gives the size - of each entry; both of these return an int value. The entry size - depends on the length of the longest name. PCRE_INFO_NAMETABLE returns + of each entry; both of these return an int value. The entry size + depends on the length of the longest name. PCRE_INFO_NAMETABLE returns a pointer to the first entry of the table. This is a pointer to char in the 8-bit library, where the first two bytes of each entry are the num- - ber of the capturing parenthesis, most significant byte first. In the - 16-bit library, the pointer points to 16-bit data units, the first of - which contains the parenthesis number. In the 32-bit library, the - pointer points to 32-bit data units, the first of which contains the - parenthesis number. The rest of the entry is the corresponding name, + ber of the capturing parenthesis, most significant byte first. In the + 16-bit library, the pointer points to 16-bit data units, the first of + which contains the parenthesis number. In the 32-bit library, the + pointer points to 32-bit data units, the first of which contains the + parenthesis number. The rest of the entry is the corresponding name, zero terminated. - The names are in alphabetical order. Duplicate names may appear if (?| + The names are in alphabetical order. Duplicate names may appear if (?| is used to create multiple groups with the same number, as described in - the section on duplicate subpattern numbers in the pcrepattern page. - Duplicate names for subpatterns with different numbers are permitted - only if PCRE_DUPNAMES is set. In all cases of duplicate names, they - appear in the table in the order in which they were found in the pat- - tern. In the absence of (?| this is the order of increasing number; + the section on duplicate subpattern numbers in the pcrepattern page. + Duplicate names for subpatterns with different numbers are permitted + only if PCRE_DUPNAMES is set. In all cases of duplicate names, they + appear in the table in the order in which they were found in the pat- + tern. In the absence of (?| this is the order of increasing number; when (?| is used this is not necessarily the case because later subpat- terns may have lower numbers. - As a simple example of the name/number table, consider the following + As a simple example of the name/number table, consider the following pattern after compilation by the 8-bit library (assume PCRE_EXTENDED is set, so white space - including newlines - is ignored): (?<date> (?<year>(\d\d)?\d\d) - (?<month>\d\d) - (?<day>\d\d) ) - There are four named subpatterns, so the table has four entries, and - each entry in the table is eight bytes long. The table is as follows, + There are four named subpatterns, so the table has four entries, and + each entry in the table is eight bytes long. The table is as follows, with non-printing bytes shows in hexadecimal, and undefined bytes shown as ??: @@ -2775,31 +2776,31 @@ INFORMATION ABOUT A PATTERN 00 04 m o n t h 00 00 02 y e a r 00 ?? - When writing code to extract data from named subpatterns using the - name-to-number map, remember that the length of the entries is likely + When writing code to extract data from named subpatterns using the + name-to-number map, remember that the length of the entries is likely to be different for each compiled pattern. PCRE_INFO_OKPARTIAL - Return 1 if the pattern can be used for partial matching with - pcre_exec(), otherwise 0. The fourth argument should point to an int - variable. From release 8.00, this always returns 1, because the - restrictions that previously applied to partial matching have been - lifted. The pcrepartial documentation gives details of partial match- + Return 1 if the pattern can be used for partial matching with + pcre_exec(), otherwise 0. The fourth argument should point to an int + variable. From release 8.00, this always returns 1, because the + restrictions that previously applied to partial matching have been + lifted. The pcrepartial documentation gives details of partial match- ing. PCRE_INFO_OPTIONS - Return a copy of the options with which the pattern was compiled. The - fourth argument should point to an unsigned long int variable. These + Return a copy of the options with which the pattern was compiled. The + fourth argument should point to an unsigned long int variable. These option bits are those specified in the call to pcre_compile(), modified by any top-level option settings at the start of the pattern itself. In - other words, they are the options that will be in force when matching - starts. For example, if the pattern /(?im)abc(?-i)d/ is compiled with - the PCRE_EXTENDED option, the result is PCRE_CASELESS, PCRE_MULTILINE, + other words, they are the options that will be in force when matching + starts. For example, if the pattern /(?im)abc(?-i)d/ is compiled with + the PCRE_EXTENDED option, the result is PCRE_CASELESS, PCRE_MULTILINE, and PCRE_EXTENDED. - A pattern is automatically anchored by PCRE if all of its top-level + A pattern is automatically anchored by PCRE if all of its top-level alternatives begin with one of the following: ^ unless PCRE_MULTILINE is set @@ -2813,40 +2814,40 @@ INFORMATION ABOUT A PATTERN PCRE_INFO_SIZE - Return the size of the compiled pattern in bytes (for both libraries). - The fourth argument should point to a size_t variable. This value does - not include the size of the pcre structure that is returned by - pcre_compile(). The value that is passed as the argument to pcre_mal- - loc() when pcre_compile() is getting memory in which to place the com- - piled data is the value returned by this option plus the size of the - pcre structure. Studying a compiled pattern, with or without JIT, does + Return the size of the compiled pattern in bytes (for both libraries). + The fourth argument should point to a size_t variable. This value does + not include the size of the pcre structure that is returned by + pcre_compile(). The value that is passed as the argument to pcre_mal- + loc() when pcre_compile() is getting memory in which to place the com- + piled data is the value returned by this option plus the size of the + pcre structure. Studying a compiled pattern, with or without JIT, does not alter the value returned by this option. PCRE_INFO_STUDYSIZE Return the size in bytes of the data block pointed to by the study_data - field in a pcre_extra block. If pcre_extra is NULL, or there is no - study data, zero is returned. The fourth argument should point to a - size_t variable. The study_data field is set by pcre_study() to record - information that will speed up matching (see the section entitled + field in a pcre_extra block. If pcre_extra is NULL, or there is no + study data, zero is returned. The fourth argument should point to a + size_t variable. The study_data field is set by pcre_study() to record + information that will speed up matching (see the section entitled "Studying a pattern" above). The format of the study_data block is pri- - vate, but its length is made available via this option so that it can + vate, but its length is made available via this option so that it can be saved and restored (see the pcreprecompile documentation for details). PCRE_INFO_FIRSTCHARACTERFLAGS Return information about the first data unit of any matched string, for - a non-anchored pattern. The fourth argument should point to an int + a non-anchored pattern. The fourth argument should point to an int variable. - If there is a fixed first value, for example, the letter "c" from a - pattern such as (cat|cow|coyote), 1 is returned, and the character + If there is a fixed first value, for example, the letter "c" from a + pattern such as (cat|cow|coyote), 1 is returned, and the character value can be retrieved using PCRE_INFO_FIRSTCHARACTER. If there is no fixed first value, and if either - (a) the pattern was compiled with the PCRE_MULTILINE option, and every + (a) the pattern was compiled with the PCRE_MULTILINE option, and every branch starts with "^", or (b) every branch of the pattern starts with ".*" and PCRE_DOTALL is not @@ -2858,45 +2859,45 @@ INFORMATION ABOUT A PATTERN PCRE_INFO_FIRSTCHARACTER - Return the fixed first character value, if PCRE_INFO_FIRSTCHARACTER- + Return the fixed first character value, if PCRE_INFO_FIRSTCHARACTER- FLAGS returned 1; otherwise returns 0. The fourth argument should point to an uint_t variable. - In the 8-bit library, the value is always less than 256. In the 16-bit - library the value can be up to 0xffff. In the 32-bit library in UTF-32 - mode the value can be up to 0x10ffff, and up to 0xffffffff when not + In the 8-bit library, the value is always less than 256. In the 16-bit + library the value can be up to 0xffff. In the 32-bit library in UTF-32 + mode the value can be up to 0x10ffff, and up to 0xffffffff when not using UTF-32 mode. If there is no fixed first value, and if either - (a) the pattern was compiled with the PCRE_MULTILINE option, and every + (a) the pattern was compiled with the PCRE_MULTILINE option, and every branch starts with "^", or (b) every branch of the pattern starts with ".*" and PCRE_DOTALL is not set (if it were set, the pattern would be anchored), - -1 is returned, indicating that the pattern matches only at the start - of a subject string or after any newline within the string. Otherwise + -1 is returned, indicating that the pattern matches only at the start + of a subject string or after any newline within the string. Otherwise -2 is returned. For anchored patterns, -2 is returned. PCRE_INFO_REQUIREDCHARFLAGS - Returns 1 if there is a rightmost literal data unit that must exist in + Returns 1 if there is a rightmost literal data unit that must exist in any matched string, other than at its start. The fourth argument should - point to an int variable. If there is no such value, 0 is returned. If + point to an int variable. If there is no such value, 0 is returned. If returning 1, the character value itself can be retrieved using PCRE_INFO_REQUIREDCHAR. For anchored patterns, a last literal value is recorded only if it fol- - lows something of variable length. For example, for the pattern - /^a\d+z\d+/ the returned value 1 (with "z" returned from + lows something of variable length. For example, for the pattern + /^a\d+z\d+/ the returned value 1 (with "z" returned from PCRE_INFO_REQUIREDCHAR), but for /^a\dz\d/ the returned value is 0. PCRE_INFO_REQUIREDCHAR - Return the value of the rightmost literal data unit that must exist in - any matched string, other than at its start, if such a value has been - recorded. The fourth argument should point to an uint32_t variable. If + Return the value of the rightmost literal data unit that must exist in + any matched string, other than at its start, if such a value has been + recorded. The fourth argument should point to an uint32_t variable. If there is no such value, 0 is returned. @@ -2904,21 +2905,21 @@ REFERENCE COUNTS int pcre_refcount(pcre *code, int adjust); - The pcre_refcount() function is used to maintain a reference count in + The pcre_refcount() function is used to maintain a reference count in the data block that contains a compiled pattern. It is provided for the - benefit of applications that operate in an object-oriented manner, + benefit of applications that operate in an object-oriented manner, where different parts of the application may be using the same compiled pattern, but you want to free the block when they are all done. When a pattern is compiled, the reference count field is initialized to - zero. It is changed only by calling this function, whose action is to - add the adjust value (which may be positive or negative) to it. The + zero. It is changed only by calling this function, whose action is to + add the adjust value (which may be positive or negative) to it. The yield of the function is the new value. However, the value of the count - is constrained to lie between 0 and 65535, inclusive. If the new value + is constrained to lie between 0 and 65535, inclusive. If the new value is outside these limits, it is forced to the appropriate limit value. - Except when it is zero, the reference count is not correctly preserved - if a pattern is compiled on one host and then transferred to a host + Except when it is zero, the reference count is not correctly preserved + if a pattern is compiled on one host and then transferred to a host whose byte-order is different. (This seems a highly unlikely scenario.) @@ -2928,22 +2929,22 @@ MATCHING A PATTERN: THE TRADITIONAL FUNCTION const char *subject, int length, int startoffset, int options, int *ovector, int ovecsize); - The function pcre_exec() is called to match a subject string against a - compiled pattern, which is passed in the code argument. If the pattern - was studied, the result of the study should be passed in the extra - argument. You can call pcre_exec() with the same code and extra argu- - ments as many times as you like, in order to match different subject + The function pcre_exec() is called to match a subject string against a + compiled pattern, which is passed in the code argument. If the pattern + was studied, the result of the study should be passed in the extra + argument. You can call pcre_exec() with the same code and extra argu- + ments as many times as you like, in order to match different subject strings with the same pattern. - This function is the main matching facility of the library, and it - operates in a Perl-like manner. For specialist use there is also an - alternative matching function, which is described below in the section + This function is the main matching facility of the library, and it + operates in a Perl-like manner. For specialist use there is also an + alternative matching function, which is described below in the section about the pcre_dfa_exec() function. - In most applications, the pattern will have been compiled (and option- - ally studied) in the same process that calls pcre_exec(). However, it + In most applications, the pattern will have been compiled (and option- + ally studied) in the same process that calls pcre_exec(). However, it is possible to save compiled patterns and study data, and then use them - later in different processes, possibly even on different hosts. For a + later in different processes, possibly even on different hosts. For a discussion about this, see the pcreprecompile documentation. Here is an example of a simple call to pcre_exec(): @@ -2962,10 +2963,10 @@ MATCHING A PATTERN: THE TRADITIONAL FUNCTION Extra data for pcre_exec() - If the extra argument is not NULL, it must point to a pcre_extra data - block. The pcre_study() function returns such a block (when it doesn't - return NULL), but you can also create one for yourself, and pass addi- - tional information in it. The pcre_extra block contains the following + If the extra argument is not NULL, it must point to a pcre_extra data + block. The pcre_study() function returns such a block (when it doesn't + return NULL), but you can also create one for yourself, and pass addi- + tional information in it. The pcre_extra block contains the following fields (not necessarily in this order): unsigned long int flags; @@ -2977,13 +2978,13 @@ MATCHING A PATTERN: THE TRADITIONAL FUNCTION const unsigned char *tables; unsigned char **mark; - In the 16-bit version of this structure, the mark field has type + In the 16-bit version of this structure, the mark field has type "PCRE_UCHAR16 **". - In the 32-bit version of this structure, the mark field has type + In the 32-bit version of this structure, the mark field has type "PCRE_UCHAR32 **". - The flags field is used to specify which of the other fields are set. + The flags field is used to specify which of the other fields are set. The flag bits are: PCRE_EXTRA_CALLOUT_DATA @@ -2994,112 +2995,112 @@ MATCHING A PATTERN: THE TRADITIONAL FUNCTION PCRE_EXTRA_STUDY_DATA PCRE_EXTRA_TABLES - Other flag bits should be set to zero. The study_data field and some- - times the executable_jit field are set in the pcre_extra block that is - returned by pcre_study(), together with the appropriate flag bits. You - should not set these yourself, but you may add to the block by setting + Other flag bits should be set to zero. The study_data field and some- + times the executable_jit field are set in the pcre_extra block that is + returned by pcre_study(), together with the appropriate flag bits. You + should not set these yourself, but you may add to the block by setting other fields and their corresponding flag bits. The match_limit field provides a means of preventing PCRE from using up - a vast amount of resources when running patterns that are not going to - match, but which have a very large number of possibilities in their - search trees. The classic example is a pattern that uses nested unlim- + a vast amount of resources when running patterns that are not going to + match, but which have a very large number of possibilities in their + search trees. The classic example is a pattern that uses nested unlim- ited repeats. - Internally, pcre_exec() uses a function called match(), which it calls - repeatedly (sometimes recursively). The limit set by match_limit is - imposed on the number of times this function is called during a match, - which has the effect of limiting the amount of backtracking that can + Internally, pcre_exec() uses a function called match(), which it calls + repeatedly (sometimes recursively). The limit set by match_limit is + imposed on the number of times this function is called during a match, + which has the effect of limiting the amount of backtracking that can take place. For patterns that are not anchored, the count restarts from zero for each position in the subject string. When pcre_exec() is called with a pattern that was successfully studied - with a JIT option, the way that the matching is executed is entirely + with a JIT option, the way that the matching is executed is entirely different. However, there is still the possibility of runaway matching that goes on for a very long time, and so the match_limit value is also used in this case (but in a different way) to limit how long the match- ing can continue. - The default value for the limit can be set when PCRE is built; the - default default is 10 million, which handles all but the most extreme - cases. You can override the default by suppling pcre_exec() with a - pcre_extra block in which match_limit is set, and - PCRE_EXTRA_MATCH_LIMIT is set in the flags field. If the limit is + The default value for the limit can be set when PCRE is built; the + default default is 10 million, which handles all but the most extreme + cases. You can override the default by suppling pcre_exec() with a + pcre_extra block in which match_limit is set, and + PCRE_EXTRA_MATCH_LIMIT is set in the flags field. If the limit is exceeded, pcre_exec() returns PCRE_ERROR_MATCHLIMIT. - The match_limit_recursion field is similar to match_limit, but instead + The match_limit_recursion field is similar to match_limit, but instead of limiting the total number of times that match() is called, it limits - the depth of recursion. The recursion depth is a smaller number than - the total number of calls, because not all calls to match() are recur- + the depth of recursion. The recursion depth is a smaller number than + the total number of calls, because not all calls to match() are recur- sive. This limit is of use only if it is set smaller than match_limit. - Limiting the recursion depth limits the amount of machine stack that - can be used, or, when PCRE has been compiled to use memory on the heap - instead of the stack, the amount of heap memory that can be used. This - limit is not relevant, and is ignored, when matching is done using JIT + Limiting the recursion depth limits the amount of machine stack that + can be used, or, when PCRE has been compiled to use memory on the heap + instead of the stack, the amount of heap memory that can be used. This + limit is not relevant, and is ignored, when matching is done using JIT compiled code. - The default value for match_limit_recursion can be set when PCRE is - built; the default default is the same value as the default for - match_limit. You can override the default by suppling pcre_exec() with - a pcre_extra block in which match_limit_recursion is set, and - PCRE_EXTRA_MATCH_LIMIT_RECURSION is set in the flags field. If the + The default value for match_limit_recursion can be set when PCRE is + built; the default default is the same value as the default for + match_limit. You can override the default by suppling pcre_exec() with + a pcre_extra block in which match_limit_recursion is set, and + PCRE_EXTRA_MATCH_LIMIT_RECURSION is set in the flags field. If the limit is exceeded, pcre_exec() returns PCRE_ERROR_RECURSIONLIMIT. - The callout_data field is used in conjunction with the "callout" fea- + The callout_data field is used in conjunction with the "callout" fea- ture, and is described in the pcrecallout documentation. - The tables field is used to pass a character tables pointer to - pcre_exec(); this overrides the value that is stored with the compiled - pattern. A non-NULL value is stored with the compiled pattern only if - custom tables were supplied to pcre_compile() via its tableptr argu- + The tables field is used to pass a character tables pointer to + pcre_exec(); this overrides the value that is stored with the compiled + pattern. A non-NULL value is stored with the compiled pattern only if + custom tables were supplied to pcre_compile() via its tableptr argu- ment. If NULL is passed to pcre_exec() using this mechanism, it forces - PCRE's internal tables to be used. This facility is helpful when re- - using patterns that have been saved after compiling with an external - set of tables, because the external tables might be at a different - address when pcre_exec() is called. See the pcreprecompile documenta- + PCRE's internal tables to be used. This facility is helpful when re- + using patterns that have been saved after compiling with an external + set of tables, because the external tables might be at a different + address when pcre_exec() is called. See the pcreprecompile documenta- tion for a discussion of saving compiled patterns for later use. - If PCRE_EXTRA_MARK is set in the flags field, the mark field must be - set to point to a suitable variable. If the pattern contains any back- - tracking control verbs such as (*MARK:NAME), and the execution ends up - with a name to pass back, a pointer to the name string (zero termi- - nated) is placed in the variable pointed to by the mark field. The - names are within the compiled pattern; if you wish to retain such a - name you must copy it before freeing the memory of a compiled pattern. - If there is no name to pass back, the variable pointed to by the mark - field is set to NULL. For details of the backtracking control verbs, + If PCRE_EXTRA_MARK is set in the flags field, the mark field must be + set to point to a suitable variable. If the pattern contains any back- + tracking control verbs such as (*MARK:NAME), and the execution ends up + with a name to pass back, a pointer to the name string (zero termi- + nated) is placed in the variable pointed to by the mark field. The + names are within the compiled pattern; if you wish to retain such a + name you must copy it before freeing the memory of a compiled pattern. + If there is no name to pass back, the variable pointed to by the mark + field is set to NULL. For details of the backtracking control verbs, see the section entitled "Backtracking control" in the pcrepattern doc- umentation. Option bits for pcre_exec() - The unused bits of the options argument for pcre_exec() must be zero. - The only bits that may be set are PCRE_ANCHORED, PCRE_NEWLINE_xxx, - PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, PCRE_NOTEMPTY_ATSTART, - PCRE_NO_START_OPTIMIZE, PCRE_NO_UTF8_CHECK, PCRE_PARTIAL_HARD, and + The unused bits of the options argument for pcre_exec() must be zero. + The only bits that may be set are PCRE_ANCHORED, PCRE_NEWLINE_xxx, + PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, PCRE_NOTEMPTY_ATSTART, + PCRE_NO_START_OPTIMIZE, PCRE_NO_UTF8_CHECK, PCRE_PARTIAL_HARD, and PCRE_PARTIAL_SOFT. - If the pattern was successfully studied with one of the just-in-time + If the pattern was successfully studied with one of the just-in-time (JIT) compile options, the only supported options for JIT execution are - PCRE_NO_UTF8_CHECK, PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, - PCRE_NOTEMPTY_ATSTART, PCRE_PARTIAL_HARD, and PCRE_PARTIAL_SOFT. If an - unsupported option is used, JIT execution is disabled and the normal + PCRE_NO_UTF8_CHECK, PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, + PCRE_NOTEMPTY_ATSTART, PCRE_PARTIAL_HARD, and PCRE_PARTIAL_SOFT. If an + unsupported option is used, JIT execution is disabled and the normal interpretive code in pcre_exec() is run. PCRE_ANCHORED - The PCRE_ANCHORED option limits pcre_exec() to matching at the first - matching position. If a pattern was compiled with PCRE_ANCHORED, or - turned out to be anchored by virtue of its contents, it cannot be made + The PCRE_ANCHORED option limits pcre_exec() to matching at the first + matching position. If a pattern was compiled with PCRE_ANCHORED, or + turned out to be anchored by virtue of its contents, it cannot be made unachored at matching time. PCRE_BSR_ANYCRLF PCRE_BSR_UNICODE These options (which are mutually exclusive) control what the \R escape - sequence matches. The choice is either to match only CR, LF, or CRLF, - or to match any Unicode newline sequence. These options override the + sequence matches. The choice is either to match only CR, LF, or CRLF, + or to match any Unicode newline sequence. These options override the choice that was made or defaulted when the pattern was compiled. PCRE_NEWLINE_CR @@ -3108,337 +3109,337 @@ MATCHING A PATTERN: THE TRADITIONAL FUNCTION PCRE_NEWLINE_ANYCRLF PCRE_NEWLINE_ANY - These options override the newline definition that was chosen or - defaulted when the pattern was compiled. For details, see the descrip- - tion of pcre_compile() above. During matching, the newline choice - affects the behaviour of the dot, circumflex, and dollar metacharac- - ters. It may also alter the way the match position is advanced after a + These options override the newline definition that was chosen or + defaulted when the pattern was compiled. For details, see the descrip- + tion of pcre_compile() above. During matching, the newline choice + affects the behaviour of the dot, circumflex, and dollar metacharac- + ters. It may also alter the way the match position is advanced after a match failure for an unanchored pattern. - When PCRE_NEWLINE_CRLF, PCRE_NEWLINE_ANYCRLF, or PCRE_NEWLINE_ANY is - set, and a match attempt for an unanchored pattern fails when the cur- - rent position is at a CRLF sequence, and the pattern contains no - explicit matches for CR or LF characters, the match position is + When PCRE_NEWLINE_CRLF, PCRE_NEWLINE_ANYCRLF, or PCRE_NEWLINE_ANY is + set, and a match attempt for an unanchored pattern fails when the cur- + rent position is at a CRLF sequence, and the pattern contains no + explicit matches for CR or LF characters, the match position is advanced by two characters instead of one, in other words, to after the CRLF. The above rule is a compromise that makes the most common cases work as - expected. For example, if the pattern is .+A (and the PCRE_DOTALL + expected. For example, if the pattern is .+A (and the PCRE_DOTALL option is not set), it does not match the string "\r\nA" because, after - failing at the start, it skips both the CR and the LF before retrying. - However, the pattern [\r\n]A does match that string, because it con- + failing at the start, it skips both the CR and the LF before retrying. + However, the pattern [\r\n]A does match that string, because it con- tains an explicit CR or LF reference, and so advances only by one char- acter after the first failure. An explicit match for CR of LF is either a literal appearance of one of - those characters, or one of the \r or \n escape sequences. Implicit - matches such as [^X] do not count, nor does \s (which includes CR and + those characters, or one of the \r or \n escape sequences. Implicit + matches such as [^X] do not count, nor does \s (which includes CR and LF in the characters that it matches). - Notwithstanding the above, anomalous effects may still occur when CRLF + Notwithstanding the above, anomalous effects may still occur when CRLF is a valid newline sequence and explicit \r or \n escapes appear in the pattern. PCRE_NOTBOL This option specifies that first character of the subject string is not - the beginning of a line, so the circumflex metacharacter should not - match before it. Setting this without PCRE_MULTILINE (at compile time) - causes circumflex never to match. This option affects only the behav- + the beginning of a line, so the circumflex metacharacter should not + match before it. Setting this without PCRE_MULTILINE (at compile time) + causes circumflex never to match. This option affects only the behav- iour of the circumflex metacharacter. It does not affect \A. PCRE_NOTEOL This option specifies that the end of the subject string is not the end - of a line, so the dollar metacharacter should not match it nor (except - in multiline mode) a newline immediately before it. Setting this with- + of a line, so the dollar metacharacter should not match it nor (except + in multiline mode) a newline immediately before it. Setting this with- out PCRE_MULTILINE (at compile time) causes dollar never to match. This - option affects only the behaviour of the dollar metacharacter. It does + option affects only the behaviour of the dollar metacharacter. It does not affect \Z or \z. PCRE_NOTEMPTY An empty string is not considered to be a valid match if this option is - set. If there are alternatives in the pattern, they are tried. If all - the alternatives match the empty string, the entire match fails. For + set. If there are alternatives in the pattern, they are tried. If all + the alternatives match the empty string, the entire match fails. For example, if the pattern a?b? - is applied to a string not beginning with "a" or "b", it matches an - empty string at the start of the subject. With PCRE_NOTEMPTY set, this + is applied to a string not beginning with "a" or "b", it matches an + empty string at the start of the subject. With PCRE_NOTEMPTY set, this match is not valid, so PCRE searches further into the string for occur- rences of "a" or "b". PCRE_NOTEMPTY_ATSTART - This is like PCRE_NOTEMPTY, except that an empty string match that is - not at the start of the subject is permitted. If the pattern is + This is like PCRE_NOTEMPTY, except that an empty string match that is + not at the start of the subject is permitted. If the pattern is anchored, such a match can occur only if the pattern contains \K. - Perl has no direct equivalent of PCRE_NOTEMPTY or - PCRE_NOTEMPTY_ATSTART, but it does make a special case of a pattern - match of the empty string within its split() function, and when using - the /g modifier. It is possible to emulate Perl's behaviour after + Perl has no direct equivalent of PCRE_NOTEMPTY or + PCRE_NOTEMPTY_ATSTART, but it does make a special case of a pattern + match of the empty string within its split() function, and when using + the /g modifier. It is possible to emulate Perl's behaviour after matching a null string by first trying the match again at the same off- - set with PCRE_NOTEMPTY_ATSTART and PCRE_ANCHORED, and then if that + set with PCRE_NOTEMPTY_ATSTART and PCRE_ANCHORED, and then if that fails, by advancing the starting offset (see below) and trying an ordi- - nary match again. There is some code that demonstrates how to do this - in the pcredemo sample program. In the most general case, you have to - check to see if the newline convention recognizes CRLF as a newline, - and if so, and the current character is CR followed by LF, advance the + nary match again. There is some code that demonstrates how to do this + in the pcredemo sample program. In the most general case, you have to + check to see if the newline convention recognizes CRLF as a newline, + and if so, and the current character is CR followed by LF, advance the starting offset by two characters instead of one. PCRE_NO_START_OPTIMIZE - There are a number of optimizations that pcre_exec() uses at the start - of a match, in order to speed up the process. For example, if it is + There are a number of optimizations that pcre_exec() uses at the start + of a match, in order to speed up the process. For example, if it is known that an unanchored match must start with a specific character, it - searches the subject for that character, and fails immediately if it - cannot find it, without actually running the main matching function. + searches the subject for that character, and fails immediately if it + cannot find it, without actually running the main matching function. This means that a special item such as (*COMMIT) at the start of a pat- - tern is not considered until after a suitable starting point for the - match has been found. When callouts or (*MARK) items are in use, these + tern is not considered until after a suitable starting point for the + match has been found. When callouts or (*MARK) items are in use, these "start-up" optimizations can cause them to be skipped if the pattern is - never actually used. The start-up optimizations are in effect a pre- + never actually used. The start-up optimizations are in effect a pre- scan of the subject that takes place before the pattern is run. - The PCRE_NO_START_OPTIMIZE option disables the start-up optimizations, - possibly causing performance to suffer, but ensuring that in cases - where the result is "no match", the callouts do occur, and that items + The PCRE_NO_START_OPTIMIZE option disables the start-up optimizations, + possibly causing performance to suffer, but ensuring that in cases + where the result is "no match", the callouts do occur, and that items such as (*COMMIT) and (*MARK) are considered at every possible starting - position in the subject string. If PCRE_NO_START_OPTIMIZE is set at - compile time, it cannot be unset at matching time. The use of + position in the subject string. If PCRE_NO_START_OPTIMIZE is set at + compile time, it cannot be unset at matching time. The use of PCRE_NO_START_OPTIMIZE disables JIT execution; when it is set, matching is always done using interpretively. - Setting PCRE_NO_START_OPTIMIZE can change the outcome of a matching + Setting PCRE_NO_START_OPTIMIZE can change the outcome of a matching operation. Consider the pattern (*COMMIT)ABC - When this is compiled, PCRE records the fact that a match must start - with the character "A". Suppose the subject string is "DEFABC". The - start-up optimization scans along the subject, finds "A" and runs the - first match attempt from there. The (*COMMIT) item means that the pat- - tern must match the current starting position, which in this case, it - does. However, if the same match is run with PCRE_NO_START_OPTIMIZE - set, the initial scan along the subject string does not happen. The - first match attempt is run starting from "D" and when this fails, - (*COMMIT) prevents any further matches being tried, so the overall - result is "no match". If the pattern is studied, more start-up opti- - mizations may be used. For example, a minimum length for the subject + When this is compiled, PCRE records the fact that a match must start + with the character "A". Suppose the subject string is "DEFABC". The + start-up optimization scans along the subject, finds "A" and runs the + first match attempt from there. The (*COMMIT) item means that the pat- + tern must match the current starting position, which in this case, it + does. However, if the same match is run with PCRE_NO_START_OPTIMIZE + set, the initial scan along the subject string does not happen. The + first match attempt is run starting from "D" and when this fails, + (*COMMIT) prevents any further matches being tried, so the overall + result is "no match". If the pattern is studied, more start-up opti- + mizations may be used. For example, a minimum length for the subject may be recorded. Consider the pattern (*MARK:A)(X|Y) - The minimum length for a match is one character. If the subject is - "ABC", there will be attempts to match "ABC", "BC", "C", and then - finally an empty string. If the pattern is studied, the final attempt - does not take place, because PCRE knows that the subject is too short, - and so the (*MARK) is never encountered. In this case, studying the - pattern does not affect the overall match result, which is still "no + The minimum length for a match is one character. If the subject is + "ABC", there will be attempts to match "ABC", "BC", "C", and then + finally an empty string. If the pattern is studied, the final attempt + does not take place, because PCRE knows that the subject is too short, + and so the (*MARK) is never encountered. In this case, studying the + pattern does not affect the overall match result, which is still "no match", but it does affect the auxiliary information that is returned. PCRE_NO_UTF8_CHECK When PCRE_UTF8 is set at compile time, the validity of the subject as a - UTF-8 string is automatically checked when pcre_exec() is subsequently + UTF-8 string is automatically checked when pcre_exec() is subsequently called. The entire string is checked before any other processing takes - place. The value of startoffset is also checked to ensure that it - points to the start of a UTF-8 character. There is a discussion about - the validity of UTF-8 strings in the pcreunicode page. If an invalid - sequence of bytes is found, pcre_exec() returns the error + place. The value of startoffset is also checked to ensure that it + points to the start of a UTF-8 character. There is a discussion about + the validity of UTF-8 strings in the pcreunicode page. If an invalid + sequence of bytes is found, pcre_exec() returns the error PCRE_ERROR_BADUTF8 or, if PCRE_PARTIAL_HARD is set and the problem is a truncated character at the end of the subject, PCRE_ERROR_SHORTUTF8. In - both cases, information about the precise nature of the error may also - be returned (see the descriptions of these errors in the section enti- - tled Error return values from pcre_exec() below). If startoffset con- + both cases, information about the precise nature of the error may also + be returned (see the descriptions of these errors in the section enti- + tled Error return values from pcre_exec() below). If startoffset con- tains a value that does not point to the start of a UTF-8 character (or to the end of the subject), PCRE_ERROR_BADUTF8_OFFSET is returned. - If you already know that your subject is valid, and you want to skip - these checks for performance reasons, you can set the - PCRE_NO_UTF8_CHECK option when calling pcre_exec(). You might want to - do this for the second and subsequent calls to pcre_exec() if you are - making repeated calls to find all the matches in a single subject - string. However, you should be sure that the value of startoffset - points to the start of a character (or the end of the subject). When + If you already know that your subject is valid, and you want to skip + these checks for performance reasons, you can set the + PCRE_NO_UTF8_CHECK option when calling pcre_exec(). You might want to + do this for the second and subsequent calls to pcre_exec() if you are + making repeated calls to find all the matches in a single subject + string. However, you should be sure that the value of startoffset + points to the start of a character (or the end of the subject). When PCRE_NO_UTF8_CHECK is set, the effect of passing an invalid string as a - subject or an invalid value of startoffset is undefined. Your program + subject or an invalid value of startoffset is undefined. Your program may crash. PCRE_PARTIAL_HARD PCRE_PARTIAL_SOFT - These options turn on the partial matching feature. For backwards com- - patibility, PCRE_PARTIAL is a synonym for PCRE_PARTIAL_SOFT. A partial - match occurs if the end of the subject string is reached successfully, - but there are not enough subject characters to complete the match. If + These options turn on the partial matching feature. For backwards com- + patibility, PCRE_PARTIAL is a synonym for PCRE_PARTIAL_SOFT. A partial + match occurs if the end of the subject string is reached successfully, + but there are not enough subject characters to complete the match. If this happens when PCRE_PARTIAL_SOFT (but not PCRE_PARTIAL_HARD) is set, - matching continues by testing any remaining alternatives. Only if no - complete match can be found is PCRE_ERROR_PARTIAL returned instead of - PCRE_ERROR_NOMATCH. In other words, PCRE_PARTIAL_SOFT says that the - caller is prepared to handle a partial match, but only if no complete + matching continues by testing any remaining alternatives. Only if no + complete match can be found is PCRE_ERROR_PARTIAL returned instead of + PCRE_ERROR_NOMATCH. In other words, PCRE_PARTIAL_SOFT says that the + caller is prepared to handle a partial match, but only if no complete match can be found. - If PCRE_PARTIAL_HARD is set, it overrides PCRE_PARTIAL_SOFT. In this - case, if a partial match is found, pcre_exec() immediately returns - PCRE_ERROR_PARTIAL, without considering any other alternatives. In - other words, when PCRE_PARTIAL_HARD is set, a partial match is consid- + If PCRE_PARTIAL_HARD is set, it overrides PCRE_PARTIAL_SOFT. In this + case, if a partial match is found, pcre_exec() immediately returns + PCRE_ERROR_PARTIAL, without considering any other alternatives. In + other words, when PCRE_PARTIAL_HARD is set, a partial match is consid- ered to be more important that an alternative complete match. - In both cases, the portion of the string that was inspected when the + In both cases, the portion of the string that was inspected when the partial match was found is set as the first matching string. There is a - more detailed discussion of partial and multi-segment matching, with + more detailed discussion of partial and multi-segment matching, with examples, in the pcrepartial documentation. The string to be matched by pcre_exec() - The subject string is passed to pcre_exec() as a pointer in subject, a - length in bytes in length, and a starting byte offset in startoffset. - If this is negative or greater than the length of the subject, - pcre_exec() returns PCRE_ERROR_BADOFFSET. When the starting offset is - zero, the search for a match starts at the beginning of the subject, + The subject string is passed to pcre_exec() as a pointer in subject, a + length in bytes in length, and a starting byte offset in startoffset. + If this is negative or greater than the length of the subject, + pcre_exec() returns PCRE_ERROR_BADOFFSET. When the starting offset is + zero, the search for a match starts at the beginning of the subject, and this is by far the most common case. In UTF-8 mode, the byte offset - must point to the start of a UTF-8 character (or the end of the sub- - ject). Unlike the pattern string, the subject may contain binary zero + must point to the start of a UTF-8 character (or the end of the sub- + ject). Unlike the pattern string, the subject may contain binary zero bytes. - A non-zero starting offset is useful when searching for another match - in the same subject by calling pcre_exec() again after a previous suc- - cess. Setting startoffset differs from just passing over a shortened - string and setting PCRE_NOTBOL in the case of a pattern that begins + A non-zero starting offset is useful when searching for another match + in the same subject by calling pcre_exec() again after a previous suc- + cess. Setting startoffset differs from just passing over a shortened + string and setting PCRE_NOTBOL in the case of a pattern that begins with any kind of lookbehind. For example, consider the pattern \Biss\B - which finds occurrences of "iss" in the middle of words. (\B matches - only if the current position in the subject is not a word boundary.) - When applied to the string "Mississipi" the first call to pcre_exec() - finds the first occurrence. If pcre_exec() is called again with just - the remainder of the subject, namely "issipi", it does not match, + which finds occurrences of "iss" in the middle of words. (\B matches + only if the current position in the subject is not a word boundary.) + When applied to the string "Mississipi" the first call to pcre_exec() + finds the first occurrence. If pcre_exec() is called again with just + the remainder of the subject, namely "issipi", it does not match, because \B is always false at the start of the subject, which is deemed - to be a word boundary. However, if pcre_exec() is passed the entire + to be a word boundary. However, if pcre_exec() is passed the entire string again, but with startoffset set to 4, it finds the second occur- - rence of "iss" because it is able to look behind the starting point to + rence of "iss" because it is able to look behind the starting point to discover that it is preceded by a letter. - Finding all the matches in a subject is tricky when the pattern can + Finding all the matches in a subject is tricky when the pattern can match an empty string. It is possible to emulate Perl's /g behaviour by - first trying the match again at the same offset, with the - PCRE_NOTEMPTY_ATSTART and PCRE_ANCHORED options, and then if that - fails, advancing the starting offset and trying an ordinary match + first trying the match again at the same offset, with the + PCRE_NOTEMPTY_ATSTART and PCRE_ANCHORED options, and then if that + fails, advancing the starting offset and trying an ordinary match again. There is some code that demonstrates how to do this in the pcre- demo sample program. In the most general case, you have to check to see - if the newline convention recognizes CRLF as a newline, and if so, and + if the newline convention recognizes CRLF as a newline, and if so, and the current character is CR followed by LF, advance the starting offset by two characters instead of one. - If a non-zero starting offset is passed when the pattern is anchored, + If a non-zero starting offset is passed when the pattern is anchored, one attempt to match at the given offset is made. This can only succeed - if the pattern does not require the match to be at the start of the + if the pattern does not require the match to be at the start of the subject. How pcre_exec() returns captured substrings - In general, a pattern matches a certain portion of the subject, and in - addition, further substrings from the subject may be picked out by - parts of the pattern. Following the usage in Jeffrey Friedl's book, - this is called "capturing" in what follows, and the phrase "capturing - subpattern" is used for a fragment of a pattern that picks out a sub- - string. PCRE supports several other kinds of parenthesized subpattern + In general, a pattern matches a certain portion of the subject, and in + addition, further substrings from the subject may be picked out by + parts of the pattern. Following the usage in Jeffrey Friedl's book, + this is called "capturing" in what follows, and the phrase "capturing + subpattern" is used for a fragment of a pattern that picks out a sub- + string. PCRE supports several other kinds of parenthesized subpattern that do not cause substrings to be captured. Captured substrings are returned to the caller via a vector of integers - whose address is passed in ovector. The number of elements in the vec- - tor is passed in ovecsize, which must be a non-negative number. Note: + whose address is passed in ovector. The number of elements in the vec- + tor is passed in ovecsize, which must be a non-negative number. Note: this argument is NOT the size of ovector in bytes. - The first two-thirds of the vector is used to pass back captured sub- - strings, each substring using a pair of integers. The remaining third - of the vector is used as workspace by pcre_exec() while matching cap- - turing subpatterns, and is not available for passing back information. - The number passed in ovecsize should always be a multiple of three. If + The first two-thirds of the vector is used to pass back captured sub- + strings, each substring using a pair of integers. The remaining third + of the vector is used as workspace by pcre_exec() while matching cap- + turing subpatterns, and is not available for passing back information. + The number passed in ovecsize should always be a multiple of three. If it is not, it is rounded down. - When a match is successful, information about captured substrings is - returned in pairs of integers, starting at the beginning of ovector, - and continuing up to two-thirds of its length at the most. The first - element of each pair is set to the byte offset of the first character - in a substring, and the second is set to the byte offset of the first - character after the end of a substring. Note: these values are always + When a match is successful, information about captured substrings is + returned in pairs of integers, starting at the beginning of ovector, + and continuing up to two-thirds of its length at the most. The first + element of each pair is set to the byte offset of the first character + in a substring, and the second is set to the byte offset of the first + character after the end of a substring. Note: these values are always byte offsets, even in UTF-8 mode. They are not character counts. - The first pair of integers, ovector[0] and ovector[1], identify the - portion of the subject string matched by the entire pattern. The next - pair is used for the first capturing subpattern, and so on. The value + The first pair of integers, ovector[0] and ovector[1], identify the + portion of the subject string matched by the entire pattern. The next + pair is used for the first capturing subpattern, and so on. The value returned by pcre_exec() is one more than the highest numbered pair that - has been set. For example, if two substrings have been captured, the - returned value is 3. If there are no capturing subpatterns, the return + has been set. For example, if two substrings have been captured, the + returned value is 3. If there are no capturing subpatterns, the return value from a successful match is 1, indicating that just the first pair of offsets has been set. If a capturing subpattern is matched repeatedly, it is the last portion of the string that it matched that is returned. - If the vector is too small to hold all the captured substring offsets, + If the vector is too small to hold all the captured substring offsets, it is used as far as possible (up to two-thirds of its length), and the - function returns a value of zero. If neither the actual string matched - nor any captured substrings are of interest, pcre_exec() may be called - with ovector passed as NULL and ovecsize as zero. However, if the pat- - tern contains back references and the ovector is not big enough to - remember the related substrings, PCRE has to get additional memory for - use during matching. Thus it is usually advisable to supply an ovector + function returns a value of zero. If neither the actual string matched + nor any captured substrings are of interest, pcre_exec() may be called + with ovector passed as NULL and ovecsize as zero. However, if the pat- + tern contains back references and the ovector is not big enough to + remember the related substrings, PCRE has to get additional memory for + use during matching. Thus it is usually advisable to supply an ovector of reasonable size. - There are some cases where zero is returned (indicating vector over- - flow) when in fact the vector is exactly the right size for the final + There are some cases where zero is returned (indicating vector over- + flow) when in fact the vector is exactly the right size for the final match. For example, consider the pattern (a)(?:(b)c|bd) - If a vector of 6 elements (allowing for only 1 captured substring) is + If a vector of 6 elements (allowing for only 1 captured substring) is given with subject string "abd", pcre_exec() will try to set the second captured string, thereby recording a vector overflow, before failing to - match "c" and backing up to try the second alternative. The zero - return, however, does correctly indicate that the maximum number of + match "c" and backing up to try the second alternative. The zero + return, however, does correctly indicate that the maximum number of slots (namely 2) have been filled. In similar cases where there is tem- - porary overflow, but the final number of used slots is actually less + porary overflow, but the final number of used slots is actually less than the maximum, a non-zero value is returned. The pcre_fullinfo() function can be used to find out how many capturing - subpatterns there are in a compiled pattern. The smallest size for - ovector that will allow for n captured substrings, in addition to the + subpatterns there are in a compiled pattern. The smallest size for + ovector that will allow for n captured substrings, in addition to the offsets of the substring matched by the whole pattern, is (n+1)*3. - It is possible for capturing subpattern number n+1 to match some part + It is possible for capturing subpattern number n+1 to match some part of the subject when subpattern n has not been used at all. For example, - if the string "abc" is matched against the pattern (a|(z))(bc) the + if the string "abc" is matched against the pattern (a|(z))(bc) the return from the function is 4, and subpatterns 1 and 3 are matched, but - 2 is not. When this happens, both values in the offset pairs corre- + 2 is not. When this happens, both values in the offset pairs corre- sponding to unused subpatterns are set to -1. - Offset values that correspond to unused subpatterns at the end of the - expression are also set to -1. For example, if the string "abc" is - matched against the pattern (abc)(x(yz)?)? subpatterns 2 and 3 are not - matched. The return from the function is 2, because the highest used - capturing subpattern number is 1, and the offsets for for the second - and third capturing subpatterns (assuming the vector is large enough, + Offset values that correspond to unused subpatterns at the end of the + expression are also set to -1. For example, if the string "abc" is + matched against the pattern (abc)(x(yz)?)? subpatterns 2 and 3 are not + matched. The return from the function is 2, because the highest used + capturing subpattern number is 1, and the offsets for for the second + and third capturing subpatterns (assuming the vector is large enough, of course) are set to -1. - Note: Elements in the first two-thirds of ovector that do not corre- - spond to capturing parentheses in the pattern are never changed. That - is, if a pattern contains n capturing parentheses, no more than ovec- - tor[0] to ovector[2n+1] are set by pcre_exec(). The other elements (in + Note: Elements in the first two-thirds of ovector that do not corre- + spond to capturing parentheses in the pattern are never changed. That + is, if a pattern contains n capturing parentheses, no more than ovec- + tor[0] to ovector[2n+1] are set by pcre_exec(). The other elements (in the first two-thirds) retain whatever values they previously had. - Some convenience functions are provided for extracting the captured + Some convenience functions are provided for extracting the captured substrings as separate strings. These are described below. Error return values from pcre_exec() - If pcre_exec() fails, it returns a negative number. The following are + If pcre_exec() fails, it returns a negative number. The following are defined in the header file: PCRE_ERROR_NOMATCH (-1) @@ -3447,7 +3448,7 @@ MATCHING A PATTERN: THE TRADITIONAL FUNCTION PCRE_ERROR_NULL (-2) - Either code or subject was passed as NULL, or ovector was NULL and + Either code or subject was passed as NULL, or ovector was NULL and ovecsize was not zero. PCRE_ERROR_BADOPTION (-3) @@ -3456,82 +3457,82 @@ MATCHING A PATTERN: THE TRADITIONAL FUNCTION PCRE_ERROR_BADMAGIC (-4) - PCRE stores a 4-byte "magic number" at the start of the compiled code, + PCRE stores a 4-byte "magic number" at the start of the compiled code, to catch the case when it is passed a junk pointer and to detect when a pattern that was compiled in an environment of one endianness is run in - an environment with the other endianness. This is the error that PCRE + an environment with the other endianness. This is the error that PCRE gives when the magic number is not present. PCRE_ERROR_UNKNOWN_OPCODE (-5) While running the pattern match, an unknown item was encountered in the - compiled pattern. This error could be caused by a bug in PCRE or by + compiled pattern. This error could be caused by a bug in PCRE or by overwriting of the compiled pattern. PCRE_ERROR_NOMEMORY (-6) - If a pattern contains back references, but the ovector that is passed + If a pattern contains back references, but the ovector that is passed to pcre_exec() is not big enough to remember the referenced substrings, - PCRE gets a block of memory at the start of matching to use for this - purpose. If the call via pcre_malloc() fails, this error is given. The + PCRE gets a block of memory at the start of matching to use for this + purpose. If the call via pcre_malloc() fails, this error is given. The memory is automatically freed at the end of matching. - This error is also given if pcre_stack_malloc() fails in pcre_exec(). - This can happen only when PCRE has been compiled with --disable-stack- + This error is also given if pcre_stack_malloc() fails in pcre_exec(). + This can happen only when PCRE has been compiled with --disable-stack- for-recursion. PCRE_ERROR_NOSUBSTRING (-7) - This error is used by the pcre_copy_substring(), pcre_get_substring(), + This error is used by the pcre_copy_substring(), pcre_get_substring(), and pcre_get_substring_list() functions (see below). It is never returned by pcre_exec(). PCRE_ERROR_MATCHLIMIT (-8) - The backtracking limit, as specified by the match_limit field in a - pcre_extra structure (or defaulted) was reached. See the description + The backtracking limit, as specified by the match_limit field in a + pcre_extra structure (or defaulted) was reached. See the description above. PCRE_ERROR_CALLOUT (-9) This error is never generated by pcre_exec() itself. It is provided for - use by callout functions that want to yield a distinctive error code. + use by callout functions that want to yield a distinctive error code. See the pcrecallout documentation for details. PCRE_ERROR_BADUTF8 (-10) - A string that contains an invalid UTF-8 byte sequence was passed as a - subject, and the PCRE_NO_UTF8_CHECK option was not set. If the size of - the output vector (ovecsize) is at least 2, the byte offset to the - start of the the invalid UTF-8 character is placed in the first ele- - ment, and a reason code is placed in the second element. The reason + A string that contains an invalid UTF-8 byte sequence was passed as a + subject, and the PCRE_NO_UTF8_CHECK option was not set. If the size of + the output vector (ovecsize) is at least 2, the byte offset to the + start of the the invalid UTF-8 character is placed in the first ele- + ment, and a reason code is placed in the second element. The reason codes are listed in the following section. For backward compatibility, - if PCRE_PARTIAL_HARD is set and the problem is a truncated UTF-8 char- - acter at the end of the subject (reason codes 1 to 5), + if PCRE_PARTIAL_HARD is set and the problem is a truncated UTF-8 char- + acter at the end of the subject (reason codes 1 to 5), PCRE_ERROR_SHORTUTF8 is returned instead of PCRE_ERROR_BADUTF8. PCRE_ERROR_BADUTF8_OFFSET (-11) - The UTF-8 byte sequence that was passed as a subject was checked and - found to be valid (the PCRE_NO_UTF8_CHECK option was not set), but the - value of startoffset did not point to the beginning of a UTF-8 charac- + The UTF-8 byte sequence that was passed as a subject was checked and + found to be valid (the PCRE_NO_UTF8_CHECK option was not set), but the + value of startoffset did not point to the beginning of a UTF-8 charac- ter or the end of the subject. PCRE_ERROR_PARTIAL (-12) - The subject string did not match, but it did match partially. See the + The subject string did not match, but it did match partially. See the pcrepartial documentation for details of partial matching. PCRE_ERROR_BADPARTIAL (-13) - This code is no longer in use. It was formerly returned when the - PCRE_PARTIAL option was used with a compiled pattern containing items - that were not supported for partial matching. From release 8.00 + This code is no longer in use. It was formerly returned when the + PCRE_PARTIAL option was used with a compiled pattern containing items + that were not supported for partial matching. From release 8.00 onwards, there are no restrictions on partial matching. PCRE_ERROR_INTERNAL (-14) - An unexpected internal error has occurred. This error could be caused + An unexpected internal error has occurred. This error could be caused by a bug in PCRE or by overwriting of the compiled pattern. PCRE_ERROR_BADCOUNT (-15) @@ -3541,7 +3542,7 @@ MATCHING A PATTERN: THE TRADITIONAL FUNCTION PCRE_ERROR_RECURSIONLIMIT (-21) The internal recursion limit, as specified by the match_limit_recursion - field in a pcre_extra structure (or defaulted) was reached. See the + field in a pcre_extra structure (or defaulted) was reached. See the description above. PCRE_ERROR_BADNEWLINE (-23) @@ -3555,29 +3556,29 @@ MATCHING A PATTERN: THE TRADITIONAL FUNCTION PCRE_ERROR_SHORTUTF8 (-25) - This error is returned instead of PCRE_ERROR_BADUTF8 when the subject - string ends with a truncated UTF-8 character and the PCRE_PARTIAL_HARD - option is set. Information about the failure is returned as for - PCRE_ERROR_BADUTF8. It is in fact sufficient to detect this case, but - this special error code for PCRE_PARTIAL_HARD precedes the implementa- - tion of returned information; it is retained for backwards compatibil- + This error is returned instead of PCRE_ERROR_BADUTF8 when the subject + string ends with a truncated UTF-8 character and the PCRE_PARTIAL_HARD + option is set. Information about the failure is returned as for + PCRE_ERROR_BADUTF8. It is in fact sufficient to detect this case, but + this special error code for PCRE_PARTIAL_HARD precedes the implementa- + tion of returned information; it is retained for backwards compatibil- ity. PCRE_ERROR_RECURSELOOP (-26) This error is returned when pcre_exec() detects a recursion loop within - the pattern. Specifically, it means that either the whole pattern or a - subpattern has been called recursively for the second time at the same + the pattern. Specifically, it means that either the whole pattern or a + subpattern has been called recursively for the second time at the same position in the subject string. Some simple patterns that might do this - are detected and faulted at compile time, but more complicated cases, + are detected and faulted at compile time, but more complicated cases, in particular mutual recursions between two different subpatterns, can- not be detected until run time. PCRE_ERROR_JIT_STACKLIMIT (-27) - This error is returned when a pattern that was successfully studied - using a JIT compile option is being matched, but the memory available - for the just-in-time processing stack is not large enough. See the + This error is returned when a pattern that was successfully studied + using a JIT compile option is being matched, but the memory available + for the just-in-time processing stack is not large enough. See the pcrejit documentation for more details. PCRE_ERROR_BADMODE (-28) @@ -3587,33 +3588,32 @@ MATCHING A PATTERN: THE TRADITIONAL FUNCTION PCRE_ERROR_BADENDIANNESS (-29) - This error is given if a pattern that was compiled and saved is - reloaded on a host with different endianness. The utility function + This error is given if a pattern that was compiled and saved is + reloaded on a host with different endianness. The utility function pcre_pattern_to_host_byte_order() can be used to convert such a pattern so that it runs on the new host. PCRE_ERROR_JIT_BADOPTION - This error is returned when a pattern that was successfully studied - using a JIT compile option is being matched, but the matching mode - (partial or complete match) does not correspond to any JIT compilation - mode. When the JIT fast path function is used, this error may be also - given for invalid options. See the pcrejit documentation for more + This error is returned when a pattern that was successfully studied + using a JIT compile option is being matched, but the matching mode + (partial or complete match) does not correspond to any JIT compilation + mode. When the JIT fast path function is used, this error may be also + given for invalid options. See the pcrejit documentation for more details. PCRE_ERROR_BADLENGTH (-32) - This error is given if pcre_exec() is called with a negative value for + This error is given if pcre_exec() is called with a negative value for the length argument. Error numbers -16 to -20, -22, and 30 are not used by pcre_exec(). Reason codes for invalid UTF-8 strings - This section applies only to the 8-bit library. The corresponding - information for the 16-bit library is given in the pcre16 page. The - corresponding information for the 32-bit library is given in the pcre32 - page. + This section applies only to the 8-bit library. The corresponding + information for the 16-bit and 32-bit libraries is given in the pcre16 + and pcre32 pages. When pcre_exec() returns either PCRE_ERROR_BADUTF8 or PCRE_ERROR_SHORT- UTF8, and the size of the output vector (ovecsize) is at least 2, the @@ -4101,11 +4101,11 @@ AUTHOR REVISION - Last updated: 31 October 2012 + Last updated: 08 November 2012 Copyright (c) 1997-2012 University of Cambridge. ------------------------------------------------------------------------------ - - + + PCRECALLOUT(3) PCRECALLOUT(3) @@ -4313,8 +4313,8 @@ REVISION Last updated: 24 June 2012 Copyright (c) 1997-2012 University of Cambridge. ------------------------------------------------------------------------------ - - + + PCRECOMPAT(3) PCRECOMPAT(3) @@ -4491,8 +4491,8 @@ REVISION Last updated: 25 August 2012 Copyright (c) 1997-2012 University of Cambridge. ------------------------------------------------------------------------------ - - + + PCREPATTERN(3) PCREPATTERN(3) @@ -4520,23 +4520,26 @@ PCRE REGULAR EXPRESSION DETAILS The original operation of PCRE was on strings of one-byte characters. However, there is now also support for UTF-8 strings in the original library, an extra library that supports 16-bit and UTF-16 character - strings, and an extra library that supports 32-bit and UTF-32 character + strings, and a third library that supports 32-bit and UTF-32 character strings. To use these features, PCRE must be built to include appropri- ate support. When using UTF strings you must either call the compiling - function with the PCRE_UTF8, PCRE_UTF16 or PCRE_UTF32 option, or the + function with the PCRE_UTF8, PCRE_UTF16, or PCRE_UTF32 option, or the pattern must start with one of these special sequences: (*UTF8) (*UTF16) (*UTF32) + (*UTF) - Starting a pattern with such a sequence is equivalent to setting the - relevant option. This feature is not Perl-compatible. How setting a UTF - mode affects pattern matching is mentioned in several places below. - There is also a summary of features in the pcreunicode page. + (*UTF) is a generic sequence that can be used with any of the + libraries. Starting a pattern with such a sequence is equivalent to + setting the relevant option. This feature is not Perl-compatible. How + setting a UTF mode affects pattern matching is mentioned in several + places below. There is also a summary of features in the pcreunicode + page. Another special sequence that may appear at the start of a pattern or - in combination with (*UTF8) or (*UTF16) or (*UTF32) is: + in combination with (*UTF8), (*UTF16), (*UTF32) or (*UTF) is: (*UCP) @@ -4600,42 +4603,43 @@ NEWLINE CONVENTIONS and that they must be in upper case. If more than one of them is present, the last one is used. - The newline convention affects the interpretation of the dot metachar- - acter when PCRE_DOTALL is not set, and also the behaviour of \N. How- - ever, it does not affect what the \R escape sequence matches. By - default, this is any Unicode newline sequence, for Perl compatibility. - However, this can be changed; see the description of \R in the section - entitled "Newline sequences" below. A change of \R setting can be com- - bined with a change of newline convention. + The newline convention affects where the circumflex and dollar asser- + tions are true. It also affects the interpretation of the dot metachar- + acter when PCRE_DOTALL is not set, and the behaviour of \N. However, it + does not affect what the \R escape sequence matches. By default, this + is any Unicode newline sequence, for Perl compatibility. However, this + can be changed; see the description of \R in the section entitled "New- + line sequences" below. A change of \R setting can be combined with a + change of newline convention. CHARACTERS AND METACHARACTERS - A regular expression is a pattern that is matched against a subject - string from left to right. Most characters stand for themselves in a - pattern, and match the corresponding characters in the subject. As a + A regular expression is a pattern that is matched against a subject + string from left to right. Most characters stand for themselves in a + pattern, and match the corresponding characters in the subject. As a trivial example, the pattern The quick brown fox matches a portion of a subject string that is identical to itself. When - caseless matching is specified (the PCRE_CASELESS option), letters are - matched independently of case. In a UTF mode, PCRE always understands - the concept of case for characters whose values are less than 128, so - caseless matching is always possible. For characters with higher val- - ues, the concept of case is supported if PCRE is compiled with Unicode - property support, but not otherwise. If you want to use caseless - matching for characters 128 and above, you must ensure that PCRE is + caseless matching is specified (the PCRE_CASELESS option), letters are + matched independently of case. In a UTF mode, PCRE always understands + the concept of case for characters whose values are less than 128, so + caseless matching is always possible. For characters with higher val- + ues, the concept of case is supported if PCRE is compiled with Unicode + property support, but not otherwise. If you want to use caseless + matching for characters 128 and above, you must ensure that PCRE is compiled with Unicode property support as well as with UTF support. - The power of regular expressions comes from the ability to include - alternatives and repetitions in the pattern. These are encoded in the + The power of regular expressions comes from the ability to include + alternatives and repetitions in the pattern. These are encoded in the pattern by the use of metacharacters, which do not stand for themselves but instead are interpreted in some special way. - There are two different sets of metacharacters: those that are recog- - nized anywhere in the pattern except within square brackets, and those - that are recognized within square brackets. Outside square brackets, + There are two different sets of metacharacters: those that are recog- + nized anywhere in the pattern except within square brackets, and those + that are recognized within square brackets. Outside square brackets, the metacharacters are as follows: \ general escape character with several uses @@ -4654,7 +4658,7 @@ CHARACTERS AND METACHARACTERS also "possessive quantifier" { start min/max quantifier - Part of a pattern that is in square brackets is called a "character + Part of a pattern that is in square brackets is called a "character class". In a character class the only metacharacters are: \ general escape character @@ -4671,30 +4675,30 @@ BACKSLASH The backslash character has several uses. Firstly, if it is followed by a character that is not a number or a letter, it takes away any special - meaning that character may have. This use of backslash as an escape + meaning that character may have. This use of backslash as an escape character applies both inside and outside character classes. - For example, if you want to match a * character, you write \* in the - pattern. This escaping action applies whether or not the following - character would otherwise be interpreted as a metacharacter, so it is - always safe to precede a non-alphanumeric with backslash to specify - that it stands for itself. In particular, if you want to match a back- + For example, if you want to match a * character, you write \* in the + pattern. This escaping action applies whether or not the following + character would otherwise be interpreted as a metacharacter, so it is + always safe to precede a non-alphanumeric with backslash to specify + that it stands for itself. In particular, if you want to match a back- slash, you write \\. - In a UTF mode, only ASCII numbers and letters have any special meaning - after a backslash. All other characters (in particular, those whose + In a UTF mode, only ASCII numbers and letters have any special meaning + after a backslash. All other characters (in particular, those whose codepoints are greater than 127) are treated as literals. - If a pattern is compiled with the PCRE_EXTENDED option, white space in - the pattern (other than in a character class) and characters between a + If a pattern is compiled with the PCRE_EXTENDED option, white space in + the pattern (other than in a character class) and characters between a # outside a character class and the next newline are ignored. An escap- - ing backslash can be used to include a white space or # character as + ing backslash can be used to include a white space or # character as part of the pattern. - If you want to remove the special meaning from a sequence of charac- - ters, you can do so by putting them between \Q and \E. This is differ- - ent from Perl in that $ and @ are handled as literals in \Q...\E - sequences in PCRE, whereas in Perl, $ and @ cause variable interpola- + If you want to remove the special meaning from a sequence of charac- + ters, you can do so by putting them between \Q and \E. This is differ- + ent from Perl in that $ and @ are handled as literals in \Q...\E + sequences in PCRE, whereas in Perl, $ and @ cause variable interpola- tion. Note the following examples: Pattern PCRE matches Perl matches @@ -4704,20 +4708,20 @@ BACKSLASH \Qabc\$xyz\E abc\$xyz abc\$xyz \Qabc\E\$\Qxyz\E abc$xyz abc$xyz - The \Q...\E sequence is recognized both inside and outside character - classes. An isolated \E that is not preceded by \Q is ignored. If \Q - is not followed by \E later in the pattern, the literal interpretation - continues to the end of the pattern (that is, \E is assumed at the - end). If the isolated \Q is inside a character class, this causes an + The \Q...\E sequence is recognized both inside and outside character + classes. An isolated \E that is not preceded by \Q is ignored. If \Q + is not followed by \E later in the pattern, the literal interpretation + continues to the end of the pattern (that is, \E is assumed at the + end). If the isolated \Q is inside a character class, this causes an error, because the character class is not terminated. Non-printing characters A second use of backslash provides a way of encoding non-printing char- - acters in patterns in a visible manner. There is no restriction on the - appearance of non-printing characters, apart from the binary zero that - terminates a pattern, but when a pattern is being prepared by text - editing, it is often easier to use one of the following escape + acters in patterns in a visible manner. There is no restriction on the + appearance of non-printing characters, apart from the binary zero that + terminates a pattern, but when a pattern is being prepared by text + editing, it is often easier to use one of the following escape sequences than the binary character it represents: \a alarm, that is, the BEL character (hex 07) @@ -4732,25 +4736,25 @@ BACKSLASH \x{hhh..} character with hex code hhh.. (non-JavaScript mode) \uhhhh character with hex code hhhh (JavaScript mode only) - The precise effect of \cx on ASCII characters is as follows: if x is a - lower case letter, it is converted to upper case. Then bit 6 of the + The precise effect of \cx on ASCII characters is as follows: if x is a + lower case letter, it is converted to upper case. Then bit 6 of the character (hex 40) is inverted. Thus \cA to \cZ become hex 01 to hex 1A - (A is 41, Z is 5A), but \c{ becomes hex 3B ({ is 7B), and \c; becomes - hex 7B (; is 3B). If the data item (byte or 16-bit value) following \c - has a value greater than 127, a compile-time error occurs. This locks + (A is 41, Z is 5A), but \c{ becomes hex 3B ({ is 7B), and \c; becomes + hex 7B (; is 3B). If the data item (byte or 16-bit value) following \c + has a value greater than 127, a compile-time error occurs. This locks out non-ASCII characters in all modes. - The \c facility was designed for use with ASCII characters, but with - the extension to Unicode it is even less useful than it once was. It - is, however, recognized when PCRE is compiled in EBCDIC mode, where - data items are always bytes. In this mode, all values are valid after - \c. If the next character is a lower case letter, it is converted to - upper case. Then the 0xc0 bits of the byte are inverted. Thus \cA - becomes hex 01, as in ASCII (A is C1), but because the EBCDIC letters - are disjoint, \cZ becomes hex 29 (Z is E9), and other characters also + The \c facility was designed for use with ASCII characters, but with + the extension to Unicode it is even less useful than it once was. It + is, however, recognized when PCRE is compiled in EBCDIC mode, where + data items are always bytes. In this mode, all values are valid after + \c. If the next character is a lower case letter, it is converted to + upper case. Then the 0xc0 bits of the byte are inverted. Thus \cA + becomes hex 01, as in ASCII (A is C1), but because the EBCDIC letters + are disjoint, \cZ becomes hex 29 (Z is E9), and other characters also generate different values. - By default, after \x, from zero to two hexadecimal digits are read + By default, after \x, from zero to two hexadecimal digits are read (letters can be in upper or lower case). Any number of hexadecimal dig- its may appear between \x{ and }, but the character code is constrained as follows: @@ -4762,48 +4766,48 @@ BACKSLASH 32-bit non-UTF mode less than 0x80000000 32-bit UTF-32 mode less than 0x10ffff and a valid codepoint - Invalid Unicode codepoints are the range 0xd800 to 0xdfff (the so- + Invalid Unicode codepoints are the range 0xd800 to 0xdfff (the so- called "surrogate" codepoints), and 0xffef. - If characters other than hexadecimal digits appear between \x{ and }, + If characters other than hexadecimal digits appear between \x{ and }, or if there is no terminating }, this form of escape is not recognized. - Instead, the initial \x will be interpreted as a basic hexadecimal - escape, with no following digits, giving a character whose value is + Instead, the initial \x will be interpreted as a basic hexadecimal + escape, with no following digits, giving a character whose value is zero. - If the PCRE_JAVASCRIPT_COMPAT option is set, the interpretation of \x - is as just described only when it is followed by two hexadecimal dig- - its. Otherwise, it matches a literal "x" character. In JavaScript + If the PCRE_JAVASCRIPT_COMPAT option is set, the interpretation of \x + is as just described only when it is followed by two hexadecimal dig- + its. Otherwise, it matches a literal "x" character. In JavaScript mode, support for code points greater than 256 is provided by \u, which - must be followed by four hexadecimal digits; otherwise it matches a - literal "u" character. Character codes specified by \u in JavaScript - mode are constrained in the same was as those specified by \x in non- + must be followed by four hexadecimal digits; otherwise it matches a + literal "u" character. Character codes specified by \u in JavaScript + mode are constrained in the same was as those specified by \x in non- JavaScript mode. Characters whose value is less than 256 can be defined by either of the - two syntaxes for \x (or by \u in JavaScript mode). There is no differ- + two syntaxes for \x (or by \u in JavaScript mode). There is no differ- ence in the way they are handled. For example, \xdc is exactly the same as \x{dc} (or \u00dc in JavaScript mode). - After \0 up to two further octal digits are read. If there are fewer - than two digits, just those that are present are used. Thus the + After \0 up to two further octal digits are read. If there are fewer + than two digits, just those that are present are used. Thus the sequence \0\x\07 specifies two binary zeros followed by a BEL character - (code value 7). Make sure you supply two digits after the initial zero + (code value 7). Make sure you supply two digits after the initial zero if the pattern character that follows is itself an octal digit. The handling of a backslash followed by a digit other than 0 is compli- cated. Outside a character class, PCRE reads it and any following dig- - its as a decimal number. If the number is less than 10, or if there + its as a decimal number. If the number is less than 10, or if there have been at least that many previous capturing left parentheses in the - expression, the entire sequence is taken as a back reference. A - description of how this works is given later, following the discussion + expression, the entire sequence is taken as a back reference. A + description of how this works is given later, following the discussion of parenthesized subpatterns. - Inside a character class, or if the decimal number is greater than 9 - and there have not been that many capturing subpatterns, PCRE re-reads + Inside a character class, or if the decimal number is greater than 9 + and there have not been that many capturing subpatterns, PCRE re-reads up to three octal digits following the backslash, and uses them to gen- erate a data character. Any subsequent digits stand for themselves. The - value of the character is constrained in the same way as characters + value of the character is constrained in the same way as characters specified in hexadecimal. For example: \040 is another way of writing an ASCII space @@ -4821,42 +4825,42 @@ BACKSLASH \81 is either a back reference, or a binary zero followed by the two characters "8" and "1" - Note that octal values of 100 or greater must not be introduced by a + Note that octal values of 100 or greater must not be introduced by a leading zero, because no more than three octal digits are ever read. All the sequences that define a single character value can be used both - inside and outside character classes. In addition, inside a character + inside and outside character classes. In addition, inside a character class, \b is interpreted as the backspace character (hex 08). - \N is not allowed in a character class. \B, \R, and \X are not special - inside a character class. Like other unrecognized escape sequences, - they are treated as the literal characters "B", "R", and "X" by - default, but cause an error if the PCRE_EXTRA option is set. Outside a + \N is not allowed in a character class. \B, \R, and \X are not special + inside a character class. Like other unrecognized escape sequences, + they are treated as the literal characters "B", "R", and "X" by + default, but cause an error if the PCRE_EXTRA option is set. Outside a character class, these sequences have different meanings. Unsupported escape sequences - In Perl, the sequences \l, \L, \u, and \U are recognized by its string - handler and used to modify the case of following characters. By - default, PCRE does not support these escape sequences. However, if the - PCRE_JAVASCRIPT_COMPAT option is set, \U matches a "U" character, and + In Perl, the sequences \l, \L, \u, and \U are recognized by its string + handler and used to modify the case of following characters. By + default, PCRE does not support these escape sequences. However, if the + PCRE_JAVASCRIPT_COMPAT option is set, \U matches a "U" character, and \u can be used to define a character by code point, as described in the previous section. Absolute and relative back references - The sequence \g followed by an unsigned or a negative number, option- - ally enclosed in braces, is an absolute or relative back reference. A + The sequence \g followed by an unsigned or a negative number, option- + ally enclosed in braces, is an absolute or relative back reference. A named back reference can be coded as \g{name}. Back references are dis- cussed later, following the discussion of parenthesized subpatterns. Absolute and relative subroutine calls - For compatibility with Oniguruma, the non-Perl syntax \g followed by a + For compatibility with Oniguruma, the non-Perl syntax \g followed by a name or a number enclosed either in angle brackets or single quotes, is - an alternative syntax for referencing a subpattern as a "subroutine". - Details are discussed later. Note that \g{...} (Perl syntax) and - \g<...> (Oniguruma syntax) are not synonymous. The former is a back + an alternative syntax for referencing a subpattern as a "subroutine". + Details are discussed later. Note that \g{...} (Perl syntax) and + \g<...> (Oniguruma syntax) are not synonymous. The former is a back reference; the latter is a subroutine call. Generic character types @@ -4875,55 +4879,55 @@ BACKSLASH \W any "non-word" character There is also the single sequence \N, which matches a non-newline char- - acter. This is the same as the "." metacharacter when PCRE_DOTALL is - not set. Perl also uses \N to match characters by name; PCRE does not + acter. This is the same as the "." metacharacter when PCRE_DOTALL is + not set. Perl also uses \N to match characters by name; PCRE does not support this. - Each pair of lower and upper case escape sequences partitions the com- - plete set of characters into two disjoint sets. Any given character - matches one, and only one, of each pair. The sequences can appear both - inside and outside character classes. They each match one character of - the appropriate type. If the current matching point is at the end of - the subject string, all of them fail, because there is no character to + Each pair of lower and upper case escape sequences partitions the com- + plete set of characters into two disjoint sets. Any given character + matches one, and only one, of each pair. The sequences can appear both + inside and outside character classes. They each match one character of + the appropriate type. If the current matching point is at the end of + the subject string, all of them fail, because there is no character to match. - For compatibility with Perl, \s does not match the VT character (code - 11). This makes it different from the the POSIX "space" class. The \s - characters are HT (9), LF (10), FF (12), CR (13), and space (32). If + For compatibility with Perl, \s does not match the VT character (code + 11). This makes it different from the the POSIX "space" class. The \s + characters are HT (9), LF (10), FF (12), CR (13), and space (32). If "use locale;" is included in a Perl script, \s may match the VT charac- ter. In PCRE, it never does. - A "word" character is an underscore or any character that is a letter - or digit. By default, the definition of letters and digits is con- - trolled by PCRE's low-valued character tables, and may vary if locale- - specific matching is taking place (see "Locale support" in the pcreapi - page). For example, in a French locale such as "fr_FR" in Unix-like - systems, or "french" in Windows, some character codes greater than 128 - are used for accented letters, and these are then matched by \w. The + A "word" character is an underscore or any character that is a letter + or digit. By default, the definition of letters and digits is con- + trolled by PCRE's low-valued character tables, and may vary if locale- + specific matching is taking place (see "Locale support" in the pcreapi + page). For example, in a French locale such as "fr_FR" in Unix-like + systems, or "french" in Windows, some character codes greater than 128 + are used for accented letters, and these are then matched by \w. The use of locales with Unicode is discouraged. - By default, in a UTF mode, characters with values greater than 128 - never match \d, \s, or \w, and always match \D, \S, and \W. These - sequences retain their original meanings from before UTF support was - available, mainly for efficiency reasons. However, if PCRE is compiled - with Unicode property support, and the PCRE_UCP option is set, the be- - haviour is changed so that Unicode properties are used to determine + By default, in a UTF mode, characters with values greater than 128 + never match \d, \s, or \w, and always match \D, \S, and \W. These + sequences retain their original meanings from before UTF support was + available, mainly for efficiency reasons. However, if PCRE is compiled + with Unicode property support, and the PCRE_UCP option is set, the be- + haviour is changed so that Unicode properties are used to determine character types, as follows: \d any character that \p{Nd} matches (decimal digit) \s any character that \p{Z} matches, plus HT, LF, FF, CR \w any character that \p{L} or \p{N} matches, plus underscore - The upper case escapes match the inverse sets of characters. Note that - \d matches only decimal digits, whereas \w matches any Unicode digit, - as well as any Unicode letter, and underscore. Note also that PCRE_UCP - affects \b, and \B because they are defined in terms of \w and \W. + The upper case escapes match the inverse sets of characters. Note that + \d matches only decimal digits, whereas \w matches any Unicode digit, + as well as any Unicode letter, and underscore. Note also that PCRE_UCP + affects \b, and \B because they are defined in terms of \w and \W. Matching these sequences is noticeably slower when PCRE_UCP is set. - The sequences \h, \H, \v, and \V are features that were added to Perl - at release 5.10. In contrast to the other sequences, which match only - ASCII characters by default, these always match certain high-valued - codepoints, whether or not PCRE_UCP is set. The horizontal space char- + The sequences \h, \H, \v, and \V are features that were added to Perl + at release 5.10. In contrast to the other sequences, which match only + ASCII characters by default, these always match certain high-valued + codepoints, whether or not PCRE_UCP is set. The horizontal space char- acters are: U+0009 Horizontal tab (HT) @@ -4961,106 +4965,106 @@ BACKSLASH Newline sequences - Outside a character class, by default, the escape sequence \R matches - any Unicode newline sequence. In 8-bit non-UTF-8 mode \R is equivalent + Outside a character class, by default, the escape sequence \R matches + any Unicode newline sequence. In 8-bit non-UTF-8 mode \R is equivalent to the following: (?>\r\n|\n|\x0b|\f|\r|\x85) - This is an example of an "atomic group", details of which are given + This is an example of an "atomic group", details of which are given below. This particular group matches either the two-character sequence - CR followed by LF, or one of the single characters LF (linefeed, - U+000A), VT (vertical tab, U+000B), FF (form feed, U+000C), CR (car- - riage return, U+000D), or NEL (next line, U+0085). The two-character + CR followed by LF, or one of the single characters LF (linefeed, + U+000A), VT (vertical tab, U+000B), FF (form feed, U+000C), CR (car- + riage return, U+000D), or NEL (next line, U+0085). The two-character sequence is treated as a single unit that cannot be split. - In other modes, two additional characters whose codepoints are greater + In other modes, two additional characters whose codepoints are greater than 255 are added: LS (line separator, U+2028) and PS (paragraph sepa- - rator, U+2029). Unicode character property support is not needed for + rator, U+2029). Unicode character property support is not needed for these characters to be recognized. It is possible to restrict \R to match only CR, LF, or CRLF (instead of - the complete set of Unicode line endings) by setting the option + the complete set of Unicode line endings) by setting the option PCRE_BSR_ANYCRLF either at compile time or when the pattern is matched. (BSR is an abbrevation for "backslash R".) This can be made the default - when PCRE is built; if this is the case, the other behaviour can be - requested via the PCRE_BSR_UNICODE option. It is also possible to - specify these settings by starting a pattern string with one of the + when PCRE is built; if this is the case, the other behaviour can be + requested via the PCRE_BSR_UNICODE option. It is also possible to + specify these settings by starting a pattern string with one of the following sequences: (*BSR_ANYCRLF) CR, LF, or CRLF only (*BSR_UNICODE) any Unicode newline sequence These override the default and the options given to the compiling func- - tion, but they can themselves be overridden by options given to a - matching function. Note that these special settings, which are not - Perl-compatible, are recognized only at the very start of a pattern, - and that they must be in upper case. If more than one of them is - present, the last one is used. They can be combined with a change of + tion, but they can themselves be overridden by options given to a + matching function. Note that these special settings, which are not + Perl-compatible, are recognized only at the very start of a pattern, + and that they must be in upper case. If more than one of them is + present, the last one is used. They can be combined with a change of newline convention; for example, a pattern can start with: (*ANY)(*BSR_ANYCRLF) - They can also be combined with the (*UTF8), (*UTF16), (*UTF32) or - (*UCP) special sequences. Inside a character class, \R is treated as an - unrecognized escape sequence, and so matches the letter "R" by default, - but causes an error if PCRE_EXTRA is set. + They can also be combined with the (*UTF8), (*UTF16), (*UTF32), (*UTF) + or (*UCP) special sequences. Inside a character class, \R is treated as + an unrecognized escape sequence, and so matches the letter "R" by + default, but causes an error if PCRE_EXTRA is set. Unicode character properties When PCRE is built with Unicode character property support, three addi- - tional escape sequences that match characters with specific properties - are available. When in 8-bit non-UTF-8 mode, these sequences are of - course limited to testing characters whose codepoints are less than + tional escape sequences that match characters with specific properties + are available. When in 8-bit non-UTF-8 mode, these sequences are of + course limited to testing characters whose codepoints are less than 256, but they do work in this mode. The extra escape sequences are: \p{xx} a character with the xx property \P{xx} a character without the xx property \X a Unicode extended grapheme cluster - The property names represented by xx above are limited to the Unicode + The property names represented by xx above are limited to the Unicode script names, the general category properties, "Any", which matches any - character (including newline), and some special PCRE properties - (described in the next section). Other Perl properties such as "InMu- - sicalSymbols" are not currently supported by PCRE. Note that \P{Any} + character (including newline), and some special PCRE properties + (described in the next section). Other Perl properties such as "InMu- + sicalSymbols" are not currently supported by PCRE. Note that \P{Any} does not match any characters, so always causes a match failure. Sets of Unicode characters are defined as belonging to certain scripts. - A character from one of these sets can be matched using a script name. + A character from one of these sets can be matched using a script name. For example: \p{Greek} \P{Han} - Those that are not part of an identified script are lumped together as + Those that are not part of an identified script are lumped together as "Common". The current list of scripts is: - Arabic, Armenian, Avestan, Balinese, Bamum, Batak, Bengali, Bopomofo, - Brahmi, Braille, Buginese, Buhid, Canadian_Aboriginal, Carian, Chakma, - Cham, Cherokee, Common, Coptic, Cuneiform, Cypriot, Cyrillic, Deseret, - Devanagari, Egyptian_Hieroglyphs, Ethiopic, Georgian, Glagolitic, - Gothic, Greek, Gujarati, Gurmukhi, Han, Hangul, Hanunoo, Hebrew, Hira- - gana, Imperial_Aramaic, Inherited, Inscriptional_Pahlavi, Inscrip- - tional_Parthian, Javanese, Kaithi, Kannada, Katakana, Kayah_Li, - Kharoshthi, Khmer, Lao, Latin, Lepcha, Limbu, Linear_B, Lisu, Lycian, + Arabic, Armenian, Avestan, Balinese, Bamum, Batak, Bengali, Bopomofo, + Brahmi, Braille, Buginese, Buhid, Canadian_Aboriginal, Carian, Chakma, + Cham, Cherokee, Common, Coptic, Cuneiform, Cypriot, Cyrillic, Deseret, + Devanagari, Egyptian_Hieroglyphs, Ethiopic, Georgian, Glagolitic, + Gothic, Greek, Gujarati, Gurmukhi, Han, Hangul, Hanunoo, Hebrew, Hira- + gana, Imperial_Aramaic, Inherited, Inscriptional_Pahlavi, Inscrip- + tional_Parthian, Javanese, Kaithi, Kannada, Katakana, Kayah_Li, + Kharoshthi, Khmer, Lao, Latin, Lepcha, Limbu, Linear_B, Lisu, Lycian, Lydian, Malayalam, Mandaic, Meetei_Mayek, Meroitic_Cursive, - Meroitic_Hieroglyphs, Miao, Mongolian, Myanmar, New_Tai_Lue, Nko, - Ogham, Old_Italic, Old_Persian, Old_South_Arabian, Old_Turkic, - Ol_Chiki, Oriya, Osmanya, Phags_Pa, Phoenician, Rejang, Runic, Samari- - tan, Saurashtra, Sharada, Shavian, Sinhala, Sora_Sompeng, Sundanese, - Syloti_Nagri, Syriac, Tagalog, Tagbanwa, Tai_Le, Tai_Tham, Tai_Viet, - Takri, Tamil, Telugu, Thaana, Thai, Tibetan, Tifinagh, Ugaritic, Vai, + Meroitic_Hieroglyphs, Miao, Mongolian, Myanmar, New_Tai_Lue, Nko, + Ogham, Old_Italic, Old_Persian, Old_South_Arabian, Old_Turkic, + Ol_Chiki, Oriya, Osmanya, Phags_Pa, Phoenician, Rejang, Runic, Samari- + tan, Saurashtra, Sharada, Shavian, Sinhala, Sora_Sompeng, Sundanese, + Syloti_Nagri, Syriac, Tagalog, Tagbanwa, Tai_Le, Tai_Tham, Tai_Viet, + Takri, Tamil, Telugu, Thaana, Thai, Tibetan, Tifinagh, Ugaritic, Vai, Yi. Each character has exactly one Unicode general category property, spec- - ified by a two-letter abbreviation. For compatibility with Perl, nega- - tion can be specified by including a circumflex between the opening - brace and the property name. For example, \p{^Lu} is the same as + ified by a two-letter abbreviation. For compatibility with Perl, nega- + tion can be specified by including a circumflex between the opening + brace and the property name. For example, \p{^Lu} is the same as \P{Lu}. If only one letter is specified with \p or \P, it includes all the gen- - eral category properties that start with that letter. In this case, in - the absence of negation, the curly brackets in the escape sequence are + eral category properties that start with that letter. In this case, in + the absence of negation, the curly brackets in the escape sequence are optional; these two examples have the same effect: \p{L} @@ -5112,72 +5116,72 @@ BACKSLASH Zp Paragraph separator Zs Space separator - The special property L& is also supported: it matches a character that - has the Lu, Ll, or Lt property, in other words, a letter that is not + The special property L& is also supported: it matches a character that + has the Lu, Ll, or Lt property, in other words, a letter that is not classified as a modifier or "other". - The Cs (Surrogate) property applies only to characters in the range - U+D800 to U+DFFF. Such characters are not valid in Unicode strings and - so cannot be tested by PCRE, unless UTF validity checking has been + The Cs (Surrogate) property applies only to characters in the range + U+D800 to U+DFFF. Such characters are not valid in Unicode strings and + so cannot be tested by PCRE, unless UTF validity checking has been turned off (see the discussion of PCRE_NO_UTF8_CHECK, - PCRE_NO_UTF16_CHECK and PCRE_NO_UTF32_CHECK in the pcreapi page). Perl + PCRE_NO_UTF16_CHECK and PCRE_NO_UTF32_CHECK in the pcreapi page). Perl does not support the Cs property. - The long synonyms for property names that Perl supports (such as - \p{Letter}) are not supported by PCRE, nor is it permitted to prefix + The long synonyms for property names that Perl supports (such as + \p{Letter}) are not supported by PCRE, nor is it permitted to prefix any of these properties with "Is". No character that is in the Unicode table has the Cn (unassigned) prop- erty. Instead, this property is assumed for any code point that is not in the Unicode table. - Specifying caseless matching does not affect these escape sequences. + Specifying caseless matching does not affect these escape sequences. For example, \p{Lu} always matches only upper case letters. - Matching characters by Unicode property is not fast, because PCRE has - to do a multistage table lookup in order to find a character's prop- + Matching characters by Unicode property is not fast, because PCRE has + to do a multistage table lookup in order to find a character's prop- erty. That is why the traditional escape sequences such as \d and \w do not use Unicode properties in PCRE by default, though you can make them - do so by setting the PCRE_UCP option or by starting the pattern with + do so by setting the PCRE_UCP option or by starting the pattern with (*UCP). Extended grapheme clusters - The \X escape matches any number of Unicode characters that form an + The \X escape matches any number of Unicode characters that form an "extended grapheme cluster", and treats the sequence as an atomic group - (see below). Up to and including release 8.31, PCRE matched an ear- + (see below). Up to and including release 8.31, PCRE matched an ear- lier, simpler definition that was equivalent to (?>\PM\pM*) - That is, it matched a character without the "mark" property, followed - by zero or more characters with the "mark" property. Characters with - the "mark" property are typically non-spacing accents that affect the + That is, it matched a character without the "mark" property, followed + by zero or more characters with the "mark" property. Characters with + the "mark" property are typically non-spacing accents that affect the preceding character. - This simple definition was extended in Unicode to include more compli- - cated kinds of composite character by giving each character a grapheme - breaking property, and creating rules that use these properties to - define the boundaries of extended grapheme clusters. In releases of + This simple definition was extended in Unicode to include more compli- + cated kinds of composite character by giving each character a grapheme + breaking property, and creating rules that use these properties to + define the boundaries of extended grapheme clusters. In releases of PCRE later than 8.31, \X matches one of these clusters. - \X always matches at least one character. Then it decides whether to + \X always matches at least one character. Then it decides whether to add additional characters according to the following rules for ending a cluster: 1. End at the end of the subject string. - 2. Do not end between CR and LF; otherwise end after any control char- + 2. Do not end between CR and LF; otherwise end after any control char- acter. - 3. Do not break Hangul (a Korean script) syllable sequences. Hangul - characters are of five types: L, V, T, LV, and LVT. An L character may - be followed by an L, V, LV, or LVT character; an LV or V character may + 3. Do not break Hangul (a Korean script) syllable sequences. Hangul + characters are of five types: L, V, T, LV, and LVT. An L character may + be followed by an L, V, LV, or LVT character; an LV or V character may be followed by a V or T character; an LVT or T character may be follwed only by a T character. - 4. Do not end before extending characters or spacing marks. Characters - with the "mark" property always have the "extend" grapheme breaking + 4. Do not end before extending characters or spacing marks. Characters + with the "mark" property always have the "extend" grapheme breaking property. 5. Do not end after prepend characters. @@ -5186,10 +5190,10 @@ BACKSLASH PCRE's additional properties - As well as the standard Unicode properties described above, PCRE sup- - ports four more that make it possible to convert traditional escape - sequences such as \w and \s and POSIX character classes to use Unicode - properties. PCRE uses these non-standard, non-Perl properties inter- + As well as the standard Unicode properties described above, PCRE sup- + ports four more that make it possible to convert traditional escape + sequences such as \w and \s and POSIX character classes to use Unicode + properties. PCRE uses these non-standard, non-Perl properties inter- nally when PCRE_UCP is set. They are: Xan Any alphanumeric character @@ -5197,40 +5201,40 @@ BACKSLASH Xsp Any Perl space character Xwd Any Perl "word" character - Xan matches characters that have either the L (letter) or the N (num- - ber) property. Xps matches the characters tab, linefeed, vertical tab, - form feed, or carriage return, and any other character that has the Z + Xan matches characters that have either the L (letter) or the N (num- + ber) property. Xps matches the characters tab, linefeed, vertical tab, + form feed, or carriage return, and any other character that has the Z (separator) property. Xsp is the same as Xps, except that vertical tab is excluded. Xwd matches the same characters as Xan, plus underscore. Resetting the match start - The escape sequence \K causes any previously matched characters not to + The escape sequence \K causes any previously matched characters not to be included in the final matched sequence. For example, the pattern: foo\Kbar - matches "foobar", but reports that it has matched "bar". This feature - is similar to a lookbehind assertion (described below). However, in - this case, the part of the subject before the real match does not have - to be of fixed length, as lookbehind assertions do. The use of \K does - not interfere with the setting of captured substrings. For example, + matches "foobar", but reports that it has matched "bar". This feature + is similar to a lookbehind assertion (described below). However, in + this case, the part of the subject before the real match does not have + to be of fixed length, as lookbehind assertions do. The use of \K does + not interfere with the setting of captured substrings. For example, when the pattern (foo)\Kbar matches "foobar", the first substring is still set to "foo". - Perl documents that the use of \K within assertions is "not well - defined". In PCRE, \K is acted upon when it occurs inside positive + Perl documents that the use of \K within assertions is "not well + defined". In PCRE, \K is acted upon when it occurs inside positive assertions, but is ignored in negative assertions. Simple assertions - The final use of backslash is for certain simple assertions. An asser- - tion specifies a condition that has to be met at a particular point in - a match, without consuming any characters from the subject string. The - use of subpatterns for more complicated assertions is described below. + The final use of backslash is for certain simple assertions. An asser- + tion specifies a condition that has to be met at a particular point in + a match, without consuming any characters from the subject string. The + use of subpatterns for more complicated assertions is described below. The backslashed assertions are: \b matches at a word boundary @@ -5241,76 +5245,81 @@ BACKSLASH \z matches only at the end of the subject \G matches at the first matching position in the subject - Inside a character class, \b has a different meaning; it matches the - backspace character. If any other of these assertions appears in a - character class, by default it matches the corresponding literal char- + Inside a character class, \b has a different meaning; it matches the + backspace character. If any other of these assertions appears in a + character class, by default it matches the corresponding literal char- acter (for example, \B matches the letter B). However, if the - PCRE_EXTRA option is set, an "invalid escape sequence" error is gener- + PCRE_EXTRA option is set, an "invalid escape sequence" error is gener- ated instead. - A word boundary is a position in the subject string where the current - character and the previous character do not both match \w or \W (i.e. - one matches \w and the other matches \W), or the start or end of the - string if the first or last character matches \w, respectively. In a - UTF mode, the meanings of \w and \W can be changed by setting the - PCRE_UCP option. When this is done, it also affects \b and \B. Neither - PCRE nor Perl has a separate "start of word" or "end of word" metase- - quence. However, whatever follows \b normally determines which it is. + A word boundary is a position in the subject string where the current + character and the previous character do not both match \w or \W (i.e. + one matches \w and the other matches \W), or the start or end of the + string if the first or last character matches \w, respectively. In a + UTF mode, the meanings of \w and \W can be changed by setting the + PCRE_UCP option. When this is done, it also affects \b and \B. Neither + PCRE nor Perl has a separate "start of word" or "end of word" metase- + quence. However, whatever follows \b normally determines which it is. For example, the fragment \ba matches "a" at the start of a word. - The \A, \Z, and \z assertions differ from the traditional circumflex + The \A, \Z, and \z assertions differ from the traditional circumflex and dollar (described in the next section) in that they only ever match - at the very start and end of the subject string, whatever options are - set. Thus, they are independent of multiline mode. These three asser- + at the very start and end of the subject string, whatever options are + set. Thus, they are independent of multiline mode. These three asser- tions are not affected by the PCRE_NOTBOL or PCRE_NOTEOL options, which - affect only the behaviour of the circumflex and dollar metacharacters. - However, if the startoffset argument of pcre_exec() is non-zero, indi- + affect only the behaviour of the circumflex and dollar metacharacters. + However, if the startoffset argument of pcre_exec() is non-zero, indi- cating that matching is to start at a point other than the beginning of - the subject, \A can never match. The difference between \Z and \z is + the subject, \A can never match. The difference between \Z and \z is that \Z matches before a newline at the end of the string as well as at the very end, whereas \z matches only at the end. - The \G assertion is true only when the current matching position is at - the start point of the match, as specified by the startoffset argument - of pcre_exec(). It differs from \A when the value of startoffset is - non-zero. By calling pcre_exec() multiple times with appropriate argu- + The \G assertion is true only when the current matching position is at + the start point of the match, as specified by the startoffset argument + of pcre_exec(). It differs from \A when the value of startoffset is + non-zero. By calling pcre_exec() multiple times with appropriate argu- ments, you can mimic Perl's /g option, and it is in this kind of imple- mentation where \G can be useful. - Note, however, that PCRE's interpretation of \G, as the start of the + Note, however, that PCRE's interpretation of \G, as the start of the current match, is subtly different from Perl's, which defines it as the - end of the previous match. In Perl, these can be different when the - previously matched string was empty. Because PCRE does just one match + end of the previous match. In Perl, these can be different when the + previously matched string was empty. Because PCRE does just one match at a time, it cannot reproduce this behaviour. - If all the alternatives of a pattern begin with \G, the expression is + If all the alternatives of a pattern begin with \G, the expression is anchored to the starting match position, and the "anchored" flag is set in the compiled regular expression. CIRCUMFLEX AND DOLLAR + The circumflex and dollar metacharacters are zero-width assertions. + That is, they test for a particular condition being true without con- + suming any characters from the subject string. + Outside a character class, in the default matching mode, the circumflex - character is an assertion that is true only if the current matching - point is at the start of the subject string. If the startoffset argu- - ment of pcre_exec() is non-zero, circumflex can never match if the - PCRE_MULTILINE option is unset. Inside a character class, circumflex + character is an assertion that is true only if the current matching + point is at the start of the subject string. If the startoffset argu- + ment of pcre_exec() is non-zero, circumflex can never match if the + PCRE_MULTILINE option is unset. Inside a character class, circumflex has an entirely different meaning (see below). - Circumflex need not be the first character of the pattern if a number - of alternatives are involved, but it should be the first thing in each - alternative in which it appears if the pattern is ever to match that - branch. If all possible alternatives start with a circumflex, that is, - if the pattern is constrained to match only at the start of the sub- - ject, it is said to be an "anchored" pattern. (There are also other + Circumflex need not be the first character of the pattern if a number + of alternatives are involved, but it should be the first thing in each + alternative in which it appears if the pattern is ever to match that + branch. If all possible alternatives start with a circumflex, that is, + if the pattern is constrained to match only at the start of the sub- + ject, it is said to be an "anchored" pattern. (There are also other constructs that can cause a pattern to be anchored.) - A dollar character is an assertion that is true only if the current - matching point is at the end of the subject string, or immediately - before a newline at the end of the string (by default). Dollar need not - be the last character of the pattern if a number of alternatives are - involved, but it should be the last item in any branch in which it - appears. Dollar has no special meaning in a character class. + The dollar character is an assertion that is true only if the current + matching point is at the end of the subject string, or immediately + before a newline at the end of the string (by default). Note, however, + that it does not actually match the newline. Dollar need not be the + last character of the pattern if a number of alternatives are involved, + but it should be the last item in any branch in which it appears. Dol- + lar has no special meaning in a character class. The meaning of dollar can be changed so that it matches only at the very end of the string, by setting the PCRE_DOLLAR_ENDONLY option at @@ -5640,10 +5649,11 @@ INTERNAL OPTION SETTING some cases the pattern can contain special leading sequences such as (*CRLF) to override what the application has set or what has been defaulted. Details are given in the section entitled "Newline - sequences" above. There are also the (*UTF8), (*UTF16),(*UTF32) and + sequences" above. There are also the (*UTF8), (*UTF16),(*UTF32), and (*UCP) leading sequences that can be used to set UTF and Unicode prop- erty modes; they are equivalent to setting the PCRE_UTF8, PCRE_UTF16, - PCRE_UTF32 and the PCRE_UCP options, respectively. + PCRE_UTF32 and the PCRE_UCP options, respectively. The (*UTF) sequence + is a generic version that can be used with any of the libraries. SUBPATTERNS @@ -5655,18 +5665,18 @@ SUBPATTERNS cat(aract|erpillar|) - matches "cataract", "caterpillar", or "cat". Without the parentheses, + matches "cataract", "caterpillar", or "cat". Without the parentheses, it would match "cataract", "erpillar" or an empty string. - 2. It sets up the subpattern as a capturing subpattern. This means - that, when the whole pattern matches, that portion of the subject + 2. It sets up the subpattern as a capturing subpattern. This means + that, when the whole pattern matches, that portion of the subject string that matched the subpattern is passed back to the caller via the - ovector argument of the matching function. (This applies only to the - traditional matching functions; the DFA matching functions do not sup- + ovector argument of the matching function. (This applies only to the + traditional matching functions; the DFA matching functions do not sup- port capturing.) Opening parentheses are counted from left to right (starting from 1) to - obtain numbers for the capturing subpatterns. For example, if the + obtain numbers for the capturing subpatterns. For example, if the string "the red king" is matched against the pattern the ((red|white) (king|queen)) @@ -5674,12 +5684,12 @@ SUBPATTERNS the captured substrings are "red king", "red", and "king", and are num- bered 1, 2, and 3, respectively. - The fact that plain parentheses fulfil two functions is not always - helpful. There are often times when a grouping subpattern is required - without a capturing requirement. If an opening parenthesis is followed - by a question mark and a colon, the subpattern does not do any captur- - ing, and is not counted when computing the number of any subsequent - capturing subpatterns. For example, if the string "the white queen" is + The fact that plain parentheses fulfil two functions is not always + helpful. There are often times when a grouping subpattern is required + without a capturing requirement. If an opening parenthesis is followed + by a question mark and a colon, the subpattern does not do any captur- + ing, and is not counted when computing the number of any subsequent + capturing subpatterns. For example, if the string "the white queen" is matched against the pattern the ((?:red|white) (king|queen)) @@ -5687,37 +5697,37 @@ SUBPATTERNS the captured substrings are "white queen" and "queen", and are numbered 1 and 2. The maximum number of capturing subpatterns is 65535. - As a convenient shorthand, if any option settings are required at the - start of a non-capturing subpattern, the option letters may appear + As a convenient shorthand, if any option settings are required at the + start of a non-capturing subpattern, the option letters may appear between the "?" and the ":". Thus the two patterns (?i:saturday|sunday) (?:(?i)saturday|sunday) match exactly the same set of strings. Because alternative branches are - tried from left to right, and options are not reset until the end of - the subpattern is reached, an option setting in one branch does affect - subsequent branches, so the above patterns match "SUNDAY" as well as + tried from left to right, and options are not reset until the end of + the subpattern is reached, an option setting in one branch does affect + subsequent branches, so the above patterns match "SUNDAY" as well as "Saturday". DUPLICATE SUBPATTERN NUMBERS Perl 5.10 introduced a feature whereby each alternative in a subpattern - uses the same numbers for its capturing parentheses. Such a subpattern - starts with (?| and is itself a non-capturing subpattern. For example, + uses the same numbers for its capturing parentheses. Such a subpattern + starts with (?| and is itself a non-capturing subpattern. For example, consider this pattern: (?|(Sat)ur|(Sun))day - Because the two alternatives are inside a (?| group, both sets of cap- - turing parentheses are numbered one. Thus, when the pattern matches, - you can look at captured substring number one, whichever alternative - matched. This construct is useful when you want to capture part, but + Because the two alternatives are inside a (?| group, both sets of cap- + turing parentheses are numbered one. Thus, when the pattern matches, + you can look at captured substring number one, whichever alternative + matched. This construct is useful when you want to capture part, but not all, of one of a number of alternatives. Inside a (?| group, paren- - theses are numbered as usual, but the number is reset at the start of - each branch. The numbers of any capturing parentheses that follow the - subpattern start after the highest number used in any branch. The fol- + theses are numbered as usual, but the number is reset at the start of + each branch. The numbers of any capturing parentheses that follow the + subpattern start after the highest number used in any branch. The fol- lowing example is taken from the Perl documentation. The numbers under- neath show in which buffer the captured content will be stored. @@ -5725,58 +5735,58 @@ DUPLICATE SUBPATTERN NUMBERS / ( a ) (?| x ( y ) z | (p (q) r) | (t) u (v) ) ( z ) /x # 1 2 2 3 2 3 4 - A back reference to a numbered subpattern uses the most recent value - that is set for that number by any subpattern. The following pattern + A back reference to a numbered subpattern uses the most recent value + that is set for that number by any subpattern. The following pattern matches "abcabc" or "defdef": /(?|(abc)|(def))\1/ - In contrast, a subroutine call to a numbered subpattern always refers - to the first one in the pattern with the given number. The following + In contrast, a subroutine call to a numbered subpattern always refers + to the first one in the pattern with the given number. The following pattern matches "abcabc" or "defabc": /(?|(abc)|(def))(?1)/ - If a condition test for a subpattern's having matched refers to a non- - unique number, the test is true if any of the subpatterns of that num- + If a condition test for a subpattern's having matched refers to a non- + unique number, the test is true if any of the subpatterns of that num- ber have matched. - An alternative approach to using this "branch reset" feature is to use + An alternative approach to using this "branch reset" feature is to use duplicate named subpatterns, as described in the next section. NAMED SUBPATTERNS - Identifying capturing parentheses by number is simple, but it can be - very hard to keep track of the numbers in complicated regular expres- - sions. Furthermore, if an expression is modified, the numbers may - change. To help with this difficulty, PCRE supports the naming of sub- + Identifying capturing parentheses by number is simple, but it can be + very hard to keep track of the numbers in complicated regular expres- + sions. Furthermore, if an expression is modified, the numbers may + change. To help with this difficulty, PCRE supports the naming of sub- patterns. This feature was not added to Perl until release 5.10. Python - had the feature earlier, and PCRE introduced it at release 4.0, using - the Python syntax. PCRE now supports both the Perl and the Python syn- - tax. Perl allows identically numbered subpatterns to have different + had the feature earlier, and PCRE introduced it at release 4.0, using + the Python syntax. PCRE now supports both the Perl and the Python syn- + tax. Perl allows identically numbered subpatterns to have different names, but PCRE does not. - In PCRE, a subpattern can be named in one of three ways: (?<name>...) - or (?'name'...) as in Perl, or (?P<name>...) as in Python. References - to capturing parentheses from other parts of the pattern, such as back - references, recursion, and conditions, can be made by name as well as + In PCRE, a subpattern can be named in one of three ways: (?<name>...) + or (?'name'...) as in Perl, or (?P<name>...) as in Python. References + to capturing parentheses from other parts of the pattern, such as back + references, recursion, and conditions, can be made by name as well as by number. - Names consist of up to 32 alphanumeric characters and underscores. - Named capturing parentheses are still allocated numbers as well as - names, exactly as if the names were not present. The PCRE API provides + Names consist of up to 32 alphanumeric characters and underscores. + Named capturing parentheses are still allocated numbers as well as + names, exactly as if the names were not present. The PCRE API provides function calls for extracting the name-to-number translation table from a compiled pattern. There is also a convenience function for extracting a captured substring by name. - By default, a name must be unique within a pattern, but it is possible + By default, a name must be unique within a pattern, but it is possible to relax this constraint by setting the PCRE_DUPNAMES option at compile - time. (Duplicate names are also always permitted for subpatterns with - the same number, set up as described in the previous section.) Dupli- - cate names can be useful for patterns where only one instance of the - named parentheses can match. Suppose you want to match the name of a - weekday, either as a 3-letter abbreviation or as the full name, and in + time. (Duplicate names are also always permitted for subpatterns with + the same number, set up as described in the previous section.) Dupli- + cate names can be useful for patterns where only one instance of the + named parentheses can match. Suppose you want to match the name of a + weekday, either as a 3-letter abbreviation or as the full name, and in both cases you want to extract the abbreviation. This pattern (ignoring the line breaks) does the job: @@ -5786,38 +5796,38 @@ NAMED SUBPATTERNS (?<DN>Thu)(?:rsday)?| (?<DN>Sat)(?:urday)? - There are five capturing substrings, but only one is ever set after a + There are five capturing substrings, but only one is ever set after a match. (An alternative way of solving this problem is to use a "branch reset" subpattern, as described in the previous section.) - The convenience function for extracting the data by name returns the - substring for the first (and in this example, the only) subpattern of - that name that matched. This saves searching to find which numbered + The convenience function for extracting the data by name returns the + substring for the first (and in this example, the only) subpattern of + that name that matched. This saves searching to find which numbered subpattern it was. - If you make a back reference to a non-unique named subpattern from - elsewhere in the pattern, the one that corresponds to the first occur- + If you make a back reference to a non-unique named subpattern from + elsewhere in the pattern, the one that corresponds to the first occur- rence of the name is used. In the absence of duplicate numbers (see the - previous section) this is the one with the lowest number. If you use a - named reference in a condition test (see the section about conditions - below), either to check whether a subpattern has matched, or to check - for recursion, all subpatterns with the same name are tested. If the - condition is true for any one of them, the overall condition is true. + previous section) this is the one with the lowest number. If you use a + named reference in a condition test (see the section about conditions + below), either to check whether a subpattern has matched, or to check + for recursion, all subpatterns with the same name are tested. If the + condition is true for any one of them, the overall condition is true. This is the same behaviour as testing by number. For further details of the interfaces for handling named subpatterns, see the pcreapi documen- tation. Warning: You cannot use different names to distinguish between two sub- - patterns with the same number because PCRE uses only the numbers when + patterns with the same number because PCRE uses only the numbers when matching. For this reason, an error is given at compile time if differ- - ent names are given to subpatterns with the same number. However, you - can give the same name to subpatterns with the same number, even when + ent names are given to subpatterns with the same number. However, you + can give the same name to subpatterns with the same number, even when PCRE_DUPNAMES is not set. REPETITION - Repetition is specified by quantifiers, which can follow any of the + Repetition is specified by quantifiers, which can follow any of the following items: a literal data character @@ -5831,17 +5841,17 @@ REPETITION a parenthesized subpattern (including assertions) a subroutine call to a subpattern (recursive or otherwise) - The general repetition quantifier specifies a minimum and maximum num- - ber of permitted matches, by giving the two numbers in curly brackets - (braces), separated by a comma. The numbers must be less than 65536, + The general repetition quantifier specifies a minimum and maximum num- + ber of permitted matches, by giving the two numbers in curly brackets + (braces), separated by a comma. The numbers must be less than 65536, and the first must be less than or equal to the second. For example: z{2,4} - matches "zz", "zzz", or "zzzz". A closing brace on its own is not a - special character. If the second number is omitted, but the comma is - present, there is no upper limit; if the second number and the comma - are both omitted, the quantifier specifies an exact number of required + matches "zz", "zzz", or "zzzz". A closing brace on its own is not a + special character. If the second number is omitted, but the comma is + present, there is no upper limit; if the second number and the comma + are both omitted, the quantifier specifies an exact number of required matches. Thus [aeiou]{3,} @@ -5850,50 +5860,50 @@ REPETITION \d{8} - matches exactly 8 digits. An opening curly bracket that appears in a - position where a quantifier is not allowed, or one that does not match - the syntax of a quantifier, is taken as a literal character. For exam- + matches exactly 8 digits. An opening curly bracket that appears in a + position where a quantifier is not allowed, or one that does not match + the syntax of a quantifier, is taken as a literal character. For exam- ple, {,6} is not a quantifier, but a literal string of four characters. In UTF modes, quantifiers apply to characters rather than to individual - data units. Thus, for example, \x{100}{2} matches two characters, each + data units. Thus, for example, \x{100}{2} matches two characters, each of which is represented by a two-byte sequence in a UTF-8 string. Simi- - larly, \X{3} matches three Unicode extended grapheme clusters, each of - which may be several data units long (and they may be of different + larly, \X{3} matches three Unicode extended grapheme clusters, each of + which may be several data units long (and they may be of different lengths). The quantifier {0} is permitted, causing the expression to behave as if the previous item and the quantifier were not present. This may be use- - ful for subpatterns that are referenced as subroutines from elsewhere + ful for subpatterns that are referenced as subroutines from elsewhere in the pattern (but see also the section entitled "Defining subpatterns - for use by reference only" below). Items other than subpatterns that + for use by reference only" below). Items other than subpatterns that have a {0} quantifier are omitted from the compiled pattern. - For convenience, the three most common quantifiers have single-charac- + For convenience, the three most common quantifiers have single-charac- ter abbreviations: * is equivalent to {0,} + is equivalent to {1,} ? is equivalent to {0,1} - It is possible to construct infinite loops by following a subpattern + It is possible to construct infinite loops by following a subpattern that can match no characters with a quantifier that has no upper limit, for example: (a?)* Earlier versions of Perl and PCRE used to give an error at compile time - for such patterns. However, because there are cases where this can be - useful, such patterns are now accepted, but if any repetition of the - subpattern does in fact match no characters, the loop is forcibly bro- + for such patterns. However, because there are cases where this can be + useful, such patterns are now accepted, but if any repetition of the + subpattern does in fact match no characters, the loop is forcibly bro- ken. - By default, the quantifiers are "greedy", that is, they match as much - as possible (up to the maximum number of permitted times), without - causing the rest of the pattern to fail. The classic example of where + By default, the quantifiers are "greedy", that is, they match as much + as possible (up to the maximum number of permitted times), without + causing the rest of the pattern to fail. The classic example of where this gives problems is in trying to match comments in C programs. These - appear between /* and */ and within the comment, individual * and / - characters may appear. An attempt to match C comments by applying the + appear between /* and */ and within the comment, individual * and / + characters may appear. An attempt to match C comments by applying the pattern /\*.*\*/ @@ -5902,19 +5912,19 @@ REPETITION /* first comment */ not comment /* second comment */ - fails, because it matches the entire string owing to the greediness of + fails, because it matches the entire string owing to the greediness of the .* item. - However, if a quantifier is followed by a question mark, it ceases to + However, if a quantifier is followed by a question mark, it ceases to be greedy, and instead matches the minimum number of times possible, so the pattern /\*.*?\*/ - does the right thing with the C comments. The meaning of the various - quantifiers is not otherwise changed, just the preferred number of - matches. Do not confuse this use of question mark with its use as a - quantifier in its own right. Because it has two uses, it can sometimes + does the right thing with the C comments. The meaning of the various + quantifiers is not otherwise changed, just the preferred number of + matches. Do not confuse this use of question mark with its use as a + quantifier in its own right. Because it has two uses, it can sometimes appear doubled, as in \d??\d @@ -5922,45 +5932,45 @@ REPETITION which matches one digit by preference, but can match two if that is the only way the rest of the pattern matches. - If the PCRE_UNGREEDY option is set (an option that is not available in - Perl), the quantifiers are not greedy by default, but individual ones - can be made greedy by following them with a question mark. In other + If the PCRE_UNGREEDY option is set (an option that is not available in + Perl), the quantifiers are not greedy by default, but individual ones + can be made greedy by following them with a question mark. In other words, it inverts the default behaviour. - When a parenthesized subpattern is quantified with a minimum repeat - count that is greater than 1 or with a limited maximum, more memory is - required for the compiled pattern, in proportion to the size of the + When a parenthesized subpattern is quantified with a minimum repeat + count that is greater than 1 or with a limited maximum, more memory is + required for the compiled pattern, in proportion to the size of the minimum or maximum. If a pattern starts with .* or .{0,} and the PCRE_DOTALL option (equiv- - alent to Perl's /s) is set, thus allowing the dot to match newlines, - the pattern is implicitly anchored, because whatever follows will be - tried against every character position in the subject string, so there - is no point in retrying the overall match at any position after the - first. PCRE normally treats such a pattern as though it were preceded + alent to Perl's /s) is set, thus allowing the dot to match newlines, + the pattern is implicitly anchored, because whatever follows will be + tried against every character position in the subject string, so there + is no point in retrying the overall match at any position after the + first. PCRE normally treats such a pattern as though it were preceded by \A. - In cases where it is known that the subject string contains no new- - lines, it is worth setting PCRE_DOTALL in order to obtain this opti- + In cases where it is known that the subject string contains no new- + lines, it is worth setting PCRE_DOTALL in order to obtain this opti- mization, or alternatively using ^ to indicate anchoring explicitly. - However, there are some cases where the optimization cannot be used. + However, there are some cases where the optimization cannot be used. When .* is inside capturing parentheses that are the subject of a back reference elsewhere in the pattern, a match at the start may fail where a later one succeeds. Consider, for example: (.*)abc\1 - If the subject is "xyz123abc123" the match point is the fourth charac- + If the subject is "xyz123abc123" the match point is the fourth charac- ter. For this reason, such a pattern is not implicitly anchored. - Another case where implicit anchoring is not applied is when the lead- - ing .* is inside an atomic group. Once again, a match at the start may + Another case where implicit anchoring is not applied is when the lead- + ing .* is inside an atomic group. Once again, a match at the start may fail where a later one succeeds. Consider this pattern: (?>.*?a)b - It matches "ab" in the subject "aab". The use of the backtracking con- + It matches "ab" in the subject "aab". The use of the backtracking con- trol verbs (*PRUNE) and (*SKIP) also disable this optimization. When a capturing subpattern is repeated, the value captured is the sub- @@ -5969,8 +5979,8 @@ REPETITION (tweedle[dume]{3}\s*)+ has matched "tweedledum tweedledee" the value of the captured substring - is "tweedledee". However, if there are nested capturing subpatterns, - the corresponding captured values may have been set in previous itera- + is "tweedledee". However, if there are nested capturing subpatterns, + the corresponding captured values may have been set in previous itera- tions. For example, after /(a|(b))+/ @@ -5980,53 +5990,53 @@ REPETITION ATOMIC GROUPING AND POSSESSIVE QUANTIFIERS - With both maximizing ("greedy") and minimizing ("ungreedy" or "lazy") - repetition, failure of what follows normally causes the repeated item - to be re-evaluated to see if a different number of repeats allows the - rest of the pattern to match. Sometimes it is useful to prevent this, - either to change the nature of the match, or to cause it fail earlier - than it otherwise might, when the author of the pattern knows there is + With both maximizing ("greedy") and minimizing ("ungreedy" or "lazy") + repetition, failure of what follows normally causes the repeated item + to be re-evaluated to see if a different number of repeats allows the + rest of the pattern to match. Sometimes it is useful to prevent this, + either to change the nature of the match, or to cause it fail earlier + than it otherwise might, when the author of the pattern knows there is no point in carrying on. - Consider, for example, the pattern \d+foo when applied to the subject + Consider, for example, the pattern \d+foo when applied to the subject line 123456bar After matching all 6 digits and then failing to match "foo", the normal - action of the matcher is to try again with only 5 digits matching the - \d+ item, and then with 4, and so on, before ultimately failing. - "Atomic grouping" (a term taken from Jeffrey Friedl's book) provides - the means for specifying that once a subpattern has matched, it is not + action of the matcher is to try again with only 5 digits matching the + \d+ item, and then with 4, and so on, before ultimately failing. + "Atomic grouping" (a term taken from Jeffrey Friedl's book) provides + the means for specifying that once a subpattern has matched, it is not to be re-evaluated in this way. - If we use atomic grouping for the previous example, the matcher gives - up immediately on failing to match "foo" the first time. The notation + If we use atomic grouping for the previous example, the matcher gives + up immediately on failing to match "foo" the first time. The notation is a kind of special parenthesis, starting with (?> as in this example: (?>\d+)foo - This kind of parenthesis "locks up" the part of the pattern it con- - tains once it has matched, and a failure further into the pattern is - prevented from backtracking into it. Backtracking past it to previous + This kind of parenthesis "locks up" the part of the pattern it con- + tains once it has matched, and a failure further into the pattern is + prevented from backtracking into it. Backtracking past it to previous items, however, works as normal. - An alternative description is that a subpattern of this type matches - the string of characters that an identical standalone pattern would + An alternative description is that a subpattern of this type matches + the string of characters that an identical standalone pattern would match, if anchored at the current point in the subject string. Atomic grouping subpatterns are not capturing subpatterns. Simple cases such as the above example can be thought of as a maximizing repeat that - must swallow everything it can. So, while both \d+ and \d+? are pre- - pared to adjust the number of digits they match in order to make the + must swallow everything it can. So, while both \d+ and \d+? are pre- + pared to adjust the number of digits they match in order to make the rest of the pattern match, (?>\d+) can only match an entire sequence of digits. - Atomic groups in general can of course contain arbitrarily complicated - subpatterns, and can be nested. However, when the subpattern for an + Atomic groups in general can of course contain arbitrarily complicated + subpatterns, and can be nested. However, when the subpattern for an atomic group is just a single repeated item, as in the example above, a - simpler notation, called a "possessive quantifier" can be used. This - consists of an additional + character following a quantifier. Using + simpler notation, called a "possessive quantifier" can be used. This + consists of an additional + character following a quantifier. Using this notation, the previous example can be rewritten as \d++foo @@ -6036,45 +6046,45 @@ ATOMIC GROUPING AND POSSESSIVE QUANTIFIERS (abc|xyz){2,3}+ - Possessive quantifiers are always greedy; the setting of the + Possessive quantifiers are always greedy; the setting of the PCRE_UNGREEDY option is ignored. They are a convenient notation for the - simpler forms of atomic group. However, there is no difference in the - meaning of a possessive quantifier and the equivalent atomic group, - though there may be a performance difference; possessive quantifiers + simpler forms of atomic group. However, there is no difference in the + meaning of a possessive quantifier and the equivalent atomic group, + though there may be a performance difference; possessive quantifiers should be slightly faster. - The possessive quantifier syntax is an extension to the Perl 5.8 syn- - tax. Jeffrey Friedl originated the idea (and the name) in the first + The possessive quantifier syntax is an extension to the Perl 5.8 syn- + tax. Jeffrey Friedl originated the idea (and the name) in the first edition of his book. Mike McCloskey liked it, so implemented it when he - built Sun's Java package, and PCRE copied it from there. It ultimately + built Sun's Java package, and PCRE copied it from there. It ultimately found its way into Perl at release 5.10. PCRE has an optimization that automatically "possessifies" certain sim- - ple pattern constructs. For example, the sequence A+B is treated as - A++B because there is no point in backtracking into a sequence of A's + ple pattern constructs. For example, the sequence A+B is treated as + A++B because there is no point in backtracking into a sequence of A's when B must follow. - When a pattern contains an unlimited repeat inside a subpattern that - can itself be repeated an unlimited number of times, the use of an - atomic group is the only way to avoid some failing matches taking a + When a pattern contains an unlimited repeat inside a subpattern that + can itself be repeated an unlimited number of times, the use of an + atomic group is the only way to avoid some failing matches taking a very long time indeed. The pattern (\D+|<\d+>)*[!?] - matches an unlimited number of substrings that either consist of non- - digits, or digits enclosed in <>, followed by either ! or ?. When it + matches an unlimited number of substrings that either consist of non- + digits, or digits enclosed in <>, followed by either ! or ?. When it matches, it runs quickly. However, if it is applied to aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa - it takes a long time before reporting failure. This is because the - string can be divided between the internal \D+ repeat and the external - * repeat in a large number of ways, and all have to be tried. (The - example uses [!?] rather than a single character at the end, because - both PCRE and Perl have an optimization that allows for fast failure - when a single character is used. They remember the last single charac- - ter that is required for a match, and fail early if it is not present - in the string.) If the pattern is changed so that it uses an atomic + it takes a long time before reporting failure. This is because the + string can be divided between the internal \D+ repeat and the external + * repeat in a large number of ways, and all have to be tried. (The + example uses [!?] rather than a single character at the end, because + both PCRE and Perl have an optimization that allows for fast failure + when a single character is used. They remember the last single charac- + ter that is required for a match, and fail early if it is not present + in the string.) If the pattern is changed so that it uses an atomic group, like this: ((?>\D+)|<\d+>)*[!?] @@ -6086,28 +6096,28 @@ BACK REFERENCES Outside a character class, a backslash followed by a digit greater than 0 (and possibly further digits) is a back reference to a capturing sub- - pattern earlier (that is, to its left) in the pattern, provided there + pattern earlier (that is, to its left) in the pattern, provided there have been that many previous capturing left parentheses. However, if the decimal number following the backslash is less than 10, - it is always taken as a back reference, and causes an error only if - there are not that many capturing left parentheses in the entire pat- - tern. In other words, the parentheses that are referenced need not be - to the left of the reference for numbers less than 10. A "forward back - reference" of this type can make sense when a repetition is involved - and the subpattern to the right has participated in an earlier itera- + it is always taken as a back reference, and causes an error only if + there are not that many capturing left parentheses in the entire pat- + tern. In other words, the parentheses that are referenced need not be + to the left of the reference for numbers less than 10. A "forward back + reference" of this type can make sense when a repetition is involved + and the subpattern to the right has participated in an earlier itera- tion. - It is not possible to have a numerical "forward back reference" to a - subpattern whose number is 10 or more using this syntax because a - sequence such as \50 is interpreted as a character defined in octal. + It is not possible to have a numerical "forward back reference" to a + subpattern whose number is 10 or more using this syntax because a + sequence such as \50 is interpreted as a character defined in octal. See the subsection entitled "Non-printing characters" above for further - details of the handling of digits following a backslash. There is no - such problem when named parentheses are used. A back reference to any + details of the handling of digits following a backslash. There is no + such problem when named parentheses are used. A back reference to any subpattern is possible using named parentheses (see below). - Another way of avoiding the ambiguity inherent in the use of digits - following a backslash is to use the \g escape sequence. This escape + Another way of avoiding the ambiguity inherent in the use of digits + following a backslash is to use the \g escape sequence. This escape must be followed by an unsigned number or a negative number, optionally enclosed in braces. These examples are all identical: @@ -6115,7 +6125,7 @@ BACK REFERENCES (ring), \g1 (ring), \g{1} - An unsigned number specifies an absolute reference without the ambigu- + An unsigned number specifies an absolute reference without the ambigu- ity that is present in the older syntax. It is also useful when literal digits follow the reference. A negative number is a relative reference. Consider this example: @@ -6124,33 +6134,33 @@ BACK REFERENCES The sequence \g{-1} is a reference to the most recently started captur- ing subpattern before \g, that is, is it equivalent to \2 in this exam- - ple. Similarly, \g{-2} would be equivalent to \1. The use of relative - references can be helpful in long patterns, and also in patterns that - are created by joining together fragments that contain references + ple. Similarly, \g{-2} would be equivalent to \1. The use of relative + references can be helpful in long patterns, and also in patterns that + are created by joining together fragments that contain references within themselves. - A back reference matches whatever actually matched the capturing sub- - pattern in the current subject string, rather than anything matching + A back reference matches whatever actually matched the capturing sub- + pattern in the current subject string, rather than anything matching the subpattern itself (see "Subpatterns as subroutines" below for a way of doing that). So the pattern (sens|respons)e and \1ibility - matches "sense and sensibility" and "response and responsibility", but - not "sense and responsibility". If caseful matching is in force at the - time of the back reference, the case of letters is relevant. For exam- + matches "sense and sensibility" and "response and responsibility", but + not "sense and responsibility". If caseful matching is in force at the + time of the back reference, the case of letters is relevant. For exam- ple, ((?i)rah)\s+\1 - matches "rah rah" and "RAH RAH", but not "RAH rah", even though the + matches "rah rah" and "RAH RAH", but not "RAH rah", even though the original capturing subpattern is matched caselessly. - There are several different ways of writing back references to named - subpatterns. The .NET syntax \k{name} and the Perl syntax \k<name> or - \k'name' are supported, as is the Python syntax (?P=name). Perl 5.10's + There are several different ways of writing back references to named + subpatterns. The .NET syntax \k{name} and the Perl syntax \k<name> or + \k'name' are supported, as is the Python syntax (?P=name). Perl 5.10's unified back reference syntax, in which \g can be used for both numeric - and named references, is also supported. We could rewrite the above + and named references, is also supported. We could rewrite the above example in any of the following ways: (?<p1>(?i)rah)\s+\k<p1> @@ -6158,83 +6168,83 @@ BACK REFERENCES (?P<p1>(?i)rah)\s+(?P=p1) (?<p1>(?i)rah)\s+\g{p1} - A subpattern that is referenced by name may appear in the pattern + A subpattern that is referenced by name may appear in the pattern before or after the reference. - There may be more than one back reference to the same subpattern. If a - subpattern has not actually been used in a particular match, any back + There may be more than one back reference to the same subpattern. If a + subpattern has not actually been used in a particular match, any back references to it always fail by default. For example, the pattern (a|(bc))\2 - always fails if it starts to match "a" rather than "bc". However, if + always fails if it starts to match "a" rather than "bc". However, if the PCRE_JAVASCRIPT_COMPAT option is set at compile time, a back refer- ence to an unset value matches an empty string. - Because there may be many capturing parentheses in a pattern, all dig- - its following a backslash are taken as part of a potential back refer- - ence number. If the pattern continues with a digit character, some - delimiter must be used to terminate the back reference. If the - PCRE_EXTENDED option is set, this can be white space. Otherwise, the + Because there may be many capturing parentheses in a pattern, all dig- + its following a backslash are taken as part of a potential back refer- + ence number. If the pattern continues with a digit character, some + delimiter must be used to terminate the back reference. If the + PCRE_EXTENDED option is set, this can be white space. Otherwise, the \g{ syntax or an empty comment (see "Comments" below) can be used. Recursive back references - A back reference that occurs inside the parentheses to which it refers - fails when the subpattern is first used, so, for example, (a\1) never - matches. However, such references can be useful inside repeated sub- + A back reference that occurs inside the parentheses to which it refers + fails when the subpattern is first used, so, for example, (a\1) never + matches. However, such references can be useful inside repeated sub- patterns. For example, the pattern (a|b\1)+ matches any number of "a"s and also "aba", "ababbaa" etc. At each iter- - ation of the subpattern, the back reference matches the character - string corresponding to the previous iteration. In order for this to - work, the pattern must be such that the first iteration does not need - to match the back reference. This can be done using alternation, as in + ation of the subpattern, the back reference matches the character + string corresponding to the previous iteration. In order for this to + work, the pattern must be such that the first iteration does not need + to match the back reference. This can be done using alternation, as in the example above, or by a quantifier with a minimum of zero. - Back references of this type cause the group that they reference to be - treated as an atomic group. Once the whole group has been matched, a - subsequent matching failure cannot cause backtracking into the middle + Back references of this type cause the group that they reference to be + treated as an atomic group. Once the whole group has been matched, a + subsequent matching failure cannot cause backtracking into the middle of the group. ASSERTIONS - An assertion is a test on the characters following or preceding the - current matching point that does not actually consume any characters. - The simple assertions coded as \b, \B, \A, \G, \Z, \z, ^ and $ are + An assertion is a test on the characters following or preceding the + current matching point that does not actually consume any characters. + The simple assertions coded as \b, \B, \A, \G, \Z, \z, ^ and $ are described above. - More complicated assertions are coded as subpatterns. There are two - kinds: those that look ahead of the current position in the subject - string, and those that look behind it. An assertion subpattern is - matched in the normal way, except that it does not cause the current + More complicated assertions are coded as subpatterns. There are two + kinds: those that look ahead of the current position in the subject + string, and those that look behind it. An assertion subpattern is + matched in the normal way, except that it does not cause the current matching position to be changed. - Assertion subpatterns are not capturing subpatterns. If such an asser- - tion contains capturing subpatterns within it, these are counted for - the purposes of numbering the capturing subpatterns in the whole pat- - tern. However, substring capturing is carried out only for positive + Assertion subpatterns are not capturing subpatterns. If such an asser- + tion contains capturing subpatterns within it, these are counted for + the purposes of numbering the capturing subpatterns in the whole pat- + tern. However, substring capturing is carried out only for positive assertions, because it does not make sense for negative assertions. - For compatibility with Perl, assertion subpatterns may be repeated; - though it makes no sense to assert the same thing several times, the - side effect of capturing parentheses may occasionally be useful. In + For compatibility with Perl, assertion subpatterns may be repeated; + though it makes no sense to assert the same thing several times, the + side effect of capturing parentheses may occasionally be useful. In practice, there only three cases: - (1) If the quantifier is {0}, the assertion is never obeyed during - matching. However, it may contain internal capturing parenthesized + (1) If the quantifier is {0}, the assertion is never obeyed during + matching. However, it may contain internal capturing parenthesized groups that are called from elsewhere via the subroutine mechanism. - (2) If quantifier is {0,n} where n is greater than zero, it is treated - as if it were {0,1}. At run time, the rest of the pattern match is + (2) If quantifier is {0,n} where n is greater than zero, it is treated + as if it were {0,1}. At run time, the rest of the pattern match is tried with and without the assertion, the order depending on the greed- iness of the quantifier. - (3) If the minimum repetition is greater than zero, the quantifier is - ignored. The assertion is obeyed just once when encountered during + (3) If the minimum repetition is greater than zero, the quantifier is + ignored. The assertion is obeyed just once when encountered during matching. Lookahead assertions @@ -6244,38 +6254,38 @@ ASSERTIONS \w+(?=;) - matches a word followed by a semicolon, but does not include the semi- + matches a word followed by a semicolon, but does not include the semi- colon in the match, and foo(?!bar) - matches any occurrence of "foo" that is not followed by "bar". Note + matches any occurrence of "foo" that is not followed by "bar". Note that the apparently similar pattern (?!foo)bar - does not find an occurrence of "bar" that is preceded by something - other than "foo"; it finds any occurrence of "bar" whatsoever, because + does not find an occurrence of "bar" that is preceded by something + other than "foo"; it finds any occurrence of "bar" whatsoever, because the assertion (?!foo) is always true when the next three characters are "bar". A lookbehind assertion is needed to achieve the other effect. If you want to force a matching failure at some point in a pattern, the - most convenient way to do it is with (?!) because an empty string - always matches, so an assertion that requires there not to be an empty + most convenient way to do it is with (?!) because an empty string + always matches, so an assertion that requires there not to be an empty string must always fail. The backtracking control verb (*FAIL) or (*F) is a synonym for (?!). Lookbehind assertions - Lookbehind assertions start with (?<= for positive assertions and (?<! + Lookbehind assertions start with (?<= for positive assertions and (?<! for negative assertions. For example, (?<!foo)bar - does find an occurrence of "bar" that is not preceded by "foo". The - contents of a lookbehind assertion are restricted such that all the + does find an occurrence of "bar" that is not preceded by "foo". The + contents of a lookbehind assertion are restricted such that all the strings it matches must have a fixed length. However, if there are sev- - eral top-level alternatives, they do not all have to have the same + eral top-level alternatives, they do not all have to have the same fixed length. Thus (?<=bullock|donkey) @@ -6284,62 +6294,62 @@ ASSERTIONS (?<!dogs?|cats?) - causes an error at compile time. Branches that match different length - strings are permitted only at the top level of a lookbehind assertion. + causes an error at compile time. Branches that match different length + strings are permitted only at the top level of a lookbehind assertion. This is an extension compared with Perl, which requires all branches to match the same length of string. An assertion such as (?<=ab(c|de)) - is not permitted, because its single top-level branch can match two + is not permitted, because its single top-level branch can match two different lengths, but it is acceptable to PCRE if rewritten to use two top-level branches: (?<=abc|abde) - In some cases, the escape sequence \K (see above) can be used instead + In some cases, the escape sequence \K (see above) can be used instead of a lookbehind assertion to get round the fixed-length restriction. - The implementation of lookbehind assertions is, for each alternative, - to temporarily move the current position back by the fixed length and + The implementation of lookbehind assertions is, for each alternative, + to temporarily move the current position back by the fixed length and then try to match. If there are insufficient characters before the cur- rent position, the assertion fails. - In a UTF mode, PCRE does not allow the \C escape (which matches a sin- - gle data unit even in a UTF mode) to appear in lookbehind assertions, - because it makes it impossible to calculate the length of the lookbe- - hind. The \X and \R escapes, which can match different numbers of data + In a UTF mode, PCRE does not allow the \C escape (which matches a sin- + gle data unit even in a UTF mode) to appear in lookbehind assertions, + because it makes it impossible to calculate the length of the lookbe- + hind. The \X and \R escapes, which can match different numbers of data units, are also not permitted. - "Subroutine" calls (see below) such as (?2) or (?&X) are permitted in - lookbehinds, as long as the subpattern matches a fixed-length string. + "Subroutine" calls (see below) such as (?2) or (?&X) are permitted in + lookbehinds, as long as the subpattern matches a fixed-length string. Recursion, however, is not supported. - Possessive quantifiers can be used in conjunction with lookbehind + Possessive quantifiers can be used in conjunction with lookbehind assertions to specify efficient matching of fixed-length strings at the end of subject strings. Consider a simple pattern such as abcd$ - when applied to a long string that does not match. Because matching + when applied to a long string that does not match. Because matching proceeds from left to right, PCRE will look for each "a" in the subject - and then see if what follows matches the rest of the pattern. If the + and then see if what follows matches the rest of the pattern. If the pattern is specified as ^.*abcd$ - the initial .* matches the entire string at first, but when this fails + the initial .* matches the entire string at first, but when this fails (because there is no following "a"), it backtracks to match all but the - last character, then all but the last two characters, and so on. Once - again the search for "a" covers the entire string, from right to left, + last character, then all but the last two characters, and so on. Once + again the search for "a" covers the entire string, from right to left, so we are no better off. However, if the pattern is written as ^.*+(?<=abcd) - there can be no backtracking for the .*+ item; it can match only the - entire string. The subsequent lookbehind assertion does a single test - on the last four characters. If it fails, the match fails immediately. - For long strings, this approach makes a significant difference to the + there can be no backtracking for the .*+ item; it can match only the + entire string. The subsequent lookbehind assertion does a single test + on the last four characters. If it fails, the match fails immediately. + For long strings, this approach makes a significant difference to the processing time. Using multiple assertions @@ -6348,18 +6358,18 @@ ASSERTIONS (?<=\d{3})(?<!999)foo - matches "foo" preceded by three digits that are not "999". Notice that - each of the assertions is applied independently at the same point in - the subject string. First there is a check that the previous three - characters are all digits, and then there is a check that the same + matches "foo" preceded by three digits that are not "999". Notice that + each of the assertions is applied independently at the same point in + the subject string. First there is a check that the previous three + characters are all digits, and then there is a check that the same three characters are not "999". This pattern does not match "foo" pre- - ceded by six characters, the first of which are digits and the last - three of which are not "999". For example, it doesn't match "123abc- + ceded by six characters, the first of which are digits and the last + three of which are not "999". For example, it doesn't match "123abc- foo". A pattern to do that is (?<=\d{3}...)(?<!999)foo - This time the first assertion looks at the preceding six characters, + This time the first assertion looks at the preceding six characters, checking that the first three are digits, and then the second assertion checks that the preceding three characters are not "999". @@ -6367,29 +6377,29 @@ ASSERTIONS (?<=(?<!foo)bar)baz - matches an occurrence of "baz" that is preceded by "bar" which in turn + matches an occurrence of "baz" that is preceded by "bar" which in turn is not preceded by "foo", while (?<=\d{3}(?!999)...)foo - is another pattern that matches "foo" preceded by three digits and any + is another pattern that matches "foo" preceded by three digits and any three characters that are not "999". CONDITIONAL SUBPATTERNS - It is possible to cause the matching process to obey a subpattern con- - ditionally or to choose between two alternative subpatterns, depending - on the result of an assertion, or whether a specific capturing subpat- - tern has already been matched. The two possible forms of conditional + It is possible to cause the matching process to obey a subpattern con- + ditionally or to choose between two alternative subpatterns, depending + on the result of an assertion, or whether a specific capturing subpat- + tern has already been matched. The two possible forms of conditional subpattern are: (?(condition)yes-pattern) (?(condition)yes-pattern|no-pattern) - If the condition is satisfied, the yes-pattern is used; otherwise the - no-pattern (if present) is used. If there are more than two alterna- - tives in the subpattern, a compile-time error occurs. Each of the two + If the condition is satisfied, the yes-pattern is used; otherwise the + no-pattern (if present) is used. If there are more than two alterna- + tives in the subpattern, a compile-time error occurs. Each of the two alternatives may itself contain nested subpatterns of any form, includ- ing conditional subpatterns; the restriction to two alternatives applies only at the level of the condition. This pattern fragment is an @@ -6398,73 +6408,73 @@ CONDITIONAL SUBPATTERNS (?(1) (A|B|C) | (D | (?(2)E|F) | E) ) - There are four kinds of condition: references to subpatterns, refer- + There are four kinds of condition: references to subpatterns, refer- ences to recursion, a pseudo-condition called DEFINE, and assertions. Checking for a used subpattern by number - If the text between the parentheses consists of a sequence of digits, + If the text between the parentheses consists of a sequence of digits, the condition is true if a capturing subpattern of that number has pre- - viously matched. If there is more than one capturing subpattern with - the same number (see the earlier section about duplicate subpattern - numbers), the condition is true if any of them have matched. An alter- - native notation is to precede the digits with a plus or minus sign. In - this case, the subpattern number is relative rather than absolute. The - most recently opened parentheses can be referenced by (?(-1), the next - most recent by (?(-2), and so on. Inside loops it can also make sense + viously matched. If there is more than one capturing subpattern with + the same number (see the earlier section about duplicate subpattern + numbers), the condition is true if any of them have matched. An alter- + native notation is to precede the digits with a plus or minus sign. In + this case, the subpattern number is relative rather than absolute. The + most recently opened parentheses can be referenced by (?(-1), the next + most recent by (?(-2), and so on. Inside loops it can also make sense to refer to subsequent groups. The next parentheses to be opened can be - referenced as (?(+1), and so on. (The value zero in any of these forms + referenced as (?(+1), and so on. (The value zero in any of these forms is not used; it provokes a compile-time error.) - Consider the following pattern, which contains non-significant white + Consider the following pattern, which contains non-significant white space to make it more readable (assume the PCRE_EXTENDED option) and to divide it into three parts for ease of discussion: ( \( )? [^()]+ (?(1) \) ) - The first part matches an optional opening parenthesis, and if that + The first part matches an optional opening parenthesis, and if that character is present, sets it as the first captured substring. The sec- - ond part matches one or more characters that are not parentheses. The - third part is a conditional subpattern that tests whether or not the - first set of parentheses matched. If they did, that is, if subject - started with an opening parenthesis, the condition is true, and so the - yes-pattern is executed and a closing parenthesis is required. Other- - wise, since no-pattern is not present, the subpattern matches nothing. - In other words, this pattern matches a sequence of non-parentheses, + ond part matches one or more characters that are not parentheses. The + third part is a conditional subpattern that tests whether or not the + first set of parentheses matched. If they did, that is, if subject + started with an opening parenthesis, the condition is true, and so the + yes-pattern is executed and a closing parenthesis is required. Other- + wise, since no-pattern is not present, the subpattern matches nothing. + In other words, this pattern matches a sequence of non-parentheses, optionally enclosed in parentheses. - If you were embedding this pattern in a larger one, you could use a + If you were embedding this pattern in a larger one, you could use a relative reference: ...other stuff... ( \( )? [^()]+ (?(-1) \) ) ... - This makes the fragment independent of the parentheses in the larger + This makes the fragment independent of the parentheses in the larger pattern. Checking for a used subpattern by name - Perl uses the syntax (?(<name>)...) or (?('name')...) to test for a - used subpattern by name. For compatibility with earlier versions of - PCRE, which had this facility before Perl, the syntax (?(name)...) is - also recognized. However, there is a possible ambiguity with this syn- - tax, because subpattern names may consist entirely of digits. PCRE - looks first for a named subpattern; if it cannot find one and the name - consists entirely of digits, PCRE looks for a subpattern of that num- - ber, which must be greater than zero. Using subpattern names that con- + Perl uses the syntax (?(<name>)...) or (?('name')...) to test for a + used subpattern by name. For compatibility with earlier versions of + PCRE, which had this facility before Perl, the syntax (?(name)...) is + also recognized. However, there is a possible ambiguity with this syn- + tax, because subpattern names may consist entirely of digits. PCRE + looks first for a named subpattern; if it cannot find one and the name + consists entirely of digits, PCRE looks for a subpattern of that num- + ber, which must be greater than zero. Using subpattern names that con- sist entirely of digits is not recommended. Rewriting the above example to use a named subpattern gives this: (?<OPEN> \( )? [^()]+ (?(<OPEN>) \) ) - If the name used in a condition of this kind is a duplicate, the test - is applied to all subpatterns of the same name, and is true if any one + If the name used in a condition of this kind is a duplicate, the test + is applied to all subpatterns of the same name, and is true if any one of them has matched. Checking for pattern recursion If the condition is the string (R), and there is no subpattern with the - name R, the condition is true if a recursive call to the whole pattern + name R, the condition is true if a recursive call to the whole pattern or any subpattern has been made. If digits or a name preceded by amper- sand follow the letter R, for example: @@ -6472,51 +6482,51 @@ CONDITIONAL SUBPATTERNS the condition is true if the most recent recursion is into a subpattern whose number or name is given. This condition does not check the entire - recursion stack. If the name used in a condition of this kind is a + recursion stack. If the name used in a condition of this kind is a duplicate, the test is applied to all subpatterns of the same name, and is true if any one of them is the most recent recursion. - At "top level", all these recursion test conditions are false. The + At "top level", all these recursion test conditions are false. The syntax for recursive patterns is described below. Defining subpatterns for use by reference only - If the condition is the string (DEFINE), and there is no subpattern - with the name DEFINE, the condition is always false. In this case, - there may be only one alternative in the subpattern. It is always - skipped if control reaches this point in the pattern; the idea of - DEFINE is that it can be used to define subroutines that can be refer- - enced from elsewhere. (The use of subroutines is described below.) For - example, a pattern to match an IPv4 address such as "192.168.23.245" + If the condition is the string (DEFINE), and there is no subpattern + with the name DEFINE, the condition is always false. In this case, + there may be only one alternative in the subpattern. It is always + skipped if control reaches this point in the pattern; the idea of + DEFINE is that it can be used to define subroutines that can be refer- + enced from elsewhere. (The use of subroutines is described below.) For + example, a pattern to match an IPv4 address such as "192.168.23.245" could be written like this (ignore white space and line breaks): (?(DEFINE) (?<byte> 2[0-4]\d | 25[0-5] | 1\d\d | [1-9]?\d) ) \b (?&byte) (\.(?&byte)){3} \b - The first part of the pattern is a DEFINE group inside which a another - group named "byte" is defined. This matches an individual component of - an IPv4 address (a number less than 256). When matching takes place, - this part of the pattern is skipped because DEFINE acts like a false - condition. The rest of the pattern uses references to the named group - to match the four dot-separated components of an IPv4 address, insist- + The first part of the pattern is a DEFINE group inside which a another + group named "byte" is defined. This matches an individual component of + an IPv4 address (a number less than 256). When matching takes place, + this part of the pattern is skipped because DEFINE acts like a false + condition. The rest of the pattern uses references to the named group + to match the four dot-separated components of an IPv4 address, insist- ing on a word boundary at each end. Assertion conditions - If the condition is not in any of the above formats, it must be an - assertion. This may be a positive or negative lookahead or lookbehind - assertion. Consider this pattern, again containing non-significant + If the condition is not in any of the above formats, it must be an + assertion. This may be a positive or negative lookahead or lookbehind + assertion. Consider this pattern, again containing non-significant white space, and with the two alternatives on the second line: (?(?=[^a-z]*[a-z]) \d{2}-[a-z]{3}-\d{2} | \d{2}-\d{2}-\d{2} ) - The condition is a positive lookahead assertion that matches an - optional sequence of non-letters followed by a letter. In other words, - it tests for the presence of at least one letter in the subject. If a - letter is found, the subject is matched against the first alternative; - otherwise it is matched against the second. This pattern matches - strings in one of the two forms dd-aaa-dd or dd-dd-dd, where aaa are + The condition is a positive lookahead assertion that matches an + optional sequence of non-letters followed by a letter. In other words, + it tests for the presence of at least one letter in the subject. If a + letter is found, the subject is matched against the first alternative; + otherwise it is matched against the second. This pattern matches + strings in one of the two forms dd-aaa-dd or dd-dd-dd, where aaa are letters and dd are digits. @@ -6525,41 +6535,41 @@ COMMENTS There are two ways of including comments in patterns that are processed by PCRE. In both cases, the start of the comment must not be in a char- acter class, nor in the middle of any other sequence of related charac- - ters such as (?: or a subpattern name or number. The characters that + ters such as (?: or a subpattern name or number. The characters that make up a comment play no part in the pattern matching. - The sequence (?# marks the start of a comment that continues up to the - next closing parenthesis. Nested parentheses are not permitted. If the + The sequence (?# marks the start of a comment that continues up to the + next closing parenthesis. Nested parentheses are not permitted. If the PCRE_EXTENDED option is set, an unescaped # character also introduces a - comment, which in this case continues to immediately after the next - newline character or character sequence in the pattern. Which charac- + comment, which in this case continues to immediately after the next + newline character or character sequence in the pattern. Which charac- ters are interpreted as newlines is controlled by the options passed to - a compiling function or by a special sequence at the start of the pat- + a compiling function or by a special sequence at the start of the pat- tern, as described in the section entitled "Newline conventions" above. Note that the end of this type of comment is a literal newline sequence - in the pattern; escape sequences that happen to represent a newline do - not count. For example, consider this pattern when PCRE_EXTENDED is + in the pattern; escape sequences that happen to represent a newline do + not count. For example, consider this pattern when PCRE_EXTENDED is set, and the default newline convention is in force: abc #comment \n still comment - On encountering the # character, pcre_compile() skips along, looking - for a newline in the pattern. The sequence \n is still literal at this - stage, so it does not terminate the comment. Only an actual character + On encountering the # character, pcre_compile() skips along, looking + for a newline in the pattern. The sequence \n is still literal at this + stage, so it does not terminate the comment. Only an actual character with the code value 0x0a (the default newline) does so. RECURSIVE PATTERNS - Consider the problem of matching a string in parentheses, allowing for - unlimited nested parentheses. Without the use of recursion, the best - that can be done is to use a pattern that matches up to some fixed - depth of nesting. It is not possible to handle an arbitrary nesting + Consider the problem of matching a string in parentheses, allowing for + unlimited nested parentheses. Without the use of recursion, the best + that can be done is to use a pattern that matches up to some fixed + depth of nesting. It is not possible to handle an arbitrary nesting depth. For some time, Perl has provided a facility that allows regular expres- - sions to recurse (amongst other things). It does this by interpolating - Perl code in the expression at run time, and the code can refer to the + sions to recurse (amongst other things). It does this by interpolating + Perl code in the expression at run time, and the code can refer to the expression itself. A Perl pattern using code interpolation to solve the parentheses problem can be created like this: @@ -6569,201 +6579,201 @@ RECURSIVE PATTERNS refers recursively to the pattern in which it appears. Obviously, PCRE cannot support the interpolation of Perl code. Instead, - it supports special syntax for recursion of the entire pattern, and - also for individual subpattern recursion. After its introduction in - PCRE and Python, this kind of recursion was subsequently introduced + it supports special syntax for recursion of the entire pattern, and + also for individual subpattern recursion. After its introduction in + PCRE and Python, this kind of recursion was subsequently introduced into Perl at release 5.10. - A special item that consists of (? followed by a number greater than - zero and a closing parenthesis is a recursive subroutine call of the - subpattern of the given number, provided that it occurs inside that - subpattern. (If not, it is a non-recursive subroutine call, which is - described in the next section.) The special item (?R) or (?0) is a + A special item that consists of (? followed by a number greater than + zero and a closing parenthesis is a recursive subroutine call of the + subpattern of the given number, provided that it occurs inside that + subpattern. (If not, it is a non-recursive subroutine call, which is + described in the next section.) The special item (?R) or (?0) is a recursive call of the entire regular expression. - This PCRE pattern solves the nested parentheses problem (assume the + This PCRE pattern solves the nested parentheses problem (assume the PCRE_EXTENDED option is set so that white space is ignored): \( ( [^()]++ | (?R) )* \) - First it matches an opening parenthesis. Then it matches any number of - substrings which can either be a sequence of non-parentheses, or a - recursive match of the pattern itself (that is, a correctly parenthe- + First it matches an opening parenthesis. Then it matches any number of + substrings which can either be a sequence of non-parentheses, or a + recursive match of the pattern itself (that is, a correctly parenthe- sized substring). Finally there is a closing parenthesis. Note the use of a possessive quantifier to avoid backtracking into sequences of non- parentheses. - If this were part of a larger pattern, you would not want to recurse + If this were part of a larger pattern, you would not want to recurse the entire pattern, so instead you could use this: ( \( ( [^()]++ | (?1) )* \) ) - We have put the pattern into parentheses, and caused the recursion to + We have put the pattern into parentheses, and caused the recursion to refer to them instead of the whole pattern. - In a larger pattern, keeping track of parenthesis numbers can be - tricky. This is made easier by the use of relative references. Instead + In a larger pattern, keeping track of parenthesis numbers can be + tricky. This is made easier by the use of relative references. Instead of (?1) in the pattern above you can write (?-2) to refer to the second - most recently opened parentheses preceding the recursion. In other - words, a negative number counts capturing parentheses leftwards from + most recently opened parentheses preceding the recursion. In other + words, a negative number counts capturing parentheses leftwards from the point at which it is encountered. - It is also possible to refer to subsequently opened parentheses, by - writing references such as (?+2). However, these cannot be recursive - because the reference is not inside the parentheses that are refer- - enced. They are always non-recursive subroutine calls, as described in + It is also possible to refer to subsequently opened parentheses, by + writing references such as (?+2). However, these cannot be recursive + because the reference is not inside the parentheses that are refer- + enced. They are always non-recursive subroutine calls, as described in the next section. - An alternative approach is to use named parentheses instead. The Perl - syntax for this is (?&name); PCRE's earlier syntax (?P>name) is also + An alternative approach is to use named parentheses instead. The Perl + syntax for this is (?&name); PCRE's earlier syntax (?P>name) is also supported. We could rewrite the above example as follows: (?<pn> \( ( [^()]++ | (?&pn) )* \) ) - If there is more than one subpattern with the same name, the earliest + If there is more than one subpattern with the same name, the earliest one is used. - This particular example pattern that we have been looking at contains + This particular example pattern that we have been looking at contains nested unlimited repeats, and so the use of a possessive quantifier for matching strings of non-parentheses is important when applying the pat- - tern to strings that do not match. For example, when this pattern is + tern to strings that do not match. For example, when this pattern is applied to (aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa() - it yields "no match" quickly. However, if a possessive quantifier is - not used, the match runs for a very long time indeed because there are - so many different ways the + and * repeats can carve up the subject, + it yields "no match" quickly. However, if a possessive quantifier is + not used, the match runs for a very long time indeed because there are + so many different ways the + and * repeats can carve up the subject, and all have to be tested before failure can be reported. - At the end of a match, the values of capturing parentheses are those - from the outermost level. If you want to obtain intermediate values, a - callout function can be used (see below and the pcrecallout documenta- + At the end of a match, the values of capturing parentheses are those + from the outermost level. If you want to obtain intermediate values, a + callout function can be used (see below and the pcrecallout documenta- tion). If the pattern above is matched against (ab(cd)ef) - the value for the inner capturing parentheses (numbered 2) is "ef", - which is the last value taken on at the top level. If a capturing sub- - pattern is not matched at the top level, its final captured value is - unset, even if it was (temporarily) set at a deeper level during the + the value for the inner capturing parentheses (numbered 2) is "ef", + which is the last value taken on at the top level. If a capturing sub- + pattern is not matched at the top level, its final captured value is + unset, even if it was (temporarily) set at a deeper level during the matching process. - If there are more than 15 capturing parentheses in a pattern, PCRE has - to obtain extra memory to store data during a recursion, which it does + If there are more than 15 capturing parentheses in a pattern, PCRE has + to obtain extra memory to store data during a recursion, which it does by using pcre_malloc, freeing it via pcre_free afterwards. If no memory can be obtained, the match fails with the PCRE_ERROR_NOMEMORY error. - Do not confuse the (?R) item with the condition (R), which tests for - recursion. Consider this pattern, which matches text in angle brack- - ets, allowing for arbitrary nesting. Only digits are allowed in nested - brackets (that is, when recursing), whereas any characters are permit- + Do not confuse the (?R) item with the condition (R), which tests for + recursion. Consider this pattern, which matches text in angle brack- + ets, allowing for arbitrary nesting. Only digits are allowed in nested + brackets (that is, when recursing), whereas any characters are permit- ted at the outer level. < (?: (?(R) \d++ | [^<>]*+) | (?R)) * > - In this pattern, (?(R) is the start of a conditional subpattern, with - two different alternatives for the recursive and non-recursive cases. + In this pattern, (?(R) is the start of a conditional subpattern, with + two different alternatives for the recursive and non-recursive cases. The (?R) item is the actual recursive call. Differences in recursion processing between PCRE and Perl - Recursion processing in PCRE differs from Perl in two important ways. - In PCRE (like Python, but unlike Perl), a recursive subpattern call is + Recursion processing in PCRE differs from Perl in two important ways. + In PCRE (like Python, but unlike Perl), a recursive subpattern call is always treated as an atomic group. That is, once it has matched some of the subject string, it is never re-entered, even if it contains untried - alternatives and there is a subsequent matching failure. This can be - illustrated by the following pattern, which purports to match a palin- - dromic string that contains an odd number of characters (for example, + alternatives and there is a subsequent matching failure. This can be + illustrated by the following pattern, which purports to match a palin- + dromic string that contains an odd number of characters (for example, "a", "aba", "abcba", "abcdcba"): ^(.|(.)(?1)\2)$ The idea is that it either matches a single character, or two identical - characters surrounding a sub-palindrome. In Perl, this pattern works; - in PCRE it does not if the pattern is longer than three characters. + characters surrounding a sub-palindrome. In Perl, this pattern works; + in PCRE it does not if the pattern is longer than three characters. Consider the subject string "abcba": - At the top level, the first character is matched, but as it is not at + At the top level, the first character is matched, but as it is not at the end of the string, the first alternative fails; the second alterna- tive is taken and the recursion kicks in. The recursive call to subpat- - tern 1 successfully matches the next character ("b"). (Note that the + tern 1 successfully matches the next character ("b"). (Note that the beginning and end of line tests are not part of the recursion). - Back at the top level, the next character ("c") is compared with what - subpattern 2 matched, which was "a". This fails. Because the recursion - is treated as an atomic group, there are now no backtracking points, - and so the entire match fails. (Perl is able, at this point, to re- - enter the recursion and try the second alternative.) However, if the + Back at the top level, the next character ("c") is compared with what + subpattern 2 matched, which was "a". This fails. Because the recursion + is treated as an atomic group, there are now no backtracking points, + and so the entire match fails. (Perl is able, at this point, to re- + enter the recursion and try the second alternative.) However, if the pattern is written with the alternatives in the other order, things are different: ^((.)(?1)\2|.)$ - This time, the recursing alternative is tried first, and continues to - recurse until it runs out of characters, at which point the recursion - fails. But this time we do have another alternative to try at the - higher level. That is the big difference: in the previous case the + This time, the recursing alternative is tried first, and continues to + recurse until it runs out of characters, at which point the recursion + fails. But this time we do have another alternative to try at the + higher level. That is the big difference: in the previous case the remaining alternative is at a deeper recursion level, which PCRE cannot use. - To change the pattern so that it matches all palindromic strings, not - just those with an odd number of characters, it is tempting to change + To change the pattern so that it matches all palindromic strings, not + just those with an odd number of characters, it is tempting to change the pattern to this: ^((.)(?1)\2|.?)$ - Again, this works in Perl, but not in PCRE, and for the same reason. - When a deeper recursion has matched a single character, it cannot be - entered again in order to match an empty string. The solution is to - separate the two cases, and write out the odd and even cases as alter- + Again, this works in Perl, but not in PCRE, and for the same reason. + When a deeper recursion has matched a single character, it cannot be + entered again in order to match an empty string. The solution is to + separate the two cases, and write out the odd and even cases as alter- natives at the higher level: ^(?:((.)(?1)\2|)|((.)(?3)\4|.)) - If you want to match typical palindromic phrases, the pattern has to + If you want to match typical palindromic phrases, the pattern has to ignore all non-word characters, which can be done like this: ^\W*+(?:((.)\W*+(?1)\W*+\2|)|((.)\W*+(?3)\W*+\4|\W*+.\W*+))\W*+$ If run with the PCRE_CASELESS option, this pattern matches phrases such as "A man, a plan, a canal: Panama!" and it works well in both PCRE and - Perl. Note the use of the possessive quantifier *+ to avoid backtrack- - ing into sequences of non-word characters. Without this, PCRE takes a - great deal longer (ten times or more) to match typical phrases, and + Perl. Note the use of the possessive quantifier *+ to avoid backtrack- + ing into sequences of non-word characters. Without this, PCRE takes a + great deal longer (ten times or more) to match typical phrases, and Perl takes so long that you think it has gone into a loop. - WARNING: The palindrome-matching patterns above work only if the sub- - ject string does not start with a palindrome that is shorter than the - entire string. For example, although "abcba" is correctly matched, if - the subject is "ababa", PCRE finds the palindrome "aba" at the start, - then fails at top level because the end of the string does not follow. - Once again, it cannot jump back into the recursion to try other alter- + WARNING: The palindrome-matching patterns above work only if the sub- + ject string does not start with a palindrome that is shorter than the + entire string. For example, although "abcba" is correctly matched, if + the subject is "ababa", PCRE finds the palindrome "aba" at the start, + then fails at top level because the end of the string does not follow. + Once again, it cannot jump back into the recursion to try other alter- natives, so the entire match fails. - The second way in which PCRE and Perl differ in their recursion pro- - cessing is in the handling of captured values. In Perl, when a subpat- - tern is called recursively or as a subpattern (see the next section), - it has no access to any values that were captured outside the recur- - sion, whereas in PCRE these values can be referenced. Consider this + The second way in which PCRE and Perl differ in their recursion pro- + cessing is in the handling of captured values. In Perl, when a subpat- + tern is called recursively or as a subpattern (see the next section), + it has no access to any values that were captured outside the recur- + sion, whereas in PCRE these values can be referenced. Consider this pattern: ^(.)(\1|a(?2)) - In PCRE, this pattern matches "bab". The first capturing parentheses - match "b", then in the second group, when the back reference \1 fails - to match "b", the second alternative matches "a" and then recurses. In - the recursion, \1 does now match "b" and so the whole match succeeds. - In Perl, the pattern fails to match because inside the recursive call + In PCRE, this pattern matches "bab". The first capturing parentheses + match "b", then in the second group, when the back reference \1 fails + to match "b", the second alternative matches "a" and then recurses. In + the recursion, \1 does now match "b" and so the whole match succeeds. + In Perl, the pattern fails to match because inside the recursive call \1 cannot access the externally set value. SUBPATTERNS AS SUBROUTINES - If the syntax for a recursive subpattern call (either by number or by - name) is used outside the parentheses to which it refers, it operates - like a subroutine in a programming language. The called subpattern may - be defined before or after the reference. A numbered reference can be + If the syntax for a recursive subpattern call (either by number or by + name) is used outside the parentheses to which it refers, it operates + like a subroutine in a programming language. The called subpattern may + be defined before or after the reference. A numbered reference can be absolute or relative, as in these examples: (...(absolute)...)...(?2)... @@ -6774,189 +6784,189 @@ SUBPATTERNS AS SUBROUTINES (sens|respons)e and \1ibility - matches "sense and sensibility" and "response and responsibility", but + matches "sense and sensibility" and "response and responsibility", but not "sense and responsibility". If instead the pattern (sens|respons)e and (?1)ibility - is used, it does match "sense and responsibility" as well as the other - two strings. Another example is given in the discussion of DEFINE + is used, it does match "sense and responsibility" as well as the other + two strings. Another example is given in the discussion of DEFINE above. - All subroutine calls, whether recursive or not, are always treated as - atomic groups. That is, once a subroutine has matched some of the sub- + All subroutine calls, whether recursive or not, are always treated as + atomic groups. That is, once a subroutine has matched some of the sub- ject string, it is never re-entered, even if it contains untried alter- - natives and there is a subsequent matching failure. Any capturing - parentheses that are set during the subroutine call revert to their + natives and there is a subsequent matching failure. Any capturing + parentheses that are set during the subroutine call revert to their previous values afterwards. - Processing options such as case-independence are fixed when a subpat- - tern is defined, so if it is used as a subroutine, such options cannot + Processing options such as case-independence are fixed when a subpat- + tern is defined, so if it is used as a subroutine, such options cannot be changed for different calls. For example, consider this pattern: (abc)(?i:(?-1)) - It matches "abcabc". It does not match "abcABC" because the change of + It matches "abcabc". It does not match "abcABC" because the change of processing option does not affect the called subpattern. ONIGURUMA SUBROUTINE SYNTAX - For compatibility with Oniguruma, the non-Perl syntax \g followed by a + For compatibility with Oniguruma, the non-Perl syntax \g followed by a name or a number enclosed either in angle brackets or single quotes, is - an alternative syntax for referencing a subpattern as a subroutine, - possibly recursively. Here are two of the examples used above, rewrit- + an alternative syntax for referencing a subpattern as a subroutine, + possibly recursively. Here are two of the examples used above, rewrit- ten using this syntax: (?<pn> \( ( (?>[^()]+) | \g<pn> )* \) ) (sens|respons)e and \g'1'ibility - PCRE supports an extension to Oniguruma: if a number is preceded by a + PCRE supports an extension to Oniguruma: if a number is preceded by a plus or a minus sign it is taken as a relative reference. For example: (abc)(?i:\g<-1>) - Note that \g{...} (Perl syntax) and \g<...> (Oniguruma syntax) are not - synonymous. The former is a back reference; the latter is a subroutine + Note that \g{...} (Perl syntax) and \g<...> (Oniguruma syntax) are not + synonymous. The former is a back reference; the latter is a subroutine call. CALLOUTS Perl has a feature whereby using the sequence (?{...}) causes arbitrary - Perl code to be obeyed in the middle of matching a regular expression. + Perl code to be obeyed in the middle of matching a regular expression. This makes it possible, amongst other things, to extract different sub- strings that match the same pair of parentheses when there is a repeti- tion. PCRE provides a similar feature, but of course it cannot obey arbitrary Perl code. The feature is called "callout". The caller of PCRE provides - an external function by putting its entry point in the global variable - pcre_callout (8-bit library) or pcre[16|32]_callout (16-bit or 32-bit - library). By default, this variable contains NULL, which disables all + an external function by putting its entry point in the global variable + pcre_callout (8-bit library) or pcre[16|32]_callout (16-bit or 32-bit + library). By default, this variable contains NULL, which disables all calling out. - Within a regular expression, (?C) indicates the points at which the - external function is to be called. If you want to identify different - callout points, you can put a number less than 256 after the letter C. - The default value is zero. For example, this pattern has two callout + Within a regular expression, (?C) indicates the points at which the + external function is to be called. If you want to identify different + callout points, you can put a number less than 256 after the letter C. + The default value is zero. For example, this pattern has two callout points: (?C1)abc(?C2)def - If the PCRE_AUTO_CALLOUT flag is passed to a compiling function, call- - outs are automatically installed before each item in the pattern. They + If the PCRE_AUTO_CALLOUT flag is passed to a compiling function, call- + outs are automatically installed before each item in the pattern. They are all numbered 255. - During matching, when PCRE reaches a callout point, the external func- - tion is called. It is provided with the number of the callout, the - position in the pattern, and, optionally, one item of data originally - supplied by the caller of the matching function. The callout function - may cause matching to proceed, to backtrack, or to fail altogether. A - complete description of the interface to the callout function is given + During matching, when PCRE reaches a callout point, the external func- + tion is called. It is provided with the number of the callout, the + position in the pattern, and, optionally, one item of data originally + supplied by the caller of the matching function. The callout function + may cause matching to proceed, to backtrack, or to fail altogether. A + complete description of the interface to the callout function is given in the pcrecallout documentation. BACKTRACKING CONTROL - Perl 5.10 introduced a number of "Special Backtracking Control Verbs", + Perl 5.10 introduced a number of "Special Backtracking Control Verbs", which are described in the Perl documentation as "experimental and sub- - ject to change or removal in a future version of Perl". It goes on to - say: "Their usage in production code should be noted to avoid problems + ject to change or removal in a future version of Perl". It goes on to + say: "Their usage in production code should be noted to avoid problems during upgrades." The same remarks apply to the PCRE features described in this section. - Since these verbs are specifically related to backtracking, most of - them can be used only when the pattern is to be matched using one of + Since these verbs are specifically related to backtracking, most of + them can be used only when the pattern is to be matched using one of the traditional matching functions, which use a backtracking algorithm. - With the exception of (*FAIL), which behaves like a failing negative - assertion, they cause an error if encountered by a DFA matching func- + With the exception of (*FAIL), which behaves like a failing negative + assertion, they cause an error if encountered by a DFA matching func- tion. - If any of these verbs are used in an assertion or in a subpattern that + If any of these verbs are used in an assertion or in a subpattern that is called as a subroutine (whether or not recursively), their effect is confined to that subpattern; it does not extend to the surrounding pat- tern, with one exception: the name from a *(MARK), (*PRUNE), or (*THEN) - that is encountered in a successful positive assertion is passed back - when a match succeeds (compare capturing parentheses in assertions). + that is encountered in a successful positive assertion is passed back + when a match succeeds (compare capturing parentheses in assertions). Note that such subpatterns are processed as anchored at the point where - they are tested. Note also that Perl's treatment of subroutines and + they are tested. Note also that Perl's treatment of subroutines and assertions is different in some cases. - The new verbs make use of what was previously invalid syntax: an open- + The new verbs make use of what was previously invalid syntax: an open- ing parenthesis followed by an asterisk. They are generally of the form - (*VERB) or (*VERB:NAME). Some may take either form, with differing be- - haviour, depending on whether or not an argument is present. A name is + (*VERB) or (*VERB:NAME). Some may take either form, with differing be- + haviour, depending on whether or not an argument is present. A name is any sequence of characters that does not include a closing parenthesis. The maximum length of name is 255 in the 8-bit library and 65535 in the 16-bit and 32-bit library. If the name is empty, that is, if the clos- - ing parenthesis immediately follows the colon, the effect is as if the + ing parenthesis immediately follows the colon, the effect is as if the colon were not there. Any number of these verbs may occur in a pattern. Optimizations that affect backtracking verbs - PCRE contains some optimizations that are used to speed up matching by + PCRE contains some optimizations that are used to speed up matching by running some checks at the start of each match attempt. For example, it - may know the minimum length of matching subject, or that a particular - character must be present. When one of these optimizations suppresses - the running of a match, any included backtracking verbs will not, of + may know the minimum length of matching subject, or that a particular + character must be present. When one of these optimizations suppresses + the running of a match, any included backtracking verbs will not, of course, be processed. You can suppress the start-of-match optimizations - by setting the PCRE_NO_START_OPTIMIZE option when calling pcre_com- + by setting the PCRE_NO_START_OPTIMIZE option when calling pcre_com- pile() or pcre_exec(), or by starting the pattern with (*NO_START_OPT). There is more discussion of this option in the section entitled "Option bits for pcre_exec()" in the pcreapi documentation. - Experiments with Perl suggest that it too has similar optimizations, + Experiments with Perl suggest that it too has similar optimizations, sometimes leading to anomalous results. Verbs that act immediately - The following verbs act as soon as they are encountered. They may not + The following verbs act as soon as they are encountered. They may not be followed by a name. (*ACCEPT) - This verb causes the match to end successfully, skipping the remainder - of the pattern. However, when it is inside a subpattern that is called - as a subroutine, only that subpattern is ended successfully. Matching - then continues at the outer level. If (*ACCEPT) is inside capturing + This verb causes the match to end successfully, skipping the remainder + of the pattern. However, when it is inside a subpattern that is called + as a subroutine, only that subpattern is ended successfully. Matching + then continues at the outer level. If (*ACCEPT) is inside capturing parentheses, the data so far is captured. For example: A((?:A|B(*ACCEPT)|C)D) - This matches "AB", "AAD", or "ACD"; when it matches "AB", "B" is cap- + This matches "AB", "AAD", or "ACD"; when it matches "AB", "B" is cap- tured by the outer parentheses. (*FAIL) or (*F) - This verb causes a matching failure, forcing backtracking to occur. It - is equivalent to (?!) but easier to read. The Perl documentation notes - that it is probably useful only when combined with (?{}) or (??{}). - Those are, of course, Perl features that are not present in PCRE. The - nearest equivalent is the callout feature, as for example in this pat- + This verb causes a matching failure, forcing backtracking to occur. It + is equivalent to (?!) but easier to read. The Perl documentation notes + that it is probably useful only when combined with (?{}) or (??{}). + Those are, of course, Perl features that are not present in PCRE. The + nearest equivalent is the callout feature, as for example in this pat- tern: a+(?C)(*FAIL) - A match with the string "aaaa" always fails, but the callout is taken + A match with the string "aaaa" always fails, but the callout is taken before each backtrack happens (in this example, 10 times). Recording which path was taken - There is one verb whose main purpose is to track how a match was - arrived at, though it also has a secondary use in conjunction with + There is one verb whose main purpose is to track how a match was + arrived at, though it also has a secondary use in conjunction with advancing the match starting point (see (*SKIP) below). (*MARK:NAME) or (*:NAME) - A name is always required with this verb. There may be as many - instances of (*MARK) as you like in a pattern, and their names do not + A name is always required with this verb. There may be as many + instances of (*MARK) as you like in a pattern, and their names do not have to be unique. - When a match succeeds, the name of the last-encountered (*MARK) on the - matching path is passed back to the caller as described in the section - entitled "Extra data for pcre_exec()" in the pcreapi documentation. - Here is an example of pcretest output, where the /K modifier requests + When a match succeeds, the name of the last-encountered (*MARK) on the + matching path is passed back to the caller as described in the section + entitled "Extra data for pcre_exec()" in the pcreapi documentation. + Here is an example of pcretest output, where the /K modifier requests the retrieval and outputting of (*MARK) data: re> /X(*MARK:A)Y|X(*MARK:B)Z/K @@ -6968,63 +6978,63 @@ BACKTRACKING CONTROL MK: B The (*MARK) name is tagged with "MK:" in this output, and in this exam- - ple it indicates which of the two alternatives matched. This is a more - efficient way of obtaining this information than putting each alterna- + ple it indicates which of the two alternatives matched. This is a more + efficient way of obtaining this information than putting each alterna- tive in its own capturing parentheses. If (*MARK) is encountered in a positive assertion, its name is recorded and passed back if it is the last-encountered. This does not happen for negative assertions. - After a partial match or a failed match, the name of the last encoun- + After a partial match or a failed match, the name of the last encoun- tered (*MARK) in the entire match process is returned. For example: re> /X(*MARK:A)Y|X(*MARK:B)Z/K data> XP No match, mark = B - Note that in this unanchored example the mark is retained from the + Note that in this unanchored example the mark is retained from the match attempt that started at the letter "X" in the subject. Subsequent match attempts starting at "P" and then with an empty string do not get as far as the (*MARK) item, but nevertheless do not reset it. - If you are interested in (*MARK) values after failed matches, you - should probably set the PCRE_NO_START_OPTIMIZE option (see above) to + If you are interested in (*MARK) values after failed matches, you + should probably set the PCRE_NO_START_OPTIMIZE option (see above) to ensure that the match is always attempted. Verbs that act after backtracking The following verbs do nothing when they are encountered. Matching con- - tinues with what follows, but if there is no subsequent match, causing - a backtrack to the verb, a failure is forced. That is, backtracking - cannot pass to the left of the verb. However, when one of these verbs - appears inside an atomic group, its effect is confined to that group, - because once the group has been matched, there is never any backtrack- - ing into it. In this situation, backtracking can "jump back" to the - left of the entire atomic group. (Remember also, as stated above, that + tinues with what follows, but if there is no subsequent match, causing + a backtrack to the verb, a failure is forced. That is, backtracking + cannot pass to the left of the verb. However, when one of these verbs + appears inside an atomic group, its effect is confined to that group, + because once the group has been matched, there is never any backtrack- + ing into it. In this situation, backtracking can "jump back" to the + left of the entire atomic group. (Remember also, as stated above, that this localization also applies in subroutine calls and assertions.) - These verbs differ in exactly what kind of failure occurs when back- + These verbs differ in exactly what kind of failure occurs when back- tracking reaches them. (*COMMIT) - This verb, which may not be followed by a name, causes the whole match + This verb, which may not be followed by a name, causes the whole match to fail outright if the rest of the pattern does not match. Even if the pattern is unanchored, no further attempts to find a match by advancing the starting point take place. Once (*COMMIT) has been passed, - pcre_exec() is committed to finding a match at the current starting + pcre_exec() is committed to finding a match at the current starting point, or not at all. For example: a+(*COMMIT)b - This matches "xxaab" but not "aacaab". It can be thought of as a kind + This matches "xxaab" but not "aacaab". It can be thought of as a kind of dynamic anchor, or "I've started, so I must finish." The name of the - most recently passed (*MARK) in the path is passed back when (*COMMIT) + most recently passed (*MARK) in the path is passed back when (*COMMIT) forces a match failure. - Note that (*COMMIT) at the start of a pattern is not the same as an - anchor, unless PCRE's start-of-match optimizations are turned off, as + Note that (*COMMIT) at the start of a pattern is not the same as an + anchor, unless PCRE's start-of-match optimizations are turned off, as shown in this pcretest example: re> /(*COMMIT)abc/ @@ -7033,111 +7043,111 @@ BACKTRACKING CONTROL xyzabc\Y No match - PCRE knows that any match must start with "a", so the optimization - skips along the subject to "a" before running the first match attempt, - which succeeds. When the optimization is disabled by the \Y escape in + PCRE knows that any match must start with "a", so the optimization + skips along the subject to "a" before running the first match attempt, + which succeeds. When the optimization is disabled by the \Y escape in the second subject, the match starts at "x" and so the (*COMMIT) causes it to fail without trying any other starting points. (*PRUNE) or (*PRUNE:NAME) - This verb causes the match to fail at the current starting position in - the subject if the rest of the pattern does not match. If the pattern - is unanchored, the normal "bumpalong" advance to the next starting - character then happens. Backtracking can occur as usual to the left of - (*PRUNE), before it is reached, or when matching to the right of - (*PRUNE), but if there is no match to the right, backtracking cannot - cross (*PRUNE). In simple cases, the use of (*PRUNE) is just an alter- - native to an atomic group or possessive quantifier, but there are some + This verb causes the match to fail at the current starting position in + the subject if the rest of the pattern does not match. If the pattern + is unanchored, the normal "bumpalong" advance to the next starting + character then happens. Backtracking can occur as usual to the left of + (*PRUNE), before it is reached, or when matching to the right of + (*PRUNE), but if there is no match to the right, backtracking cannot + cross (*PRUNE). In simple cases, the use of (*PRUNE) is just an alter- + native to an atomic group or possessive quantifier, but there are some uses of (*PRUNE) that cannot be expressed in any other way. The behav- - iour of (*PRUNE:NAME) is the same as (*MARK:NAME)(*PRUNE). In an + iour of (*PRUNE:NAME) is the same as (*MARK:NAME)(*PRUNE). In an anchored pattern (*PRUNE) has the same effect as (*COMMIT). (*SKIP) - This verb, when given without a name, is like (*PRUNE), except that if - the pattern is unanchored, the "bumpalong" advance is not to the next + This verb, when given without a name, is like (*PRUNE), except that if + the pattern is unanchored, the "bumpalong" advance is not to the next character, but to the position in the subject where (*SKIP) was encoun- - tered. (*SKIP) signifies that whatever text was matched leading up to + tered. (*SKIP) signifies that whatever text was matched leading up to it cannot be part of a successful match. Consider: a+(*SKIP)b - If the subject is "aaaac...", after the first match attempt fails - (starting at the first character in the string), the starting point + If the subject is "aaaac...", after the first match attempt fails + (starting at the first character in the string), the starting point skips on to start the next attempt at "c". Note that a possessive quan- - tifer does not have the same effect as this example; although it would - suppress backtracking during the first match attempt, the second - attempt would start at the second character instead of skipping on to + tifer does not have the same effect as this example; although it would + suppress backtracking during the first match attempt, the second + attempt would start at the second character instead of skipping on to "c". (*SKIP:NAME) - When (*SKIP) has an associated name, its behaviour is modified. If the + When (*SKIP) has an associated name, its behaviour is modified. If the following pattern fails to match, the previous path through the pattern - is searched for the most recent (*MARK) that has the same name. If one - is found, the "bumpalong" advance is to the subject position that cor- - responds to that (*MARK) instead of to where (*SKIP) was encountered. + is searched for the most recent (*MARK) that has the same name. If one + is found, the "bumpalong" advance is to the subject position that cor- + responds to that (*MARK) instead of to where (*SKIP) was encountered. If no (*MARK) with a matching name is found, the (*SKIP) is ignored. (*THEN) or (*THEN:NAME) - This verb causes a skip to the next innermost alternative if the rest - of the pattern does not match. That is, it cancels pending backtrack- - ing, but only within the current alternative. Its name comes from the + This verb causes a skip to the next innermost alternative if the rest + of the pattern does not match. That is, it cancels pending backtrack- + ing, but only within the current alternative. Its name comes from the observation that it can be used for a pattern-based if-then-else block: ( COND1 (*THEN) FOO | COND2 (*THEN) BAR | COND3 (*THEN) BAZ ) ... - If the COND1 pattern matches, FOO is tried (and possibly further items - after the end of the group if FOO succeeds); on failure, the matcher - skips to the second alternative and tries COND2, without backtracking - into COND1. The behaviour of (*THEN:NAME) is exactly the same as - (*MARK:NAME)(*THEN). If (*THEN) is not inside an alternation, it acts + If the COND1 pattern matches, FOO is tried (and possibly further items + after the end of the group if FOO succeeds); on failure, the matcher + skips to the second alternative and tries COND2, without backtracking + into COND1. The behaviour of (*THEN:NAME) is exactly the same as + (*MARK:NAME)(*THEN). If (*THEN) is not inside an alternation, it acts like (*PRUNE). - Note that a subpattern that does not contain a | character is just a - part of the enclosing alternative; it is not a nested alternation with - only one alternative. The effect of (*THEN) extends beyond such a sub- - pattern to the enclosing alternative. Consider this pattern, where A, + Note that a subpattern that does not contain a | character is just a + part of the enclosing alternative; it is not a nested alternation with + only one alternative. The effect of (*THEN) extends beyond such a sub- + pattern to the enclosing alternative. Consider this pattern, where A, B, etc. are complex pattern fragments that do not contain any | charac- ters at this level: A (B(*THEN)C) | D - If A and B are matched, but there is a failure in C, matching does not + If A and B are matched, but there is a failure in C, matching does not backtrack into A; instead it moves to the next alternative, that is, D. - However, if the subpattern containing (*THEN) is given an alternative, + However, if the subpattern containing (*THEN) is given an alternative, it behaves differently: A (B(*THEN)C | (*FAIL)) | D - The effect of (*THEN) is now confined to the inner subpattern. After a + The effect of (*THEN) is now confined to the inner subpattern. After a failure in C, matching moves to (*FAIL), which causes the whole subpat- - tern to fail because there are no more alternatives to try. In this + tern to fail because there are no more alternatives to try. In this case, matching does now backtrack into A. Note also that a conditional subpattern is not considered as having two - alternatives, because only one is ever used. In other words, the | + alternatives, because only one is ever used. In other words, the | character in a conditional subpattern has a different meaning. Ignoring white space, consider: ^.*? (?(?=a) a | b(*THEN)c ) - If the subject is "ba", this pattern does not match. Because .*? is - ungreedy, it initially matches zero characters. The condition (?=a) - then fails, the character "b" is matched, but "c" is not. At this - point, matching does not backtrack to .*? as might perhaps be expected - from the presence of the | character. The conditional subpattern is + If the subject is "ba", this pattern does not match. Because .*? is + ungreedy, it initially matches zero characters. The condition (?=a) + then fails, the character "b" is matched, but "c" is not. At this + point, matching does not backtrack to .*? as might perhaps be expected + from the presence of the | character. The conditional subpattern is part of the single alternative that comprises the whole pattern, and so - the match fails. (If there was a backtrack into .*?, allowing it to + the match fails. (If there was a backtrack into .*?, allowing it to match "b", the match would succeed.) - The verbs just described provide four different "strengths" of control + The verbs just described provide four different "strengths" of control when subsequent matching fails. (*THEN) is the weakest, carrying on the - match at the next alternative. (*PRUNE) comes next, failing the match - at the current starting position, but allowing an advance to the next - character (for an unanchored pattern). (*SKIP) is similar, except that + match at the next alternative. (*PRUNE) comes next, failing the match + at the current starting position, but allowing an advance to the next + character (for an unanchored pattern). (*SKIP) is similar, except that the advance may be more than one character. (*COMMIT) is the strongest, causing the entire match to fail. @@ -7147,15 +7157,15 @@ BACKTRACKING CONTROL (A(*COMMIT)B(*THEN)C|D) - Once A has matched, PCRE is committed to this match, at the current - starting position. If subsequently B matches, but C does not, the nor- + Once A has matched, PCRE is committed to this match, at the current + starting position. If subsequently B matches, but C does not, the nor- mal (*THEN) action of trying the next alternative (that is, D) does not happen because (*COMMIT) overrides. SEE ALSO - pcreapi(3), pcrecallout(3), pcrematching(3), pcresyntax(3), pcre(3), + pcreapi(3), pcrecallout(3), pcrematching(3), pcresyntax(3), pcre(3), pcre16(3), pcre32(3). @@ -7168,11 +7178,11 @@ AUTHOR REVISION - Last updated: 10 September 2012 + Last updated: 11 November 2012 Copyright (c) 1997-2012 University of Cambridge. ------------------------------------------------------------------------------ - - + + PCRESYNTAX(3) PCRESYNTAX(3) @@ -7421,6 +7431,7 @@ OPTION SETTING (*UTF8) set UTF-8 mode: 8-bit library (PCRE_UTF8) (*UTF16) set UTF-16 mode: 16-bit library (PCRE_UTF16) (*UTF32) set UTF-32 mode: 32-bit library (PCRE_UTF32) + (*UTF) set appropriate UTF mode for the library in use (*UCP) set PCRE_UCP (use Unicode properties for \d etc) @@ -7547,11 +7558,11 @@ AUTHOR REVISION - Last updated: 25 August 2012 + Last updated: 11 November 2012 Copyright (c) 1997-2012 University of Cambridge. ------------------------------------------------------------------------------ - - + + PCREUNICODE(3) PCREUNICODE(3) @@ -7559,151 +7570,130 @@ NAME PCRE - Perl-compatible regular expressions -UTF-8, UTF-16, AND UNICODE PROPERTY SUPPORT - - From Release 8.30, in addition to its previous UTF-8 support, PCRE also - supports UTF-16 by means of a separate 16-bit library. This can be - built as well as, or instead of, the 8-bit library. +UTF-8, UTF-16, UTF-32, AND UNICODE PROPERTY SUPPORT - From Release 8.32, in addition to its previous UTF-8 and UTF-16 sup- - port, PCRE also supports UTF-32 by means of a separate 32-bit library. - This can be built as well as, or instead of, the 8-bit and 16-bit - libraries. + As well as UTF-8 support, PCRE also supports UTF-16 (from release 8.30) + and UTF-32 (from release 8.32), by means of two additional libraries. + They can be built as well as, or instead of, the 8-bit library. UTF-8 SUPPORT - In order process UTF-8 strings, you must build PCRE's 8-bit library - with UTF support, and, in addition, you must call pcre_compile() with - the PCRE_UTF8 option flag, or the pattern must start with the sequence - (*UTF8). When either of these is the case, both the pattern and any - subject strings that are matched against it are treated as UTF-8 - strings instead of strings of 1-byte characters. - - -UTF-16 SUPPORT + In order process UTF-8 strings, you must build PCRE's 8-bit library + with UTF support, and, in addition, you must call pcre_compile() with + the PCRE_UTF8 option flag, or the pattern must start with the sequence + (*UTF8) or (*UTF). When either of these is the case, both the pattern + and any subject strings that are matched against it are treated as + UTF-8 strings instead of strings of individual 1-byte characters. - In order process UTF-16 strings, you must build PCRE's 16-bit library - with UTF support, and, in addition, you must call pcre16_compile() with - the PCRE_UTF16 option flag, or the pattern must start with the sequence - (*UTF16). When either of these is the case, both the pattern and any - subject strings that are matched against it are treated as UTF-16 - strings instead of strings of 16-bit characters. +UTF-16 AND UTF-32 SUPPORT -UTF-32 SUPPORT - - In order process UTF-32 strings, you must build PCRE's 32-bit library - with UTF support, and, in addition, you must call pcre32_compile() with - the PCRE_UTF32 option flag, or the pattern must start with the sequence - (*UTF32). When either of these is the case, both the pattern and any - subject strings that are matched against it are treated as UTF-32 - strings instead of strings of 32-bit characters. + In order process UTF-16 or UTF-32 strings, you must build PCRE's 16-bit + or 32-bit library with UTF support, and, in addition, you must call + pcre16_compile() or pcre32_compile() with the PCRE_UTF16 or PCRE_UTF32 + option flag, as appropriate. Alternatively, the pattern must start with + the sequence (*UTF16), (*UTF32), as appropriate, or (*UTF), which can + be used with either library. When UTF mode is set, both the pattern and + any subject strings that are matched against it are treated as UTF-16 + or UTF-32 strings instead of strings of individual 16-bit or 32-bit + characters. UTF SUPPORT OVERHEAD - If you compile PCRE with UTF support, but do not use it at run time, - the library will be a bit bigger, but the additional run time overhead - is limited to testing the PCRE_UTF[8|16|32] flag occasionally, so + If you compile PCRE with UTF support, but do not use it at run time, + the library will be a bit bigger, but the additional run time overhead + is limited to testing the PCRE_UTF[8|16|32] flag occasionally, so should not be very big. UNICODE PROPERTY SUPPORT If PCRE is built with Unicode character property support (which implies - UTF support), the escape sequences \p{..}, \P{..}, and \X can be used. - The available properties that can be tested are limited to the general - category properties such as Lu for an upper case letter or Nd for a + UTF support), the escape sequences \p{..}, \P{..}, and \X can be used. + The available properties that can be tested are limited to the general + category properties such as Lu for an upper case letter or Nd for a decimal number, the Unicode script names such as Arabic or Han, and the - derived properties Any and L&. A full list is given in the pcrepattern - documentation. Only the short names for properties are supported. For - example, \p{L} matches a letter. Its Perl synonym, \p{Letter}, is not - supported. Furthermore, in Perl, many properties may optionally be - prefixed by "Is", for compatibility with Perl 5.6. PCRE does not sup- - port this. + derived properties Any and L&. Full lists is given in the pcrepattern + and pcresyntax documentation. Only the short names for properties are + supported. For example, \p{L} matches a letter. Its Perl synonym, + \p{Letter}, is not supported. Furthermore, in Perl, many properties + may optionally be prefixed by "Is", for compatibility with Perl 5.6. + PCRE does not support this. Validity of UTF-8 strings - When you set the PCRE_UTF8 flag, the byte strings passed as patterns + When you set the PCRE_UTF8 flag, the byte strings passed as patterns and subjects are (by default) checked for validity on entry to the rel- evant functions. The entire string is checked before any other process- - ing takes place. From release 7.3 of PCRE, the check is according the + ing takes place. From release 7.3 of PCRE, the check is according the rules of RFC 3629, which are themselves derived from the Unicode speci- - fication. Earlier releases of PCRE followed the rules of RFC 2279, - which allows the full range of 31-bit values (0 to 0x7FFFFFFF). The - current check allows only values in the range U+0 to U+10FFFF, exclud- - ing the surrogate area, and the non-characters. - - Excluded code points are the "Surrogate Area" of Unicode. They are - reserved for use by UTF-16, where they are used in pairs to encode - codepoints with values greater than 0xFFFF. The code points that are - encoded by UTF-16 pairs are available independently in the UTF-8 encod- - ing. (In other words, the whole surrogate thing is a fudge for UTF-16 - which unfortunately messes up UTF-8.) - - Also excluded are the "Non-Characters" code points, which are U+FDD0 to - U+FDEF and the last two code points in each plane, U+??FFFE and + fication. Earlier releases of PCRE followed the rules of RFC 2279, + which allows the full range of 31-bit values (0 to 0x7FFFFFFF). The + current check allows only values in the range U+0 to U+10FFFF, exclud- + ing the surrogate area and the non-characters. + + Characters in the "Surrogate Area" of Unicode are reserved for use by + UTF-16, where they are used in pairs to encode codepoints with values + greater than 0xFFFF. The code points that are encoded by UTF-16 pairs + are available independently in the UTF-8 and UTF-32 encodings. (In + other words, the whole surrogate thing is a fudge for UTF-16 which + unfortunately messes up UTF-8 and UTF-32.) + + Also excluded are the "Non-Character" code points, which are U+FDD0 to + U+FDEF and the last two code points in each plane, U+??FFFE and U+??FFFF. If an invalid UTF-8 string is passed to PCRE, an error return is given. - At compile time, the only additional information is the offset to the + At compile time, the only additional information is the offset to the first byte of the failing character. The run-time functions pcre_exec() - and pcre_dfa_exec() also pass back this information, as well as a more - detailed reason code if the caller has provided memory in which to do + and pcre_dfa_exec() also pass back this information, as well as a more + detailed reason code if the caller has provided memory in which to do this. - In some situations, you may already know that your strings are valid, - and therefore want to skip these checks in order to improve perfor- - mance, for example in the case of a long subject string that is being - scanned repeatedly with different patterns. If you set the - PCRE_NO_UTF8_CHECK flag at compile time or at run time, PCRE assumes - that the pattern or subject it is given (respectively) contains only - valid UTF-8 codes. In this case, it does not diagnose an invalid UTF-8 - string. - - If you pass an invalid UTF-8 string when PCRE_NO_UTF8_CHECK is set, - what happens depends on why the string is invalid. If the string con- - forms to the "old" definition of UTF-8 (RFC 2279), it is processed as a - string of characters in the range 0 to 0x7FFFFFFF by pcre_dfa_exec() - and the interpreted version of pcre_exec(). In other words, apart from - the initial validity test, these functions (when in UTF-8 mode) handle - strings according to the more liberal rules of RFC 2279. However, the - just-in-time (JIT) optimization for pcre_exec() supports only RFC 3629. - If you are using JIT optimization, or if the string does not even con- - form to RFC 2279, the result is undefined. Your program may crash. - - If you want to process strings of values in the full range 0 to - 0x7FFFFFFF, encoded in a UTF-8-like manner as per the old RFC, you can - set PCRE_NO_UTF8_CHECK to bypass the more restrictive test. However, in - this situation, you will have to apply your own validity check, and - avoid the use of JIT optimization. + In some situations, you may already know that your strings are valid, + and therefore want to skip these checks in order to improve perfor- + mance, for example in the case of a long subject string that is being + scanned repeatedly. If you set the PCRE_NO_UTF8_CHECK flag at compile + time or at run time, PCRE assumes that the pattern or subject it is + given (respectively) contains only valid UTF-8 codes. In this case, it + does not diagnose an invalid UTF-8 string. + + Note that passing PCRE_NO_UTF8_CHECK to pcre_compile() just disables + the check for the pattern; it does not also apply to subject strings. + If you want to disable the check for a subject string you must pass + this option to pcre_exec() or pcre_dfa_exec(). + + If you pass an invalid UTF-8 string when PCRE_NO_UTF8_CHECK is set, the + result is undefined and your program may crash. Validity of UTF-16 strings When you set the PCRE_UTF16 flag, the strings of 16-bit data units that are passed as patterns and subjects are (by default) checked for valid- - ity on entry to the relevant functions. Values other than those in the + ity on entry to the relevant functions. Values other than those in the surrogate range U+D800 to U+DFFF are independent code points. Values in the surrogate range must be used in pairs in the correct manner. - Excluded are the "Non-Characters" code points, which are U+FDD0 to - U+FDEF and the last two code points in each plane, U+??FFFE and + Excluded are the "Non-Character" code points, which are U+FDD0 to + U+FDEF and the last two code points in each plane, U+??FFFE and U+??FFFF. - If an invalid UTF-16 string is passed to PCRE, an error return is - given. At compile time, the only additional information is the offset + If an invalid UTF-16 string is passed to PCRE, an error return is + given. At compile time, the only additional information is the offset to the first data unit of the failing character. The run-time functions pcre16_exec() and pcre16_dfa_exec() also pass back this information, as - well as a more detailed reason code if the caller has provided memory + well as a more detailed reason code if the caller has provided memory in which to do this. - In some situations, you may already know that your strings are valid, - and therefore want to skip these checks in order to improve perfor- - mance. If you set the PCRE_NO_UTF16_CHECK flag at compile time or at + In some situations, you may already know that your strings are valid, + and therefore want to skip these checks in order to improve perfor- + mance. If you set the PCRE_NO_UTF16_CHECK flag at compile time or at run time, PCRE assumes that the pattern or subject it is given (respec- tively) contains only valid UTF-16 sequences. In this case, it does not - diagnose an invalid UTF-16 string. + diagnose an invalid UTF-16 string. However, if an invalid string is + passed, the result is undefined. Validity of UTF-32 strings @@ -7711,88 +7701,77 @@ UNICODE PROPERTY SUPPORT are passed as patterns and subjects are (by default) checked for valid- ity on entry to the relevant functions. This check allows only values in the range U+0 to U+10FFFF, excluding the surrogate area U+D800 to - U+DFFF, and the "Non-Characters" code points, which are U+FDD0 to - U+FDEF and the last two characters in each plane, U+??FFFE and - U+??FFFF. + U+DFFF, and the "Non-Character" code points, which are U+FDD0 to U+FDEF + and the last two characters in each plane, U+??FFFE and U+??FFFF. - If an invalid UTF-32 string is passed to PCRE, an error return is - given. At compile time, the only additional information is the offset + If an invalid UTF-32 string is passed to PCRE, an error return is + given. At compile time, the only additional information is the offset to the first data unit of the failing character. The run-time functions pcre32_exec() and pcre32_dfa_exec() also pass back this information, as - well as a more detailed reason code if the caller has provided memory + well as a more detailed reason code if the caller has provided memory in which to do this. - In some situations, you may already know that your strings are valid, - and therefore want to skip these checks in order to improve perfor- - mance. If you set the PCRE_NO_UTF32_CHECK flag at compile time or at + In some situations, you may already know that your strings are valid, + and therefore want to skip these checks in order to improve perfor- + mance. If you set the PCRE_NO_UTF32_CHECK flag at compile time or at run time, PCRE assumes that the pattern or subject it is given (respec- tively) contains only valid UTF-32 sequences. In this case, it does not - diagnose an invalid UTF-32 string. - - UTF-32 only uses the lowest 21 bits of the 32 bit characters, and the - application may use the upper bits for internal purposes. To allow you - to pass these strings to PCRE unmodified (thus avoiding the costly - operation of creating a copy of the string with the upper bits masked), - PCRE accepts these 32-bit character strings as-is, but only uses the - lowest 21 bits for matching, if you pass the PCRE_NO_UTF32_CHECK flag - to pcre32_exec() and pcre32_dfa_exec(). However, in this situation, you - will have to apply your own validity check, and avoid the use of JIT - optimization. (The latter restriction may be lifter in a later version - of PCRE.) + diagnose an invalid UTF-32 string. However, if an invalid string is + passed, the result is undefined. General comments about UTF modes - 1. Codepoints less than 256 can be specified by either braced or - unbraced hexadecimal escape sequences (for example, \x{b3} or \xb3). - Larger values have to use braced sequences. + 1. Codepoints less than 256 can be specified in patterns by either + braced or unbraced hexadecimal escape sequences (for example, \x{b3} or + \xb3). Larger values have to use braced sequences. - 2. Octal numbers up to \777 are recognized, and in UTF-8 mode, they + 2. Octal numbers up to \777 are recognized, and in UTF-8 mode they match two-byte characters for values greater than \177. 3. Repeat quantifiers apply to complete UTF characters, not to individ- ual data units, for example: \x{100}{3}. - 4. The dot metacharacter matches one UTF character instead of a single + 4. The dot metacharacter matches one UTF character instead of a single data unit. - 5. The escape sequence \C can be used to match a single byte in UTF-8 - mode, or a single 16-bit data unit in UTF-16 mode, or a single 32-bit - data unit in UTF-32 mode, but its use can lead to some strange effects - because it breaks up multi-unit characters (see the description of \C - in the pcrepattern documentation). The use of \C is not supported in - the alternative matching function pcre[16|32]_dfa_exec(), nor is it + 5. The escape sequence \C can be used to match a single byte in UTF-8 + mode, or a single 16-bit data unit in UTF-16 mode, or a single 32-bit + data unit in UTF-32 mode, but its use can lead to some strange effects + because it breaks up multi-unit characters (see the description of \C + in the pcrepattern documentation). The use of \C is not supported in + the alternative matching function pcre[16|32]_dfa_exec(), nor is it supported in UTF mode by the JIT optimization of pcre[16|32]_exec(). If - JIT optimization is requested for a UTF pattern that contains \C, it + JIT optimization is requested for a UTF pattern that contains \C, it will not succeed, and so the matching will be carried out by the normal interpretive function. - 6. The character escapes \b, \B, \d, \D, \s, \S, \w, and \W correctly + 6. The character escapes \b, \B, \d, \D, \s, \S, \w, and \W correctly test characters of any code value, but, by default, the characters that - PCRE recognizes as digits, spaces, or word characters remain the same - set as in non-UTF mode, all with values less than 256. This remains - true even when PCRE is built to include Unicode property support, + PCRE recognizes as digits, spaces, or word characters remain the same + set as in non-UTF mode, all with values less than 256. This remains + true even when PCRE is built to include Unicode property support, because to do otherwise would slow down PCRE in many common cases. Note - in particular that this applies to \b and \B, because they are defined + in particular that this applies to \b and \B, because they are defined in terms of \w and \W. If you really want to test for a wider sense of, - say, "digit", you can use explicit Unicode property tests such as + say, "digit", you can use explicit Unicode property tests such as \p{Nd}. Alternatively, if you set the PCRE_UCP option, the way that the - character escapes work is changed so that Unicode properties are used + character escapes work is changed so that Unicode properties are used to determine which characters match. There are more details in the sec- tion on generic character types in the pcrepattern documentation. - 7. Similarly, characters that match the POSIX named character classes + 7. Similarly, characters that match the POSIX named character classes are all low-valued characters, unless the PCRE_UCP option is set. - 8. However, the horizontal and vertical white space matching escapes - (\h, \H, \v, and \V) do match all the appropriate Unicode characters, + 8. However, the horizontal and vertical white space matching escapes + (\h, \H, \v, and \V) do match all the appropriate Unicode characters, whether or not PCRE_UCP is set. - 9. Case-insensitive matching applies only to characters whose values - are less than 128, unless PCRE is built with Unicode property support. - A few Unicode characters such as Greek sigma have more than two code- + 9. Case-insensitive matching applies only to characters whose values + are less than 128, unless PCRE is built with Unicode property support. + A few Unicode characters such as Greek sigma have more than two code- points that are case-equivalent. Up to and including PCRE release 8.31, - only one-to-one case mappings were supported, but later releases (with - Unicode property support) do treat as case-equivalent all versions of + only one-to-one case mappings were supported, but later releases (with + Unicode property support) do treat as case-equivalent all versions of characters such as Greek sigma. @@ -7805,11 +7784,11 @@ AUTHOR REVISION - Last updated: 25 September 2012 + Last updated: 11 November 2012 Copyright (c) 1997-2012 University of Cambridge. ------------------------------------------------------------------------------ - - + + PCREJIT(3) PCREJIT(3) @@ -8227,8 +8206,8 @@ REVISION Last updated: 31 October 2012 Copyright (c) 1997-2012 University of Cambridge. ------------------------------------------------------------------------------ - - + + PCREPARTIAL(3) PCREPARTIAL(3) @@ -8678,8 +8657,8 @@ REVISION Last updated: 24 June 2012 Copyright (c) 1997-2012 University of Cambridge. ------------------------------------------------------------------------------ - - + + PCREPRECOMPILE(3) PCREPRECOMPILE(3) @@ -8813,8 +8792,8 @@ REVISION Last updated: 24 June 2012 Copyright (c) 1997-2012 University of Cambridge. ------------------------------------------------------------------------------ - - + + PCREPERFORM(3) PCREPERFORM(3) @@ -8983,8 +8962,8 @@ REVISION Last updated: 25 August 2012 Copyright (c) 1997-2012 University of Cambridge. ------------------------------------------------------------------------------ - - + + PCREPOSIX(3) PCREPOSIX(3) @@ -9248,8 +9227,8 @@ REVISION Last updated: 09 January 2012 Copyright (c) 1997-2012 University of Cambridge. ------------------------------------------------------------------------------ - - + + PCRECPP(3) PCRECPP(3) @@ -9591,8 +9570,8 @@ REVISION Last updated: 08 January 2012 ------------------------------------------------------------------------------ - - + + PCRESAMPLE(3) PCRESAMPLE(3) @@ -9740,8 +9719,8 @@ REVISION Last updated: 04 May 2012 Copyright (c) 1997-2012 University of Cambridge. ------------------------------------------------------------------------------ - - + + PCRESTACK(3) PCRESTACK(3) @@ -9926,5 +9905,5 @@ REVISION Last updated: 24 June 2012 Copyright (c) 1997-2012 University of Cambridge. ------------------------------------------------------------------------------ - - + + diff --git a/doc/pcre32.3 b/doc/pcre32.3 index e8b284d..48205ca 100644 --- a/doc/pcre32.3 +++ b/doc/pcre32.3 @@ -150,7 +150,7 @@ PCRE - Perl-compatible regular expressions Starting with release 8.32, it is possible to compile a PCRE library that supports 32-bit character strings, including UTF-32 strings, as well as or instead of the original 8-bit library. This work was done by Christian Persch, -based on the work done by Zoltan Herczeg for the 16-bit library. All three +based on the work done by Zoltan Herczeg for the 16-bit library. All three libraries contain identical sets of functions, used in exactly the same way. Only the names of the functions and the data types of their arguments and results are different. To avoid over-complication and reduce the documentation diff --git a/doc/pcre_jit_exec.3 b/doc/pcre_jit_exec.3 index 84c94a5..8b9d05b 100644 --- a/doc/pcre_jit_exec.3 +++ b/doc/pcre_jit_exec.3 @@ -50,7 +50,7 @@ It returns offsets to captured substrings. Its arguments are: \fIoptions\fP Option bits \fIovector\fP Points to a vector of ints for result offsets \fIovecsize\fP Number of elements in the vector (a multiple of 3) - \fIjstack\fP Pointer to a JIT stack + \fIjstack\fP Pointer to a JIT stack .sp The allowed options are: .sp @@ -73,7 +73,7 @@ The allowed options are: PCRE_PARTIAL_HARD Return PCRE_ERROR_PARTIAL for a partial match if that is found before a full match .sp -However, the PCRE_NO_UTF[8|16|32]_CHECK options have no effect, as this check +However, the PCRE_NO_UTF[8|16|32]_CHECK options have no effect, as this check is never applied. For details of partial matching, see the .\" HREF \fBpcrepartial\fP diff --git a/doc/pcreapi.3 b/doc/pcreapi.3 index e9e397c..0eebf94 100644 --- a/doc/pcreapi.3 +++ b/doc/pcreapi.3 @@ -161,7 +161,7 @@ by UTF16 or UTF32, respectively. This facility is in fact just cosmetic; the 16-bit and 32-bit option names define the same bit values. .P References to bytes and UTF-8 in this document should be read as references to -16-bit data quantities and UTF-16 when using the 16-bit library, or 32-bit data +16-bit data quantities and UTF-16 when using the 16-bit library, or 32-bit data quantities and UTF-32 when using the 32-bit library, unless specified otherwise. More details of the specific differences for the 16-bit and 32-bit libraries are given in the @@ -447,7 +447,7 @@ unaligned)". If JIT support is not available, the result is NULL. PCRE_CONFIG_NEWLINE .sp The output is an integer whose value specifies the default character sequence -that is recognized as meaning "newline". The values that are supported in +that is recognized as meaning "newline". The values that are supported in ASCII/Unicode environments are: 10 for LF, 13 for CR, 3338 for CRLF, -2 for ANYCRLF, and -1 for ANY. In EBCDIC environments, CR, ANYCRLF, and ANY yield the same values. However, the value for LF is normally 21, though some EBCDIC @@ -767,7 +767,7 @@ indicated by a single character (CR or LF, respectively). Setting PCRE_NEWLINE_CRLF specifies that a newline is indicated by the two-character CRLF sequence. Setting PCRE_NEWLINE_ANYCRLF specifies that any of the three preceding sequences should be recognized. Setting PCRE_NEWLINE_ANY specifies -that any Unicode newline sequence should be recognized. +that any Unicode newline sequence should be recognized. .P In an ASCII/Unicode environment, the Unicode newline sequences are the three just mentioned, plus the single characters VT (vertical tab, U+000B), FF (form @@ -777,8 +777,8 @@ recognized only in UTF-8 mode. .P When PCRE is compiled to run in an EBCDIC (mainframe) environment, the code for CR is 0x0d, the same as ASCII. However, the character code for LF is normally -0x15, though in some EBCDIC environments 0x25 is used. Whichever of these is -not LF is made to correspond to Unicode's NEL character. EBCDIC codes are all +0x15, though in some EBCDIC environments 0x25 is used. Whichever of these is +not LF is made to correspond to Unicode's NEL character. EBCDIC codes are all less than 256. For more details, see the .\" HREF \fBpcrebuild\fP @@ -875,8 +875,8 @@ this check for performance reasons, you can set the PCRE_NO_UTF8_CHECK option. When it is set, the effect of passing an invalid UTF-8 string as a pattern is undefined. It may cause your program to crash. Note that this option can also be passed to \fBpcre_exec()\fP and \fBpcre_dfa_exec()\fP, to suppress the -validity checking of subject strings only. If the same string is being matched -many times, the option can be safely set for the second and subsequent +validity checking of subject strings only. If the same string is being matched +many times, the option can be safely set for the second and subsequent matchings to improve performance. . . @@ -1005,7 +1005,7 @@ in the section on matching a pattern. If studying the pattern does not produce any useful information, \fBpcre_study()\fP returns NULL by default. In that circumstance, if the calling program wants to pass any of the other fields to \fBpcre_exec()\fP or -\fBpcre_dfa_exec()\fP, it must set up its own \fBpcre_extra\fP block. However, +\fBpcre_dfa_exec()\fP, it must set up its own \fBpcre_extra\fP block. However, if \fBpcre_study()\fP is called with the PCRE_STUDY_EXTRA_NEEDED option, it returns a \fBpcre_extra\fP block even if studying did not find any additional information. It may still return NULL, however, if an error occurs in @@ -2247,7 +2247,7 @@ so that it runs on the new host. .sp This error is returned when a pattern that was successfully studied using a JIT compile option is being matched, but the matching mode (partial or complete -match) does not correspond to any JIT compilation mode. When the JIT fast path +match) does not correspond to any JIT compilation mode. When the JIT fast path function is used, this error may be also given for invalid options. See the .\" HREF \fBpcrejit\fP @@ -2256,8 +2256,8 @@ documentation for more details. .sp PCRE_ERROR_BADLENGTH (-32) .sp -This error is given if \fBpcre_exec()\fP is called with a negative value for -the \fIlength\fP argument. +This error is given if \fBpcre_exec()\fP is called with a negative value for +the \fIlength\fP argument. .P Error numbers -16 to -20, -22, and 30 are not used by \fBpcre_exec()\fP. . @@ -2275,7 +2275,7 @@ and .\" HREF \fBpcre32\fP .\" -pages. +pages. .P When \fBpcre_exec()\fP returns either PCRE_ERROR_BADUTF8 or PCRE_ERROR_SHORTUTF8, and the size of the output vector (\fIovecsize\fP) is at diff --git a/doc/pcrebuild.3 b/doc/pcrebuild.3 index 9054ead..b9ae474 100644 --- a/doc/pcrebuild.3 +++ b/doc/pcrebuild.3 @@ -14,8 +14,8 @@ options can be selected in both Unix-like and non-Unix-like environments using the GUI facility of \fBcmake-gui\fP if you are using \fBCMake\fP instead of \fBconfigure\fP to build PCRE. .P -There is a lot more information about building PCRE without using -\fBconfigure\fP (including information about using \fBCMake\fP or building "by +There is a lot more information about building PCRE without using +\fBconfigure\fP (including information about using \fBCMake\fP or building "by hand") in the file called \fINON-AUTOTOOLS-BUILD\fP, which is part of the PCRE distribution. You should consult this file as well as the \fIREADME\fP file if you are building in a non-Unix-like environment. @@ -346,18 +346,18 @@ to the \fBconfigure\fP command. This setting implies an EBCDIC environment (for example, an IBM mainframe operating system). The --enable-ebcdic option is incompatible with --enable-utf. .P -The EBCDIC character that corresponds to an ASCII LF is assumed to have the -value 0x15 by default. However, in some EBCDIC environments, 0x25 is used. In +The EBCDIC character that corresponds to an ASCII LF is assumed to have the +value 0x15 by default. However, in some EBCDIC environments, 0x25 is used. In such an environment you should use .sp --enable-ebcdic-nl25 .sp -as well as, or instead of, --enable-ebcdic. The EBCDIC character for CR has the -same value as in ASCII, namely, 0x0d. Whichever of 0x15 and 0x25 is \fInot\fP -chosen as LF is made to correspond to the Unicode NEL character (which, in +as well as, or instead of, --enable-ebcdic. The EBCDIC character for CR has the +same value as in ASCII, namely, 0x0d. Whichever of 0x15 and 0x25 is \fInot\fP +chosen as LF is made to correspond to the Unicode NEL character (which, in Unicode, is 0x85). .P -The options that select newline behaviour, such as --enable-newline-is-cr, +The options that select newline behaviour, such as --enable-newline-is-cr, and equivalent run-time options, refer to these character values in an EBCDIC environment. . @@ -447,7 +447,7 @@ code coverage report for its test suite. To enable this, you must install .sp --enable-coverage .sp -to the \fBconfigure\fP command and build PCRE in the usual way. +to the \fBconfigure\fP command and build PCRE in the usual way. .P Note that using \fBccache\fP (a caching C compiler) is incompatible with code coverage reporting. If you have configured \fBccache\fP to run automatically @@ -471,7 +471,7 @@ then "make coverage-report". This zeroes the coverage counters, but does nothing else. .sp make coverage-baseline -.sp +.sp This captures baseline coverage information. .sp make coverage-report @@ -490,9 +490,9 @@ created at compile time (*.gcno). .sp make coverage-clean .sp -This cleans all coverage data including the generated coverage report. For more -information about code coverage, see the \fBgcov\fP and \fBlcov\fP -documentation. +This cleans all coverage data including the generated coverage report. For more +information about code coverage, see the \fBgcov\fP and \fBlcov\fP +documentation. . . .SH "SEE ALSO" diff --git a/doc/pcrejit.3 b/doc/pcrejit.3 index a492dcd..f05ad65 100644 --- a/doc/pcrejit.3 +++ b/doc/pcrejit.3 @@ -41,7 +41,7 @@ JIT. The support is limited to the following hardware platforms: Intel x86 32-bit and 64-bit MIPS 32-bit Power PC 32-bit and 64-bit - SPARC 32-bit (experimental) + SPARC 32-bit (experimental) .sp If --enable-jit is set on an unsupported platform, compilation fails. .P @@ -49,8 +49,8 @@ A program that is linked with PCRE 8.20 or later can tell if JIT support is available by calling \fBpcre_config()\fP with the PCRE_CONFIG_JIT option. The result is 1 when JIT is available, and 0 otherwise. However, a simple program does not need to check this in order to use JIT. The normal API is implemented -in a way that falls back to the interpretive code if JIT is not available. For -programs that need the best possible performance, there is also a "fast path" +in a way that falls back to the interpretive code if JIT is not available. For +programs that need the best possible performance, there is also a "fast path" API that is JIT-specific. .P If your program may sometimes be linked with versions of PCRE that are older @@ -387,17 +387,17 @@ callback. .SH "JIT FAST PATH API" .rs .sp -Because the API described above falls back to interpreted execution when JIT is -not available, it is convenient for programs that are written for general use -in many environments. However, calling JIT via \fBpcre_exec()\fP does have a -performance impact. Programs that are written for use where JIT is known to be +Because the API described above falls back to interpreted execution when JIT is +not available, it is convenient for programs that are written for general use +in many environments. However, calling JIT via \fBpcre_exec()\fP does have a +performance impact. Programs that are written for use where JIT is known to be available, and which need the best possible performance, can instead use a "fast path" API to call JIT execution directly instead of calling -\fBpcre_exec()\fP (obviously only for patterns that have been successfully +\fBpcre_exec()\fP (obviously only for patterns that have been successfully studied by JIT). .P -The fast path function is called \fBpcre_jit_exec()\fP, and it takes exactly -the same arguments as \fBpcre_exec()\fP, plus one additional argument that +The fast path function is called \fBpcre_jit_exec()\fP, and it takes exactly +the same arguments as \fBpcre_exec()\fP, plus one additional argument that must point to a JIT stack. The JIT stack arrangements described above do not apply. The return values are the same as for \fBpcre_exec()\fP. .P @@ -408,7 +408,7 @@ given. Also, unless PCRE_NO_UTF[8|16|32] is set, a UTF subject string is tested for validity. In the interests of speed, these checks do not happen on the JIT fast path, and if invalid data is passed, the result is undefined. .P -Bypassing the sanity checks and the \fBpcre_exec()\fP wrapping can give +Bypassing the sanity checks and the \fBpcre_exec()\fP wrapping can give speedups of more than 10%. . . diff --git a/doc/pcrepattern.3 b/doc/pcrepattern.3 index 991c52d..c9c7b45 100644 --- a/doc/pcrepattern.3 +++ b/doc/pcrepattern.3 @@ -32,7 +32,7 @@ these special sequences: (*UTF8) (*UTF16) (*UTF32) - (*UTF) + (*UTF) .sp (*UTF) is a generic sequence that can be used with any of the libraries. Starting a pattern with such a sequence is equivalent to setting the relevant @@ -76,10 +76,10 @@ page. .SH "EBCDIC CHARACTER CODES" .rs .sp -PCRE can be compiled to run in an environment that uses EBCDIC as its character -code rather than ASCII or Unicode (typically a mainframe system). In the -sections below, character code values are ASCII or Unicode; in an EBCDIC -environment these characters may have different code values, and there are no +PCRE can be compiled to run in an environment that uses EBCDIC as its character +code rather than ASCII or Unicode (typically a mainframe system). In the +sections below, character code values are ASCII or Unicode; in an EBCDIC +environment these characters may have different code values, and there are no code points greater than 255. . . @@ -274,7 +274,7 @@ recognized when PCRE is compiled in EBCDIC mode, where data items are always bytes. In this mode, all values are valid after \ec. If the next character is a lower case letter, it is converted to upper case. Then the 0xc0 bits of the byte are inverted. Thus \ecA becomes hex 01, as in ASCII (A is C1), but because -the EBCDIC letters are disjoint, \ecZ becomes hex 29 (Z is E9), and other +the EBCDIC letters are disjoint, \ecZ becomes hex 29 (Z is E9), and other characters also generate different values. .P By default, after \ex, from zero to two hexadecimal digits are read (letters @@ -835,16 +835,16 @@ property, and creating rules that use these properties to define the boundaries of extended grapheme clusters. In releases of PCRE later than 8.31, \eX matches one of these clusters. .P -\eX always matches at least one character. Then it decides whether to add +\eX always matches at least one character. Then it decides whether to add additional characters according to the following rules for ending a cluster: .P 1. End at the end of the subject string. .P 2. Do not end between CR and LF; otherwise end after any control character. .P -3. Do not break Hangul (a Korean script) syllable sequences. Hangul characters +3. Do not break Hangul (a Korean script) syllable sequences. Hangul characters are of five types: L, V, T, LV, and LVT. An L character may be followed by an -L, V, LV, or LVT character; an LV or V character may be followed by a V or T +L, V, LV, or LVT character; an LV or V character may be followed by a V or T character; an LVT or T character may be follwed only by a T character. .P 4. Do not end before extending characters or spacing marks. Characters with @@ -979,8 +979,8 @@ regular expression. .SH "CIRCUMFLEX AND DOLLAR" .rs .sp -The circumflex and dollar metacharacters are zero-width assertions. That is, -they test for a particular condition being true without consuming any +The circumflex and dollar metacharacters are zero-width assertions. That is, +they test for a particular condition being true without consuming any characters from the subject string. .P Outside a character class, in the default matching mode, the circumflex @@ -1693,7 +1693,7 @@ one succeeds. Consider this pattern: .sp (?>.*?a)b .sp -It matches "ab" in the subject "aab". The use of the backtracking control verbs +It matches "ab" in the subject "aab". The use of the backtracking control verbs (*PRUNE) and (*SKIP) also disable this optimization. .P When a capturing subpattern is repeated, the value captured is the substring diff --git a/doc/pcretest.1 b/doc/pcretest.1 index c3cef3d..41ef6ac 100644 --- a/doc/pcretest.1 +++ b/doc/pcretest.1 @@ -25,7 +25,7 @@ and .\" HREF \fBpcre32\fP .\" -documentation. +documentation. .P The input for \fBpcretest\fP is a sequence of regular expression patterns and strings to be matched, as described below. The output shows the result of each @@ -36,7 +36,7 @@ As PCRE has evolved, it has acquired many different features, and as a result, \fBpcretest\fP now has rather a lot of obscure options for testing every possible feature. Some of these options are specifically designed for use in conjunction with the test script and data files that are distributed as part of -PCRE, and are unlikely to be of use otherwise. They are all documented here, +PCRE, and are unlikely to be of use otherwise. They are all documented here, but without much justification. . . @@ -94,7 +94,7 @@ functionality is intended for use in scripts such as \fBRunTest\fP. The following options output the value indicated: .sp ebcdic-nl the code for LF (= NL) in an EBCDIC environment: - 0x15 or 0x25 + 0x15 or 0x25 0 if used in an ASCII environment linksize the internal link size (2, 3, or 4) newline the default newline setting: @@ -177,7 +177,7 @@ If \fB-s++\fP is used instead of \fB-s+\fP (with or without a following digit), the text "(JIT)" is added to the first output line after a match or no match when JIT-compiled code was actually used. .sp -Note that there are pattern options that can override \fB-s\fP, either +Note that there are pattern options that can override \fB-s\fP, either specifying no studying at all, or suppressing JIT compilation. .sp If the \fB/I\fP or \fB/D\fP option is present on a pattern (requesting output @@ -310,8 +310,8 @@ sections. \fB/X\fP set PCRE_EXTRA \fB/x\fP set PCRE_EXTENDED \fB/Y\fP set PCRE_NO_START_OPTIMIZE - \fB/Z\fP don't show lengths in \fB/B\fP output -.sp + \fB/Z\fP don't show lengths in \fB/B\fP output +.sp \fB/<any>\fP set PCRE_NEWLINE_ANY \fB/<anycrlf>\fP set PCRE_NEWLINE_ANYCRLF \fB/<cr>\fP set PCRE_NEWLINE_CR @@ -485,11 +485,11 @@ JIT compiled code is also output. .P The \fB/S\fP modifier causes \fBpcre[16|32]_study()\fP to be called after the expression has been compiled, and the results used when the expression is -matched. There are a number of qualifying characters that may follow \fB/S\fP. +matched. There are a number of qualifying characters that may follow \fB/S\fP. They may appear in any order. .P -If \fBS\fP is followed by an exclamation mark, \fBpcre[16|32]_study()\fP is called -with the PCRE_STUDY_EXTRA_NEEDED option, causing it always to return a +If \fBS\fP is followed by an exclamation mark, \fBpcre[16|32]_study()\fP is called +with the PCRE_STUDY_EXTRA_NEEDED option, causing it always to return a \fBpcre_extra\fP block, even when studying discovers no useful information. .P If \fB/S\fP is followed by a second S character, it suppresses studying, even diff --git a/doc/pcreunicode.3 b/doc/pcreunicode.3 index 3faaa70..d4ffcc7 100644 --- a/doc/pcreunicode.3 +++ b/doc/pcreunicode.3 @@ -26,7 +26,7 @@ instead of strings of individual 1-byte characters. .SH "UTF-16 AND UTF-32 SUPPORT" .rs .sp -In order process UTF-16 or UTF-32 strings, you must build PCRE's 16-bit or +In order process UTF-16 or UTF-32 strings, you must build PCRE's 16-bit or 32-bit library with UTF support, and, in addition, you must call .\" HREF \fBpcre16_compile()\fP @@ -90,7 +90,7 @@ Characters in the "Surrogate Area" of Unicode are reserved for use by UTF-16, where they are used in pairs to encode codepoints with values greater than 0xFFFF. The code points that are encoded by UTF-16 pairs are available independently in the UTF-8 and UTF-32 encodings. (In other words, the whole -surrogate thing is a fudge for UTF-16 which unfortunately messes up UTF-8 and +surrogate thing is a fudge for UTF-16 which unfortunately messes up UTF-8 and UTF-32.) .P Also excluded are the "Non-Character" code points, which are U+FDD0 to U+FDEF @@ -109,12 +109,12 @@ If you set the PCRE_NO_UTF8_CHECK flag at compile time or at run time, PCRE assumes that the pattern or subject it is given (respectively) contains only valid UTF-8 codes. In this case, it does not diagnose an invalid UTF-8 string. .P -Note that passing PCRE_NO_UTF8_CHECK to \fBpcre_compile()\fP just disables the -check for the pattern; it does not also apply to subject strings. If you want +Note that passing PCRE_NO_UTF8_CHECK to \fBpcre_compile()\fP just disables the +check for the pattern; it does not also apply to subject strings. If you want to disable the check for a subject string you must pass this option to \fBpcre_exec()\fP or \fBpcre_dfa_exec()\fP. .P -If you pass an invalid UTF-8 string when PCRE_NO_UTF8_CHECK is set, the result +If you pass an invalid UTF-8 string when PCRE_NO_UTF8_CHECK is set, the result is undefined and your program may crash. . . @@ -166,7 +166,7 @@ In some situations, you may already know that your strings are valid, and therefore want to skip these checks in order to improve performance. If you set the PCRE_NO_UTF32_CHECK flag at compile time or at run time, PCRE assumes that the pattern or subject it is given (respectively) contains only valid UTF-32 -sequences. In this case, it does not diagnose an invalid UTF-32 string. +sequences. In this case, it does not diagnose an invalid UTF-32 string. However, if an invalid string is passed, the result is undefined. . . @@ -105,7 +105,7 @@ compiling). Some options for pcre_compile() change its behaviour but do not affect the behaviour of the execution functions. Other options are passed through to the execution functions and affect their behaviour, with or without affecting the -behaviour of pcre_compile(). +behaviour of pcre_compile(). Options that can be passed to pcre_compile() are tagged Cx below, with these variants: diff --git a/pcre_compile.c b/pcre_compile.c index aff0208..5f0c8ed 100644 --- a/pcre_compile.c +++ b/pcre_compile.c @@ -80,12 +80,12 @@ to check them every time. */ /* Definitions to allow mutual recursion */ static int - add_list_to_class(pcre_uint8 *, pcre_uchar **, int, compile_data *, + add_list_to_class(pcre_uint8 *, pcre_uchar **, int, compile_data *, const pcre_uint32 *, unsigned int); static BOOL compile_regex(int, pcre_uchar **, const pcre_uchar **, int *, BOOL, BOOL, int, int, - pcre_uint32 *, pcre_int32 *, pcre_uint32 *, pcre_int32 *, branch_chain *, + pcre_uint32 *, pcre_int32 *, pcre_uint32 *, pcre_int32 *, branch_chain *, compile_data *, int *); @@ -773,7 +773,7 @@ Returns: zero => a data character */ static int -check_escape(const pcre_uchar **ptrptr, pcre_uint32 *chptr, int *errorcodeptr, +check_escape(const pcre_uchar **ptrptr, pcre_uint32 *chptr, int *errorcodeptr, int bracount, int options, BOOL isclass) { /* PCRE_UTF16 has the same value as PCRE_UTF8. */ @@ -1211,7 +1211,7 @@ Returns: TRUE if the type value was found, or FALSE for an invalid type */ static BOOL -get_ucp(const pcre_uchar **ptrptr, BOOL *negptr, unsigned int *ptypeptr, +get_ucp(const pcre_uchar **ptrptr, BOOL *negptr, unsigned int *ptypeptr, unsigned int *pdataptr, int *errorcodeptr) { pcre_uchar c; @@ -1432,7 +1432,7 @@ if (ptr[0] == CHAR_LEFT_PARENTHESIS) else if (ptr[2] == CHAR_NUMBER_SIGN) { - for (ptr += 3; *ptr != CHAR_NULL; ptr++) + for (ptr += 3; *ptr != CHAR_NULL; ptr++) if (*ptr == CHAR_RIGHT_PARENTHESIS) break; goto FAIL_EXIT; } @@ -1879,7 +1879,7 @@ for (;;) case OP_TYPEEXACT: branchlength += GET2(cc,1); - if (cc[1 + IMM2_SIZE] == OP_PROP || cc[1 + IMM2_SIZE] == OP_NOTPROP) + if (cc[1 + IMM2_SIZE] == OP_PROP || cc[1 + IMM2_SIZE] == OP_NOTPROP) cc += 2; cc += 1 + IMM2_SIZE + 1; break; @@ -2122,7 +2122,7 @@ for (;;) case OP_TYPEMINUPTO: case OP_TYPEEXACT: case OP_TYPEPOSUPTO: - if (code[1 + IMM2_SIZE] == OP_PROP || code[1 + IMM2_SIZE] == OP_NOTPROP) + if (code[1 + IMM2_SIZE] == OP_PROP || code[1 + IMM2_SIZE] == OP_NOTPROP) code += 2; break; @@ -2242,7 +2242,7 @@ for (;;) case OP_TYPEUPTO: case OP_TYPEMINUPTO: case OP_TYPEEXACT: - if (code[1 + IMM2_SIZE] == OP_PROP || code[1 + IMM2_SIZE] == OP_NOTPROP) + if (code[1 + IMM2_SIZE] == OP_PROP || code[1 + IMM2_SIZE] == OP_NOTPROP) code += 2; break; @@ -2568,7 +2568,7 @@ for (code = first_significant_code(code + PRIV(OP_lengths)[*code], TRUE); case OP_TYPEUPTO: case OP_TYPEMINUPTO: case OP_TYPEPOSUPTO: - if (code[1 + IMM2_SIZE] == OP_PROP || code[1 + IMM2_SIZE] == OP_NOTPROP) + if (code[1 + IMM2_SIZE] == OP_PROP || code[1 + IMM2_SIZE] == OP_NOTPROP) code += 2; break; @@ -2903,7 +2903,7 @@ PUT(previous_callout, 2 + LINK_SIZE, length); /* This function is passed the start and end of a class range, in UTF-8 mode with UCP support. It searches up the characters, looking for ranges of characters in the "other" case. Each call returns the next one, updating the -start address. A character with multiple other cases is returned on its own +start address. A character with multiple other cases is returned on its own with a special return value. Arguments: @@ -2915,7 +2915,7 @@ Arguments: Yield: -1 when no more 0 when a range is returned >0 the CASESET offset for char with multiple other cases - in this case, ocptr contains the original + in this case, ocptr contains the original */ static int @@ -2925,18 +2925,18 @@ get_othercase_range(pcre_uint32 *cptr, pcre_uint32 d, pcre_uint32 *ocptr, pcre_uint32 c, othercase, next; unsigned int co; -/* Find the first character that has an other case. If it has multiple other +/* Find the first character that has an other case. If it has multiple other cases, return its case offset value. */ for (c = *cptr; c <= d; c++) - { + { if ((co = UCD_CASESET(c)) != 0) { *ocptr = c++; /* Character that has the set */ *cptr = c; /* Rest of input range */ return (int)co; - } - if ((othercase = UCD_OTHERCASE(c)) != c) break; + } + if ((othercase = UCD_OTHERCASE(c)) != c) break; } if (c > d) return -1; /* Reached end of range */ @@ -3019,7 +3019,7 @@ switch(ptype) return (PRIV(ucp_gentype)[prop->chartype] == ucp_L || PRIV(ucp_gentype)[prop->chartype] == ucp_N || c == CHAR_UNDERSCORE) == negated; - + #ifdef SUPPORT_UCP case PT_CLIST: p = PRIV(ucd_caseless_sets) + prop->caseset; @@ -3139,7 +3139,7 @@ if (*ptr == CHAR_ASTERISK || *ptr == CHAR_QUESTION_MARK || /* If the previous item is a character, get its value. */ -if (op_code == OP_CHAR || op_code == OP_CHARI || +if (op_code == OP_CHAR || op_code == OP_CHARI || op_code == OP_NOT || op_code == OP_NOTI) { #ifdef SUPPORT_UTF @@ -3156,7 +3156,7 @@ if (escape == 0) { /* For a caseless UTF match, the next character may have more than one other case, which maps to the special PT_CLIST property. Check this first. */ - + #ifdef SUPPORT_UCP if (utf && c != NOTACHAR && (options & PCRE_CASELESS) != 0) { @@ -3172,7 +3172,7 @@ if (escape == 0) /* For CHARI (caseless character) we must check the other case. If we have Unicode property support, we can use it to test the other case of - high-valued characters. We know that next can have only one other case, + high-valued characters. We know that next can have only one other case, because multi-other-case characters are dealt with above. */ case OP_CHARI: @@ -3192,10 +3192,10 @@ if (escape == 0) else #endif /* SUPPORT_UTF */ return (c != TABLE_GET(next, cd->fcc, next)); /* Not UTF */ - + case OP_NOT: return c == next; - + case OP_NOTI: if (c == next) return TRUE; #ifdef SUPPORT_UTF @@ -3239,7 +3239,7 @@ if (escape == 0) case OP_NOT_HSPACE: switch(next) { - HSPACE_CASES: + HSPACE_CASES: return op_code == OP_NOT_HSPACE; default: @@ -3251,7 +3251,7 @@ if (escape == 0) case OP_NOT_VSPACE: switch(next) { - VSPACE_CASES: + VSPACE_CASES: return op_code == OP_NOT_VSPACE; default: @@ -3305,9 +3305,9 @@ switch(op_code) case ESC_H: switch(c) { - HSPACE_CASES: + HSPACE_CASES: return escape != ESC_h; - + default: return escape == ESC_h; } @@ -3316,7 +3316,7 @@ switch(op_code) case ESC_V: switch(c) { - VSPACE_CASES: + VSPACE_CASES: return escape != ESC_v; default: @@ -3428,18 +3428,18 @@ switch(op_code) *************************************************/ /* This function packages up the logic of adding a character or range of -characters to a class. The character values in the arguments will be within the -valid values for the current mode (8-bit, 16-bit, UTF, etc). This function is +characters to a class. The character values in the arguments will be within the +valid values for the current mode (8-bit, 16-bit, UTF, etc). This function is mutually recursive with the function immediately below. Arguments: classbits the bit map for characters < 256 uchardptr points to the pointer for extra data options the options word - cd contains pointers to tables etc. + cd contains pointers to tables etc. start start of range character end end of range character - + Returns: the number of < 256 characters added the pointer to extra data is updated */ @@ -3451,37 +3451,37 @@ add_to_class(pcre_uint8 *classbits, pcre_uchar **uchardptr, int options, pcre_uint32 c; int n8 = 0; -/* If caseless matching is required, scan the range and process alternate -cases. In Unicode, there are 8-bit characters that have alternate cases that -are greater than 255 and vice-versa. Sometimes we can just extend the original +/* If caseless matching is required, scan the range and process alternate +cases. In Unicode, there are 8-bit characters that have alternate cases that +are greater than 255 and vice-versa. Sometimes we can just extend the original range. */ if ((options & PCRE_CASELESS) != 0) { #ifdef SUPPORT_UCP if ((options & PCRE_UTF8) != 0) - { - int rc; + { + int rc; pcre_uint32 oc, od; - + options &= ~PCRE_CASELESS; /* Remove for recursive calls */ c = start; - + while ((rc = get_othercase_range(&c, end, &oc, &od)) >= 0) { /* Handle a single character that has more than one other case. */ - + if (rc > 0) n8 += add_list_to_class(classbits, uchardptr, options, cd, PRIV(ucd_caseless_sets) + rc, oc); - + /* Do nothing if the other case range is within the original range. */ - + else if (oc >= start && od <= end) continue; - + /* Extend the original range if there is overlap, noting that if oc < c, we can't have od > end because a subrange is always shorter than the basic range. Otherwise, use a recursive call to add the additional range. */ - + else if (oc < start && od >= start - 1) start = oc; /* Extend downwards */ else if (od > end && oc <= end + 1) end = od; /* Extend upwards */ else n8 += add_to_class(classbits, uchardptr, options, cd, oc, od); @@ -3491,14 +3491,14 @@ if ((options & PCRE_CASELESS) != 0) #endif /* SUPPORT_UCP */ /* Not UTF-mode, or no UCP */ - - for (c = start; c <= end && c < 256; c++) - { + + for (c = start; c <= end && c < 256; c++) + { SETBIT(classbits, cd->fcc[c]); - n8++; - } - } - + n8++; + } + } + /* Now handle the original range. Adjust the final value according to the bit length - this means that the same lists of (e.g.) horizontal spaces can be used in all cases. */ @@ -3524,39 +3524,39 @@ if (end < 0x100) { for (c = start; c <= end; c++) { - n8++; + n8++; SETBIT(classbits, c); - } + } } - + else - { + { pcre_uchar *uchardata = *uchardptr; - + #ifdef SUPPORT_UTF if ((options & PCRE_UTF8) != 0) /* All UTFs use the same flag bit */ { if (start < end) { *uchardata++ = XCL_RANGE; - uchardata += PRIV(ord2utf)(start, uchardata); - uchardata += PRIV(ord2utf)(end, uchardata); + uchardata += PRIV(ord2utf)(start, uchardata); + uchardata += PRIV(ord2utf)(end, uchardata); } else if (start == end) { *uchardata++ = XCL_SINGLE; - uchardata += PRIV(ord2utf)(start, uchardata); + uchardata += PRIV(ord2utf)(start, uchardata); } } else -#endif /* SUPPORT_UTF */ - +#endif /* SUPPORT_UTF */ + /* Without UTF support, character values are constrained by the bit length, and can only be > 256 for 16-bit and 32-bit libraries. */ - + #ifdef COMPILE_PCRE8 {} -#else +#else if (start < end) { *uchardata++ = XCL_RANGE; @@ -3567,23 +3567,23 @@ else { *uchardata++ = XCL_SINGLE; *uchardata++ = start; - } + } #endif *uchardptr = uchardata; /* Updata extra data pointer */ - } + } return n8; /* Number of 8-bit characters */ -} - - +} + + /************************************************* * Add a list of characters to a class * *************************************************/ -/* This function is used for adding a list of case-equivalent characters to a +/* This function is used for adding a list of case-equivalent characters to a class, and also for adding a list of horizontal or vertical whitespace. If the list is in order (which it should be), ranges of characters are detected and handled appropriately. This function is mutually recursive with the function @@ -3593,12 +3593,12 @@ Arguments: classbits the bit map for characters < 256 uchardptr points to the pointer for extra data options the options word - cd contains pointers to tables etc. - p points to row of 32-bit values, terminated by NOTACHAR + cd contains pointers to tables etc. + p points to row of 32-bit values, terminated by NOTACHAR except character to omit; this is used when adding lists of case-equivalent characters to avoid including the one we - already know about - + already know about + Returns: the number of < 256 characters added the pointer to extra data is updated */ @@ -3612,14 +3612,14 @@ while (p[0] < NOTACHAR) { int n = 0; if (p[0] != except) - { + { while(p[n+1] == p[0] + n + 1) n++; n8 += add_to_class(classbits, uchardptr, options, cd, p[0], p[n]); - } - p += n + 1; - } + } + p += n + 1; + } return n8; -} +} @@ -3634,15 +3634,15 @@ Arguments: classbits the bit map for characters < 256 uchardptr points to the pointer for extra data options the options word - cd contains pointers to tables etc. - p points to row of 32-bit values, terminated by NOTACHAR - + cd contains pointers to tables etc. + p points to row of 32-bit values, terminated by NOTACHAR + Returns: the number of < 256 characters added the pointer to extra data is updated */ static int -add_not_list_to_class(pcre_uint8 *classbits, pcre_uchar **uchardptr, +add_not_list_to_class(pcre_uint8 *classbits, pcre_uchar **uchardptr, int options, compile_data *cd, const pcre_uint32 *p) { BOOL utf = (options & PCRE_UTF8) != 0; @@ -3654,10 +3654,10 @@ while (p[0] < NOTACHAR) while (p[1] == p[0] + 1) p++; n8 += add_to_class(classbits, uchardptr, options, cd, p[0] + 1, (p[1] == NOTACHAR) ? (utf ? 0x10ffffu : 0xffffffffu) : p[1] - 1); - p++; - } + p++; + } return n8; -} +} @@ -3741,8 +3741,8 @@ BOOL utf = FALSE; #endif /* Helper variables for OP_XCLASS opcode (for characters > 255). We define -class_uchardata always so that it can be passed to add_to_class() always, -though it will not be used in non-UTF 8-bit cases. This avoids having to supply +class_uchardata always so that it can be passed to add_to_class() always, +though it will not be used in non-UTF 8-bit cases. This avoids having to supply alternative calls for the different cases. */ pcre_uchar *class_uchardata; @@ -4136,7 +4136,7 @@ for (;; ptr++) /* In the pre-compile phase, accumulate the length of any extra data and reset the pointer. This is so that very large classes that contain a zillion > 255 characters no longer overwrite the work space - (which is on the stack). We have to remember that there was XCLASS data, + (which is on the stack). We have to remember that there was XCLASS data, however. */ if (lengthptr != NULL && class_uchardata > class_uchardata_base) @@ -4200,7 +4200,7 @@ for (;; ptr++) alpha. This relies on the fact that the class table starts with alpha, lower, upper as the first 3 entries. */ - if ((options & PCRE_CASELESS) != 0 && posix_class <= 2) + if ((options & PCRE_CASELESS) != 0 && posix_class <= 2) posix_class = 0; /* When PCRE_UCP is set, some of the POSIX classes are converted to @@ -4356,27 +4356,27 @@ for (;; ptr++) for (c = 0; c < 32; c++) classbits[c] |= ~cbits[c+cbit_space]; classbits[1] |= 0x08; /* Perl 5.004 onwards omits VT from \s */ continue; - + /* The rest apply in both UCP and non-UCP cases. */ case ESC_h: (void)add_list_to_class(classbits, &class_uchardata, options, cd, - PRIV(hspace_list), NOTACHAR); + PRIV(hspace_list), NOTACHAR); continue; case ESC_H: - (void)add_not_list_to_class(classbits, &class_uchardata, options, - cd, PRIV(hspace_list)); + (void)add_not_list_to_class(classbits, &class_uchardata, options, + cd, PRIV(hspace_list)); continue; case ESC_v: (void)add_list_to_class(classbits, &class_uchardata, options, cd, - PRIV(vspace_list), NOTACHAR); + PRIV(vspace_list), NOTACHAR); continue; case ESC_V: - (void)add_not_list_to_class(classbits, &class_uchardata, options, - cd, PRIV(vspace_list)); + (void)add_not_list_to_class(classbits, &class_uchardata, options, + cd, PRIV(vspace_list)); continue; #ifdef SUPPORT_UCP @@ -4414,7 +4414,7 @@ for (;; ptr++) /* Fall through if the escape just defined a single character (c >= 0). This may be greater than 256. */ - + escape = 0; } /* End of backslash handling */ @@ -4455,7 +4455,7 @@ for (;; ptr++) inescq = TRUE; break; } - + /* Minus (hyphen) at the end of a class is treated as a literal, so put back the pointer and jump to handle the character that preceded it. */ @@ -4464,7 +4464,7 @@ for (;; ptr++) ptr = oldptr; goto CLASS_SINGLE_CHARACTER; } - + /* Otherwise, we have a potential range; pick up the next character */ #ifdef SUPPORT_UTF @@ -4511,23 +4511,23 @@ for (;; ptr++) /* We have found a character range, so single character optimizations cannot be done anymore. Any value greater than 1 indicates that there is more than one character. */ - + class_one_char = 2; /* Remember an explicit \r or \n, and add the range to the class. */ if (d == CHAR_CR || d == CHAR_NL) cd->external_flags |= PCRE_HASCRORLF; - - class_has_8bitchar += + + class_has_8bitchar += add_to_class(classbits, &class_uchardata, options, cd, c, d); - + continue; /* Go get the next char in the class */ } /* Handle a single character - we can get here for a normal non-escape char, or after \ that introduces a single character or for an apparent - range that isn't. Only the value 1 matters for class_one_char, so don't - increase it if it is already 2 or more ... just in case there's a class + range that isn't. Only the value 1 matters for class_one_char, so don't + increase it if it is already 2 or more ... just in case there's a class with a zillion characters in it. */ CLASS_SINGLE_CHARACTER: @@ -4550,9 +4550,9 @@ for (;; ptr++) if (negate_class) { -#ifdef SUPPORT_UCP +#ifdef SUPPORT_UCP int d; -#endif +#endif if (firstcharflags == REQ_UNSET) firstcharflags = REQ_NONE; zerofirstchar = firstchar; zerofirstcharflags = firstcharflags; @@ -4560,16 +4560,16 @@ for (;; ptr++) /* For caseless UTF-8 mode when UCP support is available, check whether this character has more than one other case. If so, generate a special OP_NOTPROP item instead of OP_NOTI. */ - + #ifdef SUPPORT_UCP - if (utf && (options & PCRE_CASELESS) != 0 && + if (utf && (options & PCRE_CASELESS) != 0 && (d = UCD_CASESET(c)) != 0) { *code++ = OP_NOTPROP; *code++ = PT_CLIST; *code++ = d; } - else + else #endif /* Char has only one other case, or UCP not available */ @@ -4582,9 +4582,9 @@ for (;; ptr++) #endif *code++ = c; } - + /* We are finished with this character class */ - + goto END_CLASS; } @@ -4602,11 +4602,11 @@ for (;; ptr++) } goto ONE_CHAR; } /* End of 1-char optimization */ - + /* There is more than one character in the class, or an XCLASS item has been generated. Add this character to the class. */ - - class_has_8bitchar += + + class_has_8bitchar += add_to_class(classbits, &class_uchardata, options, cd, c, c); } @@ -4627,14 +4627,14 @@ for (;; ptr++) goto FAILED; } - /* We will need an XCLASS if data has been placed in class_uchardata. In - the second phase this is a sufficient test. However, in the pre-compile - phase, class_uchardata gets emptied to prevent workspace overflow, so it - only if the very last character in the class needs XCLASS will it contain + /* We will need an XCLASS if data has been placed in class_uchardata. In + the second phase this is a sufficient test. However, in the pre-compile + phase, class_uchardata gets emptied to prevent workspace overflow, so it + only if the very last character in the class needs XCLASS will it contain anything at this point. For this reason, xclass gets set TRUE above when uchar_classdata is emptied, and that's why this code is the way it is here instead of just doing a test on class_uchardata below. */ - + #if defined SUPPORT_UTF || !defined COMPILE_PCRE8 if (class_uchardata > class_uchardata_base) xclass = TRUE; #endif @@ -4703,7 +4703,7 @@ for (;; ptr++) memcpy(code, classbits, 32); } code += 32 / sizeof(pcre_uchar); - + END_CLASS: break; @@ -6703,7 +6703,7 @@ for (;; ptr++) /* If the subpattern set a required byte (or set a first byte that isn't really the first byte - see above), set it. */ - if (subreqcharflags >= 0) + if (subreqcharflags >= 0) { reqchar = subreqchar; reqcharflags = subreqcharflags; @@ -6969,11 +6969,11 @@ for (;; ptr++) ONE_CHAR: previous = code; - - /* For caseless UTF-8 mode when UCP support is available, check whether - this character has more than one other case. If so, generate a special + + /* For caseless UTF-8 mode when UCP support is available, check whether + this character has more than one other case. If so, generate a special OP_PROP item instead of OP_CHARI. */ - + #ifdef SUPPORT_UCP if (utf && (options & PCRE_CASELESS) != 0) { @@ -6983,14 +6983,14 @@ for (;; ptr++) *code++ = OP_PROP; *code++ = PT_CLIST; *code++ = c; - if (firstcharflags == REQ_UNSET) firstcharflags = zerofirstcharflags = REQ_NONE; - break; - } - } + if (firstcharflags == REQ_UNSET) firstcharflags = zerofirstcharflags = REQ_NONE; + break; + } + } #endif - + /* Caseful matches, or not one of the multicase characters. */ - + *code++ = ((options & PCRE_CASELESS) != 0)? OP_CHARI : OP_CHAR; for (c = 0; c < mclength; c++) *code++ = mcbuffer[c]; @@ -7180,7 +7180,7 @@ for (;;) into the length. */ if (!compile_branch(&options, &code, &ptr, errorcodeptr, &branchfirstchar, - &branchfirstcharflags, &branchreqchar, &branchreqcharflags, &bc, + &branchfirstcharflags, &branchreqchar, &branchreqcharflags, &bc, cond_depth, cd, (lengthptr == NULL)? NULL : &length)) { *ptrptr = ptr; @@ -7218,10 +7218,10 @@ for (;;) we have to abandon the firstchar for the regex, but if there was previously no reqchar, it takes on the value of the old firstchar. */ - if (firstcharflags >= 0 && + if (firstcharflags >= 0 && (firstcharflags != branchfirstcharflags || firstchar != branchfirstchar)) { - if (reqcharflags < 0) + if (reqcharflags < 0) { reqchar = firstchar; reqcharflags = firstcharflags; @@ -7580,7 +7580,7 @@ do { { if (!is_startline(scode, bracket_map, cd, atomcount)) return FALSE; } - + /* Atomic brackets */ else if (op == OP_ONCE || op == OP_ONCE_NC) @@ -7848,10 +7848,10 @@ while (ptr[skipatstart] == CHAR_LEFT_PARENTHESIS && { int newnl = 0; int newbsr = 0; - + /* For completeness and backward compatibility, (*UTFn) is supported in the -relevant libraries, but (*UTF) is generic and always supported. Note that -PCRE_UTF8 == PCRE_UTF16 == PCRE_UTF32. */ +relevant libraries, but (*UTF) is generic and always supported. Note that +PCRE_UTF8 == PCRE_UTF16 == PCRE_UTF32. */ #ifdef COMPILE_PCRE8 if (STRNCMP_UC_C8(ptr+skipatstart+2, STRING_UTF8_RIGHTPAR, 5) == 0) @@ -7867,7 +7867,7 @@ PCRE_UTF8 == PCRE_UTF16 == PCRE_UTF32. */ #endif else if (STRNCMP_UC_C8(ptr+skipatstart+2, STRING_UTF_RIGHTPAR, 4) == 0) - { skipatstart += 6; options |= PCRE_UTF8; continue; } + { skipatstart += 6; options |= PCRE_UTF8; continue; } else if (STRNCMP_UC_C8(ptr+skipatstart+2, STRING_UCP_RIGHTPAR, 4) == 0) { skipatstart += 6; options |= PCRE_UCP; continue; } else if (STRNCMP_UC_C8(ptr+skipatstart+2, STRING_NO_START_OPT_RIGHTPAR, 13) == 0) @@ -8139,7 +8139,7 @@ if (code - codestart > length) errorcode = ERR23; #ifdef SUPPORT_VALGRIND /* If the estimated length exceeds the really used length, mark the extra -allocated memory as unadressable, so that any out-of-bound reads can be +allocated memory as unadressable, so that any out-of-bound reads can be detected. */ VALGRIND_MAKE_MEM_NOACCESS(code, (length - (code - codestart)) * sizeof(pcre_uchar)); #endif diff --git a/pcre_dfa_exec.c b/pcre_dfa_exec.c index 98a2798..91fb730 100644 --- a/pcre_dfa_exec.c +++ b/pcre_dfa_exec.c @@ -1062,7 +1062,7 @@ for (;;) if (clen > 0) { BOOL OK; - const pcre_uint32 *cp; + const pcre_uint32 *cp; const ucd_record * prop = GET_UCD(c); switch(code[1]) { @@ -1110,15 +1110,15 @@ for (;;) PRIV(ucp_gentype)[prop->chartype] == ucp_N || c == CHAR_UNDERSCORE; break; - + case PT_CLIST: cp = PRIV(ucd_caseless_sets) + code[2]; for (;;) { if (c < *cp) { OK = FALSE; break; } if (c == *cp++) { OK = TRUE; break; } - } - break; + } + break; /* Should never occur, but keep compilers from grumbling. */ @@ -1306,7 +1306,7 @@ for (;;) if (clen > 0) { BOOL OK; - const pcre_uint32 *cp; + const pcre_uint32 *cp; const ucd_record * prop = GET_UCD(c); switch(code[2]) { @@ -1361,8 +1361,8 @@ for (;;) { if (c < *cp) { OK = FALSE; break; } if (c == *cp++) { OK = TRUE; break; } - } - break; + } + break; /* Should never occur, but keep compilers from grumbling. */ @@ -1470,7 +1470,7 @@ for (;;) BOOL OK; switch (c) { - VSPACE_CASES: + VSPACE_CASES: OK = TRUE; break; @@ -1503,7 +1503,7 @@ for (;;) BOOL OK; switch (c) { - HSPACE_CASES: + HSPACE_CASES: OK = TRUE; break; @@ -1544,7 +1544,7 @@ for (;;) if (clen > 0) { BOOL OK; - const pcre_uint32 *cp; + const pcre_uint32 *cp; const ucd_record * prop = GET_UCD(c); switch(code[2]) { @@ -1599,8 +1599,8 @@ for (;;) { if (c < *cp) { OK = FALSE; break; } if (c == *cp++) { OK = TRUE; break; } - } - break; + } + break; /* Should never occur, but keep compilers from grumbling. */ @@ -1733,7 +1733,7 @@ for (;;) BOOL OK; switch (c) { - VSPACE_CASES: + VSPACE_CASES: OK = TRUE; break; @@ -1773,7 +1773,7 @@ for (;;) BOOL OK; switch (c) { - HSPACE_CASES: + HSPACE_CASES: OK = TRUE; break; @@ -1807,7 +1807,7 @@ for (;;) if (clen > 0) { BOOL OK; - const pcre_uint32 *cp; + const pcre_uint32 *cp; const ucd_record * prop = GET_UCD(c); switch(code[1 + IMM2_SIZE + 1]) { @@ -1862,8 +1862,8 @@ for (;;) { if (c < *cp) { OK = FALSE; break; } if (c == *cp++) { OK = TRUE; break; } - } - break; + } + break; /* Should never occur, but keep compilers from grumbling. */ @@ -1985,7 +1985,7 @@ for (;;) BOOL OK; switch (c) { - VSPACE_CASES: + VSPACE_CASES: OK = TRUE; break; @@ -2021,7 +2021,7 @@ for (;;) BOOL OK; switch (c) { - HSPACE_CASES: + HSPACE_CASES: OK = TRUE; break; @@ -2164,7 +2164,7 @@ for (;;) case OP_NOT_VSPACE: if (clen > 0) switch(c) { - VSPACE_CASES: + VSPACE_CASES: break; default: @@ -2177,11 +2177,11 @@ for (;;) case OP_VSPACE: if (clen > 0) switch(c) { - VSPACE_CASES: + VSPACE_CASES: ADD_NEW(state_offset + 1, 0); break; - default: + default: break; } break; @@ -2190,7 +2190,7 @@ for (;;) case OP_NOT_HSPACE: if (clen > 0) switch(c) { - HSPACE_CASES: + HSPACE_CASES: break; default: @@ -2203,12 +2203,12 @@ for (;;) case OP_HSPACE: if (clen > 0) switch(c) { - HSPACE_CASES: + HSPACE_CASES: ADD_NEW(state_offset + 1, 0); break; - + default: - break; + break; } break; diff --git a/pcre_exec.c b/pcre_exec.c index e4059c0..05d0e52 100644 --- a/pcre_exec.c +++ b/pcre_exec.c @@ -199,9 +199,9 @@ if (caseless) GETCHARINC(c, eptr); GETCHARINC(d, p); ur = GET_UCD(d); - if (c != d && c != d + ur->other_case) + if (c != d && c != d + ur->other_case) { - const pcre_uint32 *pp = PRIV(ucd_caseless_sets) + ur->caseset; + const pcre_uint32 *pp = PRIV(ucd_caseless_sets) + ur->caseset; for (;;) { if (c < *pp) return -1; @@ -2532,7 +2532,7 @@ for (;;) } GETCHARINCTEST(c, eptr); { - const pcre_uint32 *cp; + const pcre_uint32 *cp; const ucd_record *prop = GET_UCD(c); switch(ecode[1]) @@ -4203,10 +4203,10 @@ for (;;) RRETURN(MATCH_NOMATCH); } break; - + case PT_CLIST: for (i = 1; i <= min; i++) - { + { const pcre_uint32 *cp; if (eptr >= md->end_subject) { @@ -4217,14 +4217,14 @@ for (;;) cp = PRIV(ucd_caseless_sets) + prop_value; for (;;) { - if (c < *cp) + if (c < *cp) { if (prop_fail_result) break; else { RRETURN(MATCH_NOMATCH); } } if (c == *cp++) { if (prop_fail_result) { RRETURN(MATCH_NOMATCH); } else break; } } } break; - + /* This should not occur */ default: @@ -4954,7 +4954,7 @@ for (;;) case PT_CLIST: for (fi = min;; fi++) - { + { const pcre_uint32 *cp; RMATCH(eptr, ecode, offset_top, md, eptrb, RM67); if (rrc != MATCH_NOMATCH) RRETURN(rrc); @@ -5445,7 +5445,7 @@ for (;;) eptr+= len; } break; - + case PT_CLIST: for (i = min; i < max; i++) { @@ -5460,14 +5460,14 @@ for (;;) cp = PRIV(ucd_caseless_sets) + prop_value; for (;;) { - if (c < *cp) + if (c < *cp) { if (prop_fail_result) break; else goto GOT_MAX; } if (c == *cp++) { if (prop_fail_result) goto GOT_MAX; else break; } - } - eptr += len; + } + eptr += len; } - GOT_MAX: + GOT_MAX: break; default: diff --git a/pcre_internal.h b/pcre_internal.h index c5d4914..f3cb001 100644 --- a/pcre_internal.h +++ b/pcre_internal.h @@ -531,9 +531,9 @@ capturing parenthesis numbers in back references. */ #define PUT2(a,n,d) \ a[n] = (d) >> 8; \ a[(n)+1] = (d) & 255 - -/* For reasons that I do not understand, the expression in this GET2 macro is -treated by gcc as a signed expression, even when a is declared as unsigned. It + +/* For reasons that I do not understand, the expression in this GET2 macro is +treated by gcc as a signed expression, even when a is declared as unsigned. It seems that any kind of arithmetic results in a signed value. */ #define GET2(a,n) \ @@ -999,7 +999,7 @@ pointer. */ /* If the pointer is not at the start of a character, move it back until it is. This is called only in UTF-32 mode - we don't put a test within the macro because almost all calls are already within a block of UTF-32 only -code. +code. These are all no-ops since all UTF-32 characters fit into one pcre_uchar. */ #define BACKCHAR(eptr) do { } while (0) @@ -1026,7 +1026,7 @@ are defined. These values are also required as lists in pcre_compile.c when processing \h, \H, \v and \V in a character class. The lists are defined in pcre_tables.c, but macros that define the values are here so that all the definitions are -together. The lists must be in ascending character order, terminated by +together. The lists must be in ascending character order, terminated by NOTACHAR (which is 0xffffffff). Any changes should ensure that the various macros are kept in step with each @@ -1040,7 +1040,7 @@ other. NOTE: The values also appear in pcre_jit_compile.c. */ CHAR_HT, CHAR_SPACE, 0xa0, \ 0x1680, 0x180e, 0x2000, 0x2001, 0x2002, 0x2003, 0x2004, 0x2005, \ 0x2006, 0x2007, 0x2008, 0x2009, 0x200A, 0x202f, 0x205f, 0x3000, \ - NOTACHAR + NOTACHAR #define HSPACE_MULTIBYTE_CASES \ case 0x1680: /* OGHAM SPACE MARK */ \ @@ -1064,13 +1064,13 @@ other. NOTE: The values also appear in pcre_jit_compile.c. */ case CHAR_HT: \ case CHAR_SPACE: \ case 0xa0 /* NBSP */ - + #define HSPACE_CASES \ HSPACE_BYTE_CASES: \ HSPACE_MULTIBYTE_CASES #define VSPACE_LIST \ - CHAR_LF, CHAR_VT, CHAR_FF, CHAR_CR, CHAR_NEL, 0x2028, 0x2029, NOTACHAR + CHAR_LF, CHAR_VT, CHAR_FF, CHAR_CR, CHAR_NEL, 0x2028, 0x2029, NOTACHAR #define VSPACE_MULTIBYTE_CASES \ case 0x2028: /* LINE SEPARATOR */ \ @@ -1100,11 +1100,11 @@ other. NOTE: The values also appear in pcre_jit_compile.c. */ #ifdef EBCDIC_NL25 #define VSPACE_LIST \ - CHAR_VT, CHAR_FF, CHAR_CR, CHAR_NEL, CHAR_LF, NOTACHAR + CHAR_VT, CHAR_FF, CHAR_CR, CHAR_NEL, CHAR_LF, NOTACHAR #else #define VSPACE_LIST \ - CHAR_VT, CHAR_FF, CHAR_CR, CHAR_LF, CHAR_NEL, NOTACHAR -#endif + CHAR_VT, CHAR_FF, CHAR_CR, CHAR_LF, CHAR_NEL, NOTACHAR +#endif #define VSPACE_BYTE_CASES \ case CHAR_LF: \ diff --git a/pcre_jit_compile.c b/pcre_jit_compile.c index 7b5b4ce..cc9f097 100644 --- a/pcre_jit_compile.c +++ b/pcre_jit_compile.c @@ -3532,7 +3532,7 @@ if (caseless && char_has_othercase(common, cc)) othercasebit &= 0xff; #elif defined COMPILE_PCRE16 || defined COMPILE_PCRE32 /* Note that this code only handles characters in the BMP. If there - ever are characters outside the BMP whose othercase differs in only one + ever are characters outside the BMP whose othercase differs in only one bit from itself (there currently are none), this code will need to be revised for COMPILE_PCRE32. */ othercasechar = cc + (othercasebit >> 9); diff --git a/pcre_newline.c b/pcre_newline.c index f81e8f7..b8f5a4d 100644 --- a/pcre_newline.c +++ b/pcre_newline.c @@ -60,7 +60,7 @@ http://unicode.org/unicode/reports/tr18/. */ *************************************************/ /* It is guaranteed that the initial value of ptr is less than the end of the -string that is being processed. +string that is being processed. Arguments: ptr pointer to possible newline @@ -86,8 +86,8 @@ if (utf) else #endif /* SUPPORT_UTF */ c = *ptr; - -/* Note that this function is called only for ANY or ANYCRLF. */ + +/* Note that this function is called only for ANY or ANYCRLF. */ if (type == NLTYPE_ANYCRLF) switch(c) { @@ -103,12 +103,12 @@ else switch(c) { #ifdef EBCDIC case CHAR_NEL: -#endif +#endif case CHAR_LF: case CHAR_VT: case CHAR_FF: *lenptr = 1; return TRUE; - case CHAR_CR: + case CHAR_CR: *lenptr = (ptr < endptr - 1 && ptr[1] == CHAR_LF)? 2 : 1; return TRUE; @@ -164,14 +164,14 @@ else #endif /* SUPPORT_UTF */ c = *ptr; -/* Note that this function is called only for ANY or ANYCRLF. */ +/* Note that this function is called only for ANY or ANYCRLF. */ if (type == NLTYPE_ANYCRLF) switch(c) { - case CHAR_LF: + case CHAR_LF: *lenptr = (ptr > startptr && ptr[-1] == CHAR_CR)? 2 : 1; return TRUE; - + case CHAR_CR: *lenptr = 1; return TRUE; default: return FALSE; } @@ -180,18 +180,18 @@ if (type == NLTYPE_ANYCRLF) switch(c) else switch(c) { - case CHAR_LF: + case CHAR_LF: *lenptr = (ptr > startptr && ptr[-1] == CHAR_CR)? 2 : 1; return TRUE; - + #ifdef EBCDIC case CHAR_NEL: -#endif +#endif case CHAR_VT: case CHAR_FF: case CHAR_CR: *lenptr = 1; return TRUE; - -#ifndef EBCDIC + +#ifndef EBCDIC #ifdef COMPILE_PCRE8 case CHAR_NEL: *lenptr = utf? 2 : 1; return TRUE; case 0x2028: /* LS */ diff --git a/pcre_ord2utf8.c b/pcre_ord2utf8.c index 90dd6b3..95f1beb 100644 --- a/pcre_ord2utf8.c +++ b/pcre_ord2utf8.c @@ -63,7 +63,7 @@ Arguments: Returns: number of characters placed in the buffer */ -unsigned +unsigned int PRIV(ord2utf)(pcre_uint32 cvalue, pcre_uchar *buffer) { diff --git a/pcre_printint.c b/pcre_printint.c index 11884df..10b5754 100644 --- a/pcre_printint.c +++ b/pcre_printint.c @@ -133,7 +133,7 @@ return 0; if (!utf || (c & 0xc0) != 0xc0) { - if (PRINTABLE(c)) fprintf(f, "%c", (char)c); + if (PRINTABLE(c)) fprintf(f, "%c", (char)c); else if (c < 0x80) fprintf(f, "\\x%02x", c); else fprintf(f, "\\x{%02x}", c); return 0; @@ -254,10 +254,10 @@ return (ptype == pvalue)? "??" : "??"; * Print Unicode property value * *************************************************/ -/* "Normal" properties can be printed from tables. The PT_CLIST property is a -pseudo-property that contains a pointer to a list of case-equivalent -characters. This is used only when UCP support is available and UTF mode is -selected. It should never occur otherwise, but just in case it does, have +/* "Normal" properties can be printed from tables. The PT_CLIST property is a +pseudo-property that contains a pointer to a list of case-equivalent +characters. This is used only when UCP support is available and UTF mode is +selected. It should never occur otherwise, but just in case it does, have something ready to print. */ static void @@ -265,21 +265,21 @@ print_prop(FILE *f, pcre_uchar *code, const char *before, const char *after) { if (code[1] != PT_CLIST) { - fprintf(f, "%s%s %s%s", before, priv_OP_names[*code], get_ucpname(code[1], + fprintf(f, "%s%s %s%s", before, priv_OP_names[*code], get_ucpname(code[1], code[2]), after); } else { const char *not = (*code == OP_PROP)? "" : "not "; -#ifndef SUPPORT_UCP +#ifndef SUPPORT_UCP fprintf(f, "%s%sclist %d%s", before, not, code[2], after); #else const pcre_uint32 *p = PRIV(ucd_caseless_sets) + code[2]; fprintf (f, "%s%sclist", before, not); - while (*p < NOTACHAR) fprintf(f, " %04x", *p++); - fprintf(f, "%s", after); -#endif - } + while (*p < NOTACHAR) fprintf(f, " %04x", *p++); + fprintf(f, "%s", after); +#endif + } } diff --git a/pcre_study.c b/pcre_study.c index 2205dd7..12d2a66 100644 --- a/pcre_study.c +++ b/pcre_study.c @@ -572,7 +572,7 @@ if (utf && c > 127) return p; } #else /* Not SUPPORT_UTF */ -(void)(utf); /* Stops warning for unused parameter */ +(void)(utf); /* Stops warning for unused parameter */ #endif /* SUPPORT_UTF */ /* Not UTF-8 mode, or character is less than 127. */ @@ -605,7 +605,7 @@ if (utf && c > 127) return p; } #else /* Not SUPPORT_UTF */ -(void)(utf); /* Stops warning for unused parameter */ +(void)(utf); /* Stops warning for unused parameter */ #endif /* SUPPORT_UTF */ if (caseless && (cd->ctypes[c] & ctype_letter) != 0) SET_BIT(cd->fcc[c]); @@ -1012,9 +1012,9 @@ do else #endif /* SUPPORT_UTF */ { -#ifndef EBCDIC +#ifndef EBCDIC SET_BIT(0xA0); -#endif /* Not EBCDIC */ +#endif /* Not EBCDIC */ #if defined COMPILE_PCRE16 || defined COMPILE_PCRE32 SET_BIT(0xFF); /* For characters > 255 */ #endif /* COMPILE_PCRE[16|32] */ @@ -1066,7 +1066,7 @@ do break; /* The cbit_space table has vertical tab as whitespace; we have to - ensure it is set as not whitespace. Luckily, the code value is the same + ensure it is set as not whitespace. Luckily, the code value is the same (0x0b) in ASCII and EBCDIC, so we can just adjust the appropriate bit. */ case OP_NOT_WHITESPACE: @@ -1150,7 +1150,7 @@ do #endif /* SUPPORT_UTF */ #ifndef EBCDIC SET_BIT(0xA0); -#endif /* Not EBCDIC */ +#endif /* Not EBCDIC */ break; case OP_ANYNL: @@ -1430,7 +1430,7 @@ switch(min = find_minlength(code, code, re->options, 0)) } /* If a set of starting bytes has been identified, or if the minimum length is -greater than zero, or if JIT optimization has been requested, or if +greater than zero, or if JIT optimization has been requested, or if PCRE_STUDY_EXTRA_NEEDED is set, get a pcre[16]_extra block and a pcre_study_data block. The study data is put in the latter, which is pointed to by the former, which may also get additional data set later by the calling @@ -1441,7 +1441,7 @@ becomes variable in the future, we don't have to change that code. */ if (bits_set || min > 0 || (options & ( #ifdef SUPPORT_JIT PCRE_STUDY_JIT_COMPILE | PCRE_STUDY_JIT_PARTIAL_SOFT_COMPILE | - PCRE_STUDY_JIT_PARTIAL_HARD_COMPILE | + PCRE_STUDY_JIT_PARTIAL_HARD_COMPILE | #endif PCRE_STUDY_EXTRA_NEEDED)) != 0) { @@ -1497,7 +1497,7 @@ if (bits_set || min > 0 || (options & ( /* If JIT support was compiled and requested, attempt the JIT compilation. If no starting bytes were found, and the minimum length is zero, and JIT - compilation fails, abandon the extra block and return NULL, unless + compilation fails, abandon the extra block and return NULL, unless PCRE_STUDY_EXTRA_NEEDED is set. */ #ifdef SUPPORT_JIT diff --git a/pcre_tables.c b/pcre_tables.c index 8a1b3a9..34ee048 100644 --- a/pcre_tables.c +++ b/pcre_tables.c @@ -132,49 +132,49 @@ two code points. The breaking rules are as follows: controls. 3. Do not break Hangul syllable sequences, the rules for which are: - + L may be followed by L, V, LV or LVT LV or V may be followed by V or T - LVT or T may be followed by T + LVT or T may be followed by T 4. Do not break before extending characters. The next two rules are only for extended grapheme clusters (but that's what we are implementing). - + 5. Do not break before SpacingMarks. - + 6. Do not break after Prepend characters. - + 7. Otherwise, break everywhere. */ const pcre_uint32 PRIV(ucp_gbtable[]) = { - (1<<ucp_gbLF), /* 0 CR */ - 0, /* 1 LF */ - 0, /* 2 Control */ - (1<<ucp_gbExtend)|(1<<ucp_gbSpacingMark), /* 3 Extend */ - (1<<ucp_gbExtend)|(1<<ucp_gbPrepend)| /* 4 Prepend */ - (1<<ucp_gbSpacingMark)|(1<<ucp_gbL)| - (1<<ucp_gbV)|(1<<ucp_gbT)|(1<<ucp_gbLV)| - (1<<ucp_gbLVT)|(1<<ucp_gbOther), - - (1<<ucp_gbExtend)|(1<<ucp_gbSpacingMark), /* 5 SpacingMark */ - (1<<ucp_gbExtend)|(1<<ucp_gbSpacingMark)|(1<<ucp_gbL)| /* 6 L */ + (1<<ucp_gbLF), /* 0 CR */ + 0, /* 1 LF */ + 0, /* 2 Control */ + (1<<ucp_gbExtend)|(1<<ucp_gbSpacingMark), /* 3 Extend */ + (1<<ucp_gbExtend)|(1<<ucp_gbPrepend)| /* 4 Prepend */ + (1<<ucp_gbSpacingMark)|(1<<ucp_gbL)| + (1<<ucp_gbV)|(1<<ucp_gbT)|(1<<ucp_gbLV)| + (1<<ucp_gbLVT)|(1<<ucp_gbOther), + + (1<<ucp_gbExtend)|(1<<ucp_gbSpacingMark), /* 5 SpacingMark */ + (1<<ucp_gbExtend)|(1<<ucp_gbSpacingMark)|(1<<ucp_gbL)| /* 6 L */ (1<<ucp_gbL)|(1<<ucp_gbV)|(1<<ucp_gbLV)|(1<<ucp_gbLVT), (1<<ucp_gbExtend)|(1<<ucp_gbSpacingMark)|(1<<ucp_gbV)| /* 7 V */ (1<<ucp_gbT), - (1<<ucp_gbExtend)|(1<<ucp_gbSpacingMark)|(1<<ucp_gbT), /* 8 T */ - (1<<ucp_gbExtend)|(1<<ucp_gbSpacingMark)|(1<<ucp_gbV)| /* 9 LV */ + (1<<ucp_gbExtend)|(1<<ucp_gbSpacingMark)|(1<<ucp_gbT), /* 8 T */ + (1<<ucp_gbExtend)|(1<<ucp_gbSpacingMark)|(1<<ucp_gbV)| /* 9 LV */ (1<<ucp_gbT), - (1<<ucp_gbExtend)|(1<<ucp_gbSpacingMark)|(1<<ucp_gbT), /* 10 LVT */ + (1<<ucp_gbExtend)|(1<<ucp_gbSpacingMark)|(1<<ucp_gbT), /* 10 LVT */ (1<<ucp_gbRegionalIndicator), /* 11 RegionalIndicator */ (1<<ucp_gbExtend)|(1<<ucp_gbSpacingMark) /* 12 Other */ -}; - +}; + #ifdef SUPPORT_JIT /* This table reverses PRIV(ucp_gentype). We can save the cost of a memory load. */ @@ -522,9 +522,9 @@ int RE::TryMatch(const StringPiece& text, } // int options = 0; - // Changed by PH as a result of bugzilla #1288 + // Changed by PH as a result of bugzilla #1288 int options = (options_.all_options() & PCRE_NO_UTF8_CHECK); - + if (anchor != UNANCHORED) options |= PCRE_ANCHORED; if (!empty_ok) @@ -1704,7 +1704,7 @@ while (ptr < endptr) { BOOL printed = FALSE; omstr *om; - + for (om = only_matching; om != NULL; om = om->next) { int n = om->groupnum; @@ -1713,7 +1713,7 @@ while (ptr < endptr) int plen = offsets[2*n + 1] - offsets[2*n]; if (plen > 0) { - if (printed) fprintf(stdout, "%s", om_separator); + if (printed) fprintf(stdout, "%s", om_separator); if (do_colour) fprintf(stdout, "%c[%sm", 0x1b, colour_string); FWRITE(matchptr + offsets[n*2], 1, plen, stdout); if (do_colour) fprintf(stdout, "%c[00m", 0x1b); @@ -1721,7 +1721,7 @@ while (ptr < endptr) } } } - + if (printed || printname != NULL || number) fprintf(stdout, "\n"); } @@ -2261,12 +2261,12 @@ switch(letter) case 'L': filenames = FN_NOMATCH_ONLY; break; case 'M': multiline = TRUE; options |= PCRE_MULTILINE|PCRE_FIRSTLINE; break; case 'n': number = TRUE; break; - + case 'o': only_matching_last = add_number(0, only_matching_last); if (only_matching == NULL) only_matching = only_matching_last; break; - + case 'q': quiet = TRUE; break; case 'r': dee_action = dee_RECURSE; break; case 's': silent = TRUE; break; @@ -2652,7 +2652,7 @@ for (i = 1; i < argc; i++) { char *s = argv[i] + 1; longop = FALSE; - + while (*s != 0) { for (op = optionlist; op->one_char != 0; op++) @@ -2665,13 +2665,13 @@ for (i = 1; i < argc; i++) *s, argv[i]); pcregrep_exit(usage(2)); } - + option_data = s+1; - - /* Break out if this is the last character in the string; it's handled + + /* Break out if this is the last character in the string; it's handled below like a single multi-char option. */ - - if (*option_data == 0) break; + + if (*option_data == 0) break; /* Check for a single-character option that has data: OP_OP_NUMBER(S) are used for ones that either have a numerical number or defaults, i.e. @@ -2689,11 +2689,11 @@ for (i = 1; i < argc; i++) /* Handle a single-character option with no data, then loop for the next character in the string. */ - + pcre_options = handle_option(*s++, pcre_options); } } - + /* At this point we should have op pointing to a matched option. If the type is NO_DATA, it means that there is no data, and the option might set something in the PCRE options. */ @@ -2708,7 +2708,7 @@ for (i = 1; i < argc; i++) either has a value or defaults to something. It cannot have data in a separate item. At the moment, the only such options are "colo(u)r", "only-matching", and Jeffrey Friedl's special -S debugging option. */ - + if (*option_data == 0 && (op->type == OP_OP_STRING || op->type == OP_OP_NUMBER || op->type == OP_OP_NUMBERS)) diff --git a/pcreposix.c b/pcreposix.c index 9898e5b..15195c0 100644 --- a/pcreposix.c +++ b/pcreposix.c @@ -285,7 +285,7 @@ if (preg->re_pcre == NULL) (void)pcre_fullinfo((const pcre *)preg->re_pcre, NULL, PCRE_INFO_CAPTURECOUNT, &re_nsub); -preg->re_nsub = (size_t)re_nsub; +preg->re_nsub = (size_t)re_nsub; return 0; } @@ -36,7 +36,7 @@ POSSIBILITY OF SUCH DAMAGE. ----------------------------------------------------------------------------- */ -/* This program now supports the testing of all of the 8-bit, 16-bit, and +/* This program now supports the testing of all of the 8-bit, 16-bit, and 32-bit PCRE libraries in a single program. This is different from the modules such as pcre_compile.c in the library itself, which are compiled separately for each mode. If two modes are enabled, for example, pcre_compile.c is compiled @@ -288,8 +288,8 @@ argument, the casting might be incorrectly applied. */ #define PCRE_JIT_STACK_FREE8(stack) \ pcre_jit_stack_free(stack) - -#define pcre8_maketables pcre_maketables + +#define pcre8_maketables pcre_maketables #endif /* SUPPORT_PCRE8 */ @@ -1131,7 +1131,7 @@ static const char *errtexts[] = { "pattern compiled with other endianness", "invalid data in workspace for DFA restart", "bad JIT option", - "bad length" + "bad length" }; @@ -4721,7 +4721,7 @@ while (!done) continue; } - /* We now have a character value in c that may be greater than 255. + /* We now have a character value in c that may be greater than 255. In 8-bit mode we convert to UTF-8 if we are in UTF mode. Values greater than 127 in UTF mode must have come from \x{...} or octal constructs because values from \x.. get this far only in non-UTF mode. */ @@ -4736,8 +4736,8 @@ while (!done) { fprintf(outfile, "** Character \\x{%x} is greater than 0x7fffffff " "and so cannot be converted to UTF-8\n", c); - goto NEXT_DATA; - } + goto NEXT_DATA; + } q8 += ord2utf8(c, q8); } else @@ -60,8 +60,8 @@ enum { ucp_Zs /* Space separator */ }; -/* These are grapheme break properties. Note that the code for processing them -assumes that the values are less than 16. If more values are added that take +/* These are grapheme break properties. Note that the code for processing them +assumes that the values are less than 16. If more values are added that take the number to 16 or more, the code will have to be rewritten. */ enum { |