From: Nuno Lopes Date: Mon, 14 Jan 2008 09:39:41 +0000 (+0000) Subject: upgrade PCRE to version 7.5 (as asked by Ilia X-Git-Tag: php-5.2.6RC1~170 X-Git-Url: https://granicus.if.org/sourcecode?a=commitdiff_plain;h=255a7b9cf0865894db3917c1eb4dea55d7efbf45;p=php upgrade PCRE to version 7.5 (as asked by Ilia --- diff --git a/NEWS b/NEWS index 9abb9bbc73..4e0c1c78ec 100644 --- a/NEWS +++ b/NEWS @@ -6,6 +6,7 @@ PHP NEWS (Ilia) - Fixed a bug with PDO::FETCH_COLUMN|PDO::FETCH_GROUP mode when a column # by which to group by data is specified. (Ilia) +- Upgraded PCRE to version 7.5 (Nuno) - Fixed faulty fix for bug #40189 (endless loop in zlib.inflate stream filter) (Greg) diff --git a/ext/pcre/pcrelib/ChangeLog b/ext/pcre/pcrelib/ChangeLog index 3b18524fe6..a6978962cd 100644 --- a/ext/pcre/pcrelib/ChangeLog +++ b/ext/pcre/pcrelib/ChangeLog @@ -1,6 +1,218 @@ ChangeLog for PCRE ------------------ +Version 7.5 10-Jan-08 +--------------------- + +1. Applied a patch from Craig: "This patch makes it possible to 'ignore' + values in parens when parsing an RE using the C++ wrapper." + +2. Negative specials like \S did not work in character classes in UTF-8 mode. + Characters greater than 255 were excluded from the class instead of being + included. + +3. The same bug as (2) above applied to negated POSIX classes such as + [:^space:]. + +4. PCRECPP_STATIC was referenced in pcrecpp_internal.h, but nowhere was it + defined or documented. It seems to have been a typo for PCRE_STATIC, so + I have changed it. + +5. The construct (?&) was not diagnosed as a syntax error (it referenced the + first named subpattern) and a construct such as (?&a) would reference the + first named subpattern whose name started with "a" (in other words, the + length check was missing). Both these problems are fixed. "Subpattern name + expected" is now given for (?&) (a zero-length name), and this patch also + makes it give the same error for \k'' (previously it complained that that + was a reference to a non-existent subpattern). + +6. The erroneous patterns (?+-a) and (?-+a) give different error messages; + this is right because (?- can be followed by option settings as well as by + digits. I have, however, made the messages clearer. + +7. Patterns such as (?(1)a|b) (a pattern that contains fewer subpatterns + than the number used in the conditional) now cause a compile-time error. + This is actually not compatible with Perl, which accepts such patterns, but + treats the conditional as always being FALSE (as PCRE used to), but it + seems to me that giving a diagnostic is better. + +8. Change "alphameric" to the more common word "alphanumeric" in comments + and messages. + +9. Fix two occurrences of "backslash" in comments that should have been + "backspace". + +10. Remove two redundant lines of code that can never be obeyed (their function + was moved elsewhere). + +11. The program that makes PCRE's Unicode character property table had a bug + which caused it to generate incorrect table entries for sequences of + characters that have the same character type, but are in different scripts. + It amalgamated them into a single range, with the script of the first of + them. In other words, some characters were in the wrong script. There were + thirteen such cases, affecting characters in the following ranges: + + U+002b0 - U+002c1 + U+0060c - U+0060d + U+0061e - U+00612 + U+0064b - U+0065e + U+0074d - U+0076d + U+01800 - U+01805 + U+01d00 - U+01d77 + U+01d9b - U+01dbf + U+0200b - U+0200f + U+030fc - U+030fe + U+03260 - U+0327f + U+0fb46 - U+0fbb1 + U+10450 - U+1049d + +12. The -o option (show only the matching part of a line) for pcregrep was not + compatible with GNU grep in that, if there was more than one match in a + line, it showed only the first of them. It now behaves in the same way as + GNU grep. + +13. If the -o and -v options were combined for pcregrep, it printed a blank + line for every non-matching line. GNU grep prints nothing, and pcregrep now + does the same. The return code can be used to tell if there were any + non-matching lines. + +14. Added --file-offsets and --line-offsets to pcregrep. + +15. The pattern (?=something)(?R) was not being diagnosed as a potentially + infinitely looping recursion. The bug was that positive lookaheads were not + being skipped when checking for a possible empty match (negative lookaheads + and both kinds of lookbehind were skipped). + +16. Fixed two typos in the Windows-only code in pcregrep.c, and moved the + inclusion of to before rather than after the definition of + INVALID_FILE_ATTRIBUTES (patch from David Byron). + +17. Specifying a possessive quantifier with a specific limit for a Unicode + character property caused pcre_compile() to compile bad code, which led at + runtime to PCRE_ERROR_INTERNAL (-14). Examples of patterns that caused this + are: /\p{Zl}{2,3}+/8 and /\p{Cc}{2}+/8. It was the possessive "+" that + caused the error; without that there was no problem. + +18. Added --enable-pcregrep-libz and --enable-pcregrep-libbz2. + +19. Added --enable-pcretest-libreadline. + +20. In pcrecpp.cc, the variable 'count' was incremented twice in + RE::GlobalReplace(). As a result, the number of replacements returned was + double what it should be. I removed one of the increments, but Craig sent a + later patch that removed the other one (the right fix) and added unit tests + that check the return values (which was not done before). + +21. Several CMake things: + + (1) Arranged that, when cmake is used on Unix, the libraries end up with + the names libpcre and libpcreposix, not just pcre and pcreposix. + + (2) The above change means that pcretest and pcregrep are now correctly + linked with the newly-built libraries, not previously installed ones. + + (3) Added PCRE_SUPPORT_LIBREADLINE, PCRE_SUPPORT_LIBZ, PCRE_SUPPORT_LIBBZ2. + +22. In UTF-8 mode, with newline set to "any", a pattern such as .*a.*=.b.* + crashed when matching a string such as a\x{2029}b (note that \x{2029} is a + UTF-8 newline character). The key issue is that the pattern starts .*; + this means that the match must be either at the beginning, or after a + newline. The bug was in the code for advancing after a failed match and + checking that the new position followed a newline. It was not taking + account of UTF-8 characters correctly. + +23. PCRE was behaving differently from Perl in the way it recognized POSIX + character classes. PCRE was not treating the sequence [:...:] as a + character class unless the ... were all letters. Perl, however, seems to + allow any characters between [: and :], though of course it rejects as + unknown any "names" that contain non-letters, because all the known class + names consist only of letters. Thus, Perl gives an error for [[:1234:]], + for example, whereas PCRE did not - it did not recognize a POSIX character + class. This seemed a bit dangerous, so the code has been changed to be + closer to Perl. The behaviour is not identical to Perl, because PCRE will + diagnose an unknown class for, for example, [[:l\ower:]] where Perl will + treat it as [[:lower:]]. However, PCRE does now give "unknown" errors where + Perl does, and where it didn't before. + +24. Rewrite so as to remove the single use of %n from pcregrep because in some + Windows environments %n is disabled by default. + + +Version 7.4 21-Sep-07 +--------------------- + +1. Change 7.3/28 was implemented for classes by looking at the bitmap. This + means that a class such as [\s] counted as "explicit reference to CR or + LF". That isn't really right - the whole point of the change was to try to + help when there was an actual mention of one of the two characters. So now + the change happens only if \r or \n (or a literal CR or LF) character is + encountered. + +2. The 32-bit options word was also used for 6 internal flags, but the numbers + of both had grown to the point where there were only 3 bits left. + Fortunately, there was spare space in the data structure, and so I have + moved the internal flags into a new 16-bit field to free up more option + bits. + +3. The appearance of (?J) at the start of a pattern set the DUPNAMES option, + but did not set the internal JCHANGED flag - either of these is enough to + control the way the "get" function works - but the PCRE_INFO_JCHANGED + facility is supposed to tell if (?J) was ever used, so now (?J) at the + start sets both bits. + +4. Added options (at build time, compile time, exec time) to change \R from + matching any Unicode line ending sequence to just matching CR, LF, or CRLF. + +5. doc/pcresyntax.html was missing from the distribution. + +6. Put back the definition of PCRE_ERROR_NULLWSLIMIT, for backward + compatibility, even though it is no longer used. + +7. Added macro for snprintf to pcrecpp_unittest.cc and also for strtoll and + strtoull to pcrecpp.cc to select the available functions in WIN32 when the + windows.h file is present (where different names are used). [This was + reversed later after testing - see 16 below.] + +8. Changed all #include to #include "config.h". There were also + some further cases that I changed to "pcre.h". + +9. When pcregrep was used with the --colour option, it missed the line ending + sequence off the lines that it output. + +10. It was pointed out to me that arrays of string pointers cause lots of + relocations when a shared library is dynamically loaded. A technique of + using a single long string with a table of offsets can drastically reduce + these. I have refactored PCRE in four places to do this. The result is + dramatic: + + Originally: 290 + After changing UCP table: 187 + After changing error message table: 43 + After changing table of "verbs" 36 + After changing table of Posix names 22 + + Thanks to the folks working on Gregex for glib for this insight. + +11. --disable-stack-for-recursion caused compiling to fail unless -enable- + unicode-properties was also set. + +12. Updated the tests so that they work when \R is defaulted to ANYCRLF. + +13. Added checks for ANY and ANYCRLF to pcrecpp.cc where it previously + checked only for CRLF. + +14. Added casts to pcretest.c to avoid compiler warnings. + +15. Added Craig's patch to various pcrecpp modules to avoid compiler warnings. + +16. Added Craig's patch to remove the WINDOWS_H tests, that were not working, + and instead check for _strtoi64 explicitly, and avoid the use of snprintf() + entirely. This removes changes made in 7 above. + +17. The CMake files have been updated, and there is now more information about + building with CMake in the NON-UNIX-USE document. + + Version 7.3 28-Aug-07 --------------------- diff --git a/ext/pcre/pcrelib/NEWS b/ext/pcre/pcrelib/NEWS index 6a30805bb7..185463db0f 100644 --- a/ext/pcre/pcrelib/NEWS +++ b/ext/pcre/pcrelib/NEWS @@ -1,6 +1,25 @@ News about PCRE releases ------------------------ +Release 7.5 10-Jan-08 +--------------------- + +This is mainly a bug-fix release. However the ability to link pcregrep with +libz or libbz2 and the ability to link pcretest with libreadline have been +added. Also the --line-offsets and --file-offsets options were added to +pcregrep. + + +Release 7.4 21-Sep-07 +--------------------- + +The only change of specification is the addition of options to control whether +\R matches any Unicode line ending (the default) or just CR, LF, and CRLF. +Otherwise, the changes are bug fixes and a refactoring to reduce the number of +relocations needed in a shared library. There have also been some documentation +updates, in particular, some more information about using CMake to build PCRE +has been added to the NON-UNIX-USE file. + Release 7.3 28-Aug-07 --------------------- diff --git a/ext/pcre/pcrelib/NON-UNIX-USE b/ext/pcre/pcrelib/NON-UNIX-USE index f1047baa70..9239838e70 100644 --- a/ext/pcre/pcrelib/NON-UNIX-USE +++ b/ext/pcre/pcrelib/NON-UNIX-USE @@ -9,6 +9,7 @@ This document contains the following sections: Building for virtual Pascal Stack size in Windows environments Comments about Win32 builds + Building PCRE with CMake Building under Windows with BCC5.5 Building PCRE on OpenVMS @@ -30,9 +31,10 @@ library consists entirely of code written in Standard C, and so should compile successfully on any system that has a Standard C compiler and library. The C++ wrapper functions are a separate issue (see below). -The PCRE distribution contains some experimental support for "cmake", but this -is incomplete and not documented. However if you are a "cmake" user you might -like to try building with "cmake". +The PCRE distribution includes support for CMake. This support is relatively +new, but has already been used successfully to build PCRE in multiple build +environments on Windows. There are some instructions in the section entitled +"Building PCRE with CMake" below. GENERIC INSTRUCTIONS FOR THE PCRE C LIBRARY @@ -42,10 +44,13 @@ The following are generic comments about building the PCRE C library "by hand". (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, if you want to force a specific value for newline, you can - define the NEWLINE macro. + define the NEWLINE macro. 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. An alternative approach is not to edit config.h, but to use -D on the - compiler command line to make any changes that you need. + compiler command line to make any changes that you need to the + configuration options. In this case -DHAVE_CONFIG_H must not be set. NOTE: There have been occasions when the way in which certain parameters in config.h are used has changed between releases. (In the configure/make @@ -59,13 +64,14 @@ The following are generic comments about building the PCRE C library "by hand". Copy or rename file pcre_chartables.c.dist as pcre_chartables.c. OR: - Compile dftables.c as a stand-alone program, and then run it with the - single argument "pcre_chartables.c". This generates a set of standard - character tables and writes them to that file. The tables are generated - using the default C locale for your system. If you want to use a locale - that is specified by LC_xxx environment variables, add the -L option to - the dftables command. You must use this method if you are building on - a system that uses EBCDIC code. + Compile dftables.c as a stand-alone program (using -DHAVE_CONFIG_H if + you have set up config.h), and then run it with the single argument + "pcre_chartables.c". This generates a set of standard character tables + and writes them to that file. The tables are generated using the default + C locale for your system. If you want to use a locale that is specified + by LC_xxx environment variables, add the -L option to the dftables + command. You must use this method if you are building on a system that + uses EBCDIC code. The tables in pcre_chartables.c are defaults. The caller of PCRE can specify alternative tables at run time. @@ -78,11 +84,13 @@ The following are generic comments about building the PCRE C library "by hand". ucptable.h (5) Also ensure that you have the following file, which is #included as source - when building a debugging version of PCRE and is also used by pcretest. + when building a debugging version of PCRE, and is also used by pcretest. pcre_printint.src - (6) Compile the following source files: + (6) Compile the following source files, setting -DHAVE_CONFIG_H as a compiler + option if you have set up config.h with your configuration, or else use + other -D settings to change the configuration as required. pcre_chartables.c pcre_compile.c @@ -115,18 +123,21 @@ The following are generic comments about building the PCRE C library "by hand". your system has static and shared libraries, you may have to do this once for each type. - (8) Similarly, compile pcreposix.c and link the result (on its own) as the - pcreposix library. + (8) Similarly, compile pcreposix.c (remembering -DHAVE_CONFIG_H if necessary) + and link the result (on its own) as the pcreposix library. - (9) Compile the test program pcretest.c. This needs the functions in the - pcre and pcreposix libraries when linking. It also needs the - pcre_printint.src source file, which it #includes. + (9) Compile the test program pcretest.c (again, don't forget -DHAVE_CONFIG_H). + This needs the functions in the pcre and pcreposix libraries when linking. + It also needs the pcre_printint.src source file, which it #includes. (10) Run pcretest on the testinput files in the testdata directory, and check that the output matches the corresponding testoutput files. Note that the supplied files are in Unix format, with just LF characters as line terminators. You may need to edit them to change this if your system uses - a different convention. + a different convention. If you are using Windows, you probably should use + the wintestinput3 file instead of testinput3 (and the corresponding output + file). This is a locale test; wintestinput3 sets the locale to "french" + rather than "fr_FR", and there some minor output differences. (11) If you want to use the pcregrep command, compile and link pcregrep.c; it uses only the basic PCRE library (it does not need the pcreposix library). @@ -158,11 +169,15 @@ fail because of this. Normally, running out of stack causes a crash, but there have been cases where the test program has just died silently. See your linker documentation for how to increase stack size if you experience problems. The Linux default of 8Mb is a reasonable choice for the stack, though even that can -be too small for some pattern/subject combinations. There is more about stack -usage in the "pcrestack" documentation. +be too small for some pattern/subject combinations. +PCRE has a compile configuration option to disable the use of stack for +recursion so that heap is used instead. However, pattern matching is +significantly slower when this is done. There is more about stack usage in the +"pcrestack" documentation. -COMMENTS ABOUT WIN32 BUILDS + +COMMENTS ABOUT WIN32 BUILDS (see also "BUILDING PCRE WITH CMAKE" below) There are two ways of building PCRE using the "configure, make, make install" paradigm on Windows systems: using MinGW or using Cygwin. These are not at all @@ -237,6 +252,60 @@ terminators in order to get some of the tests to work. We hope to improve things in this area in future. +BUILDING PCRE WITH CMAKE + +CMake is an alternative build facility that can be used instead of the +traditional Unix "configure". CMake version 2.4.7 supports Borland makefiles, +MinGW makefiles, MSYS makefiles, NMake makefiles, UNIX makefiles, Visual Studio +6, Visual Studio 7, Visual Studio 8, and Watcom W8. The following instructions +were contributed by a PCRE user. + +1. Download CMake 2.4.7 or above from http://www.cmake.org/, install and ensure + that cmake\bin is on your path. + +2. Unzip (retaining folder structure) the PCRE source tree into a source + directory such as C:\pcre. + +3. Create a new, empty build directory: C:\pcre\build\ + +4. Run CMakeSetup from the Shell envirornment of your build tool, e.g., Msys + for Msys/MinGW or Visual Studio Command Prompt for VC/VC++ + +5. Enter C:\pcre\pcre-xx and C:\pcre\build for the source and build + directories, respectively + +6. Hit the "Configure" button. + +7. Select the particular IDE / build tool that you are using (Visual Studio, + MSYS makefiles, MinGW makefiles, etc.) + +8. The GUI will then list several configuration options. This is where you can + enable UTF-8 support, etc. + +9. Hit "Configure" again. The adjacent "OK" button should now be active. + +10. Hit "OK". + +11. The build directory should now contain a usable build system, be it a + solution file for Visual Studio, makefiles for MinGW, etc. + +Testing with RunTest.bat + +1. Copy RunTest.bat into the directory where pcretest.exe has been created. + +2. Edit RunTest.bat and insert a line that indentifies the relative location of + the pcre source, e.g.: + + set srcdir=..\pcre-7.4-RC3 + +3. Run RunTest.bat from a command shell environment. Test outputs will + automatically be compared to expected results, and discrepancies will + identified in the console output. + +4. To test pcrecpp, run pcrecpp_unittest.exe, pcre_stringpiece_unittest.exe and + pcre_scanner_unittest.exe. + + BUILDING UNDER WINDOWS WITH BCC5.5 Michael Roy sent these comments about building PCRE under Windows with BCC5.5: @@ -315,5 +384,5 @@ $! Locale could not be set to fr $! ========================= -Last Updated: 01 August 2007 +Last Updated: 21 September 2007 **** diff --git a/ext/pcre/pcrelib/README b/ext/pcre/pcrelib/README index 2f4d3c5771..ad6ca4dbfd 100644 --- a/ext/pcre/pcrelib/README +++ b/ext/pcre/pcrelib/README @@ -103,7 +103,9 @@ Building PCRE on non-Unix systems For a non-Unix system, please read the comments in the file NON-UNIX-USE, though if your system supports the use of "configure" and "make" you may be -able to build PCRE in the same way as for Unix-like systems. +able to build PCRE in the same way as for Unix-like systems. PCRE can also be +configured in many platform environments using the GUI facility of CMake's +CMakeSetup. It creates Makefiles, solution files, etc. PCRE has been compiled on many different operating systems. It should be straightforward to build PCRE on any system that has a Standard C compiler and @@ -184,6 +186,12 @@ library. You can read more about them in the pcrebuild man page. --enable-newline-is-any, many tests should succeed, but there may be some failures. +. By default, the sequence \R in a pattern matches any Unicode line ending + sequence. This is independent of the option specifying what PCRE considers to + be the end of a line (see above). However, the caller of PCRE can restrict \R + to match only CR, LF, or CRLF. You can make this the default by adding + --enable-bsr-anycrlf to the "configure" command (bsr = "backslash R"). + . When called via the POSIX interface, PCRE uses malloc() to get additional storage for processing capturing parentheses if there are more than 10 of them in a pattern. You can increase this threshold by setting, for example, @@ -250,6 +258,24 @@ library. You can read more about them in the pcrebuild man page. This automatically implies --enable-rebuild-chartables (see above). +. It is possible to compile pcregrep to use libz and/or libbz2, in order to + read .gz and .bz2 files (respectively), by specifying one or both of + + --enable-pcregrep-libz + --enable-pcregrep-libbz2 + + Of course, the relevant libraries must be installed on your system. + +. It is possible to compile pcretest so that it links with the libreadline + library, by specifying + + --enable-pcretest-libreadline + + If this is done, when pcretest's input is from a terminal, it reads it using + the readline() function. This provides line-editing and history facilities. + Note that libreadline is GPL-licenced, so if you distribute a binary of + pcretest linked in this way, there may be licensing issues. + The "configure" script builds the following files for the basic C library: . Makefile is the makefile that builds the library @@ -500,7 +526,10 @@ in the comparison output, it means that locale is not available on your system, despite being listed by "locale". This does not mean that PCRE is broken. [If you are trying to run this test on Windows, you may be able to get it to -work by changing "fr_FR" to "french" everywhere it occurs.] +work by changing "fr_FR" to "french" everywhere it occurs. Alternatively, use +RunTest.bat. The version of RunTest.bat included with PCRE 7.4 and above uses +Windows versions of test 2. More info on using RunTest.bat is included in the +document entitled NON-UNIX-USE.] The fourth test checks the UTF-8 support. It is not run automatically unless PCRE is built with UTF-8 support. To do this you must set --enable-utf8 when @@ -714,4 +743,4 @@ The distribution should contain the following files: Philip Hazel Email local part: ph10 Email domain: cam.ac.uk -Last updated: 24 April 2007 +Last updated: 18 December 2007 diff --git a/ext/pcre/pcrelib/config.h b/ext/pcre/pcrelib/config.h index b16c6b6500..005e3f8b0c 100644 --- a/ext/pcre/pcrelib/config.h +++ b/ext/pcre/pcrelib/config.h @@ -20,13 +20,24 @@ it to run on SunOS4 and other "close to standard" systems. If you are going to build PCRE "by hand" on a system without "configure" you should copy the distributed config.h.generic to config.h, and then set up the -macros the way you need them. Alternatively, you can avoid editing by using -D -on the compiler command line to set the macro values. +macro definitions the way you need them. You must then add -DHAVE_CONFIG_H to +all of your compile commands, so that config.h is included at the start of +every source. + +Alternatively, you can avoid editing by using -D on the compiler command line +to set the macro values. In this case, you do not have to set -DHAVE_CONFIG_H. PCRE uses memmove() if HAVE_MEMMOVE is set to 1; otherwise it uses bcopy() if HAVE_BCOPY is set to 1. If your system has neither bcopy() nor memmove(), set them both to 0; an emulation function will be used. */ +/* By default, the \R escape sequence matches any Unicode line ending + character or sequence of characters. If BSR_ANYCRLF is defined, this is + changed so that backslash-R matches only CR, LF, or CRLF. The build- time + default can be overridden by the user of PCRE at runtime. On systems that + support it, "configure" can be used to override the default. */ +/* #undef BSR_ANYCRLF */ + /* If you are compiling for a system that uses EBCDIC instead of ASCII character codes, define this macro as 1. On systems that can use "configure", this can be done via --enable-ebcdic. */ @@ -40,6 +51,11 @@ them both to 0; an emulation function will be used. */ /* Define to 1 if you have the header file. */ /* #undef HAVE_BITS_TYPE_TRAITS_H */ +/* Define to 1 if you have the header file. */ +#ifndef HAVE_BZLIB_H +#define HAVE_BZLIB_H 1 +#endif + /* Define to 1 if you have the header file. */ #ifndef HAVE_DIRENT_H #define HAVE_DIRENT_H 1 @@ -75,6 +91,16 @@ them both to 0; an emulation function will be used. */ #define HAVE_MEMORY_H 1 #endif +/* Define to 1 if you have the header file. */ +#ifndef HAVE_READLINE_HISTORY_H +#define HAVE_READLINE_HISTORY_H 1 +#endif + +/* Define to 1 if you have the header file. */ +#ifndef HAVE_READLINE_READLINE_H +#define HAVE_READLINE_READLINE_H 1 +#endif + /* Define to 1 if you have the header file. */ #ifndef HAVE_STDINT_H #define HAVE_STDINT_H 1 @@ -141,6 +167,14 @@ them both to 0; an emulation function will be used. */ /* Define to 1 if you have the header file. */ /* #undef HAVE_WINDOWS_H */ +/* Define to 1 if you have the header file. */ +#ifndef HAVE_ZLIB_H +#define HAVE_ZLIB_H 1 +#endif + +/* Define to 1 if you have the `_strtoi64' function. */ +/* #undef HAVE__STRTOI64 */ + /* The value of LINK_SIZE determines the number of bytes used to store links as offsets within the compiled regex. The default is 2, which allows for compiled patterns up to 64K long. This covers the vast majority of cases. @@ -189,10 +223,10 @@ them both to 0; an emulation function will be used. */ #define MAX_NAME_SIZE 32 #endif -/* The value of NEWLINE determines the newline character sequence. On - Unix-like systems, "configure" can be used to override the default, which - is 10. The possible values are 10 (LF), 13 (CR), 3338 (CRLF), -1 (ANY), or - -2 (ANYCRLF). */ +/* The value of NEWLINE determines the newline character sequence. On systems + that support it, "configure" can be used to override the default, which is + 10. The possible values are 10 (LF), 13 (CR), 3338 (CRLF), -1 (ANY), or -2 + (ANYCRLF). */ #ifndef NEWLINE #define NEWLINE 10 #endif @@ -217,13 +251,13 @@ them both to 0; an emulation function will be used. */ #define PACKAGE_NAME "PCRE" /* Define to the full name and version of this package. */ -#define PACKAGE_STRING "PCRE 7.3" +#define PACKAGE_STRING "PCRE 7.5" /* Define to the one symbol short name of this package. */ #define PACKAGE_TARNAME "pcre" /* Define to the version of this package. */ -#define PACKAGE_VERSION "7.3" +#define PACKAGE_VERSION "7.5" /* If you are compiling for a system other than a Unix-like system or @@ -257,6 +291,17 @@ them both to 0; an emulation function will be used. */ #define STDC_HEADERS 1 #endif +/* Define to allow pcregrep to be linked with libbz2, so that it is able to + handle .bz2 files. */ +/* #undef SUPPORT_LIBBZ2 */ + +/* Define to allow pcretest to be linked with libreadline. */ +/* #undef SUPPORT_LIBREADLINE */ + +/* Define to allow pcregrep to be linked with libz, so that it is able to + handle .gz files. */ +/* #undef SUPPORT_LIBZ */ + /* Define to enable support for Unicode properties */ /* #undef SUPPORT_UCP */ @@ -265,7 +310,7 @@ them both to 0; an emulation function will be used. */ /* Version number of package */ #ifndef VERSION -#define VERSION "7.3" +#define VERSION "7.5" #endif /* Define to empty if `const' does not conform to ANSI C. */ diff --git a/ext/pcre/pcrelib/dftables.c b/ext/pcre/pcrelib/dftables.c index cf3b21052f..895373ee43 100644 --- a/ext/pcre/pcrelib/dftables.c +++ b/ext/pcre/pcrelib/dftables.c @@ -43,7 +43,7 @@ character tables for PCRE. The tables are built according to the current locale. Now that pcre_maketables is a function visible to the outside world, we make use of its code from here in order to be consistent. */ -#include +#include "config.h" #include #include @@ -108,7 +108,7 @@ fprintf(f, "outside this compilation unit might reference this\" and so it will always\n" "be supplied to the linker. */\n\n" "#ifdef HAVE_CONFIG_H\n" - "#include \n" + "#include \"config.h\"\n" "#endif\n\n" "#include \"pcre_internal.h\"\n\n"); fprintf(f, diff --git a/ext/pcre/pcrelib/doc/pcre.txt b/ext/pcre/pcrelib/doc/pcre.txt index f924f6de89..1a298f0d6e 100644 --- a/ext/pcre/pcrelib/doc/pcre.txt +++ b/ext/pcre/pcrelib/doc/pcre.txt @@ -271,19 +271,24 @@ NAME PCRE BUILD-TIME OPTIONS This document describes the optional features of PCRE that can be - selected when the library is compiled. They are all selected, or dese- - lected, by providing options to the configure script that is run before - the make command. The complete list of options for configure (which - includes the standard ones such as the selection of the installation - directory) can be obtained by running + selected when the library is compiled. It assumes use of the configure + script, where the optional features are selected or deselected by pro- + viding options to configure before running the make command. However, + the same options can be selected in both Unix-like and non-Unix-like + environments using the GUI facility of CMakeSetup if you are using + CMake instead of configure to build PCRE. + + The complete list of options for configure (which includes the standard + ones such as the selection of the installation directory) can be + obtained by running ./configure --help - The following sections include descriptions of options whose names + The following sections include descriptions of options whose names begin with --enable or --disable. These settings specify changes to the - defaults for the configure command. Because of the way that configure - works, --enable and --disable always come in pairs, so the complemen- - tary option always exists as well, but as it specifies the default, it + defaults for the configure command. Because of the way that configure + works, --enable and --disable always come in pairs, so the complemen- + tary option always exists as well, but as it specifies the default, it is not described. @@ -304,40 +309,40 @@ UTF-8 SUPPORT --enable-utf8 - to the configure command. Of itself, this does not make PCRE treat - strings as UTF-8. As well as compiling PCRE with this option, you also - have have to set the PCRE_UTF8 option when you call the pcre_compile() + to the configure command. Of itself, this does not make PCRE treat + strings as UTF-8. As well as compiling PCRE with this option, you also + have have to set the PCRE_UTF8 option when you call the pcre_compile() function. UNICODE CHARACTER PROPERTY SUPPORT - UTF-8 support allows PCRE to process character values greater than 255 - in the strings that it handles. On its own, however, it does not pro- + UTF-8 support allows PCRE to process character values greater than 255 + in the strings that it handles. On its own, however, it does not pro- vide any facilities for accessing the properties of such characters. If - you want to be able to use the pattern escapes \P, \p, and \X, which + you want to be able to use the pattern escapes \P, \p, and \X, which refer to Unicode character properties, you must add --enable-unicode-properties - to the configure command. This implies UTF-8 support, even if you have + to the configure command. This implies UTF-8 support, even if you have not explicitly requested it. - Including Unicode property support adds around 30K of tables to the - PCRE library. Only the general category properties such as Lu and Nd + Including Unicode property support adds around 30K of tables to the + PCRE library. Only the general category properties such as Lu and Nd are supported. Details are given in the pcrepattern documentation. CODE VALUE OF NEWLINE - By default, PCRE interprets character 10 (linefeed, LF) as indicating - the end of a line. This is the normal newline character on Unix-like + By default, PCRE interprets character 10 (linefeed, LF) as indicating + the end of a line. This is the normal newline character on Unix-like systems. You can compile PCRE to use character 13 (carriage return, CR) instead, by adding --enable-newline-is-cr - to the configure command. There is also a --enable-newline-is-lf + to the configure command. There is also a --enable-newline-is-lf option, which explicitly specifies linefeed as the newline character. Alternatively, you can specify that line endings are to be indicated by @@ -349,22 +354,35 @@ CODE VALUE OF NEWLINE --enable-newline-is-anycrlf - which causes PCRE to recognize any of the three sequences CR, LF, or + which causes PCRE to recognize any of the three sequences CR, LF, or CRLF as indicating a line ending. Finally, a fifth option, specified by --enable-newline-is-any causes PCRE to recognize any Unicode newline sequence. - Whatever line ending convention is selected when PCRE is built can be - overridden when the library functions are called. At build time it is + Whatever line ending convention is selected when PCRE is built can be + overridden when the library functions are called. At build time it is conventional to use the standard for your operating system. +WHAT \R MATCHES + + By default, the sequence \R in a pattern matches any Unicode newline + sequence, whatever has been selected as the line ending sequence. If + you specify + + --enable-bsr-anycrlf + + the default is changed so that \R matches only CR, LF, or CRLF. What- + ever is selected when PCRE is built can be overridden when the library + functions are called. + + BUILDING SHARED AND STATIC LIBRARIES - The PCRE building process uses libtool to build both shared and static - Unix libraries by default. You can suppress one of these by adding one + The PCRE building process uses libtool to build both shared and static + Unix libraries by default. You can suppress one of these by adding one of --disable-shared @@ -376,9 +394,9 @@ BUILDING SHARED AND STATIC LIBRARIES POSIX MALLOC USAGE When PCRE is called through the POSIX interface (see the pcreposix doc- - umentation), additional working storage is required for holding the - pointers to capturing substrings, because PCRE requires three integers - per substring, whereas the POSIX interface provides only two. If the + umentation), additional working storage is required for holding the + pointers to capturing substrings, because PCRE requires three integers + per substring, whereas the POSIX interface provides only two. If the number of expected substrings is small, the wrapper function uses space on the stack, because this is faster than using malloc() for each call. The default threshold above which the stack is no longer used is 10; it @@ -391,114 +409,141 @@ POSIX MALLOC USAGE HANDLING VERY LARGE PATTERNS - Within a compiled pattern, offset values are used to point from one - part to another (for example, from an opening parenthesis to an alter- - nation metacharacter). By default, two-byte values are used for these - offsets, leading to a maximum size for a compiled pattern of around - 64K. This is sufficient to handle all but the most gigantic patterns. - Nevertheless, some people do want to process enormous patterns, so it - is possible to compile PCRE to use three-byte or four-byte offsets by + Within a compiled pattern, offset values are used to point from one + part to another (for example, from an opening parenthesis to an alter- + nation metacharacter). By default, two-byte values are used for these + offsets, leading to a maximum size for a compiled pattern of around + 64K. This is sufficient to handle all but the most gigantic patterns. + Nevertheless, some people do want to process enormous patterns, so it + is possible to compile PCRE to use three-byte or four-byte offsets by adding a setting such as --with-link-size=3 - to the configure command. The value given must be 2, 3, or 4. Using - longer offsets slows down the operation of PCRE because it has to load + to the configure command. The value given must be 2, 3, or 4. Using + longer offsets slows down the operation of PCRE because it has to load additional bytes when handling them. AVOIDING EXCESSIVE STACK USAGE When matching with the pcre_exec() function, PCRE implements backtrack- - ing by making recursive calls to an internal function called match(). - In environments where the size of the stack is limited, this can se- - verely limit PCRE's operation. (The Unix environment does not usually + ing by making recursive calls to an internal function called match(). + In environments where the size of the stack is limited, this can se- + verely limit PCRE's operation. (The Unix environment does not usually suffer from this problem, but it may sometimes be necessary to increase - the maximum stack size. There is a discussion in the pcrestack docu- - mentation.) An alternative approach to recursion that uses memory from - the heap to remember data, instead of using recursive function calls, - has been implemented to work round the problem of limited stack size. + the maximum stack size. There is a discussion in the pcrestack docu- + mentation.) An alternative approach to recursion that uses memory from + the heap to remember data, instead of using recursive function calls, + has been implemented to work round the problem of limited stack size. If you want to build a version of PCRE that works this way, add --disable-stack-for-recursion - to the configure command. With this configuration, PCRE will use the - pcre_stack_malloc and pcre_stack_free variables to call memory manage- - ment functions. By default these point to malloc() and free(), but you + to the configure command. With this configuration, PCRE will use the + pcre_stack_malloc and pcre_stack_free variables to call memory manage- + ment functions. By default these point to malloc() and free(), but you can replace the pointers so that your own functions are used. - Separate functions are provided rather than using pcre_malloc and - pcre_free because the usage is very predictable: the block sizes - requested are always the same, and the blocks are always freed in - reverse order. A calling program might be able to implement optimized - functions that perform better than malloc() and free(). PCRE runs + Separate functions are provided rather than using pcre_malloc and + pcre_free because the usage is very predictable: the block sizes + requested are always the same, and the blocks are always freed in + reverse order. A calling program might be able to implement optimized + functions that perform better than malloc() and free(). PCRE runs noticeably more slowly when built in this way. This option affects only - the pcre_exec() function; it is not relevant for the the + the pcre_exec() function; it is not relevant for the the pcre_dfa_exec() function. LIMITING PCRE RESOURCE USAGE - Internally, PCRE has a function called match(), which it calls repeat- - edly (sometimes recursively) when matching a pattern with the - pcre_exec() function. By controlling the maximum number of times this - function may be called during a single matching operation, a limit can - be placed on the resources used by a single call to pcre_exec(). The - limit can be changed at run time, as described in the pcreapi documen- - tation. The default is 10 million, but this can be changed by adding a + Internally, PCRE has a function called match(), which it calls repeat- + edly (sometimes recursively) when matching a pattern with the + pcre_exec() function. By controlling the maximum number of times this + function may be called during a single matching operation, a limit can + be placed on the resources used by a single call to pcre_exec(). The + limit can be changed at run time, as described in the pcreapi documen- + tation. The default is 10 million, but this can be changed by adding a setting such as --with-match-limit=500000 - to the configure command. This setting has no effect on the + to the configure command. This setting has no effect on the pcre_dfa_exec() matching function. - In some environments it is desirable to limit the depth of recursive + In some environments it is desirable to limit the depth of recursive calls of match() more strictly than the total number of calls, in order - to restrict the maximum amount of stack (or heap, if --disable-stack- + to restrict the maximum amount of stack (or heap, if --disable-stack- for-recursion is specified) that is used. A second limit controls this; - it defaults to the value that is set for --with-match-limit, which - imposes no additional constraints. However, you can set a lower limit + it defaults to the value that is set for --with-match-limit, which + imposes no additional constraints. However, you can set a lower limit by adding, for example, --with-match-limit-recursion=10000 - to the configure command. This value can also be overridden at run + to the configure command. This value can also be overridden at run time. CREATING CHARACTER TABLES AT BUILD TIME - PCRE uses fixed tables for processing characters whose code values are - less than 256. By default, PCRE is built with a set of tables that are - distributed in the file pcre_chartables.c.dist. These tables are for + PCRE uses fixed tables for processing characters whose code values are + less than 256. By default, PCRE is built with a set of tables that are + distributed in the file pcre_chartables.c.dist. These tables are for ASCII codes only. If you add --enable-rebuild-chartables - to the configure command, the distributed tables are no longer used. - Instead, a program called dftables is compiled and run. This outputs + to the configure command, the distributed tables are no longer used. + Instead, a program called dftables is compiled and run. This outputs the source for new set of tables, created in the default locale of your C runtime system. (This method of replacing the tables does not work if - you are cross compiling, because dftables is run on the local host. If - you need to create alternative tables when cross compiling, you will + you are cross compiling, because dftables is run on the local host. If + you need to create alternative tables when cross compiling, you will have to do so "by hand".) USING EBCDIC CODE - PCRE assumes by default that it will run in an environment where the - character code is ASCII (or Unicode, which is a superset of ASCII). - This is the case for most computer operating systems. PCRE can, how- + PCRE assumes by default that it will run in an environment where the + character code is ASCII (or Unicode, which is a superset of ASCII). + This is the case for most computer operating systems. PCRE can, how- ever, be compiled to run in an EBCDIC environment by adding --enable-ebcdic to the configure command. This setting implies --enable-rebuild-charta- - bles. You should only use it if you know that you are in an EBCDIC + bles. You should only use it if you know that you are in an EBCDIC environment (for example, an IBM mainframe operating system). +PCREGREP OPTIONS FOR COMPRESSED FILE SUPPORT + + By default, pcregrep reads all files as plain text. You can build it so + that it recognizes files whose names end in .gz or .bz2, and reads them + with libz or libbz2, respectively, by adding one or both of + + --enable-pcregrep-libz + --enable-pcregrep-libbz2 + + to the configure command. These options naturally require that the rel- + evant libraries are installed on your system. Configuration will fail + if they are not. + + +PCRETEST OPTION FOR LIBREADLINE SUPPORT + + If you add + + --enable-pcretest-libreadline + + to the configure command, pcretest is linked with the libreadline + library, and when its input is from a terminal, it reads it using the + readline() function. This provides line-editing and history facilities. + Note that libreadline is GPL-licenced, so if you distribute a binary of + pcretest linked in this way, there may be licensing issues. + + SEE ALSO pcreapi(3), pcre_config(3). @@ -513,7 +558,7 @@ AUTHOR REVISION - Last updated: 30 July 2007 + Last updated: 18 December 2007 Copyright (c) 1997-2007 University of Cambridge. ------------------------------------------------------------------------------ @@ -919,18 +964,21 @@ NEWLINES dollar metacharacters, the handling of #-comments in /x mode, and, when CRLF is a recognized line ending sequence, the match position advance- ment for a non-anchored pattern. There is more detail about this in the - section on pcre_exec() options below. The choice of newline convention - does not affect the interpretation of the \n or \r escape sequences. + section on pcre_exec() options below. + + The choice of newline convention does not affect the interpretation of + the \n or \r escape sequences, nor does it affect what \R matches, + which is controlled in a similar way, but by separate options. MULTITHREADING - The PCRE functions can be used in multi-threading applications, with + The 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. @@ -938,10 +986,10 @@ MULTITHREADING 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. However, compiling a regular expression - with one version of PCRE for use with a different version is not guar- + 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. However, compiling a regular expression + with one version of PCRE for use with a different version is not guar- anteed to work and may cause crashes. @@ -949,69 +997,77 @@ 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 following information is + into which the information is placed. The following information is available: PCRE_CONFIG_UTF8 - The output is an integer that is set to one if UTF-8 support is avail- + The output is an integer that is set to one if UTF-8 support is avail- able; otherwise it is set to zero. PCRE_CONFIG_UNICODE_PROPERTIES - The output is an integer that is set to one if support for Unicode + The output is an integer that is set to one if support for Unicode character properties is available; otherwise it is set to zero. PCRE_CONFIG_NEWLINE - The output is an integer whose value specifies the default character - sequence that is recognized as meaning "newline". The four values that + The output is an integer whose value specifies the default character + sequence that is recognized as meaning "newline". The four values that are supported are: 10 for LF, 13 for CR, 3338 for CRLF, -2 for ANYCRLF, - and -1 for ANY. The default should normally be the standard sequence + and -1 for ANY. The default should normally be the standard sequence for your operating system. + PCRE_CONFIG_BSR + + The output is an integer whose value indicates what character sequences + the \R escape sequence matches by default. A value of 0 means that \R + matches any Unicode line ending sequence; a value of 1 means that \R + matches only CR, LF, or CRLF. The default can be overridden when a pat- + tern is compiled or matched. + PCRE_CONFIG_LINK_SIZE - The output is an integer that contains the number of bytes used for + The output is an integer that contains the number of bytes used for internal linkage in compiled regular expressions. The value is 2, 3, or - 4. Larger values allow larger regular expressions to be compiled, at - the expense of slower matching. The default value of 2 is sufficient - for all but the most massive patterns, since it allows the compiled + 4. Larger values allow larger regular expressions to be compiled, at + the expense of slower matching. The default value of 2 is sufficient + for all but the most massive patterns, since it allows the compiled pattern to be up to 64K in size. PCRE_CONFIG_POSIX_MALLOC_THRESHOLD - The output is an integer that contains the threshold above which the - POSIX interface uses malloc() for output vectors. Further details are + The output is an integer that contains the threshold above which the + POSIX interface uses malloc() for output vectors. Further details are given in the pcreposix documentation. PCRE_CONFIG_MATCH_LIMIT The output is an integer that gives the default limit for the number of - internal matching function calls in a pcre_exec() execution. Further + internal matching function calls in a pcre_exec() execution. Further details are given with pcre_exec() below. PCRE_CONFIG_MATCH_LIMIT_RECURSION - The output is an integer that gives the default limit for the depth of - recursion when calling the internal matching function in a pcre_exec() + The output is an integer that gives the default limit for the depth of + recursion when calling the internal matching function in a pcre_exec() execution. Further details are given with pcre_exec() below. PCRE_CONFIG_STACKRECURSE - The output is an integer that is set to one if internal recursion when + 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. @@ -1028,55 +1084,55 @@ 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, + the two interfaces is that pcre_compile2() has an additional argument, errorcodeptr, via which a numerical error code can be returned. The pattern is a C string terminated by a binary zero, and is passed in - the pattern argument. A pointer to a single block of memory that is - obtained via pcre_malloc is returned. This contains the compiled code + 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, can also be set and unset from within the - pattern (see the detailed description in the pcrepattern documenta- - tion). For these options, the contents of the options argument speci- - fies their initial settings at the start of compilation and execution. - The PCRE_ANCHORED and PCRE_NEWLINE_xxx options can be set at the time + 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, can also be set and unset from within the + pattern (see the detailed description in the pcrepattern documenta- + tion). For these options, the contents of the options argument speci- + fies their initial settings at the start of compilation and execution. + The PCRE_ANCHORED and PCRE_NEWLINE_xxx options can be set at the time of matching as well as at compile time. If errptr is NULL, pcre_compile() returns NULL immediately. Otherwise, - if compilation of a pattern fails, pcre_compile() returns NULL, and + if compilation of a pattern fails, pcre_compile() returns NULL, and sets the variable pointed to by errptr to point to a textual error mes- sage. This is a static string that is part of the library. You must not try to free it. The offset from the start of the pattern to the charac- ter where the error was discovered is placed in the variable pointed to - by erroffset, which must not be NULL. If it is, an immediate error is + by erroffset, which must not be NULL. If it is, an immediate error is given. - If pcre_compile2() is used instead of pcre_compile(), and the error- - codeptr argument is not NULL, a non-zero error code number is returned - via this argument in the event of an error. This is in addition to the + 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; @@ -1089,111 +1145,120 @@ 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, + 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 metacharater in the pattern matches all char- - acters, including those that indicate newline. Without it, a dot does - not match when the current position is at a newline. This option is - equivalent to Perl's /s option, and it can be changed within a pattern - by a (?s) option setting. A negative class such as [^a] always matches + acters, including those that indicate newline. Without it, a dot does + not match when the current position is at a newline. This option is + equivalent to Perl's /s option, and it can be changed within a pattern + by a (?s) option setting. A negative class such as [^a] always matches newline characters, independent of the setting 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, whitespace data characters in the pattern are + If this bit is set, whitespace data characters in the pattern are totally ignored except when escaped or inside a character class. White- space does not include the VT character (code 11). In addition, charac- ters between an unescaped # outside a character class and the next new- - line, inclusive, are also ignored. This is equivalent to Perl's /x - option, and it can be changed within a pattern by a (?x) option set- + line, inclusive, are also ignored. This is equivalent to Perl's /x + option, and it can be changed within a pattern by a (?x) option set- ting. - This option makes it possible to include comments inside complicated - patterns. Note, however, that this applies only to data characters. - Whitespace characters may never appear within special character - sequences in a pattern, for example within the sequence (?( which + This option makes it possible to include comments inside complicated + patterns. Note, however, that this applies only to data characters. + Whitespace characters may never appear within special character + sequences in a pattern, for example within the sequence (?( which introduces a conditional subpattern. PCRE_EXTRA - This option was invented in order to turn on additional functionality - of PCRE that is incompatible with Perl, but it is currently of very - little use. When set, any backslash in a pattern that is followed by a - letter that has no special meaning causes an error, thus reserving - these combinations for future expansion. By default, as in Perl, a - backslash followed by a letter with no special meaning is treated as a - literal. (Perl can, however, be persuaded to give a warning for this.) - There are at present no other features controlled by this option. It + This option was invented in order to turn on additional functionality + of PCRE that is incompatible with Perl, but it is currently of very + little use. When set, any backslash in a pattern that is followed by a + letter that has no special meaning causes an error, thus reserving + these combinations for future expansion. By default, as in Perl, a + backslash followed by a letter with no special meaning is treated as a + literal. (Perl can, however, be persuaded to give a warning for this.) + There are at present no other features controlled by this option. It can also be set by a (?X) option setting within a pattern. PCRE_FIRSTLINE - If this option is set, an unanchored pattern is required to match - before or at the first newline in the subject string, though the + If this option is set, an unanchored pattern is required to match + before or at the first newline in the subject string, though the matched text may continue over the newline. PCRE_MULTILINE - By default, PCRE treats the subject string as consisting of a single - line of characters (even if it actually contains newlines). The "start - of line" metacharacter (^) matches only at the start of the string, - while the "end of line" metacharacter ($) matches only at the end of + 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 @@ -1202,81 +1267,81 @@ 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. The Unicode newline sequences are the three just mentioned, - plus the single characters VT (vertical tab, U+000B), FF (formfeed, - U+000C), NEL (next line, U+0085), LS (line separator, U+2028), and PS - (paragraph separator, U+2029). The last two are recognized only in + plus the single characters VT (vertical tab, U+000B), FF (formfeed, + U+000C), NEL (next line, U+0085), LS (line separator, U+2028), and PS + (paragraph separator, U+2029). The last two are recognized only in UTF-8 mode. - 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 is specially recognized when compiling - a pattern is if PCRE_EXTENDED is set, and an unescaped # outside a - character class is encountered. This indicates a comment that lasts - until after the next line break sequence. In other circumstances, line - break sequences are treated as literal data, except that in + The only time that a line break is specially recognized when compiling + a pattern is if PCRE_EXTENDED is set, and an unescaped # outside a + character class is encountered. This indicates a comment that lasts + until after the next line break sequence. In other circumstances, line + break sequences are treated as literal data, except that in PCRE_EXTENDED mode, both CR and LF are treated as whitespace characters and are therefore ignored. The newline option that is set at compile time becomes the default that - is used for pcre_exec() and pcre_dfa_exec(), but it can be overridden. + is used for pcre_exec() and pcre_dfa_exec(), but it can be overridden. PCRE_NO_AUTO_CAPTURE If this option is set, it disables the use of numbered capturing paren- - theses in the pattern. Any opening parenthesis that is not followed by - ? behaves as if it were followed by ?: but named parentheses can still - be used for capturing (and they acquire numbers in the usual way). + theses in the pattern. Any opening parenthesis that is not followed by + ? behaves as if it were followed by ?: but named parentheses can still + be used for capturing (and they acquire numbers in the usual way). There is no equivalent of this option in Perl. PCRE_UNGREEDY - This option inverts the "greediness" of the quantifiers so that they - are not greedy by default, but become greedy if followed by "?". It is - not compatible with Perl. It can also be set by a (?U) option setting + This option inverts the "greediness" of the quantifiers so that they + are not greedy by default, but become greedy if followed by "?". It is + not compatible with Perl. It can also be set by a (?U) option setting within the pattern. PCRE_UTF8 - This option causes PCRE to regard both the pattern and the subject as - strings of UTF-8 characters instead of single-byte character strings. - However, it is available only when PCRE is built to include UTF-8 sup- - port. If not, the use of this option provokes an error. Details of how - this option changes the behaviour of PCRE are given in the section on + This option causes PCRE to regard both the pattern and the subject as + strings of UTF-8 characters instead of single-byte character strings. + However, it is available only when PCRE is built to include UTF-8 sup- + port. If not, the use of this option provokes an error. Details of how + this option changes the behaviour of PCRE are given in the section on UTF-8 support in the main pcre page. PCRE_NO_UTF8_CHECK When PCRE_UTF8 is set, the validity of the pattern as a UTF-8 string is - automatically checked. There is a discussion about the validity of - UTF-8 strings in the main pcre page. If an invalid UTF-8 sequence of - bytes is found, pcre_compile() returns an error. If you already know + automatically checked. There is a discussion about the validity of + UTF-8 strings in the main pcre page. If an invalid UTF-8 sequence of + bytes is found, pcre_compile() returns an error. If you already know that your pattern is valid, and you want to skip this check for perfor- - mance reasons, you can set the PCRE_NO_UTF8_CHECK option. When it is - set, the effect of passing an invalid UTF-8 string as a pattern is - undefined. It may cause your program to crash. Note that this option - can also be passed to pcre_exec() and pcre_dfa_exec(), to suppress the + mance reasons, you can set the PCRE_NO_UTF8_CHECK option. When it is + set, the effect of passing an invalid UTF-8 string as a pattern is + undefined. It may cause your program to crash. Note that this option + can also be passed to pcre_exec() and pcre_dfa_exec(), to suppress the UTF-8 validity checking of subject strings. COMPILATION ERROR CODES - The following table lists the error codes than may be returned by - pcre_compile2(), along with the error messages that may be returned by - both compiling functions. As PCRE has developed, some error codes 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. As PCRE has developed, some error codes have fallen out of use. To avoid confusion, they have not been re-used. 0 no error @@ -1291,7 +1356,7 @@ COMPILATION ERROR CODES 9 nothing to repeat 10 [this code is not in use] 11 internal error: unexpected repeat - 12 unrecognized character after (? + 12 unrecognized character after (? or (?- 13 POSIX named classes are supported only within a class 14 missing ) 15 reference to non-existent subpattern @@ -1299,7 +1364,7 @@ COMPILATION ERROR CODES 17 unknown option bit(s) set 18 missing ) after comment 19 [this code is not in use] - 20 regular expression too large + 20 regular expression is too large 21 failed to get memory 22 unmatched parentheses 23 internal error: code overflow @@ -1328,18 +1393,26 @@ COMPILATION ERROR CODES 46 malformed \P or \p sequence 47 unknown property name after \P or \p 48 subpattern name is too long (maximum 32 characters) - 49 too many named subpatterns (maximum 10,000) + 49 too many named subpatterns (maximum 10000) 50 [this code is not in use] 51 octal value is greater than \377 (not in UTF-8 mode) 52 internal error: overran compiling workspace - 53 internal error: previously-checked referenced subpattern not + 53 internal error: previously-checked referenced subpattern not found 54 DEFINE group contains more than one branch 55 repeating a DEFINE group is not allowed - 56 inconsistent NEWLINE options" + 56 inconsistent NEWLINE options 57 \g is not followed by a braced name or an optionally braced non-zero number 58 (?+ or (?- or (?(+ or (?(- must be followed by a non-zero number + 59 (*VERB) with an argument is not supported + 60 (*VERB) not recognized + 61 number is too big + 62 subpattern name expected + 63 digit expected after (?+ + + The numbers 32 and 10000 in errors 48 and 49 are defaults; different + values may be used if the limits were changed when PCRE was built. STUDYING A PATTERN @@ -1532,21 +1605,22 @@ INFORMATION ABOUT A PATTERN 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. + variable. An explicit match is either a literal CR or LF character, or + \r or \n. PCRE_INFO_JCHANGED - Return 1 if the (?J) option setting is used in the pattern, otherwise - 0. The fourth argument should point to an int variable. The (?J) inter- - nal option setting changes the local PCRE_DUPNAMES option. + 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_LASTLITERAL - Return the value of the rightmost literal byte that must exist in any - matched string, other than at its start, if such a byte has been + Return the value of the rightmost literal byte that must exist in any + matched string, other than at its start, if such a byte has been recorded. The fourth argument should point to an int variable. If there - is no such byte, -1 is returned. For anchored patterns, a last literal - byte is recorded only if it follows something of variable length. For + is no such byte, -1 is returned. For anchored patterns, a last literal + byte is recorded only if it follows something of variable length. For example, for the pattern /^a\d+z\d+/ the returned value is "z", but for /^a\dz\d/ the returned value is -1. @@ -1554,34 +1628,34 @@ INFORMATION ABOUT A PATTERN 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 - a pointer to the first entry of the table (a pointer to char). The + of each entry; both of these return an int value. The entry size + depends on the length of the longest name. PCRE_INFO_NAMETABLE returns + a pointer to the first entry of the table (a pointer to char). The first two bytes of each entry are the number of the capturing parenthe- - sis, most significant byte first. The rest of the entry is the corre- - sponding name, zero terminated. The names are in alphabetical order. + sis, most significant byte first. The rest of the entry is the corre- + sponding name, zero terminated. The names are in alphabetical order. When PCRE_DUPNAMES is set, duplicate names are in order of their paren- - theses numbers. For example, consider the following pattern (assume - PCRE_EXTENDED is set, so white space - including newlines - is + theses numbers. For example, consider the following pattern (assume + PCRE_EXTENDED is set, so white space - including newlines - is ignored): (? (?(\d\d)?\d\d) - (?\d\d) - (?\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 ??: @@ -1590,29 +1664,29 @@ 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, otherwise 0. - The fourth argument should point to an int variable. The pcrepartial - documentation lists the restrictions that apply to patterns when par- + Return 1 if the pattern can be used for partial matching, otherwise 0. + The fourth argument should point to an int variable. The pcrepartial + documentation lists the restrictions that apply to patterns when par- tial matching is used. 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 @@ -1626,7 +1700,7 @@ INFORMATION ABOUT A PATTERN PCRE_INFO_SIZE - Return the size of the compiled pattern, that is, the value that was + Return the size of the compiled pattern, that is, the value that was passed as the argument to pcre_malloc() when PCRE was getting memory in which to place the compiled data. The fourth argument should point to a size_t variable. @@ -1634,9 +1708,9 @@ INFORMATION ABOUT A PATTERN PCRE_INFO_STUDYSIZE Return the size of the data block pointed to by the study_data field in - a pcre_extra block. That is, it is the value that was passed to + a pcre_extra block. That is, it is the value that was passed to pcre_malloc() when PCRE was getting memory into which to place the data - created by pcre_study(). The fourth argument should point to a size_t + created by pcre_study(). The fourth argument should point to a size_t variable. @@ -1644,21 +1718,21 @@ OBSOLETE INFO FUNCTION int pcre_info(const pcre *code, int *optptr, int *firstcharptr); - The pcre_info() function is now obsolete because its interface is too - restrictive to return all the available data about a compiled pattern. - New programs should use pcre_fullinfo() instead. The yield of - pcre_info() is the number of capturing subpatterns, or one of the fol- + The pcre_info() function is now obsolete because its interface is too + restrictive to return all the available data about a compiled pattern. + New programs should use pcre_fullinfo() instead. The yield of + pcre_info() is the number of capturing subpatterns, or one of the fol- lowing negative numbers: PCRE_ERROR_NULL the argument code was NULL PCRE_ERROR_BADMAGIC the "magic number" was not found - If the optptr argument is not NULL, a copy of the options with which - the pattern was compiled is placed in the integer it points to (see + If the optptr argument is not NULL, a copy of the options with which + the pattern was compiled is placed in the integer it points to (see PCRE_INFO_OPTIONS above). - If the pattern is not anchored and the firstcharptr argument is not - NULL, it is used to pass back information about the first character of + If the pattern is not anchored and the firstcharptr argument is not + NULL, it is used to pass back information about the first character of any matched string (see PCRE_INFO_FIRSTBYTE above). @@ -1666,21 +1740,21 @@ 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.) @@ -1690,18 +1764,18 @@ 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 + The function pcre_exec() is called to match a subject string against a + compiled pattern, which is passed in the code argument. If the pattern has been studied, the result of the study should be passed in the extra - argument. This function is the main matching facility of the library, + argument. This function is the main matching facility of the library, and it operates in a Perl-like manner. For specialist use there is also - an alternative matching function, which is described below in the sec- + an alternative matching function, which is described below in the sec- tion about the pcre_dfa_exec() function. - In most applications, the pattern will have been compiled (and option- - ally studied) in the same process that calls pcre_exec(). However, it + 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(): @@ -1720,10 +1794,10 @@ 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; @@ -1733,7 +1807,7 @@ MATCHING A PATTERN: THE TRADITIONAL FUNCTION void *callout_data; const unsigned char *tables; - The flags field is a bitmap that specifies which of the other fields + The flags field is a bitmap that specifies which of the other fields are set. The flag bits are: PCRE_EXTRA_STUDY_DATA @@ -1742,77 +1816,85 @@ MATCHING A PATTERN: THE TRADITIONAL FUNCTION PCRE_EXTRA_CALLOUT_DATA PCRE_EXTRA_TABLES - Other flag bits should be set to zero. The study_data field is set in - the pcre_extra block that is returned by pcre_study(), together with + Other flag bits should be set to zero. The study_data field is set in + the pcre_extra block that is returned by pcre_study(), together with the appropriate flag bit. You should not set this yourself, but you may - add to the block by setting the other fields and their corresponding + add to the block by setting the other fields and their corresponding flag bits. The match_limit field provides a means of preventing PCRE from using up - a vast amount of resources when running patterns that are not going to - match, but which have a very large number of possibilities in their - search trees. The classic example is the use of nested unlimited + a vast amount of resources when running patterns that are not going to + match, but which have a very large number of possibilities in their + search trees. The classic example is the use of nested unlimited repeats. - Internally, PCRE uses a function called match() which it calls repeat- - edly (sometimes recursively). The limit set by match_limit is imposed - on the number of times this function is called during a match, which - has the effect of limiting the amount of backtracking that can take + Internally, PCRE uses a function called match() which it calls repeat- + edly (sometimes recursively). The limit set by match_limit is imposed + on the number of times this function is called during a match, which + has the effect of limiting the amount of backtracking that can take place. For patterns that are not anchored, the count restarts from zero for each position in the subject string. - The default value for the limit can be set when PCRE is built; the - default default is 10 million, which handles all but the most extreme - cases. You can override the default by suppling pcre_exec() with a - pcre_extra block in which match_limit is set, and - PCRE_EXTRA_MATCH_LIMIT is set in the flags field. If the limit is + 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 stack that can be + Limiting the recursion depth limits the amount of stack that can be used, or, when PCRE has been compiled to use memory on the heap instead of the stack, the amount of heap memory that can be used. - The default value for match_limit_recursion can be set when PCRE is - built; the default default is the same value as the default for - match_limit. You can override the default by suppling pcre_exec() with - a pcre_extra block in which match_limit_recursion is set, and - PCRE_EXTRA_MATCH_LIMIT_RECURSION is set in the flags field. If the + The default value for match_limit_recursion can be set when PCRE is + built; the default default is the same value as the default for + match_limit. You can override the default by suppling pcre_exec() with + a pcre_extra block in which match_limit_recursion is set, and + PCRE_EXTRA_MATCH_LIMIT_RECURSION is set in the flags field. If the limit is exceeded, pcre_exec() returns PCRE_ERROR_RECURSIONLIMIT. - The pcre_callout field is used in conjunction with the "callout" fea- + The pcre_callout field is used in conjunction with the "callout" fea- ture, which is described in the pcrecallout documentation. - The tables field is used to pass a character tables pointer to - pcre_exec(); this overrides the value that is stored with the compiled - pattern. A non-NULL value is stored with the compiled pattern only if - custom tables were supplied to pcre_compile() via its tableptr argu- + 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. 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, + The unused bits of the options argument for pcre_exec() must be zero. + The only bits that may be set are PCRE_ANCHORED, PCRE_NEWLINE_xxx, PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, PCRE_NO_UTF8_CHECK and PCRE_PARTIAL. PCRE_ANCHORED - The PCRE_ANCHORED option limits pcre_exec() to matching at the first - matching position. If a pattern was compiled with PCRE_ANCHORED, or - turned out to be anchored by virtue of its contents, it cannot be made + The PCRE_ANCHORED option limits pcre_exec() to matching at the first + matching position. If a pattern was compiled with PCRE_ANCHORED, or + turned out to be anchored by virtue of its contents, it cannot be made unachored at matching time. + PCRE_BSR_ANYCRLF + PCRE_BSR_UNICODE + + These options (which are mutually exclusive) control what the \R escape + sequence matches. The choice is either to match only CR, LF, or CRLF, + or to match any Unicode newline sequence. These options override the + choice that was made or defaulted when the pattern was compiled. + PCRE_NEWLINE_CR PCRE_NEWLINE_LF PCRE_NEWLINE_CRLF @@ -1829,7 +1911,7 @@ MATCHING A PATTERN: THE TRADITIONAL FUNCTION 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 NL characters, the match position is + 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. @@ -1839,194 +1921,197 @@ MATCHING A PATTERN: THE TRADITIONAL FUNCTION 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. Note than an explicit CR or LF refer- - ence occurs for negated character classes such as [^X] because they can - match CR or LF characters. + acter after the first failure. + + An explicit match for CR of LF is either a literal appearance of one of + those characters, or one of the \r or \n escape sequences. Implicit + matches such as [^X] do not count, nor does \s (which includes CR and + LF in the characters that it matches). - Notwithstanding the above, anomalous effects may still occur when CRLF + 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 the - 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 the + empty string at the start of the subject. With PCRE_NOTEMPTY set, this match is not valid, so PCRE searches further into the string for occur- rences of "a" or "b". Perl has no direct equivalent of PCRE_NOTEMPTY, but it does make a spe- - cial case of a pattern match of the empty string within its split() - function, and when using the /g modifier. It is possible to emulate + cial case of a pattern match of the empty string within its split() + function, and when using the /g modifier. It is possible to emulate Perl's behaviour after matching a null string by first trying the match again at the same offset with PCRE_NOTEMPTY and PCRE_ANCHORED, and then - if that fails by advancing the starting offset (see below) and trying + if that fails by advancing the starting offset (see below) and trying an ordinary match again. There is some code that demonstrates how to do this in the pcredemo.c sample program. PCRE_NO_UTF8_CHECK When PCRE_UTF8 is set at compile time, the validity of the subject as a - UTF-8 string is automatically checked when pcre_exec() is subsequently - called. The value of startoffset is also checked to ensure that it - points to the start of a UTF-8 character. There is a discussion about - the validity of UTF-8 strings in the section on UTF-8 support in the - main pcre page. If an invalid UTF-8 sequence of bytes is found, - pcre_exec() returns the error PCRE_ERROR_BADUTF8. If startoffset con- + UTF-8 string is automatically checked when pcre_exec() is subsequently + called. The value of startoffset is also checked to ensure that it + points to the start of a UTF-8 character. There is a discussion about + the validity of UTF-8 strings in the section on UTF-8 support in the + main pcre page. If an invalid UTF-8 sequence of bytes is found, + pcre_exec() returns the error PCRE_ERROR_BADUTF8. If startoffset con- tains an invalid value, PCRE_ERROR_BADUTF8_OFFSET is returned. - If you already know that your subject is valid, and you want to skip - these checks for performance reasons, you can set the - PCRE_NO_UTF8_CHECK option when calling pcre_exec(). You might want to - do this for the second and subsequent calls to pcre_exec() if you are - making repeated calls to find all the matches in a single subject - string. However, you should be sure that the value of startoffset - points to the start of a UTF-8 character. When PCRE_NO_UTF8_CHECK is - set, the effect of passing an invalid UTF-8 string as a subject, or a - value of startoffset that does not point to the start of a UTF-8 char- + If you already know that your subject is valid, and you want to skip + these checks for performance reasons, you can set the + PCRE_NO_UTF8_CHECK option when calling pcre_exec(). You might want to + do this for the second and subsequent calls to pcre_exec() if you are + making repeated calls to find all the matches in a single subject + string. However, you should be sure that the value of startoffset + points to the start of a UTF-8 character. When PCRE_NO_UTF8_CHECK is + set, the effect of passing an invalid UTF-8 string as a subject, or a + value of startoffset that does not point to the start of a UTF-8 char- acter, is undefined. Your program may crash. PCRE_PARTIAL - This option turns on the partial matching feature. If the subject - string fails to match the pattern, but at some point during the match- - ing process the end of the subject was reached (that is, the subject - partially matches the pattern and the failure to match occurred only - because there were not enough subject characters), pcre_exec() returns - PCRE_ERROR_PARTIAL instead of PCRE_ERROR_NOMATCH. When PCRE_PARTIAL is - used, there are restrictions on what may appear in the pattern. These + This option turns on the partial matching feature. If the subject + string fails to match the pattern, but at some point during the match- + ing process the end of the subject was reached (that is, the subject + partially matches the pattern and the failure to match occurred only + because there were not enough subject characters), pcre_exec() returns + PCRE_ERROR_PARTIAL instead of PCRE_ERROR_NOMATCH. When PCRE_PARTIAL is + used, there are restrictions on what may appear in the pattern. These are discussed in the pcrepartial documentation. The string to be matched by pcre_exec() - The subject string is passed to pcre_exec() as a pointer in subject, a - length in length, and a starting byte offset in startoffset. In UTF-8 - mode, the byte offset must point to the start of a UTF-8 character. - Unlike the pattern string, the subject may contain binary zero bytes. - When the starting offset is zero, the search for a match starts at the + The subject string is passed to pcre_exec() as a pointer in subject, a + length in length, and a starting byte offset in startoffset. In UTF-8 + mode, the byte offset must point to the start of a UTF-8 character. + Unlike the pattern string, the subject may contain binary zero bytes. + When the starting offset is zero, the search for a match starts at the beginning of the subject, and this is by far the most common case. - A non-zero starting offset is useful when searching for another match - in the same subject by calling pcre_exec() again after a previous suc- - cess. Setting startoffset differs from just passing over a shortened - string and setting PCRE_NOTBOL in the case of a pattern that begins + 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. - 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 integer - offsets whose address is passed in ovector. The number of elements in - the vector is passed in ovecsize, which must be a non-negative number. + Captured substrings are returned to the caller via a vector of integer + offsets whose address is passed in ovector. The number of elements in + the vector is passed in ovecsize, which must be a non-negative number. Note: this argument is NOT the size of ovector in bytes. - The first two-thirds of the vector is used to pass back captured sub- - strings, each substring using a pair of integers. The remaining third - of the vector is used as workspace by pcre_exec() while matching cap- - turing subpatterns, and is not available for passing back information. - The length passed in ovecsize should always be a multiple of three. If + The first two-thirds of the vector is used to pass back captured sub- + strings, each substring using a pair of integers. The remaining third + of the vector is used as workspace by pcre_exec() while matching cap- + turing subpatterns, and is not available for passing back information. + The length passed in ovecsize should always be a multiple of three. If it is not, it is rounded down. - When a match is successful, information about captured substrings is - returned in pairs of integers, starting at the beginning of ovector, - and continuing up to two-thirds of its length at the most. The first + When a match is successful, information about captured substrings is + returned in pairs of integers, starting at the beginning of ovector, + and continuing up to two-thirds of its length at the most. The first element of a pair is set to the offset of the first character in a sub- - string, and the second is set to the offset of the first character - after the end of a substring. The first pair, ovector[0] and ovec- - tor[1], identify the portion of the subject string matched by the - entire pattern. The next pair is used for the first capturing subpat- + string, and the second is set to the offset of the first character + after the end of a substring. The first pair, ovector[0] and ovec- + tor[1], identify the portion of the subject string matched by the + entire pattern. The next pair is used for the first capturing subpat- tern, and so on. The value returned by pcre_exec() is one more than the highest numbered pair that has been set. For example, if two substrings - have been captured, the returned value is 3. If there are no capturing - subpatterns, the return value from a successful match is 1, indicating + 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. In particular, if the substring off- + function returns a value of zero. In particular, if the substring off- sets are not of interest, pcre_exec() may be called with ovector passed - as NULL and ovecsize as zero. However, if the pattern contains back - references and the ovector is not big enough to remember the related - substrings, PCRE has to get additional memory for use during matching. + as NULL and ovecsize as zero. However, if the pattern contains back + references and the ovector is not big enough to remember the related + substrings, PCRE has to get additional memory for use during matching. Thus it is usually advisable to supply an ovector. - The pcre_info() function can be used to find out how many capturing - subpatterns there are in a compiled pattern. The smallest size for - ovector that will allow for n captured substrings, in addition to the + The pcre_info() function can be used to find out how many capturing + subpatterns there are in a compiled pattern. The smallest size for + ovector that will allow for n captured substrings, in addition to the offsets of the substring matched by the whole pattern, is (n+1)*3. - It is possible for capturing subpattern number n+1 to match some part + 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 + Offset values that correspond to unused subpatterns at the end of the + expression are also set to -1. For example, if the string "abc" is + matched against the pattern (abc)(x(yz)?)? subpatterns 2 and 3 are not + matched. The return from the function is 2, because the highest used capturing subpattern number is 1. However, you can refer to the offsets - for the second and third capturing subpatterns if you wish (assuming + for the second and third capturing subpatterns if you wish (assuming the vector is large enough, of course). - Some convenience functions are provided for extracting the captured + 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) @@ -2035,7 +2120,7 @@ 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) @@ -2044,79 +2129,79 @@ 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. 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 + A string that contains an invalid UTF-8 byte sequence was passed as a subject. PCRE_ERROR_BADUTF8_OFFSET (-11) The UTF-8 byte sequence that was passed as a subject was valid, but the - value of startoffset did not point to the beginning of a UTF-8 charac- + value of startoffset did not point to the beginning of a UTF-8 charac- ter. PCRE_ERROR_PARTIAL (-12) - The subject string did not match, but it did match partially. See the + The subject string did not match, but it did match partially. See the pcrepartial documentation for details of partial matching. PCRE_ERROR_BADPARTIAL (-13) - The PCRE_PARTIAL option was used with a compiled pattern containing - items that are not supported for partial matching. See the pcrepartial + The PCRE_PARTIAL option was used with a compiled pattern containing + items that are not supported for partial matching. See the pcrepartial documentation for details of partial matching. PCRE_ERROR_INTERNAL (-14) - An unexpected internal error has occurred. This error could be caused + An unexpected internal error has occurred. This error could be caused by a bug in PCRE or by overwriting of the compiled pattern. PCRE_ERROR_BADCOUNT (-15) - This error is given if the value of the ovecsize argument is negative. + This error is given if the value of the ovecsize argument is negative. PCRE_ERROR_RECURSIONLIMIT (-21) The internal recursion limit, as specified by the match_limit_recursion - field in a pcre_extra structure (or defaulted) was reached. See the + field in a pcre_extra structure (or defaulted) was reached. See the description above. PCRE_ERROR_BADNEWLINE (-23) @@ -2139,78 +2224,78 @@ EXTRACTING CAPTURED SUBSTRINGS BY NUMBER int pcre_get_substring_list(const char *subject, int *ovector, int stringcount, const char ***listptr); - Captured substrings can be accessed directly by using the offsets - returned by pcre_exec() in ovector. For convenience, the functions + Captured substrings can be accessed directly by using the offsets + returned by pcre_exec() in ovector. For convenience, the functions pcre_copy_substring(), pcre_get_substring(), and pcre_get_sub- - string_list() are provided for extracting captured substrings as new, - separate, zero-terminated strings. These functions identify substrings - by number. The next section describes functions for extracting named + string_list() are provided for extracting captured substrings as new, + separate, zero-terminated strings. These functions identify substrings + by number. The next section describes functions for extracting named substrings. - A substring that contains a binary zero is correctly extracted and has - a further zero added on the end, but the result is not, of course, a C - string. However, you can process such a string by referring to the - length that is returned by pcre_copy_substring() and pcre_get_sub- + A substring that contains a binary zero is correctly extracted and has + a further zero added on the end, but the result is not, of course, a C + string. However, you can process such a string by referring to the + length that is returned by pcre_copy_substring() and pcre_get_sub- string(). Unfortunately, the interface to pcre_get_substring_list() is - not adequate for handling strings containing binary zeros, because the + not adequate for handling strings containing binary zeros, because the end of the final string is not independently indicated. - The first three arguments are the same for all three of these func- - tions: subject is the subject string that has just been successfully + The first three arguments are the same for all three of these func- + tions: subject is the subject string that has just been successfully matched, ovector is a pointer to the vector of integer offsets that was passed to pcre_exec(), and stringcount is the number of substrings that - were captured by the match, including the substring that matched the + were captured by the match, including the substring that matched the entire regular expression. This is the value returned by pcre_exec() if - it is greater than zero. If pcre_exec() returned zero, indicating that - it ran out of space in ovector, the value passed as stringcount should + it is greater than zero. If pcre_exec() returned zero, indicating that + it ran out of space in ovector, the value passed as stringcount should be the number of elements in the vector divided by three. - The functions pcre_copy_substring() and pcre_get_substring() extract a - single substring, whose number is given as stringnumber. A value of - zero extracts the substring that matched the entire pattern, whereas - higher values extract the captured substrings. For pcre_copy_sub- - string(), the string is placed in buffer, whose length is given by - buffersize, while for pcre_get_substring() a new block of memory is - obtained via pcre_malloc, and its address is returned via stringptr. - The yield of the function is the length of the string, not including + The functions pcre_copy_substring() and pcre_get_substring() extract a + single substring, whose number is given as stringnumber. A value of + zero extracts the substring that matched the entire pattern, whereas + higher values extract the captured substrings. For pcre_copy_sub- + string(), the string is placed in buffer, whose length is given by + buffersize, while for pcre_get_substring() a new block of memory is + obtained via pcre_malloc, and its address is returned via stringptr. + The yield of the function is the length of the string, not including the terminating zero, or one of these error codes: PCRE_ERROR_NOMEMORY (-6) - The buffer was too small for pcre_copy_substring(), or the attempt to + The buffer was too small for pcre_copy_substring(), or the attempt to get memory failed for pcre_get_substring(). PCRE_ERROR_NOSUBSTRING (-7) There is no substring whose number is stringnumber. - The pcre_get_substring_list() function extracts all available sub- - strings and builds a list of pointers to them. All this is done in a + The pcre_get_substring_list() function extracts all available sub- + strings and builds a list of pointers to them. All this is done in a single block of memory that is obtained via pcre_malloc. The address of - the memory block is returned via listptr, which is also the start of - the list of string pointers. The end of the list is marked by a NULL - pointer. The yield of the function is zero if all went well, or the + the memory block is returned via listptr, which is also the start of + the list of string pointers. The end of the list is marked by a NULL + pointer. The yield of the function is zero if all went well, or the error code PCRE_ERROR_NOMEMORY (-6) if the attempt to get the memory block failed. - When any of these functions encounter a substring that is unset, which - can happen when capturing subpattern number n+1 matches some part of - the subject, but subpattern n has not been used at all, they return an + When any of these functions encounter a substring that is unset, which + can happen when capturing subpattern number n+1 matches some part of + the subject, but subpattern n has not been used at all, they return an empty string. This can be distinguished from a genuine zero-length sub- - string by inspecting the appropriate offset in ovector, which is nega- + string by inspecting the appropriate offset in ovector, which is nega- tive for unset substrings. - The two convenience functions pcre_free_substring() and pcre_free_sub- - string_list() can be used to free the memory returned by a previous + The two convenience functions pcre_free_substring() and pcre_free_sub- + string_list() can be used to free the memory returned by a previous call of pcre_get_substring() or pcre_get_substring_list(), respec- - tively. They do nothing more than call the function pointed to by - pcre_free, which of course could be called directly from a C program. - However, PCRE is used in some situations where it is linked via a spe- - cial interface to another programming language that cannot use - pcre_free directly; it is for these cases that the functions are pro- + tively. They do nothing more than call the function pointed to by + pcre_free, which of course could be called directly from a C program. + However, PCRE is used in some situations where it is linked via a spe- + cial interface to another programming language that cannot use + pcre_free directly; it is for these cases that the functions are pro- vided. @@ -2229,7 +2314,7 @@ EXTRACTING CAPTURED SUBSTRINGS BY NAME int stringcount, const char *stringname, const char **stringptr); - To extract a substring by name, you first have to find associated num- + To extract a substring by name, you first have to find associated num- ber. For example, for this pattern (a+)b(?\d+)... @@ -2238,27 +2323,27 @@ EXTRACTING CAPTURED SUBSTRINGS BY NAME be unique (PCRE_DUPNAMES was not set), you can find the number from the name by calling pcre_get_stringnumber(). The first argument is the com- piled pattern, and the second is the name. The yield of the function is - the subpattern number, or PCRE_ERROR_NOSUBSTRING (-7) if there is no + the subpattern number, or PCRE_ERROR_NOSUBSTRING (-7) if there is no subpattern of that name. Given the number, you can extract the substring directly, or use one of the functions described in the previous section. For convenience, there are also two functions that do the whole job. - Most of the arguments of pcre_copy_named_substring() and - pcre_get_named_substring() are the same as those for the similarly - named functions that extract by number. As these are described in the - previous section, they are not re-described here. There are just two + Most of the arguments of pcre_copy_named_substring() and + pcre_get_named_substring() are the same as those for the similarly + named functions that extract by number. As these are described in the + previous section, they are not re-described here. There are just two differences: - First, instead of a substring number, a substring name is given. Sec- + First, instead of a substring number, a substring name is given. Sec- ond, there is an extra argument, given at the start, which is a pointer - to the compiled pattern. This is needed in order to gain access to the + to the compiled pattern. This is needed in order to gain access to the name-to-number translation table. - These functions call pcre_get_stringnumber(), and if it succeeds, they - then call pcre_copy_substring() or pcre_get_substring(), as appropri- - ate. NOTE: If PCRE_DUPNAMES is set and there are duplicate names, the + These functions call pcre_get_stringnumber(), and if it succeeds, they + then call pcre_copy_substring() or pcre_get_substring(), as appropri- + ate. NOTE: If PCRE_DUPNAMES is set and there are duplicate names, the behaviour may not be what you want (see the next section). @@ -2267,47 +2352,47 @@ DUPLICATE SUBPATTERN NAMES int pcre_get_stringtable_entries(const pcre *code, const char *name, char **first, char **last); - When a pattern is compiled with the PCRE_DUPNAMES option, names for - subpatterns are not required to be unique. Normally, patterns with - duplicate names are such that in any one match, only one of the named - subpatterns participates. An example is shown in the pcrepattern docu- + When a pattern is compiled with the PCRE_DUPNAMES option, names for + subpatterns are not required to be unique. Normally, patterns with + duplicate names are such that in any one match, only one of the named + subpatterns participates. An example is shown in the pcrepattern docu- mentation. - When duplicates are present, pcre_copy_named_substring() and - pcre_get_named_substring() return the first substring corresponding to - the given name that is set. If none are set, PCRE_ERROR_NOSUBSTRING - (-7) is returned; no data is returned. The pcre_get_stringnumber() - function returns one of the numbers that are associated with the name, + When duplicates are present, pcre_copy_named_substring() and + pcre_get_named_substring() return the first substring corresponding to + the given name that is set. If none are set, PCRE_ERROR_NOSUBSTRING + (-7) is returned; no data is returned. The pcre_get_stringnumber() + function returns one of the numbers that are associated with the name, but it is not defined which it is. - If you want to get full details of all captured substrings for a given - name, you must use the pcre_get_stringtable_entries() function. The + If you want to get full details of all captured substrings for a given + name, you must use the pcre_get_stringtable_entries() function. The first argument is the compiled pattern, and the second is the name. The - third and fourth are pointers to variables which are updated by the + third and fourth are pointers to variables which are updated by the function. After it has run, they point to the first and last entries in - the name-to-number table for the given name. The function itself - returns the length of each entry, or PCRE_ERROR_NOSUBSTRING (-7) if - there are none. The format of the table is described above in the sec- - tion entitled Information about a pattern. Given all the relevant - entries for the name, you can extract each of their numbers, and hence + the name-to-number table for the given name. The function itself + returns the length of each entry, or PCRE_ERROR_NOSUBSTRING (-7) if + there are none. The format of the table is described above in the sec- + tion entitled Information about a pattern. Given all the relevant + entries for the name, you can extract each of their numbers, and hence the captured data, if any. FINDING ALL POSSIBLE MATCHES - The traditional matching function uses a similar algorithm to Perl, + The traditional matching function uses a similar algorithm to Perl, which stops when it finds the first match, starting at a given point in - the subject. If you want to find all possible matches, or the longest - possible match, consider using the alternative matching function (see - below) instead. If you cannot use the alternative function, but still - need to find all possible matches, you can kludge it up by making use + the subject. If you want to find all possible matches, or the longest + possible match, consider using the alternative matching function (see + below) instead. If you cannot use the alternative function, but still + need to find all possible matches, you can kludge it up by making use of the callout facility, which is described in the pcrecallout documen- tation. What you have to do is to insert a callout right at the end of the pat- - tern. When your callout function is called, extract and save the cur- - rent matched substring. Then return 1, which forces pcre_exec() to - backtrack and try other alternatives. Ultimately, when it runs out of + tern. When your callout function is called, extract and save the cur- + rent matched substring. Then return 1, which forces pcre_exec() to + backtrack and try other alternatives. Ultimately, when it runs out of matches, pcre_exec() will yield PCRE_ERROR_NOMATCH. @@ -2318,25 +2403,25 @@ MATCHING A PATTERN: THE ALTERNATIVE FUNCTION int options, int *ovector, int ovecsize, int *workspace, int wscount); - The function pcre_dfa_exec() is called to match a subject string - against a compiled pattern, using a matching algorithm that scans the - subject string just once, and does not backtrack. This has different - characteristics to the normal algorithm, and is not compatible with - Perl. Some of the features of PCRE patterns are not supported. Never- - theless, there are times when this kind of matching can be useful. For + The function pcre_dfa_exec() is called to match a subject string + against a compiled pattern, using a matching algorithm that scans the + subject string just once, and does not backtrack. This has different + characteristics to the normal algorithm, and is not compatible with + Perl. Some of the features of PCRE patterns are not supported. Never- + theless, there are times when this kind of matching can be useful. For a discussion of the two matching algorithms, see the pcrematching docu- mentation. - The arguments for the pcre_dfa_exec() function are the same as for + The arguments for the pcre_dfa_exec() function are the same as for pcre_exec(), plus two extras. The ovector argument is used in a differ- - ent way, and this is described below. The other common arguments are - used in the same way as for pcre_exec(), so their description is not + ent way, and this is described below. The other common arguments are + used in the same way as for pcre_exec(), so their description is not repeated here. - The two additional arguments provide workspace for the function. The - workspace vector should contain at least 20 elements. It is used for + The two additional arguments provide workspace for the function. The + workspace vector should contain at least 20 elements. It is used for keeping track of multiple paths through the pattern tree. More - workspace will be needed for patterns and subjects where there are a + workspace will be needed for patterns and subjects where there are a lot of potential matches. Here is an example of a simple call to pcre_dfa_exec(): @@ -2358,47 +2443,47 @@ MATCHING A PATTERN: THE ALTERNATIVE FUNCTION Option bits for pcre_dfa_exec() - The unused bits of the options argument for pcre_dfa_exec() must be - zero. The only bits that may be set are PCRE_ANCHORED, PCRE_NEW- - LINE_xxx, PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, PCRE_NO_UTF8_CHECK, + The unused bits of the options argument for pcre_dfa_exec() must be + zero. The only bits that may be set are PCRE_ANCHORED, PCRE_NEW- + LINE_xxx, PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, PCRE_NO_UTF8_CHECK, PCRE_PARTIAL, PCRE_DFA_SHORTEST, and PCRE_DFA_RESTART. All but the last three of these are the same as for pcre_exec(), so their description is not repeated here. PCRE_PARTIAL - This has the same general effect as it does for pcre_exec(), but the - details are slightly different. When PCRE_PARTIAL is set for - pcre_dfa_exec(), the return code PCRE_ERROR_NOMATCH is converted into - PCRE_ERROR_PARTIAL if the end of the subject is reached, there have + This has the same general effect as it does for pcre_exec(), but the + details are slightly different. When PCRE_PARTIAL is set for + pcre_dfa_exec(), the return code PCRE_ERROR_NOMATCH is converted into + PCRE_ERROR_PARTIAL if the end of the subject is reached, there have been no complete matches, but there is still at least one matching pos- - sibility. The portion of the string that provided the partial match is + sibility. The portion of the string that provided the partial match is set as the first matching string. PCRE_DFA_SHORTEST - Setting the PCRE_DFA_SHORTEST option causes the matching algorithm to + Setting the PCRE_DFA_SHORTEST option causes the matching algorithm to stop as soon as it has found one match. Because of the way the alterna- - tive algorithm works, this is necessarily the shortest possible match + tive algorithm works, this is necessarily the shortest possible match at the first possible matching point in the subject string. PCRE_DFA_RESTART - When pcre_dfa_exec() is called with the PCRE_PARTIAL option, and - returns a partial match, it is possible to call it again, with addi- - tional subject characters, and have it continue with the same match. - The PCRE_DFA_RESTART option requests this action; when it is set, the - workspace and wscount options must reference the same vector as before - because data about the match so far is left in them after a partial - match. There is more discussion of this facility in the pcrepartial + When pcre_dfa_exec() is called with the PCRE_PARTIAL option, and + returns a partial match, it is possible to call it again, with addi- + tional subject characters, and have it continue with the same match. + The PCRE_DFA_RESTART option requests this action; when it is set, the + workspace and wscount options must reference the same vector as before + because data about the match so far is left in them after a partial + match. There is more discussion of this facility in the pcrepartial documentation. Successful returns from pcre_dfa_exec() - When pcre_dfa_exec() succeeds, it may have matched more than one sub- + When pcre_dfa_exec() succeeds, it may have matched more than one sub- string in the subject. Note, however, that all the matches from one run - of the function start at the same point in the subject. The shorter - matches are all initial substrings of the longer matches. For example, + of the function start at the same point in the subject. The shorter + matches are all initial substrings of the longer matches. For example, if the pattern <.*> @@ -2413,62 +2498,62 @@ MATCHING A PATTERN: THE ALTERNATIVE FUNCTION - On success, the yield of the function is a number greater than zero, - which is the number of matched substrings. The substrings themselves - are returned in ovector. Each string uses two elements; the first is - the offset to the start, and the second is the offset to the end. In - fact, all the strings have the same start offset. (Space could have - been saved by giving this only once, but it was decided to retain some - compatibility with the way pcre_exec() returns data, even though the + On success, the yield of the function is a number greater than zero, + which is the number of matched substrings. The substrings themselves + are returned in ovector. Each string uses two elements; the first is + the offset to the start, and the second is the offset to the end. In + fact, all the strings have the same start offset. (Space could have + been saved by giving this only once, but it was decided to retain some + compatibility with the way pcre_exec() returns data, even though the meaning of the strings is different.) The strings are returned in reverse order of length; that is, the long- - est matching string is given first. If there were too many matches to - fit into ovector, the yield of the function is zero, and the vector is + est matching string is given first. If there were too many matches to + fit into ovector, the yield of the function is zero, and the vector is filled with the longest matches. Error returns from pcre_dfa_exec() - The pcre_dfa_exec() function returns a negative number when it fails. - Many of the errors are the same as for pcre_exec(), and these are - described above. There are in addition the following errors that are + The pcre_dfa_exec() function returns a negative number when it fails. + Many of the errors are the same as for pcre_exec(), and these are + described above. There are in addition the following errors that are specific to pcre_dfa_exec(): PCRE_ERROR_DFA_UITEM (-16) - This return is given if pcre_dfa_exec() encounters an item in the pat- - tern that it does not support, for instance, the use of \C or a back + This return is given if pcre_dfa_exec() encounters an item in the pat- + tern that it does not support, for instance, the use of \C or a back reference. PCRE_ERROR_DFA_UCOND (-17) - This return is given if pcre_dfa_exec() encounters a condition item - that uses a back reference for the condition, or a test for recursion + This return is given if pcre_dfa_exec() encounters a condition item + that uses a back reference for the condition, or a test for recursion in a specific group. These are not supported. PCRE_ERROR_DFA_UMLIMIT (-18) - This return is given if pcre_dfa_exec() is called with an extra block + This return is given if pcre_dfa_exec() is called with an extra block that contains a setting of the match_limit field. This is not supported (it is meaningless). PCRE_ERROR_DFA_WSSIZE (-19) - This return is given if pcre_dfa_exec() runs out of space in the + This return is given if pcre_dfa_exec() runs out of space in the workspace vector. PCRE_ERROR_DFA_RECURSE (-20) - When a recursive subpattern is processed, the matching function calls - itself recursively, using private vectors for ovector and workspace. - This error is given if the output vector is not large enough. This + When a recursive subpattern is processed, the matching function calls + itself recursively, using private vectors for ovector and workspace. + This error is given if the output vector is not large enough. This should be extremely rare, as a vector of size 1000 is used. SEE ALSO - pcrebuild(3), pcrecallout(3), pcrecpp(3)(3), pcrematching(3), pcrepar- - tial(3), pcreposix(3), pcreprecompile(3), pcresample(3), pcrestack(3). + pcrebuild(3), pcrecallout(3), pcrecpp(3)(3), pcrematching(3), pcrepar- + tial(3), pcreposix(3), pcreprecompile(3), pcresample(3), pcrestack(3). AUTHOR @@ -2480,7 +2565,7 @@ AUTHOR REVISION - Last updated: 21 August 2007 + Last updated: 26 December 2007 Copyright (c) 1997-2007 University of Cambridge. ------------------------------------------------------------------------------ @@ -2765,16 +2850,23 @@ DIFFERENCES BETWEEN PCRE AND PERL (f) The PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, and PCRE_NO_AUTO_CAP- TURE options for pcre_exec() have no Perl equivalents. - (g) The callout facility is PCRE-specific. + (g) The \R escape sequence can be restricted to match only CR, LF, or + CRLF by the PCRE_BSR_ANYCRLF option. - (h) The partial matching facility is PCRE-specific. + (h) The callout facility is PCRE-specific. - (i) Patterns compiled by PCRE can be saved and re-used at a later time, + (i) The partial matching facility is PCRE-specific. + + (j) Patterns compiled by PCRE can be saved and re-used at a later time, even on different hosts that have the other endianness. - (j) The alternative matching function (pcre_dfa_exec()) matches in a + (k) The alternative matching function (pcre_dfa_exec()) matches in a different way and is not Perl-compatible. + (l) PCRE recognizes some special sequences such as (*CR) at the start + of a pattern that set overall options that cannot be changed within the + pattern. + AUTHOR @@ -2785,7 +2877,7 @@ AUTHOR REVISION - Last updated: 08 August 2007 + Last updated: 11 September 2007 Copyright (c) 1997-2007 University of Cambridge. ------------------------------------------------------------------------------ @@ -2853,36 +2945,43 @@ NEWLINE CONVENTIONS changes the convention to CR. That pattern matches "a\nb" because LF is no longer a newline. Note that these special settings, which are not Perl-compatible, are recognized only at the very start of a pattern, - and that they must be in upper case. + and that they must be in upper case. If more than one of them is + present, the last one is used. + + The newline convention 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 set- + ting 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 UTF-8 mode, PCRE always understands - the concept of case for characters whose values are less than 128, so - caseless matching is always possible. For characters with higher val- - ues, the concept of case is supported if PCRE is compiled with Unicode - property support, but not otherwise. If you want to use caseless - matching for characters 128 and above, you must ensure that PCRE is + caseless matching is specified (the PCRE_CASELESS option), letters are + matched independently of case. In UTF-8 mode, PCRE always understands + the concept of case for characters whose values are less than 128, so + caseless matching is always possible. For characters with higher val- + ues, the concept of case is supported if PCRE is compiled with Unicode + property support, but not otherwise. If you want to use caseless + matching for characters 128 and above, you must ensure that PCRE is compiled with Unicode property support as well as with UTF-8 support. - The power of regular expressions comes from the ability to include - alternatives and repetitions in the pattern. These are encoded in the + 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 @@ -2901,7 +3000,7 @@ 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 @@ -2911,33 +3010,33 @@ CHARACTERS AND METACHARACTERS syntax) ] terminates the character class - The following sections describe the use of each of the metacharacters. + The following sections describe the use of each of the metacharacters. BACKSLASH The backslash character has several uses. Firstly, if it is followed by - a non-alphanumeric character, it takes away any special meaning that - character may have. This use of backslash as an escape character + a non-alphanumeric character, it takes away any special meaning that + character may have. This use of backslash as an escape character applies both inside and outside character classes. - For example, if you want to match a * character, you write \* in the - pattern. This escaping action applies whether or not the following - character would otherwise be interpreted as a metacharacter, so it is - always safe to precede a non-alphanumeric with backslash to specify - that it stands for itself. In particular, if you want to match a back- + For example, if you want to match a * character, you write \* in the + pattern. This escaping action applies whether or not the following + character would otherwise be interpreted as a metacharacter, so it is + always safe to precede a non-alphanumeric with backslash to specify + that it stands for itself. In particular, if you want to match a back- slash, you write \\. - If a pattern is compiled with the PCRE_EXTENDED option, whitespace in - the pattern (other than in a character class) and characters between a + If a pattern is compiled with the PCRE_EXTENDED option, whitespace in + the pattern (other than in a character class) and characters between a # outside a character class and the next newline are ignored. An escap- - ing backslash can be used to include a whitespace or # character as + ing backslash can be used to include a whitespace or # character as part of the pattern. - If you want to remove the special meaning from a sequence of charac- - ters, you can do so by putting them between \Q and \E. This is differ- - ent from Perl in that $ and @ are handled as literals in \Q...\E - sequences in PCRE, whereas in Perl, $ and @ cause variable interpola- + 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 @@ -2947,16 +3046,16 @@ 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 + The \Q...\E sequence is recognized both inside and outside character classes. Non-printing characters A second use of backslash provides a way of encoding non-printing char- - acters in patterns in a visible manner. There is no restriction on the - appearance of non-printing characters, apart from the binary zero that - terminates a pattern, but when a pattern is being prepared by text - editing, it is usually easier to use one of the following escape + acters in patterns in a visible manner. There is no restriction on the + appearance of non-printing characters, apart from the binary zero that + terminates a pattern, but when a pattern is being prepared by text + editing, it is usually easier to use one of the following escape sequences than the binary character it represents: \a alarm, that is, the BEL character (hex 07) @@ -2970,48 +3069,48 @@ BACKSLASH \xhh character with hex code hh \x{hhh..} character with hex code hhh.. - The precise effect of \cx is as follows: if x is a lower case letter, - it is converted to upper case. Then bit 6 of the character (hex 40) is - inverted. Thus \cz becomes hex 1A, but \c{ becomes hex 3B, while \c; + The precise effect of \cx is as follows: if x is a lower case letter, + it is converted to upper case. Then bit 6 of the character (hex 40) is + inverted. Thus \cz becomes hex 1A, but \c{ becomes hex 3B, while \c; becomes hex 7B. - After \x, from zero to two hexadecimal digits are read (letters can be - in upper or lower case). Any number of hexadecimal digits may appear - between \x{ and }, but the value of the character code must be less + After \x, from zero to two hexadecimal digits are read (letters can be + in upper or lower case). Any number of hexadecimal digits may appear + between \x{ and }, but the value of the character code must be less than 256 in non-UTF-8 mode, and less than 2**31 in UTF-8 mode. That is, - the maximum value in hexadecimal is 7FFFFFFF. Note that this is bigger + the maximum value in hexadecimal is 7FFFFFFF. Note that this is bigger than the largest Unicode code point, which is 10FFFF. - 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. Characters whose value is less than 256 can be defined by either of the - two syntaxes for \x. There is no difference in the way they are han- + two syntaxes for \x. There is no difference in the way they are han- dled. For example, \xdc is exactly the same as \x{dc}. - After \0 up to two further octal digits are read. If there are fewer - than two digits, just those that are present are used. Thus the + 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. In - non-UTF-8 mode, the value of a character specified in octal must be - less than \400. In UTF-8 mode, values up to \777 are permitted. For + erate a data character. Any subsequent digits stand for themselves. In + non-UTF-8 mode, the value of a character specified in octal must be + less than \400. In UTF-8 mode, values up to \777 are permitted. For example: \040 is another way of writing a space @@ -3029,20 +3128,20 @@ 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 - class, the sequence \b is interpreted as the backspace character (hex - 08), and the sequences \R and \X are interpreted as the characters "R" - and "X", respectively. Outside a character class, these sequences have + inside and outside character classes. In addition, inside a character + class, the sequence \b is interpreted as the backspace character (hex + 08), and the sequences \R and \X are interpreted as the characters "R" + and "X", respectively. Outside a character class, these sequences have different meanings (see below). 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. @@ -3063,28 +3162,28 @@ BACKSLASH \W any "non-word" character Each pair of escape sequences partitions the complete set of characters - into two disjoint sets. Any given character matches one, and only one, + into two disjoint sets. Any given character matches one, and only one, of each pair. These character type sequences can appear both inside and outside char- - acter classes. They each match one character of the appropriate type. - If the current matching point is at the end of the subject string, all + acter classes. They each match one character of the appropriate type. + If the current matching point is at the end of the subject string, all of them fail, since there is no character to match. - For compatibility with Perl, \s does not match the VT character (code - 11). This makes it different from the the POSIX "space" class. The \s - characters are HT (9), LF (10), FF (12), CR (13), and space (32). If + 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. - In UTF-8 mode, characters with values greater than 128 never match \d, + In UTF-8 mode, characters with values greater than 128 never match \d, \s, or \w, and always match \D, \S, and \W. This is true even when Uni- - code character property support is available. These sequences retain + code character property support is available. These sequences retain their original meanings from before UTF-8 support was available, mainly for efficiency reasons. The sequences \h, \H, \v, and \V are Perl 5.10 features. In contrast to - the other sequences, these do match certain high-valued codepoints in + the other sequences, these do match certain high-valued codepoints in UTF-8 mode. The horizontal space characters are: U+0009 Horizontal tab @@ -3118,34 +3217,56 @@ BACKSLASH U+2029 Paragraph separator A "word" character is an underscore or any character less than 256 that - is a letter or digit. The definition of letters and digits is con- - trolled by PCRE's low-valued character tables, and may vary if locale- - specific matching is taking place (see "Locale support" in the pcreapi - page). For example, in 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 matched by \w. The use of + is a letter or digit. The definition of letters and digits is con- + trolled by PCRE's low-valued character tables, and may vary if locale- + specific matching is taking place (see "Locale support" in the pcreapi + page). For example, in 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 matched by \w. The use of locales with Unicode is discouraged. Newline sequences - Outside a character class, the escape sequence \R matches any Unicode - newline sequence. This is a Perl 5.10 feature. In non-UTF-8 mode \R is - equivalent to the following: + Outside a character class, by default, the escape sequence \R matches + any Unicode newline sequence. This is a Perl 5.10 feature. In 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, + CR followed by LF, or one of the single characters LF (linefeed, U+000A), VT (vertical tab, U+000B), FF (formfeed, U+000C), CR (carriage return, U+000D), or NEL (next line, U+0085). The two-character sequence is treated as a single unit that cannot be split. - In UTF-8 mode, two additional characters whose codepoints are greater + In UTF-8 mode, 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 + PCRE_BSR_ANYCRLF either at compile time or when the pattern is matched. + (BSR is an abbrevation for "backslash R".) This can be made the default + when PCRE is built; if this is the case, the other behaviour can be + requested via the PCRE_BSR_UNICODE option. It is also possible to + specify these settings by starting a pattern string with one of the + following sequences: + + (*BSR_ANYCRLF) CR, LF, or CRLF only + (*BSR_UNICODE) any Unicode newline sequence + + These override the default and the options given to pcre_compile(), but + they can be overridden by options given to pcre_exec(). 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) + Inside a character class, \R matches the letter "R". Unicode character properties @@ -3601,9 +3722,9 @@ VERTICAL BAR INTERNAL OPTION SETTING The settings of the PCRE_CASELESS, PCRE_MULTILINE, PCRE_DOTALL, and - PCRE_EXTENDED options can be changed from within the pattern by a - sequence of Perl option letters enclosed between "(?" and ")". The - option letters are + PCRE_EXTENDED options (which are Perl-compatible) can be changed from + within the pattern by a sequence of Perl option letters enclosed + between "(?" and ")". The option letters are i for PCRE_CASELESS m for PCRE_MULTILINE @@ -3617,6 +3738,10 @@ INTERNAL OPTION SETTING is also permitted. If a letter appears both before and after the hyphen, the option is unset. + The PCRE-specific options PCRE_DUPNAMES, PCRE_UNGREEDY, and PCRE_EXTRA + can be changed in the same way as the Perl-compatible options by using + the characters J, U and X respectively. + When an option change occurs at top level (that is, not inside subpat- tern parentheses), the change applies to the remainder of the pattern that follows. If the change is placed right at the start of a pattern, @@ -3642,9 +3767,11 @@ INTERNAL OPTION SETTING the effects of option settings happen at compile time. There would be some very weird behaviour otherwise. - The PCRE-specific options PCRE_DUPNAMES, PCRE_UNGREEDY, and PCRE_EXTRA - can be changed in the same way as the Perl-compatible options by using - the characters J, U and X respectively. + Note: There are other PCRE-specific options that can be set by the + application when the compile or match functions are called. In some + cases the pattern can contain special leading sequences to override + what the application has set or what has been defaulted. Details are + given in the section entitled "Newline sequences" above. SUBPATTERNS @@ -4644,7 +4771,7 @@ CALLOUTS is given in the pcrecallout documentation. -BACTRACKING CONTROL +BACKTRACKING CONTROL Perl 5.10 introduced a number of "Special Backtracking Control Verbs", which are described in the Perl documentation as "experimental and sub- @@ -4775,7 +4902,7 @@ AUTHOR REVISION - Last updated: 21 August 2007 + Last updated: 17 September 2007 Copyright (c) 1997-2007 University of Cambridge. ------------------------------------------------------------------------------ @@ -4904,7 +5031,7 @@ CHARACTER CLASSES [^...] negative character class [x-y] range (can be used for hex characters) [[:xxx:]] positive POSIX named set - [[^:xxx:]] negative POSIX named set + [[:^xxx:]] negative POSIX named set alnum alphanumeric alpha alphabetic @@ -5074,7 +5201,8 @@ BACKTRACKING CONTROL NEWLINE CONVENTIONS - These are recognized only at the very start of a pattern. + These are recognized only at the very start of the pattern or after a + (*BSR_...) option. (*CR) (*LF) @@ -5083,6 +5211,15 @@ NEWLINE CONVENTIONS (*ANY) +WHAT \R MATCHES + + These are recognized only at the very start of the pattern or after a + (*...) option that sets the newline convention. + + (*BSR_ANYCRLF) + (*BSR_UNICODE) + + CALLOUTS (?C) callout @@ -5103,7 +5240,7 @@ AUTHOR REVISION - Last updated: 21 August 2007 + Last updated: 14 November 2007 Copyright (c) 1997-2007 University of Cambridge. ------------------------------------------------------------------------------ @@ -5907,7 +6044,8 @@ MATCHING INTERFACE c. The "i"th argument has a suitable type for holding the string captured as the "i"th sub-pattern. If you pass in - NULL for the "i"th argument, or pass fewer arguments than + void * NULL for the "i"th argument, or a non-void * NULL + of the correct type, or pass fewer arguments than the number of sub-patterns, "i"th captured sub-pattern is ignored. @@ -6155,7 +6293,7 @@ AUTHOR REVISION - Last updated: 06 March 2007 + Last updated: 12 November 2007 ------------------------------------------------------------------------------ diff --git a/ext/pcre/pcrelib/pcre.h b/ext/pcre/pcrelib/pcre.h index a002bbd5aa..a3cc3c7ef2 100644 --- a/ext/pcre/pcrelib/pcre.h +++ b/ext/pcre/pcrelib/pcre.h @@ -42,9 +42,9 @@ POSSIBILITY OF SUCH DAMAGE. /* The current PCRE version information. */ #define PCRE_MAJOR 7 -#define PCRE_MINOR 3 +#define PCRE_MINOR 5 #define PCRE_PRERELEASE -#define PCRE_DATE 2007-08-28 +#define PCRE_DATE 2008-01-10 /* When an application links to a PCRE DLL in Windows, the symbols that are imported have to be identified as such. When building PCRE, the appropriate @@ -122,6 +122,8 @@ extern "C" { #define PCRE_NEWLINE_CRLF 0x00300000 #define PCRE_NEWLINE_ANY 0x00400000 #define PCRE_NEWLINE_ANYCRLF 0x00500000 +#define PCRE_BSR_ANYCRLF 0x00800000 +#define PCRE_BSR_UNICODE 0x01000000 /* Exec-time and get/set-time error codes */ @@ -147,7 +149,7 @@ extern "C" { #define PCRE_ERROR_DFA_WSSIZE (-19) #define PCRE_ERROR_DFA_RECURSE (-20) #define PCRE_ERROR_RECURSIONLIMIT (-21) -#define PCRE_ERROR_NOTUSED (-22) +#define PCRE_ERROR_NULLWSLIMIT (-22) /* No longer actually used */ #define PCRE_ERROR_BADNEWLINE (-23) /* Request types for pcre_fullinfo() */ @@ -180,6 +182,7 @@ compatible. */ #define PCRE_CONFIG_STACKRECURSE 5 #define PCRE_CONFIG_UNICODE_PROPERTIES 6 #define PCRE_CONFIG_MATCH_LIMIT_RECURSION 7 +#define PCRE_CONFIG_BSR 8 /* Bit flags for the pcre_extra structure. Do not re-arrange or redefine these bits, just add new ones on the end, in order to remain compatible. */ diff --git a/ext/pcre/pcrelib/pcre_chartables.c b/ext/pcre/pcrelib/pcre_chartables.c index bec2d0c046..f1dbaaedf2 100644 --- a/ext/pcre/pcrelib/pcre_chartables.c +++ b/ext/pcre/pcrelib/pcre_chartables.c @@ -20,7 +20,7 @@ and dead code stripping is activated. This leads to link errors. Pulling in the header ensures that the array gets flagged as "someone outside this compilation unit might reference this" and so it will always be supplied to the linker. */ -#include +#include "config.h" #include "pcre_internal.h" diff --git a/ext/pcre/pcrelib/pcre_compile.c b/ext/pcre/pcrelib/pcre_compile.c index 77ec51cace..ef33cfc388 100644 --- a/ext/pcre/pcrelib/pcre_compile.c +++ b/ext/pcre/pcrelib/pcre_compile.c @@ -42,7 +42,7 @@ POSSIBILITY OF SUCH DAMAGE. supporting internal functions that are not used by other modules. */ -#include +#include "config.h" #define NLBLOCK cd /* Block containing newline information */ #define PSSTART start_pattern /* Field containing processed string start */ @@ -138,35 +138,47 @@ static const short int escapes[] = { #endif -/* Table of special "verbs" like (*PRUNE) */ +/* Table of special "verbs" like (*PRUNE). This is a short table, so it is +searched linearly. Put all the names into a single string, in order to reduce +the number of relocations when a shared library is dynamically linked. */ typedef struct verbitem { - const char *name; int len; int op; } verbitem; +static const char verbnames[] = + "ACCEPT\0" + "COMMIT\0" + "F\0" + "FAIL\0" + "PRUNE\0" + "SKIP\0" + "THEN"; + static verbitem verbs[] = { - { "ACCEPT", 6, OP_ACCEPT }, - { "COMMIT", 6, OP_COMMIT }, - { "F", 1, OP_FAIL }, - { "FAIL", 4, OP_FAIL }, - { "PRUNE", 5, OP_PRUNE }, - { "SKIP", 4, OP_SKIP }, - { "THEN", 4, OP_THEN } + { 6, OP_ACCEPT }, + { 6, OP_COMMIT }, + { 1, OP_FAIL }, + { 4, OP_FAIL }, + { 5, OP_PRUNE }, + { 4, OP_SKIP }, + { 4, OP_THEN } }; static int verbcount = sizeof(verbs)/sizeof(verbitem); -/* Tables of names of POSIX character classes and their lengths. The list is -terminated by a zero length entry. The first three must be alpha, lower, upper, -as this is assumed for handling case independence. */ +/* Tables of names of POSIX character classes and their lengths. The names are +now all in a single string, to reduce the number of relocations when a shared +library is dynamically loaded. The list of lengths is terminated by a zero +length entry. The first three must be alpha, lower, upper, as this is assumed +for handling case independence. */ -static const char *const posix_names[] = { - "alpha", "lower", "upper", - "alnum", "ascii", "blank", "cntrl", "digit", "graph", - "print", "punct", "space", "word", "xdigit" }; +static const char posix_names[] = + "alpha\0" "lower\0" "upper\0" "alnum\0" "ascii\0" "blank\0" + "cntrl\0" "digit\0" "graph\0" "print\0" "punct\0" "space\0" + "word\0" "xdigit"; static const uschar posix_name_lengths[] = { 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 4, 6, 0 }; @@ -205,84 +217,90 @@ static const int posix_class_maps[] = { /* The texts of compile-time error messages. These are "char *" because they are passed to the outside world. Do not ever re-use any error number, because they are documented. Always add a new error instead. Messages marked DEAD below -are no longer used. */ - -static const char *error_texts[] = { - "no error", - "\\ at end of pattern", - "\\c at end of pattern", - "unrecognized character follows \\", - "numbers out of order in {} quantifier", +are no longer used. This used to be a table of strings, but in order to reduce +the number of relocations needed when a shared library is loaded dynamically, +it is now one long string. We cannot use a table of offsets, because the +lengths of inserts such as XSTRING(MAX_NAME_SIZE) are not known. Instead, we +simply count through to the one we want - this isn't a performance issue +because these strings are used only when there is a compilation error. */ + +static const char error_texts[] = + "no error\0" + "\\ at end of pattern\0" + "\\c at end of pattern\0" + "unrecognized character follows \\\0" + "numbers out of order in {} quantifier\0" /* 5 */ - "number too big in {} quantifier", - "missing terminating ] for character class", - "invalid escape sequence in character class", - "range out of order in character class", - "nothing to repeat", + "number too big in {} quantifier\0" + "missing terminating ] for character class\0" + "invalid escape sequence in character class\0" + "range out of order in character class\0" + "nothing to repeat\0" /* 10 */ - "operand of unlimited repeat could match the empty string", /** DEAD **/ - "internal error: unexpected repeat", - "unrecognized character after (?", - "POSIX named classes are supported only within a class", - "missing )", + "operand of unlimited repeat could match the empty string\0" /** DEAD **/ + "internal error: unexpected repeat\0" + "unrecognized character after (? or (?-\0" + "POSIX named classes are supported only within a class\0" + "missing )\0" /* 15 */ - "reference to non-existent subpattern", - "erroffset passed as NULL", - "unknown option bit(s) set", - "missing ) after comment", - "parentheses nested too deeply", /** DEAD **/ + "reference to non-existent subpattern\0" + "erroffset passed as NULL\0" + "unknown option bit(s) set\0" + "missing ) after comment\0" + "parentheses nested too deeply\0" /** DEAD **/ /* 20 */ - "regular expression is too large", - "failed to get memory", - "unmatched parentheses", - "internal error: code overflow", - "unrecognized character after (?<", + "regular expression is too large\0" + "failed to get memory\0" + "unmatched parentheses\0" + "internal error: code overflow\0" + "unrecognized character after (?<\0" /* 25 */ - "lookbehind assertion is not fixed length", - "malformed number or name after (?(", - "conditional group contains more than two branches", - "assertion expected after (?(", - "(?R or (?[+-]digits must be followed by )", + "lookbehind assertion is not fixed length\0" + "malformed number or name after (?(\0" + "conditional group contains more than two branches\0" + "assertion expected after (?(\0" + "(?R or (?[+-]digits must be followed by )\0" /* 30 */ - "unknown POSIX class name", - "POSIX collating elements are not supported", - "this version of PCRE is not compiled with PCRE_UTF8 support", - "spare error", /** DEAD **/ - "character value in \\x{...} sequence is too large", + "unknown POSIX class name\0" + "POSIX collating elements are not supported\0" + "this version of PCRE is not compiled with PCRE_UTF8 support\0" + "spare error\0" /** DEAD **/ + "character value in \\x{...} sequence is too large\0" /* 35 */ - "invalid condition (?(0)", - "\\C not allowed in lookbehind assertion", - "PCRE does not support \\L, \\l, \\N, \\U, or \\u", - "number after (?C is > 255", - "closing ) for (?C expected", + "invalid condition (?(0)\0" + "\\C not allowed in lookbehind assertion\0" + "PCRE does not support \\L, \\l, \\N, \\U, or \\u\0" + "number after (?C is > 255\0" + "closing ) for (?C expected\0" /* 40 */ - "recursive call could loop indefinitely", - "unrecognized character after (?P", - "syntax error in subpattern name (missing terminator)", - "two named subpatterns have the same name", - "invalid UTF-8 string", + "recursive call could loop indefinitely\0" + "unrecognized character after (?P\0" + "syntax error in subpattern name (missing terminator)\0" + "two named subpatterns have the same name\0" + "invalid UTF-8 string\0" /* 45 */ - "support for \\P, \\p, and \\X has not been compiled", - "malformed \\P or \\p sequence", - "unknown property name after \\P or \\p", - "subpattern name is too long (maximum " XSTRING(MAX_NAME_SIZE) " characters)", - "too many named subpatterns (maximum " XSTRING(MAX_NAME_COUNT) ")", + "support for \\P, \\p, and \\X has not been compiled\0" + "malformed \\P or \\p sequence\0" + "unknown property name after \\P or \\p\0" + "subpattern name is too long (maximum " XSTRING(MAX_NAME_SIZE) " characters)\0" + "too many named subpatterns (maximum " XSTRING(MAX_NAME_COUNT) ")\0" /* 50 */ - "repeated subpattern is too long", /** DEAD **/ - "octal value is greater than \\377 (not in UTF-8 mode)", - "internal error: overran compiling workspace", - "internal error: previously-checked referenced subpattern not found", - "DEFINE group contains more than one branch", + "repeated subpattern is too long\0" /** DEAD **/ + "octal value is greater than \\377 (not in UTF-8 mode)\0" + "internal error: overran compiling workspace\0" + "internal error: previously-checked referenced subpattern not found\0" + "DEFINE group contains more than one branch\0" /* 55 */ - "repeating a DEFINE group is not allowed", - "inconsistent NEWLINE options", - "\\g is not followed by a braced name or an optionally braced non-zero number", - "(?+ or (?- or (?(+ or (?(- must be followed by a non-zero number", - "(*VERB) with an argument is not supported", + "repeating a DEFINE group is not allowed\0" + "inconsistent NEWLINE options\0" + "\\g is not followed by a braced name or an optionally braced non-zero number\0" + "(?+ or (?- or (?(+ or (?(- must be followed by a non-zero number\0" + "(*VERB) with an argument is not supported\0" /* 60 */ - "(*VERB) not recognized", - "number is too big" -}; + "(*VERB) not recognized\0" + "number is too big\0" + "subpattern name expected\0" + "digit expected after (?+"; /* Table to identify digits and hex digits. This is used when compiling @@ -417,6 +435,28 @@ static BOOL +/************************************************* +* Find an error text * +*************************************************/ + +/* The error texts are now all in one long string, to save on relocations. As +some of the text is of unknown length, we can't use a table of offsets. +Instead, just count through the strings. This is not a performance issue +because it happens only when there has been a compilation error. + +Argument: the error number +Returns: pointer to the error string +*/ + +static const char * +find_error_text(int n) +{ +const char *s = error_texts; +for (; n > 0; n--) while (*s++ != 0); +return s; +} + + /************************************************* * Handle escapes * *************************************************/ @@ -456,16 +496,16 @@ ptr--; /* Set pointer back to the last byte */ if (c == 0) *errorcodeptr = ERR1; -/* Non-alphamerics are literals. For digits or letters, do an initial lookup in -a table. A non-zero result is something that can be returned immediately. +/* Non-alphanumerics are literals. For digits or letters, do an initial lookup +in a table. A non-zero result is something that can be returned immediately. Otherwise further processing may be required. */ #ifndef EBCDIC /* ASCII coding */ -else if (c < '0' || c > 'z') {} /* Not alphameric */ +else if (c < '0' || c > 'z') {} /* Not alphanumeric */ else if ((i = escapes[c - '0']) != 0) c = i; #else /* EBCDIC coding */ -else if (c < 'a' || (ebcdic_chartab[c] & 0x0E) == 0) {} /* Not alphameric */ +else if (c < 'a' || (ebcdic_chartab[c] & 0x0E) == 0) {} /* Not alphanumeric */ else if ((i = escapes[c - 0x48]) != 0) c = i; #endif @@ -682,10 +722,10 @@ else break; /* PCRE_EXTRA enables extensions to Perl in the matter of escapes. Any - other alphameric following \ is an error if PCRE_EXTRA was set; otherwise, - for Perl compatibility, it is a literal. This code looks a bit odd, but - there used to be some cases other than the default, and there may be again - in future, so I haven't "optimized" it. */ + other alphanumeric following \ is an error if PCRE_EXTRA was set; + otherwise, for Perl compatibility, it is a literal. This code looks a bit + odd, but there used to be some cases other than the default, and there may + be again in future, so I haven't "optimized" it. */ default: if ((options & PCRE_EXTRA) != 0) switch(c) @@ -774,7 +814,7 @@ top = _pcre_utt_size; while (bot < top) { i = (bot + top) >> 1; - c = strcmp(name, _pcre_utt[i].name); + c = strcmp(name, _pcre_utt_names + _pcre_utt[i].name_offset); if (c == 0) { *dptr = _pcre_utt[i].value; @@ -1466,8 +1506,9 @@ for (;;) can match the empty string or not. It is called from could_be_empty() below and from compile_branch() when checking for an unlimited repeat of a group that can match nothing. Note that first_significant_code() skips over -assertions. If we hit an unclosed bracket, we return "empty" - this means we've -struck an inner bracket whose current branch will already have been scanned. +backward and negative forward assertions when its final argument is TRUE. If we +hit an unclosed bracket, we return "empty" - this means we've struck an inner +bracket whose current branch will already have been scanned. Arguments: code points to start of search @@ -1489,6 +1530,16 @@ for (code = first_significant_code(code + _pcre_OP_lengths[*code], NULL, 0, TRUE c = *code; + /* Skip over forward assertions; the other assertions are skipped by + first_significant_code() with a TRUE final argument. */ + + if (c == OP_ASSERT) + { + do code += GET(code, 1); while (*code == OP_ALT); + c = *code; + continue; + } + /* Groups with zero repeats can of course be empty; skip them. */ if (c == OP_BRAZERO || c == OP_BRAMINZERO) @@ -1684,29 +1735,48 @@ return TRUE; *************************************************/ /* This function is called when the sequence "[:" or "[." or "[=" is -encountered in a character class. It checks whether this is followed by an -optional ^ and then a sequence of letters, terminated by a matching ":]" or -".]" or "=]". +encountered in a character class. It checks whether this is followed by a +sequence of characters terminated by a matching ":]" or ".]" or "=]". If we +reach an unescaped ']' without the special preceding character, return FALSE. + +Originally, this function only recognized a sequence of letters between the +terminators, but it seems that Perl recognizes any sequence of characters, +though of course unknown POSIX names are subsequently rejected. Perl gives an +"Unknown POSIX class" error for [:f\oo:] for example, where previously PCRE +didn't consider this to be a POSIX class. Likewise for [:1234:]. + +The problem in trying to be exactly like Perl is in the handling of escapes. We +have to be sure that [abc[:x\]pqr] is *not* treated as containing a POSIX +class, but [abc[:x\]pqr:]] is (so that an error can be generated). The code +below handles the special case of \], but does not try to do any other escape +processing. This makes it different from Perl for cases such as [:l\ower:] +where Perl recognizes it as the POSIX class "lower" but PCRE does not recognize +"l\ower". This is a lesser evil that not diagnosing bad classes when Perl does, +I think. -Argument: +Arguments: ptr pointer to the initial [ endptr where to return the end pointer - cd pointer to compile data Returns: TRUE or FALSE */ static BOOL -check_posix_syntax(const uschar *ptr, const uschar **endptr, compile_data *cd) +check_posix_syntax(const uschar *ptr, const uschar **endptr) { int terminator; /* Don't combine these lines; the Solaris cc */ terminator = *(++ptr); /* compiler warns about "non-constant" initializer. */ -if (*(++ptr) == '^') ptr++; -while ((cd->ctypes[*ptr] & ctype_letter) != 0) ptr++; -if (*ptr == terminator && ptr[1] == ']') +for (++ptr; *ptr != 0; ptr++) { - *endptr = ptr; - return TRUE; + if (*ptr == '\\' && ptr[1] == ']') ptr++; else + { + if (*ptr == ']') return FALSE; + if (*ptr == terminator && ptr[1] == ']') + { + *endptr = ptr; + return TRUE; + } + } } return FALSE; } @@ -1731,11 +1801,13 @@ Returns: a value representing the name, or -1 if unknown static int check_posix_name(const uschar *ptr, int len) { +const char *pn = posix_names; register int yield = 0; while (posix_name_lengths[yield] != 0) { if (len == posix_name_lengths[yield] && - strncmp((const char *)ptr, posix_names[yield], len) == 0) return yield; + strncmp((const char *)ptr, pn, len) == 0) return yield; + pn += posix_name_lengths[yield] + 1; yield++; } return -1; @@ -2341,6 +2413,7 @@ req_caseopt = ((options & PCRE_CASELESS) != 0)? REQ_CASELESS : 0; for (;; ptr++) { BOOL negate_class; + BOOL should_flip_negation; BOOL possessive_quantifier; BOOL is_quantifier; BOOL is_recurse; @@ -2564,7 +2637,7 @@ for (;; ptr++) they are encountered at the top level, so we'll do that too. */ if ((ptr[1] == ':' || ptr[1] == '.' || ptr[1] == '=') && - check_posix_syntax(ptr, &tempptr, cd)) + check_posix_syntax(ptr, &tempptr)) { *errorcodeptr = (ptr[1] == ':')? ERR13 : ERR31; goto FAILED; @@ -2589,6 +2662,12 @@ for (;; ptr++) else break; } + /* If a class contains a negative special such as \S, we need to flip the + negation flag at the end, so that support for characters > 255 works + correctly (they are all included in the class). */ + + should_flip_negation = FALSE; + /* Keep a count of chars with values < 256 so that we can optimize the case of just a single character (as long as it's < 256). However, For higher valued UTF-8 characters, we don't yet do any optimization. */ @@ -2644,7 +2723,7 @@ for (;; ptr++) if (c == '[' && (ptr[1] == ':' || ptr[1] == '.' || ptr[1] == '=') && - check_posix_syntax(ptr, &tempptr, cd)) + check_posix_syntax(ptr, &tempptr)) { BOOL local_negate = FALSE; int posix_class, taboffset, tabopt; @@ -2661,6 +2740,7 @@ for (;; ptr++) if (*ptr == '^') { local_negate = TRUE; + should_flip_negation = TRUE; /* Note negative special */ ptr++; } @@ -2735,7 +2815,7 @@ for (;; ptr++) c = check_escape(&ptr, errorcodeptr, cd->bracount, options, TRUE); if (*errorcodeptr != 0) goto FAILED; - if (-c == ESC_b) c = '\b'; /* \b is backslash in a class */ + if (-c == ESC_b) c = '\b'; /* \b is backspace in a class */ else if (-c == ESC_X) c = 'X'; /* \X is literal X in a class */ else if (-c == ESC_R) c = 'R'; /* \R is literal R in a class */ else if (-c == ESC_Q) /* Handle start of quoted string */ @@ -2763,6 +2843,7 @@ for (;; ptr++) continue; case ESC_D: + should_flip_negation = TRUE; for (c = 0; c < 32; c++) classbits[c] |= ~cbits[c+cbit_digit]; continue; @@ -2771,6 +2852,7 @@ for (;; ptr++) continue; case ESC_W: + should_flip_negation = TRUE; for (c = 0; c < 32; c++) classbits[c] |= ~cbits[c+cbit_word]; continue; @@ -2780,13 +2862,11 @@ for (;; ptr++) continue; case ESC_S: + should_flip_negation = TRUE; for (c = 0; c < 32; c++) classbits[c] |= ~cbits[c+cbit_space]; classbits[1] |= 0x08; /* Perl 5.004 onwards omits VT from \s */ continue; - case ESC_E: /* Perl ignores an orphan \E */ - continue; - default: /* Not recognized; fall through */ break; /* Need "default" setting to stop compiler warning. */ } @@ -2974,6 +3054,12 @@ for (;; ptr++) oldptr = ptr; + /* Remember \r or \n */ + + if (c == '\r' || c == '\n') cd->external_flags |= PCRE_HASCRORLF; + + /* Check for range */ + if (!inescq && ptr[1] == '-') { int d; @@ -3015,7 +3101,7 @@ for (;; ptr++) d = check_escape(&ptr, errorcodeptr, cd->bracount, options, TRUE); if (*errorcodeptr != 0) goto FAILED; - /* \b is backslash; \X is literal X; \R is literal R; any other + /* \b is backspace; \X is literal X; \R is literal R; any other special means the '-' was literal */ if (d < 0) @@ -3041,6 +3127,10 @@ for (;; ptr++) if (d == c) goto LONE_SINGLE_CHARACTER; /* A few lines below */ + /* Remember \r or \n */ + + if (d == '\r' || d == '\n') cd->external_flags |= PCRE_HASCRORLF; + /* In UTF-8 mode, if the upper limit is > 255, or > 127 for caseless matching, we have to use an XCLASS with extra data items. Caseless matching for characters > 127 is available only if UCP support is @@ -3194,16 +3284,24 @@ for (;; ptr++) goto FAILED; } + +/* This code has been disabled because it would mean that \s counts as +an explicit \r or \n reference, and that's not really what is wanted. Now +we set the flag only if there is a literal "\r" or "\n" in the class. */ + +#if 0 /* Remember whether \r or \n are in this class */ if (negate_class) { - if ((classbits[1] & 0x24) != 0x24) cd->external_options |= PCRE_HASCRORLF; + if ((classbits[1] & 0x24) != 0x24) cd->external_flags |= PCRE_HASCRORLF; } else { - if ((classbits[1] & 0x24) != 0) cd->external_options |= PCRE_HASCRORLF; + if ((classbits[1] & 0x24) != 0) cd->external_flags |= PCRE_HASCRORLF; } +#endif + /* If class_charcount is 1, we saw precisely one character whose value is less than 256. As long as there were no characters >= 128 and there was no @@ -3267,11 +3365,14 @@ for (;; ptr++) zeroreqbyte = reqbyte; /* If there are characters with values > 255, we have to compile an - extended class, with its own opcode. If there are no characters < 256, - we can omit the bitmap in the actual compiled code. */ + extended class, with its own opcode, unless there was a negated special + such as \S in the class, because in that case all characters > 255 are in + the class, so any that were explicitly given as well can be ignored. If + (when there are explicit characters > 255 that must be listed) there are no + characters < 256, we can omit the bitmap in the actual compiled code. */ #ifdef SUPPORT_UTF8 - if (class_utf8) + if (class_utf8 && !should_flip_negation) { *class_utf8data++ = XCL_END; /* Marks the end of extra data */ *code++ = OP_XCLASS; @@ -3297,20 +3398,19 @@ for (;; ptr++) } #endif - /* If there are no characters > 255, negate the 32-byte map if necessary, - and copy it into the code vector. If this is the first thing in the branch, - there can be no first char setting, whatever the repeat count. Any reqbyte - setting must remain unchanged after any kind of repeat. */ + /* If there are no characters > 255, set the opcode to OP_CLASS or + OP_NCLASS, depending on whether the whole class was negated and whether + there were negative specials such as \S in the class. Then copy the 32-byte + map into the code vector, negating it if necessary. */ + *code++ = (negate_class == should_flip_negation) ? OP_CLASS : OP_NCLASS; if (negate_class) { - *code++ = OP_NCLASS; if (lengthptr == NULL) /* Save time in the pre-compile phase */ for (c = 0; c < 32; c++) code[c] = ~classbits[c]; } else { - *code++ = OP_CLASS; memcpy(code, classbits, 32); } code += 32; @@ -3496,7 +3596,7 @@ for (;; ptr++) /* All real repeats make it impossible to handle partial matching (maybe one day we will be able to remove this restriction). */ - if (repeat_max != 1) cd->nopartial = TRUE; + if (repeat_max != 1) cd->external_flags |= PCRE_NOPARTIAL; /* Combine the op_type with the repeat_type */ @@ -3646,7 +3746,7 @@ for (;; ptr++) /* All real repeats make it impossible to handle partial matching (maybe one day we will be able to remove this restriction). */ - if (repeat_max != 1) cd->nopartial = TRUE; + if (repeat_max != 1) cd->external_flags |= PCRE_NOPARTIAL; if (repeat_min == 0 && repeat_max == -1) *code++ = OP_CRSTAR + repeat_type; @@ -3946,7 +4046,9 @@ for (;; ptr++) int len; if (*tempcode == OP_EXACT || *tempcode == OP_TYPEEXACT || *tempcode == OP_NOTEXACT) - tempcode += _pcre_OP_lengths[*tempcode]; + tempcode += _pcre_OP_lengths[*tempcode] + + ((*tempcode == OP_TYPEEXACT && + (tempcode[3] == OP_PROP || tempcode[3] == OP_NOTPROP))? 2:0); len = code - tempcode; if (len > 0) switch (*tempcode) { @@ -4004,6 +4106,7 @@ for (;; ptr++) if (*(++ptr) == '*' && (cd->ctypes[ptr[1]] & ctype_letter) != 0) { int i, namelen; + const char *vn = verbnames; const uschar *name = ++ptr; previous = NULL; while ((cd->ctypes[*++ptr] & ctype_letter) != 0); @@ -4021,12 +4124,13 @@ for (;; ptr++) for (i = 0; i < verbcount; i++) { if (namelen == verbs[i].len && - strncmp((char *)name, verbs[i].name, namelen) == 0) + strncmp((char *)name, vn, namelen) == 0) { *code = verbs[i].op; if (*code++ == OP_ACCEPT) cd->had_accept = TRUE; break; } + vn += verbs[i].len + 1; } if (i < verbcount) continue; *errorcodeptr = ERR60; @@ -4171,16 +4275,13 @@ for (;; ptr++) *errorcodeptr = ERR58; goto FAILED; } - if (refsign == '-') + recno = (refsign == '-')? + cd->bracount - recno + 1 : recno +cd->bracount; + if (recno <= 0 || recno > cd->final_bracount) { - recno = cd->bracount - recno + 1; - if (recno <= 0) - { - *errorcodeptr = ERR15; - goto FAILED; - } + *errorcodeptr = ERR15; + goto FAILED; } - else recno += cd->bracount; PUT2(code, 2+LINK_SIZE, recno); break; } @@ -4252,9 +4353,10 @@ for (;; ptr++) skipbytes = 1; } - /* Check for the "name" actually being a subpattern number. */ + /* Check for the "name" actually being a subpattern number. We are + in the second pass here, so final_bracount is set. */ - else if (recno > 0) + else if (recno > 0 && recno <= cd->final_bracount) { PUT2(code, 2+LINK_SIZE, recno); } @@ -4448,7 +4550,9 @@ for (;; ptr++) /* We come here from the Python syntax above that handles both references (?P=name) and recursion (?P>name), as well as falling - through from the Perl recursion syntax (?&name). */ + through from the Perl recursion syntax (?&name). We also come here from + the Perl \k or \k'name' back reference syntax and the \k{name} + .NET syntax. */ NAMED_REF_OR_RECURSE: name = ++ptr; @@ -4460,6 +4564,11 @@ for (;; ptr++) if (lengthptr != NULL) { + if (namelen == 0) + { + *errorcodeptr = ERR62; + goto FAILED; + } if (*ptr != terminator) { *errorcodeptr = ERR42; @@ -4473,14 +4582,19 @@ for (;; ptr++) recno = 0; } - /* In the real compile, seek the name in the table */ + /* In the real compile, seek the name in the table. We check the name + first, and then check that we have reached the end of the name in the + table. That way, if the name that is longer than any in the table, + the comparison will fail without reading beyond the table entry. */ else { slot = cd->name_table; for (i = 0; i < cd->names_found; i++) { - if (strncmp((char *)name, (char *)slot+2, namelen) == 0) break; + if (strncmp((char *)name, (char *)slot+2, namelen) == 0 && + slot[2+namelen] == 0) + break; slot += cd->name_entry_size; } @@ -4517,7 +4631,15 @@ for (;; ptr++) { const uschar *called; - if ((refsign = *ptr) == '+') ptr++; + if ((refsign = *ptr) == '+') + { + ptr++; + if ((digitab[*ptr] & ctype_digit) == 0) + { + *errorcodeptr = ERR63; + goto FAILED; + } + } else if (refsign == '-') { if ((digitab[ptr[1]] & ctype_digit) == 0) @@ -4643,7 +4765,7 @@ for (;; ptr++) case 'J': /* Record that it changed in the external options */ *optset |= PCRE_DUPNAMES; - cd->external_options |= PCRE_JCHANGED; + cd->external_flags |= PCRE_JCHANGED; break; case 'i': *optset |= PCRE_CASELESS; break; @@ -5063,7 +5185,7 @@ for (;; ptr++) /* Remember if \r or \n were seen */ if (mcbuffer[0] == '\r' || mcbuffer[0] == '\n') - cd->external_options |= PCRE_HASCRORLF; + cd->external_flags |= PCRE_HASCRORLF; /* Set the first and required bytes appropriately. If no previous first byte, set it from this character, but revert to none on a zero repeat. @@ -5743,24 +5865,46 @@ cd->fcc = tables + fcc_offset; cd->cbits = tables + cbits_offset; cd->ctypes = tables + ctypes_offset; -/* Check for newline settings at the start of the pattern, and remember the -offset for later. */ +/* Check for global one-time settings at the start of the pattern, and remember +the offset for later. */ -if (ptr[0] == '(' && ptr[1] == '*') +while (ptr[skipatstart] == '(' && ptr[skipatstart+1] == '*') { int newnl = 0; - if (strncmp((char *)(ptr+2), "CR)", 3) == 0) - { skipatstart = 5; newnl = PCRE_NEWLINE_CR; } - else if (strncmp((char *)(ptr+2), "LF)", 3) == 0) - { skipatstart = 5; newnl = PCRE_NEWLINE_LF; } - else if (strncmp((char *)(ptr+2), "CRLF)", 5) == 0) - { skipatstart = 7; newnl = PCRE_NEWLINE_CR + PCRE_NEWLINE_LF; } - else if (strncmp((char *)(ptr+2), "ANY)", 4) == 0) - { skipatstart = 6; newnl = PCRE_NEWLINE_ANY; } - else if (strncmp((char *)(ptr+2), "ANYCRLF)", 8) == 0) - { skipatstart = 10; newnl = PCRE_NEWLINE_ANYCRLF; } - if (skipatstart > 0) + int newbsr = 0; + + if (strncmp((char *)(ptr+skipatstart+2), "CR)", 3) == 0) + { skipatstart += 5; newnl = PCRE_NEWLINE_CR; } + else if (strncmp((char *)(ptr+skipatstart+2), "LF)", 3) == 0) + { skipatstart += 5; newnl = PCRE_NEWLINE_LF; } + else if (strncmp((char *)(ptr+skipatstart+2), "CRLF)", 5) == 0) + { skipatstart += 7; newnl = PCRE_NEWLINE_CR + PCRE_NEWLINE_LF; } + else if (strncmp((char *)(ptr+skipatstart+2), "ANY)", 4) == 0) + { skipatstart += 6; newnl = PCRE_NEWLINE_ANY; } + else if (strncmp((char *)(ptr+skipatstart+2), "ANYCRLF)", 8) == 0) + { skipatstart += 10; newnl = PCRE_NEWLINE_ANYCRLF; } + + else if (strncmp((char *)(ptr+skipatstart+2), "BSR_ANYCRLF)", 12) == 0) + { skipatstart += 14; newbsr = PCRE_BSR_ANYCRLF; } + else if (strncmp((char *)(ptr+skipatstart+2), "BSR_UNICODE)", 12) == 0) + { skipatstart += 14; newbsr = PCRE_BSR_UNICODE; } + + if (newnl != 0) options = (options & ~PCRE_NEWLINE_BITS) | newnl; + else if (newbsr != 0) + options = (options & ~(PCRE_BSR_ANYCRLF|PCRE_BSR_UNICODE)) | newbsr; + else break; + } + +/* Check validity of \R options. */ + +switch (options & (PCRE_BSR_ANYCRLF|PCRE_BSR_UNICODE)) + { + case 0: + case PCRE_BSR_ANYCRLF: + case PCRE_BSR_UNICODE: + break; + default: errorcode = ERR56; goto PCRE_EARLY_ERROR_RETURN; } /* Handle different types of newline. The three bits give seven cases. The @@ -5822,7 +5966,7 @@ to compile parts of the pattern into; the compiled code is discarded when it is no longer needed, so hopefully this workspace will never overflow, though there is a test for its doing so. */ -cd->bracount = 0; +cd->bracount = cd->final_bracount = 0; cd->names_found = 0; cd->name_entry_size = 0; cd->name_table = NULL; @@ -5832,8 +5976,8 @@ cd->hwm = cworkspace; cd->start_pattern = (const uschar *)pattern; cd->end_pattern = (const uschar *)(pattern + strlen(pattern)); cd->req_varyopt = 0; -cd->nopartial = FALSE; cd->external_options = options; +cd->external_flags = 0; /* Now do the pre-compile. On error, errorcode will be set non-zero, so we don't need to look at the result of the function here. The initial options have @@ -5872,14 +6016,16 @@ if (re == NULL) goto PCRE_EARLY_ERROR_RETURN; } -/* Put in the magic number, and save the sizes, initial options, and character -table pointer. NULL is used for the default character tables. The nullpad field -is at the end; it's there to help in the case when a regex compiled on a system -with 4-byte pointers is run on another with 8-byte pointers. */ +/* Put in the magic number, and save the sizes, initial options, internal +flags, and character table pointer. NULL is used for the default character +tables. The nullpad field is at the end; it's there to help in the case when a +regex compiled on a system with 4-byte pointers is run on another with 8-byte +pointers. */ re->magic_number = MAGIC_NUMBER; re->size = size; re->options = cd->external_options; +re->flags = cd->external_flags; re->dummy1 = 0; re->first_byte = 0; re->req_byte = 0; @@ -5897,6 +6043,7 @@ field. Reset the bracket count and the names_found field. Also reset the hwm field; this time it's used for remembering forward references to subpatterns. */ +cd->final_bracount = cd->bracount; /* Save for checking forward references */ cd->bracount = 0; cd->names_found = 0; cd->name_table = (uschar *)re + re->name_table_offset; @@ -5904,7 +6051,6 @@ codestart = cd->name_table + re->name_entry_size * re->name_count; cd->start_code = codestart; cd->hwm = cworkspace; cd->req_varyopt = 0; -cd->nopartial = FALSE; cd->had_accept = FALSE; /* Set up a starting, non-extracting bracket, then compile the expression. On @@ -5918,8 +6064,8 @@ code = (uschar *)codestart; &errorcode, FALSE, FALSE, 0, &firstbyte, &reqbyte, NULL, cd, NULL); re->top_bracket = cd->bracount; re->top_backref = cd->top_backref; +re->flags = cd->external_flags; -if (cd->nopartial) re->options |= PCRE_NOPARTIAL; if (cd->had_accept) reqbyte = -1; /* Must disable after (*ACCEPT) */ /* If not reached end of pattern on success, there's an excess bracket. */ @@ -5962,7 +6108,7 @@ if (errorcode != 0) PCRE_EARLY_ERROR_RETURN: *erroroffset = ptr - (const uschar *)pattern; PCRE_EARLY_ERROR_RETURN2: - *errorptr = error_texts[errorcode]; + *errorptr = find_error_text(errorcode); if (errorcodeptr != NULL) *errorcodeptr = errorcode; return NULL; } @@ -5991,10 +6137,10 @@ if ((re->options & PCRE_ANCHORED) == 0) int ch = firstbyte & 255; re->first_byte = ((firstbyte & REQ_CASELESS) != 0 && cd->fcc[ch] == ch)? ch : firstbyte; - re->options |= PCRE_FIRSTSET; + re->flags |= PCRE_FIRSTSET; } else if (is_startline(codestart, 0, cd->backref_map)) - re->options |= PCRE_STARTLINE; + re->flags |= PCRE_STARTLINE; } } @@ -6008,7 +6154,7 @@ if (reqbyte >= 0 && int ch = reqbyte & 255; re->req_byte = ((reqbyte & REQ_CASELESS) != 0 && cd->fcc[ch] == ch)? (reqbyte & ~REQ_CASELESS) : reqbyte; - re->options |= PCRE_REQCHSET; + re->flags |= PCRE_REQCHSET; } /* Print out the compiled data if debugging is enabled. This is never the @@ -6021,7 +6167,7 @@ printf("Length = %d top_bracket = %d top_backref = %d\n", printf("Options=%08x\n", re->options); -if ((re->options & PCRE_FIRSTSET) != 0) +if ((re->flags & PCRE_FIRSTSET) != 0) { int ch = re->first_byte & 255; const char *caseless = ((re->first_byte & REQ_CASELESS) == 0)? @@ -6030,7 +6176,7 @@ if ((re->options & PCRE_FIRSTSET) != 0) else printf("First char = \\x%02x%s\n", ch, caseless); } -if ((re->options & PCRE_REQCHSET) != 0) +if ((re->flags & PCRE_REQCHSET) != 0) { int ch = re->req_byte & 255; const char *caseless = ((re->req_byte & REQ_CASELESS) == 0)? @@ -6047,7 +6193,7 @@ was compiled can be seen. */ if (code - codestart > length) { (pcre_free)(re); - *errorptr = error_texts[ERR23]; + *errorptr = find_error_text(ERR23); *erroroffset = ptr - (uschar *)pattern; if (errorcodeptr != NULL) *errorcodeptr = ERR23; return NULL; diff --git a/ext/pcre/pcrelib/pcre_config.c b/ext/pcre/pcrelib/pcre_config.c index 700a5d2918..667c4f1b52 100644 --- a/ext/pcre/pcrelib/pcre_config.c +++ b/ext/pcre/pcrelib/pcre_config.c @@ -41,7 +41,7 @@ POSSIBILITY OF SUCH DAMAGE. /* This module contains the external function pcre_config(). */ -#include +#include "config.h" #include "pcre_internal.h" @@ -85,6 +85,14 @@ switch (what) *((int *)where) = NEWLINE; break; + case PCRE_CONFIG_BSR: +#ifdef BSR_ANYCRLF + *((int *)where) = 1; +#else + *((int *)where) = 0; +#endif + break; + case PCRE_CONFIG_LINK_SIZE: *((int *)where) = LINK_SIZE; break; diff --git a/ext/pcre/pcrelib/pcre_exec.c b/ext/pcre/pcrelib/pcre_exec.c index 1c570a03bd..593707fc89 100644 --- a/ext/pcre/pcrelib/pcre_exec.c +++ b/ext/pcre/pcrelib/pcre_exec.c @@ -42,7 +42,7 @@ POSSIBILITY OF SUCH DAMAGE. pattern matching using an NFA algorithm, trying to mimic Perl as closely as possible. There are also some static supporting functions. */ -#include +#include "config.h" #define NLBLOCK md /* Block containing newline information */ #define PSSTART start_subject /* Field containing processed string start */ @@ -1524,12 +1524,16 @@ for (;;) case 0x000d: if (eptr < md->end_subject && *eptr == 0x0a) eptr++; break; + case 0x000a: + break; + case 0x000b: case 0x000c: case 0x0085: case 0x2028: case 0x2029: + if (md->bsr_anycrlf) RRETURN(MATCH_NOMATCH); break; } ecode++; @@ -2952,12 +2956,16 @@ for (;;) case 0x000d: if (eptr < md->end_subject && *eptr == 0x0a) eptr++; break; + case 0x000a: + break; + case 0x000b: case 0x000c: case 0x0085: case 0x2028: case 0x2029: + if (md->bsr_anycrlf) RRETURN(MATCH_NOMATCH); break; } } @@ -3170,9 +3178,12 @@ for (;;) if (eptr < md->end_subject && *eptr == 0x0a) eptr++; break; case 0x000a: + break; + case 0x000b: case 0x000c: case 0x0085: + if (md->bsr_anycrlf) RRETURN(MATCH_NOMATCH); break; } } @@ -3424,11 +3435,14 @@ for (;;) if (eptr < md->end_subject && *eptr == 0x0a) eptr++; break; case 0x000a: + break; + case 0x000b: case 0x000c: case 0x0085: case 0x2028: case 0x2029: + if (md->bsr_anycrlf) RRETURN(MATCH_NOMATCH); break; } break; @@ -3580,10 +3594,14 @@ for (;;) case 0x000d: if (eptr < md->end_subject && *eptr == 0x0a) eptr++; break; + case 0x000a: + break; + case 0x000b: case 0x000c: case 0x0085: + if (md->bsr_anycrlf) RRETURN(MATCH_NOMATCH); break; } break; @@ -3881,8 +3899,10 @@ for (;;) } else { - if (c != 0x000a && c != 0x000b && c != 0x000c && - c != 0x0085 && c != 0x2028 && c != 0x2029) + if (c != 0x000a && + (md->bsr_anycrlf || + (c != 0x000b && c != 0x000c && + c != 0x0085 && c != 0x2028 && c != 0x2029))) break; eptr += len; } @@ -4072,7 +4092,9 @@ for (;;) } else { - if (c != 0x000a && c != 0x000b && c != 0x000c && c != 0x0085) + if (c != 0x000a && + (md->bsr_anycrlf || + (c != 0x000b && c != 0x000c && c != 0x0085))) break; eptr++; } @@ -4222,12 +4244,17 @@ HEAP_RETURN: switch (frame->Xwhere) { LBL( 1) LBL( 2) LBL( 3) LBL( 4) LBL( 5) LBL( 6) LBL( 7) LBL( 8) - LBL( 9) LBL(10) LBL(11) LBL(12) LBL(13) LBL(14) LBL(15) LBL(16) - LBL(17) LBL(18) LBL(19) LBL(20) LBL(21) LBL(22) LBL(23) LBL(24) - LBL(25) LBL(26) LBL(27) LBL(28) LBL(29) LBL(30) LBL(31) LBL(32) - LBL(33) LBL(34) LBL(35) LBL(36) LBL(37) LBL(38) LBL(39) LBL(40) - LBL(41) LBL(42) LBL(43) LBL(44) LBL(45) LBL(46) LBL(47) LBL(48) - LBL(49) LBL(50) LBL(51) LBL(52) LBL(53) LBL(54) + LBL( 9) LBL(10) LBL(11) LBL(12) LBL(13) LBL(14) LBL(15) LBL(17) + LBL(19) LBL(24) LBL(25) LBL(26) LBL(27) LBL(29) LBL(31) LBL(33) + LBL(35) LBL(43) LBL(47) LBL(48) LBL(49) LBL(50) LBL(51) LBL(52) + LBL(53) LBL(54) +#ifdef SUPPORT_UTF8 + LBL(16) LBL(18) LBL(20) LBL(21) LBL(22) LBL(23) LBL(28) LBL(30) + LBL(32) LBL(34) LBL(42) LBL(46) +#ifdef SUPPORT_UCP + LBL(36) LBL(37) LBL(38) LBL(39) LBL(40) LBL(41) LBL(44) LBL(45) +#endif /* SUPPORT_UCP */ +#endif /* SUPPORT_UTF8 */ default: DPRINTF(("jump error in pcre match: label %d non-existent\n", frame->Xwhere)); return PCRE_ERROR_INTERNAL; @@ -4406,7 +4433,7 @@ if (re->magic_number != MAGIC_NUMBER) /* Set up other data */ anchored = ((re->options | options) & PCRE_ANCHORED) != 0; -startline = (re->options & PCRE_STARTLINE) != 0; +startline = (re->flags & PCRE_STARTLINE) != 0; firstline = (re->options & PCRE_FIRSTLINE) != 0; /* The code starts after the real_pcre block and the capture name table. */ @@ -4433,11 +4460,37 @@ md->recursive = NULL; /* No recursion at top level */ md->lcc = tables + lcc_offset; md->ctypes = tables + ctypes_offset; +/* Handle different \R options. */ + +switch (options & (PCRE_BSR_ANYCRLF|PCRE_BSR_UNICODE)) + { + case 0: + if ((re->options & (PCRE_BSR_ANYCRLF|PCRE_BSR_UNICODE)) != 0) + md->bsr_anycrlf = (re->options & PCRE_BSR_ANYCRLF) != 0; + else +#ifdef BSR_ANYCRLF + md->bsr_anycrlf = TRUE; +#else + md->bsr_anycrlf = FALSE; +#endif + break; + + case PCRE_BSR_ANYCRLF: + md->bsr_anycrlf = TRUE; + break; + + case PCRE_BSR_UNICODE: + md->bsr_anycrlf = FALSE; + break; + + default: return PCRE_ERROR_BADNEWLINE; + } + /* Handle different types of newline. The three bits give eight cases. If nothing is set at run time, whatever was used at compile time applies. */ -switch ((((options & PCRE_NEWLINE_BITS) == 0)? re->options : (pcre_uint32)options) & - PCRE_NEWLINE_BITS) +switch ((((options & PCRE_NEWLINE_BITS) == 0)? re->options : + (pcre_uint32)options) & PCRE_NEWLINE_BITS) { case 0: newline = NEWLINE; break; /* Compile-time default */ case PCRE_NEWLINE_CR: newline = '\r'; break; @@ -4476,7 +4529,7 @@ else /* Partial matching is supported only for a restricted set of regexes at the moment. */ -if (md->partial && (re->options & PCRE_NOPARTIAL) != 0) +if (md->partial && (re->flags & PCRE_NOPARTIAL) != 0) return PCRE_ERROR_BADPARTIAL; /* Check a UTF-8 string if required. Unfortunately there's no way of passing @@ -4553,7 +4606,7 @@ studied, there may be a bitmap of possible first characters. */ if (!anchored) { - if ((re->options & PCRE_FIRSTSET) != 0) + if ((re->flags & PCRE_FIRSTSET) != 0) { first_byte = re->first_byte & 255; if ((first_byte_caseless = ((re->first_byte & REQ_CASELESS) != 0)) == TRUE) @@ -4568,7 +4621,7 @@ if (!anchored) /* For anchored or unanchored matches, there may be a "last known required character" set. */ -if ((re->options & PCRE_REQCHSET) != 0) +if ((re->flags & PCRE_REQCHSET) != 0) { req_byte = re->req_byte & 255; req_byte_caseless = (re->req_byte & REQ_CASELESS) != 0; @@ -4615,10 +4668,10 @@ for(;;) if (first_byte_caseless) while (start_match < end_subject && md->lcc[*start_match] != first_byte) - start_match++; + { NEXTCHAR(start_match); } else while (start_match < end_subject && *start_match != first_byte) - start_match++; + { NEXTCHAR(start_match); } } /* Or to just after a linebreak for a multiline match if possible */ @@ -4628,7 +4681,7 @@ for(;;) if (start_match > md->start_subject + start_offset) { while (start_match <= end_subject && !WAS_NEWLINE(start_match)) - start_match++; + { NEXTCHAR(start_match); } /* If we have just passed a CR and the newline option is ANY or ANYCRLF, and we are now at a LF, advance the match position by one more character. @@ -4649,7 +4702,9 @@ for(;;) while (start_match < end_subject) { register unsigned int c = *start_match; - if ((start_bits[c/8] & (1 << (c&7))) == 0) start_match++; else break; + if ((start_bits[c/8] & (1 << (c&7))) == 0) + { NEXTCHAR(start_match); } + else break; } } @@ -4790,7 +4845,7 @@ for(;;) if (start_match[-1] == '\r' && start_match < end_subject && *start_match == '\n' && - (re->options & PCRE_HASCRORLF) == 0 && + (re->flags & PCRE_HASCRORLF) == 0 && (md->nltype == NLTYPE_ANY || md->nltype == NLTYPE_ANYCRLF || md->nllen == 2)) diff --git a/ext/pcre/pcrelib/pcre_fullinfo.c b/ext/pcre/pcrelib/pcre_fullinfo.c index 1554292e66..3d6a473109 100644 --- a/ext/pcre/pcrelib/pcre_fullinfo.c +++ b/ext/pcre/pcrelib/pcre_fullinfo.c @@ -42,7 +42,7 @@ POSSIBILITY OF SUCH DAMAGE. information about a compiled pattern. */ -#include +#include "config.h" #include "pcre_internal.h" @@ -108,8 +108,8 @@ switch (what) case PCRE_INFO_FIRSTBYTE: *((int *)where) = - ((re->options & PCRE_FIRSTSET) != 0)? re->first_byte : - ((re->options & PCRE_STARTLINE) != 0)? -1 : -2; + ((re->flags & PCRE_FIRSTSET) != 0)? re->first_byte : + ((re->flags & PCRE_STARTLINE) != 0)? -1 : -2; break; /* Make sure we pass back the pointer to the bit vector in the external @@ -123,7 +123,7 @@ switch (what) case PCRE_INFO_LASTLITERAL: *((int *)where) = - ((re->options & PCRE_REQCHSET) != 0)? re->req_byte : -1; + ((re->flags & PCRE_REQCHSET) != 0)? re->req_byte : -1; break; case PCRE_INFO_NAMEENTRYSIZE: @@ -143,15 +143,15 @@ switch (what) break; case PCRE_INFO_OKPARTIAL: - *((int *)where) = (re->options & PCRE_NOPARTIAL) == 0; + *((int *)where) = (re->flags & PCRE_NOPARTIAL) == 0; break; case PCRE_INFO_JCHANGED: - *((int *)where) = (re->options & PCRE_JCHANGED) != 0; + *((int *)where) = (re->flags & PCRE_JCHANGED) != 0; break; case PCRE_INFO_HASCRORLF: - *((int *)where) = (re->options & PCRE_HASCRORLF) != 0; + *((int *)where) = (re->flags & PCRE_HASCRORLF) != 0; break; default: return PCRE_ERROR_BADOPTION; diff --git a/ext/pcre/pcrelib/pcre_get.c b/ext/pcre/pcrelib/pcre_get.c index 898f051e89..c13914dae4 100644 --- a/ext/pcre/pcrelib/pcre_get.c +++ b/ext/pcre/pcrelib/pcre_get.c @@ -43,7 +43,7 @@ from the subject string after a regex match has succeeded. The original idea for these functions came from Scott Wimer. */ -#include +#include "config.h" #include "pcre_internal.h" @@ -187,7 +187,7 @@ const real_pcre *re = (const real_pcre *)code; int entrysize; char *first, *last; uschar *entry; -if ((re->options & (PCRE_DUPNAMES | PCRE_JCHANGED)) == 0) +if ((re->options & PCRE_DUPNAMES) == 0 && (re->flags & PCRE_JCHANGED) == 0) return pcre_get_stringnumber(code, stringname); entrysize = pcre_get_stringtable_entries(code, stringname, &first, &last); if (entrysize <= 0) return entrysize; diff --git a/ext/pcre/pcrelib/pcre_globals.c b/ext/pcre/pcrelib/pcre_globals.c index a56f13aa2f..bfe21ecbe1 100644 --- a/ext/pcre/pcrelib/pcre_globals.c +++ b/ext/pcre/pcrelib/pcre_globals.c @@ -46,7 +46,7 @@ indirection. These values can be changed by the caller, but are shared between all threads. However, when compiling for Virtual Pascal, things are done differently, and global variables are not used (see pcre.in). */ -#include +#include "config.h" #include "pcre_internal.h" diff --git a/ext/pcre/pcrelib/pcre_info.c b/ext/pcre/pcrelib/pcre_info.c index 6970e7953f..02a0cd43d4 100644 --- a/ext/pcre/pcrelib/pcre_info.c +++ b/ext/pcre/pcrelib/pcre_info.c @@ -43,7 +43,7 @@ information about a compiled pattern. However, use of this function is now deprecated, as it has been superseded by pcre_fullinfo(). */ -#include +#include "config.h" #include "pcre_internal.h" @@ -83,8 +83,8 @@ if (re->magic_number != MAGIC_NUMBER) } if (optptr != NULL) *optptr = (int)(re->options & PUBLIC_OPTIONS); if (first_byte != NULL) - *first_byte = ((re->options & PCRE_FIRSTSET) != 0)? re->first_byte : - ((re->options & PCRE_STARTLINE) != 0)? -1 : -2; + *first_byte = ((re->flags & PCRE_FIRSTSET) != 0)? re->first_byte : + ((re->flags & PCRE_STARTLINE) != 0)? -1 : -2; return re->top_bracket; } diff --git a/ext/pcre/pcrelib/pcre_internal.h b/ext/pcre/pcrelib/pcre_internal.h index a2409f9425..0b2603b2b1 100644 --- a/ext/pcre/pcrelib/pcre_internal.h +++ b/ext/pcre/pcrelib/pcre_internal.h @@ -363,6 +363,7 @@ never be called in byte mode. To make sure it can never even appear when UTF-8 support is omitted, we don't even define it. */ #ifndef SUPPORT_UTF8 +#define NEXTCHAR(p) p++; #define GETCHAR(c, eptr) c = *eptr; #define GETCHARTEST(c, eptr) c = *eptr; #define GETCHARINC(c, eptr) c = *eptr++; @@ -372,6 +373,13 @@ support is omitted, we don't even define it. */ #else /* SUPPORT_UTF8 */ +/* Advance a character pointer one byte in non-UTF-8 mode and by one character +in UTF-8 mode. */ + +#define NEXTCHAR(p) \ + p++; \ + if (utf8) { while((*p & 0xc0) == 0x80) p++; } + /* Get the next UTF-8 character, not advancing the pointer. This is called when we know we are in UTF-8 mode. */ @@ -481,18 +489,16 @@ Standard C system should have one. */ #define PCRE_IMS (PCRE_CASELESS|PCRE_MULTILINE|PCRE_DOTALL) -/* Private options flags start at the most significant end of the four bytes. -The public options defined in pcre.h start at the least significant end. Make -sure they don't overlap! The bits are getting a bit scarce now -- when we run -out, there is a dummy word in the structure that could be used for the private -bits. */ +/* Private flags containing information about the compiled regex. They used to +live at the top end of the options word, but that got almost full, so now they +are in a 16-bit flags word. */ -#define PCRE_NOPARTIAL 0x80000000 /* can't use partial with this regex */ -#define PCRE_FIRSTSET 0x40000000 /* first_byte is set */ -#define PCRE_REQCHSET 0x20000000 /* req_byte is set */ -#define PCRE_STARTLINE 0x10000000 /* start after \n for multiline */ -#define PCRE_JCHANGED 0x08000000 /* j option changes within regex */ -#define PCRE_HASCRORLF 0x04000000 /* explicit \r or \n in pattern */ +#define PCRE_NOPARTIAL 0x0001 /* can't use partial with this regex */ +#define PCRE_FIRSTSET 0x0002 /* first_byte is set */ +#define PCRE_REQCHSET 0x0004 /* req_byte is set */ +#define PCRE_STARTLINE 0x0008 /* start after \n for multiline */ +#define PCRE_JCHANGED 0x0010 /* j option used in regex */ +#define PCRE_HASCRORLF 0x0020 /* explicit \r or \n in pattern */ /* Options for the "extra" block produced by pcre_study(). */ @@ -508,15 +514,16 @@ time, run time, or study time, respectively. */ (PCRE_CASELESS|PCRE_EXTENDED|PCRE_ANCHORED|PCRE_MULTILINE| \ PCRE_DOTALL|PCRE_DOLLAR_ENDONLY|PCRE_EXTRA|PCRE_UNGREEDY|PCRE_UTF8| \ PCRE_NO_AUTO_CAPTURE|PCRE_NO_UTF8_CHECK|PCRE_AUTO_CALLOUT|PCRE_FIRSTLINE| \ - PCRE_DUPNAMES|PCRE_NEWLINE_BITS) + PCRE_DUPNAMES|PCRE_NEWLINE_BITS|PCRE_BSR_ANYCRLF|PCRE_BSR_UNICODE) #define PUBLIC_EXEC_OPTIONS \ (PCRE_ANCHORED|PCRE_NOTBOL|PCRE_NOTEOL|PCRE_NOTEMPTY|PCRE_NO_UTF8_CHECK| \ - PCRE_PARTIAL|PCRE_NEWLINE_BITS) + PCRE_PARTIAL|PCRE_NEWLINE_BITS|PCRE_BSR_ANYCRLF|PCRE_BSR_UNICODE) #define PUBLIC_DFA_EXEC_OPTIONS \ (PCRE_ANCHORED|PCRE_NOTBOL|PCRE_NOTEOL|PCRE_NOTEMPTY|PCRE_NO_UTF8_CHECK| \ - PCRE_PARTIAL|PCRE_DFA_SHORTEST|PCRE_DFA_RESTART|PCRE_NEWLINE_BITS) + PCRE_PARTIAL|PCRE_DFA_SHORTEST|PCRE_DFA_RESTART|PCRE_NEWLINE_BITS| \ + PCRE_BSR_ANYCRLF|PCRE_BSR_UNICODE) #define PUBLIC_STUDY_OPTIONS 0 /* None defined */ @@ -872,7 +879,7 @@ enum { ERR0, ERR1, ERR2, ERR3, ERR4, ERR5, ERR6, ERR7, ERR8, ERR9, ERR30, ERR31, ERR32, ERR33, ERR34, ERR35, ERR36, ERR37, ERR38, ERR39, ERR40, ERR41, ERR42, ERR43, ERR44, ERR45, ERR46, ERR47, ERR48, ERR49, ERR50, ERR51, ERR52, ERR53, ERR54, ERR55, ERR56, ERR57, ERR58, ERR59, - ERR60, ERR61 }; + ERR60, ERR61, ERR62, ERR63 }; /* The real format of the start of the pcre block; the index of names and the code vector run on as long as necessary after the end. We store an explicit @@ -894,9 +901,9 @@ NOTE NOTE NOTE: typedef struct real_pcre { pcre_uint32 magic_number; pcre_uint32 size; /* Total that was malloced */ - pcre_uint32 options; - pcre_uint32 dummy1; /* For future use, maybe */ - + pcre_uint32 options; /* Public options */ + pcre_uint16 flags; /* Private flags */ + pcre_uint16 dummy1; /* For future use */ pcre_uint16 top_bracket; pcre_uint16 top_backref; pcre_uint16 first_byte; @@ -935,12 +942,13 @@ typedef struct compile_data { uschar *name_table; /* The name/number table */ int names_found; /* Number of entries so far */ int name_entry_size; /* Size of each entry */ - int bracount; /* Count of capturing parens */ + int bracount; /* Count of capturing parens as we compile */ + int final_bracount; /* Saved value after first pass */ int top_backref; /* Maximum back reference */ unsigned int backref_map; /* Bitmap of low back refs */ int external_options; /* External (initial) options */ + int external_flags; /* External flag bits to be set */ int req_varyopt; /* "After variable item" flag for reqbyte */ - BOOL nopartial; /* Set TRUE if partial won't work */ BOOL had_accept; /* (*ACCEPT) encountered */ int nltype; /* Newline type */ int nllen; /* Newline string length */ @@ -1000,6 +1008,7 @@ typedef struct match_data { BOOL notempty; /* Empty string match not wanted */ BOOL partial; /* PARTIAL flag */ BOOL hitend; /* Hit the end of the subject at some point */ + BOOL bsr_anycrlf; /* \R is just any CRLF, not full Unicode */ const uschar *start_code; /* For use when recursing */ USPTR start_subject; /* Start of the subject string */ USPTR end_subject; /* End of the subject string */ @@ -1036,7 +1045,7 @@ typedef struct dfa_match_data { #define ctype_letter 0x02 #define ctype_digit 0x04 #define ctype_xdigit 0x08 -#define ctype_word 0x10 /* alphameric or '_' */ +#define ctype_word 0x10 /* alphanumeric or '_' */ #define ctype_meta 0x80 /* regexp meta char or zero (end pattern) */ /* Offsets for the bitmap tables in pcre_cbits. Each table contains a set @@ -1064,10 +1073,12 @@ total length. */ #define tables_length (ctypes_offset + 256) /* Layout of the UCP type table that translates property names into types and -codes. */ +codes. Each entry used to point directly to a name, but to reduce the number of +relocations in shared libraries, it now has an offset into a single string +instead. */ typedef struct { - const char *name; + pcre_uint16 name_offset; pcre_uint16 type; pcre_uint16 value; } ucp_type_table; @@ -1085,6 +1096,7 @@ extern const uschar _pcre_utf8_table4[]; extern const int _pcre_utf8_table1_size; +extern const char _pcre_utt_names[]; extern const ucp_type_table _pcre_utt[]; extern const int _pcre_utt_size; diff --git a/ext/pcre/pcrelib/pcre_maketables.c b/ext/pcre/pcrelib/pcre_maketables.c index cba42260ce..c68a4bebaf 100644 --- a/ext/pcre/pcrelib/pcre_maketables.c +++ b/ext/pcre/pcrelib/pcre_maketables.c @@ -45,7 +45,7 @@ compilation of dftables.c, in which case the macro DFTABLES is defined. */ #ifndef DFTABLES -# include +# include "config.h" # include "pcre_internal.h" #endif diff --git a/ext/pcre/pcrelib/pcre_newline.c b/ext/pcre/pcrelib/pcre_newline.c index 9725c723da..8261979239 100644 --- a/ext/pcre/pcrelib/pcre_newline.c +++ b/ext/pcre/pcrelib/pcre_newline.c @@ -47,7 +47,7 @@ and NLTYPE_ANY. The full list of Unicode newline characters is taken from http://unicode.org/unicode/reports/tr18/. */ -#include +#include "config.h" #include "pcre_internal.h" diff --git a/ext/pcre/pcrelib/pcre_ord2utf8.c b/ext/pcre/pcrelib/pcre_ord2utf8.c index ebb8a9d483..5554ed77b2 100644 --- a/ext/pcre/pcrelib/pcre_ord2utf8.c +++ b/ext/pcre/pcrelib/pcre_ord2utf8.c @@ -41,7 +41,7 @@ POSSIBILITY OF SUCH DAMAGE. /* This file contains a private PCRE function that converts an ordinal character value into a UTF8 string. */ -#include +#include "config.h" #include "pcre_internal.h" diff --git a/ext/pcre/pcrelib/pcre_printint.src b/ext/pcre/pcrelib/pcre_printint.src index 90381ed969..d51cbe0354 100644 --- a/ext/pcre/pcrelib/pcre_printint.src +++ b/ext/pcre/pcrelib/pcre_printint.src @@ -126,7 +126,7 @@ for (i = _pcre_utt_size - 1; i >= 0; i--) { if (ptype == _pcre_utt[i].type && pvalue == _pcre_utt[i].value) break; } -return (i >= 0)? _pcre_utt[i].name : "??"; +return (i >= 0)? _pcre_utt_names + _pcre_utt[i].name_offset : "??"; #else /* It gets harder and harder to shut off unwanted compiler warnings. */ ptype = ptype * pvalue; diff --git a/ext/pcre/pcrelib/pcre_refcount.c b/ext/pcre/pcrelib/pcre_refcount.c index 7d3b7981c4..4209ce23b7 100644 --- a/ext/pcre/pcrelib/pcre_refcount.c +++ b/ext/pcre/pcrelib/pcre_refcount.c @@ -44,7 +44,7 @@ pattern data block. This might be helpful in applications where the block is shared by different users. */ -#include +#include "config.h" #include "pcre_internal.h" diff --git a/ext/pcre/pcrelib/pcre_study.c b/ext/pcre/pcrelib/pcre_study.c index 8c82d1ce61..02e0c5288c 100644 --- a/ext/pcre/pcrelib/pcre_study.c +++ b/ext/pcre/pcrelib/pcre_study.c @@ -42,7 +42,7 @@ POSSIBILITY OF SUCH DAMAGE. supporting functions. */ -#include +#include "config.h" #include "pcre_internal.h" @@ -525,7 +525,8 @@ code = (uschar *)re + re->name_table_offset + a multiline pattern that matches only at "line starts", no further processing at present. */ -if ((re->options & (PCRE_ANCHORED|PCRE_FIRSTSET|PCRE_STARTLINE)) != 0) +if ((re->options & PCRE_ANCHORED) != 0 || + (re->flags & (PCRE_FIRSTSET|PCRE_STARTLINE)) != 0) return NULL; /* Set the character tables in the block that is passed around */ diff --git a/ext/pcre/pcrelib/pcre_tables.c b/ext/pcre/pcrelib/pcre_tables.c index 95d166975f..a3f28621c2 100644 --- a/ext/pcre/pcrelib/pcre_tables.c +++ b/ext/pcre/pcrelib/pcre_tables.c @@ -44,7 +44,7 @@ uses macros to change their names from _pcre_xxx to xxxx, thereby avoiding name clashes with the library. */ -#include +#include "config.h" #include "pcre_internal.h" @@ -85,115 +85,228 @@ const uschar _pcre_utf8_table4[] = { 2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2, 3,3,3,3,3,3,3,3,4,4,4,4,5,5,5,5 }; -/* This table translates Unicode property names into type and code values. It -is searched by binary chop, so must be in collating sequence of name. */ +/* The pcre_utt[] table below translates Unicode property names into type and +code values. It is searched by binary chop, so must be in collating sequence of +name. Originally, the table contained pointers to the name strings in the first +field of each entry. However, that leads to a large number of relocations when +a shared library is dynamically loaded. A significant reduction is made by +putting all the names into a single, large string and then using offsets in the +table itself. Maintenance is more error-prone, but frequent changes to this +data is unlikely. */ + +const char _pcre_utt_names[] = + "Any\0" + "Arabic\0" + "Armenian\0" + "Balinese\0" + "Bengali\0" + "Bopomofo\0" + "Braille\0" + "Buginese\0" + "Buhid\0" + "C\0" + "Canadian_Aboriginal\0" + "Cc\0" + "Cf\0" + "Cherokee\0" + "Cn\0" + "Co\0" + "Common\0" + "Coptic\0" + "Cs\0" + "Cuneiform\0" + "Cypriot\0" + "Cyrillic\0" + "Deseret\0" + "Devanagari\0" + "Ethiopic\0" + "Georgian\0" + "Glagolitic\0" + "Gothic\0" + "Greek\0" + "Gujarati\0" + "Gurmukhi\0" + "Han\0" + "Hangul\0" + "Hanunoo\0" + "Hebrew\0" + "Hiragana\0" + "Inherited\0" + "Kannada\0" + "Katakana\0" + "Kharoshthi\0" + "Khmer\0" + "L\0" + "L&\0" + "Lao\0" + "Latin\0" + "Limbu\0" + "Linear_B\0" + "Ll\0" + "Lm\0" + "Lo\0" + "Lt\0" + "Lu\0" + "M\0" + "Malayalam\0" + "Mc\0" + "Me\0" + "Mn\0" + "Mongolian\0" + "Myanmar\0" + "N\0" + "Nd\0" + "New_Tai_Lue\0" + "Nko\0" + "Nl\0" + "No\0" + "Ogham\0" + "Old_Italic\0" + "Old_Persian\0" + "Oriya\0" + "Osmanya\0" + "P\0" + "Pc\0" + "Pd\0" + "Pe\0" + "Pf\0" + "Phags_Pa\0" + "Phoenician\0" + "Pi\0" + "Po\0" + "Ps\0" + "Runic\0" + "S\0" + "Sc\0" + "Shavian\0" + "Sinhala\0" + "Sk\0" + "Sm\0" + "So\0" + "Syloti_Nagri\0" + "Syriac\0" + "Tagalog\0" + "Tagbanwa\0" + "Tai_Le\0" + "Tamil\0" + "Telugu\0" + "Thaana\0" + "Thai\0" + "Tibetan\0" + "Tifinagh\0" + "Ugaritic\0" + "Yi\0" + "Z\0" + "Zl\0" + "Zp\0" + "Zs\0"; const ucp_type_table _pcre_utt[] = { - { "Any", PT_ANY, 0 }, - { "Arabic", PT_SC, ucp_Arabic }, - { "Armenian", PT_SC, ucp_Armenian }, - { "Balinese", PT_SC, ucp_Balinese }, - { "Bengali", PT_SC, ucp_Bengali }, - { "Bopomofo", PT_SC, ucp_Bopomofo }, - { "Braille", PT_SC, ucp_Braille }, - { "Buginese", PT_SC, ucp_Buginese }, - { "Buhid", PT_SC, ucp_Buhid }, - { "C", PT_GC, ucp_C }, - { "Canadian_Aboriginal", PT_SC, ucp_Canadian_Aboriginal }, - { "Cc", PT_PC, ucp_Cc }, - { "Cf", PT_PC, ucp_Cf }, - { "Cherokee", PT_SC, ucp_Cherokee }, - { "Cn", PT_PC, ucp_Cn }, - { "Co", PT_PC, ucp_Co }, - { "Common", PT_SC, ucp_Common }, - { "Coptic", PT_SC, ucp_Coptic }, - { "Cs", PT_PC, ucp_Cs }, - { "Cuneiform", PT_SC, ucp_Cuneiform }, - { "Cypriot", PT_SC, ucp_Cypriot }, - { "Cyrillic", PT_SC, ucp_Cyrillic }, - { "Deseret", PT_SC, ucp_Deseret }, - { "Devanagari", PT_SC, ucp_Devanagari }, - { "Ethiopic", PT_SC, ucp_Ethiopic }, - { "Georgian", PT_SC, ucp_Georgian }, - { "Glagolitic", PT_SC, ucp_Glagolitic }, - { "Gothic", PT_SC, ucp_Gothic }, - { "Greek", PT_SC, ucp_Greek }, - { "Gujarati", PT_SC, ucp_Gujarati }, - { "Gurmukhi", PT_SC, ucp_Gurmukhi }, - { "Han", PT_SC, ucp_Han }, - { "Hangul", PT_SC, ucp_Hangul }, - { "Hanunoo", PT_SC, ucp_Hanunoo }, - { "Hebrew", PT_SC, ucp_Hebrew }, - { "Hiragana", PT_SC, ucp_Hiragana }, - { "Inherited", PT_SC, ucp_Inherited }, - { "Kannada", PT_SC, ucp_Kannada }, - { "Katakana", PT_SC, ucp_Katakana }, - { "Kharoshthi", PT_SC, ucp_Kharoshthi }, - { "Khmer", PT_SC, ucp_Khmer }, - { "L", PT_GC, ucp_L }, - { "L&", PT_LAMP, 0 }, - { "Lao", PT_SC, ucp_Lao }, - { "Latin", PT_SC, ucp_Latin }, - { "Limbu", PT_SC, ucp_Limbu }, - { "Linear_B", PT_SC, ucp_Linear_B }, - { "Ll", PT_PC, ucp_Ll }, - { "Lm", PT_PC, ucp_Lm }, - { "Lo", PT_PC, ucp_Lo }, - { "Lt", PT_PC, ucp_Lt }, - { "Lu", PT_PC, ucp_Lu }, - { "M", PT_GC, ucp_M }, - { "Malayalam", PT_SC, ucp_Malayalam }, - { "Mc", PT_PC, ucp_Mc }, - { "Me", PT_PC, ucp_Me }, - { "Mn", PT_PC, ucp_Mn }, - { "Mongolian", PT_SC, ucp_Mongolian }, - { "Myanmar", PT_SC, ucp_Myanmar }, - { "N", PT_GC, ucp_N }, - { "Nd", PT_PC, ucp_Nd }, - { "New_Tai_Lue", PT_SC, ucp_New_Tai_Lue }, - { "Nko", PT_SC, ucp_Nko }, - { "Nl", PT_PC, ucp_Nl }, - { "No", PT_PC, ucp_No }, - { "Ogham", PT_SC, ucp_Ogham }, - { "Old_Italic", PT_SC, ucp_Old_Italic }, - { "Old_Persian", PT_SC, ucp_Old_Persian }, - { "Oriya", PT_SC, ucp_Oriya }, - { "Osmanya", PT_SC, ucp_Osmanya }, - { "P", PT_GC, ucp_P }, - { "Pc", PT_PC, ucp_Pc }, - { "Pd", PT_PC, ucp_Pd }, - { "Pe", PT_PC, ucp_Pe }, - { "Pf", PT_PC, ucp_Pf }, - { "Phags_Pa", PT_SC, ucp_Phags_Pa }, - { "Phoenician", PT_SC, ucp_Phoenician }, - { "Pi", PT_PC, ucp_Pi }, - { "Po", PT_PC, ucp_Po }, - { "Ps", PT_PC, ucp_Ps }, - { "Runic", PT_SC, ucp_Runic }, - { "S", PT_GC, ucp_S }, - { "Sc", PT_PC, ucp_Sc }, - { "Shavian", PT_SC, ucp_Shavian }, - { "Sinhala", PT_SC, ucp_Sinhala }, - { "Sk", PT_PC, ucp_Sk }, - { "Sm", PT_PC, ucp_Sm }, - { "So", PT_PC, ucp_So }, - { "Syloti_Nagri", PT_SC, ucp_Syloti_Nagri }, - { "Syriac", PT_SC, ucp_Syriac }, - { "Tagalog", PT_SC, ucp_Tagalog }, - { "Tagbanwa", PT_SC, ucp_Tagbanwa }, - { "Tai_Le", PT_SC, ucp_Tai_Le }, - { "Tamil", PT_SC, ucp_Tamil }, - { "Telugu", PT_SC, ucp_Telugu }, - { "Thaana", PT_SC, ucp_Thaana }, - { "Thai", PT_SC, ucp_Thai }, - { "Tibetan", PT_SC, ucp_Tibetan }, - { "Tifinagh", PT_SC, ucp_Tifinagh }, - { "Ugaritic", PT_SC, ucp_Ugaritic }, - { "Yi", PT_SC, ucp_Yi }, - { "Z", PT_GC, ucp_Z }, - { "Zl", PT_PC, ucp_Zl }, - { "Zp", PT_PC, ucp_Zp }, - { "Zs", PT_PC, ucp_Zs } + { 0, PT_ANY, 0 }, + { 4, PT_SC, ucp_Arabic }, + { 11, PT_SC, ucp_Armenian }, + { 20, PT_SC, ucp_Balinese }, + { 29, PT_SC, ucp_Bengali }, + { 37, PT_SC, ucp_Bopomofo }, + { 46, PT_SC, ucp_Braille }, + { 54, PT_SC, ucp_Buginese }, + { 63, PT_SC, ucp_Buhid }, + { 69, PT_GC, ucp_C }, + { 71, PT_SC, ucp_Canadian_Aboriginal }, + { 91, PT_PC, ucp_Cc }, + { 94, PT_PC, ucp_Cf }, + { 97, PT_SC, ucp_Cherokee }, + { 106, PT_PC, ucp_Cn }, + { 109, PT_PC, ucp_Co }, + { 112, PT_SC, ucp_Common }, + { 119, PT_SC, ucp_Coptic }, + { 126, PT_PC, ucp_Cs }, + { 129, PT_SC, ucp_Cuneiform }, + { 139, PT_SC, ucp_Cypriot }, + { 147, PT_SC, ucp_Cyrillic }, + { 156, PT_SC, ucp_Deseret }, + { 164, PT_SC, ucp_Devanagari }, + { 175, PT_SC, ucp_Ethiopic }, + { 184, PT_SC, ucp_Georgian }, + { 193, PT_SC, ucp_Glagolitic }, + { 204, PT_SC, ucp_Gothic }, + { 211, PT_SC, ucp_Greek }, + { 217, PT_SC, ucp_Gujarati }, + { 226, PT_SC, ucp_Gurmukhi }, + { 235, PT_SC, ucp_Han }, + { 239, PT_SC, ucp_Hangul }, + { 246, PT_SC, ucp_Hanunoo }, + { 254, PT_SC, ucp_Hebrew }, + { 261, PT_SC, ucp_Hiragana }, + { 270, PT_SC, ucp_Inherited }, + { 280, PT_SC, ucp_Kannada }, + { 288, PT_SC, ucp_Katakana }, + { 297, PT_SC, ucp_Kharoshthi }, + { 308, PT_SC, ucp_Khmer }, + { 314, PT_GC, ucp_L }, + { 316, PT_LAMP, 0 }, + { 319, PT_SC, ucp_Lao }, + { 323, PT_SC, ucp_Latin }, + { 329, PT_SC, ucp_Limbu }, + { 335, PT_SC, ucp_Linear_B }, + { 344, PT_PC, ucp_Ll }, + { 347, PT_PC, ucp_Lm }, + { 350, PT_PC, ucp_Lo }, + { 353, PT_PC, ucp_Lt }, + { 356, PT_PC, ucp_Lu }, + { 359, PT_GC, ucp_M }, + { 361, PT_SC, ucp_Malayalam }, + { 371, PT_PC, ucp_Mc }, + { 374, PT_PC, ucp_Me }, + { 377, PT_PC, ucp_Mn }, + { 380, PT_SC, ucp_Mongolian }, + { 390, PT_SC, ucp_Myanmar }, + { 398, PT_GC, ucp_N }, + { 400, PT_PC, ucp_Nd }, + { 403, PT_SC, ucp_New_Tai_Lue }, + { 415, PT_SC, ucp_Nko }, + { 419, PT_PC, ucp_Nl }, + { 422, PT_PC, ucp_No }, + { 425, PT_SC, ucp_Ogham }, + { 431, PT_SC, ucp_Old_Italic }, + { 442, PT_SC, ucp_Old_Persian }, + { 454, PT_SC, ucp_Oriya }, + { 460, PT_SC, ucp_Osmanya }, + { 468, PT_GC, ucp_P }, + { 470, PT_PC, ucp_Pc }, + { 473, PT_PC, ucp_Pd }, + { 476, PT_PC, ucp_Pe }, + { 479, PT_PC, ucp_Pf }, + { 482, PT_SC, ucp_Phags_Pa }, + { 491, PT_SC, ucp_Phoenician }, + { 502, PT_PC, ucp_Pi }, + { 505, PT_PC, ucp_Po }, + { 508, PT_PC, ucp_Ps }, + { 511, PT_SC, ucp_Runic }, + { 517, PT_GC, ucp_S }, + { 519, PT_PC, ucp_Sc }, + { 522, PT_SC, ucp_Shavian }, + { 530, PT_SC, ucp_Sinhala }, + { 538, PT_PC, ucp_Sk }, + { 541, PT_PC, ucp_Sm }, + { 544, PT_PC, ucp_So }, + { 547, PT_SC, ucp_Syloti_Nagri }, + { 560, PT_SC, ucp_Syriac }, + { 567, PT_SC, ucp_Tagalog }, + { 575, PT_SC, ucp_Tagbanwa }, + { 584, PT_SC, ucp_Tai_Le }, + { 591, PT_SC, ucp_Tamil }, + { 597, PT_SC, ucp_Telugu }, + { 604, PT_SC, ucp_Thaana }, + { 611, PT_SC, ucp_Thai }, + { 616, PT_SC, ucp_Tibetan }, + { 624, PT_SC, ucp_Tifinagh }, + { 633, PT_SC, ucp_Ugaritic }, + { 642, PT_SC, ucp_Yi }, + { 645, PT_GC, ucp_Z }, + { 647, PT_PC, ucp_Zl }, + { 650, PT_PC, ucp_Zp }, + { 653, PT_PC, ucp_Zs } }; const int _pcre_utt_size = sizeof(_pcre_utt)/sizeof(ucp_type_table); diff --git a/ext/pcre/pcrelib/pcre_try_flipped.c b/ext/pcre/pcrelib/pcre_try_flipped.c index cd7d21eccc..9868ff8f48 100644 --- a/ext/pcre/pcrelib/pcre_try_flipped.c +++ b/ext/pcre/pcrelib/pcre_try_flipped.c @@ -43,7 +43,7 @@ see if it was compiled with the opposite endianness. If so, it uses an auxiliary local function to flip the appropriate bytes. */ -#include +#include "config.h" #include "pcre_internal.h" @@ -106,6 +106,7 @@ if (byteflip(re->magic_number, sizeof(re->magic_number)) != MAGIC_NUMBER) *internal_re = *re; /* To copy other fields */ internal_re->size = byteflip(re->size, sizeof(re->size)); internal_re->options = byteflip(re->options, sizeof(re->options)); +internal_re->flags = (pcre_uint16)byteflip(re->flags, sizeof(re->flags)); internal_re->top_bracket = (pcre_uint16)byteflip(re->top_bracket, sizeof(re->top_bracket)); internal_re->top_backref = diff --git a/ext/pcre/pcrelib/pcre_ucp_searchfuncs.c b/ext/pcre/pcrelib/pcre_ucp_searchfuncs.c index 95d42cf7cd..b40092eefb 100644 --- a/ext/pcre/pcrelib/pcre_ucp_searchfuncs.c +++ b/ext/pcre/pcrelib/pcre_ucp_searchfuncs.c @@ -41,7 +41,7 @@ POSSIBILITY OF SUCH DAMAGE. /* This module contains code for searching the table of Unicode character properties. */ -#include +#include "config.h" #include "pcre_internal.h" diff --git a/ext/pcre/pcrelib/pcre_valid_utf8.c b/ext/pcre/pcrelib/pcre_valid_utf8.c index 223e740857..4c5ef69c93 100644 --- a/ext/pcre/pcrelib/pcre_valid_utf8.c +++ b/ext/pcre/pcrelib/pcre_valid_utf8.c @@ -42,7 +42,7 @@ POSSIBILITY OF SUCH DAMAGE. strings. */ -#include +#include "config.h" #include "pcre_internal.h" @@ -60,7 +60,7 @@ an invalid string are then undefined. Originally, this function checked according to RFC 2279, allowing for values in the range 0 to 0x7fffffff, up to 6 bytes long, but ensuring that they were in the canonical format. Once somebody had pointed out RFC 3629 to me (it -obsoletes 2279), additional restrictions were applies. The values are now +obsoletes 2279), additional restrictions were applied. The values are now limited to be between 0 and 0x0010ffff, no more than 4 bytes long, and the subrange 0xd000 to 0xdfff is excluded. diff --git a/ext/pcre/pcrelib/pcre_version.c b/ext/pcre/pcrelib/pcre_version.c index 865453d9bc..9efc852778 100644 --- a/ext/pcre/pcrelib/pcre_version.c +++ b/ext/pcre/pcrelib/pcre_version.c @@ -42,7 +42,7 @@ POSSIBILITY OF SUCH DAMAGE. string that identifies the PCRE version that is in use. */ -#include +#include "config.h" #include "pcre_internal.h" diff --git a/ext/pcre/pcrelib/pcre_xclass.c b/ext/pcre/pcrelib/pcre_xclass.c index db5331b638..f24f10f9b2 100644 --- a/ext/pcre/pcrelib/pcre_xclass.c +++ b/ext/pcre/pcrelib/pcre_xclass.c @@ -43,7 +43,7 @@ class (one that contains characters whose values are > 255). It is used by both pcre_exec() and pcre_def_exec(). */ -#include +#include "config.h" #include "pcre_internal.h" diff --git a/ext/pcre/pcrelib/pcregrep.c b/ext/pcre/pcrelib/pcregrep.c index 29338d1599..d6e559a7bb 100644 --- a/ext/pcre/pcrelib/pcregrep.c +++ b/ext/pcre/pcrelib/pcregrep.c @@ -37,7 +37,7 @@ POSSIBILITY OF SUCH DAMAGE. ----------------------------------------------------------------------------- */ -#include +#include "config.h" #include #include @@ -53,7 +53,15 @@ POSSIBILITY OF SUCH DAMAGE. #include #endif -#include +#ifdef SUPPORT_LIBZ +#include +#endif + +#ifdef SUPPORT_LIBBZ2 +#include +#endif + +#include "pcre.h" #define FALSE 0 #define TRUE 1 @@ -74,6 +82,10 @@ all values greater than FN_DEFAULT. */ enum { FN_NONE, FN_DEFAULT, FN_ONLY, FN_NOMATCH_ONLY, FN_FORCE }; +/* File reading styles */ + +enum { FR_PLAIN, FR_LIBZ, FR_LIBBZ2 }; + /* Actions for the -d and -D options */ enum { dee_READ, dee_SKIP, dee_RECURSE }; @@ -140,8 +152,10 @@ static int process_options = 0; static BOOL count_only = FALSE; static BOOL do_colour = FALSE; +static BOOL file_offsets = FALSE; static BOOL hyphenpending = FALSE; static BOOL invert = FALSE; +static BOOL line_offsets = FALSE; static BOOL multiline = FALSE; static BOOL number = FALSE; static BOOL only_matching = FALSE; @@ -172,6 +186,8 @@ used to identify them. */ #define N_LABEL (-5) #define N_LOCALE (-6) #define N_NULL (-7) +#define N_LOFFSETS (-8) +#define N_FOFFSETS (-9) static option_item optionlist[] = { { OP_NODATA, N_NULL, NULL, "", " terminate options" }, @@ -187,15 +203,17 @@ static option_item optionlist[] = { { OP_PATLIST, 'e', NULL, "regex(p)", "specify pattern (may be used more than once)" }, { OP_NODATA, 'F', NULL, "fixed_strings", "patterns are sets of newline-separated strings" }, { OP_STRING, 'f', &pattern_filename, "file=path", "read patterns from file" }, + { OP_NODATA, N_FOFFSETS, NULL, "file-offsets", "output file offsets, not text" }, { OP_NODATA, 'H', NULL, "with-filename", "force the prefixing filename on output" }, { OP_NODATA, 'h', NULL, "no-filename", "suppress the prefixing filename on output" }, { OP_NODATA, 'i', NULL, "ignore-case", "ignore case distinctions" }, { OP_NODATA, 'l', NULL, "files-with-matches", "print only FILE names containing matches" }, { OP_NODATA, 'L', NULL, "files-without-match","print only FILE names not containing matches" }, { OP_STRING, N_LABEL, &stdin_name, "label=name", "set name for standard input" }, + { OP_NODATA, N_LOFFSETS, NULL, "line-offsets", "output line numbers and offsets, not text" }, { OP_STRING, N_LOCALE, &locale, "locale=locale", "use the named locale" }, { OP_NODATA, 'M', NULL, "multiline", "run in multiline mode" }, - { OP_STRING, 'N', &newline, "newline=type", "specify newline type (CR, LF, CRLF, ANYCRLF or ANY)" }, + { OP_STRING, 'N', &newline, "newline=type", "set newline type (CR, LF, CRLF, ANYCRLF or ANY)" }, { OP_NODATA, 'n', NULL, "line-number", "print line number with output lines" }, { OP_NODATA, 'o', NULL, "only-matching", "show only the part of the line that matched" }, { OP_NODATA, 'q', NULL, "quiet", "suppress output, just set return code" }, @@ -314,8 +332,9 @@ return isatty(fileno(stdout)); /* I (Philip Hazel) have no means of testing this code. It was contributed by Lionel Fourquaux. David Burgess added a patch to define INVALID_FILE_ATTRIBUTES -when it did not exist. */ - +when it did not exist. David Byron added a patch that moved the #include of + to before the INVALID_FILE_ATTRIBUTES definition rather than after. +*/ #elif HAVE_WINDOWS_H @@ -325,12 +344,13 @@ when it did not exist. */ #ifndef WIN32_LEAN_AND_MEAN # define WIN32_LEAN_AND_MEAN #endif + +#include + #ifndef INVALID_FILE_ATTRIBUTES #define INVALID_FILE_ATTRIBUTES 0xFFFFFFFF #endif -#include - typedef struct directory_type { HANDLE handle; @@ -415,7 +435,7 @@ regular if they are not directories. */ int isregfile(char *filename) { -return !isdirectory(filename) +return !isdirectory(filename); } @@ -426,7 +446,7 @@ return !isdirectory(filename) static BOOL is_stdout_tty(void) { -FALSE; +return FALSE; } @@ -802,22 +822,27 @@ be in the middle third most of the time, so the bottom third is available for "before" context printing. Arguments: - in the fopened FILE stream + handle the fopened FILE stream for a normal file + the gzFile pointer when reading is via libz + the BZFILE pointer when reading is via libbz2 + frtype FR_PLAIN, FR_LIBZ, or FR_LIBBZ2 printname the file name if it is to be printed for each match or NULL if the file name is not to be printed it cannot be NULL if filenames[_nomatch]_only is set Returns: 0 if there was at least one match 1 otherwise (no matches) + 2 if there is a read error on a .bz2 file */ static int -pcregrep(FILE *in, char *printname) +pcregrep(void *handle, int frtype, char *printname) { int rc = 1; int linenumber = 1; int lastmatchnumber = 0; int count = 0; +int filepos = 0; int offsets[99]; char *lastmatchrestart = NULL; char buffer[3*MBUFTHIRD]; @@ -825,11 +850,46 @@ char *ptr = buffer; char *endptr; size_t bufflength; BOOL endhyphenpending = FALSE; +FILE *in = NULL; /* Ensure initialized */ + +#ifdef SUPPORT_LIBZ +gzFile ingz = NULL; +#endif + +#ifdef SUPPORT_LIBBZ2 +BZFILE *inbz2 = NULL; +#endif -/* Do the first read into the start of the buffer and set up the pointer to -end of what we have. */ -bufflength = fread(buffer, 1, 3*MBUFTHIRD, in); +/* Do the first read into the start of the buffer and set up the pointer to end +of what we have. In the case of libz, a non-zipped .gz file will be read as a +plain file. However, if a .bz2 file isn't actually bzipped, the first read will +fail. */ + +#ifdef SUPPORT_LIBZ +if (frtype == FR_LIBZ) + { + ingz = (gzFile)handle; + bufflength = gzread (ingz, buffer, 3*MBUFTHIRD); + } +else +#endif + +#ifdef SUPPORT_LIBBZ2 +if (frtype == FR_LIBBZ2) + { + inbz2 = (BZFILE *)handle; + bufflength = BZ2_bzread(inbz2, buffer, 3*MBUFTHIRD); + if ((int)bufflength < 0) return 2; /* Gotcha: bufflength is size_t; */ + } /* without the cast it is unsigned. */ +else +#endif + + { + in = (FILE *)handle; + bufflength = fread(buffer, 1, 3*MBUFTHIRD, in); + } + endptr = buffer + bufflength; /* Loop while the current pointer is not at the end of the file. For large @@ -842,6 +902,7 @@ while (ptr < endptr) int i, endlinelength; int mrc = 0; BOOL match = FALSE; + char *matchptr = ptr; char *t = ptr; size_t length, linelength; @@ -904,13 +965,17 @@ while (ptr < endptr) } #endif + /* We come back here after a match when the -o option (only_matching) is set, + in order to find any further matches in the same line. */ + + ONLY_MATCHING_RESTART: /* Run through all the patterns until one matches. Note that we don't include the final newline in the subject string. */ for (i = 0; i < pattern_count; i++) { - mrc = pcre_exec(pattern_list[i], hints_list[i], ptr, length, 0, 0, + mrc = pcre_exec(pattern_list[i], hints_list[i], matchptr, length, 0, 0, offsets, 99); if (mrc >= 0) { match = TRUE; break; } if (mrc != PCRE_ERROR_NOMATCH) @@ -918,7 +983,7 @@ while (ptr < endptr) fprintf(stderr, "pcregrep: pcre_exec() error %d while matching ", mrc); if (pattern_count > 1) fprintf(stderr, "pattern number %d to ", i+1); fprintf(stderr, "this line:\n"); - fwrite(ptr, 1, linelength, stderr); /* In case binary zero included */ + fwrite(matchptr, 1, linelength, stderr); /* In case binary zero included */ fprintf(stderr, "\n"); if (error_count == 0 && (mrc == PCRE_ERROR_MATCHLIMIT || mrc == PCRE_ERROR_RECURSIONLIMIT)) @@ -965,14 +1030,33 @@ while (ptr < endptr) else if (quiet) return 0; /* The --only-matching option prints just the substring that matched, and - does not pring any context. */ + the --file-offsets and --line-offsets options output offsets for the + matching substring (they both force --only-matching). None of these options + prints any context. Afterwards, adjust the start and length, and then jump + back to look for further matches in the same line. If we are in invert + mode, however, nothing is printed - this could be still useful because the + return code is set. */ else if (only_matching) { - if (printname != NULL) fprintf(stdout, "%s:", printname); - if (number) fprintf(stdout, "%d:", linenumber); - fwrite(ptr + offsets[0], 1, offsets[1] - offsets[0], stdout); - fprintf(stdout, "\n"); + if (!invert) + { + if (printname != NULL) fprintf(stdout, "%s:", printname); + if (number) fprintf(stdout, "%d:", linenumber); + if (line_offsets) + fprintf(stdout, "%d,%d", matchptr + offsets[0] - ptr, + offsets[1] - offsets[0]); + else if (file_offsets) + fprintf(stdout, "%d,%d", filepos + matchptr + offsets[0] - ptr, + offsets[1] - offsets[0]); + else + fwrite(matchptr + offsets[0], 1, offsets[1] - offsets[0], stdout); + fprintf(stdout, "\n"); + matchptr += offsets[1]; + length -= offsets[1]; + match = FALSE; + goto ONLY_MATCHING_RESTART; + } } /* This is the default case when none of the above options is set. We print @@ -1111,7 +1195,8 @@ while (ptr < endptr) fprintf(stdout, "%c[%sm", 0x1b, colour_string); fwrite(ptr + offsets[0], 1, offsets[1] - offsets[0], stdout); fprintf(stdout, "%c[00m", 0x1b); - fwrite(ptr + offsets[1], 1, linelength - offsets[1], stdout); + fwrite(ptr + offsets[1], 1, (linelength + endlinelength) - offsets[1], + stdout); } else fwrite(ptr, 1, linelength + endlinelength, stdout); } @@ -1145,9 +1230,11 @@ while (ptr < endptr) linelength = endmatch - ptr - ellength; } - /* Advance to after the newline and increment the line number. */ + /* Advance to after the newline and increment the line number. The file + offset to the current line is maintained in filepos. */ ptr += linelength + endlinelength; + filepos += linelength + endlinelength; linenumber++; /* If we haven't yet reached the end of the file (the buffer is full), and @@ -1169,7 +1256,23 @@ while (ptr < endptr) memmove(buffer, buffer + MBUFTHIRD, 2*MBUFTHIRD); ptr -= MBUFTHIRD; + +#ifdef SUPPORT_LIBZ + if (frtype == FR_LIBZ) + bufflength = 2*MBUFTHIRD + + gzread (ingz, buffer + 2*MBUFTHIRD, MBUFTHIRD); + else +#endif + +#ifdef SUPPORT_LIBBZ2 + if (frtype == FR_LIBBZ2) + bufflength = 2*MBUFTHIRD + + BZ2_bzread(inbz2, buffer + 2*MBUFTHIRD, MBUFTHIRD); + else +#endif + bufflength = 2*MBUFTHIRD + fread(buffer + 2*MBUFTHIRD, 1, MBUFTHIRD, in); + endptr = buffer + bufflength; /* Adjust any last match point */ @@ -1233,18 +1336,28 @@ grep_or_recurse(char *pathname, BOOL dir_recurse, BOOL only_one_at_top) { int rc = 1; int sep; -FILE *in; +int frtype; +int pathlen; +void *handle; +FILE *in = NULL; /* Ensure initialized */ + +#ifdef SUPPORT_LIBZ +gzFile ingz = NULL; +#endif + +#ifdef SUPPORT_LIBBZ2 +BZFILE *inbz2 = NULL; +#endif /* If the file name is "-" we scan stdin */ if (strcmp(pathname, "-") == 0) { - return pcregrep(stdin, + return pcregrep(stdin, FR_PLAIN, (filenames > FN_DEFAULT || (filenames == FN_DEFAULT && !only_one_at_top))? stdin_name : NULL); } - /* If the file is a directory, skip if skipping or if we are recursing, scan each file within it, subject to any include or exclude patterns that were set. The scanning code is localized so it can be made system-specific. */ @@ -1301,8 +1414,54 @@ skipping was not requested. The scan proceeds. If this is the first and only argument at top level, we don't show the file name, unless we are only showing the file name, or the filename was forced (-H). */ -in = fopen(pathname, "r"); -if (in == NULL) +pathlen = strlen(pathname); + +/* Open using zlib if it is supported and the file name ends with .gz. */ + +#ifdef SUPPORT_LIBZ +if (pathlen > 3 && strcmp(pathname + pathlen - 3, ".gz") == 0) + { + ingz = gzopen(pathname, "rb"); + if (ingz == NULL) + { + if (!silent) + fprintf(stderr, "pcregrep: Failed to open %s: %s\n", pathname, + strerror(errno)); + return 2; + } + handle = (void *)ingz; + frtype = FR_LIBZ; + } +else +#endif + +/* Otherwise open with bz2lib if it is supported and the name ends with .bz2. */ + +#ifdef SUPPORT_LIBBZ2 +if (pathlen > 4 && strcmp(pathname + pathlen - 4, ".bz2") == 0) + { + inbz2 = BZ2_bzopen(pathname, "rb"); + handle = (void *)inbz2; + frtype = FR_LIBBZ2; + } +else +#endif + +/* Otherwise use plain fopen(). The label is so that we can come back here if +an attempt to read a .bz2 file indicates that it really is a plain file. */ + +#ifdef SUPPORT_LIBBZ2 +PLAIN_FILE: +#endif + { + in = fopen(pathname, "r"); + handle = (void *)in; + frtype = FR_PLAIN; + } + +/* All the opening methods return errno when they fail. */ + +if (handle == NULL) { if (!silent) fprintf(stderr, "pcregrep: Failed to open %s: %s\n", pathname, @@ -1310,10 +1469,50 @@ if (in == NULL) return 2; } -rc = pcregrep(in, (filenames > FN_DEFAULT || +/* Now grep the file */ + +rc = pcregrep(handle, frtype, (filenames > FN_DEFAULT || (filenames == FN_DEFAULT && !only_one_at_top))? pathname : NULL); +/* Close in an appropriate manner. */ + +#ifdef SUPPORT_LIBZ +if (frtype == FR_LIBZ) + gzclose(ingz); +else +#endif + +/* If it is a .bz2 file and the result is 2, it means that the first attempt to +read failed. If the error indicates that the file isn't in fact bzipped, try +again as a normal file. */ + +#ifdef SUPPORT_LIBBZ2 +if (frtype == FR_LIBBZ2) + { + if (rc == 2) + { + int errnum; + const char *err = BZ2_bzerror(inbz2, &errnum); + if (errnum == BZ_DATA_ERROR_MAGIC) + { + BZ2_bzclose(inbz2); + goto PLAIN_FILE; + } + else if (!silent) + fprintf(stderr, "pcregrep: Failed to read %s using bzlib: %s\n", + pathname, err); + } + BZ2_bzclose(inbz2); + } +else +#endif + +/* Normal file close */ + fclose(in); + +/* Pass back the yield from pcregrep(). */ + return rc; } @@ -1334,7 +1533,8 @@ for (op = optionlist; op->one_char != 0; op++) if (op->one_char > 0) fprintf(stderr, "%c", op->one_char); } fprintf(stderr, "] [long options] [pattern] [files]\n"); -fprintf(stderr, "Type `pcregrep --help' for more information.\n"); +fprintf(stderr, "Type `pcregrep --help' for more information and the long " + "options.\n"); return rc; } @@ -1353,9 +1553,23 @@ option_item *op; printf("Usage: pcregrep [OPTION]... [PATTERN] [FILE1 FILE2 ...]\n"); printf("Search for PATTERN in each FILE or standard input.\n"); printf("PATTERN must be present if neither -e nor -f is used.\n"); -printf("\"-\" can be used as a file name to mean STDIN.\n\n"); -printf("Example: pcregrep -i 'hello.*world' menu.h main.c\n\n"); +printf("\"-\" can be used as a file name to mean STDIN.\n"); + +#ifdef SUPPORT_LIBZ +printf("Files whose names end in .gz are read using zlib.\n"); +#endif + +#ifdef SUPPORT_LIBBZ2 +printf("Files whose names end in .bz2 are read using bzlib2.\n"); +#endif +#if defined SUPPORT_LIBZ || defined SUPPORT_LIBBZ2 +printf("Other files and the standard input are read as plain files.\n\n"); +#else +printf("All files are read as plain files, without any interpretation.\n\n"); +#endif + +printf("Example: pcregrep -i 'hello.*world' menu.h main.c\n\n"); printf("Options:\n"); for (op = optionlist; op->one_char != 0; op++) @@ -1363,8 +1577,7 @@ for (op = optionlist; op->one_char != 0; op++) int n; char s[4]; if (op->one_char > 0) sprintf(s, "-%c,", op->one_char); else strcpy(s, " "); - printf(" %s --%s%n", s, op->long_name, &n); - n = 30 - n; + n = 30 - printf(" %s --%s", s, op->long_name); if (n < 1) n = 1; printf("%.*s%s\n", n, " ", op->help_text); } @@ -1389,7 +1602,9 @@ handle_option(int letter, int options) { switch(letter) { + case N_FOFFSETS: file_offsets = TRUE; break; case N_HELP: help(); exit(0); + case N_LOFFSETS: line_offsets = number = TRUE; break; case 'c': count_only = TRUE; break; case 'F': process_options |= PO_FIXED_STRINGS; break; case 'H': filenames = FN_FORCE; break; @@ -1826,6 +2041,19 @@ if (both_context > 0) if (before_context == 0) before_context = both_context; } +/* Only one of --only-matching, --file-offsets, or --line-offsets is permitted. +However, the latter two set the only_matching flag. */ + +if ((only_matching && (file_offsets || line_offsets)) || + (file_offsets && line_offsets)) + { + fprintf(stderr, "pcregrep: Cannot mix --only-matching, --file-offsets " + "and/or --line-offsets\n"); + exit(usage(2)); + } + +if (file_offsets || line_offsets) only_matching = TRUE; + /* If a locale has not been provided as an option, see if the LC_CTYPE or LC_ALL environment variable is set, and if so, use it. */ @@ -2063,7 +2291,7 @@ if (include_pattern != NULL) if (i >= argc) { - rc = pcregrep(stdin, (filenames > FN_DEFAULT)? stdin_name : NULL); + rc = pcregrep(stdin, FR_PLAIN, (filenames > FN_DEFAULT)? stdin_name : NULL); goto EXIT; } diff --git a/ext/pcre/pcrelib/pcreposix.c b/ext/pcre/pcrelib/pcreposix.c index 9c0adebb96..6f1f9c58a6 100644 --- a/ext/pcre/pcrelib/pcreposix.c +++ b/ext/pcre/pcrelib/pcreposix.c @@ -42,7 +42,7 @@ POSSIBILITY OF SUCH DAMAGE. functions. */ -#include +#include "config.h" /* Ensure that the PCREPOSIX_EXP_xxx macros are set appropriately for @@ -55,12 +55,11 @@ previously been set. */ # define PCREPOSIX_EXP_DEFN __declspec(dllexport) #endif -#include +#include "pcre.h" #include "pcre_internal.h" #include "pcreposix.h" - /* Table to translate PCRE compile time error codes into POSIX error codes. */ static const int eint[] = { @@ -123,7 +122,9 @@ static const int eint[] = { REG_INVARG, /* inconsistent NEWLINE options */ REG_BADPAT, /* \g is not followed followed by an (optionally braced) non-zero number */ REG_BADPAT, /* (?+ or (?- must be followed by a non-zero number */ - REG_BADPAT /* number is too big */ + REG_BADPAT, /* number is too big */ + REG_BADPAT, /* subpattern name expected */ + REG_BADPAT /* digit expected after (?+ */ }; /* Table of texts corresponding to POSIX error codes */ diff --git a/ext/pcre/pcrelib/testdata/grepoutput b/ext/pcre/pcrelib/testdata/grepoutput index d5506a1097..3241984c1c 100644 --- a/ext/pcre/pcrelib/testdata/grepoutput +++ b/ext/pcre/pcrelib/testdata/grepoutput @@ -358,10 +358,13 @@ after the binary zero ./testdata/grepinput:597:after the binary zero ---------------------------- Test 42 ------------------------------ 595:before +595:zero 596:zero 597:after +597:zero ---------------------------- Test 43 ------------------------------ 595:before +595:zero 596:zero 597:zero ---------------------------- Test 44 ------------------------------ @@ -385,3 +388,17 @@ PUT NEW DATA ABOVE THIS LINE. ---------------------------- Test 49 ------------------------------ ---------------------------- Test 50 ------------------------------ over the lazy dog. +---------------------------- Test 51 ------------------------------ +fox jumps +---------------------------- Test 52 ------------------------------ +36972,6 +36990,4 +37024,4 +37066,5 +37083,4 +---------------------------- Test 53 ------------------------------ +595:15,6 +595:33,4 +596:28,4 +597:15,5 +597:32,4 diff --git a/ext/pcre/pcrelib/testdata/testinput1 b/ext/pcre/pcrelib/testdata/testinput1 index 79c98fa7bd..91554ffc49 100644 --- a/ext/pcre/pcrelib/testdata/testinput1 +++ b/ext/pcre/pcrelib/testdata/testinput1 @@ -3421,11 +3421,6 @@ /((?m)^b)/ a\nb\nc\n -/(?(1)a|b)/ - -/(?(1)b|a)/ - a - /(x)?(?(1)a|b)/ *** Failers a @@ -4030,4 +4025,15 @@ /( (?(1)0|)* )/x abcd +/[[:abcd:xyz]]/ + a] + :] + +/[abc[:x\]pqr]/ + a + [ + : + ] + p + / End of testinput1 / diff --git a/ext/pcre/pcrelib/testdata/testinput2 b/ext/pcre/pcrelib/testdata/testinput2 index c9f1018a90..1a13fa8dd9 100644 --- a/ext/pcre/pcrelib/testdata/testinput2 +++ b/ext/pcre/pcrelib/testdata/testinput2 @@ -398,8 +398,6 @@ /(?(1?)a|b)/ -/(?(1)a|b|c)/ - /[a[:xyz:/ /(?<=x+)y/ @@ -568,15 +566,15 @@ /ab\d+/I -/a(?(1)b)/I +/a(?(1)b)(.)/I -/a(?(1)bag|big)/I +/a(?(1)bag|big)(.)/I -/a(?(1)bag|big)*/I +/a(?(1)bag|big)*(.)/I -/a(?(1)bag|big)+/I +/a(?(1)bag|big)+(.)/I -/a(?(1)b..|b..)/I +/a(?(1)b..|b..)(.)/I /ab\d{0}e/I @@ -977,13 +975,13 @@ /()a/I -/(?(1)ab|ac)/I +/(?(1)ab|ac)(.)/I -/(?(1)abz|acz)/I +/(?(1)abz|acz)(.)/I -/(?(1)abz)/I +/(?(1)abz)(.)/I -/(?(1)abz)123/I +/(?(1)abz)(1)23/I /(a)+/I @@ -1999,7 +1997,7 @@ a random value. /Ix /a/ -/^a\Rb/ +/^a\Rb/ a\nb a\rb a\r\nb @@ -2009,7 +2007,7 @@ a random value. /Ix ** Failers a\n\rb -/^a\R*b/ +/^a\R*b/ ab a\nb a\rb @@ -2020,7 +2018,7 @@ a random value. /Ix a\n\rb a\n\r\x85\x0cb -/^a\R+b/ +/^a\R+b/ a\nb a\rb a\r\nb @@ -2032,7 +2030,7 @@ a random value. /Ix ** Failers ab -/^a\R{1,3}b/ +/^a\R{1,3}b/ a\nb a\n\rb a\n\r\x85b @@ -2044,7 +2042,7 @@ a random value. /Ix a\n\n\n\rb a\r -/^a[\R]b/ +/^a[\R]b/ aRb ** Failers a\nb @@ -2190,8 +2188,8 @@ a random value. /Ix /((?(-2)a))/BZ -/^(?(+1)X|Y)/BZ - Y +/^(?(+1)X|Y)(.)/BZ + Y! /(foo)\Kbar/ foobar @@ -2464,4 +2462,131 @@ a random value. /Ix a\r\nb a\x85b +/a\Rb/I + a\rb + a\nb + a\r\nb + ** Failers + a\x85b + a\x0bb + +/a\Rb/I + a\rb + a\nb + a\r\nb + a\x85b + a\x0bb + ** Failers + a\x85b\ + a\x0bb\ + +/a\R?b/I + a\rb + a\nb + a\r\nb + ** Failers + a\x85b + a\x0bb + +/a\R?b/I + a\rb + a\nb + a\r\nb + a\x85b + a\x0bb + ** Failers + a\x85b\ + a\x0bb\ + +/a\R{2,4}b/I + a\r\n\nb + a\n\r\rb + a\r\n\r\n\r\n\r\nb + ** Failers + a\x85\85b + a\x0b\0bb + +/a\R{2,4}b/I + a\r\rb + a\n\n\nb + a\r\n\n\r\rb + a\x85\85b + a\x0b\0bb + ** Failers + a\r\r\r\r\rb + a\x85\85b\ + a\x0b\0bb\ + +/(*BSR_ANYCRLF)a\Rb/I + a\nb + a\rb + +/(*BSR_UNICODE)a\Rb/I + a\x85b + +/(*BSR_ANYCRLF)(*CRLF)a\Rb/I + a\nb + a\rb + +/(*CRLF)(*BSR_UNICODE)a\Rb/I + a\x85b + +/(*CRLF)(*BSR_ANYCRLF)(*CR)ab/I + +/(?)(?&)/ + +/(?)(?&a)/ + +/(?)(?&aaaaaaaaaaaaaaaaaaaaaaa)/ + +/(?+-a)/ + +/(?-+a)/ + +/(?(-1))/ + +/(?(+10))/ + +/(?(10))/ + +/(?(+2))()()/ + +/(?(2))()()/ + +/\k''/ + +/\k<>/ + +/\k{}/ + +/(?P=)/ + +/(?P>)/ + +/(?!\w)(?R)/ + +/(?=\w)(?R)/ + +/(? abc1\x0a abc2\x0b abc3\x0c abc4\x0d abc5\x0d\x0a abc6\x{0085} abc7\x{2028} abc8\x{2029} abc9 -/^a\Rb/8 +/^a\Rb/8 a\nb a\rb a\r\nb @@ -324,7 +324,7 @@ can't tell the difference.) --/ ** Failers a\n\rb -/^a\R*b/8 +/^a\R*b/8 ab a\nb a\rb @@ -335,7 +335,7 @@ can't tell the difference.) --/ a\n\rb a\n\r\x{85}\x0cb -/^a\R+b/8 +/^a\R+b/8 a\nb a\rb a\r\nb @@ -347,7 +347,7 @@ can't tell the difference.) --/ ** Failers ab -/^a\R{1,3}b/8 +/^a\R{1,3}b/8 a\nb a\n\rb a\n\r\x{85}b @@ -417,4 +417,48 @@ can't tell the difference.) --/ \x{7fffffff} \x{7fffffff}\? +/a\Rb/I8 + a\rb + a\nb + a\r\nb + ** Failers + a\x{85}b + a\x0bb + +/a\Rb/I8 + a\rb + a\nb + a\r\nb + a\x{85}b + a\x0bb + ** Failers + a\x{85}b\ + a\x0bb\ + +/a\R?b/I8 + a\rb + a\nb + a\r\nb + ** Failers + a\x{85}b + a\x0bb + +/a\R?b/I8 + a\rb + a\nb + a\r\nb + a\x{85}b + a\x0bb + ** Failers + a\x{85}b\ + a\x0bb\ + +/.*a.*=.b.*/8 + QQQ\x{2029}ABCaXYZ=!bPQR + ** Failers + a\x{2029}b + \x61\xe2\x80\xa9\x62 + +/[[:a\x{100}b:]]/8 + / End of testinput5 / diff --git a/ext/pcre/pcrelib/testdata/testinput6 b/ext/pcre/pcrelib/testdata/testinput6 index 53d2b328ff..0204a7acae 100644 --- a/ext/pcre/pcrelib/testdata/testinput6 +++ b/ext/pcre/pcrelib/testdata/testinput6 @@ -832,4 +832,79 @@ was broken in all cases./ /(\p{Yi}{0,3}+\277)*/ +/^[\p{Arabic}]/8 + \x{60e} + \x{656} + \x{657} + \x{658} + \x{659} + \x{65a} + \x{65b} + \x{65c} + \x{65d} + \x{65e} + \x{66a} + \x{6e9} + \x{6ef} + \x{6fa} + ** Failers + \x{600} + \x{650} + \x{651} + \x{652} + \x{653} + \x{654} + \x{655} + \x{65f} + +/^\p{Cyrillic}/8 + \x{1d2b} + +/^\p{Common}/8 + \x{589} + \x{60c} + \x{61f} + \x{964} + \x{965} + \x{970} + +/^\p{Inherited}/8 + \x{64b} + \x{654} + \x{655} + \x{200c} + ** Failers + \x{64a} + \x{656} + +/^\p{Shavian}/8 + \x{10450} + \x{1047f} + +/^\p{Deseret}/8 + \x{10400} + \x{1044f} + +/^\p{Osmanya}/8 + \x{10480} + \x{1049d} + \x{104a0} + \x{104a9} + ** Failers + \x{1049e} + \x{1049f} + \x{104aa} + +/\p{Zl}{2,3}+/8BZ + \xe2\x80\xa8\xe2\x80\xa8 + \x{2028}\x{2028}\x{2028} + +/\p{Zl}/8BZ + +/\p{Lu}{3}+/8BZ + +/\pL{2}+/8BZ + +/\p{Cc}{2}+/8BZ + / End of testinput6 / diff --git a/ext/pcre/pcrelib/testdata/testinput7 b/ext/pcre/pcrelib/testdata/testinput7 index 76524b725a..221bc938b1 100644 --- a/ext/pcre/pcrelib/testdata/testinput7 +++ b/ext/pcre/pcrelib/testdata/testinput7 @@ -4156,7 +4156,7 @@ /abc.$/mgx abc1\x0a abc2\x0b abc3\x0c abc4\x0d abc5\x0d\x0a abc6\x85 abc7\x{2028} abc8\x{2029} abc9 -/^a\Rb/ +/^a\Rb/ a\nb a\rb a\r\nb @@ -4166,7 +4166,7 @@ ** Failers a\n\rb -/^a\R*b/ +/^a\R*b/ ab a\nb a\rb @@ -4177,7 +4177,7 @@ a\n\rb a\n\r\x85\x0cb -/^a\R+b/ +/^a\R+b/ a\nb a\rb a\r\nb @@ -4189,7 +4189,7 @@ ** Failers ab -/^a\R{1,3}b/ +/^a\R{1,3}b/ a\nb a\n\rb a\n\r\x85b @@ -4201,7 +4201,7 @@ a\n\n\n\rb a\r -/^a[\R]b/ +/^a[\R]b/ aRb ** Failers a\nb @@ -4310,4 +4310,59 @@ /(\r|\n)A/ \r\nA +/a\Rb/I + a\rb + a\nb + a\r\nb + ** Failers + a\x85b + a\x0bb + +/a\Rb/I + a\rb + a\nb + a\r\nb + a\x85b + a\x0bb + ** Failers + a\x85b\ + a\x0bb\ + +/a\R?b/I + a\rb + a\nb + a\r\nb + ** Failers + a\x85b + a\x0bb + +/a\R?b/I + a\rb + a\nb + a\r\nb + a\x85b + a\x0bb + ** Failers + a\x85b\ + a\x0bb\ + +/a\R{2,4}b/I + a\r\n\nb + a\n\r\rb + a\r\n\r\n\r\n\r\nb + ** Failers + a\x85\85b + a\x0b\0bb + +/a\R{2,4}b/I + a\r\rb + a\n\n\nb + a\r\n\n\r\rb + a\x85\85b + a\x0b\0bb + ** Failers + a\r\r\r\r\rb + a\x85\85b\ + a\x0b\0bb\ + / End of testinput7 / diff --git a/ext/pcre/pcrelib/testdata/testinput8 b/ext/pcre/pcrelib/testdata/testinput8 index 61e70e55ac..5bcfab5c08 100644 --- a/ext/pcre/pcrelib/testdata/testinput8 +++ b/ext/pcre/pcrelib/testdata/testinput8 @@ -543,7 +543,7 @@ /abc.$/mgx8 abc1\x0a abc2\x0b abc3\x0c abc4\x0d abc5\x0d\x0a abc6\x{0085} abc7\x{2028} abc8\x{2029} abc9 -/^a\Rb/8 +/^a\Rb/8 a\nb a\rb a\r\nb @@ -555,7 +555,7 @@ ** Failers a\n\rb -/^a\R*b/8 +/^a\R*b/8 ab a\nb a\rb @@ -566,7 +566,7 @@ a\n\rb a\n\r\x{85}\x0cb -/^a\R+b/8 +/^a\R+b/8 a\nb a\rb a\r\nb @@ -578,7 +578,7 @@ ** Failers ab -/^a\R{1,3}b/8 +/^a\R{1,3}b/8 a\nb a\n\rb a\n\r\x{85}b @@ -628,4 +628,40 @@ ** Failers \x09\x{200a}\x{a0}\x{2028}\x0b +/a\Rb/I8 + a\rb + a\nb + a\r\nb + ** Failers + a\x{85}b + a\x0bb + +/a\Rb/I8 + a\rb + a\nb + a\r\nb + a\x{85}b + a\x0bb + ** Failers + a\x{85}b\ + a\x0bb\ + +/a\R?b/I8 + a\rb + a\nb + a\r\nb + ** Failers + a\x{85}b + a\x0bb + +/a\R?b/I8 + a\rb + a\nb + a\r\nb + a\x{85}b + a\x0bb + ** Failers + a\x{85}b\ + a\x0bb\ + / End of testinput 8 / diff --git a/ext/pcre/pcrelib/testdata/testoutput1 b/ext/pcre/pcrelib/testdata/testoutput1 index 4c0e680d11..9b8b268edb 100644 --- a/ext/pcre/pcrelib/testdata/testoutput1 +++ b/ext/pcre/pcrelib/testdata/testoutput1 @@ -5551,12 +5551,6 @@ No match 0: b 1: b -/(?(1)a|b)/ - -/(?(1)b|a)/ - a - 0: a - /(x)?(?(1)a|b)/ *** Failers No match @@ -6593,4 +6587,22 @@ No match 0: 1: +/[[:abcd:xyz]]/ + a] + 0: a] + :] + 0: :] + +/[abc[:x\]pqr]/ + a + 0: a + [ + 0: [ + : + 0: : + ] + 0: ] + p + 0: p + / End of testinput1 / diff --git a/ext/pcre/pcrelib/testdata/testoutput2 b/ext/pcre/pcrelib/testdata/testoutput2 index a1c071d8b0..dba227f503 100644 --- a/ext/pcre/pcrelib/testdata/testoutput2 +++ b/ext/pcre/pcrelib/testdata/testoutput2 @@ -109,7 +109,7 @@ Failed: missing ) at offset 4 Failed: missing ) after comment at offset 7 /(?z)abc/ -Failed: unrecognized character after (? at offset 2 +Failed: unrecognized character after (? or (?- at offset 2 /.*b/I Capturing subpattern count = 0 @@ -166,7 +166,6 @@ Starting byte set: a b c d /(a|[^\dZ])/IS Capturing subpattern count = 1 -Contains explicit CR or LF match No options No first char No need char @@ -311,7 +310,7 @@ No match No match /ab(?z)cd/ -Failed: unrecognized character after (? at offset 4 +Failed: unrecognized character after (? or (?- at offset 4 /^abc|def/I Capturing subpattern count = 0 @@ -403,7 +402,6 @@ Failed: missing terminating ] for character class at offset 4 /[^aeiou ]{3,}/I Capturing subpattern count = 0 Partial matching not supported -Contains explicit CR or LF match No options No first char No need char @@ -948,26 +946,23 @@ Failed: missing ) at offset 4 Failed: unrecognized character after (?< at offset 3 /a(?{)b/ -Failed: unrecognized character after (? at offset 3 +Failed: unrecognized character after (? or (?- at offset 3 /a(?{{})b/ -Failed: unrecognized character after (? at offset 3 +Failed: unrecognized character after (? or (?- at offset 3 /a(?{}})b/ -Failed: unrecognized character after (? at offset 3 +Failed: unrecognized character after (? or (?- at offset 3 /a(?{"{"})b/ -Failed: unrecognized character after (? at offset 3 +Failed: unrecognized character after (? or (?- at offset 3 /a(?{"{"}})b/ -Failed: unrecognized character after (? at offset 3 +Failed: unrecognized character after (? or (?- at offset 3 /(?(1?)a|b)/ Failed: malformed number or name after (?( at offset 4 -/(?(1)a|b|c)/ -Failed: conditional group contains more than two branches at offset 10 - /[a[:xyz:/ Failed: missing terminating ] for character class at offset 8 @@ -1440,7 +1435,6 @@ Need char = 'a' /"([^\\"]+|\\.)*"/I Capturing subpattern count = 1 Partial matching not supported -Contains explicit CR or LF match No options First char = '"' Need char = '"' @@ -1602,32 +1596,32 @@ No options First char = 'a' Need char = 'b' -/a(?(1)b)/I -Capturing subpattern count = 0 +/a(?(1)b)(.)/I +Capturing subpattern count = 1 No options First char = 'a' No need char -/a(?(1)bag|big)/I -Capturing subpattern count = 0 +/a(?(1)bag|big)(.)/I +Capturing subpattern count = 1 No options First char = 'a' Need char = 'g' -/a(?(1)bag|big)*/I -Capturing subpattern count = 0 +/a(?(1)bag|big)*(.)/I +Capturing subpattern count = 1 No options First char = 'a' No need char -/a(?(1)bag|big)+/I -Capturing subpattern count = 0 +/a(?(1)bag|big)+(.)/I +Capturing subpattern count = 1 No options First char = 'a' Need char = 'g' -/a(?(1)b..|b..)/I -Capturing subpattern count = 0 +/a(?(1)b..|b..)(.)/I +Capturing subpattern count = 1 No options First char = 'a' Need char = 'b' @@ -1716,7 +1710,6 @@ Study returned NULL /Ix Capturing subpattern count = 0 Partial matching not supported -Contains explicit CR or LF match Options: extended First char = '(' Need char = ')' @@ -1746,7 +1739,6 @@ No match /\( ( (?>[^()]+) | (?R) )* \) /Ixg Capturing subpattern count = 1 Partial matching not supported -Contains explicit CR or LF match Options: extended First char = '(' Need char = ')' @@ -1762,7 +1754,6 @@ Need char = ')' /\( (?: (?>[^()]+) | (?R) ) \) /Ix Capturing subpattern count = 0 Partial matching not supported -Contains explicit CR or LF match Options: extended First char = '(' Need char = ')' @@ -1782,7 +1773,6 @@ No match /\( (?: (?>[^()]+) | (?R) )? \) /Ix Capturing subpattern count = 0 Partial matching not supported -Contains explicit CR or LF match Options: extended First char = '(' Need char = ')' @@ -1794,7 +1784,6 @@ Need char = ')' /\( ( (?>[^()]+) | (?R) )* \) /Ix Capturing subpattern count = 1 Partial matching not supported -Contains explicit CR or LF match Options: extended First char = '(' Need char = ')' @@ -1805,7 +1794,6 @@ Need char = ')' /\( ( ( (?>[^()]+) | (?R) )* ) \) /Ix Capturing subpattern count = 2 Partial matching not supported -Contains explicit CR or LF match Options: extended First char = '(' Need char = ')' @@ -1817,7 +1805,6 @@ Need char = ')' /\( (123)? ( ( (?>[^()]+) | (?R) )* ) \) /Ix Capturing subpattern count = 3 Partial matching not supported -Contains explicit CR or LF match Options: extended First char = '(' Need char = ')' @@ -1835,7 +1822,6 @@ Need char = ')' /\( ( (123)? ( (?>[^()]+) | (?R) )* ) \) /Ix Capturing subpattern count = 3 Partial matching not supported -Contains explicit CR or LF match Options: extended First char = '(' Need char = ')' @@ -1853,7 +1839,6 @@ Need char = ')' /\( (((((((((( ( (?>[^()]+) | (?R) )* )))))))))) \) /Ix Capturing subpattern count = 11 Partial matching not supported -Contains explicit CR or LF match Options: extended First char = '(' Need char = ')' @@ -1874,7 +1859,6 @@ Need char = ')' /\( ( ( (?>[^()<>]+) | ((?>[^()]+)) | (?R) )* ) \) /Ix Capturing subpattern count = 3 Partial matching not supported -Contains explicit CR or LF match Options: extended First char = '(' Need char = ')' @@ -1887,7 +1871,6 @@ Need char = ')' /\( ( ( (?>[^()]+) | ((?R)) )* ) \) /Ix Capturing subpattern count = 3 Partial matching not supported -Contains explicit CR or LF match Options: extended First char = '(' Need char = ')' @@ -1919,12 +1902,11 @@ No need char ------------------------------------------------------------------ Bra ^ - [\x00-/:-@[-`{-\xff] + [\x00-/:-@[-`{-\xff] (neg) Ket End ------------------------------------------------------------------ Capturing subpattern count = 0 -Contains explicit CR or LF match Options: anchored No first char No need char @@ -1946,12 +1928,11 @@ No need char ------------------------------------------------------------------ Bra ^ - [\x00-@[-`{-\xff] + [\x00-@[-`{-\xff] (neg) Ket End ------------------------------------------------------------------ Capturing subpattern count = 0 -Contains explicit CR or LF match Options: anchored No first char No need char @@ -1973,7 +1954,6 @@ Starting byte set: A B C D E F G H I J K L M N O P Q R S T U V W X Y Z End ------------------------------------------------------------------ Capturing subpattern count = 0 -Contains explicit CR or LF match Options: anchored No first char No need char @@ -1982,7 +1962,7 @@ No need char ------------------------------------------------------------------ Bra ^ - [\x80-\xff] + [\x80-\xff] (neg) Ket End ------------------------------------------------------------------ @@ -2008,12 +1988,11 @@ No need char ------------------------------------------------------------------ Bra ^ - [\x00-\x08\x0a-\x1f!-\xff] + [\x00-\x08\x0a-\x1f!-\xff] (neg) Ket End ------------------------------------------------------------------ Capturing subpattern count = 0 -Contains explicit CR or LF match Options: anchored No first char No need char @@ -2035,7 +2014,6 @@ Starting byte set: \x09 \x0a \x0b \x0c \x0d \x20 End ------------------------------------------------------------------ Capturing subpattern count = 0 -Contains explicit CR or LF match Options: anchored No first char No need char @@ -2114,7 +2092,6 @@ No need char End ------------------------------------------------------------------ Capturing subpattern count = 0 -Contains explicit CR or LF match Options: anchored No first char No need char @@ -2162,7 +2139,7 @@ No need char ------------------------------------------------------------------ Bra ^ - [ -~\x80-\xff] + [ -~\x80-\xff] (neg) Ket End ------------------------------------------------------------------ @@ -2175,12 +2152,11 @@ No need char ------------------------------------------------------------------ Bra ^ - [\x00-/12:-\xff] + [\x00-/12:-\xff] (neg) Ket End ------------------------------------------------------------------ Capturing subpattern count = 0 -Contains explicit CR or LF match Options: anchored No first char No need char @@ -2189,12 +2165,11 @@ No need char ------------------------------------------------------------------ Bra ^ - [\x00-\x08\x0a-\x1f!-\xff] + [\x00-\x08\x0a-\x1f!-\xff] (neg) Ket End ------------------------------------------------------------------ Capturing subpattern count = 0 -Contains explicit CR or LF match Options: anchored No first char No need char @@ -2758,7 +2733,7 @@ No need char /[\S]/DZ ------------------------------------------------------------------ Bra - [\x00-\x08\x0b\x0e-\x1f!-\xff] + [\x00-\x08\x0b\x0e-\x1f!-\xff] (neg) Ket End ------------------------------------------------------------------ @@ -3083,7 +3058,6 @@ Need char = 'b' /([^()]++|\([^()]*\))+/I Capturing subpattern count = 1 Partial matching not supported -Contains explicit CR or LF match No options No first char No need char @@ -3094,7 +3068,6 @@ No need char /\(([^()]++|\([^()]+\))+\)/I Capturing subpattern count = 1 Partial matching not supported -Contains explicit CR or LF match No options First char = '(' Need char = ')' @@ -3295,7 +3268,6 @@ No need char End ------------------------------------------------------------------ Capturing subpattern count = 0 -Contains explicit CR or LF match No options No first char No need char @@ -3308,7 +3280,6 @@ No need char End ------------------------------------------------------------------ Capturing subpattern count = 0 -Contains explicit CR or LF match No options No first char No need char @@ -3316,7 +3287,6 @@ No need char /< (?: (?(R) \d++ | [^<>]*+) | (?R)) * >/Ix Capturing subpattern count = 0 Partial matching not supported -Contains explicit CR or LF match Options: extended First char = '<' Need char = '>' @@ -3468,26 +3438,26 @@ No options No first char Need char = 'a' -/(?(1)ab|ac)/I -Capturing subpattern count = 0 +/(?(1)ab|ac)(.)/I +Capturing subpattern count = 1 No options First char = 'a' No need char -/(?(1)abz|acz)/I -Capturing subpattern count = 0 +/(?(1)abz|acz)(.)/I +Capturing subpattern count = 1 No options First char = 'a' Need char = 'z' -/(?(1)abz)/I -Capturing subpattern count = 0 +/(?(1)abz)(.)/I +Capturing subpattern count = 1 No options No first char No need char -/(?(1)abz)123/I -Capturing subpattern count = 0 +/(?(1)abz)(1)23/I +Capturing subpattern count = 1 No options No first char Need char = '3' @@ -3531,7 +3501,6 @@ Starting byte set: a b /[^a]/I Capturing subpattern count = 0 -Contains explicit CR or LF match No options No first char No need char @@ -3991,7 +3960,6 @@ Failed: recursive call could loop indefinitely at offset 16 /^([^()]|\((?1)*\))*$/I Capturing subpattern count = 1 -Contains explicit CR or LF match Options: anchored No first char No need char @@ -4011,7 +3979,6 @@ No match /^>abc>([^()]|\((?1)*\))*]*+) | (?2)) * >))/Ix Capturing subpattern count = 2 Partial matching not supported -Contains explicit CR or LF match Options: extended First char = '<' Need char = '>' @@ -5958,7 +5924,6 @@ Matched, but too many substrings /[^()]*(?:\((?R)\)[^()]*)*/I Capturing subpattern count = 0 Partial matching not supported -Contains explicit CR or LF match No options No first char No need char @@ -5972,7 +5937,6 @@ No need char /[^()]*(?:\((?>(?R))\)[^()]*)*/I Capturing subpattern count = 0 Partial matching not supported -Contains explicit CR or LF match No options No first char No need char @@ -5984,7 +5948,6 @@ No need char /[^()]*(?:\((?R)\))*[^()]*/I Capturing subpattern count = 0 Partial matching not supported -Contains explicit CR or LF match No options No first char No need char @@ -5996,7 +5959,6 @@ No need char /(?:\((?R)\))*[^()]*/I Capturing subpattern count = 0 Partial matching not supported -Contains explicit CR or LF match No options No first char No need char @@ -6010,7 +5972,6 @@ No need char /(?:\((?R)\))|[^()]*/I Capturing subpattern count = 0 Partial matching not supported -Contains explicit CR or LF match No options No first char No need char @@ -6205,6 +6166,7 @@ Named capturing subpatterns: A 2 A 3 Options: anchored dupnames +Duplicate name status changes No first char No need char a1b\CA @@ -7913,7 +7875,7 @@ No match /a/ Failed: inconsistent NEWLINE options at offset 0 -/^a\Rb/ +/^a\Rb/ a\nb 0: a\x0ab a\rb @@ -7931,7 +7893,7 @@ No match a\n\rb No match -/^a\R*b/ +/^a\R*b/ ab 0: ab a\nb @@ -7951,7 +7913,7 @@ No match a\n\r\x85\x0cb 0: a\x0a\x0d\x85\x0cb -/^a\R+b/ +/^a\R+b/ a\nb 0: a\x0ab a\rb @@ -7973,7 +7935,7 @@ No match ab No match -/^a\R{1,3}b/ +/^a\R{1,3}b/ a\nb 0: a\x0ab a\n\rb @@ -7995,7 +7957,7 @@ No match a\r No match -/^a[\R]b/ +/^a[\R]b/ aRb 0: aRb ** Failers @@ -8343,7 +8305,7 @@ Failed: reference to non-existent subpattern at offset 6 /((?(-2)a))/BZ Failed: reference to non-existent subpattern at offset 7 -/^(?(+1)X|Y)/BZ +/^(?(+1)X|Y)(.)/BZ ------------------------------------------------------------------ Bra ^ @@ -8353,11 +8315,15 @@ Failed: reference to non-existent subpattern at offset 7 Alt Y Ket + CBra 1 + Any + Ket Ket End ------------------------------------------------------------------ - Y - 0: Y + Y! + 0: Y! + 1: ! /(foo)\Kbar/ foobar @@ -9168,4 +9134,255 @@ No match a\x85b No match +/a\Rb/I +Capturing subpattern count = 0 +Options: bsr_anycrlf +First char = 'a' +Need char = 'b' + a\rb + 0: a\x0db + a\nb + 0: a\x0ab + a\r\nb + 0: a\x0d\x0ab + ** Failers +No match + a\x85b +No match + a\x0bb +No match + +/a\Rb/I +Capturing subpattern count = 0 +Options: bsr_unicode +First char = 'a' +Need char = 'b' + a\rb + 0: a\x0db + a\nb + 0: a\x0ab + a\r\nb + 0: a\x0d\x0ab + a\x85b + 0: a\x85b + a\x0bb + 0: a\x0bb + ** Failers +No match + a\x85b\ +No match + a\x0bb\ +No match + +/a\R?b/I +Capturing subpattern count = 0 +Options: bsr_anycrlf +First char = 'a' +Need char = 'b' + a\rb + 0: a\x0db + a\nb + 0: a\x0ab + a\r\nb + 0: a\x0d\x0ab + ** Failers +No match + a\x85b +No match + a\x0bb +No match + +/a\R?b/I +Capturing subpattern count = 0 +Options: bsr_unicode +First char = 'a' +Need char = 'b' + a\rb + 0: a\x0db + a\nb + 0: a\x0ab + a\r\nb + 0: a\x0d\x0ab + a\x85b + 0: a\x85b + a\x0bb + 0: a\x0bb + ** Failers +No match + a\x85b\ +No match + a\x0bb\ +No match + +/a\R{2,4}b/I +Capturing subpattern count = 0 +Partial matching not supported +Options: bsr_anycrlf +First char = 'a' +Need char = 'b' + a\r\n\nb + 0: a\x0d\x0a\x0ab + a\n\r\rb + 0: a\x0a\x0d\x0db + a\r\n\r\n\r\n\r\nb + 0: a\x0d\x0a\x0d\x0a\x0d\x0a\x0d\x0ab + ** Failers +No match + a\x85\85b +No match + a\x0b\0bb +No match + +/a\R{2,4}b/I +Capturing subpattern count = 0 +Partial matching not supported +Options: bsr_unicode +First char = 'a' +Need char = 'b' + a\r\rb + 0: a\x0d\x0db + a\n\n\nb + 0: a\x0a\x0a\x0ab + a\r\n\n\r\rb + 0: a\x0d\x0a\x0a\x0d\x0db + a\x85\85b +No match + a\x0b\0bb +No match + ** Failers +No match + a\r\r\r\r\rb +No match + a\x85\85b\ +No match + a\x0b\0bb\ +No match + +/(*BSR_ANYCRLF)a\Rb/I +Capturing subpattern count = 0 +Options: bsr_anycrlf +First char = 'a' +Need char = 'b' + a\nb + 0: a\x0ab + a\rb + 0: a\x0db + +/(*BSR_UNICODE)a\Rb/I +Capturing subpattern count = 0 +Options: bsr_unicode +First char = 'a' +Need char = 'b' + a\x85b + 0: a\x85b + +/(*BSR_ANYCRLF)(*CRLF)a\Rb/I +Capturing subpattern count = 0 +Options: bsr_anycrlf +Forced newline sequence: CRLF +First char = 'a' +Need char = 'b' + a\nb + 0: a\x0ab + a\rb + 0: a\x0db + +/(*CRLF)(*BSR_UNICODE)a\Rb/I +Capturing subpattern count = 0 +Options: bsr_unicode +Forced newline sequence: CRLF +First char = 'a' +Need char = 'b' + a\x85b + 0: a\x85b + +/(*CRLF)(*BSR_ANYCRLF)(*CR)ab/I +Capturing subpattern count = 0 +Options: bsr_anycrlf +Forced newline sequence: CR +First char = 'a' +Need char = 'b' + +/(?)(?&)/ +Failed: subpattern name expected at offset 9 + +/(?)(?&a)/ +Failed: reference to non-existent subpattern at offset 12 + +/(?)(?&aaaaaaaaaaaaaaaaaaaaaaa)/ +Failed: reference to non-existent subpattern at offset 32 + +/(?+-a)/ +Failed: digit expected after (?+ at offset 3 + +/(?-+a)/ +Failed: unrecognized character after (? or (?- at offset 3 + +/(?(-1))/ +Failed: reference to non-existent subpattern at offset 6 + +/(?(+10))/ +Failed: reference to non-existent subpattern at offset 7 + +/(?(10))/ +Failed: reference to non-existent subpattern at offset 6 + +/(?(+2))()()/ + +/(?(2))()()/ + +/\k''/ +Failed: subpattern name expected at offset 3 + +/\k<>/ +Failed: subpattern name expected at offset 3 + +/\k{}/ +Failed: subpattern name expected at offset 3 + +/(?P=)/ +Failed: subpattern name expected at offset 4 + +/(?P>)/ +Failed: subpattern name expected at offset 4 + +/(?!\w)(?R)/ +Failed: recursive call could loop indefinitely at offset 9 + +/(?=\w)(?R)/ +Failed: recursive call could loop indefinitely at offset 9 + +/(? a\nb 0: a\x{0a}b a\rb @@ -1336,7 +1329,7 @@ No match a\n\rb No match -/^a\R*b/8 +/^a\R*b/8 ab 0: ab a\nb @@ -1356,7 +1349,7 @@ No match a\n\r\x{85}\x0cb 0: a\x{0a}\x{0d}\x{85}\x{0c}b -/^a\R+b/8 +/^a\R+b/8 a\nb 0: a\x{0a}b a\rb @@ -1378,7 +1371,7 @@ No match ab No match -/^a\R{1,3}b/8 +/^a\R{1,3}b/8 a\nb 0: a\x{0a}b a\n\rb @@ -1522,4 +1515,97 @@ Error -10 \x{7fffffff}\? No match +/a\Rb/I8 +Capturing subpattern count = 0 +Options: bsr_anycrlf utf8 +First char = 'a' +Need char = 'b' + a\rb + 0: a\x{0d}b + a\nb + 0: a\x{0a}b + a\r\nb + 0: a\x{0d}\x{0a}b + ** Failers +No match + a\x{85}b +No match + a\x0bb +No match + +/a\Rb/I8 +Capturing subpattern count = 0 +Options: bsr_unicode utf8 +First char = 'a' +Need char = 'b' + a\rb + 0: a\x{0d}b + a\nb + 0: a\x{0a}b + a\r\nb + 0: a\x{0d}\x{0a}b + a\x{85}b + 0: a\x{85}b + a\x0bb + 0: a\x{0b}b + ** Failers +No match + a\x{85}b\ +No match + a\x0bb\ +No match + +/a\R?b/I8 +Capturing subpattern count = 0 +Options: bsr_anycrlf utf8 +First char = 'a' +Need char = 'b' + a\rb + 0: a\x{0d}b + a\nb + 0: a\x{0a}b + a\r\nb + 0: a\x{0d}\x{0a}b + ** Failers +No match + a\x{85}b +No match + a\x0bb +No match + +/a\R?b/I8 +Capturing subpattern count = 0 +Options: bsr_unicode utf8 +First char = 'a' +Need char = 'b' + a\rb + 0: a\x{0d}b + a\nb + 0: a\x{0a}b + a\r\nb + 0: a\x{0d}\x{0a}b + a\x{85}b + 0: a\x{85}b + a\x0bb + 0: a\x{0b}b + ** Failers +No match + a\x{85}b\ +No match + a\x0bb\ +No match + +/.*a.*=.b.*/8 + QQQ\x{2029}ABCaXYZ=!bPQR + 0: ABCaXYZ=!bPQR + ** Failers +No match + a\x{2029}b +No match + \x61\xe2\x80\xa9\x62 +No match + +/[[:a\x{100}b:]]/8 +Failed: unknown POSIX class name at offset 3 + / End of testinput5 / diff --git a/ext/pcre/pcrelib/testdata/testoutput6 b/ext/pcre/pcrelib/testdata/testoutput6 index 0a58b844f1..db825b08c1 100644 --- a/ext/pcre/pcrelib/testdata/testoutput6 +++ b/ext/pcre/pcrelib/testdata/testoutput6 @@ -1522,4 +1522,161 @@ No match /(\p{Yi}{0,3}+\277)*/ +/^[\p{Arabic}]/8 + \x{60e} + 0: \x{60e} + \x{656} + 0: \x{656} + \x{657} + 0: \x{657} + \x{658} + 0: \x{658} + \x{659} + 0: \x{659} + \x{65a} + 0: \x{65a} + \x{65b} + 0: \x{65b} + \x{65c} + 0: \x{65c} + \x{65d} + 0: \x{65d} + \x{65e} + 0: \x{65e} + \x{66a} + 0: \x{66a} + \x{6e9} + 0: \x{6e9} + \x{6ef} + 0: \x{6ef} + \x{6fa} + 0: \x{6fa} + ** Failers +No match + \x{600} +No match + \x{650} +No match + \x{651} +No match + \x{652} +No match + \x{653} +No match + \x{654} +No match + \x{655} +No match + \x{65f} +No match + +/^\p{Cyrillic}/8 + \x{1d2b} + 0: \x{1d2b} + +/^\p{Common}/8 + \x{589} + 0: \x{589} + \x{60c} + 0: \x{60c} + \x{61f} + 0: \x{61f} + \x{964} + 0: \x{964} + \x{965} + 0: \x{965} + \x{970} + 0: \x{970} + +/^\p{Inherited}/8 + \x{64b} + 0: \x{64b} + \x{654} + 0: \x{654} + \x{655} + 0: \x{655} + \x{200c} + 0: \x{200c} + ** Failers +No match + \x{64a} +No match + \x{656} +No match + +/^\p{Shavian}/8 + \x{10450} + 0: \x{10450} + \x{1047f} + 0: \x{1047f} + +/^\p{Deseret}/8 + \x{10400} + 0: \x{10400} + \x{1044f} + 0: \x{1044f} + +/^\p{Osmanya}/8 + \x{10480} + 0: \x{10480} + \x{1049d} + 0: \x{1049d} + \x{104a0} + 0: \x{104a0} + \x{104a9} + 0: \x{104a9} + ** Failers +No match + \x{1049e} +No match + \x{1049f} +No match + \x{104aa} +No match + +/\p{Zl}{2,3}+/8BZ +------------------------------------------------------------------ + Bra + prop Zl {2} + prop Zl ?+ + Ket + End +------------------------------------------------------------------ + \xe2\x80\xa8\xe2\x80\xa8 + 0: \x{2028}\x{2028} + \x{2028}\x{2028}\x{2028} + 0: \x{2028}\x{2028}\x{2028} + +/\p{Zl}/8BZ +------------------------------------------------------------------ + Bra + prop Zl + Ket + End +------------------------------------------------------------------ + +/\p{Lu}{3}+/8BZ +------------------------------------------------------------------ + Bra + prop Lu {3} + Ket + End +------------------------------------------------------------------ + +/\pL{2}+/8BZ +------------------------------------------------------------------ + Bra + prop L {2} + Ket + End +------------------------------------------------------------------ + +/\p{Cc}{2}+/8BZ +------------------------------------------------------------------ + Bra + prop Cc {2} + Ket + End +------------------------------------------------------------------ + / End of testinput6 / diff --git a/ext/pcre/pcrelib/testdata/testoutput7 b/ext/pcre/pcrelib/testdata/testoutput7 index 39c50750ec..d8e3833f39 100644 --- a/ext/pcre/pcrelib/testdata/testoutput7 +++ b/ext/pcre/pcrelib/testdata/testoutput7 @@ -6824,7 +6824,7 @@ No match 0: abc6 0: abc9 -/^a\Rb/ +/^a\Rb/ a\nb 0: a\x0ab a\rb @@ -6842,7 +6842,7 @@ No match a\n\rb No match -/^a\R*b/ +/^a\R*b/ ab 0: ab a\nb @@ -6862,7 +6862,7 @@ No match a\n\r\x85\x0cb 0: a\x0a\x0d\x85\x0cb -/^a\R+b/ +/^a\R+b/ a\nb 0: a\x0ab a\rb @@ -6884,7 +6884,7 @@ No match ab No match -/^a\R{1,3}b/ +/^a\R{1,3}b/ a\nb 0: a\x0ab a\n\rb @@ -6906,7 +6906,7 @@ No match a\r No match -/^a[\R]b/ +/^a[\R]b/ aRb 0: aRb ** Failers @@ -7088,4 +7088,128 @@ No match \r\nA 0: \x0aA +/a\Rb/I +Capturing subpattern count = 0 +Options: bsr_anycrlf +First char = 'a' +Need char = 'b' + a\rb + 0: a\x0db + a\nb + 0: a\x0ab + a\r\nb + 0: a\x0d\x0ab + ** Failers +No match + a\x85b +No match + a\x0bb +No match + +/a\Rb/I +Capturing subpattern count = 0 +Options: bsr_unicode +First char = 'a' +Need char = 'b' + a\rb + 0: a\x0db + a\nb + 0: a\x0ab + a\r\nb + 0: a\x0d\x0ab + a\x85b + 0: a\x85b + a\x0bb + 0: a\x0bb + ** Failers +No match + a\x85b\ +No match + a\x0bb\ +No match + +/a\R?b/I +Capturing subpattern count = 0 +Options: bsr_anycrlf +First char = 'a' +Need char = 'b' + a\rb + 0: a\x0db + a\nb + 0: a\x0ab + a\r\nb + 0: a\x0d\x0ab + ** Failers +No match + a\x85b +No match + a\x0bb +No match + +/a\R?b/I +Capturing subpattern count = 0 +Options: bsr_unicode +First char = 'a' +Need char = 'b' + a\rb + 0: a\x0db + a\nb + 0: a\x0ab + a\r\nb + 0: a\x0d\x0ab + a\x85b + 0: a\x85b + a\x0bb + 0: a\x0bb + ** Failers +No match + a\x85b\ +No match + a\x0bb\ +No match + +/a\R{2,4}b/I +Capturing subpattern count = 0 +Partial matching not supported +Options: bsr_anycrlf +First char = 'a' +Need char = 'b' + a\r\n\nb + 0: a\x0d\x0a\x0ab + a\n\r\rb + 0: a\x0a\x0d\x0db + a\r\n\r\n\r\n\r\nb + 0: a\x0d\x0a\x0d\x0a\x0d\x0a\x0d\x0ab + ** Failers +No match + a\x85\85b +No match + a\x0b\0bb +No match + +/a\R{2,4}b/I +Capturing subpattern count = 0 +Partial matching not supported +Options: bsr_unicode +First char = 'a' +Need char = 'b' + a\r\rb + 0: a\x0d\x0db + a\n\n\nb + 0: a\x0a\x0a\x0ab + a\r\n\n\r\rb + 0: a\x0d\x0a\x0a\x0d\x0db + a\x85\85b +No match + a\x0b\0bb +No match + ** Failers +No match + a\r\r\r\r\rb +No match + a\x85\85b\ +No match + a\x0b\0bb\ +No match + / End of testinput7 / diff --git a/ext/pcre/pcrelib/testdata/testoutput8 b/ext/pcre/pcrelib/testdata/testoutput8 index db0f4ade3f..631e5b82f9 100644 --- a/ext/pcre/pcrelib/testdata/testoutput8 +++ b/ext/pcre/pcrelib/testdata/testoutput8 @@ -1052,7 +1052,7 @@ No match 0: abc8 0: abc9 -/^a\Rb/8 +/^a\Rb/8 a\nb 0: a\x{0a}b a\rb @@ -1074,7 +1074,7 @@ No match a\n\rb No match -/^a\R*b/8 +/^a\R*b/8 ab 0: ab a\nb @@ -1094,7 +1094,7 @@ No match a\n\r\x{85}\x0cb 0: a\x{0a}\x{0d}\x{85}\x{0c}b -/^a\R+b/8 +/^a\R+b/8 a\nb 0: a\x{0a}b a\rb @@ -1116,7 +1116,7 @@ No match ab No match -/^a\R{1,3}b/8 +/^a\R{1,3}b/8 a\nb 0: a\x{0a}b a\n\rb @@ -1204,4 +1204,84 @@ No match \x09\x{200a}\x{a0}\x{2028}\x0b No match +/a\Rb/I8 +Capturing subpattern count = 0 +Options: bsr_anycrlf utf8 +First char = 'a' +Need char = 'b' + a\rb + 0: a\x{0d}b + a\nb + 0: a\x{0a}b + a\r\nb + 0: a\x{0d}\x{0a}b + ** Failers +No match + a\x{85}b +No match + a\x0bb +No match + +/a\Rb/I8 +Capturing subpattern count = 0 +Options: bsr_unicode utf8 +First char = 'a' +Need char = 'b' + a\rb + 0: a\x{0d}b + a\nb + 0: a\x{0a}b + a\r\nb + 0: a\x{0d}\x{0a}b + a\x{85}b + 0: a\x{85}b + a\x0bb + 0: a\x{0b}b + ** Failers +No match + a\x{85}b\ +No match + a\x0bb\ +No match + +/a\R?b/I8 +Capturing subpattern count = 0 +Options: bsr_anycrlf utf8 +First char = 'a' +Need char = 'b' + a\rb + 0: a\x{0d}b + a\nb + 0: a\x{0a}b + a\r\nb + 0: a\x{0d}\x{0a}b + ** Failers +No match + a\x{85}b +No match + a\x0bb +No match + +/a\R?b/I8 +Capturing subpattern count = 0 +Options: bsr_unicode utf8 +First char = 'a' +Need char = 'b' + a\rb + 0: a\x{0d}b + a\nb + 0: a\x{0a}b + a\r\nb + 0: a\x{0d}\x{0a}b + a\x{85}b + 0: a\x{85}b + a\x0bb + 0: a\x{0b}b + ** Failers +No match + a\x{85}b\ +No match + a\x0bb\ +No match + / End of testinput 8 / diff --git a/ext/pcre/pcrelib/ucptable.h b/ext/pcre/pcrelib/ucptable.h index 07eaced8f2..a274d443ee 100644 --- a/ext/pcre/pcrelib/ucptable.h +++ b/ext/pcre/pcrelib/ucptable.h @@ -539,7 +539,8 @@ static const cnode ucp_table[] = { { 0x21000293, 0x14000000 }, { 0x21000294, 0x1c000000 }, { 0x21800295, 0x1400001a }, - { 0x218002b0, 0x18000011 }, + { 0x218002b0, 0x18000008 }, + { 0x098002b9, 0x18000008 }, { 0x098002c2, 0x60000003 }, { 0x098002c6, 0x1800000b }, { 0x098002d2, 0x6000000d }, @@ -1039,15 +1040,18 @@ static const cnode ucp_table[] = { { 0x198005f3, 0x54000001 }, { 0x09800600, 0x04000003 }, { 0x0000060b, 0x5c000000 }, - { 0x0980060c, 0x54000001 }, + { 0x0900060c, 0x54000000 }, + { 0x0000060d, 0x54000000 }, { 0x0080060e, 0x68000001 }, { 0x00800610, 0x30000005 }, { 0x0900061b, 0x54000000 }, - { 0x0080061e, 0x54000001 }, + { 0x0000061e, 0x54000000 }, + { 0x0900061f, 0x54000000 }, { 0x00800621, 0x1c000019 }, { 0x09000640, 0x18000000 }, { 0x00800641, 0x1c000009 }, - { 0x1b80064b, 0x30000013 }, + { 0x1b80064b, 0x3000000a }, + { 0x00800656, 0x30000008 }, { 0x09800660, 0x34000009 }, { 0x0080066a, 0x54000003 }, { 0x0080066e, 0x1c000001 }, @@ -1074,7 +1078,8 @@ static const cnode ucp_table[] = { { 0x31000711, 0x30000000 }, { 0x31800712, 0x1c00001d }, { 0x31800730, 0x3000001a }, - { 0x3180074d, 0x1c000020 }, + { 0x3180074d, 0x1c000002 }, + { 0x00800750, 0x1c00001d }, { 0x37800780, 0x1c000025 }, { 0x378007a6, 0x3000000a }, { 0x370007b1, 0x1c000000 }, @@ -1460,7 +1465,10 @@ static const cnode ucp_table[] = { { 0x1f0017dd, 0x30000000 }, { 0x1f8017e0, 0x34000009 }, { 0x1f8017f0, 0x3c000009 }, - { 0x25801800, 0x54000005 }, + { 0x25801800, 0x54000001 }, + { 0x09801802, 0x54000001 }, + { 0x25001804, 0x54000000 }, + { 0x09001805, 0x54000000 }, { 0x25001806, 0x44000000 }, { 0x25801807, 0x54000003 }, { 0x2580180b, 0x30000002 }, @@ -1513,14 +1521,20 @@ static const cnode ucp_table[] = { { 0x3d801b61, 0x68000009 }, { 0x3d801b6b, 0x30000008 }, { 0x3d801b74, 0x68000008 }, - { 0x21801d00, 0x1400002b }, - { 0x21801d2c, 0x18000035 }, - { 0x21801d62, 0x14000015 }, + { 0x21801d00, 0x14000025 }, + { 0x13801d26, 0x14000004 }, + { 0x0c001d2b, 0x14000000 }, + { 0x21801d2c, 0x18000030 }, + { 0x13801d5d, 0x18000004 }, + { 0x21801d62, 0x14000003 }, + { 0x13801d66, 0x14000004 }, + { 0x21801d6b, 0x1400000c }, { 0x0c001d78, 0x18000000 }, { 0x21801d79, 0x14000003 }, { 0x21001d7d, 0x14000ee6 }, { 0x21801d7e, 0x1400001c }, - { 0x21801d9b, 0x18000024 }, + { 0x21801d9b, 0x18000023 }, + { 0x13001dbf, 0x18000000 }, { 0x1b801dc0, 0x3000000a }, { 0x1b801dfe, 0x30000001 }, { 0x21001e00, 0x24000001 }, @@ -1982,7 +1996,9 @@ static const cnode ucp_table[] = { { 0x13001ffc, 0x2000fff7 }, { 0x13801ffd, 0x60000001 }, { 0x09802000, 0x7400000a }, - { 0x0980200b, 0x04000004 }, + { 0x0900200b, 0x04000000 }, + { 0x1b80200c, 0x04000001 }, + { 0x0980200e, 0x04000001 }, { 0x09802010, 0x44000005 }, { 0x09802016, 0x54000001 }, { 0x09002018, 0x50000000 }, @@ -2615,7 +2631,8 @@ static const cnode ucp_table[] = { { 0x090030a0, 0x44000000 }, { 0x1d8030a1, 0x1c000059 }, { 0x090030fb, 0x54000000 }, - { 0x098030fc, 0x18000002 }, + { 0x090030fc, 0x18000000 }, + { 0x1d8030fd, 0x18000001 }, { 0x1d0030ff, 0x1c000000 }, { 0x03803105, 0x1c000027 }, { 0x17803131, 0x1c00005d }, @@ -2630,7 +2647,8 @@ static const cnode ucp_table[] = { { 0x0980322a, 0x68000019 }, { 0x09003250, 0x68000000 }, { 0x09803251, 0x3c00000e }, - { 0x17803260, 0x6800001f }, + { 0x17803260, 0x6800001d }, + { 0x0980327e, 0x68000001 }, { 0x09803280, 0x3c000009 }, { 0x0980328a, 0x68000026 }, { 0x098032b1, 0x3c00000e }, @@ -2678,7 +2696,8 @@ static const cnode ucp_table[] = { { 0x1900fb3e, 0x1c000000 }, { 0x1980fb40, 0x1c000001 }, { 0x1980fb43, 0x1c000001 }, - { 0x1980fb46, 0x1c00006b }, + { 0x1980fb46, 0x1c000009 }, + { 0x0080fb50, 0x1c000061 }, { 0x0080fbd3, 0x1c00016a }, { 0x0900fd3e, 0x58000000 }, { 0x0900fd3f, 0x48000000 }, @@ -2944,7 +2963,8 @@ static const cnode ucp_table[] = { { 0x0d01044d, 0x1400ffd8 }, { 0x0d01044e, 0x1400ffd8 }, { 0x0d01044f, 0x1400ffd8 }, - { 0x2e810450, 0x1c00004d }, + { 0x2e810450, 0x1c00002f }, + { 0x2c810480, 0x1c00001d }, { 0x2c8104a0, 0x34000009 }, { 0x0b810800, 0x1c000005 }, { 0x0b010808, 0x1c000000 }, diff --git a/ext/pcre/upgrade-pcre.php b/ext/pcre/upgrade-pcre.php index dd0a8a783a..43a98c94be 100644 --- a/ext/pcre/upgrade-pcre.php +++ b/ext/pcre/upgrade-pcre.php @@ -37,9 +37,9 @@ function recurse($path) if ($file[0] === '.' || $file === 'CVS' || - substr_compare($file, '.lo', -3, 3) == 0 || - substr_compare($file, '.loT', -4, 4) == 0 || - substr_compare($file, '.o', -2, 2) == 0) continue; + @substr_compare($file, '.lo', -3, 3) === 0 || + @substr_compare($file, '.loT', -4, 4) === 0 || + @substr_compare($file, '.o', -2, 2) === 0) continue; $file = "$path/$file";