From beb6916cfc16bd2fc1e5b304a79a5ca6e52fa166 Mon Sep 17 00:00:00 2001 From: Andrei Zmievski Date: Tue, 11 Apr 2000 17:35:42 +0000 Subject: [PATCH] *** empty log message *** --- ext/pcre/pcrelib/ChangeLog | 519 ---- ext/pcre/pcrelib/LICENCE | 32 - ext/pcre/pcrelib/Makefile.in | 11 - ext/pcre/pcrelib/README | 416 --- ext/pcre/pcrelib/RunTest | 94 - ext/pcre/pcrelib/Tech.Notes | 239 -- ext/pcre/pcrelib/chartables.c | 146 - ext/pcre/pcrelib/dftables.c | 146 - ext/pcre/pcrelib/dll.mk | 60 - ext/pcre/pcrelib/get.c | 189 -- ext/pcre/pcrelib/internal.h | 343 --- ext/pcre/pcrelib/maketables.c | 113 - ext/pcre/pcrelib/pcre.3 | 1499 ---------- ext/pcre/pcrelib/pcre.3.html | 1973 ------------- ext/pcre/pcrelib/pcre.3.txt | 1739 ----------- ext/pcre/pcrelib/pcre.c | 4477 ----------------------------- ext/pcre/pcrelib/pcre.def | 19 - ext/pcre/pcrelib/pcre.h | 96 - ext/pcre/pcrelib/pcreposix.3 | 141 - ext/pcre/pcrelib/pcreposix.3.html | 182 -- ext/pcre/pcrelib/pcreposix.3.txt | 150 - ext/pcre/pcrelib/pcreposix.c | 250 -- ext/pcre/pcrelib/pcreposix.h | 82 - ext/pcre/pcrelib/pcretest.c | 1010 ------- ext/pcre/pcrelib/perltest | 143 - ext/pcre/pcrelib/pgrep.1 | 76 - ext/pcre/pcrelib/pgrep.1.html | 105 - ext/pcre/pcrelib/pgrep.1.txt | 86 - ext/pcre/pcrelib/pgrep.c | 225 -- ext/pcre/pcrelib/study.c | 397 --- ext/pcre/pcrelib/testinput1 | 1890 ------------ ext/pcre/pcrelib/testinput2 | 589 ---- ext/pcre/pcrelib/testinput3 | 1692 ----------- ext/pcre/pcrelib/testinput4 | 64 - ext/pcre/pcrelib/testoutput1 | 2887 ------------------- ext/pcre/pcrelib/testoutput2 | 1624 ----------- ext/pcre/pcrelib/testoutput3 | 2929 ------------------- ext/pcre/pcrelib/testoutput4 | 115 - 38 files changed, 26748 deletions(-) delete mode 100644 ext/pcre/pcrelib/ChangeLog delete mode 100644 ext/pcre/pcrelib/LICENCE delete mode 100644 ext/pcre/pcrelib/Makefile.in delete mode 100644 ext/pcre/pcrelib/README delete mode 100755 ext/pcre/pcrelib/RunTest delete mode 100644 ext/pcre/pcrelib/Tech.Notes delete mode 100644 ext/pcre/pcrelib/chartables.c delete mode 100644 ext/pcre/pcrelib/dftables.c delete mode 100644 ext/pcre/pcrelib/dll.mk delete mode 100644 ext/pcre/pcrelib/get.c delete mode 100644 ext/pcre/pcrelib/internal.h delete mode 100644 ext/pcre/pcrelib/maketables.c delete mode 100644 ext/pcre/pcrelib/pcre.3 delete mode 100644 ext/pcre/pcrelib/pcre.3.html delete mode 100644 ext/pcre/pcrelib/pcre.3.txt delete mode 100644 ext/pcre/pcrelib/pcre.c delete mode 100644 ext/pcre/pcrelib/pcre.def delete mode 100644 ext/pcre/pcrelib/pcre.h delete mode 100644 ext/pcre/pcrelib/pcreposix.3 delete mode 100644 ext/pcre/pcrelib/pcreposix.3.html delete mode 100644 ext/pcre/pcrelib/pcreposix.3.txt delete mode 100644 ext/pcre/pcrelib/pcreposix.c delete mode 100644 ext/pcre/pcrelib/pcreposix.h delete mode 100644 ext/pcre/pcrelib/pcretest.c delete mode 100755 ext/pcre/pcrelib/perltest delete mode 100644 ext/pcre/pcrelib/pgrep.1 delete mode 100644 ext/pcre/pcrelib/pgrep.1.html delete mode 100644 ext/pcre/pcrelib/pgrep.1.txt delete mode 100644 ext/pcre/pcrelib/pgrep.c delete mode 100644 ext/pcre/pcrelib/study.c delete mode 100644 ext/pcre/pcrelib/testinput1 delete mode 100644 ext/pcre/pcrelib/testinput2 delete mode 100644 ext/pcre/pcrelib/testinput3 delete mode 100644 ext/pcre/pcrelib/testinput4 delete mode 100644 ext/pcre/pcrelib/testoutput1 delete mode 100644 ext/pcre/pcrelib/testoutput2 delete mode 100644 ext/pcre/pcrelib/testoutput3 delete mode 100644 ext/pcre/pcrelib/testoutput4 diff --git a/ext/pcre/pcrelib/ChangeLog b/ext/pcre/pcrelib/ChangeLog deleted file mode 100644 index cad637d959..0000000000 --- a/ext/pcre/pcrelib/ChangeLog +++ /dev/null @@ -1,519 +0,0 @@ -ChangeLog for PCRE ------------------- - - -Version 2.08 31-Aug-99 ----------------------- - -1. When startoffset was not zero and the pattern began with ".*", PCRE was not -trying to match at the startoffset position, but instead was moving forward to -the next newline as if a previous match had failed. - -2. pcretest was not making use of PCRE_NOTEMPTY when repeating for /g and /G, -and could get into a loop if a null string was matched other than at the start -of the subject. - -3. Added definitions of PCRE_MAJOR and PCRE_MINOR to pcre.h so the version can -be distinguished at compile time, and for completeness also added PCRE_DATE. - -5. Added Paul Sokolovsky's minor changes to make it easy to compile a Win32 DLL -in GnuWin32 environments. - - -Version 2.07 29-Jul-99 ----------------------- - -1. The documentation is now supplied in plain text form and HTML as well as in -the form of man page sources. - -2. C++ compilers don't like assigning (void *) values to other pointer types. -In particular this affects malloc(). Although there is no problem in Standard -C, I've put in casts to keep C++ compilers happy. - -3. Typo on pcretest.c; a cast of (unsigned char *) in the POSIX regexec() call -should be (const char *). - -4. If NOPOSIX is defined, pcretest.c compiles without POSIX support. This may -be useful for non-Unix systems who don't want to bother with the POSIX stuff. -However, I haven't made this a standard facility. The documentation doesn't -mention it, and the Makefile doesn't support it. - -5. The Makefile now contains an "install" target, with editable destinations at -the top of the file. The pcretest program is not installed. - -6. pgrep -V now gives the PCRE version number and date. - -7. Fixed bug: a zero repetition after a literal string (e.g. /abcde{0}/) was -causing the entire string to be ignored, instead of just the last character. - -8. If a pattern like /"([^\\"]+|\\.)*"/ is applied in the normal way to a -non-matching string, it can take a very, very long time, even for strings of -quite modest length, because of the nested recursion. PCRE now does better in -some of these cases. It does this by remembering the last required literal -character in the pattern, and pre-searching the subject to ensure it is present -before running the real match. In other words, it applies a heuristic to detect -some types of certain failure quickly, and in the above example, if presented -with a string that has no trailing " it gives "no match" very quickly. - -9. A new runtime option PCRE_NOTEMPTY causes null string matches to be ignored; -other alternatives are tried instead. - - -Version 2.06 09-Jun-99 ----------------------- - -1. Change pcretest's output for amount of store used to show just the code -space, because the remainder (the data block) varies in size between 32-bit and -64-bit systems. - -2. Added an extra argument to pcre_exec() to supply an offset in the subject to -start matching at. This allows lookbehinds to work when searching for multiple -occurrences in a string. - -3. Added additional options to pcretest for testing multiple occurrences: - - /+ outputs the rest of the string that follows a match - /g loops for multiple occurrences, using the new startoffset argument - /G loops for multiple occurrences by passing an incremented pointer - -4. PCRE wasn't doing the "first character" optimization for patterns starting -with \b or \B, though it was doing it for other lookbehind assertions. That is, -it wasn't noticing that a match for a pattern such as /\bxyz/ has to start with -the letter 'x'. On long subject strings, this gives a significant speed-up. - - -Version 2.05 21-Apr-99 ----------------------- - -1. Changed the type of magic_number from int to long int so that it works -properly on 16-bit systems. - -2. Fixed a bug which caused patterns starting with .* not to work correctly -when the subject string contained newline characters. PCRE was assuming -anchoring for such patterns in all cases, which is not correct because .* will -not pass a newline unless PCRE_DOTALL is set. It now assumes anchoring only if -DOTALL is set at top level; otherwise it knows that patterns starting with .* -must be retried after every newline in the subject. - - -Version 2.04 18-Feb-99 ----------------------- - -1. For parenthesized subpatterns with repeats whose minimum was zero, the -computation of the store needed to hold the pattern was incorrect (too large). -If such patterns were nested a few deep, this could multiply and become a real -problem. - -2. Added /M option to pcretest to show the memory requirement of a specific -pattern. Made -m a synonym of -s (which does this globally) for compatibility. - -3. Subpatterns of the form (regex){n,m} (i.e. limited maximum) were being -compiled in such a way that the backtracking after subsequent failure was -pessimal. Something like (a){0,3} was compiled as (a)?(a)?(a)? instead of -((a)((a)(a)?)?)? with disastrous performance if the maximum was of any size. - - -Version 2.03 02-Feb-99 ----------------------- - -1. Fixed typo and small mistake in man page. - -2. Added 4th condition (GPL supersedes if conflict) and created separate -LICENCE file containing the conditions. - -3. Updated pcretest so that patterns such as /abc\/def/ work like they do in -Perl, that is the internal \ allows the delimiter to be included in the -pattern. Locked out the use of \ as a delimiter. If \ immediately follows -the final delimiter, add \ to the end of the pattern (to test the error). - -4. Added the convenience functions for extracting substrings after a successful -match. Updated pcretest to make it able to test these functions. - - -Version 2.02 14-Jan-99 ----------------------- - -1. Initialized the working variables associated with each extraction so that -their saving and restoring doesn't refer to uninitialized store. - -2. Put dummy code into study.c in order to trick the optimizer of the IBM C -compiler for OS/2 into generating correct code. Apparently IBM isn't going to -fix the problem. - -3. Pcretest: the timing code wasn't using LOOPREPEAT for timing execution -calls, and wasn't printing the correct value for compiling calls. Increased the -default value of LOOPREPEAT, and the number of significant figures in the -times. - -4. Changed "/bin/rm" in the Makefile to "-rm" so it works on Windows NT. - -5. Renamed "deftables" as "dftables" to get it down to 8 characters, to avoid -a building problem on Windows NT with a FAT file system. - - -Version 2.01 21-Oct-98 ----------------------- - -1. Changed the API for pcre_compile() to allow for the provision of a pointer -to character tables built by pcre_maketables() in the current locale. If NULL -is passed, the default tables are used. - - -Version 2.00 24-Sep-98 ----------------------- - -1. Since the (>?) facility is in Perl 5.005, don't require PCRE_EXTRA to enable -it any more. - -2. Allow quantification of (?>) groups, and make it work correctly. - -3. The first character computation wasn't working for (?>) groups. - -4. Correct the implementation of \Z (it is permitted to match on the \n at the -end of the subject) and add 5.005's \z, which really does match only at the -very end of the subject. - -5. Remove the \X "cut" facility; Perl doesn't have it, and (?> is neater. - -6. Remove the ability to specify CASELESS, MULTILINE, DOTALL, and -DOLLAR_END_ONLY at runtime, to make it possible to implement the Perl 5.005 -localized options. All options to pcre_study() were also removed. - -7. Add other new features from 5.005: - - $(?<= positive lookbehind - $(?a*))*/ (a PCRE_EXTRA facility). - - -Version 1.00 18-Nov-97 ----------------------- - -1. Added compile-time macros to support systems such as SunOS4 which don't have -memmove() or strerror() but have other things that can be used instead. - -2. Arranged that "make clean" removes the executables. - - -Version 0.99 27-Oct-97 ----------------------- - -1. Fixed bug in code for optimizing classes with only one character. It was -initializing a 32-byte map regardless, which could cause it to run off the end -of the memory it had got. - -2. Added, conditional on PCRE_EXTRA, the proposed (?>REGEX) construction. - - -Version 0.98 22-Oct-97 ----------------------- - -1. Fixed bug in code for handling temporary memory usage when there are more -back references than supplied space in the ovector. This could cause segfaults. - - -Version 0.97 21-Oct-97 ----------------------- - -1. Added the \X "cut" facility, conditional on PCRE_EXTRA. - -2. Optimized negated single characters not to use a bit map. - -3. Brought error texts together as macro definitions; clarified some of them; -fixed one that was wrong - it said "range out of order" when it meant "invalid -escape sequence". - -4. Changed some char * arguments to const char *. - -5. Added PCRE_NOTBOL and PCRE_NOTEOL (from POSIX). - -6. Added the POSIX-style API wrapper in pcreposix.a and testing facilities in -pcretest. - - -Version 0.96 16-Oct-97 ----------------------- - -1. Added a simple "pgrep" utility to the distribution. - -2. Fixed an incompatibility with Perl: "{" is now treated as a normal character -unless it appears in one of the precise forms "{ddd}", "{ddd,}", or "{ddd,ddd}" -where "ddd" means "one or more decimal digits". - -3. Fixed serious bug. If a pattern had a back reference, but the call to -pcre_exec() didn't supply a large enough ovector to record the related -identifying subpattern, the match always failed. PCRE now remembers the number -of the largest back reference, and gets some temporary memory in which to save -the offsets during matching if necessary, in order to ensure that -backreferences always work. - -4. Increased the compatibility with Perl in a number of ways: - - (a) . no longer matches \n by default; an option PCRE_DOTALL is provided - to request this handling. The option can be set at compile or exec time. - - (b) $ matches before a terminating newline by default; an option - PCRE_DOLLAR_ENDONLY is provided to override this (but not in multiline - mode). The option can be set at compile or exec time. - - (c) The handling of \ followed by a digit other than 0 is now supposed to be - the same as Perl's. If the decimal number it represents is less than 10 - or there aren't that many previous left capturing parentheses, an octal - escape is read. Inside a character class, it's always an octal escape, - even if it is a single digit. - - (d) An escaped but undefined alphabetic character is taken as a literal, - unless PCRE_EXTRA is set. Currently this just reserves the remaining - escapes. - - (e) {0} is now permitted. (The previous item is removed from the compiled - pattern). - -5. Changed all the names of code files so that the basic parts are no longer -than 10 characters, and abolished the teeny "globals.c" file. - -6. Changed the handling of character classes; they are now done with a 32-byte -bit map always. - -7. Added the -d and /D options to pcretest to make it possible to look at the -internals of compilation without having to recompile pcre. - - -Version 0.95 23-Sep-97 ----------------------- - -1. Fixed bug in pre-pass concerning escaped "normal" characters such as \x5c or -\x20 at the start of a run of normal characters. These were being treated as -real characters, instead of the source characters being re-checked. - - -Version 0.94 18-Sep-97 ----------------------- - -1. The functions are now thread-safe, with the caveat that the global variables -containing pointers to malloc() and free() or alternative functions are the -same for all threads. - -2. Get pcre_study() to generate a bitmap of initial characters for non- -anchored patterns when this is possible, and use it if passed to pcre_exec(). - - -Version 0.93 15-Sep-97 ----------------------- - -1. /(b)|(:+)/ was computing an incorrect first character. - -2. Add pcre_study() to the API and the passing of pcre_extra to pcre_exec(), -but not actually doing anything yet. - -3. Treat "-" characters in classes that cannot be part of ranges as literals, -as Perl does (e.g. [-az] or [az-]). - -4. Set the anchored flag if a branch starts with .* or .*? because that tests -all possible positions. - -5. Split up into different modules to avoid including unneeded functions in a -compiled binary. However, compile and exec are still in one module. The "study" -function is split off. - -6. The character tables are now in a separate module whose source is generated -by an auxiliary program - but can then be edited by hand if required. There are -now no calls to isalnum(), isspace(), isdigit(), isxdigit(), tolower() or -toupper() in the code. - -7. Turn the malloc/free funtions variables into pcre_malloc and pcre_free and -make them global. Abolish the function for setting them, as the caller can now -set them directly. - - -Version 0.92 11-Sep-97 ----------------------- - -1. A repeat with a fixed maximum and a minimum of 1 for an ordinary character -(e.g. /a{1,3}/) was broken (I mis-optimized it). - -2. Caseless matching was not working in character classes if the characters in -the pattern were in upper case. - -3. Make ranges like [W-c] work in the same way as Perl for caseless matching. - -4. Make PCRE_ANCHORED public and accept as a compile option. - -5. Add an options word to pcre_exec() and accept PCRE_ANCHORED and -PCRE_CASELESS at run time. Add escapes \A and \I to pcretest to cause it to -pass them. - -6. Give an error if bad option bits passed at compile or run time. - -7. Add PCRE_MULTILINE at compile and exec time, and (?m) as well. Add \M to -pcretest to cause it to pass that flag. - -8. Add pcre_info(), to get the number of identifying subpatterns, the stored -options, and the first character, if set. - -9. Recognize C+ or C{n,m} where n >= 1 as providing a fixed starting character. - - -Version 0.91 10-Sep-97 ----------------------- - -1. PCRE was failing to diagnose unlimited repeats of subpatterns that could -match the empty string as in /(a*)*/. It was looping and ultimately crashing. - -2. PCRE was looping on encountering an indefinitely repeated back reference to -a subpattern that had matched an empty string, e.g. /(a|)\1*/. It now does what -Perl does - treats the match as successful. - -**** diff --git a/ext/pcre/pcrelib/LICENCE b/ext/pcre/pcrelib/LICENCE deleted file mode 100644 index 246515ae75..0000000000 --- a/ext/pcre/pcrelib/LICENCE +++ /dev/null @@ -1,32 +0,0 @@ -PCRE LICENCE ------------- - -PCRE is a library of functions to support regular expressions whose syntax -and semantics are as close as possible to those of the Perl 5 language. - -Written by: Philip Hazel - -University of Cambridge Computing Service, -Cambridge, England. Phone: +44 1223 334714. - -Copyright (c) 1997-1999 University of Cambridge - -Permission is granted to anyone to use this software for any purpose on any -computer system, and to redistribute it freely, subject to the following -restrictions: - -1. This software is distributed in the hope that it will be useful, - but WITHOUT ANY WARRANTY; without even the implied warranty of - MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. - -2. The origin of this software must not be misrepresented, either by - explicit claim or by omission. - -3. Altered versions must be plainly marked as such, and must not be - misrepresented as being the original software. - -4. If PCRE is embedded in any software that is released under the GNU - General Purpose Licence (GPL), then the terms of that licence shall - supersede any condition above with which it is incompatible. - -End diff --git a/ext/pcre/pcrelib/Makefile.in b/ext/pcre/pcrelib/Makefile.in deleted file mode 100644 index 3d435c758b..0000000000 --- a/ext/pcre/pcrelib/Makefile.in +++ /dev/null @@ -1,11 +0,0 @@ - -DEPTH = ../../.. -topsrcdir = @topsrcdir@ -srcdir = @srcdir@ -VPATH = @srcdir@ - -LTLIBRARY_NAME = libpcre.la -LTLIBRARY_SOURCES = maketables.c get.c study.c pcre.c - -include $(topsrcdir)/build/ltlib.mk - diff --git a/ext/pcre/pcrelib/README b/ext/pcre/pcrelib/README deleted file mode 100644 index c9696bab48..0000000000 --- a/ext/pcre/pcrelib/README +++ /dev/null @@ -1,416 +0,0 @@ -README file for PCRE (Perl-compatible regular expressions) ----------------------------------------------------------- - -******************************************************************************* -* IMPORTANT FOR THOSE UPGRADING FROM VERSIONS BEFORE 2.00 * -* * -* Please note that there has been a change in the API such that a larger * -* ovector is required at matching time, to provide some additional workspace. * -* The new man page has details. This change was necessary in order to support * -* some of the new functionality in Perl 5.005. * -* * -* IMPORTANT FOR THOSE UPGRADING FROM VERSION 2.00 * -* * -* Another (I hope this is the last!) change has been made to the API for the * -* pcre_compile() function. An additional argument has been added to make it * -* possible to pass over a pointer to character tables built in the current * -* locale by pcre_maketables(). To use the default tables, this new arguement * -* should be passed as NULL. * -* * -* IMPORTANT FOR THOSE UPGRADING FROM VERSION 2.05 * -* * -* Yet another (and again I hope this really is the last) change has been made * -* to the API for the pcre_exec() function. An additional argument has been * -* added to make it possible to start the match other than at the start of the * -* subject string. This is important if there are lookbehinds. The new man * -* page has the details, but you just want to convert existing programs, all * -* you need to do is to stick in a new fifth argument to pcre_exec(), with a * -* value of zero. For example, change * -* * -* pcre_exec(pattern, extra, subject, length, options, ovec, ovecsize) * -* to * -* pcre_exec(pattern, extra, subject, length, 0, options, ovec, ovecsize) * -******************************************************************************* - - -The distribution should contain the following files: - - ChangeLog log of changes to the code - LICENCE conditions for the use of PCRE - Makefile for building PCRE in Unix systems - README this file - RunTest a Unix shell script for running tests - Tech.Notes notes on the encoding - pcre.3 man page source for the functions - pcre.3.txt plain text version - pcre.3.html HTML version - pcreposix.3 man page source for the POSIX wrapper API - pcreposix.3.txt plain text version - pcreposix.3.HTML HTML version - dftables.c auxiliary program for building chartables.c - get.c ) - maketables.c ) - study.c ) source of - pcre.c ) the functions - pcreposix.c ) - pcre.h header for the external API - pcreposix.h header for the external POSIX wrapper API - internal.h header for internal use - pcretest.c test program - pgrep.1 man page source for pgrep - pgrep.1.txt plain text version - pgrep.1.HTML HTML version - pgrep.c source of a grep utility that uses PCRE - perltest Perl test program - testinput1 test data, compatible with Perl 5.004 and 5.005 - testinput2 test data for error messages and non-Perl things - testinput3 test data, compatible with Perl 5.005 - testinput4 test data for locale-specific tests - testoutput1 test results corresponding to testinput1 - testoutput2 test results corresponding to testinput2 - testoutput3 test results corresponding to testinput3 - testoutput4 test results corresponding to testinput4 - dll.mk for Win32 DLL - pcre.def ditto - -To build PCRE on a Unix system, first edit Makefile for your system. It is a -fairly simple make file, and there are some comments near the top, after the -text "On a Unix system". Then run "make". It builds two libraries called -libpcre.a and libpcreposix.a, a test program called pcretest, and the pgrep -command. You can use "make install" to copy these, and the public header file -pcre.h, to appropriate live directories on your system. These installation -directories are defined at the top of the Makefile, and you should edit them if -necessary. - -For a non-Unix system, read the comments at the top of Makefile, which give -some hints on what needs to be done. PCRE has been compiled on Windows systems -and on Macintoshes, but I don't know the details as I don't use those systems. -It should be straightforward to build PCRE on any system that has a Standard C -compiler. - -Some help in building a Win32 DLL of PCRE in GnuWin32 environments was -contributed by Paul.Sokolovsky@technologist.com. These environments are -Mingw32 (http://www.xraylith.wisc.edu/~khan/software/gnu-win32/) and -CygWin (http://sourceware.cygnus.com/cygwin/). Paul comments: - - For CygWin, set CFLAGS=-mno-cygwin, and do 'make dll'. You'll get - pcre.dll (containing pcreposix also), libpcre.dll.a, and dynamically - linked pgrep and pcretest. If you have /bin/sh, run RunTest (three - main test go ok, locale not supported). - -To test PCRE, run the RunTest script in the pcre directory. This can also be -run by "make runtest". It runs the pcretest test program (which is documented -below) on each of the testinput files in turn, and compares the output with the -contents of the corresponding testoutput file. A file called testtry is used to -hold the output from pcretest. To run pcretest on just one of the test files, -give its number as an argument to RunTest, for example: - - RunTest 3 - -The first and third test files can also be fed directly into the perltest -script to check that Perl gives the same results. The third file requires the -additional features of release 5.005, which is why it is kept separate from the -main test input, which needs only Perl 5.004. In the long run, when 5.005 is -widespread, these two test files may get amalgamated. - -The second set of tests check pcre_info(), pcre_study(), pcre_copy_substring(), -pcre_get_substring(), pcre_get_substring_list(), error detection and run-time -flags that are specific to PCRE, as well as the POSIX wrapper API. - -The fourth set of tests checks pcre_maketables(), the facility for building a -set of character tables for a specific locale and using them instead of the -default tables. The tests make use of the "fr" (French) locale. Before running -the test, the script checks for the presence of this locale by running the -"locale" command. If that command fails, or if it doesn't include "fr" in the -list of available locales, the fourth test cannot be run, and a comment is -output to say why. If running this test produces instances of the error - - ** Failed to set locale "fr" - -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. - -PCRE has its own native API, but a set of "wrapper" functions that are based on -the POSIX API are also supplied in the library libpcreposix.a. Note that this -just provides a POSIX calling interface to PCRE: the regular expressions -themselves still follow Perl syntax and semantics. The header file -for the POSIX-style functions is called pcreposix.h. The official POSIX name is -regex.h, but I didn't want to risk possible problems with existing files of -that name by distributing it that way. To use it with an existing program that -uses the POSIX API, it will have to be renamed or pointed at by a link. - - -Character tables ----------------- - -PCRE uses four tables for manipulating and identifying characters. The final -argument of the pcre_compile() function is a pointer to a block of memory -containing the concatenated tables. A call to pcre_maketables() can be used to -generate a set of tables in the current locale. If the final argument for -pcre_compile() is passed as NULL, a set of default tables that is built into -the binary is used. - -The source file called chartables.c contains the default set of tables. This is -not supplied in the distribution, but is built by the program dftables -(compiled from dftables.c), which uses the ANSI C character handling functions -such as isalnum(), isalpha(), isupper(), islower(), etc. to build the table -sources. This means that the default C locale which is set for your system will -control the contents of these default tables. You can change the default tables -by editing chartables.c and then re-building PCRE. If you do this, you should -probably also edit Makefile to ensure that the file doesn't ever get -re-generated. - -The first two 256-byte tables provide lower casing and case flipping functions, -respectively. The next table consists of three 32-byte bit maps which identify -digits, "word" characters, and white space, respectively. These are used when -building 32-byte bit maps that represent character classes. - -The final 256-byte table has bits indicating various character types, as -follows: - - 1 white space character - 2 letter - 4 decimal digit - 8 hexadecimal digit - 16 alphanumeric or '_' - 128 regular expression metacharacter or binary zero - -You should not alter the set of characters that contain the 128 bit, as that -will cause PCRE to malfunction. - - -The pcretest program --------------------- - -This program is intended for testing PCRE, but it can also be used for -experimenting with regular expressions. - -If it is given two filename arguments, it reads from the first and writes to -the second. If it is given only one filename argument, it reads from that file -and writes to stdout. Otherwise, it reads from stdin and writes to stdout, and -prompts for each line of input. - -The program handles any number of sets of input on a single input file. Each -set starts with a regular expression, and continues with any number of data -lines to be matched against the pattern. An empty line signals the end of the -set. The regular expressions are given enclosed in any non-alphameric -delimiters other than backslash, for example - - /(a|bc)x+yz/ - -White space before the initial delimiter is ignored. A regular expression may -be continued over several input lines, in which case the newline characters are -included within it. See the testinput files for many examples. It is possible -to include the delimiter within the pattern by escaping it, for example - - /abc\/def/ - -If you do so, the escape and the delimiter form part of the pattern, but since -delimiters are always non-alphameric, this does not affect its interpretation. -If the terminating delimiter is immediately followed by a backslash, for -example, - - /abc/\ - -then a backslash is added to the end of the pattern. This is done to provide a -way of testing the error condition that arises if a pattern finishes with a -backslash, because - - /abc\/ - -is interpreted as the first line of a pattern that starts with "abc/", causing -pcretest to read the next line as a continuation of the regular expression. - -The pattern may be followed by i, m, s, or x to set the PCRE_CASELESS, -PCRE_MULTILINE, PCRE_DOTALL, or PCRE_EXTENDED options, respectively. For -example: - - /caseless/i - -These modifier letters have the same effect as they do in Perl. There are -others which set PCRE options that do not correspond to anything in Perl: /A, -/E, and /X set PCRE_ANCHORED, PCRE_DOLLAR_ENDONLY, and PCRE_EXTRA respectively. - -Searching for all possible matches within each subject string can be requested -by the /g or /G modifier. After finding a match, PCRE is called again to search -the remainder of the subject string. The difference between /g and /G is that -the former uses the startoffset argument to pcre_exec() to start searching at -a new point within the entire string (which is in effect what Perl does), -whereas the latter passes over a shortened substring. This makes a difference -to the matching process if the pattern begins with a lookbehind assertion -(including \b or \B). - -If any call to pcre_exec() in a /g or /G sequence matches an empty string, the -next call is done with the PCRE_NOTEMPTY flag set so that it cannot match an -empty string again. This imitates the way Perl handles such cases when using -the /g modifier or the split() function. - -There are a number of other modifiers for controlling the way pcretest -operates. - -The /+ modifier requests that as well as outputting the substring that matched -the entire pattern, pcretest should in addition output the remainder of the -subject string. This is useful for tests where the subject contains multiple -copies of the same substring. - -The /L modifier must be followed directly by the name of a locale, for example, - - /pattern/Lfr - -For this reason, it must be the last modifier letter. The given locale is set, -pcre_maketables() is called to build a set of character tables for the locale, -and this is then passed to pcre_compile() when compiling the regular -expression. Without an /L modifier, NULL is passed as the tables pointer; that -is, /L applies only to the expression on which it appears. - -The /I modifier requests that pcretest output information about the compiled -expression (whether it is anchored, has a fixed first character, and so on). It -does this by calling pcre_info() after compiling an expression, and outputting -the information it gets back. If the pattern is studied, the results of that -are also output. - -The /D modifier is a PCRE debugging feature, which also assumes /I. It causes -the internal form of compiled regular expressions to be output after -compilation. - -The /S modifier causes pcre_study() to be called after the expression has been -compiled, and the results used when the expression is matched. - -The /M modifier causes the size of memory block used to hold the compiled -pattern to be output. - -Finally, the /P modifier causes pcretest to call PCRE via the POSIX wrapper API -rather than its native API. When this is done, all other modifiers except /i, -/m, and /+ are ignored. REG_ICASE is set if /i is present, and REG_NEWLINE is -set if /m is present. The wrapper functions force PCRE_DOLLAR_ENDONLY always, -and PCRE_DOTALL unless REG_NEWLINE is set. - -Before each data line is passed to pcre_exec(), leading and trailing whitespace -is removed, and it is then scanned for \ escapes. The following are recognized: - - \a alarm (= BEL) - \b backspace - \e escape - \f formfeed - \n newline - \r carriage return - \t tab - \v vertical tab - \nnn octal character (up to 3 octal digits) - \xhh hexadecimal character (up to 2 hex digits) - - \A pass the PCRE_ANCHORED option to pcre_exec() - \B pass the PCRE_NOTBOL option to pcre_exec() - \Cdd call pcre_copy_substring() for substring dd after a successful match - (any decimal number less than 32) - \Gdd call pcre_get_substring() for substring dd after a successful match - (any decimal number less than 32) - \L call pcre_get_substringlist() after a successful match - \N pass the PCRE_NOTEMPTY option to pcre_exec() - \Odd set the size of the output vector passed to pcre_exec() to dd - (any number of decimal digits) - \Z pass the PCRE_NOTEOL option to pcre_exec() - -A backslash followed by anything else just escapes the anything else. If the -very last character is a backslash, it is ignored. This gives a way of passing -an empty line as data, since a real empty line terminates the data input. - -If /P was present on the regex, causing the POSIX wrapper API to be used, only -\B, and \Z have any effect, causing REG_NOTBOL and REG_NOTEOL to be passed to -regexec() respectively. - -When a match succeeds, pcretest outputs the list of captured substrings that -pcre_exec() returns, starting with number 0 for the string that matched the -whole pattern. Here is an example of an interactive pcretest run. - - $ pcretest - PCRE version 2.06 08-Jun-1999 - - re> /^abc(\d+)/ - data> abc123 - 0: abc123 - 1: 123 - data> xyz - No match - -If the strings contain any non-printing characters, they are output as \0x -escapes. If the pattern has the /+ modifier, then the output for substring 0 is -followed by the the rest of the subject string, identified by "0+" like this: - - re> /cat/+ - data> cataract - 0: cat - 0+ aract - -If the pattern has the /g or /G modifier, the results of successive matching -attempts are output in sequence, like this: - - re> /\Bi(\w\w)/g - data> Mississippi - 0: iss - 1: ss - 0: iss - 1: ss - 0: ipp - 1: pp - -"No match" is output only if the first match attempt fails. - -If any of \C, \G, or \L are present in a data line that is successfully -matched, the substrings extracted by the convenience functions are output with -C, G, or L after the string number instead of a colon. This is in addition to -the normal full list. The string length (that is, the return from the -extraction function) is given in parentheses after each string for \C and \G. - -Note that while patterns can be continued over several lines (a plain ">" -prompt is used for continuations), data lines may not. However newlines can be -included in data by means of the \n escape. - -If the -p option is given to pcretest, it is equivalent to adding /P to each -regular expression: the POSIX wrapper API is used to call PCRE. None of the -following flags has any effect in this case. - -If the option -d is given to pcretest, it is equivalent to adding /D to each -regular expression: the internal form is output after compilation. - -If the option -i is given to pcretest, it is equivalent to adding /I to each -regular expression: information about the compiled pattern is given after -compilation. - -If the option -m is given to pcretest, it outputs the size of each compiled -pattern after it has been compiled. It is equivalent to adding /M to each -regular expression. For compatibility with earlier versions of pcretest, -s is -a synonym for -m. - -If the -t option is given, each compile, study, and match is run 20000 times -while being timed, and the resulting time per compile or match is output in -milliseconds. Do not set -t with -s, because you will then get the size output -20000 times and the timing will be distorted. If you want to change the number -of repetitions used for timing, edit the definition of LOOPREPEAT at the top of -pcretest.c - - - -The perltest program --------------------- - -The perltest program tests Perl's regular expressions; it has the same -specification as pcretest, and so can be given identical input, except that -input patterns can be followed only by Perl's lower case modifiers. The -contents of testinput1 and testinput3 meet this condition. - -The data lines are processed as Perl double-quoted strings, so if they contain -" \ $ or @ characters, these have to be escaped. For this reason, all such -characters in testinput1 and testinput3 are escaped so that they can be used -for perltest as well as for pcretest, and the special upper case modifiers such -as /A that pcretest recognizes are not used in these files. The output should -be identical, apart from the initial identifying banner. - -The testinput2 and testinput4 files are not suitable for feeding to perltest, -since they do make use of the special upper case modifiers and escapes that -pcretest uses to test some features of PCRE. The first of these files also -contains malformed regular expressions, in order to check that PCRE diagnoses -them correctly. - -Philip Hazel -July 1999 diff --git a/ext/pcre/pcrelib/RunTest b/ext/pcre/pcrelib/RunTest deleted file mode 100755 index a23c51108f..0000000000 --- a/ext/pcre/pcrelib/RunTest +++ /dev/null @@ -1,94 +0,0 @@ -#! /bin/sh - -# Run PCRE tests - -cf=diff - -# Select which tests to run; if no selection, run all - -do1=no -do2=no -do3=no -do4=no - -while [ $# -gt 0 ] ; do - case $1 in - 1) do1=yes;; - 2) do2=yes;; - 3) do3=yes;; - 4) do4=yes;; - *) echo "Unknown test number $1"; exit 1;; - esac - shift -done - -if [ $do1 = no -a $do2 = no -a $do3 = no -a $do4 = no ] ; then - do1=yes - do2=yes - do3=yes - do4=yes -fi - -# Primary test, Perl-compatible - -if [ $do1 = yes ] ; then - echo "Testing main functionality (Perl compatible)" - ./pcretest testinput1 testtry - if [ $? = 0 ] ; then - $cf testtry testoutput1 - if [ $? != 0 ] ; then exit 1; fi - else exit 1 - fi -fi - -# PCRE tests that are not Perl-compatible - API & error tests, mostly - -if [ $do2 = yes ] ; then - echo "Testing API and error handling (not Perl compatible)" - ./pcretest -i testinput2 testtry - if [ $? = 0 ] ; then - $cf testtry testoutput2 - if [ $? != 0 ] ; then exit 1; fi - else exit 1 - fi -fi - -# Additional Perl-compatible tests for Perl 5.005's new features - -if [ $do3 = yes ] ; then - echo "Testing Perl 5.005 features (Perl 5.005 compatible)" - ./pcretest testinput3 testtry - if [ $? = 0 ] ; then - $cf testtry testoutput3 - if [ $? != 0 ] ; then exit 1; fi - else exit 1 - fi -fi - -if [ $do1 = yes -a $do2 = yes -a $do3 = yes ] ; then - echo "The three main tests all ran OK" - echo " " -fi - -# Locale-specific tests, provided the "fr" locale is available - -if [ $do4 = yes ] ; then - locale -a | grep '^fr$' >/dev/null - if [ $? -eq 0 ] ; then - echo "Testing locale-specific features (using 'fr' locale)" - ./pcretest testinput4 testtry - if [ $? = 0 ] ; then - $cf testtry testoutput4 - if [ $? != 0 ] ; then exit 1; fi - echo "Locale test ran OK" - echo " " - else exit 1 - fi - else - echo "Cannot test locale-specific features - 'fr' locale not found," - echo "or the \"locale\" command is not available to check for it." - echo " " - fi -fi - -# End diff --git a/ext/pcre/pcrelib/Tech.Notes b/ext/pcre/pcrelib/Tech.Notes deleted file mode 100644 index d485a4ec59..0000000000 --- a/ext/pcre/pcrelib/Tech.Notes +++ /dev/null @@ -1,239 +0,0 @@ -Technical Notes about PCRE --------------------------- - -Many years ago I implemented some regular expression functions to an algorithm -suggested by Martin Richards. These were not Unix-like in form, and were quite -restricted in what they could do by comparison with Perl. The interesting part -about the algorithm was that the amount of space required to hold the compiled -form of an expression was known in advance. The code to apply an expression did -not operate by backtracking, as the Henry Spencer and Perl code does, but -instead checked all possibilities simultaneously by keeping a list of current -states and checking all of them as it advanced through the subject string. (In -the terminology of Jeffrey Friedl's book, it was a "DFA algorithm".) When the -pattern was all used up, all remaining states were possible matches, and the -one matching the longest subset of the subject string was chosen. This did not -necessarily maximize the individual wild portions of the pattern, as is -expected in Unix and Perl-style regular expressions. - -By contrast, the code originally written by Henry Spencer and subsequently -heavily modified for Perl actually compiles the expression twice: once in a -dummy mode in order to find out how much store will be needed, and then for -real. The execution function operates by backtracking and maximizing (or, -optionally, minimizing in Perl) the amount of the subject that matches -individual wild portions of the pattern. This is an "NFA algorithm" in Friedl's -terminology. - -For this set of functions that forms PCRE, I tried at first to invent an -algorithm that used an amount of store bounded by a multiple of the number of -characters in the pattern, to save on compiling time. However, because of the -greater complexity in Perl regular expressions, I couldn't do this. In any -case, a first pass through the pattern is needed, in order to find internal -flag settings like (?i) at top level. So it works by running a very degenerate -first pass to calculate a maximum store size, and then a second pass to do the -real compile - which may use a bit less than the predicted amount of store. The -idea is that this is going to turn out faster because the first pass is -degenerate and the second can just store stuff straight into the vector. It -does make the compiling functions bigger, of course, but they have got quite -big anyway to handle all the Perl stuff. - -The compiled form of a pattern is a vector of bytes, containing items of -variable length. The first byte in an item is an opcode, and the length of the -item is either implicit in the opcode or contained in the data bytes which -follow it. A list of all the opcodes follows: - -Opcodes with no following data ------------------------------- - -These items are all just one byte long - - OP_END end of pattern - OP_ANY match any character - OP_SOD match start of data: \A - OP_CIRC ^ (start of data, or after \n in multiline) - OP_NOT_WORD_BOUNDARY \W - OP_WORD_BOUNDARY \w - OP_NOT_DIGIT \D - OP_DIGIT \d - OP_NOT_WHITESPACE \S - OP_WHITESPACE \s - OP_NOT_WORDCHAR \W - OP_WORDCHAR \w - OP_EODN match end of data or \n at end: \Z - OP_EOD match end of data: \z - OP_DOLL $ (end of data, or before \n in multiline) - - -Repeating single characters ---------------------------- - -The common repeats (*, +, ?) when applied to a single character appear as -two-byte items using the following opcodes: - - OP_STAR - OP_MINSTAR - OP_PLUS - OP_MINPLUS - OP_QUERY - OP_MINQUERY - -Those with "MIN" in their name are the minimizing versions. Each is followed by -the character that is to be repeated. Other repeats make use of - - OP_UPTO - OP_MINUPTO - OP_EXACT - -which are followed by a two-byte count (most significant first) and the -repeated character. OP_UPTO matches from 0 to the given number. A repeat with a -non-zero minimum and a fixed maximum is coded as an OP_EXACT followed by an -OP_UPTO (or OP_MINUPTO). - - -Repeating character types -------------------------- - -Repeats of things like \d are done exactly as for single characters, except -that instead of a character, the opcode for the type is stored in the data -byte. The opcodes are: - - OP_TYPESTAR - OP_TYPEMINSTAR - OP_TYPEPLUS - OP_TYPEMINPLUS - OP_TYPEQUERY - OP_TYPEMINQUERY - OP_TYPEUPTO - OP_TYPEMINUPTO - OP_TYPEEXACT - - -Matching a character string ---------------------------- - -The OP_CHARS opcode is followed by a one-byte count and then that number of -characters. If there are more than 255 characters in sequence, successive -instances of OP_CHARS are used. - - -Character classes ------------------ - -OP_CLASS is used for a character class, provided there are at least two -characters in the class. If there is only one character, OP_CHARS is used for a -positive class, and OP_NOT for a negative one (that is, for something like -[^a]). Another set of repeating opcodes (OP_NOTSTAR etc.) are used for a -repeated, negated, single-character class. The normal ones (OP_STAR etc.) are -used for a repeated positive single-character class. - -OP_CLASS is followed by a 32-byte bit map containing a 1 -bit for every character that is acceptable. The bits are counted from the least -significant end of each byte. - - -Back references ---------------- - -OP_REF is followed by a single byte containing the reference number. - - -Repeating character classes and back references ------------------------------------------------ - -Single-character classes are handled specially (see above). This applies to -OP_CLASS and OP_REF. In both cases, the repeat information follows the base -item. The matching code looks at the following opcode to see if it is one of - - OP_CRSTAR - OP_CRMINSTAR - OP_CRPLUS - OP_CRMINPLUS - OP_CRQUERY - OP_CRMINQUERY - OP_CRRANGE - OP_CRMINRANGE - -All but the last two are just single-byte items. The others are followed by -four bytes of data, comprising the minimum and maximum repeat counts. - - -Brackets and alternation ------------------------- - -A pair of non-identifying (round) brackets is wrapped round each expression at -compile time, so alternation always happens in the context of brackets. -Non-identifying brackets use the opcode OP_BRA, while identifying brackets use -OP_BRA+1, OP_BRA+2, etc. [Note for North Americans: "bracket" to some English -speakers, including myself, can be round, square, or curly. Hence this usage.] - -A bracket opcode is followed by two bytes which give the offset to the next -alternative OP_ALT or, if there aren't any branches, to the matching KET -opcode. Each OP_ALT is followed by two bytes giving the offset to the next one, -or to the KET opcode. - -OP_KET is used for subpatterns that do not repeat indefinitely, while -OP_KETRMIN and OP_KETRMAX are used for indefinite repetitions, minimally or -maximally respectively. All three are followed by two bytes giving (as a -positive number) the offset back to the matching BRA opcode. - -If a subpattern is quantified such that it is permitted to match zero times, it -is preceded by one of OP_BRAZERO or OP_BRAMINZERO. These are single-byte -opcodes which tell the matcher that skipping this subpattern entirely is a -valid branch. - -A subpattern with an indefinite maximum repetition is replicated in the -compiled data its minimum number of times (or once with a BRAZERO if the -minimum is zero), with the final copy terminating with a KETRMIN or KETRMAX as -appropriate. - -A subpattern with a bounded maximum repetition is replicated in a nested -fashion up to the maximum number of times, with BRAZERO or BRAMINZERO before -each replication after the minimum, so that, for example, (abc){2,5} is -compiled as (abc)(abc)((abc)((abc)(abc)?)?)?. The 200-bracket limit does not -apply to these internally generated brackets. - - -Assertions ----------- - -Forward assertions are just like other subpatterns, but starting with one of -the opcodes OP_ASSERT or OP_ASSERT_NOT. Backward assertions use the opcodes -OP_ASSERTBACK and OP_ASSERTBACK_NOT, and the first opcode inside the assertion -is OP_REVERSE, followed by a two byte count of the number of characters to move -back the pointer in the subject string. A separate count is present in each -alternative of a lookbehind assertion, allowing them to have different fixed -lengths. - - -Once-only subpatterns ---------------------- - -These are also just like other subpatterns, but they start with the opcode -OP_ONCE. - - -Conditional subpatterns ------------------------ - -These are like other subpatterns, but they start with the opcode OP_COND. If -the condition is a back reference, this is stored at the start of the -subpattern using the opcode OP_CREF followed by one byte containing the -reference number. Otherwise, a conditional subpattern will always start with -one of the assertions. - - -Changing options ----------------- - -If any of the /i, /m, or /s options are changed within a parenthesized group, -an OP_OPT opcode is compiled, followed by one byte containing the new settings -of these flags. If there are several alternatives in a group, there is an -occurrence of OP_OPT at the start of all those following the first options -change, to set appropriate options for the start of the alternative. -Immediately after the end of the group there is another such item to reset the -flags to their previous values. Other changes of flag within the pattern can be -handled entirely at compile time, and so do not cause anything to be put into -the compiled data. - - -Philip Hazel -January 1999 diff --git a/ext/pcre/pcrelib/chartables.c b/ext/pcre/pcrelib/chartables.c deleted file mode 100644 index 5ef8089a93..0000000000 --- a/ext/pcre/pcrelib/chartables.c +++ /dev/null @@ -1,146 +0,0 @@ -/************************************************* -* Perl-Compatible Regular Expressions * -*************************************************/ - -/* This file is automatically written by the dftables auxiliary -program. If you edit it by hand, you might like to edit the Makefile to -prevent its ever being regenerated. - -This file is #included in the compilation of pcre.c to build the default -character tables which are used when no tables are passed to the compile -function. */ - -static unsigned char pcre_default_tables[] = { - -/* This table is a lower casing table. */ - - 0, 1, 2, 3, 4, 5, 6, 7, - 8, 9, 10, 11, 12, 13, 14, 15, - 16, 17, 18, 19, 20, 21, 22, 23, - 24, 25, 26, 27, 28, 29, 30, 31, - 32, 33, 34, 35, 36, 37, 38, 39, - 40, 41, 42, 43, 44, 45, 46, 47, - 48, 49, 50, 51, 52, 53, 54, 55, - 56, 57, 58, 59, 60, 61, 62, 63, - 64, 97, 98, 99,100,101,102,103, - 104,105,106,107,108,109,110,111, - 112,113,114,115,116,117,118,119, - 120,121,122, 91, 92, 93, 94, 95, - 96, 97, 98, 99,100,101,102,103, - 104,105,106,107,108,109,110,111, - 112,113,114,115,116,117,118,119, - 120,121,122,123,124,125,126,127, - 128,129,130,131,132,133,134,135, - 136,137,138,139,140,141,142,143, - 144,145,146,147,148,149,150,151, - 152,153,154,155,156,157,158,159, - 160,161,162,163,164,165,166,167, - 168,169,170,171,172,173,174,175, - 176,177,178,179,180,181,182,183, - 184,185,186,187,188,189,190,191, - 192,193,194,195,196,197,198,199, - 200,201,202,203,204,205,206,207, - 208,209,210,211,212,213,214,215, - 216,217,218,219,220,221,222,223, - 224,225,226,227,228,229,230,231, - 232,233,234,235,236,237,238,239, - 240,241,242,243,244,245,246,247, - 248,249,250,251,252,253,254,255, - -/* This table is a case flipping table. */ - - 0, 1, 2, 3, 4, 5, 6, 7, - 8, 9, 10, 11, 12, 13, 14, 15, - 16, 17, 18, 19, 20, 21, 22, 23, - 24, 25, 26, 27, 28, 29, 30, 31, - 32, 33, 34, 35, 36, 37, 38, 39, - 40, 41, 42, 43, 44, 45, 46, 47, - 48, 49, 50, 51, 52, 53, 54, 55, - 56, 57, 58, 59, 60, 61, 62, 63, - 64, 97, 98, 99,100,101,102,103, - 104,105,106,107,108,109,110,111, - 112,113,114,115,116,117,118,119, - 120,121,122, 91, 92, 93, 94, 95, - 96, 65, 66, 67, 68, 69, 70, 71, - 72, 73, 74, 75, 76, 77, 78, 79, - 80, 81, 82, 83, 84, 85, 86, 87, - 88, 89, 90,123,124,125,126,127, - 128,129,130,131,132,133,134,135, - 136,137,138,139,140,141,142,143, - 144,145,146,147,148,149,150,151, - 152,153,154,155,156,157,158,159, - 160,161,162,163,164,165,166,167, - 168,169,170,171,172,173,174,175, - 176,177,178,179,180,181,182,183, - 184,185,186,187,188,189,190,191, - 192,193,194,195,196,197,198,199, - 200,201,202,203,204,205,206,207, - 208,209,210,211,212,213,214,215, - 216,217,218,219,220,221,222,223, - 224,225,226,227,228,229,230,231, - 232,233,234,235,236,237,238,239, - 240,241,242,243,244,245,246,247, - 248,249,250,251,252,253,254,255, - -/* This table contains bit maps for digits, 'word' chars, and white -space. Each map is 32 bytes long and the bits run from the least -significant end of each byte. */ - - 0x00,0x00,0x00,0x00,0x00,0x00,0xff,0x03, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - - 0x00,0x00,0x00,0x00,0x00,0x00,0xff,0x03, - 0xfe,0xff,0xff,0x87,0xfe,0xff,0xff,0x07, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - - 0x00,0x3e,0x00,0x00,0x01,0x00,0x00,0x00, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00 , - -/* This table identifies various classes of character by individual bits: - 0x01 white space character - 0x02 letter - 0x04 decimal digit - 0x08 hexadecimal digit - 0x10 alphanumeric or '_' - 0x80 regular expression metacharacter or binary zero -*/ - - 0x80,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 0- 7 */ - 0x00,0x01,0x01,0x01,0x01,0x01,0x00,0x00, /* 8- 15 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 16- 23 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 24- 31 */ - 0x01,0x00,0x00,0x00,0x80,0x00,0x00,0x00, /* - ' */ - 0x80,0x80,0x80,0x80,0x00,0x00,0x80,0x00, /* ( - / */ - 0x1c,0x1c,0x1c,0x1c,0x1c,0x1c,0x1c,0x1c, /* 0 - 7 */ - 0x1c,0x1c,0x00,0x00,0x00,0x00,0x00,0x80, /* 8 - ? */ - 0x00,0x1a,0x1a,0x1a,0x1a,0x1a,0x1a,0x12, /* @ - G */ - 0x12,0x12,0x12,0x12,0x12,0x12,0x12,0x12, /* H - O */ - 0x12,0x12,0x12,0x12,0x12,0x12,0x12,0x12, /* P - W */ - 0x12,0x12,0x12,0x80,0x00,0x00,0x80,0x10, /* X - _ */ - 0x00,0x1a,0x1a,0x1a,0x1a,0x1a,0x1a,0x12, /* ` - g */ - 0x12,0x12,0x12,0x12,0x12,0x12,0x12,0x12, /* h - o */ - 0x12,0x12,0x12,0x12,0x12,0x12,0x12,0x12, /* p - w */ - 0x12,0x12,0x12,0x80,0x80,0x00,0x00,0x00, /* x -127 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 128-135 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 136-143 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 144-151 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 152-159 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 160-167 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 168-175 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 176-183 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 184-191 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 192-199 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 200-207 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 208-215 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 216-223 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 224-231 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 232-239 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 240-247 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00};/* 248-255 */ - -/* End of chartables.c */ diff --git a/ext/pcre/pcrelib/dftables.c b/ext/pcre/pcrelib/dftables.c deleted file mode 100644 index 7b336e6f1e..0000000000 --- a/ext/pcre/pcrelib/dftables.c +++ /dev/null @@ -1,146 +0,0 @@ -/************************************************* -* Perl-Compatible Regular Expressions * -*************************************************/ - -/* -PCRE is a library of functions to support regular expressions whose syntax -and semantics are as close as possible to those of the Perl 5 language. - -Written by: Philip Hazel - - Copyright (c) 1997-1999 University of Cambridge - ------------------------------------------------------------------------------ -Permission is granted to anyone to use this software for any purpose on any -computer system, and to redistribute it freely, subject to the following -restrictions: - -1. This software is distributed in the hope that it will be useful, - but WITHOUT ANY WARRANTY; without even the implied warranty of - MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. - -2. The origin of this software must not be misrepresented, either by - explicit claim or by omission. - -3. Altered versions must be plainly marked as such, and must not be - misrepresented as being the original software. - -4. If PCRE is embedded in any software that is released under the GNU - General Purpose Licence (GPL), then the terms of that licence shall - supersede any condition above with which it is incompatible. ------------------------------------------------------------------------------ - -See the file Tech.Notes for some information on the internals. -*/ - - -/* This is a support program to generate the file chartables.c, containing -character tables of various kinds. They are built according to the default C -locale and used as the default tables by PCRE. 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 -#include - -#include "internal.h" - -#define DFTABLES /* maketables.c notices this */ -#include "maketables.c" - - -int main(void) -{ -int i; -unsigned const char *tables = pcre_maketables(); - -printf( - "/*************************************************\n" - "* Perl-Compatible Regular Expressions *\n" - "*************************************************/\n\n" - "/* This file is automatically written by the dftables auxiliary \n" - "program. If you edit it by hand, you might like to edit the Makefile to \n" - "prevent its ever being regenerated.\n\n" - "This file is #included in the compilation of pcre.c to build the default\n" - "character tables which are used when no tables are passed to the compile\n" - "function. */\n\n" - "static unsigned char pcre_default_tables[] = {\n\n" - "/* This table is a lower casing table. */\n\n"); - -printf(" "); -for (i = 0; i < 256; i++) - { - if ((i & 7) == 0 && i != 0) printf("\n "); - printf("%3d", *tables++); - if (i != 255) printf(","); - } -printf(",\n\n"); - -printf("/* This table is a case flipping table. */\n\n"); - -printf(" "); -for (i = 0; i < 256; i++) - { - if ((i & 7) == 0 && i != 0) printf("\n "); - printf("%3d", *tables++); - if (i != 255) printf(","); - } -printf(",\n\n"); - -printf( - "/* This table contains bit maps for digits, 'word' chars, and white\n" - "space. Each map is 32 bytes long and the bits run from the least\n" - "significant end of each byte. */\n\n"); - -printf(" "); -for (i = 0; i < cbit_length; i++) - { - if ((i & 7) == 0 && i != 0) - { - if ((i & 31) == 0) printf("\n"); - printf("\n "); - } - printf("0x%02x", *tables++); - if (i != cbit_length - 1) printf(","); - } -printf(" ,\n\n"); - -printf( - "/* This table identifies various classes of character by individual bits:\n" - " 0x%02x white space character\n" - " 0x%02x letter\n" - " 0x%02x decimal digit\n" - " 0x%02x hexadecimal digit\n" - " 0x%02x alphanumeric or '_'\n" - " 0x%02x regular expression metacharacter or binary zero\n*/\n\n", - ctype_space, ctype_letter, ctype_digit, ctype_xdigit, ctype_word, - ctype_meta); - -printf(" "); -for (i = 0; i < 256; i++) - { - if ((i & 7) == 0 && i != 0) - { - printf(" /* "); - if (isprint(i-8)) printf(" %c -", i-8); - else printf("%3d-", i-8); - if (isprint(i-1)) printf(" %c ", i-1); - else printf("%3d", i-1); - printf(" */\n "); - } - printf("0x%02x", *tables++); - if (i != 255) printf(","); - } - -printf("};/* "); -if (isprint(i-8)) printf(" %c -", i-8); - else printf("%3d-", i-8); -if (isprint(i-1)) printf(" %c ", i-1); - else printf("%3d", i-1); -printf(" */\n\n/* End of chartables.c */\n"); - -return 0; -} - -/* End of dftables.c */ diff --git a/ext/pcre/pcrelib/dll.mk b/ext/pcre/pcrelib/dll.mk deleted file mode 100644 index d8b728e57e..0000000000 --- a/ext/pcre/pcrelib/dll.mk +++ /dev/null @@ -1,60 +0,0 @@ -# dll.mk - auxilary Makefile to easy build dll's for mingw32 target -# ver. 0.6 of 1999-03-25 -# -# Homepage of this makefile - http://www.is.lg.ua/~paul/devel/ -# Homepage of original mingw32 project - -# http://www.fu.is.saga-u.ac.jp/~colin/gcc.html -# -# How to use: -# This makefile can: -# 1. Create automatical .def file from list of objects -# 2. Create .dll from objects and .def file, either automatical, or your -# hand-written (maybe) file, which must have same basename as dll -# WARNING! There MUST be object, which name match dll's name. Make sux. -# 3. Create import library from .def (as for .dll, only its name required, -# not dll itself) -# By convention implibs for dll have .dll.a suffix, e.g. libstuff.dll.a -# Why not just libstuff.a? 'Cos that's name for static lib, ok? -# Process divided into 3 phases because: -# 1. Pre-existent .def possible -# 2. Generating implib is enough time-consuming -# -# Variables: -# DLL_LDLIBS - libs for linking dll -# DLL_LDFLAGS - flags for linking dll -# -# By using $(DLL_SUFFIX) instead of 'dll', e.g. stuff.$(DLL_SUFFIX) -# you may help porting makefiles to other platforms -# -# Put this file in your make's include path (e.g. main include dir, for -# more information see include section in make doc). Put in the beginning -# of your own Makefile line "include dll.mk". Specify dependences, e.g.: -# -# Do all stuff in one step -# libstuff.dll.a: $(OBJECTS) stuff.def -# stuff.def: $(OBJECTS) -# -# Steps separated, pre-provided .def, link with user32 -# -# DLL_LDLIBS=-luser32 -# stuff.dll: $(OBJECTS) -# libstuff.dll.a: $(OBJECTS) - - -DLLWRAP=dllwrap -DLLTOOL=dlltool - -DLL_SUFFIX=dll - -.SUFFIXES: .o .$(DLL_SUFFIX) - -_%.def: %.o - $(DLLTOOL) --export-all --output-def $@ $^ - -%.$(DLL_SUFFIX): %.o - $(DLLWRAP) --dllname $(notdir $@) --driver-name $(CC) --def $*.def -o $@ $(filter %.o,$^) $(DLL_LDFLAGS) $(DLL_LDLIBS) - -lib%.$(DLL_SUFFIX).a:%.def - $(DLLTOOL) --dllname $(notdir $*.dll) --def $< --output-lib $@ - -# End diff --git a/ext/pcre/pcrelib/get.c b/ext/pcre/pcrelib/get.c deleted file mode 100644 index 035668e301..0000000000 --- a/ext/pcre/pcrelib/get.c +++ /dev/null @@ -1,189 +0,0 @@ -/************************************************* -* Perl-Compatible Regular Expressions * -*************************************************/ - -/* -This is a library of functions to support regular expressions whose syntax -and semantics are as close as possible to those of the Perl 5 language. See -the file Tech.Notes for some information on the internals. - -Written by: Philip Hazel - - Copyright (c) 1997-1999 University of Cambridge - ------------------------------------------------------------------------------ -Permission is granted to anyone to use this software for any purpose on any -computer system, and to redistribute it freely, subject to the following -restrictions: - -1. This software is distributed in the hope that it will be useful, - but WITHOUT ANY WARRANTY; without even the implied warranty of - MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. - -2. The origin of this software must not be misrepresented, either by - explicit claim or by omission. - -3. Altered versions must be plainly marked as such, and must not be - misrepresented as being the original software. - -4. If PCRE is embedded in any software that is released under the GNU - General Purpose Licence (GPL), then the terms of that licence shall - supersede any condition above with which it is incompatible. ------------------------------------------------------------------------------ -*/ - -/* This module contains some convenience functions for extracting substrings -from the subject string after a regex match has succeeded. The original idea -for these functions came from Scott Wimer . */ - - -/* Include the internals header, which itself includes Standard C headers plus -the external pcre header. */ - -#include "internal.h" - - - -/************************************************* -* Copy captured string to given buffer * -*************************************************/ - -/* This function copies a single captured substring into a given buffer. -Note that we use memcpy() rather than strncpy() in case there are binary zeros -in the string. - -Arguments: - subject the subject string that was matched - ovector pointer to the offsets table - stringcount the number of substrings that were captured - (i.e. the yield of the pcre_exec call, unless - that was zero, in which case it should be 1/3 - of the offset table size) - stringnumber the number of the required substring - buffer where to put the substring - size the size of the buffer - -Returns: if successful: - the length of the copied string, not including the zero - that is put on the end; can be zero - if not successful: - PCRE_ERROR_NOMEMORY (-6) buffer too small - PCRE_ERROR_NOSUBSTRING (-7) no such captured substring -*/ - -int -pcre_copy_substring(const char *subject, int *ovector, int stringcount, - int stringnumber, char *buffer, int size) -{ -int yield; -if (stringnumber < 0 || stringnumber >= stringcount) - return PCRE_ERROR_NOSUBSTRING; -stringnumber *= 2; -yield = ovector[stringnumber+1] - ovector[stringnumber]; -if (size < yield + 1) return PCRE_ERROR_NOMEMORY; -memcpy(buffer, subject + ovector[stringnumber], yield); -buffer[yield] = 0; -return yield; -} - - - -/************************************************* -* Copy all captured strings to new store * -*************************************************/ - -/* This function gets one chunk of store and builds a list of pointers and all -of the captured substrings in it. A NULL pointer is put on the end of the list. - -Arguments: - subject the subject string that was matched - ovector pointer to the offsets table - stringcount the number of substrings that were captured - (i.e. the yield of the pcre_exec call, unless - that was zero, in which case it should be 1/3 - of the offset table size) - listptr set to point to the list of pointers - -Returns: if successful: 0 - if not successful: - PCRE_ERROR_NOMEMORY (-6) failed to get store -*/ - -int -pcre_get_substring_list(const char *subject, int *ovector, int stringcount, - const char ***listptr) -{ -int i; -int size = sizeof(char *); -int double_count = stringcount * 2; -char **stringlist; -char *p; - -for (i = 0; i < double_count; i += 2) - size += sizeof(char *) + ovector[i+1] - ovector[i] + 1; - -stringlist = (char **)(pcre_malloc)(size); -if (stringlist == NULL) return PCRE_ERROR_NOMEMORY; - -*listptr = (const char **)stringlist; -p = (char *)(stringlist + stringcount + 1); - -for (i = 0; i < double_count; i += 2) - { - int len = ovector[i+1] - ovector[i]; - memcpy(p, subject + ovector[i], len); - *stringlist++ = p; - p += len; - *p++ = 0; - } - -*stringlist = NULL; -return 0; -} - - - -/************************************************* -* Copy captured string to new store * -*************************************************/ - -/* This function copies a single captured substring into a piece of new -store - -Arguments: - subject the subject string that was matched - ovector pointer to the offsets table - stringcount the number of substrings that were captured - (i.e. the yield of the pcre_exec call, unless - that was zero, in which case it should be 1/3 - of the offset table size) - stringnumber the number of the required substring - stringptr where to put a pointer to the substring - -Returns: if successful: - the length of the string, not including the zero that - is put on the end; can be zero - if not successful: - PCRE_ERROR_NOMEMORY (-6) failed to get store - PCRE_ERROR_NOSUBSTRING (-7) substring not present -*/ - -int -pcre_get_substring(const char *subject, int *ovector, int stringcount, - int stringnumber, const char **stringptr) -{ -int yield; -char *substring; -if (stringnumber < 0 || stringnumber >= stringcount) - return PCRE_ERROR_NOSUBSTRING; -stringnumber *= 2; -yield = ovector[stringnumber+1] - ovector[stringnumber]; -substring = (char *)(pcre_malloc)(yield + 1); -if (substring == NULL) return PCRE_ERROR_NOMEMORY; -memcpy(substring, subject + ovector[stringnumber], yield); -substring[yield] = 0; -*stringptr = substring; -return yield; -} - -/* End of get.c */ diff --git a/ext/pcre/pcrelib/internal.h b/ext/pcre/pcrelib/internal.h deleted file mode 100644 index 13df1d60f1..0000000000 --- a/ext/pcre/pcrelib/internal.h +++ /dev/null @@ -1,343 +0,0 @@ -/************************************************* -* Perl-Compatible Regular Expressions * -*************************************************/ - - -/* This is a library of functions to support regular expressions whose syntax -and semantics are as close as possible to those of the Perl 5 language. See -the file Tech.Notes for some information on the internals. - -Written by: Philip Hazel - - Copyright (c) 1997-1999 University of Cambridge - ------------------------------------------------------------------------------ -Permission is granted to anyone to use this software for any purpose on any -computer system, and to redistribute it freely, subject to the following -restrictions: - -1. This software is distributed in the hope that it will be useful, - but WITHOUT ANY WARRANTY; without even the implied warranty of - MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. - -2. The origin of this software must not be misrepresented, either by - explicit claim or by omission. - -3. Altered versions must be plainly marked as such, and must not be - misrepresented as being the original software. - -4. If PCRE is embedded in any software that is released under the GNU - General Purpose Licence (GPL), then the terms of that licence shall - supersede any condition above with which it is incompatible. ------------------------------------------------------------------------------ -*/ - -/* This header contains definitions that are shared between the different -modules, but which are not relevant to the outside. */ - -/* To cope with SunOS4 and other systems that lack memmove() but have bcopy(), -define a macro for memmove() if USE_BCOPY is defined. */ - -#ifdef USE_BCOPY -#undef memmove /* some systems may have a macro */ -#define memmove(a, b, c) bcopy(b, a, c) -#endif - -/* Standard C headers plus the external interface definition */ - -#include -#include -#include -#include -#include -#include -#include "pcre.h" - -/* In case there is no definition of offsetof() provided - though any proper -Standard C system should have one. */ - -#ifndef offsetof -#define offsetof(p_type,field) ((size_t)&(((p_type *)0)->field)) -#endif - -/* These are the public options that can change during matching. */ - -#define PCRE_IMS (PCRE_CASELESS|PCRE_MULTILINE|PCRE_DOTALL) - -/* Private options flags start at the most significant end of the four bytes, -but skip the top bit so we can use ints for convenience without getting tangled -with negative values. The public options defined in pcre.h start at the least -significant end. Make sure they don't overlap, though now that we have expanded -to four bytes there is plenty of space. */ - -#define PCRE_FIRSTSET 0x40000000 /* first_char is set */ -#define PCRE_REQCHSET 0x20000000 /* req_char is set */ -#define PCRE_STARTLINE 0x10000000 /* start after \n for multiline */ -#define PCRE_INGROUP 0x08000000 /* compiling inside a group */ -#define PCRE_ICHANGED 0x04000000 /* i option changes within regex */ - -/* Options for the "extra" block produced by pcre_study(). */ - -#define PCRE_STUDY_MAPPED 0x01 /* a map of starting chars exists */ - -/* Masks for identifying the public options which are permitted at compile -time, run time or study time, respectively. */ - -#define PUBLIC_OPTIONS \ - (PCRE_CASELESS|PCRE_EXTENDED|PCRE_ANCHORED|PCRE_MULTILINE| \ - PCRE_DOTALL|PCRE_DOLLAR_ENDONLY|PCRE_EXTRA|PCRE_UNGREEDY) - -#define PUBLIC_EXEC_OPTIONS \ - (PCRE_ANCHORED|PCRE_NOTBOL|PCRE_NOTEOL|PCRE_NOTEMPTY) - -#define PUBLIC_STUDY_OPTIONS 0 /* None defined */ - -/* Magic number to provide a small check against being handed junk. */ - -#define MAGIC_NUMBER 0x50435245UL /* 'PCRE' */ - -/* Miscellaneous definitions */ - -typedef int BOOL; - -#define FALSE 0 -#define TRUE 1 - -/* These are escaped items that aren't just an encoding of a particular data -value such as \n. They must have non-zero values, as check_escape() returns -their negation. Also, they must appear in the same order as in the opcode -definitions below, up to ESC_z. The final one must be ESC_REF as subsequent -values are used for \1, \2, \3, etc. There is a test in the code for an escape -greater than ESC_b and less than ESC_X to detect the types that may be -repeated. If any new escapes are put in-between that don't consume a character, -that code will have to change. */ - -enum { ESC_A = 1, ESC_B, ESC_b, ESC_D, ESC_d, ESC_S, ESC_s, ESC_W, ESC_w, - ESC_Z, ESC_z, ESC_REF }; - -/* Opcode table: OP_BRA must be last, as all values >= it are used for brackets -that extract substrings. Starting from 1 (i.e. after OP_END), the values up to -OP_EOD must correspond in order to the list of escapes immediately above. */ - -enum { - OP_END, /* End of pattern */ - - /* Values corresponding to backslashed metacharacters */ - - OP_SOD, /* Start of data: \A */ - OP_NOT_WORD_BOUNDARY, /* \B */ - OP_WORD_BOUNDARY, /* \b */ - OP_NOT_DIGIT, /* \D */ - OP_DIGIT, /* \d */ - OP_NOT_WHITESPACE, /* \S */ - OP_WHITESPACE, /* \s */ - OP_NOT_WORDCHAR, /* \W */ - OP_WORDCHAR, /* \w */ - OP_EODN, /* End of data or \n at end of data: \Z. */ - OP_EOD, /* End of data: \z */ - - OP_OPT, /* Set runtime options */ - OP_CIRC, /* Start of line - varies with multiline switch */ - OP_DOLL, /* End of line - varies with multiline switch */ - OP_ANY, /* Match any character */ - OP_CHARS, /* Match string of characters */ - OP_NOT, /* Match anything but the following char */ - - OP_STAR, /* The maximizing and minimizing versions of */ - OP_MINSTAR, /* all these opcodes must come in pairs, with */ - OP_PLUS, /* the minimizing one second. */ - OP_MINPLUS, /* This first set applies to single characters */ - OP_QUERY, - OP_MINQUERY, - OP_UPTO, /* From 0 to n matches */ - OP_MINUPTO, - OP_EXACT, /* Exactly n matches */ - - OP_NOTSTAR, /* The maximizing and minimizing versions of */ - OP_NOTMINSTAR, /* all these opcodes must come in pairs, with */ - OP_NOTPLUS, /* the minimizing one second. */ - OP_NOTMINPLUS, /* This first set applies to "not" single characters */ - OP_NOTQUERY, - OP_NOTMINQUERY, - OP_NOTUPTO, /* From 0 to n matches */ - OP_NOTMINUPTO, - OP_NOTEXACT, /* Exactly n matches */ - - OP_TYPESTAR, /* The maximizing and minimizing versions of */ - OP_TYPEMINSTAR, /* all these opcodes must come in pairs, with */ - OP_TYPEPLUS, /* the minimizing one second. These codes must */ - OP_TYPEMINPLUS, /* be in exactly the same order as those above. */ - OP_TYPEQUERY, /* This set applies to character types such as \d */ - OP_TYPEMINQUERY, - OP_TYPEUPTO, /* From 0 to n matches */ - OP_TYPEMINUPTO, - OP_TYPEEXACT, /* Exactly n matches */ - - OP_CRSTAR, /* The maximizing and minimizing versions of */ - OP_CRMINSTAR, /* all these opcodes must come in pairs, with */ - OP_CRPLUS, /* the minimizing one second. These codes must */ - OP_CRMINPLUS, /* be in exactly the same order as those above. */ - OP_CRQUERY, /* These are for character classes and back refs */ - OP_CRMINQUERY, - OP_CRRANGE, /* These are different to the three seta above. */ - OP_CRMINRANGE, - - OP_CLASS, /* Match a character class */ - OP_REF, /* Match a back reference */ - - OP_ALT, /* Start of alternation */ - OP_KET, /* End of group that doesn't have an unbounded repeat */ - OP_KETRMAX, /* These two must remain together and in this */ - OP_KETRMIN, /* order. They are for groups the repeat for ever. */ - - /* The assertions must come before ONCE and COND */ - - OP_ASSERT, /* Positive lookahead */ - OP_ASSERT_NOT, /* Negative lookahead */ - OP_ASSERTBACK, /* Positive lookbehind */ - OP_ASSERTBACK_NOT, /* Negative lookbehind */ - OP_REVERSE, /* Move pointer back - used in lookbehind assertions */ - - /* ONCE and COND must come after the assertions, with ONCE first, as there's - a test for >= ONCE for a subpattern that isn't an assertion. */ - - OP_ONCE, /* Once matched, don't back up into the subpattern */ - OP_COND, /* Conditional group */ - OP_CREF, /* Used to hold an extraction string number */ - - OP_BRAZERO, /* These two must remain together and in this */ - OP_BRAMINZERO, /* order. */ - - OP_BRA /* This and greater values are used for brackets that - extract substrings. */ -}; - -/* The highest extraction number. This is limited by the number of opcodes -left after OP_BRA, i.e. 255 - OP_BRA. We actually set it somewhat lower. */ - -#define EXTRACT_MAX 99 - -/* The texts of compile-time error messages are defined as macros here so that -they can be accessed by the POSIX wrapper and converted into error codes. Yes, -I could have used error codes in the first place, but didn't feel like changing -just to accommodate the POSIX wrapper. */ - -#define ERR1 "\\ at end of pattern" -#define ERR2 "\\c at end of pattern" -#define ERR3 "unrecognized character follows \\" -#define ERR4 "numbers out of order in {} quantifier" -#define ERR5 "number too big in {} quantifier" -#define ERR6 "missing terminating ] for character class" -#define ERR7 "invalid escape sequence in character class" -#define ERR8 "range out of order in character class" -#define ERR9 "nothing to repeat" -#define ERR10 "operand of unlimited repeat could match the empty string" -#define ERR11 "internal error: unexpected repeat" -#define ERR12 "unrecognized character after (?" -#define ERR13 "too many capturing parenthesized sub-patterns" -#define ERR14 "missing )" -#define ERR15 "back reference to non-existent subpattern" -#define ERR16 "erroffset passed as NULL" -#define ERR17 "unknown option bit(s) set" -#define ERR18 "missing ) after comment" -#define ERR19 "too many sets of parentheses" -#define ERR20 "regular expression too large" -#define ERR21 "failed to get memory" -#define ERR22 "unmatched parentheses" -#define ERR23 "internal error: code overflow" -#define ERR24 "unrecognized character after (?<" -#define ERR25 "lookbehind assertion is not fixed length" -#define ERR26 "malformed number after (?(" -#define ERR27 "conditional group contains more than two branches" -#define ERR28 "assertion expected after (?(" - -/* All character handling must be done as unsigned characters. Otherwise there -are problems with top-bit-set characters and functions such as isspace(). -However, we leave the interface to the outside world as char *, because that -should make things easier for callers. We define a short type for unsigned char -to save lots of typing. I tried "uchar", but it causes problems on Digital -Unix, where it is defined in sys/types, so use "uschar" instead. */ - -typedef unsigned char uschar; - -/* The real format of the start of the pcre block; the actual code vector -runs on as long as necessary after the end. */ - -typedef struct real_pcre { - unsigned long int magic_number; - const unsigned char *tables; - unsigned long int options; - uschar top_bracket; - uschar top_backref; - uschar first_char; - uschar req_char; - uschar code[1]; -} real_pcre; - -/* The real format of the extra block returned by pcre_study(). */ - -typedef struct real_pcre_extra { - uschar options; - uschar start_bits[32]; -} real_pcre_extra; - - -/* Structure for passing "static" information around between the functions -doing the compiling, so that they are thread-safe. */ - -typedef struct compile_data { - const uschar *lcc; /* Points to lower casing table */ - const uschar *fcc; /* Points to case-flipping table */ - const uschar *cbits; /* Points to character type table */ - const uschar *ctypes; /* Points to table of type maps */ -} compile_data; - -/* Structure for passing "static" information around between the functions -doing the matching, so that they are thread-safe. */ - -typedef struct match_data { - int errorcode; /* As it says */ - int *offset_vector; /* Offset vector */ - int offset_end; /* One past the end */ - int offset_max; /* The maximum usable for return data */ - const uschar *lcc; /* Points to lower casing table */ - const uschar *ctypes; /* Points to table of type maps */ - BOOL offset_overflow; /* Set if too many extractions */ - BOOL notbol; /* NOTBOL flag */ - BOOL noteol; /* NOTEOL flag */ - BOOL endonly; /* Dollar not before final \n */ - BOOL notempty; /* Empty string match not wanted */ - const uschar *start_subject; /* Start of the subject string */ - const uschar *end_subject; /* End of the subject string */ - const uschar *start_match; /* Start of this match attempt */ - const uschar *end_match_ptr; /* Subject position at end match */ - int end_offset_top; /* Highwater mark at end of match */ -} match_data; - -/* Bit definitions for entries in the pcre_ctypes table. */ - -#define ctype_space 0x01 -#define ctype_letter 0x02 -#define ctype_digit 0x04 -#define ctype_xdigit 0x08 -#define ctype_word 0x10 /* alphameric or '_' */ -#define ctype_meta 0x80 /* regexp meta char or zero (end pattern) */ - -/* Offsets for the bitmap tables in pcre_cbits. Each table contains a set -of bits for a class map. */ - -#define cbit_digit 0 /* for \d */ -#define cbit_word 32 /* for \w */ -#define cbit_space 64 /* for \s */ -#define cbit_length 96 /* Length of the cbits table */ - -/* Offsets of the various tables from the base tables pointer, and -total length. */ - -#define lcc_offset 0 -#define fcc_offset 256 -#define cbits_offset 512 -#define ctypes_offset (cbits_offset + cbit_length) -#define tables_length (ctypes_offset + 256) - -/* End of internal.h */ diff --git a/ext/pcre/pcrelib/maketables.c b/ext/pcre/pcrelib/maketables.c deleted file mode 100644 index eb5fcd107e..0000000000 --- a/ext/pcre/pcrelib/maketables.c +++ /dev/null @@ -1,113 +0,0 @@ -/************************************************* -* Perl-Compatible Regular Expressions * -*************************************************/ - -/* -PCRE is a library of functions to support regular expressions whose syntax -and semantics are as close as possible to those of the Perl 5 language. - -Written by: Philip Hazel - - Copyright (c) 1997-1999 University of Cambridge - ------------------------------------------------------------------------------ -Permission is granted to anyone to use this software for any purpose on any -computer system, and to redistribute it freely, subject to the following -restrictions: - -1. This software is distributed in the hope that it will be useful, - but WITHOUT ANY WARRANTY; without even the implied warranty of - MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. - -2. The origin of this software must not be misrepresented, either by - explicit claim or by omission. - -3. Altered versions must be plainly marked as such, and must not be - misrepresented as being the original software. - -4. If PCRE is embedded in any software that is released under the GNU - General Purpose Licence (GPL), then the terms of that licence shall - supersede any condition above with which it is incompatible. ------------------------------------------------------------------------------ - -See the file Tech.Notes for some information on the internals. -*/ - - -/* This file is compiled on its own as part of the PCRE library. However, -it is also included in the compilation of dftables.c, in which case the macro -DFTABLES is defined. */ - -#ifndef DFTABLES -#include "internal.h" -#endif - - - -/************************************************* -* Create PCRE character tables * -*************************************************/ - -/* This function builds a set of character tables for use by PCRE and returns -a pointer to them. They are build using the ctype functions, and consequently -their contents will depend upon the current locale setting. When compiled as -part of the library, the store is obtained via pcre_malloc(), but when compiled -inside dftables, use malloc(). - -Arguments: none -Returns: pointer to the contiguous block of data -*/ - -unsigned const char * -pcre_maketables(void) -{ -unsigned char *yield, *p; -int i; - -#ifndef DFTABLES -yield = (unsigned char*)(pcre_malloc)(tables_length); -#else -yield = (unsigned char*)malloc(tables_length); -#endif - -if (yield == NULL) return NULL; -p = yield; - -/* First comes the lower casing table */ - -for (i = 0; i < 256; i++) *p++ = tolower(i); - -/* Next the case-flipping table */ - -for (i = 0; i < 256; i++) *p++ = islower(i)? toupper(i) : tolower(i); - -/* Then the character class tables */ - -memset(p, 0, cbit_length); -for (i = 0; i < 256; i++) - { - if (isdigit(i)) p[cbit_digit + i/8] |= 1 << (i&7); - if (isalnum(i) || i == '_') - p[cbit_word + i/8] |= 1 << (i&7); - if (isspace(i)) p[cbit_space + i/8] |= 1 << (i&7); - } -p += cbit_length; - -/* Finally, the character type table */ - -for (i = 0; i < 256; i++) - { - int x = 0; - if (isspace(i)) x += ctype_space; - if (isalpha(i)) x += ctype_letter; - if (isdigit(i)) x += ctype_digit; - if (isxdigit(i)) x += ctype_xdigit; - if (isalnum(i) || i == '_') x += ctype_word; - if (strchr("*+?{^.$|()[", i) != 0) x += ctype_meta; - *p++ = x; - } - -return yield; -} - -/* End of maketables.c */ diff --git a/ext/pcre/pcrelib/pcre.3 b/ext/pcre/pcrelib/pcre.3 deleted file mode 100644 index 3f4ad4f659..0000000000 --- a/ext/pcre/pcrelib/pcre.3 +++ /dev/null @@ -1,1499 +0,0 @@ -.TH PCRE 3 -.SH NAME -pcre - Perl-compatible regular expressions. -.SH SYNOPSIS -.B #include -.PP -.SM -.br -.B pcre *pcre_compile(const char *\fIpattern\fR, int \fIoptions\fR, -.ti +5n -.B const char **\fIerrptr\fR, int *\fIerroffset\fR, -.ti +5n -.B const unsigned char *\fItableptr\fR); -.PP -.br -.B pcre_extra *pcre_study(const pcre *\fIcode\fR, int \fIoptions\fR, -.ti +5n -.B const char **\fIerrptr\fR); -.PP -.br -.B int pcre_exec(const pcre *\fIcode\fR, "const pcre_extra *\fIextra\fR," -.ti +5n -.B "const char *\fIsubject\fR," int \fIlength\fR, int \fIstartoffset\fR, -.ti +5n -.B int \fIoptions\fR, int *\fIovector\fR, int \fIovecsize\fR); -.PP -.br -.B int pcre_copy_substring(const char *\fIsubject\fR, int *\fIovector\fR, -.ti +5n -.B int \fIstringcount\fR, int \fIstringnumber\fR, char *\fIbuffer\fR, -.ti +5n -.B int \fIbuffersize\fR); -.PP -.br -.B int pcre_get_substring(const char *\fIsubject\fR, int *\fIovector\fR, -.ti +5n -.B int \fIstringcount\fR, int \fIstringnumber\fR, -.ti +5n -.B const char **\fIstringptr\fR); -.PP -.br -.B int pcre_get_substring_list(const char *\fIsubject\fR, -.ti +5n -.B int *\fIovector\fR, int \fIstringcount\fR, "const char ***\fIlistptr\fR);" -.PP -.br -.B const unsigned char *pcre_maketables(void); -.PP -.br -.B int pcre_info(const pcre *\fIcode\fR, int *\fIoptptr\fR, int -.B *\fIfirstcharptr\fR); -.PP -.br -.B char *pcre_version(void); -.PP -.br -.B void *(*pcre_malloc)(size_t); -.PP -.br -.B void (*pcre_free)(void *); - - - -.SH DESCRIPTION -The PCRE library is a set of functions that implement regular expression -pattern matching using the same syntax and semantics as Perl 5, with just a few -differences (see below). The current implementation corresponds to Perl 5.005. - -PCRE has its own native API, which is described in this document. There is also -a set of wrapper functions that correspond to the POSIX API. These are -described in the \fBpcreposix\fR documentation. - -The native API function prototypes are defined in the header file \fBpcre.h\fR, -and on Unix systems the library itself is called \fBlibpcre.a\fR, so can be -accessed by adding \fB-lpcre\fR to the command for linking an application which -calls it. - -The functions \fBpcre_compile()\fR, \fBpcre_study()\fR, and \fBpcre_exec()\fR -are used for compiling and matching regular expressions, while -\fBpcre_copy_substring()\fR, \fBpcre_get_substring()\fR, and -\fBpcre_get_substring_list()\fR are convenience functions for extracting -captured substrings from a matched subject string. The function -\fBpcre_maketables()\fR is used (optionally) to build a set of character tables -in the current locale for passing to \fBpcre_compile()\fR. - -The function \fBpcre_info()\fR is used to find out information about a compiled -pattern, while the function \fBpcre_version()\fR returns a pointer to a string -containing the version of PCRE and its date of release. - -The global variables \fBpcre_malloc\fR and \fBpcre_free\fR initially contain -the entry points of the standard \fBmalloc()\fR and \fBfree()\fR functions -respectively. PCRE calls the memory management functions via these variables, -so a calling program can replace them if it wishes to intercept the calls. This -should be done before calling any PCRE functions. - - -.SH MULTI-THREADING -The PCRE functions can be used in multi-threading applications, with the -proviso that the memory management functions pointed to by \fBpcre_malloc\fR -and \fBpcre_free\fR are shared by all threads. - -The compiled form of a regular expression is not altered during matching, so -the same compiled pattern can safely be used by several threads at once. - - -.SH COMPILING A PATTERN -The function \fBpcre_compile()\fR is called to compile a pattern into an -internal form. The pattern is a C string terminated by a binary zero, and -is passed in the argument \fIpattern\fR. A pointer to a single block of memory -that is obtained via \fBpcre_malloc\fR is returned. This contains the -compiled code and related data. The \fBpcre\fR type is defined for this for -convenience, but in fact \fBpcre\fR is just a typedef for \fBvoid\fR, since the -contents of the block are not externally defined. It is up to the caller to -free the memory when it is no longer required. -.PP -The size of a compiled pattern is roughly proportional to the length of the -pattern string, except that each character class (other than those containing -just a single character, negated or not) requires 33 bytes, and repeat -quantifiers with a minimum greater than one or a bounded maximum cause the -relevant portions of the compiled pattern to be replicated. -.PP -The \fIoptions\fR argument contains independent bits that affect the -compilation. It should be zero if no options are required. Some of the options, -in particular, those that are compatible with Perl, can also be set and unset -from within the pattern (see the detailed description of regular expressions -below). For these options, the contents of the \fIoptions\fR argument specifies -their initial settings at the start of compilation and execution. The -PCRE_ANCHORED option can be set at the time of matching as well as at compile -time. -.PP -If \fIerrptr\fR is NULL, \fBpcre_compile()\fR returns NULL immediately. -Otherwise, if compilation of a pattern fails, \fBpcre_compile()\fR returns -NULL, and sets the variable pointed to by \fIerrptr\fR to point to a textual -error message. The offset from the start of the pattern to the character where -the error was discovered is placed in the variable pointed to by -\fIerroffset\fR, which must not be NULL. If it is, an immediate error is given. -.PP -If the final argument, \fItableptr\fR, is NULL, PCRE uses a default set of -character tables which are built when it is compiled, using the default C -locale. Otherwise, \fItableptr\fR must be the result of a call to -\fBpcre_maketables()\fR. See the section on locale support below. -.PP -The following option bits are defined in the 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 start of the string which 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_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. - - 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 the final character if it is a newline (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. - - PCRE_DOTALL - -If this bit is set, a dot metacharater in the pattern matches all characters, -including newlines. Without it, newlines are excluded. This option is -equivalent to Perl's /s option. A negative class such as [^a] always matches a -newline character, independent of the setting of this option. - - PCRE_EXTENDED - -If this bit is set, whitespace data characters in the pattern are totally -ignored except when escaped or inside a character class, and characters between -an unescaped # outside a character class and the next newline character, -inclusive, are also ignored. This is equivalent to Perl's /x option, and 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 turns on additional functionality of PCRE that is incompatible with -Perl. 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. There are at present no other features -controlled by this option. - - PCRE_MULTILINE - -By default, PCRE treats the subject string as consisting of a single "line" of -characters (even if it actually contains several 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 any newline in the subject -string, respectively, as well as at the very start and end. This is equivalent -to Perl's /m option. If there are no "\\n" characters in a subject string, or -no occurrences of ^ or $ in a pattern, setting PCRE_MULTILINE has no -effect. - - PCRE_UNGREEDY - -This option inverts the "greediness" of the quantifiers so that they are not -greedy by default, but become greedy if followed by "?". It is not compatible -with Perl. It can also be set by a (?U) option setting within the pattern. - - -.SH STUDYING A PATTERN -When a pattern is going to be used several times, it is worth spending more -time analyzing it in order to speed up the time taken for matching. The -function \fBpcre_study()\fR takes a pointer to a compiled pattern as its first -argument, and returns a pointer to a \fBpcre_extra\fR block (another \fBvoid\fR -typedef) containing additional information about the pattern; this can be -passed to \fBpcre_exec()\fR. If no additional information is available, NULL -is returned. - -The second argument contains option bits. At present, no options are defined -for \fBpcre_study()\fR, and this argument should always be zero. - -The third argument for \fBpcre_study()\fR is a pointer to an error message. If -studying succeeds (even if no data is returned), the variable it points to is -set to NULL. Otherwise it points to a textual error message. - -At present, studying a pattern is useful only for non-anchored patterns that do -not have a single fixed starting character. A bitmap of possible starting -characters is created. - - -.SH LOCALE SUPPORT -PCRE handles caseless matching, and determines whether characters are letters, -digits, or whatever, by reference to a set of tables. The library contains a -default set of tables which is created in the default C locale when PCRE is -compiled. This is used when the final argument of \fBpcre_compile()\fR is NULL, -and is sufficient for many applications. - -An alternative set of tables can, however, be supplied. Such tables are built -by calling the \fBpcre_maketables()\fR function, which has no arguments, in the -relevant locale. The result can then be passed to \fBpcre_compile()\fR as often -as necessary. For example, to build and use tables that are appropriate for the -French locale (where accented characters with codes greater than 128 are -treated as letters), the following code could be used: - - setlocale(LC_CTYPE, "fr"); - tables = pcre_maketables(); - re = pcre_compile(..., tables); - -The tables are built in memory that is obtained via \fBpcre_malloc\fR. The -pointer that is passed to \fBpcre_compile\fR is saved with the compiled -pattern, and the same tables are used via this pointer by \fBpcre_study()\fR -and \fBpcre_exec()\fR. Thus for any single pattern, compilation, studying and -matching all happen in the same locale, but different patterns can be compiled -in different locales. It is the caller's responsibility to ensure that the -memory containing the tables remains available for as long as it is needed. - - -.SH INFORMATION ABOUT A PATTERN -The \fBpcre_info()\fR function returns information about a compiled pattern. -Its yield is the number of capturing subpatterns, or one of the following -negative numbers: - - PCRE_ERROR_NULL the argument \fIcode\fR was NULL - PCRE_ERROR_BADMAGIC the "magic number" was not found - -If the \fIoptptr\fR argument is not NULL, a copy of the options with which the -pattern was compiled is placed in the integer it points to. These option bits -are those specified in the call to \fBpcre_compile()\fR, modified by any -top-level option settings within the pattern itself, and with the PCRE_ANCHORED -bit set if the form of the pattern implies that it can match only at the start -of a subject string. - -If the pattern is not anchored and the \fIfirstcharptr\fR argument is not NULL, -it is used to pass back information about the first character of any matched -string. If there is a fixed first character, e.g. from a pattern such as -(cat|cow|coyote), then it is returned in the integer pointed to by -\fIfirstcharptr\fR. Otherwise, if either - -(a) the pattern was compiled with the PCRE_MULTILINE option, and every branch -starts with "^", or - -(b) every branch of the pattern starts with ".*" and PCRE_DOTALL is not set -(if it were set, the pattern would be anchored), - -then -1 is returned, indicating that the pattern matches only at the -start of a subject string or after any "\\n" within the string. Otherwise -2 is -returned. - - -.SH MATCHING A PATTERN -The function \fBpcre_exec()\fR is called to match a subject string against a -pre-compiled pattern, which is passed in the \fIcode\fR argument. If the -pattern has been studied, the result of the study should be passed in the -\fIextra\fR argument. Otherwise this must be NULL. - -The PCRE_ANCHORED option can be passed in the \fIoptions\fR argument, whose -unused bits must be zero. However, 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. - -There are also three further options that can be set only at matching time: - - PCRE_NOTBOL - -The first character of the 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. - - PCRE_NOTEOL - -The end of the 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 without PCRE_MULTILINE (at compile time) causes dollar never -to match. - - PCRE_NOTEMPTY - -An empty string is not considered to be a valid match if this option is set. If -there are alternatives in the pattern, they are tried. If all the alternatives -match the empty string, the entire match fails. For example, if the pattern - - a?b? - -is applied to a string not beginning with "a" or "b", it matches the empty -string at the start of the subject. With PCRE_NOTEMPTY set, this match is not -valid, so PCRE searches further into the string for occurrences of "a" or "b". -Perl has no direct equivalent of this option, but it makes a special case of -a pattern match of the empty string within its \fBsplit()\fR function, or when -using the /g modifier. Using PCRE_NOTEMPTY it is possible to emulate this -behaviour. - -The subject string is passed as a pointer in \fIsubject\fR, a length in -\fIlength\fR, and a starting offset in \fIstartoffset\fR. Unlike the pattern -string, it may contain binary zero characters. 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 \fBpcre_exec()\fR again after a previous success. -Setting \fIstartoffset\fR 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 \fBpcre_exec()\fR finds the first -occurrence. If \fBpcre_exec()\fR 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 -\fBpcre_exec()\fR is passed the entire string again, but with \fIstartoffset\fR -set to 4, it finds the second occurrence of "iss" because it is able to look -behind the starting point to discover that it is preceded by a letter. - -If a non-zero starting offset is passed when the pattern is anchored, one -attempt to match at the given offset is tried. This can only succeed if the -pattern does not require the match to be at the start of the subject. - -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 substring. 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 \fIovector\fR. The number of elements in the vector -is passed in \fIovecsize\fR. The first two-thirds of the vector is used to pass -back captured substrings, each substring using a pair of integers. The -remaining third of the vector is used as workspace by \fBpcre_exec()\fR while -matching capturing subpatterns, and is not available for passing back -information. The length passed in \fIovecsize\fR should always be a multiple of -three. If it is not, it is rounded down. - -When a match has been successful, information about captured substrings is -returned in pairs of integers, starting at the beginning of \fIovector\fR, 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 substring, and the second -is set to the offset of the first character after the end of a substring. The -first pair, \fIovector[0]\fR and \fIovector[1]\fR, identify the portion of the -subject string matched by the entire pattern. The next pair is used for the -first capturing subpattern, and so on. The value returned by \fBpcre_exec()\fR -is the number of pairs that have been set. 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. - -Some convenience functions are provided for extracting the captured substrings -as separate strings. These are described in the following section. - -It is possible for an capturing subpattern number \fIn+1\fR to match some -part of the subject when subpattern \fIn\fR has not been used at all. For -example, if the string "abc" is matched against the pattern (a|(z))(bc) -subpatterns 1 and 3 are matched, but 2 is not. When this happens, both offset -values corresponding to the unused subpattern are set to -1. - -If a capturing subpattern is matched repeatedly, it is the last portion of the -string that it matched that gets returned. - -If the vector is too small to hold all the captured substrings, 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 offsets are not of interest, -\fBpcre_exec()\fR may be called with \fIovector\fR passed as NULL and -\fIovecsize\fR as zero. However, if the pattern contains back references and -the \fIovector\fR isn't 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 \fIovector\fR. - -Note that \fBpcre_info()\fR can be used to find out how many capturing -subpatterns there are in a compiled pattern. The smallest size for -\fIovector\fR that will allow for \fIn\fR captured substrings in addition to -the offsets of the substring matched by the whole pattern is (\fIn\fR+1)*3. - -If \fBpcre_exec()\fR fails, it returns a negative number. The following are -defined in the header file: - - PCRE_ERROR_NOMATCH (-1) - -The subject string did not match the pattern. - - PCRE_ERROR_NULL (-2) - -Either \fIcode\fR or \fIsubject\fR was passed as NULL, or \fIovector\fR was -NULL and \fIovecsize\fR was not zero. - - PCRE_ERROR_BADOPTION (-3) - -An unrecognized bit was set in the \fIoptions\fR argument. - - PCRE_ERROR_BADMAGIC (-4) - -PCRE stores a 4-byte "magic number" at the start of the compiled code, to catch -the case when it is passed a junk pointer. This is the error it gives when the -magic number isn't present. - - PCRE_ERROR_UNKNOWN_NODE (-5) - -While running the pattern match, an unknown item was encountered in the -compiled pattern. This error could be caused by a bug in PCRE or by overwriting -of the compiled pattern. - - PCRE_ERROR_NOMEMORY (-6) - -If a pattern contains back references, but the \fIovector\fR that is passed to -\fBpcre_exec()\fR 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 \fBpcre_malloc()\fR fails, this error is given. The memory is freed at -the end of matching. - - -.SH EXTRACTING CAPTURED SUBSTRINGS -Captured substrings can be accessed directly by using the offsets returned by -\fBpcre_exec()\fR in \fIovector\fR. For convenience, the functions -\fBpcre_copy_substring()\fR, \fBpcre_get_substring()\fR, and -\fBpcre_get_substring_list()\fR are provided for extracting captured substrings -as new, separate, zero-terminated strings. A substring that contains a binary -zero is correctly extracted and has a further zero added on the end, but the -result does not, of course, function as a C string. - -The first three arguments are the same for all three functions: \fIsubject\fR -is the subject string which has just been successfully matched, \fIovector\fR -is a pointer to the vector of integer offsets that was passed to -\fBpcre_exec()\fR, and \fIstringcount\fR is the number of substrings that -were captured by the match, including the substring that matched the entire -regular expression. This is the value returned by \fBpcre_exec\fR if it -is greater than zero. If \fBpcre_exec()\fR returned zero, indicating that it -ran out of space in \fIovector\fR, then the value passed as -\fIstringcount\fR should be the size of the vector divided by three. - -The functions \fBpcre_copy_substring()\fR and \fBpcre_get_substring()\fR -extract a single substring, whose number is given as \fIstringnumber\fR. A -value of zero extracts the substring that matched the entire pattern, while -higher values extract the captured substrings. For \fBpcre_copy_substring()\fR, -the string is placed in \fIbuffer\fR, whose length is given by -\fIbuffersize\fR, while for \fBpcre_get_substring()\fR a new block of store is -obtained via \fBpcre_malloc\fR, and its address is returned via -\fIstringptr\fR. The yield of the function is the length of the string, not -including the terminating zero, or one of - - PCRE_ERROR_NOMEMORY (-6) - -The buffer was too small for \fBpcre_copy_substring()\fR, or the attempt to get -memory failed for \fBpcre_get_substring()\fR. - - PCRE_ERROR_NOSUBSTRING (-7) - -There is no substring whose number is \fIstringnumber\fR. - -The \fBpcre_get_substring_list()\fR function extracts all available substrings -and builds a list of pointers to them. All this is done in a single block of -memory which is obtained via \fBpcre_malloc\fR. The address of the memory block -is returned via \fIlistptr\fR, which is also the start of the list of string -pointers. The end of the list is marked by a NULL pointer. The yield of the -function is zero if all went well, or - - PCRE_ERROR_NOMEMORY (-6) - -if the attempt to get the memory block failed. - -When any of these functions encounter a substring that is unset, which can -happen when capturing subpattern number \fIn+1\fR matches some part of the -subject, but subpattern \fIn\fR has not been used at all, they return an empty -string. This can be distinguished from a genuine zero-length substring by -inspecting the appropriate offset in \fIovector\fR, which is negative for unset -substrings. - - - -.SH LIMITATIONS -There are some size limitations in PCRE but it is hoped that they will never in -practice be relevant. -The maximum length of a compiled pattern is 65539 (sic) bytes. -All values in repeating quantifiers must be less than 65536. -The maximum number of capturing subpatterns is 99. -The maximum number of all parenthesized subpatterns, including capturing -subpatterns, assertions, and other types of subpattern, is 200. - -The maximum length of a subject string is the largest positive number that an -integer variable can hold. However, PCRE uses recursion to handle subpatterns -and indefinite repetition. This means that the available stack space may limit -the size of a subject string that can be processed by certain patterns. - - -.SH DIFFERENCES FROM PERL -The differences described here are with respect to Perl 5.005. - -1. By default, a whitespace character is any character that the C library -function \fBisspace()\fR recognizes, though it is possible to compile PCRE with -alternative character type tables. Normally \fBisspace()\fR matches space, -formfeed, newline, carriage return, horizontal tab, and vertical tab. Perl 5 -no longer includes vertical tab in its set of whitespace characters. The \\v -escape that was in the Perl documentation for a long time was never in fact -recognized. However, the character itself was treated as whitespace at least -up to 5.002. In 5.004 and 5.005 it does not match \\s. - -2. PCRE does not allow repeat quantifiers on lookahead assertions. Perl permits -them, but they do not mean what you might think. For example, (?!a){3} does -not assert that the next three characters are not "a". It just asserts that the -next character is not "a" three times. - -3. Capturing subpatterns that occur inside negative lookahead assertions are -counted, but their entries in the offsets vector are never set. Perl sets its -numerical variables from any such patterns that are matched before the -assertion fails to match something (thereby succeeding), but only if the -negative lookahead assertion contains just one branch. - -4. Though binary zero characters are supported in the subject string, they are -not allowed in a pattern string because it is passed as a normal C string, -terminated by zero. The escape sequence "\\0" can be used in the pattern to -represent a binary zero. - -5. The following Perl escape sequences are not supported: \\l, \\u, \\L, \\U, -\\E, \\Q. In fact these are implemented by Perl's general string-handling and -are not part of its pattern matching engine. - -6. The Perl \\G assertion is not supported as it is not relevant to single -pattern matches. - -7. Fairly obviously, PCRE does not support the (?{code}) construction. - -8. There are at the time of writing some oddities in Perl 5.005_02 concerned -with the settings of captured strings when part of a pattern is repeated. For -example, matching "aba" against the pattern /^(a(b)?)+$/ sets $2 to the value -"b", but matching "aabbaa" against /^(aa(bb)?)+$/ leaves $2 unset. However, if -the pattern is changed to /^(aa(b(b))?)+$/ then $2 (and $3) get set. - -In Perl 5.004 $2 is set in both cases, and that is also true of PCRE. If in the -future Perl changes to a consistent state that is different, PCRE may change to -follow. - -9. Another as yet unresolved discrepancy is that in Perl 5.005_02 the pattern -/^(a)?(?(1)a|b)+$/ matches the string "a", whereas in PCRE it does not. -However, in both Perl and PCRE /^(a)?a/ matched against "a" leaves $1 unset. - -10. PCRE provides some extensions to the Perl regular expression facilities: - -(a) Although lookbehind assertions must match fixed length strings, each -alternative branch of a lookbehind assertion can match a different length of -string. Perl 5.005 requires them all to have the same length. - -(b) If PCRE_DOLLAR_ENDONLY is set and PCRE_MULTILINE is not set, the $ meta- -character matches only at the very end of the string. - -(c) If PCRE_EXTRA is set, a backslash followed by a letter with no special -meaning is faulted. - -(d) If PCRE_UNGREEDY is set, the greediness of the repetition quantifiers is -inverted, that is, by default they are not greedy, but if followed by a -question mark they are. - -(e) PCRE_ANCHORED can be used to force a pattern to be tried only at the start -of the subject. - -(f) The PCRE_NOTBOL, PCRE_NOTEOL, and PCRE_NOTEMPTY options for -\fBpcre_exec()\fR have no Perl equivalents. - - -.SH REGULAR EXPRESSION DETAILS -The syntax and semantics of the regular expressions supported by PCRE are -described below. Regular expressions are also described in the Perl -documentation and in a number of other books, some of which have copious -examples. Jeffrey Friedl's "Mastering Regular Expressions", published by -O'Reilly (ISBN 1-56592-257-3), covers them in great detail. The description -here is intended as reference documentation. - -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. 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 -\fImeta-characters\fR, which do not stand for themselves but instead are -interpreted in some special way. - -There are two different sets of meta-characters: those that are recognized -anywhere in the pattern except within square brackets, and those that are -recognized in square brackets. Outside square brackets, the meta-characters are -as follows: - - \\ general escape character with several uses - ^ assert start of subject (or line, in multiline mode) - $ assert end of subject (or line, in multiline mode) - . match any character except newline (by default) - [ start character class definition - | start of alternative branch - ( start subpattern - ) end subpattern - ? extends the meaning of ( - also 0 or 1 quantifier - also quantifier minimizer - * 0 or more quantifier - + 1 or more quantifier - { start min/max quantifier - -Part of a pattern that is in square brackets is called a "character class". In -a character class the only meta-characters are: - - \\ general escape character - ^ negate the class, but only if the first character - - indicates character range - ] terminates the character class - -The following sections describe the use of each of the meta-characters. - - -.SH BACKSLASH -The backslash character has several uses. Firstly, if it is followed by a -non-alphameric 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 applies whether or not the following character would otherwise be -interpreted as a meta-character, so it is always safe to precede a -non-alphameric with "\\" to specify that it stands for itself. In particular, -if you want to match a backslash, you write "\\\\". - -If a pattern is compiled with the PCRE_EXTENDED option, whitespace in the -pattern (other than in a character class) and characters between a "#" outside -a character class and the next newline character are ignored. An escaping -backslash can be used to include a whitespace or "#" character as part of the -pattern. - -A second use of backslash provides a way of encoding non-printing characters -in patterns in a visible manner. There is no restriction on the appearance of -non-printing characters, apart from the binary zero that terminates a pattern, -but when a pattern is being prepared by text editing, it is usually easier to -use one of the following escape sequences than the binary character it -represents: - - \\a alarm, that is, the BEL character (hex 07) - \\cx "control-x", where x is any character - \\e escape (hex 1B) - \\f formfeed (hex 0C) - \\n newline (hex 0A) - \\r carriage return (hex 0D) - \\t tab (hex 09) - \\xhh character with hex code hh - \\ddd character with octal code ddd, or backreference - -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", up to two hexadecimal digits are read (letters can be in upper or -lower case). - -After "\\0" up to two further octal digits are read. In both cases, 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. -Make sure you supply two digits after the initial zero if the character that -follows is itself an octal digit. - -The handling of a backslash followed by a digit other than 0 is complicated. -Outside a character class, PCRE reads it and any following digits 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 \fIback reference\fR. A description of how this works is given -later, following the discussion of parenthesized subpatterns. - -Inside a character class, or if the decimal number is greater than 9 and there -have not been that many capturing subpatterns, PCRE re-reads up to three octal -digits following the backslash, and generates a single byte from the least -significant 8 bits of the value. Any subsequent digits stand for themselves. -For example: - - \\040 is another way of writing a space - \\40 is the same, provided there are fewer than 40 - previous capturing subpatterns - \\7 is always a back reference - \\11 might be a back reference, or another way of - writing a tab - \\011 is always a tab - \\0113 is a tab followed by the character "3" - \\113 is the character with octal code 113 (since there - can be no more than 99 back references) - \\377 is a byte consisting entirely of 1 bits - \\81 is either a back reference, or a binary zero - followed by the two characters "8" and "1" - -Note that octal values of 100 or greater must not be introduced by a leading -zero, because no more than three octal digits are ever read. - -All the sequences that define a single byte 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). Outside a character -class it has a different meaning (see below). - -The third use of backslash is for specifying generic character types: - - \\d any decimal digit - \\D any character that is not a decimal digit - \\s any whitespace character - \\S any character that is not a whitespace character - \\w any "word" character - \\W any "non-word" character - -Each pair of escape sequences partitions the complete set of characters into -two disjoint sets. Any given character matches one, and only one, of each pair. - -A "word" character is any letter or digit or the underscore character, that is, -any character which can be part of a Perl "word". The definition of letters and -digits is controlled by PCRE's character tables, and may vary if locale- -specific matching is taking place (see "Locale support" above). For example, in -the "fr" (French) locale, some character codes greater than 128 are used for -accented letters, and these are matched by \\w. - -These character type sequences can appear both inside and outside character -classes. They each match one character of the appropriate type. If the current -matching point is at the end of the subject string, all of them fail, since -there is no character to match. - -The fourth use of backslash is for certain simple assertions. An assertion -specifies a condition that has to be met at a particular point in a match, -without consuming any characters from the subject string. The use of -subpatterns for more complicated assertions is described below. The backslashed -assertions are - - \\b word boundary - \\B not a word boundary - \\A start of subject (independent of multiline mode) - \\Z end of subject or newline at end (independent of multiline mode) - \\z end of subject (independent of multiline mode) - -These assertions may not appear in character classes (but note that "\\b" has a -different meaning, namely the backspace character, inside a character class). - -A word boundary is a position in the subject string where the current character -and the previous character do not both match \\w or \\W (i.e. one matches -\\w and the other matches \\W), or the start or end of the string if the -first or last character matches \\w, respectively. - -The \\A, \\Z, and \\z assertions differ from the traditional circumflex and -dollar (described below) in that they only ever match at the very start and end -of the subject string, whatever options are set. They are not affected by the -PCRE_NOTBOL or PCRE_NOTEOL options. If the \fIstartoffset\fR argument of -\fBpcre_exec()\fR is non-zero, \\A can never match. The difference between \\Z -and \\z is that \\Z matches before a newline that is the last character of the -string as well as at the end of the string, whereas \\z matches only at the -end. - - -.SH CIRCUMFLEX AND DOLLAR -Outside a character class, in the default matching mode, the circumflex -character is an assertion which is true only if the current matching point is -at the start of the subject string. If the \fIstartoffset\fR argument of -\fBpcre_exec()\fR is non-zero, circumflex can never match. Inside a character -class, circumflex has an entirely different meaning (see below). - -Circumflex need not be the first character of the pattern if a number of -alternatives are involved, but it should be the first thing in each alternative -in which it appears if the pattern is ever to match that branch. If all -possible alternatives start with a circumflex, that is, if the pattern is -constrained to match only at the start of the subject, it is said to be an -"anchored" pattern. (There are also other constructs that can cause a pattern -to be anchored.) - -A dollar character is an assertion which is true only if the current matching -point is at the end of the subject string, or immediately before a newline -character that is the last character in the string (by default). Dollar need -not be the last character of the pattern if a number of alternatives are -involved, but it should be the last item in any branch in which it appears. -Dollar has no special meaning in a character class. - -The meaning of dollar can be changed so that it matches only at the very end of -the string, by setting the PCRE_DOLLAR_ENDONLY option at compile or matching -time. This does not affect the \\Z assertion. - -The meanings of the circumflex and dollar characters are changed if the -PCRE_MULTILINE option is set. When this is the case, they match immediately -after and immediately before an internal "\\n" character, respectively, in -addition to matching at the start and end of the subject string. For example, -the pattern /^abc$/ matches the subject string "def\\nabc" in multiline mode, -but not otherwise. Consequently, patterns that are anchored in single line mode -because all branches start with "^" are not anchored in multiline mode, and a -match for circumflex is possible when the \fIstartoffset\fR argument of -\fBpcre_exec()\fR is non-zero. The PCRE_DOLLAR_ENDONLY option is ignored if -PCRE_MULTILINE is set. - -Note that the sequences \\A, \\Z, and \\z can be used to match the start and -end of the subject in both modes, and if all branches of a pattern start with -\\A is it always anchored, whether PCRE_MULTILINE is set or not. - - -.SH FULL STOP (PERIOD, DOT) -Outside a character class, a dot in the pattern matches any one character in -the subject, including a non-printing character, but not (by default) newline. -If the PCRE_DOTALL option is set, then dots match newlines as well. The -handling of dot is entirely independent of the handling of circumflex and -dollar, the only relationship being that they both involve newline characters. -Dot has no special meaning in a character class. - - -.SH SQUARE BRACKETS -An opening square bracket introduces a character class, terminated by a closing -square bracket. A closing square bracket on its own is not special. If a -closing square bracket is required as a member of the class, it should be the -first data character in the class (after an initial circumflex, if present) or -escaped with a backslash. - -A character class matches a single character in the subject; the character must -be in the set of characters defined by the class, unless the first character in -the class is a circumflex, in which case the subject character must not be in -the set defined by the class. If a circumflex is actually required as a member -of the class, ensure it is not the first character, or escape it with a -backslash. - -For example, the character class [aeiou] matches any lower case vowel, while -[^aeiou] matches any character that is not a lower case vowel. Note that a -circumflex is just a convenient notation for specifying the characters which -are in the class by enumerating those that are not. It is not an assertion: it -still consumes a character from the subject string, and fails if the current -pointer is at the end of the string. - -When caseless matching is set, any letters in a class represent both their -upper case and lower case versions, so for example, a caseless [aeiou] matches -"A" as well as "a", and a caseless [^aeiou] does not match "A", whereas a -caseful version would. - -The newline character is never treated in any special way in character classes, -whatever the setting of the PCRE_DOTALL or PCRE_MULTILINE options is. A class -such as [^a] will always match a newline. - -The minus (hyphen) character can be used to specify a range of characters in a -character class. For example, [d-m] matches any letter between d and m, -inclusive. If a minus character is required in a class, it must be escaped with -a backslash or appear in a position where it cannot be interpreted as -indicating a range, typically as the first or last character in the class. - -It is not possible to have the literal character "]" as the end character of a -range. A pattern such as [W-]46] is interpreted as a class of two characters -("W" and "-") followed by a literal string "46]", so it would match "W46]" or -"-46]". However, if the "]" is escaped with a backslash it is interpreted as -the end of range, so [W-\\]46] is interpreted as a single class containing a -range followed by two separate characters. The octal or hexadecimal -representation of "]" can also be used to end a range. - -Ranges operate in ASCII collating sequence. They can also be used for -characters specified numerically, for example [\\000-\\037]. If a range that -includes letters is used when caseless matching is set, it matches the letters -in either case. For example, [W-c] is equivalent to [][\\^_`wxyzabc], matched -caselessly, and if character tables for the "fr" locale are in use, -[\\xc8-\\xcb] matches accented E characters in both cases. - -The character types \\d, \\D, \\s, \\S, \\w, and \\W may also appear in a -character class, and add the characters that they match to the class. For -example, [\\dABCDEF] matches any hexadecimal digit. A circumflex can -conveniently be used with the upper case character types to specify a more -restricted set of characters than the matching lower case type. For example, -the class [^\\W_] matches any letter or digit, but not underscore. - -All non-alphameric characters other than \\, -, ^ (at the start) and the -terminating ] are non-special in character classes, but it does no harm if they -are escaped. - - -.SH VERTICAL BAR -Vertical bar characters are used to separate alternative patterns. For example, -the pattern - - gilbert|sullivan - -matches either "gilbert" or "sullivan". Any number of alternatives may appear, -and an empty alternative is permitted (matching the empty string). -The matching process tries each alternative in turn, from left to right, -and the first one that succeeds is used. If the alternatives are within a -subpattern (defined below), "succeeds" means matching the rest of the main -pattern as well as the alternative in the subpattern. - - -.SH INTERNAL OPTION SETTING -The settings of PCRE_CASELESS, PCRE_MULTILINE, PCRE_DOTALL, and PCRE_EXTENDED -can be changed from within the pattern by a sequence of Perl option letters -enclosed between "(?" and ")". The option letters are - - i for PCRE_CASELESS - m for PCRE_MULTILINE - s for PCRE_DOTALL - x for PCRE_EXTENDED - -For example, (?im) sets caseless, multiline matching. It is also possible to -unset these options by preceding the letter with a hyphen, and a combined -setting and unsetting such as (?im-sx), which sets PCRE_CASELESS and -PCRE_MULTILINE while unsetting PCRE_DOTALL and PCRE_EXTENDED, is also -permitted. If a letter appears both before and after the hyphen, the option is -unset. - -The scope of these option changes depends on where in the pattern the setting -occurs. For settings that are outside any subpattern (defined below), the -effect is the same as if the options were set or unset at the start of -matching. The following patterns all behave in exactly the same way: - - (?i)abc - a(?i)bc - ab(?i)c - abc(?i) - -which in turn is the same as compiling the pattern abc with PCRE_CASELESS set. -In other words, such "top level" settings apply to the whole pattern (unless -there are other changes inside subpatterns). If there is more than one setting -of the same option at top level, the rightmost setting is used. - -If an option change occurs inside a subpattern, the effect is different. This -is a change of behaviour in Perl 5.005. An option change inside a subpattern -affects only that part of the subpattern that follows it, so - - (a(?i)b)c - -matches abc and aBc and no other strings (assuming PCRE_CASELESS is not used). -By this means, options can be made to have different settings in different -parts of the pattern. Any changes made in one alternative do carry on -into subsequent branches within the same subpattern. For example, - - (a(?i)b|c) - -matches "ab", "aB", "c", and "C", even though when matching "C" the first -branch is abandoned before the option setting. This is because the effects of -option settings happen at compile time. There would be some very weird -behaviour otherwise. - -The PCRE-specific options PCRE_UNGREEDY and PCRE_EXTRA can be changed in the -same way as the Perl-compatible options by using the characters U and X -respectively. The (?X) flag setting is special in that it must always occur -earlier in the pattern than any of the additional features it turns on, even -when it is at top level. It is best put at the start. - - -.SH SUBPATTERNS -Subpatterns are delimited by parentheses (round brackets), which can be nested. -Marking part of a pattern as a subpattern does two things: - -1. It localizes a set of alternatives. For example, the pattern - - cat(aract|erpillar|) - -matches one of the words "cat", "cataract", or "caterpillar". Without the -parentheses, it would match "cataract", "erpillar" or the empty string. - -2. It sets up the subpattern as a capturing subpattern (as defined above). -When the whole pattern matches, that portion of the subject string that matched -the subpattern is passed back to the caller via the \fIovector\fR argument of -\fBpcre_exec()\fR. Opening parentheses are counted from left to right (starting -from 1) to obtain the numbers of the capturing subpatterns. - -For example, if the string "the red king" is matched against the pattern - - the ((red|white) (king|queen)) - -the captured substrings are "red king", "red", and "king", and are numbered 1, -2, and 3. - -The fact that plain parentheses fulfil two functions is not always helpful. -There are often times when a grouping subpattern is required without a -capturing requirement. If an opening parenthesis is followed by "?:", the -subpattern does not do any capturing, and is not counted when computing the -number of any subsequent capturing subpatterns. For example, if the string "the -white queen" is matched against the pattern - - the ((?:red|white) (king|queen)) - -the captured substrings are "white queen" and "queen", and are numbered 1 and -2. The maximum number of captured substrings is 99, and the maximum number of -all subpatterns, both capturing and non-capturing, is 200. - -As a convenient shorthand, if any option settings are required at the start of -a non-capturing subpattern, the option letters may appear between the "?" and -the ":". Thus the two patterns - - (?i:saturday|sunday) - (?:(?i)saturday|sunday) - -match exactly the same set of strings. Because alternative branches are tried -from left to right, and options are not reset until the end of the subpattern -is reached, an option setting in one branch does affect subsequent branches, so -the above patterns match "SUNDAY" as well as "Saturday". - - -.SH REPETITION -Repetition is specified by quantifiers, which can follow any of the following -items: - - a single character, possibly escaped - the . metacharacter - a character class - a back reference (see next section) - a parenthesized subpattern (unless it is an assertion - see below) - -The general repetition quantifier specifies a minimum and maximum number of -permitted matches, by giving the two numbers in curly brackets (braces), -separated by a comma. The numbers must be less than 65536, and the first must -be less than or equal to the second. For example: - - z{2,4} - -matches "zz", "zzz", or "zzzz". A closing brace on its own is not a special -character. If the second number is omitted, but the comma is present, there is -no upper limit; if the second number and the comma are both omitted, the -quantifier specifies an exact number of required matches. Thus - - [aeiou]{3,} - -matches at least 3 successive vowels, but may match many more, while - - \\d{8} - -matches exactly 8 digits. An opening curly bracket that appears in a position -where a quantifier is not allowed, or one that does not match the syntax of a -quantifier, is taken as a literal character. For example, {,6} is not a -quantifier, but a literal string of four characters. - -The quantifier {0} is permitted, causing the expression to behave as if the -previous item and the quantifier were not present. - -For convenience (and historical compatibility) the three most common -quantifiers have single-character abbreviations: - - * is equivalent to {0,} - + is equivalent to {1,} - ? is equivalent to {0,1} - -It is possible to construct infinite loops by following a subpattern that can -match no characters with a quantifier that has no upper limit, for example: - - (a?)* - -Earlier versions of Perl and PCRE used to give an error at compile time for -such patterns. However, because there are cases where this can be useful, such -patterns are now accepted, but if any repetition of the subpattern does in fact -match no characters, the loop is forcibly broken. - -By default, the quantifiers are "greedy", that is, they match as much as -possible (up to the maximum number of permitted times), without causing the -rest of the pattern to fail. The classic example of where this gives problems -is in trying to match comments in C programs. These appear between the -sequences /* and */ and within the sequence, individual * and / characters may -appear. An attempt to match C comments by applying the pattern - - /\\*.*\\*/ - -to the string - - /* first command */ not comment /* second comment */ - -fails, because it matches the entire string due to the greediness of the .* -item. - -However, if a quantifier is followed by a question mark, then it ceases to be -greedy, and instead matches the minimum number of times possible, so the -pattern - - /\\*.*?\\*/ - -does the right thing with the C comments. The meaning of the various -quantifiers is not otherwise changed, just the preferred number of matches. -Do not confuse this use of question mark with its use as a quantifier in its -own right. Because it has two uses, it can sometimes appear doubled, as in - - \\d??\\d - -which matches one digit by preference, but can match two if that is the only -way the rest of the pattern matches. - -If the PCRE_UNGREEDY option is set (an option which is not available in Perl) -then the quantifiers are not greedy by default, but individual ones can be made -greedy by following them with a question mark. In other words, it inverts the -default behaviour. - -When a parenthesized subpattern is quantified with a minimum repeat count that -is greater than 1 or with a limited maximum, more store is required for the -compiled pattern, in proportion to the size of the minimum or maximum. - -If a pattern starts with .* or .{0,} and the PCRE_DOTALL option (equivalent -to Perl's /s) is set, thus allowing the . to match newlines, then the pattern -is implicitly anchored, because whatever follows will be tried against every -character position in the subject string, so there is no point in retrying the -overall match at any position after the first. PCRE treats such a pattern as -though it were preceded by \\A. In cases where it is known that the subject -string contains no newlines, it is worth setting PCRE_DOTALL when the pattern -begins with .* in order to obtain this optimization, or alternatively using ^ -to indicate anchoring explicitly. - -When a capturing subpattern is repeated, the value captured is the substring -that matched the final iteration. For example, after - - (tweedle[dume]{3}\\s*)+ - -has matched "tweedledum tweedledee" the value of the captured substring is -"tweedledee". However, if there are nested capturing subpatterns, the -corresponding captured values may have been set in previous iterations. For -example, after - - /(a|(b))+/ - -matches "aba" the value of the second captured substring is "b". - - -.SH BACK REFERENCES -Outside a character class, a backslash followed by a digit greater than 0 (and -possibly further digits) is a back reference to a capturing subpattern earlier -(i.e. to its left) in the pattern, provided there have been that many previous -capturing left parentheses. - -However, if the decimal number following the backslash is less than 10, it is -always taken as a back reference, and causes an error only if there are not -that many capturing left parentheses in the entire pattern. In other words, the -parentheses that are referenced need not be to the left of the reference for -numbers less than 10. See the section entitled "Backslash" above for further -details of the handling of digits following a backslash. - -A back reference matches whatever actually matched the capturing subpattern in -the current subject string, rather than anything matching the subpattern -itself. So the pattern - - (sens|respons)e and \\1ibility - -matches "sense and sensibility" and "response and responsibility", but not -"sense and responsibility". If caseful matching is in force at the time of the -back reference, then the case of letters is relevant. For example, - - ((?i)rah)\\s+\\1 - -matches "rah rah" and "RAH RAH", but not "RAH rah", even though the original -capturing subpattern is matched caselessly. - -There may be more than one back reference to the same subpattern. If a -subpattern has not actually been used in a particular match, then any back -references to it always fail. For example, the pattern - - (a|(bc))\\2 - -always fails if it starts to match "a" rather than "bc". Because there may be -up to 99 back references, all digits following the backslash are taken -as part of a potential back reference number. If the pattern continues with a -digit character, then some delimiter must be used to terminate the back -reference. If the PCRE_EXTENDED option is set, this can be whitespace. -Otherwise an empty comment can be used. - -A back reference that occurs inside the parentheses to which it refers fails -when the subpattern is first used, so, for example, (a\\1) never matches. -However, such references can be useful inside repeated subpatterns. For -example, the pattern - - (a|b\\1)+ - -matches any number of "a"s and also "aba", "ababaa" etc. At each iteration of -the subpattern, the back reference matches the character string corresponding -to the previous iteration. In order for this to work, the pattern must be such -that the first iteration does not need to match the back reference. This can be -done using alternation, as in the example above, or by a quantifier with a -minimum of zero. - - -.SH ASSERTIONS -An assertion is a test on the characters following or preceding the current -matching point that does not actually consume any characters. The simple -assertions coded as \\b, \\B, \\A, \\Z, \\z, ^ and $ are described above. More -complicated assertions are coded as subpatterns. There are two kinds: those -that look ahead of the current position in the subject string, and those that -look behind it. - -An assertion subpattern is matched in the normal way, except that it does not -cause the current matching position to be changed. Lookahead assertions start -with (?= for positive assertions and (?! for negative assertions. For example, - - \\w+(?=;) - -matches a word followed by a semicolon, but does not include the semicolon in -the match, and - - foo(?!bar) - -matches any occurrence of "foo" that is not followed by "bar". Note that the -apparently similar pattern - - (?!foo)bar - -does not find an occurrence of "bar" that is preceded by something other than -"foo"; it finds any occurrence of "bar" whatsoever, because the assertion -(?!foo) is always true when the next three characters are "bar". A -lookbehind assertion is needed to achieve this effect. - -Lookbehind assertions start with (?<= for positive assertions and (? as in this example: - - (?>\\d+)bar - -This kind of parenthesis "locks up" the part of the pattern it contains once -it has matched, and a failure further into the pattern is prevented from -backtracking into it. Backtracking past it to previous items, however, works as -normal. - -An alternative description is that a subpattern of this type matches the string -of characters that an identical standalone pattern would match, if anchored at -the current point in the subject string. - -Once-only subpatterns are not capturing subpatterns. Simple cases such as the -above example can be thought of as a maximizing repeat that must swallow -everything it can. So, while both \\d+ and \\d+? are prepared to adjust the -number of digits they match in order to make the rest of the pattern match, -(?>\\d+) can only match an entire sequence of digits. - -This construction can of course contain arbitrarily complicated subpatterns, -and it can be nested. - -Once-only subpatterns can be used in conjunction with lookbehind assertions to -specify efficient matching at the end of the subject string. Consider a simple -pattern such as - - abcd$ - -when applied to a long string which does not match it. Because matching -proceeds from left to right, PCRE will look for each "a" in the subject and -then see if what follows matches the rest of the pattern. If the pattern is -specified as - - ^.*abcd$ - -then the initial .* matches the entire string at first, but when this fails, it -backtracks to match all but the last character, then all but the last two -characters, and so on. Once again the search for "a" covers the entire string, -from right to left, so we are no better off. However, if the pattern is written -as - - ^(?>.*)(?<=abcd) - -then there can be no backtracking for the .* item; it can match only the entire -string. The subsequent lookbehind assertion does a single test on the last four -characters. If it fails, the match fails immediately. For long strings, this -approach makes a significant difference to the processing time. - - -.SH CONDITIONAL SUBPATTERNS -It is possible to cause the matching process to obey a subpattern -conditionally or to choose between two alternative subpatterns, depending on -the result of an assertion, or whether a previous capturing subpattern matched -or not. The two possible forms of conditional subpattern are - - (?(condition)yes-pattern) - (?(condition)yes-pattern|no-pattern) - -If the condition is satisfied, the yes-pattern is used; otherwise the -no-pattern (if present) is used. If there are more than two alternatives in the -subpattern, a compile-time error occurs. - -There are two kinds of condition. If the text between the parentheses consists -of a sequence of digits, then the condition is satisfied if the capturing -subpattern of that number has previously matched. Consider the following -pattern, which contains non-significant white space to make it more readable -(assume the PCRE_EXTENDED option) and to divide it into three parts for ease -of discussion: - - ( \\( )? [^()]+ (?(1) \\) ) - -The first part matches an optional opening parenthesis, and if that -character is present, sets it as the first captured substring. The second part -matches one or more characters that are not parentheses. The third part is a -conditional subpattern that tests whether the first set of parentheses matched -or not. If they did, that is, if subject started with an opening parenthesis, -the condition is true, and so the yes-pattern is executed and a closing -parenthesis is required. Otherwise, since no-pattern is not present, the -subpattern matches nothing. In other words, this pattern matches a sequence of -non-parentheses, optionally enclosed in parentheses. - -If the condition is not a sequence of digits, it must be an assertion. This may -be a positive or negative lookahead or lookbehind assertion. Consider this -pattern, again containing non-significant white space, and with the two -alternatives on the second line: - - (?(?=[^a-z]*[a-z]) - \\d{2}[a-z]{3}-\\d{2} | \\d{2}-\\d{2}-\\d{2} ) - -The condition is a positive lookahead assertion that matches an optional -sequence of non-letters followed by a letter. In other words, it tests for the -presence of at least one letter in the subject. If a letter is found, the -subject is matched against the first alternative; otherwise it is matched -against the second. This pattern matches strings in one of the two forms -dd-aaa-dd or dd-dd-dd, where aaa are letters and dd are digits. - - -.SH COMMENTS -The sequence (?# marks the start of a comment which continues up to the next -closing parenthesis. Nested parentheses are not permitted. The characters -that make up a comment play no part in the pattern matching at all. - -If the PCRE_EXTENDED option is set, an unescaped # character outside a -character class introduces a comment that continues up to the next newline -character in the pattern. - - -.SH PERFORMANCE -Certain items that may appear in patterns are more efficient than others. It is -more efficient to use a character class like [aeiou] than a set of alternatives -such as (a|e|i|o|u). In general, the simplest construction that provides the -required behaviour is usually the most efficient. Jeffrey Friedl's book -contains a lot of discussion about optimizing regular expressions for efficient -performance. - -When a pattern begins with .* and the PCRE_DOTALL option is set, the pattern is -implicitly anchored by PCRE, since it can match only at the start of a subject -string. However, if PCRE_DOTALL is not set, PCRE cannot make this optimization, -because the . metacharacter does not then match a newline, and if the subject -string contains newlines, the pattern may match from the character immediately -following one of them instead of from the very start. For example, the pattern - - (.*) second - -matches the subject "first\\nand second" (where \\n stands for a newline -character) with the first captured substring being "and". In order to do this, -PCRE has to retry the match starting after every newline in the subject. - -If you are using such a pattern with subject strings that do not contain -newlines, the best performance is obtained by setting PCRE_DOTALL, or starting -the pattern with ^.* to indicate explicit anchoring. That saves PCRE from -having to scan along the subject looking for a newline to restart at. - -Beware of patterns that contain nested indefinite repeats. These can take a -long time to run when applied to a string that does not match. Consider the -pattern fragment - - (a+)* - -This can match "aaaa" in 33 different ways, and this number increases very -rapidly as the string gets longer. (The * repeat can match 0, 1, 2, 3, or 4 -times, and for each of those cases other than 0, the + repeats can match -different numbers of times.) When the remainder of the pattern is such that the -entire match is going to fail, PCRE has in principle to try every possible -variation, and this can take an extremely long time. - -An optimization catches some of the more simple cases such as - - (a+)*b - -where a literal character follows. Before embarking on the standard matching -procedure, PCRE checks that there is a "b" later in the subject string, and if -there is not, it fails the match immediately. However, when there is no -following literal this optimization cannot be used. You can see the difference -by comparing the behaviour of - - (a+)*\\d - -with the pattern above. The former gives a failure almost instantly when -applied to a whole line of "a" characters, whereas the latter takes an -appreciable time with strings longer than about 20 characters. - -.SH AUTHOR -Philip Hazel -.br -University Computing Service, -.br -New Museums Site, -.br -Cambridge CB2 3QG, England. -.br -Phone: +44 1223 334714 - -Last updated: 29 July 1999 -.br -Copyright (c) 1997-1999 University of Cambridge. diff --git a/ext/pcre/pcrelib/pcre.3.html b/ext/pcre/pcrelib/pcre.3.html deleted file mode 100644 index 3417579904..0000000000 --- a/ext/pcre/pcrelib/pcre.3.html +++ /dev/null @@ -1,1973 +0,0 @@ - - -pcre specification - - -

pcre specification

-This HTML document has been generated automatically from the original man page. -If there is any nonsense in it, please consult the man page in case the -conversion went wrong. - -
  • NAME -

    -pcre - Perl-compatible regular expressions. -

    -
  • SYNOPSIS -

    -#include <pcre.h> -

    -

    -pcre *pcre_compile(const char *pattern, int options, -const char **errptr, int *erroffset, -const unsigned char *tableptr); -

    -

    -pcre_extra *pcre_study(const pcre *code, int options, -const char **errptr); -

    -

    -int pcre_exec(const pcre *code, const pcre_extra *extra, -const char *subject, int length, int startoffset, -int options, int *ovector, int ovecsize); -

    -

    -int pcre_copy_substring(const char *subject, int *ovector, -int stringcount, int stringnumber, char *buffer, -int buffersize); -

    -

    -int pcre_get_substring(const char *subject, int *ovector, -int stringcount, int stringnumber, -const char **stringptr); -

    -

    -int pcre_get_substring_list(const char *subject, -int *ovector, int stringcount, const char ***listptr); -

    -

    -const unsigned char *pcre_maketables(void); -

    -

    -int pcre_info(const pcre *code, int *optptr, int -*firstcharptr); -

    -

    -char *pcre_version(void); -

    -

    -void *(*pcre_malloc)(size_t); -

    -

    -void (*pcre_free)(void *); -

    -
  • DESCRIPTION -

    -The PCRE library is a set of functions that implement regular expression -pattern matching using the same syntax and semantics as Perl 5, with just a few -differences (see below). The current implementation corresponds to Perl 5.005. -

    -

    -PCRE has its own native API, which is described in this document. There is also -a set of wrapper functions that correspond to the POSIX API. These are -described in the pcreposix documentation. -

    -

    -The native API function prototypes are defined in the header file pcre.h, -and on Unix systems the library itself is called libpcre.a, so can be -accessed by adding -lpcre to the command for linking an application which -calls it. -

    -

    -The functions pcre_compile(), pcre_study(), and pcre_exec() -are used for compiling and matching regular expressions, while -pcre_copy_substring(), pcre_get_substring(), and -pcre_get_substring_list() are convenience functions for extracting -captured substrings from a matched subject string. The function -pcre_maketables() is used (optionally) to build a set of character tables -in the current locale for passing to pcre_compile(). -

    -

    -The function pcre_info() is used to find out information about a compiled -pattern, while the function pcre_version() returns a pointer to a string -containing the version of PCRE and its date of release. -

    -

    -The global variables pcre_malloc and pcre_free initially contain -the entry points of the standard malloc() and free() functions -respectively. PCRE calls the memory management functions via these variables, -so a calling program can replace them if it wishes to intercept the calls. This -should be done before calling any PCRE functions. -

    -
  • MULTI-THREADING -

    -The PCRE functions can be used in multi-threading applications, with the -proviso that the memory management functions pointed to by pcre_malloc -and pcre_free are shared by all threads. -

    -

    -The compiled form of a regular expression is not altered during matching, so -the same compiled pattern can safely be used by several threads at once. -

    -
  • COMPILING A PATTERN -

    -The function pcre_compile() is called to compile a pattern into an -internal form. The pattern is a C string terminated by a binary zero, and -is passed in the argument pattern. 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 this for -convenience, but in fact pcre is just a typedef for void, since the -contents of the block are not externally defined. It is up to the caller to -free the memory when it is no longer required. -

    -

    -The size of a compiled pattern is roughly proportional to the length of the -pattern string, except that each character class (other than those containing -just a single character, negated or not) requires 33 bytes, and repeat -quantifiers with a minimum greater than one or a bounded maximum cause the -relevant portions of the compiled pattern to be replicated. -

    -

    -The options argument contains independent bits that affect the -compilation. It should be zero if no options are required. Some of the options, -in particular, those that are compatible with Perl, can also be set and unset -from within the pattern (see the detailed description of regular expressions -below). For these options, the contents of the options argument specifies -their initial settings at the start of compilation and execution. The -PCRE_ANCHORED option can be set at the time of matching as well as at compile -time. -

    -

    -If errptr is NULL, pcre_compile() returns NULL immediately. -Otherwise, if compilation of a pattern fails, pcre_compile() returns -NULL, and sets the variable pointed to by errptr to point to a textual -error message. The offset from the start of the pattern to the character where -the error was discovered is placed in the variable pointed to by -erroffset, which must not be NULL. If it is, an immediate error is given. -

    -

    -If the final argument, tableptr, is NULL, PCRE uses a default set of -character tables which are built when it is compiled, using the default C -locale. Otherwise, tableptr must be the result of a call to -pcre_maketables(). See the section on locale support below. -

    -

    -The following option bits are defined in the 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 start of the string which 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_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. -

    -

    -

    -  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 the final character if it is a newline (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. -

    -

    -

    -  PCRE_DOTALL
-
    -

    -

    -If this bit is set, a dot metacharater in the pattern matches all characters, -including newlines. Without it, newlines are excluded. This option is -equivalent to Perl's /s option. A negative class such as [^a] always matches a -newline character, independent of the setting of this option. -

    -

    -

    -  PCRE_EXTENDED
-
    -

    -

    -If this bit is set, whitespace data characters in the pattern are totally -ignored except when escaped or inside a character class, and characters between -an unescaped # outside a character class and the next newline character, -inclusive, are also ignored. This is equivalent to Perl's /x option, and 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 turns on additional functionality of PCRE that is incompatible with -Perl. 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. There are at present no other features -controlled by this option. -

    -

    -

    -  PCRE_MULTILINE
-
    -

    -

    -By default, PCRE treats the subject string as consisting of a single "line" of -characters (even if it actually contains several 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 any newline in the subject -string, respectively, as well as at the very start and end. This is equivalent -to Perl's /m option. If there are no "\n" characters in a subject string, or -no occurrences of ^ or $ in a pattern, setting PCRE_MULTILINE has no -effect. -

    -

    -

    -  PCRE_UNGREEDY
-
    -

    -

    -This option inverts the "greediness" of the quantifiers so that they are not -greedy by default, but become greedy if followed by "?". It is not compatible -with Perl. It can also be set by a (?U) option setting within the pattern. -

    -
  • STUDYING A PATTERN -

    -When a pattern is going to be used several times, it is worth spending more -time analyzing it in order to speed up the time taken for matching. The -function pcre_study() takes a pointer to a compiled pattern as its first -argument, and returns a pointer to a pcre_extra block (another void -typedef) containing additional information about the pattern; this can be -passed to pcre_exec(). If no additional information is available, NULL -is returned. -

    -

    -The second argument contains option bits. At present, no options are defined -for pcre_study(), and this argument should always be zero. -

    -

    -The third argument for pcre_study() is a pointer to an error message. If -studying succeeds (even if no data is returned), the variable it points to is -set to NULL. Otherwise it points to a textual error message. -

    -

    -At present, studying a pattern is useful only for non-anchored patterns that do -not have a single fixed starting character. A bitmap of possible starting -characters is created. -

    -
  • LOCALE SUPPORT -

    -PCRE handles caseless matching, and determines whether characters are letters, -digits, or whatever, by reference to a set of tables. The library contains a -default set of tables which is created in the default C locale when PCRE is -compiled. This is used when the final argument of pcre_compile() is NULL, -and is sufficient for many applications. -

    -

    -An alternative set of tables can, however, be supplied. Such tables are built -by calling the pcre_maketables() function, which has no arguments, in the -relevant locale. The result can then be passed to pcre_compile() as often -as necessary. For example, to build and use tables that are appropriate for the -French locale (where accented characters with codes greater than 128 are -treated as letters), the following code could be used: -

    -

    -

    -  setlocale(LC_CTYPE, "fr");
-  tables = pcre_maketables();
-  re = pcre_compile(..., tables);
-
    -

    -

    -The tables are built in memory that is obtained via pcre_malloc. The -pointer that is passed to pcre_compile is saved with the compiled -pattern, and the same tables are used via this pointer by pcre_study() -and pcre_exec(). Thus for any single pattern, compilation, studying and -matching all happen in the same locale, but different patterns can be compiled -in different locales. It is the caller's responsibility to ensure that the -memory containing the tables remains available for as long as it is needed. -

    -
  • INFORMATION ABOUT A PATTERN -

    -The pcre_info() function returns information about a compiled pattern. -Its yield is the number of capturing subpatterns, or one of the following -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. These option bits -are those specified in the call to pcre_compile(), modified by any -top-level option settings within the pattern itself, and with the PCRE_ANCHORED -bit set if the form of the pattern implies that it can match only at the start -of a subject string. -

    -

    -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. If there is a fixed first character, e.g. from a pattern such as -(cat|cow|coyote), then it is returned in the integer pointed to by -firstcharptr. Otherwise, if either -

    -

    -(a) the pattern was compiled with the PCRE_MULTILINE option, and every branch -starts with "^", or -

    -

    -(b) every branch of the pattern starts with ".*" and PCRE_DOTALL is not set -(if it were set, the pattern would be anchored), -

    -

    -then -1 is returned, indicating that the pattern matches only at the -start of a subject string or after any "\n" within the string. Otherwise -2 is -returned. -

    -
  • MATCHING A PATTERN -

    -The function pcre_exec() is called to match a subject string against a -pre-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. Otherwise this must be NULL. -

    -

    -The PCRE_ANCHORED option can be passed in the options argument, whose -unused bits must be zero. However, 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. -

    -

    -There are also three further options that can be set only at matching time: -

    -

    -

    -  PCRE_NOTBOL
-
    -

    -

    -The first character of the 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. -

    -

    -

    -  PCRE_NOTEOL
-
    -

    -

    -The end of the 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 without PCRE_MULTILINE (at compile time) causes dollar never -to match. -

    -

    -

    -  PCRE_NOTEMPTY
-
    -

    -

    -An empty string is not considered to be a valid match if this option is set. If -there are alternatives in the pattern, they are tried. If all the alternatives -match the empty string, the entire match fails. For example, if the pattern -

    -

    -

    -  a?b?
-
    -

    -

    -is applied to a string not beginning with "a" or "b", it matches the empty -string at the start of the subject. With PCRE_NOTEMPTY set, this match is not -valid, so PCRE searches further into the string for occurrences of "a" or "b". -Perl has no direct equivalent of this option, but it makes a special case of -a pattern match of the empty string within its split() function, or when -using the /g modifier. Using PCRE_NOTEMPTY it is possible to emulate this -behaviour. -

    -

    -The subject string is passed as a pointer in subject, a length in -length, and a starting offset in startoffset. Unlike the pattern -string, it may contain binary zero characters. 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 success. -Setting startoffset differs from just passing over a shortened string and -setting PCRE_NOTBOL in the case of a pattern that begins with any kind of -lookbehind. For example, consider the pattern -

    -

    -

    -  \Biss\B
-
    -

    -

    -which finds occurrences of "iss" in the middle of words. (\B matches only if -the current position in the subject is not a word boundary.) When applied to -the string "Mississipi" the first call to pcre_exec() finds the first -occurrence. If pcre_exec() is called again with just the remainder of the -subject, namely "issipi", it does not match, because \B is always false at the -start of the subject, which is deemed to be a word boundary. However, if -pcre_exec() is passed the entire string again, but with startoffset -set to 4, it finds the second occurrence of "iss" because it is able to look -behind the starting point to discover that it is preceded by a letter. -

    -

    -If a non-zero starting offset is passed when the pattern is anchored, one -attempt to match at the given offset is tried. This can only succeed if the -pattern does not require the match to be at the start of the subject. -

    -

    -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 substring. 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. The first two-thirds of the vector is used to pass -back captured substrings, each substring using a pair of integers. The -remaining third of the vector is used as workspace by pcre_exec() while -matching capturing 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 has been 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 substring, and the second -is set to the offset of the first character after the end of a substring. The -first pair, ovector[0] and ovector[1], identify the portion of the -subject string matched by the entire pattern. The next pair is used for the -first capturing subpattern, and so on. The value returned by pcre_exec() -is the number of pairs that have been set. 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. -

    -

    -Some convenience functions are provided for extracting the captured substrings -as separate strings. These are described in the following section. -

    -

    -It is possible for an 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) -subpatterns 1 and 3 are matched, but 2 is not. When this happens, both offset -values corresponding to the unused subpattern are set to -1. -

    -

    -If a capturing subpattern is matched repeatedly, it is the last portion of the -string that it matched that gets returned. -

    -

    -If the vector is too small to hold all the captured substrings, 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 offsets 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 isn't 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. -

    -

    -Note that pcre_info() 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. -

    -

    -If pcre_exec() fails, it returns a negative number. The following are -defined in the header file: -

    -

    -

    -  PCRE_ERROR_NOMATCH        (-1)
-
    -

    -

    -The subject string did not match the pattern. -

    -

    -

    -  PCRE_ERROR_NULL           (-2)
-
    -

    -

    -Either code or subject was passed as NULL, or ovector was -NULL and ovecsize was not zero. -

    -

    -

    -  PCRE_ERROR_BADOPTION      (-3)
-
    -

    -

    -An unrecognized bit was set in the options argument. -

    -

    -

    -  PCRE_ERROR_BADMAGIC       (-4)
-
    -

    -

    -PCRE stores a 4-byte "magic number" at the start of the compiled code, to catch -the case when it is passed a junk pointer. This is the error it gives when the -magic number isn't present. -

    -

    -

    -  PCRE_ERROR_UNKNOWN_NODE   (-5)
-
    -

    -

    -While running the pattern match, an unknown item was encountered in the -compiled pattern. This error could be caused by a bug in PCRE or by overwriting -of the compiled pattern. -

    -

    -

    -  PCRE_ERROR_NOMEMORY       (-6)
-
    -

    -

    -If a pattern contains back references, but the ovector that is passed to -pcre_exec() is not big enough to remember the referenced substrings, PCRE -gets a block of memory at the start of matching to use for this purpose. If the -call via pcre_malloc() fails, this error is given. The memory is freed at -the end of matching. -

    -
  • EXTRACTING CAPTURED SUBSTRINGS -

    -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_substring_list() are provided for extracting captured substrings -as new, separate, zero-terminated strings. A substring that contains a binary -zero is correctly extracted and has a further zero added on the end, but the -result does not, of course, function as a C string. -

    -

    -The first three arguments are the same for all three functions: subject -is the subject string which has just been successfully matched, ovector -is a pointer to the vector of integer offsets that was passed to -pcre_exec(), and stringcount is the number of substrings that -were captured by the match, including the substring that matched the entire -regular expression. This is the value returned by pcre_exec if it -is greater than zero. If pcre_exec() returned zero, indicating that it -ran out of space in ovector, then the value passed as -stringcount should be the size of 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, while -higher values extract the captured substrings. For pcre_copy_substring(), -the string is placed in buffer, whose length is given by -buffersize, while for pcre_get_substring() a new block of store is -obtained via pcre_malloc, and its address is returned via -stringptr. The yield of the function is the length of the string, not -including the terminating zero, or one of -

    -

    -

    -  PCRE_ERROR_NOMEMORY       (-6)
-
    -

    -

    -The buffer was too small for pcre_copy_substring(), or the attempt to get -memory failed for pcre_get_substring(). -

    -

    -

    -  PCRE_ERROR_NOSUBSTRING    (-7)
-
    -

    -

    -There is no substring whose number is stringnumber. -

    -

    -The pcre_get_substring_list() function extracts all available substrings -and builds a list of pointers to them. All this is done in a single block of -memory which is obtained via pcre_malloc. The address of the memory block -is returned via listptr, which is also the start of the list of string -pointers. The end of the list is marked by a NULL pointer. The yield of the -function is zero if all went well, or -

    -

    -

    -  PCRE_ERROR_NOMEMORY       (-6)
-
    -

    -

    -if the attempt to get the memory block failed. -

    -

    -When any of these functions encounter a substring that is unset, which can -happen when capturing subpattern number n+1 matches some part of the -subject, but subpattern n has not been used at all, they return an empty -string. This can be distinguished from a genuine zero-length substring by -inspecting the appropriate offset in ovector, which is negative for unset -substrings. -

    -
  • LIMITATIONS -

    -There are some size limitations in PCRE but it is hoped that they will never in -practice be relevant. -The maximum length of a compiled pattern is 65539 (sic) bytes. -All values in repeating quantifiers must be less than 65536. -The maximum number of capturing subpatterns is 99. -The maximum number of all parenthesized subpatterns, including capturing -subpatterns, assertions, and other types of subpattern, is 200. -

    -

    -The maximum length of a subject string is the largest positive number that an -integer variable can hold. However, PCRE uses recursion to handle subpatterns -and indefinite repetition. This means that the available stack space may limit -the size of a subject string that can be processed by certain patterns. -

    -
  • DIFFERENCES FROM PERL -

    -The differences described here are with respect to Perl 5.005. -

    -

    -1. By default, a whitespace character is any character that the C library -function isspace() recognizes, though it is possible to compile PCRE with -alternative character type tables. Normally isspace() matches space, -formfeed, newline, carriage return, horizontal tab, and vertical tab. Perl 5 -no longer includes vertical tab in its set of whitespace characters. The \v -escape that was in the Perl documentation for a long time was never in fact -recognized. However, the character itself was treated as whitespace at least -up to 5.002. In 5.004 and 5.005 it does not match \s. -

    -

    -2. PCRE does not allow repeat quantifiers on lookahead assertions. Perl permits -them, but they do not mean what you might think. For example, (?!a){3} does -not assert that the next three characters are not "a". It just asserts that the -next character is not "a" three times. -

    -

    -3. Capturing subpatterns that occur inside negative lookahead assertions are -counted, but their entries in the offsets vector are never set. Perl sets its -numerical variables from any such patterns that are matched before the -assertion fails to match something (thereby succeeding), but only if the -negative lookahead assertion contains just one branch. -

    -

    -4. Though binary zero characters are supported in the subject string, they are -not allowed in a pattern string because it is passed as a normal C string, -terminated by zero. The escape sequence "\0" can be used in the pattern to -represent a binary zero. -

    -

    -5. The following Perl escape sequences are not supported: \l, \u, \L, \U, -\E, \Q. In fact these are implemented by Perl's general string-handling and -are not part of its pattern matching engine. -

    -

    -6. The Perl \G assertion is not supported as it is not relevant to single -pattern matches. -

    -

    -7. Fairly obviously, PCRE does not support the (?{code}) construction. -

    -

    -8. There are at the time of writing some oddities in Perl 5.005_02 concerned -with the settings of captured strings when part of a pattern is repeated. For -example, matching "aba" against the pattern /^(a(b)?)+$/ sets $2 to the value -"b", but matching "aabbaa" against /^(aa(bb)?)+$/ leaves $2 unset. However, if -the pattern is changed to /^(aa(b(b))?)+$/ then $2 (and $3) get set. -

    -

    -In Perl 5.004 $2 is set in both cases, and that is also true of PCRE. If in the -future Perl changes to a consistent state that is different, PCRE may change to -follow. -

    -

    -9. Another as yet unresolved discrepancy is that in Perl 5.005_02 the pattern -/^(a)?(?(1)a|b)+$/ matches the string "a", whereas in PCRE it does not. -However, in both Perl and PCRE /^(a)?a/ matched against "a" leaves $1 unset. -

    -

    -10. PCRE provides some extensions to the Perl regular expression facilities: -

    -

    -(a) Although lookbehind assertions must match fixed length strings, each -alternative branch of a lookbehind assertion can match a different length of -string. Perl 5.005 requires them all to have the same length. -

    -

    -(b) If PCRE_DOLLAR_ENDONLY is set and PCRE_MULTILINE is not set, the $ meta- -character matches only at the very end of the string. -

    -

    -(c) If PCRE_EXTRA is set, a backslash followed by a letter with no special -meaning is faulted. -

    -

    -(d) If PCRE_UNGREEDY is set, the greediness of the repetition quantifiers is -inverted, that is, by default they are not greedy, but if followed by a -question mark they are. -

    -

    -(e) PCRE_ANCHORED can be used to force a pattern to be tried only at the start -of the subject. -

    -

    -(f) The PCRE_NOTBOL, PCRE_NOTEOL, and PCRE_NOTEMPTY options for -pcre_exec() have no Perl equivalents. -

    -
  • REGULAR EXPRESSION DETAILS -

    -The syntax and semantics of the regular expressions supported by PCRE are -described below. Regular expressions are also described in the Perl -documentation and in a number of other books, some of which have copious -examples. Jeffrey Friedl's "Mastering Regular Expressions", published by -O'Reilly (ISBN 1-56592-257-3), covers them in great detail. The description -here is intended as reference documentation. -

    -

    -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. 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 -meta-characters, which do not stand for themselves but instead are -interpreted in some special way. -

    -

    -There are two different sets of meta-characters: those that are recognized -anywhere in the pattern except within square brackets, and those that are -recognized in square brackets. Outside square brackets, the meta-characters are -as follows: -

    -

    -

    -  \      general escape character with several uses
-  ^      assert start of subject (or line, in multiline mode)
-  $      assert end of subject (or line, in multiline mode)
-  .      match any character except newline (by default)
-  [      start character class definition
-  |      start of alternative branch
-  (      start subpattern
-  )      end subpattern
-  ?      extends the meaning of (
-         also 0 or 1 quantifier
-         also quantifier minimizer
-  *      0 or more quantifier
-  +      1 or more quantifier
-  {      start min/max quantifier
-
    -

    -

    -Part of a pattern that is in square brackets is called a "character class". In -a character class the only meta-characters are: -

    -

    -

    -  \      general escape character
-  ^      negate the class, but only if the first character
-  -      indicates character range
-  ]      terminates the character class
-
    -

    -

    -The following sections describe the use of each of the meta-characters. -

    -
  • BACKSLASH -

    -The backslash character has several uses. Firstly, if it is followed by a -non-alphameric 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 applies whether or not the following character would otherwise be -interpreted as a meta-character, so it is always safe to precede a -non-alphameric with "\" to specify that it stands for itself. In particular, -if you want to match a backslash, you write "\\". -

    -

    -If a pattern is compiled with the PCRE_EXTENDED option, whitespace in the -pattern (other than in a character class) and characters between a "#" outside -a character class and the next newline character are ignored. An escaping -backslash can be used to include a whitespace or "#" character as part of the -pattern. -

    -

    -A second use of backslash provides a way of encoding non-printing characters -in patterns in a visible manner. There is no restriction on the appearance of -non-printing characters, apart from the binary zero that terminates a pattern, -but when a pattern is being prepared by text editing, it is usually easier to -use one of the following escape sequences than the binary character it -represents: -

    -

    -

    -  \a     alarm, that is, the BEL character (hex 07)
-  \cx    "control-x", where x is any character
-  \e     escape (hex 1B)
-  \f     formfeed (hex 0C)
-  \n     newline (hex 0A)
-  \r     carriage return (hex 0D)
-  \t     tab (hex 09)
-  \xhh   character with hex code hh
-  \ddd   character with octal code ddd, or backreference
-
    -

    -

    -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", up to two hexadecimal digits are read (letters can be in upper or -lower case). -

    -

    -After "\0" up to two further octal digits are read. In both cases, 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. -Make sure you supply two digits after the initial zero if the character that -follows is itself an octal digit. -

    -

    -The handling of a backslash followed by a digit other than 0 is complicated. -Outside a character class, PCRE reads it and any following digits as a decimal -number. If the number is less than 10, or if there have been at least that many -previous capturing left parentheses in the expression, the entire sequence is -taken as a back reference. A description of how this works is given -later, following the discussion of parenthesized subpatterns. -

    -

    -Inside a character class, or if the decimal number is greater than 9 and there -have not been that many capturing subpatterns, PCRE re-reads up to three octal -digits following the backslash, and generates a single byte from the least -significant 8 bits of the value. Any subsequent digits stand for themselves. -For example: -

    -

    -

    -  \040   is another way of writing a space
-  \40    is the same, provided there are fewer than 40
-            previous capturing subpatterns
-  \7     is always a back reference
-  \11    might be a back reference, or another way of
-            writing a tab
-  \011   is always a tab
-  \0113  is a tab followed by the character "3"
-  \113   is the character with octal code 113 (since there
-            can be no more than 99 back references)
-  \377   is a byte consisting entirely of 1 bits
-  \81    is either a back reference, or a binary zero
-            followed by the two characters "8" and "1"
-
    -

    -

    -Note that octal values of 100 or greater must not be introduced by a leading -zero, because no more than three octal digits are ever read. -

    -

    -All the sequences that define a single byte 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). Outside a character -class it has a different meaning (see below). -

    -

    -The third use of backslash is for specifying generic character types: -

    -

    -

    -  \d     any decimal digit
-  \D     any character that is not a decimal digit
-  \s     any whitespace character
-  \S     any character that is not a whitespace character
-  \w     any "word" character
-  \W     any "non-word" character
-
    -

    -

    -Each pair of escape sequences partitions the complete set of characters into -two disjoint sets. Any given character matches one, and only one, of each pair. -

    -

    -A "word" character is any letter or digit or the underscore character, that is, -any character which can be part of a Perl "word". The definition of letters and -digits is controlled by PCRE's character tables, and may vary if locale- -specific matching is taking place (see "Locale support" above). For example, in -the "fr" (French) locale, some character codes greater than 128 are used for -accented letters, and these are matched by \w. -

    -

    -These character type sequences can appear both inside and outside character -classes. They each match one character of the appropriate type. If the current -matching point is at the end of the subject string, all of them fail, since -there is no character to match. -

    -

    -The fourth use of backslash is for certain simple assertions. An assertion -specifies a condition that has to be met at a particular point in a match, -without consuming any characters from the subject string. The use of -subpatterns for more complicated assertions is described below. The backslashed -assertions are -

    -

    -

    -  \b     word boundary
-  \B     not a word boundary
-  \A     start of subject (independent of multiline mode)
-  \Z     end of subject or newline at end (independent of multiline mode)
-  \z     end of subject (independent of multiline mode)
-
    -

    -

    -These assertions may not appear in character classes (but note that "\b" has a -different meaning, namely the backspace character, inside a character class). -

    -

    -A word boundary is a position in the subject string where the current character -and the previous character do not both match \w or \W (i.e. one matches -\w and the other matches \W), or the start or end of the string if the -first or last character matches \w, respectively. -

    -

    -The \A, \Z, and \z assertions differ from the traditional circumflex and -dollar (described below) in that they only ever match at the very start and end -of the subject string, whatever options are set. They are not affected by the -PCRE_NOTBOL or PCRE_NOTEOL options. If the startoffset argument of -pcre_exec() is non-zero, \A can never match. The difference between \Z -and \z is that \Z matches before a newline that is the last character of the -string as well as at the end of the string, whereas \z matches only at the -end. -

    -
  • CIRCUMFLEX AND DOLLAR -

    -Outside a character class, in the default matching mode, the circumflex -character is an assertion which is true only if the current matching point is -at the start of the subject string. If the startoffset argument of -pcre_exec() is non-zero, circumflex can never match. Inside a character -class, circumflex has an entirely different meaning (see below). -

    -

    -Circumflex need not be the first character of the pattern if a number of -alternatives are involved, but it should be the first thing in each alternative -in which it appears if the pattern is ever to match that branch. If all -possible alternatives start with a circumflex, that is, if the pattern is -constrained to match only at the start of the subject, it is said to be an -"anchored" pattern. (There are also other constructs that can cause a pattern -to be anchored.) -

    -

    -A dollar character is an assertion which is true only if the current matching -point is at the end of the subject string, or immediately before a newline -character that is the last character in the string (by default). Dollar need -not be the last character of the pattern if a number of alternatives are -involved, but it should be the last item in any branch in which it appears. -Dollar has no special meaning in a character class. -

    -

    -The meaning of dollar can be changed so that it matches only at the very end of -the string, by setting the PCRE_DOLLAR_ENDONLY option at compile or matching -time. This does not affect the \Z assertion. -

    -

    -The meanings of the circumflex and dollar characters are changed if the -PCRE_MULTILINE option is set. When this is the case, they match immediately -after and immediately before an internal "\n" character, respectively, in -addition to matching at the start and end of the subject string. For example, -the pattern /^abc$/ matches the subject string "def\nabc" in multiline mode, -but not otherwise. Consequently, patterns that are anchored in single line mode -because all branches start with "^" are not anchored in multiline mode, and a -match for circumflex is possible when the startoffset argument of -pcre_exec() is non-zero. The PCRE_DOLLAR_ENDONLY option is ignored if -PCRE_MULTILINE is set. -

    -

    -Note that the sequences \A, \Z, and \z can be used to match the start and -end of the subject in both modes, and if all branches of a pattern start with -\A is it always anchored, whether PCRE_MULTILINE is set or not. -

    -
  • FULL STOP (PERIOD, DOT) -

    -Outside a character class, a dot in the pattern matches any one character in -the subject, including a non-printing character, but not (by default) newline. -If the PCRE_DOTALL option is set, then dots match newlines as well. The -handling of dot is entirely independent of the handling of circumflex and -dollar, the only relationship being that they both involve newline characters. -Dot has no special meaning in a character class. -

    -
  • SQUARE BRACKETS -

    -An opening square bracket introduces a character class, terminated by a closing -square bracket. A closing square bracket on its own is not special. If a -closing square bracket is required as a member of the class, it should be the -first data character in the class (after an initial circumflex, if present) or -escaped with a backslash. -

    -

    -A character class matches a single character in the subject; the character must -be in the set of characters defined by the class, unless the first character in -the class is a circumflex, in which case the subject character must not be in -the set defined by the class. If a circumflex is actually required as a member -of the class, ensure it is not the first character, or escape it with a -backslash. -

    -

    -For example, the character class [aeiou] matches any lower case vowel, while -[^aeiou] matches any character that is not a lower case vowel. Note that a -circumflex is just a convenient notation for specifying the characters which -are in the class by enumerating those that are not. It is not an assertion: it -still consumes a character from the subject string, and fails if the current -pointer is at the end of the string. -

    -

    -When caseless matching is set, any letters in a class represent both their -upper case and lower case versions, so for example, a caseless [aeiou] matches -"A" as well as "a", and a caseless [^aeiou] does not match "A", whereas a -caseful version would. -

    -

    -The newline character is never treated in any special way in character classes, -whatever the setting of the PCRE_DOTALL or PCRE_MULTILINE options is. A class -such as [^a] will always match a newline. -

    -

    -The minus (hyphen) character can be used to specify a range of characters in a -character class. For example, [d-m] matches any letter between d and m, -inclusive. If a minus character is required in a class, it must be escaped with -a backslash or appear in a position where it cannot be interpreted as -indicating a range, typically as the first or last character in the class. -

    -

    -It is not possible to have the literal character "]" as the end character of a -range. A pattern such as [W-]46] is interpreted as a class of two characters -("W" and "-") followed by a literal string "46]", so it would match "W46]" or -"-46]". However, if the "]" is escaped with a backslash it is interpreted as -the end of range, so [W-\]46] is interpreted as a single class containing a -range followed by two separate characters. The octal or hexadecimal -representation of "]" can also be used to end a range. -

    -

    -Ranges operate in ASCII collating sequence. They can also be used for -characters specified numerically, for example [\000-\037]. If a range that -includes letters is used when caseless matching is set, it matches the letters -in either case. For example, [W-c] is equivalent to [][\^_`wxyzabc], matched -caselessly, and if character tables for the "fr" locale are in use, -[\xc8-\xcb] matches accented E characters in both cases. -

    -

    -The character types \d, \D, \s, \S, \w, and \W may also appear in a -character class, and add the characters that they match to the class. For -example, [\dABCDEF] matches any hexadecimal digit. A circumflex can -conveniently be used with the upper case character types to specify a more -restricted set of characters than the matching lower case type. For example, -the class [^\W_] matches any letter or digit, but not underscore. -

    -

    -All non-alphameric characters other than \, -, ^ (at the start) and the -terminating ] are non-special in character classes, but it does no harm if they -are escaped. -

    -
  • VERTICAL BAR -

    -Vertical bar characters are used to separate alternative patterns. For example, -the pattern -

    -

    -

    -  gilbert|sullivan
-
    -

    -

    -matches either "gilbert" or "sullivan". Any number of alternatives may appear, -and an empty alternative is permitted (matching the empty string). -The matching process tries each alternative in turn, from left to right, -and the first one that succeeds is used. If the alternatives are within a -subpattern (defined below), "succeeds" means matching the rest of the main -pattern as well as the alternative in the subpattern. -

    -
  • INTERNAL OPTION SETTING -

    -The settings of PCRE_CASELESS, PCRE_MULTILINE, PCRE_DOTALL, and PCRE_EXTENDED -can be changed from within the pattern by a sequence of Perl option letters -enclosed between "(?" and ")". The option letters are -

    -

    -

    -  i  for PCRE_CASELESS
-  m  for PCRE_MULTILINE
-  s  for PCRE_DOTALL
-  x  for PCRE_EXTENDED
-
    -

    -

    -For example, (?im) sets caseless, multiline matching. It is also possible to -unset these options by preceding the letter with a hyphen, and a combined -setting and unsetting such as (?im-sx), which sets PCRE_CASELESS and -PCRE_MULTILINE while unsetting PCRE_DOTALL and PCRE_EXTENDED, is also -permitted. If a letter appears both before and after the hyphen, the option is -unset. -

    -

    -The scope of these option changes depends on where in the pattern the setting -occurs. For settings that are outside any subpattern (defined below), the -effect is the same as if the options were set or unset at the start of -matching. The following patterns all behave in exactly the same way: -

    -

    -

    -  (?i)abc
-  a(?i)bc
-  ab(?i)c
-  abc(?i)
-
    -

    -

    -which in turn is the same as compiling the pattern abc with PCRE_CASELESS set. -In other words, such "top level" settings apply to the whole pattern (unless -there are other changes inside subpatterns). If there is more than one setting -of the same option at top level, the rightmost setting is used. -

    -

    -If an option change occurs inside a subpattern, the effect is different. This -is a change of behaviour in Perl 5.005. An option change inside a subpattern -affects only that part of the subpattern that follows it, so -

    -

    -

    -  (a(?i)b)c
-
    -

    -

    -matches abc and aBc and no other strings (assuming PCRE_CASELESS is not used). -By this means, options can be made to have different settings in different -parts of the pattern. Any changes made in one alternative do carry on -into subsequent branches within the same subpattern. For example, -

    -

    -

    -  (a(?i)b|c)
-
    -

    -

    -matches "ab", "aB", "c", and "C", even though when matching "C" the first -branch is abandoned before the option setting. This is because the effects of -option settings happen at compile time. There would be some very weird -behaviour otherwise. -

    -

    -The PCRE-specific options PCRE_UNGREEDY and PCRE_EXTRA can be changed in the -same way as the Perl-compatible options by using the characters U and X -respectively. The (?X) flag setting is special in that it must always occur -earlier in the pattern than any of the additional features it turns on, even -when it is at top level. It is best put at the start. -

    -
  • SUBPATTERNS -

    -Subpatterns are delimited by parentheses (round brackets), which can be nested. -Marking part of a pattern as a subpattern does two things: -

    -

    -1. It localizes a set of alternatives. For example, the pattern -

    -

    -

    -  cat(aract|erpillar|)
-
    -

    -

    -matches one of the words "cat", "cataract", or "caterpillar". Without the -parentheses, it would match "cataract", "erpillar" or the empty string. -

    -

    -2. It sets up the subpattern as a capturing subpattern (as defined above). -When the whole pattern matches, that portion of the subject string that matched -the subpattern is passed back to the caller via the ovector argument of -pcre_exec(). Opening parentheses are counted from left to right (starting -from 1) to obtain the numbers of the capturing subpatterns. -

    -

    -For example, if the string "the red king" is matched against the pattern -

    -

    -

    -  the ((red|white) (king|queen))
-
    -

    -

    -the captured substrings are "red king", "red", and "king", and are numbered 1, -2, and 3. -

    -

    -The fact that plain parentheses fulfil two functions is not always helpful. -There are often times when a grouping subpattern is required without a -capturing requirement. If an opening parenthesis is followed by "?:", the -subpattern does not do any capturing, and is not counted when computing the -number of any subsequent capturing subpatterns. For example, if the string "the -white queen" is matched against the pattern -

    -

    -

    -  the ((?:red|white) (king|queen))
-
    -

    -

    -the captured substrings are "white queen" and "queen", and are numbered 1 and -2. The maximum number of captured substrings is 99, and the maximum number of -all subpatterns, both capturing and non-capturing, is 200. -

    -

    -As a convenient shorthand, if any option settings are required at the start of -a non-capturing subpattern, the option letters may appear between the "?" and -the ":". Thus the two patterns -

    -

    -

    -  (?i:saturday|sunday)
-  (?:(?i)saturday|sunday)
-
    -

    -

    -match exactly the same set of strings. Because alternative branches are tried -from left to right, and options are not reset until the end of the subpattern -is reached, an option setting in one branch does affect subsequent branches, so -the above patterns match "SUNDAY" as well as "Saturday". -

    -
  • REPETITION -

    -Repetition is specified by quantifiers, which can follow any of the following -items: -

    -

    -

    -  a single character, possibly escaped
-  the . metacharacter
-  a character class
-  a back reference (see next section)
-  a parenthesized subpattern (unless it is an assertion - see below)
-
    -

    -

    -The general repetition quantifier specifies a minimum and maximum number of -permitted matches, by giving the two numbers in curly brackets (braces), -separated by a comma. The numbers must be less than 65536, and the first must -be less than or equal to the second. For example: -

    -

    -

    -  z{2,4}
-
    -

    -

    -matches "zz", "zzz", or "zzzz". A closing brace on its own is not a special -character. If the second number is omitted, but the comma is present, there is -no upper limit; if the second number and the comma are both omitted, the -quantifier specifies an exact number of required matches. Thus -

    -

    -

    -  [aeiou]{3,}
-
    -

    -

    -matches at least 3 successive vowels, but may match many more, while -

    -

    -

    -  \d{8}
-
    -

    -

    -matches exactly 8 digits. An opening curly bracket that appears in a position -where a quantifier is not allowed, or one that does not match the syntax of a -quantifier, is taken as a literal character. For example, {,6} is not a -quantifier, but a literal string of four characters. -

    -

    -The quantifier {0} is permitted, causing the expression to behave as if the -previous item and the quantifier were not present. -

    -

    -For convenience (and historical compatibility) the three most common -quantifiers have single-character abbreviations: -

    -

    -

    -  *    is equivalent to {0,}
-  +    is equivalent to {1,}
-  ?    is equivalent to {0,1}
-
    -

    -

    -It is possible to construct infinite loops by following a subpattern that can -match no characters with a quantifier that has no upper limit, for example: -

    -

    -

    -  (a?)*
-
    -

    -

    -Earlier versions of Perl and PCRE used to give an error at compile time for -such patterns. However, because there are cases where this can be useful, such -patterns are now accepted, but if any repetition of the subpattern does in fact -match no characters, the loop is forcibly broken. -

    -

    -By default, the quantifiers are "greedy", that is, they match as much as -possible (up to the maximum number of permitted times), without causing the -rest of the pattern to fail. The classic example of where this gives problems -is in trying to match comments in C programs. These appear between the -sequences /* and */ and within the sequence, individual * and / characters may -appear. An attempt to match C comments by applying the pattern -

    -

    -

    -  /\*.*\*/
-
    -

    -

    -to the string -

    -

    -

    -  /* first command */  not comment  /* second comment */
-
    -

    -

    -fails, because it matches the entire string due to the greediness of the .* -item. -

    -

    -However, if a quantifier is followed by a question mark, then it ceases to be -greedy, and instead matches the minimum number of times possible, so the -pattern -

    -

    -

    -  /\*.*?\*/
-
    -

    -

    -does the right thing with the C comments. The meaning of the various -quantifiers is not otherwise changed, just the preferred number of matches. -Do not confuse this use of question mark with its use as a quantifier in its -own right. Because it has two uses, it can sometimes appear doubled, as in -

    -

    -

    -  \d??\d
-
    -

    -

    -which matches one digit by preference, but can match two if that is the only -way the rest of the pattern matches. -

    -

    -If the PCRE_UNGREEDY option is set (an option which is not available in Perl) -then the quantifiers are not greedy by default, but individual ones can be made -greedy by following them with a question mark. In other words, it inverts the -default behaviour. -

    -

    -When a parenthesized subpattern is quantified with a minimum repeat count that -is greater than 1 or with a limited maximum, more store is required for the -compiled pattern, in proportion to the size of the minimum or maximum. -

    -

    -If a pattern starts with .* or .{0,} and the PCRE_DOTALL option (equivalent -to Perl's /s) is set, thus allowing the . to match newlines, then the pattern -is implicitly anchored, because whatever follows will be tried against every -character position in the subject string, so there is no point in retrying the -overall match at any position after the first. PCRE treats such a pattern as -though it were preceded by \A. In cases where it is known that the subject -string contains no newlines, it is worth setting PCRE_DOTALL when the pattern -begins with .* in order to obtain this optimization, or alternatively using ^ -to indicate anchoring explicitly. -

    -

    -When a capturing subpattern is repeated, the value captured is the substring -that matched the final iteration. For example, after -

    -

    -

    -  (tweedle[dume]{3}\s*)+
-
    -

    -

    -has matched "tweedledum tweedledee" the value of the captured substring is -"tweedledee". However, if there are nested capturing subpatterns, the -corresponding captured values may have been set in previous iterations. For -example, after -

    -

    -

    -  /(a|(b))+/
-
    -

    -

    -matches "aba" the value of the second captured substring is "b". -

    -
  • BACK REFERENCES -

    -Outside a character class, a backslash followed by a digit greater than 0 (and -possibly further digits) is a back reference to a capturing subpattern earlier -(i.e. to its left) in the pattern, provided there have been that many previous -capturing left parentheses. -

    -

    -However, if the decimal number following the backslash is less than 10, it is -always taken as a back reference, and causes an error only if there are not -that many capturing left parentheses in the entire pattern. In other words, the -parentheses that are referenced need not be to the left of the reference for -numbers less than 10. See the section entitled "Backslash" above for further -details of the handling of digits following a backslash. -

    -

    -A back reference matches whatever actually matched the capturing subpattern in -the current subject string, rather than anything matching the subpattern -itself. So the pattern -

    -

    -

    -  (sens|respons)e and \1ibility
-
    -

    -

    -matches "sense and sensibility" and "response and responsibility", but not -"sense and responsibility". If caseful matching is in force at the time of the -back reference, then the case of letters is relevant. For example, -

    -

    -

    -  ((?i)rah)\s+\1
-
    -

    -

    -matches "rah rah" and "RAH RAH", but not "RAH rah", even though the original -capturing subpattern is matched caselessly. -

    -

    -There may be more than one back reference to the same subpattern. If a -subpattern has not actually been used in a particular match, then any back -references to it always fail. For example, the pattern -

    -

    -

    -  (a|(bc))\2
-
    -

    -

    -always fails if it starts to match "a" rather than "bc". Because there may be -up to 99 back references, all digits following the backslash are taken -as part of a potential back reference number. If the pattern continues with a -digit character, then some delimiter must be used to terminate the back -reference. If the PCRE_EXTENDED option is set, this can be whitespace. -Otherwise an empty comment can be used. -

    -

    -A back reference that occurs inside the parentheses to which it refers fails -when the subpattern is first used, so, for example, (a\1) never matches. -However, such references can be useful inside repeated subpatterns. For -example, the pattern -

    -

    -

    -  (a|b\1)+
-
    -

    -

    -matches any number of "a"s and also "aba", "ababaa" etc. At each iteration of -the subpattern, the back reference matches the character string corresponding -to the previous iteration. In order for this to work, the pattern must be such -that the first iteration does not need to match the back reference. This can be -done using alternation, as in the example above, or by a quantifier with a -minimum of zero. -

    -
  • ASSERTIONS -

    -An assertion is a test on the characters following or preceding the current -matching point that does not actually consume any characters. The simple -assertions coded as \b, \B, \A, \Z, \z, ^ and $ are described above. More -complicated assertions are coded as subpatterns. There are two kinds: those -that look ahead of the current position in the subject string, and those that -look behind it. -

    -

    -An assertion subpattern is matched in the normal way, except that it does not -cause the current matching position to be changed. Lookahead assertions start -with (?= for positive assertions and (?! for negative assertions. For example, -

    -

    -

    -  \w+(?=;)
-
    -

    -

    -matches a word followed by a semicolon, but does not include the semicolon in -the match, and -

    -

    -

    -  foo(?!bar)
-
    -

    -

    -matches any occurrence of "foo" that is not followed by "bar". Note that the -apparently similar pattern -

    -

    -

    -  (?!foo)bar
-
    -

    -

    -does not find an occurrence of "bar" that is preceded by something other than -"foo"; it finds any occurrence of "bar" whatsoever, because the assertion -(?!foo) is always true when the next three characters are "bar". A -lookbehind assertion is needed to achieve this effect. -

    -

    -Lookbehind assertions start with (?<= for positive assertions and (?<! for -negative assertions. For example, -

    -

    -

    -  (?<!foo)bar
-
    -

    -

    -does find an occurrence of "bar" that is not preceded by "foo". The contents of -a lookbehind assertion are restricted such that all the strings it matches must -have a fixed length. However, if there are several alternatives, they do not -all have to have the same fixed length. Thus -

    -

    -

    -  (?<=bullock|donkey)
-
    -

    -

    -is permitted, but -

    -

    -

    -  (?<!dogs?|cats?)
-
    -

    -

    -causes an error at compile time. Branches that match different length strings -are permitted only at the top level of a lookbehind assertion. This is an -extension compared with Perl 5.005, which requires all branches to match the -same length of string. An assertion such as -

    -

    -

    -  (?<=ab(c|de))
-
    -

    -

    -is not permitted, because its single top-level branch can match two different -lengths, but it is acceptable if rewritten to use two top-level branches: -

    -

    -

    -  (?<=abc|abde)
-
    -

    -

    -The implementation of lookbehind assertions is, for each alternative, to -temporarily move the current position back by the fixed width and then try to -match. If there are insufficient characters before the current position, the -match is deemed to fail. Lookbehinds in conjunction with once-only subpatterns -can be particularly useful for matching at the ends of strings; an example is -given at the end of the section on once-only subpatterns. -

    -

    -Several assertions (of any sort) may occur in succession. For example, -

    -

    -

    -  (?<=\d{3})(?<!999)foo
-
    -

    -

    -matches "foo" preceded by three digits that are not "999". Notice that each of -the assertions is applied independently at the same point in the subject -string. First there is a check that the previous three characters are all -digits, then there is a check that the same three characters are not "999". -This pattern does not match "foo" preceded by six characters, the first -of which are digits and the last three of which are not "999". For example, it -doesn't match "123abcfoo". A pattern to do that is -

    -

    -

    -  (?<=\d{3}...)(?<!999)foo
-
    -

    -

    -This time the first assertion looks at the preceding six characters, checking -that the first three are digits, and then the second assertion checks that the -preceding three characters are not "999". -

    -

    -Assertions can be nested in any combination. For example, -

    -

    -

    -  (?<=(?<!foo)bar)baz
-
    -

    -

    -matches an occurrence of "baz" that is preceded by "bar" which in turn is not -preceded by "foo", while -

    -

    -

    -  (?<=\d{3}(?!999)...)foo
-
    -

    -

    -is another pattern which matches "foo" preceded by three digits and any three -characters that are not "999". -

    -

    -Assertion subpatterns are not capturing subpatterns, and may not be repeated, -because it makes no sense to assert the same thing several times. If any kind -of assertion contains capturing subpatterns within it, these are counted for -the purposes of numbering the capturing subpatterns in the whole pattern. -However, substring capturing is carried out only for positive assertions, -because it does not make sense for negative assertions. -

    -

    -Assertions count towards the maximum of 200 parenthesized subpatterns. -

    -
  • ONCE-ONLY SUBPATTERNS -

    -With both maximizing and minimizing repetition, failure of what follows -normally causes the repeated item to be re-evaluated to see if a different -number of repeats allows the rest of the pattern to match. Sometimes it is -useful to prevent this, either to change the nature of the match, or to cause -it fail earlier than it otherwise might, when the author of the pattern knows -there is no point in carrying on. -

    -

    -Consider, for example, the pattern \d+foo when applied to the subject line -

    -

    -

    -  123456bar
-
    -

    -

    -After matching all 6 digits and then failing to match "foo", the normal -action of the matcher is to try again with only 5 digits matching the \d+ -item, and then with 4, and so on, before ultimately failing. Once-only -subpatterns provide the means for specifying that once a portion of the pattern -has matched, it is not to be re-evaluated in this way, so the matcher would -give up immediately on failing to match "foo" the first time. The notation is -another kind of special parenthesis, starting with (?> as in this example: -

    -

    -

    -  (?>\d+)bar
-
    -

    -

    -This kind of parenthesis "locks up" the part of the pattern it contains once -it has matched, and a failure further into the pattern is prevented from -backtracking into it. Backtracking past it to previous items, however, works as -normal. -

    -

    -An alternative description is that a subpattern of this type matches the string -of characters that an identical standalone pattern would match, if anchored at -the current point in the subject string. -

    -

    -Once-only subpatterns are not capturing subpatterns. Simple cases such as the -above example can be thought of as a maximizing repeat that must swallow -everything it can. So, while both \d+ and \d+? are prepared to adjust the -number of digits they match in order to make the rest of the pattern match, -(?>\d+) can only match an entire sequence of digits. -

    -

    -This construction can of course contain arbitrarily complicated subpatterns, -and it can be nested. -

    -

    -Once-only subpatterns can be used in conjunction with lookbehind assertions to -specify efficient matching at the end of the subject string. Consider a simple -pattern such as -

    -

    -

    -  abcd$
-
    -

    -

    -when applied to a long string which does not match it. Because matching -proceeds from left to right, PCRE will look for each "a" in the subject and -then see if what follows matches the rest of the pattern. If the pattern is -specified as -

    -

    -

    -  ^.*abcd$
-
    -

    -

    -then the initial .* matches the entire string at first, but when this fails, it -backtracks to match all but the last character, then all but the last two -characters, and so on. Once again the search for "a" covers the entire string, -from right to left, so we are no better off. However, if the pattern is written -as -

    -

    -

    -  ^(?>.*)(?<=abcd)
-
    -

    -

    -then there can be no backtracking for the .* item; it can match only the entire -string. The subsequent lookbehind assertion does a single test on the last four -characters. If it fails, the match fails immediately. For long strings, this -approach makes a significant difference to the processing time. -

    -
  • CONDITIONAL SUBPATTERNS -

    -It is possible to cause the matching process to obey a subpattern -conditionally or to choose between two alternative subpatterns, depending on -the result of an assertion, or whether a previous capturing subpattern matched -or not. The two possible forms of conditional subpattern are -

    -

    -

    -  (?(condition)yes-pattern)
-  (?(condition)yes-pattern|no-pattern)
-
    -

    -

    -If the condition is satisfied, the yes-pattern is used; otherwise the -no-pattern (if present) is used. If there are more than two alternatives in the -subpattern, a compile-time error occurs. -

    -

    -There are two kinds of condition. If the text between the parentheses consists -of a sequence of digits, then the condition is satisfied if the capturing -subpattern of that number has previously matched. Consider the following -pattern, which contains non-significant white space to make it more readable -(assume the PCRE_EXTENDED option) and to divide it into three parts for ease -of discussion: -

    -

    -

    -  ( \( )?    [^()]+    (?(1) \) )
-
    -

    -

    -The first part matches an optional opening parenthesis, and if that -character is present, sets it as the first captured substring. The second part -matches one or more characters that are not parentheses. The third part is a -conditional subpattern that tests whether the first set of parentheses matched -or not. If they did, that is, if subject started with an opening parenthesis, -the condition is true, and so the yes-pattern is executed and a closing -parenthesis is required. Otherwise, since no-pattern is not present, the -subpattern matches nothing. In other words, this pattern matches a sequence of -non-parentheses, optionally enclosed in parentheses. -

    -

    -If the condition is not a sequence of digits, it must be an assertion. This may -be a positive or negative lookahead or lookbehind assertion. Consider this -pattern, again containing non-significant white space, and with the two -alternatives on the second line: -

    -

    -

    -  (?(?=[^a-z]*[a-z])
-  \d{2}[a-z]{3}-\d{2}  |  \d{2}-\d{2}-\d{2} )
-
    -

    -

    -The condition is a positive lookahead assertion that matches an optional -sequence of non-letters followed by a letter. In other words, it tests for the -presence of at least one letter in the subject. If a letter is found, the -subject is matched against the first alternative; otherwise it is matched -against the second. This pattern matches strings in one of the two forms -dd-aaa-dd or dd-dd-dd, where aaa are letters and dd are digits. -

    -
  • COMMENTS -

    -The sequence (?# marks the start of a comment which continues up to the next -closing parenthesis. Nested parentheses are not permitted. The characters -that make up a comment play no part in the pattern matching at all. -

    -

    -If the PCRE_EXTENDED option is set, an unescaped # character outside a -character class introduces a comment that continues up to the next newline -character in the pattern. -

    -
  • PERFORMANCE -

    -Certain items that may appear in patterns are more efficient than others. It is -more efficient to use a character class like [aeiou] than a set of alternatives -such as (a|e|i|o|u). In general, the simplest construction that provides the -required behaviour is usually the most efficient. Jeffrey Friedl's book -contains a lot of discussion about optimizing regular expressions for efficient -performance. -

    -

    -When a pattern begins with .* and the PCRE_DOTALL option is set, the pattern is -implicitly anchored by PCRE, since it can match only at the start of a subject -string. However, if PCRE_DOTALL is not set, PCRE cannot make this optimization, -because the . metacharacter does not then match a newline, and if the subject -string contains newlines, the pattern may match from the character immediately -following one of them instead of from the very start. For example, the pattern -

    -

    -

    -  (.*) second
-
    -

    -

    -matches the subject "first\nand second" (where \n stands for a newline -character) with the first captured substring being "and". In order to do this, -PCRE has to retry the match starting after every newline in the subject. -

    -

    -If you are using such a pattern with subject strings that do not contain -newlines, the best performance is obtained by setting PCRE_DOTALL, or starting -the pattern with ^.* to indicate explicit anchoring. That saves PCRE from -having to scan along the subject looking for a newline to restart at. -

    -

    -Beware of patterns that contain nested indefinite repeats. These can take a -long time to run when applied to a string that does not match. Consider the -pattern fragment -

    -

    -

    -  (a+)*
-
    -

    -

    -This can match "aaaa" in 33 different ways, and this number increases very -rapidly as the string gets longer. (The * repeat can match 0, 1, 2, 3, or 4 -times, and for each of those cases other than 0, the + repeats can match -different numbers of times.) When the remainder of the pattern is such that the -entire match is going to fail, PCRE has in principle to try every possible -variation, and this can take an extremely long time. -

    -

    -An optimization catches some of the more simple cases such as -

    -

    -

    -  (a+)*b
-
    -

    -

    -where a literal character follows. Before embarking on the standard matching -procedure, PCRE checks that there is a "b" later in the subject string, and if -there is not, it fails the match immediately. However, when there is no -following literal this optimization cannot be used. You can see the difference -by comparing the behaviour of -

    -

    -

    -  (a+)*\d
-
    -

    -

    -with the pattern above. The former gives a failure almost instantly when -applied to a whole line of "a" characters, whereas the latter takes an -appreciable time with strings longer than about 20 characters. -

    -
  • AUTHOR -

    -Philip Hazel <ph10@cam.ac.uk> -
    -University Computing Service, -
    -New Museums Site, -
    -Cambridge CB2 3QG, England. -
    -Phone: +44 1223 334714 -

    -

    -Last updated: 29 July 1999 -
    -Copyright (c) 1997-1999 University of Cambridge. diff --git a/ext/pcre/pcrelib/pcre.3.txt b/ext/pcre/pcrelib/pcre.3.txt deleted file mode 100644 index 8bd367c215..0000000000 --- a/ext/pcre/pcrelib/pcre.3.txt +++ /dev/null @@ -1,1739 +0,0 @@ -NAME - pcre - Perl-compatible regular expressions. - - - -SYNOPSIS - #include - - pcre *pcre_compile(const char *pattern, int options, - const char **errptr, int *erroffset, - const unsigned char *tableptr); - - pcre_extra *pcre_study(const pcre *code, int options, - const char **errptr); - - int pcre_exec(const pcre *code, const pcre_extra *extra, - const char *subject, int length, int startoffset, - int options, int *ovector, int ovecsize); - - int pcre_copy_substring(const char *subject, int *ovector, - int stringcount, int stringnumber, char *buffer, - int buffersize); - - int pcre_get_substring(const char *subject, int *ovector, - int stringcount, int stringnumber, - const char **stringptr); - - int pcre_get_substring_list(const char *subject, - int *ovector, int stringcount, const char ***listptr); - - const unsigned char *pcre_maketables(void); - - int pcre_info(const pcre *code, int *optptr, *firstcharptr); - - char *pcre_version(void); - - void *(*pcre_malloc)(size_t); - - void (*pcre_free)(void *); - - - - -DESCRIPTION - The PCRE library is a set of functions that implement regu- - lar expression pattern matching using the same syntax and - semantics as Perl 5, with just a few differences (see - below). The current implementation corresponds to Perl - 5.005. - - PCRE has its own native API, which is described in this - document. There is also a set of wrapper functions that - correspond to the POSIX API. These are described in the - pcreposix documentation. - The native API function prototypes are defined in the header - file pcre.h, and on Unix systems the library itself is - called libpcre.a, so can be accessed by adding -lpcre to the - command for linking an application which calls it. - - The functions pcre_compile(), pcre_study(), and pcre_exec() - are used for compiling and matching regular expressions, - while pcre_copy_substring(), pcre_get_substring(), and - pcre_get_substring_list() are convenience functions for - extracting captured substrings from a matched subject - string. The function pcre_maketables() is used (optionally) - to build a set of character tables in the current locale for - passing to pcre_compile(). - - The function pcre_info() is used to find out information - about a compiled pattern, while the function pcre_version() - returns a pointer to a string containing the version of PCRE - and its date of release. - - The global variables pcre_malloc and pcre_free initially - contain the entry points of the standard malloc() and free() - functions respectively. PCRE calls the memory management - functions via these variables, so a calling program can - replace them if it wishes to intercept the calls. This - should be done before calling any PCRE functions. - - - -MULTI-THREADING - The PCRE functions can be used in multi-threading applica- - tions, with the proviso that the memory management functions - pointed to by pcre_malloc and pcre_free are shared by all - threads. - - The compiled form of a regular expression is not altered - during matching, so the same compiled pattern can safely be - used by several threads at once. - - - -COMPILING A PATTERN - The function pcre_compile() is called to compile a pattern - into an internal form. The pattern is a C string terminated - by a binary zero, and is passed in the argument pattern. 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 this for conveni- - ence, but in fact pcre is just a typedef for void, since the - contents of the block are not externally defined. It is up - to the caller to free the memory when it is no longer - required. - - The size of a compiled pattern is roughly proportional to - the length of the pattern string, except that each character - class (other than those containing just a single character, - negated or not) requires 33 bytes, and repeat quantifiers - with a minimum greater than one or a bounded maximum cause - the relevant portions of the compiled pattern to be repli- - cated. - - The options argument contains independent bits that affect - the compilation. It should be zero if no options are - required. Some of the options, in particular, those that are - compatible with Perl, can also be set and unset from within - the pattern (see the detailed description of regular expres- - sions below). For these options, the contents of the options - argument specifies their initial settings at the start of - compilation and execution. The PCRE_ANCHORED option can be - set at the time of matching as well as at compile time. - - If errptr is NULL, pcre_compile() returns NULL immediately. - Otherwise, if compilation of a pattern fails, pcre_compile() - returns NULL, and sets the variable pointed to by errptr to - point to a textual error message. The offset from the start - of the pattern to the character where the error was - discovered is placed in the variable pointed to by - erroffset, which must not be NULL. If it is, an immediate - error is given. - - If the final argument, tableptr, is NULL, PCRE uses a - default set of character tables which are built when it is - compiled, using the default C locale. Otherwise, tableptr - must be the result of a call to pcre_maketables(). See the - section on locale support below. - - The following option bits are defined in the 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 start of the - string which 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_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. - - 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 the final - character if it is a newline (but not before any other new- - lines). The PCRE_DOLLAR_ENDONLY option is ignored if - PCRE_MULTILINE is set. There is no equivalent to this option - in Perl. - - PCRE_DOTALL - - If this bit is set, a dot metacharater in the pattern - matches all characters, including newlines. Without it, new- - lines are excluded. This option is equivalent to Perl's /s - option. A negative class such as [^a] always matches a new- - line character, independent of the setting of this option. - - PCRE_EXTENDED - - If this bit is set, whitespace data characters in the pat- - tern are totally ignored except when escaped or inside a - character class, and characters between an unescaped # out- - side a character class and the next newline character, - inclusive, are also ignored. This is equivalent to Perl's /x - option, and 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 sub- - pattern. - - PCRE_EXTRA - - This option turns on additional functionality of PCRE that - is incompatible with Perl. 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. - There are at present no other features controlled by this - option. - - PCRE_MULTILINE - - By default, PCRE treats the subject string as consisting of - a single "line" of characters (even if it actually contains - several 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 any newline in the subject string, - respectively, as well as at the very start and end. This is - equivalent to Perl's /m option. If there are no "\n" charac- - ters in a subject string, or no occurrences of ^ or $ in a - pattern, setting PCRE_MULTILINE has no effect. - - PCRE_UNGREEDY - - This option inverts the "greediness" of the quantifiers so - that they are not greedy by default, but become greedy if - followed by "?". It is not compatible with Perl. It can also - be set by a (?U) option setting within the pattern. - - - -STUDYING A PATTERN - When a pattern is going to be used several times, it is - worth spending more time analyzing it in order to speed up - the time taken for matching. The function pcre_study() takes - a pointer to a compiled pattern as its first argument, and - returns a pointer to a pcre_extra block (another void - typedef) containing additional information about the pat- - tern; this can be passed to pcre_exec(). If no additional - information is available, NULL is returned. - - The second argument contains option bits. At present, no - options are defined for pcre_study(), and this argument - should always be zero. - - The third argument for pcre_study() is a pointer to an error - message. If studying succeeds (even if no data is returned), - the variable it points to is set to NULL. Otherwise it - points to a textual error message. - - At present, studying a pattern is useful only for non- - anchored patterns that do not have a single fixed starting - character. A bitmap of possible starting characters is - created. - - - -LOCALE SUPPORT - PCRE handles caseless matching, and determines whether char- - acters are letters, digits, or whatever, by reference to a - set of tables. The library contains a default set of tables - which is created in the default C locale when PCRE is com- - piled. This is used when the final argument of - pcre_compile() is NULL, and is sufficient for many applica- - tions. - - An alternative set of tables can, however, be supplied. Such - tables are built by calling the pcre_maketables() function, - which has no arguments, in the relevant locale. The result - can then be passed to pcre_compile() as often as necessary. - For example, to build and use tables that are appropriate - for the French locale (where accented characters with codes - greater than 128 are treated as letters), the following code - could be used: - - setlocale(LC_CTYPE, "fr"); - tables = pcre_maketables(); - re = pcre_compile(..., tables); - - The tables are built in memory that is obtained via - pcre_malloc. The pointer that is passed to pcre_compile is - saved with the compiled pattern, and the same tables are - used via this pointer by pcre_study() and pcre_exec(). Thus - for any single pattern, compilation, studying and matching - all happen in the same locale, but different patterns can be - compiled in different locales. It is the caller's responsi- - bility to ensure that the memory containing the tables - remains available for as long as it is needed. - - - -INFORMATION ABOUT A PATTERN - The pcre_info() function returns information about a com- - piled pattern. Its yield is the number of capturing subpat- - terns, or one of the following 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. These option bits are those specified in the - call to pcre_compile(), modified by any top-level option - settings within the pattern itself, and with the - PCRE_ANCHORED bit set if the form of the pattern implies - that it can match only at the start of a subject string. - - 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. If there is a fixed - first character, e.g. from a pattern such as - (cat|cow|coyote), then it is returned in the integer pointed - to by firstcharptr. Otherwise, if either - - (a) the pattern was compiled with the PCRE_MULTILINE option, - and every branch starts with "^", or - - (b) every branch of the pattern starts with ".*" and - PCRE_DOTALL is not set (if it were set, the pattern would be - anchored), - then -1 is returned, indicating that the pattern matches - only at the start of a subject string or after any "\n" - within the string. Otherwise -2 is returned. - - - -MATCHING A PATTERN - The function pcre_exec() is called to match a subject string - against a pre-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. Otherwise this - must be NULL. - - The PCRE_ANCHORED option can be passed in the options argu- - ment, whose unused bits must be zero. However, 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. - - There are also three further options that can be set only at - matching time: - - PCRE_NOTBOL - - The first character of the 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. - - PCRE_NOTEOL - - The end of the string is not the end of a line, so the dol- - lar metacharacter should not match it nor (except in multi- - line mode) a newline immediately before it. Setting this - without PCRE_MULTILINE (at compile time) causes dollar never - to match. - - PCRE_NOTEMPTY - - An empty string is not considered to be a valid match if - this option is set. If there are alternatives in the pat- - tern, they are tried. If all the alternatives match the - empty string, the entire match fails. For example, if the - pattern - - a?b? - - is applied to a string not beginning with "a" or "b", it - matches the empty string at the start of the subject. With - PCRE_NOTEMPTY set, this match is not valid, so PCRE searches - further into the string for occurrences of "a" or "b". Perl - has no direct equivalent of this option, but it makes a - special case of a pattern match of the empty string within - its split() function, or when using the /g modifier. Using - PCRE_NOTEMPTY it is possible to emulate this behaviour. - - The subject string is passed as a pointer in subject, a - length in length, and a starting offset in startoffset. - Unlike the pattern string, it may contain binary zero char- - acters. 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 success. Setting startoffset differs - from just passing over a shortened string and setting - PCRE_NOTBOL in the case of a pattern that begins with any - kind of lookbehind. For example, consider the pattern - - \Biss\B - - which finds occurrences of "iss" in the middle of words. (\B - matches only if the current position in the subject is not a - word boundary.) When applied to the string "Mississipi" the - first call to pcre_exec() finds the first occurrence. If - pcre_exec() is called again with just the remainder of the - subject, namely "issipi", it does not match, because \B is - always false at the start of the subject, which is deemed to - be a word boundary. However, if pcre_exec() is passed the - entire string again, but with startoffset set to 4, it finds - the second occurrence of "iss" because it is able to look - behind the starting point to discover that it is preceded by - a letter. - - If a non-zero starting offset is passed when the pattern is - anchored, one attempt to match at the given offset is tried. - This can only succeed if the pattern does not require the - match to be at the start of the subject. - - In general, a pattern matches a certain portion of the sub- - ject, 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 substring. - PCRE supports several other kinds of parenthesized subpat- - tern 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. The - first two-thirds of the vector is used to pass back captured - substrings, each substring using a pair of integers. The - remaining third of the vector is used as workspace by - pcre_exec() while matching capturing 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 has been 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 substring, 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 subpattern, and so on. The value returned by - pcre_exec() is the number of pairs that have been set. 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. - - Some convenience functions are provided for extracting the - captured substrings as separate strings. These are described - in the following section. - - It is possible for an 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) subpatterns 1 and 3 - are matched, but 2 is not. When this happens, both offset - values corresponding to the unused subpattern are set to -1. - - If a capturing subpattern is matched repeatedly, it is the - last portion of the string that it matched that gets - returned. - - If the vector is too small to hold all the captured sub- - strings, 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 offsets 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 isn't 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. - - Note that pcre_info() can be used to find out how many cap- - turing 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. - If pcre_exec() fails, it returns a negative number. The fol- - lowing are defined in the header file: - - PCRE_ERROR_NOMATCH (-1) - - The subject string did not match the pattern. - - PCRE_ERROR_NULL (-2) - - Either code or subject was passed as NULL, or ovector was - NULL and ovecsize was not zero. - - PCRE_ERROR_BADOPTION (-3) - - An unrecognized bit was set in the options argument. - - PCRE_ERROR_BADMAGIC (-4) - - PCRE stores a 4-byte "magic number" at the start of the com- - piled code, to catch the case when it is passed a junk - pointer. This is the error it gives when the magic number - isn't present. - - PCRE_ERROR_UNKNOWN_NODE (-5) - - While running the pattern match, an unknown item was encoun- - tered in the compiled pattern. This error could be caused by - a bug in PCRE or by overwriting of the compiled pattern. - - PCRE_ERROR_NOMEMORY (-6) - - If a pattern contains back references, but the ovector that - is passed to pcre_exec() is not big enough to remember the - referenced substrings, PCRE gets a block of memory at the - start of matching to use for this purpose. If the call via - pcre_malloc() fails, this error is given. The memory is - freed at the end of matching. - - - -EXTRACTING CAPTURED SUBSTRINGS - 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_substring_list() are provided for extracting - captured substrings as new, separate, zero-terminated - strings. A substring that contains a binary zero is - correctly extracted and has a further zero added on the end, - but the result does not, of course, function as a C string. - - The first three arguments are the same for all three func- - tions: subject is the subject string which has just been - successfully matched, ovector is a pointer to the vector of - integer offsets that was passed to pcre_exec(), and - stringcount is the number of substrings that were captured - by the match, including the substring that matched the - entire regular expression. This is the value returned by - pcre_exec if it is greater than zero. If pcre_exec() - returned zero, indicating that it ran out of space in ovec- - tor, then the value passed as stringcount should be the size - of the vector divided by three. - - The functions pcre_copy_substring() and pcre_get_substring() - extract a single substring, whose number is given as string- - number. A value of zero extracts the substring that matched - the entire pattern, while higher values extract the captured - substrings. For pcre_copy_substring(), the string is placed - in buffer, whose length is given by buffersize, while for - pcre_get_substring() a new block of store is obtained via - pcre_malloc, and its address is returned via stringptr. The - yield of the function is the length of the string, not - including the terminating zero, or one of - - PCRE_ERROR_NOMEMORY (-6) - - The buffer was too small for pcre_copy_substring(), or the - attempt to get memory failed for pcre_get_substring(). - - PCRE_ERROR_NOSUBSTRING (-7) - - There is no substring whose number is stringnumber. - - The pcre_get_substring_list() function extracts all avail- - able substrings and builds a list of pointers to them. All - this is done in a single block of memory which is obtained - via pcre_malloc. The address of the memory block is returned - via listptr, which is also the start of the list of string - pointers. The end of the list is marked by a NULL pointer. - The yield of the function is zero if all went well, or - - PCRE_ERROR_NOMEMORY (-6) - - if the attempt to get the memory block failed. - - When any of these functions encounter a substring that is - unset, which can happen when capturing subpattern number n+1 - matches some part of the subject, but subpattern n has not - been used at all, they return an empty string. This can be - distinguished from a genuine zero-length substring by - inspecting the appropriate offset in ovector, which is nega- - tive for unset substrings. - - - -LIMITATIONS - There are some size limitations in PCRE but it is hoped that - they will never in practice be relevant. The maximum length - of a compiled pattern is 65539 (sic) bytes. All values in - repeating quantifiers must be less than 65536. The maximum - number of capturing subpatterns is 99. The maximum number - of all parenthesized subpatterns, including capturing sub- - patterns, assertions, and other types of subpattern, is 200. - - The maximum length of a subject string is the largest posi- - tive number that an integer variable can hold. However, PCRE - uses recursion to handle subpatterns and indefinite repeti- - tion. This means that the available stack space may limit - the size of a subject string that can be processed by cer- - tain patterns. - - - -DIFFERENCES FROM PERL - The differences described here are with respect to Perl - 5.005. - - 1. By default, a whitespace character is any character that - the C library function isspace() recognizes, though it is - possible to compile PCRE with alternative character type - tables. Normally isspace() matches space, formfeed, newline, - carriage return, horizontal tab, and vertical tab. Perl 5 no - longer includes vertical tab in its set of whitespace char- - acters. The \v escape that was in the Perl documentation for - a long time was never in fact recognized. However, the char- - acter itself was treated as whitespace at least up to 5.002. - In 5.004 and 5.005 it does not match \s. - - 2. PCRE does not allow repeat quantifiers on lookahead - assertions. Perl permits them, but they do not mean what you - might think. For example, (?!a){3} does not assert that the - next three characters are not "a". It just asserts that the - next character is not "a" three times. - - 3. Capturing subpatterns that occur inside negative looka- - head assertions are counted, but their entries in the - offsets vector are never set. Perl sets its numerical vari- - ables from any such patterns that are matched before the - assertion fails to match something (thereby succeeding), but - only if the negative lookahead assertion contains just one - branch. - - 4. Though binary zero characters are supported in the sub- - ject string, they are not allowed in a pattern string - because it is passed as a normal C string, terminated by - zero. The escape sequence "\0" can be used in the pattern to - represent a binary zero. - 5. The following Perl escape sequences are not supported: - \l, \u, \L, \U, \E, \Q. In fact these are implemented by - Perl's general string-handling and are not part of its pat- - tern matching engine. - - 6. The Perl \G assertion is not supported as it is not - relevant to single pattern matches. - - 7. Fairly obviously, PCRE does not support the (?{code}) - construction. - - 8. There are at the time of writing some oddities in Perl - 5.005_02 concerned with the settings of captured strings - when part of a pattern is repeated. For example, matching - "aba" against the pattern /^(a(b)?)+$/ sets $2 to the value - "b", but matching "aabbaa" against /^(aa(bb)?)+$/ leaves $2 - unset. However, if the pattern is changed to - /^(aa(b(b))?)+$/ then $2 (and $3) get set. - - In Perl 5.004 $2 is set in both cases, and that is also true - of PCRE. If in the future Perl changes to a consistent state - that is different, PCRE may change to follow. - - 9. Another as yet unresolved discrepancy is that in Perl - 5.005_02 the pattern /^(a)?(?(1)a|b)+$/ matches the string - "a", whereas in PCRE it does not. However, in both Perl and - PCRE /^(a)?a/ matched against "a" leaves $1 unset. - - 10. PCRE provides some extensions to the Perl regular - expression facilities: - - (a) Although lookbehind assertions must match fixed length - strings, each alternative branch of a lookbehind assertion - can match a different length of string. Perl 5.005 requires - them all to have the same length. - - (b) If PCRE_DOLLAR_ENDONLY is set and PCRE_MULTILINE is not - set, the $ meta- character matches only at the very end of - the string. - - (c) If PCRE_EXTRA is set, a backslash followed by a letter - with no special meaning is faulted. - - (d) If PCRE_UNGREEDY is set, the greediness of the repeti- - tion quantifiers is inverted, that is, by default they are - not greedy, but if followed by a question mark they are. - - (e) PCRE_ANCHORED can be used to force a pattern to be tried - only at the start of the subject. - - (f) The PCRE_NOTBOL, PCRE_NOTEOL, and PCRE_NOTEMPTY options - for pcre_exec() have no Perl equivalents. - - - -REGULAR EXPRESSION DETAILS - The syntax and semantics of the regular expressions sup- - ported by PCRE are described below. Regular expressions are - also described in the Perl documentation and in a number of - other books, some of which have copious examples. Jeffrey - Friedl's "Mastering Regular Expressions", published by - O'Reilly (ISBN 1-56592-257-3), covers them in great detail. - The description here is intended as reference documentation. - - 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 charac- - ters 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. The power of regular expressions comes from the - ability to include alternatives and repetitions in the pat- - tern. These are encoded in the pattern by the use of meta- - characters, which do not stand for themselves but instead - are interpreted in some special way. - - There are two different sets of meta-characters: those that - are recognized anywhere in the pattern except within square - brackets, and those that are recognized in square brackets. - Outside square brackets, the meta-characters are as follows: - - \ general escape character with several uses - ^ assert start of subject (or line, in multiline - mode) - $ assert end of subject (or line, in multiline mode) - . match any character except newline (by default) - [ start character class definition - | start of alternative branch - ( start subpattern - ) end subpattern - ? extends the meaning of ( - also 0 or 1 quantifier - also quantifier minimizer - * 0 or more quantifier - + 1 or more quantifier - { start min/max quantifier - - Part of a pattern that is in square brackets is called a - "character class". In a character class the only meta- - characters are: - - \ general escape character - ^ negate the class, but only if the first character - - indicates character range - ] terminates the character class - - The following sections describe the use of each of the - meta-characters. - - - -BACKSLASH - The backslash character has several uses. Firstly, if it is - followed by a non-alphameric 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 applies whether or not the follow- - ing character would otherwise be interpreted as a meta- - character, so it is always safe to precede a non-alphameric - with "\" to specify that it stands for itself. In particu- - lar, if you want to match a backslash, you write "\\". - - If a pattern is compiled with the PCRE_EXTENDED option, whi- - tespace in the pattern (other than in a character class) and - characters between a "#" outside a character class and the - next newline character are ignored. An escaping backslash - can be used to include a whitespace or "#" character as part - of the pattern. - - A second use of backslash provides a way of encoding non- - printing characters in patterns in a visible manner. There - is no restriction on the appearance of non-printing charac- - ters, apart from the binary zero that terminates a pattern, - but when a pattern is being prepared by text editing, it is - usually easier to use one of the following escape sequences - than the binary character it represents: - - \a alarm, that is, the BEL character (hex 07) - \cx "control-x", where x is any character - \e escape (hex 1B) - \f formfeed (hex 0C) - \n newline (hex 0A) - \r carriage return (hex 0D) - \t tab (hex 09) - \xhh character with hex code hh - \ddd character with octal code ddd, or backreference - - 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", up to two hexadecimal digits are read (letters - can be in upper or lower case). - - After "\0" up to two further octal digits are read. In both - cases, 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. Make sure you - supply two digits after the initial zero if the character - that follows is itself an octal digit. - - The handling of a backslash followed by a digit other than 0 - is complicated. Outside a character class, PCRE reads it - and any following digits as a decimal number. If the number - is less than 10, or if there have been at least that many - previous capturing left parentheses in the expression, the - entire sequence is taken as a back reference. A description - of how this works is given later, following the discussion - of parenthesized subpatterns. - - Inside a character class, or if the decimal number is - greater than 9 and there have not been that many capturing - subpatterns, PCRE re-reads up to three octal digits follow- - ing the backslash, and generates a single byte from the - least significant 8 bits of the value. Any subsequent digits - stand for themselves. For example: - - \040 is another way of writing a space - \40 is the same, provided there are fewer than 40 - previous capturing subpatterns - \7 is always a back reference - \11 might be a back reference, or another way of - writing a tab - \011 is always a tab - \0113 is a tab followed by the character "3" - \113 is the character with octal code 113 (since there - can be no more than 99 back references) - \377 is a byte consisting entirely of 1 bits - \81 is either a back reference, or a binary zero - followed by the two characters "8" and "1" - - Note that octal values of 100 or greater must not be intro- - duced by a leading zero, because no more than three octal - digits are ever read. - - All the sequences that define a single byte 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). Outside a character - class it has a different meaning (see below). - - The third use of backslash is for specifying generic charac- - ter types: - - \d any decimal digit - \D any character that is not a decimal digit - any whitespace character - \S any character that is not a whitespace character - \w any "word" character - \W any "non-word" character - - Each pair of escape sequences partitions the complete set of - characters into two disjoint sets. Any given character - matches one, and only one, of each pair. - - A "word" character is any letter or digit or the underscore - character, that is, any character which can be part of a - Perl "word". The definition of letters and digits is con- - trolled by PCRE's character tables, and may vary if locale- - specific matching is taking place (see "Locale support" - above). For example, in the "fr" (French) locale, some char- - acter codes greater than 128 are used for accented letters, - and these are matched by \w. - - These character type sequences can appear both inside and - outside character classes. They each match one character of - the appropriate type. If the current matching point is at - the end of the subject string, all of them fail, since there - is no character to match. - - The fourth use of backslash is for certain simple asser- - tions. An assertion specifies a condition that has to be met - at a particular point in a match, without consuming any - characters from the subject string. The use of subpatterns - for more complicated assertions is described below. The - backslashed assertions are - - \b word boundary - \B not a word boundary - \A start of subject (independent of multiline mode) - \Z end of subject or newline at end (independent of - multiline mode) - \z end of subject (independent of multiline mode) - - These assertions may not appear in character classes (but - note that "\b" has a different meaning, namely the backspace - character, inside a character class). - - A word boundary is a position in the subject string where - the current character and the previous character do not both - match \w or \W (i.e. one matches \w and the other matches - \W), or the start or end of the string if the first or last - character matches \w, respectively. - - The \A, \Z, and \z assertions differ from the traditional - circumflex and dollar (described below) in that they only - ever match at the very start and end of the subject string, - whatever options are set. They are not affected by the - PCRE_NOTBOL or PCRE_NOTEOL options. If the startoffset argu- - ment of pcre_exec() is non-zero, \A can never match. The - difference between \Z and \z is that \Z matches before a - newline that is the last character of the string as well as - at the end of the string, whereas \z matches only at the - end. - - - -CIRCUMFLEX AND DOLLAR - Outside a character class, in the default matching mode, the - circumflex character is an assertion which is true only if - the current matching point is at the start of the subject - string. If the startoffset argument of pcre_exec() is non- - zero, circumflex can never match. Inside a character class, - circumflex has an entirely different meaning (see below). - - Circumflex need not be the first character of the pattern if - a number of alternatives are involved, but it should be the - first thing in each alternative in which it appears if the - pattern is ever to match that branch. If all possible alter- - natives start with a circumflex, that is, if the pattern is - constrained to match only at the start of the subject, it is - said to be an "anchored" pattern. (There are also other con- - structs that can cause a pattern to be anchored.) - - A dollar character is an assertion which is true only if the - current matching point is at the end of the subject string, - or immediately before a newline character that is the last - character in the string (by default). Dollar need not be the - last character of the pattern if a number of alternatives - are involved, but it should be the last item in any branch - in which it appears. Dollar has no special meaning in a - character class. - - The meaning of dollar can be changed so that it matches only - at the very end of the string, by setting the - PCRE_DOLLAR_ENDONLY option at compile or matching time. This - does not affect the \Z assertion. - - The meanings of the circumflex and dollar characters are - changed if the PCRE_MULTILINE option is set. When this is - the case, they match immediately after and immediately - before an internal "\n" character, respectively, in addition - to matching at the start and end of the subject string. For - example, the pattern /^abc$/ matches the subject string - "def\nabc" in multiline mode, but not otherwise. Conse- - quently, patterns that are anchored in single line mode - because all branches start with "^" are not anchored in mul- - tiline mode, and a match for circumflex is possible when the - startoffset argument of pcre_exec() is non-zero. The - PCRE_DOLLAR_ENDONLY option is ignored if PCRE_MULTILINE is - set. - - Note that the sequences \A, \Z, and \z can be used to match - the start and end of the subject in both modes, and if all - branches of a pattern start with \A is it always anchored, - whether PCRE_MULTILINE is set or not. - - - -FULL STOP (PERIOD, DOT) - Outside a character class, a dot in the pattern matches any - one character in the subject, including a non-printing char- - acter, but not (by default) newline. If the PCRE_DOTALL - option is set, then dots match newlines as well. The han- - dling of dot is entirely independent of the handling of cir- - cumflex and dollar, the only relationship being that they - both involve newline characters. Dot has no special meaning - in a character class. - - - -SQUARE BRACKETS - An opening square bracket introduces a character class, ter- - minated by a closing square bracket. A closing square - bracket on its own is not special. If a closing square - bracket is required as a member of the class, it should be - the first data character in the class (after an initial cir- - cumflex, if present) or escaped with a backslash. - - A character class matches a single character in the subject; - the character must be in the set of characters defined by - the class, unless the first character in the class is a cir- - cumflex, in which case the subject character must not be in - the set defined by the class. If a circumflex is actually - required as a member of the class, ensure it is not the - first character, or escape it with a backslash. - - For example, the character class [aeiou] matches any lower - case vowel, while [^aeiou] matches any character that is not - a lower case vowel. Note that a circumflex is just a con- - venient notation for specifying the characters which are in - the class by enumerating those that are not. It is not an - assertion: it still consumes a character from the subject - string, and fails if the current pointer is at the end of - the string. - - When caseless matching is set, any letters in a class - represent both their upper case and lower case versions, so - for example, a caseless [aeiou] matches "A" as well as "a", - and a caseless [^aeiou] does not match "A", whereas a case- - ful version would. - - The newline character is never treated in any special way in - character classes, whatever the setting of the PCRE_DOTALL - or PCRE_MULTILINE options is. A class such as [^a] will - always match a newline. - - The minus (hyphen) character can be used to specify a range - of characters in a character class. For example, [d-m] - matches any letter between d and m, inclusive. If a minus - character is required in a class, it must be escaped with a - backslash or appear in a position where it cannot be inter- - preted as indicating a range, typically as the first or last - character in the class. - - It is not possible to have the literal character "]" as the - end character of a range. A pattern such as [W-]46] is - interpreted as a class of two characters ("W" and "-") fol- - lowed by a literal string "46]", so it would match "W46]" or - "-46]". However, if the "]" is escaped with a backslash it - is interpreted as the end of range, so [W-\]46] is inter- - preted as a single class containing a range followed by two - separate characters. The octal or hexadecimal representation - of "]" can also be used to end a range. - - Ranges operate in ASCII collating sequence. They can also be - used for characters specified numerically, for example - [\000-\037]. If a range that includes letters is used when - caseless matching is set, it matches the letters in either - case. For example, [W-c] is equivalent to [][\^_`wxyzabc], - matched caselessly, and if character tables for the "fr" - locale are in use, [\xc8-\xcb] matches accented E characters - in both cases. - - The character types \d, \D, \s, \S, \w, and \W may also - appear in a character class, and add the characters that - they match to the class. For example, [\dABCDEF] matches any - hexadecimal digit. A circumflex can conveniently be used - with the upper case character types to specify a more res- - tricted set of characters than the matching lower case type. - For example, the class [^\W_] matches any letter or digit, - but not underscore. - - All non-alphameric characters other than \, -, ^ (at the - start) and the terminating ] are non-special in character - classes, but it does no harm if they are escaped. - - - -VERTICAL BAR - Vertical bar characters are used to separate alternative - patterns. For example, the pattern - - gilbert|sullivan - - matches either "gilbert" or "sullivan". Any number of alter- - natives may appear, and an empty alternative is permitted - (matching the empty string). The matching process tries - each alternative in turn, from left to right, and the first - one that succeeds is used. If the alternatives are within a - subpattern (defined below), "succeeds" means matching the - rest of the main pattern as well as the alternative in the - subpattern. - - - -INTERNAL OPTION SETTING - The settings of PCRE_CASELESS, PCRE_MULTILINE, PCRE_DOTALL, - and PCRE_EXTENDED can be changed from within the pattern by - a sequence of Perl option letters enclosed between "(?" and - ")". The option letters are - - i for PCRE_CASELESS - m for PCRE_MULTILINE - s for PCRE_DOTALL - x for PCRE_EXTENDED - - For example, (?im) sets caseless, multiline matching. It is - also possible to unset these options by preceding the letter - with a hyphen, and a combined setting and unsetting such as - (?im-sx), which sets PCRE_CASELESS and PCRE_MULTILINE while - unsetting PCRE_DOTALL and PCRE_EXTENDED, is also permitted. - If a letter appears both before and after the hyphen, the - option is unset. - - The scope of these option changes depends on where in the - pattern the setting occurs. For settings that are outside - any subpattern (defined below), the effect is the same as if - the options were set or unset at the start of matching. The - following patterns all behave in exactly the same way: - - (?i)abc - a(?i)bc - ab(?i)c - abc(?i) - - which in turn is the same as compiling the pattern abc with - PCRE_CASELESS set. In other words, such "top level" set- - tings apply to the whole pattern (unless there are other - changes inside subpatterns). If there is more than one set- - ting of the same option at top level, the rightmost setting - is used. - - If an option change occurs inside a subpattern, the effect - is different. This is a change of behaviour in Perl 5.005. - An option change inside a subpattern affects only that part - of the subpattern that follows it, so - - (a(?i)b)c - - matches abc and aBc and no other strings (assuming - PCRE_CASELESS is not used). By this means, options can be - made to have different settings in different parts of the - pattern. Any changes made in one alternative do carry on - into subsequent branches within the same subpattern. For - example, - - (a(?i)b|c) - - matches "ab", "aB", "c", and "C", even though when matching - "C" the first branch is abandoned before the option setting. - This is because the effects of option settings happen at - compile time. There would be some very weird behaviour oth- - erwise. - - The PCRE-specific options PCRE_UNGREEDY and PCRE_EXTRA can - be changed in the same way as the Perl-compatible options by - using the characters U and X respectively. The (?X) flag - setting is special in that it must always occur earlier in - the pattern than any of the additional features it turns on, - even when it is at top level. It is best put at the start. - - - -SUBPATTERNS - Subpatterns are delimited by parentheses (round brackets), - which can be nested. Marking part of a pattern as a subpat- - tern does two things: - - 1. It localizes a set of alternatives. For example, the pat- - tern - - cat(aract|erpillar|) - - matches one of the words "cat", "cataract", or "caterpil- - lar". Without the parentheses, it would match "cataract", - "erpillar" or the empty string. - - 2. It sets up the subpattern as a capturing subpattern (as - defined above). When the whole pattern matches, that por- - tion of the subject string that matched the subpattern is - passed back to the caller via the ovector argument of - pcre_exec(). Opening parentheses are counted from left to - right (starting from 1) to obtain the numbers of the captur- - ing subpatterns. - - For example, if the string "the red king" is matched against - the pattern - - the ((red|white) (king|queen)) - - the captured substrings are "red king", "red", and "king", - and are numbered 1, 2, and 3. - - The fact that plain parentheses fulfil two functions is not - always helpful. There are often times when a grouping sub- - pattern is required without a capturing requirement. If an - opening parenthesis is followed by "?:", the subpattern does - not do any capturing, and is not counted when computing the - number of any subsequent capturing subpatterns. For example, - if the string "the white queen" is matched against the pat- - tern - - the ((?:red|white) (king|queen)) - - the captured substrings are "white queen" and "queen", and - are numbered 1 and 2. The maximum number of captured sub- - strings is 99, and the maximum number of all subpatterns, - both capturing and non-capturing, is 200. - - As a convenient shorthand, if any option settings are - required at the start of a non-capturing subpattern, the - option letters may appear between the "?" and the ":". Thus - the two patterns - - (?i:saturday|sunday) - (?:(?i)saturday|sunday) - - match exactly the same set of strings. Because alternative - branches are tried from left to right, and options are not - reset until the end of the subpattern is reached, an option - setting in one branch does affect subsequent branches, so - the above patterns match "SUNDAY" as well as "Saturday". - - - -REPETITION - Repetition is specified by quantifiers, which can follow any - of the following items: - - a single character, possibly escaped - the . metacharacter - a character class - a back reference (see next section) - a parenthesized subpattern (unless it is an assertion - - see below) - - The general repetition quantifier specifies a minimum and - maximum number of permitted matches, by giving the two - numbers in curly brackets (braces), separated by a comma. - The numbers must be less than 65536, and the first must be - less than or equal to the second. For example: - - z{2,4} - - matches "zz", "zzz", or "zzzz". A closing brace on its own - is not a special character. If the second number is omitted, - but the comma is present, there is no upper limit; if the - second number and the comma are both omitted, the quantifier - specifies an exact number of required matches. Thus - - [aeiou]{3,} - - matches at least 3 successive vowels, but may match many - more, while - - \d{8} - - matches exactly 8 digits. An opening curly bracket that - appears in a position where a quantifier is not allowed, or - one that does not match the syntax of a quantifier, is taken - as a literal character. For example, {,6} is not a quantif- - ier, but a literal string of four characters. - - The quantifier {0} is permitted, causing the expression to - behave as if the previous item and the quantifier were not - present. - - For convenience (and historical compatibility) the three - most common quantifiers have single-character abbreviations: - - * is equivalent to {0,} - + is equivalent to {1,} - ? is equivalent to {0,1} - - It is possible to construct infinite loops by following a - subpattern that can match no characters with a quantifier - that has no upper limit, for example: - - (a?)* - - Earlier versions of Perl and PCRE used to give an error at - compile time for such patterns. However, because there are - cases where this can be useful, such patterns are now - accepted, but if any repetition of the subpattern does in - fact match no characters, the loop is forcibly broken. - - By default, the quantifiers are "greedy", that is, they - match as much as possible (up to the maximum number of per- - mitted times), without causing the rest of the pattern to - fail. The classic example of where this gives problems is in - trying to match comments in C programs. These appear between - the sequences /* and */ and within the sequence, individual - * and / characters may appear. An attempt to match C com- - ments by applying the pattern - - /\*.*\*/ - - to the string - - /* first command */ not comment /* second comment */ - - fails, because it matches the entire string due to the - greediness of the .* item. - - However, if a quantifier is followed by a question mark, - then it ceases to be greedy, and instead matches the minimum - number of times possible, so the pattern - - /\*.*?\*/ - - does the right thing with the C comments. The meaning of the - various quantifiers is not otherwise changed, just the pre- - ferred number of matches. Do not confuse this use of ques- - tion mark with its use as a quantifier in its own right. - Because it has two uses, it can sometimes appear doubled, as - in - - \d??\d - - which matches one digit by preference, but can match two if - that is the only way the rest of the pattern matches. - - If the PCRE_UNGREEDY option is set (an option which is not - available in Perl) then the quantifiers are not greedy by - default, but individual ones can be made greedy by following - them with a question mark. In other words, it inverts the - default behaviour. - - When a parenthesized subpattern is quantified with a minimum - repeat count that is greater than 1 or with a limited max- - imum, more store is required for the compiled pattern, in - proportion to the size of the minimum or maximum. - - If a pattern starts with .* or .{0,} and the PCRE_DOTALL - option (equivalent to Perl's /s) is set, thus allowing the . - to match newlines, then the pattern is implicitly anchored, - because whatever follows will be tried against every charac- - ter position in the subject string, so there is no point in - retrying the overall match at any position after the first. - PCRE treats such a pattern as though it were preceded by \A. - In cases where it is known that the subject string contains - no newlines, it is worth setting PCRE_DOTALL when the pat- - tern begins with .* in order to obtain this optimization, or - alternatively using ^ to indicate anchoring explicitly. - - When a capturing subpattern is repeated, the value captured - is the substring that matched the final iteration. For - example, after - - (tweedle[dume]{3}\s*)+ - - has matched "tweedledum tweedledee" the value of the cap- - tured substring is "tweedledee". However, if there are - nested capturing subpatterns, the corresponding captured - values may have been set in previous iterations. For exam- - ple, after - - /(a|(b))+/ - - matches "aba" the value of the second captured substring is - "b". - - - -BACK REFERENCES - Outside a character class, a backslash followed by a digit - greater than 0 (and possibly further digits) is a back - reference to a capturing subpattern earlier (i.e. to its - left) in the pattern, provided there have been that many - previous capturing left parentheses. - - However, if the decimal number following the backslash is - less than 10, it is always taken as a back reference, and - causes an error only if there are not that many capturing - left parentheses in the entire pattern. In other words, the - parentheses that are referenced need not be to the left of - the reference for numbers less than 10. See the section - entitled "Backslash" above for further details of the han- - dling of digits following a backslash. - - A back reference matches whatever actually matched the cap- - turing subpattern in the current subject string, rather than - anything matching the subpattern itself. So the pattern - - (sens|respons)e and \1ibility - - matches "sense and sensibility" and "response and responsi- - bility", but not "sense and responsibility". If caseful - matching is in force at the time of the back reference, then - the case of letters is relevant. For example, - - ((?i)rah)\s+\1 - - matches "rah rah" and "RAH RAH", but not "RAH rah", even - though the original capturing subpattern is matched case- - lessly. - - There may be more than one back reference to the same sub- - pattern. If a subpattern has not actually been used in a - particular match, then any back references to it always - fail. For example, the pattern - - (a|(bc))\2 - - always fails if it starts to match "a" rather than "bc". - Because there may be up to 99 back references, all digits - following the backslash are taken as part of a potential - back reference number. If the pattern continues with a digit - character, then some delimiter must be used to terminate the - back reference. If the PCRE_EXTENDED option is set, this can - be whitespace. Otherwise an empty comment can be used. - - A back reference that occurs inside the parentheses to which - it refers fails when the subpattern is first used, so, for - example, (a\1) never matches. However, such references can - be useful inside repeated subpatterns. For example, the pat- - tern - - (a|b\1)+ - - matches any number of "a"s and also "aba", "ababaa" etc. At - each iteration of the subpattern, the back reference matches - the character string corresponding to the previous itera- - tion. In order for this to work, the pattern must be such - that the first iteration does not need to match the back - reference. This can be done using alternation, as in the - example above, or by a quantifier with a minimum of zero. - - - -ASSERTIONS - An assertion is a test on the characters following or - preceding the current matching point that does not actually - consume any characters. The simple assertions coded as \b, - \B, \A, \Z, \z, ^ and $ are described above. More compli- - cated assertions are coded as subpatterns. There are two - kinds: those that look ahead of the current position in the - subject string, and those that look behind it. - - An assertion subpattern is matched in the normal way, except - that it does not cause the current matching position to be - changed. Lookahead assertions start with (?= for positive - assertions and (?! for negative assertions. For example, - - \w+(?=;) - - matches a word followed by a semicolon, but does not include - the semicolon in the match, and - - foo(?!bar) - - matches any occurrence of "foo" that is not followed by - "bar". Note that the apparently similar pattern - - (?!foo)bar - - does not find an occurrence of "bar" that is preceded by - something other than "foo"; it finds any occurrence of "bar" - whatsoever, because the assertion (?!foo) is always true - when the next three characters are "bar". A lookbehind - assertion is needed to achieve this effect. - - Lookbehind assertions start with (?<= for positive asser- - tions and (? as in this example: - - (?>\d+)bar - - This kind of parenthesis "locks up" the part of the pattern - it contains once it has matched, and a failure further into - the pattern is prevented from backtracking into it. Back- - tracking past it to previous items, however, works as nor- - mal. - - An alternative description is that a subpattern of this type - matches the string of characters that an identical stan- - dalone pattern would match, if anchored at the current point - in the subject string. - - Once-only subpatterns are not capturing subpatterns. Simple - cases such as the above example can be thought of as a max- - imizing repeat that must swallow everything it can. So, - while both \d+ and \d+? are prepared to adjust the number of - digits they match in order to make the rest of the pattern - match, (?>\d+) can only match an entire sequence of digits. - - This construction can of course contain arbitrarily compli- - cated subpatterns, and it can be nested. - - Once-only subpatterns can be used in conjunction with look- - behind assertions to specify efficient matching at the end - of the subject string. Consider a simple pattern such as - - abcd$ - - when applied to a long string which does not match it. - Because matching proceeds from left to right, PCRE will look - for each "a" in the subject and then see if what follows - matches the rest of the pattern. If the pattern is specified - as - - ^.*abcd$ - - then the initial .* matches the entire string at first, but - when this fails, it backtracks to match all but the last - character, then all but the last two characters, and so on. - Once again the search for "a" covers the entire string, from - right to left, so we are no better off. However, if the pat- - tern is written as - - ^(?>.*)(?<=abcd) - - then there can be no backtracking for the .* item; it can - match only the entire string. The subsequent lookbehind - assertion does a single test on the last four characters. If - it fails, the match fails immediately. For long strings, - this approach makes a significant difference to the process- - ing time. - - - -CONDITIONAL SUBPATTERNS - It is possible to cause the matching process to obey a sub- - pattern conditionally or to choose between two alternative - subpatterns, depending on the result of an assertion, or - whether a previous capturing subpattern matched or not. The - two possible forms of conditional subpattern are - - (?(condition)yes-pattern) - (?(condition)yes-pattern|no-pattern) - - If the condition is satisfied, the yes-pattern is used; oth- - erwise the no-pattern (if present) is used. If there are - more than two alternatives in the subpattern, a compile-time - error occurs. - - There are two kinds of condition. If the text between the - parentheses consists of a sequence of digits, then the con- - dition is satisfied if the capturing subpattern of that - number has previously matched. Consider the following pat- - tern, which contains non-significant white space to make it - more readable (assume the PCRE_EXTENDED option) and to - divide it into three parts for ease of discussion: - - ( \( )? [^()]+ (?(1) \) ) - - The first part matches an optional opening parenthesis, and - if that character is present, sets it as the first captured - substring. The second part matches one or more characters - that are not parentheses. The third part is a conditional - subpattern that tests whether the first set of parentheses - matched or not. If they did, that is, if subject started - with an opening parenthesis, the condition is true, and so - the yes-pattern is executed and a closing parenthesis is - required. Otherwise, since no-pattern is not present, the - subpattern matches nothing. In other words, this pattern - matches a sequence of non-parentheses, optionally enclosed - in parentheses. - - If the condition is not a sequence of digits, it must be an - assertion. This may be a positive or negative lookahead or - lookbehind assertion. Consider this pattern, again contain- - ing non-significant white space, and with the two alterna- - tives on the second line: - - (?(?=[^a-z]*[a-z]) - \d{2}[a-z]{3}-\d{2} | \d{2}-\d{2}-\d{2} ) - - The condition is a positive lookahead assertion that matches - an optional sequence of non-letters followed by a letter. In - other words, it tests for the presence of at least one - letter in the subject. If a letter is found, the subject is - matched against the first alternative; otherwise it is - matched against the second. This pattern matches strings in - one of the two forms dd-aaa-dd or dd-dd-dd, where aaa are - letters and dd are digits. - - - -COMMENTS - The sequence (?# marks the start of a comment which contin- - ues up to the next closing parenthesis. Nested parentheses - are not permitted. The characters that make up a comment - play no part in the pattern matching at all. - - If the PCRE_EXTENDED option is set, an unescaped # character - outside a character class introduces a comment that contin- - ues up to the next newline character in the pattern. - - - -PERFORMANCE - Certain items that may appear in patterns are more efficient - than others. It is more efficient to use a character class - like [aeiou] than a set of alternatives such as (a|e|i|o|u). - In general, the simplest construction that provides the - required behaviour is usually the most efficient. Jeffrey - Friedl's book contains a lot of discussion about optimizing - regular expressions for efficient performance. - - When a pattern begins with .* and the PCRE_DOTALL option is - set, the pattern is implicitly anchored by PCRE, since it - can match only at the start of a subject string. However, if - PCRE_DOTALL is not set, PCRE cannot make this optimization, - because the . metacharacter does not then match a newline, - and if the subject string contains newlines, the pattern may - match from the character immediately following one of them - instead of from the very start. For example, the pattern - - (.*) second - - matches the subject "first\nand second" (where \n stands for - a newline character) with the first captured substring being - "and". In order to do this, PCRE has to retry the match - starting after every newline in the subject. - - If you are using such a pattern with subject strings that do - not contain newlines, the best performance is obtained by - setting PCRE_DOTALL, or starting the pattern with ^.* to - indicate explicit anchoring. That saves PCRE from having to - scan along the subject looking for a newline to restart at. - - Beware of patterns that contain nested indefinite repeats. - These can take a long time to run when applied to a string - that does not match. Consider the pattern fragment - - (a+)* - - This can match "aaaa" in 33 different ways, and this number - increases very rapidly as the string gets longer. (The * - repeat can match 0, 1, 2, 3, or 4 times, and for each of - those cases other than 0, the + repeats can match different - numbers of times.) When the remainder of the pattern is such - that the entire match is going to fail, PCRE has in princi- - ple to try every possible variation, and this can take an - extremely long time. - - An optimization catches some of the more simple cases such - as - - (a+)*b - - where a literal character follows. Before embarking on the - standard matching procedure, PCRE checks that there is a "b" - later in the subject string, and if there is not, it fails - the match immediately. However, when there is no following - literal this optimization cannot be used. You can see the - difference by comparing the behaviour of - - (a+)*\d - - with the pattern above. The former gives a failure almost - instantly when applied to a whole line of "a" characters, - whereas the latter takes an appreciable time with strings - longer than about 20 characters. - - - -AUTHOR - Philip Hazel - University Computing Service, - New Museums Site, - Cambridge CB2 3QG, England. - Phone: +44 1223 334714 - - Last updated: 29 July 1999 - Copyright (c) 1997-1999 University of Cambridge. diff --git a/ext/pcre/pcrelib/pcre.c b/ext/pcre/pcrelib/pcre.c deleted file mode 100644 index 6735b823d4..0000000000 --- a/ext/pcre/pcrelib/pcre.c +++ /dev/null @@ -1,4477 +0,0 @@ -/************************************************* -* Perl-Compatible Regular Expressions * -*************************************************/ - -/* -This is a library of functions to support regular expressions whose syntax -and semantics are as close as possible to those of the Perl 5 language. See -the file Tech.Notes for some information on the internals. - -Written by: Philip Hazel - - Copyright (c) 1997-1999 University of Cambridge - ------------------------------------------------------------------------------ -Permission is granted to anyone to use this software for any purpose on any -computer system, and to redistribute it freely, subject to the following -restrictions: - -1. This software is distributed in the hope that it will be useful, - but WITHOUT ANY WARRANTY; without even the implied warranty of - MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. - -2. The origin of this software must not be misrepresented, either by - explicit claim or by omission. - -3. Altered versions must be plainly marked as such, and must not be - misrepresented as being the original software. - -4. If PCRE is embedded in any software that is released under the GNU - General Purpose Licence (GPL), then the terms of that licence shall - supersede any condition above with which it is incompatible. ------------------------------------------------------------------------------ -*/ - - -/* Define DEBUG to get debugging output on stdout. */ - -/* #define DEBUG */ - -/* Use a macro for debugging printing, 'cause that eliminates the use of #ifdef -inline, and there are *still* stupid compilers about that don't like indented -pre-processor statements. I suppose it's only been 10 years... */ - -#ifdef DEBUG -#define DPRINTF(p) printf p -#else -#define DPRINTF(p) /*nothing*/ -#endif - -/* Include the internals header, which itself includes Standard C headers plus -the external pcre header. */ - -#include "internal.h" - - -/* Allow compilation as C++ source code, should anybody want to do that. */ - -#ifdef __cplusplus -#define class pcre_class -#endif - - -/* Number of items on the nested bracket stacks at compile time. This should -not be set greater than 200. */ - -#define BRASTACK_SIZE 200 - - -/* Min and max values for the common repeats; for the maxima, 0 => infinity */ - -static const char rep_min[] = { 0, 0, 1, 1, 0, 0 }; -static const char rep_max[] = { 0, 0, 0, 0, 1, 1 }; - -/* Text forms of OP_ values and things, for debugging (not all used) */ - -#ifdef DEBUG -static const char *OP_names[] = { - "End", "\\A", "\\B", "\\b", "\\D", "\\d", - "\\S", "\\s", "\\W", "\\w", "\\Z", "\\z", - "Opt", "^", "$", "Any", "chars", "not", - "*", "*?", "+", "+?", "?", "??", "{", "{", "{", - "*", "*?", "+", "+?", "?", "??", "{", "{", "{", - "*", "*?", "+", "+?", "?", "??", "{", "{", "{", - "*", "*?", "+", "+?", "?", "??", "{", "{", - "class", "Ref", - "Alt", "Ket", "KetRmax", "KetRmin", "Assert", "Assert not", - "AssertB", "AssertB not", "Reverse", "Once", "Cond", "Cref", - "Brazero", "Braminzero", "Bra" -}; -#endif - -/* Table for handling escaped characters in the range '0'-'z'. Positive returns -are simple data values; negative values are for special things like \d and so -on. Zero means further processing is needed (for things like \x), or the escape -is invalid. */ - -static const short int escapes[] = { - 0, 0, 0, 0, 0, 0, 0, 0, /* 0 - 7 */ - 0, 0, ':', ';', '<', '=', '>', '?', /* 8 - ? */ - '@', -ESC_A, -ESC_B, 0, -ESC_D, 0, 0, 0, /* @ - G */ - 0, 0, 0, 0, 0, 0, 0, 0, /* H - O */ - 0, 0, 0, -ESC_S, 0, 0, 0, -ESC_W, /* P - W */ - 0, 0, -ESC_Z, '[', '\\', ']', '^', '_', /* X - _ */ - '`', 7, -ESC_b, 0, -ESC_d, 27, '\f', 0, /* ` - g */ - 0, 0, 0, 0, 0, 0, '\n', 0, /* h - o */ - 0, 0, '\r', -ESC_s, '\t', 0, 0, -ESC_w, /* p - w */ - 0, 0, -ESC_z /* x - z */ -}; - -/* Definition to allow mutual recursion */ - -static BOOL - compile_regex(int, int, int *, uschar **, const uschar **, const char **, - BOOL, int, int *, int *, compile_data *); - - - -/************************************************* -* Global variables * -*************************************************/ - -/* PCRE is thread-clean and doesn't use any global variables in the normal -sense. However, it calls memory allocation and free functions via the two -indirections below, which are can be changed by the caller, but are shared -between all threads. */ - -void *(*pcre_malloc)(size_t) = malloc; -void (*pcre_free)(void *) = free; - - - - -/************************************************* -* Default character tables * -*************************************************/ - -/* A default set of character tables is included in the PCRE binary. Its source -is built by the maketables auxiliary program, which uses the default C ctypes -functions, and put in the file chartables.c. These tables are used by PCRE -whenever the caller of pcre_compile() does not provide an alternate set of -tables. */ - -#include "chartables.c" - - - -/************************************************* -* Return version string * -*************************************************/ - -#define STRING(a) # a -#define XSTRING(s) STRING(s) - -const char * -pcre_version(void) -{ -return XSTRING(PCRE_MAJOR) "." XSTRING(PCRE_MINOR) " " XSTRING(PCRE_DATE); -} - - - - -/************************************************* -* Return info about a compiled pattern * -*************************************************/ - -/* This function picks potentially useful data out of the private -structure. The public options are passed back in an int - though the -re->options field has been expanded to a long int, all the public options -at the low end of it, and so even on 16-bit systems this will still be OK. -Therefore, I haven't changed the API for pcre_info(). - -Arguments: - external_re points to compiled code - optptr where to pass back the options - first_char where to pass back the first character, - or -1 if multiline and all branches start ^, - or -2 otherwise - -Returns: number of identifying extraction brackets - or negative values on error -*/ - -int -pcre_info(const pcre *external_re, int *optptr, int *first_char) -{ -const real_pcre *re = (const real_pcre *)external_re; -if (re == NULL) return PCRE_ERROR_NULL; -if (re->magic_number != MAGIC_NUMBER) return PCRE_ERROR_BADMAGIC; -if (optptr != NULL) *optptr = (int)(re->options & PUBLIC_OPTIONS); -if (first_char != NULL) - *first_char = ((re->options & PCRE_FIRSTSET) != 0)? re->first_char : - ((re->options & PCRE_STARTLINE) != 0)? -1 : -2; -return re->top_bracket; -} - - - - -#ifdef DEBUG -/************************************************* -* Debugging function to print chars * -*************************************************/ - -/* Print a sequence of chars in printable format, stopping at the end of the -subject if the requested. - -Arguments: - p points to characters - length number to print - is_subject TRUE if printing from within md->start_subject - md pointer to matching data block, if is_subject is TRUE - -Returns: nothing -*/ - -static void -pchars(const uschar *p, int length, BOOL is_subject, match_data *md) -{ -int c; -if (is_subject && length > md->end_subject - p) length = md->end_subject - p; -while (length-- > 0) - if (isprint(c = *(p++))) printf("%c", c); else printf("\\x%02x", c); -} -#endif - - - - -/************************************************* -* Handle escapes * -*************************************************/ - -/* This function is called when a \ has been encountered. It either returns a -positive value for a simple escape such as \n, or a negative value which -encodes one of the more complicated things such as \d. On entry, ptr is -pointing at the \. On exit, it is on the final character of the escape -sequence. - -Arguments: - ptrptr points to the pattern position pointer - errorptr points to the pointer to the error message - bracount number of previous extracting brackets - options the options bits - isclass TRUE if inside a character class - cd pointer to char tables block - -Returns: zero or positive => a data character - negative => a special escape sequence - on error, errorptr is set -*/ - -static int -check_escape(const uschar **ptrptr, const char **errorptr, int bracount, - int options, BOOL isclass, compile_data *cd) -{ -const uschar *ptr = *ptrptr; -int c = *(++ptr) & 255; /* Ensure > 0 on signed-char systems */ -int i; - -if (c == 0) *errorptr = ERR1; - -/* Digits or letters may have special meaning; all others are literals. */ - -else if (c < '0' || c > 'z') {} - -/* Do an initial lookup in a table. A non-zero result is something that can be -returned immediately. Otherwise further processing may be required. */ - -else if ((i = escapes[c - '0']) != 0) c = i; - -/* Escapes that need further processing, or are illegal. */ - -else - { - const uschar *oldptr; - switch (c) - { - /* The handling of escape sequences consisting of a string of digits - starting with one that is not zero is not straightforward. By experiment, - the way Perl works seems to be as follows: - - Outside a character class, the digits are read as a decimal number. If the - number is less than 10, or if there are that many previous extracting - left brackets, then it is a back reference. Otherwise, up to three octal - digits are read to form an escaped byte. Thus \123 is likely to be octal - 123 (cf \0123, which is octal 012 followed by the literal 3). If the octal - value is greater than 377, the least significant 8 bits are taken. Inside a - character class, \ followed by a digit is always an octal number. */ - - case '1': case '2': case '3': case '4': case '5': - case '6': case '7': case '8': case '9': - - if (!isclass) - { - oldptr = ptr; - c -= '0'; - while ((cd->ctypes[ptr[1]] & ctype_digit) != 0) - c = c * 10 + *(++ptr) - '0'; - if (c < 10 || c <= bracount) - { - c = -(ESC_REF + c); - break; - } - ptr = oldptr; /* Put the pointer back and fall through */ - } - - /* Handle an octal number following \. If the first digit is 8 or 9, Perl - generates a binary zero byte and treats the digit as a following literal. - Thus we have to pull back the pointer by one. */ - - if ((c = *ptr) >= '8') - { - ptr--; - c = 0; - break; - } - - /* \0 always starts an octal number, but we may drop through to here with a - larger first octal digit */ - - case '0': - c -= '0'; - while(i++ < 2 && (cd->ctypes[ptr[1]] & ctype_digit) != 0 && - ptr[1] != '8' && ptr[1] != '9') - c = c * 8 + *(++ptr) - '0'; - break; - - /* Special escapes not starting with a digit are straightforward */ - - case 'x': - c = 0; - while (i++ < 2 && (cd->ctypes[ptr[1]] & ctype_xdigit) != 0) - { - ptr++; - c = c * 16 + cd->lcc[*ptr] - - (((cd->ctypes[*ptr] & ctype_digit) != 0)? '0' : 'W'); - } - break; - - case 'c': - c = *(++ptr); - if (c == 0) - { - *errorptr = ERR2; - return 0; - } - - /* A letter is upper-cased; then the 0x40 bit is flipped */ - - if (c >= 'a' && c <= 'z') c = cd->fcc[c]; - c ^= 0x40; - break; - - /* PCRE_EXTRA enables extensions to Perl in the matter of escapes. Any - other alphameric following \ is an error if PCRE_EXTRA was set; otherwise, - for Perl compatibility, it is a literal. This code looks a bit odd, but - there used to be some cases other than the default, and there may be again - in future, so I haven't "optimized" it. */ - - default: - if ((options & PCRE_EXTRA) != 0) switch(c) - { - default: - *errorptr = ERR3; - break; - } - break; - } - } - -*ptrptr = ptr; -return c; -} - - - -/************************************************* -* Check for counted repeat * -*************************************************/ - -/* This function is called when a '{' is encountered in a place where it might -start a quantifier. It looks ahead to see if it really is a quantifier or not. -It is only a quantifier if it is one of the forms {ddd} {ddd,} or {ddd,ddd} -where the ddds are digits. - -Arguments: - p pointer to the first char after '{' - cd pointer to char tables block - -Returns: TRUE or FALSE -*/ - -static BOOL -is_counted_repeat(const uschar *p, compile_data *cd) -{ -if ((cd->ctypes[*p++] & ctype_digit) == 0) return FALSE; -while ((cd->ctypes[*p] & ctype_digit) != 0) p++; -if (*p == '}') return TRUE; - -if (*p++ != ',') return FALSE; -if (*p == '}') return TRUE; - -if ((cd->ctypes[*p++] & ctype_digit) == 0) return FALSE; -while ((cd->ctypes[*p] & ctype_digit) != 0) p++; -return (*p == '}'); -} - - - -/************************************************* -* Read repeat counts * -*************************************************/ - -/* Read an item of the form {n,m} and return the values. This is called only -after is_counted_repeat() has confirmed that a repeat-count quantifier exists, -so the syntax is guaranteed to be correct, but we need to check the values. - -Arguments: - p pointer to first char after '{' - minp pointer to int for min - maxp pointer to int for max - returned as -1 if no max - errorptr points to pointer to error message - cd pointer to character tables clock - -Returns: pointer to '}' on success; - current ptr on error, with errorptr set -*/ - -static const uschar * -read_repeat_counts(const uschar *p, int *minp, int *maxp, - const char **errorptr, compile_data *cd) -{ -int min = 0; -int max = -1; - -while ((cd->ctypes[*p] & ctype_digit) != 0) min = min * 10 + *p++ - '0'; - -if (*p == '}') max = min; else - { - if (*(++p) != '}') - { - max = 0; - while((cd->ctypes[*p] & ctype_digit) != 0) max = max * 10 + *p++ - '0'; - if (max < min) - { - *errorptr = ERR4; - return p; - } - } - } - -/* Do paranoid checks, then fill in the required variables, and pass back the -pointer to the terminating '}'. */ - -if (min > 65535 || max > 65535) - *errorptr = ERR5; -else - { - *minp = min; - *maxp = max; - } -return p; -} - - - -/************************************************* -* Find the fixed length of a pattern * -*************************************************/ - -/* Scan a pattern and compute the fixed length of subject that will match it, -if the length is fixed. This is needed for dealing with backward assertions. - -Arguments: - code points to the start of the pattern (the bracket) - -Returns: the fixed length, or -1 if there is no fixed length -*/ - -static int -find_fixedlength(uschar *code) -{ -int length = -1; - -register int branchlength = 0; -register uschar *cc = code + 3; - -/* Scan along the opcodes for this branch. If we get to the end of the -branch, check the length against that of the other branches. */ - -for (;;) - { - int d; - register int op = *cc; - if (op >= OP_BRA) op = OP_BRA; - - switch (op) - { - case OP_BRA: - case OP_ONCE: - case OP_COND: - d = find_fixedlength(cc); - if (d < 0) return -1; - branchlength += d; - do cc += (cc[1] << 8) + cc[2]; while (*cc == OP_ALT); - cc += 3; - break; - - /* Reached end of a branch; if it's a ket it is the end of a nested - call. If it's ALT it is an alternation in a nested call. If it is - END it's the end of the outer call. All can be handled by the same code. */ - - case OP_ALT: - case OP_KET: - case OP_KETRMAX: - case OP_KETRMIN: - case OP_END: - if (length < 0) length = branchlength; - else if (length != branchlength) return -1; - if (*cc != OP_ALT) return length; - cc += 3; - branchlength = 0; - break; - - /* Skip over assertive subpatterns */ - - case OP_ASSERT: - case OP_ASSERT_NOT: - case OP_ASSERTBACK: - case OP_ASSERTBACK_NOT: - do cc += (cc[1] << 8) + cc[2]; while (*cc == OP_ALT); - cc += 3; - break; - - /* Skip over things that don't match chars */ - - case OP_REVERSE: - cc++; - /* Fall through */ - - case OP_CREF: - case OP_OPT: - cc++; - /* Fall through */ - - case OP_SOD: - case OP_EOD: - case OP_EODN: - case OP_CIRC: - case OP_DOLL: - case OP_NOT_WORD_BOUNDARY: - case OP_WORD_BOUNDARY: - cc++; - break; - - /* Handle char strings */ - - case OP_CHARS: - branchlength += *(++cc); - cc += *cc + 1; - break; - - /* Handle exact repetitions */ - - case OP_EXACT: - case OP_TYPEEXACT: - branchlength += (cc[1] << 8) + cc[2]; - cc += 4; - break; - - /* Handle single-char matchers */ - - case OP_NOT_DIGIT: - case OP_DIGIT: - case OP_NOT_WHITESPACE: - case OP_WHITESPACE: - case OP_NOT_WORDCHAR: - case OP_WORDCHAR: - case OP_ANY: - branchlength++; - cc++; - break; - - - /* Check a class for variable quantification */ - - case OP_CLASS: - cc += (*cc == OP_REF)? 2 : 33; - - switch (*cc) - { - case OP_CRSTAR: - case OP_CRMINSTAR: - case OP_CRQUERY: - case OP_CRMINQUERY: - return -1; - - case OP_CRRANGE: - case OP_CRMINRANGE: - if ((cc[1] << 8) + cc[2] != (cc[3] << 8) + cc[4]) return -1; - branchlength += (cc[1] << 8) + cc[2]; - cc += 5; - break; - - default: - branchlength++; - } - break; - - /* Anything else is variable length */ - - default: - return -1; - } - } -/* Control never gets here */ -} - - - - -/************************************************* -* Compile one branch * -*************************************************/ - -/* Scan the pattern, compiling it into the code vector. - -Arguments: - options the option bits - brackets points to number of brackets used - code points to the pointer to the current code point - ptrptr points to the current pattern pointer - errorptr points to pointer to error message - optchanged set to the value of the last OP_OPT item compiled - reqchar set to the last literal character required, else -1 - countlits set to count of mandatory literal characters - cd contains pointers to tables - -Returns: TRUE on success - FALSE, with *errorptr set on error -*/ - -static BOOL -compile_branch(int options, int *brackets, uschar **codeptr, - const uschar **ptrptr, const char **errorptr, int *optchanged, - int *reqchar, int *countlits, compile_data *cd) -{ -int repeat_type, op_type; -int repeat_min, repeat_max; -int bravalue, length; -int greedy_default, greedy_non_default; -int prevreqchar; -int condcount = 0; -int subcountlits = 0; -register int c; -register uschar *code = *codeptr; -uschar *tempcode; -const uschar *ptr = *ptrptr; -const uschar *tempptr; -uschar *previous = NULL; -uschar class[32]; - -/* Set up the default and non-default settings for greediness */ - -greedy_default = ((options & PCRE_UNGREEDY) != 0); -greedy_non_default = greedy_default ^ 1; - -/* Initialize no required char, and count of literals */ - -*reqchar = prevreqchar = -1; -*countlits = 0; - -/* Switch on next character until the end of the branch */ - -for (;; ptr++) - { - BOOL negate_class; - int class_charcount; - int class_lastchar; - int newoptions; - int condref; - int subreqchar; - - c = *ptr; - if ((options & PCRE_EXTENDED) != 0) - { - if ((cd->ctypes[c] & ctype_space) != 0) continue; - if (c == '#') - { - while ((c = *(++ptr)) != 0 && c != '\n'); - continue; - } - } - - switch(c) - { - /* The branch terminates at end of string, |, or ). */ - - case 0: - case '|': - case ')': - *codeptr = code; - *ptrptr = ptr; - return TRUE; - - /* Handle single-character metacharacters */ - - case '^': - previous = NULL; - *code++ = OP_CIRC; - break; - - case '$': - previous = NULL; - *code++ = OP_DOLL; - break; - - case '.': - previous = code; - *code++ = OP_ANY; - break; - - /* Character classes. These always build a 32-byte bitmap of the permitted - characters, except in the special case where there is only one character. - For negated classes, we build the map as usual, then invert it at the end. - */ - - case '[': - previous = code; - *code++ = OP_CLASS; - - /* If the first character is '^', set the negation flag and skip it. */ - - if ((c = *(++ptr)) == '^') - { - negate_class = TRUE; - c = *(++ptr); - } - else negate_class = FALSE; - - /* Keep a count of chars so that we can optimize the case of just a single - character. */ - - class_charcount = 0; - class_lastchar = -1; - - /* Initialize the 32-char bit map to all zeros. We have to build the - map in a temporary bit of store, in case the class contains only 1 - character, because in that case the compiled code doesn't use the - bit map. */ - - memset(class, 0, 32 * sizeof(uschar)); - - /* Process characters until ] is reached. By writing this as a "do" it - means that an initial ] is taken as a data character. */ - - do - { - if (c == 0) - { - *errorptr = ERR6; - goto FAILED; - } - - /* Backslash may introduce a single character, or it may introduce one - of the specials, which just set a flag. Escaped items are checked for - validity in the pre-compiling pass. The sequence \b is a special case. - Inside a class (and only there) it is treated as backspace. Elsewhere - it marks a word boundary. Other escapes have preset maps ready to - or into the one we are building. We assume they have more than one - character in them, so set class_count bigger than one. */ - - if (c == '\\') - { - c = check_escape(&ptr, errorptr, *brackets, options, TRUE, cd); - if (-c == ESC_b) c = '\b'; - else if (c < 0) - { - register const uschar *cbits = cd->cbits; - class_charcount = 10; - switch (-c) - { - case ESC_d: - for (c = 0; c < 32; c++) class[c] |= cbits[c+cbit_digit]; - continue; - - case ESC_D: - for (c = 0; c < 32; c++) class[c] |= ~cbits[c+cbit_digit]; - continue; - - case ESC_w: - for (c = 0; c < 32; c++) - class[c] |= (cbits[c+cbit_digit] | cbits[c+cbit_word]); - continue; - - case ESC_W: - for (c = 0; c < 32; c++) - class[c] |= ~(cbits[c+cbit_digit] | cbits[c+cbit_word]); - continue; - - case ESC_s: - for (c = 0; c < 32; c++) class[c] |= cbits[c+cbit_space]; - continue; - - case ESC_S: - for (c = 0; c < 32; c++) class[c] |= ~cbits[c+cbit_space]; - continue; - - default: - *errorptr = ERR7; - goto FAILED; - } - } - /* Fall through if single character */ - } - - /* A single character may be followed by '-' to form a range. However, - Perl does not permit ']' to be the end of the range. A '-' character - here is treated as a literal. */ - - if (ptr[1] == '-' && ptr[2] != ']') - { - int d; - ptr += 2; - d = *ptr; - - if (d == 0) - { - *errorptr = ERR6; - goto FAILED; - } - - /* The second part of a range can be a single-character escape, but - not any of the other escapes. */ - - if (d == '\\') - { - d = check_escape(&ptr, errorptr, *brackets, options, TRUE, cd); - if (d < 0) - { - if (d == -ESC_b) d = '\b'; else - { - *errorptr = ERR7; - goto FAILED; - } - } - } - - if (d < c) - { - *errorptr = ERR8; - goto FAILED; - } - - for (; c <= d; c++) - { - class[c/8] |= (1 << (c&7)); - if ((options & PCRE_CASELESS) != 0) - { - int uc = cd->fcc[c]; /* flip case */ - class[uc/8] |= (1 << (uc&7)); - } - class_charcount++; /* in case a one-char range */ - class_lastchar = c; - } - continue; /* Go get the next char in the class */ - } - - /* Handle a lone single character - we can get here for a normal - non-escape char, or after \ that introduces a single character. */ - - class [c/8] |= (1 << (c&7)); - if ((options & PCRE_CASELESS) != 0) - { - c = cd->fcc[c]; /* flip case */ - class[c/8] |= (1 << (c&7)); - } - class_charcount++; - class_lastchar = c; - } - - /* Loop until ']' reached; the check for end of string happens inside the - loop. This "while" is the end of the "do" above. */ - - while ((c = *(++ptr)) != ']'); - - /* If class_charcount is 1 and class_lastchar is not negative, we saw - precisely one character. This doesn't need the whole 32-byte bit map. - We turn it into a 1-character OP_CHAR if it's positive, or OP_NOT if - it's negative. */ - - if (class_charcount == 1 && class_lastchar >= 0) - { - if (negate_class) - { - code[-1] = OP_NOT; - } - else - { - code[-1] = OP_CHARS; - *code++ = 1; - } - *code++ = class_lastchar; - } - - /* Otherwise, negate the 32-byte map if necessary, and copy it into - the code vector. */ - - else - { - if (negate_class) - for (c = 0; c < 32; c++) code[c] = ~class[c]; - else - memcpy(code, class, 32); - code += 32; - } - break; - - /* Various kinds of repeat */ - - case '{': - if (!is_counted_repeat(ptr+1, cd)) goto NORMAL_CHAR; - ptr = read_repeat_counts(ptr+1, &repeat_min, &repeat_max, errorptr, cd); - if (*errorptr != NULL) goto FAILED; - goto REPEAT; - - case '*': - repeat_min = 0; - repeat_max = -1; - goto REPEAT; - - case '+': - repeat_min = 1; - repeat_max = -1; - goto REPEAT; - - case '?': - repeat_min = 0; - repeat_max = 1; - - REPEAT: - if (previous == NULL) - { - *errorptr = ERR9; - goto FAILED; - } - - /* If the next character is '?' this is a minimizing repeat, by default, - but if PCRE_UNGREEDY is set, it works the other way round. Advance to the - next character. */ - - if (ptr[1] == '?') - { repeat_type = greedy_non_default; ptr++; } - else repeat_type = greedy_default; - - /* If previous was a string of characters, chop off the last one and use it - as the subject of the repeat. If there was only one character, we can - abolish the previous item altogether. A repeat with a zero minimum wipes - out any reqchar setting, backing up to the previous value. We must also - adjust the countlits value. */ - - if (*previous == OP_CHARS) - { - int len = previous[1]; - - if (repeat_min == 0) *reqchar = prevreqchar; - *countlits += repeat_min - 1; - - if (len == 1) - { - c = previous[2]; - code = previous; - } - else - { - c = previous[len+1]; - previous[1]--; - code--; - } - op_type = 0; /* Use single-char op codes */ - goto OUTPUT_SINGLE_REPEAT; /* Code shared with single character types */ - } - - /* If previous was a single negated character ([^a] or similar), we use - one of the special opcodes, replacing it. The code is shared with single- - character repeats by adding a suitable offset into repeat_type. */ - - else if ((int)*previous == OP_NOT) - { - op_type = OP_NOTSTAR - OP_STAR; /* Use "not" opcodes */ - c = previous[1]; - code = previous; - goto OUTPUT_SINGLE_REPEAT; - } - - /* If previous was a character type match (\d or similar), abolish it and - create a suitable repeat item. The code is shared with single-character - repeats by adding a suitable offset into repeat_type. */ - - else if ((int)*previous < OP_EODN || *previous == OP_ANY) - { - op_type = OP_TYPESTAR - OP_STAR; /* Use type opcodes */ - c = *previous; - code = previous; - - OUTPUT_SINGLE_REPEAT: - - /* If the maximum is zero then the minimum must also be zero; Perl allows - this case, so we do too - by simply omitting the item altogether. */ - - if (repeat_max == 0) goto END_REPEAT; - - /* Combine the op_type with the repeat_type */ - - repeat_type += op_type; - - /* A minimum of zero is handled either as the special case * or ?, or as - an UPTO, with the maximum given. */ - - if (repeat_min == 0) - { - if (repeat_max == -1) *code++ = OP_STAR + repeat_type; - else if (repeat_max == 1) *code++ = OP_QUERY + repeat_type; - else - { - *code++ = OP_UPTO + repeat_type; - *code++ = repeat_max >> 8; - *code++ = (repeat_max & 255); - } - } - - /* The case {1,} is handled as the special case + */ - - else if (repeat_min == 1 && repeat_max == -1) - *code++ = OP_PLUS + repeat_type; - - /* The case {n,n} is just an EXACT, while the general case {n,m} is - handled as an EXACT followed by an UPTO. An EXACT of 1 is optimized. */ - - else - { - if (repeat_min != 1) - { - *code++ = OP_EXACT + op_type; /* NB EXACT doesn't have repeat_type */ - *code++ = repeat_min >> 8; - *code++ = (repeat_min & 255); - } - - /* If the mininum is 1 and the previous item was a character string, - we either have to put back the item that got cancelled if the string - length was 1, or add the character back onto the end of a longer - string. For a character type nothing need be done; it will just get - put back naturally. Note that the final character is always going to - get added below. */ - - else if (*previous == OP_CHARS) - { - if (code == previous) code += 2; else previous[1]++; - } - - /* For a single negated character we also have to put back the - item that got cancelled. */ - - else if (*previous == OP_NOT) code++; - - /* If the maximum is unlimited, insert an OP_STAR. */ - - if (repeat_max < 0) - { - *code++ = c; - *code++ = OP_STAR + repeat_type; - } - - /* Else insert an UPTO if the max is greater than the min. */ - - else if (repeat_max != repeat_min) - { - *code++ = c; - repeat_max -= repeat_min; - *code++ = OP_UPTO + repeat_type; - *code++ = repeat_max >> 8; - *code++ = (repeat_max & 255); - } - } - - /* The character or character type itself comes last in all cases. */ - - *code++ = c; - } - - /* If previous was a character class or a back reference, we put the repeat - stuff after it, but just skip the item if the repeat was {0,0}. */ - - else if (*previous == OP_CLASS || *previous == OP_REF) - { - if (repeat_max == 0) - { - code = previous; - goto END_REPEAT; - } - if (repeat_min == 0 && repeat_max == -1) - *code++ = OP_CRSTAR + repeat_type; - else if (repeat_min == 1 && repeat_max == -1) - *code++ = OP_CRPLUS + repeat_type; - else if (repeat_min == 0 && repeat_max == 1) - *code++ = OP_CRQUERY + repeat_type; - else - { - *code++ = OP_CRRANGE + repeat_type; - *code++ = repeat_min >> 8; - *code++ = repeat_min & 255; - if (repeat_max == -1) repeat_max = 0; /* 2-byte encoding for max */ - *code++ = repeat_max >> 8; - *code++ = repeat_max & 255; - } - } - - /* If previous was a bracket group, we may have to replicate it in certain - cases. */ - - else if ((int)*previous >= OP_BRA || (int)*previous == OP_ONCE || - (int)*previous == OP_COND) - { - register int i; - int ketoffset = 0; - int len = code - previous; - uschar *bralink = NULL; - - /* If the maximum repeat count is unlimited, find the end of the bracket - by scanning through from the start, and compute the offset back to it - from the current code pointer. There may be an OP_OPT setting following - the final KET, so we can't find the end just by going back from the code - pointer. */ - - if (repeat_max == -1) - { - register uschar *ket = previous; - do ket += (ket[1] << 8) + ket[2]; while (*ket != OP_KET); - ketoffset = code - ket; - } - - /* The case of a zero minimum is special because of the need to stick - OP_BRAZERO in front of it, and because the group appears once in the - data, whereas in other cases it appears the minimum number of times. For - this reason, it is simplest to treat this case separately, as otherwise - the code gets far too mess. There are several special subcases when the - minimum is zero. */ - - if (repeat_min == 0) - { - /* If we set up a required char from the bracket, we must back off - to the previous value and reset the countlits value too. */ - - if (subcountlits > 0) - { - *reqchar = prevreqchar; - *countlits -= subcountlits; - } - - /* If the maximum is also zero, we just omit the group from the output - altogether. */ - - if (repeat_max == 0) - { - code = previous; - goto END_REPEAT; - } - - /* If the maximum is 1 or unlimited, we just have to stick in the - BRAZERO and do no more at this point. */ - - if (repeat_max <= 1) - { - memmove(previous+1, previous, len); - code++; - *previous++ = OP_BRAZERO + repeat_type; - } - - /* If the maximum is greater than 1 and limited, we have to replicate - in a nested fashion, sticking OP_BRAZERO before each set of brackets. - The first one has to be handled carefully because it's the original - copy, which has to be moved up. The remainder can be handled by code - that is common with the non-zero minimum case below. We just have to - adjust the value or repeat_max, since one less copy is required. */ - - else - { - int offset; - memmove(previous+4, previous, len); - code += 4; - *previous++ = OP_BRAZERO + repeat_type; - *previous++ = OP_BRA; - - /* We chain together the bracket offset fields that have to be - filled in later when the ends of the brackets are reached. */ - - offset = (bralink == NULL)? 0 : previous - bralink; - bralink = previous; - *previous++ = offset >> 8; - *previous++ = offset & 255; - } - - repeat_max--; - } - - /* If the minimum is greater than zero, replicate the group as many - times as necessary, and adjust the maximum to the number of subsequent - copies that we need. */ - - else - { - for (i = 1; i < repeat_min; i++) - { - memcpy(code, previous, len); - code += len; - } - if (repeat_max > 0) repeat_max -= repeat_min; - } - - /* This code is common to both the zero and non-zero minimum cases. If - the maximum is limited, it replicates the group in a nested fashion, - remembering the bracket starts on a stack. In the case of a zero minimum, - the first one was set up above. In all cases the repeat_max now specifies - the number of additional copies needed. */ - - if (repeat_max >= 0) - { - for (i = repeat_max - 1; i >= 0; i--) - { - *code++ = OP_BRAZERO + repeat_type; - - /* All but the final copy start a new nesting, maintaining the - chain of brackets outstanding. */ - - if (i != 0) - { - int offset; - *code++ = OP_BRA; - offset = (bralink == NULL)? 0 : code - bralink; - bralink = code; - *code++ = offset >> 8; - *code++ = offset & 255; - } - - memcpy(code, previous, len); - code += len; - } - - /* Now chain through the pending brackets, and fill in their length - fields (which are holding the chain links pro tem). */ - - while (bralink != NULL) - { - int oldlinkoffset; - int offset = code - bralink + 1; - uschar *bra = code - offset; - oldlinkoffset = (bra[1] << 8) + bra[2]; - bralink = (oldlinkoffset == 0)? NULL : bralink - oldlinkoffset; - *code++ = OP_KET; - *code++ = bra[1] = offset >> 8; - *code++ = bra[2] = (offset & 255); - } - } - - /* If the maximum is unlimited, set a repeater in the final copy. We - can't just offset backwards from the current code point, because we - don't know if there's been an options resetting after the ket. The - correct offset was computed above. */ - - else code[-ketoffset] = OP_KETRMAX + repeat_type; - } - - /* Else there's some kind of shambles */ - - else - { - *errorptr = ERR11; - goto FAILED; - } - - /* In all case we no longer have a previous item. */ - - END_REPEAT: - previous = NULL; - break; - - - /* Start of nested bracket sub-expression, or comment or lookahead or - lookbehind or option setting or condition. First deal with special things - that can come after a bracket; all are introduced by ?, and the appearance - of any of them means that this is not a referencing group. They were - checked for validity in the first pass over the string, so we don't have to - check for syntax errors here. */ - - case '(': - newoptions = options; - condref = -1; - - if (*(++ptr) == '?') - { - int set, unset; - int *optset; - - switch (*(++ptr)) - { - case '#': /* Comment; skip to ket */ - ptr++; - while (*ptr != ')') ptr++; - continue; - - case ':': /* Non-extracting bracket */ - bravalue = OP_BRA; - ptr++; - break; - - case '(': - bravalue = OP_COND; /* Conditional group */ - if ((cd->ctypes[*(++ptr)] & ctype_digit) != 0) - { - condref = *ptr - '0'; - while (*(++ptr) != ')') condref = condref*10 + *ptr - '0'; - ptr++; - } - else ptr--; - break; - - case '=': /* Positive lookahead */ - bravalue = OP_ASSERT; - ptr++; - break; - - case '!': /* Negative lookahead */ - bravalue = OP_ASSERT_NOT; - ptr++; - break; - - case '<': /* Lookbehinds */ - switch (*(++ptr)) - { - case '=': /* Positive lookbehind */ - bravalue = OP_ASSERTBACK; - ptr++; - break; - - case '!': /* Negative lookbehind */ - bravalue = OP_ASSERTBACK_NOT; - ptr++; - break; - - default: /* Syntax error */ - *errorptr = ERR24; - goto FAILED; - } - break; - - case '>': /* One-time brackets */ - bravalue = OP_ONCE; - ptr++; - break; - - default: /* Option setting */ - set = unset = 0; - optset = &set; - - while (*ptr != ')' && *ptr != ':') - { - switch (*ptr++) - { - case '-': optset = &unset; break; - - case 'i': *optset |= PCRE_CASELESS; break; - case 'm': *optset |= PCRE_MULTILINE; break; - case 's': *optset |= PCRE_DOTALL; break; - case 'x': *optset |= PCRE_EXTENDED; break; - case 'U': *optset |= PCRE_UNGREEDY; break; - case 'X': *optset |= PCRE_EXTRA; break; - - default: - *errorptr = ERR12; - goto FAILED; - } - } - - /* Set up the changed option bits, but don't change anything yet. */ - - newoptions = (options | set) & (~unset); - - /* If the options ended with ')' this is not the start of a nested - group with option changes, so the options change at this level. At top - level there is nothing else to be done (the options will in fact have - been set from the start of compiling as a result of the first pass) but - at an inner level we must compile code to change the ims options if - necessary, and pass the new setting back so that it can be put at the - start of any following branches, and when this group ends, a resetting - item can be compiled. */ - - if (*ptr == ')') - { - if ((options & PCRE_INGROUP) != 0 && - (options & PCRE_IMS) != (newoptions & PCRE_IMS)) - { - *code++ = OP_OPT; - *code++ = *optchanged = newoptions & PCRE_IMS; - } - options = newoptions; /* Change options at this level */ - previous = NULL; /* This item can't be repeated */ - continue; /* It is complete */ - } - - /* If the options ended with ':' we are heading into a nested group - with possible change of options. Such groups are non-capturing and are - not assertions of any kind. All we need to do is skip over the ':'; - the newoptions value is handled below. */ - - bravalue = OP_BRA; - ptr++; - } - } - - /* Else we have a referencing group; adjust the opcode. */ - - else - { - if (++(*brackets) > EXTRACT_MAX) - { - *errorptr = ERR13; - goto FAILED; - } - bravalue = OP_BRA + *brackets; - } - - /* Process nested bracketed re. Assertions may not be repeated, but other - kinds can be. We copy code into a non-register variable in order to be able - to pass its address because some compilers complain otherwise. Pass in a - new setting for the ims options if they have changed. */ - - previous = (bravalue >= OP_ONCE)? code : NULL; - *code = bravalue; - tempcode = code; - - if (!compile_regex( - options | PCRE_INGROUP, /* Set for all nested groups */ - ((options & PCRE_IMS) != (newoptions & PCRE_IMS))? - newoptions & PCRE_IMS : -1, /* Pass ims options if changed */ - brackets, /* Bracket level */ - &tempcode, /* Where to put code (updated) */ - &ptr, /* Input pointer (updated) */ - errorptr, /* Where to put an error message */ - (bravalue == OP_ASSERTBACK || - bravalue == OP_ASSERTBACK_NOT), /* TRUE if back assert */ - condref, /* Condition reference number */ - &subreqchar, /* For possible last char */ - &subcountlits, /* For literal count */ - cd)) /* Tables block */ - goto FAILED; - - /* At the end of compiling, code is still pointing to the start of the - group, while tempcode has been updated to point past the end of the group - and any option resetting that may follow it. The pattern pointer (ptr) - is on the bracket. */ - - /* If this is a conditional bracket, check that there are no more than - two branches in the group. */ - - if (bravalue == OP_COND) - { - uschar *tc = code; - condcount = 0; - - do { - condcount++; - tc += (tc[1] << 8) | tc[2]; - } - while (*tc != OP_KET); - - if (condcount > 2) - { - *errorptr = ERR27; - goto FAILED; - } - } - - /* Handle updating of the required character. If the subpattern didn't - set one, leave it as it was. Otherwise, update it for normal brackets of - all kinds, forward assertions, and conditions with two branches. Don't - update the literal count for forward assertions, however. If the bracket - is followed by a quantifier with zero repeat, we have to back off. Hence - the definition of prevreqchar and subcountlits outside the main loop so - that they can be accessed for the back off. */ - - if (subreqchar > 0 && - (bravalue >= OP_BRA || bravalue == OP_ONCE || bravalue == OP_ASSERT || - (bravalue == OP_COND && condcount == 2))) - { - prevreqchar = *reqchar; - *reqchar = subreqchar; - if (bravalue != OP_ASSERT) *countlits += subcountlits; - } - - /* Now update the main code pointer to the end of the group. */ - - code = tempcode; - - /* Error if hit end of pattern */ - - if (*ptr != ')') - { - *errorptr = ERR14; - goto FAILED; - } - break; - - /* Check \ for being a real metacharacter; if not, fall through and handle - it as a data character at the start of a string. Escape items are checked - for validity in the pre-compiling pass. */ - - case '\\': - tempptr = ptr; - c = check_escape(&ptr, errorptr, *brackets, options, FALSE, cd); - - /* Handle metacharacters introduced by \. For ones like \d, the ESC_ values - are arranged to be the negation of the corresponding OP_values. For the - back references, the values are ESC_REF plus the reference number. Only - back references and those types that consume a character may be repeated. - We can test for values between ESC_b and ESC_Z for the latter; this may - have to change if any new ones are ever created. */ - - if (c < 0) - { - if (-c >= ESC_REF) - { - previous = code; - *code++ = OP_REF; - *code++ = -c - ESC_REF; - } - else - { - previous = (-c > ESC_b && -c < ESC_Z)? code : NULL; - *code++ = -c; - } - continue; - } - - /* Data character: reset and fall through */ - - ptr = tempptr; - c = '\\'; - - /* Handle a run of data characters until a metacharacter is encountered. - The first character is guaranteed not to be whitespace or # when the - extended flag is set. */ - - NORMAL_CHAR: - default: - previous = code; - *code = OP_CHARS; - code += 2; - length = 0; - - do - { - if ((options & PCRE_EXTENDED) != 0) - { - if ((cd->ctypes[c] & ctype_space) != 0) continue; - if (c == '#') - { - while ((c = *(++ptr)) != 0 && c != '\n'); - if (c == 0) break; - continue; - } - } - - /* Backslash may introduce a data char or a metacharacter. Escaped items - are checked for validity in the pre-compiling pass. Stop the string - before a metaitem. */ - - if (c == '\\') - { - tempptr = ptr; - c = check_escape(&ptr, errorptr, *brackets, options, FALSE, cd); - if (c < 0) { ptr = tempptr; break; } - } - - /* Ordinary character or single-char escape */ - - *code++ = c; - length++; - } - - /* This "while" is the end of the "do" above. */ - - while (length < 255 && (cd->ctypes[c = *(++ptr)] & ctype_meta) == 0); - - /* Update the last character and the count of literals */ - - prevreqchar = (length > 1)? code[-2] : *reqchar; - *reqchar = code[-1]; - *countlits += length; - - /* Compute the length and set it in the data vector, and advance to - the next state. */ - - previous[1] = length; - if (length < 255) ptr--; - break; - } - } /* end of big loop */ - -/* Control never reaches here by falling through, only by a goto for all the -error states. Pass back the position in the pattern so that it can be displayed -to the user for diagnosing the error. */ - -FAILED: -*ptrptr = ptr; -return FALSE; -} - - - - -/************************************************* -* Compile sequence of alternatives * -*************************************************/ - -/* On entry, ptr is pointing past the bracket character, but on return -it points to the closing bracket, or vertical bar, or end of string. -The code variable is pointing at the byte into which the BRA operator has been -stored. If the ims options are changed at the start (for a (?ims: group) or -during any branch, we need to insert an OP_OPT item at the start of every -following branch to ensure they get set correctly at run time, and also pass -the new options into every subsequent branch compile. - -Argument: - options the option bits - optchanged new ims options to set as if (?ims) were at the start, or -1 - for no change - brackets -> int containing the number of extracting brackets used - codeptr -> the address of the current code pointer - ptrptr -> the address of the current pattern pointer - errorptr -> pointer to error message - lookbehind TRUE if this is a lookbehind assertion - condref > 0 for OPT_CREF setting at start of conditional group - reqchar -> place to put the last required character, or a negative number - countlits -> place to put the shortest literal count of any branch - cd points to the data block with tables pointers - -Returns: TRUE on success -*/ - -static BOOL -compile_regex(int options, int optchanged, int *brackets, uschar **codeptr, - const uschar **ptrptr, const char **errorptr, BOOL lookbehind, int condref, - int *reqchar, int *countlits, compile_data *cd) -{ -const uschar *ptr = *ptrptr; -uschar *code = *codeptr; -uschar *last_branch = code; -uschar *start_bracket = code; -uschar *reverse_count = NULL; -int oldoptions = options & PCRE_IMS; -int branchreqchar, branchcountlits; - -*reqchar = -1; -*countlits = INT_MAX; -code += 3; - -/* At the start of a reference-based conditional group, insert the reference -number as an OP_CREF item. */ - -if (condref > 0) - { - *code++ = OP_CREF; - *code++ = condref; - } - -/* Loop for each alternative branch */ - -for (;;) - { - int length; - - /* Handle change of options */ - - if (optchanged >= 0) - { - *code++ = OP_OPT; - *code++ = optchanged; - options = (options & ~PCRE_IMS) | optchanged; - } - - /* Set up dummy OP_REVERSE if lookbehind assertion */ - - if (lookbehind) - { - *code++ = OP_REVERSE; - reverse_count = code; - *code++ = 0; - *code++ = 0; - } - - /* Now compile the branch */ - - if (!compile_branch(options, brackets, &code, &ptr, errorptr, &optchanged, - &branchreqchar, &branchcountlits, cd)) - { - *ptrptr = ptr; - return FALSE; - } - - /* Fill in the length of the last branch */ - - length = code - last_branch; - last_branch[1] = length >> 8; - last_branch[2] = length & 255; - - /* Save the last required character if all branches have the same; a current - value of -1 means unset, while -2 means "previous branch had no last required - char". */ - - if (*reqchar != -2) - { - if (branchreqchar >= 0) - { - if (*reqchar == -1) *reqchar = branchreqchar; - else if (*reqchar != branchreqchar) *reqchar = -2; - } - else *reqchar = -2; - } - - /* Keep the shortest literal count */ - - if (branchcountlits < *countlits) *countlits = branchcountlits; - DPRINTF(("literal count = %d min=%d\n", branchcountlits, *countlits)); - - /* If lookbehind, check that this branch matches a fixed-length string, - and put the length into the OP_REVERSE item. Temporarily mark the end of - the branch with OP_END. */ - - if (lookbehind) - { - *code = OP_END; - length = find_fixedlength(last_branch); - DPRINTF(("fixed length = %d\n", length)); - if (length < 0) - { - *errorptr = ERR25; - *ptrptr = ptr; - return FALSE; - } - reverse_count[0] = (length >> 8); - reverse_count[1] = length & 255; - } - - /* Reached end of expression, either ')' or end of pattern. Insert a - terminating ket and the length of the whole bracketed item, and return, - leaving the pointer at the terminating char. If any of the ims options - were changed inside the group, compile a resetting op-code following. */ - - if (*ptr != '|') - { - length = code - start_bracket; - *code++ = OP_KET; - *code++ = length >> 8; - *code++ = length & 255; - if (optchanged >= 0) - { - *code++ = OP_OPT; - *code++ = oldoptions; - } - *codeptr = code; - *ptrptr = ptr; - return TRUE; - } - - /* Another branch follows; insert an "or" node and advance the pointer. */ - - *code = OP_ALT; - last_branch = code; - code += 3; - ptr++; - } -/* Control never reaches here */ -} - - - - -/************************************************* -* Find first significant op code * -*************************************************/ - -/* This is called by several functions that scan a compiled expression looking -for a fixed first character, or an anchoring op code etc. It skips over things -that do not influence this. For one application, a change of caseless option is -important. - -Arguments: - code pointer to the start of the group - options pointer to external options - optbit the option bit whose changing is significant, or - zero if none are - optstop TRUE to return on option change, otherwise change the options - value and continue - -Returns: pointer to the first significant opcode -*/ - -static const uschar* -first_significant_code(const uschar *code, int *options, int optbit, - BOOL optstop) -{ -for (;;) - { - switch ((int)*code) - { - case OP_OPT: - if (optbit > 0 && ((int)code[1] & optbit) != (*options & optbit)) - { - if (optstop) return code; - *options = (int)code[1]; - } - code += 2; - break; - - case OP_CREF: - code += 2; - break; - - case OP_WORD_BOUNDARY: - case OP_NOT_WORD_BOUNDARY: - code++; - break; - - case OP_ASSERT_NOT: - case OP_ASSERTBACK: - case OP_ASSERTBACK_NOT: - do code += (code[1] << 8) + code[2]; while (*code == OP_ALT); - code += 3; - break; - - default: - return code; - } - } -/* Control never reaches here */ -} - - - - -/************************************************* -* Check for anchored expression * -*************************************************/ - -/* Try to find out if this is an anchored regular expression. Consider each -alternative branch. If they all start with OP_SOD or OP_CIRC, or with a bracket -all of whose alternatives start with OP_SOD or OP_CIRC (recurse ad lib), then -it's anchored. However, if this is a multiline pattern, then only OP_SOD -counts, since OP_CIRC can match in the middle. - -A branch is also implicitly anchored if it starts with .* and DOTALL is set, -because that will try the rest of the pattern at all possible matching points, -so there is no point trying them again. - -Arguments: - code points to start of expression (the bracket) - options points to the options setting - -Returns: TRUE or FALSE -*/ - -static BOOL -is_anchored(register const uschar *code, int *options) -{ -do { - const uschar *scode = first_significant_code(code + 3, options, - PCRE_MULTILINE, FALSE); - register int op = *scode; - if (op >= OP_BRA || op == OP_ASSERT || op == OP_ONCE || op == OP_COND) - { if (!is_anchored(scode, options)) return FALSE; } - else if ((op == OP_TYPESTAR || op == OP_TYPEMINSTAR) && - (*options & PCRE_DOTALL) != 0) - { if (scode[1] != OP_ANY) return FALSE; } - else if (op != OP_SOD && - ((*options & PCRE_MULTILINE) != 0 || op != OP_CIRC)) - return FALSE; - code += (code[1] << 8) + code[2]; - } -while (*code == OP_ALT); -return TRUE; -} - - - -/************************************************* -* Check for starting with ^ or .* * -*************************************************/ - -/* This is called to find out if every branch starts with ^ or .* so that -"first char" processing can be done to speed things up in multiline -matching and for non-DOTALL patterns that start with .* (which must start at -the beginning or after \n). - -Argument: points to start of expression (the bracket) -Returns: TRUE or FALSE -*/ - -static BOOL -is_startline(const uschar *code) -{ -do { - const uschar *scode = first_significant_code(code + 3, NULL, 0, FALSE); - register int op = *scode; - if (op >= OP_BRA || op == OP_ASSERT || op == OP_ONCE || op == OP_COND) - { if (!is_startline(scode)) return FALSE; } - else if (op == OP_TYPESTAR || op == OP_TYPEMINSTAR) - { if (scode[1] != OP_ANY) return FALSE; } - else if (op != OP_CIRC) return FALSE; - code += (code[1] << 8) + code[2]; - } -while (*code == OP_ALT); -return TRUE; -} - - - -/************************************************* -* Check for fixed first char * -*************************************************/ - -/* Try to find out if there is a fixed first character. This is called for -unanchored expressions, as it speeds up their processing quite considerably. -Consider each alternative branch. If they all start with the same char, or with -a bracket all of whose alternatives start with the same char (recurse ad lib), -then we return that char, otherwise -1. - -Arguments: - code points to start of expression (the bracket) - options pointer to the options (used to check casing changes) - -Returns: -1 or the fixed first char -*/ - -static int -find_firstchar(const uschar *code, int *options) -{ -register int c = -1; -do { - int d; - const uschar *scode = first_significant_code(code + 3, options, - PCRE_CASELESS, TRUE); - register int op = *scode; - - if (op >= OP_BRA) op = OP_BRA; - - switch(op) - { - default: - return -1; - - case OP_BRA: - case OP_ASSERT: - case OP_ONCE: - case OP_COND: - if ((d = find_firstchar(scode, options)) < 0) return -1; - if (c < 0) c = d; else if (c != d) return -1; - break; - - case OP_EXACT: /* Fall through */ - scode++; - - case OP_CHARS: /* Fall through */ - scode++; - - case OP_PLUS: - case OP_MINPLUS: - if (c < 0) c = scode[1]; else if (c != scode[1]) return -1; - break; - } - - code += (code[1] << 8) + code[2]; - } -while (*code == OP_ALT); -return c; -} - - - - - -/************************************************* -* Compile a Regular Expression * -*************************************************/ - -/* This function takes a string and returns a pointer to a block of store -holding a compiled version of the expression. - -Arguments: - pattern the regular expression - options various option bits - errorptr pointer to pointer to error text - erroroffset ptr offset in pattern where error was detected - tables pointer to character tables or NULL - -Returns: pointer to compiled data block, or NULL on error, - with errorptr and erroroffset set -*/ - -pcre * -pcre_compile(const char *pattern, int options, const char **errorptr, - int *erroroffset, const unsigned char *tables) -{ -real_pcre *re; -int length = 3; /* For initial BRA plus length */ -int runlength; -int c, size, reqchar, countlits; -int bracount = 0; -int top_backref = 0; -int branch_extra = 0; -int branch_newextra; -unsigned int brastackptr = 0; -uschar *code; -const uschar *ptr; -compile_data compile_block; -int brastack[BRASTACK_SIZE]; -uschar bralenstack[BRASTACK_SIZE]; - -#ifdef DEBUG -uschar *code_base, *code_end; -#endif - -/* We can't pass back an error message if errorptr is NULL; I guess the best we -can do is just return NULL. */ - -if (errorptr == NULL) return NULL; -*errorptr = NULL; - -/* However, we can give a message for this error */ - -if (erroroffset == NULL) - { - *errorptr = ERR16; - return NULL; - } -*erroroffset = 0; - -if ((options & ~PUBLIC_OPTIONS) != 0) - { - *errorptr = ERR17; - return NULL; - } - -/* Set up pointers to the individual character tables */ - -if (tables == NULL) tables = pcre_default_tables; -compile_block.lcc = tables + lcc_offset; -compile_block.fcc = tables + fcc_offset; -compile_block.cbits = tables + cbits_offset; -compile_block.ctypes = tables + ctypes_offset; - -/* Reflect pattern for debugging output */ - -DPRINTF(("------------------------------------------------------------------\n")); -DPRINTF(("%s\n", pattern)); - -/* The first thing to do is to make a pass over the pattern to compute the -amount of store required to hold the compiled code. This does not have to be -perfect as long as errors are overestimates. At the same time we can detect any -internal flag settings. Make an attempt to correct for any counted white space -if an "extended" flag setting appears late in the pattern. We can't be so -clever for #-comments. */ - -ptr = (const uschar *)(pattern - 1); -while ((c = *(++ptr)) != 0) - { - int min, max; - int class_charcount; - - if ((options & PCRE_EXTENDED) != 0) - { - if ((compile_block.ctypes[c] & ctype_space) != 0) continue; - if (c == '#') - { - while ((c = *(++ptr)) != 0 && c != '\n'); - continue; - } - } - - switch(c) - { - /* A backslashed item may be an escaped "normal" character or a - character type. For a "normal" character, put the pointers and - character back so that tests for whitespace etc. in the input - are done correctly. */ - - case '\\': - { - const uschar *save_ptr = ptr; - c = check_escape(&ptr, errorptr, bracount, options, FALSE, &compile_block); - if (*errorptr != NULL) goto PCRE_ERROR_RETURN; - if (c >= 0) - { - ptr = save_ptr; - c = '\\'; - goto NORMAL_CHAR; - } - } - length++; - - /* A back reference needs an additional char, plus either one or 5 - bytes for a repeat. We also need to keep the value of the highest - back reference. */ - - if (c <= -ESC_REF) - { - int refnum = -c - ESC_REF; - if (refnum > top_backref) top_backref = refnum; - length++; /* For single back reference */ - if (ptr[1] == '{' && is_counted_repeat(ptr+2, &compile_block)) - { - ptr = read_repeat_counts(ptr+2, &min, &max, errorptr, &compile_block); - if (*errorptr != NULL) goto PCRE_ERROR_RETURN; - if ((min == 0 && (max == 1 || max == -1)) || - (min == 1 && max == -1)) - length++; - else length += 5; - if (ptr[1] == '?') ptr++; - } - } - continue; - - case '^': - case '.': - case '$': - case '*': /* These repeats won't be after brackets; */ - case '+': /* those are handled separately */ - case '?': - length++; - continue; - - /* This covers the cases of repeats after a single char, metachar, class, - or back reference. */ - - case '{': - if (!is_counted_repeat(ptr+1, &compile_block)) goto NORMAL_CHAR; - ptr = read_repeat_counts(ptr+1, &min, &max, errorptr, &compile_block); - if (*errorptr != NULL) goto PCRE_ERROR_RETURN; - if ((min == 0 && (max == 1 || max == -1)) || - (min == 1 && max == -1)) - length++; - else - { - length--; /* Uncount the original char or metachar */ - if (min == 1) length++; else if (min > 0) length += 4; - if (max > 0) length += 4; else length += 2; - } - if (ptr[1] == '?') ptr++; - continue; - - /* An alternation contains an offset to the next branch or ket. If any ims - options changed in the previous branch(es), and/or if we are in a - lookbehind assertion, extra space will be needed at the start of the - branch. This is handled by branch_extra. */ - - case '|': - length += 3 + branch_extra; - continue; - - /* A character class uses 33 characters. Don't worry about character types - that aren't allowed in classes - they'll get picked up during the compile. - A character class that contains only one character uses 2 or 3 bytes, - depending on whether it is negated or not. Notice this where we can. */ - - case '[': - class_charcount = 0; - if (*(++ptr) == '^') ptr++; - do - { - if (*ptr == '\\') - { - int ch = check_escape(&ptr, errorptr, bracount, options, TRUE, - &compile_block); - if (*errorptr != NULL) goto PCRE_ERROR_RETURN; - if (-ch == ESC_b) class_charcount++; else class_charcount = 10; - } - else class_charcount++; - ptr++; - } - while (*ptr != 0 && *ptr != ']'); - - /* Repeats for negated single chars are handled by the general code */ - - if (class_charcount == 1) length += 3; else - { - length += 33; - - /* A repeat needs either 1 or 5 bytes. */ - - if (*ptr != 0 && ptr[1] == '{' && is_counted_repeat(ptr+2, &compile_block)) - { - ptr = read_repeat_counts(ptr+2, &min, &max, errorptr, &compile_block); - if (*errorptr != NULL) goto PCRE_ERROR_RETURN; - if ((min == 0 && (max == 1 || max == -1)) || - (min == 1 && max == -1)) - length++; - else length += 5; - if (ptr[1] == '?') ptr++; - } - } - continue; - - /* Brackets may be genuine groups or special things */ - - case '(': - branch_newextra = 0; - - /* Handle special forms of bracket, which all start (? */ - - if (ptr[1] == '?') - { - int set, unset; - int *optset; - - switch (c = ptr[2]) - { - /* Skip over comments entirely */ - case '#': - ptr += 3; - while (*ptr != 0 && *ptr != ')') ptr++; - if (*ptr == 0) - { - *errorptr = ERR18; - goto PCRE_ERROR_RETURN; - } - continue; - - /* Non-referencing groups and lookaheads just move the pointer on, and - then behave like a non-special bracket, except that they don't increment - the count of extracting brackets. Ditto for the "once only" bracket, - which is in Perl from version 5.005. */ - - case ':': - case '=': - case '!': - case '>': - ptr += 2; - break; - - /* Lookbehinds are in Perl from version 5.005 */ - - case '<': - if (ptr[3] == '=' || ptr[3] == '!') - { - ptr += 3; - branch_newextra = 3; - length += 3; /* For the first branch */ - break; - } - *errorptr = ERR24; - goto PCRE_ERROR_RETURN; - - /* Conditionals are in Perl from version 5.005. The bracket must either - be followed by a number (for bracket reference) or by an assertion - group. */ - - case '(': - if ((compile_block.ctypes[ptr[3]] & ctype_digit) != 0) - { - ptr += 4; - length += 2; - while ((compile_block.ctypes[*ptr] & ctype_digit) != 0) ptr++; - if (*ptr != ')') - { - *errorptr = ERR26; - goto PCRE_ERROR_RETURN; - } - } - else /* An assertion must follow */ - { - ptr++; /* Can treat like ':' as far as spacing is concerned */ - - if (ptr[2] != '?' || strchr("=!<", ptr[3]) == NULL) - { - ptr += 2; /* To get right offset in message */ - *errorptr = ERR28; - goto PCRE_ERROR_RETURN; - } - } - break; - - /* Else loop checking valid options until ) is met. Anything else is an - error. If we are without any brackets, i.e. at top level, the settings - act as if specified in the options, so massage the options immediately. - This is for backward compatibility with Perl 5.004. */ - - default: - set = unset = 0; - optset = &set; - ptr += 2; - - for (;; ptr++) - { - c = *ptr; - switch (c) - { - case 'i': - *optset |= PCRE_CASELESS; - continue; - - case 'm': - *optset |= PCRE_MULTILINE; - continue; - - case 's': - *optset |= PCRE_DOTALL; - continue; - - case 'x': - *optset |= PCRE_EXTENDED; - continue; - - case 'X': - *optset |= PCRE_EXTRA; - continue; - - case 'U': - *optset |= PCRE_UNGREEDY; - continue; - - case '-': - optset = &unset; - continue; - - /* A termination by ')' indicates an options-setting-only item; - this is global at top level; otherwise nothing is done here and - it is handled during the compiling process on a per-bracket-group - basis. */ - - case ')': - if (brastackptr == 0) - { - options = (options | set) & (~unset); - set = unset = 0; /* To save length */ - } - /* Fall through */ - - /* A termination by ':' indicates the start of a nested group with - the given options set. This is again handled at compile time, but - we must allow for compiled space if any of the ims options are - set. We also have to allow for resetting space at the end of - the group, which is why 4 is added to the length and not just 2. - If there are several changes of options within the same group, this - will lead to an over-estimate on the length, but this shouldn't - matter very much. We also have to allow for resetting options at - the start of any alternations, which we do by setting - branch_newextra to 2. Finally, we record whether the case-dependent - flag ever changes within the regex. This is used by the "required - character" code. */ - - case ':': - if (((set|unset) & PCRE_IMS) != 0) - { - length += 4; - branch_newextra = 2; - if (((set|unset) & PCRE_CASELESS) != 0) options |= PCRE_ICHANGED; - } - goto END_OPTIONS; - - /* Unrecognized option character */ - - default: - *errorptr = ERR12; - goto PCRE_ERROR_RETURN; - } - } - - /* If we hit a closing bracket, that's it - this is a freestanding - option-setting. We need to ensure that branch_extra is updated if - necessary. The only values branch_newextra can have here are 0 or 2. - If the value is 2, then branch_extra must either be 2 or 5, depending - on whether this is a lookbehind group or not. */ - - END_OPTIONS: - if (c == ')') - { - if (branch_newextra == 2 && (branch_extra == 0 || branch_extra == 3)) - branch_extra += branch_newextra; - continue; - } - - /* If options were terminated by ':' control comes here. Fall through - to handle the group below. */ - } - } - - /* Extracting brackets must be counted so we can process escapes in a - Perlish way. */ - - else bracount++; - - /* Non-special forms of bracket. Save length for computing whole length - at end if there's a repeat that requires duplication of the group. Also - save the current value of branch_extra, and start the new group with - the new value. If non-zero, this will either be 2 for a (?imsx: group, or 3 - for a lookbehind assertion. */ - - if (brastackptr >= sizeof(brastack)/sizeof(int)) - { - *errorptr = ERR19; - goto PCRE_ERROR_RETURN; - } - - bralenstack[brastackptr] = branch_extra; - branch_extra = branch_newextra; - - brastack[brastackptr++] = length; - length += 3; - continue; - - /* Handle ket. Look for subsequent max/min; for certain sets of values we - have to replicate this bracket up to that many times. If brastackptr is - 0 this is an unmatched bracket which will generate an error, but take care - not to try to access brastack[-1] when computing the length and restoring - the branch_extra value. */ - - case ')': - length += 3; - { - int minval = 1; - int maxval = 1; - int duplength; - - if (brastackptr > 0) - { - duplength = length - brastack[--brastackptr]; - branch_extra = bralenstack[brastackptr]; - } - else duplength = 0; - - /* Leave ptr at the final char; for read_repeat_counts this happens - automatically; for the others we need an increment. */ - - if ((c = ptr[1]) == '{' && is_counted_repeat(ptr+2, &compile_block)) - { - ptr = read_repeat_counts(ptr+2, &minval, &maxval, errorptr, - &compile_block); - if (*errorptr != NULL) goto PCRE_ERROR_RETURN; - } - else if (c == '*') { minval = 0; maxval = -1; ptr++; } - else if (c == '+') { maxval = -1; ptr++; } - else if (c == '?') { minval = 0; ptr++; } - - /* If the minimum is zero, we have to allow for an OP_BRAZERO before the - group, and if the maximum is greater than zero, we have to replicate - maxval-1 times; each replication acquires an OP_BRAZERO plus a nesting - bracket set - hence the 7. */ - - if (minval == 0) - { - length++; - if (maxval > 0) length += (maxval - 1) * (duplength + 7); - } - - /* When the minimum is greater than zero, 1 we have to replicate up to - minval-1 times, with no additions required in the copies. Then, if - there is a limited maximum we have to replicate up to maxval-1 times - allowing for a BRAZERO item before each optional copy and nesting - brackets for all but one of the optional copies. */ - - else - { - length += (minval - 1) * duplength; - if (maxval > minval) /* Need this test as maxval=-1 means no limit */ - length += (maxval - minval) * (duplength + 7) - 6; - } - } - continue; - - /* Non-special character. For a run of such characters the length required - is the number of characters + 2, except that the maximum run length is 255. - We won't get a skipped space or a non-data escape or the start of a # - comment as the first character, so the length can't be zero. */ - - NORMAL_CHAR: - default: - length += 2; - runlength = 0; - do - { - if ((options & PCRE_EXTENDED) != 0) - { - if ((compile_block.ctypes[c] & ctype_space) != 0) continue; - if (c == '#') - { - while ((c = *(++ptr)) != 0 && c != '\n'); - continue; - } - } - - /* Backslash may introduce a data char or a metacharacter; stop the - string before the latter. */ - - if (c == '\\') - { - const uschar *saveptr = ptr; - c = check_escape(&ptr, errorptr, bracount, options, FALSE, - &compile_block); - if (*errorptr != NULL) goto PCRE_ERROR_RETURN; - if (c < 0) { ptr = saveptr; break; } - } - - /* Ordinary character or single-char escape */ - - runlength++; - } - - /* This "while" is the end of the "do" above. */ - - while (runlength < 255 && - (compile_block.ctypes[c = *(++ptr)] & ctype_meta) == 0); - - ptr--; - length += runlength; - continue; - } - } - -length += 4; /* For final KET and END */ - -if (length > 65539) - { - *errorptr = ERR20; - return NULL; - } - -/* Compute the size of data block needed and get it, either from malloc or -externally provided function. We specify "code[0]" in the offsetof() expression -rather than just "code", because it has been reported that one broken compiler -fails on "code" because it is also an independent variable. It should make no -difference to the value of the offsetof(). */ - -size = length + offsetof(real_pcre, code[0]); -re = (real_pcre *)(pcre_malloc)(size); - -if (re == NULL) - { - *errorptr = ERR21; - return NULL; - } - -/* Put in the magic number and the options. */ - -re->magic_number = MAGIC_NUMBER; -re->options = options; -re->tables = tables; - -/* Set up a starting, non-extracting bracket, then compile the expression. On -error, *errorptr will be set non-NULL, so we don't need to look at the result -of the function here. */ - -ptr = (const uschar *)pattern; -code = re->code; -*code = OP_BRA; -bracount = 0; -(void)compile_regex(options, -1, &bracount, &code, &ptr, errorptr, FALSE, -1, - &reqchar, &countlits, &compile_block); -re->top_bracket = bracount; -re->top_backref = top_backref; - -/* If not reached end of pattern on success, there's an excess bracket. */ - -if (*errorptr == NULL && *ptr != 0) *errorptr = ERR22; - -/* Fill in the terminating state and check for disastrous overflow, but -if debugging, leave the test till after things are printed out. */ - -*code++ = OP_END; - -#ifndef DEBUG -if (code - re->code > length) *errorptr = ERR23; -#endif - -/* Give an error if there's back reference to a non-existent capturing -subpattern. */ - -if (top_backref > re->top_bracket) *errorptr = ERR15; - -/* Failed to compile */ - -if (*errorptr != NULL) - { - (pcre_free)(re); - PCRE_ERROR_RETURN: - *erroroffset = ptr - (const uschar *)pattern; - return NULL; - } - -/* If the anchored option was not passed, set flag if we can determine that the -pattern is anchored by virtue of ^ characters or \A or anything else (such as -starting with .* when DOTALL is set). - -Otherwise, see if we can determine what the first character has to be, because -that speeds up unanchored matches no end. If not, see if we can set the -PCRE_STARTLINE flag. This is helpful for multiline matches when all branches -start with ^. and also when all branches start with .* for non-DOTALL matches. -*/ - -if ((options & PCRE_ANCHORED) == 0) - { - int temp_options = options; - if (is_anchored(re->code, &temp_options)) - re->options |= PCRE_ANCHORED; - else - { - int ch = find_firstchar(re->code, &temp_options); - if (ch >= 0) - { - re->first_char = ch; - re->options |= PCRE_FIRSTSET; - } - else if (is_startline(re->code)) - re->options |= PCRE_STARTLINE; - } - } - -/* Save the last required character if there are at least two literal -characters on all paths, or if there is no first character setting. */ - -if (reqchar >= 0 && (countlits > 1 || (re->options & PCRE_FIRSTSET) == 0)) - { - re->req_char = reqchar; - re->options |= PCRE_REQCHSET; - } - -/* Print out the compiled data for debugging */ - -#ifdef DEBUG - -printf("Length = %d top_bracket = %d top_backref = %d\n", - length, re->top_bracket, re->top_backref); - -if (re->options != 0) - { - printf("%s%s%s%s%s%s%s%s%s\n", - ((re->options & PCRE_ANCHORED) != 0)? "anchored " : "", - ((re->options & PCRE_CASELESS) != 0)? "caseless " : "", - ((re->options & PCRE_ICHANGED) != 0)? "case state changed " : "", - ((re->options & PCRE_EXTENDED) != 0)? "extended " : "", - ((re->options & PCRE_MULTILINE) != 0)? "multiline " : "", - ((re->options & PCRE_DOTALL) != 0)? "dotall " : "", - ((re->options & PCRE_DOLLAR_ENDONLY) != 0)? "endonly " : "", - ((re->options & PCRE_EXTRA) != 0)? "extra " : "", - ((re->options & PCRE_UNGREEDY) != 0)? "ungreedy " : ""); - } - -if ((re->options & PCRE_FIRSTSET) != 0) - { - if (isprint(re->first_char)) printf("First char = %c\n", re->first_char); - else printf("First char = \\x%02x\n", re->first_char); - } - -if ((re->options & PCRE_REQCHSET) != 0) - { - if (isprint(re->req_char)) printf("Req char = %c\n", re->req_char); - else printf("Req char = \\x%02x\n", re->req_char); - } - -code_end = code; -code_base = code = re->code; - -while (code < code_end) - { - int charlength; - - printf("%3d ", code - code_base); - - if (*code >= OP_BRA) - { - printf("%3d Bra %d", (code[1] << 8) + code[2], *code - OP_BRA); - code += 2; - } - - else switch(*code) - { - case OP_OPT: - printf(" %.2x %s", code[1], OP_names[*code]); - code++; - break; - - case OP_COND: - printf("%3d Cond", (code[1] << 8) + code[2]); - code += 2; - break; - - case OP_CREF: - printf(" %.2d %s", code[1], OP_names[*code]); - code++; - break; - - case OP_CHARS: - charlength = *(++code); - printf("%3d ", charlength); - while (charlength-- > 0) - if (isprint(c = *(++code))) printf("%c", c); else printf("\\x%02x", c); - break; - - case OP_KETRMAX: - case OP_KETRMIN: - case OP_ALT: - case OP_KET: - case OP_ASSERT: - case OP_ASSERT_NOT: - case OP_ASSERTBACK: - case OP_ASSERTBACK_NOT: - case OP_ONCE: - printf("%3d %s", (code[1] << 8) + code[2], OP_names[*code]); - code += 2; - break; - - case OP_REVERSE: - printf("%3d %s", (code[1] << 8) + code[2], OP_names[*code]); - code += 2; - break; - - case OP_STAR: - case OP_MINSTAR: - case OP_PLUS: - case OP_MINPLUS: - case OP_QUERY: - case OP_MINQUERY: - case OP_TYPESTAR: - case OP_TYPEMINSTAR: - case OP_TYPEPLUS: - case OP_TYPEMINPLUS: - case OP_TYPEQUERY: - case OP_TYPEMINQUERY: - if (*code >= OP_TYPESTAR) - printf(" %s", OP_names[code[1]]); - else if (isprint(c = code[1])) printf(" %c", c); - else printf(" \\x%02x", c); - printf("%s", OP_names[*code++]); - break; - - case OP_EXACT: - case OP_UPTO: - case OP_MINUPTO: - if (isprint(c = code[3])) printf(" %c{", c); - else printf(" \\x%02x{", c); - if (*code != OP_EXACT) printf("0,"); - printf("%d}", (code[1] << 8) + code[2]); - if (*code == OP_MINUPTO) printf("?"); - code += 3; - break; - - case OP_TYPEEXACT: - case OP_TYPEUPTO: - case OP_TYPEMINUPTO: - printf(" %s{", OP_names[code[3]]); - if (*code != OP_TYPEEXACT) printf(","); - printf("%d}", (code[1] << 8) + code[2]); - if (*code == OP_TYPEMINUPTO) printf("?"); - code += 3; - break; - - case OP_NOT: - if (isprint(c = *(++code))) printf(" [^%c]", c); - else printf(" [^\\x%02x]", c); - break; - - case OP_NOTSTAR: - case OP_NOTMINSTAR: - case OP_NOTPLUS: - case OP_NOTMINPLUS: - case OP_NOTQUERY: - case OP_NOTMINQUERY: - if (isprint(c = code[1])) printf(" [^%c]", c); - else printf(" [^\\x%02x]", c); - printf("%s", OP_names[*code++]); - break; - - case OP_NOTEXACT: - case OP_NOTUPTO: - case OP_NOTMINUPTO: - if (isprint(c = code[3])) printf(" [^%c]{", c); - else printf(" [^\\x%02x]{", c); - if (*code != OP_NOTEXACT) printf(","); - printf("%d}", (code[1] << 8) + code[2]); - if (*code == OP_NOTMINUPTO) printf("?"); - code += 3; - break; - - case OP_REF: - printf(" \\%d", *(++code)); - code ++; - goto CLASS_REF_REPEAT; - - case OP_CLASS: - { - int i, min, max; - code++; - printf(" ["); - - for (i = 0; i < 256; i++) - { - if ((code[i/8] & (1 << (i&7))) != 0) - { - int j; - for (j = i+1; j < 256; j++) - if ((code[j/8] & (1 << (j&7))) == 0) break; - if (i == '-' || i == ']') printf("\\"); - if (isprint(i)) printf("%c", i); else printf("\\x%02x", i); - if (--j > i) - { - printf("-"); - if (j == '-' || j == ']') printf("\\"); - if (isprint(j)) printf("%c", j); else printf("\\x%02x", j); - } - i = j; - } - } - printf("]"); - code += 32; - - CLASS_REF_REPEAT: - - switch(*code) - { - case OP_CRSTAR: - case OP_CRMINSTAR: - case OP_CRPLUS: - case OP_CRMINPLUS: - case OP_CRQUERY: - case OP_CRMINQUERY: - printf("%s", OP_names[*code]); - break; - - case OP_CRRANGE: - case OP_CRMINRANGE: - min = (code[1] << 8) + code[2]; - max = (code[3] << 8) + code[4]; - if (max == 0) printf("{%d,}", min); - else printf("{%d,%d}", min, max); - if (*code == OP_CRMINRANGE) printf("?"); - code += 4; - break; - - default: - code--; - } - } - break; - - /* Anything else is just a one-node item */ - - default: - printf(" %s", OP_names[*code]); - break; - } - - code++; - printf("\n"); - } -printf("------------------------------------------------------------------\n"); - -/* This check is done here in the debugging case so that the code that -was compiled can be seen. */ - -if (code - re->code > length) - { - *errorptr = ERR23; - (pcre_free)(re); - *erroroffset = ptr - (uschar *)pattern; - return NULL; - } -#endif - -return (pcre *)re; -} - - - -/************************************************* -* Match a back-reference * -*************************************************/ - -/* If a back reference hasn't been set, the length that is passed is greater -than the number of characters left in the string, so the match fails. - -Arguments: - offset index into the offset vector - eptr points into the subject - length length to be matched - md points to match data block - ims the ims flags - -Returns: TRUE if matched -*/ - -static BOOL -match_ref(int offset, register const uschar *eptr, int length, match_data *md, - unsigned long int ims) -{ -const uschar *p = md->start_subject + md->offset_vector[offset]; - -#ifdef DEBUG -if (eptr >= md->end_subject) - printf("matching subject "); -else - { - printf("matching subject "); - pchars(eptr, length, TRUE, md); - } -printf(" against backref "); -pchars(p, length, FALSE, md); -printf("\n"); -#endif - -/* Always fail if not enough characters left */ - -if (length > md->end_subject - eptr) return FALSE; - -/* Separate the caselesss case for speed */ - -if ((ims & PCRE_CASELESS) != 0) - { - while (length-- > 0) - if (md->lcc[*p++] != md->lcc[*eptr++]) return FALSE; - } -else - { while (length-- > 0) if (*p++ != *eptr++) return FALSE; } - -return TRUE; -} - - - -/************************************************* -* Match from current position * -*************************************************/ - -/* On entry ecode points to the first opcode, and eptr to the first character -in the subject string, while eptrb holds the value of eptr at the start of the -last bracketed group - used for breaking infinite loops matching zero-length -strings. - -Arguments: - eptr pointer in subject - ecode position in code - offset_top current top pointer - md pointer to "static" info for the match - ims current /i, /m, and /s options - condassert TRUE if called to check a condition assertion - eptrb eptr at start of last bracket - -Returns: TRUE if matched -*/ - -static BOOL -match(register const uschar *eptr, register const uschar *ecode, - int offset_top, match_data *md, unsigned long int ims, BOOL condassert, - const uschar *eptrb) -{ -unsigned long int original_ims = ims; /* Save for resetting on ')' */ - -for (;;) - { - int op = (int)*ecode; - int min, max, ctype; - register int i; - register int c; - BOOL minimize = FALSE; - - /* Opening capturing bracket. If there is space in the offset vector, save - the current subject position in the working slot at the top of the vector. We - mustn't change the current values of the data slot, because they may be set - from a previous iteration of this group, and be referred to by a reference - inside the group. - - If the bracket fails to match, we need to restore this value and also the - values of the final offsets, in case they were set by a previous iteration of - the same bracket. - - If there isn't enough space in the offset vector, treat this as if it were a - non-capturing bracket. Don't worry about setting the flag for the error case - here; that is handled in the code for KET. */ - - if (op > OP_BRA) - { - int number = op - OP_BRA; - int offset = number << 1; - -#ifdef DEBUG - printf("start bracket %d subject=", number); - pchars(eptr, 16, TRUE, md); - printf("\n"); -#endif - - if (offset < md->offset_max) - { - int save_offset1 = md->offset_vector[offset]; - int save_offset2 = md->offset_vector[offset+1]; - int save_offset3 = md->offset_vector[md->offset_end - number]; - - DPRINTF(("saving %d %d %d\n", save_offset1, save_offset2, save_offset3)); - md->offset_vector[md->offset_end - number] = eptr - md->start_subject; - - do - { - if (match(eptr, ecode+3, offset_top, md, ims, FALSE, eptr)) return TRUE; - ecode += (ecode[1] << 8) + ecode[2]; - } - while (*ecode == OP_ALT); - - DPRINTF(("bracket %d failed\n", number)); - - md->offset_vector[offset] = save_offset1; - md->offset_vector[offset+1] = save_offset2; - md->offset_vector[md->offset_end - number] = save_offset3; - return FALSE; - } - - /* Insufficient room for saving captured contents */ - - else op = OP_BRA; - } - - /* Other types of node can be handled by a switch */ - - switch(op) - { - case OP_BRA: /* Non-capturing bracket: optimized */ - DPRINTF(("start bracket 0\n")); - do - { - if (match(eptr, ecode+3, offset_top, md, ims, FALSE, eptr)) return TRUE; - ecode += (ecode[1] << 8) + ecode[2]; - } - while (*ecode == OP_ALT); - DPRINTF(("bracket 0 failed\n")); - return FALSE; - - /* Conditional group: compilation checked that there are no more than - two branches. If the condition is false, skipping the first branch takes us - past the end if there is only one branch, but that's OK because that is - exactly what going to the ket would do. */ - - case OP_COND: - if (ecode[3] == OP_CREF) /* Condition is extraction test */ - { - int offset = ecode[4] << 1; /* Doubled reference number */ - return match(eptr, - ecode + ((offset < offset_top && md->offset_vector[offset] >= 0)? - 5 : 3 + (ecode[1] << 8) + ecode[2]), - offset_top, md, ims, FALSE, eptr); - } - - /* The condition is an assertion. Call match() to evaluate it - setting - the final argument TRUE causes it to stop at the end of an assertion. */ - - else - { - if (match(eptr, ecode+3, offset_top, md, ims, TRUE, NULL)) - { - ecode += 3 + (ecode[4] << 8) + ecode[5]; - while (*ecode == OP_ALT) ecode += (ecode[1] << 8) + ecode[2]; - } - else ecode += (ecode[1] << 8) + ecode[2]; - return match(eptr, ecode+3, offset_top, md, ims, FALSE, eptr); - } - /* Control never reaches here */ - - /* Skip over conditional reference data if encountered (should not be) */ - - case OP_CREF: - ecode += 2; - break; - - /* End of the pattern. If PCRE_NOTEMPTY is set, fail if we have matched - an empty string - recursion will then try other alternatives, if any. */ - - case OP_END: - if (md->notempty && eptr == md->start_match) return FALSE; - md->end_match_ptr = eptr; /* Record where we ended */ - md->end_offset_top = offset_top; /* and how many extracts were taken */ - return TRUE; - - /* Change option settings */ - - case OP_OPT: - ims = ecode[1]; - ecode += 2; - DPRINTF(("ims set to %02lx\n", ims)); - break; - - /* Assertion brackets. Check the alternative branches in turn - the - matching won't pass the KET for an assertion. If any one branch matches, - the assertion is true. Lookbehind assertions have an OP_REVERSE item at the - start of each branch to move the current point backwards, so the code at - this level is identical to the lookahead case. */ - - case OP_ASSERT: - case OP_ASSERTBACK: - do - { - if (match(eptr, ecode+3, offset_top, md, ims, FALSE, NULL)) break; - ecode += (ecode[1] << 8) + ecode[2]; - } - while (*ecode == OP_ALT); - if (*ecode == OP_KET) return FALSE; - - /* If checking an assertion for a condition, return TRUE. */ - - if (condassert) return TRUE; - - /* Continue from after the assertion, updating the offsets high water - mark, since extracts may have been taken during the assertion. */ - - do ecode += (ecode[1] << 8) + ecode[2]; while (*ecode == OP_ALT); - ecode += 3; - offset_top = md->end_offset_top; - continue; - - /* Negative assertion: all branches must fail to match */ - - case OP_ASSERT_NOT: - case OP_ASSERTBACK_NOT: - do - { - if (match(eptr, ecode+3, offset_top, md, ims, FALSE, NULL)) return FALSE; - ecode += (ecode[1] << 8) + ecode[2]; - } - while (*ecode == OP_ALT); - - if (condassert) return TRUE; - ecode += 3; - continue; - - /* Move the subject pointer back. This occurs only at the start of - each branch of a lookbehind assertion. If we are too close to the start to - move back, this match function fails. */ - - case OP_REVERSE: - eptr -= (ecode[1] << 8) + ecode[2]; - if (eptr < md->start_subject) return FALSE; - ecode += 3; - break; - - - /* "Once" brackets are like assertion brackets except that after a match, - the point in the subject string is not moved back. Thus there can never be - a move back into the brackets. Check the alternative branches in turn - the - matching won't pass the KET for this kind of subpattern. If any one branch - matches, we carry on as at the end of a normal bracket, leaving the subject - pointer. */ - - case OP_ONCE: - { - const uschar *prev = ecode; - - do - { - if (match(eptr, ecode+3, offset_top, md, ims, FALSE, eptr)) break; - ecode += (ecode[1] << 8) + ecode[2]; - } - while (*ecode == OP_ALT); - - /* If hit the end of the group (which could be repeated), fail */ - - if (*ecode != OP_ONCE && *ecode != OP_ALT) return FALSE; - - /* Continue as from after the assertion, updating the offsets high water - mark, since extracts may have been taken. */ - - do ecode += (ecode[1] << 8) + ecode[2]; while (*ecode == OP_ALT); - - offset_top = md->end_offset_top; - eptr = md->end_match_ptr; - - /* For a non-repeating ket, just continue at this level. This also - happens for a repeating ket if no characters were matched in the group. - This is the forcible breaking of infinite loops as implemented in Perl - 5.005. If there is an options reset, it will get obeyed in the normal - course of events. */ - - if (*ecode == OP_KET || eptr == eptrb) - { - ecode += 3; - break; - } - - /* The repeating kets try the rest of the pattern or restart from the - preceding bracket, in the appropriate order. We need to reset any options - that changed within the bracket before re-running it, so check the next - opcode. */ - - if (ecode[3] == OP_OPT) - { - ims = (ims & ~PCRE_IMS) | ecode[4]; - DPRINTF(("ims set to %02lx at group repeat\n", ims)); - } - - if (*ecode == OP_KETRMIN) - { - if (match(eptr, ecode+3, offset_top, md, ims, FALSE, eptr) || - match(eptr, prev, offset_top, md, ims, FALSE, eptr)) return TRUE; - } - else /* OP_KETRMAX */ - { - if (match(eptr, prev, offset_top, md, ims, FALSE, eptr) || - match(eptr, ecode+3, offset_top, md, ims, FALSE, eptr)) return TRUE; - } - } - return FALSE; - - /* An alternation is the end of a branch; scan along to find the end of the - bracketed group and go to there. */ - - case OP_ALT: - do ecode += (ecode[1] << 8) + ecode[2]; while (*ecode == OP_ALT); - break; - - /* BRAZERO and BRAMINZERO occur just before a bracket group, indicating - that it may occur zero times. It may repeat infinitely, or not at all - - i.e. it could be ()* or ()? in the pattern. Brackets with fixed upper - repeat limits are compiled as a number of copies, with the optional ones - preceded by BRAZERO or BRAMINZERO. */ - - case OP_BRAZERO: - { - const uschar *next = ecode+1; - if (match(eptr, next, offset_top, md, ims, FALSE, eptr)) return TRUE; - do next += (next[1] << 8) + next[2]; while (*next == OP_ALT); - ecode = next + 3; - } - break; - - case OP_BRAMINZERO: - { - const uschar *next = ecode+1; - do next += (next[1] << 8) + next[2]; while (*next == OP_ALT); - if (match(eptr, next+3, offset_top, md, ims, FALSE, eptr)) return TRUE; - ecode++; - } - break; - - /* End of a group, repeated or non-repeating. If we are at the end of - an assertion "group", stop matching and return TRUE, but record the - current high water mark for use by positive assertions. Do this also - for the "once" (not-backup up) groups. */ - - case OP_KET: - case OP_KETRMIN: - case OP_KETRMAX: - { - const uschar *prev = ecode - (ecode[1] << 8) - ecode[2]; - - if (*prev == OP_ASSERT || *prev == OP_ASSERT_NOT || - *prev == OP_ASSERTBACK || *prev == OP_ASSERTBACK_NOT || - *prev == OP_ONCE) - { - md->end_match_ptr = eptr; /* For ONCE */ - md->end_offset_top = offset_top; - return TRUE; - } - - /* In all other cases except a conditional group we have to check the - group number back at the start and if necessary complete handling an - extraction by setting the offsets and bumping the high water mark. */ - - if (*prev != OP_COND) - { - int number = *prev - OP_BRA; - int offset = number << 1; - - DPRINTF(("end bracket %d\n", number)); - - if (number > 0) - { - if (offset >= md->offset_max) md->offset_overflow = TRUE; else - { - md->offset_vector[offset] = - md->offset_vector[md->offset_end - number]; - md->offset_vector[offset+1] = eptr - md->start_subject; - if (offset_top <= offset) offset_top = offset + 2; - } - } - } - - /* Reset the value of the ims flags, in case they got changed during - the group. */ - - ims = original_ims; - DPRINTF(("ims reset to %02lx\n", ims)); - - /* For a non-repeating ket, just continue at this level. This also - happens for a repeating ket if no characters were matched in the group. - This is the forcible breaking of infinite loops as implemented in Perl - 5.005. If there is an options reset, it will get obeyed in the normal - course of events. */ - - if (*ecode == OP_KET || eptr == eptrb) - { - ecode += 3; - break; - } - - /* The repeating kets try the rest of the pattern or restart from the - preceding bracket, in the appropriate order. */ - - if (*ecode == OP_KETRMIN) - { - if (match(eptr, ecode+3, offset_top, md, ims, FALSE, eptr) || - match(eptr, prev, offset_top, md, ims, FALSE, eptr)) return TRUE; - } - else /* OP_KETRMAX */ - { - if (match(eptr, prev, offset_top, md, ims, FALSE, eptr) || - match(eptr, ecode+3, offset_top, md, ims, FALSE, eptr)) return TRUE; - } - } - return FALSE; - - /* Start of subject unless notbol, or after internal newline if multiline */ - - case OP_CIRC: - if (md->notbol && eptr == md->start_subject) return FALSE; - if ((ims & PCRE_MULTILINE) != 0) - { - if (eptr != md->start_subject && eptr[-1] != '\n') return FALSE; - ecode++; - break; - } - /* ... else fall through */ - - /* Start of subject assertion */ - - case OP_SOD: - if (eptr != md->start_subject) return FALSE; - ecode++; - break; - - /* Assert before internal newline if multiline, or before a terminating - newline unless endonly is set, else end of subject unless noteol is set. */ - - case OP_DOLL: - if ((ims & PCRE_MULTILINE) != 0) - { - if (eptr < md->end_subject) { if (*eptr != '\n') return FALSE; } - else { if (md->noteol) return FALSE; } - ecode++; - break; - } - else - { - if (md->noteol) return FALSE; - if (!md->endonly) - { - if (eptr < md->end_subject - 1 || - (eptr == md->end_subject - 1 && *eptr != '\n')) return FALSE; - - ecode++; - break; - } - } - /* ... else fall through */ - - /* End of subject assertion (\z) */ - - case OP_EOD: - if (eptr < md->end_subject) return FALSE; - ecode++; - break; - - /* End of subject or ending \n assertion (\Z) */ - - case OP_EODN: - if (eptr < md->end_subject - 1 || - (eptr == md->end_subject - 1 && *eptr != '\n')) return FALSE; - ecode++; - break; - - /* Word boundary assertions */ - - case OP_NOT_WORD_BOUNDARY: - case OP_WORD_BOUNDARY: - { - BOOL prev_is_word = (eptr != md->start_subject) && - ((md->ctypes[eptr[-1]] & ctype_word) != 0); - BOOL cur_is_word = (eptr < md->end_subject) && - ((md->ctypes[*eptr] & ctype_word) != 0); - if ((*ecode++ == OP_WORD_BOUNDARY)? - cur_is_word == prev_is_word : cur_is_word != prev_is_word) - return FALSE; - } - break; - - /* Match a single character type; inline for speed */ - - case OP_ANY: - if ((ims & PCRE_DOTALL) == 0 && eptr < md->end_subject && *eptr == '\n') - return FALSE; - if (eptr++ >= md->end_subject) return FALSE; - ecode++; - break; - - case OP_NOT_DIGIT: - if (eptr >= md->end_subject || - (md->ctypes[*eptr++] & ctype_digit) != 0) - return FALSE; - ecode++; - break; - - case OP_DIGIT: - if (eptr >= md->end_subject || - (md->ctypes[*eptr++] & ctype_digit) == 0) - return FALSE; - ecode++; - break; - - case OP_NOT_WHITESPACE: - if (eptr >= md->end_subject || - (md->ctypes[*eptr++] & ctype_space) != 0) - return FALSE; - ecode++; - break; - - case OP_WHITESPACE: - if (eptr >= md->end_subject || - (md->ctypes[*eptr++] & ctype_space) == 0) - return FALSE; - ecode++; - break; - - case OP_NOT_WORDCHAR: - if (eptr >= md->end_subject || - (md->ctypes[*eptr++] & ctype_word) != 0) - return FALSE; - ecode++; - break; - - case OP_WORDCHAR: - if (eptr >= md->end_subject || - (md->ctypes[*eptr++] & ctype_word) == 0) - return FALSE; - ecode++; - break; - - /* Match a back reference, possibly repeatedly. Look past the end of the - item to see if there is repeat information following. The code is similar - to that for character classes, but repeated for efficiency. Then obey - similar code to character type repeats - written out again for speed. - However, if the referenced string is the empty string, always treat - it as matched, any number of times (otherwise there could be infinite - loops). */ - - case OP_REF: - { - int length; - int offset = ecode[1] << 1; /* Doubled reference number */ - ecode += 2; /* Advance past the item */ - - /* If the reference is unset, set the length to be longer than the amount - of subject left; this ensures that every attempt at a match fails. We - can't just fail here, because of the possibility of quantifiers with zero - minima. */ - - length = (offset >= offset_top || md->offset_vector[offset] < 0)? - md->end_subject - eptr + 1 : - md->offset_vector[offset+1] - md->offset_vector[offset]; - - /* Set up for repetition, or handle the non-repeated case */ - - switch (*ecode) - { - case OP_CRSTAR: - case OP_CRMINSTAR: - case OP_CRPLUS: - case OP_CRMINPLUS: - case OP_CRQUERY: - case OP_CRMINQUERY: - c = *ecode++ - OP_CRSTAR; - minimize = (c & 1) != 0; - min = rep_min[c]; /* Pick up values from tables; */ - max = rep_max[c]; /* zero for max => infinity */ - if (max == 0) max = INT_MAX; - break; - - case OP_CRRANGE: - case OP_CRMINRANGE: - minimize = (*ecode == OP_CRMINRANGE); - min = (ecode[1] << 8) + ecode[2]; - max = (ecode[3] << 8) + ecode[4]; - if (max == 0) max = INT_MAX; - ecode += 5; - break; - - default: /* No repeat follows */ - if (!match_ref(offset, eptr, length, md, ims)) return FALSE; - eptr += length; - continue; /* With the main loop */ - } - - /* If the length of the reference is zero, just continue with the - main loop. */ - - if (length == 0) continue; - - /* First, ensure the minimum number of matches are present. We get back - the length of the reference string explicitly rather than passing the - address of eptr, so that eptr can be a register variable. */ - - for (i = 1; i <= min; i++) - { - if (!match_ref(offset, eptr, length, md, ims)) return FALSE; - eptr += length; - } - - /* If min = max, continue at the same level without recursion. - They are not both allowed to be zero. */ - - if (min == max) continue; - - /* If minimizing, keep trying and advancing the pointer */ - - if (minimize) - { - for (i = min;; i++) - { - if (match(eptr, ecode, offset_top, md, ims, FALSE, eptrb)) - return TRUE; - if (i >= max || !match_ref(offset, eptr, length, md, ims)) - return FALSE; - eptr += length; - } - /* Control never gets here */ - } - - /* If maximizing, find the longest string and work backwards */ - - else - { - const uschar *pp = eptr; - for (i = min; i < max; i++) - { - if (!match_ref(offset, eptr, length, md, ims)) break; - eptr += length; - } - while (eptr >= pp) - { - if (match(eptr, ecode, offset_top, md, ims, FALSE, eptrb)) - return TRUE; - eptr -= length; - } - return FALSE; - } - } - /* Control never gets here */ - - - - /* Match a character class, possibly repeatedly. Look past the end of the - item to see if there is repeat information following. Then obey similar - code to character type repeats - written out again for speed. */ - - case OP_CLASS: - { - const uschar *data = ecode + 1; /* Save for matching */ - ecode += 33; /* Advance past the item */ - - switch (*ecode) - { - case OP_CRSTAR: - case OP_CRMINSTAR: - case OP_CRPLUS: - case OP_CRMINPLUS: - case OP_CRQUERY: - case OP_CRMINQUERY: - c = *ecode++ - OP_CRSTAR; - minimize = (c & 1) != 0; - min = rep_min[c]; /* Pick up values from tables; */ - max = rep_max[c]; /* zero for max => infinity */ - if (max == 0) max = INT_MAX; - break; - - case OP_CRRANGE: - case OP_CRMINRANGE: - minimize = (*ecode == OP_CRMINRANGE); - min = (ecode[1] << 8) + ecode[2]; - max = (ecode[3] << 8) + ecode[4]; - if (max == 0) max = INT_MAX; - ecode += 5; - break; - - default: /* No repeat follows */ - min = max = 1; - break; - } - - /* First, ensure the minimum number of matches are present. */ - - for (i = 1; i <= min; i++) - { - if (eptr >= md->end_subject) return FALSE; - c = *eptr++; - if ((data[c/8] & (1 << (c&7))) != 0) continue; - return FALSE; - } - - /* If max == min we can continue with the main loop without the - need to recurse. */ - - if (min == max) continue; - - /* If minimizing, keep testing the rest of the expression and advancing - the pointer while it matches the class. */ - - if (minimize) - { - for (i = min;; i++) - { - if (match(eptr, ecode, offset_top, md, ims, FALSE, eptrb)) - return TRUE; - if (i >= max || eptr >= md->end_subject) return FALSE; - c = *eptr++; - if ((data[c/8] & (1 << (c&7))) != 0) continue; - return FALSE; - } - /* Control never gets here */ - } - - /* If maximizing, find the longest possible run, then work backwards. */ - - else - { - const uschar *pp = eptr; - for (i = min; i < max; eptr++, i++) - { - if (eptr >= md->end_subject) break; - c = *eptr; - if ((data[c/8] & (1 << (c&7))) != 0) continue; - break; - } - - while (eptr >= pp) - if (match(eptr--, ecode, offset_top, md, ims, FALSE, eptrb)) - return TRUE; - return FALSE; - } - } - /* Control never gets here */ - - /* Match a run of characters */ - - case OP_CHARS: - { - register int length = ecode[1]; - ecode += 2; - -#ifdef DEBUG /* Sigh. Some compilers never learn. */ - if (eptr >= md->end_subject) - printf("matching subject against pattern "); - else - { - printf("matching subject "); - pchars(eptr, length, TRUE, md); - printf(" against pattern "); - } - pchars(ecode, length, FALSE, md); - printf("\n"); -#endif - - if (length > md->end_subject - eptr) return FALSE; - if ((ims & PCRE_CASELESS) != 0) - { - while (length-- > 0) - if (md->lcc[*ecode++] != md->lcc[*eptr++]) - return FALSE; - } - else - { - while (length-- > 0) if (*ecode++ != *eptr++) return FALSE; - } - } - break; - - /* Match a single character repeatedly; different opcodes share code. */ - - case OP_EXACT: - min = max = (ecode[1] << 8) + ecode[2]; - ecode += 3; - goto REPEATCHAR; - - case OP_UPTO: - case OP_MINUPTO: - min = 0; - max = (ecode[1] << 8) + ecode[2]; - minimize = *ecode == OP_MINUPTO; - ecode += 3; - goto REPEATCHAR; - - case OP_STAR: - case OP_MINSTAR: - case OP_PLUS: - case OP_MINPLUS: - case OP_QUERY: - case OP_MINQUERY: - c = *ecode++ - OP_STAR; - minimize = (c & 1) != 0; - min = rep_min[c]; /* Pick up values from tables; */ - max = rep_max[c]; /* zero for max => infinity */ - if (max == 0) max = INT_MAX; - - /* Common code for all repeated single-character matches. We can give - up quickly if there are fewer than the minimum number of characters left in - the subject. */ - - REPEATCHAR: - if (min > md->end_subject - eptr) return FALSE; - c = *ecode++; - - /* The code is duplicated for the caseless and caseful cases, for speed, - since matching characters is likely to be quite common. First, ensure the - minimum number of matches are present. If min = max, continue at the same - level without recursing. Otherwise, if minimizing, keep trying the rest of - the expression and advancing one matching character if failing, up to the - maximum. Alternatively, if maximizing, find the maximum number of - characters and work backwards. */ - - DPRINTF(("matching %c{%d,%d} against subject %.*s\n", c, min, max, - max, eptr)); - - if ((ims & PCRE_CASELESS) != 0) - { - c = md->lcc[c]; - for (i = 1; i <= min; i++) - if (c != md->lcc[*eptr++]) return FALSE; - if (min == max) continue; - if (minimize) - { - for (i = min;; i++) - { - if (match(eptr, ecode, offset_top, md, ims, FALSE, eptrb)) - return TRUE; - if (i >= max || eptr >= md->end_subject || - c != md->lcc[*eptr++]) - return FALSE; - } - /* Control never gets here */ - } - else - { - const uschar *pp = eptr; - for (i = min; i < max; i++) - { - if (eptr >= md->end_subject || c != md->lcc[*eptr]) break; - eptr++; - } - while (eptr >= pp) - if (match(eptr--, ecode, offset_top, md, ims, FALSE, eptrb)) - return TRUE; - return FALSE; - } - /* Control never gets here */ - } - - /* Caseful comparisons */ - - else - { - for (i = 1; i <= min; i++) if (c != *eptr++) return FALSE; - if (min == max) continue; - if (minimize) - { - for (i = min;; i++) - { - if (match(eptr, ecode, offset_top, md, ims, FALSE, eptrb)) - return TRUE; - if (i >= max || eptr >= md->end_subject || c != *eptr++) return FALSE; - } - /* Control never gets here */ - } - else - { - const uschar *pp = eptr; - for (i = min; i < max; i++) - { - if (eptr >= md->end_subject || c != *eptr) break; - eptr++; - } - while (eptr >= pp) - if (match(eptr--, ecode, offset_top, md, ims, FALSE, eptrb)) - return TRUE; - return FALSE; - } - } - /* Control never gets here */ - - /* Match a negated single character */ - - case OP_NOT: - if (eptr >= md->end_subject) return FALSE; - ecode++; - if ((ims & PCRE_CASELESS) != 0) - { - if (md->lcc[*ecode++] == md->lcc[*eptr++]) return FALSE; - } - else - { - if (*ecode++ == *eptr++) return FALSE; - } - break; - - /* Match a negated single character repeatedly. This is almost a repeat of - the code for a repeated single character, but I haven't found a nice way of - commoning these up that doesn't require a test of the positive/negative - option for each character match. Maybe that wouldn't add very much to the - time taken, but character matching *is* what this is all about... */ - - case OP_NOTEXACT: - min = max = (ecode[1] << 8) + ecode[2]; - ecode += 3; - goto REPEATNOTCHAR; - - case OP_NOTUPTO: - case OP_NOTMINUPTO: - min = 0; - max = (ecode[1] << 8) + ecode[2]; - minimize = *ecode == OP_NOTMINUPTO; - ecode += 3; - goto REPEATNOTCHAR; - - case OP_NOTSTAR: - case OP_NOTMINSTAR: - case OP_NOTPLUS: - case OP_NOTMINPLUS: - case OP_NOTQUERY: - case OP_NOTMINQUERY: - c = *ecode++ - OP_NOTSTAR; - minimize = (c & 1) != 0; - min = rep_min[c]; /* Pick up values from tables; */ - max = rep_max[c]; /* zero for max => infinity */ - if (max == 0) max = INT_MAX; - - /* Common code for all repeated single-character matches. We can give - up quickly if there are fewer than the minimum number of characters left in - the subject. */ - - REPEATNOTCHAR: - if (min > md->end_subject - eptr) return FALSE; - c = *ecode++; - - /* The code is duplicated for the caseless and caseful cases, for speed, - since matching characters is likely to be quite common. First, ensure the - minimum number of matches are present. If min = max, continue at the same - level without recursing. Otherwise, if minimizing, keep trying the rest of - the expression and advancing one matching character if failing, up to the - maximum. Alternatively, if maximizing, find the maximum number of - characters and work backwards. */ - - DPRINTF(("negative matching %c{%d,%d} against subject %.*s\n", c, min, max, - max, eptr)); - - if ((ims & PCRE_CASELESS) != 0) - { - c = md->lcc[c]; - for (i = 1; i <= min; i++) - if (c == md->lcc[*eptr++]) return FALSE; - if (min == max) continue; - if (minimize) - { - for (i = min;; i++) - { - if (match(eptr, ecode, offset_top, md, ims, FALSE, eptrb)) - return TRUE; - if (i >= max || eptr >= md->end_subject || - c == md->lcc[*eptr++]) - return FALSE; - } - /* Control never gets here */ - } - else - { - const uschar *pp = eptr; - for (i = min; i < max; i++) - { - if (eptr >= md->end_subject || c == md->lcc[*eptr]) break; - eptr++; - } - while (eptr >= pp) - if (match(eptr--, ecode, offset_top, md, ims, FALSE, eptrb)) - return TRUE; - return FALSE; - } - /* Control never gets here */ - } - - /* Caseful comparisons */ - - else - { - for (i = 1; i <= min; i++) if (c == *eptr++) return FALSE; - if (min == max) continue; - if (minimize) - { - for (i = min;; i++) - { - if (match(eptr, ecode, offset_top, md, ims, FALSE, eptrb)) - return TRUE; - if (i >= max || eptr >= md->end_subject || c == *eptr++) return FALSE; - } - /* Control never gets here */ - } - else - { - const uschar *pp = eptr; - for (i = min; i < max; i++) - { - if (eptr >= md->end_subject || c == *eptr) break; - eptr++; - } - while (eptr >= pp) - if (match(eptr--, ecode, offset_top, md, ims, FALSE, eptrb)) - return TRUE; - return FALSE; - } - } - /* Control never gets here */ - - /* Match a single character type repeatedly; several different opcodes - share code. This is very similar to the code for single characters, but we - repeat it in the interests of efficiency. */ - - case OP_TYPEEXACT: - min = max = (ecode[1] << 8) + ecode[2]; - minimize = TRUE; - ecode += 3; - goto REPEATTYPE; - - case OP_TYPEUPTO: - case OP_TYPEMINUPTO: - min = 0; - max = (ecode[1] << 8) + ecode[2]; - minimize = *ecode == OP_TYPEMINUPTO; - ecode += 3; - goto REPEATTYPE; - - case OP_TYPESTAR: - case OP_TYPEMINSTAR: - case OP_TYPEPLUS: - case OP_TYPEMINPLUS: - case OP_TYPEQUERY: - case OP_TYPEMINQUERY: - c = *ecode++ - OP_TYPESTAR; - minimize = (c & 1) != 0; - min = rep_min[c]; /* Pick up values from tables; */ - max = rep_max[c]; /* zero for max => infinity */ - if (max == 0) max = INT_MAX; - - /* Common code for all repeated single character type matches */ - - REPEATTYPE: - ctype = *ecode++; /* Code for the character type */ - - /* First, ensure the minimum number of matches are present. Use inline - code for maximizing the speed, and do the type test once at the start - (i.e. keep it out of the loop). Also test that there are at least the - minimum number of characters before we start. */ - - if (min > md->end_subject - eptr) return FALSE; - if (min > 0) switch(ctype) - { - case OP_ANY: - if ((ims & PCRE_DOTALL) == 0) - { for (i = 1; i <= min; i++) if (*eptr++ == '\n') return FALSE; } - else eptr += min; - break; - - case OP_NOT_DIGIT: - for (i = 1; i <= min; i++) - if ((md->ctypes[*eptr++] & ctype_digit) != 0) return FALSE; - break; - - case OP_DIGIT: - for (i = 1; i <= min; i++) - if ((md->ctypes[*eptr++] & ctype_digit) == 0) return FALSE; - break; - - case OP_NOT_WHITESPACE: - for (i = 1; i <= min; i++) - if ((md->ctypes[*eptr++] & ctype_space) != 0) return FALSE; - break; - - case OP_WHITESPACE: - for (i = 1; i <= min; i++) - if ((md->ctypes[*eptr++] & ctype_space) == 0) return FALSE; - break; - - case OP_NOT_WORDCHAR: - for (i = 1; i <= min; i++) - if ((md->ctypes[*eptr++] & ctype_word) != 0) - return FALSE; - break; - - case OP_WORDCHAR: - for (i = 1; i <= min; i++) - if ((md->ctypes[*eptr++] & ctype_word) == 0) - return FALSE; - break; - } - - /* If min = max, continue at the same level without recursing */ - - if (min == max) continue; - - /* If minimizing, we have to test the rest of the pattern before each - subsequent match. */ - - if (minimize) - { - for (i = min;; i++) - { - if (match(eptr, ecode, offset_top, md, ims, FALSE, eptrb)) return TRUE; - if (i >= max || eptr >= md->end_subject) return FALSE; - - c = *eptr++; - switch(ctype) - { - case OP_ANY: - if ((ims & PCRE_DOTALL) == 0 && c == '\n') return FALSE; - break; - - case OP_NOT_DIGIT: - if ((md->ctypes[c] & ctype_digit) != 0) return FALSE; - break; - - case OP_DIGIT: - if ((md->ctypes[c] & ctype_digit) == 0) return FALSE; - break; - - case OP_NOT_WHITESPACE: - if ((md->ctypes[c] & ctype_space) != 0) return FALSE; - break; - - case OP_WHITESPACE: - if ((md->ctypes[c] & ctype_space) == 0) return FALSE; - break; - - case OP_NOT_WORDCHAR: - if ((md->ctypes[c] & ctype_word) != 0) return FALSE; - break; - - case OP_WORDCHAR: - if ((md->ctypes[c] & ctype_word) == 0) return FALSE; - break; - } - } - /* Control never gets here */ - } - - /* If maximizing it is worth using inline code for speed, doing the type - test once at the start (i.e. keep it out of the loop). */ - - else - { - const uschar *pp = eptr; - switch(ctype) - { - case OP_ANY: - if ((ims & PCRE_DOTALL) == 0) - { - for (i = min; i < max; i++) - { - if (eptr >= md->end_subject || *eptr == '\n') break; - eptr++; - } - } - else - { - c = max - min; - if (c > md->end_subject - eptr) c = md->end_subject - eptr; - eptr += c; - } - break; - - case OP_NOT_DIGIT: - for (i = min; i < max; i++) - { - if (eptr >= md->end_subject || (md->ctypes[*eptr] & ctype_digit) != 0) - break; - eptr++; - } - break; - - case OP_DIGIT: - for (i = min; i < max; i++) - { - if (eptr >= md->end_subject || (md->ctypes[*eptr] & ctype_digit) == 0) - break; - eptr++; - } - break; - - case OP_NOT_WHITESPACE: - for (i = min; i < max; i++) - { - if (eptr >= md->end_subject || (md->ctypes[*eptr] & ctype_space) != 0) - break; - eptr++; - } - break; - - case OP_WHITESPACE: - for (i = min; i < max; i++) - { - if (eptr >= md->end_subject || (md->ctypes[*eptr] & ctype_space) == 0) - break; - eptr++; - } - break; - - case OP_NOT_WORDCHAR: - for (i = min; i < max; i++) - { - if (eptr >= md->end_subject || (md->ctypes[*eptr] & ctype_word) != 0) - break; - eptr++; - } - break; - - case OP_WORDCHAR: - for (i = min; i < max; i++) - { - if (eptr >= md->end_subject || (md->ctypes[*eptr] & ctype_word) == 0) - break; - eptr++; - } - break; - } - - while (eptr >= pp) - if (match(eptr--, ecode, offset_top, md, ims, FALSE, eptrb)) - return TRUE; - return FALSE; - } - /* Control never gets here */ - - /* There's been some horrible disaster. */ - - default: - DPRINTF(("Unknown opcode %d\n", *ecode)); - md->errorcode = PCRE_ERROR_UNKNOWN_NODE; - return FALSE; - } - - /* Do not stick any code in here without much thought; it is assumed - that "continue" in the code above comes out to here to repeat the main - loop. */ - - } /* End of main loop */ -/* Control never reaches here */ -} - - - - -/************************************************* -* Execute a Regular Expression * -*************************************************/ - -/* This function applies a compiled re to a subject string and picks out -portions of the string if it matches. Two elements in the vector are set for -each substring: the offsets to the start and end of the substring. - -Arguments: - external_re points to the compiled expression - external_extra points to "hints" from pcre_study() or is NULL - subject points to the subject string - length length of subject string (may contain binary zeros) - start_offset where to start in the subject string - options option bits - offsets points to a vector of ints to be filled in with offsets - offsetcount the number of elements in the vector - -Returns: > 0 => success; value is the number of elements filled in - = 0 => success, but offsets is not big enough - -1 => failed to match - < -1 => some kind of unexpected problem -*/ - -int -pcre_exec(const pcre *external_re, const pcre_extra *external_extra, - const char *subject, int length, int start_offset, int options, int *offsets, - int offsetcount) -{ -int resetcount, ocount; -int first_char = -1; -int req_char = -1; -int req_char2 = -1; -unsigned long int ims = 0; -match_data match_block; -const uschar *start_bits = NULL; -const uschar *start_match = (const uschar *)subject + start_offset; -const uschar *end_subject; -const uschar *req_char_ptr = start_match - 1; -const real_pcre *re = (const real_pcre *)external_re; -const real_pcre_extra *extra = (const real_pcre_extra *)external_extra; -BOOL using_temporary_offsets = FALSE; -BOOL anchored = ((re->options | options) & PCRE_ANCHORED) != 0; -BOOL startline = (re->options & PCRE_STARTLINE) != 0; - -if ((options & ~PUBLIC_EXEC_OPTIONS) != 0) return PCRE_ERROR_BADOPTION; - -if (re == NULL || subject == NULL || - (offsets == NULL && offsetcount > 0)) return PCRE_ERROR_NULL; -if (re->magic_number != MAGIC_NUMBER) return PCRE_ERROR_BADMAGIC; - -match_block.start_subject = (const uschar *)subject; -match_block.end_subject = match_block.start_subject + length; -end_subject = match_block.end_subject; - -match_block.endonly = (re->options & PCRE_DOLLAR_ENDONLY) != 0; - -match_block.notbol = (options & PCRE_NOTBOL) != 0; -match_block.noteol = (options & PCRE_NOTEOL) != 0; -match_block.notempty = (options & PCRE_NOTEMPTY) != 0; - -match_block.errorcode = PCRE_ERROR_NOMATCH; /* Default error */ - -match_block.lcc = re->tables + lcc_offset; -match_block.ctypes = re->tables + ctypes_offset; - -/* The ims options can vary during the matching as a result of the presence -of (?ims) items in the pattern. They are kept in a local variable so that -restoring at the exit of a group is easy. */ - -ims = re->options & (PCRE_CASELESS|PCRE_MULTILINE|PCRE_DOTALL); - -/* If the expression has got more back references than the offsets supplied can -hold, we get a temporary bit of working store to use during the matching. -Otherwise, we can use the vector supplied, rounding down its size to a multiple -of 3. */ - -ocount = offsetcount - (offsetcount % 3); - -if (re->top_backref > 0 && re->top_backref >= ocount/3) - { - ocount = re->top_backref * 3 + 3; - match_block.offset_vector = (int *)(pcre_malloc)(ocount * sizeof(int)); - if (match_block.offset_vector == NULL) return PCRE_ERROR_NOMEMORY; - using_temporary_offsets = TRUE; - DPRINTF(("Got memory to hold back references\n")); - } -else match_block.offset_vector = offsets; - -match_block.offset_end = ocount; -match_block.offset_max = (2*ocount)/3; -match_block.offset_overflow = FALSE; - -/* Compute the minimum number of offsets that we need to reset each time. Doing -this makes a huge difference to execution time when there aren't many brackets -in the pattern. */ - -resetcount = 2 + re->top_bracket * 2; -if (resetcount > offsetcount) resetcount = ocount; - -/* Reset the working variable associated with each extraction. These should -never be used unless previously set, but they get saved and restored, and so we -initialize them to avoid reading uninitialized locations. */ - -if (match_block.offset_vector != NULL) - { - register int *iptr = match_block.offset_vector + ocount; - register int *iend = iptr - resetcount/2 + 1; - while (--iptr >= iend) *iptr = -1; - } - -/* Set up the first character to match, if available. The first_char value is -never set for an anchored regular expression, but the anchoring may be forced -at run time, so we have to test for anchoring. The first char may be unset for -an unanchored pattern, of course. If there's no first char and the pattern was -studied, there may be a bitmap of possible first characters. */ - -if (!anchored) - { - if ((re->options & PCRE_FIRSTSET) != 0) - { - first_char = re->first_char; - if ((ims & PCRE_CASELESS) != 0) first_char = match_block.lcc[first_char]; - } - else - if (!startline && extra != NULL && - (extra->options & PCRE_STUDY_MAPPED) != 0) - start_bits = extra->start_bits; - } - -/* For anchored or unanchored matches, there may be a "last known required -character" set. If the PCRE_CASELESS is set, implying that the match starts -caselessly, or if there are any changes of this flag within the regex, set up -both cases of the character. Otherwise set the two values the same, which will -avoid duplicate testing (which takes significant time). This covers the vast -majority of cases. It will be suboptimal when the case flag changes in a regex -and the required character in fact is caseful. */ - -if ((re->options & PCRE_REQCHSET) != 0) - { - req_char = re->req_char; - req_char2 = ((re->options & (PCRE_CASELESS | PCRE_ICHANGED)) != 0)? - (re->tables + fcc_offset)[req_char] : req_char; - } - -/* Loop for handling unanchored repeated matching attempts; for anchored regexs -the loop runs just once. */ - -do - { - int rc; - register int *iptr = match_block.offset_vector; - register int *iend = iptr + resetcount; - - /* Reset the maximum number of extractions we might see. */ - - while (iptr < iend) *iptr++ = -1; - - /* Advance to a unique first char if possible */ - - if (first_char >= 0) - { - if ((ims & PCRE_CASELESS) != 0) - while (start_match < end_subject && - match_block.lcc[*start_match] != first_char) - start_match++; - else - while (start_match < end_subject && *start_match != first_char) - start_match++; - } - - /* Or to just after \n for a multiline match if possible */ - - else if (startline) - { - if (start_match > match_block.start_subject + start_offset) - { - while (start_match < end_subject && start_match[-1] != '\n') - start_match++; - } - } - - /* Or to a non-unique first char after study */ - - else if (start_bits != NULL) - { - while (start_match < end_subject) - { - register int c = *start_match; - if ((start_bits[c/8] & (1 << (c&7))) == 0) start_match++; else break; - } - } - -#ifdef DEBUG /* Sigh. Some compilers never learn. */ - printf(">>>> Match against: "); - pchars(start_match, end_subject - start_match, TRUE, &match_block); - printf("\n"); -#endif - - /* If req_char is set, we know that that character must appear in the subject - for the match to succeed. If the first character is set, req_char must be - later in the subject; otherwise the test starts at the match point. This - optimization can save a huge amount of backtracking in patterns with nested - unlimited repeats that aren't going to match. We don't know what the state of - case matching may be when this character is hit, so test for it in both its - cases if necessary. However, the different cased versions will not be set up - unless PCRE_CASELESS was given or the casing state changes within the regex. - Writing separate code makes it go faster, as does using an autoincrement and - backing off on a match. */ - - if (req_char >= 0) - { - register const uschar *p = start_match + ((first_char >= 0)? 1 : 0); - - /* We don't need to repeat the search if we haven't yet reached the - place we found it at last time. */ - - if (p > req_char_ptr) - { - /* Do a single test if no case difference is set up */ - - if (req_char == req_char2) - { - while (p < end_subject) - { - if (*p++ == req_char) { p--; break; } - } - } - - /* Otherwise test for either case */ - - else - { - while (p < end_subject) - { - register int pp = *p++; - if (pp == req_char || pp == req_char2) { p--; break; } - } - } - - /* If we can't find the required character, break the matching loop */ - - if (p >= end_subject) break; - - /* If we have found the required character, save the point where we - found it, so that we don't search again next time round the loop if - the start hasn't passed this character yet. */ - - req_char_ptr = p; - } - } - - /* When a match occurs, substrings will be set for all internal extractions; - we just need to set up the whole thing as substring 0 before returning. If - there were too many extractions, set the return code to zero. In the case - where we had to get some local store to hold offsets for backreferences, copy - those back references that we can. In this case there need not be overflow - if certain parts of the pattern were not used. */ - - match_block.start_match = start_match; - if (!match(start_match, re->code, 2, &match_block, ims, FALSE, start_match)) - continue; - - /* Copy the offset information from temporary store if necessary */ - - if (using_temporary_offsets) - { - if (offsetcount >= 4) - { - memcpy(offsets + 2, match_block.offset_vector + 2, - (offsetcount - 2) * sizeof(int)); - DPRINTF(("Copied offsets from temporary memory\n")); - } - if (match_block.end_offset_top > offsetcount) - match_block.offset_overflow = TRUE; - - DPRINTF(("Freeing temporary memory\n")); - (pcre_free)(match_block.offset_vector); - } - - rc = match_block.offset_overflow? 0 : match_block.end_offset_top/2; - - if (match_block.offset_end < 2) rc = 0; else - { - offsets[0] = start_match - match_block.start_subject; - offsets[1] = match_block.end_match_ptr - match_block.start_subject; - } - - DPRINTF((">>>> returning %d\n", rc)); - return rc; - } - -/* This "while" is the end of the "do" above */ - -while (!anchored && - match_block.errorcode == PCRE_ERROR_NOMATCH && - start_match++ < end_subject); - -if (using_temporary_offsets) - { - DPRINTF(("Freeing temporary memory\n")); - (pcre_free)(match_block.offset_vector); - } - -DPRINTF((">>>> returning %d\n", match_block.errorcode)); - -return match_block.errorcode; -} - -/* End of pcre.c */ diff --git a/ext/pcre/pcrelib/pcre.def b/ext/pcre/pcrelib/pcre.def deleted file mode 100644 index 0e8cf3f442..0000000000 --- a/ext/pcre/pcrelib/pcre.def +++ /dev/null @@ -1,19 +0,0 @@ -EXPORTS - -pcre_malloc DATA -pcre_free DATA - -pcre_compile -pcre_copy_substring -pcre_exec -pcre_get_substring -pcre_get_substring_list -pcre_info -pcre_maketables -pcre_study -pcre_version - -regcomp -regexec -regerror -regfree diff --git a/ext/pcre/pcrelib/pcre.h b/ext/pcre/pcrelib/pcre.h deleted file mode 100644 index b7012bcbe0..0000000000 --- a/ext/pcre/pcrelib/pcre.h +++ /dev/null @@ -1,96 +0,0 @@ -/************************************************* -* Perl-Compatible Regular Expressions * -*************************************************/ - -/* Copyright (c) 1997-1999 University of Cambridge */ - -#ifndef _PCRE_H -#define _PCRE_H - -#define PCRE_MAJOR 2 -#define PCRE_MINOR 08 -#define PCRE_DATE 31-Aug-1999 - -#include "php_compat.h" - -/* Win32 uses DLL by default */ - -#ifdef _WIN32 -# ifdef STATIC -# define PCRE_DL_IMPORT -# else -# define PCRE_DL_IMPORT __declspec(dllimport) -# endif -#else -# define PCRE_DL_IMPORT -#endif - -/* Have to include stdlib.h in order to ensure that size_t is defined; -it is needed here for malloc. */ - -#include -#include - -/* Allow for C++ users */ - -#ifdef __cplusplus -extern "C" { -#endif - -/* Options */ - -#define PCRE_CASELESS 0x0001 -#define PCRE_MULTILINE 0x0002 -#define PCRE_DOTALL 0x0004 -#define PCRE_EXTENDED 0x0008 -#define PCRE_ANCHORED 0x0010 -#define PCRE_DOLLAR_ENDONLY 0x0020 -#define PCRE_EXTRA 0x0040 -#define PCRE_NOTBOL 0x0080 -#define PCRE_NOTEOL 0x0100 -#define PCRE_UNGREEDY 0x0200 -#define PCRE_NOTEMPTY 0x0400 - -/* Exec-time and get-time error codes */ - -#define PCRE_ERROR_NOMATCH (-1) -#define PCRE_ERROR_NULL (-2) -#define PCRE_ERROR_BADOPTION (-3) -#define PCRE_ERROR_BADMAGIC (-4) -#define PCRE_ERROR_UNKNOWN_NODE (-5) -#define PCRE_ERROR_NOMEMORY (-6) -#define PCRE_ERROR_NOSUBSTRING (-7) - -/* Types */ - -typedef void pcre; -typedef void pcre_extra; - -/* Store get and free functions. These can be set to alternative malloc/free -functions if required. Some magic is required for Win32 DLL; it is null on -other OS. */ - -PCRE_DL_IMPORT extern void *(*pcre_malloc)(size_t); -PCRE_DL_IMPORT extern void (*pcre_free)(void *); - -#undef PCRE_DL_IMPORT - -/* Functions */ - -extern pcre *pcre_compile(const char *, int, const char **, int *, - const unsigned char *); -extern int pcre_copy_substring(const char *, int *, int, int, char *, int); -extern int pcre_exec(const pcre *, const pcre_extra *, const char *, - int, int, int, int *, int); -extern int pcre_get_substring(const char *, int *, int, int, const char **); -extern int pcre_get_substring_list(const char *, int *, int, const char ***); -extern int pcre_info(const pcre *, int *, int *); -extern unsigned const char *pcre_maketables(void); -extern pcre_extra *pcre_study(const pcre *, int, const char **); -extern const char *pcre_version(void); - -#ifdef __cplusplus -} /* extern "C" */ -#endif - -#endif /* End of pcre.h */ diff --git a/ext/pcre/pcrelib/pcreposix.3 b/ext/pcre/pcrelib/pcreposix.3 deleted file mode 100644 index 0a40369bdd..0000000000 --- a/ext/pcre/pcrelib/pcreposix.3 +++ /dev/null @@ -1,141 +0,0 @@ -.TH PCRE 3 -.SH NAME -pcreposix - POSIX API for Perl-compatible regular expressions. -.SH SYNOPSIS -.B #include -.PP -.SM -.br -.B int regcomp(regex_t *\fIpreg\fR, const char *\fIpattern\fR, -.ti +5n -.B int \fIcflags\fR); -.PP -.br -.B int regexec(regex_t *\fIpreg\fR, const char *\fIstring\fR, -.ti +5n -.B size_t \fInmatch\fR, regmatch_t \fIpmatch\fR[], int \fIeflags\fR); -.PP -.br -.B size_t regerror(int \fIerrcode\fR, const regex_t *\fIpreg\fR, -.ti +5n -.B char *\fIerrbuf\fR, size_t \fIerrbuf_size\fR); -.PP -.br -.B void regfree(regex_t *\fIpreg\fR); - - -.SH DESCRIPTION -This set of functions provides a POSIX-style API to the PCRE regular expression -package. See the \fBpcre\fR documentation for a description of the native API, -which contains additional functionality. - -The functions described here are just wrapper functions that ultimately call -the native API. Their prototypes are defined in the \fBpcreposix.h\fR header -file, and on Unix systems the library itself is called \fBpcreposix.a\fR, so -can be accessed by adding \fB-lpcreposix\fR to the command for linking an -application which uses them. Because the POSIX functions call the native ones, -it is also necessary to add \fR-lpcre\fR. - -As I am pretty ignorant about POSIX, these functions must be considered as -experimental. I have implemented only those option bits that can be reasonably -mapped to PCRE native options. Other POSIX options are not even defined. It may -be that it is useful to define, but ignore, other options. Feedback from more -knowledgeable folk may cause this kind of detail to change. - -When PCRE is called via these functions, it is only the API that is POSIX-like -in style. The syntax and semantics of the regular expressions themselves are -still those of Perl, subject to the setting of various PCRE options, as -described below. - -The header for these functions is supplied as \fBpcreposix.h\fR to avoid any -potential clash with other POSIX libraries. It can, of course, be renamed or -aliased as \fBregex.h\fR, which is the "correct" name. It provides two -structure types, \fIregex_t\fR for compiled internal forms, and -\fIregmatch_t\fR for returning captured substrings. It also defines some -constants whose names start with "REG_"; these are used for setting options and -identifying error codes. - - -.SH COMPILING A PATTERN - -The function \fBregcomp()\fR is called to compile a pattern into an -internal form. The pattern is a C string terminated by a binary zero, and -is passed in the argument \fIpattern\fR. The \fIpreg\fR argument is a pointer -to a regex_t structure which is used as a base for storing information about -the compiled expression. - -The argument \fIcflags\fR is either zero, or contains one or more of the bits -defined by the following macros: - - REG_ICASE - -The PCRE_CASELESS option is set when the expression is passed for compilation -to the native function. - - REG_NEWLINE - -The PCRE_MULTILINE option is set when the expression is passed for compilation -to the native function. - -The yield of \fBregcomp()\fR is zero on success, and non-zero otherwise. The -\fIpreg\fR structure is filled in on success, and one member of the structure -is publicized: \fIre_nsub\fR contains the number of capturing subpatterns in -the regular expression. Various error codes are defined in the header file. - - -.SH MATCHING A PATTERN -The function \fBregexec()\fR is called to match a pre-compiled pattern -\fIpreg\fR against a given \fIstring\fR, which is terminated by a zero byte, -subject to the options in \fIeflags\fR. These can be: - - REG_NOTBOL - -The PCRE_NOTBOL option is set when calling the underlying PCRE matching -function. - - REG_NOTEOL - -The PCRE_NOTEOL option is set when calling the underlying PCRE matching -function. - -The portion of the string that was matched, and also any captured substrings, -are returned via the \fIpmatch\fR argument, which points to an array of -\fInmatch\fR structures of type \fIregmatch_t\fR, containing the members -\fIrm_so\fR and \fIrm_eo\fR. These contain the offset to the first character of -each substring and the offset to the first character after the end of each -substring, respectively. The 0th element of the vector relates to the entire -portion of \fIstring\fR that was matched; subsequent elements relate to the -capturing subpatterns of the regular expression. Unused entries in the array -have both structure members set to -1. - -A successful match yields a zero return; various error codes are defined in the -header file, of which REG_NOMATCH is the "expected" failure code. - - -.SH ERROR MESSAGES -The \fBregerror()\fR function maps a non-zero errorcode from either -\fBregcomp\fR or \fBregexec\fR to a printable message. If \fIpreg\fR is not -NULL, the error should have arisen from the use of that structure. A message -terminated by a binary zero is placed in \fIerrbuf\fR. The length of the -message, including the zero, is limited to \fIerrbuf_size\fR. The yield of the -function is the size of buffer needed to hold the whole message. - - -.SH STORAGE -Compiling a regular expression causes memory to be allocated and associated -with the \fIpreg\fR structure. The function \fBregfree()\fR frees all such -memory, after which \fIpreg\fR may no longer be used as a compiled expression. - - -.SH AUTHOR -Philip Hazel -.br -University Computing Service, -.br -New Museums Site, -.br -Cambridge CB2 3QG, England. -.br -Phone: +44 1223 334714 - -Copyright (c) 1997-1999 University of Cambridge. diff --git a/ext/pcre/pcrelib/pcreposix.3.html b/ext/pcre/pcrelib/pcreposix.3.html deleted file mode 100644 index 2c764b6776..0000000000 --- a/ext/pcre/pcrelib/pcreposix.3.html +++ /dev/null @@ -1,182 +0,0 @@ - - -pcreposix specification - - -

    pcreposix specification

    -This HTML document has been generated automatically from the original man page. -If there is any nonsense in it, please consult the man page in case the -conversion went wrong. - -
  • NAME -

    -pcreposix - POSIX API for Perl-compatible regular expressions. -

    -
  • SYNOPSIS -

    -#include <pcreposix.h> -

    -

    -int regcomp(regex_t *preg, const char *pattern, -int cflags); -

    -

    -int regexec(regex_t *preg, const char *string, -size_t nmatch, regmatch_t pmatch[], int eflags); -

    -

    -size_t regerror(int errcode, const regex_t *preg, -char *errbuf, size_t errbuf_size); -

    -

    -void regfree(regex_t *preg); -

    -
  • DESCRIPTION -

    -This set of functions provides a POSIX-style API to the PCRE regular expression -package. See the pcre documentation for a description of the native API, -which contains additional functionality. -

    -

    -The functions described here are just wrapper functions that ultimately call -the native API. Their prototypes are defined in the pcreposix.h header -file, and on Unix systems the library itself is called pcreposix.a, so -can be accessed by adding -lpcreposix to the command for linking an -application which uses them. Because the POSIX functions call the native ones, -it is also necessary to add \fR-lpcre\fR. -

    -

    -As I am pretty ignorant about POSIX, these functions must be considered as -experimental. I have implemented only those option bits that can be reasonably -mapped to PCRE native options. Other POSIX options are not even defined. It may -be that it is useful to define, but ignore, other options. Feedback from more -knowledgeable folk may cause this kind of detail to change. -

    -

    -When PCRE is called via these functions, it is only the API that is POSIX-like -in style. The syntax and semantics of the regular expressions themselves are -still those of Perl, subject to the setting of various PCRE options, as -described below. -

    -

    -The header for these functions is supplied as pcreposix.h to avoid any -potential clash with other POSIX libraries. It can, of course, be renamed or -aliased as regex.h, which is the "correct" name. It provides two -structure types, regex_t for compiled internal forms, and -regmatch_t for returning captured substrings. It also defines some -constants whose names start with "REG_"; these are used for setting options and -identifying error codes. -

    -
  • COMPILING A PATTERN -

    -The function regcomp() is called to compile a pattern into an -internal form. The pattern is a C string terminated by a binary zero, and -is passed in the argument pattern. The preg argument is a pointer -to a regex_t structure which is used as a base for storing information about -the compiled expression. -

    -

    -The argument cflags is either zero, or contains one or more of the bits -defined by the following macros: -

    -

    -

    -  REG_ICASE
-
    -

    -

    -The PCRE_CASELESS option is set when the expression is passed for compilation -to the native function. -

    -

    -

    -  REG_NEWLINE
-
    -

    -

    -The PCRE_MULTILINE option is set when the expression is passed for compilation -to the native function. -

    -

    -The yield of regcomp() is zero on success, and non-zero otherwise. The -preg structure is filled in on success, and one member of the structure -is publicized: re_nsub contains the number of capturing subpatterns in -the regular expression. Various error codes are defined in the header file. -

    -
  • MATCHING A PATTERN -

    -The function regexec() is called to match a pre-compiled pattern -preg against a given string, which is terminated by a zero byte, -subject to the options in eflags. These can be: -

    -

    -

    -  REG_NOTBOL
-
    -

    -

    -The PCRE_NOTBOL option is set when calling the underlying PCRE matching -function. -

    -

    -

    -  REG_NOTEOL
-
    -

    -

    -The PCRE_NOTEOL option is set when calling the underlying PCRE matching -function. -

    -

    -The portion of the string that was matched, and also any captured substrings, -are returned via the pmatch argument, which points to an array of -nmatch structures of type regmatch_t, containing the members -rm_so and rm_eo. These contain the offset to the first character of -each substring and the offset to the first character after the end of each -substring, respectively. The 0th element of the vector relates to the entire -portion of string that was matched; subsequent elements relate to the -capturing subpatterns of the regular expression. Unused entries in the array -have both structure members set to -1. -

    -

    -A successful match yields a zero return; various error codes are defined in the -header file, of which REG_NOMATCH is the "expected" failure code. -

    -
  • ERROR MESSAGES -

    -The regerror() function maps a non-zero errorcode from either -regcomp or regexec to a printable message. If preg is not -NULL, the error should have arisen from the use of that structure. A message -terminated by a binary zero is placed in errbuf. The length of the -message, including the zero, is limited to errbuf_size. The yield of the -function is the size of buffer needed to hold the whole message. -

    -
  • STORAGE -

    -Compiling a regular expression causes memory to be allocated and associated -with the preg structure. The function regfree() frees all such -memory, after which preg may no longer be used as a compiled expression. -

    -
  • AUTHOR -

    -Philip Hazel <ph10@cam.ac.uk> -
    -University Computing Service, -
    -New Museums Site, -
    -Cambridge CB2 3QG, England. -
    -Phone: +44 1223 334714 -

    -

    -Copyright (c) 1997-1999 University of Cambridge. diff --git a/ext/pcre/pcrelib/pcreposix.3.txt b/ext/pcre/pcrelib/pcreposix.3.txt deleted file mode 100644 index c85fb8438c..0000000000 --- a/ext/pcre/pcrelib/pcreposix.3.txt +++ /dev/null @@ -1,150 +0,0 @@ -NAME - pcreposix - POSIX API for Perl-compatible regular expres- - sions. - - - -SYNOPSIS - #include - - int regcomp(regex_t *preg, const char *pattern, - int cflags); - - int regexec(regex_t *preg, const char *string, - size_t nmatch, regmatch_t pmatch[], int eflags); - - size_t regerror(int errcode, const regex_t *preg, - char *errbuf, size_t errbuf_size); - - void regfree(regex_t *preg); - - - -DESCRIPTION - This set of functions provides a POSIX-style API to the PCRE - regular expression package. See the pcre documentation for a - description of the native API, which contains additional - functionality. - - The functions described here are just wrapper functions that - ultimately call the native API. Their prototypes are defined - in the pcreposix.h header file, and on Unix systems the - library itself is called pcreposix.a, so can be accessed by - adding -lpcreposix to the command for linking an application - which uses them. Because the POSIX functions call the native - ones, it is also necessary to add -lpcre. - - As I am pretty ignorant about POSIX, these functions must be - considered as experimental. I have implemented only those - option bits that can be reasonably mapped to PCRE native - options. Other POSIX options are not even defined. It may be - that it is useful to define, but ignore, other options. - Feedback from more knowledgeable folk may cause this kind of - detail to change. - - When PCRE is called via these functions, it is only the API - that is POSIX-like in style. The syntax and semantics of the - regular expressions themselves are still those of Perl, sub- - ject to the setting of various PCRE options, as described - below. - - The header for these functions is supplied as pcreposix.h to - avoid any potential clash with other POSIX libraries. It - can, of course, be renamed or aliased as regex.h, which is - the "correct" name. It provides two structure types, regex_t - for compiled internal forms, and regmatch_t for returning - captured substrings. It also defines some constants whose - names start with "REG_"; these are used for setting options - and identifying error codes. - - - -COMPILING A PATTERN - The function regcomp() is called to compile a pattern into - an internal form. The pattern is a C string terminated by a - binary zero, and is passed in the argument pattern. The preg - argument is a pointer to a regex_t structure which is used - as a base for storing information about the compiled expres- - sion. - - The argument cflags is either zero, or contains one or more - of the bits defined by the following macros: - - REG_ICASE - - The PCRE_CASELESS option is set when the expression is - passed for compilation to the native function. - - REG_NEWLINE - - The PCRE_MULTILINE option is set when the expression is - passed for compilation to the native function. - - The yield of regcomp() is zero on success, and non-zero oth- - erwise. The preg structure is filled in on success, and one - member of the structure is publicized: re_nsub contains the - number of capturing subpatterns in the regular expression. - Various error codes are defined in the header file. - - - -MATCHING A PATTERN - The function regexec() is called to match a pre-compiled - pattern preg against a given string, which is terminated by - a zero byte, subject to the options in eflags. These can be: - - REG_NOTBOL - - The PCRE_NOTBOL option is set when calling the underlying - PCRE matching function. - - REG_NOTEOL - - The PCRE_NOTEOL option is set when calling the underlying - PCRE matching function. - - The portion of the string that was matched, and also any - captured substrings, are returned via the pmatch argument, - which points to an array of nmatch structures of type - regmatch_t, containing the members rm_so and rm_eo. These - contain the offset to the first character of each substring - and the offset to the first character after the end of each - substring, respectively. The 0th element of the vector - relates to the entire portion of string that was matched; - subsequent elements relate to the capturing subpatterns of - the regular expression. Unused entries in the array have - both structure members set to -1. - - A successful match yields a zero return; various error codes - are defined in the header file, of which REG_NOMATCH is the - "expected" failure code. - - - -ERROR MESSAGES - The regerror() function maps a non-zero errorcode from - either regcomp or regexec to a printable message. If preg is - not NULL, the error should have arisen from the use of that - structure. A message terminated by a binary zero is placed - in errbuf. The length of the message, including the zero, is - limited to errbuf_size. The yield of the function is the - size of buffer needed to hold the whole message. - - - -STORAGE - Compiling a regular expression causes memory to be allocated - and associated with the preg structure. The function reg- - free() frees all such memory, after which preg may no longer - be used as a compiled expression. - - - -AUTHOR - Philip Hazel - University Computing Service, - New Museums Site, - Cambridge CB2 3QG, England. - Phone: +44 1223 334714 - - Copyright (c) 1997-1999 University of Cambridge. diff --git a/ext/pcre/pcrelib/pcreposix.c b/ext/pcre/pcrelib/pcreposix.c deleted file mode 100644 index 3c56d63c68..0000000000 --- a/ext/pcre/pcrelib/pcreposix.c +++ /dev/null @@ -1,250 +0,0 @@ -/************************************************* -* Perl-Compatible Regular Expressions * -*************************************************/ - -/* -This is a library of functions to support regular expressions whose syntax -and semantics are as close as possible to those of the Perl 5 language. See -the file Tech.Notes for some information on the internals. - -This module is a wrapper that provides a POSIX API to the underlying PCRE -functions. - -Written by: Philip Hazel - - Copyright (c) 1997-1999 University of Cambridge - ------------------------------------------------------------------------------ -Permission is granted to anyone to use this software for any purpose on any -computer system, and to redistribute it freely, subject to the following -restrictions: - -1. This software is distributed in the hope that it will be useful, - but WITHOUT ANY WARRANTY; without even the implied warranty of - MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. - -2. The origin of this software must not be misrepresented, either by - explicit claim or by omission. - -3. Altered versions must be plainly marked as such, and must not be - misrepresented as being the original software. - -4. If PCRE is embedded in any software that is released under the GNU - General Purpose Licence (GPL), then the terms of that licence shall - supersede any condition above with which it is incompatible. ------------------------------------------------------------------------------ -*/ - -#include "internal.h" -#include "pcreposix.h" -#include "stdlib.h" - - - -/* Corresponding tables of PCRE error messages and POSIX error codes. */ - -static const char *estring[] = { - ERR1, ERR2, ERR3, ERR4, ERR5, ERR6, ERR7, ERR8, ERR9, ERR10, - ERR11, ERR12, ERR13, ERR14, ERR15, ERR16, ERR17, ERR18, ERR19, ERR20, - ERR21, ERR22, ERR23, ERR24, ERR25 }; - -static int eint[] = { - REG_EESCAPE, /* "\\ at end of pattern" */ - REG_EESCAPE, /* "\\c at end of pattern" */ - REG_EESCAPE, /* "unrecognized character follows \\" */ - REG_BADBR, /* "numbers out of order in {} quantifier" */ - REG_BADBR, /* "number too big in {} quantifier" */ - REG_EBRACK, /* "missing terminating ] for character class" */ - REG_ECTYPE, /* "invalid escape sequence in character class" */ - REG_ERANGE, /* "range out of order in character class" */ - REG_BADRPT, /* "nothing to repeat" */ - REG_BADRPT, /* "operand of unlimited repeat could match the empty string" */ - REG_ASSERT, /* "internal error: unexpected repeat" */ - REG_BADPAT, /* "unrecognized character after (?" */ - REG_ESIZE, /* "too many capturing parenthesized sub-patterns" */ - REG_EPAREN, /* "missing )" */ - REG_ESUBREG, /* "back reference to non-existent subpattern" */ - REG_INVARG, /* "erroffset passed as NULL" */ - REG_INVARG, /* "unknown option bit(s) set" */ - REG_EPAREN, /* "missing ) after comment" */ - REG_ESIZE, /* "too many sets of parentheses" */ - REG_ESIZE, /* "regular expression too large" */ - REG_ESPACE, /* "failed to get memory" */ - REG_EPAREN, /* "unmatched brackets" */ - REG_ASSERT, /* "internal error: code overflow" */ - REG_BADPAT, /* "unrecognized character after (?<" */ - REG_BADPAT, /* "lookbehind assertion is not fixed length" */ - REG_BADPAT, /* "malformed number after (?(" */ - REG_BADPAT, /* "conditional group containe more than two branches" */ - REG_BADPAT /* "assertion expected after (?(" */ -}; - -/* Table of texts corresponding to POSIX error codes */ - -static const char *pstring[] = { - "", /* Dummy for value 0 */ - "internal error", /* REG_ASSERT */ - "invalid repeat counts in {}", /* BADBR */ - "pattern error", /* BADPAT */ - "? * + invalid", /* BADRPT */ - "unbalanced {}", /* EBRACE */ - "unbalanced []", /* EBRACK */ - "collation error - not relevant", /* ECOLLATE */ - "bad class", /* ECTYPE */ - "bad escape sequence", /* EESCAPE */ - "empty expression", /* EMPTY */ - "unbalanced ()", /* EPAREN */ - "bad range inside []", /* ERANGE */ - "expression too big", /* ESIZE */ - "failed to get memory", /* ESPACE */ - "bad back reference", /* ESUBREG */ - "bad argument", /* INVARG */ - "match failed" /* NOMATCH */ -}; - - - - -/************************************************* -* Translate PCRE text code to int * -*************************************************/ - -/* PCRE compile-time errors are given as strings defined as macros. We can just -look them up in a table to turn them into POSIX-style error codes. */ - -static int -pcre_posix_error_code(const char *s) -{ -size_t i; -for (i = 0; i < sizeof(estring)/sizeof(char *); i++) - if (strcmp(s, estring[i]) == 0) return eint[i]; -return REG_ASSERT; -} - - - -/************************************************* -* Translate error code to string * -*************************************************/ - -size_t -regerror(int errcode, const regex_t *preg, char *errbuf, size_t errbuf_size) -{ -const char *message, *addmessage; -size_t length, addlength; - -message = (errcode >= (int)(sizeof(pstring)/sizeof(char *)))? - "unknown error code" : pstring[errcode]; -length = strlen(message) + 1; - -addmessage = " at offset "; -addlength = (preg != NULL && (int)preg->re_erroffset != -1)? - strlen(addmessage) + 6 : 0; - -if (errbuf_size > 0) - { - if (addlength > 0 && errbuf_size >= length + addlength) - sprintf(errbuf, "%s%s%-6d", message, addmessage, (int)preg->re_erroffset); - else - { - strncpy(errbuf, message, errbuf_size - 1); - errbuf[errbuf_size-1] = 0; - } - } - -return length + addlength; -} - - - - -/************************************************* -* Free store held by a regex * -*************************************************/ - -void -regfree(regex_t *preg) -{ -(pcre_free)(preg->re_pcre); -} - - - - -/************************************************* -* Compile a regular expression * -*************************************************/ - -/* -Arguments: - preg points to a structure for recording the compiled expression - pattern the pattern to compile - cflags compilation flags - -Returns: 0 on success - various non-zero codes on failure -*/ - -int -regcomp(regex_t *preg, const char *pattern, int cflags) -{ -const char *errorptr; -int erroffset; -int options = 0; - -if ((cflags & REG_ICASE) != 0) options |= PCRE_CASELESS; -if ((cflags & REG_NEWLINE) != 0) options |= PCRE_MULTILINE; - -preg->re_pcre = pcre_compile(pattern, options, &errorptr, &erroffset, NULL); -preg->re_erroffset = erroffset; - -if (preg->re_pcre == NULL) return pcre_posix_error_code(errorptr); - -preg->re_nsub = pcre_info(preg->re_pcre, NULL, NULL); -return 0; -} - - - - -/************************************************* -* Match a regular expression * -*************************************************/ - -int -regexec(regex_t *preg, const char *str, size_t nmatch, - regmatch_t pmatch[], int eflags) -{ -int rc; -int options = 0; - -if ((eflags & REG_NOTBOL) != 0) options |= PCRE_NOTBOL; -if ((eflags & REG_NOTEOL) != 0) options |= PCRE_NOTEOL; - -preg->re_erroffset = (size_t)(-1); /* Only has meaning after compile */ - -rc = pcre_exec(preg->re_pcre, NULL, str, (int)strlen(str), 0, options, - (int *)pmatch, nmatch * 2); - -if (rc == 0) return 0; /* All pmatch were filled in */ - -if (rc > 0) - { - size_t i; - for (i = rc; i < nmatch; i++) pmatch[i].rm_so = pmatch[i].rm_eo = -1; - return 0; - } - -else switch(rc) - { - case PCRE_ERROR_NOMATCH: return REG_NOMATCH; - case PCRE_ERROR_NULL: return REG_INVARG; - case PCRE_ERROR_BADOPTION: return REG_INVARG; - case PCRE_ERROR_BADMAGIC: return REG_INVARG; - case PCRE_ERROR_UNKNOWN_NODE: return REG_ASSERT; - case PCRE_ERROR_NOMEMORY: return REG_ESPACE; - default: return REG_ASSERT; - } -} - -/* End of pcreposix.c */ diff --git a/ext/pcre/pcrelib/pcreposix.h b/ext/pcre/pcrelib/pcreposix.h deleted file mode 100644 index 208db354b0..0000000000 --- a/ext/pcre/pcrelib/pcreposix.h +++ /dev/null @@ -1,82 +0,0 @@ -/************************************************* -* Perl-Compatible Regular Expressions * -*************************************************/ - -/* Copyright (c) 1997-1999 University of Cambridge */ - -#ifndef _PCREPOSIX_H -#define _PCREPOSIX_H - -/* This is the header for the POSIX wrapper interface to the PCRE Perl- -Compatible Regular Expression library. It defines the things POSIX says should -be there. I hope. */ - -/* Have to include stdlib.h in order to ensure that size_t is defined. */ - -#include - -/* Allow for C++ users */ - -#ifdef __cplusplus -extern "C" { -#endif - -/* Options defined by POSIX. */ - -#define REG_ICASE 0x01 -#define REG_NEWLINE 0x02 -#define REG_NOTBOL 0x04 -#define REG_NOTEOL 0x08 - -/* Error values. Not all these are relevant or used by the wrapper. */ - -enum { - REG_ASSERT = 1, /* internal error ? */ - REG_BADBR, /* invalid repeat counts in {} */ - REG_BADPAT, /* pattern error */ - REG_BADRPT, /* ? * + invalid */ - REG_EBRACE, /* unbalanced {} */ - REG_EBRACK, /* unbalanced [] */ - REG_ECOLLATE, /* collation error - not relevant */ - REG_ECTYPE, /* bad class */ - REG_EESCAPE, /* bad escape sequence */ - REG_EMPTY, /* empty expression */ - REG_EPAREN, /* unbalanced () */ - REG_ERANGE, /* bad range inside [] */ - REG_ESIZE, /* expression too big */ - REG_ESPACE, /* failed to get memory */ - REG_ESUBREG, /* bad back reference */ - REG_INVARG, /* bad argument */ - REG_NOMATCH /* match failed */ -}; - - -/* The structure representing a compiled regular expression. */ - -typedef struct { - void *re_pcre; - size_t re_nsub; - size_t re_erroffset; -} regex_t; - -/* The structure in which a captured offset is returned. */ - -typedef int regoff_t; - -typedef struct { - regoff_t rm_so; - regoff_t rm_eo; -} regmatch_t; - -/* The functions */ - -extern int regcomp(regex_t *, const char *, int); -extern int regexec(regex_t *, const char *, size_t, regmatch_t *, int); -extern size_t regerror(int, const regex_t *, char *, size_t); -extern void regfree(regex_t *); - -#ifdef __cplusplus -} /* extern "C" */ -#endif - -#endif /* End of pcreposix.h */ diff --git a/ext/pcre/pcrelib/pcretest.c b/ext/pcre/pcrelib/pcretest.c deleted file mode 100644 index b2fe20eafc..0000000000 --- a/ext/pcre/pcrelib/pcretest.c +++ /dev/null @@ -1,1010 +0,0 @@ -/************************************************* -* PCRE testing program * -*************************************************/ - -#include -#include -#include -#include -#include -#include - -/* Use the internal info for displaying the results of pcre_study(). */ - -#include "internal.h" - -/* It is possible to compile this test program without including support for -testing the POSIX interface, though this is not available via the standard -Makefile. */ - -#if !defined NOPOSIX -#include "pcreposix.h" -#endif - -#ifndef CLOCKS_PER_SEC -#ifdef CLK_TCK -#define CLOCKS_PER_SEC CLK_TCK -#else -#define CLOCKS_PER_SEC 100 -#endif -#endif - -#define LOOPREPEAT 20000 - - -static FILE *outfile; -static int log_store = 0; - - - -/* Debugging function to print the internal form of the regex. This is the same -code as contained in pcre.c under the DEBUG macro. */ - -static const char *OP_names[] = { - "End", "\\A", "\\B", "\\b", "\\D", "\\d", - "\\S", "\\s", "\\W", "\\w", "\\Z", "\\z", - "Opt", "^", "$", "Any", "chars", "not", - "*", "*?", "+", "+?", "?", "??", "{", "{", "{", - "*", "*?", "+", "+?", "?", "??", "{", "{", "{", - "*", "*?", "+", "+?", "?", "??", "{", "{", "{", - "*", "*?", "+", "+?", "?", "??", "{", "{", - "class", "Ref", - "Alt", "Ket", "KetRmax", "KetRmin", "Assert", "Assert not", - "AssertB", "AssertB not", "Reverse", "Once", "Cond", "Cref", - "Brazero", "Braminzero", "Bra" -}; - - -static void print_internals(pcre *re) -{ -unsigned char *code = ((real_pcre *)re)->code; - -fprintf(outfile, "------------------------------------------------------------------\n"); - -for(;;) - { - int c; - int charlength; - - fprintf(outfile, "%3d ", (int)(code - ((real_pcre *)re)->code)); - - if (*code >= OP_BRA) - { - fprintf(outfile, "%3d Bra %d", (code[1] << 8) + code[2], *code - OP_BRA); - code += 2; - } - - else switch(*code) - { - case OP_END: - fprintf(outfile, " %s\n", OP_names[*code]); - fprintf(outfile, "------------------------------------------------------------------\n"); - return; - - case OP_OPT: - fprintf(outfile, " %.2x %s", code[1], OP_names[*code]); - code++; - break; - - case OP_COND: - fprintf(outfile, "%3d Cond", (code[1] << 8) + code[2]); - code += 2; - break; - - case OP_CREF: - fprintf(outfile, " %.2d %s", code[1], OP_names[*code]); - code++; - break; - - case OP_CHARS: - charlength = *(++code); - fprintf(outfile, "%3d ", charlength); - while (charlength-- > 0) - if (isprint(c = *(++code))) fprintf(outfile, "%c", c); - else fprintf(outfile, "\\x%02x", c); - break; - - case OP_KETRMAX: - case OP_KETRMIN: - case OP_ALT: - case OP_KET: - case OP_ASSERT: - case OP_ASSERT_NOT: - case OP_ASSERTBACK: - case OP_ASSERTBACK_NOT: - case OP_ONCE: - fprintf(outfile, "%3d %s", (code[1] << 8) + code[2], OP_names[*code]); - code += 2; - break; - - case OP_REVERSE: - fprintf(outfile, "%3d %s", (code[1] << 8) + code[2], OP_names[*code]); - code += 2; - break; - - case OP_STAR: - case OP_MINSTAR: - case OP_PLUS: - case OP_MINPLUS: - case OP_QUERY: - case OP_MINQUERY: - case OP_TYPESTAR: - case OP_TYPEMINSTAR: - case OP_TYPEPLUS: - case OP_TYPEMINPLUS: - case OP_TYPEQUERY: - case OP_TYPEMINQUERY: - if (*code >= OP_TYPESTAR) - fprintf(outfile, " %s", OP_names[code[1]]); - else if (isprint(c = code[1])) fprintf(outfile, " %c", c); - else fprintf(outfile, " \\x%02x", c); - fprintf(outfile, "%s", OP_names[*code++]); - break; - - case OP_EXACT: - case OP_UPTO: - case OP_MINUPTO: - if (isprint(c = code[3])) fprintf(outfile, " %c{", c); - else fprintf(outfile, " \\x%02x{", c); - if (*code != OP_EXACT) fprintf(outfile, ","); - fprintf(outfile, "%d}", (code[1] << 8) + code[2]); - if (*code == OP_MINUPTO) fprintf(outfile, "?"); - code += 3; - break; - - case OP_TYPEEXACT: - case OP_TYPEUPTO: - case OP_TYPEMINUPTO: - fprintf(outfile, " %s{", OP_names[code[3]]); - if (*code != OP_TYPEEXACT) fprintf(outfile, "0,"); - fprintf(outfile, "%d}", (code[1] << 8) + code[2]); - if (*code == OP_TYPEMINUPTO) fprintf(outfile, "?"); - code += 3; - break; - - case OP_NOT: - if (isprint(c = *(++code))) fprintf(outfile, " [^%c]", c); - else fprintf(outfile, " [^\\x%02x]", c); - break; - - case OP_NOTSTAR: - case OP_NOTMINSTAR: - case OP_NOTPLUS: - case OP_NOTMINPLUS: - case OP_NOTQUERY: - case OP_NOTMINQUERY: - if (isprint(c = code[1])) fprintf(outfile, " [^%c]", c); - else fprintf(outfile, " [^\\x%02x]", c); - fprintf(outfile, "%s", OP_names[*code++]); - break; - - case OP_NOTEXACT: - case OP_NOTUPTO: - case OP_NOTMINUPTO: - if (isprint(c = code[3])) fprintf(outfile, " [^%c]{", c); - else fprintf(outfile, " [^\\x%02x]{", c); - if (*code != OP_NOTEXACT) fprintf(outfile, ","); - fprintf(outfile, "%d}", (code[1] << 8) + code[2]); - if (*code == OP_NOTMINUPTO) fprintf(outfile, "?"); - code += 3; - break; - - case OP_REF: - fprintf(outfile, " \\%d", *(++code)); - code++; - goto CLASS_REF_REPEAT; - - case OP_CLASS: - { - int i, min, max; - code++; - fprintf(outfile, " ["); - - for (i = 0; i < 256; i++) - { - if ((code[i/8] & (1 << (i&7))) != 0) - { - int j; - for (j = i+1; j < 256; j++) - if ((code[j/8] & (1 << (j&7))) == 0) break; - if (i == '-' || i == ']') fprintf(outfile, "\\"); - if (isprint(i)) fprintf(outfile, "%c", i); else fprintf(outfile, "\\x%02x", i); - if (--j > i) - { - fprintf(outfile, "-"); - if (j == '-' || j == ']') fprintf(outfile, "\\"); - if (isprint(j)) fprintf(outfile, "%c", j); else fprintf(outfile, "\\x%02x", j); - } - i = j; - } - } - fprintf(outfile, "]"); - code += 32; - - CLASS_REF_REPEAT: - - switch(*code) - { - case OP_CRSTAR: - case OP_CRMINSTAR: - case OP_CRPLUS: - case OP_CRMINPLUS: - case OP_CRQUERY: - case OP_CRMINQUERY: - fprintf(outfile, "%s", OP_names[*code]); - break; - - case OP_CRRANGE: - case OP_CRMINRANGE: - min = (code[1] << 8) + code[2]; - max = (code[3] << 8) + code[4]; - if (max == 0) fprintf(outfile, "{%d,}", min); - else fprintf(outfile, "{%d,%d}", min, max); - if (*code == OP_CRMINRANGE) fprintf(outfile, "?"); - code += 4; - break; - - default: - code--; - } - } - break; - - /* Anything else is just a one-node item */ - - default: - fprintf(outfile, " %s", OP_names[*code]); - break; - } - - code++; - fprintf(outfile, "\n"); - } -} - - - -/* Character string printing function. */ - -static void pchars(unsigned char *p, int length) -{ -int c; -while (length-- > 0) - if (isprint(c = *(p++))) fprintf(outfile, "%c", c); - else fprintf(outfile, "\\x%02x", c); -} - - - -/* Alternative malloc function, to test functionality and show the size of the -compiled re. */ - -static void *new_malloc(size_t size) -{ -if (log_store) - fprintf(outfile, "Memory allocation (code space): %d\n", - (int)((int)size - offsetof(real_pcre, code[0]))); -return malloc(size); -} - - - -/* Read lines from named file or stdin and write to named file or stdout; lines -consist of a regular expression, in delimiters and optionally followed by -options, followed by a set of test data, terminated by an empty line. */ - -int main(int argc, char **argv) -{ -FILE *infile = stdin; -int options = 0; -int study_options = 0; -int op = 1; -int timeit = 0; -int showinfo = 0; -int showstore = 0; -int posix = 0; -int debug = 0; -int done = 0; -unsigned char buffer[30000]; -unsigned char dbuffer[1024]; - -/* Static so that new_malloc can use it. */ - -outfile = stdout; - -/* Scan options */ - -while (argc > 1 && argv[op][0] == '-') - { - if (strcmp(argv[op], "-s") == 0 || strcmp(argv[op], "-m") == 0) - showstore = 1; - else if (strcmp(argv[op], "-t") == 0) timeit = 1; - else if (strcmp(argv[op], "-i") == 0) showinfo = 1; - else if (strcmp(argv[op], "-d") == 0) showinfo = debug = 1; - else if (strcmp(argv[op], "-p") == 0) posix = 1; - else - { - printf("*** Unknown option %s\n", argv[op]); - printf("Usage: pcretest [-d] [-i] [-p] [-s] [-t] [ []]\n"); - printf(" -d debug: show compiled code; implies -i\n" - " -i show information about compiled pattern\n" - " -p use POSIX interface\n" - " -s output store information\n" - " -t time compilation and execution\n"); - return 1; - } - op++; - argc--; - } - -/* Sort out the input and output files */ - -if (argc > 1) - { - infile = fopen(argv[op], "r"); - if (infile == NULL) - { - printf("** Failed to open %s\n", argv[op]); - return 1; - } - } - -if (argc > 2) - { - outfile = fopen(argv[op+1], "w"); - if (outfile == NULL) - { - printf("** Failed to open %s\n", argv[op+1]); - return 1; - } - } - -/* Set alternative malloc function */ - -pcre_malloc = new_malloc; - -/* Heading line, then prompt for first regex if stdin */ - -fprintf(outfile, "PCRE version %s\n\n", pcre_version()); - -/* Main loop */ - -while (!done) - { - pcre *re = NULL; - pcre_extra *extra = NULL; - -#if !defined NOPOSIX /* There are still compilers that require no indent */ - regex_t preg; -#endif - - const char *error; - unsigned char *p, *pp, *ppp; - unsigned const char *tables = NULL; - int do_study = 0; - int do_debug = debug; - int do_G = 0; - int do_g = 0; - int do_showinfo = showinfo; - int do_showrest = 0; - int do_posix = 0; - int erroroffset, len, delimiter; - - if (infile == stdin) printf(" re> "); - if (fgets((char *)buffer, sizeof(buffer), infile) == NULL) break; - if (infile != stdin) fprintf(outfile, "%s", (char *)buffer); - - p = buffer; - while (isspace(*p)) p++; - if (*p == 0) continue; - - /* Get the delimiter and seek the end of the pattern; if is isn't - complete, read more. */ - - delimiter = *p++; - - if (isalnum(delimiter) || delimiter == '\\') - { - fprintf(outfile, "** Delimiter must not be alphameric or \\\n"); - goto SKIP_DATA; - } - - pp = p; - - for(;;) - { - while (*pp != 0) - { - if (*pp == '\\' && pp[1] != 0) pp++; - else if (*pp == delimiter) break; - pp++; - } - if (*pp != 0) break; - - len = sizeof(buffer) - (pp - buffer); - if (len < 256) - { - fprintf(outfile, "** Expression too long - missing delimiter?\n"); - goto SKIP_DATA; - } - - if (infile == stdin) printf(" > "); - if (fgets((char *)pp, len, infile) == NULL) - { - fprintf(outfile, "** Unexpected EOF\n"); - done = 1; - goto CONTINUE; - } - if (infile != stdin) fprintf(outfile, "%s", (char *)pp); - } - - /* If the first character after the delimiter is backslash, make - the pattern end with backslash. This is purely to provide a way - of testing for the error message when a pattern ends with backslash. */ - - if (pp[1] == '\\') *pp++ = '\\'; - - /* Terminate the pattern at the delimiter */ - - *pp++ = 0; - - /* Look for options after final delimiter */ - - options = 0; - study_options = 0; - log_store = showstore; /* default from command line */ - - while (*pp != 0) - { - switch (*pp++) - { - case 'g': do_g = 1; break; - case 'i': options |= PCRE_CASELESS; break; - case 'm': options |= PCRE_MULTILINE; break; - case 's': options |= PCRE_DOTALL; break; - case 'x': options |= PCRE_EXTENDED; break; - - case '+': do_showrest = 1; break; - case 'A': options |= PCRE_ANCHORED; break; - case 'D': do_debug = do_showinfo = 1; break; - case 'E': options |= PCRE_DOLLAR_ENDONLY; break; - case 'G': do_G = 1; break; - case 'I': do_showinfo = 1; break; - case 'M': log_store = 1; break; - -#if !defined NOPOSIX - case 'P': do_posix = 1; break; -#endif - - case 'S': do_study = 1; break; - case 'U': options |= PCRE_UNGREEDY; break; - case 'X': options |= PCRE_EXTRA; break; - - case 'L': - ppp = pp; - while (*ppp != '\n' && *ppp != ' ') ppp++; - *ppp = 0; - if (setlocale(LC_CTYPE, (const char *)pp) == NULL) - { - fprintf(outfile, "** Failed to set locale \"%s\"\n", pp); - goto SKIP_DATA; - } - tables = pcre_maketables(); - pp = ppp; - break; - - case '\n': case ' ': break; - default: - fprintf(outfile, "** Unknown option '%c'\n", pp[-1]); - goto SKIP_DATA; - } - } - - /* Handle compiling via the POSIX interface, which doesn't support the - timing, showing, or debugging options, nor the ability to pass over - local character tables. */ - -#if !defined NOPOSIX - if (posix || do_posix) - { - int rc; - int cflags = 0; - if ((options & PCRE_CASELESS) != 0) cflags |= REG_ICASE; - if ((options & PCRE_MULTILINE) != 0) cflags |= REG_NEWLINE; - rc = regcomp(&preg, (char *)p, cflags); - - /* Compilation failed; go back for another re, skipping to blank line - if non-interactive. */ - - if (rc != 0) - { - (void)regerror(rc, &preg, (char *)buffer, sizeof(buffer)); - fprintf(outfile, "Failed: POSIX code %d: %s\n", rc, buffer); - goto SKIP_DATA; - } - } - - /* Handle compiling via the native interface */ - - else -#endif /* !defined NOPOSIX */ - - { - if (timeit) - { - register int i; - clock_t time_taken; - clock_t start_time = clock(); - for (i = 0; i < LOOPREPEAT; i++) - { - re = pcre_compile((char *)p, options, &error, &erroroffset, tables); - if (re != NULL) free(re); - } - time_taken = clock() - start_time; - fprintf(outfile, "Compile time %.3f milliseconds\n", - ((double)time_taken * 1000.0) / - ((double)LOOPREPEAT * (double)CLOCKS_PER_SEC)); - } - - re = pcre_compile((char *)p, options, &error, &erroroffset, tables); - - /* Compilation failed; go back for another re, skipping to blank line - if non-interactive. */ - - if (re == NULL) - { - fprintf(outfile, "Failed: %s at offset %d\n", error, erroroffset); - SKIP_DATA: - if (infile != stdin) - { - for (;;) - { - if (fgets((char *)buffer, sizeof(buffer), infile) == NULL) - { - done = 1; - goto CONTINUE; - } - len = (int)strlen((char *)buffer); - while (len > 0 && isspace(buffer[len-1])) len--; - if (len == 0) break; - } - fprintf(outfile, "\n"); - } - goto CONTINUE; - } - - /* Compilation succeeded; print data if required */ - - if (do_showinfo) - { - int first_char, count; - - if (do_debug) print_internals(re); - - count = pcre_info(re, &options, &first_char); - if (count < 0) fprintf(outfile, - "Error %d while reading info\n", count); - else - { - fprintf(outfile, "Identifying subpattern count = %d\n", count); - if (options == 0) fprintf(outfile, "No options\n"); - else fprintf(outfile, "Options:%s%s%s%s%s%s%s%s\n", - ((options & PCRE_ANCHORED) != 0)? " anchored" : "", - ((options & PCRE_CASELESS) != 0)? " caseless" : "", - ((options & PCRE_EXTENDED) != 0)? " extended" : "", - ((options & PCRE_MULTILINE) != 0)? " multiline" : "", - ((options & PCRE_DOTALL) != 0)? " dotall" : "", - ((options & PCRE_DOLLAR_ENDONLY) != 0)? " dollar_endonly" : "", - ((options & PCRE_EXTRA) != 0)? " extra" : "", - ((options & PCRE_UNGREEDY) != 0)? " ungreedy" : ""); - - if (((((real_pcre *)re)->options) & PCRE_ICHANGED) != 0) - fprintf(outfile, "Case state changes\n"); - - if (first_char == -1) - { - fprintf(outfile, "First char at start or follows \\n\n"); - } - else if (first_char < 0) - { - fprintf(outfile, "No first char\n"); - } - else - { - if (isprint(first_char)) - fprintf(outfile, "First char = \'%c\'\n", first_char); - else - fprintf(outfile, "First char = %d\n", first_char); - } - - if (((((real_pcre *)re)->options) & PCRE_REQCHSET) != 0) - { - int req_char = ((real_pcre *)re)->req_char; - if (isprint(req_char)) - fprintf(outfile, "Req char = \'%c\'\n", req_char); - else - fprintf(outfile, "Req char = %d\n", req_char); - } - else fprintf(outfile, "No req char\n"); - } - } - - /* If /S was present, study the regexp to generate additional info to - help with the matching. */ - - if (do_study) - { - if (timeit) - { - register int i; - clock_t time_taken; - clock_t start_time = clock(); - for (i = 0; i < LOOPREPEAT; i++) - extra = pcre_study(re, study_options, &error); - time_taken = clock() - start_time; - if (extra != NULL) free(extra); - fprintf(outfile, " Study time %.3f milliseconds\n", - ((double)time_taken * 1000.0)/ - ((double)LOOPREPEAT * (double)CLOCKS_PER_SEC)); - } - - extra = pcre_study(re, study_options, &error); - if (error != NULL) - fprintf(outfile, "Failed to study: %s\n", error); - else if (extra == NULL) - fprintf(outfile, "Study returned NULL\n"); - - /* This looks at internal information. A bit kludgy to do it this - way, but it is useful for testing. */ - - else if (do_showinfo) - { - real_pcre_extra *xx = (real_pcre_extra *)extra; - if ((xx->options & PCRE_STUDY_MAPPED) == 0) - fprintf(outfile, "No starting character set\n"); - else - { - int i; - int c = 24; - fprintf(outfile, "Starting character set: "); - for (i = 0; i < 256; i++) - { - if ((xx->start_bits[i/8] & (1<<(i%8))) != 0) - { - if (c > 75) - { - fprintf(outfile, "\n "); - c = 2; - } - if (isprint(i) && i != ' ') - { - fprintf(outfile, "%c ", i); - c += 2; - } - else - { - fprintf(outfile, "\\x%02x ", i); - c += 5; - } - } - } - fprintf(outfile, "\n"); - } - } - } - } - - /* Read data lines and test them */ - - for (;;) - { - unsigned char *q; - unsigned char *bptr = dbuffer; - int count, c; - int copystrings = 0; - int getstrings = 0; - int getlist = 0; - int gmatched = 0; - int start_offset = 0; - int offsets[45]; - int size_offsets = sizeof(offsets)/sizeof(int); - - options = 0; - - if (infile == stdin) printf("data> "); - if (fgets((char *)buffer, sizeof(buffer), infile) == NULL) - { - done = 1; - goto CONTINUE; - } - if (infile != stdin) fprintf(outfile, "%s", (char *)buffer); - - len = (int)strlen((char *)buffer); - while (len > 0 && isspace(buffer[len-1])) len--; - buffer[len] = 0; - if (len == 0) break; - - p = buffer; - while (isspace(*p)) p++; - - q = dbuffer; - while ((c = *p++) != 0) - { - int i = 0; - int n = 0; - if (c == '\\') switch ((c = *p++)) - { - case 'a': c = 7; break; - case 'b': c = '\b'; break; - case 'e': c = 27; break; - case 'f': c = '\f'; break; - case 'n': c = '\n'; break; - case 'r': c = '\r'; break; - case 't': c = '\t'; break; - case 'v': c = '\v'; break; - - case '0': case '1': case '2': case '3': - case '4': case '5': case '6': case '7': - c -= '0'; - while (i++ < 2 && isdigit(*p) && *p != '8' && *p != '9') - c = c * 8 + *p++ - '0'; - break; - - case 'x': - c = 0; - while (i++ < 2 && isxdigit(*p)) - { - c = c * 16 + tolower(*p) - ((isdigit(*p))? '0' : 'W'); - p++; - } - break; - - case 0: /* Allows for an empty line */ - p--; - continue; - - case 'A': /* Option setting */ - options |= PCRE_ANCHORED; - continue; - - case 'B': - options |= PCRE_NOTBOL; - continue; - - case 'C': - while(isdigit(*p)) n = n * 10 + *p++ - '0'; - copystrings |= 1 << n; - continue; - - case 'G': - while(isdigit(*p)) n = n * 10 + *p++ - '0'; - getstrings |= 1 << n; - continue; - - case 'L': - getlist = 1; - continue; - - case 'N': - options |= PCRE_NOTEMPTY; - continue; - - case 'O': - while(isdigit(*p)) n = n * 10 + *p++ - '0'; - if (n <= (int)(sizeof(offsets)/sizeof(int))) size_offsets = n; - continue; - - case 'Z': - options |= PCRE_NOTEOL; - continue; - } - *q++ = c; - } - *q = 0; - len = q - dbuffer; - - /* Handle matching via the POSIX interface, which does not - support timing. */ - -#if !defined NOPOSIX - if (posix || do_posix) - { - int rc; - int eflags = 0; - regmatch_t pmatch[30]; - if ((options & PCRE_NOTBOL) != 0) eflags |= REG_NOTBOL; - if ((options & PCRE_NOTEOL) != 0) eflags |= REG_NOTEOL; - - rc = regexec(&preg, (const char *)bptr, - sizeof(pmatch)/sizeof(regmatch_t), pmatch, eflags); - - if (rc != 0) - { - (void)regerror(rc, &preg, (char *)buffer, sizeof(buffer)); - fprintf(outfile, "No match: POSIX code %d: %s\n", rc, buffer); - } - else - { - size_t i; - for (i = 0; i < sizeof(pmatch)/sizeof(regmatch_t); i++) - { - if (pmatch[i].rm_so >= 0) - { - fprintf(outfile, "%2d: ", (int)i); - pchars(dbuffer + pmatch[i].rm_so, - pmatch[i].rm_eo - pmatch[i].rm_so); - fprintf(outfile, "\n"); - if (i == 0 && do_showrest) - { - fprintf(outfile, " 0+ "); - pchars(dbuffer + pmatch[i].rm_eo, len - pmatch[i].rm_eo); - fprintf(outfile, "\n"); - } - } - } - } - } - - /* Handle matching via the native interface - repeats for /g and /G */ - - else -#endif /* !defined NOPOSIX */ - - for (;; gmatched++) /* Loop for /g or /G */ - { - if (timeit) - { - register int i; - clock_t time_taken; - clock_t start_time = clock(); - for (i = 0; i < LOOPREPEAT; i++) - count = pcre_exec(re, extra, (char *)bptr, len, - start_offset, options, offsets, size_offsets); - time_taken = clock() - start_time; - fprintf(outfile, "Execute time %.3f milliseconds\n", - ((double)time_taken * 1000.0)/ - ((double)LOOPREPEAT * (double)CLOCKS_PER_SEC)); - } - - count = pcre_exec(re, extra, (char *)bptr, len, - start_offset, options, offsets, size_offsets); - - if (count == 0) - { - fprintf(outfile, "Matched, but too many substrings\n"); - count = size_offsets/3; - } - - /* Matched */ - - if (count >= 0) - { - int i; - for (i = 0; i < count * 2; i += 2) - { - if (offsets[i] < 0) - fprintf(outfile, "%2d: \n", i/2); - else - { - fprintf(outfile, "%2d: ", i/2); - pchars(bptr + offsets[i], offsets[i+1] - offsets[i]); - fprintf(outfile, "\n"); - if (i == 0) - { - if (do_showrest) - { - fprintf(outfile, " 0+ "); - pchars(bptr + offsets[i+1], len - offsets[i+1]); - fprintf(outfile, "\n"); - } - } - } - } - - for (i = 0; i < 32; i++) - { - if ((copystrings & (1 << i)) != 0) - { - char copybuffer[16]; - int rc = pcre_copy_substring((char *)bptr, offsets, count, - i, copybuffer, sizeof(copybuffer)); - if (rc < 0) - fprintf(outfile, "copy substring %d failed %d\n", i, rc); - else - fprintf(outfile, "%2dC %s (%d)\n", i, copybuffer, rc); - } - } - - for (i = 0; i < 32; i++) - { - if ((getstrings & (1 << i)) != 0) - { - const char *substring; - int rc = pcre_get_substring((char *)bptr, offsets, count, - i, &substring); - if (rc < 0) - fprintf(outfile, "get substring %d failed %d\n", i, rc); - else - { - fprintf(outfile, "%2dG %s (%d)\n", i, substring, rc); - free((void *)substring); - } - } - } - - if (getlist) - { - const char **stringlist; - int rc = pcre_get_substring_list((char *)bptr, offsets, count, - &stringlist); - if (rc < 0) - fprintf(outfile, "get substring list failed %d\n", rc); - else - { - for (i = 0; i < count; i++) - fprintf(outfile, "%2dL %s\n", i, stringlist[i]); - if (stringlist[i] != NULL) - fprintf(outfile, "string list not terminated by NULL\n"); - free((void *)stringlist); - } - } - } - - /* Failed to match */ - - else - { - if (gmatched == 0) - { - if (count == -1) fprintf(outfile, "No match\n"); - else fprintf(outfile, "Error %d\n", count); - } - break; /* Out of the /g loop */ - } - - /* If not /g or /G we are done */ - - if (!do_g && !do_G) break; - - /* If we have matched an empty string, set PCRE_NOTEMPTY for the next - match. This mimics what Perl's /g option does. */ - - if (offsets[1] == offsets[0]) - options |= PCRE_NOTEMPTY; - else - options &= ~PCRE_NOTEMPTY; - - /* For /g, update the start offset, leaving the rest alone */ - - if (do_g) start_offset = offsets[1]; - - /* For /G, update the pointer and length */ - - else - { - bptr += offsets[1]; - len -= offsets[1]; - } - } /* End of loop for /g and /G */ - } /* End of loop for data lines */ - - CONTINUE: - -#if !defined NOPOSIX - if (posix || do_posix) regfree(&preg); -#endif - - if (re != NULL) free(re); - if (extra != NULL) free(extra); - if (tables != NULL) - { - free((void *)tables); - setlocale(LC_CTYPE, "C"); - } - } - -fprintf(outfile, "\n"); -return 0; -} - -/* End */ diff --git a/ext/pcre/pcrelib/perltest b/ext/pcre/pcrelib/perltest deleted file mode 100755 index c6faedafaf..0000000000 --- a/ext/pcre/pcrelib/perltest +++ /dev/null @@ -1,143 +0,0 @@ -#! /usr/bin/perl - -# Program for testing regular expressions with perl to check that PCRE handles -# them the same. - - -# Function for turning a string into a string of printing chars - -sub pchars { -my($t) = ""; - -foreach $c (split(//, @_[0])) - { - if (ord $c >= 32 && ord $c < 127) { $t .= $c; } - else { $t .= sprintf("\\x%02x", ord $c); } - } -$t; -} - - - -# Read lines from named file or stdin and write to named file or stdout; lines -# consist of a regular expression, in delimiters and optionally followed by -# options, followed by a set of test data, terminated by an empty line. - -# Sort out the input and output files - -if (@ARGV > 0) - { - open(INFILE, "<$ARGV[0]") || die "Failed to open $ARGV[0]\n"; - $infile = "INFILE"; - } -else { $infile = "STDIN"; } - -if (@ARGV > 1) - { - open(OUTFILE, ">$ARGV[1]") || die "Failed to open $ARGV[1]\n"; - $outfile = "OUTFILE"; - } -else { $outfile = "STDOUT"; } - -printf($outfile "Perl $] Regular Expressions\n\n"); - -# Main loop - -NEXT_RE: -for (;;) - { - printf " re> " if $infile eq "STDIN"; - last if ! ($_ = <$infile>); - printf $outfile "$_" if $infile ne "STDIN"; - next if ($_ eq ""); - - $pattern = $_; - - $delimiter = substr($_, 0, 1); - while ($pattern !~ /^\s*(.).*\1/s) - { - printf " > " if $infile eq "STDIN"; - last if ! ($_ = <$infile>); - printf $outfile "$_" if $infile ne "STDIN"; - $pattern .= $_; - } - - chomp($pattern); - $pattern =~ s/\s+$//; - - # Check that the pattern is valid - - eval "\$_ =~ ${pattern}"; - if ($@) - { - printf $outfile "Error: $@"; - next NEXT_RE; - } - - # Read data lines and test them - - for (;;) - { - printf "data> " if $infile eq "STDIN"; - last NEXT_RE if ! ($_ = <$infile>); - chomp; - printf $outfile "$_\n" if $infile ne "STDIN"; - - s/\s+$//; - s/^\s+//; - - last if ($_ eq ""); - - $_ = eval "\"$_\""; # To get escapes processed - - $ok = 0; - eval "if (\$_ =~ ${pattern}) {" . - "\$z = \$&;" . - "\$a = \$1;" . - "\$b = \$2;" . - "\$c = \$3;" . - "\$d = \$4;" . - "\$e = \$5;" . - "\$f = \$6;" . - "\$g = \$7;" . - "\$h = \$8;" . - "\$i = \$9;" . - "\$j = \$10;" . - "\$k = \$11;" . - "\$l = \$12;" . - "\$m = \$13;" . - "\$n = \$14;" . - "\$o = \$15;" . - "\$p = \$16;" . - "\$ok = 1; }"; - - if ($@) - { - printf $outfile "Error: $@\n"; - next NEXT_RE; - } - elsif (!$ok) - { - printf $outfile "No match\n"; - } - else - { - @subs = ($z,$a,$b,$c,$d,$e,$f,$g,$h,$i,$j,$k,$l,$m,$n,$o,$p); - $last_printed = 0; - for ($i = 0; $i <= 17; $i++) - { - if ($i == 0 || defined $subs[$i]) - { - while ($last_printed++ < $i-1) - { printf $outfile ("%2d: \n", $last_printed); } - printf $outfile ("%2d: %s\n", $i, &pchars($subs[$i])); - $last_printed = $i; - } - } - } - } - } - -printf $outfile "\n"; - -# End diff --git a/ext/pcre/pcrelib/pgrep.1 b/ext/pcre/pcrelib/pgrep.1 deleted file mode 100644 index d9e9b575e0..0000000000 --- a/ext/pcre/pcrelib/pgrep.1 +++ /dev/null @@ -1,76 +0,0 @@ -.TH PGREP 1 -.SH NAME -pgrep - a grep with Perl-compatible regular expressions. -.SH SYNOPSIS -.B pgrep [-Vchilnsvx] pattern [file] ... - - -.SH DESCRIPTION -\fBpgrep\fR searches files for character patterns, in the same way as other -grep commands do, but it uses the PCRE regular expression library to support -patterns that are compatible with the regular expressions of Perl 5. See -\fBpcre(3)\fR for a full description of syntax and semantics. - -If no files are specified, \fBpgrep\fR reads the standard input. By default, -each line that matches the pattern is copied to the standard output, and if -there is more than one file, the file name is printed before each line of -output. However, there are options that can change how \fBpgrep\fR behaves. - -Lines are limited to BUFSIZ characters. BUFSIZ is defined in \fB\fR. -The newline character is removed from the end of each line before it is matched -against the pattern. - - -.SH OPTIONS -.TP 10 -\fB-V\fR -Write the version number of the PCRE library being used to the standard error -stream. -.TP -\fB-c\fR -Do not print individual lines; instead just print a count of the number of -lines that would otherwise have been printed. If several files are given, a -count is printed for each of them. -.TP -\fB-h\fR -Suppress printing of filenames when searching multiple files. -.TP -\fB-i\fR -Ignore upper/lower case distinctions during comparisons. -.TP -\fB-l\fR -Instead of printing lines from the files, just print the names of the files -containing lines that would have been printed. Each file name is printed -once, on a separate line. -.TP -\fB-n\fR -Precede each line by its line number in the file. -.TP -\fB-s\fR -Work silently, that is, display nothing except error messages. -The exit status indicates whether any matches were found. -.TP -\fB-v\fR -Invert the sense of the match, so that lines which do \fInot\fR match the -pattern are now the ones that are found. -.TP -\fB-x\fR -Force the pattern to be anchored (it must start matching at the beginning of -the line) and in addition, require it to match the entire line. This is -equivalent to having ^ and $ characters at the start and end of each -alternative branch in the regular expression. - - -.SH SEE ALSO -\fBpcre(3)\fR, Perl 5 documentation - - -.SH DIAGNOSTICS -Exit status is 0 if any matches were found, 1 if no matches were found, and 2 -for syntax errors or inacessible files (even if matches were found). - - -.SH AUTHOR -Philip Hazel -.br -Copyright (c) 1997-1999 University of Cambridge. diff --git a/ext/pcre/pcrelib/pgrep.1.html b/ext/pcre/pcrelib/pgrep.1.html deleted file mode 100644 index 54efed6785..0000000000 --- a/ext/pcre/pcrelib/pgrep.1.html +++ /dev/null @@ -1,105 +0,0 @@ - - -pgrep specification - - -

    pgrep specification

    -This HTML document has been generated automatically from the original man page. -If there is any nonsense in it, please consult the man page in case the -conversion went wrong. - -
  • NAME -

    -pgrep - a grep with Perl-compatible regular expressions. -

    -
  • SYNOPSIS -

    -pgrep [-Vchilnsvx] pattern [file] ... -

    -
  • DESCRIPTION -

    -pgrep searches files for character patterns, in the same way as other -grep commands do, but it uses the PCRE regular expression library to support -patterns that are compatible with the regular expressions of Perl 5. See -pcre(3) for a full description of syntax and semantics. -

    -

    -If no files are specified, pgrep reads the standard input. By default, -each line that matches the pattern is copied to the standard output, and if -there is more than one file, the file name is printed before each line of -output. However, there are options that can change how pgrep behaves. -

    -

    -Lines are limited to BUFSIZ characters. BUFSIZ is defined in <stdio.h>. -The newline character is removed from the end of each line before it is matched -against the pattern. -

    -
  • OPTIONS -

    --V -Write the version number of the PCRE library being used to the standard error -stream. -

    -

    --c -Do not print individual lines; instead just print a count of the number of -lines that would otherwise have been printed. If several files are given, a -count is printed for each of them. -

    -

    --h -Suppress printing of filenames when searching multiple files. -

    -

    --i -Ignore upper/lower case distinctions during comparisons. -

    -

    --l -Instead of printing lines from the files, just print the names of the files -containing lines that would have been printed. Each file name is printed -once, on a separate line. -

    -

    --n -Precede each line by its line number in the file. -

    -

    --s -Work silently, that is, display nothing except error messages. -The exit status indicates whether any matches were found. -

    -

    --v -Invert the sense of the match, so that lines which do not match the -pattern are now the ones that are found. -

    -

    --x -Force the pattern to be anchored (it must start matching at the beginning of -the line) and in addition, require it to match the entire line. This is -equivalent to having ^ and $ characters at the start and end of each -alternative branch in the regular expression. -

    -
  • SEE ALSO -

    -pcre(3), Perl 5 documentation -

    -
  • DIAGNOSTICS -

    -Exit status is 0 if any matches were found, 1 if no matches were found, and 2 -for syntax errors or inacessible files (even if matches were found). -

    -
  • AUTHOR -

    -Philip Hazel <ph10@cam.ac.uk> -
    -Copyright (c) 1997-1999 University of Cambridge. diff --git a/ext/pcre/pcrelib/pgrep.1.txt b/ext/pcre/pcrelib/pgrep.1.txt deleted file mode 100644 index bcd08c0aab..0000000000 --- a/ext/pcre/pcrelib/pgrep.1.txt +++ /dev/null @@ -1,86 +0,0 @@ -NAME - pgrep - a grep with Perl-compatible regular expressions. - - - -SYNOPSIS - pgrep [-Vchilnsvx] pattern [file] ... - - - -DESCRIPTION - pgrep searches files for character patterns, in the same way - as other grep commands do, but it uses the PCRE regular - expression library to support patterns that are compatible - with the regular expressions of Perl 5. See pcre(3) for a - full description of syntax and semantics. - - If no files are specified, pgrep reads the standard input. - By default, each line that matches the pattern is copied to - the standard output, and if there is more than one file, the - file name is printed before each line of output. However, - there are options that can change how pgrep behaves. - - Lines are limited to BUFSIZ characters. BUFSIZ is defined in - . The newline character is removed from the end of - each line before it is matched against the pattern. - - - -OPTIONS - -V Write the version number of the PCRE library being - used to the standard error stream. - - -c Do not print individual lines; instead just print - a count of the number of lines that would other- - wise have been printed. If several files are - given, a count is printed for each of them. - - -h Suppress printing of filenames when searching mul- - tiple files. - - -i Ignore upper/lower case distinctions during com- - parisons. - - -l Instead of printing lines from the files, just - print the names of the files containing lines that - would have been printed. Each file name is printed - once, on a separate line. - - -n Precede each line by its line number in the file. - - -s Work silently, that is, display nothing except - error messages. The exit status indicates whether - any matches were found. - - -v Invert the sense of the match, so that lines which - do not match the pattern are now the ones that are - found. - - -x Force the pattern to be anchored (it must start - matching at the beginning of the line) and in - addition, require it to match the entire line. - This is equivalent to having ^ and $ characters at - the start and end of each alternative branch in - the regular expression. - - - -SEE ALSO - pcre(3), Perl 5 documentation - - - - - -DIAGNOSTICS - Exit status is 0 if any matches were found, 1 if no matches - were found, and 2 for syntax errors or inacessible files - (even if matches were found). - - - -AUTHOR - Philip Hazel - Copyright (c) 1997-1999 University of Cambridge. - diff --git a/ext/pcre/pcrelib/pgrep.c b/ext/pcre/pcrelib/pgrep.c deleted file mode 100644 index 5bc48ee84a..0000000000 --- a/ext/pcre/pcrelib/pgrep.c +++ /dev/null @@ -1,225 +0,0 @@ -/************************************************* -* PCRE grep program * -*************************************************/ - -#include -#include -#include -#include -#include "pcre.h" - - -#define FALSE 0 -#define TRUE 1 - -typedef int BOOL; - - - -/************************************************* -* Global variables * -*************************************************/ - -static pcre *pattern; -static pcre_extra *hints; - -static BOOL count_only = FALSE; -static BOOL filenames_only = FALSE; -static BOOL invert = FALSE; -static BOOL number = FALSE; -static BOOL silent = FALSE; -static BOOL whole_lines = FALSE; - - - -#ifdef STRERROR_FROM_ERRLIST -/************************************************* -* Provide strerror() for non-ANSI libraries * -*************************************************/ - -/* Some old-fashioned systems still around (e.g. SunOS4) don't have strerror() -in their libraries, but can provide the same facility by this simple -alternative function. */ - -extern int sys_nerr; -extern char *sys_errlist[]; - -char * -strerror(int n) -{ -if (n < 0 || n >= sys_nerr) return "unknown error number"; -return sys_errlist[n]; -} -#endif /* STRERROR_FROM_ERRLIST */ - - - -/************************************************* -* Grep an individual file * -*************************************************/ - -static int -pgrep(FILE *in, char *name) -{ -int rc = 1; -int linenumber = 0; -int count = 0; -int offsets[99]; -char buffer[BUFSIZ]; - -while (fgets(buffer, sizeof(buffer), in) != NULL) - { - BOOL match; - int length = (int)strlen(buffer); - if (length > 0 && buffer[length-1] == '\n') buffer[--length] = 0; - linenumber++; - - match = pcre_exec(pattern, hints, buffer, length, 0, 0, offsets, 99) >= 0; - if (match && whole_lines && offsets[1] != length) match = FALSE; - - if (match != invert) - { - if (count_only) count++; - - else if (filenames_only) - { - fprintf(stdout, "%s\n", (name == NULL)? "" : name); - return 0; - } - - else if (silent) return 0; - - else - { - if (name != NULL) fprintf(stdout, "%s:", name); - if (number) fprintf(stdout, "%d:", linenumber); - fprintf(stdout, "%s\n", buffer); - } - - rc = 0; - } - } - -if (count_only) - { - if (name != NULL) fprintf(stdout, "%s:", name); - fprintf(stdout, "%d\n", count); - } - -return rc; -} - - - - -/************************************************* -* Usage function * -*************************************************/ - -static int -usage(int rc) -{ -fprintf(stderr, "Usage: pgrep [-Vchilnsvx] pattern [file] ...\n"); -return rc; -} - - - - -/************************************************* -* Main program * -*************************************************/ - -int -main(int argc, char **argv) -{ -int i; -int rc = 1; -int options = 0; -int errptr; -const char *error; -BOOL filenames = TRUE; - -/* Process the options */ - -for (i = 1; i < argc; i++) - { - char *s; - if (argv[i][0] != '-') break; - s = argv[i] + 1; - while (*s != 0) - { - switch (*s++) - { - case 'c': count_only = TRUE; break; - case 'h': filenames = FALSE; break; - case 'i': options |= PCRE_CASELESS; break; - case 'l': filenames_only = TRUE; - case 'n': number = TRUE; break; - case 's': silent = TRUE; break; - case 'v': invert = TRUE; break; - case 'x': whole_lines = TRUE; options |= PCRE_ANCHORED; break; - - case 'V': - fprintf(stderr, "PCRE version %s\n", pcre_version()); - break; - - default: - fprintf(stderr, "pgrep: unknown option %c\n", s[-1]); - return usage(2); - } - } - } - -/* There must be at least a regexp argument */ - -if (i >= argc) return usage(0); - -/* Compile the regular expression. */ - -pattern = pcre_compile(argv[i++], options, &error, &errptr, NULL); -if (pattern == NULL) - { - fprintf(stderr, "pgrep: error in regex at offset %d: %s\n", errptr, error); - return 2; - } - -/* Study the regular expression, as we will be running it may times */ - -hints = pcre_study(pattern, 0, &error); -if (error != NULL) - { - fprintf(stderr, "pgrep: error while studing regex: %s\n", error); - return 2; - } - -/* If there are no further arguments, do the business on stdin and exit */ - -if (i >= argc) return pgrep(stdin, NULL); - -/* Otherwise, work through the remaining arguments as files. If there is only -one, don't give its name on the output. */ - -if (i == argc - 1) filenames = FALSE; -if (filenames_only) filenames = TRUE; - -for (; i < argc; i++) - { - FILE *in = fopen(argv[i], "r"); - if (in == NULL) - { - fprintf(stderr, "%s: failed to open: %s\n", argv[i], strerror(errno)); - rc = 2; - } - else - { - int frc = pgrep(in, filenames? argv[i] : NULL); - if (frc == 0 && rc == 1) rc = 0; - fclose(in); - } - } - -return rc; -} - -/* End */ diff --git a/ext/pcre/pcrelib/study.c b/ext/pcre/pcrelib/study.c deleted file mode 100644 index 284833ba04..0000000000 --- a/ext/pcre/pcrelib/study.c +++ /dev/null @@ -1,397 +0,0 @@ -/************************************************* -* Perl-Compatible Regular Expressions * -*************************************************/ - -/* -This is a library of functions to support regular expressions whose syntax -and semantics are as close as possible to those of the Perl 5 language. See -the file Tech.Notes for some information on the internals. - -Written by: Philip Hazel - - Copyright (c) 1997-1999 University of Cambridge - ------------------------------------------------------------------------------ -Permission is granted to anyone to use this software for any purpose on any -computer system, and to redistribute it freely, subject to the following -restrictions: - -1. This software is distributed in the hope that it will be useful, - but WITHOUT ANY WARRANTY; without even the implied warranty of - MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. - -2. The origin of this software must not be misrepresented, either by - explicit claim or by omission. - -3. Altered versions must be plainly marked as such, and must not be - misrepresented as being the original software. - -4. If PCRE is embedded in any software that is released under the GNU - General Purpose Licence (GPL), then the terms of that licence shall - supersede any condition above with which it is incompatible. ------------------------------------------------------------------------------ -*/ - - -/* Include the internals header, which itself includes Standard C headers plus -the external pcre header. */ - -#include "internal.h" - - - -/************************************************* -* Set a bit and maybe its alternate case * -*************************************************/ - -/* Given a character, set its bit in the table, and also the bit for the other -version of a letter if we are caseless. - -Arguments: - start_bits points to the bit map - c is the character - caseless the caseless flag - cd the block with char table pointers - -Returns: nothing -*/ - -static void -set_bit(uschar *start_bits, int c, BOOL caseless, compile_data *cd) -{ -start_bits[c/8] |= (1 << (c&7)); -if (caseless && (cd->ctypes[c] & ctype_letter) != 0) - start_bits[cd->fcc[c]/8] |= (1 << (cd->fcc[c]&7)); -} - - - -/************************************************* -* Create bitmap of starting chars * -*************************************************/ - -/* This function scans a compiled unanchored expression and attempts to build a -bitmap of the set of initial characters. If it can't, it returns FALSE. As time -goes by, we may be able to get more clever at doing this. - -Arguments: - code points to an expression - start_bits points to a 32-byte table, initialized to 0 - caseless the current state of the caseless flag - cd the block with char table pointers - -Returns: TRUE if table built, FALSE otherwise -*/ - -static BOOL -set_start_bits(const uschar *code, uschar *start_bits, BOOL caseless, - compile_data *cd) -{ -register int c; - -/* This next statement and the later reference to dummy are here in order to -trick the optimizer of the IBM C compiler for OS/2 into generating correct -code. Apparently IBM isn't going to fix the problem, and we would rather not -disable optimization (in this module it actually makes a big difference, and -the pcre module can use all the optimization it can get). */ - -volatile int dummy; - -do - { - const uschar *tcode = code + 3; - BOOL try_next = TRUE; - - while (try_next) - { - try_next = FALSE; - - /* If a branch starts with a bracket or a positive lookahead assertion, - recurse to set bits from within them. That's all for this branch. */ - - if ((int)*tcode >= OP_BRA || *tcode == OP_ASSERT) - { - if (!set_start_bits(tcode, start_bits, caseless, cd)) - return FALSE; - } - - else switch(*tcode) - { - default: - return FALSE; - - /* Skip over lookbehind and negative lookahead assertions */ - - case OP_ASSERT_NOT: - case OP_ASSERTBACK: - case OP_ASSERTBACK_NOT: - try_next = TRUE; - do tcode += (tcode[1] << 8) + tcode[2]; while (*tcode == OP_ALT); - tcode += 3; - break; - - /* Skip over an option setting, changing the caseless flag */ - - case OP_OPT: - caseless = (tcode[1] & PCRE_CASELESS) != 0; - tcode += 2; - try_next = TRUE; - break; - - /* BRAZERO does the bracket, but carries on. */ - - case OP_BRAZERO: - case OP_BRAMINZERO: - if (!set_start_bits(++tcode, start_bits, caseless, cd)) - return FALSE; - dummy = 1; - do tcode += (tcode[1] << 8) + tcode[2]; while (*tcode == OP_ALT); - tcode += 3; - try_next = TRUE; - break; - - /* Single-char * or ? sets the bit and tries the next item */ - - case OP_STAR: - case OP_MINSTAR: - case OP_QUERY: - case OP_MINQUERY: - set_bit(start_bits, tcode[1], caseless, cd); - tcode += 2; - try_next = TRUE; - break; - - /* Single-char upto sets the bit and tries the next */ - - case OP_UPTO: - case OP_MINUPTO: - set_bit(start_bits, tcode[3], caseless, cd); - tcode += 4; - try_next = TRUE; - break; - - /* At least one single char sets the bit and stops */ - - case OP_EXACT: /* Fall through */ - tcode++; - - case OP_CHARS: /* Fall through */ - tcode++; - - case OP_PLUS: - case OP_MINPLUS: - set_bit(start_bits, tcode[1], caseless, cd); - break; - - /* Single character type sets the bits and stops */ - - case OP_NOT_DIGIT: - for (c = 0; c < 32; c++) - start_bits[c] |= ~cd->cbits[c+cbit_digit]; - break; - - case OP_DIGIT: - for (c = 0; c < 32; c++) - start_bits[c] |= cd->cbits[c+cbit_digit]; - break; - - case OP_NOT_WHITESPACE: - for (c = 0; c < 32; c++) - start_bits[c] |= ~cd->cbits[c+cbit_space]; - break; - - case OP_WHITESPACE: - for (c = 0; c < 32; c++) - start_bits[c] |= cd->cbits[c+cbit_space]; - break; - - case OP_NOT_WORDCHAR: - for (c = 0; c < 32; c++) - start_bits[c] |= ~(cd->cbits[c] | cd->cbits[c+cbit_word]); - break; - - case OP_WORDCHAR: - for (c = 0; c < 32; c++) - start_bits[c] |= (cd->cbits[c] | cd->cbits[c+cbit_word]); - break; - - /* One or more character type fudges the pointer and restarts, knowing - it will hit a single character type and stop there. */ - - case OP_TYPEPLUS: - case OP_TYPEMINPLUS: - tcode++; - try_next = TRUE; - break; - - case OP_TYPEEXACT: - tcode += 3; - try_next = TRUE; - break; - - /* Zero or more repeats of character types set the bits and then - try again. */ - - case OP_TYPEUPTO: - case OP_TYPEMINUPTO: - tcode += 2; /* Fall through */ - - case OP_TYPESTAR: - case OP_TYPEMINSTAR: - case OP_TYPEQUERY: - case OP_TYPEMINQUERY: - switch(tcode[1]) - { - case OP_NOT_DIGIT: - for (c = 0; c < 32; c++) - start_bits[c] |= ~cd->cbits[c+cbit_digit]; - break; - - case OP_DIGIT: - for (c = 0; c < 32; c++) - start_bits[c] |= cd->cbits[c+cbit_digit]; - break; - - case OP_NOT_WHITESPACE: - for (c = 0; c < 32; c++) - start_bits[c] |= ~cd->cbits[c+cbit_space]; - break; - - case OP_WHITESPACE: - for (c = 0; c < 32; c++) - start_bits[c] |= cd->cbits[c+cbit_space]; - break; - - case OP_NOT_WORDCHAR: - for (c = 0; c < 32; c++) - start_bits[c] |= ~(cd->cbits[c] | cd->cbits[c+cbit_word]); - break; - - case OP_WORDCHAR: - for (c = 0; c < 32; c++) - start_bits[c] |= (cd->cbits[c] | cd->cbits[c+cbit_word]); - break; - } - - tcode += 2; - try_next = TRUE; - break; - - /* Character class: set the bits and either carry on or not, - according to the repeat count. */ - - case OP_CLASS: - { - tcode++; - for (c = 0; c < 32; c++) start_bits[c] |= tcode[c]; - tcode += 32; - switch (*tcode) - { - case OP_CRSTAR: - case OP_CRMINSTAR: - case OP_CRQUERY: - case OP_CRMINQUERY: - tcode++; - try_next = TRUE; - break; - - case OP_CRRANGE: - case OP_CRMINRANGE: - if (((tcode[1] << 8) + tcode[2]) == 0) - { - tcode += 5; - try_next = TRUE; - } - break; - } - } - break; /* End of class handling */ - - } /* End of switch */ - } /* End of try_next loop */ - - code += (code[1] << 8) + code[2]; /* Advance to next branch */ - } -while (*code == OP_ALT); -return TRUE; -} - - - -/************************************************* -* Study a compiled expression * -*************************************************/ - -/* This function is handed a compiled expression that it must study to produce -information that will speed up the matching. It returns a pcre_extra block -which then gets handed back to pcre_exec(). - -Arguments: - re points to the compiled expression - options contains option bits - errorptr points to where to place error messages; - set NULL unless error - -Returns: pointer to a pcre_extra block, - NULL on error or if no optimization possible -*/ - -pcre_extra * -pcre_study(const pcre *external_re, int options, const char **errorptr) -{ -uschar start_bits[32]; -real_pcre_extra *extra; -const real_pcre *re = (const real_pcre *)external_re; -compile_data compile_block; - -*errorptr = NULL; - -if (re == NULL || re->magic_number != MAGIC_NUMBER) - { - *errorptr = "argument is not a compiled regular expression"; - return NULL; - } - -if ((options & ~PUBLIC_STUDY_OPTIONS) != 0) - { - *errorptr = "unknown or incorrect option bit(s) set"; - return NULL; - } - -/* For an anchored pattern, or an unchored pattern that has a first char, or a -multiline pattern that matches only at "line starts", no further processing at -present. */ - -if ((re->options & (PCRE_ANCHORED|PCRE_FIRSTSET|PCRE_STARTLINE)) != 0) - return NULL; - -/* Set the character tables in the block which is passed around */ - -compile_block.lcc = re->tables + lcc_offset; -compile_block.fcc = re->tables + fcc_offset; -compile_block.cbits = re->tables + cbits_offset; -compile_block.ctypes = re->tables + ctypes_offset; - -/* See if we can find a fixed set of initial characters for the pattern. */ - -memset(start_bits, 0, 32 * sizeof(uschar)); -if (!set_start_bits(re->code, start_bits, (re->options & PCRE_CASELESS) != 0, - &compile_block)) return NULL; - -/* Get an "extra" block and put the information therein. */ - -extra = (real_pcre_extra *)(pcre_malloc)(sizeof(real_pcre_extra)); - -if (extra == NULL) - { - *errorptr = "failed to get memory"; - return NULL; - } - -extra->options = PCRE_STUDY_MAPPED; -memcpy(extra->start_bits, start_bits, sizeof(start_bits)); - -return (pcre_extra *)extra; -} - -/* End of study.c */ diff --git a/ext/pcre/pcrelib/testinput1 b/ext/pcre/pcrelib/testinput1 deleted file mode 100644 index 3adb635289..0000000000 --- a/ext/pcre/pcrelib/testinput1 +++ /dev/null @@ -1,1890 +0,0 @@ -/the quick brown fox/ - the quick brown fox - The quick brown FOX - What do you know about the quick brown fox? - What do you know about THE QUICK BROWN FOX? - -/The quick brown fox/i - the quick brown fox - The quick brown FOX - What do you know about the quick brown fox? - What do you know about THE QUICK BROWN FOX? - -/abcd\t\n\r\f\a\e\071\x3b\$\\\?caxyz/ - abcd\t\n\r\f\a\e9;\$\\?caxyz - -/a*abc?xyz+pqr{3}ab{2,}xy{4,5}pq{0,6}AB{0,}zz/ - abxyzpqrrrabbxyyyypqAzz - abxyzpqrrrabbxyyyypqAzz - aabxyzpqrrrabbxyyyypqAzz - aaabxyzpqrrrabbxyyyypqAzz - aaaabxyzpqrrrabbxyyyypqAzz - abcxyzpqrrrabbxyyyypqAzz - aabcxyzpqrrrabbxyyyypqAzz - aaabcxyzpqrrrabbxyyyypAzz - aaabcxyzpqrrrabbxyyyypqAzz - aaabcxyzpqrrrabbxyyyypqqAzz - aaabcxyzpqrrrabbxyyyypqqqAzz - aaabcxyzpqrrrabbxyyyypqqqqAzz - aaabcxyzpqrrrabbxyyyypqqqqqAzz - aaabcxyzpqrrrabbxyyyypqqqqqqAzz - aaaabcxyzpqrrrabbxyyyypqAzz - abxyzzpqrrrabbxyyyypqAzz - aabxyzzzpqrrrabbxyyyypqAzz - aaabxyzzzzpqrrrabbxyyyypqAzz - aaaabxyzzzzpqrrrabbxyyyypqAzz - abcxyzzpqrrrabbxyyyypqAzz - aabcxyzzzpqrrrabbxyyyypqAzz - aaabcxyzzzzpqrrrabbxyyyypqAzz - aaaabcxyzzzzpqrrrabbxyyyypqAzz - aaaabcxyzzzzpqrrrabbbxyyyypqAzz - aaaabcxyzzzzpqrrrabbbxyyyyypqAzz - aaabcxyzpqrrrabbxyyyypABzz - aaabcxyzpqrrrabbxyyyypABBzz - >>>aaabxyzpqrrrabbxyyyypqAzz - >aaaabxyzpqrrrabbxyyyypqAzz - >>>>abcxyzpqrrrabbxyyyypqAzz - *** Failers - abxyzpqrrabbxyyyypqAzz - abxyzpqrrrrabbxyyyypqAzz - abxyzpqrrrabxyyyypqAzz - aaaabcxyzzzzpqrrrabbbxyyyyyypqAzz - aaaabcxyzzzzpqrrrabbbxyyypqAzz - aaabcxyzpqrrrabbxyyyypqqqqqqqAzz - -/^(abc){1,2}zz/ - abczz - abcabczz - *** Failers - zz - abcabcabczz - >>abczz - -/^(b+?|a){1,2}?c/ - bc - bbc - bbbc - bac - bbac - aac - abbbbbbbbbbbc - bbbbbbbbbbbac - *** Failers - aaac - abbbbbbbbbbbac - -/^(b+|a){1,2}c/ - bc - bbc - bbbc - bac - bbac - aac - abbbbbbbbbbbc - bbbbbbbbbbbac - *** Failers - aaac - abbbbbbbbbbbac - -/^(b+|a){1,2}?bc/ - bbc - -/^(b*|ba){1,2}?bc/ - babc - bbabc - bababc - *** Failers - bababbc - babababc - -/^(ba|b*){1,2}?bc/ - babc - bbabc - bababc - *** Failers - bababbc - babababc - -/^\ca\cA\c[\c{\c:/ - \x01\x01\e;z - -/^[ab\]cde]/ - athing - bthing - ]thing - cthing - dthing - ething - *** Failers - fthing - [thing - \\thing - -/^[]cde]/ - ]thing - cthing - dthing - ething - *** Failers - athing - fthing - -/^[^ab\]cde]/ - fthing - [thing - \\thing - *** Failers - athing - bthing - ]thing - cthing - dthing - ething - -/^[^]cde]/ - athing - fthing - *** Failers - ]thing - cthing - dthing - ething - -/^\/ -  - -/^ÿ/ - ÿ - -/^[0-9]+$/ - 0 - 1 - 2 - 3 - 4 - 5 - 6 - 7 - 8 - 9 - 10 - 100 - *** Failers - abc - -/^.*nter/ - enter - inter - uponter - -/^xxx[0-9]+$/ - xxx0 - xxx1234 - *** Failers - xxx - -/^.+[0-9][0-9][0-9]$/ - x123 - xx123 - 123456 - *** Failers - 123 - x1234 - -/^.+?[0-9][0-9][0-9]$/ - x123 - xx123 - 123456 - *** Failers - 123 - x1234 - -/^([^!]+)!(.+)=apquxz\.ixr\.zzz\.ac\.uk$/ - abc!pqr=apquxz.ixr.zzz.ac.uk - *** Failers - !pqr=apquxz.ixr.zzz.ac.uk - abc!=apquxz.ixr.zzz.ac.uk - abc!pqr=apquxz:ixr.zzz.ac.uk - abc!pqr=apquxz.ixr.zzz.ac.ukk - -/:/ - Well, we need a colon: somewhere - *** Fail if we don't - -/([\da-f:]+)$/i - 0abc - abc - fed - E - :: - 5f03:12C0::932e - fed def - Any old stuff - *** Failers - 0zzz - gzzz - fed\x20 - Any old rubbish - -/^.*\.(\d{1,3})\.(\d{1,3})\.(\d{1,3})$/ - .1.2.3 - A.12.123.0 - *** Failers - .1.2.3333 - 1.2.3 - 1234.2.3 - -/^(\d+)\s+IN\s+SOA\s+(\S+)\s+(\S+)\s*\(\s*$/ - 1 IN SOA non-sp1 non-sp2( - 1 IN SOA non-sp1 non-sp2 ( - *** Failers - 1IN SOA non-sp1 non-sp2( - -/^[a-zA-Z\d][a-zA-Z\d\-]*(\.[a-zA-Z\d][a-zA-z\d\-]*)*\.$/ - a. - Z. - 2. - ab-c.pq-r. - sxk.zzz.ac.uk. - x-.y-. - *** Failers - -abc.peq. - -/^\*\.[a-z]([a-z\-\d]*[a-z\d]+)?(\.[a-z]([a-z\-\d]*[a-z\d]+)?)*$/ - *.a - *.b0-a - *.c3-b.c - *.c-a.b-c - *** Failers - *.0 - *.a- - *.a-b.c- - *.c-a.0-c - -/^(?=ab(de))(abd)(e)/ - abde - -/^(?!(ab)de|x)(abd)(f)/ - abdf - -/^(?=(ab(cd)))(ab)/ - abcd - -/^[\da-f](\.[\da-f])*$/i - a.b.c.d - A.B.C.D - a.b.c.1.2.3.C - -/^\".*\"\s*(;.*)?$/ - \"1234\" - \"abcd\" ; - \"\" ; rhubarb - *** Failers - \"1234\" : things - -/^$/ - \ - *** Failers - -/ ^ a (?# begins with a) b\sc (?# then b c) $ (?# then end)/x - ab c - *** Failers - abc - ab cde - -/(?x) ^ a (?# begins with a) b\sc (?# then b c) $ (?# then end)/ - ab c - *** Failers - abc - ab cde - -/^ a\ b[c ]d $/x - a bcd - a b d - *** Failers - abcd - ab d - -/^(a(b(c)))(d(e(f)))(h(i(j)))(k(l(m)))$/ - abcdefhijklm - -/^(?:a(b(c)))(?:d(e(f)))(?:h(i(j)))(?:k(l(m)))$/ - abcdefhijklm - -/^[\w][\W][\s][\S][\d][\D][\b][\n][\c]][\022]/ - a+ Z0+\x08\n\x1d\x12 - -/^[.^$|()*+?{,}]+/ - .^\$(*+)|{?,?} - -/^a*\w/ - z - az - aaaz - a - aa - aaaa - a+ - aa+ - -/^a*?\w/ - z - az - aaaz - a - aa - aaaa - a+ - aa+ - -/^a+\w/ - az - aaaz - aa - aaaa - aa+ - -/^a+?\w/ - az - aaaz - aa - aaaa - aa+ - -/^\d{8}\w{2,}/ - 1234567890 - 12345678ab - 12345678__ - *** Failers - 1234567 - -/^[aeiou\d]{4,5}$/ - uoie - 1234 - 12345 - aaaaa - *** Failers - 123456 - -/^[aeiou\d]{4,5}?/ - uoie - 1234 - 12345 - aaaaa - 123456 - -/\A(abc|def)=(\1){2,3}\Z/ - abc=abcabc - def=defdefdef - *** Failers - abc=defdef - -/^(a)(b)(c)(d)(e)(f)(g)(h)(i)(j)(k)\11*(\3\4)\1(?#)2$/ - abcdefghijkcda2 - abcdefghijkkkkcda2 - -/(cat(a(ract|tonic)|erpillar)) \1()2(3)/ - cataract cataract23 - catatonic catatonic23 - caterpillar caterpillar23 - - -/^From +([^ ]+) +[a-zA-Z][a-zA-Z][a-zA-Z] +[a-zA-Z][a-zA-Z][a-zA-Z] +[0-9]?[0-9] +[0-9][0-9]:[0-9][0-9]/ - From abcd Mon Sep 01 12:33:02 1997 - -/^From\s+\S+\s+([a-zA-Z]{3}\s+){2}\d{1,2}\s+\d\d:\d\d/ - From abcd Mon Sep 01 12:33:02 1997 - From abcd Mon Sep 1 12:33:02 1997 - *** Failers - From abcd Sep 01 12:33:02 1997 - -/^12.34/s - 12\n34 - 12\r34 - -/\w+(?=\t)/ - the quick brown\t fox - -/foo(?!bar)(.*)/ - foobar is foolish see? - -/(?:(?!foo)...|^.{0,2})bar(.*)/ - foobar crowbar etc - barrel - 2barrel - A barrel - -/^(\D*)(?=\d)(?!123)/ - abc456 - *** Failers - abc123 - -/^1234(?# test newlines - inside)/ - 1234 - -/^1234 #comment in extended re - /x - 1234 - -/#rhubarb - abcd/x - abcd - -/^abcd#rhubarb/x - abcd - -/^(a)\1{2,3}(.)/ - aaab - aaaab - aaaaab - aaaaaab - -/(?!^)abc/ - the abc - *** Failers - abc - -/(?=^)abc/ - abc - *** Failers - the abc - -/^[ab]{1,3}(ab*|b)/ - aabbbbb - -/^[ab]{1,3}?(ab*|b)/ - aabbbbb - -/^[ab]{1,3}?(ab*?|b)/ - aabbbbb - -/^[ab]{1,3}(ab*?|b)/ - aabbbbb - -/ (?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* # optional leading comment -(?: (?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| -" (?: # opening quote... -[^\\\x80-\xff\n\015"] # Anything except backslash and quote -| # or -\\ [^\x80-\xff] # Escaped something (something != CR) -)* " # closing quote -) # initial word -(?: (?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* \. (?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* (?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| -" (?: # opening quote... -[^\\\x80-\xff\n\015"] # Anything except backslash and quote -| # or -\\ [^\x80-\xff] # Escaped something (something != CR) -)* " # closing quote -) )* # further okay, if led by a period -(?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* @ (?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* (?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| \[ # [ -(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff -\] # ] -) # initial subdomain -(?: # -(?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* \. # if led by a period... -(?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* (?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| \[ # [ -(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff -\] # ] -) # ...further okay -)* -# address -| # or -(?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| -" (?: # opening quote... -[^\\\x80-\xff\n\015"] # Anything except backslash and quote -| # or -\\ [^\x80-\xff] # Escaped something (something != CR) -)* " # closing quote -) # one word, optionally followed by.... -(?: -[^()<>@,;:".\\\[\]\x80-\xff\000-\010\012-\037] | # atom and space parts, or... -\( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) | # comments, or... - -" (?: # opening quote... -[^\\\x80-\xff\n\015"] # Anything except backslash and quote -| # or -\\ [^\x80-\xff] # Escaped something (something != CR) -)* " # closing quote -# quoted strings -)* -< (?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* # leading < -(?: @ (?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* (?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| \[ # [ -(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff -\] # ] -) # initial subdomain -(?: # -(?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* \. # if led by a period... -(?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* (?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| \[ # [ -(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff -\] # ] -) # ...further okay -)* - -(?: (?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* , (?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* @ (?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* (?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| \[ # [ -(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff -\] # ] -) # initial subdomain -(?: # -(?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* \. # if led by a period... -(?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* (?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| \[ # [ -(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff -\] # ] -) # ...further okay -)* -)* # further okay, if led by comma -: # closing colon -(?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* )? # optional route -(?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| -" (?: # opening quote... -[^\\\x80-\xff\n\015"] # Anything except backslash and quote -| # or -\\ [^\x80-\xff] # Escaped something (something != CR) -)* " # closing quote -) # initial word -(?: (?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* \. (?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* (?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| -" (?: # opening quote... -[^\\\x80-\xff\n\015"] # Anything except backslash and quote -| # or -\\ [^\x80-\xff] # Escaped something (something != CR) -)* " # closing quote -) )* # further okay, if led by a period -(?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* @ (?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* (?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| \[ # [ -(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff -\] # ] -) # initial subdomain -(?: # -(?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* \. # if led by a period... -(?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* (?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| \[ # [ -(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff -\] # ] -) # ...further okay -)* -# address spec -(?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* > # trailing > -# name and address -) (?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* # optional trailing comment -/x - Alan Other - - user\@dom.ain - \"A. Other\" (a comment) - A. Other (a comment) - \"/s=user/ou=host/o=place/prmd=uu.yy/admd= /c=gb/\"\@x400-re.lay - A missing angle @,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -# Atom -| # or -" # " -[^\\\x80-\xff\n\015"] * # normal -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015"] * )* # ( special normal* )* -" # " -# Quoted string -) -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -(?: -\. -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -(?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -# Atom -| # or -" # " -[^\\\x80-\xff\n\015"] * # normal -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015"] * )* # ( special normal* )* -" # " -# Quoted string -) -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -# additional words -)* -@ -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -(?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| -\[ # [ -(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff -\] # ] -) -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -# optional trailing comments -(?: -\. -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -(?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| -\[ # [ -(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff -\] # ] -) -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -# optional trailing comments -)* -# address -| # or -(?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -# Atom -| # or -" # " -[^\\\x80-\xff\n\015"] * # normal -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015"] * )* # ( special normal* )* -" # " -# Quoted string -) -# leading word -[^()<>@,;:".\\\[\]\x80-\xff\000-\010\012-\037] * # "normal" atoms and or spaces -(?: -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -| -" # " -[^\\\x80-\xff\n\015"] * # normal -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015"] * )* # ( special normal* )* -" # " -) # "special" comment or quoted string -[^()<>@,;:".\\\[\]\x80-\xff\000-\010\012-\037] * # more "normal" -)* -< -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -# < -(?: -@ -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -(?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| -\[ # [ -(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff -\] # ] -) -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -# optional trailing comments -(?: -\. -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -(?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| -\[ # [ -(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff -\] # ] -) -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -# optional trailing comments -)* -(?: , -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -@ -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -(?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| -\[ # [ -(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff -\] # ] -) -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -# optional trailing comments -(?: -\. -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -(?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| -\[ # [ -(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff -\] # ] -) -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -# optional trailing comments -)* -)* # additional domains -: -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -# optional trailing comments -)? # optional route -(?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -# Atom -| # or -" # " -[^\\\x80-\xff\n\015"] * # normal -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015"] * )* # ( special normal* )* -" # " -# Quoted string -) -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -(?: -\. -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -(?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -# Atom -| # or -" # " -[^\\\x80-\xff\n\015"] * # normal -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015"] * )* # ( special normal* )* -" # " -# Quoted string -) -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -# additional words -)* -@ -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -(?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| -\[ # [ -(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff -\] # ] -) -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -# optional trailing comments -(?: -\. -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -(?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| -\[ # [ -(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff -\] # ] -) -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -# optional trailing comments -)* -# address spec -> # > -# name and address -) -/x - Alan Other - - user\@dom.ain - \"A. Other\" (a comment) - A. Other (a comment) - \"/s=user/ou=host/o=place/prmd=uu.yy/admd= /c=gb/\"\@x400-re.lay - A missing angle / - abcghinop - -/<.*?>/ - abcghinop - -/<.*>/U - abcghinop - -/<.*>(?U)/ - abcghinop - -/<.*?>/U - abcghinop - -/={3,}/U - abc========def - -/(?U)={3,}?/ - abc========def - -/(?^abc)/m - abc - def\nabc - *** Failers - defabc - -/(?<=ab(c+)d)ef/ - -/(?<=ab(?<=c+)d)ef/ - -/(?<=ab(c|de)f)g/ - -/The next three are in testinput2 because they have variable length branches/ - -/(?<=bullock|donkey)-cart/ - the bullock-cart - a donkey-cart race - *** Failers - cart - horse-and-cart - -/(?<=ab(?i)x|y|z)/ - -/(?>.*)(?<=(abcd)|(xyz))/ - alphabetabcd - endingxyz - -/(?<=ab(?i)x(?-i)y|(?i)z|b)ZZ/ - abxyZZ - abXyZZ - ZZZ - zZZ - bZZ - BZZ - *** Failers - ZZ - abXYZZ - zzz - bzz - -/(?.*/)foo" - /this/is/a/very/long/line/in/deed/with/very/many/slashes/in/it/you/see/ - -"(?>.*/)foo" - /this/is/a/very/long/line/in/deed/with/very/many/slashes/in/and/foo - -/(?>(\.\d\d[1-9]?))\d+/ - 1.230003938 - 1.875000282 - *** Failers - 1.235 - -/^((?>\w+)|(?>\s+))*$/ - now is the time for all good men to come to the aid of the party - *** Failers - this is not a line with only words and spaces! - -/(\d+)(\w)/ - 12345a - 12345+ - -/((?>\d+))(\w)/ - 12345a - *** Failers - 12345+ - -/(?>a+)b/ - aaab - -/((?>a+)b)/ - aaab - -/(?>(a+))b/ - aaab - -/(?>b)+/ - aaabbbccc - -/(?>a+|b+|c+)*c/ - aaabbbbccccd - -/((?>[^()]+)|\([^()]*\))+/ - ((abc(ade)ufh()()x - -/\(((?>[^()]+)|\([^()]+\))+\)/ - (abc) - (abc(def)xyz) - *** Failers - ((()aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa - -/a(?-i)b/i - ab - *** Failers - Ab - aB - AB - -/(a (?x)b c)d e/ - a bcd e - *** Failers - a b cd e - abcd e - a bcde - -/(a b(?x)c d (?-x)e f)/ - a bcde f - *** Failers - abcdef - -/(a(?i)b)c/ - abc - aBc - *** Failers - abC - aBC - Abc - ABc - ABC - AbC - -/a(?i:b)c/ - abc - aBc - *** Failers - ABC - abC - aBC - -/a(?i:b)*c/ - aBc - aBBc - *** Failers - aBC - aBBC - -/a(?=b(?i)c)\w\wd/ - abcd - abCd - *** Failers - aBCd - abcD - -/(?s-i:more.*than).*million/i - more than million - more than MILLION - more \n than Million - *** Failers - MORE THAN MILLION - more \n than \n million - -/(?:(?s-i)more.*than).*million/i - more than million - more than MILLION - more \n than Million - *** Failers - MORE THAN MILLION - more \n than \n million - -/(?>a(?i)b+)+c/ - abc - aBbc - aBBc - *** Failers - Abc - abAb - abbC - -/(?=a(?i)b)\w\wc/ - abc - aBc - *** Failers - Ab - abC - aBC - -/(?<=a(?i)b)(\w\w)c/ - abxxc - aBxxc - *** Failers - Abxxc - ABxxc - abxxC - -/(?:(a)|b)(?(1)A|B)/ - aA - bB - *** Failers - aB - bA - -/^(a)?(?(1)a|b)+$/ - aa - b - bb - *** Failers - ab - -/^(?(?=abc)\w{3}:|\d\d)$/ - abc: - 12 - *** Failers - 123 - xyz - -/^(?(?!abc)\d\d|\w{3}:)$/ - abc: - 12 - *** Failers - 123 - xyz - -/(?(?<=foo)bar|cat)/ - foobar - cat - fcat - focat - *** Failers - foocat - -/(?(?a*)*/ - a - aa - aaaa - -/(abc|)+/ - abc - abcabc - abcabcabc - xyz - -/([a]*)*/ - a - aaaaa - -/([ab]*)*/ - a - b - ababab - aaaabcde - bbbb - -/([^a]*)*/ - b - bbbb - aaa - -/([^ab]*)*/ - cccc - abab - -/([a]*?)*/ - a - aaaa - -/([ab]*?)*/ - a - b - abab - baba - -/([^a]*?)*/ - b - bbbb - aaa - -/([^ab]*?)*/ - c - cccc - baba - -/(?>a*)*/ - a - aaabcde - -/((?>a*))*/ - aaaaa - aabbaa - -/((?>a*?))*/ - aaaaa - aabbaa - -/(?(?=[^a-z]+[a-z]) \d{2}-[a-z]{3}-\d{2} | \d{2}-\d{2}-\d{2} ) /x - 12-sep-98 - 12-09-98 - *** Failers - sep-12-98 - -/(?<=(foo))bar\1/ - foobarfoo - foobarfootling - *** Failers - foobar - barfoo - -/(?i:saturday|sunday)/ - saturday - sunday - Saturday - Sunday - SATURDAY - SUNDAY - SunDay - -/(a(?i)bc|BB)x/ - abcx - aBCx - bbx - BBx - *** Failers - abcX - aBCX - bbX - BBX - -/^([ab](?i)[cd]|[ef])/ - ac - aC - bD - elephant - Europe - frog - France - *** Failers - Africa - -/^(ab|a(?i)[b-c](?m-i)d|x(?i)y|z)/ - ab - aBd - xy - xY - zebra - Zambesi - *** Failers - aCD - XY - -/(?<=foo\n)^bar/m - foo\nbar - *** Failers - bar - baz\nbar - -/(?<=(?]&/ - <&OUT - -/^(a\1?){4}$/ - aaaaaaaaaa - *** Failers - AB - aaaaaaaaa - aaaaaaaaaaa - -/^(a(?(1)\1)){4}$/ - aaaaaaaaaa - *** Failers - aaaaaaaaa - aaaaaaaaaaa - -/(?:(f)(o)(o)|(b)(a)(r))*/ - foobar - -/(?<=a)b/ - ab - *** Failers - cb - b - -/(?a+)ab/ - -/(?>a+)b/ - aaab - -/([[:]+)/ - a:[b]: - -/([[=]+)/ - a=[b]= - -/([[.]+)/ - a.[b]. - -/((?>a+)b)/ - aaab - -/(?>(a+))b/ - aaab - -/((?>[^()]+)|\([^()]*\))+/ - ((abc(ade)ufh()()x - -/a\Z/ - *** Failers - aaab - a\nb\n - -/b\Z/ - a\nb\n - -/b\z/ - -/b\Z/ - a\nb - -/b\z/ - a\nb - *** Failers - -/^(?>(?(1)\.|())[^\W_](?>[a-z0-9-]*[^\W_])?)+$/ - a - abc - a-b - 0-9 - a.b - 5.6.7 - the.quick.brown.fox - a100.b200.300c - 12-ab.1245 - ***Failers - \ - .a - -a - a- - a. - a_b - a.- - a.. - ab..bc - the.quick.brown.fox- - the.quick.brown.fox. - the.quick.brown.fox_ - the.quick.brown.fox+ - -/(?>.*)(?<=(abcd|wxyz))/ - alphabetabcd - endingwxyz - *** Failers - a rather long string that doesn't end with one of them - -/word (?>(?:(?!otherword)[a-zA-Z0-9]+ ){0,30})otherword/ - word cat dog elephant mussel cow horse canary baboon snake shark otherword - word cat dog elephant mussel cow horse canary baboon snake shark - -/word (?>[a-zA-Z0-9]+ ){0,30}otherword/ - word cat dog elephant mussel cow horse canary baboon snake shark the quick brown fox and the lazy dog and several other words getting close to thirty by now I hope - -/(?<=\d{3}(?!999))foo/ - 999foo - 123999foo - *** Failers - 123abcfoo - -/(?<=(?!...999)\d{3})foo/ - 999foo - 123999foo - *** Failers - 123abcfoo - -/(?<=\d{3}(?!999)...)foo/ - 123abcfoo - 123456foo - *** Failers - 123999foo - -/(?<=\d{3}...)(?\s*)=(?>\s*) # find >>aaabxyzpqrrrabbxyyyypqAzz - 0: aaabxyzpqrrrabbxyyyypqAzz - >aaaabxyzpqrrrabbxyyyypqAzz - 0: aaaabxyzpqrrrabbxyyyypqAzz - >>>>abcxyzpqrrrabbxyyyypqAzz - 0: abcxyzpqrrrabbxyyyypqAzz - *** Failers -No match - abxyzpqrrabbxyyyypqAzz -No match - abxyzpqrrrrabbxyyyypqAzz -No match - abxyzpqrrrabxyyyypqAzz -No match - aaaabcxyzzzzpqrrrabbbxyyyyyypqAzz -No match - aaaabcxyzzzzpqrrrabbbxyyypqAzz -No match - aaabcxyzpqrrrabbxyyyypqqqqqqqAzz -No match - -/^(abc){1,2}zz/ - abczz - 0: abczz - 1: abc - abcabczz - 0: abcabczz - 1: abc - *** Failers -No match - zz -No match - abcabcabczz -No match - >>abczz -No match - -/^(b+?|a){1,2}?c/ - bc - 0: bc - 1: b - bbc - 0: bbc - 1: b - bbbc - 0: bbbc - 1: bb - bac - 0: bac - 1: a - bbac - 0: bbac - 1: a - aac - 0: aac - 1: a - abbbbbbbbbbbc - 0: abbbbbbbbbbbc - 1: bbbbbbbbbbb - bbbbbbbbbbbac - 0: bbbbbbbbbbbac - 1: a - *** Failers -No match - aaac -No match - abbbbbbbbbbbac -No match - -/^(b+|a){1,2}c/ - bc - 0: bc - 1: b - bbc - 0: bbc - 1: bb - bbbc - 0: bbbc - 1: bbb - bac - 0: bac - 1: a - bbac - 0: bbac - 1: a - aac - 0: aac - 1: a - abbbbbbbbbbbc - 0: abbbbbbbbbbbc - 1: bbbbbbbbbbb - bbbbbbbbbbbac - 0: bbbbbbbbbbbac - 1: a - *** Failers -No match - aaac -No match - abbbbbbbbbbbac -No match - -/^(b+|a){1,2}?bc/ - bbc - 0: bbc - 1: b - -/^(b*|ba){1,2}?bc/ - babc - 0: babc - 1: ba - bbabc - 0: bbabc - 1: ba - bababc - 0: bababc - 1: ba - *** Failers -No match - bababbc -No match - babababc -No match - -/^(ba|b*){1,2}?bc/ - babc - 0: babc - 1: ba - bbabc - 0: bbabc - 1: ba - bababc - 0: bababc - 1: ba - *** Failers -No match - bababbc -No match - babababc -No match - -/^\ca\cA\c[\c{\c:/ - \x01\x01\e;z - 0: \x01\x01\x1b;z - -/^[ab\]cde]/ - athing - 0: a - bthing - 0: b - ]thing - 0: ] - cthing - 0: c - dthing - 0: d - ething - 0: e - *** Failers -No match - fthing -No match - [thing -No match - \\thing -No match - -/^[]cde]/ - ]thing - 0: ] - cthing - 0: c - dthing - 0: d - ething - 0: e - *** Failers -No match - athing -No match - fthing -No match - -/^[^ab\]cde]/ - fthing - 0: f - [thing - 0: [ - \\thing - 0: \ - *** Failers - 0: * - athing -No match - bthing -No match - ]thing -No match - cthing -No match - dthing -No match - ething -No match - -/^[^]cde]/ - athing - 0: a - fthing - 0: f - *** Failers - 0: * - ]thing -No match - cthing -No match - dthing -No match - ething -No match - -/^\/ -  - 0: \x81 - -/^ÿ/ - ÿ - 0: \xff - -/^[0-9]+$/ - 0 - 0: 0 - 1 - 0: 1 - 2 - 0: 2 - 3 - 0: 3 - 4 - 0: 4 - 5 - 0: 5 - 6 - 0: 6 - 7 - 0: 7 - 8 - 0: 8 - 9 - 0: 9 - 10 - 0: 10 - 100 - 0: 100 - *** Failers -No match - abc -No match - -/^.*nter/ - enter - 0: enter - inter - 0: inter - uponter - 0: uponter - -/^xxx[0-9]+$/ - xxx0 - 0: xxx0 - xxx1234 - 0: xxx1234 - *** Failers -No match - xxx -No match - -/^.+[0-9][0-9][0-9]$/ - x123 - 0: x123 - xx123 - 0: xx123 - 123456 - 0: 123456 - *** Failers -No match - 123 -No match - x1234 - 0: x1234 - -/^.+?[0-9][0-9][0-9]$/ - x123 - 0: x123 - xx123 - 0: xx123 - 123456 - 0: 123456 - *** Failers -No match - 123 -No match - x1234 - 0: x1234 - -/^([^!]+)!(.+)=apquxz\.ixr\.zzz\.ac\.uk$/ - abc!pqr=apquxz.ixr.zzz.ac.uk - 0: abc!pqr=apquxz.ixr.zzz.ac.uk - 1: abc - 2: pqr - *** Failers -No match - !pqr=apquxz.ixr.zzz.ac.uk -No match - abc!=apquxz.ixr.zzz.ac.uk -No match - abc!pqr=apquxz:ixr.zzz.ac.uk -No match - abc!pqr=apquxz.ixr.zzz.ac.ukk -No match - -/:/ - Well, we need a colon: somewhere - 0: : - *** Fail if we don't -No match - -/([\da-f:]+)$/i - 0abc - 0: 0abc - 1: 0abc - abc - 0: abc - 1: abc - fed - 0: fed - 1: fed - E - 0: E - 1: E - :: - 0: :: - 1: :: - 5f03:12C0::932e - 0: 5f03:12C0::932e - 1: 5f03:12C0::932e - fed def - 0: def - 1: def - Any old stuff - 0: ff - 1: ff - *** Failers -No match - 0zzz -No match - gzzz -No match - fed\x20 -No match - Any old rubbish -No match - -/^.*\.(\d{1,3})\.(\d{1,3})\.(\d{1,3})$/ - .1.2.3 - 0: .1.2.3 - 1: 1 - 2: 2 - 3: 3 - A.12.123.0 - 0: A.12.123.0 - 1: 12 - 2: 123 - 3: 0 - *** Failers -No match - .1.2.3333 -No match - 1.2.3 -No match - 1234.2.3 -No match - -/^(\d+)\s+IN\s+SOA\s+(\S+)\s+(\S+)\s*\(\s*$/ - 1 IN SOA non-sp1 non-sp2( - 0: 1 IN SOA non-sp1 non-sp2( - 1: 1 - 2: non-sp1 - 3: non-sp2 - 1 IN SOA non-sp1 non-sp2 ( - 0: 1 IN SOA non-sp1 non-sp2 ( - 1: 1 - 2: non-sp1 - 3: non-sp2 - *** Failers -No match - 1IN SOA non-sp1 non-sp2( -No match - -/^[a-zA-Z\d][a-zA-Z\d\-]*(\.[a-zA-Z\d][a-zA-z\d\-]*)*\.$/ - a. - 0: a. - Z. - 0: Z. - 2. - 0: 2. - ab-c.pq-r. - 0: ab-c.pq-r. - 1: .pq-r - sxk.zzz.ac.uk. - 0: sxk.zzz.ac.uk. - 1: .uk - x-.y-. - 0: x-.y-. - 1: .y- - *** Failers -No match - -abc.peq. -No match - -/^\*\.[a-z]([a-z\-\d]*[a-z\d]+)?(\.[a-z]([a-z\-\d]*[a-z\d]+)?)*$/ - *.a - 0: *.a - *.b0-a - 0: *.b0-a - 1: 0-a - *.c3-b.c - 0: *.c3-b.c - 1: 3-b - 2: .c - *.c-a.b-c - 0: *.c-a.b-c - 1: -a - 2: .b-c - 3: -c - *** Failers -No match - *.0 -No match - *.a- -No match - *.a-b.c- -No match - *.c-a.0-c -No match - -/^(?=ab(de))(abd)(e)/ - abde - 0: abde - 1: de - 2: abd - 3: e - -/^(?!(ab)de|x)(abd)(f)/ - abdf - 0: abdf - 1: - 2: abd - 3: f - -/^(?=(ab(cd)))(ab)/ - abcd - 0: ab - 1: abcd - 2: cd - 3: ab - -/^[\da-f](\.[\da-f])*$/i - a.b.c.d - 0: a.b.c.d - 1: .d - A.B.C.D - 0: A.B.C.D - 1: .D - a.b.c.1.2.3.C - 0: a.b.c.1.2.3.C - 1: .C - -/^\".*\"\s*(;.*)?$/ - \"1234\" - 0: "1234" - \"abcd\" ; - 0: "abcd" ; - 1: ; - \"\" ; rhubarb - 0: "" ; rhubarb - 1: ; rhubarb - *** Failers -No match - \"1234\" : things -No match - -/^$/ - \ - 0: - *** Failers -No match - -/ ^ a (?# begins with a) b\sc (?# then b c) $ (?# then end)/x - ab c - 0: ab c - *** Failers -No match - abc -No match - ab cde -No match - -/(?x) ^ a (?# begins with a) b\sc (?# then b c) $ (?# then end)/ - ab c - 0: ab c - *** Failers -No match - abc -No match - ab cde -No match - -/^ a\ b[c ]d $/x - a bcd - 0: a bcd - a b d - 0: a b d - *** Failers -No match - abcd -No match - ab d -No match - -/^(a(b(c)))(d(e(f)))(h(i(j)))(k(l(m)))$/ - abcdefhijklm - 0: abcdefhijklm - 1: abc - 2: bc - 3: c - 4: def - 5: ef - 6: f - 7: hij - 8: ij - 9: j -10: klm -11: lm -12: m - -/^(?:a(b(c)))(?:d(e(f)))(?:h(i(j)))(?:k(l(m)))$/ - abcdefhijklm - 0: abcdefhijklm - 1: bc - 2: c - 3: ef - 4: f - 5: ij - 6: j - 7: lm - 8: m - -/^[\w][\W][\s][\S][\d][\D][\b][\n][\c]][\022]/ - a+ Z0+\x08\n\x1d\x12 - 0: a+ Z0+\x08\x0a\x1d\x12 - -/^[.^$|()*+?{,}]+/ - .^\$(*+)|{?,?} - 0: .^$(*+)|{?,?} - -/^a*\w/ - z - 0: z - az - 0: az - aaaz - 0: aaaz - a - 0: a - aa - 0: aa - aaaa - 0: aaaa - a+ - 0: a - aa+ - 0: aa - -/^a*?\w/ - z - 0: z - az - 0: a - aaaz - 0: a - a - 0: a - aa - 0: a - aaaa - 0: a - a+ - 0: a - aa+ - 0: a - -/^a+\w/ - az - 0: az - aaaz - 0: aaaz - aa - 0: aa - aaaa - 0: aaaa - aa+ - 0: aa - -/^a+?\w/ - az - 0: az - aaaz - 0: aa - aa - 0: aa - aaaa - 0: aa - aa+ - 0: aa - -/^\d{8}\w{2,}/ - 1234567890 - 0: 1234567890 - 12345678ab - 0: 12345678ab - 12345678__ - 0: 12345678__ - *** Failers -No match - 1234567 -No match - -/^[aeiou\d]{4,5}$/ - uoie - 0: uoie - 1234 - 0: 1234 - 12345 - 0: 12345 - aaaaa - 0: aaaaa - *** Failers -No match - 123456 -No match - -/^[aeiou\d]{4,5}?/ - uoie - 0: uoie - 1234 - 0: 1234 - 12345 - 0: 1234 - aaaaa - 0: aaaa - 123456 - 0: 1234 - -/\A(abc|def)=(\1){2,3}\Z/ - abc=abcabc - 0: abc=abcabc - 1: abc - 2: abc - def=defdefdef - 0: def=defdefdef - 1: def - 2: def - *** Failers -No match - abc=defdef -No match - -/^(a)(b)(c)(d)(e)(f)(g)(h)(i)(j)(k)\11*(\3\4)\1(?#)2$/ - abcdefghijkcda2 - 0: abcdefghijkcda2 - 1: a - 2: b - 3: c - 4: d - 5: e - 6: f - 7: g - 8: h - 9: i -10: j -11: k -12: cd - abcdefghijkkkkcda2 - 0: abcdefghijkkkkcda2 - 1: a - 2: b - 3: c - 4: d - 5: e - 6: f - 7: g - 8: h - 9: i -10: j -11: k -12: cd - -/(cat(a(ract|tonic)|erpillar)) \1()2(3)/ - cataract cataract23 - 0: cataract cataract23 - 1: cataract - 2: aract - 3: ract - 4: - 5: 3 - catatonic catatonic23 - 0: catatonic catatonic23 - 1: catatonic - 2: atonic - 3: tonic - 4: - 5: 3 - caterpillar caterpillar23 - 0: caterpillar caterpillar23 - 1: caterpillar - 2: erpillar - 3: - 4: - 5: 3 - - -/^From +([^ ]+) +[a-zA-Z][a-zA-Z][a-zA-Z] +[a-zA-Z][a-zA-Z][a-zA-Z] +[0-9]?[0-9] +[0-9][0-9]:[0-9][0-9]/ - From abcd Mon Sep 01 12:33:02 1997 - 0: From abcd Mon Sep 01 12:33 - 1: abcd - -/^From\s+\S+\s+([a-zA-Z]{3}\s+){2}\d{1,2}\s+\d\d:\d\d/ - From abcd Mon Sep 01 12:33:02 1997 - 0: From abcd Mon Sep 01 12:33 - 1: Sep - From abcd Mon Sep 1 12:33:02 1997 - 0: From abcd Mon Sep 1 12:33 - 1: Sep - *** Failers -No match - From abcd Sep 01 12:33:02 1997 -No match - -/^12.34/s - 12\n34 - 0: 12\x0a34 - 12\r34 - 0: 12\x0d34 - -/\w+(?=\t)/ - the quick brown\t fox - 0: brown - -/foo(?!bar)(.*)/ - foobar is foolish see? - 0: foolish see? - 1: lish see? - -/(?:(?!foo)...|^.{0,2})bar(.*)/ - foobar crowbar etc - 0: rowbar etc - 1: etc - barrel - 0: barrel - 1: rel - 2barrel - 0: 2barrel - 1: rel - A barrel - 0: A barrel - 1: rel - -/^(\D*)(?=\d)(?!123)/ - abc456 - 0: abc - 1: abc - *** Failers -No match - abc123 -No match - -/^1234(?# test newlines - inside)/ - 1234 - 0: 1234 - -/^1234 #comment in extended re - /x - 1234 - 0: 1234 - -/#rhubarb - abcd/x - abcd - 0: abcd - -/^abcd#rhubarb/x - abcd - 0: abcd - -/^(a)\1{2,3}(.)/ - aaab - 0: aaab - 1: a - 2: b - aaaab - 0: aaaab - 1: a - 2: b - aaaaab - 0: aaaaa - 1: a - 2: a - aaaaaab - 0: aaaaa - 1: a - 2: a - -/(?!^)abc/ - the abc - 0: abc - *** Failers -No match - abc -No match - -/(?=^)abc/ - abc - 0: abc - *** Failers -No match - the abc -No match - -/^[ab]{1,3}(ab*|b)/ - aabbbbb - 0: aabb - 1: b - -/^[ab]{1,3}?(ab*|b)/ - aabbbbb - 0: aabbbbb - 1: abbbbb - -/^[ab]{1,3}?(ab*?|b)/ - aabbbbb - 0: aa - 1: a - -/^[ab]{1,3}(ab*?|b)/ - aabbbbb - 0: aabb - 1: b - -/ (?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* # optional leading comment -(?: (?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| -" (?: # opening quote... -[^\\\x80-\xff\n\015"] # Anything except backslash and quote -| # or -\\ [^\x80-\xff] # Escaped something (something != CR) -)* " # closing quote -) # initial word -(?: (?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* \. (?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* (?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| -" (?: # opening quote... -[^\\\x80-\xff\n\015"] # Anything except backslash and quote -| # or -\\ [^\x80-\xff] # Escaped something (something != CR) -)* " # closing quote -) )* # further okay, if led by a period -(?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* @ (?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* (?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| \[ # [ -(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff -\] # ] -) # initial subdomain -(?: # -(?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* \. # if led by a period... -(?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* (?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| \[ # [ -(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff -\] # ] -) # ...further okay -)* -# address -| # or -(?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| -" (?: # opening quote... -[^\\\x80-\xff\n\015"] # Anything except backslash and quote -| # or -\\ [^\x80-\xff] # Escaped something (something != CR) -)* " # closing quote -) # one word, optionally followed by.... -(?: -[^()<>@,;:".\\\[\]\x80-\xff\000-\010\012-\037] | # atom and space parts, or... -\( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) | # comments, or... - -" (?: # opening quote... -[^\\\x80-\xff\n\015"] # Anything except backslash and quote -| # or -\\ [^\x80-\xff] # Escaped something (something != CR) -)* " # closing quote -# quoted strings -)* -< (?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* # leading < -(?: @ (?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* (?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| \[ # [ -(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff -\] # ] -) # initial subdomain -(?: # -(?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* \. # if led by a period... -(?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* (?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| \[ # [ -(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff -\] # ] -) # ...further okay -)* - -(?: (?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* , (?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* @ (?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* (?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| \[ # [ -(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff -\] # ] -) # initial subdomain -(?: # -(?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* \. # if led by a period... -(?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* (?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| \[ # [ -(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff -\] # ] -) # ...further okay -)* -)* # further okay, if led by comma -: # closing colon -(?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* )? # optional route -(?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| -" (?: # opening quote... -[^\\\x80-\xff\n\015"] # Anything except backslash and quote -| # or -\\ [^\x80-\xff] # Escaped something (something != CR) -)* " # closing quote -) # initial word -(?: (?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* \. (?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* (?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| -" (?: # opening quote... -[^\\\x80-\xff\n\015"] # Anything except backslash and quote -| # or -\\ [^\x80-\xff] # Escaped something (something != CR) -)* " # closing quote -) )* # further okay, if led by a period -(?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* @ (?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* (?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| \[ # [ -(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff -\] # ] -) # initial subdomain -(?: # -(?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* \. # if led by a period... -(?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* (?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| \[ # [ -(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff -\] # ] -) # ...further okay -)* -# address spec -(?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* > # trailing > -# name and address -) (?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* # optional trailing comment -/x - Alan Other - 0: Alan Other - - 0: user@dom.ain - user\@dom.ain - 0: user@dom.ain - \"A. Other\" (a comment) - 0: "A. Other" (a comment) - A. Other (a comment) - 0: Other (a comment) - \"/s=user/ou=host/o=place/prmd=uu.yy/admd= /c=gb/\"\@x400-re.lay - 0: "/s=user/ou=host/o=place/prmd=uu.yy/admd= /c=gb/"@x400-re.lay - A missing angle @,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -# Atom -| # or -" # " -[^\\\x80-\xff\n\015"] * # normal -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015"] * )* # ( special normal* )* -" # " -# Quoted string -) -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -(?: -\. -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -(?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -# Atom -| # or -" # " -[^\\\x80-\xff\n\015"] * # normal -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015"] * )* # ( special normal* )* -" # " -# Quoted string -) -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -# additional words -)* -@ -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -(?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| -\[ # [ -(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff -\] # ] -) -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -# optional trailing comments -(?: -\. -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -(?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| -\[ # [ -(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff -\] # ] -) -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -# optional trailing comments -)* -# address -| # or -(?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -# Atom -| # or -" # " -[^\\\x80-\xff\n\015"] * # normal -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015"] * )* # ( special normal* )* -" # " -# Quoted string -) -# leading word -[^()<>@,;:".\\\[\]\x80-\xff\000-\010\012-\037] * # "normal" atoms and or spaces -(?: -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -| -" # " -[^\\\x80-\xff\n\015"] * # normal -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015"] * )* # ( special normal* )* -" # " -) # "special" comment or quoted string -[^()<>@,;:".\\\[\]\x80-\xff\000-\010\012-\037] * # more "normal" -)* -< -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -# < -(?: -@ -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -(?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| -\[ # [ -(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff -\] # ] -) -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -# optional trailing comments -(?: -\. -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -(?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| -\[ # [ -(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff -\] # ] -) -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -# optional trailing comments -)* -(?: , -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -@ -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -(?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| -\[ # [ -(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff -\] # ] -) -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -# optional trailing comments -(?: -\. -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -(?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| -\[ # [ -(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff -\] # ] -) -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -# optional trailing comments -)* -)* # additional domains -: -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -# optional trailing comments -)? # optional route -(?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -# Atom -| # or -" # " -[^\\\x80-\xff\n\015"] * # normal -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015"] * )* # ( special normal* )* -" # " -# Quoted string -) -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -(?: -\. -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -(?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -# Atom -| # or -" # " -[^\\\x80-\xff\n\015"] * # normal -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015"] * )* # ( special normal* )* -" # " -# Quoted string -) -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -# additional words -)* -@ -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -(?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| -\[ # [ -(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff -\] # ] -) -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -# optional trailing comments -(?: -\. -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -(?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| -\[ # [ -(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff -\] # ] -) -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -# optional trailing comments -)* -# address spec -> # > -# name and address -) -/x - Alan Other - 0: Alan Other - - 0: user@dom.ain - user\@dom.ain - 0: user@dom.ain - \"A. Other\" (a comment) - 0: "A. Other" - A. Other (a comment) - 0: Other - \"/s=user/ou=host/o=place/prmd=uu.yy/admd= /c=gb/\"\@x400-re.lay - 0: "/s=user/ou=host/o=place/prmd=uu.yy/admd= /c=gb/"@x400-re.lay - A missing angle ?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\]^_`abcdefghijklmnopqrstuvwxyz{|}~\x7f\x80\x81\x82\x83\x84\x85\x86\x87\x88\x89\x8a\x8b\x8c\x8d\x8e\x8f\x90\x91\x92\x93\x94\x95\x96\x97\x98\x99\x9a\x9b\x9c\x9d\x9e\x9f\xa0\xa1\xa2\xa3\xa4\xa5\xa6\xa7\xa8\xa9\xaa\xab\xac\xad\xae\xaf\xb0\xb1\xb2\xb3\xb4\xb5\xb6\xb7\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf\xc0\xc1\xc2\xc3\xc4\xc5\xc6\xc7\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf\xd0\xd1\xd2\xd3\xd4\xd5\xd6\xd7\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7\xe8\xe9\xea\xeb\xec\xed\xee\xef\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff - -/P[^*]TAIRE[^*]{1,6}?LL/ - xxxxxxxxxxxPSTAIREISLLxxxxxxxxx - 0: PSTAIREISLL - -/P[^*]TAIRE[^*]{1,}?LL/ - xxxxxxxxxxxPSTAIREISLLxxxxxxxxx - 0: PSTAIREISLL - -/(\.\d\d[1-9]?)\d+/ - 1.230003938 - 0: .230003938 - 1: .23 - 1.875000282 - 0: .875000282 - 1: .875 - 1.235 - 0: .235 - 1: .23 - -/(\.\d\d((?=0)|\d(?=\d)))/ - 1.230003938 - 0: .23 - 1: .23 - 2: - 1.875000282 - 0: .875 - 1: .875 - 2: 5 - *** Failers -No match - 1.235 -No match - -/a(?)b/ - ab - 0: ab - -/\b(foo)\s+(\w+)/i - Food is on the foo table - 0: foo table - 1: foo - 2: table - -/foo(.*)bar/ - The food is under the bar in the barn. - 0: food is under the bar in the bar - 1: d is under the bar in the - -/foo(.*?)bar/ - The food is under the bar in the barn. - 0: food is under the bar - 1: d is under the - -/(.*)(\d*)/ - I have 2 numbers: 53147 - 0: I have 2 numbers: 53147 - 1: I have 2 numbers: 53147 - 2: - -/(.*)(\d+)/ - I have 2 numbers: 53147 - 0: I have 2 numbers: 53147 - 1: I have 2 numbers: 5314 - 2: 7 - -/(.*?)(\d*)/ - I have 2 numbers: 53147 - 0: - 1: - 2: - -/(.*?)(\d+)/ - I have 2 numbers: 53147 - 0: I have 2 - 1: I have - 2: 2 - -/(.*)(\d+)$/ - I have 2 numbers: 53147 - 0: I have 2 numbers: 53147 - 1: I have 2 numbers: 5314 - 2: 7 - -/(.*?)(\d+)$/ - I have 2 numbers: 53147 - 0: I have 2 numbers: 53147 - 1: I have 2 numbers: - 2: 53147 - -/(.*)\b(\d+)$/ - I have 2 numbers: 53147 - 0: I have 2 numbers: 53147 - 1: I have 2 numbers: - 2: 53147 - -/(.*\D)(\d+)$/ - I have 2 numbers: 53147 - 0: I have 2 numbers: 53147 - 1: I have 2 numbers: - 2: 53147 - -/^\D*(?!123)/ - ABC123 - 0: AB - -/^(\D*)(?=\d)(?!123)/ - ABC445 - 0: ABC - 1: ABC - *** Failers -No match - ABC123 -No match - -/^[W-]46]/ - W46]789 - 0: W46] - -46]789 - 0: -46] - *** Failers -No match - Wall -No match - Zebra -No match - 42 -No match - [abcd] -No match - ]abcd[ -No match - -/^[W-\]46]/ - W46]789 - 0: W - Wall - 0: W - Zebra - 0: Z - Xylophone - 0: X - 42 - 0: 4 - [abcd] - 0: [ - ]abcd[ - 0: ] - \\backslash - 0: \ - *** Failers -No match - -46]789 -No match - well -No match - -/\d\d\/\d\d\/\d\d\d\d/ - 01/01/2000 - 0: 01/01/2000 - -/word (?:[a-zA-Z0-9]+ ){0,10}otherword/ - word cat dog elephant mussel cow horse canary baboon snake shark otherword - 0: word cat dog elephant mussel cow horse canary baboon snake shark otherword - word cat dog elephant mussel cow horse canary baboon snake shark -No match - -/word (?:[a-zA-Z0-9]+ ){0,300}otherword/ - word cat dog elephant mussel cow horse canary baboon snake shark the quick brown fox and the lazy dog and several other words getting close to thirty by now I hope -No match - -/^(a){0,0}/ - bcd - 0: - abc - 0: - aab - 0: - -/^(a){0,1}/ - bcd - 0: - abc - 0: a - 1: a - aab - 0: a - 1: a - -/^(a){0,2}/ - bcd - 0: - abc - 0: a - 1: a - aab - 0: aa - 1: a - -/^(a){0,3}/ - bcd - 0: - abc - 0: a - 1: a - aab - 0: aa - 1: a - aaa - 0: aaa - 1: a - -/^(a){0,}/ - bcd - 0: - abc - 0: a - 1: a - aab - 0: aa - 1: a - aaa - 0: aaa - 1: a - aaaaaaaa - 0: aaaaaaaa - 1: a - -/^(a){1,1}/ - bcd -No match - abc - 0: a - 1: a - aab - 0: a - 1: a - -/^(a){1,2}/ - bcd -No match - abc - 0: a - 1: a - aab - 0: aa - 1: a - -/^(a){1,3}/ - bcd -No match - abc - 0: a - 1: a - aab - 0: aa - 1: a - aaa - 0: aaa - 1: a - -/^(a){1,}/ - bcd -No match - abc - 0: a - 1: a - aab - 0: aa - 1: a - aaa - 0: aaa - 1: a - aaaaaaaa - 0: aaaaaaaa - 1: a - -/.*\.gif/ - borfle\nbib.gif\nno - 0: bib.gif - -/.{0,}\.gif/ - borfle\nbib.gif\nno - 0: bib.gif - -/.*\.gif/m - borfle\nbib.gif\nno - 0: bib.gif - -/.*\.gif/s - borfle\nbib.gif\nno - 0: borfle\x0abib.gif - -/.*\.gif/ms - borfle\nbib.gif\nno - 0: borfle\x0abib.gif - -/.*$/ - borfle\nbib.gif\nno - 0: no - -/.*$/m - borfle\nbib.gif\nno - 0: borfle - -/.*$/s - borfle\nbib.gif\nno - 0: borfle\x0abib.gif\x0ano - -/.*$/ms - borfle\nbib.gif\nno - 0: borfle\x0abib.gif\x0ano - -/.*$/ - borfle\nbib.gif\nno\n - 0: no - -/.*$/m - borfle\nbib.gif\nno\n - 0: borfle - -/.*$/s - borfle\nbib.gif\nno\n - 0: borfle\x0abib.gif\x0ano\x0a - -/.*$/ms - borfle\nbib.gif\nno\n - 0: borfle\x0abib.gif\x0ano\x0a - -/(.*X|^B)/ - abcde\n1234Xyz - 0: 1234X - 1: 1234X - BarFoo - 0: B - 1: B - *** Failers -No match - abcde\nBar -No match - -/(.*X|^B)/m - abcde\n1234Xyz - 0: 1234X - 1: 1234X - BarFoo - 0: B - 1: B - abcde\nBar - 0: B - 1: B - -/(.*X|^B)/s - abcde\n1234Xyz - 0: abcde\x0a1234X - 1: abcde\x0a1234X - BarFoo - 0: B - 1: B - *** Failers -No match - abcde\nBar -No match - -/(.*X|^B)/ms - abcde\n1234Xyz - 0: abcde\x0a1234X - 1: abcde\x0a1234X - BarFoo - 0: B - 1: B - abcde\nBar - 0: B - 1: B - -/(?s)(.*X|^B)/ - abcde\n1234Xyz - 0: abcde\x0a1234X - 1: abcde\x0a1234X - BarFoo - 0: B - 1: B - *** Failers -No match - abcde\nBar -No match - -/(?s:.*X|^B)/ - abcde\n1234Xyz - 0: abcde\x0a1234X - BarFoo - 0: B - *** Failers -No match - abcde\nBar -No match - -/^.*B/ - **** Failers -No match - abc\nB -No match - -/(?s)^.*B/ - abc\nB - 0: abc\x0aB - -/(?m)^.*B/ - abc\nB - 0: B - -/(?ms)^.*B/ - abc\nB - 0: abc\x0aB - -/(?ms)^B/ - abc\nB - 0: B - -/(?s)B$/ - B\n - 0: B - -/^[0-9][0-9][0-9][0-9][0-9][0-9][0-9][0-9][0-9][0-9][0-9][0-9]/ - 123456654321 - 0: 123456654321 - -/^\d\d\d\d\d\d\d\d\d\d\d\d/ - 123456654321 - 0: 123456654321 - -/^[\d][\d][\d][\d][\d][\d][\d][\d][\d][\d][\d][\d]/ - 123456654321 - 0: 123456654321 - -/^[abc]{12}/ - abcabcabcabc - 0: abcabcabcabc - -/^[a-c]{12}/ - abcabcabcabc - 0: abcabcabcabc - -/^(a|b|c){12}/ - abcabcabcabc - 0: abcabcabcabc - 1: c - -/^[abcdefghijklmnopqrstuvwxy0123456789]/ - n - 0: n - *** Failers -No match - z -No match - -/abcde{0,0}/ - abcd - 0: abcd - *** Failers -No match - abce -No match - -/ab[cd]{0,0}e/ - abe - 0: abe - *** Failers -No match - abcde -No match - -/ab(c){0,0}d/ - abd - 0: abd - *** Failers -No match - abcd -No match - -/a(b*)/ - a - 0: a - 1: - ab - 0: ab - 1: b - abbbb - 0: abbbb - 1: bbbb - *** Failers - 0: a - 1: - bbbbb -No match - -/ab\d{0}e/ - abe - 0: abe - *** Failers -No match - ab1e -No match - -/"([^\\"]+|\\.)*"/ - the \"quick\" brown fox - 0: "quick" - 1: quick - \"the \\\"quick\\\" brown fox\" - 0: "the \"quick\" brown fox" - 1: brown fox - -/ End of test input / - diff --git a/ext/pcre/pcrelib/testoutput2 b/ext/pcre/pcrelib/testoutput2 deleted file mode 100644 index 5950a913e3..0000000000 --- a/ext/pcre/pcrelib/testoutput2 +++ /dev/null @@ -1,1624 +0,0 @@ -PCRE version 2.08 31-Aug-1999 - -/(a)b|/ -Identifying subpattern count = 1 -No options -No first char -No req char - -/abc/ -Identifying subpattern count = 0 -No options -First char = 'a' -Req char = 'c' - abc - 0: abc - defabc - 0: abc - \Aabc - 0: abc - *** Failers -No match - \Adefabc -No match - ABC -No match - -/^abc/ -Identifying subpattern count = 0 -Options: anchored -No first char -Req char = 'c' - abc - 0: abc - \Aabc - 0: abc - *** Failers -No match - defabc -No match - \Adefabc -No match - -/a+bc/ -Identifying subpattern count = 0 -No options -First char = 'a' -Req char = 'c' - -/a*bc/ -Identifying subpattern count = 0 -No options -No first char -Req char = 'c' - -/a{3}bc/ -Identifying subpattern count = 0 -No options -First char = 'a' -Req char = 'c' - -/(abc|a+z)/ -Identifying subpattern count = 1 -No options -First char = 'a' -No req char - -/^abc$/ -Identifying subpattern count = 0 -Options: anchored -No first char -Req char = 'c' - abc - 0: abc - *** Failers -No match - def\nabc -No match - -/ab\gdef/X -Failed: unrecognized character follows \ at offset 3 - -/(?X)ab\gdef/X -Failed: unrecognized character follows \ at offset 7 - -/x{5,4}/ -Failed: numbers out of order in {} quantifier at offset 5 - -/z{65536}/ -Failed: number too big in {} quantifier at offset 7 - -/[abcd/ -Failed: missing terminating ] for character class at offset 5 - -/[\B]/ -Failed: invalid escape sequence in character class at offset 2 - -/[a-\w]/ -Failed: invalid escape sequence in character class at offset 4 - -/[z-a]/ -Failed: range out of order in character class at offset 3 - -/^*/ -Failed: nothing to repeat at offset 1 - -/(abc/ -Failed: missing ) at offset 4 - -/(?# abc/ -Failed: missing ) after comment at offset 7 - -/(?z)abc/ -Failed: unrecognized character after (? at offset 2 - -/.*b/ -Identifying subpattern count = 0 -No options -First char at start or follows \n -Req char = 'b' - -/.*?b/ -Identifying subpattern count = 0 -No options -First char at start or follows \n -Req char = 'b' - -/cat|dog|elephant/ -Identifying subpattern count = 0 -No options -No first char -No req char - this sentence eventually mentions a cat - 0: cat - this sentences rambles on and on for a while and then reaches elephant - 0: elephant - -/cat|dog|elephant/S -Identifying subpattern count = 0 -No options -No first char -No req char -Starting character set: c d e - this sentence eventually mentions a cat - 0: cat - this sentences rambles on and on for a while and then reaches elephant - 0: elephant - -/cat|dog|elephant/iS -Identifying subpattern count = 0 -Options: caseless -No first char -No req char -Starting character set: C D E c d e - this sentence eventually mentions a CAT cat - 0: CAT - this sentences rambles on and on for a while to elephant ElePhant - 0: elephant - -/a|[bcd]/S -Identifying subpattern count = 0 -No options -No first char -No req char -Starting character set: a b c d - -/(a|[^\dZ])/S -Identifying subpattern count = 1 -No options -No first char -No req char -Starting character set: \x00 \x01 \x02 \x03 \x04 \x05 \x06 \x07 \x08 \x09 \x0a - \x0b \x0c \x0d \x0e \x0f \x10 \x11 \x12 \x13 \x14 \x15 \x16 \x17 \x18 \x19 - \x1a \x1b \x1c \x1d \x1e \x1f \x20 ! " # $ % & ' ( ) * + , - . / : ; < = > - ? @ A B C D E F G H I J K L M N O P Q R S T U V W X Y [ \ ] ^ _ ` a b c d - e f g h i j k l m n o p q r s t u v w x y z { | } ~ \x7f \x80 \x81 \x82 \x83 - \x84 \x85 \x86 \x87 \x88 \x89 \x8a \x8b \x8c \x8d \x8e \x8f \x90 \x91 \x92 - \x93 \x94 \x95 \x96 \x97 \x98 \x99 \x9a \x9b \x9c \x9d \x9e \x9f \xa0 \xa1 - \xa2 \xa3 \xa4 \xa5 \xa6 \xa7 \xa8 \xa9 \xaa \xab \xac \xad \xae \xaf \xb0 - \xb1 \xb2 \xb3 \xb4 \xb5 \xb6 \xb7 \xb8 \xb9 \xba \xbb \xbc \xbd \xbe \xbf - \xc0 \xc1 \xc2 \xc3 \xc4 \xc5 \xc6 \xc7 \xc8 \xc9 \xca \xcb \xcc \xcd \xce - \xcf \xd0 \xd1 \xd2 \xd3 \xd4 \xd5 \xd6 \xd7 \xd8 \xd9 \xda \xdb \xdc \xdd - \xde \xdf \xe0 \xe1 \xe2 \xe3 \xe4 \xe5 \xe6 \xe7 \xe8 \xe9 \xea \xeb \xec - \xed \xee \xef \xf0 \xf1 \xf2 \xf3 \xf4 \xf5 \xf6 \xf7 \xf8 \xf9 \xfa \xfb - \xfc \xfd \xfe \xff - -/(a|b)*[\s]/S -Identifying subpattern count = 1 -No options -No first char -No req char -Starting character set: \x09 \x0a \x0b \x0c \x0d \x20 a b - -/(ab\2)/ -Failed: back reference to non-existent subpattern at offset 6 - -/{4,5}abc/ -Failed: nothing to repeat at offset 4 - -/(a)(b)(c)\2/ -Identifying subpattern count = 3 -No options -First char = 'a' -Req char = 'c' - abcb - 0: abcb - 1: a - 2: b - 3: c - \O0abcb -Matched, but too many substrings - \O3abcb -Matched, but too many substrings - 0: abcb - \O6abcb -Matched, but too many substrings - 0: abcb - 1: a - \O9abcb -Matched, but too many substrings - 0: abcb - 1: a - 2: b - \O12abcb - 0: abcb - 1: a - 2: b - 3: c - -/(a)bc|(a)(b)\2/ -Identifying subpattern count = 3 -No options -First char = 'a' -No req char - abc - 0: abc - 1: a - \O0abc -Matched, but too many substrings - \O3abc -Matched, but too many substrings - 0: abc - \O6abc - 0: abc - 1: a - aba - 0: aba - 1: - 2: a - 3: b - \O0aba -Matched, but too many substrings - \O3aba -Matched, but too many substrings - 0: aba - \O6aba -Matched, but too many substrings - 0: aba - 1: - \O9aba -Matched, but too many substrings - 0: aba - 1: - 2: a - \O12aba - 0: aba - 1: - 2: a - 3: b - -/abc$/E -Identifying subpattern count = 0 -Options: dollar_endonly -First char = 'a' -Req char = 'c' - abc - 0: abc - *** Failers -No match - abc\n -No match - abc\ndef -No match - -/(a)(b)(c)(d)(e)\6/ -Failed: back reference to non-existent subpattern at offset 17 - -/the quick brown fox/ -Identifying subpattern count = 0 -No options -First char = 't' -Req char = 'x' - the quick brown fox - 0: the quick brown fox - this is a line with the quick brown fox - 0: the quick brown fox - -/the quick brown fox/A -Identifying subpattern count = 0 -Options: anchored -No first char -Req char = 'x' - the quick brown fox - 0: the quick brown fox - *** Failers -No match - this is a line with the quick brown fox -No match - -/ab(?z)cd/ -Failed: unrecognized character after (? at offset 4 - -/^abc|def/ -Identifying subpattern count = 0 -No options -No first char -No req char - abcdef - 0: abc - abcdef\B - 0: def - -/.*((abc)$|(def))/ -Identifying subpattern count = 3 -No options -First char at start or follows \n -No req char - defabc - 0: defabc - 1: abc - 2: abc - \Zdefabc - 0: def - 1: def - 2: - 3: def - -/abc/P - abc - 0: abc - *** Failers -No match: POSIX code 17: match failed - -/^abc|def/P - abcdef - 0: abc - abcdef\B - 0: def - -/.*((abc)$|(def))/P - defabc - 0: defabc - 1: abc - 2: abc - \Zdefabc - 0: def - 1: def - 3: def - -/the quick brown fox/P - the quick brown fox - 0: the quick brown fox - *** Failers -No match: POSIX code 17: match failed - The Quick Brown Fox -No match: POSIX code 17: match failed - -/the quick brown fox/Pi - the quick brown fox - 0: the quick brown fox - The Quick Brown Fox - 0: The Quick Brown Fox - -/abc.def/P - *** Failers -No match: POSIX code 17: match failed - abc\ndef -No match: POSIX code 17: match failed - -/abc$/P - abc - 0: abc - abc\n - 0: abc - -/(abc)\2/P -Failed: POSIX code 15: bad back reference at offset 7 - -/(abc\1)/P - abc -No match: POSIX code 17: match failed - -/)/ -Failed: unmatched parentheses at offset 0 - -/a[]b/ -Failed: missing terminating ] for character class at offset 4 - -/[^aeiou ]{3,}/ -Identifying subpattern count = 0 -No options -No first char -No req char - co-processors, and for - 0: -pr - -/<.*>/ -Identifying subpattern count = 0 -No options -First char = '<' -Req char = '>' - abcghinop - 0: ghi - -/<.*?>/ -Identifying subpattern count = 0 -No options -First char = '<' -Req char = '>' - abcghinop - 0: - -/<.*>/U -Identifying subpattern count = 0 -Options: ungreedy -First char = '<' -Req char = '>' - abcghinop - 0: - -/<.*>(?U)/ -Identifying subpattern count = 0 -Options: ungreedy -First char = '<' -Req char = '>' - abcghinop - 0: - -/<.*?>/U -Identifying subpattern count = 0 -Options: ungreedy -First char = '<' -Req char = '>' - abcghinop - 0: ghi - -/={3,}/U -Identifying subpattern count = 0 -Options: ungreedy -First char = '=' -Req char = '=' - abc========def - 0: === - -/(?U)={3,}?/ -Identifying subpattern count = 0 -Options: ungreedy -First char = '=' -Req char = '=' - abc========def - 0: ======== - -/(?^abc)/m -Identifying subpattern count = 0 -Options: multiline -First char at start or follows \n -Req char = 'c' - abc - 0: abc - def\nabc - 0: abc - *** Failers -No match - defabc -No match - -/(?<=ab(c+)d)ef/ -Failed: lookbehind assertion is not fixed length at offset 11 - -/(?<=ab(?<=c+)d)ef/ -Failed: lookbehind assertion is not fixed length at offset 12 - -/(?<=ab(c|de)f)g/ -Failed: lookbehind assertion is not fixed length at offset 13 - -/The next three are in testinput2 because they have variable length branches/ -Identifying subpattern count = 0 -No options -First char = 'T' -Req char = 's' - -/(?<=bullock|donkey)-cart/ -Identifying subpattern count = 0 -No options -First char = '-' -Req char = 't' - the bullock-cart - 0: -cart - a donkey-cart race - 0: -cart - *** Failers -No match - cart -No match - horse-and-cart -No match - -/(?<=ab(?i)x|y|z)/ -Identifying subpattern count = 0 -No options -Case state changes -No first char -No req char - -/(?>.*)(?<=(abcd)|(xyz))/ -Identifying subpattern count = 2 -No options -First char at start or follows \n -No req char - alphabetabcd - 0: alphabetabcd - 1: abcd - endingxyz - 0: endingxyz - 1: - 2: xyz - -/(?<=ab(?i)x(?-i)y|(?i)z|b)ZZ/ -Identifying subpattern count = 0 -No options -Case state changes -First char = 'Z' -Req char = 'Z' - abxyZZ - 0: ZZ - abXyZZ - 0: ZZ - ZZZ - 0: ZZ - zZZ - 0: ZZ - bZZ - 0: ZZ - BZZ - 0: ZZ - *** Failers -No match - ZZ -No match - abXYZZ -No match - zzz -No match - bzz -No match - -/(? - 3: f - 1G a (1) - 2G (0) - 3G f (1) -get substring 4 failed -7 - 0L adef - 1L a - 2L - 3L f - bcdef\G1\G2\G3\G4\L - 0: bcdef - 1: bc - 2: bc - 3: f - 1G bc (2) - 2G bc (2) - 3G f (1) -get substring 4 failed -7 - 0L bcdef - 1L bc - 2L bc - 3L f - adefghijk\C0 - 0: adef - 1: a - 2: - 3: f - 0C adef (4) - -/^abc\00def/ -Identifying subpattern count = 0 -Options: anchored -No first char -Req char = 'f' - abc\00def\L\C0 - 0: abc\x00def - 0C abc (7) - 0L abc - -/word ((?:[a-zA-Z0-9]+ )((?:[a-zA-Z0-9]+ )((?:[a-zA-Z0-9]+ )((?:[a-zA-Z0-9]+ -)((?:[a-zA-Z0-9]+ )((?:[a-zA-Z0-9]+ )((?:[a-zA-Z0-9]+ )((?:[a-zA-Z0-9]+ -)?)?)?)?)?)?)?)?)?otherword/M -Memory allocation (code space): 428 -Identifying subpattern count = 8 -No options -First char = 'w' -Req char = 'd' - -/.*X/D ------------------------------------------------------------------- - 0 8 Bra 0 - 3 Any* - 5 1 X - 8 8 Ket - 11 End ------------------------------------------------------------------- -Identifying subpattern count = 0 -No options -First char at start or follows \n -Req char = 'X' - -/.*X/Ds ------------------------------------------------------------------- - 0 8 Bra 0 - 3 Any* - 5 1 X - 8 8 Ket - 11 End ------------------------------------------------------------------- -Identifying subpattern count = 0 -Options: anchored dotall -No first char -Req char = 'X' - -/(.*X|^B)/D ------------------------------------------------------------------- - 0 21 Bra 0 - 3 8 Bra 1 - 6 Any* - 8 1 X - 11 7 Alt - 14 ^ - 15 1 B - 18 15 Ket - 21 21 Ket - 24 End ------------------------------------------------------------------- -Identifying subpattern count = 1 -No options -First char at start or follows \n -No req char - -/(.*X|^B)/Ds ------------------------------------------------------------------- - 0 21 Bra 0 - 3 8 Bra 1 - 6 Any* - 8 1 X - 11 7 Alt - 14 ^ - 15 1 B - 18 15 Ket - 21 21 Ket - 24 End ------------------------------------------------------------------- -Identifying subpattern count = 1 -Options: anchored dotall -No first char -No req char - -/(?s)(.*X|^B)/D ------------------------------------------------------------------- - 0 21 Bra 0 - 3 8 Bra 1 - 6 Any* - 8 1 X - 11 7 Alt - 14 ^ - 15 1 B - 18 15 Ket - 21 21 Ket - 24 End ------------------------------------------------------------------- -Identifying subpattern count = 1 -Options: anchored dotall -No first char -No req char - -/(?s:.*X|^B)/D ------------------------------------------------------------------- - 0 27 Bra 0 - 3 10 Bra 0 - 6 04 Opt - 8 Any* - 10 1 X - 13 9 Alt - 16 04 Opt - 18 ^ - 19 1 B - 22 19 Ket - 25 00 Opt - 27 27 Ket - 30 End ------------------------------------------------------------------- -Identifying subpattern count = 0 -No options -First char at start or follows \n -No req char - -/\Biss\B/+ -Identifying subpattern count = 0 -No options -First char = 'i' -Req char = 's' - Mississippi - 0: iss - 0+ issippi - -/\Biss\B/+P - Mississippi - 0: iss - 0+ issippi - -/iss/G+ -Identifying subpattern count = 0 -No options -First char = 'i' -Req char = 's' - Mississippi - 0: iss - 0+ issippi - 0: iss - 0+ ippi - -/\Biss\B/G+ -Identifying subpattern count = 0 -No options -First char = 'i' -Req char = 's' - Mississippi - 0: iss - 0+ issippi - -/\Biss\B/g+ -Identifying subpattern count = 0 -No options -First char = 'i' -Req char = 's' - Mississippi - 0: iss - 0+ issippi - 0: iss - 0+ ippi - *** Failers -No match - Mississippi\A -No match - -/(?<=[Ms])iss/g+ -Identifying subpattern count = 0 -No options -First char = 'i' -Req char = 's' - Mississippi - 0: iss - 0+ issippi - 0: iss - 0+ ippi - -/(?<=[Ms])iss/G+ -Identifying subpattern count = 0 -No options -First char = 'i' -Req char = 's' - Mississippi - 0: iss - 0+ issippi - -/^iss/g+ -Identifying subpattern count = 0 -Options: anchored -No first char -Req char = 's' - ississippi - 0: iss - 0+ issippi - -/.*iss/g+ -Identifying subpattern count = 0 -No options -First char at start or follows \n -Req char = 's' - abciss\nxyzisspqr - 0: abciss - 0+ \x0axyzisspqr - 0: xyziss - 0+ pqr - -/.i./+g -Identifying subpattern count = 0 -No options -No first char -Req char = 'i' - Mississippi - 0: Mis - 0+ sissippi - 0: sis - 0+ sippi - 0: sip - 0+ pi - Mississippi\A - 0: Mis - 0+ sissippi - 0: sis - 0+ sippi - 0: sip - 0+ pi - Missouri river - 0: Mis - 0+ souri river - 0: ri - 0+ river - 0: riv - 0+ er - Missouri river\A - 0: Mis - 0+ souri river - -/^.is/+g -Identifying subpattern count = 0 -Options: anchored -No first char -Req char = 's' - Mississippi - 0: Mis - 0+ sissippi - -/^ab\n/g+ -Identifying subpattern count = 0 -Options: anchored -No first char -Req char = 10 - ab\nab\ncd - 0: ab\x0a - 0+ ab\x0acd - -/^ab\n/mg+ -Identifying subpattern count = 0 -Options: multiline -First char at start or follows \n -Req char = 10 - ab\nab\ncd - 0: ab\x0a - 0+ ab\x0acd - 0: ab\x0a - 0+ cd - -/abc/ -Identifying subpattern count = 0 -No options -First char = 'a' -Req char = 'c' - -/abc|bac/ -Identifying subpattern count = 0 -No options -No first char -Req char = 'c' - -/(abc|bac)/ -Identifying subpattern count = 1 -No options -No first char -Req char = 'c' - -/(abc|(c|dc))/ -Identifying subpattern count = 2 -No options -No first char -Req char = 'c' - -/(abc|(d|de)c)/ -Identifying subpattern count = 2 -No options -No first char -Req char = 'c' - -/a*/ -Identifying subpattern count = 0 -No options -No first char -No req char - -/a+/ -Identifying subpattern count = 0 -No options -First char = 'a' -No req char - -/(baa|a+)/ -Identifying subpattern count = 1 -No options -No first char -Req char = 'a' - -/a{0,3}/ -Identifying subpattern count = 0 -No options -No first char -No req char - -/baa{3,}/ -Identifying subpattern count = 0 -No options -First char = 'b' -Req char = 'a' - -/"([^\\"]+|\\.)*"/ -Identifying subpattern count = 1 -No options -First char = '"' -Req char = '"' - -/(abc|ab[cd])/ -Identifying subpattern count = 1 -No options -First char = 'a' -No req char - -/(a|.)/ -Identifying subpattern count = 1 -No options -No first char -No req char - -/a|ba|\w/ -Identifying subpattern count = 0 -No options -No first char -No req char - -/abc(?=pqr)/ -Identifying subpattern count = 0 -No options -First char = 'a' -Req char = 'r' - -/...(?<=abc)/ -Identifying subpattern count = 0 -No options -No first char -No req char - -/abc(?!pqr)/ -Identifying subpattern count = 0 -No options -First char = 'a' -Req char = 'c' - -/ab./ -Identifying subpattern count = 0 -No options -First char = 'a' -Req char = 'b' - -/ab[xyz]/ -Identifying subpattern count = 0 -No options -First char = 'a' -Req char = 'b' - -/abc*/ -Identifying subpattern count = 0 -No options -First char = 'a' -Req char = 'b' - -/ab.c*/ -Identifying subpattern count = 0 -No options -First char = 'a' -Req char = 'b' - -/a.c*/ -Identifying subpattern count = 0 -No options -First char = 'a' -No req char - -/.c*/ -Identifying subpattern count = 0 -No options -No first char -No req char - -/ac*/ -Identifying subpattern count = 0 -No options -First char = 'a' -No req char - -/(a.c*|b.c*)/ -Identifying subpattern count = 1 -No options -No first char -No req char - -/a.c*|aba/ -Identifying subpattern count = 0 -No options -First char = 'a' -No req char - -/.+a/ -Identifying subpattern count = 0 -No options -No first char -Req char = 'a' - -/(?=abcda)a.*/ -Identifying subpattern count = 0 -No options -First char = 'a' -No req char - -/(?=a)a.*/ -Identifying subpattern count = 0 -No options -First char = 'a' -No req char - -/a(b)*/ -Identifying subpattern count = 1 -No options -First char = 'a' -No req char - -/a\d*/ -Identifying subpattern count = 0 -No options -First char = 'a' -No req char - -/ab\d*/ -Identifying subpattern count = 0 -No options -First char = 'a' -Req char = 'b' - -/a(\d)*/ -Identifying subpattern count = 1 -No options -First char = 'a' -No req char - -/abcde{0,0}/ -Identifying subpattern count = 0 -No options -First char = 'a' -Req char = 'd' - -/ab\d+/ -Identifying subpattern count = 0 -No options -First char = 'a' -Req char = 'b' - -/a(?(1)b)/ -Identifying subpattern count = 0 -No options -First char = 'a' -No req char - -/a(?(1)bag|big)/ -Identifying subpattern count = 0 -No options -First char = 'a' -Req char = 'g' - -/a(?(1)bag|big)*/ -Identifying subpattern count = 0 -No options -First char = 'a' -No req char - -/a(?(1)bag|big)+/ -Identifying subpattern count = 0 -No options -First char = 'a' -Req char = 'g' - -/a(?(1)b..|b..)/ -Identifying subpattern count = 0 -No options -First char = 'a' -Req char = 'b' - -/ab\d{0}e/ -Identifying subpattern count = 0 -No options -First char = 'a' -Req char = 'e' - -/a?b?/ -Identifying subpattern count = 0 -No options -No first char -No req char - a - 0: a - b - 0: b - ab - 0: ab - \ - 0: - *** Failers - 0: - \N -No match - -/|-/ -Identifying subpattern count = 0 -No options -No first char -No req char - abcd - 0: - -abc - 0: - \Nab-c - 0: - - *** Failers - 0: - \Nabc -No match - -/.*?/g+ -Identifying subpattern count = 0 -No options -First char at start or follows \n -No req char - abc - 0: - 0+ abc - 0: a - 0+ bc - 0: - 0+ bc - 0: b - 0+ c - 0: - 0+ c - 0: c - 0+ - 0: - 0+ - -/ End of test input / -Identifying subpattern count = 0 -No options -First char = ' ' -Req char = ' ' - diff --git a/ext/pcre/pcrelib/testoutput3 b/ext/pcre/pcrelib/testoutput3 deleted file mode 100644 index d9976598f2..0000000000 --- a/ext/pcre/pcrelib/testoutput3 +++ /dev/null @@ -1,2929 +0,0 @@ -PCRE version 2.08 31-Aug-1999 - -/(?.*/)foo" - /this/is/a/very/long/line/in/deed/with/very/many/slashes/in/it/you/see/ -No match - -"(?>.*/)foo" - /this/is/a/very/long/line/in/deed/with/very/many/slashes/in/and/foo - 0: /this/is/a/very/long/line/in/deed/with/very/many/slashes/in/and/foo - -/(?>(\.\d\d[1-9]?))\d+/ - 1.230003938 - 0: .230003938 - 1: .23 - 1.875000282 - 0: .875000282 - 1: .875 - *** Failers -No match - 1.235 -No match - -/^((?>\w+)|(?>\s+))*$/ - now is the time for all good men to come to the aid of the party - 0: now is the time for all good men to come to the aid of the party - 1: party - *** Failers -No match - this is not a line with only words and spaces! -No match - -/(\d+)(\w)/ - 12345a - 0: 12345a - 1: 12345 - 2: a - 12345+ - 0: 12345 - 1: 1234 - 2: 5 - -/((?>\d+))(\w)/ - 12345a - 0: 12345a - 1: 12345 - 2: a - *** Failers -No match - 12345+ -No match - -/(?>a+)b/ - aaab - 0: aaab - -/((?>a+)b)/ - aaab - 0: aaab - 1: aaab - -/(?>(a+))b/ - aaab - 0: aaab - 1: aaa - -/(?>b)+/ - aaabbbccc - 0: bbb - -/(?>a+|b+|c+)*c/ - aaabbbbccccd - 0: aaabbbbc - -/((?>[^()]+)|\([^()]*\))+/ - ((abc(ade)ufh()()x - 0: abc(ade)ufh()()x - 1: x - -/\(((?>[^()]+)|\([^()]+\))+\)/ - (abc) - 0: (abc) - 1: abc - (abc(def)xyz) - 0: (abc(def)xyz) - 1: xyz - *** Failers -No match - ((()aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa -No match - -/a(?-i)b/i - ab - 0: ab - *** Failers -No match - Ab -No match - aB -No match - AB -No match - -/(a (?x)b c)d e/ - a bcd e - 0: a bcd e - 1: a bc - *** Failers -No match - a b cd e -No match - abcd e -No match - a bcde -No match - -/(a b(?x)c d (?-x)e f)/ - a bcde f - 0: a bcde f - 1: a bcde f - *** Failers -No match - abcdef -No match - -/(a(?i)b)c/ - abc - 0: abc - 1: ab - aBc - 0: aBc - 1: aB - *** Failers -No match - abC -No match - aBC -No match - Abc -No match - ABc -No match - ABC -No match - AbC -No match - -/a(?i:b)c/ - abc - 0: abc - aBc - 0: aBc - *** Failers -No match - ABC -No match - abC -No match - aBC -No match - -/a(?i:b)*c/ - aBc - 0: aBc - aBBc - 0: aBBc - *** Failers -No match - aBC -No match - aBBC -No match - -/a(?=b(?i)c)\w\wd/ - abcd - 0: abcd - abCd - 0: abCd - *** Failers -No match - aBCd -No match - abcD -No match - -/(?s-i:more.*than).*million/i - more than million - 0: more than million - more than MILLION - 0: more than MILLION - more \n than Million - 0: more \x0a than Million - *** Failers -No match - MORE THAN MILLION -No match - more \n than \n million -No match - -/(?:(?s-i)more.*than).*million/i - more than million - 0: more than million - more than MILLION - 0: more than MILLION - more \n than Million - 0: more \x0a than Million - *** Failers -No match - MORE THAN MILLION -No match - more \n than \n million -No match - -/(?>a(?i)b+)+c/ - abc - 0: abc - aBbc - 0: aBbc - aBBc - 0: aBBc - *** Failers -No match - Abc -No match - abAb -No match - abbC -No match - -/(?=a(?i)b)\w\wc/ - abc - 0: abc - aBc - 0: aBc - *** Failers -No match - Ab -No match - abC -No match - aBC -No match - -/(?<=a(?i)b)(\w\w)c/ - abxxc - 0: xxc - 1: xx - aBxxc - 0: xxc - 1: xx - *** Failers -No match - Abxxc -No match - ABxxc -No match - abxxC -No match - -/(?:(a)|b)(?(1)A|B)/ - aA - 0: aA - 1: a - bB - 0: bB - *** Failers -No match - aB -No match - bA -No match - -/^(a)?(?(1)a|b)+$/ - aa - 0: aa - 1: a - b - 0: b - bb - 0: bb - *** Failers -No match - ab -No match - -/^(?(?=abc)\w{3}:|\d\d)$/ - abc: - 0: abc: - 12 - 0: 12 - *** Failers -No match - 123 -No match - xyz -No match - -/^(?(?!abc)\d\d|\w{3}:)$/ - abc: - 0: abc: - 12 - 0: 12 - *** Failers -No match - 123 -No match - xyz -No match - -/(?(?<=foo)bar|cat)/ - foobar - 0: bar - cat - 0: cat - fcat - 0: cat - focat - 0: cat - *** Failers -No match - foocat -No match - -/(?(?a*)*/ - a - 0: a - aa - 0: aa - aaaa - 0: aaaa - -/(abc|)+/ - abc - 0: abc - 1: - abcabc - 0: abcabc - 1: - abcabcabc - 0: abcabcabc - 1: - xyz - 0: - 1: - -/([a]*)*/ - a - 0: a - 1: - aaaaa - 0: aaaaa - 1: - -/([ab]*)*/ - a - 0: a - 1: - b - 0: b - 1: - ababab - 0: ababab - 1: - aaaabcde - 0: aaaab - 1: - bbbb - 0: bbbb - 1: - -/([^a]*)*/ - b - 0: b - 1: - bbbb - 0: bbbb - 1: - aaa - 0: - 1: - -/([^ab]*)*/ - cccc - 0: cccc - 1: - abab - 0: - 1: - -/([a]*?)*/ - a - 0: - 1: - aaaa - 0: - 1: - -/([ab]*?)*/ - a - 0: - 1: - b - 0: - 1: - abab - 0: - 1: - baba - 0: - 1: - -/([^a]*?)*/ - b - 0: - 1: - bbbb - 0: - 1: - aaa - 0: - 1: - -/([^ab]*?)*/ - c - 0: - 1: - cccc - 0: - 1: - baba - 0: - 1: - -/(?>a*)*/ - a - 0: a - aaabcde - 0: aaa - -/((?>a*))*/ - aaaaa - 0: aaaaa - 1: - aabbaa - 0: aa - 1: - -/((?>a*?))*/ - aaaaa - 0: - 1: - aabbaa - 0: - 1: - -/(?(?=[^a-z]+[a-z]) \d{2}-[a-z]{3}-\d{2} | \d{2}-\d{2}-\d{2} ) /x - 12-sep-98 - 0: 12-sep-98 - 12-09-98 - 0: 12-09-98 - *** Failers -No match - sep-12-98 -No match - -/(?<=(foo))bar\1/ - foobarfoo - 0: barfoo - 1: foo - foobarfootling - 0: barfoo - 1: foo - *** Failers -No match - foobar -No match - barfoo -No match - -/(?i:saturday|sunday)/ - saturday - 0: saturday - sunday - 0: sunday - Saturday - 0: Saturday - Sunday - 0: Sunday - SATURDAY - 0: SATURDAY - SUNDAY - 0: SUNDAY - SunDay - 0: SunDay - -/(a(?i)bc|BB)x/ - abcx - 0: abcx - 1: abc - aBCx - 0: aBCx - 1: aBC - bbx - 0: bbx - 1: bb - BBx - 0: BBx - 1: BB - *** Failers -No match - abcX -No match - aBCX -No match - bbX -No match - BBX -No match - -/^([ab](?i)[cd]|[ef])/ - ac - 0: ac - 1: ac - aC - 0: aC - 1: aC - bD - 0: bD - 1: bD - elephant - 0: e - 1: e - Europe - 0: E - 1: E - frog - 0: f - 1: f - France - 0: F - 1: F - *** Failers -No match - Africa -No match - -/^(ab|a(?i)[b-c](?m-i)d|x(?i)y|z)/ - ab - 0: ab - 1: ab - aBd - 0: aBd - 1: aBd - xy - 0: xy - 1: xy - xY - 0: xY - 1: xY - zebra - 0: z - 1: z - Zambesi - 0: Z - 1: Z - *** Failers -No match - aCD -No match - XY -No match - -/(?<=foo\n)^bar/m - foo\nbar - 0: bar - *** Failers -No match - bar -No match - baz\nbar -No match - -/(?<=(?]&/ - <&OUT - 0: <& - -/^(a\1?){4}$/ - aaaaaaaaaa - 0: aaaaaaaaaa - 1: aaaa - *** Failers -No match - AB -No match - aaaaaaaaa -No match - aaaaaaaaaaa -No match - -/^(a(?(1)\1)){4}$/ - aaaaaaaaaa - 0: aaaaaaaaaa - 1: aaaa - *** Failers -No match - aaaaaaaaa -No match - aaaaaaaaaaa -No match - -/(?:(f)(o)(o)|(b)(a)(r))*/ - foobar - 0: foobar - 1: f - 2: o - 3: o - 4: b - 5: a - 6: r - -/(?<=a)b/ - ab - 0: b - *** Failers -No match - cb -No match - b -No match - -/(? - 2: abcd - xy:z:::abcd - 0: xy:z:::abcd - 1: xy:z::: - 2: abcd - -/^[^bcd]*(c+)/ - aexycd - 0: aexyc - 1: c - -/(a*)b+/ - caab - 0: aab - 1: aa - -/([\w:]+::)?(\w+)$/ - abcd - 0: abcd - 1: - 2: abcd - xy:z:::abcd - 0: xy:z:::abcd - 1: xy:z::: - 2: abcd - *** Failers - 0: Failers - 1: - 2: Failers - abcd: -No match - abcd: -No match - -/^[^bcd]*(c+)/ - aexycd - 0: aexyc - 1: c - -/(>a+)ab/ - -/(?>a+)b/ - aaab - 0: aaab - -/([[:]+)/ - a:[b]: - 0: :[ - 1: :[ - -/([[=]+)/ - a=[b]= - 0: =[ - 1: =[ - -/([[.]+)/ - a.[b]. - 0: .[ - 1: .[ - -/((?>a+)b)/ - aaab - 0: aaab - 1: aaab - -/(?>(a+))b/ - aaab - 0: aaab - 1: aaa - -/((?>[^()]+)|\([^()]*\))+/ - ((abc(ade)ufh()()x - 0: abc(ade)ufh()()x - 1: x - -/a\Z/ - *** Failers -No match - aaab -No match - a\nb\n -No match - -/b\Z/ - a\nb\n - 0: b - -/b\z/ - -/b\Z/ - a\nb - 0: b - -/b\z/ - a\nb - 0: b - *** Failers -No match - -/^(?>(?(1)\.|())[^\W_](?>[a-z0-9-]*[^\W_])?)+$/ - a - 0: a - 1: - abc - 0: abc - 1: - a-b - 0: a-b - 1: - 0-9 - 0: 0-9 - 1: - a.b - 0: a.b - 1: - 5.6.7 - 0: 5.6.7 - 1: - the.quick.brown.fox - 0: the.quick.brown.fox - 1: - a100.b200.300c - 0: a100.b200.300c - 1: - 12-ab.1245 - 0: 12-ab.1245 - 1: - ***Failers -No match - \ -No match - .a -No match - -a -No match - a- -No match - a. -No match - a_b -No match - a.- -No match - a.. -No match - ab..bc -No match - the.quick.brown.fox- -No match - the.quick.brown.fox. -No match - the.quick.brown.fox_ -No match - the.quick.brown.fox+ -No match - -/(?>.*)(?<=(abcd|wxyz))/ - alphabetabcd - 0: alphabetabcd - 1: abcd - endingwxyz - 0: endingwxyz - 1: wxyz - *** Failers -No match - a rather long string that doesn't end with one of them -No match - -/word (?>(?:(?!otherword)[a-zA-Z0-9]+ ){0,30})otherword/ - word cat dog elephant mussel cow horse canary baboon snake shark otherword - 0: word cat dog elephant mussel cow horse canary baboon snake shark otherword - word cat dog elephant mussel cow horse canary baboon snake shark -No match - -/word (?>[a-zA-Z0-9]+ ){0,30}otherword/ - word cat dog elephant mussel cow horse canary baboon snake shark the quick brown fox and the lazy dog and several other words getting close to thirty by now I hope -No match - -/(?<=\d{3}(?!999))foo/ - 999foo - 0: foo - 123999foo - 0: foo - *** Failers -No match - 123abcfoo -No match - -/(?<=(?!...999)\d{3})foo/ - 999foo - 0: foo - 123999foo - 0: foo - *** Failers -No match - 123abcfoo -No match - -/(?<=\d{3}(?!999)...)foo/ - 123abcfoo - 0: foo - 123456foo - 0: foo - *** Failers -No match - 123999foo -No match - -/(?<=\d{3}...)(? - 2: - 3: abcd - - 2: - 3: abcd - \s*)=(?>\s*) # find - 2: - 3: abcd -