# # # delete "pcre/pcre.h" # # delete "pcre/pcre_config.h" # # rename "pcre/README" # to "pcre/README.monotone" # # add_dir "pcre/testdata" # # add_file "pcre/AUTHORS" # content [0a6869fdafea3787010242cafd48566bd5bf3822] # # add_file "pcre/ChangeLog" # content [14e1741ce6683161f3ee88513de088477610bd30] # # add_file "pcre/HACKING" # content [cacc10be9c2edc7f1aec03a9fd0bc6f4894bdd71] # # add_file "pcre/LICENCE" # content [c5acb2598e023ab1d8b4ac2db0914c70f0f89765] # # add_file "pcre/NEWS" # content [e2e595652eb911e9efaa93148c4db4b984145b90] # # add_file "pcre/NON-UNIX-USE" # content [12b5c9442fc316b6a0b30e91bbfe2eae2355d045] # # add_file "pcre/README" # content [7897b63cee2850ff1ca833886101d23a2505c097] # # add_file "pcre/RunGrepTest" # content [77b7b1753167de06e81dab91ff81664f4659ccf4] # # add_file "pcre/RunTest" # content [18799bc463805cdf4a832bc5b813a4df1906f8ee] # # add_file "pcre/libpcre.pc.in" # content [de06c34023f57c74ddf5fc9789b94e9d24356d2b] # # add_file "pcre/pcre-config.in" # content [b7e2758681ecb746ecca102f8890cbdcd5fbf0a0] # # add_file "pcre/pcre.h.in" # content [2148860d34970adc8d64287f983388b9a9a3b90d] # # add_file "pcre/pcre_printint.src" # content [fc4f01edd2cece38438822fbd7c7e44f3e60a3ff] # # add_file "pcre/pcregrep.c" # content [0b275ab7db5158f115c94f5eab55b544cbc48dfc] # # add_file "pcre/pcreposix.c" # content [f6a92b5557f732f33174f3ab9ceb7bfb5b2de84c] # # add_file "pcre/pcreposix.h" # content [addb29678ba48228a35a1615fc20594a0491eb9b] # # add_file "pcre/pcretest.c" # content [7e8d2a6a44eabedd1d7d38c1ea84bb569a3aef29] # # add_file "pcre/perltest.pl" # content [3d543a0df21fd56f18c11f12a781fbdd88e896a9] # # add_file "pcre/testdata/grepinput" # content [2b4fbed95a5558d5e26a144f533161690ea898fb] # # add_file "pcre/testdata/grepinput8" # content [9d5c883e6983fda4de43a652c139c0c3f669fc81] # # add_file "pcre/testdata/grepinputv" # content [0e3301f9c1e83edf2d14d28d633a05f590a8b883] # # add_file "pcre/testdata/grepinputx" # content [030ddb5e5fed1effe5c0f091564905cfa180360d] # # add_file "pcre/testdata/greplist" # content [4d254ae0639c86a42acd3597bd17ed9952cdd1b6] # # add_file "pcre/testdata/grepoutput" # content [496871212fa08f3ae148157a958abced53f82ba1] # # add_file "pcre/testdata/grepoutput8" # content [a4ac385a152e8059e61ad4fad232a2b9d6626be0] # # add_file "pcre/testdata/grepoutputN" # content [5a63ff41c215a35c4f24230efff9aa0476b8a7cb] # # add_file "pcre/testdata/testinput1" # content [fbff0a02d34292e714926f48610e54abadab73cb] # # add_file "pcre/testdata/testinput10" # content [1f1b05d42e2d0c8b9204fb3386a9becea2c148fa] # # add_file "pcre/testdata/testinput2" # content [38b626ec78ec4bb1e340a7a7de1adc6bf68cd29e] # # add_file "pcre/testdata/testinput3" # content [5da96df2879fa0d8b46dd2bfae3514a5e787b721] # # add_file "pcre/testdata/testinput4" # content [69926fa19d1d52326720485ba9599bf2ba83647b] # # add_file "pcre/testdata/testinput5" # content [831b6bdf626dd414715c339efe3dd17e3ddfbf35] # # add_file "pcre/testdata/testinput6" # content [6fb7d308bae37cdb1036002e102b1abf35e94ce2] # # add_file "pcre/testdata/testinput7" # content [ab83b1c56e8cde03dce8f3b0ebf5dae2d3bf781e] # # add_file "pcre/testdata/testinput8" # content [093f7be73e2abafdc80b27118e73c91af35de039] # # add_file "pcre/testdata/testinput9" # content [759482b0f140104cc0ffa7614dc22ac4151e43ff] # # add_file "pcre/testdata/testoutput1" # content [7f49698c6e01158633a5dbe609828263a27ad765] # # add_file "pcre/testdata/testoutput10" # content [e9dcc074057a61b51f3ff2b717ee97664933d1b6] # # add_file "pcre/testdata/testoutput2" # content [395e58b959ef57672eed4ff095fdb3ab64cb6801] # # add_file "pcre/testdata/testoutput3" # content [3263045b5c40030a01d2b28f8b719853423806dc] # # add_file "pcre/testdata/testoutput4" # content [c6e830eb2fa45f6cd1961fc88d4ca9a63cf6f1b9] # # add_file "pcre/testdata/testoutput5" # content [28f6c3ad4fdce2d334745ca505ec2045a90c9860] # # add_file "pcre/testdata/testoutput6" # content [6dcc68e8f1e3a9303f845c8c5f7742b53326c7c9] # # add_file "pcre/testdata/testoutput7" # content [c6238bcfb0787c277cf5aaf4041d23a6242ed87a] # # add_file "pcre/testdata/testoutput8" # content [8e1da687952041359d64e7737984a11bfcc4ec27] # # add_file "pcre/testdata/testoutput9" # content [05ca3a0c9ba18ce295485db9aa6c169414b962d8] # # add_file "pcre/testdata/wintestinput3" # content [f97066de294d2afdd41d845e5aab61839a2e7357] # # add_file "pcre/testdata/wintestoutput3" # content [bca3918ac3ffe14f168eb2ed1359fb5b1062269a] # # patch "pcre/Makefile.am" # from [c98bdfd14eec6c05e7dc9d469f5e6adfe3764aac] # to [528e12a68cb3126ff7d9be07c9191af9563c7603] # # patch "pcre/README.monotone" # from [420b5f8ab281ef77f9caa6cde682d24ea5f68322] # to [d7f7b32bbfd398885310a4a42ab1311e33891843] # # patch "pcre/configure.ac" # from [04d79c5a15950d1a813dc6bd64ca4f89aa7cb412] # to [5572186007517c995ada22a89658b3bf65a5b8b2] # # patch "pcre/pcre_compile.c" # from [3a08469385200a7e1bee6f35399a1494aa50611a] # to [717d57cf17c0f05684269e1ac4100fc1df7f16ba] # # patch "pcre/pcre_config.c" # from [fe26da3d3d90d22d5d90c330858ee2628c395892] # to [b9135c9f9870623f17a8d274ad36bfd315447855] # # patch "pcre/pcre_dfa_exec.c" # from [2fbee25dff3b1a89178c7666cc57d8ffa3850462] # to [376b18542aa834a63cd47003295306d5eaea322d] # # patch "pcre/pcre_exec.c" # from [5d79ad415ec123623b0d8bfced2f87f93f13ed3e] # to [88f40e08b80f3352e2c07822f596f494d4769f3c] # # patch "pcre/pcre_fullinfo.c" # from [cfe87732c2a7ff49b946b0cef32a94201b6d5d8a] # to [11e0fc5840d2bf6318d2048455e8a0c80706743d] # # patch "pcre/pcre_get.c" # from [d1400b33a0738dc2fd25f675c09017c1008c2df5] # to [46b3af9367c4a4f314344ca2eef136e610389649] # # patch "pcre/pcre_globals.c" # from [8fe626d0db539f06b1161166b7c434178c2392b0] # to [f15e191815d7e7ce0b71476016273ece9e84a1ac] # # patch "pcre/pcre_info.c" # from [b767abb2c7478d4dfd810e8dad698086881d9166] # to [7cc6f8c9165fde021f74d7488d554f5dbde4bfc8] # # patch "pcre/pcre_maketables.c" # from [8036b1f3772cf076c761fb8bbaaabb312d681e59] # to [9926176a28fc0c094e4312ac77be2c97a0ba8111] # # patch "pcre/pcre_newline.c" # from [88f9b74f1dcfab4da15e7ca2e0acc76deded42a7] # to [bdecd4910fe61c4de58f0e7f0ab064d2253d7eb1] # # patch "pcre/pcre_ord2utf8.c" # from [dfa43ef059a1d075f09a82e402836d1980d695b1] # to [9419dc8d0b1d864a291dde1f95b90067bcddc40b] # # patch "pcre/pcre_refcount.c" # from [2b18333691e83b9a3745bb18688e7a38f864a3ab] # to [bcc91ccd753e74e0622e8b4283b65ec4b8a83df1] # # patch "pcre/pcre_study.c" # from [43df641947553eec2c8487b9b42cdc6ad2c5a86c] # to [add82fa25791c05b3746fee7975e33bb6f45746d] # # patch "pcre/pcre_tables.c" # from [556d518067a568f8e9f8326d70c8207f7db0efc9] # to [b8b5097a22552f0f161680d8d372cbc3a2b1d6e4] # # patch "pcre/pcre_try_flipped.c" # from [194ea39ba5e0cc8cad7c9571b2fe39a607d68a17] # to [1c7ae4d77bc9fb02017512af57891627f19bba23] # # patch "pcre/pcre_ucp_searchfuncs.c" # from [da98ce81b5a387c0240a1d4c4fc571957f83a340] # to [af3f027bac5fa5f2aa0833726a7698392f3f3725] # # patch "pcre/pcre_valid_utf8.c" # from [f4354314ba53b3caaec709d8aa4868bd387530fc] # to [d42b3714d30fa6b7247c7af16dbb129e33293a3f] # # patch "pcre/pcre_version.c" # from [97d0df5b29a822927867080761143b73b95538ff] # to [eac130667745f0a3f0374bab7cca39dc0d99cee4] # # patch "pcre/pcre_xclass.c" # from [a62818c3e4c06be6a798b02a9cacfe443ca7e6d8] # to [df695a32824e47b978c4ee69efacfc8d78ac63d7] # # set "pcre/RunGrepTest" # attr "mtn:execute" # value "true" # # set "pcre/RunTest" # attr "mtn:execute" # value "true" # # set "pcre/perltest.pl" # attr "mtn:execute" # value "true" # ============================================================ --- pcre/AUTHORS 0a6869fdafea3787010242cafd48566bd5bf3822 +++ pcre/AUTHORS 0a6869fdafea3787010242cafd48566bd5bf3822 @@ -0,0 +1,23 @@ +THE MAIN PCRE LIBRARY +--------------------- + +Written by: Philip Hazel +Email local part: ph10 +Email domain: cam.ac.uk + +University of Cambridge Computing Service, +Cambridge, England. + +Copyright (c) 1997-2008 University of Cambridge +All rights reserved + + +THE C++ WRAPPER LIBRARY +----------------------- + +Written by: Google Inc. + +Copyright (c) 2007-2008 Google Inc +All rights reserved + +#### ============================================================ --- pcre/ChangeLog 14e1741ce6683161f3ee88513de088477610bd30 +++ pcre/ChangeLog 14e1741ce6683161f3ee88513de088477610bd30 @@ -0,0 +1,3200 @@ +ChangeLog for PCRE +------------------ + +Version 7.6 28-Jan-08 +--------------------- + +1. A character class containing a very large number of characters with + codepoints greater than 255 (in UTF-8 mode, of course) caused a buffer + overflow. + +2. Patch to cut out the "long long" test in pcrecpp_unittest when + HAVE_LONG_LONG is not defined. + +3. Applied Christian Ehrlicher's patch to update the CMake build files to + bring them up to date and include new features. This patch includes: + + - Fixed PH's badly added libz and libbz2 support. + - Fixed a problem with static linking. + - Added pcredemo. [But later removed - see 7 below.] + - Fixed dftables problem and added an option. + - Added a number of HAVE_XXX tests, including HAVE_WINDOWS_H and + HAVE_LONG_LONG. + - Added readline support for pcretest. + - Added an listing of the option settings after cmake has run. + +4. A user submitted a patch to Makefile that makes it easy to create + "pcre.dll" under mingw when using Configure/Make. I added stuff to + Makefile.am that cause it to include this special target, without + affecting anything else. Note that the same mingw target plus all + the other distribution libraries and programs are now supported + when configuring with CMake (see 6 below) instead of with + Configure/Make. + +5. Applied Craig's patch that moves no_arg into the RE class in the C++ code. + This is an attempt to solve the reported problem "pcrecpp::no_arg is not + exported in the Windows port". It has not yet been confirmed that the patch + solves the problem, but it does no harm. + +6. Applied Sheri's patch to CMakeLists.txt to add NON_STANDARD_LIB_PREFIX and + NON_STANDARD_LIB_SUFFIX for dll names built with mingw when configured + with CMake, and also correct the comment about stack recursion. + +7. Remove the automatic building of pcredemo from the ./configure system and + from CMakeLists.txt. The whole idea of pcredemo.c is that it is an example + of a program that users should build themselves after PCRE is installed, so + building it automatically is not really right. What is more, it gave + trouble in some build environments. + +8. Further tidies to CMakeLists.txt from Sheri and Christian. + + +Version 7.5 10-Jan-08 +--------------------- + +1. Applied a patch from Craig: "This patch makes it possible to 'ignore' + values in parens when parsing an RE using the C++ wrapper." + +2. Negative specials like \S did not work in character classes in UTF-8 mode. + Characters greater than 255 were excluded from the class instead of being + included. + +3. The same bug as (2) above applied to negated POSIX classes such as + [:^space:]. + +4. PCRECPP_STATIC was referenced in pcrecpp_internal.h, but nowhere was it + defined or documented. It seems to have been a typo for PCRE_STATIC, so + I have changed it. + +5. The construct (?&) was not diagnosed as a syntax error (it referenced the + first named subpattern) and a construct such as (?&a) would reference the + first named subpattern whose name started with "a" (in other words, the + length check was missing). Both these problems are fixed. "Subpattern name + expected" is now given for (?&) (a zero-length name), and this patch also + makes it give the same error for \k'' (previously it complained that that + was a reference to a non-existent subpattern). + +6. The erroneous patterns (?+-a) and (?-+a) give different error messages; + this is right because (?- can be followed by option settings as well as by + digits. I have, however, made the messages clearer. + +7. Patterns such as (?(1)a|b) (a pattern that contains fewer subpatterns + than the number used in the conditional) now cause a compile-time error. + This is actually not compatible with Perl, which accepts such patterns, but + treats the conditional as always being FALSE (as PCRE used to), but it + seems to me that giving a diagnostic is better. + +8. Change "alphameric" to the more common word "alphanumeric" in comments + and messages. + +9. Fix two occurrences of "backslash" in comments that should have been + "backspace". + +10. Remove two redundant lines of code that can never be obeyed (their function + was moved elsewhere). + +11. The program that makes PCRE's Unicode character property table had a bug + which caused it to generate incorrect table entries for sequences of + characters that have the same character type, but are in different scripts. + It amalgamated them into a single range, with the script of the first of + them. In other words, some characters were in the wrong script. There were + thirteen such cases, affecting characters in the following ranges: + + U+002b0 - U+002c1 + U+0060c - U+0060d + U+0061e - U+00612 + U+0064b - U+0065e + U+0074d - U+0076d + U+01800 - U+01805 + U+01d00 - U+01d77 + U+01d9b - U+01dbf + U+0200b - U+0200f + U+030fc - U+030fe + U+03260 - U+0327f + U+0fb46 - U+0fbb1 + U+10450 - U+1049d + +12. The -o option (show only the matching part of a line) for pcregrep was not + compatible with GNU grep in that, if there was more than one match in a + line, it showed only the first of them. It now behaves in the same way as + GNU grep. + +13. If the -o and -v options were combined for pcregrep, it printed a blank + line for every non-matching line. GNU grep prints nothing, and pcregrep now + does the same. The return code can be used to tell if there were any + non-matching lines. + +14. Added --file-offsets and --line-offsets to pcregrep. + +15. The pattern (?=something)(?R) was not being diagnosed as a potentially + infinitely looping recursion. The bug was that positive lookaheads were not + being skipped when checking for a possible empty match (negative lookaheads + and both kinds of lookbehind were skipped). + +16. Fixed two typos in the Windows-only code in pcregrep.c, and moved the + inclusion of to before rather than after the definition of + INVALID_FILE_ATTRIBUTES (patch from David Byron). + +17. Specifying a possessive quantifier with a specific limit for a Unicode + character property caused pcre_compile() to compile bad code, which led at + runtime to PCRE_ERROR_INTERNAL (-14). Examples of patterns that caused this + are: /\p{Zl}{2,3}+/8 and /\p{Cc}{2}+/8. It was the possessive "+" that + caused the error; without that there was no problem. + +18. Added --enable-pcregrep-libz and --enable-pcregrep-libbz2. + +19. Added --enable-pcretest-libreadline. + +20. In pcrecpp.cc, the variable 'count' was incremented twice in + RE::GlobalReplace(). As a result, the number of replacements returned was + double what it should be. I removed one of the increments, but Craig sent a + later patch that removed the other one (the right fix) and added unit tests + that check the return values (which was not done before). + +21. Several CMake things: + + (1) Arranged that, when cmake is used on Unix, the libraries end up with + the names libpcre and libpcreposix, not just pcre and pcreposix. + + (2) The above change means that pcretest and pcregrep are now correctly + linked with the newly-built libraries, not previously installed ones. + + (3) Added PCRE_SUPPORT_LIBREADLINE, PCRE_SUPPORT_LIBZ, PCRE_SUPPORT_LIBBZ2. + +22. In UTF-8 mode, with newline set to "any", a pattern such as .*a.*=.b.* + crashed when matching a string such as a\x{2029}b (note that \x{2029} is a + UTF-8 newline character). The key issue is that the pattern starts .*; + this means that the match must be either at the beginning, or after a + newline. The bug was in the code for advancing after a failed match and + checking that the new position followed a newline. It was not taking + account of UTF-8 characters correctly. + +23. PCRE was behaving differently from Perl in the way it recognized POSIX + character classes. PCRE was not treating the sequence [:...:] as a + character class unless the ... were all letters. Perl, however, seems to + allow any characters between [: and :], though of course it rejects as + unknown any "names" that contain non-letters, because all the known class + names consist only of letters. Thus, Perl gives an error for [[:1234:]], + for example, whereas PCRE did not - it did not recognize a POSIX character + class. This seemed a bit dangerous, so the code has been changed to be + closer to Perl. The behaviour is not identical to Perl, because PCRE will + diagnose an unknown class for, for example, [[:l\ower:]] where Perl will + treat it as [[:lower:]]. However, PCRE does now give "unknown" errors where + Perl does, and where it didn't before. + +24. Rewrite so as to remove the single use of %n from pcregrep because in some + Windows environments %n is disabled by default. + + +Version 7.4 21-Sep-07 +--------------------- + +1. Change 7.3/28 was implemented for classes by looking at the bitmap. This + means that a class such as [\s] counted as "explicit reference to CR or + LF". That isn't really right - the whole point of the change was to try to + help when there was an actual mention of one of the two characters. So now + the change happens only if \r or \n (or a literal CR or LF) character is + encountered. + +2. The 32-bit options word was also used for 6 internal flags, but the numbers + of both had grown to the point where there were only 3 bits left. + Fortunately, there was spare space in the data structure, and so I have + moved the internal flags into a new 16-bit field to free up more option + bits. + +3. The appearance of (?J) at the start of a pattern set the DUPNAMES option, + but did not set the internal JCHANGED flag - either of these is enough to + control the way the "get" function works - but the PCRE_INFO_JCHANGED + facility is supposed to tell if (?J) was ever used, so now (?J) at the + start sets both bits. + +4. Added options (at build time, compile time, exec time) to change \R from + matching any Unicode line ending sequence to just matching CR, LF, or CRLF. + +5. doc/pcresyntax.html was missing from the distribution. + +6. Put back the definition of PCRE_ERROR_NULLWSLIMIT, for backward + compatibility, even though it is no longer used. + +7. Added macro for snprintf to pcrecpp_unittest.cc and also for strtoll and + strtoull to pcrecpp.cc to select the available functions in WIN32 when the + windows.h file is present (where different names are used). [This was + reversed later after testing - see 16 below.] + +8. Changed all #include to #include "config.h". There were also + some further cases that I changed to "pcre.h". + +9. When pcregrep was used with the --colour option, it missed the line ending + sequence off the lines that it output. + +10. It was pointed out to me that arrays of string pointers cause lots of + relocations when a shared library is dynamically loaded. A technique of + using a single long string with a table of offsets can drastically reduce + these. I have refactored PCRE in four places to do this. The result is + dramatic: + + Originally: 290 + After changing UCP table: 187 + After changing error message table: 43 + After changing table of "verbs" 36 + After changing table of Posix names 22 + + Thanks to the folks working on Gregex for glib for this insight. + +11. --disable-stack-for-recursion caused compiling to fail unless -enable- + unicode-properties was also set. + +12. Updated the tests so that they work when \R is defaulted to ANYCRLF. + +13. Added checks for ANY and ANYCRLF to pcrecpp.cc where it previously + checked only for CRLF. + +14. Added casts to pcretest.c to avoid compiler warnings. + +15. Added Craig's patch to various pcrecpp modules to avoid compiler warnings. + +16. Added Craig's patch to remove the WINDOWS_H tests, that were not working, + and instead check for _strtoi64 explicitly, and avoid the use of snprintf() + entirely. This removes changes made in 7 above. + +17. The CMake files have been updated, and there is now more information about + building with CMake in the NON-UNIX-USE document. + + +Version 7.3 28-Aug-07 +--------------------- + + 1. In the rejigging of the build system that eventually resulted in 7.1, the + line "#include " was included in pcre_internal.h. The use of angle + brackets there is not right, since it causes compilers to look for an + installed pcre.h, not the version that is in the source that is being + compiled (which of course may be different). I have changed it back to: + + #include "pcre.h" + + I have a vague recollection that the change was concerned with compiling in + different directories, but in the new build system, that is taken care of + by the VPATH setting the Makefile. + + 2. The pattern .*$ when run in not-DOTALL UTF-8 mode with newline=any failed + when the subject happened to end in the byte 0x85 (e.g. if the last + character was \x{1ec5}). *Character* 0x85 is one of the "any" newline + characters but of course it shouldn't be taken as a newline when it is part + of another character. The bug was that, for an unlimited repeat of . in + not-DOTALL UTF-8 mode, PCRE was advancing by bytes rather than by + characters when looking for a newline. + + 3. A small performance improvement in the DOTALL UTF-8 mode .* case. + + 4. Debugging: adjusted the names of opcodes for different kinds of parentheses + in debug output. + + 5. Arrange to use "%I64d" instead of "%lld" and "%I64u" instead of "%llu" for + long printing in the pcrecpp unittest when running under MinGW. + + 6. ESC_K was left out of the EBCDIC table. + + 7. Change 7.0/38 introduced a new limit on the number of nested non-capturing + parentheses; I made it 1000, which seemed large enough. Unfortunately, the + limit also applies to "virtual nesting" when a pattern is recursive, and in + this case 1000 isn't so big. I have been able to remove this limit at the + expense of backing off one optimization in certain circumstances. Normally, + when pcre_exec() would call its internal match() function recursively and + immediately return the result unconditionally, it uses a "tail recursion" + feature to save stack. However, when a subpattern that can match an empty + string has an unlimited repetition quantifier, it no longer makes this + optimization. That gives it a stack frame in which to save the data for + checking that an empty string has been matched. Previously this was taken + from the 1000-entry workspace that had been reserved. So now there is no + explicit limit, but more stack is used. + + 8. Applied Daniel's patches to solve problems with the import/export magic + syntax that is required for Windows, and which was going wrong for the + pcreposix and pcrecpp parts of the library. These were overlooked when this + problem was solved for the main library. + + 9. There were some crude static tests to avoid integer overflow when computing + the size of patterns that contain repeated groups with explicit upper + limits. As the maximum quantifier is 65535, the maximum group length was + set at 30,000 so that the product of these two numbers did not overflow a + 32-bit integer. However, it turns out that people want to use groups that + are longer than 30,000 bytes (though not repeat them that many times). + Change 7.0/17 (the refactoring of the way the pattern size is computed) has + made it possible to implement the integer overflow checks in a much more + dynamic way, which I have now done. The artificial limitation on group + length has been removed - we now have only the limit on the total length of + the compiled pattern, which depends on the LINK_SIZE setting. + +10. Fixed a bug in the documentation for get/copy named substring when + duplicate names are permitted. If none of the named substrings are set, the + functions return PCRE_ERROR_NOSUBSTRING (7); the doc said they returned an + empty string. + +11. Because Perl interprets \Q...\E at a high level, and ignores orphan \E + instances, patterns such as [\Q\E] or [\E] or even [^\E] cause an error, + because the ] is interpreted as the first data character and the + terminating ] is not found. PCRE has been made compatible with Perl in this + regard. Previously, it interpreted [\Q\E] as an empty class, and [\E] could + cause memory overwriting. + +10. Like Perl, PCRE automatically breaks an unlimited repeat after an empty + string has been matched (to stop an infinite loop). It was not recognizing + a conditional subpattern that could match an empty string if that + subpattern was within another subpattern. For example, it looped when + trying to match (((?(1)X|))*) but it was OK with ((?(1)X|)*) where the + condition was not nested. This bug has been fixed. + +12. A pattern like \X?\d or \P{L}?\d in non-UTF-8 mode could cause a backtrack + past the start of the subject in the presence of bytes with the top bit + set, for example "\x8aBCD". + +13. Added Perl 5.10 experimental backtracking controls (*FAIL), (*F), (*PRUNE), + (*SKIP), (*THEN), (*COMMIT), and (*ACCEPT). + +14. Optimized (?!) to (*FAIL). + +15. Updated the test for a valid UTF-8 string to conform to the later RFC 3629. + This restricts code points to be within the range 0 to 0x10FFFF, excluding + the "low surrogate" sequence 0xD800 to 0xDFFF. Previously, PCRE allowed the + full range 0 to 0x7FFFFFFF, as defined by RFC 2279. Internally, it still + does: it's just the validity check that is more restrictive. + +16. Inserted checks for integer overflows during escape sequence (backslash) + processing, and also fixed erroneous offset values for syntax errors during + backslash processing. + +17. Fixed another case of looking too far back in non-UTF-8 mode (cf 12 above) + for patterns like [\PPP\x8a]{1,}\x80 with the subject "A\x80". + +18. An unterminated class in a pattern like (?1)\c[ with a "forward reference" + caused an overrun. + +19. A pattern like (?:[\PPa*]*){8,} which had an "extended class" (one with + something other than just ASCII characters) inside a group that had an + unlimited repeat caused a loop at compile time (while checking to see + whether the group could match an empty string). + +20. Debugging a pattern containing \p or \P could cause a crash. For example, + [\P{Any}] did so. (Error in the code for printing property names.) + +21. An orphan \E inside a character class could cause a crash. + +22. A repeated capturing bracket such as (A)? could cause a wild memory + reference during compilation. + +23. There are several functions in pcre_compile() that scan along a compiled + expression for various reasons (e.g. to see if it's fixed length for look + behind). There were bugs in these functions when a repeated \p or \P was + present in the pattern. These operators have additional parameters compared + with \d, etc, and these were not being taken into account when moving along + the compiled data. Specifically: + + (a) A item such as \p{Yi}{3} in a lookbehind was not treated as fixed + length. + + (b) An item such as \pL+ within a repeated group could cause crashes or + loops. + + (c) A pattern such as \p{Yi}+(\P{Yi}+)(?1) could give an incorrect + "reference to non-existent subpattern" error. + + (d) A pattern like (\P{Yi}{2}\277)? could loop at compile time. + +24. A repeated \S or \W in UTF-8 mode could give wrong answers when multibyte + characters were involved (for example /\S{2}/8g with "A\x{a3}BC"). + +25. Using pcregrep in multiline, inverted mode (-Mv) caused it to loop. + +26. Patterns such as [\P{Yi}A] which include \p or \P and just one other + character were causing crashes (broken optimization). + +27. Patterns such as (\P{Yi}*\277)* (group with possible zero repeat containing + \p or \P) caused a compile-time loop. + +28. More problems have arisen in unanchored patterns when CRLF is a valid line + break. For example, the unstudied pattern [\r\n]A does not match the string + "\r\nA" because change 7.0/46 below moves the current point on by two + characters after failing to match at the start. However, the pattern \nA + *does* match, because it doesn't start till \n, and if [\r\n]A is studied, + the same is true. There doesn't seem any very clean way out of this, but + what I have chosen to do makes the common cases work: PCRE now takes note + of whether there can be an explicit match for \r or \n anywhere in the + pattern, and if so, 7.0/46 no longer applies. As part of this change, + there's a new PCRE_INFO_HASCRORLF option for finding out whether a compiled + pattern has explicit CR or LF references. + +29. Added (*CR) etc for changing newline setting at start of pattern. + + +Version 7.2 19-Jun-07 +--------------------- + + 1. If the fr_FR locale cannot be found for test 3, try the "french" locale, + which is apparently normally available under Windows. + + 2. Re-jig the pcregrep tests with different newline settings in an attempt + to make them independent of the local environment's newline setting. + + 3. Add code to configure.ac to remove -g from the CFLAGS default settings. + + 4. Some of the "internals" tests were previously cut out when the link size + was not 2, because the output contained actual offsets. The recent new + "Z" feature of pcretest means that these can be cut out, making the tests + usable with all link sizes. + + 5. Implemented Stan Switzer's goto replacement for longjmp() when not using + stack recursion. This gives a massive performance boost under BSD, but just + a small improvement under Linux. However, it saves one field in the frame + in all cases. + + 6. Added more features from the forthcoming Perl 5.10: + + (a) (?-n) (where n is a string of digits) is a relative subroutine or + recursion call. It refers to the nth most recently opened parentheses. + + (b) (?+n) is also a relative subroutine call; it refers to the nth next + to be opened parentheses. + + (c) Conditions that refer to capturing parentheses can be specified + relatively, for example, (?(-2)... or (?(+3)... + + (d) \K resets the start of the current match so that everything before + is not part of it. + + (e) \k{name} is synonymous with \k and \k'name' (.NET compatible). + + (f) \g{name} is another synonym - part of Perl 5.10's unification of + reference syntax. + + (g) (?| introduces a group in which the numbering of parentheses in each + alternative starts with the same number. + + (h) \h, \H, \v, and \V match horizontal and vertical whitespace. + + 7. Added two new calls to pcre_fullinfo(): PCRE_INFO_OKPARTIAL and + PCRE_INFO_JCHANGED. + + 8. A pattern such as (.*(.)?)* caused pcre_exec() to fail by either not + terminating or by crashing. Diagnosed by Viktor Griph; it was in the code + for detecting groups that can match an empty string. + + 9. A pattern with a very large number of alternatives (more than several + hundred) was running out of internal workspace during the pre-compile + phase, where pcre_compile() figures out how much memory will be needed. A + bit of new cunning has reduced the workspace needed for groups with + alternatives. The 1000-alternative test pattern now uses 12 bytes of + workspace instead of running out of the 4096 that are available. + +10. Inserted some missing (unsigned int) casts to get rid of compiler warnings. + +11. Applied patch from Google to remove an optimization that didn't quite work. + The report of the bug said: + + pcrecpp::RE("a*").FullMatch("aaa") matches, while + pcrecpp::RE("a*?").FullMatch("aaa") does not, and + pcrecpp::RE("a*?\\z").FullMatch("aaa") does again. + +12. If \p or \P was used in non-UTF-8 mode on a character greater than 127 + it matched the wrong number of bytes. + + +Version 7.1 24-Apr-07 +--------------------- + + 1. Applied Bob Rossi and Daniel G's patches to convert the build system to one + that is more "standard", making use of automake and other Autotools. There + is some re-arrangement of the files and adjustment of comments consequent + on this. + + 2. Part of the patch fixed a problem with the pcregrep tests. The test of -r + for recursive directory scanning broke on some systems because the files + are not scanned in any specific order and on different systems the order + was different. A call to "sort" has been inserted into RunGrepTest for the + approprate test as a short-term fix. In the longer term there may be an + alternative. + + 3. I had an email from Eric Raymond about problems translating some of PCRE's + man pages to HTML (despite the fact that I distribute HTML pages, some + people do their own conversions for various reasons). The problems + concerned the use of low-level troff macros .br and .in. I have therefore + removed all such uses from the man pages (some were redundant, some could + be replaced by .nf/.fi pairs). The 132html script that I use to generate + HTML has been updated to handle .nf/.fi and to complain if it encounters + .br or .in. + + 4. Updated comments in configure.ac that get placed in config.h.in and also + arranged for config.h to be included in the distribution, with the name + config.h.generic, for the benefit of those who have to compile without + Autotools (compare pcre.h, which is now distributed as pcre.h.generic). + + 5. Updated the support (such as it is) for Virtual Pascal, thanks to Stefan + Weber: (1) pcre_internal.h was missing some function renames; (2) updated + makevp.bat for the current PCRE, using the additional files + makevp_c.txt, makevp_l.txt, and pcregexp.pas. + + 6. A Windows user reported a minor discrepancy with test 2, which turned out + to be caused by a trailing space on an input line that had got lost in his + copy. The trailing space was an accident, so I've just removed it. + + 7. Add -Wl,-R... flags in pcre-config.in for *BSD* systems, as I'm told + that is needed. + + 8. Mark ucp_table (in ucptable.h) and ucp_gentype (in pcre_ucp_searchfuncs.c) + as "const" (a) because they are and (b) because it helps the PHP + maintainers who have recently made a script to detect big data structures + in the php code that should be moved to the .rodata section. I remembered + to update Builducptable as well, so it won't revert if ucptable.h is ever + re-created. + + 9. Added some extra #ifdef SUPPORT_UTF8 conditionals into pcretest.c, + pcre_printint.src, pcre_compile.c, pcre_study.c, and pcre_tables.c, in + order to be able to cut out the UTF-8 tables in the latter when UTF-8 + support is not required. This saves 1.5-2K of code, which is important in + some applications. + + Later: more #ifdefs are needed in pcre_ord2utf8.c and pcre_valid_utf8.c + so as not to refer to the tables, even though these functions will never be + called when UTF-8 support is disabled. Otherwise there are problems with a + shared library. + +10. Fixed two bugs in the emulated memmove() function in pcre_internal.h: + + (a) It was defining its arguments as char * instead of void *. + + (b) It was assuming that all moves were upwards in memory; this was true + a long time ago when I wrote it, but is no longer the case. + + The emulated memove() is provided for those environments that have neither + memmove() nor bcopy(). I didn't think anyone used it these days, but that + is clearly not the case, as these two bugs were recently reported. + +11. The script PrepareRelease is now distributed: it calls 132html, CleanTxt, + and Detrail to create the HTML documentation, the .txt form of the man + pages, and it removes trailing spaces from listed files. It also creates + pcre.h.generic and config.h.generic from pcre.h and config.h. In the latter + case, it wraps all the #defines with #ifndefs. This script should be run + before "make dist". + +12. Fixed two fairly obscure bugs concerned with quantified caseless matching + with Unicode property support. + + (a) For a maximizing quantifier, if the two different cases of the + character were of different lengths in their UTF-8 codings (there are + some cases like this - I found 11), and the matching function had to + back up over a mixture of the two cases, it incorrectly assumed they + were both the same length. + + (b) When PCRE was configured to use the heap rather than the stack for + recursion during matching, it was not correctly preserving the data for + the other case of a UTF-8 character when checking ahead for a match + while processing a minimizing repeat. If the check also involved + matching a wide character, but failed, corruption could cause an + erroneous result when trying to check for a repeat of the original + character. + +13. Some tidying changes to the testing mechanism: + + (a) The RunTest script now detects the internal link size and whether there + is UTF-8 and UCP support by running ./pcretest -C instead of relying on + values substituted by "configure". (The RunGrepTest script already did + this for UTF-8.) The configure.ac script no longer substitutes the + relevant variables. + + (b) The debugging options /B and /D in pcretest show the compiled bytecode + with length and offset values. This means that the output is different + for different internal link sizes. Test 2 is skipped for link sizes + other than 2 because of this, bypassing the problem. Unfortunately, + there was also a test in test 3 (the locale tests) that used /B and + failed for link sizes other than 2. Rather than cut the whole test out, + I have added a new /Z option to pcretest that replaces the length and + offset values with spaces. This is now used to make test 3 independent + of link size. (Test 2 will be tidied up later.) + +14. If erroroffset was passed as NULL to pcre_compile, it provoked a + segmentation fault instead of returning the appropriate error message. + +15. In multiline mode when the newline sequence was set to "any", the pattern + ^$ would give a match between the \r and \n of a subject such as "A\r\nB". + This doesn't seem right; it now treats the CRLF combination as the line + ending, and so does not match in that case. It's only a pattern such as ^$ + that would hit this one: something like ^ABC$ would have failed after \r + and then tried again after \r\n. + +16. Changed the comparison command for RunGrepTest from "diff -u" to "diff -ub" + in an attempt to make files that differ only in their line terminators + compare equal. This works on Linux. + +17. Under certain error circumstances pcregrep might try to free random memory + as it exited. This is now fixed, thanks to valgrind. + +19. In pcretest, if the pattern /(?m)^$/g was matched against the string + "abc\r\n\r\n", it found an unwanted second match after the second \r. This + was because its rules for how to advance for /g after matching an empty + string at the end of a line did not allow for this case. They now check for + it specially. + +20. pcretest is supposed to handle patterns and data of any length, by + extending its buffers when necessary. It was getting this wrong when the + buffer for a data line had to be extended. + +21. Added PCRE_NEWLINE_ANYCRLF which is like ANY, but matches only CR, LF, or + CRLF as a newline sequence. + +22. Code for handling Unicode properties in pcre_dfa_exec() wasn't being cut + out by #ifdef SUPPORT_UCP. This did no harm, as it could never be used, but + I have nevertheless tidied it up. + +23. Added some casts to kill warnings from HP-UX ia64 compiler. + +24. Added a man page for pcre-config. + + +Version 7.0 19-Dec-06 +--------------------- + + 1. Fixed a signed/unsigned compiler warning in pcre_compile.c, shown up by + moving to gcc 4.1.1. + + 2. The -S option for pcretest uses setrlimit(); I had omitted to #include + sys/time.h, which is documented as needed for this function. It doesn't + seem to matter on Linux, but it showed up on some releases of OS X. + + 3. It seems that there are systems where bytes whose values are greater than + 127 match isprint() in the "C" locale. The "C" locale should be the + default when a C program starts up. In most systems, only ASCII printing + characters match isprint(). This difference caused the output from pcretest + to vary, making some of the tests fail. I have changed pcretest so that: + + (a) When it is outputting text in the compiled version of a pattern, bytes + other than 32-126 are always shown as hex escapes. + + (b) When it is outputting text that is a matched part of a subject string, + it does the same, unless a different locale has been set for the match + (using the /L modifier). In this case, it uses isprint() to decide. + + 4. Fixed a major bug that caused incorrect computation of the amount of memory + required for a compiled pattern when options that changed within the + pattern affected the logic of the preliminary scan that determines the + length. The relevant options are -x, and -i in UTF-8 mode. The result was + that the computed length was too small. The symptoms of this bug were + either the PCRE error "internal error: code overflow" from pcre_compile(), + or a glibc crash with a message such as "pcretest: free(): invalid next + size (fast)". Examples of patterns that provoked this bug (shown in + pcretest format) are: + + /(?-x: )/x + /(?x)(?-x: \s*#\s*)/ + /((?i)[\x{c0}])/8 + /(?i:[\x{c0}])/8 + + HOWEVER: Change 17 below makes this fix obsolete as the memory computation + is now done differently. + + 5. Applied patches from Google to: (a) add a QuoteMeta function to the C++ + wrapper classes; (b) implement a new function in the C++ scanner that is + more efficient than the old way of doing things because it avoids levels of + recursion in the regex matching; (c) add a paragraph to the documentation + for the FullMatch() function. + + 6. The escape sequence \n was being treated as whatever was defined as + "newline". Not only was this contrary to the documentation, which states + that \n is character 10 (hex 0A), but it also went horribly wrong when + "newline" was defined as CRLF. This has been fixed. + + 7. In pcre_dfa_exec.c the value of an unsigned integer (the variable called c) + was being set to -1 for the "end of line" case (supposedly a value that no + character can have). Though this value is never used (the check for end of + line is "zero bytes in current character"), it caused compiler complaints. + I've changed it to 0xffffffff. + + 8. In pcre_version.c, the version string was being built by a sequence of + C macros that, in the event of PCRE_PRERELEASE being defined as an empty + string (as it is for production releases) called a macro with an empty + argument. The C standard says the result of this is undefined. The gcc + compiler treats it as an empty string (which was what was wanted) but it is + reported that Visual C gives an error. The source has been hacked around to + avoid this problem. + + 9. On the advice of a Windows user, included and in Windows + builds of pcretest, and changed the call to _setmode() to use _O_BINARY + instead of 0x8000. Made all the #ifdefs test both _WIN32 and WIN32 (not all + of them did). + +10. Originally, pcretest opened its input and output without "b"; then I was + told that "b" was needed in some environments, so it was added for release + 5.0 to both the input and output. (It makes no difference on Unix-like + systems.) Later I was told that it is wrong for the input on Windows. I've + now abstracted the modes into two macros, to make it easier to fiddle with + them, and removed "b" from the input mode under Windows. + +11. Added pkgconfig support for the C++ wrapper library, libpcrecpp. + +12. Added -help and --help to pcretest as an official way of being reminded + of the options. + +13. Removed some redundant semicolons after macro calls in pcrecpparg.h.in + and pcrecpp.cc because they annoy compilers at high warning levels. + +14. A bit of tidying/refactoring in pcre_exec.c in the main bumpalong loop. + +15. Fixed an occurrence of == in configure.ac that should have been = (shell + scripts are not C programs :-) and which was not noticed because it works + on Linux. + +16. pcretest is supposed to handle any length of pattern and data line (as one + line or as a continued sequence of lines) by extending its input buffer if + necessary. This feature was broken for very long pattern lines, leading to + a string of junk being passed to pcre_compile() if the pattern was longer + than about 50K. + +17. I have done a major re-factoring of the way pcre_compile() computes the + amount of memory needed for a compiled pattern. Previously, there was code + that made a preliminary scan of the pattern in order to do this. That was + OK when PCRE was new, but as the facilities have expanded, it has become + harder and harder to keep it in step with the real compile phase, and there + have been a number of bugs (see for example, 4 above). I have now found a + cunning way of running the real compile function in a "fake" mode that + enables it to compute how much memory it would need, while actually only + ever using a few hundred bytes of working memory and without too many + tests of the mode. This should make future maintenance and development + easier. A side effect of this work is that the limit of 200 on the nesting + depth of parentheses has been removed (though this was never a serious + limitation, I suspect). However, there is a downside: pcre_compile() now + runs more slowly than before (30% or more, depending on the pattern). I + hope this isn't a big issue. There is no effect on runtime performance. + +18. Fixed a minor bug in pcretest: if a pattern line was not terminated by a + newline (only possible for the last line of a file) and it was a + pattern that set a locale (followed by /Lsomething), pcretest crashed. + +19. Added additional timing features to pcretest. (1) The -tm option now times + matching only, not compiling. (2) Both -t and -tm can be followed, as a + separate command line item, by a number that specifies the number of + repeats to use when timing. The default is 50000; this gives better + precision, but takes uncomfortably long for very large patterns. + +20. Extended pcre_study() to be more clever in cases where a branch of a + subpattern has no definite first character. For example, (a*|b*)[cd] would + previously give no result from pcre_study(). Now it recognizes that the + first character must be a, b, c, or d. + +21. There was an incorrect error "recursive call could loop indefinitely" if + a subpattern (or the entire pattern) that was being tested for matching an + empty string contained only one non-empty item after a nested subpattern. + For example, the pattern (?>\x{100}*)\d(?R) provoked this error + incorrectly, because the \d was being skipped in the check. + +22. The pcretest program now has a new pattern option /B and a command line + option -b, which is equivalent to adding /B to every pattern. This causes + it to show the compiled bytecode, without the additional information that + -d shows. The effect of -d is now the same as -b with -i (and similarly, /D + is the same as /B/I). + +23. A new optimization is now able automatically to treat some sequences such + as a*b as a*+b. More specifically, if something simple (such as a character + or a simple class like \d) has an unlimited quantifier, and is followed by + something that cannot possibly match the quantified thing, the quantifier + is automatically "possessified". + +24. A recursive reference to a subpattern whose number was greater than 39 + went wrong under certain circumstances in UTF-8 mode. This bug could also + have affected the operation of pcre_study(). + +25. Realized that a little bit of performance could be had by replacing + (c & 0xc0) == 0xc0 with c >= 0xc0 when processing UTF-8 characters. + +26. Timing data from pcretest is now shown to 4 decimal places instead of 3. + +27. Possessive quantifiers such as a++ were previously implemented by turning + them into atomic groups such as ($>a+). Now they have their own opcodes, + which improves performance. This includes the automatically created ones + from 23 above. + +28. A pattern such as (?=(\w+))\1: which simulates an atomic group using a + lookahead was broken if it was not anchored. PCRE was mistakenly expecting + the first matched character to be a colon. This applied both to named and + numbered groups. + +29. The ucpinternal.h header file was missing its idempotency #ifdef. + +30. I was sent a "project" file called libpcre.a.dev which I understand makes + building PCRE on Windows easier, so I have included it in the distribution. + +31. There is now a check in pcretest against a ridiculously large number being + returned by pcre_exec() or pcre_dfa_exec(). If this happens in a /g or /G + loop, the loop is abandoned. + +32. Forward references to subpatterns in conditions such as (?(2)...) where + subpattern 2 is defined later cause pcre_compile() to search forwards in + the pattern for the relevant set of parentheses. This search went wrong + when there were unescaped parentheses in a character class, parentheses + escaped with \Q...\E, or parentheses in a #-comment in /x mode. + +33. "Subroutine" calls and backreferences were previously restricted to + referencing subpatterns earlier in the regex. This restriction has now + been removed. + +34. Added a number of extra features that are going to be in Perl 5.10. On the + whole, these are just syntactic alternatives for features that PCRE had + previously implemented using the Python syntax or my own invention. The + other formats are all retained for compatibility. + + (a) Named groups can now be defined as (?...) or (?'name'...) as well + as (?P...). The new forms, as well as being in Perl 5.10, are + also .NET compatible. + + (b) A recursion or subroutine call to a named group can now be defined as + (?&name) as well as (?P>name). + + (c) A backreference to a named group can now be defined as \k or + \k'name' as well as (?P=name). The new forms, as well as being in Perl + 5.10, are also .NET compatible. + + (d) A conditional reference to a named group can now use the syntax + (?() or (?('name') as well as (?(name). + + (e) A "conditional group" of the form (?(DEFINE)...) can be used to define + groups (named and numbered) that are never evaluated inline, but can be + called as "subroutines" from elsewhere. In effect, the DEFINE condition + is always false. There may be only one alternative in such a group. + + (f) A test for recursion can be given as (?(R1).. or (?(R&name)... as well + as the simple (?(R). The condition is true only if the most recent + recursion is that of the given number or name. It does not search out + through the entire recursion stack. + + (g) The escape \gN or \g{N} has been added, where N is a positive or + negative number, specifying an absolute or relative reference. + +35. Tidied to get rid of some further signed/unsigned compiler warnings and + some "unreachable code" warnings. + +36. Updated the Unicode property tables to Unicode version 5.0.0. Amongst other + things, this adds five new scripts. + +37. Perl ignores orphaned \E escapes completely. PCRE now does the same. + There were also incompatibilities regarding the handling of \Q..\E inside + character classes, for example with patterns like [\Qa\E-\Qz\E] where the + hyphen was adjacent to \Q or \E. I hope I've cleared all this up now. + +38. Like Perl, PCRE detects when an indefinitely repeated parenthesized group + matches an empty string, and forcibly breaks the loop. There were bugs in + this code in non-simple cases. For a pattern such as ^(a()*)* matched + against aaaa the result was just "a" rather than "aaaa", for example. Two + separate and independent bugs (that affected different cases) have been + fixed. + +39. Refactored the code to abolish the use of different opcodes for small + capturing bracket numbers. This is a tidy that I avoided doing when I + removed the limit on the number of capturing brackets for 3.5 back in 2001. + The new approach is not only tidier, it makes it possible to reduce the + memory needed to fix the previous bug (38). + +40. Implemented PCRE_NEWLINE_ANY to recognize any of the Unicode newline + sequences (http://unicode.org/unicode/reports/tr18/) as "newline" when + processing dot, circumflex, or dollar metacharacters, or #-comments in /x + mode. + +41. Add \R to match any Unicode newline sequence, as suggested in the Unicode + report. + +42. Applied patch, originally from Ari Pollak, modified by Google, to allow + copy construction and assignment in the C++ wrapper. + +43. Updated pcregrep to support "--newline=any". In the process, I fixed a + couple of bugs that could have given wrong results in the "--newline=crlf" + case. + +44. Added a number of casts and did some reorganization of signed/unsigned int + variables following suggestions from Dair Grant. Also renamed the variable + "this" as "item" because it is a C++ keyword. + +45. Arranged for dftables to add + + #include "pcre_internal.h" + + to pcre_chartables.c because without it, gcc 4.x may remove the array + definition from the final binary if PCRE is built into a static library and + dead code stripping is activated. + +46. For an unanchored pattern, if a match attempt fails at the start of a + newline sequence, and the newline setting is CRLF or ANY, and the next two + characters are CRLF, advance by two characters instead of one. + + +Version 6.7 04-Jul-06 +--------------------- + + 1. In order to handle tests when input lines are enormously long, pcretest has + been re-factored so that it automatically extends its buffers when + necessary. The code is crude, but this _is_ just a test program. The + default size has been increased from 32K to 50K. + + 2. The code in pcre_study() was using the value of the re argument before + testing it for NULL. (Of course, in any sensible call of the function, it + won't be NULL.) + + 3. The memmove() emulation function in pcre_internal.h, which is used on + systems that lack both memmove() and bcopy() - that is, hardly ever - + was missing a "static" storage class specifier. + + 4. When UTF-8 mode was not set, PCRE looped when compiling certain patterns + containing an extended class (one that cannot be represented by a bitmap + because it contains high-valued characters or Unicode property items, e.g. + [\pZ]). Almost always one would set UTF-8 mode when processing such a + pattern, but PCRE should not loop if you do not (it no longer does). + [Detail: two cases were found: (a) a repeated subpattern containing an + extended class; (b) a recursive reference to a subpattern that followed a + previous extended class. It wasn't skipping over the extended class + correctly when UTF-8 mode was not set.] + + 5. A negated single-character class was not being recognized as fixed-length + in lookbehind assertions such as (?<=[^f]), leading to an incorrect + compile error "lookbehind assertion is not fixed length". + + 6. The RunPerlTest auxiliary script was showing an unexpected difference + between PCRE and Perl for UTF-8 tests. It turns out that it is hard to + write a Perl script that can interpret lines of an input file either as + byte characters or as UTF-8, which is what "perltest" was being required to + do for the non-UTF-8 and UTF-8 tests, respectively. Essentially what you + can't do is switch easily at run time between having the "use utf8;" pragma + or not. In the end, I fudged it by using the RunPerlTest script to insert + "use utf8;" explicitly for the UTF-8 tests. + + 7. In multiline (/m) mode, PCRE was matching ^ after a terminating newline at + the end of the subject string, contrary to the documentation and to what + Perl does. This was true of both matching functions. Now it matches only at + the start of the subject and immediately after *internal* newlines. + + 8. A call of pcre_fullinfo() from pcretest to get the option bits was passing + a pointer to an int instead of a pointer to an unsigned long int. This + caused problems on 64-bit systems. + + 9. Applied a patch from the folks at Google to pcrecpp.cc, to fix "another + instance of the 'standard' template library not being so standard". + +10. There was no check on the number of named subpatterns nor the maximum + length of a subpattern name. The product of these values is used to compute + the size of the memory block for a compiled pattern. By supplying a very + long subpattern name and a large number of named subpatterns, the size + computation could be caused to overflow. This is now prevented by limiting + the length of names to 32 characters, and the number of named subpatterns + to 10,000. + +11. Subpatterns that are repeated with specific counts have to be replicated in + the compiled pattern. The size of memory for this was computed from the + length of the subpattern and the repeat count. The latter is limited to + 65535, but there was no limit on the former, meaning that integer overflow + could in principle occur. The compiled length of a repeated subpattern is + now limited to 30,000 bytes in order to prevent this. + +12. Added the optional facility to have named substrings with the same name. + +13. Added the ability to use a named substring as a condition, using the + Python syntax: (?(name)yes|no). This overloads (?(R)... and names that + are numbers (not recommended). Forward references are permitted. + +14. Added forward references in named backreferences (if you see what I mean). + +15. In UTF-8 mode, with the PCRE_DOTALL option set, a quantified dot in the + pattern could run off the end of the subject. For example, the pattern + "(?s)(.{1,5})"8 did this with the subject "ab". + +16. If PCRE_DOTALL or PCRE_MULTILINE were set, pcre_dfa_exec() behaved as if + PCRE_CASELESS was set when matching characters that were quantified with ? + or *. + +17. A character class other than a single negated character that had a minimum + but no maximum quantifier - for example [ab]{6,} - was not handled + correctly by pce_dfa_exec(). It would match only one character. + +18. A valid (though odd) pattern that looked like a POSIX character + class but used an invalid character after [ (for example [[,abc,]]) caused + pcre_compile() to give the error "Failed: internal error: code overflow" or + in some cases to crash with a glibc free() error. This could even happen if + the pattern terminated after [[ but there just happened to be a sequence of + letters, a binary zero, and a closing ] in the memory that followed. + +19. Perl's treatment of octal escapes in the range \400 to \777 has changed + over the years. Originally (before any Unicode support), just the bottom 8 + bits were taken. Thus, for example, \500 really meant \100. Nowadays the + output from "man perlunicode" includes this: + + The regular expression compiler produces polymorphic opcodes. That + is, the pattern adapts to the data and automatically switches to + the Unicode character scheme when presented with Unicode data--or + instead uses a traditional byte scheme when presented with byte + data. + + Sadly, a wide octal escape does not cause a switch, and in a string with + no other multibyte characters, these octal escapes are treated as before. + Thus, in Perl, the pattern /\500/ actually matches \100 but the pattern + /\500|\x{1ff}/ matches \500 or \777 because the whole thing is treated as a + Unicode string. + + I have not perpetrated such confusion in PCRE. Up till now, it took just + the bottom 8 bits, as in old Perl. I have now made octal escapes with + values greater than \377 illegal in non-UTF-8 mode. In UTF-8 mode they + translate to the appropriate multibyte character. + +29. Applied some refactoring to reduce the number of warnings from Microsoft + and Borland compilers. This has included removing the fudge introduced + seven years ago for the OS/2 compiler (see 2.02/2 below) because it caused + a warning about an unused variable. + +21. PCRE has not included VT (character 0x0b) in the set of whitespace + characters since release 4.0, because Perl (from release 5.004) does not. + [Or at least, is documented not to: some releases seem to be in conflict + with the documentation.] However, when a pattern was studied with + pcre_study() and all its branches started with \s, PCRE still included VT + as a possible starting character. Of course, this did no harm; it just + caused an unnecessary match attempt. + +22. Removed a now-redundant internal flag bit that recorded the fact that case + dependency changed within the pattern. This was once needed for "required + byte" processing, but is no longer used. This recovers a now-scarce options + bit. Also moved the least significant internal flag bit to the most- + significant bit of the word, which was not previously used (hangover from + the days when it was an int rather than a uint) to free up another bit for + the future. + +23. Added support for CRLF line endings as well as CR and LF. As well as the + default being selectable at build time, it can now be changed at runtime + via the PCRE_NEWLINE_xxx flags. There are now options for pcregrep to + specify that it is scanning data with non-default line endings. + +24. Changed the definition of CXXLINK to make it agree with the definition of + LINK in the Makefile, by replacing LDFLAGS to CXXFLAGS. + +25. Applied Ian Taylor's patches to avoid using another stack frame for tail + recursions. This makes a big different to stack usage for some patterns. + +26. If a subpattern containing a named recursion or subroutine reference such + as (?P>B) was quantified, for example (xxx(?P>B)){3}, the calculation of + the space required for the compiled pattern went wrong and gave too small a + value. Depending on the environment, this could lead to "Failed: internal + error: code overflow at offset 49" or "glibc detected double free or + corruption" errors. + +27. Applied patches from Google (a) to support the new newline modes and (b) to + advance over multibyte UTF-8 characters in GlobalReplace. + +28. Change free() to pcre_free() in pcredemo.c. Apparently this makes a + difference for some implementation of PCRE in some Windows version. + +29. Added some extra testing facilities to pcretest: + + \q in a data line sets the "match limit" value + \Q in a data line sets the "match recursion limt" value + -S sets the stack size, where is in megabytes + + The -S option isn't available for Windows. + + +Version 6.6 06-Feb-06 +--------------------- + + 1. Change 16(a) for 6.5 broke things, because PCRE_DATA_SCOPE was not defined + in pcreposix.h. I have copied the definition from pcre.h. + + 2. Change 25 for 6.5 broke compilation in a build directory out-of-tree + because pcre.h is no longer a built file. + + 3. Added Jeff Friedl's additional debugging patches to pcregrep. These are + not normally included in the compiled code. + + +Version 6.5 01-Feb-06 +--------------------- + + 1. When using the partial match feature with pcre_dfa_exec(), it was not + anchoring the second and subsequent partial matches at the new starting + point. This could lead to incorrect results. For example, with the pattern + /1234/, partially matching against "123" and then "a4" gave a match. + + 2. Changes to pcregrep: + + (a) All non-match returns from pcre_exec() were being treated as failures + to match the line. Now, unless the error is PCRE_ERROR_NOMATCH, an + error message is output. Some extra information is given for the + PCRE_ERROR_MATCHLIMIT and PCRE_ERROR_RECURSIONLIMIT errors, which are + probably the only errors that are likely to be caused by users (by + specifying a regex that has nested indefinite repeats, for instance). + If there are more than 20 of these errors, pcregrep is abandoned. + + (b) A binary zero was treated as data while matching, but terminated the + output line if it was written out. This has been fixed: binary zeroes + are now no different to any other data bytes. + + (c) Whichever of the LC_ALL or LC_CTYPE environment variables is set is + used to set a locale for matching. The --locale=xxxx long option has + been added (no short equivalent) to specify a locale explicitly on the + pcregrep command, overriding the environment variables. + + (d) When -B was used with -n, some line numbers in the output were one less + than they should have been. + + (e) Added the -o (--only-matching) option. + + (f) If -A or -C was used with -c (count only), some lines of context were + accidentally printed for the final match. + + (g) Added the -H (--with-filename) option. + + (h) The combination of options -rh failed to suppress file names for files + that were found from directory arguments. + + (i) Added the -D (--devices) and -d (--directories) options. + + (j) Added the -F (--fixed-strings) option. + + (k) Allow "-" to be used as a file name for -f as well as for a data file. + + (l) Added the --colo(u)r option. + + (m) Added Jeffrey Friedl's -S testing option, but within #ifdefs so that it + is not present by default. + + 3. A nasty bug was discovered in the handling of recursive patterns, that is, + items such as (?R) or (?1), when the recursion could match a number of + alternatives. If it matched one of the alternatives, but subsequently, + outside the recursion, there was a failure, the code tried to back up into + the recursion. However, because of the way PCRE is implemented, this is not + possible, and the result was an incorrect result from the match. + + In order to prevent this happening, the specification of recursion has + been changed so that all such subpatterns are automatically treated as + atomic groups. Thus, for example, (?R) is treated as if it were (?>(?R)). + + 4. I had overlooked the fact that, in some locales, there are characters for + which isalpha() is true but neither isupper() nor islower() are true. In + the fr_FR locale, for instance, the \xAA and \xBA characters (ordmasculine + and ordfeminine) are like this. This affected the treatment of \w and \W + when they appeared in character classes, but not when they appeared outside + a character class. The bit map for "word" characters is now created + separately from the results of isalnum() instead of just taking it from the + upper, lower, and digit maps. (Plus the underscore character, of course.) + + 5. The above bug also affected the handling of POSIX character classes such as + [[:alpha:]] and [[:alnum:]]. These do not have their own bit maps in PCRE's + permanent tables. Instead, the bit maps for such a class were previously + created as the appropriate unions of the upper, lower, and digit bitmaps. + Now they are created by subtraction from the [[:word:]] class, which has + its own bitmap. + + 6. The [[:blank:]] character class matches horizontal, but not vertical space. + It is created by subtracting the vertical space characters (\x09, \x0a, + \x0b, \x0c) from the [[:space:]] bitmap. Previously, however, the + subtraction was done in the overall bitmap for a character class, meaning + that a class such as [\x0c[:blank:]] was incorrect because \x0c would not + be recognized. This bug has been fixed. + + 7. Patches from the folks at Google: + + (a) pcrecpp.cc: "to handle a corner case that may or may not happen in + real life, but is still worth protecting against". + + (b) pcrecpp.cc: "corrects a bug when negative radixes are used with + regular expressions". + + (c) pcre_scanner.cc: avoid use of std::count() because not all systems + have it. + + (d) Split off pcrecpparg.h from pcrecpp.h and had the former built by + "configure" and the latter not, in order to fix a problem somebody had + with compiling the Arg class on HP-UX. + + (e) Improve the error-handling of the C++ wrapper a little bit. + + (f) New tests for checking recursion limiting. + + 8. The pcre_memmove() function, which is used only if the environment does not + have a standard memmove() function (and is therefore rarely compiled), + contained two bugs: (a) use of int instead of size_t, and (b) it was not + returning a result (though PCRE never actually uses the result). + + 9. In the POSIX regexec() interface, if nmatch is specified as a ridiculously + large number - greater than INT_MAX/(3*sizeof(int)) - REG_ESPACE is + returned instead of calling malloc() with an overflowing number that would + most likely cause subsequent chaos. + +10. The debugging option of pcretest was not showing the NO_AUTO_CAPTURE flag. + +11. The POSIX flag REG_NOSUB is now supported. When a pattern that was compiled + with this option is matched, the nmatch and pmatch options of regexec() are + ignored. + +12. Added REG_UTF8 to the POSIX interface. This is not defined by POSIX, but is + provided in case anyone wants to the the POSIX interface with UTF-8 + strings. + +13. Added CXXLDFLAGS to the Makefile parameters to provide settings only on the + C++ linking (needed for some HP-UX environments). + +14. Avoid compiler warnings in get_ucpname() when compiled without UCP support + (unused parameter) and in the pcre_printint() function (omitted "default" + switch label when the default is to do nothing). + +15. Added some code to make it possible, when PCRE is compiled as a C++ + library, to replace subject pointers for pcre_exec() with a smart pointer + class, thus making it possible to process discontinuous strings. + +16. The two macros PCRE_EXPORT and PCRE_DATA_SCOPE are confusing, and perform + much the same function. They were added by different people who were trying + to make PCRE easy to compile on non-Unix systems. It has been suggested + that PCRE_EXPORT be abolished now that there is more automatic apparatus + for compiling on Windows systems. I have therefore replaced it with + PCRE_DATA_SCOPE. This is set automatically for Windows; if not set it + defaults to "extern" for C or "extern C" for C++, which works fine on + Unix-like systems. It is now possible to override the value of PCRE_DATA_ + SCOPE with something explicit in config.h. In addition: + + (a) pcreposix.h still had just "extern" instead of either of these macros; + I have replaced it with PCRE_DATA_SCOPE. + + (b) Functions such as _pcre_xclass(), which are internal to the library, + but external in the C sense, all had PCRE_EXPORT in their definitions. + This is apparently wrong for the Windows case, so I have removed it. + (It makes no difference on Unix-like systems.) + +17. Added a new limit, MATCH_LIMIT_RECURSION, which limits the depth of nesting + of recursive calls to match(). This is different to MATCH_LIMIT because + that limits the total number of calls to match(), not all of which increase + the depth of recursion. Limiting the recursion depth limits the amount of + stack (or heap if NO_RECURSE is set) that is used. The default can be set + when PCRE is compiled, and changed at run time. A patch from Google adds + this functionality to the C++ interface. + +18. Changes to the handling of Unicode character properties: + + (a) Updated the table to Unicode 4.1.0. + + (b) Recognize characters that are not in the table as "Cn" (undefined). + + (c) I revised the way the table is implemented to a much improved format + which includes recognition of ranges. It now supports the ranges that + are defined in UnicodeData.txt, and it also amalgamates other + characters into ranges. This has reduced the number of entries in the + table from around 16,000 to around 3,000, thus reducing its size + considerably. I realized I did not need to use a tree structure after + all - a binary chop search is just as efficient. Having reduced the + number of entries, I extended their size from 6 bytes to 8 bytes to + allow for more data. + + (d) Added support for Unicode script names via properties such as \p{Han}. + +19. In UTF-8 mode, a backslash followed by a non-Ascii character was not + matching that character. + +20. When matching a repeated Unicode property with a minimum greater than zero, + (for example \pL{2,}), PCRE could look past the end of the subject if it + reached it while seeking the minimum number of characters. This could + happen only if some of the characters were more than one byte long, because + there is a check for at least the minimum number of bytes. + +21. Refactored the implementation of \p and \P so as to be more general, to + allow for more different types of property in future. This has changed the + compiled form incompatibly. Anybody with saved compiled patterns that use + \p or \P will have to recompile them. + +22. Added "Any" and "L&" to the supported property types. + +23. Recognize \x{...} as a code point specifier, even when not in UTF-8 mode, + but give a compile time error if the value is greater than 0xff. + +24. The man pages for pcrepartial, pcreprecompile, and pcre_compile2 were + accidentally not being installed or uninstalled. + +25. The pcre.h file was built from pcre.h.in, but the only changes that were + made were to insert the current release number. This seemed silly, because + it made things harder for people building PCRE on systems that don't run + "configure". I have turned pcre.h into a distributed file, no longer built + by "configure", with the version identification directly included. There is + no longer a pcre.h.in file. + + However, this change necessitated a change to the pcre-config script as + well. It is built from pcre-config.in, and one of the substitutions was the + release number. I have updated configure.ac so that ./configure now finds + the release number by grepping pcre.h. + +26. Added the ability to run the tests under valgrind. + + +Version 6.4 05-Sep-05 +--------------------- + + 1. Change 6.0/10/(l) to pcregrep introduced a bug that caused separator lines + "--" to be printed when multiple files were scanned, even when none of the + -A, -B, or -C options were used. This is not compatible with Gnu grep, so I + consider it to be a bug, and have restored the previous behaviour. + + 2. A couple of code tidies to get rid of compiler warnings. + + 3. The pcretest program used to cheat by referring to symbols in the library + whose names begin with _pcre_. These are internal symbols that are not + really supposed to be visible externally, and in some environments it is + possible to suppress them. The cheating is now confined to including + certain files from the library's source, which is a bit cleaner. + + 4. Renamed pcre.in as pcre.h.in to go with pcrecpp.h.in; it also makes the + file's purpose clearer. + + 5. Reorganized pcre_ucp_findchar(). + + +Version 6.3 15-Aug-05 +--------------------- + + 1. The file libpcre.pc.in did not have general read permission in the tarball. + + 2. There were some problems when building without C++ support: + + (a) If C++ support was not built, "make install" and "make test" still + tried to test it. + + (b) There were problems when the value of CXX was explicitly set. Some + changes have been made to try to fix these, and ... + + (c) --disable-cpp can now be used to explicitly disable C++ support. + + (d) The use of @CPP_OBJ@ directly caused a blank line preceded by a + backslash in a target when C++ was disabled. This confuses some + versions of "make", apparently. Using an intermediate variable solves + this. (Same for CPP_LOBJ.) + + 3. $(LINK_FOR_BUILD) now includes $(CFLAGS_FOR_BUILD) and $(LINK) + (non-Windows) now includes $(CFLAGS) because these flags are sometimes + necessary on certain architectures. + + 4. Added a setting of -export-symbols-regex to the link command to remove + those symbols that are exported in the C sense, but actually are local + within the library, and not documented. Their names all begin with + "_pcre_". This is not a perfect job, because (a) we have to except some + symbols that pcretest ("illegally") uses, and (b) the facility isn't always + available (and never for static libraries). I have made a note to try to + find a way round (a) in the future. + + +Version 6.2 01-Aug-05 +--------------------- + + 1. There was no test for integer overflow of quantifier values. A construction + such as {1111111111111111} would give undefined results. What is worse, if + a minimum quantifier for a parenthesized subpattern overflowed and became + negative, the calculation of the memory size went wrong. This could have + led to memory overwriting. + + 2. Building PCRE using VPATH was broken. Hopefully it is now fixed. + + 3. Added "b" to the 2nd argument of fopen() in dftables.c, for non-Unix-like + operating environments where this matters. + + 4. Applied Giuseppe Maxia's patch to add additional features for controlling + PCRE options from within the C++ wrapper. + + 5. Named capturing subpatterns were not being correctly counted when a pattern + was compiled. This caused two problems: (a) If there were more than 100 + such subpatterns, the calculation of the memory needed for the whole + compiled pattern went wrong, leading to an overflow error. (b) Numerical + back references of the form \12, where the number was greater than 9, were + not recognized as back references, even though there were sufficient + previous subpatterns. + + 6. Two minor patches to pcrecpp.cc in order to allow it to compile on older + versions of gcc, e.g. 2.95.4. + + +Version 6.1 21-Jun-05 +--------------------- + + 1. There was one reference to the variable "posix" in pcretest.c that was not + surrounded by "#if !defined NOPOSIX". + + 2. Make it possible to compile pcretest without DFA support, UTF8 support, or + the cross-check on the old pcre_info() function, for the benefit of the + cut-down version of PCRE that is currently imported into Exim. + + 3. A (silly) pattern starting with (?i)(?-i) caused an internal space + allocation error. I've done the easy fix, which wastes 2 bytes for sensible + patterns that start (?i) but I don't think that matters. The use of (?i) is + just an example; this all applies to the other options as well. + + 4. Since libtool seems to echo the compile commands it is issuing, the output + from "make" can be reduced a bit by putting "@" in front of each libtool + compile command. + + 5. Patch from the folks at Google for configure.in to be a bit more thorough + in checking for a suitable C++ installation before trying to compile the + C++ stuff. This should fix a reported problem when a compiler was present, + but no suitable headers. + + 6. The man pages all had just "PCRE" as their title. I have changed them to + be the relevant file name. I have also arranged that these names are + retained in the file doc/pcre.txt, which is a concatenation in text format + of all the man pages except the little individual ones for each function. + + 7. The NON-UNIX-USE file had not been updated for the different set of source + files that come with release 6. I also added a few comments about the C++ + wrapper. + + +Version 6.0 07-Jun-05 +--------------------- + + 1. Some minor internal re-organization to help with my DFA experiments. + + 2. Some missing #ifdef SUPPORT_UCP conditionals in pcretest and printint that + didn't matter for the library itself when fully configured, but did matter + when compiling without UCP support, or within Exim, where the ucp files are + not imported. + + 3. Refactoring of the library code to split up the various functions into + different source modules. The addition of the new DFA matching code (see + below) to a single monolithic source would have made it really too + unwieldy, quite apart from causing all the code to be include in a + statically linked application, when only some functions are used. This is + relevant even without the DFA addition now that patterns can be compiled in + one application and matched in another. + + The downside of splitting up is that there have to be some external + functions and data tables that are used internally in different modules of + the library but which are not part of the API. These have all had their + names changed to start with "_pcre_" so that they are unlikely to clash + with other external names. + + 4. Added an alternate matching function, pcre_dfa_exec(), which matches using + a different (DFA) algorithm. Although it is slower than the original + function, it does have some advantages for certain types of matching + problem. + + 5. Upgrades to pcretest in order to test the features of pcre_dfa_exec(), + including restarting after a partial match. + + 6. A patch for pcregrep that defines INVALID_FILE_ATTRIBUTES if it is not + defined when compiling for Windows was sent to me. I have put it into the + code, though I have no means of testing or verifying it. + + 7. Added the pcre_refcount() auxiliary function. + + 8. Added the PCRE_FIRSTLINE option. This constrains an unanchored pattern to + match before or at the first newline in the subject string. In pcretest, + the /f option on a pattern can be used to set this. + + 9. A repeated \w when used in UTF-8 mode with characters greater than 256 + would behave wrongly. This has been present in PCRE since release 4.0. + +10. A number of changes to the pcregrep command: + + (a) Refactored how -x works; insert ^(...)$ instead of setting + PCRE_ANCHORED and checking the length, in preparation for adding + something similar for -w. + + (b) Added the -w (match as a word) option. + + (c) Refactored the way lines are read and buffered so as to have more + than one at a time available. + + (d) Implemented a pcregrep test script. + + (e) Added the -M (multiline match) option. This allows patterns to match + over several lines of the subject. The buffering ensures that at least + 8K, or the rest of the document (whichever is the shorter) is available + for matching (and similarly the previous 8K for lookbehind assertions). + + (f) Changed the --help output so that it now says + + -w, --word-regex(p) + + instead of two lines, one with "regex" and the other with "regexp" + because that confused at least one person since the short forms are the + same. (This required a bit of code, as the output is generated + automatically from a table. It wasn't just a text change.) + + (g) -- can be used to terminate pcregrep options if the next thing isn't an + option but starts with a hyphen. Could be a pattern or a path name + starting with a hyphen, for instance. + + (h) "-" can be given as a file name to represent stdin. + + (i) When file names are being printed, "(standard input)" is used for + the standard input, for compatibility with GNU grep. Previously + "" was used. + + (j) The option --label=xxx can be used to supply a name to be used for + stdin when file names are being printed. There is no short form. + + (k) Re-factored the options decoding logic because we are going to add + two more options that take data. Such options can now be given in four + different ways, e.g. "-fname", "-f name", "--file=name", "--file name". + + (l) Added the -A, -B, and -C options for requesting that lines of context + around matches be printed. + + (m) Added the -L option to print the names of files that do not contain + any matching lines, that is, the complement of -l. + + (n) The return code is 2 if any file cannot be opened, but pcregrep does + continue to scan other files. + + (o) The -s option was incorrectly implemented. For compatibility with other + greps, it now suppresses the error message for a non-existent or non- + accessible file (but not the return code). There is a new option called + -q that suppresses the output of matching lines, which was what -s was + previously doing. + + (p) Added --include and --exclude options to specify files for inclusion + and exclusion when recursing. + +11. The Makefile was not using the Autoconf-supported LDFLAGS macro properly. + Hopefully, it now does. + +12. Missing cast in pcre_study(). + +13. Added an "uninstall" target to the makefile. + +14. Replaced "extern" in the function prototypes in Makefile.in with + "PCRE_DATA_SCOPE", which defaults to 'extern' or 'extern "C"' in the Unix + world, but is set differently for Windows. + +15. Added a second compiling function called pcre_compile2(). The only + difference is that it has an extra argument, which is a pointer to an + integer error code. When there is a compile-time failure, this is set + non-zero, in addition to the error test pointer being set to point to an + error message. The new argument may be NULL if no error number is required + (but then you may as well call pcre_compile(), which is now just a + wrapper). This facility is provided because some applications need a + numeric error indication, but it has also enabled me to tidy up the way + compile-time errors are handled in the POSIX wrapper. + +16. Added VPATH=.libs to the makefile; this should help when building with one + prefix path and installing with another. (Or so I'm told by someone who + knows more about this stuff than I do.) + +17. Added a new option, REG_DOTALL, to the POSIX function regcomp(). This + passes PCRE_DOTALL to the pcre_compile() function, making the "." character + match everything, including newlines. This is not POSIX-compatible, but + somebody wanted the feature. From pcretest it can be activated by using + both the P and the s flags. + +18. AC_PROG_LIBTOOL appeared twice in Makefile.in. Removed one. + +19. libpcre.pc was being incorrectly installed as executable. + +20. A couple of places in pcretest check for end-of-line by looking for '\n'; + it now also looks for '\r' so that it will work unmodified on Windows. + +21. Added Google's contributed C++ wrapper to the distribution. + +22. Added some untidy missing memory free() calls in pcretest, to keep + Electric Fence happy when testing. + + + +Version 5.0 13-Sep-04 +--------------------- + + 1. Internal change: literal characters are no longer packed up into items + containing multiple characters in a single byte-string. Each character + is now matched using a separate opcode. However, there may be more than one + byte in the character in UTF-8 mode. + + 2. The pcre_callout_block structure has two new fields: pattern_position and + next_item_length. These contain the offset in the pattern to the next match + item, and its length, respectively. + + 3. The PCRE_AUTO_CALLOUT option for pcre_compile() requests the automatic + insertion of callouts before each pattern item. Added the /C option to + pcretest to make use of this. + + 4. On the advice of a Windows user, the lines + + #if defined(_WIN32) || defined(WIN32) + _setmode( _fileno( stdout ), 0x8000 ); + #endif /* defined(_WIN32) || defined(WIN32) */ + + have been added to the source of pcretest. This apparently does useful + magic in relation to line terminators. + + 5. Changed "r" and "w" in the calls to fopen() in pcretest to "rb" and "wb" + for the benefit of those environments where the "b" makes a difference. + + 6. The icc compiler has the same options as gcc, but "configure" doesn't seem + to know about it. I have put a hack into configure.in that adds in code + to set GCC=yes if CC=icc. This seems to end up at a point in the + generated configure script that is early enough to affect the setting of + compiler options, which is what is needed, but I have no means of testing + whether it really works. (The user who reported this had patched the + generated configure script, which of course I cannot do.) + + LATER: After change 22 below (new libtool files), the configure script + seems to know about icc (and also ecc). Therefore, I have commented out + this hack in configure.in. + + 7. Added support for pkg-config (2 patches were sent in). + + 8. Negated POSIX character classes that used a combination of internal tables + were completely broken. These were [[:^alpha:]], [[:^alnum:]], and + [[:^ascii]]. Typically, they would match almost any characters. The other + POSIX classes were not broken in this way. + + 9. Matching the pattern "\b.*?" against "ab cd", starting at offset 1, failed + to find the match, as PCRE was deluded into thinking that the match had to + start at the start point or following a newline. The same bug applied to + patterns with negative forward assertions or any backward assertions + preceding ".*" at the start, unless the pattern required a fixed first + character. This was a failing pattern: "(?!.bcd).*". The bug is now fixed. + +10. In UTF-8 mode, when moving forwards in the subject after a failed match + starting at the last subject character, bytes beyond the end of the subject + string were read. + +11. Renamed the variable "class" as "classbits" to make life easier for C++ + users. (Previously there was a macro definition, but it apparently wasn't + enough.) + +12. Added the new field "tables" to the extra data so that tables can be passed + in at exec time, or the internal tables can be re-selected. This allows + a compiled regex to be saved and re-used at a later time by a different + program that might have everything at different addresses. + +13. Modified the pcre-config script so that, when run on Solaris, it shows a + -R library as well as a -L library. + +14. The debugging options of pcretest (-d on the command line or D on a + pattern) showed incorrect output for anything following an extended class + that contained multibyte characters and which was followed by a quantifier. + +15. Added optional support for general category Unicode character properties + via the \p, \P, and \X escapes. Unicode property support implies UTF-8 + support. It adds about 90K to the size of the library. The meanings of the + inbuilt class escapes such as \d and \s have NOT been changed. + +16. Updated pcredemo.c to include calls to free() to release the memory for the + compiled pattern. + +17. The generated file chartables.c was being created in the source directory + instead of in the building directory. This caused the build to fail if the + source directory was different from the building directory, and was + read-only. + +18. Added some sample Win commands from Mark Tetrode into the NON-UNIX-USE + file. No doubt somebody will tell me if they don't make sense... Also added + Dan Mooney's comments about building on OpenVMS. + +19. Added support for partial matching via the PCRE_PARTIAL option for + pcre_exec() and the \P data escape in pcretest. + +20. Extended pcretest with 3 new pattern features: + + (i) A pattern option of the form ">rest-of-line" causes pcretest to + write the compiled pattern to the file whose name is "rest-of-line". + This is a straight binary dump of the data, with the saved pointer to + the character tables forced to be NULL. The study data, if any, is + written too. After writing, pcretest reads a new pattern. + + (ii) If, instead of a pattern, ": new target + : new target + : use native compiler + : use native linker + : handle Windows platform correctly + : ditto + : ditto + copy DLL to top builddir before testing + + As part of these changes, -no-undefined was removed again. This was reported + to give trouble on HP-UX 11.0, so getting rid of it seems like a good idea + in any case. + +3. Some tidies to get rid of compiler warnings: + + . In the match_data structure, match_limit was an unsigned long int, whereas + match_call_count was an int. I've made them both unsigned long ints. + + . In pcretest the fact that a const uschar * doesn't automatically cast to + a void * provoked a warning. + + . Turning on some more compiler warnings threw up some "shadow" variables + and a few more missing casts. + +4. If PCRE was complied with UTF-8 support, but called without the PCRE_UTF8 + option, a class that contained a single character with a value between 128 + and 255 (e.g. /[\xFF]/) caused PCRE to crash. + +5. If PCRE was compiled with UTF-8 support, but called without the PCRE_UTF8 + option, a class that contained several characters, but with at least one + whose value was between 128 and 255 caused PCRE to crash. + + +Version 4.1 12-Mar-03 +--------------------- + +1. Compiling with gcc -pedantic found a couple of places where casts were +needed, and a string in dftables.c that was longer than standard compilers are +required to support. + +2. Compiling with Sun's compiler found a few more places where the code could +be tidied up in order to avoid warnings. + +3. The variables for cross-compiling were called HOST_CC and HOST_CFLAGS; the +first of these names is deprecated in the latest Autoconf in favour of the name +CC_FOR_BUILD, because "host" is typically used to mean the system on which the +compiled code will be run. I can't find a reference for HOST_CFLAGS, but by +analogy I have changed it to CFLAGS_FOR_BUILD. + +4. Added -no-undefined to the linking command in the Makefile, because this is +apparently helpful for Windows. To make it work, also added "-L. -lpcre" to the +linking step for the pcreposix library. + +5. PCRE was failing to diagnose the case of two named groups with the same +name. + +6. A problem with one of PCRE's optimizations was discovered. PCRE remembers a +literal character that is needed in the subject for a match, and scans along to +ensure that it is present before embarking on the full matching process. This +saves time in cases of nested unlimited repeats that are never going to match. +Problem: the scan can take a lot of time if the subject is very long (e.g. +megabytes), thus penalizing straightforward matches. It is now done only if the +amount of subject to be scanned is less than 1000 bytes. + +7. A lesser problem with the same optimization is that it was recording the +first character of an anchored pattern as "needed", thus provoking a search +right along the subject, even when the first match of the pattern was going to +fail. The "needed" character is now not set for anchored patterns, unless it +follows something in the pattern that is of non-fixed length. Thus, it still +fulfils its original purpose of finding quick non-matches in cases of nested +unlimited repeats, but isn't used for simple anchored patterns such as /^abc/. + + +Version 4.0 17-Feb-03 +--------------------- + +1. If a comment in an extended regex that started immediately after a meta-item +extended to the end of string, PCRE compiled incorrect data. This could lead to +all kinds of weird effects. Example: /#/ was bad; /()#/ was bad; /a#/ was not. + +2. Moved to autoconf 2.53 and libtool 1.4.2. + +3. Perl 5.8 no longer needs "use utf8" for doing UTF-8 things. Consequently, +the special perltest8 script is no longer needed - all the tests can be run +from a single perltest script. + +4. From 5.004, Perl has not included the VT character (0x0b) in the set defined +by \s. It has now been removed in PCRE. This means it isn't recognized as +whitespace in /x regexes too, which is the same as Perl. Note that the POSIX +class [:space:] *does* include VT, thereby creating a mess. + +5. Added the class [:blank:] (a GNU extension from Perl 5.8) to match only +space and tab. + +6. Perl 5.005 was a long time ago. It's time to amalgamate the tests that use +its new features into the main test script, reducing the number of scripts. + +7. Perl 5.8 has changed the meaning of patterns like /a(?i)b/. Earlier versions +were backward compatible, and made the (?i) apply to the whole pattern, as if +/i were given. Now it behaves more logically, and applies the option setting +only to what follows. PCRE has been changed to follow suit. However, if it +finds options settings right at the start of the pattern, it extracts them into +the global options, as before. Thus, they show up in the info data. + +8. Added support for the \Q...\E escape sequence. Characters in between are +treated as literals. This is slightly different from Perl in that $ and @ are +also handled as literals inside the quotes. In Perl, they will cause variable +interpolation. Note the following examples: + + Pattern PCRE matches Perl matches + + \Qabc$xyz\E abc$xyz abc followed by the contents of $xyz + \Qabc\$xyz\E abc\$xyz abc\$xyz + \Qabc\E\$\Qxyz\E abc$xyz abc$xyz + +For compatibility with Perl, \Q...\E sequences are recognized inside character +classes as well as outside them. + +9. Re-organized 3 code statements in pcretest to avoid "overflow in +floating-point constant arithmetic" warnings from a Microsoft compiler. Added a +(size_t) cast to one statement in pcretest and one in pcreposix to avoid +signed/unsigned warnings. + +10. SunOS4 doesn't have strtoul(). This was used only for unpicking the -o +option for pcretest, so I've replaced it by a simple function that does just +that job. + +11. pcregrep was ending with code 0 instead of 2 for the commands "pcregrep" or +"pcregrep -". + +12. Added "possessive quantifiers" ?+, *+, ++, and {,}+ which come from Sun's +Java package. This provides some syntactic sugar for simple cases of what my +documentation calls "once-only subpatterns". A pattern such as x*+ is the same +as (?>x*). In other words, if what is inside (?>...) is just a single repeated +item, you can use this simplified notation. Note that only makes sense with +greedy quantifiers. Consequently, the use of the possessive quantifier forces +greediness, whatever the setting of the PCRE_UNGREEDY option. + +13. A change of greediness default within a pattern was not taking effect at +the current level for patterns like /(b+(?U)a+)/. It did apply to parenthesized +subpatterns that followed. Patterns like /b+(?U)a+/ worked because the option +was abstracted outside. + +14. PCRE now supports the \G assertion. It is true when the current matching +position is at the start point of the match. This differs from \A when the +starting offset is non-zero. Used with the /g option of pcretest (or similar +code), it works in the same way as it does for Perl's /g option. If all +alternatives of a regex begin with \G, the expression is anchored to the start +match position, and the "anchored" flag is set in the compiled expression. + +15. Some bugs concerning the handling of certain option changes within patterns +have been fixed. These applied to options other than (?ims). For example, +"a(?x: b c )d" did not match "XabcdY" but did match "Xa b c dY". It should have +been the other way round. Some of this was related to change 7 above. + +16. PCRE now gives errors for /[.x.]/ and /[=x=]/ as unsupported POSIX +features, as Perl does. Previously, PCRE gave the warnings only for /[[.x.]]/ +and /[[=x=]]/. PCRE now also gives an error for /[:name:]/ because it supports +POSIX classes only within a class (e.g. /[[:alpha:]]/). + +17. Added support for Perl's \C escape. This matches one byte, even in UTF8 +mode. Unlike ".", it always matches newline, whatever the setting of +PCRE_DOTALL. However, PCRE does not permit \C to appear in lookbehind +assertions. Perl allows it, but it doesn't (in general) work because it can't +calculate the length of the lookbehind. At least, that's the case for Perl +5.8.0 - I've been told they are going to document that it doesn't work in +future. + +18. Added an error diagnosis for escapes that PCRE does not support: these are +\L, \l, \N, \P, \p, \U, \u, and \X. + +19. Although correctly diagnosing a missing ']' in a character class, PCRE was +reading past the end of the pattern in cases such as /[abcd/. + +20. PCRE was getting more memory than necessary for patterns with classes that +contained both POSIX named classes and other characters, e.g. /[[:space:]abc/. + +21. Added some code, conditional on #ifdef VPCOMPAT, to make life easier for +compiling PCRE for use with Virtual Pascal. + +22. Small fix to the Makefile to make it work properly if the build is done +outside the source tree. + +23. Added a new extension: a condition to go with recursion. If a conditional +subpattern starts with (?(R) the "true" branch is used if recursion has +happened, whereas the "false" branch is used only at the top level. + +24. When there was a very long string of literal characters (over 255 bytes +without UTF support, over 250 bytes with UTF support), the computation of how +much memory was required could be incorrect, leading to segfaults or other +strange effects. + +25. PCRE was incorrectly assuming anchoring (either to start of subject or to +start of line for a non-DOTALL pattern) when a pattern started with (.*) and +there was a subsequent back reference to those brackets. This meant that, for +example, /(.*)\d+\1/ failed to match "abc123bc". Unfortunately, it isn't +possible to check for precisely this case. All we can do is abandon the +optimization if .* occurs inside capturing brackets when there are any back +references whatsoever. (See below for a better fix that came later.) + +26. The handling of the optimization for finding the first character of a +non-anchored pattern, and for finding a character that is required later in the +match were failing in some cases. This didn't break the matching; it just +failed to optimize when it could. The way this is done has been re-implemented. + +27. Fixed typo in error message for invalid (?R item (it said "(?p"). + +28. Added a new feature that provides some of the functionality that Perl +provides with (?{...}). The facility is termed a "callout". The way it is done +in PCRE is for the caller to provide an optional function, by setting +pcre_callout to its entry point. Like pcre_malloc and pcre_free, this is a +global variable. By default it is unset, which disables all calling out. To get +the function called, the regex must include (?C) at appropriate points. This +is, in fact, equivalent to (?C0), and any number <= 255 may be given with (?C). +This provides a means of identifying different callout points. When PCRE +reaches such a point in the regex, if pcre_callout has been set, the external +function is called. It is provided with data in a structure called +pcre_callout_block, which is defined in pcre.h. If the function returns 0, +matching continues; if it returns a non-zero value, the match at the current +point fails. However, backtracking will occur if possible. [This was changed +later and other features added - see item 49 below.] + +29. pcretest is upgraded to test the callout functionality. It provides a +callout function that displays information. By default, it shows the start of +the match and the current position in the text. There are some new data escapes +to vary what happens: + + \C+ in addition, show current contents of captured substrings + \C- do not supply a callout function + \C!n return 1 when callout number n is reached + \C!n!m return 1 when callout number n is reached for the mth time + +30. If pcregrep was called with the -l option and just a single file name, it +output "" if a match was found, instead of the file name. + +31. Improve the efficiency of the POSIX API to PCRE. If the number of capturing +slots is less than POSIX_MALLOC_THRESHOLD, use a block on the stack to pass to +pcre_exec(). This saves a malloc/free per call. The default value of +POSIX_MALLOC_THRESHOLD is 10; it can be changed by --with-posix-malloc-threshold +when configuring. + +32. The default maximum size of a compiled pattern is 64K. There have been a +few cases of people hitting this limit. The code now uses macros to handle the +storing of links as offsets within the compiled pattern. It defaults to 2-byte +links, but this can be changed to 3 or 4 bytes by --with-link-size when +configuring. Tests 2 and 5 work only with 2-byte links because they output +debugging information about compiled patterns. + +33. Internal code re-arrangements: + +(a) Moved the debugging function for printing out a compiled regex into + its own source file (printint.c) and used #include to pull it into + pcretest.c and, when DEBUG is defined, into pcre.c, instead of having two + separate copies. + +(b) Defined the list of op-code names for debugging as a macro in + internal.h so that it is next to the definition of the opcodes. + +(c) Defined a table of op-code lengths for simpler skipping along compiled + code. This is again a macro in internal.h so that it is next to the + definition of the opcodes. + +34. Added support for recursive calls to individual subpatterns, along the +lines of Robin Houston's patch (but implemented somewhat differently). + +35. Further mods to the Makefile to help Win32. Also, added code to pcregrep to +allow it to read and process whole directories in Win32. This code was +contributed by Lionel Fourquaux; it has not been tested by me. + +36. Added support for named subpatterns. The Python syntax (?P...) is +used to name a group. Names consist of alphanumerics and underscores, and must +be unique. Back references use the syntax (?P=name) and recursive calls use +(?P>name) which is a PCRE extension to the Python extension. Groups still have +numbers. The function pcre_fullinfo() can be used after compilation to extract +a name/number map. There are three relevant calls: + + PCRE_INFO_NAMEENTRYSIZE yields the size of each entry in the map + PCRE_INFO_NAMECOUNT yields the number of entries + PCRE_INFO_NAMETABLE yields a pointer to the map. + +The map is a vector of fixed-size entries. The size of each entry depends on +the length of the longest name used. The first two bytes of each entry are the +group number, most significant byte first. There follows the corresponding +name, zero terminated. The names are in alphabetical order. + +37. Make the maximum literal string in the compiled code 250 for the non-UTF-8 +case instead of 255. Making it the same both with and without UTF-8 support +means that the same test output works with both. + +38. There was a case of malloc(0) in the POSIX testing code in pcretest. Avoid +calling malloc() with a zero argument. + +39. Change 25 above had to resort to a heavy-handed test for the .* anchoring +optimization. I've improved things by keeping a bitmap of backreferences with +numbers 1-31 so that if .* occurs inside capturing brackets that are not in +fact referenced, the optimization can be applied. It is unlikely that a +relevant occurrence of .* (i.e. one which might indicate anchoring or forcing +the match to follow \n) will appear inside brackets with a number greater than +31, but if it does, any back reference > 31 suppresses the optimization. + +40. Added a new compile-time option PCRE_NO_AUTO_CAPTURE. This has the effect +of disabling numbered capturing parentheses. Any opening parenthesis that is +not followed by ? behaves as if it were followed by ?: but named parentheses +can still be used for capturing (and they will acquire numbers in the usual +way). + +41. Redesigned the return codes from the match() function into yes/no/error so +that errors can be passed back from deep inside the nested calls. A malloc +failure while inside a recursive subpattern call now causes the +PCRE_ERROR_NOMEMORY return instead of quietly going wrong. + +42. It is now possible to set a limit on the number of times the match() +function is called in a call to pcre_exec(). This facility makes it possible to +limit the amount of recursion and backtracking, though not in a directly +obvious way, because the match() function is used in a number of different +circumstances. The count starts from zero for each position in the subject +string (for non-anchored patterns). The default limit is, for compatibility, a +large number, namely 10 000 000. You can change this in two ways: + +(a) When configuring PCRE before making, you can use --with-match-limit=n + to set a default value for the compiled library. + +(b) For each call to pcre_exec(), you can pass a pcre_extra block in which + a different value is set. See 45 below. + +If the limit is exceeded, pcre_exec() returns PCRE_ERROR_MATCHLIMIT. + +43. Added a new function pcre_config(int, void *) to enable run-time extraction +of things that can be changed at compile time. The first argument specifies +what is wanted and the second points to where the information is to be placed. +The current list of available information is: + + PCRE_CONFIG_UTF8 + +The output is an integer that is set to one if UTF-8 support is available; +otherwise it is set to zero. + + PCRE_CONFIG_NEWLINE + +The output is an integer that it set to the value of the code that is used for +newline. It is either LF (10) or CR (13). + + PCRE_CONFIG_LINK_SIZE + +The output is an integer that contains the number of bytes used for internal +linkage in compiled expressions. The value is 2, 3, or 4. See item 32 above. + + PCRE_CONFIG_POSIX_MALLOC_THRESHOLD + +The output is an integer that contains the threshold above which the POSIX +interface uses malloc() for output vectors. See item 31 above. + + PCRE_CONFIG_MATCH_LIMIT + +The output is an unsigned integer that contains the default limit of the number +of match() calls in a pcre_exec() execution. See 42 above. + +44. pcretest has been upgraded by the addition of the -C option. This causes it +to extract all the available output from the new pcre_config() function, and to +output it. The program then exits immediately. + +45. A need has arisen to pass over additional data with calls to pcre_exec() in +order to support additional features. One way would have been to define +pcre_exec2() (for example) with extra arguments, but this would not have been +extensible, and would also have required all calls to the original function to +be mapped to the new one. Instead, I have chosen to extend the mechanism that +is used for passing in "extra" data from pcre_study(). + +The pcre_extra structure is now exposed and defined in pcre.h. It currently +contains the following fields: + + flags a bitmap indicating which of the following fields are set + study_data opaque data from pcre_study() + match_limit a way of specifying a limit on match() calls for a specific + call to pcre_exec() + callout_data data for callouts (see 49 below) + +The flag bits are also defined in pcre.h, and are + + PCRE_EXTRA_STUDY_DATA + PCRE_EXTRA_MATCH_LIMIT + PCRE_EXTRA_CALLOUT_DATA + +The pcre_study() function now returns one of these new pcre_extra blocks, with +the actual study data pointed to by the study_data field, and the +PCRE_EXTRA_STUDY_DATA flag set. This can be passed directly to pcre_exec() as +before. That is, this change is entirely upwards-compatible and requires no +change to existing code. + +If you want to pass in additional data to pcre_exec(), you can either place it +in a pcre_extra block provided by pcre_study(), or create your own pcre_extra +block. + +46. pcretest has been extended to test the PCRE_EXTRA_MATCH_LIMIT feature. If a +data string contains the escape sequence \M, pcretest calls pcre_exec() several +times with different match limits, until it finds the minimum value needed for +pcre_exec() to complete. The value is then output. This can be instructive; for +most simple matches the number is quite small, but for pathological cases it +gets very large very quickly. + +47. There's a new option for pcre_fullinfo() called PCRE_INFO_STUDYSIZE. It +returns the size of the data block pointed to by the study_data field in a +pcre_extra block, that is, the value that was passed as the argument to +pcre_malloc() when PCRE was getting memory in which to place the information +created by pcre_study(). The fourth argument should point to a size_t variable. +pcretest has been extended so that this information is shown after a successful +pcre_study() call when information about the compiled regex is being displayed. + +48. Cosmetic change to Makefile: there's no need to have / after $(DESTDIR) +because what follows is always an absolute path. (Later: it turns out that this +is more than cosmetic for MinGW, because it doesn't like empty path +components.) + +49. Some changes have been made to the callout feature (see 28 above): + +(i) A callout function now has three choices for what it returns: + + 0 => success, carry on matching + > 0 => failure at this point, but backtrack if possible + < 0 => serious error, return this value from pcre_exec() + + Negative values should normally be chosen from the set of PCRE_ERROR_xxx + values. In particular, returning PCRE_ERROR_NOMATCH forces a standard + "match failed" error. The error number PCRE_ERROR_CALLOUT is reserved for + use by callout functions. It will never be used by PCRE itself. + +(ii) The pcre_extra structure (see 45 above) has a void * field called + callout_data, with corresponding flag bit PCRE_EXTRA_CALLOUT_DATA. The + pcre_callout_block structure has a field of the same name. The contents of + the field passed in the pcre_extra structure are passed to the callout + function in the corresponding field in the callout block. This makes it + easier to use the same callout-containing regex from multiple threads. For + testing, the pcretest program has a new data escape + + \C*n pass the number n (may be negative) as callout_data + + If the callout function in pcretest receives a non-zero value as + callout_data, it returns that value. + +50. Makefile wasn't handling CFLAGS properly when compiling dftables. Also, +there were some redundant $(CFLAGS) in commands that are now specified as +$(LINK), which already includes $(CFLAGS). + +51. Extensions to UTF-8 support are listed below. These all apply when (a) PCRE +has been compiled with UTF-8 support *and* pcre_compile() has been compiled +with the PCRE_UTF8 flag. Patterns that are compiled without that flag assume +one-byte characters throughout. Note that case-insensitive matching applies +only to characters whose values are less than 256. PCRE doesn't support the +notion of cases for higher-valued characters. + +(i) A character class whose characters are all within 0-255 is handled as + a bit map, and the map is inverted for negative classes. Previously, a + character > 255 always failed to match such a class; however it should + match if the class was a negative one (e.g. [^ab]). This has been fixed. + +(ii) A negated character class with a single character < 255 is coded as + "not this character" (OP_NOT). This wasn't working properly when the test + character was multibyte, either singly or repeated. + +(iii) Repeats of multibyte characters are now handled correctly in UTF-8 + mode, for example: \x{100}{2,3}. + +(iv) The character escapes \b, \B, \d, \D, \s, \S, \w, and \W (either + singly or repeated) now correctly test multibyte characters. However, + PCRE doesn't recognize any characters with values greater than 255 as + digits, spaces, or word characters. Such characters always match \D, \S, + and \W, and never match \d, \s, or \w. + +(v) Classes may now contain characters and character ranges with values + greater than 255. For example: [ab\x{100}-\x{400}]. + +(vi) pcregrep now has a --utf-8 option (synonym -u) which makes it call + PCRE in UTF-8 mode. + +52. The info request value PCRE_INFO_FIRSTCHAR has been renamed +PCRE_INFO_FIRSTBYTE because it is a byte value. However, the old name is +retained for backwards compatibility. (Note that LASTLITERAL is also a byte +value.) + +53. The single man page has become too large. I have therefore split it up into +a number of separate man pages. These also give rise to individual HTML pages; +these are now put in a separate directory, and there is an index.html page that +lists them all. Some hyperlinking between the pages has been installed. + +54. Added convenience functions for handling named capturing parentheses. + +55. Unknown escapes inside character classes (e.g. [\M]) and escapes that +aren't interpreted therein (e.g. [\C]) are literals in Perl. This is now also +true in PCRE, except when the PCRE_EXTENDED option is set, in which case they +are faulted. + +56. Introduced HOST_CC and HOST_CFLAGS which can be set in the environment when +calling configure. These values are used when compiling the dftables.c program +which is run to generate the source of the default character tables. They +default to the values of CC and CFLAGS. If you are cross-compiling PCRE, +you will need to set these values. + +57. Updated the building process for Windows DLL, as provided by Fred Cox. + + +Version 3.9 02-Jan-02 +--------------------- + +1. A bit of extraneous text had somehow crept into the pcregrep documentation. + +2. If --disable-static was given, the building process failed when trying to +build pcretest and pcregrep. (For some reason it was using libtool to compile +them, which is not right, as they aren't part of the library.) + + +Version 3.8 18-Dec-01 +--------------------- + +1. The experimental UTF-8 code was completely screwed up. It was packing the +bytes in the wrong order. How dumb can you get? + + +Version 3.7 29-Oct-01 +--------------------- + +1. In updating pcretest to check change 1 of version 3.6, I screwed up. +This caused pcretest, when used on the test data, to segfault. Unfortunately, +this didn't happen under Solaris 8, where I normally test things. + +2. The Makefile had to be changed to make it work on BSD systems, where 'make' +doesn't seem to recognize that ./xxx and xxx are the same file. (This entry +isn't in ChangeLog distributed with 3.7 because I forgot when I hastily made +this fix an hour or so after the initial 3.7 release.) + + +Version 3.6 23-Oct-01 +--------------------- + +1. Crashed with /(sens|respons)e and \1ibility/ and "sense and sensibility" if +offsets passed as NULL with zero offset count. + +2. The config.guess and config.sub files had not been updated when I moved to +the latest autoconf. + + +Version 3.5 15-Aug-01 +--------------------- + +1. Added some missing #if !defined NOPOSIX conditionals in pcretest.c that +had been forgotten. + +2. By using declared but undefined structures, we can avoid using "void" +definitions in pcre.h while keeping the internal definitions of the structures +private. + +3. The distribution is now built using autoconf 2.50 and libtool 1.4. From a +user point of view, this means that both static and shared libraries are built +by default, but this can be individually controlled. More of the work of +handling this static/shared cases is now inside libtool instead of PCRE's make +file. + +4. The pcretest utility is now installed along with pcregrep because it is +useful for users (to test regexs) and by doing this, it automatically gets +relinked by libtool. The documentation has been turned into a man page, so +there are now .1, .txt, and .html versions in /doc. + +5. Upgrades to pcregrep: + (i) Added long-form option names like gnu grep. + (ii) Added --help to list all options with an explanatory phrase. + (iii) Added -r, --recursive to recurse into sub-directories. + (iv) Added -f, --file to read patterns from a file. + +6. pcre_exec() was referring to its "code" argument before testing that +argument for NULL (and giving an error if it was NULL). + +7. Upgraded Makefile.in to allow for compiling in a different directory from +the source directory. + +8. Tiny buglet in pcretest: when pcre_fullinfo() was called to retrieve the +options bits, the pointer it was passed was to an int instead of to an unsigned +long int. This mattered only on 64-bit systems. + +9. Fixed typo (3.4/1) in pcre.h again. Sigh. I had changed pcre.h (which is +generated) instead of pcre.in, which it its source. Also made the same change +in several of the .c files. + +10. A new release of gcc defines printf() as a macro, which broke pcretest +because it had an ifdef in the middle of a string argument for printf(). Fixed +by using separate calls to printf(). + +11. Added --enable-newline-is-cr and --enable-newline-is-lf to the configure +script, to force use of CR or LF instead of \n in the source. On non-Unix +systems, the value can be set in config.h. + +12. The limit of 200 on non-capturing parentheses is a _nesting_ limit, not an +absolute limit. Changed the text of the error message to make this clear, and +likewise updated the man page. + +13. The limit of 99 on the number of capturing subpatterns has been removed. +The new limit is 65535, which I hope will not be a "real" limit. + + +Version 3.4 22-Aug-00 +--------------------- + +1. Fixed typo in pcre.h: unsigned const char * changed to const unsigned char *. + +2. Diagnose condition (?(0) as an error instead of crashing on matching. + + +Version 3.3 01-Aug-00 +--------------------- + +1. If an octal character was given, but the value was greater than \377, it +was not getting masked to the least significant bits, as documented. This could +lead to crashes in some systems. + +2. Perl 5.6 (if not earlier versions) accepts classes like [a-\d] and treats +the hyphen as a literal. PCRE used to give an error; it now behaves like Perl. + +3. Added the functions pcre_free_substring() and pcre_free_substring_list(). +These just pass their arguments on to (pcre_free)(), but they are provided +because some uses of PCRE bind it to non-C systems that can call its functions, +but cannot call free() or pcre_free() directly. + +4. Add "make test" as a synonym for "make check". Corrected some comments in +the Makefile. + +5. Add $(DESTDIR)/ in front of all the paths in the "install" target in the +Makefile. + +6. Changed the name of pgrep to pcregrep, because Solaris has introduced a +command called pgrep for grepping around the active processes. + +7. Added the beginnings of support for UTF-8 character strings. + +8. Arranged for the Makefile to pass over the settings of CC, CFLAGS, and +RANLIB to ./ltconfig so that they are used by libtool. I think these are all +the relevant ones. (AR is not passed because ./ltconfig does its own figuring +out for the ar command.) + + +Version 3.2 12-May-00 +--------------------- + +This is purely a bug fixing release. + +1. If the pattern /((Z)+|A)*/ was matched agained ZABCDEFG it matched Z instead +of ZA. This was just one example of several cases that could provoke this bug, +which was introduced by change 9 of version 2.00. The code for breaking +infinite loops after an iteration that matches an empty string was't working +correctly. + +2. The pcretest program was not imitating Perl correctly for the pattern /a*/g +when matched against abbab (for example). After matching an empty string, it +wasn't forcing anchoring when setting PCRE_NOTEMPTY for the next attempt; this +caused it to match further down the string than it should. + +3. The code contained an inclusion of sys/types.h. It isn't clear why this +was there because it doesn't seem to be needed, and it causes trouble on some +systems, as it is not a Standard C header. It has been removed. + +4. Made 4 silly changes to the source to avoid stupid compiler warnings that +were reported on the Macintosh. The changes were from + + while ((c = *(++ptr)) != 0 && c != '\n'); +to + while ((c = *(++ptr)) != 0 && c != '\n') ; + +Totally extraordinary, but if that's what it takes... + +5. PCRE is being used in one environment where neither memmove() nor bcopy() is +available. Added HAVE_BCOPY and an autoconf test for it; if neither +HAVE_MEMMOVE nor HAVE_BCOPY is set, use a built-in emulation function which +assumes the way PCRE uses memmove() (always moving upwards). + +6. PCRE is being used in one environment where strchr() is not available. There +was only one use in pcre.c, and writing it out to avoid strchr() probably gives +faster code anyway. + + +Version 3.1 09-Feb-00 +--------------------- + +The only change in this release is the fixing of some bugs in Makefile.in for +the "install" target: + +(1) It was failing to install pcreposix.h. + +(2) It was overwriting the pcre.3 man page with the pcreposix.3 man page. + + +Version 3.0 01-Feb-00 +--------------------- + +1. Add support for the /+ modifier to perltest (to output $` like it does in +pcretest). + +2. Add support for the /g modifier to perltest. + +3. Fix pcretest so that it behaves even more like Perl for /g when the pattern +matches null strings. + +4. Fix perltest so that it doesn't do unwanted things when fed an empty +pattern. Perl treats empty patterns specially - it reuses the most recent +pattern, which is not what we want. Replace // by /(?#)/ in order to avoid this +effect. + +5. The POSIX interface was broken in that it was just handing over the POSIX +captured string vector to pcre_exec(), but (since release 2.00) PCRE has +required a bigger vector, with some working space on the end. This means that +the POSIX wrapper now has to get and free some memory, and copy the results. + +6. Added some simple autoconf support, placing the test data and the +documentation in separate directories, re-organizing some of the +information files, and making it build pcre-config (a GNU standard). Also added +libtool support for building PCRE as a shared library, which is now the +default. + +7. Got rid of the leading zero in the definition of PCRE_MINOR because 08 and +09 are not valid octal constants. Single digits will be used for minor values +less than 10. + +8. Defined REG_EXTENDED and REG_NOSUB as zero in the POSIX header, so that +existing programs that set these in the POSIX interface can use PCRE without +modification. + +9. Added a new function, pcre_fullinfo() with an extensible interface. It can +return all that pcre_info() returns, plus additional data. The pcre_info() +function is retained for compatibility, but is considered to be obsolete. + +10. Added experimental recursion feature (?R) to handle one common case that +Perl 5.6 will be able to do with (?p{...}). + +11. Added support for POSIX character classes like [:alpha:], which Perl is +adopting. + + +Version 2.08 31-Aug-99 +---------------------- + +1. When startoffset was not zero and the pattern began with ".*", PCRE was not +trying to match at the startoffset position, but instead was moving forward to +the next newline as if a previous match had failed. + +2. pcretest was not making use of PCRE_NOTEMPTY when repeating for /g and /G, +and could get into a loop if a null string was matched other than at the start +of the subject. + +3. Added definitions of PCRE_MAJOR and PCRE_MINOR to pcre.h so the version can +be distinguished at compile time, and for completeness also added PCRE_DATE. + +5. Added Paul Sokolovsky's minor changes to make it easy to compile a Win32 DLL +in GnuWin32 environments. + + +Version 2.07 29-Jul-99 +---------------------- + +1. The documentation is now supplied in plain text form and HTML as well as in +the form of man page sources. + +2. C++ compilers don't like assigning (void *) values to other pointer types. +In particular this affects malloc(). Although there is no problem in Standard +C, I've put in casts to keep C++ compilers happy. + +3. Typo on pcretest.c; a cast of (unsigned char *) in the POSIX regexec() call +should be (const char *). + +4. If NOPOSIX is defined, pcretest.c compiles without POSIX support. This may +be useful for non-Unix systems who don't want to bother with the POSIX stuff. +However, I haven't made this a standard facility. The documentation doesn't +mention it, and the Makefile doesn't support it. + +5. The Makefile now contains an "install" target, with editable destinations at +the top of the file. The pcretest program is not installed. + +6. pgrep -V now gives the PCRE version number and date. + +7. Fixed bug: a zero repetition after a literal string (e.g. /abcde{0}/) was +causing the entire string to be ignored, instead of just the last character. + +8. If a pattern like /"([^\\"]+|\\.)*"/ is applied in the normal way to a +non-matching string, it can take a very, very long time, even for strings of +quite modest length, because of the nested recursion. PCRE now does better in +some of these cases. It does this by remembering the last required literal +character in the pattern, and pre-searching the subject to ensure it is present +before running the real match. In other words, it applies a heuristic to detect +some types of certain failure quickly, and in the above example, if presented +with a string that has no trailing " it gives "no match" very quickly. + +9. A new runtime option PCRE_NOTEMPTY causes null string matches to be ignored; +other alternatives are tried instead. + + +Version 2.06 09-Jun-99 +---------------------- + +1. Change pcretest's output for amount of store used to show just the code +space, because the remainder (the data block) varies in size between 32-bit and +64-bit systems. + +2. Added an extra argument to pcre_exec() to supply an offset in the subject to +start matching at. This allows lookbehinds to work when searching for multiple +occurrences in a string. + +3. Added additional options to pcretest for testing multiple occurrences: + + /+ outputs the rest of the string that follows a match + /g loops for multiple occurrences, using the new startoffset argument + /G loops for multiple occurrences by passing an incremented pointer + +4. PCRE wasn't doing the "first character" optimization for patterns starting +with \b or \B, though it was doing it for other lookbehind assertions. That is, +it wasn't noticing that a match for a pattern such as /\bxyz/ has to start with +the letter 'x'. On long subject strings, this gives a significant speed-up. + + +Version 2.05 21-Apr-99 +---------------------- + +1. Changed the type of magic_number from int to long int so that it works +properly on 16-bit systems. + +2. Fixed a bug which caused patterns starting with .* not to work correctly +when the subject string contained newline characters. PCRE was assuming +anchoring for such patterns in all cases, which is not correct because .* will +not pass a newline unless PCRE_DOTALL is set. It now assumes anchoring only if +DOTALL is set at top level; otherwise it knows that patterns starting with .* +must be retried after every newline in the subject. + + +Version 2.04 18-Feb-99 +---------------------- + +1. For parenthesized subpatterns with repeats whose minimum was zero, the +computation of the store needed to hold the pattern was incorrect (too large). +If such patterns were nested a few deep, this could multiply and become a real +problem. + +2. Added /M option to pcretest to show the memory requirement of a specific +pattern. Made -m a synonym of -s (which does this globally) for compatibility. + +3. Subpatterns of the form (regex){n,m} (i.e. limited maximum) were being +compiled in such a way that the backtracking after subsequent failure was +pessimal. Something like (a){0,3} was compiled as (a)?(a)?(a)? instead of +((a)((a)(a)?)?)? with disastrous performance if the maximum was of any size. + + +Version 2.03 02-Feb-99 +---------------------- + +1. Fixed typo and small mistake in man page. + +2. Added 4th condition (GPL supersedes if conflict) and created separate +LICENCE file containing the conditions. + +3. Updated pcretest so that patterns such as /abc\/def/ work like they do in +Perl, that is the internal \ allows the delimiter to be included in the +pattern. Locked out the use of \ as a delimiter. If \ immediately follows +the final delimiter, add \ to the end of the pattern (to test the error). + +4. Added the convenience functions for extracting substrings after a successful +match. Updated pcretest to make it able to test these functions. + + +Version 2.02 14-Jan-99 +---------------------- + +1. Initialized the working variables associated with each extraction so that +their saving and restoring doesn't refer to uninitialized store. + +2. Put dummy code into study.c in order to trick the optimizer of the IBM C +compiler for OS/2 into generating correct code. Apparently IBM isn't going to +fix the problem. + +3. Pcretest: the timing code wasn't using LOOPREPEAT for timing execution +calls, and wasn't printing the correct value for compiling calls. Increased the +default value of LOOPREPEAT, and the number of significant figures in the +times. + +4. Changed "/bin/rm" in the Makefile to "-rm" so it works on Windows NT. + +5. Renamed "deftables" as "dftables" to get it down to 8 characters, to avoid +a building problem on Windows NT with a FAT file system. + + +Version 2.01 21-Oct-98 +---------------------- + +1. Changed the API for pcre_compile() to allow for the provision of a pointer +to character tables built by pcre_maketables() in the current locale. If NULL +is passed, the default tables are used. + + +Version 2.00 24-Sep-98 +---------------------- + +1. Since the (>?) facility is in Perl 5.005, don't require PCRE_EXTRA to enable +it any more. + +2. Allow quantification of (?>) groups, and make it work correctly. + +3. The first character computation wasn't working for (?>) groups. + +4. Correct the implementation of \Z (it is permitted to match on the \n at the +end of the subject) and add 5.005's \z, which really does match only at the +very end of the subject. + +5. Remove the \X "cut" facility; Perl doesn't have it, and (?> is neater. + +6. Remove the ability to specify CASELESS, MULTILINE, DOTALL, and +DOLLAR_END_ONLY at runtime, to make it possible to implement the Perl 5.005 +localized options. All options to pcre_study() were also removed. + +7. Add other new features from 5.005: + + $(?<= positive lookbehind + $(?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. + +**** ============================================================ --- pcre/HACKING cacc10be9c2edc7f1aec03a9fd0bc6f4894bdd71 +++ pcre/HACKING cacc10be9c2edc7f1aec03a9fd0bc6f4894bdd71 @@ -0,0 +1,414 @@ +Technical Notes about PCRE +-------------------------- + +These are very rough technical notes that record potentially useful information +about PCRE internals. + +Historical note 1 +----------------- + +Many years ago I implemented some regular expression functions to an algorithm +suggested by Martin Richards. These were not Unix-like in form, and were quite +restricted in what they could do by comparison with Perl. The interesting part +about the algorithm was that the amount of space required to hold the compiled +form of an expression was known in advance. The code to apply an expression did +not operate by backtracking, as the original Henry Spencer code and current +Perl code does, but instead checked all possibilities simultaneously by keeping +a list of current states and checking all of them as it advanced through the +subject string. In the terminology of Jeffrey Friedl's book, it was a "DFA +algorithm", though it was not a traditional Finite State Machine (FSM). When +the pattern was all used up, all remaining states were possible matches, and +the one matching the longest subset of the subject string was chosen. This did +not necessarily maximize the individual wild portions of the pattern, as is +expected in Unix and Perl-style regular expressions. + +Historical note 2 +----------------- + +By contrast, the code originally written by Henry Spencer (which was +subsequently heavily modified for Perl) compiles the expression twice: once in +a dummy mode in order to find out how much store will be needed, and then for +real. (The Perl version probably doesn't do this any more; I'm talking about +the original library.) The execution function operates by backtracking and +maximizing (or, optionally, minimizing in Perl) the amount of the subject that +matches individual wild portions of the pattern. This is an "NFA algorithm" in +Friedl's terminology. + +OK, here's the real stuff +------------------------- + +For the set of functions that form the "basic" PCRE library (which are +unrelated to those mentioned above), I tried at first to invent an algorithm +that used an amount of store bounded by a multiple of the number of characters +in the pattern, to save on compiling time. However, because of the greater +complexity in Perl regular expressions, I couldn't do this. In any case, a +first pass through the pattern is helpful for other reasons. + +Computing the memory requirement: how it was +-------------------------------------------- + +Up to and including release 6.7, PCRE worked by running a very degenerate first +pass to calculate a maximum store size, and then a second pass to do the real +compile - which might use a bit less than the predicted amount of memory. The +idea was that this would turn out faster than the Henry Spencer code because +the first pass is degenerate and the second pass can just store stuff straight +into the vector, which it knows is big enough. + +Computing the memory requirement: how it is +------------------------------------------- + +By the time I was working on a potential 6.8 release, the degenerate first pass +had become very complicated and hard to maintain. Indeed one of the early +things I did for 6.8 was to fix Yet Another Bug in the memory computation. Then +I had a flash of inspiration as to how I could run the real compile function in +a "fake" mode that enables it to compute how much memory it would need, while +actually only ever using a few hundred bytes of working memory, and without too +many tests of the mode that might slow it down. So I re-factored the compiling +functions to work this way. This got rid of about 600 lines of source. It +should make future maintenance and development easier. As this was such a major +change, I never released 6.8, instead upping the number to 7.0 (other quite +major changes are also present in the 7.0 release). + +A side effect of this work is that the previous limit of 200 on the nesting +depth of parentheses was removed. However, there is a downside: pcre_compile() +runs more slowly than before (30% or more, depending on the pattern) because it +is doing a full analysis of the pattern. My hope is that this is not a big +issue. + +Traditional matching function +----------------------------- + +The "traditional", and original, matching function is called pcre_exec(), and +it implements an NFA algorithm, similar to the original Henry Spencer algorithm +and the way that Perl works. Not surprising, since it is intended to be as +compatible with Perl as possible. This is the function most users of PCRE will +use most of the time. + +Supplementary matching function +------------------------------- + +From PCRE 6.0, there is also a supplementary matching function called +pcre_dfa_exec(). This implements a DFA matching algorithm that searches +simultaneously for all possible matches that start at one point in the subject +string. (Going back to my roots: see Historical Note 1 above.) This function +intreprets the same compiled pattern data as pcre_exec(); however, not all the +facilities are available, and those that are do not always work in quite the +same way. See the user documentation for details. + +The algorithm that is used for pcre_dfa_exec() is not a traditional FSM, +because it may have a number of states active at one time. More work would be +needed at compile time to produce a traditional FSM where only one state is +ever active at once. I believe some other regex matchers work this way. + + +Format of compiled patterns +--------------------------- + +The compiled form of a pattern is a vector of bytes, containing items of +variable length. The first byte in an item is an opcode, and the length of the +item is either implicit in the opcode or contained in the data bytes that +follow it. + +In many cases below LINK_SIZE data values are specified for offsets within the +compiled pattern. The default value for LINK_SIZE is 2, but PCRE can be +compiled to use 3-byte or 4-byte values for these offsets (impairing the +performance). This is necessary only when patterns whose compiled length is +greater than 64K are going to be processed. In this description, we assume the +"normal" compilation options. Data values that are counts (e.g. for +quantifiers) are always just two bytes long. + +A list of the opcodes follows: + +Opcodes with no following data +------------------------------ + +These items are all just one byte long + + OP_END end of pattern + OP_ANY match any character + OP_ANYBYTE match any single byte, even in UTF-8 mode + OP_SOD match start of data: \A + OP_SOM, start of match (subject + offset): \G + OP_SET_SOM, set start of match (\K) + 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_HSPACE \H + OP_HSPACE \h + OP_NOT_WHITESPACE \S + OP_WHITESPACE \s + OP_NOT_VSPACE \V + OP_VSPACE \v + OP_NOT_WORDCHAR \W + OP_WORDCHAR \w + OP_EODN match end of data or \n at end: \Z + OP_EOD match end of data: \z + OP_DOLL $ (end of data, or before \n in multiline) + OP_EXTUNI match an extended Unicode character + OP_ANYNL match any Unicode newline sequence + + OP_ACCEPT ) + OP_COMMIT ) + OP_FAIL ) These are Perl 5.10's "backtracking + OP_PRUNE ) control verbs". + OP_SKIP ) + OP_THEN ) + + +Repeating single characters +--------------------------- + +The common repeats (*, +, ?) when applied to a single character use the +following opcodes: + + OP_STAR + OP_MINSTAR + OP_POSSTAR + OP_PLUS + OP_MINPLUS + OP_POSPLUS + OP_QUERY + OP_MINQUERY + OP_POSQUERY + +In ASCII mode, these are two-byte items; in UTF-8 mode, the length is variable. +Those with "MIN" in their name are the minimizing versions. Those with "POS" in +their names are possessive versions. Each is followed by the character that is +to be repeated. Other repeats make use of + + OP_UPTO + OP_MINUPTO + OP_POSUPTO + 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 or OPT_POSUPTO). + + +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_TYPEPOSSTAR + OP_TYPEPLUS + OP_TYPEMINPLUS + OP_TYPEPOSPLUS + OP_TYPEQUERY + OP_TYPEMINQUERY + OP_TYPEPOSQUERY + OP_TYPEUPTO + OP_TYPEMINUPTO + OP_TYPEPOSUPTO + OP_TYPEEXACT + + +Match by Unicode property +------------------------- + +OP_PROP and OP_NOTPROP are used for positive and negative matches of a +character by testing its Unicode property (the \p and \P escape sequences). +Each is followed by two bytes that encode the desired property as a type and a +value. + +Repeats of these items use the OP_TYPESTAR etc. set of opcodes, followed by +three bytes: OP_PROP or OP_NOTPROP and then the desired property type and +value. + + +Matching literal characters +--------------------------- + +The OP_CHAR opcode is followed by a single character that is to be matched +casefully. For caseless matching, OP_CHARNC is used. In UTF-8 mode, the +character may be more than one byte long. (Earlier versions of PCRE used +multi-character strings, but this was changed to allow some new features to be +added.) + + +Character classes +----------------- + +If there is only one character, OP_CHAR or OP_CHARNC is used for a positive +class, and OP_NOT for a negative one (that is, for something like [^a]). +However, in UTF-8 mode, the use of OP_NOT applies only to characters with +values < 128, because OP_NOT is confined to single bytes. + +Another set of repeating opcodes (OP_NOTSTAR etc.) are used for a repeated, +negated, single-character class. The normal ones (OP_STAR etc.) are used for a +repeated positive single-character class. + +When there's more than one character in a class and all the characters are less +than 256, OP_CLASS is used for a positive class, and OP_NCLASS for a negative +one. In either case, the opcode is followed by a 32-byte bit map containing a 1 +bit for every character that is acceptable. The bits are counted from the least +significant end of each byte. + +The reason for having both OP_CLASS and OP_NCLASS is so that, in UTF-8 mode, +subject characters with values greater than 256 can be handled correctly. For +OP_CLASS they don't match, whereas for OP_NCLASS they do. + +For classes containing characters with values > 255, OP_XCLASS is used. It +optionally uses a bit map (if any characters lie within it), followed by a list +of pairs and single characters. There is a flag character than indicates +whether it's a positive or a negative class. + + +Back references +--------------- + +OP_REF is followed by two bytes containing the reference number. + + +Repeating character classes and back references +----------------------------------------------- + +Single-character classes are handled specially (see above). This section +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. There are +no special possessive opcodes for these repeats; a possessive repeat is +compiled into an atomic group. + + +Brackets and alternation +------------------------ + +A pair of non-capturing (round) brackets is wrapped round each expression at +compile time, so alternation always happens in the context of brackets. + +[Note for North Americans: "bracket" to some English speakers, including +myself, can be round, square, curly, or pointy. Hence this usage.] + +Non-capturing brackets use the opcode OP_BRA. Originally PCRE was limited to 99 +capturing brackets and it used a different opcode for each one. From release +3.5, the limit was removed by putting the bracket number into the data for +higher-numbered brackets. From release 7.0 all capturing brackets are handled +this way, using the single opcode OP_CBRA. + +A bracket opcode is followed by LINK_SIZE bytes which give the offset to the +next alternative OP_ALT or, if there aren't any branches, to the matching +OP_KET opcode. Each OP_ALT is followed by LINK_SIZE bytes giving the offset to +the next one, or to the OP_KET opcode. For capturing brackets, the bracket +number immediately follows the offset, always as a 2-byte item. + +OP_KET is used for subpatterns that do not repeat indefinitely, while +OP_KETRMIN and OP_KETRMAX are used for indefinite repetitions, minimally or +maximally respectively. All three are followed by LINK_SIZE bytes giving (as a +positive number) the offset back to the matching bracket opcode. + +If a subpattern is quantified such that it is permitted to match zero times, it +is preceded by one of OP_BRAZERO or OP_BRAMINZERO. These are single-byte +opcodes which tell the matcher that skipping this subpattern entirely is a +valid branch. + +A subpattern with an indefinite maximum repetition is replicated in the +compiled data its minimum number of times (or once with OP_BRAZERO if the +minimum is zero), with the final copy terminating with OP_KETRMIN or OP_KETRMAX +as appropriate. + +A subpattern with a bounded maximum repetition is replicated in a nested +fashion up to the maximum number of times, with OP_BRAZERO or OP_BRAMINZERO +before each replication after the minimum, so that, for example, (abc){2,5} is +compiled as (abc)(abc)((abc)((abc)(abc)?)?)?, except that each bracketed group +has the same number. + +When a repeated subpattern has an unbounded upper limit, it is checked to see +whether it could match an empty string. If this is the case, the opcode in the +final replication is changed to OP_SBRA or OP_SCBRA. This tells the matcher +that it needs to check for matching an empty string when it hits OP_KETRMIN or +OP_KETRMAX, and if so, to break the loop. + + +Assertions +---------- + +Forward assertions are just like other subpatterns, but starting with one of +the opcodes OP_ASSERT or OP_ASSERT_NOT. Backward assertions use the opcodes +OP_ASSERTBACK and OP_ASSERTBACK_NOT, and the first opcode inside the assertion +is OP_REVERSE, followed by a two byte count of the number of characters to move +back the pointer in the subject string. When operating in UTF-8 mode, the count +is a character count rather than a byte count. A separate count is present in +each alternative of a lookbehind assertion, allowing them to have different +fixed lengths. + + +Once-only (atomic) subpatterns +------------------------------ + +These are also just like other subpatterns, but they start with the opcode +OP_ONCE. The check for matching an empty string in an unbounded repeat is +handled entirely at runtime, so there is just this one opcode. + + +Conditional subpatterns +----------------------- + +These are like other subpatterns, but they start with the opcode OP_COND, or +OP_SCOND for one that might match an empty string in an unbounded repeat. If +the condition is a back reference, this is stored at the start of the +subpattern using the opcode OP_CREF followed by two bytes containing the +reference number. If the condition is "in recursion" (coded as "(?(R)"), or "in +recursion of group x" (coded as "(?(Rx)"), the group number is stored at the +start of the subpattern using the opcode OP_RREF, and a value of zero for "the +whole pattern". For a DEFINE condition, just the single byte OP_DEF is used (it +has no associated data). Otherwise, a conditional subpattern always starts with +one of the assertions. + + +Recursion +--------- + +Recursion either matches the current regex, or some subexpression. The opcode +OP_RECURSE is followed by an value which is the offset to the starting bracket +from the start of the whole pattern. From release 6.5, OP_RECURSE is +automatically wrapped inside OP_ONCE brackets (because otherwise some patterns +broke it). OP_RECURSE is also used for "subroutine" calls, even though they +are not strictly a recursion. + + +Callout +------- + +OP_CALLOUT is followed by one byte of data that holds a callout number in the +range 0 to 254 for manual callouts, or 255 for an automatic callout. In both +cases there follows a two-byte value giving the offset in the pattern to the +start of the following item, and another two-byte item giving the length of the +next item. + + +Changing options +---------------- + +If any of the /i, /m, or /s options are changed within a pattern, an OP_OPT +opcode is compiled, followed by one byte containing the new settings of these +flags. If there are several alternatives, there is an occurrence of OP_OPT at +the start of all those following the first options change, to set appropriate +options for the start of the alternative. Immediately after the end of the +group there is another such item to reset the flags to their previous values. A +change of flag right at the very start of the pattern can be handled entirely +at compile time, and so does not cause anything to be put into the compiled +data. + +Philip Hazel +August 2007 ============================================================ --- pcre/LICENCE c5acb2598e023ab1d8b4ac2db0914c70f0f89765 +++ pcre/LICENCE c5acb2598e023ab1d8b4ac2db0914c70f0f89765 @@ -0,0 +1,68 @@ +PCRE LICENCE +------------ + +PCRE is a library of functions to support regular expressions whose syntax +and semantics are as close as possible to those of the Perl 5 language. + +Release 7 of PCRE is distributed under the terms of the "BSD" licence, as +specified below. The documentation for PCRE, supplied in the "doc" +directory, is distributed under the same terms as the software itself. + +The basic library functions are written in C and are freestanding. Also +included in the distribution is a set of C++ wrapper functions. + + +THE BASIC LIBRARY FUNCTIONS +--------------------------- + +Written by: Philip Hazel +Email local part: ph10 +Email domain: cam.ac.uk + +University of Cambridge Computing Service, +Cambridge, England. + +Copyright (c) 1997-2008 University of Cambridge +All rights reserved. + + +THE C++ WRAPPER FUNCTIONS +------------------------- + +Contributed by: Google Inc. + +Copyright (c) 2007-2008, Google Inc. +All rights reserved. + + +THE "BSD" LICENCE +----------------- + +Redistribution and use in source and binary forms, with or without +modification, are permitted provided that the following conditions are met: + + * Redistributions of source code must retain the above copyright notice, + this list of conditions and the following disclaimer. + + * Redistributions in binary form must reproduce the above copyright + notice, this list of conditions and the following disclaimer in the + documentation and/or other materials provided with the distribution. + + * Neither the name of the University of Cambridge nor the name of Google + Inc. nor the names of their contributors may be used to endorse or + promote products derived from this software without specific prior + written permission. + +THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" +AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE +IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE +ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE +LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR +CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF +SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS +INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN +CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) +ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE +POSSIBILITY OF SUCH DAMAGE. + +End ============================================================ --- pcre/NEWS e2e595652eb911e9efaa93148c4db4b984145b90 +++ pcre/NEWS e2e595652eb911e9efaa93148c4db4b984145b90 @@ -0,0 +1,408 @@ +News about PCRE releases +------------------------ + +Release 7.6 28-Jan-08 +--------------------- + +The main reason for having this release so soon after 7.5 is because it fixes a +potential buffer overflow problem in pcre_compile() when run in UTF-8 mode. In +addition, the CMake configuration files have been brought up to date. + + +Release 7.5 10-Jan-08 +--------------------- + +This is mainly a bug-fix release. However the ability to link pcregrep with +libz or libbz2 and the ability to link pcretest with libreadline have been +added. Also the --line-offsets and --file-offsets options were added to +pcregrep. + + +Release 7.4 21-Sep-07 +--------------------- + +The only change of specification is the addition of options to control whether +\R matches any Unicode line ending (the default) or just CR, LF, and CRLF. +Otherwise, the changes are bug fixes and a refactoring to reduce the number of +relocations needed in a shared library. There have also been some documentation +updates, in particular, some more information about using CMake to build PCRE +has been added to the NON-UNIX-USE file. + + +Release 7.3 28-Aug-07 +--------------------- + +Most changes are bug fixes. Some that are not: + +1. There is some support for Perl 5.10's experimental "backtracking control + verbs" such as (*PRUNE). + +2. UTF-8 checking is now as per RFC 3629 instead of RFC 2279; this is more + restrictive in the strings it accepts. + +3. Checking for potential integer overflow has been made more dynamic, and as a + consequence there is no longer a hard limit on the size of a subpattern that + has a limited repeat count. + +4. When CRLF is a valid line-ending sequence, pcre_exec() and pcre_dfa_exec() + no longer advance by two characters instead of one when an unanchored match + fails at CRLF if there are explicit CR or LF matches within the pattern. + This gets rid of some anomalous effects that previously occurred. + +5. Some PCRE-specific settings for varying the newline options at the start of + a pattern have been added. + + +Release 7.2 19-Jun-07 +--------------------- + +WARNING: saved patterns that were compiled by earlier versions of PCRE must be +recompiled for use with 7.2 (necessitated by the addition of \K, \h, \H, \v, +and \V). + +Correction to the notes for 7.1: the note about shared libraries for Windows is +wrong. Previously, three libraries were built, but each could function +independently. For example, the pcreposix library also included all the +functions from the basic pcre library. The change is that the three libraries +are no longer independent. They are like the Unix libraries. To use the +pcreposix functions, for example, you need to link with both the pcreposix and +the basic pcre library. + +Some more features from Perl 5.10 have been added: + + (?-n) and (?+n) relative references for recursion and subroutines. + + (?(-n) and (?(+n) relative references as conditions. + + \k{name} and \g{name} are synonyms for \k. + + \K to reset the start of the matched string; for example, (foo)\Kbar + matches bar preceded by foo, but only sets bar as the matched string. + + (?| introduces a group where the capturing parentheses in each alternative + start from the same number; for example, (?|(abc)|(xyz)) sets capturing + parentheses number 1 in both cases. + + \h, \H, \v, \V match horizontal and vertical whitespace, respectively. + + +Release 7.1 24-Apr-07 +--------------------- + +There is only one new feature in this release: a linebreak setting of +PCRE_NEWLINE_ANYCRLF. It is a cut-down version of PCRE_NEWLINE_ANY, which +recognizes only CRLF, CR, and LF as linebreaks. + +A few bugs are fixed (see ChangeLog for details), but the major change is a +complete re-implementation of the build system. This now has full Autotools +support and so is now "standard" in some sense. It should help with compiling +PCRE in a wide variety of environments. + +NOTE: when building shared libraries for Windows, three dlls are now built, +called libpcre, libpcreposix, and libpcrecpp. Previously, everything was +included in a single dll. + +Another important change is that the dftables auxiliary program is no longer +compiled and run at "make" time by default. Instead, a default set of character +tables (assuming ASCII coding) is used. If you want to use dftables to generate +the character tables as previously, add --enable-rebuild-chartables to the +"configure" command. You must do this if you are compiling PCRE to run on a +system that uses EBCDIC code. + +There is a discussion about character tables in the README file. The default is +not to use dftables so that that there is no problem when cross-compiling. + + +Release 7.0 19-Dec-06 +--------------------- + +This release has a new major number because there have been some internal +upheavals to facilitate the addition of new optimizations and other facilities, +and to make subsequent maintenance and extension easier. Compilation is likely +to be a bit slower, but there should be no major effect on runtime performance. +Previously compiled patterns are NOT upwards compatible with this release. If +you have saved compiled patterns from a previous release, you will have to +re-compile them. Important changes that are visible to users are: + +1. The Unicode property tables have been updated to Unicode 5.0.0, which adds + some more scripts. + +2. The option PCRE_NEWLINE_ANY causes PCRE to recognize any Unicode newline + sequence as a newline. + +3. The \R escape matches a single Unicode newline sequence as a single unit. + +4. New features that will appear in Perl 5.10 are now in PCRE. These include + alternative Perl syntax for named parentheses, and Perl syntax for + recursion. + +5. The C++ wrapper interface has been extended by the addition of a + QuoteMeta function and the ability to allow copy construction and + assignment. + +For a complete list of changes, see the ChangeLog file. + + +Release 6.7 04-Jul-06 +--------------------- + +The main additions to this release are the ability to use the same name for +multiple sets of parentheses, and support for CRLF line endings in both the +library and pcregrep (and in pcretest for testing). + +Thanks to Ian Taylor, the stack usage for many kinds of pattern has been +significantly reduced for certain subject strings. + + +Release 6.5 01-Feb-06 +--------------------- + +Important changes in this release: + +1. A number of new features have been added to pcregrep. + +2. The Unicode property tables have been updated to Unicode 4.1.0, and the + supported properties have been extended with script names such as "Arabic", + and the derived properties "Any" and "L&". This has necessitated a change to + the interal format of compiled patterns. Any saved compiled patterns that + use \p or \P must be recompiled. + +3. The specification of recursion in patterns has been changed so that all + recursive subpatterns are automatically treated as atomic groups. Thus, for + example, (?R) is treated as if it were (?>(?R)). This is necessary because + otherwise there are situations where recursion does not work. + +See the ChangeLog for a complete list of changes, which include a number of bug +fixes and tidies. + + +Release 6.0 07-Jun-05 +--------------------- + +The release number has been increased to 6.0 because of the addition of several +major new pieces of functionality. + +A new function, pcre_dfa_exec(), which implements pattern matching using a DFA +algorithm, has been added. This has a number of advantages for certain cases, +though it does run more slowly, and lacks the ability to capture substrings. On +the other hand, it does find all matches, not just the first, and it works +better for partial matching. The pcrematching man page discusses the +differences. + +The pcretest program has been enhanced so that it can make use of the new +pcre_dfa_exec() matching function and the extra features it provides. + +The distribution now includes a C++ wrapper library. This is built +automatically if a C++ compiler is found. The pcrecpp man page discusses this +interface. + +The code itself has been re-organized into many more files, one for each +function, so it no longer requires everything to be linked in when static +linkage is used. As a consequence, some internal functions have had to have +their names exposed. These functions all have names starting with _pcre_. They +are undocumented, and are not intended for use by outside callers. + +The pcregrep program has been enhanced with new functionality such as +multiline-matching and options for output more matching context. See the +ChangeLog for a complete list of changes to the library and the utility +programs. + + +Release 5.0 13-Sep-04 +--------------------- + +The licence under which PCRE is released has been changed to the more +conventional "BSD" licence. + +In the code, some bugs have been fixed, and there are also some major changes +in this release (which is why I've increased the number to 5.0). Some changes +are internal rearrangements, and some provide a number of new facilities. The +new features are: + +1. There's an "automatic callout" feature that inserts callouts before every + item in the regex, and there's a new callout field that gives the position + in the pattern - useful for debugging and tracing. + +2. The extra_data structure can now be used to pass in a set of character + tables at exec time. This is useful if compiled regex are saved and re-used + at a later time when the tables may not be at the same address. If the + default internal tables are used, the pointer saved with the compiled + pattern is now set to NULL, which means that you don't need to do anything + special unless you are using custom tables. + +3. It is possible, with some restrictions on the content of the regex, to + request "partial" matching. A special return code is given if all of the + subject string matched part of the regex. This could be useful for testing + an input field as it is being typed. + +4. There is now some optional support for Unicode character properties, which + means that the patterns items such as \p{Lu} and \X can now be used. Only + the general category properties are supported. If PCRE is compiled with this + support, an additional 90K data structure is include, which increases the + size of the library dramatically. + +5. There is support for saving compiled patterns and re-using them later. + +6. There is support for running regular expressions that were compiled on a + different host with the opposite endianness. + +7. The pcretest program has been extended to accommodate the new features. + +The main internal rearrangement is that sequences of literal characters are no +longer handled as strings. Instead, each character is handled on its own. This +makes some UTF-8 handling easier, and makes the support of partial matching +possible. Compiled patterns containing long literal strings will be larger as a +result of this change; I hope that performance will not be much affected. + + +Release 4.5 01-Dec-03 +--------------------- + +Again mainly a bug-fix and tidying release, with only a couple of new features: + +1. It's possible now to compile PCRE so that it does not use recursive +function calls when matching. Instead it gets memory from the heap. This slows +things down, but may be necessary on systems with limited stacks. + +2. UTF-8 string checking has been tightened to reject overlong sequences and to +check that a starting offset points to the start of a character. Failure of the +latter returns a new error code: PCRE_ERROR_BADUTF8_OFFSET. + +3. PCRE can now be compiled for systems that use EBCDIC code. + + +Release 4.4 21-Aug-03 +--------------------- + +This is mainly a bug-fix and tidying release. The only new feature is that PCRE +checks UTF-8 strings for validity by default. There is an option to suppress +this, just in case anybody wants that teeny extra bit of performance. + + +Releases 4.1 - 4.3 +------------------ + +Sorry, I forgot about updating the NEWS file for these releases. Please take a +look at ChangeLog. + + +Release 4.0 17-Feb-03 +--------------------- + +There have been a lot of changes for the 4.0 release, adding additional +functionality and mending bugs. Below is a list of the highlights of the new +functionality. For full details of these features, please consult the +documentation. For a complete list of changes, see the ChangeLog file. + +1. Support for Perl's \Q...\E escapes. + +2. "Possessive quantifiers" ?+, *+, ++, and {,}+ which come from Sun's Java +package. They provide some syntactic sugar for simple cases of "atomic +grouping". + +3. Support for the \G assertion. It is true when the current matching position +is at the start point of the match. + +4. A new feature that provides some of the functionality that Perl provides +with (?{...}). The facility is termed a "callout". The way it is done in PCRE +is for the caller to provide an optional function, by setting pcre_callout to +its entry point. To get the function called, the regex must include (?C) at +appropriate points. + +5. Support for recursive calls to individual subpatterns. This makes it really +easy to get totally confused. + +6. Support for named subpatterns. The Python syntax (?P...) is used to +name a group. + +7. Several extensions to UTF-8 support; it is now fairly complete. There is an +option for pcregrep to make it operate in UTF-8 mode. + +8. The single man page has been split into a number of separate man pages. +These also give rise to individual HTML pages which are put in a separate +directory. There is an index.html page that lists them all. Some hyperlinking +between the pages has been installed. + + +Release 3.5 15-Aug-01 +--------------------- + +1. The configuring system has been upgraded to use later versions of autoconf +and libtool. By default it builds both a shared and a static library if the OS +supports it. You can use --disable-shared or --disable-static on the configure +command if you want only one of them. + +2. The pcretest utility is now installed along with pcregrep because it is +useful for users (to test regexs) and by doing this, it automatically gets +relinked by libtool. The documentation has been turned into a man page, so +there are now .1, .txt, and .html versions in /doc. + +3. Upgrades to pcregrep: + (i) Added long-form option names like gnu grep. + (ii) Added --help to list all options with an explanatory phrase. + (iii) Added -r, --recursive to recurse into sub-directories. + (iv) Added -f, --file to read patterns from a file. + +4. Added --enable-newline-is-cr and --enable-newline-is-lf to the configure +script, to force use of CR or LF instead of \n in the source. On non-Unix +systems, the value can be set in config.h. + +5. The limit of 200 on non-capturing parentheses is a _nesting_ limit, not an +absolute limit. Changed the text of the error message to make this clear, and +likewise updated the man page. + +6. The limit of 99 on the number of capturing subpatterns has been removed. +The new limit is 65535, which I hope will not be a "real" limit. + + +Release 3.3 01-Aug-00 +--------------------- + +There is some support for UTF-8 character strings. This is incomplete and +experimental. The documentation describes what is and what is not implemented. +Otherwise, this is just a bug-fixing release. + + +Release 3.0 01-Feb-00 +--------------------- + +1. A "configure" script is now used to configure PCRE for Unix systems. It +builds a Makefile, a config.h file, and the pcre-config script. + +2. PCRE is built as a shared library by default. + +3. There is support for POSIX classes such as [:alpha:]. + +5. There is an experimental recursion feature. + +---------------------------------------------------------------------------- + IMPORTANT FOR THOSE UPGRADING FROM VERSIONS BEFORE 2.00 + +Please note that there has been a change in the API such that a larger +ovector is required at matching time, to provide some additional workspace. +The new man page has details. This change was necessary in order to support +some of the new functionality in Perl 5.005. + + IMPORTANT FOR THOSE UPGRADING FROM VERSION 2.00 + +Another (I hope this is the last!) change has been made to the API for the +pcre_compile() function. An additional argument has been added to make it +possible to pass over a pointer to character tables built in the current +locale by pcre_maketables(). To use the default tables, this new arguement +should be passed as NULL. + + IMPORTANT FOR THOSE UPGRADING FROM VERSION 2.05 + +Yet another (and again I hope this really is the last) change has been made +to the API for the pcre_exec() function. An additional argument has been +added to make it possible to start the match other than at the start of the +subject string. This is important if there are lookbehinds. The new man +page has the details, but you just want to convert existing programs, all +you need to do is to stick in a new fifth argument to pcre_exec(), with a +value of zero. For example, change + + pcre_exec(pattern, extra, subject, length, options, ovec, ovecsize) +to + pcre_exec(pattern, extra, subject, length, 0, options, ovec, ovecsize) + +**** ============================================================ --- pcre/NON-UNIX-USE 12b5c9442fc316b6a0b30e91bbfe2eae2355d045 +++ pcre/NON-UNIX-USE 12b5c9442fc316b6a0b30e91bbfe2eae2355d045 @@ -0,0 +1,432 @@ +Compiling PCRE on non-Unix systems +---------------------------------- + +This document contains the following sections: + + General + Generic instructions for the PCRE C library + The C++ wrapper functions + Building for virtual Pascal + Stack size in Windows environments + Linking programs in Windows environments + Comments about Win32 builds + Building PCRE on Windows with CMake + Use of relative paths with CMake on Windows + Testing with runtest.bat + Building under Windows with BCC5.5 + Building PCRE on OpenVMS + + +GENERAL + +I (Philip Hazel) have no experience of Windows or VMS sytems and how their +libraries work. The items in the PCRE distribution and Makefile that relate to +anything other than Unix-like systems are untested by me. + +There are some other comments and files in the Contrib directory on the ftp +site that you may find useful. See + + ftp://ftp.csx.cam.ac.uk/pub/software/programming/pcre/Contrib + +If you want to compile PCRE for a non-Unix system (especially for a system that +does not support "configure" and "make" files), note that the basic PCRE +library consists entirely of code written in Standard C, and so should compile +successfully on any system that has a Standard C compiler and library. The C++ +wrapper functions are a separate issue (see below). + +The PCRE distribution includes a "configure" file for use by the Configure/Make +build system, as found in many Unix-like environments. There is also support +support for CMake, which some users prefer, in particular in Windows +environments. There are some instructions for CMake under Windows in the +section entitled "Building PCRE with CMake" below. CMake can also be used to +build PCRE in Unix-like systems. + + +GENERIC INSTRUCTIONS FOR THE PCRE C LIBRARY + +The following are generic comments about building the PCRE C library "by hand". + + (1) Copy or rename the file config.h.generic as config.h, and edit the macro + settings that it contains to whatever is appropriate for your environment. + In particular, if you want to force a specific value for newline, you can + define the NEWLINE macro. When you compile any of the PCRE modules, you + must specify -DHAVE_CONFIG_H to your compiler so that config.h is included + in the sources. + + An alternative approach is not to edit config.h, but to use -D on the + compiler command line to make any changes that you need to the + configuration options. In this case -DHAVE_CONFIG_H must not be set. + + NOTE: There have been occasions when the way in which certain parameters + in config.h are used has changed between releases. (In the configure/make + world, this is handled automatically.) When upgrading to a new release, + you are strongly advised to review config.h.generic before re-using what + you had previously. + + (2) Copy or rename the file pcre.h.generic as pcre.h. + + (3) EITHER: + Copy or rename file pcre_chartables.c.dist as pcre_chartables.c. + + OR: + Compile dftables.c as a stand-alone program (using -DHAVE_CONFIG_H if + you have set up config.h), and then run it with the single argument + "pcre_chartables.c". This generates a set of standard character tables + and writes them to that file. The tables are generated using the default + C locale for your system. If you want to use a locale that is specified + by LC_xxx environment variables, add the -L option to the dftables + command. You must use this method if you are building on a system that + uses EBCDIC code. + + The tables in pcre_chartables.c are defaults. The caller of PCRE can + specify alternative tables at run time. + + (4) Ensure that you have the following header files: + + pcre_internal.h + ucp.h + ucpinternal.h + ucptable.h + + (5) Also ensure that you have the following file, which is #included as source + when building a debugging version of PCRE, and is also used by pcretest. + + pcre_printint.src + + (6) Compile the following source files, setting -DHAVE_CONFIG_H as a compiler + option if you have set up config.h with your configuration, or else use + other -D settings to change the configuration as required. + + pcre_chartables.c + pcre_compile.c + pcre_config.c + pcre_dfa_exec.c + pcre_exec.c + pcre_fullinfo.c + pcre_get.c + pcre_globals.c + pcre_info.c + pcre_maketables.c + pcre_newline.c + pcre_ord2utf8.c + pcre_refcount.c + pcre_study.c + pcre_tables.c + pcre_try_flipped.c + pcre_ucp_searchfuncs.c + pcre_valid_utf8.c + pcre_version.c + pcre_xclass.c + + Make sure that you include -I. in the compiler command (or equivalent for + an unusual compiler) so that all included PCRE header files are first + sought in the current directory. Otherwise you run the risk of picking up + a previously-installed file from somewhere else. + + (7) Now link all the compiled code into an object library in whichever form + your system keeps such libraries. This is the basic PCRE C library. If + your system has static and shared libraries, you may have to do this once + for each type. + + (8) Similarly, compile pcreposix.c (remembering -DHAVE_CONFIG_H if necessary) + and link the result (on its own) as the pcreposix library. + + (9) Compile the test program pcretest.c (again, don't forget -DHAVE_CONFIG_H). + This needs the functions in the pcre and pcreposix libraries when linking. + It also needs the pcre_printint.src source file, which it #includes. + +(10) Run pcretest on the testinput files in the testdata directory, and check + that the output matches the corresponding testoutput files. Note that the + supplied files are in Unix format, with just LF characters as line + terminators. You may need to edit them to change this if your system uses + a different convention. If you are using Windows, you probably should use + the wintestinput3 file instead of testinput3 (and the corresponding output + file). This is a locale test; wintestinput3 sets the locale to "french" + rather than "fr_FR", and there some minor output differences. + +(11) If you want to use the pcregrep command, compile and link pcregrep.c; it + uses only the basic PCRE library (it does not need the pcreposix library). + + +THE C++ WRAPPER FUNCTIONS + +The PCRE distribution also contains some C++ wrapper functions and tests, +contributed by Google Inc. On a system that can use "configure" and "make", +the functions are automatically built into a library called pcrecpp. It should +be straightforward to compile the .cc files manually on other systems. The +files called xxx_unittest.cc are test programs for each of the corresponding +xxx.cc files. + + +BUILDING FOR VIRTUAL PASCAL + +A script for building PCRE using Borland's C++ compiler for use with VPASCAL +was contributed by Alexander Tokarev. Stefan Weber updated the script and added +additional files. The following files in the distribution are for building PCRE +for use with VP/Borland: makevp_c.txt, makevp_l.txt, makevp.bat, pcregexp.pas. + + +STACK SIZE IN WINDOWS ENVIRONMENTS + +The default processor stack size of 1Mb in some Windows environments is too +small for matching patterns that need much recursion. In particular, test 2 may +fail because of this. Normally, running out of stack causes a crash, but there +have been cases where the test program has just died silently. See your linker +documentation for how to increase stack size if you experience problems. The +Linux default of 8Mb is a reasonable choice for the stack, though even that can +be too small for some pattern/subject combinations. + +PCRE has a compile configuration option to disable the use of stack for +recursion so that heap is used instead. However, pattern matching is +significantly slower when this is done. There is more about stack usage in the +"pcrestack" documentation. + + +LINKING PROGRAMS IN WINDOWS ENVIRONMENTS + +If you want to statically link a program against a PCRE library in the form of +a non-dll .a file, you must define PCRE_STATIC before including pcre.h, +otherwise the pcre_malloc() and pcre_free() exported functions will be declared +__declspec(dllimport), with unwanted results. + + +COMMENTS ABOUT WIN32 BUILDS (see also "BUILDING PCRE WITH CMAKE" below) + +There are two ways of building PCRE using the "configure, make, make install" +paradigm on Windows systems: using MinGW or using Cygwin. These are not at all +the same thing; they are completely different from each other. There is also +support for building using CMake, which some users find a more straightforward +way of building PCRE under Windows. However, the tests are not run +automatically when CMake is used. + +The MinGW home page (http://www.mingw.org/) says this: + + MinGW: A collection of freely available and freely distributable Windows + specific header files and import libraries combined with GNU toolsets that + allow one to produce native Windows programs that do not rely on any + 3rd-party C runtime DLLs. + +The Cygwin home page (http://www.cygwin.com/) says this: + + Cygwin is a Linux-like environment for Windows. It consists of two parts: + + . A DLL (cygwin1.dll) which acts as a Linux API emulation layer providing + substantial Linux API functionality + + . A collection of tools which provide Linux look and feel. + + The Cygwin DLL currently works with all recent, commercially released x86 32 + bit and 64 bit versions of Windows, with the exception of Windows CE. + +On both MinGW and Cygwin, PCRE should build correctly using: + + ./configure && make && make install + +This should create two libraries called libpcre and libpcreposix, and, if you +have enabled building the C++ wrapper, a third one called libpcrecpp. These are +independent libraries: when you like with libpcreposix or libpcrecpp you must +also link with libpcre, which contains the basic functions. (Some earlier +releases of PCRE included the basic libpcre functions in libpcreposix. This no +longer happens.) + +A user submitted a special-purpose patch that makes it easy to create +"pcre.dll" under mingw32 using the "msys" environment. It provides "pcre.dll" +as a special target. If you use this target, no other files are built, and in +particular, the pcretest and pcregrep programs are not built. An example of how +this might be used is: + + ./configure --enable-utf --disable-cpp CFLAGS="-03 -s"; make pcre.dll + +Using Cygwin's compiler generates libraries and executables that depend on +cygwin1.dll. If a library that is generated this way is distributed, +cygwin1.dll has to be distributed as well. Since cygwin1.dll is under the GPL +licence, this forces not only PCRE to be under the GPL, but also the entire +application. A distributor who wants to keep their own code proprietary must +purchase an appropriate Cygwin licence. + +MinGW has no such restrictions. The MinGW compiler generates a library or +executable that can run standalone on Windows without any third party dll or +licensing issues. + +But there is more complication: + +If a Cygwin user uses the -mno-cygwin Cygwin gcc flag, what that really does is +to tell Cygwin's gcc to use the MinGW gcc. Cygwin's gcc is only acting as a +front end to MinGW's gcc (if you install Cygwin's gcc, you get both Cygwin's +gcc and MinGW's gcc). So, a user can: + +. Build native binaries by using MinGW or by getting Cygwin and using + -mno-cygwin. + +. Build binaries that depend on cygwin1.dll by using Cygwin with the normal + compiler flags. + +The test files that are supplied with PCRE are in Unix format, with LF +characters as line terminators. It may be necessary to change the line +terminators in order to get some of the tests to work. We hope to improve +things in this area in future. + + +BUILDING PCRE ON WINDOWS WITH CMAKE + +CMake is an alternative build facility that can be used instead of the +traditional Unix "configure". CMake version 2.4.7 supports Borland makefiles, +MinGW makefiles, MSYS makefiles, NMake makefiles, UNIX makefiles, Visual Studio +6, Visual Studio 7, Visual Studio 8, and Watcom W8. The following instructions +were contributed by a PCRE user. + +1. Download CMake 2.4.7 or above from http://www.cmake.org/, install and ensure + that cmake\bin is on your path. + +2. Unzip (retaining folder structure) the PCRE source tree into a source + directory such as C:\pcre. + +3. Create a new, empty build directory: C:\pcre\build\ + +4. Run CMakeSetup from the Shell envirornment of your build tool, e.g., Msys + for Msys/MinGW or Visual Studio Command Prompt for VC/VC++ + +5. Enter C:\pcre\pcre-xx and C:\pcre\build for the source and build + directories, respectively + +6. Hit the "Configure" button. + +7. Select the particular IDE / build tool that you are using (Visual Studio, + MSYS makefiles, MinGW makefiles, etc.) + +8. The GUI will then list several configuration options. This is where you can + enable UTF-8 support, etc. + +9. Hit "Configure" again. The adjacent "OK" button should now be active. + +10. Hit "OK". + +11. The build directory should now contain a usable build system, be it a + solution file for Visual Studio, makefiles for MinGW, etc. + + +USE OF RELATIVE PATHS WITH CMAKE ON WINDOWS + +A PCRE user comments as follows: + +I thought that others may want to know the current state of +CMAKE_USE_RELATIVE_PATHS support on Windows. + +Here it is: +-- AdditionalIncludeDirectories is only partially modified (only the +first path - see below) +-- Only some of the contained file paths are modified - shown below for +pcre.vcproj +-- It properly modifies + +I am sure CMake people can fix that if they want to. Until then one will +need to replace existing absolute paths in project files with relative +paths manually (e.g. from VS) - relative to project file location. I did +just that before being told to try CMAKE_USE_RELATIVE_PATHS. Not a big +deal. + +AdditionalIncludeDirectories="E:\builds\pcre\build;E:\builds\pcre\pcre-7.5;" +AdditionalIncludeDirectories=".;E:\builds\pcre\pcre-7.5;" + +RelativePath="pcre.h"> +RelativePath="pcre_chartables.c"> +RelativePath="pcre_chartables.c.rule"> + + +TESTING WITH RUNTEST.BAT + +1. Copy RunTest.bat into the directory where pcretest.exe has been created. + +2. Edit RunTest.bat and insert a line that indentifies the relative location of + the pcre source, e.g.: + + set srcdir=..\pcre-7.4-RC3 + +3. Run RunTest.bat from a command shell environment. Test outputs will + automatically be compared to expected results, and discrepancies will + identified in the console output. + +4. To test pcrecpp, run pcrecpp_unittest.exe, pcre_stringpiece_unittest.exe and + pcre_scanner_unittest.exe. + + +BUILDING UNDER WINDOWS WITH BCC5.5 + +Michael Roy sent these comments about building PCRE under Windows with BCC5.5: + + Some of the core BCC libraries have a version of PCRE from 1998 built in, + which can lead to pcre_exec() giving an erroneous PCRE_ERROR_NULL from a + version mismatch. I'm including an easy workaround below, if you'd like to + include it in the non-unix instructions: + + When linking a project with BCC5.5, pcre.lib must be included before any of + the libraries cw32.lib, cw32i.lib, cw32mt.lib, and cw32mti.lib on the command + line. + + +BUILDING PCRE ON OPENVMS + +Dan Mooney sent the following comments about building PCRE on OpenVMS. They +relate to an older version of PCRE that used fewer source files, so the exact +commands will need changing. See the current list of source files above. + +"It was quite easy to compile and link the library. I don't have a formal +make file but the attached file [reproduced below] contains the OpenVMS DCL +commands I used to build the library. I had to add #define +POSIX_MALLOC_THRESHOLD 10 to pcre.h since it was not defined anywhere. + +The library was built on: +O/S: HP OpenVMS v7.3-1 +Compiler: Compaq C v6.5-001-48BCD +Linker: vA13-01 + +The test results did not match 100% due to the issues you mention in your +documentation regarding isprint(), iscntrl(), isgraph() and ispunct(). I +modified some of the character tables temporarily and was able to get the +results to match. Tests using the fr locale did not match since I don't have +that locale loaded. The study size was always reported to be 3 less than the +value in the standard test output files." + +========================= +$! This DCL procedure builds PCRE on OpenVMS +$! +$! I followed the instructions in the non-unix-use file in the distribution. +$! +$ COMPILE == "CC/LIST/NOMEMBER_ALIGNMENT/PREFIX_LIBRARY_ENTRIES=ALL_ENTRIES +$ COMPILE DFTABLES.C +$ LINK/EXE=DFTABLES.EXE DFTABLES.OBJ +$ RUN DFTABLES.EXE/OUTPUT=CHARTABLES.C +$ COMPILE MAKETABLES.C +$ COMPILE GET.C +$ COMPILE STUDY.C +$! I had to set POSIX_MALLOC_THRESHOLD to 10 in PCRE.H since the symbol +$! did not seem to be defined anywhere. +$! I edited pcre.h and added #DEFINE SUPPORT_UTF8 to enable UTF8 support. +$ COMPILE PCRE.C +$ LIB/CREATE PCRE MAKETABLES.OBJ, GET.OBJ, STUDY.OBJ, PCRE.OBJ +$! I had to set POSIX_MALLOC_THRESHOLD to 10 in PCRE.H since the symbol +$! did not seem to be defined anywhere. +$ COMPILE PCREPOSIX.C +$ LIB/CREATE PCREPOSIX PCREPOSIX.OBJ +$ COMPILE PCRETEST.C +$ LINK/EXE=PCRETEST.EXE PCRETEST.OBJ, PCRE/LIB, PCREPOSIX/LIB +$! C programs that want access to command line arguments must be +$! defined as a symbol +$ PCRETEST :== "$ SYS$ROADSUSERS:[DMOONEY.REGEXP]PCRETEST.EXE" +$! Arguments must be enclosed in quotes. +$ PCRETEST "-C" +$! Test results: +$! +$! The test results did not match 100%. The functions isprint(), iscntrl(), +$! isgraph() and ispunct() on OpenVMS must not produce the same results +$! as the system that built the test output files provided with the +$! distribution. +$! +$! The study size did not match and was always 3 less on OpenVMS. +$! +$! Locale could not be set to fr +$! +========================= + +Last Updated: 25 January 2008 +**** ============================================================ --- pcre/README 7897b63cee2850ff1ca833886101d23a2505c097 +++ pcre/README 7897b63cee2850ff1ca833886101d23a2505c097 @@ -0,0 +1,743 @@ +README file for PCRE (Perl-compatible regular expression library) +----------------------------------------------------------------- + +The latest release of PCRE is always available from + + ftp://ftp.csx.cam.ac.uk/pub/software/programming/pcre/pcre-xxx.tar.gz + +There is a mailing list for discussion about the development of PCRE at + + address@hidden + +Please read the NEWS file if you are upgrading from a previous release. +The contents of this README file are: + + The PCRE APIs + Documentation for PCRE + Contributions by users of PCRE + Building PCRE on non-Unix systems + Building PCRE on Unix-like systems + Retrieving configuration information on Unix-like systems + Shared libraries on Unix-like systems + Cross-compiling on Unix-like systems + Using HP's ANSI C++ compiler (aCC) + Making new tarballs + Testing PCRE + Character tables + File manifest + + +The PCRE APIs +------------- + +PCRE is written in C, and it has its own API. The distribution also includes a +set of C++ wrapper functions (see the pcrecpp man page for details), courtesy +of Google Inc. + +In addition, there is a set of C wrapper functions that are based on the POSIX +regular expression API (see the pcreposix man page). These end up in the +library called libpcreposix. Note that this just provides a POSIX calling +interface to PCRE; the regular expressions themselves still follow Perl syntax +and semantics. The POSIX API is restricted, and does not give full access to +all of PCRE's facilities. + +The header file for the POSIX-style functions is called pcreposix.h. The +official POSIX name is regex.h, but I did not want to risk possible problems +with existing files of that name by distributing it that way. To use PCRE with +an existing program that uses the POSIX API, pcreposix.h will have to be +renamed or pointed at by a link. + +If you are using the POSIX interface to PCRE and there is already a POSIX regex +library installed on your system, as well as worrying about the regex.h header +file (as mentioned above), you must also take care when linking programs to +ensure that they link with PCRE's libpcreposix library. Otherwise they may pick +up the POSIX functions of the same name from the other library. + +One way of avoiding this confusion is to compile PCRE with the addition of +-Dregcomp=PCREregcomp (and similarly for the other POSIX functions) to the +compiler flags (CFLAGS if you are using "configure" -- see below). This has the +effect of renaming the functions so that the names no longer clash. Of course, +you have to do the same thing for your applications, or write them using the +new names. + + +Documentation for PCRE +---------------------- + +If you install PCRE in the normal way on a Unix-like system, you will end up +with a set of man pages whose names all start with "pcre". The one that is just +called "pcre" lists all the others. In addition to these man pages, the PCRE +documentation is supplied in two other forms: + + 1. There are files called doc/pcre.txt, doc/pcregrep.txt, and + doc/pcretest.txt in the source distribution. The first of these is a + concatenation of the text forms of all the section 3 man pages except + those that summarize individual functions. The other two are the text + forms of the section 1 man pages for the pcregrep and pcretest commands. + These text forms are provided for ease of scanning with text editors or + similar tools. They are installed in /share/doc/pcre, where + is the installation prefix (defaulting to /usr/local). + + 2. A set of files containing all the documentation in HTML form, hyperlinked + in various ways, and rooted in a file called index.html, is distributed in + doc/html and installed in /share/doc/pcre/html. + + +Contributions by users of PCRE +------------------------------ + +You can find contributions from PCRE users in the directory + + ftp://ftp.csx.cam.ac.uk/pub/software/programming/pcre/Contrib + +There is a README file giving brief descriptions of what they are. Some are +complete in themselves; others are pointers to URLs containing relevant files. +Some of this material is likely to be well out-of-date. Several of the earlier +contributions provided support for compiling PCRE on various flavours of +Windows (I myself do not use Windows). Nowadays there is more Windows support +in the standard distribution, so these contibutions have been archived. + + +Building PCRE on non-Unix systems +--------------------------------- + +For a non-Unix system, please read the comments in the file NON-UNIX-USE, +though if your system supports the use of "configure" and "make" you may be +able to build PCRE in the same way as for Unix-like systems. PCRE can also be +configured in many platform environments using the GUI facility of CMake's +CMakeSetup. It creates Makefiles, solution files, etc. + +PCRE has been compiled on many different operating systems. It should be +straightforward to build PCRE on any system that has a Standard C compiler and +library, because it uses only Standard C functions. + + +Building PCRE on Unix-like systems +---------------------------------- + +If you are using HP's ANSI C++ compiler (aCC), please see the special note +in the section entitled "Using HP's ANSI C++ compiler (aCC)" below. + +The following instructions assume the use of the widely used "configure, make, +make install" process. There is also support for CMake in the PCRE +distribution; there are some comments about using CMake in the NON-UNIX-USE +file, though it can also be used in Unix-like systems. + +To build PCRE on a Unix-like system, first run the "configure" command from the +PCRE distribution directory, with your current directory set to the directory +where you want the files to be created. This command is a standard GNU +"autoconf" configuration script, for which generic instructions are supplied in +the file INSTALL. + +Most commonly, people build PCRE within its own distribution directory, and in +this case, on many systems, just running "./configure" is sufficient. However, +the usual methods of changing standard defaults are available. For example: + +CFLAGS='-O2 -Wall' ./configure --prefix=/opt/local + +specifies that the C compiler should be run with the flags '-O2 -Wall' instead +of the default, and that "make install" should install PCRE under /opt/local +instead of the default /usr/local. + +If you want to build in a different directory, just run "configure" with that +directory as current. For example, suppose you have unpacked the PCRE source +into /source/pcre/pcre-xxx, but you want to build it in /build/pcre/pcre-xxx: + +cd /build/pcre/pcre-xxx +/source/pcre/pcre-xxx/configure + +PCRE is written in C and is normally compiled as a C library. However, it is +possible to build it as a C++ library, though the provided building apparatus +does not have any features to support this. + +There are some optional features that can be included or omitted from the PCRE +library. You can read more about them in the pcrebuild man page. + +. If you want to suppress the building of the C++ wrapper library, you can add + --disable-cpp to the "configure" command. Otherwise, when "configure" is run, + it will try to find a C++ compiler and C++ header files, and if it succeeds, + it will try to build the C++ wrapper. + +. If you want to make use of the support for UTF-8 character strings in PCRE, + you must add --enable-utf8 to the "configure" command. Without it, the code + for handling UTF-8 is not included in the library. (Even when included, it + still has to be enabled by an option at run time.) + +. If, in addition to support for UTF-8 character strings, you want to include + support for the \P, \p, and \X sequences that recognize Unicode character + properties, you must add --enable-unicode-properties to the "configure" + command. This adds about 30K to the size of the library (in the form of a + property table); only the basic two-letter properties such as Lu are + supported. + +. You can build PCRE to recognize either CR or LF or the sequence CRLF or any + of the preceding, or any of the Unicode newline sequences as indicating the + end of a line. Whatever you specify at build time is the default; the caller + of PCRE can change the selection at run time. The default newline indicator + is a single LF character (the Unix standard). You can specify the default + newline indicator by adding --enable-newline-is-cr or --enable-newline-is-lf + or --enable-newline-is-crlf or --enable-newline-is-anycrlf or + --enable-newline-is-any to the "configure" command, respectively. + + If you specify --enable-newline-is-cr or --enable-newline-is-crlf, some of + the standard tests will fail, because the lines in the test files end with + LF. Even if the files are edited to change the line endings, there are likely + to be some failures. With --enable-newline-is-anycrlf or + --enable-newline-is-any, many tests should succeed, but there may be some + failures. + +. By default, the sequence \R in a pattern matches any Unicode line ending + sequence. This is independent of the option specifying what PCRE considers to + be the end of a line (see above). However, the caller of PCRE can restrict \R + to match only CR, LF, or CRLF. You can make this the default by adding + --enable-bsr-anycrlf to the "configure" command (bsr = "backslash R"). + +. When called via the POSIX interface, PCRE uses malloc() to get additional + storage for processing capturing parentheses if there are more than 10 of + them in a pattern. You can increase this threshold by setting, for example, + + --with-posix-malloc-threshold=20 + + on the "configure" command. + +. PCRE has a counter that can be set to limit the amount of resources it uses. + If the limit is exceeded during a match, the match fails. The default is ten + million. You can change the default by setting, for example, + + --with-match-limit=500000 + + on the "configure" command. This is just the default; individual calls to + pcre_exec() can supply their own value. There is more discussion on the + pcreapi man page. + +. There is a separate counter that limits the depth of recursive function calls + during a matching process. This also has a default of ten million, which is + essentially "unlimited". You can change the default by setting, for example, + + --with-match-limit-recursion=500000 + + Recursive function calls use up the runtime stack; running out of stack can + cause programs to crash in strange ways. There is a discussion about stack + sizes in the pcrestack man page. + +. The default maximum compiled pattern size is around 64K. You can increase + this by adding --with-link-size=3 to the "configure" command. You can + increase it even more by setting --with-link-size=4, but this is unlikely + ever to be necessary. Increasing the internal link size will reduce + performance. + +. You can build PCRE so that its internal match() function that is called from + pcre_exec() does not call itself recursively. Instead, it uses memory blocks + obtained from the heap via the special functions pcre_stack_malloc() and + pcre_stack_free() to save data that would otherwise be saved on the stack. To + build PCRE like this, use + + --disable-stack-for-recursion + + on the "configure" command. PCRE runs more slowly in this mode, but it may be + necessary in environments with limited stack sizes. This applies only to the + pcre_exec() function; it does not apply to pcre_dfa_exec(), which does not + use deeply nested recursion. There is a discussion about stack sizes in the + pcrestack man page. + +. For speed, PCRE uses four tables for manipulating and identifying characters + whose code point values are less than 256. By default, it uses a set of + tables for ASCII encoding that is part of the distribution. If you specify + + --enable-rebuild-chartables + + a program called dftables is compiled and run in the default C locale when + you obey "make". It builds a source file called pcre_chartables.c. If you do + not specify this option, pcre_chartables.c is created as a copy of + pcre_chartables.c.dist. See "Character tables" below for further information. + +. It is possible to compile PCRE for use on systems that use EBCDIC as their + default character code (as opposed to ASCII) by specifying + + --enable-ebcdic + + This automatically implies --enable-rebuild-chartables (see above). + +. It is possible to compile pcregrep to use libz and/or libbz2, in order to + read .gz and .bz2 files (respectively), by specifying one or both of + + --enable-pcregrep-libz + --enable-pcregrep-libbz2 + + Of course, the relevant libraries must be installed on your system. + +. It is possible to compile pcretest so that it links with the libreadline + library, by specifying + + --enable-pcretest-libreadline + + If this is done, when pcretest's input is from a terminal, it reads it using + the readline() function. This provides line-editing and history facilities. + Note that libreadline is GPL-licenced, so if you distribute a binary of + pcretest linked in this way, there may be licensing issues. + +The "configure" script builds the following files for the basic C library: + +. Makefile is the makefile that builds the library +. config.h contains build-time configuration options for the library +. pcre.h is the public PCRE header file +. pcre-config is a script that shows the settings of "configure" options +. libpcre.pc is data for the pkg-config command +. libtool is a script that builds shared and/or static libraries +. RunTest is a script for running tests on the basic C library +. RunGrepTest is a script for running tests on the pcregrep command + +Versions of config.h and pcre.h are distributed in the PCRE tarballs under +the names config.h.generic and pcre.h.generic. These are provided for the +benefit of those who have to built PCRE without the benefit of "configure". If +you use "configure", the .generic versions are not used. + +If a C++ compiler is found, the following files are also built: + +. libpcrecpp.pc is data for the pkg-config command +. pcrecpparg.h is a header file for programs that call PCRE via the C++ wrapper +. pcre_stringpiece.h is the header for the C++ "stringpiece" functions + +The "configure" script also creates config.status, which is an executable +script that can be run to recreate the configuration, and config.log, which +contains compiler output from tests that "configure" runs. + +Once "configure" has run, you can run "make". It builds two libraries, called +libpcre and libpcreposix, a test program called pcretest, and the pcregrep +command. If a C++ compiler was found on your system, "make" also builds the C++ +wrapper library, which is called libpcrecpp, and some test programs called +pcrecpp_unittest, pcre_scanner_unittest, and pcre_stringpiece_unittest. +Building the C++ wrapper can be disabled by adding --disable-cpp to the +"configure" command. + +The command "make check" runs all the appropriate tests. Details of the PCRE +tests are given below in a separate section of this document. + +You can use "make install" to install PCRE into live directories on your +system. The following are installed (file names are all relative to the + that is set when "configure" is run): + + Commands (bin): + pcretest + pcregrep + pcre-config + + Libraries (lib): + libpcre + libpcreposix + libpcrecpp (if C++ support is enabled) + + Configuration information (lib/pkgconfig): + libpcre.pc + libpcrecpp.pc (if C++ support is enabled) + + Header files (include): + pcre.h + pcreposix.h + pcre_scanner.h ) + pcre_stringpiece.h ) if C++ support is enabled + pcrecpp.h ) + pcrecpparg.h ) + + Man pages (share/man/man{1,3}): + pcregrep.1 + pcretest.1 + pcre.3 + pcre*.3 (lots more pages, all starting "pcre") + + HTML documentation (share/doc/pcre/html): + index.html + *.html (lots more pages, hyperlinked from index.html) + + Text file documentation (share/doc/pcre): + AUTHORS + COPYING + ChangeLog + LICENCE + NEWS + README + pcre.txt (a concatenation of the man(3) pages) + pcretest.txt the pcretest man page + pcregrep.txt the pcregrep man page + +If you want to remove PCRE from your system, you can run "make uninstall". +This removes all the files that "make install" installed. However, it does not +remove any directories, because these are often shared with other programs. + + +Retrieving configuration information on Unix-like systems +--------------------------------------------------------- + +Running "make install" installs the command pcre-config, which can be used to +recall information about the PCRE configuration and installation. For example: + + pcre-config --version + +prints the version number, and + + pcre-config --libs + +outputs information about where the library is installed. This command can be +included in makefiles for programs that use PCRE, saving the programmer from +having to remember too many details. + +The pkg-config command is another system for saving and retrieving information +about installed libraries. Instead of separate commands for each library, a +single command is used. For example: + + pkg-config --cflags pcre + +The data is held in *.pc files that are installed in a directory called +/lib/pkgconfig. + + +Shared libraries on Unix-like systems +------------------------------------- + +The default distribution builds PCRE as shared libraries and static libraries, +as long as the operating system supports shared libraries. Shared library +support relies on the "libtool" script which is built as part of the +"configure" process. + +The libtool script is used to compile and link both shared and static +libraries. They are placed in a subdirectory called .libs when they are newly +built. The programs pcretest and pcregrep are built to use these uninstalled +libraries (by means of wrapper scripts in the case of shared libraries). When +you use "make install" to install shared libraries, pcregrep and pcretest are +automatically re-built to use the newly installed shared libraries before being +installed themselves. However, the versions left in the build directory still +use the uninstalled libraries. + +To build PCRE using static libraries only you must use --disable-shared when +configuring it. For example: + +./configure --prefix=/usr/gnu --disable-shared + +Then run "make" in the usual way. Similarly, you can use --disable-static to +build only shared libraries. + + +Cross-compiling on Unix-like systems +------------------------------------ + +You can specify CC and CFLAGS in the normal way to the "configure" command, in +order to cross-compile PCRE for some other host. However, you should NOT +specify --enable-rebuild-chartables, because if you do, the dftables.c source +file is compiled and run on the local host, in order to generate the inbuilt +character tables (the pcre_chartables.c file). This will probably not work, +because dftables.c needs to be compiled with the local compiler, not the cross +compiler. + +When --enable-rebuild-chartables is not specified, pcre_chartables.c is created +by making a copy of pcre_chartables.c.dist, which is a default set of tables +that assumes ASCII code. Cross-compiling with the default tables should not be +a problem. + +If you need to modify the character tables when cross-compiling, you should +move pcre_chartables.c.dist out of the way, then compile dftables.c by hand and +run it on the local host to make a new version of pcre_chartables.c.dist. +Then when you cross-compile PCRE this new version of the tables will be used. + + +Using HP's ANSI C++ compiler (aCC) +---------------------------------- + +Unless C++ support is disabled by specifying the "--disable-cpp" option of the +"configure" script, you must include the "-AA" option in the CXXFLAGS +environment variable in order for the C++ components to compile correctly. + +Also, note that the aCC compiler on PA-RISC platforms may have a defect whereby +needed libraries fail to get included when specifying the "-AA" compiler +option. If you experience unresolved symbols when linking the C++ programs, +use the workaround of specifying the following environment variable prior to +running the "configure" script: + + CXXLDFLAGS="-lstd_v2 -lCsup_v2" + + +Making new tarballs +------------------- + +The command "make dist" creates three PCRE tarballs, in tar.gz, tar.bz2, and +zip formats. The command "make distcheck" does the same, but then does a trial +build of the new distribution to ensure that it works. + +If you have modified any of the man page sources in the doc directory, you +should first run the PrepareRelease script before making a distribution. This +script creates the .txt and HTML forms of the documentation from the man pages. + + +Testing PCRE +------------ + +To test the basic PCRE library on a Unix system, run the RunTest script that is +created by the configuring process. There is also a script called RunGrepTest +that tests the options of the pcregrep command. If the C++ wrapper library is +built, three test programs called pcrecpp_unittest, pcre_scanner_unittest, and +pcre_stringpiece_unittest are also built. + +Both the scripts and all the program tests are run if you obey "make check" or +"make test". For other systems, see the instructions in NON-UNIX-USE. + +The RunTest script runs the pcretest test program (which is documented in its +own man page) on each of the testinput files in the testdata directory in +turn, and compares the output with the contents of the corresponding testoutput +files. A file called testtry is used to hold the main output from pcretest +(testsavedregex is also used as a working file). To run pcretest on just one of +the test files, give its number as an argument to RunTest, for example: + + RunTest 2 + +The first test file can also be fed directly into the perltest.pl script to +check that Perl gives the same results. The only difference you should see is +in the first few lines, where the Perl version is given instead of the PCRE +version. + +The second set of tests check pcre_fullinfo(), pcre_info(), pcre_study(), +pcre_copy_substring(), pcre_get_substring(), pcre_get_substring_list(), error +detection, and run-time flags that are specific to PCRE, as well as the POSIX +wrapper API. It also uses the debugging flags to check some of the internals of +pcre_compile(). + +If you build PCRE with a locale setting that is not the standard C locale, the +character tables may be different (see next paragraph). In some cases, this may +cause failures in the second set of tests. For example, in a locale where the +isprint() function yields TRUE for characters in the range 128-255, the use of +[:isascii:] inside a character class defines a different set of characters, and +this shows up in this test as a difference in the compiled code, which is being +listed for checking. Where the comparison test output contains [\x00-\x7f] the +test will contain [\x00-\xff], and similarly in some other cases. This is not a +bug in PCRE. + +The third set of tests checks pcre_maketables(), the facility for building a +set of character tables for a specific locale and using them instead of the +default tables. The tests make use of the "fr_FR" (French) locale. Before +running the test, the script checks for the presence of this locale by running +the "locale" command. If that command fails, or if it doesn't include "fr_FR" +in the list of available locales, the third test cannot be run, and a comment +is output to say why. If running this test produces instances of the error + + ** Failed to set locale "fr_FR" + +in the comparison output, it means that locale is not available on your system, +despite being listed by "locale". This does not mean that PCRE is broken. + +[If you are trying to run this test on Windows, you may be able to get it to +work by changing "fr_FR" to "french" everywhere it occurs. Alternatively, use +RunTest.bat. The version of RunTest.bat included with PCRE 7.4 and above uses +Windows versions of test 2. More info on using RunTest.bat is included in the +document entitled NON-UNIX-USE.] + +The fourth test checks the UTF-8 support. It is not run automatically unless +PCRE is built with UTF-8 support. To do this you must set --enable-utf8 when +running "configure". This file can be also fed directly to the perltest script, +provided you are running Perl 5.8 or higher. (For Perl 5.6, a small patch, +commented in the script, can be be used.) + +The fifth test checks error handling with UTF-8 encoding, and internal UTF-8 +features of PCRE that are not relevant to Perl. + +The sixth test checks the support for Unicode character properties. It it not +run automatically unless PCRE is built with Unicode property support. To to +this you must set --enable-unicode-properties when running "configure". + +The seventh, eighth, and ninth tests check the pcre_dfa_exec() alternative +matching function, in non-UTF-8 mode, UTF-8 mode, and UTF-8 mode with Unicode +property support, respectively. The eighth and ninth tests are not run +automatically unless PCRE is build with the relevant support. + + +Character tables +---------------- + +For speed, PCRE uses four tables for manipulating and identifying characters +whose code point values are less than 256. The final argument of the +pcre_compile() function is a pointer to a block of memory containing the +concatenated tables. A call to pcre_maketables() can be used to generate a set +of tables in the current locale. If the final argument for pcre_compile() is +passed as NULL, a set of default tables that is built into the binary is used. + +The source file called pcre_chartables.c contains the default set of tables. By +default, this is created as a copy of pcre_chartables.c.dist, which contains +tables for ASCII coding. However, if --enable-rebuild-chartables is specified +for ./configure, a different version of pcre_chartables.c 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 pcre_chartables.c and then re-building PCRE. If +you do this, you should take care to ensure that the file does not get +automatically re-generated. The best way to do this is to move +pcre_chartables.c.dist out of the way and replace it with your customized +tables. + +When the dftables program is run as a result of --enable-rebuild-chartables, +it uses the default C locale that is set on your system. It does not pay +attention to the LC_xxx environment variables. In other words, it uses the +system's default locale rather than whatever the compiling user happens to have +set. If you really do want to build a source set of character tables in a +locale that is specified by the LC_xxx variables, you can run the dftables +program by hand with the -L option. For example: + + ./dftables -L pcre_chartables.c.special + +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 for code points less +than 256. + +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. + + +File manifest +------------- + +The distribution should contain the following files: + +(A) Source files of the PCRE library functions and their headers: + + dftables.c auxiliary program for building pcre_chartables.c + when --enable-rebuild-chartables is specified + + pcre_chartables.c.dist a default set of character tables that assume ASCII + coding; used, unless --enable-rebuild-chartables is + specified, by copying to pcre_chartables.c + + pcreposix.c ) + pcre_compile.c ) + pcre_config.c ) + pcre_dfa_exec.c ) + pcre_exec.c ) + pcre_fullinfo.c ) + pcre_get.c ) sources for the functions in the library, + pcre_globals.c ) and some internal functions that they use + pcre_info.c ) + pcre_maketables.c ) + pcre_newline.c ) + pcre_ord2utf8.c ) + pcre_refcount.c ) + pcre_study.c ) + pcre_tables.c ) + pcre_try_flipped.c ) + pcre_ucp_searchfuncs.c ) + pcre_valid_utf8.c ) + pcre_version.c ) + pcre_xclass.c ) + pcre_printint.src ) debugging function that is #included in pcretest, + ) and can also be #included in pcre_compile() + pcre.h.in template for pcre.h when built by "configure" + pcreposix.h header for the external POSIX wrapper API + pcre_internal.h header for internal use + ucp.h ) headers concerned with + ucpinternal.h ) Unicode property handling + ucptable.h ) (this one is the data table) + + config.h.in template for config.h, which is built by "configure" + + pcrecpp.h public header file for the C++ wrapper + pcrecpparg.h.in template for another C++ header file + pcre_scanner.h public header file for C++ scanner functions + pcrecpp.cc ) + pcre_scanner.cc ) source for the C++ wrapper library + + pcre_stringpiece.h.in template for pcre_stringpiece.h, the header for the + C++ stringpiece functions + pcre_stringpiece.cc source for the C++ stringpiece functions + +(B) Source files for programs that use PCRE: + + pcredemo.c simple demonstration of coding calls to PCRE + pcregrep.c source of a grep utility that uses PCRE + pcretest.c comprehensive test program + +(C) Auxiliary files: + + 132html script to turn "man" pages into HTML + AUTHORS information about the author of PCRE + ChangeLog log of changes to the code + CleanTxt script to clean nroff output for txt man pages + Detrail script to remove trailing spaces + HACKING some notes about the internals of PCRE + INSTALL generic installation instructions + LICENCE conditions for the use of PCRE + COPYING the same, using GNU's standard name + Makefile.in ) template for Unix Makefile, which is built by + ) "configure" + Makefile.am ) the automake input that was used to create + ) Makefile.in + NEWS important changes in this release + NON-UNIX-USE notes on building PCRE on non-Unix systems + PrepareRelease script to make preparations for "make dist" + README this file + RunTest a Unix shell script for running tests + RunGrepTest a Unix shell script for pcregrep tests + aclocal.m4 m4 macros (generated by "aclocal") + config.guess ) files used by libtool, + config.sub ) used only when building a shared library + configure a configuring shell script (built by autoconf) + configure.ac ) the autoconf input that was used to build + ) "configure" and config.h + depcomp ) script to find program dependencies, generated by + ) automake + doc/*.3 man page sources for the PCRE functions + doc/*.1 man page sources for pcregrep and pcretest + doc/index.html.src the base HTML page + doc/html/* HTML documentation + doc/pcre.txt plain text version of the man pages + doc/pcretest.txt plain text documentation of test program + doc/perltest.txt plain text documentation of Perl test program + install-sh a shell script for installing files + libpcre.pc.in template for libpcre.pc for pkg-config + libpcrecpp.pc.in template for libpcrecpp.pc for pkg-config + ltmain.sh file used to build a libtool script + missing ) common stub for a few missing GNU programs while + ) installing, generated by automake + mkinstalldirs script for making install directories + perltest.pl Perl test program + pcre-config.in source of script which retains PCRE information + pcrecpp_unittest.cc ) + pcre_scanner_unittest.cc ) test programs for the C++ wrapper + pcre_stringpiece_unittest.cc ) + testdata/testinput* test data for main library tests + testdata/testoutput* expected test results + testdata/grep* input and output for pcregrep tests + +(D) Auxiliary files for cmake support + + CMakeLists.txt + config-cmake.h.in + +(E) Auxiliary files for VPASCAL + + makevp.bat + makevp_c.txt + makevp_l.txt + pcregexp.pas + +(F) Auxiliary files for building PCRE "by hand" + + pcre.h.generic ) a version of the public PCRE header file + ) for use in non-"configure" environments + config.h.generic ) a version of config.h for use in non-"configure" + ) environments + +(F) Miscellaneous + + RunTest.bat a script for running tests under Windows + +Philip Hazel +Email local part: ph10 +Email domain: cam.ac.uk +Last updated: 25 January 2008 ============================================================ --- pcre/RunGrepTest 77b7b1753167de06e81dab91ff81664f4659ccf4 +++ pcre/RunGrepTest 77b7b1753167de06e81dab91ff81664f4659ccf4 @@ -0,0 +1,277 @@ +#! /bin/sh + +# Run pcregrep tests. The assumption is that the PCRE tests check the library +# itself. What we are checking here is the file handling and options that are +# supported by pcregrep. + +# Set the C locale, so that sort(1) behaves predictably. +LC_ALL=C +export LC_ALL + +pcregrep=`pwd`/pcregrep + +echo " " +echo "Testing pcregrep" +$pcregrep -V + +cf="diff -ub" +valgrind= + +while [ $# -gt 0 ] ; do + case $1 in + valgrind) valgrind="valgrind -q --leak-check=no";; + *) echo "Unknown argument $1"; exit 1;; + esac + shift +done + +# If PCRE has been built in a directory other than the source directory, and +# this test is being run from "make check" as usual, then $(srcdir) will be +# set. If not, set it to the current directory. We then arrange to run the +# pcregrep command in the source directory so that the file names that appear +# in the output are always the same. + +if [ -z "$srcdir" -o ! -d "$srcdir/testdata" ] ; then + srcdir=. +fi + +# Check for the availability of UTF-8 support + +./pcretest -C | ./pcregrep "No UTF-8 support" >/dev/null +utf8=$? + +echo "---------------------------- Test 1 ------------------------------" >testtry +(cd $srcdir; $valgrind $pcregrep PATTERN ./testdata/grepinput) >>testtry + +echo "---------------------------- Test 2 ------------------------------" >>testtry +(cd $srcdir; $valgrind $pcregrep '^PATTERN' ./testdata/grepinput) >>testtry + +echo "---------------------------- Test 3 ------------------------------" >>testtry +(cd $srcdir; $valgrind $pcregrep -in PATTERN ./testdata/grepinput) >>testtry + +echo "---------------------------- Test 4 ------------------------------" >>testtry +(cd $srcdir; $valgrind $pcregrep -ic PATTERN ./testdata/grepinput) >>testtry + +echo "---------------------------- Test 5 ------------------------------" >>testtry +(cd $srcdir; $valgrind $pcregrep -in PATTERN ./testdata/grepinput ./testdata/grepinputx) >>testtry + +echo "---------------------------- Test 6 ------------------------------" >>testtry +(cd $srcdir; $valgrind $pcregrep -inh PATTERN ./testdata/grepinput ./testdata/grepinputx) >>testtry + +echo "---------------------------- Test 7 ------------------------------" >>testtry +(cd $srcdir; $valgrind $pcregrep -il PATTERN ./testdata/grepinput ./testdata/grepinputx) >>testtry + +echo "---------------------------- Test 8 ------------------------------" >>testtry +(cd $srcdir; $valgrind $pcregrep -l PATTERN ./testdata/grepinput ./testdata/grepinputx) >>testtry + +echo "---------------------------- Test 9 ------------------------------" >>testtry +(cd $srcdir; $valgrind $pcregrep -q PATTERN ./testdata/grepinput ./testdata/grepinputx) >>testtry +echo "RC=$?" >>testtry + +echo "---------------------------- Test 10 -----------------------------" >>testtry +(cd $srcdir; $valgrind $pcregrep -q NEVER-PATTERN ./testdata/grepinput ./testdata/grepinputx) >>testtry +echo "RC=$?" >>testtry + +echo "---------------------------- Test 11 -----------------------------" >>testtry +(cd $srcdir; $valgrind $pcregrep -vn pattern ./testdata/grepinputx) >>testtry + +echo "---------------------------- Test 12 -----------------------------" >>testtry +(cd $srcdir; $valgrind $pcregrep -ix pattern ./testdata/grepinputx) >>testtry + +echo "---------------------------- Test 13 -----------------------------" >>testtry +(cd $srcdir; $valgrind $pcregrep -f./testdata/greplist ./testdata/grepinputx) >>testtry + +echo "---------------------------- Test 14 -----------------------------" >>testtry +(cd $srcdir; $valgrind $pcregrep -w pat ./testdata/grepinput ./testdata/grepinputx) >>testtry + +echo "---------------------------- Test 15 -----------------------------" >>testtry +(cd $srcdir; $valgrind $pcregrep 'abc^*' ./testdata/grepinput) 2>>testtry >>testtry + +echo "---------------------------- Test 16 -----------------------------" >>testtry +(cd $srcdir; $valgrind $pcregrep abc ./testdata/grepinput ./testdata/nonexistfile) 2>>testtry >>testtry + +echo "---------------------------- Test 17 -----------------------------" >>testtry +(cd $srcdir; $valgrind $pcregrep -M 'the\noutput' ./testdata/grepinput) >>testtry + +echo "---------------------------- Test 18 -----------------------------" >>testtry +(cd $srcdir; $valgrind $pcregrep -Mn '(the\noutput|dog\.\n--)' ./testdata/grepinput) >>testtry + +echo "---------------------------- Test 19 -----------------------------" >>testtry +(cd $srcdir; $valgrind $pcregrep -Mix 'Pattern' ./testdata/grepinputx) >>testtry + +echo "---------------------------- Test 20 -----------------------------" >>testtry +(cd $srcdir; $valgrind $pcregrep -Mixn 'complete pair\nof lines' ./testdata/grepinputx) >>testtry + +echo "---------------------------- Test 21 -----------------------------" >>testtry +(cd $srcdir; $valgrind $pcregrep -nA3 'four' ./testdata/grepinputx) >>testtry + +echo "---------------------------- Test 22 -----------------------------" >>testtry +(cd $srcdir; $valgrind $pcregrep -nB3 'four' ./testdata/grepinputx) >>testtry + +echo "---------------------------- Test 23 -----------------------------" >>testtry +(cd $srcdir; $valgrind $pcregrep -C3 'four' ./testdata/grepinputx) >>testtry + +echo "---------------------------- Test 24 -----------------------------" >>testtry +(cd $srcdir; $valgrind $pcregrep -A9 'four' ./testdata/grepinputx) >>testtry + +echo "---------------------------- Test 25 -----------------------------" >>testtry +(cd $srcdir; $valgrind $pcregrep -nB9 'four' ./testdata/grepinputx) >>testtry + +echo "---------------------------- Test 26 -----------------------------" >>testtry +(cd $srcdir; $valgrind $pcregrep -A9 -B9 'four' ./testdata/grepinputx) >>testtry + +echo "---------------------------- Test 27 -----------------------------" >>testtry +(cd $srcdir; $valgrind $pcregrep -A10 'four' ./testdata/grepinputx) >>testtry + +echo "---------------------------- Test 28 -----------------------------" >>testtry +(cd $srcdir; $valgrind $pcregrep -nB10 'four' ./testdata/grepinputx) >>testtry + +echo "---------------------------- Test 29 -----------------------------" >>testtry +(cd $srcdir; $valgrind $pcregrep -C12 -B10 'four' ./testdata/grepinputx) >>testtry + +echo "---------------------------- Test 30 -----------------------------" >>testtry +(cd $srcdir; $valgrind $pcregrep -inB3 'pattern' ./testdata/grepinput ./testdata/grepinputx) >>testtry + +echo "---------------------------- Test 31 -----------------------------" >>testtry +(cd $srcdir; $valgrind $pcregrep -inA3 'pattern' ./testdata/grepinput ./testdata/grepinputx) >>testtry + +echo "---------------------------- Test 32 -----------------------------" >>testtry +(cd $srcdir; $valgrind $pcregrep -L 'fox' ./testdata/grepinput ./testdata/grepinputx) >>testtry + +echo "---------------------------- Test 33 -----------------------------" >>testtry +(cd $srcdir; $valgrind $pcregrep 'fox' ./testdata/grepnonexist) >>testtry 2>&1 +echo "RC=$?" >>testtry + +echo "---------------------------- Test 34 -----------------------------" >>testtry +(cd $srcdir; $valgrind $pcregrep -s 'fox' ./testdata/grepnonexist) >>testtry 2>&1 +echo "RC=$?" >>testtry + +echo "---------------------------- Test 35 -----------------------------" >>testtry +(cd $srcdir; $valgrind $pcregrep -L -r --include=grepinputx 'fox' ./testdata) >>testtry +echo "RC=$?" >>testtry + +echo "---------------------------- Test 36 -----------------------------" >>testtry +(cd $srcdir; $valgrind $pcregrep -L -r --include=grepinput --exclude 'grepinput$' 'fox' ./testdata | sort) >>testtry +echo "RC=$?" >>testtry + +echo "---------------------------- Test 37 -----------------------------" >>testtry +(cd $srcdir; $valgrind $pcregrep '^(a+)*\d' ./testdata/grepinput) >>testtry 2>teststderr +echo "RC=$?" >>testtry +echo "======== STDERR ========" >>testtry +cat teststderr >>testtry + +echo "---------------------------- Test 38 ------------------------------" >>testtry +(cd $srcdir; $valgrind $pcregrep '>\x00<' ./testdata/grepinput) >>testtry + +echo "---------------------------- Test 39 ------------------------------" >>testtry +(cd $srcdir; $valgrind $pcregrep -A1 'before the binary zero' ./testdata/grepinput) >>testtry + +echo "---------------------------- Test 40 ------------------------------" >>testtry +(cd $srcdir; $valgrind $pcregrep -B1 'after the binary zero' ./testdata/grepinput) >>testtry + +echo "---------------------------- Test 41 ------------------------------" >>testtry +(cd $srcdir; $valgrind $pcregrep -B1 -o '\w+ the binary zero' ./testdata/grepinput) >>testtry + +echo "---------------------------- Test 41 ------------------------------" >>testtry +(cd $srcdir; $valgrind $pcregrep -B1 -onH '\w+ the binary zero' ./testdata/grepinput) >>testtry + +echo "---------------------------- Test 42 ------------------------------" >>testtry +(cd $srcdir; $valgrind $pcregrep -on 'before|zero|after' ./testdata/grepinput) >>testtry + +echo "---------------------------- Test 43 ------------------------------" >>testtry +(cd $srcdir; $valgrind $pcregrep -on -e before -e zero -e after ./testdata/grepinput) >>testtry + +echo "---------------------------- Test 44 ------------------------------" >>testtry +(cd $srcdir; $valgrind $pcregrep -on -f ./testdata/greplist -e binary ./testdata/grepinput) >>testtry + +echo "---------------------------- Test 45 ------------------------------" >>testtry +(cd $srcdir; $valgrind $pcregrep -e abc -e '(unclosed' ./testdata/grepinput) 2>>testtry >>testtry + +echo "---------------------------- Test 46 ------------------------------" >>testtry +(cd $srcdir; $valgrind $pcregrep -Fx "AB.VE +elephant" ./testdata/grepinput) >>testtry + +echo "---------------------------- Test 47 ------------------------------" >>testtry +(cd $srcdir; $valgrind $pcregrep -F "AB.VE +elephant" ./testdata/grepinput) >>testtry + +echo "---------------------------- Test 48 ------------------------------" >>testtry +(cd $srcdir; $valgrind $pcregrep -F -e DATA -e "AB.VE +elephant" ./testdata/grepinput) >>testtry + +echo "---------------------------- Test 49 ------------------------------" >>testtry +(cd $srcdir; $valgrind $pcregrep "^(abc|def|ghi|jkl)" ./testdata/grepinputx) >>testtry + +echo "---------------------------- Test 50 ------------------------------" >>testtry +(cd $srcdir; $valgrind $pcregrep -Mv "brown\sfox" ./testdata/grepinputv) >>testtry + +echo "---------------------------- Test 51 ------------------------------" >>testtry +(cd $srcdir; $valgrind $pcregrep --colour=always jumps ./testdata/grepinputv) >>testtry + +echo "---------------------------- Test 52 ------------------------------" >>testtry +(cd $srcdir; $valgrind $pcregrep --file-offsets 'before|zero|after' ./testdata/grepinput) >>testtry + +echo "---------------------------- Test 53 ------------------------------" >>testtry +(cd $srcdir; $valgrind $pcregrep --line-offsets 'before|zero|after' ./testdata/grepinput) >>testtry + +# Now compare the results. + +$cf $srcdir/testdata/grepoutput testtry +if [ $? != 0 ] ; then exit 1; fi + + +# These tests require UTF-8 support + +if [ $utf8 -ne 0 ] ; then + echo "Testing pcregrep UTF-8 features" + + echo "---------------------------- Test U1 ------------------------------" >testtry + (cd $srcdir; $valgrind $pcregrep -n -u --newline=any "^X" ./testdata/grepinput8) >>testtry + + echo "---------------------------- Test U2 ------------------------------" >>testtry + (cd $srcdir; $valgrind $pcregrep -n -u -C 3 --newline=any "Match" ./testdata/grepinput8) >>testtry + + $cf $srcdir/testdata/grepoutput8 testtry + if [ $? != 0 ] ; then exit 1; fi + +else + echo "Skipping pcregrep UTF-8 tests: no UTF-8 support in PCRE library" +fi + + +# We go to some contortions to try to ensure that the tests for the various +# newline settings will work in environments where the normal newline sequence +# is not \n. Do not use exported files, whose line endings might be changed. +# Instead, create an input file using printf so that its contents are exactly +# what we want. Note the messy fudge to get printf to write a string that +# starts with a hyphen. + +echo "Testing pcregrep newline settings" +printf "abc\rdef\r\nghi\njkl" >testNinput + +printf "%c--------------------------- Test N1 ------------------------------\r\n" - >testtry +$valgrind $pcregrep -n -N CR "^(abc|def|ghi|jkl)" testNinput >>testtry + +printf "%c--------------------------- Test N2 ------------------------------\r\n" - >>testtry +$valgrind $pcregrep -n --newline=crlf "^(abc|def|ghi|jkl)" testNinput >>testtry + +printf "%c--------------------------- Test N3 ------------------------------\r\n" - >>testtry +pattern=`printf 'def\rjkl'` +$valgrind $pcregrep -n --newline=cr -F "$pattern" testNinput >>testtry + +printf "%c--------------------------- Test N4 ------------------------------\r\n" - >>testtry +pattern=`printf 'xxx\r\njkl'` +$valgrind $pcregrep -n --newline=crlf -F "$pattern" testNinput >>testtry + +printf "%c--------------------------- Test N5 ------------------------------\r\n" - >>testtry +$valgrind $pcregrep -n --newline=any "^(abc|def|ghi|jkl)" testNinput >>testtry + +printf "%c--------------------------- Test N6 ------------------------------\r\n" - >>testtry +$valgrind $pcregrep -n --newline=anycrlf "^(abc|def|ghi|jkl)" testNinput >>testtry + +$cf $srcdir/testdata/grepoutputN testtry +if [ $? != 0 ] ; then exit 1; fi + +exit 0 + +# End ============================================================ --- pcre/RunTest 18799bc463805cdf4a832bc5b813a4df1906f8ee +++ pcre/RunTest 18799bc463805cdf4a832bc5b813a4df1906f8ee @@ -0,0 +1,279 @@ +#! /bin/sh + +# Run PCRE tests + +cf="diff -u" +valgrind= +testdata=testdata + +if [ -n "$srcdir" -a -d "$srcdir" ] ; then + testdata="$srcdir/testdata" +fi + +# Find which optional facilities are available + +case `./pcretest -C | ./pcregrep 'Internal link size'` in + *2) link_size=2;; + *3) link_size=3;; + *4) link_size=4;; + *) echo "Failed to find internal link size"; exit 1;; +esac + +./pcretest -C | ./pcregrep 'No UTF-8 support' >/dev/null +utf8=$? + +./pcretest -C | ./pcregrep 'No Unicode properties support' >/dev/null +ucp=$? + +# Select which tests to run; for those that are explicitly requested, check +# that the necessary optional facilities are available. + +do1=no +do2=no +do3=no +do4=no +do5=no +do6=no +do7=no +do8=no +do9=no +do10=no + +while [ $# -gt 0 ] ; do + case $1 in + 1) do1=yes;; + 2) do2=yes;; + 3) do3=yes;; + 4) do4=yes;; + 5) do5=yes;; + 6) do6=yes;; + 7) do7=yes;; + 8) do8=yes;; + 9) do9=yes;; + 10) do10=yes;; + valgrind) valgrind="valgrind -q";; + *) echo "Unknown test number $1"; exit 1;; + esac + shift +done + +if [ $utf8 -eq 0 ] ; then + if [ $do4 = yes ] ; then + echo "Can't run test 4 because UTF-8 support is not configured" + exit 1 + fi + if [ $do5 = yes ] ; then + echo "Can't run test 5 because UTF-8 support is not configured" + exit 1 + fi + if [ $do8 = yes ] ; then + echo "Can't run test 8 because UTF-8 support is not configured" + exit 1 + fi +fi + +if [ $ucp -eq 0 ] ; then + if [ $do6 = yes ] ; then + echo "Can't run test 6 because Unicode property support is not configured" + exit 1 + fi + if [ $do9 = yes ] ; then + echo "Can't run test 9 because Unicode property support is not configured" + exit 1 + fi + if [ $do10 = yes ] ; then + echo "Can't run test 10 because Unicode property support is not configured" + exit 1 + fi +fi + +if [ $link_size -ne 2 ] ; then + if [ $do10 = yes ] ; then + echo "Can't run test 10 because the link size ($link_size) is not 2" + exit 1 + fi +fi + +# If no specific tests were requested, select all that are relevant. + +if [ $do1 = no -a $do2 = no -a $do3 = no -a $do4 = no -a \ + $do5 = no -a $do6 = no -a $do7 = no -a $do8 = no -a \ + $do9 = no -a $do10 = no ] ; then + do1=yes + do2=yes + do3=yes + if [ $utf8 -ne 0 ] ; then do4=yes; fi + if [ $utf8 -ne 0 ] ; then do5=yes; fi + if [ $utf8 -ne 0 -a $ucp -ne 0 ] ; then do6=yes; fi + do7=yes + if [ $utf8 -ne 0 ] ; then do8=yes; fi + if [ $utf8 -ne 0 -a $ucp -ne 0 ] ; then do9=yes; fi + if [ $link_size -eq 2 -a $ucp -ne 0 ] ; then do10=yes; fi +fi + +# Show which release + +echo "" +echo PCRE C library tests +./pcretest /dev/null + +# Primary test, Perl-compatible + +if [ $do1 = yes ] ; then + echo "Test 1: main functionality (Perl compatible)" + $valgrind ./pcretest -q $testdata/testinput1 testtry + if [ $? = 0 ] ; then + $cf $testdata/testoutput1 testtry + if [ $? != 0 ] ; then exit 1; fi + else exit 1 + fi + echo "OK" +fi + +# PCRE tests that are not Perl-compatible - API & error tests, mostly + +if [ $do2 = yes ] ; then + echo "Test 2: API and error handling (not Perl compatible)" + $valgrind ./pcretest -q $testdata/testinput2 testtry + if [ $? = 0 ] ; then + $cf $testdata/testoutput2 testtry + if [ $? != 0 ] ; then exit 1; fi + else exit 1 + fi + echo "OK" +fi + +# Locale-specific tests, provided that either the "fr_FR" or the "french" +# locale is available. The former is the Unix-like standard; the latter is +# for Windows. + +if [ $do3 = yes ] ; then + locale -a | grep '^fr_FR$' >/dev/null + if [ $? -eq 0 ] ; then + locale=fr_FR + infile=$testdata/testinput3 + outfile=$testdata/testoutput3 + else + locale -a | grep '^french$' >/dev/null + if [ $? -eq 0 ] ; then + locale=french + sed 's/fr_FR/french/' $testdata/testinput3 >test3input + sed 's/fr_FR/french/' $testdata/testoutput3 >test3output + infile=test3input + outfile=test3output + else + locale= + fi + fi + + if [ "$locale" != "" ] ; then + echo "Test 3: locale-specific features (using '$locale' locale)" + $valgrind ./pcretest -q $infile testtry + if [ $? = 0 ] ; then + $cf $outfile testtry + if [ $? != 0 ] ; then + echo " " + echo "Locale test did not run entirely successfully." + echo "This usually means that there is a problem with the locale" + echo "settings rather than a bug in PCRE." + else + echo "OK" + fi + else exit 1 + fi + else + echo "Cannot test locale-specific features - neither the 'fr_FR' nor the" + echo "'french' locale exists, or the \"locale\" command is not available" + echo "to check for them." + echo " " + fi +fi + +# Additional tests for UTF8 support + +if [ $do4 = yes ] ; then + echo "Test 4: UTF-8 support (Perl compatible)" + $valgrind ./pcretest -q $testdata/testinput4 testtry + if [ $? = 0 ] ; then + $cf $testdata/testoutput4 testtry + if [ $? != 0 ] ; then exit 1; fi + else exit 1 + fi + echo "OK" +fi + +if [ $do5 = yes ] ; then + echo "Test 5: API and internals for UTF-8 support (not Perl compatible)" + $valgrind ./pcretest -q $testdata/testinput5 testtry + if [ $? = 0 ] ; then + $cf $testdata/testoutput5 testtry + if [ $? != 0 ] ; then exit 1; fi + else exit 1 + fi + echo "OK" +fi + +if [ $do6 = yes ] ; then + echo "Test 6: Unicode property support" + $valgrind ./pcretest -q $testdata/testinput6 testtry + if [ $? = 0 ] ; then + $cf $testdata/testoutput6 testtry + if [ $? != 0 ] ; then exit 1; fi + else exit 1 + fi + echo "OK" +fi + +# Tests for DFA matching support + +if [ $do7 = yes ] ; then + echo "Test 7: DFA matching" + $valgrind ./pcretest -q -dfa $testdata/testinput7 testtry + if [ $? = 0 ] ; then + $cf $testdata/testoutput7 testtry + if [ $? != 0 ] ; then exit 1; fi + else exit 1 + fi + echo "OK" +fi + +if [ $do8 = yes ] ; then + echo "Test 8: DFA matching with UTF-8" + $valgrind ./pcretest -q -dfa $testdata/testinput8 testtry + if [ $? = 0 ] ; then + $cf $testdata/testoutput8 testtry + if [ $? != 0 ] ; then exit 1; fi + else exit 1 + fi + echo "OK" +fi + +if [ $do9 = yes ] ; then + echo "Test 9: DFA matching with Unicode properties" + $valgrind ./pcretest -q -dfa $testdata/testinput9 testtry + if [ $? = 0 ] ; then + $cf $testdata/testoutput9 testtry + if [ $? != 0 ] ; then exit 1; fi + else exit 1 + fi + echo "OK" +fi + +# Test of internal offsets and code sizes. This test is run only when there +# is Unicode property support and the link size is 2. The actual tests are +# mostly the same as in some of the above, but in this test we inspect some +# offsets and sizes that require a known link size. This is a doublecheck for +# the maintainer, just in case something changes unexpectely. + +if [ $do10 = yes ] ; then + echo "Test 10: Internal offsets and code size tests" + $valgrind ./pcretest -q $testdata/testinput10 testtry + if [ $? = 0 ] ; then + $cf $testdata/testoutput10 testtry + if [ $? != 0 ] ; then exit 1; fi + else exit 1 + fi + echo "OK" +fi + +# End ============================================================ --- pcre/libpcre.pc.in de06c34023f57c74ddf5fc9789b94e9d24356d2b +++ pcre/libpcre.pc.in de06c34023f57c74ddf5fc9789b94e9d24356d2b @@ -0,0 +1,12 @@ +# Package Information for pkg-config + address@hidden@ address@hidden@ address@hidden@ address@hidden@ + +Name: libpcre +Description: PCRE - Perl compatible regular expressions C library +Version: @PACKAGE_VERSION@ +Libs: -L${libdir} -lpcre +Cflags: -I${includedir} ============================================================ --- pcre/pcre-config.in b7e2758681ecb746ecca102f8890cbdcd5fbf0a0 +++ pcre/pcre-config.in b7e2758681ecb746ecca102f8890cbdcd5fbf0a0 @@ -0,0 +1,69 @@ +#!/bin/sh + address@hidden@ address@hidden@ +exec_prefix_set=no + +usage="\ +Usage: pcre-config [--prefix] [--exec-prefix] [--version] [--libs] [--libs-posix] [--cflags] [--cflags-posix]" + +if test $# -eq 0; then + echo "${usage}" 1>&2 + exit 1 +fi + +libR= +case `uname -s` in + *SunOS*) + libR=" address@hidden@" + ;; + *BSD*) + libR=" -Wl,address@hidden@" + ;; +esac + +while test $# -gt 0; do + case "$1" in + -*=*) optarg=`echo "$1" | sed 's/[-_a-zA-Z0-9]*=//'` ;; + *) optarg= ;; + esac + + case $1 in + --prefix=*) + prefix=$optarg + if test $exec_prefix_set = no ; then + exec_prefix=$optarg + fi + ;; + --prefix) + echo $prefix + ;; + --exec-prefix=*) + exec_prefix=$optarg + exec_prefix_set=yes + ;; + --exec-prefix) + echo $exec_prefix + ;; + --version) + echo @PACKAGE_VERSION@ + ;; + --cflags | --cflags-posix) + if test @includedir@ != /usr/include ; then + address@hidden@ + fi + echo $includes + ;; + --libs-posix) + echo address@hidden@$libR -lpcreposix -lpcre + ;; + --libs) + echo address@hidden@$libR -lpcre + ;; + *) + echo "${usage}" 1>&2 + exit 1 + ;; + esac + shift +done ============================================================ --- pcre/pcre.h.in 2148860d34970adc8d64287f983388b9a9a3b90d +++ pcre/pcre.h.in 2148860d34970adc8d64287f983388b9a9a3b90d @@ -0,0 +1,303 @@ +/************************************************* +* Perl-Compatible Regular Expressions * +*************************************************/ + +/* This is the public header file for the PCRE library, to be #included by +applications that call the PCRE functions. + + Copyright (c) 1997-2008 University of Cambridge + +----------------------------------------------------------------------------- +Redistribution and use in source and binary forms, with or without +modification, are permitted provided that the following conditions are met: + + * Redistributions of source code must retain the above copyright notice, + this list of conditions and the following disclaimer. + + * Redistributions in binary form must reproduce the above copyright + notice, this list of conditions and the following disclaimer in the + documentation and/or other materials provided with the distribution. + + * Neither the name of the University of Cambridge nor the names of its + contributors may be used to endorse or promote products derived from + this software without specific prior written permission. + +THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" +AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE +IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE +ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE +LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR +CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF +SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS +INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN +CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) +ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE +POSSIBILITY OF SUCH DAMAGE. +----------------------------------------------------------------------------- +*/ + +#ifndef _PCRE_H +#define _PCRE_H + +/* The current PCRE version information. */ + +#define PCRE_MAJOR @PCRE_MAJOR@ +#define PCRE_MINOR @PCRE_MINOR@ +#define PCRE_PRERELEASE @PCRE_PRERELEASE@ +#define PCRE_DATE @PCRE_DATE@ + +/* When an application links to a PCRE DLL in Windows, the symbols that are +imported have to be identified as such. When building PCRE, the appropriate +export setting is defined in pcre_internal.h, which includes this file. So we +don't change existing definitions of PCRE_EXP_DECL and PCRECPP_EXP_DECL. */ + +#if defined(_WIN32) && !defined(PCRE_STATIC) +# ifndef PCRE_EXP_DECL +# define PCRE_EXP_DECL extern __declspec(dllimport) +# endif +# ifdef __cplusplus +# ifndef PCRECPP_EXP_DECL +# define PCRECPP_EXP_DECL extern __declspec(dllimport) +# endif +# ifndef PCRECPP_EXP_DEFN +# define PCRECPP_EXP_DEFN __declspec(dllimport) +# endif +# endif +#endif + +/* By default, we use the standard "extern" declarations. */ + +#ifndef PCRE_EXP_DECL +# ifdef __cplusplus +# define PCRE_EXP_DECL extern "C" +# else +# define PCRE_EXP_DECL extern +# endif +#endif + +#ifdef __cplusplus +# ifndef PCRECPP_EXP_DECL +# define PCRECPP_EXP_DECL extern +# endif +# ifndef PCRECPP_EXP_DEFN +# define PCRECPP_EXP_DEFN +# endif +#endif + +/* Have to include stdlib.h in order to ensure that size_t is defined; +it is needed here for malloc. */ + +#include + +/* Allow for C++ users */ + +#ifdef __cplusplus +extern "C" { +#endif + +/* Options */ + +#define PCRE_CASELESS 0x00000001 +#define PCRE_MULTILINE 0x00000002 +#define PCRE_DOTALL 0x00000004 +#define PCRE_EXTENDED 0x00000008 +#define PCRE_ANCHORED 0x00000010 +#define PCRE_DOLLAR_ENDONLY 0x00000020 +#define PCRE_EXTRA 0x00000040 +#define PCRE_NOTBOL 0x00000080 +#define PCRE_NOTEOL 0x00000100 +#define PCRE_UNGREEDY 0x00000200 +#define PCRE_NOTEMPTY 0x00000400 +#define PCRE_UTF8 0x00000800 +#define PCRE_NO_AUTO_CAPTURE 0x00001000 +#define PCRE_NO_UTF8_CHECK 0x00002000 +#define PCRE_AUTO_CALLOUT 0x00004000 +#define PCRE_PARTIAL 0x00008000 +#define PCRE_DFA_SHORTEST 0x00010000 +#define PCRE_DFA_RESTART 0x00020000 +#define PCRE_FIRSTLINE 0x00040000 +#define PCRE_DUPNAMES 0x00080000 +#define PCRE_NEWLINE_CR 0x00100000 +#define PCRE_NEWLINE_LF 0x00200000 +#define PCRE_NEWLINE_CRLF 0x00300000 +#define PCRE_NEWLINE_ANY 0x00400000 +#define PCRE_NEWLINE_ANYCRLF 0x00500000 +#define PCRE_BSR_ANYCRLF 0x00800000 +#define PCRE_BSR_UNICODE 0x01000000 + +/* Exec-time and get/set-time error codes */ + +#define PCRE_ERROR_NOMATCH (-1) +#define PCRE_ERROR_NULL (-2) +#define PCRE_ERROR_BADOPTION (-3) +#define PCRE_ERROR_BADMAGIC (-4) +#define PCRE_ERROR_UNKNOWN_OPCODE (-5) +#define PCRE_ERROR_UNKNOWN_NODE (-5) /* For backward compatibility */ +#define PCRE_ERROR_NOMEMORY (-6) +#define PCRE_ERROR_NOSUBSTRING (-7) +#define PCRE_ERROR_MATCHLIMIT (-8) +#define PCRE_ERROR_CALLOUT (-9) /* Never used by PCRE itself */ +#define PCRE_ERROR_BADUTF8 (-10) +#define PCRE_ERROR_BADUTF8_OFFSET (-11) +#define PCRE_ERROR_PARTIAL (-12) +#define PCRE_ERROR_BADPARTIAL (-13) +#define PCRE_ERROR_INTERNAL (-14) +#define PCRE_ERROR_BADCOUNT (-15) +#define PCRE_ERROR_DFA_UITEM (-16) +#define PCRE_ERROR_DFA_UCOND (-17) +#define PCRE_ERROR_DFA_UMLIMIT (-18) +#define PCRE_ERROR_DFA_WSSIZE (-19) +#define PCRE_ERROR_DFA_RECURSE (-20) +#define PCRE_ERROR_RECURSIONLIMIT (-21) +#define PCRE_ERROR_NULLWSLIMIT (-22) /* No longer actually used */ +#define PCRE_ERROR_BADNEWLINE (-23) + +/* Request types for pcre_fullinfo() */ + +#define PCRE_INFO_OPTIONS 0 +#define PCRE_INFO_SIZE 1 +#define PCRE_INFO_CAPTURECOUNT 2 +#define PCRE_INFO_BACKREFMAX 3 +#define PCRE_INFO_FIRSTBYTE 4 +#define PCRE_INFO_FIRSTCHAR 4 /* For backwards compatibility */ +#define PCRE_INFO_FIRSTTABLE 5 +#define PCRE_INFO_LASTLITERAL 6 +#define PCRE_INFO_NAMEENTRYSIZE 7 +#define PCRE_INFO_NAMECOUNT 8 +#define PCRE_INFO_NAMETABLE 9 +#define PCRE_INFO_STUDYSIZE 10 +#define PCRE_INFO_DEFAULT_TABLES 11 +#define PCRE_INFO_OKPARTIAL 12 +#define PCRE_INFO_JCHANGED 13 +#define PCRE_INFO_HASCRORLF 14 + +/* Request types for pcre_config(). Do not re-arrange, in order to remain +compatible. */ + +#define PCRE_CONFIG_UTF8 0 +#define PCRE_CONFIG_NEWLINE 1 +#define PCRE_CONFIG_LINK_SIZE 2 +#define PCRE_CONFIG_POSIX_MALLOC_THRESHOLD 3 +#define PCRE_CONFIG_MATCH_LIMIT 4 +#define PCRE_CONFIG_STACKRECURSE 5 +#define PCRE_CONFIG_UNICODE_PROPERTIES 6 +#define PCRE_CONFIG_MATCH_LIMIT_RECURSION 7 +#define PCRE_CONFIG_BSR 8 + +/* Bit flags for the pcre_extra structure. Do not re-arrange or redefine +these bits, just add new ones on the end, in order to remain compatible. */ + +#define PCRE_EXTRA_STUDY_DATA 0x0001 +#define PCRE_EXTRA_MATCH_LIMIT 0x0002 +#define PCRE_EXTRA_CALLOUT_DATA 0x0004 +#define PCRE_EXTRA_TABLES 0x0008 +#define PCRE_EXTRA_MATCH_LIMIT_RECURSION 0x0010 + +/* Types */ + +struct real_pcre; /* declaration; the definition is private */ +typedef struct real_pcre pcre; + +/* When PCRE is compiled as a C++ library, the subject pointer type can be +replaced with a custom type. For conventional use, the public interface is a +const char *. */ + +#ifndef PCRE_SPTR +#define PCRE_SPTR const char * +#endif + +/* The structure for passing additional data to pcre_exec(). This is defined in +such as way as to be extensible. Always add new fields at the end, in order to +remain compatible. */ + +typedef struct pcre_extra { + unsigned long int flags; /* Bits for which fields are set */ + void *study_data; /* Opaque data from pcre_study() */ + unsigned long int match_limit; /* Maximum number of calls to match() */ + void *callout_data; /* Data passed back in callouts */ + const unsigned char *tables; /* Pointer to character tables */ + unsigned long int match_limit_recursion; /* Max recursive calls to match() */ +} pcre_extra; + +/* The structure for passing out data via the pcre_callout_function. We use a +structure so that new fields can be added on the end in future versions, +without changing the API of the function, thereby allowing old clients to work +without modification. */ + +typedef struct pcre_callout_block { + int version; /* Identifies version of block */ + /* ------------------------ Version 0 ------------------------------- */ + int callout_number; /* Number compiled into pattern */ + int *offset_vector; /* The offset vector */ + PCRE_SPTR subject; /* The subject being matched */ + int subject_length; /* The length of the subject */ + int start_match; /* Offset to start of this match attempt */ + int current_position; /* Where we currently are in the subject */ + int capture_top; /* Max current capture */ + int capture_last; /* Most recently closed capture */ + void *callout_data; /* Data passed in with the call */ + /* ------------------- Added for Version 1 -------------------------- */ + int pattern_position; /* Offset to next item in the pattern */ + int next_item_length; /* Length of next item in the pattern */ + /* ------------------------------------------------------------------ */ +} pcre_callout_block; + +/* Indirection for store get and free functions. These can be set to +alternative malloc/free functions if required. Special ones are used in the +non-recursive case for "frames". There is also an optional callout function +that is triggered by the (?) regex item. For Virtual Pascal, these definitions +have to take another form. */ + +#ifndef VPCOMPAT +PCRE_EXP_DECL void *(*pcre_malloc)(size_t); +PCRE_EXP_DECL void (*pcre_free)(void *); +PCRE_EXP_DECL void *(*pcre_stack_malloc)(size_t); +PCRE_EXP_DECL void (*pcre_stack_free)(void *); +PCRE_EXP_DECL int (*pcre_callout)(pcre_callout_block *); +#else /* VPCOMPAT */ +PCRE_EXP_DECL void *pcre_malloc(size_t); +PCRE_EXP_DECL void pcre_free(void *); +PCRE_EXP_DECL void *pcre_stack_malloc(size_t); +PCRE_EXP_DECL void pcre_stack_free(void *); +PCRE_EXP_DECL int pcre_callout(pcre_callout_block *); +#endif /* VPCOMPAT */ + +/* Exported PCRE functions */ + +PCRE_EXP_DECL pcre *pcre_compile(const char *, int, const char **, int *, + const unsigned char *); +PCRE_EXP_DECL pcre *pcre_compile2(const char *, int, int *, const char **, + int *, const unsigned char *); +PCRE_EXP_DECL int pcre_config(int, void *); +PCRE_EXP_DECL int pcre_copy_named_substring(const pcre *, const char *, + int *, int, const char *, char *, int); +PCRE_EXP_DECL int pcre_copy_substring(const char *, int *, int, int, char *, + int); +PCRE_EXP_DECL int pcre_dfa_exec(const pcre *, const pcre_extra *, + const char *, int, int, int, int *, int , int *, int); +PCRE_EXP_DECL int pcre_exec(const pcre *, const pcre_extra *, PCRE_SPTR, + int, int, int, int *, int); +PCRE_EXP_DECL void pcre_free_substring(const char *); +PCRE_EXP_DECL void pcre_free_substring_list(const char **); +PCRE_EXP_DECL int pcre_fullinfo(const pcre *, const pcre_extra *, int, + void *); +PCRE_EXP_DECL int pcre_get_named_substring(const pcre *, const char *, + int *, int, const char *, const char **); +PCRE_EXP_DECL int pcre_get_stringnumber(const pcre *, const char *); +PCRE_EXP_DECL int pcre_get_stringtable_entries(const pcre *, const char *, + char **, char **); +PCRE_EXP_DECL int pcre_get_substring(const char *, int *, int, int, + const char **); +PCRE_EXP_DECL int pcre_get_substring_list(const char *, int *, int, + const char ***); +PCRE_EXP_DECL int pcre_info(const pcre *, int *, int *); +PCRE_EXP_DECL const unsigned char *pcre_maketables(void); +PCRE_EXP_DECL int pcre_refcount(pcre *, int); +PCRE_EXP_DECL pcre_extra *pcre_study(const pcre *, int, const char **); +PCRE_EXP_DECL const char *pcre_version(void); + +#ifdef __cplusplus +} /* extern "C" */ +#endif + +#endif /* End of pcre.h */ ============================================================ --- pcre/pcre_printint.src fc4f01edd2cece38438822fbd7c7e44f3e60a3ff +++ pcre/pcre_printint.src fc4f01edd2cece38438822fbd7c7e44f3e60a3ff @@ -0,0 +1,512 @@ +/************************************************* +* 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) 1997-2008 University of Cambridge + +----------------------------------------------------------------------------- +Redistribution and use in source and binary forms, with or without +modification, are permitted provided that the following conditions are met: + + * Redistributions of source code must retain the above copyright notice, + this list of conditions and the following disclaimer. + + * Redistributions in binary form must reproduce the above copyright + notice, this list of conditions and the following disclaimer in the + documentation and/or other materials provided with the distribution. + + * Neither the name of the University of Cambridge nor the names of its + contributors may be used to endorse or promote products derived from + this software without specific prior written permission. + +THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" +AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE +IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE +ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE +LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR +CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF +SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS +INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN +CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) +ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE +POSSIBILITY OF SUCH DAMAGE. +----------------------------------------------------------------------------- +*/ + + +/* This module contains a PCRE private debugging function for printing out the +internal form of a compiled regular expression, along with some supporting +local functions. This source file is used in two places: + +(1) It is #included by pcre_compile.c when it is compiled in debugging mode +(DEBUG defined in pcre_internal.h). It is not included in production compiles. + +(2) It is always #included by pcretest.c, which can be asked to print out a +compiled regex for debugging purposes. */ + + +/* Macro that decides whether a character should be output as a literal or in +hexadecimal. We don't use isprint() because that can vary from system to system +(even without the use of locales) and we want the output always to be the same, +for testing purposes. This macro is used in pcretest as well as in this file. */ + +#define PRINTABLE(c) ((c) >= 32 && (c) < 127) + +/* The table of operator names. */ + +static const char *OP_names[] = { OP_NAME_LIST }; + + + +/************************************************* +* Print single- or multi-byte character * +*************************************************/ + +static int +print_char(FILE *f, uschar *ptr, BOOL utf8) +{ +int c = *ptr; + +#ifndef SUPPORT_UTF8 +utf8 = utf8; /* Avoid compiler warning */ +if (PRINTABLE(c)) fprintf(f, "%c", c); else fprintf(f, "\\x%02x", c); +return 0; + +#else +if (!utf8 || (c & 0xc0) != 0xc0) + { + if (PRINTABLE(c)) fprintf(f, "%c", c); else fprintf(f, "\\x%02x", c); + return 0; + } +else + { + int i; + int a = _pcre_utf8_table4[c & 0x3f]; /* Number of additional bytes */ + int s = 6*a; + c = (c & _pcre_utf8_table3[a]) << s; + for (i = 1; i <= a; i++) + { + /* This is a check for malformed UTF-8; it should only occur if the sanity + check has been turned off. Rather than swallow random bytes, just stop if + we hit a bad one. Print it with \X instead of \x as an indication. */ + + if ((ptr[i] & 0xc0) != 0x80) + { + fprintf(f, "\\X{%x}", c); + return i - 1; + } + + /* The byte is OK */ + + s -= 6; + c |= (ptr[i] & 0x3f) << s; + } + if (c < 128) fprintf(f, "\\x%02x", c); else fprintf(f, "\\x{%x}", c); + return a; + } +#endif +} + + + +/************************************************* +* Find Unicode property name * +*************************************************/ + +static const char * +get_ucpname(int ptype, int pvalue) +{ +#ifdef SUPPORT_UCP +int i; +for (i = _pcre_utt_size - 1; i >= 0; i--) + { + if (ptype == _pcre_utt[i].type && pvalue == _pcre_utt[i].value) break; + } +return (i >= 0)? _pcre_utt_names + _pcre_utt[i].name_offset : "??"; +#else +/* It gets harder and harder to shut off unwanted compiler warnings. */ +ptype = ptype * pvalue; +return (ptype == pvalue)? "??" : "??"; +#endif +} + + + +/************************************************* +* Print compiled regex * +*************************************************/ + +/* Make this function work for a regex with integers either byte order. +However, we assume that what we are passed is a compiled regex. The +print_lengths flag controls whether offsets and lengths of items are printed. +They can be turned off from pcretest so that automatic tests on bytecode can be +written that do not depend on the value of LINK_SIZE. */ + +static void +pcre_printint(pcre *external_re, FILE *f, BOOL print_lengths) +{ +real_pcre *re = (real_pcre *)external_re; +uschar *codestart, *code; +BOOL utf8; + +unsigned int options = re->options; +int offset = re->name_table_offset; +int count = re->name_count; +int size = re->name_entry_size; + +if (re->magic_number != MAGIC_NUMBER) + { + offset = ((offset << 8) & 0xff00) | ((offset >> 8) & 0xff); + count = ((count << 8) & 0xff00) | ((count >> 8) & 0xff); + size = ((size << 8) & 0xff00) | ((size >> 8) & 0xff); + options = ((options << 24) & 0xff000000) | + ((options << 8) & 0x00ff0000) | + ((options >> 8) & 0x0000ff00) | + ((options >> 24) & 0x000000ff); + } + +code = codestart = (uschar *)re + offset + count * size; +utf8 = (options & PCRE_UTF8) != 0; + +for(;;) + { + uschar *ccode; + int c; + int extra = 0; + + if (print_lengths) + fprintf(f, "%3d ", (int)(code - codestart)); + else + fprintf(f, " "); + + switch(*code) + { + case OP_END: + fprintf(f, " %s\n", OP_names[*code]); + fprintf(f, "------------------------------------------------------------------\n"); + return; + + case OP_OPT: + fprintf(f, " %.2x %s", code[1], OP_names[*code]); + break; + + case OP_CHAR: + fprintf(f, " "); + do + { + code++; + code += 1 + print_char(f, code, utf8); + } + while (*code == OP_CHAR); + fprintf(f, "\n"); + continue; + + case OP_CHARNC: + fprintf(f, " NC "); + do + { + code++; + code += 1 + print_char(f, code, utf8); + } + while (*code == OP_CHARNC); + fprintf(f, "\n"); + continue; + + case OP_CBRA: + case OP_SCBRA: + if (print_lengths) fprintf(f, "%3d ", GET(code, 1)); + else fprintf(f, " "); + fprintf(f, "%s %d", OP_names[*code], GET2(code, 1+LINK_SIZE)); + break; + + case OP_BRA: + case OP_SBRA: + case OP_KETRMAX: + case OP_KETRMIN: + case OP_ALT: + case OP_KET: + case OP_ASSERT: + case OP_ASSERT_NOT: + case OP_ASSERTBACK: + case OP_ASSERTBACK_NOT: + case OP_ONCE: + case OP_COND: + case OP_SCOND: + case OP_REVERSE: + if (print_lengths) fprintf(f, "%3d ", GET(code, 1)); + else fprintf(f, " "); + fprintf(f, "%s", OP_names[*code]); + break; + + case OP_CREF: + fprintf(f, "%3d %s", GET2(code,1), OP_names[*code]); + break; + + case OP_RREF: + c = GET2(code, 1); + if (c == RREF_ANY) + fprintf(f, " Cond recurse any"); + else + fprintf(f, " Cond recurse %d", c); + break; + + case OP_DEF: + fprintf(f, " Cond def"); + break; + + case OP_STAR: + case OP_MINSTAR: + case OP_POSSTAR: + case OP_PLUS: + case OP_MINPLUS: + case OP_POSPLUS: + case OP_QUERY: + case OP_MINQUERY: + case OP_POSQUERY: + case OP_TYPESTAR: + case OP_TYPEMINSTAR: + case OP_TYPEPOSSTAR: + case OP_TYPEPLUS: + case OP_TYPEMINPLUS: + case OP_TYPEPOSPLUS: + case OP_TYPEQUERY: + case OP_TYPEMINQUERY: + case OP_TYPEPOSQUERY: + fprintf(f, " "); + if (*code >= OP_TYPESTAR) + { + fprintf(f, "%s", OP_names[code[1]]); + if (code[1] == OP_PROP || code[1] == OP_NOTPROP) + { + fprintf(f, " %s ", get_ucpname(code[2], code[3])); + extra = 2; + } + } + else extra = print_char(f, code+1, utf8); + fprintf(f, "%s", OP_names[*code]); + break; + + case OP_EXACT: + case OP_UPTO: + case OP_MINUPTO: + case OP_POSUPTO: + fprintf(f, " "); + extra = print_char(f, code+3, utf8); + fprintf(f, "{"); + if (*code != OP_EXACT) fprintf(f, "0,"); + fprintf(f, "%d}", GET2(code,1)); + if (*code == OP_MINUPTO) fprintf(f, "?"); + else if (*code == OP_POSUPTO) fprintf(f, "+"); + break; + + case OP_TYPEEXACT: + case OP_TYPEUPTO: + case OP_TYPEMINUPTO: + case OP_TYPEPOSUPTO: + fprintf(f, " %s", OP_names[code[3]]); + if (code[3] == OP_PROP || code[3] == OP_NOTPROP) + { + fprintf(f, " %s ", get_ucpname(code[4], code[5])); + extra = 2; + } + fprintf(f, "{"); + if (*code != OP_TYPEEXACT) fprintf(f, "0,"); + fprintf(f, "%d}", GET2(code,1)); + if (*code == OP_TYPEMINUPTO) fprintf(f, "?"); + else if (*code == OP_TYPEPOSUPTO) fprintf(f, "+"); + break; + + case OP_NOT: + c = code[1]; + if (PRINTABLE(c)) fprintf(f, " [^%c]", c); + else fprintf(f, " [^\\x%02x]", c); + break; + + case OP_NOTSTAR: + case OP_NOTMINSTAR: + case OP_NOTPOSSTAR: + case OP_NOTPLUS: + case OP_NOTMINPLUS: + case OP_NOTPOSPLUS: + case OP_NOTQUERY: + case OP_NOTMINQUERY: + case OP_NOTPOSQUERY: + c = code[1]; + if (PRINTABLE(c)) fprintf(f, " [^%c]", c); + else fprintf(f, " [^\\x%02x]", c); + fprintf(f, "%s", OP_names[*code]); + break; + + case OP_NOTEXACT: + case OP_NOTUPTO: + case OP_NOTMINUPTO: + case OP_NOTPOSUPTO: + c = code[3]; + if (PRINTABLE(c)) fprintf(f, " [^%c]{", c); + else fprintf(f, " [^\\x%02x]{", c); + if (*code != OP_NOTEXACT) fprintf(f, "0,"); + fprintf(f, "%d}", GET2(code,1)); + if (*code == OP_NOTMINUPTO) fprintf(f, "?"); + else if (*code == OP_NOTPOSUPTO) fprintf(f, "+"); + break; + + case OP_RECURSE: + if (print_lengths) fprintf(f, "%3d ", GET(code, 1)); + else fprintf(f, " "); + fprintf(f, "%s", OP_names[*code]); + break; + + case OP_REF: + fprintf(f, " \\%d", GET2(code,1)); + ccode = code + _pcre_OP_lengths[*code]; + goto CLASS_REF_REPEAT; + + case OP_CALLOUT: + fprintf(f, " %s %d %d %d", OP_names[*code], code[1], GET(code,2), + GET(code, 2 + LINK_SIZE)); + break; + + case OP_PROP: + case OP_NOTPROP: + fprintf(f, " %s %s", OP_names[*code], get_ucpname(code[1], code[2])); + break; + + /* OP_XCLASS can only occur in UTF-8 mode. However, there's no harm in + having this code always here, and it makes it less messy without all those + #ifdefs. */ + + case OP_CLASS: + case OP_NCLASS: + case OP_XCLASS: + { + int i, min, max; + BOOL printmap; + + fprintf(f, " ["); + + if (*code == OP_XCLASS) + { + extra = GET(code, 1); + ccode = code + LINK_SIZE + 1; + printmap = (*ccode & XCL_MAP) != 0; + if ((*ccode++ & XCL_NOT) != 0) fprintf(f, "^"); + } + else + { + printmap = TRUE; + ccode = code + 1; + } + + /* Print a bit map */ + + if (printmap) + { + for (i = 0; i < 256; i++) + { + if ((ccode[i/8] & (1 << (i&7))) != 0) + { + int j; + for (j = i+1; j < 256; j++) + if ((ccode[j/8] & (1 << (j&7))) == 0) break; + if (i == '-' || i == ']') fprintf(f, "\\"); + if (PRINTABLE(i)) fprintf(f, "%c", i); + else fprintf(f, "\\x%02x", i); + if (--j > i) + { + if (j != i + 1) fprintf(f, "-"); + if (j == '-' || j == ']') fprintf(f, "\\"); + if (PRINTABLE(j)) fprintf(f, "%c", j); + else fprintf(f, "\\x%02x", j); + } + i = j; + } + } + ccode += 32; + } + + /* For an XCLASS there is always some additional data */ + + if (*code == OP_XCLASS) + { + int ch; + while ((ch = *ccode++) != XCL_END) + { + if (ch == XCL_PROP) + { + int ptype = *ccode++; + int pvalue = *ccode++; + fprintf(f, "\\p{%s}", get_ucpname(ptype, pvalue)); + } + else if (ch == XCL_NOTPROP) + { + int ptype = *ccode++; + int pvalue = *ccode++; + fprintf(f, "\\P{%s}", get_ucpname(ptype, pvalue)); + } + else + { + ccode += 1 + print_char(f, ccode, TRUE); + if (ch == XCL_RANGE) + { + fprintf(f, "-"); + ccode += 1 + print_char(f, ccode, TRUE); + } + } + } + } + + /* Indicate a non-UTF8 class which was created by negation */ + + fprintf(f, "]%s", (*code == OP_NCLASS)? " (neg)" : ""); + + /* Handle repeats after a class or a back reference */ + + CLASS_REF_REPEAT: + switch(*ccode) + { + case OP_CRSTAR: + case OP_CRMINSTAR: + case OP_CRPLUS: + case OP_CRMINPLUS: + case OP_CRQUERY: + case OP_CRMINQUERY: + fprintf(f, "%s", OP_names[*ccode]); + extra += _pcre_OP_lengths[*ccode]; + break; + + case OP_CRRANGE: + case OP_CRMINRANGE: + min = GET2(ccode,1); + max = GET2(ccode,3); + if (max == 0) fprintf(f, "{%d,}", min); + else fprintf(f, "{%d,%d}", min, max); + if (*ccode == OP_CRMINRANGE) fprintf(f, "?"); + extra += _pcre_OP_lengths[*ccode]; + break; + + /* Do nothing if it's not a repeat; this code stops picky compilers + warning about the lack of a default code path. */ + + default: + break; + } + } + break; + + /* Anything else is just an item with no data*/ + + default: + fprintf(f, " %s", OP_names[*code]); + break; + } + + code += _pcre_OP_lengths[*code] + extra; + fprintf(f, "\n"); + } +} + +/* End of pcre_printint.src */ ============================================================ --- pcre/pcregrep.c 0b275ab7db5158f115c94f5eab55b544cbc48dfc +++ pcre/pcregrep.c 0b275ab7db5158f115c94f5eab55b544cbc48dfc @@ -0,0 +1,2333 @@ +/************************************************* +* pcregrep program * +*************************************************/ + +/* This is a grep program that uses the PCRE regular expression library to do +its pattern matching. On a Unix or Win32 system it can recurse into +directories. + + Copyright (c) 1997-2008 University of Cambridge + +----------------------------------------------------------------------------- +Redistribution and use in source and binary forms, with or without +modification, are permitted provided that the following conditions are met: + + * Redistributions of source code must retain the above copyright notice, + this list of conditions and the following disclaimer. + + * Redistributions in binary form must reproduce the above copyright + notice, this list of conditions and the following disclaimer in the + documentation and/or other materials provided with the distribution. + + * Neither the name of the University of Cambridge nor the names of its + contributors may be used to endorse or promote products derived from + this software without specific prior written permission. + +THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" +AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE +IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE +ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE +LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR +CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF +SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS +INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN +CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) +ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE +POSSIBILITY OF SUCH DAMAGE. +----------------------------------------------------------------------------- +*/ + +#ifdef HAVE_CONFIG_H +#include "config.h" +#endif + +#include +#include +#include +#include +#include +#include + +#include +#include + +#ifdef HAVE_UNISTD_H +#include +#endif + +#ifdef SUPPORT_LIBZ +#include +#endif + +#ifdef SUPPORT_LIBBZ2 +#include +#endif + +#include "pcre.h" + +#define FALSE 0 +#define TRUE 1 + +typedef int BOOL; + +#define MAX_PATTERN_COUNT 100 + +#if BUFSIZ > 8192 +#define MBUFTHIRD BUFSIZ +#else +#define MBUFTHIRD 8192 +#endif + +/* Values for the "filenames" variable, which specifies options for file name +output. The order is important; it is assumed that a file name is wanted for +all values greater than FN_DEFAULT. */ + +enum { FN_NONE, FN_DEFAULT, FN_ONLY, FN_NOMATCH_ONLY, FN_FORCE }; + +/* File reading styles */ + +enum { FR_PLAIN, FR_LIBZ, FR_LIBBZ2 }; + +/* Actions for the -d and -D options */ + +enum { dee_READ, dee_SKIP, dee_RECURSE }; +enum { DEE_READ, DEE_SKIP }; + +/* Actions for special processing options (flag bits) */ + +#define PO_WORD_MATCH 0x0001 +#define PO_LINE_MATCH 0x0002 +#define PO_FIXED_STRINGS 0x0004 + +/* Line ending types */ + +enum { EL_LF, EL_CR, EL_CRLF, EL_ANY, EL_ANYCRLF }; + + + +/************************************************* +* Global variables * +*************************************************/ + +/* Jeffrey Friedl has some debugging requirements that are not part of the +regular code. */ + +#ifdef JFRIEDL_DEBUG +static int S_arg = -1; +static unsigned int jfriedl_XR = 0; /* repeat regex attempt this many times */ +static unsigned int jfriedl_XT = 0; /* replicate text this many times */ +static const char *jfriedl_prefix = ""; +static const char *jfriedl_postfix = ""; +#endif + +static int endlinetype; + +static char *colour_string = (char *)"1;31"; +static char *colour_option = NULL; +static char *dee_option = NULL; +static char *DEE_option = NULL; +static char *newline = NULL; +static char *pattern_filename = NULL; +static char *stdin_name = (char *)"(standard input)"; +static char *locale = NULL; + +static const unsigned char *pcretables = NULL; + +static int pattern_count = 0; +static pcre **pattern_list = NULL; +static pcre_extra **hints_list = NULL; + +static char *include_pattern = NULL; +static char *exclude_pattern = NULL; + +static pcre *include_compiled = NULL; +static pcre *exclude_compiled = NULL; + +static int after_context = 0; +static int before_context = 0; +static int both_context = 0; +static int dee_action = dee_READ; +static int DEE_action = DEE_READ; +static int error_count = 0; +static int filenames = FN_DEFAULT; +static int process_options = 0; + +static BOOL count_only = FALSE; +static BOOL do_colour = FALSE; +static BOOL file_offsets = FALSE; +static BOOL hyphenpending = FALSE; +static BOOL invert = FALSE; +static BOOL line_offsets = FALSE; +static BOOL multiline = FALSE; +static BOOL number = FALSE; +static BOOL only_matching = FALSE; +static BOOL quiet = FALSE; +static BOOL silent = FALSE; +static BOOL utf8 = FALSE; + +/* Structure for options and list of them */ + +enum { OP_NODATA, OP_STRING, OP_OP_STRING, OP_NUMBER, OP_OP_NUMBER, + OP_PATLIST }; + +typedef struct option_item { + int type; + int one_char; + void *dataptr; + const char *long_name; + const char *help_text; +} option_item; + +/* Options without a single-letter equivalent get a negative value. This can be +used to identify them. */ + +#define N_COLOUR (-1) +#define N_EXCLUDE (-2) +#define N_HELP (-3) +#define N_INCLUDE (-4) +#define N_LABEL (-5) +#define N_LOCALE (-6) +#define N_NULL (-7) +#define N_LOFFSETS (-8) +#define N_FOFFSETS (-9) + +static option_item optionlist[] = { + { OP_NODATA, N_NULL, NULL, "", " terminate options" }, + { OP_NODATA, N_HELP, NULL, "help", "display this help and exit" }, + { OP_NUMBER, 'A', &after_context, "after-context=number", "set number of following context lines" }, + { OP_NUMBER, 'B', &before_context, "before-context=number", "set number of prior context lines" }, + { OP_OP_STRING, N_COLOUR, &colour_option, "color=option", "matched text color option" }, + { OP_NUMBER, 'C', &both_context, "context=number", "set number of context lines, before & after" }, + { OP_NODATA, 'c', NULL, "count", "print only a count of matching lines per FILE" }, + { OP_OP_STRING, N_COLOUR, &colour_option, "colour=option", "matched text colour option" }, + { OP_STRING, 'D', &DEE_option, "devices=action","how to handle devices, FIFOs, and sockets" }, + { OP_STRING, 'd', &dee_option, "directories=action", "how to handle directories" }, + { OP_PATLIST, 'e', NULL, "regex(p)", "specify pattern (may be used more than once)" }, + { OP_NODATA, 'F', NULL, "fixed_strings", "patterns are sets of newline-separated strings" }, + { OP_STRING, 'f', &pattern_filename, "file=path", "read patterns from file" }, + { OP_NODATA, N_FOFFSETS, NULL, "file-offsets", "output file offsets, not text" }, + { OP_NODATA, 'H', NULL, "with-filename", "force the prefixing filename on output" }, + { OP_NODATA, 'h', NULL, "no-filename", "suppress the prefixing filename on output" }, + { OP_NODATA, 'i', NULL, "ignore-case", "ignore case distinctions" }, + { OP_NODATA, 'l', NULL, "files-with-matches", "print only FILE names containing matches" }, + { OP_NODATA, 'L', NULL, "files-without-match","print only FILE names not containing matches" }, + { OP_STRING, N_LABEL, &stdin_name, "label=name", "set name for standard input" }, + { OP_NODATA, N_LOFFSETS, NULL, "line-offsets", "output line numbers and offsets, not text" }, + { OP_STRING, N_LOCALE, &locale, "locale=locale", "use the named locale" }, + { OP_NODATA, 'M', NULL, "multiline", "run in multiline mode" }, + { OP_STRING, 'N', &newline, "newline=type", "set newline type (CR, LF, CRLF, ANYCRLF or ANY)" }, + { OP_NODATA, 'n', NULL, "line-number", "print line number with output lines" }, + { OP_NODATA, 'o', NULL, "only-matching", "show only the part of the line that matched" }, + { OP_NODATA, 'q', NULL, "quiet", "suppress output, just set return code" }, + { OP_NODATA, 'r', NULL, "recursive", "recursively scan sub-directories" }, + { OP_STRING, N_EXCLUDE,&exclude_pattern, "exclude=pattern","exclude matching files when recursing" }, + { OP_STRING, N_INCLUDE,&include_pattern, "include=pattern","include matching files when recursing" }, +#ifdef JFRIEDL_DEBUG + { OP_OP_NUMBER, 'S', &S_arg, "jeffS", "replace matched (sub)string with X" }, +#endif + { OP_NODATA, 's', NULL, "no-messages", "suppress error messages" }, + { OP_NODATA, 'u', NULL, "utf-8", "use UTF-8 mode" }, + { OP_NODATA, 'V', NULL, "version", "print version information and exit" }, + { OP_NODATA, 'v', NULL, "invert-match", "select non-matching lines" }, + { OP_NODATA, 'w', NULL, "word-regex(p)", "force patterns to match only as words" }, + { OP_NODATA, 'x', NULL, "line-regex(p)", "force patterns to match only whole lines" }, + { OP_NODATA, 0, NULL, NULL, NULL } +}; + +/* Tables for prefixing and suffixing patterns, according to the -w, -x, and -F +options. These set the 1, 2, and 4 bits in process_options, respectively. Note +that the combination of -w and -x has the same effect as -x on its own, so we +can treat them as the same. */ + +static const char *prefix[] = { + "", "\\b", "^(?:", "^(?:", "\\Q", "\\b\\Q", "^(?:\\Q", "^(?:\\Q" }; + +static const char *suffix[] = { + "", "\\b", ")$", ")$", "\\E", "\\E\\b", "\\E)$", "\\E)$" }; + +/* UTF-8 tables - used only when the newline setting is "any". */ + +const int utf8_table3[] = { 0xff, 0x1f, 0x0f, 0x07, 0x03, 0x01}; + +const char utf8_table4[] = { + 1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1, + 1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1, + 2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2, + 3,3,3,3,3,3,3,3,4,4,4,4,5,5,5,5 }; + + + +/************************************************* +* OS-specific functions * +*************************************************/ + +/* These functions are defined so that they can be made system specific, +although at present the only ones are for Unix, Win32, and for "no support". */ + + +/************* Directory scanning in Unix ***********/ + +#if defined HAVE_SYS_STAT_H && defined HAVE_DIRENT_H && defined HAVE_SYS_TYPES_H +#include +#include +#include + +typedef DIR directory_type; + +static int +isdirectory(char *filename) +{ +struct stat statbuf; +if (stat(filename, &statbuf) < 0) + return 0; /* In the expectation that opening as a file will fail */ +return ((statbuf.st_mode & S_IFMT) == S_IFDIR)? '/' : 0; +} + +static directory_type * +opendirectory(char *filename) +{ +return opendir(filename); +} + +static char * +readdirectory(directory_type *dir) +{ +for (;;) + { + struct dirent *dent = readdir(dir); + if (dent == NULL) return NULL; + if (strcmp(dent->d_name, ".") != 0 && strcmp(dent->d_name, "..") != 0) + return dent->d_name; + } +/* Control never reaches here */ +} + +static void +closedirectory(directory_type *dir) +{ +closedir(dir); +} + + +/************* Test for regular file in Unix **********/ + +static int +isregfile(char *filename) +{ +struct stat statbuf; +if (stat(filename, &statbuf) < 0) + return 1; /* In the expectation that opening as a file will fail */ +return (statbuf.st_mode & S_IFMT) == S_IFREG; +} + + +/************* Test stdout for being a terminal in Unix **********/ + +static BOOL +is_stdout_tty(void) +{ +return isatty(fileno(stdout)); +} + + +/************* Directory scanning in Win32 ***********/ + +/* I (Philip Hazel) have no means of testing this code. It was contributed by +Lionel Fourquaux. David Burgess added a patch to define INVALID_FILE_ATTRIBUTES +when it did not exist. David Byron added a patch that moved the #include of + to before the INVALID_FILE_ATTRIBUTES definition rather than after. +*/ + +#elif HAVE_WINDOWS_H + +#ifndef STRICT +# define STRICT +#endif +#ifndef WIN32_LEAN_AND_MEAN +# define WIN32_LEAN_AND_MEAN +#endif + +#include + +#ifndef INVALID_FILE_ATTRIBUTES +#define INVALID_FILE_ATTRIBUTES 0xFFFFFFFF +#endif + +typedef struct directory_type +{ +HANDLE handle; +BOOL first; +WIN32_FIND_DATA data; +} directory_type; + +int +isdirectory(char *filename) +{ +DWORD attr = GetFileAttributes(filename); +if (attr == INVALID_FILE_ATTRIBUTES) + return 0; +return ((attr & FILE_ATTRIBUTE_DIRECTORY) != 0) ? '/' : 0; +} + +directory_type * +opendirectory(char *filename) +{ +size_t len; +char *pattern; +directory_type *dir; +DWORD err; +len = strlen(filename); +pattern = (char *) malloc(len + 3); +dir = (directory_type *) malloc(sizeof(*dir)); +if ((pattern == NULL) || (dir == NULL)) + { + fprintf(stderr, "pcregrep: malloc failed\n"); + exit(2); + } +memcpy(pattern, filename, len); +memcpy(&(pattern[len]), "\\*", 3); +dir->handle = FindFirstFile(pattern, &(dir->data)); +if (dir->handle != INVALID_HANDLE_VALUE) + { + free(pattern); + dir->first = TRUE; + return dir; + } +err = GetLastError(); +free(pattern); +free(dir); +errno = (err == ERROR_ACCESS_DENIED) ? EACCES : ENOENT; +return NULL; +} + +char * +readdirectory(directory_type *dir) +{ +for (;;) + { + if (!dir->first) + { + if (!FindNextFile(dir->handle, &(dir->data))) + return NULL; + } + else + { + dir->first = FALSE; + } + if (strcmp(dir->data.cFileName, ".") != 0 && strcmp(dir->data.cFileName, "..") != 0) + return dir->data.cFileName; + } +#ifndef _MSC_VER +return NULL; /* Keep compiler happy; never executed */ +#endif +} + +void +closedirectory(directory_type *dir) +{ +FindClose(dir->handle); +free(dir); +} + + +/************* Test for regular file in Win32 **********/ + +/* I don't know how to do this, or if it can be done; assume all paths are +regular if they are not directories. */ + +int isregfile(char *filename) +{ +return !isdirectory(filename); +} + + +/************* Test stdout for being a terminal in Win32 **********/ + +/* I don't know how to do this; assume never */ + +static BOOL +is_stdout_tty(void) +{ +return FALSE; +} + + +/************* Directory scanning when we can't do it ***********/ + +/* The type is void, and apart from isdirectory(), the functions do nothing. */ + +#else + +typedef void directory_type; + +int isdirectory(char *filename) { return 0; } +directory_type * opendirectory(char *filename) { return (directory_type*)0;} +char *readdirectory(directory_type *dir) { return (char*)0;} +void closedirectory(directory_type *dir) {} + + +/************* Test for regular when we can't do it **********/ + +/* Assume all files are regular. */ + +int isregfile(char *filename) { return 1; } + + +/************* Test stdout for being a terminal when we can't do it **********/ + +static BOOL +is_stdout_tty(void) +{ +return FALSE; +} + + +#endif + + + +#ifndef HAVE_STRERROR +/************************************************* +* Provide strerror() for non-ANSI libraries * +*************************************************/ + +/* Some old-fashioned systems still around (e.g. SunOS4) don't have strerror() +in their libraries, but can provide the same facility by this simple +alternative function. */ + +extern int sys_nerr; +extern char *sys_errlist[]; + +char * +strerror(int n) +{ +if (n < 0 || n >= sys_nerr) return "unknown error number"; +return sys_errlist[n]; +} +#endif /* HAVE_STRERROR */ + + + +/************************************************* +* Find end of line * +*************************************************/ + +/* The length of the endline sequence that is found is set via lenptr. This may +be zero at the very end of the file if there is no line-ending sequence there. + +Arguments: + p current position in line + endptr end of available data + lenptr where to put the length of the eol sequence + +Returns: pointer to the last byte of the line +*/ + +static char * +end_of_line(char *p, char *endptr, int *lenptr) +{ +switch(endlinetype) + { + default: /* Just in case */ + case EL_LF: + while (p < endptr && *p != '\n') p++; + if (p < endptr) + { + *lenptr = 1; + return p + 1; + } + *lenptr = 0; + return endptr; + + case EL_CR: + while (p < endptr && *p != '\r') p++; + if (p < endptr) + { + *lenptr = 1; + return p + 1; + } + *lenptr = 0; + return endptr; + + case EL_CRLF: + for (;;) + { + while (p < endptr && *p != '\r') p++; + if (++p >= endptr) + { + *lenptr = 0; + return endptr; + } + if (*p == '\n') + { + *lenptr = 2; + return p + 1; + } + } + break; + + case EL_ANYCRLF: + while (p < endptr) + { + int extra = 0; + register int c = *((unsigned char *)p); + + if (utf8 && c >= 0xc0) + { + int gcii, gcss; + extra = utf8_table4[c & 0x3f]; /* Number of additional bytes */ + gcss = 6*extra; + c = (c & utf8_table3[extra]) << gcss; + for (gcii = 1; gcii <= extra; gcii++) + { + gcss -= 6; + c |= (p[gcii] & 0x3f) << gcss; + } + } + + p += 1 + extra; + + switch (c) + { + case 0x0a: /* LF */ + *lenptr = 1; + return p; + + case 0x0d: /* CR */ + if (p < endptr && *p == 0x0a) + { + *lenptr = 2; + p++; + } + else *lenptr = 1; + return p; + + default: + break; + } + } /* End of loop for ANYCRLF case */ + + *lenptr = 0; /* Must have hit the end */ + return endptr; + + case EL_ANY: + while (p < endptr) + { + int extra = 0; + register int c = *((unsigned char *)p); + + if (utf8 && c >= 0xc0) + { + int gcii, gcss; + extra = utf8_table4[c & 0x3f]; /* Number of additional bytes */ + gcss = 6*extra; + c = (c & utf8_table3[extra]) << gcss; + for (gcii = 1; gcii <= extra; gcii++) + { + gcss -= 6; + c |= (p[gcii] & 0x3f) << gcss; + } + } + + p += 1 + extra; + + switch (c) + { + case 0x0a: /* LF */ + case 0x0b: /* VT */ + case 0x0c: /* FF */ + *lenptr = 1; + return p; + + case 0x0d: /* CR */ + if (p < endptr && *p == 0x0a) + { + *lenptr = 2; + p++; + } + else *lenptr = 1; + return p; + + case 0x85: /* NEL */ + *lenptr = utf8? 2 : 1; + return p; + + case 0x2028: /* LS */ + case 0x2029: /* PS */ + *lenptr = 3; + return p; + + default: + break; + } + } /* End of loop for ANY case */ + + *lenptr = 0; /* Must have hit the end */ + return endptr; + } /* End of overall switch */ +} + + + +/************************************************* +* Find start of previous line * +*************************************************/ + +/* This is called when looking back for before lines to print. + +Arguments: + p start of the subsequent line + startptr start of available data + +Returns: pointer to the start of the previous line +*/ + +static char * +previous_line(char *p, char *startptr) +{ +switch(endlinetype) + { + default: /* Just in case */ + case EL_LF: + p--; + while (p > startptr && p[-1] != '\n') p--; + return p; + + case EL_CR: + p--; + while (p > startptr && p[-1] != '\n') p--; + return p; + + case EL_CRLF: + for (;;) + { + p -= 2; + while (p > startptr && p[-1] != '\n') p--; + if (p <= startptr + 1 || p[-2] == '\r') return p; + } + return p; /* But control should never get here */ + + case EL_ANY: + case EL_ANYCRLF: + if (*(--p) == '\n' && p > startptr && p[-1] == '\r') p--; + if (utf8) while ((*p & 0xc0) == 0x80) p--; + + while (p > startptr) + { + register int c; + char *pp = p - 1; + + if (utf8) + { + int extra = 0; + while ((*pp & 0xc0) == 0x80) pp--; + c = *((unsigned char *)pp); + if (c >= 0xc0) + { + int gcii, gcss; + extra = utf8_table4[c & 0x3f]; /* Number of additional bytes */ + gcss = 6*extra; + c = (c & utf8_table3[extra]) << gcss; + for (gcii = 1; gcii <= extra; gcii++) + { + gcss -= 6; + c |= (pp[gcii] & 0x3f) << gcss; + } + } + } + else c = *((unsigned char *)pp); + + if (endlinetype == EL_ANYCRLF) switch (c) + { + case 0x0a: /* LF */ + case 0x0d: /* CR */ + return p; + + default: + break; + } + + else switch (c) + { + case 0x0a: /* LF */ + case 0x0b: /* VT */ + case 0x0c: /* FF */ + case 0x0d: /* CR */ + case 0x85: /* NEL */ + case 0x2028: /* LS */ + case 0x2029: /* PS */ + return p; + + default: + break; + } + + p = pp; /* Back one character */ + } /* End of loop for ANY case */ + + return startptr; /* Hit start of data */ + } /* End of overall switch */ +} + + + + + +/************************************************* +* Print the previous "after" lines * +*************************************************/ + +/* This is called if we are about to lose said lines because of buffer filling, +and at the end of the file. The data in the line is written using fwrite() so +that a binary zero does not terminate it. + +Arguments: + lastmatchnumber the number of the last matching line, plus one + lastmatchrestart where we restarted after the last match + endptr end of available data + printname filename for printing + +Returns: nothing +*/ + +static void do_after_lines(int lastmatchnumber, char *lastmatchrestart, + char *endptr, char *printname) +{ +if (after_context > 0 && lastmatchnumber > 0) + { + int count = 0; + while (lastmatchrestart < endptr && count++ < after_context) + { + int ellength; + char *pp = lastmatchrestart; + if (printname != NULL) fprintf(stdout, "%s-", printname); + if (number) fprintf(stdout, "%d-", lastmatchnumber++); + pp = end_of_line(pp, endptr, &ellength); + fwrite(lastmatchrestart, 1, pp - lastmatchrestart, stdout); + lastmatchrestart = pp; + } + hyphenpending = TRUE; + } +} + + + +/************************************************* +* Grep an individual file * +*************************************************/ + +/* This is called from grep_or_recurse() below. It uses a buffer that is three +times the value of MBUFTHIRD. The matching point is never allowed to stray into +the top third of the buffer, thus keeping more of the file available for +context printing or for multiline scanning. For large files, the pointer will +be in the middle third most of the time, so the bottom third is available for +"before" context printing. + +Arguments: + handle the fopened FILE stream for a normal file + the gzFile pointer when reading is via libz + the BZFILE pointer when reading is via libbz2 + frtype FR_PLAIN, FR_LIBZ, or FR_LIBBZ2 + printname the file name if it is to be printed for each match + or NULL if the file name is not to be printed + it cannot be NULL if filenames[_nomatch]_only is set + +Returns: 0 if there was at least one match + 1 otherwise (no matches) + 2 if there is a read error on a .bz2 file +*/ + +static int +pcregrep(void *handle, int frtype, char *printname) +{ +int rc = 1; +int linenumber = 1; +int lastmatchnumber = 0; +int count = 0; +int filepos = 0; +int offsets[99]; +char *lastmatchrestart = NULL; +char buffer[3*MBUFTHIRD]; +char *ptr = buffer; +char *endptr; +size_t bufflength; +BOOL endhyphenpending = FALSE; +FILE *in = NULL; /* Ensure initialized */ + +#ifdef SUPPORT_LIBZ +gzFile ingz = NULL; +#endif + +#ifdef SUPPORT_LIBBZ2 +BZFILE *inbz2 = NULL; +#endif + + +/* Do the first read into the start of the buffer and set up the pointer to end +of what we have. In the case of libz, a non-zipped .gz file will be read as a +plain file. However, if a .bz2 file isn't actually bzipped, the first read will +fail. */ + +#ifdef SUPPORT_LIBZ +if (frtype == FR_LIBZ) + { + ingz = (gzFile)handle; + bufflength = gzread (ingz, buffer, 3*MBUFTHIRD); + } +else +#endif + +#ifdef SUPPORT_LIBBZ2 +if (frtype == FR_LIBBZ2) + { + inbz2 = (BZFILE *)handle; + bufflength = BZ2_bzread(inbz2, buffer, 3*MBUFTHIRD); + if ((int)bufflength < 0) return 2; /* Gotcha: bufflength is size_t; */ + } /* without the cast it is unsigned. */ +else +#endif + + { + in = (FILE *)handle; + bufflength = fread(buffer, 1, 3*MBUFTHIRD, in); + } + +endptr = buffer + bufflength; + +/* Loop while the current pointer is not at the end of the file. For large +files, endptr will be at the end of the buffer when we are in the middle of the +file, but ptr will never get there, because as soon as it gets over 2/3 of the +way, the buffer is shifted left and re-filled. */ + +while (ptr < endptr) + { + int i, endlinelength; + int mrc = 0; + BOOL match = FALSE; + char *matchptr = ptr; + char *t = ptr; + size_t length, linelength; + + /* At this point, ptr is at the start of a line. We need to find the length + of the subject string to pass to pcre_exec(). In multiline mode, it is the + length remainder of the data in the buffer. Otherwise, it is the length of + the next line. After matching, we always advance by the length of the next + line. In multiline mode the PCRE_FIRSTLINE option is used for compiling, so + that any match is constrained to be in the first line. */ + + t = end_of_line(t, endptr, &endlinelength); + linelength = t - ptr - endlinelength; + length = multiline? (size_t)(endptr - ptr) : linelength; + + /* Extra processing for Jeffrey Friedl's debugging. */ + +#ifdef JFRIEDL_DEBUG + if (jfriedl_XT || jfriedl_XR) + { + #include + #include + struct timeval start_time, end_time; + struct timezone dummy; + + if (jfriedl_XT) + { + unsigned long newlen = length * jfriedl_XT + strlen(jfriedl_prefix) + strlen(jfriedl_postfix); + const char *orig = ptr; + ptr = malloc(newlen + 1); + if (!ptr) { + printf("out of memory"); + exit(2); + } + endptr = ptr; + strcpy(endptr, jfriedl_prefix); endptr += strlen(jfriedl_prefix); + for (i = 0; i < jfriedl_XT; i++) { + strncpy(endptr, orig, length); + endptr += length; + } + strcpy(endptr, jfriedl_postfix); endptr += strlen(jfriedl_postfix); + length = newlen; + } + + if (gettimeofday(&start_time, &dummy) != 0) + perror("bad gettimeofday"); + + + for (i = 0; i < jfriedl_XR; i++) + match = (pcre_exec(pattern_list[0], hints_list[0], ptr, length, 0, 0, offsets, 99) >= 0); + + if (gettimeofday(&end_time, &dummy) != 0) + perror("bad gettimeofday"); + + double delta = ((end_time.tv_sec + (end_time.tv_usec / 1000000.0)) + - + (start_time.tv_sec + (start_time.tv_usec / 1000000.0))); + + printf("%s TIMER[%.4f]\n", match ? "MATCH" : "FAIL", delta); + return 0; + } +#endif + + /* We come back here after a match when the -o option (only_matching) is set, + in order to find any further matches in the same line. */ + + ONLY_MATCHING_RESTART: + + /* Run through all the patterns until one matches. Note that we don't include + the final newline in the subject string. */ + + for (i = 0; i < pattern_count; i++) + { + mrc = pcre_exec(pattern_list[i], hints_list[i], matchptr, length, 0, 0, + offsets, 99); + if (mrc >= 0) { match = TRUE; break; } + if (mrc != PCRE_ERROR_NOMATCH) + { + fprintf(stderr, "pcregrep: pcre_exec() error %d while matching ", mrc); + if (pattern_count > 1) fprintf(stderr, "pattern number %d to ", i+1); + fprintf(stderr, "this line:\n"); + fwrite(matchptr, 1, linelength, stderr); /* In case binary zero included */ + fprintf(stderr, "\n"); + if (error_count == 0 && + (mrc == PCRE_ERROR_MATCHLIMIT || mrc == PCRE_ERROR_RECURSIONLIMIT)) + { + fprintf(stderr, "pcregrep: error %d means that a resource limit " + "was exceeded\n", mrc); + fprintf(stderr, "pcregrep: check your regex for nested unlimited loops\n"); + } + if (error_count++ > 20) + { + fprintf(stderr, "pcregrep: too many errors - abandoned\n"); + exit(2); + } + match = invert; /* No more matching; don't show the line again */ + break; + } + } + + /* If it's a match or a not-match (as required), do what's wanted. */ + + if (match != invert) + { + BOOL hyphenprinted = FALSE; + + /* We've failed if we want a file that doesn't have any matches. */ + + if (filenames == FN_NOMATCH_ONLY) return 1; + + /* Just count if just counting is wanted. */ + + if (count_only) count++; + + /* If all we want is a file name, there is no need to scan any more lines + in the file. */ + + else if (filenames == FN_ONLY) + { + fprintf(stdout, "%s\n", printname); + return 0; + } + + /* Likewise, if all we want is a yes/no answer. */ + + else if (quiet) return 0; + + /* The --only-matching option prints just the substring that matched, and + the --file-offsets and --line-offsets options output offsets for the + matching substring (they both force --only-matching). None of these options + prints any context. Afterwards, adjust the start and length, and then jump + back to look for further matches in the same line. If we are in invert + mode, however, nothing is printed - this could be still useful because the + return code is set. */ + + else if (only_matching) + { + if (!invert) + { + if (printname != NULL) fprintf(stdout, "%s:", printname); + if (number) fprintf(stdout, "%d:", linenumber); + if (line_offsets) + fprintf(stdout, "%d,%d", matchptr + offsets[0] - ptr, + offsets[1] - offsets[0]); + else if (file_offsets) + fprintf(stdout, "%d,%d", filepos + matchptr + offsets[0] - ptr, + offsets[1] - offsets[0]); + else + fwrite(matchptr + offsets[0], 1, offsets[1] - offsets[0], stdout); + fprintf(stdout, "\n"); + matchptr += offsets[1]; + length -= offsets[1]; + match = FALSE; + goto ONLY_MATCHING_RESTART; + } + } + + /* This is the default case when none of the above options is set. We print + the matching lines(s), possibly preceded and/or followed by other lines of + context. */ + + else + { + /* See if there is a requirement to print some "after" lines from a + previous match. We never print any overlaps. */ + + if (after_context > 0 && lastmatchnumber > 0) + { + int ellength; + int linecount = 0; + char *p = lastmatchrestart; + + while (p < ptr && linecount < after_context) + { + p = end_of_line(p, ptr, &ellength); + linecount++; + } + + /* It is important to advance lastmatchrestart during this printing so + that it interacts correctly with any "before" printing below. Print + each line's data using fwrite() in case there are binary zeroes. */ + + while (lastmatchrestart < p) + { + char *pp = lastmatchrestart; + if (printname != NULL) fprintf(stdout, "%s-", printname); + if (number) fprintf(stdout, "%d-", lastmatchnumber++); + pp = end_of_line(pp, endptr, &ellength); + fwrite(lastmatchrestart, 1, pp - lastmatchrestart, stdout); + lastmatchrestart = pp; + } + if (lastmatchrestart != ptr) hyphenpending = TRUE; + } + + /* If there were non-contiguous lines printed above, insert hyphens. */ + + if (hyphenpending) + { + fprintf(stdout, "--\n"); + hyphenpending = FALSE; + hyphenprinted = TRUE; + } + + /* See if there is a requirement to print some "before" lines for this + match. Again, don't print overlaps. */ + + if (before_context > 0) + { + int linecount = 0; + char *p = ptr; + + while (p > buffer && (lastmatchnumber == 0 || p > lastmatchrestart) && + linecount < before_context) + { + linecount++; + p = previous_line(p, buffer); + } + + if (lastmatchnumber > 0 && p > lastmatchrestart && !hyphenprinted) + fprintf(stdout, "--\n"); + + while (p < ptr) + { + int ellength; + char *pp = p; + if (printname != NULL) fprintf(stdout, "%s-", printname); + if (number) fprintf(stdout, "%d-", linenumber - linecount--); + pp = end_of_line(pp, endptr, &ellength); + fwrite(p, 1, pp - p, stdout); + p = pp; + } + } + + /* Now print the matching line(s); ensure we set hyphenpending at the end + of the file if any context lines are being output. */ + + if (after_context > 0 || before_context > 0) + endhyphenpending = TRUE; + + if (printname != NULL) fprintf(stdout, "%s:", printname); + if (number) fprintf(stdout, "%d:", linenumber); + + /* In multiline mode, we want to print to the end of the line in which + the end of the matched string is found, so we adjust linelength and the + line number appropriately, but only when there actually was a match + (invert not set). Because the PCRE_FIRSTLINE option is set, the start of + the match will always be before the first newline sequence. */ + + if (multiline) + { + int ellength; + char *endmatch = ptr; + if (!invert) + { + endmatch += offsets[1]; + t = ptr; + while (t < endmatch) + { + t = end_of_line(t, endptr, &ellength); + if (t <= endmatch) linenumber++; else break; + } + } + endmatch = end_of_line(endmatch, endptr, &ellength); + linelength = endmatch - ptr - ellength; + } + + /*** NOTE: Use only fwrite() to output the data line, so that binary + zeroes are treated as just another data character. */ + + /* This extra option, for Jeffrey Friedl's debugging requirements, + replaces the matched string, or a specific captured string if it exists, + with X. When this happens, colouring is ignored. */ + +#ifdef JFRIEDL_DEBUG + if (S_arg >= 0 && S_arg < mrc) + { + int first = S_arg * 2; + int last = first + 1; + fwrite(ptr, 1, offsets[first], stdout); + fprintf(stdout, "X"); + fwrite(ptr + offsets[last], 1, linelength - offsets[last], stdout); + } + else +#endif + + /* We have to split the line(s) up if colouring. */ + + if (do_colour) + { + fwrite(ptr, 1, offsets[0], stdout); + fprintf(stdout, "%c[%sm", 0x1b, colour_string); + fwrite(ptr + offsets[0], 1, offsets[1] - offsets[0], stdout); + fprintf(stdout, "%c[00m", 0x1b); + fwrite(ptr + offsets[1], 1, (linelength + endlinelength) - offsets[1], + stdout); + } + else fwrite(ptr, 1, linelength + endlinelength, stdout); + } + + /* End of doing what has to be done for a match */ + + rc = 0; /* Had some success */ + + /* Remember where the last match happened for after_context. We remember + where we are about to restart, and that line's number. */ + + lastmatchrestart = ptr + linelength + endlinelength; + lastmatchnumber = linenumber + 1; + } + + /* For a match in multiline inverted mode (which of course did not cause + anything to be printed), we have to move on to the end of the match before + proceeding. */ + + if (multiline && invert && match) + { + int ellength; + char *endmatch = ptr + offsets[1]; + t = ptr; + while (t < endmatch) + { + t = end_of_line(t, endptr, &ellength); + if (t <= endmatch) linenumber++; else break; + } + endmatch = end_of_line(endmatch, endptr, &ellength); + linelength = endmatch - ptr - ellength; + } + + /* Advance to after the newline and increment the line number. The file + offset to the current line is maintained in filepos. */ + + ptr += linelength + endlinelength; + filepos += linelength + endlinelength; + linenumber++; + + /* If we haven't yet reached the end of the file (the buffer is full), and + the current point is in the top 1/3 of the buffer, slide the buffer down by + 1/3 and refill it. Before we do this, if some unprinted "after" lines are + about to be lost, print them. */ + + if (bufflength >= sizeof(buffer) && ptr > buffer + 2*MBUFTHIRD) + { + if (after_context > 0 && + lastmatchnumber > 0 && + lastmatchrestart < buffer + MBUFTHIRD) + { + do_after_lines(lastmatchnumber, lastmatchrestart, endptr, printname); + lastmatchnumber = 0; + } + + /* Now do the shuffle */ + + memmove(buffer, buffer + MBUFTHIRD, 2*MBUFTHIRD); + ptr -= MBUFTHIRD; + +#ifdef SUPPORT_LIBZ + if (frtype == FR_LIBZ) + bufflength = 2*MBUFTHIRD + + gzread (ingz, buffer + 2*MBUFTHIRD, MBUFTHIRD); + else +#endif + +#ifdef SUPPORT_LIBBZ2 + if (frtype == FR_LIBBZ2) + bufflength = 2*MBUFTHIRD + + BZ2_bzread(inbz2, buffer + 2*MBUFTHIRD, MBUFTHIRD); + else +#endif + + bufflength = 2*MBUFTHIRD + fread(buffer + 2*MBUFTHIRD, 1, MBUFTHIRD, in); + + endptr = buffer + bufflength; + + /* Adjust any last match point */ + + if (lastmatchnumber > 0) lastmatchrestart -= MBUFTHIRD; + } + } /* Loop through the whole file */ + +/* End of file; print final "after" lines if wanted; do_after_lines sets +hyphenpending if it prints something. */ + +if (!only_matching && !count_only) + { + do_after_lines(lastmatchnumber, lastmatchrestart, endptr, printname); + hyphenpending |= endhyphenpending; + } + +/* Print the file name if we are looking for those without matches and there +were none. If we found a match, we won't have got this far. */ + +if (filenames == FN_NOMATCH_ONLY) + { + fprintf(stdout, "%s\n", printname); + return 0; + } + +/* Print the match count if wanted */ + +if (count_only) + { + if (printname != NULL) fprintf(stdout, "%s:", printname); + fprintf(stdout, "%d\n", count); + } + +return rc; +} + + + +/************************************************* +* Grep a file or recurse into a directory * +*************************************************/ + +/* Given a path name, if it's a directory, scan all the files if we are +recursing; if it's a file, grep it. + +Arguments: + pathname the path to investigate + dir_recurse TRUE if recursing is wanted (-r or -drecurse) + only_one_at_top TRUE if the path is the only one at toplevel + +Returns: 0 if there was at least one match + 1 if there were no matches + 2 there was some kind of error + +However, file opening failures are suppressed if "silent" is set. +*/ + +static int +grep_or_recurse(char *pathname, BOOL dir_recurse, BOOL only_one_at_top) +{ +int rc = 1; +int sep; +int frtype; +int pathlen; +void *handle; +FILE *in = NULL; /* Ensure initialized */ + +#ifdef SUPPORT_LIBZ +gzFile ingz = NULL; +#endif + +#ifdef SUPPORT_LIBBZ2 +BZFILE *inbz2 = NULL; +#endif + +/* If the file name is "-" we scan stdin */ + +if (strcmp(pathname, "-") == 0) + { + return pcregrep(stdin, FR_PLAIN, + (filenames > FN_DEFAULT || (filenames == FN_DEFAULT && !only_one_at_top))? + stdin_name : NULL); + } + +/* If the file is a directory, skip if skipping or if we are recursing, scan +each file within it, subject to any include or exclude patterns that were set. +The scanning code is localized so it can be made system-specific. */ + +if ((sep = isdirectory(pathname)) != 0) + { + if (dee_action == dee_SKIP) return 1; + if (dee_action == dee_RECURSE) + { + char buffer[1024]; + char *nextfile; + directory_type *dir = opendirectory(pathname); + + if (dir == NULL) + { + if (!silent) + fprintf(stderr, "pcregrep: Failed to open directory %s: %s\n", pathname, + strerror(errno)); + return 2; + } + + while ((nextfile = readdirectory(dir)) != NULL) + { + int frc, blen; + sprintf(buffer, "%.512s%c%.128s", pathname, sep, nextfile); + blen = strlen(buffer); + + if (exclude_compiled != NULL && + pcre_exec(exclude_compiled, NULL, buffer, blen, 0, 0, NULL, 0) >= 0) + continue; + + if (include_compiled != NULL && + pcre_exec(include_compiled, NULL, buffer, blen, 0, 0, NULL, 0) < 0) + continue; + + frc = grep_or_recurse(buffer, dir_recurse, FALSE); + if (frc > 1) rc = frc; + else if (frc == 0 && rc == 1) rc = 0; + } + + closedirectory(dir); + return rc; + } + } + +/* If the file is not a directory and not a regular file, skip it if that's +been requested. */ + +else if (!isregfile(pathname) && DEE_action == DEE_SKIP) return 1; + +/* Control reaches here if we have a regular file, or if we have a directory +and recursion or skipping was not requested, or if we have anything else and +skipping was not requested. The scan proceeds. If this is the first and only +argument at top level, we don't show the file name, unless we are only showing +the file name, or the filename was forced (-H). */ + +pathlen = strlen(pathname); + +/* Open using zlib if it is supported and the file name ends with .gz. */ + +#ifdef SUPPORT_LIBZ +if (pathlen > 3 && strcmp(pathname + pathlen - 3, ".gz") == 0) + { + ingz = gzopen(pathname, "rb"); + if (ingz == NULL) + { + if (!silent) + fprintf(stderr, "pcregrep: Failed to open %s: %s\n", pathname, + strerror(errno)); + return 2; + } + handle = (void *)ingz; + frtype = FR_LIBZ; + } +else +#endif + +/* Otherwise open with bz2lib if it is supported and the name ends with .bz2. */ + +#ifdef SUPPORT_LIBBZ2 +if (pathlen > 4 && strcmp(pathname + pathlen - 4, ".bz2") == 0) + { + inbz2 = BZ2_bzopen(pathname, "rb"); + handle = (void *)inbz2; + frtype = FR_LIBBZ2; + } +else +#endif + +/* Otherwise use plain fopen(). The label is so that we can come back here if +an attempt to read a .bz2 file indicates that it really is a plain file. */ + +#ifdef SUPPORT_LIBBZ2 +PLAIN_FILE: +#endif + { + in = fopen(pathname, "r"); + handle = (void *)in; + frtype = FR_PLAIN; + } + +/* All the opening methods return errno when they fail. */ + +if (handle == NULL) + { + if (!silent) + fprintf(stderr, "pcregrep: Failed to open %s: %s\n", pathname, + strerror(errno)); + return 2; + } + +/* Now grep the file */ + +rc = pcregrep(handle, frtype, (filenames > FN_DEFAULT || + (filenames == FN_DEFAULT && !only_one_at_top))? pathname : NULL); + +/* Close in an appropriate manner. */ + +#ifdef SUPPORT_LIBZ +if (frtype == FR_LIBZ) + gzclose(ingz); +else +#endif + +/* If it is a .bz2 file and the result is 2, it means that the first attempt to +read failed. If the error indicates that the file isn't in fact bzipped, try +again as a normal file. */ + +#ifdef SUPPORT_LIBBZ2 +if (frtype == FR_LIBBZ2) + { + if (rc == 2) + { + int errnum; + const char *err = BZ2_bzerror(inbz2, &errnum); + if (errnum == BZ_DATA_ERROR_MAGIC) + { + BZ2_bzclose(inbz2); + goto PLAIN_FILE; + } + else if (!silent) + fprintf(stderr, "pcregrep: Failed to read %s using bzlib: %s\n", + pathname, err); + } + BZ2_bzclose(inbz2); + } +else +#endif + +/* Normal file close */ + +fclose(in); + +/* Pass back the yield from pcregrep(). */ + +return rc; +} + + + + +/************************************************* +* Usage function * +*************************************************/ + +static int +usage(int rc) +{ +option_item *op; +fprintf(stderr, "Usage: pcregrep [-"); +for (op = optionlist; op->one_char != 0; op++) + { + if (op->one_char > 0) fprintf(stderr, "%c", op->one_char); + } +fprintf(stderr, "] [long options] [pattern] [files]\n"); +fprintf(stderr, "Type `pcregrep --help' for more information and the long " + "options.\n"); +return rc; +} + + + + +/************************************************* +* Help function * +*************************************************/ + +static void +help(void) +{ +option_item *op; + +printf("Usage: pcregrep [OPTION]... [PATTERN] [FILE1 FILE2 ...]\n"); +printf("Search for PATTERN in each FILE or standard input.\n"); +printf("PATTERN must be present if neither -e nor -f is used.\n"); +printf("\"-\" can be used as a file name to mean STDIN.\n"); + +#ifdef SUPPORT_LIBZ +printf("Files whose names end in .gz are read using zlib.\n"); +#endif + +#ifdef SUPPORT_LIBBZ2 +printf("Files whose names end in .bz2 are read using bzlib2.\n"); +#endif + +#if defined SUPPORT_LIBZ || defined SUPPORT_LIBBZ2 +printf("Other files and the standard input are read as plain files.\n\n"); +#else +printf("All files are read as plain files, without any interpretation.\n\n"); +#endif + +printf("Example: pcregrep -i 'hello.*world' menu.h main.c\n\n"); +printf("Options:\n"); + +for (op = optionlist; op->one_char != 0; op++) + { + int n; + char s[4]; + if (op->one_char > 0) sprintf(s, "-%c,", op->one_char); else strcpy(s, " "); + n = 30 - printf(" %s --%s", s, op->long_name); + if (n < 1) n = 1; + printf("%.*s%s\n", n, " ", op->help_text); + } + +printf("\nWhen reading patterns from a file instead of using a command line option,\n"); +printf("trailing white space is removed and blank lines are ignored.\n"); +printf("There is a maximum of %d patterns.\n", MAX_PATTERN_COUNT); + +printf("\nWith no FILEs, read standard input. If fewer than two FILEs given, assume -h.\n"); +printf("Exit status is 0 if any matches, 1 if no matches, and 2 if trouble.\n"); +} + + + + +/************************************************* +* Handle a single-letter, no data option * +*************************************************/ + +static int +handle_option(int letter, int options) +{ +switch(letter) + { + case N_FOFFSETS: file_offsets = TRUE; break; + case N_HELP: help(); exit(0); + case N_LOFFSETS: line_offsets = number = TRUE; break; + case 'c': count_only = TRUE; break; + case 'F': process_options |= PO_FIXED_STRINGS; break; + case 'H': filenames = FN_FORCE; break; + case 'h': filenames = FN_NONE; break; + case 'i': options |= PCRE_CASELESS; break; + case 'l': filenames = FN_ONLY; break; + case 'L': filenames = FN_NOMATCH_ONLY; break; + case 'M': multiline = TRUE; options |= PCRE_MULTILINE|PCRE_FIRSTLINE; break; + case 'n': number = TRUE; break; + case 'o': only_matching = TRUE; break; + case 'q': quiet = TRUE; break; + case 'r': dee_action = dee_RECURSE; break; + case 's': silent = TRUE; break; + case 'u': options |= PCRE_UTF8; utf8 = TRUE; break; + case 'v': invert = TRUE; break; + case 'w': process_options |= PO_WORD_MATCH; break; + case 'x': process_options |= PO_LINE_MATCH; break; + + case 'V': + fprintf(stderr, "pcregrep version %s\n", pcre_version()); + exit(0); + break; + + default: + fprintf(stderr, "pcregrep: Unknown option -%c\n", letter); + exit(usage(2)); + } + +return options; +} + + + + +/************************************************* +* Construct printed ordinal * +*************************************************/ + +/* This turns a number into "1st", "3rd", etc. */ + +static char * +ordin(int n) +{ +static char buffer[8]; +char *p = buffer; +sprintf(p, "%d", n); +while (*p != 0) p++; +switch (n%10) + { + case 1: strcpy(p, "st"); break; + case 2: strcpy(p, "nd"); break; + case 3: strcpy(p, "rd"); break; + default: strcpy(p, "th"); break; + } +return buffer; +} + + + +/************************************************* +* Compile a single pattern * +*************************************************/ + +/* When the -F option has been used, this is called for each substring. +Otherwise it's called for each supplied pattern. + +Arguments: + pattern the pattern string + options the PCRE options + filename the file name, or NULL for a command-line pattern + count 0 if this is the only command line pattern, or + number of the command line pattern, or + linenumber for a pattern from a file + +Returns: TRUE on success, FALSE after an error +*/ + +static BOOL +compile_single_pattern(char *pattern, int options, char *filename, int count) +{ +char buffer[MBUFTHIRD + 16]; +const char *error; +int errptr; + +if (pattern_count >= MAX_PATTERN_COUNT) + { + fprintf(stderr, "pcregrep: Too many %spatterns (max %d)\n", + (filename == NULL)? "command-line " : "", MAX_PATTERN_COUNT); + return FALSE; + } + +sprintf(buffer, "%s%.*s%s", prefix[process_options], MBUFTHIRD, pattern, + suffix[process_options]); +pattern_list[pattern_count] = + pcre_compile(buffer, options, &error, &errptr, pcretables); +if (pattern_list[pattern_count] != NULL) + { + pattern_count++; + return TRUE; + } + +/* Handle compile errors */ + +errptr -= (int)strlen(prefix[process_options]); +if (errptr > (int)strlen(pattern)) errptr = (int)strlen(pattern); + +if (filename == NULL) + { + if (count == 0) + fprintf(stderr, "pcregrep: Error in command-line regex " + "at offset %d: %s\n", errptr, error); + else + fprintf(stderr, "pcregrep: Error in %s command-line regex " + "at offset %d: %s\n", ordin(count), errptr, error); + } +else + { + fprintf(stderr, "pcregrep: Error in regex in line %d of %s " + "at offset %d: %s\n", count, filename, errptr, error); + } + +return FALSE; +} + + + +/************************************************* +* Compile one supplied pattern * +*************************************************/ + +/* When the -F option has been used, each string may be a list of strings, +separated by line breaks. They will be matched literally. + +Arguments: + pattern the pattern string + options the PCRE options + filename the file name, or NULL for a command-line pattern + count 0 if this is the only command line pattern, or + number of the command line pattern, or + linenumber for a pattern from a file + +Returns: TRUE on success, FALSE after an error +*/ + +static BOOL +compile_pattern(char *pattern, int options, char *filename, int count) +{ +if ((process_options & PO_FIXED_STRINGS) != 0) + { + char *eop = pattern + strlen(pattern); + char buffer[MBUFTHIRD]; + for(;;) + { + int ellength; + char *p = end_of_line(pattern, eop, &ellength); + if (ellength == 0) + return compile_single_pattern(pattern, options, filename, count); + sprintf(buffer, "%.*s", (int)(p - pattern - ellength), pattern); + pattern = p; + if (!compile_single_pattern(buffer, options, filename, count)) + return FALSE; + } + } +else return compile_single_pattern(pattern, options, filename, count); +} + + + +/************************************************* +* Main program * +*************************************************/ + +/* Returns 0 if something matched, 1 if nothing matched, 2 after an error. */ + +int +main(int argc, char **argv) +{ +int i, j; +int rc = 1; +int pcre_options = 0; +int cmd_pattern_count = 0; +int hint_count = 0; +int errptr; +BOOL only_one_at_top; +char *patterns[MAX_PATTERN_COUNT]; +const char *locale_from = "--locale"; +const char *error; + +/* Set the default line ending value from the default in the PCRE library; +"lf", "cr", "crlf", and "any" are supported. Anything else is treated as "lf". +*/ + +(void)pcre_config(PCRE_CONFIG_NEWLINE, &i); +switch(i) + { + default: newline = (char *)"lf"; break; + case '\r': newline = (char *)"cr"; break; + case ('\r' << 8) | '\n': newline = (char *)"crlf"; break; + case -1: newline = (char *)"any"; break; + case -2: newline = (char *)"anycrlf"; break; + } + +/* Process the options */ + +for (i = 1; i < argc; i++) + { + option_item *op = NULL; + char *option_data = (char *)""; /* default to keep compiler happy */ + BOOL longop; + BOOL longopwasequals = FALSE; + + if (argv[i][0] != '-') break; + + /* If we hit an argument that is just "-", it may be a reference to STDIN, + but only if we have previously had -e or -f to define the patterns. */ + + if (argv[i][1] == 0) + { + if (pattern_filename != NULL || pattern_count > 0) break; + else exit(usage(2)); + } + + /* Handle a long name option, or -- to terminate the options */ + + if (argv[i][1] == '-') + { + char *arg = argv[i] + 2; + char *argequals = strchr(arg, '='); + + if (*arg == 0) /* -- terminates options */ + { + i++; + break; /* out of the options-handling loop */ + } + + longop = TRUE; + + /* Some long options have data that follows after =, for example file=name. + Some options have variations in the long name spelling: specifically, we + allow "regexp" because GNU grep allows it, though I personally go along + with Jeffrey Friedl and Larry Wall in preferring "regex" without the "p". + These options are entered in the table as "regex(p)". No option is in both + these categories, fortunately. */ + + for (op = optionlist; op->one_char != 0; op++) + { + char *opbra = strchr(op->long_name, '('); + char *equals = strchr(op->long_name, '='); + if (opbra == NULL) /* Not a (p) case */ + { + if (equals == NULL) /* Not thing=data case */ + { + if (strcmp(arg, op->long_name) == 0) break; + } + else /* Special case xxx=data */ + { + int oplen = equals - op->long_name; + int arglen = (argequals == NULL)? (int)strlen(arg) : argequals - arg; + if (oplen == arglen && strncmp(arg, op->long_name, oplen) == 0) + { + option_data = arg + arglen; + if (*option_data == '=') + { + option_data++; + longopwasequals = TRUE; + } + break; + } + } + } + else /* Special case xxxx(p) */ + { + char buff1[24]; + char buff2[24]; + int baselen = opbra - op->long_name; + sprintf(buff1, "%.*s", baselen, op->long_name); + sprintf(buff2, "%s%.*s", buff1, + (int)strlen(op->long_name) - baselen - 2, opbra + 1); + if (strcmp(arg, buff1) == 0 || strcmp(arg, buff2) == 0) + break; + } + } + + if (op->one_char == 0) + { + fprintf(stderr, "pcregrep: Unknown option %s\n", argv[i]); + exit(usage(2)); + } + } + + + /* Jeffrey Friedl's debugging harness uses these additional options which + are not in the right form for putting in the option table because they use + only one hyphen, yet are more than one character long. By putting them + separately here, they will not get displayed as part of the help() output, + but I don't think Jeffrey will care about that. */ + +#ifdef JFRIEDL_DEBUG + else if (strcmp(argv[i], "-pre") == 0) { + jfriedl_prefix = argv[++i]; + continue; + } else if (strcmp(argv[i], "-post") == 0) { + jfriedl_postfix = argv[++i]; + continue; + } else if (strcmp(argv[i], "-XT") == 0) { + sscanf(argv[++i], "%d", &jfriedl_XT); + continue; + } else if (strcmp(argv[i], "-XR") == 0) { + sscanf(argv[++i], "%d", &jfriedl_XR); + continue; + } +#endif + + + /* One-char options; many that have no data may be in a single argument; we + continue till we hit the last one or one that needs data. */ + + else + { + char *s = argv[i] + 1; + longop = FALSE; + while (*s != 0) + { + for (op = optionlist; op->one_char != 0; op++) + { if (*s == op->one_char) break; } + if (op->one_char == 0) + { + fprintf(stderr, "pcregrep: Unknown option letter '%c' in \"%s\"\n", + *s, argv[i]); + exit(usage(2)); + } + if (op->type != OP_NODATA || s[1] == 0) + { + option_data = s+1; + break; + } + pcre_options = handle_option(*s++, pcre_options); + } + } + + /* At this point we should have op pointing to a matched option. If the type + is NO_DATA, it means that there is no data, and the option might set + something in the PCRE options. */ + + if (op->type == OP_NODATA) + { + pcre_options = handle_option(op->one_char, pcre_options); + continue; + } + + /* If the option type is OP_OP_STRING or OP_OP_NUMBER, it's an option that + either has a value or defaults to something. It cannot have data in a + separate item. At the moment, the only such options are "colo(u)r" and + Jeffrey Friedl's special -S debugging option. */ + + if (*option_data == 0 && + (op->type == OP_OP_STRING || op->type == OP_OP_NUMBER)) + { + switch (op->one_char) + { + case N_COLOUR: + colour_option = (char *)"auto"; + break; +#ifdef JFRIEDL_DEBUG + case 'S': + S_arg = 0; + break; +#endif + } + continue; + } + + /* Otherwise, find the data string for the option. */ + + if (*option_data == 0) + { + if (i >= argc - 1 || longopwasequals) + { + fprintf(stderr, "pcregrep: Data missing after %s\n", argv[i]); + exit(usage(2)); + } + option_data = argv[++i]; + } + + /* If the option type is OP_PATLIST, it's the -e option, which can be called + multiple times to create a list of patterns. */ + + if (op->type == OP_PATLIST) + { + if (cmd_pattern_count >= MAX_PATTERN_COUNT) + { + fprintf(stderr, "pcregrep: Too many command-line patterns (max %d)\n", + MAX_PATTERN_COUNT); + return 2; + } + patterns[cmd_pattern_count++] = option_data; + } + + /* Otherwise, deal with single string or numeric data values. */ + + else if (op->type != OP_NUMBER && op->type != OP_OP_NUMBER) + { + *((char **)op->dataptr) = option_data; + } + else + { + char *endptr; + int n = strtoul(option_data, &endptr, 10); + if (*endptr != 0) + { + if (longop) + { + char *equals = strchr(op->long_name, '='); + int nlen = (equals == NULL)? (int)strlen(op->long_name) : + equals - op->long_name; + fprintf(stderr, "pcregrep: Malformed number \"%s\" after --%.*s\n", + option_data, nlen, op->long_name); + } + else + fprintf(stderr, "pcregrep: Malformed number \"%s\" after -%c\n", + option_data, op->one_char); + exit(usage(2)); + } + *((int *)op->dataptr) = n; + } + } + +/* Options have been decoded. If -C was used, its value is used as a default +for -A and -B. */ + +if (both_context > 0) + { + if (after_context == 0) after_context = both_context; + if (before_context == 0) before_context = both_context; + } + +/* Only one of --only-matching, --file-offsets, or --line-offsets is permitted. +However, the latter two set the only_matching flag. */ + +if ((only_matching && (file_offsets || line_offsets)) || + (file_offsets && line_offsets)) + { + fprintf(stderr, "pcregrep: Cannot mix --only-matching, --file-offsets " + "and/or --line-offsets\n"); + exit(usage(2)); + } + +if (file_offsets || line_offsets) only_matching = TRUE; + +/* If a locale has not been provided as an option, see if the LC_CTYPE or +LC_ALL environment variable is set, and if so, use it. */ + +if (locale == NULL) + { + locale = getenv("LC_ALL"); + locale_from = "LCC_ALL"; + } + +if (locale == NULL) + { + locale = getenv("LC_CTYPE"); + locale_from = "LC_CTYPE"; + } + +/* If a locale has been provided, set it, and generate the tables the PCRE +needs. Otherwise, pcretables==NULL, which causes the use of default tables. */ + +if (locale != NULL) + { + if (setlocale(LC_CTYPE, locale) == NULL) + { + fprintf(stderr, "pcregrep: Failed to set locale %s (obtained from %s)\n", + locale, locale_from); + return 2; + } + pcretables = pcre_maketables(); + } + +/* Sort out colouring */ + +if (colour_option != NULL && strcmp(colour_option, "never") != 0) + { + if (strcmp(colour_option, "always") == 0) do_colour = TRUE; + else if (strcmp(colour_option, "auto") == 0) do_colour = is_stdout_tty(); + else + { + fprintf(stderr, "pcregrep: Unknown colour setting \"%s\"\n", + colour_option); + return 2; + } + if (do_colour) + { + char *cs = getenv("PCREGREP_COLOUR"); + if (cs == NULL) cs = getenv("PCREGREP_COLOR"); + if (cs != NULL) colour_string = cs; + } + } + +/* Interpret the newline type; the default settings are Unix-like. */ + +if (strcmp(newline, "cr") == 0 || strcmp(newline, "CR") == 0) + { + pcre_options |= PCRE_NEWLINE_CR; + endlinetype = EL_CR; + } +else if (strcmp(newline, "lf") == 0 || strcmp(newline, "LF") == 0) + { + pcre_options |= PCRE_NEWLINE_LF; + endlinetype = EL_LF; + } +else if (strcmp(newline, "crlf") == 0 || strcmp(newline, "CRLF") == 0) + { + pcre_options |= PCRE_NEWLINE_CRLF; + endlinetype = EL_CRLF; + } +else if (strcmp(newline, "any") == 0 || strcmp(newline, "ANY") == 0) + { + pcre_options |= PCRE_NEWLINE_ANY; + endlinetype = EL_ANY; + } +else if (strcmp(newline, "anycrlf") == 0 || strcmp(newline, "ANYCRLF") == 0) + { + pcre_options |= PCRE_NEWLINE_ANYCRLF; + endlinetype = EL_ANYCRLF; + } +else + { + fprintf(stderr, "pcregrep: Invalid newline specifier \"%s\"\n", newline); + return 2; + } + +/* Interpret the text values for -d and -D */ + +if (dee_option != NULL) + { + if (strcmp(dee_option, "read") == 0) dee_action = dee_READ; + else if (strcmp(dee_option, "recurse") == 0) dee_action = dee_RECURSE; + else if (strcmp(dee_option, "skip") == 0) dee_action = dee_SKIP; + else + { + fprintf(stderr, "pcregrep: Invalid value \"%s\" for -d\n", dee_option); + return 2; + } + } + +if (DEE_option != NULL) + { + if (strcmp(DEE_option, "read") == 0) DEE_action = DEE_READ; + else if (strcmp(DEE_option, "skip") == 0) DEE_action = DEE_SKIP; + else + { + fprintf(stderr, "pcregrep: Invalid value \"%s\" for -D\n", DEE_option); + return 2; + } + } + +/* Check the values for Jeffrey Friedl's debugging options. */ + +#ifdef JFRIEDL_DEBUG +if (S_arg > 9) + { + fprintf(stderr, "pcregrep: bad value for -S option\n"); + return 2; + } +if (jfriedl_XT != 0 || jfriedl_XR != 0) + { + if (jfriedl_XT == 0) jfriedl_XT = 1; + if (jfriedl_XR == 0) jfriedl_XR = 1; + } +#endif + +/* Get memory to store the pattern and hints lists. */ + +pattern_list = (pcre **)malloc(MAX_PATTERN_COUNT * sizeof(pcre *)); +hints_list = (pcre_extra **)malloc(MAX_PATTERN_COUNT * sizeof(pcre_extra *)); + +if (pattern_list == NULL || hints_list == NULL) + { + fprintf(stderr, "pcregrep: malloc failed\n"); + goto EXIT2; + } + +/* If no patterns were provided by -e, and there is no file provided by -f, +the first argument is the one and only pattern, and it must exist. */ + +if (cmd_pattern_count == 0 && pattern_filename == NULL) + { + if (i >= argc) return usage(2); + patterns[cmd_pattern_count++] = argv[i++]; + } + +/* Compile the patterns that were provided on the command line, either by +multiple uses of -e or as a single unkeyed pattern. */ + +for (j = 0; j < cmd_pattern_count; j++) + { + if (!compile_pattern(patterns[j], pcre_options, NULL, + (j == 0 && cmd_pattern_count == 1)? 0 : j + 1)) + goto EXIT2; + } + +/* Compile the regular expressions that are provided in a file. */ + +if (pattern_filename != NULL) + { + int linenumber = 0; + FILE *f; + char *filename; + char buffer[MBUFTHIRD]; + + if (strcmp(pattern_filename, "-") == 0) + { + f = stdin; + filename = stdin_name; + } + else + { + f = fopen(pattern_filename, "r"); + if (f == NULL) + { + fprintf(stderr, "pcregrep: Failed to open %s: %s\n", pattern_filename, + strerror(errno)); + goto EXIT2; + } + filename = pattern_filename; + } + + while (fgets(buffer, MBUFTHIRD, f) != NULL) + { + char *s = buffer + (int)strlen(buffer); + while (s > buffer && isspace((unsigned char)(s[-1]))) s--; + *s = 0; + linenumber++; + if (buffer[0] == 0) continue; /* Skip blank lines */ + if (!compile_pattern(buffer, pcre_options, filename, linenumber)) + goto EXIT2; + } + + if (f != stdin) fclose(f); + } + +/* Study the regular expressions, as we will be running them many times */ + +for (j = 0; j < pattern_count; j++) + { + hints_list[j] = pcre_study(pattern_list[j], 0, &error); + if (error != NULL) + { + char s[16]; + if (pattern_count == 1) s[0] = 0; else sprintf(s, " number %d", j); + fprintf(stderr, "pcregrep: Error while studying regex%s: %s\n", s, error); + goto EXIT2; + } + hint_count++; + } + +/* If there are include or exclude patterns, compile them. */ + +if (exclude_pattern != NULL) + { + exclude_compiled = pcre_compile(exclude_pattern, 0, &error, &errptr, + pcretables); + if (exclude_compiled == NULL) + { + fprintf(stderr, "pcregrep: Error in 'exclude' regex at offset %d: %s\n", + errptr, error); + goto EXIT2; + } + } + +if (include_pattern != NULL) + { + include_compiled = pcre_compile(include_pattern, 0, &error, &errptr, + pcretables); + if (include_compiled == NULL) + { + fprintf(stderr, "pcregrep: Error in 'include' regex at offset %d: %s\n", + errptr, error); + goto EXIT2; + } + } + +/* If there are no further arguments, do the business on stdin and exit. */ + +if (i >= argc) + { + rc = pcregrep(stdin, FR_PLAIN, (filenames > FN_DEFAULT)? stdin_name : NULL); + goto EXIT; + } + +/* Otherwise, work through the remaining arguments as files or directories. +Pass in the fact that there is only one argument at top level - this suppresses +the file name if the argument is not a directory and filenames are not +otherwise forced. */ + +only_one_at_top = i == argc - 1; /* Catch initial value of i */ + +for (; i < argc; i++) + { + int frc = grep_or_recurse(argv[i], dee_action == dee_RECURSE, + only_one_at_top); + if (frc > 1) rc = frc; + else if (frc == 0 && rc == 1) rc = 0; + } + +EXIT: +if (pattern_list != NULL) + { + for (i = 0; i < pattern_count; i++) free(pattern_list[i]); + free(pattern_list); + } +if (hints_list != NULL) + { + for (i = 0; i < hint_count; i++) free(hints_list[i]); + free(hints_list); + } +return rc; + +EXIT2: +rc = 2; +goto EXIT; +} + +/* End of pcregrep */ ============================================================ --- pcre/pcreposix.c f6a92b5557f732f33174f3ab9ceb7bfb5b2de84c +++ pcre/pcreposix.c f6a92b5557f732f33174f3ab9ceb7bfb5b2de84c @@ -0,0 +1,339 @@ +/************************************************* +* 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) 1997-2008 University of Cambridge + +----------------------------------------------------------------------------- +Redistribution and use in source and binary forms, with or without +modification, are permitted provided that the following conditions are met: + + * Redistributions of source code must retain the above copyright notice, + this list of conditions and the following disclaimer. + + * Redistributions in binary form must reproduce the above copyright + notice, this list of conditions and the following disclaimer in the + documentation and/or other materials provided with the distribution. + + * Neither the name of the University of Cambridge nor the names of its + contributors may be used to endorse or promote products derived from + this software without specific prior written permission. + +THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" +AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE +IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE +ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE +LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR +CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF +SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS +INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN +CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) +ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE +POSSIBILITY OF SUCH DAMAGE. +----------------------------------------------------------------------------- +*/ + + +/* This module is a wrapper that provides a POSIX API to the underlying PCRE +functions. */ + + +#ifdef HAVE_CONFIG_H +#include "config.h" +#endif + + +/* Ensure that the PCREPOSIX_EXP_xxx macros are set appropriately for +compiling these functions. This must come before including pcreposix.h, where +they are set for an application (using these functions) if they have not +previously been set. */ + +#if defined(_WIN32) && !defined(PCRE_STATIC) +# define PCREPOSIX_EXP_DECL extern __declspec(dllexport) +# define PCREPOSIX_EXP_DEFN __declspec(dllexport) +#endif + +#include "pcre.h" +#include "pcre_internal.h" +#include "pcreposix.h" + + +/* Table to translate PCRE compile time error codes into POSIX error codes. */ + +static const int eint[] = { + 0, /* no error */ + REG_EESCAPE, /* \ at end of pattern */ + REG_EESCAPE, /* \c at end of pattern */ + REG_EESCAPE, /* unrecognized character follows \ */ + REG_BADBR, /* numbers out of order in {} quantifier */ + REG_BADBR, /* number too big in {} quantifier */ + REG_EBRACK, /* missing terminating ] for character class */ + REG_ECTYPE, /* invalid escape sequence in character class */ + REG_ERANGE, /* range out of order in character class */ + REG_BADRPT, /* nothing to repeat */ + REG_BADRPT, /* operand of unlimited repeat could match the empty string */ + REG_ASSERT, /* internal error: unexpected repeat */ + REG_BADPAT, /* unrecognized character after (? */ + REG_BADPAT, /* POSIX named classes are supported only within a class */ + REG_EPAREN, /* missing ) */ + REG_ESUBREG, /* reference to non-existent subpattern */ + REG_INVARG, /* erroffset passed as NULL */ + REG_INVARG, /* unknown option bit(s) set */ + REG_EPAREN, /* missing ) after comment */ + REG_ESIZE, /* parentheses nested too deeply */ + REG_ESIZE, /* regular expression too large */ + REG_ESPACE, /* failed to get memory */ + REG_EPAREN, /* unmatched brackets */ + REG_ASSERT, /* internal error: code overflow */ + REG_BADPAT, /* unrecognized character after (?< */ + REG_BADPAT, /* lookbehind assertion is not fixed length */ + REG_BADPAT, /* malformed number or name after (?( */ + REG_BADPAT, /* conditional group contains more than two branches */ + REG_BADPAT, /* assertion expected after (?( */ + REG_BADPAT, /* (?R or (?[+-]digits must be followed by ) */ + REG_ECTYPE, /* unknown POSIX class name */ + REG_BADPAT, /* POSIX collating elements are not supported */ + REG_INVARG, /* this version of PCRE is not compiled with PCRE_UTF8 support */ + REG_BADPAT, /* spare error */ + REG_BADPAT, /* character value in \x{...} sequence is too large */ + REG_BADPAT, /* invalid condition (?(0) */ + REG_BADPAT, /* \C not allowed in lookbehind assertion */ + REG_EESCAPE, /* PCRE does not support \L, \l, \N, \U, or \u */ + REG_BADPAT, /* number after (?C is > 255 */ + REG_BADPAT, /* closing ) for (?C expected */ + REG_BADPAT, /* recursive call could loop indefinitely */ + REG_BADPAT, /* unrecognized character after (?P */ + REG_BADPAT, /* syntax error in subpattern name (missing terminator) */ + REG_BADPAT, /* two named subpatterns have the same name */ + REG_BADPAT, /* invalid UTF-8 string */ + REG_BADPAT, /* support for \P, \p, and \X has not been compiled */ + REG_BADPAT, /* malformed \P or \p sequence */ + REG_BADPAT, /* unknown property name after \P or \p */ + REG_BADPAT, /* subpattern name is too long (maximum 32 characters) */ + REG_BADPAT, /* too many named subpatterns (maximum 10,000) */ + REG_BADPAT, /* repeated subpattern is too long */ + REG_BADPAT, /* octal value is greater than \377 (not in UTF-8 mode) */ + REG_BADPAT, /* internal error: overran compiling workspace */ + REG_BADPAT, /* internal error: previously-checked referenced subpattern not found */ + REG_BADPAT, /* DEFINE group contains more than one branch */ + REG_BADPAT, /* repeating a DEFINE group is not allowed */ + REG_INVARG, /* inconsistent NEWLINE options */ + REG_BADPAT, /* \g is not followed followed by an (optionally braced) non-zero number */ + REG_BADPAT, /* (?+ or (?- must be followed by a non-zero number */ + REG_BADPAT, /* number is too big */ + REG_BADPAT, /* subpattern name expected */ + REG_BADPAT /* digit expected after (?+ */ +}; + +/* Table of texts corresponding to POSIX error codes */ + +static const char *const pstring[] = { + "", /* Dummy for value 0 */ + "internal error", /* REG_ASSERT */ + "invalid repeat counts in {}", /* BADBR */ + "pattern error", /* BADPAT */ + "? * + invalid", /* BADRPT */ + "unbalanced {}", /* EBRACE */ + "unbalanced []", /* EBRACK */ + "collation error - not relevant", /* ECOLLATE */ + "bad class", /* ECTYPE */ + "bad escape sequence", /* EESCAPE */ + "empty expression", /* EMPTY */ + "unbalanced ()", /* EPAREN */ + "bad range inside []", /* ERANGE */ + "expression too big", /* ESIZE */ + "failed to get memory", /* ESPACE */ + "bad back reference", /* ESUBREG */ + "bad argument", /* INVARG */ + "match failed" /* NOMATCH */ +}; + + + + +/************************************************* +* Translate error code to string * +*************************************************/ + +PCREPOSIX_EXP_DEFN 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 * +*************************************************/ + +PCREPOSIX_EXP_DEFN 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 +*/ + +PCREPOSIX_EXP_DEFN int +regcomp(regex_t *preg, const char *pattern, int cflags) +{ +const char *errorptr; +int erroffset; +int errorcode; +int options = 0; + +if ((cflags & REG_ICASE) != 0) options |= PCRE_CASELESS; +if ((cflags & REG_NEWLINE) != 0) options |= PCRE_MULTILINE; +if ((cflags & REG_DOTALL) != 0) options |= PCRE_DOTALL; +if ((cflags & REG_NOSUB) != 0) options |= PCRE_NO_AUTO_CAPTURE; +if ((cflags & REG_UTF8) != 0) options |= PCRE_UTF8; + +preg->re_pcre = pcre_compile2(pattern, options, &errorcode, &errorptr, + &erroffset, NULL); +preg->re_erroffset = erroffset; + +if (preg->re_pcre == NULL) return eint[errorcode]; + +preg->re_nsub = pcre_info((const pcre *)preg->re_pcre, NULL, NULL); +return 0; +} + + + + +/************************************************* +* Match a regular expression * +*************************************************/ + +/* Unfortunately, PCRE requires 3 ints of working space for each captured +substring, so we have to get and release working store instead of just using +the POSIX structures as was done in earlier releases when PCRE needed only 2 +ints. However, if the number of possible capturing brackets is small, use a +block of store on the stack, to reduce the use of malloc/free. The threshold is +in a macro that can be changed at configure time. + +If REG_NOSUB was specified at compile time, the PCRE_NO_AUTO_CAPTURE flag will +be set. When this is the case, the nmatch and pmatch arguments are ignored, and +the only result is yes/no/error. */ + +PCREPOSIX_EXP_DEFN int +regexec(const regex_t *preg, const char *string, size_t nmatch, + regmatch_t pmatch[], int eflags) +{ +int rc; +int options = 0; +int *ovector = NULL; +int small_ovector[POSIX_MALLOC_THRESHOLD * 3]; +BOOL allocated_ovector = FALSE; +BOOL nosub = + (((const pcre *)preg->re_pcre)->options & PCRE_NO_AUTO_CAPTURE) != 0; + +if ((eflags & REG_NOTBOL) != 0) options |= PCRE_NOTBOL; +if ((eflags & REG_NOTEOL) != 0) options |= PCRE_NOTEOL; + +((regex_t *)preg)->re_erroffset = (size_t)(-1); /* Only has meaning after compile */ + +/* When no string data is being returned, ensure that nmatch is zero. +Otherwise, ensure the vector for holding the return data is large enough. */ + +if (nosub) nmatch = 0; + +else if (nmatch > 0) + { + if (nmatch <= POSIX_MALLOC_THRESHOLD) + { + ovector = &(small_ovector[0]); + } + else + { + if (nmatch > INT_MAX/(sizeof(int) * 3)) return REG_ESPACE; + ovector = (int *)malloc(sizeof(int) * nmatch * 3); + if (ovector == NULL) return REG_ESPACE; + allocated_ovector = TRUE; + } + } + +rc = pcre_exec((const pcre *)preg->re_pcre, NULL, string, (int)strlen(string), + 0, options, ovector, nmatch * 3); + +if (rc == 0) rc = nmatch; /* All captured slots were filled in */ + +if (rc >= 0) + { + size_t i; + if (!nosub) + { + for (i = 0; i < (size_t)rc; i++) + { + pmatch[i].rm_so = ovector[i*2]; + pmatch[i].rm_eo = ovector[i*2+1]; + } + if (allocated_ovector) free(ovector); + for (; i < nmatch; i++) pmatch[i].rm_so = pmatch[i].rm_eo = -1; + } + return 0; + } + +else + { + if (allocated_ovector) free(ovector); + switch(rc) + { + case PCRE_ERROR_NOMATCH: return REG_NOMATCH; + case PCRE_ERROR_NULL: return REG_INVARG; + case PCRE_ERROR_BADOPTION: return REG_INVARG; + case PCRE_ERROR_BADMAGIC: return REG_INVARG; + case PCRE_ERROR_UNKNOWN_NODE: return REG_ASSERT; + case PCRE_ERROR_NOMEMORY: return REG_ESPACE; + case PCRE_ERROR_MATCHLIMIT: return REG_ESPACE; + case PCRE_ERROR_BADUTF8: return REG_INVARG; + case PCRE_ERROR_BADUTF8_OFFSET: return REG_INVARG; + default: return REG_ASSERT; + } + } +} + +/* End of pcreposix.c */ ============================================================ --- pcre/pcreposix.h addb29678ba48228a35a1615fc20594a0491eb9b +++ pcre/pcreposix.h addb29678ba48228a35a1615fc20594a0491eb9b @@ -0,0 +1,142 @@ +/************************************************* +* Perl-Compatible Regular Expressions * +*************************************************/ + +#ifndef _PCREPOSIX_H +#define _PCREPOSIX_H + +/* This is the header for the POSIX wrapper interface to the PCRE Perl- +Compatible Regular Expression library. It defines the things POSIX says should +be there. I hope. + + Copyright (c) 1997-2008 University of Cambridge + +----------------------------------------------------------------------------- +Redistribution and use in source and binary forms, with or without +modification, are permitted provided that the following conditions are met: + + * Redistributions of source code must retain the above copyright notice, + this list of conditions and the following disclaimer. + + * Redistributions in binary form must reproduce the above copyright + notice, this list of conditions and the following disclaimer in the + documentation and/or other materials provided with the distribution. + + * Neither the name of the University of Cambridge nor the names of its + contributors may be used to endorse or promote products derived from + this software without specific prior written permission. + +THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" +AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE +IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE +ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE +LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR +CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF +SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS +INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN +CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) +ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE +POSSIBILITY OF SUCH DAMAGE. +----------------------------------------------------------------------------- +*/ + +/* Have to include stdlib.h in order to ensure that size_t is defined. */ + +#include + +/* Allow for C++ users */ + +#ifdef __cplusplus +extern "C" { +#endif + +/* Options, mostly defined by POSIX, but with a couple of extras. */ + +#define REG_ICASE 0x0001 +#define REG_NEWLINE 0x0002 +#define REG_NOTBOL 0x0004 +#define REG_NOTEOL 0x0008 +#define REG_DOTALL 0x0010 /* NOT defined by POSIX. */ +#define REG_NOSUB 0x0020 +#define REG_UTF8 0x0040 /* NOT defined by POSIX. */ + +/* This is not used by PCRE, but by defining it we make it easier +to slot PCRE into existing programs that make POSIX calls. */ + +#define REG_EXTENDED 0 + +/* Error values. Not all these are relevant or used by the wrapper. */ + +enum { + REG_ASSERT = 1, /* internal error ? */ + REG_BADBR, /* invalid repeat counts in {} */ + REG_BADPAT, /* pattern error */ + REG_BADRPT, /* ? * + invalid */ + REG_EBRACE, /* unbalanced {} */ + REG_EBRACK, /* unbalanced [] */ + REG_ECOLLATE, /* collation error - not relevant */ + REG_ECTYPE, /* bad class */ + REG_EESCAPE, /* bad escape sequence */ + REG_EMPTY, /* empty expression */ + REG_EPAREN, /* unbalanced () */ + REG_ERANGE, /* bad range inside [] */ + REG_ESIZE, /* expression too big */ + REG_ESPACE, /* failed to get memory */ + REG_ESUBREG, /* bad back reference */ + REG_INVARG, /* bad argument */ + REG_NOMATCH /* match failed */ +}; + + +/* The structure representing a compiled regular expression. */ + +typedef struct { + void *re_pcre; + size_t re_nsub; + size_t re_erroffset; +} regex_t; + +/* The structure in which a captured offset is returned. */ + +typedef int regoff_t; + +typedef struct { + regoff_t rm_so; + regoff_t rm_eo; +} regmatch_t; + +/* When an application links to a PCRE DLL in Windows, the symbols that are +imported have to be identified as such. When building PCRE, the appropriate +export settings are needed, and are set in pcreposix.c before including this +file. */ + +#if defined(_WIN32) && !defined(PCRE_STATIC) && !defined(PCREPOSIX_EXP_DECL) +# define PCREPOSIX_EXP_DECL extern __declspec(dllimport) +# define PCREPOSIX_EXP_DEFN __declspec(dllimport) +#endif + +/* By default, we use the standard "extern" declarations. */ + +#ifndef PCREPOSIX_EXP_DECL +# ifdef __cplusplus +# define PCREPOSIX_EXP_DECL extern "C" +# define PCREPOSIX_EXP_DEFN extern "C" +# else +# define PCREPOSIX_EXP_DECL extern +# define PCREPOSIX_EXP_DEFN extern +# endif +#endif + +/* The functions */ + +PCREPOSIX_EXP_DECL int regcomp(regex_t *, const char *, int); +PCREPOSIX_EXP_DECL int regexec(const regex_t *, const char *, size_t, + regmatch_t *, int); +PCREPOSIX_EXP_DECL size_t regerror(int, const regex_t *, char *, size_t); +PCREPOSIX_EXP_DECL void regfree(regex_t *); + +#ifdef __cplusplus +} /* extern "C" */ +#endif + +#endif /* End of pcreposix.h */ ============================================================ --- pcre/pcretest.c 7e8d2a6a44eabedd1d7d38c1ea84bb569a3aef29 +++ pcre/pcretest.c 7e8d2a6a44eabedd1d7d38c1ea84bb569a3aef29 @@ -0,0 +1,2435 @@ +/************************************************* +* PCRE testing program * +*************************************************/ + +/* This program was hacked up as a tester for PCRE. I really should have +written it more tidily in the first place. Will I ever learn? It has grown and +been extended and consequently is now rather, er, *very* untidy in places. + +----------------------------------------------------------------------------- +Redistribution and use in source and binary forms, with or without +modification, are permitted provided that the following conditions are met: + + * Redistributions of source code must retain the above copyright notice, + this list of conditions and the following disclaimer. + + * Redistributions in binary form must reproduce the above copyright + notice, this list of conditions and the following disclaimer in the + documentation and/or other materials provided with the distribution. + + * Neither the name of the University of Cambridge nor the names of its + contributors may be used to endorse or promote products derived from + this software without specific prior written permission. + +THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" +AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE +IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE +ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE +LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR +CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF +SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS +INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN +CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) +ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE +POSSIBILITY OF SUCH DAMAGE. +----------------------------------------------------------------------------- +*/ + + +#ifdef HAVE_CONFIG_H +#include "config.h" +#endif + +#include +#include +#include +#include +#include +#include +#include + +#ifdef SUPPORT_LIBREADLINE +#include +#include +#include +#endif + + +/* A number of things vary for Windows builds. Originally, pcretest opened its +input and output without "b"; then I was told that "b" was needed in some +environments, so it was added for release 5.0 to both the input and output. (It +makes no difference on Unix-like systems.) Later I was told that it is wrong +for the input on Windows. I've now abstracted the modes into two macros that +are set here, to make it easier to fiddle with them, and removed "b" from the +input mode under Windows. */ + +#if defined(_WIN32) || defined(WIN32) +#include /* For _setmode() */ +#include /* For _O_BINARY */ +#define INPUT_MODE "r" +#define OUTPUT_MODE "wb" + +#else +#include /* These two includes are needed */ +#include /* for setrlimit(). */ +#define INPUT_MODE "rb" +#define OUTPUT_MODE "wb" +#endif + + +/* We have to include pcre_internal.h because we need the internal info for +displaying the results of pcre_study() and we also need to know about the +internal macros, structures, and other internal data values; pcretest has +"inside information" compared to a program that strictly follows the PCRE API. + +Although pcre_internal.h does itself include pcre.h, we explicitly include it +here before pcre_internal.h so that the PCRE_EXP_xxx macros get set +appropriately for an application, not for building PCRE. */ + +#include "pcre.h" +#include "pcre_internal.h" + +/* We need access to the data tables that PCRE uses. So as not to have to keep +two copies, we include the source file here, changing the names of the external +symbols to prevent clashes. */ + +#define _pcre_utf8_table1 utf8_table1 +#define _pcre_utf8_table1_size utf8_table1_size +#define _pcre_utf8_table2 utf8_table2 +#define _pcre_utf8_table3 utf8_table3 +#define _pcre_utf8_table4 utf8_table4 +#define _pcre_utt utt +#define _pcre_utt_size utt_size +#define _pcre_utt_names utt_names +#define _pcre_OP_lengths OP_lengths + +#include "pcre_tables.c" + +/* We also need the pcre_printint() function for printing out compiled +patterns. This function is in a separate file so that it can be included in +pcre_compile.c when that module is compiled with debugging enabled. + +The definition of the macro PRINTABLE, which determines whether to print an +output character as-is or as a hex value when showing compiled patterns, is +contained in this file. We uses it here also, in cases when the locale has not +been explicitly changed, so as to get consistent output from systems that +differ in their output from isprint() even in the "C" locale. */ + +#include "pcre_printint.src" + +#define PRINTHEX(c) (locale_set? isprint(c) : PRINTABLE(c)) + + +/* It is possible to compile this test program without including support for +testing the POSIX interface, though this is not available via the standard +Makefile. */ + +#if !defined NOPOSIX +#include "pcreposix.h" +#endif + +/* It is also possible, for the benefit of the version currently imported into +Exim, to build pcretest without support for UTF8 (define NOUTF8), without the +interface to the DFA matcher (NODFA), and without the doublecheck of the old +"info" function (define NOINFOCHECK). In fact, we automatically cut out the +UTF8 support if PCRE is built without it. */ + +#ifndef SUPPORT_UTF8 +#ifndef NOUTF8 +#define NOUTF8 +#endif +#endif + + +/* Other parameters */ + +#ifndef CLOCKS_PER_SEC +#ifdef CLK_TCK +#define CLOCKS_PER_SEC CLK_TCK +#else +#define CLOCKS_PER_SEC 100 +#endif +#endif + +/* This is the default loop count for timing. */ + +#define LOOPREPEAT 500000 + +/* Static variables */ + +static FILE *outfile; +static int log_store = 0; +static int callout_count; +static int callout_extra; +static int callout_fail_count; +static int callout_fail_id; +static int debug_lengths; +static int first_callout; +static int locale_set = 0; +static int show_malloc; +static int use_utf8; +static size_t gotten_store; + +/* The buffers grow automatically if very long input lines are encountered. */ + +static int buffer_size = 50000; +static uschar *buffer = NULL; +static uschar *dbuffer = NULL; +static uschar *pbuffer = NULL; + + + +/************************************************* +* Read or extend an input line * +*************************************************/ + +/* Input lines are read into buffer, but both patterns and data lines can be +continued over multiple input lines. In addition, if the buffer fills up, we +want to automatically expand it so as to be able to handle extremely large +lines that are needed for certain stress tests. When the input buffer is +expanded, the other two buffers must also be expanded likewise, and the +contents of pbuffer, which are a copy of the input for callouts, must be +preserved (for when expansion happens for a data line). This is not the most +optimal way of handling this, but hey, this is just a test program! + +Arguments: + f the file to read + start where in buffer to start (this *must* be within buffer) + prompt for stdin or readline() + +Returns: pointer to the start of new data + could be a copy of start, or could be moved + NULL if no data read and EOF reached +*/ + +static uschar * +extend_inputline(FILE *f, uschar *start, const char *prompt) +{ +uschar *here = start; + +for (;;) + { + int rlen = buffer_size - (here - buffer); + + if (rlen > 1000) + { + int dlen; + + /* If libreadline support is required, use readline() to read a line if the + input is a terminal. Note that readline() removes the trailing newline, so + we must put it back again, to be compatible with fgets(). */ + +#ifdef SUPPORT_LIBREADLINE + if (isatty(fileno(f))) + { + size_t len; + char *s = readline(prompt); + if (s == NULL) return (here == start)? NULL : start; + len = strlen(s); + if (len > 0) add_history(s); + if (len > rlen - 1) len = rlen - 1; + memcpy(here, s, len); + here[len] = '\n'; + here[len+1] = 0; + free(s); + } + else +#endif + + /* Read the next line by normal means, prompting if the file is stdin. */ + + { + if (f == stdin) printf(prompt); + if (fgets((char *)here, rlen, f) == NULL) + return (here == start)? NULL : start; + } + + dlen = (int)strlen((char *)here); + if (dlen > 0 && here[dlen - 1] == '\n') return start; + here += dlen; + } + + else + { + int new_buffer_size = 2*buffer_size; + uschar *new_buffer = (unsigned char *)malloc(new_buffer_size); + uschar *new_dbuffer = (unsigned char *)malloc(new_buffer_size); + uschar *new_pbuffer = (unsigned char *)malloc(new_buffer_size); + + if (new_buffer == NULL || new_dbuffer == NULL || new_pbuffer == NULL) + { + fprintf(stderr, "pcretest: malloc(%d) failed\n", new_buffer_size); + exit(1); + } + + memcpy(new_buffer, buffer, buffer_size); + memcpy(new_pbuffer, pbuffer, buffer_size); + + buffer_size = new_buffer_size; + + start = new_buffer + (start - buffer); + here = new_buffer + (here - buffer); + + free(buffer); + free(dbuffer); + free(pbuffer); + + buffer = new_buffer; + dbuffer = new_dbuffer; + pbuffer = new_pbuffer; + } + } + +return NULL; /* Control never gets here */ +} + + + + + + + +/************************************************* +* Read number from string * +*************************************************/ + +/* We don't use strtoul() because SunOS4 doesn't have it. Rather than mess +around with conditional compilation, just do the job by hand. It is only used +for unpicking arguments, so just keep it simple. + +Arguments: + str string to be converted + endptr where to put the end pointer + +Returns: the unsigned long +*/ + +static int +get_value(unsigned char *str, unsigned char **endptr) +{ +int result = 0; +while(*str != 0 && isspace(*str)) str++; +while (isdigit(*str)) result = result * 10 + (int)(*str++ - '0'); +*endptr = str; +return(result); +} + + + + +/************************************************* +* Convert UTF-8 string to value * +*************************************************/ + +/* This function takes one or more bytes that represents a UTF-8 character, +and returns the value of the character. + +Argument: + utf8bytes a pointer to the byte vector + vptr a pointer to an int to receive the value + +Returns: > 0 => the number of bytes consumed + -6 to 0 => malformed UTF-8 character at offset = (-return) +*/ + +#if !defined NOUTF8 + +static int +utf82ord(unsigned char *utf8bytes, int *vptr) +{ +int c = *utf8bytes++; +int d = c; +int i, j, s; + +for (i = -1; i < 6; i++) /* i is number of additional bytes */ + { + if ((d & 0x80) == 0) break; + d <<= 1; + } + +if (i == -1) { *vptr = c; return 1; } /* ascii character */ +if (i == 0 || i == 6) return 0; /* invalid UTF-8 */ + +/* i now has a value in the range 1-5 */ + +s = 6*i; +d = (c & utf8_table3[i]) << s; + +for (j = 0; j < i; j++) + { + c = *utf8bytes++; + if ((c & 0xc0) != 0x80) return -(j+1); + s -= 6; + d |= (c & 0x3f) << s; + } + +/* Check that encoding was the correct unique one */ + +for (j = 0; j < utf8_table1_size; j++) + if (d <= utf8_table1[j]) break; +if (j != i) return -(i+1); + +/* Valid value */ + +*vptr = d; +return i+1; +} + +#endif + + + +/************************************************* +* Convert character value to UTF-8 * +*************************************************/ + +/* This function takes an integer value in the range 0 - 0x7fffffff +and encodes it as a UTF-8 character in 0 to 6 bytes. + +Arguments: + cvalue the character value + utf8bytes pointer to buffer for result - at least 6 bytes long + +Returns: number of characters placed in the buffer +*/ + +#if !defined NOUTF8 + +static int +ord2utf8(int cvalue, uschar *utf8bytes) +{ +register int i, j; +for (i = 0; i < utf8_table1_size; i++) + if (cvalue <= utf8_table1[i]) break; +utf8bytes += i; +for (j = i; j > 0; j--) + { + *utf8bytes-- = 0x80 | (cvalue & 0x3f); + cvalue >>= 6; + } +*utf8bytes = utf8_table2[i] | cvalue; +return i + 1; +} + +#endif + + + +/************************************************* +* Print character string * +*************************************************/ + +/* Character string printing function. Must handle UTF-8 strings in utf8 +mode. Yields number of characters printed. If handed a NULL file, just counts +chars without printing. */ + +static int pchars(unsigned char *p, int length, FILE *f) +{ +int c = 0; +int yield = 0; + +while (length-- > 0) + { +#if !defined NOUTF8 + if (use_utf8) + { + int rc = utf82ord(p, &c); + + if (rc > 0 && rc <= length + 1) /* Mustn't run over the end */ + { + length -= rc - 1; + p += rc; + if (PRINTHEX(c)) + { + if (f != NULL) fprintf(f, "%c", c); + yield++; + } + else + { + int n = 4; + if (f != NULL) fprintf(f, "\\x{%02x}", c); + yield += (n <= 0x000000ff)? 2 : + (n <= 0x00000fff)? 3 : + (n <= 0x0000ffff)? 4 : + (n <= 0x000fffff)? 5 : 6; + } + continue; + } + } +#endif + + /* Not UTF-8, or malformed UTF-8 */ + + c = *p++; + if (PRINTHEX(c)) + { + if (f != NULL) fprintf(f, "%c", c); + yield++; + } + else + { + if (f != NULL) fprintf(f, "\\x%02x", c); + yield += 4; + } + } + +return yield; +} + + + +/************************************************* +* Callout function * +*************************************************/ + +/* Called from PCRE as a result of the (?C) item. We print out where we are in +the match. Yield zero unless more callouts than the fail count, or the callout +data is not zero. */ + +static int callout(pcre_callout_block *cb) +{ +FILE *f = (first_callout | callout_extra)? outfile : NULL; +int i, pre_start, post_start, subject_length; + +if (callout_extra) + { + fprintf(f, "Callout %d: last capture = %d\n", + cb->callout_number, cb->capture_last); + + for (i = 0; i < cb->capture_top * 2; i += 2) + { + if (cb->offset_vector[i] < 0) + fprintf(f, "%2d: \n", i/2); + else + { + fprintf(f, "%2d: ", i/2); + (void)pchars((unsigned char *)cb->subject + cb->offset_vector[i], + cb->offset_vector[i+1] - cb->offset_vector[i], f); + fprintf(f, "\n"); + } + } + } + +/* Re-print the subject in canonical form, the first time or if giving full +datails. On subsequent calls in the same match, we use pchars just to find the +printed lengths of the substrings. */ + +if (f != NULL) fprintf(f, "--->"); + +pre_start = pchars((unsigned char *)cb->subject, cb->start_match, f); +post_start = pchars((unsigned char *)(cb->subject + cb->start_match), + cb->current_position - cb->start_match, f); + +subject_length = pchars((unsigned char *)cb->subject, cb->subject_length, NULL); + +(void)pchars((unsigned char *)(cb->subject + cb->current_position), + cb->subject_length - cb->current_position, f); + +if (f != NULL) fprintf(f, "\n"); + +/* Always print appropriate indicators, with callout number if not already +shown. For automatic callouts, show the pattern offset. */ + +if (cb->callout_number == 255) + { + fprintf(outfile, "%+3d ", cb->pattern_position); + if (cb->pattern_position > 99) fprintf(outfile, "\n "); + } +else + { + if (callout_extra) fprintf(outfile, " "); + else fprintf(outfile, "%3d ", cb->callout_number); + } + +for (i = 0; i < pre_start; i++) fprintf(outfile, " "); +fprintf(outfile, "^"); + +if (post_start > 0) + { + for (i = 0; i < post_start - 1; i++) fprintf(outfile, " "); + fprintf(outfile, "^"); + } + +for (i = 0; i < subject_length - pre_start - post_start + 4; i++) + fprintf(outfile, " "); + +fprintf(outfile, "%.*s", (cb->next_item_length == 0)? 1 : cb->next_item_length, + pbuffer + cb->pattern_position); + +fprintf(outfile, "\n"); +first_callout = 0; + +if (cb->callout_data != NULL) + { + int callout_data = *((int *)(cb->callout_data)); + if (callout_data != 0) + { + fprintf(outfile, "Callout data = %d\n", callout_data); + return callout_data; + } + } + +return (cb->callout_number != callout_fail_id)? 0 : + (++callout_count >= callout_fail_count)? 1 : 0; +} + + +/************************************************* +* Local malloc functions * +*************************************************/ + +/* Alternative malloc function, to test functionality and show the size of the +compiled re. */ + +static void *new_malloc(size_t size) +{ +void *block = malloc(size); +gotten_store = size; +if (show_malloc) + fprintf(outfile, "malloc %3d %p\n", (int)size, block); +return block; +} + +static void new_free(void *block) +{ +if (show_malloc) + fprintf(outfile, "free %p\n", block); +free(block); +} + + +/* For recursion malloc/free, to test stacking calls */ + +static void *stack_malloc(size_t size) +{ +void *block = malloc(size); +if (show_malloc) + fprintf(outfile, "stack_malloc %3d %p\n", (int)size, block); +return block; +} + +static void stack_free(void *block) +{ +if (show_malloc) + fprintf(outfile, "stack_free %p\n", block); +free(block); +} + + +/************************************************* +* Call pcre_fullinfo() * +*************************************************/ + +/* Get one piece of information from the pcre_fullinfo() function */ + +static void new_info(pcre *re, pcre_extra *study, int option, void *ptr) +{ +int rc; +if ((rc = pcre_fullinfo(re, study, option, ptr)) < 0) + fprintf(outfile, "Error %d from pcre_fullinfo(%d)\n", rc, option); +} + + + +/************************************************* +* Byte flipping function * +*************************************************/ + +static unsigned long int +byteflip(unsigned long int value, int n) +{ +if (n == 2) return ((value & 0x00ff) << 8) | ((value & 0xff00) >> 8); +return ((value & 0x000000ff) << 24) | + ((value & 0x0000ff00) << 8) | + ((value & 0x00ff0000) >> 8) | + ((value & 0xff000000) >> 24); +} + + + + +/************************************************* +* Check match or recursion limit * +*************************************************/ + +static int +check_match_limit(pcre *re, pcre_extra *extra, uschar *bptr, int len, + int start_offset, int options, int *use_offsets, int use_size_offsets, + int flag, unsigned long int *limit, int errnumber, const char *msg) +{ +int count; +int min = 0; +int mid = 64; +int max = -1; + +extra->flags |= flag; + +for (;;) + { + *limit = mid; + + count = pcre_exec(re, extra, (char *)bptr, len, start_offset, options, + use_offsets, use_size_offsets); + + if (count == errnumber) + { + /* fprintf(outfile, "Testing %s limit = %d\n", msg, mid); */ + min = mid; + mid = (mid == max - 1)? max : (max > 0)? (min + max)/2 : mid*2; + } + + else if (count >= 0 || count == PCRE_ERROR_NOMATCH || + count == PCRE_ERROR_PARTIAL) + { + if (mid == min + 1) + { + fprintf(outfile, "Minimum %s limit = %d\n", msg, mid); + break; + } + /* fprintf(outfile, "Testing %s limit = %d\n", msg, mid); */ + max = mid; + mid = (min + mid)/2; + } + else break; /* Some other error */ + } + +extra->flags &= ~flag; +return count; +} + + + +/************************************************* +* Case-independent strncmp() function * +*************************************************/ + +/* +Arguments: + s first string + t second string + n number of characters to compare + +Returns: < 0, = 0, or > 0, according to the comparison +*/ + +static int +strncmpic(uschar *s, uschar *t, int n) +{ +while (n--) + { + int c = tolower(*s++) - tolower(*t++); + if (c) return c; + } +return 0; +} + + + +/************************************************* +* Check newline indicator * +*************************************************/ + +/* This is used both at compile and run-time to check for escapes, where +xxx is LF, CR, CRLF, ANYCRLF, or ANY. Print a message and return 0 if there is +no match. + +Arguments: + p points after the leading '<' + f file for error message + +Returns: appropriate PCRE_NEWLINE_xxx flags, or 0 +*/ + +static int +check_newline(uschar *p, FILE *f) +{ +if (strncmpic(p, (uschar *)"cr>", 3) == 0) return PCRE_NEWLINE_CR; +if (strncmpic(p, (uschar *)"lf>", 3) == 0) return PCRE_NEWLINE_LF; +if (strncmpic(p, (uschar *)"crlf>", 5) == 0) return PCRE_NEWLINE_CRLF; +if (strncmpic(p, (uschar *)"anycrlf>", 8) == 0) return PCRE_NEWLINE_ANYCRLF; +if (strncmpic(p, (uschar *)"any>", 4) == 0) return PCRE_NEWLINE_ANY; +if (strncmpic(p, (uschar *)"bsr_anycrlf>", 12) == 0) return PCRE_BSR_ANYCRLF; +if (strncmpic(p, (uschar *)"bsr_unicode>", 12) == 0) return PCRE_BSR_UNICODE; +fprintf(f, "Unknown newline type at: <%s\n", p); +return 0; +} + + + +/************************************************* +* Usage function * +*************************************************/ + +static void +usage(void) +{ +printf("Usage: pcretest [options] [ []]\n\n"); +printf("Input and output default to stdin and stdout.\n"); +#ifdef SUPPORT_LIBREADLINE +printf("If input is a terminal, readline() is used to read from it.\n"); +#else +printf("This version of pcretest is not linked with readline().\n"); +#endif +printf("\nOptions:\n"); +printf(" -b show compiled code (bytecode)\n"); +printf(" -C show PCRE compile-time options and exit\n"); +printf(" -d debug: show compiled code and information (-b and -i)\n"); +#if !defined NODFA +printf(" -dfa force DFA matching for all subjects\n"); +#endif +printf(" -help show usage information\n"); +printf(" -i show information about compiled patterns\n" + " -m output memory used information\n" + " -o set size of offsets vector to \n"); +#if !defined NOPOSIX +printf(" -p use POSIX interface\n"); +#endif +printf(" -q quiet: do not output PCRE version number at start\n"); +printf(" -S set stack size to megabytes\n"); +printf(" -s output store (memory) used information\n" + " -t time compilation and execution\n"); +printf(" -t time compilation and execution, repeating times\n"); +printf(" -tm time execution (matching) only\n"); +printf(" -tm time execution (matching) only, repeating times\n"); +} + + + +/************************************************* +* Main Program * +*************************************************/ + +/* Read lines from named file or stdin and write to named file or stdout; lines +consist of a regular expression, in delimiters and optionally followed by +options, followed by a set of test data, terminated by an empty line. */ + +int main(int argc, char **argv) +{ +FILE *infile = stdin; +int options = 0; +int study_options = 0; +int op = 1; +int timeit = 0; +int timeitm = 0; +int showinfo = 0; +int showstore = 0; +int quiet = 0; +int size_offsets = 45; +int size_offsets_max; +int *offsets = NULL; +#if !defined NOPOSIX +int posix = 0; +#endif +int debug = 0; +int done = 0; +int all_use_dfa = 0; +int yield = 0; +int stack_size; + +/* These vectors store, end-to-end, a list of captured substring names. Assume +that 1024 is plenty long enough for the few names we'll be testing. */ + +uschar copynames[1024]; +uschar getnames[1024]; + +uschar *copynamesptr; +uschar *getnamesptr; + +/* Get buffers from malloc() so that Electric Fence will check their misuse +when I am debugging. They grow automatically when very long lines are read. */ + +buffer = (unsigned char *)malloc(buffer_size); +dbuffer = (unsigned char *)malloc(buffer_size); +pbuffer = (unsigned char *)malloc(buffer_size); + +/* The outfile variable is static so that new_malloc can use it. */ + +outfile = stdout; + +/* The following _setmode() stuff is some Windows magic that tells its runtime +library to translate CRLF into a single LF character. At least, that's what +I've been told: never having used Windows I take this all on trust. Originally +it set 0x8000, but then I was advised that _O_BINARY was better. */ + +#if defined(_WIN32) || defined(WIN32) +_setmode( _fileno( stdout ), _O_BINARY ); +#endif + +/* Scan options */ + +while (argc > 1 && argv[op][0] == '-') + { + unsigned char *endptr; + + if (strcmp(argv[op], "-s") == 0 || strcmp(argv[op], "-m") == 0) + showstore = 1; + else if (strcmp(argv[op], "-q") == 0) quiet = 1; + else if (strcmp(argv[op], "-b") == 0) debug = 1; + else if (strcmp(argv[op], "-i") == 0) showinfo = 1; + else if (strcmp(argv[op], "-d") == 0) showinfo = debug = 1; +#if !defined NODFA + else if (strcmp(argv[op], "-dfa") == 0) all_use_dfa = 1; +#endif + else if (strcmp(argv[op], "-o") == 0 && argc > 2 && + ((size_offsets = get_value((unsigned char *)argv[op+1], &endptr)), + *endptr == 0)) + { + op++; + argc--; + } + else if (strcmp(argv[op], "-t") == 0 || strcmp(argv[op], "-tm") == 0) + { + int both = argv[op][2] == 0; + int temp; + if (argc > 2 && (temp = get_value((unsigned char *)argv[op+1], &endptr), + *endptr == 0)) + { + timeitm = temp; + op++; + argc--; + } + else timeitm = LOOPREPEAT; + if (both) timeit = timeitm; + } + else if (strcmp(argv[op], "-S") == 0 && argc > 2 && + ((stack_size = get_value((unsigned char *)argv[op+1], &endptr)), + *endptr == 0)) + { +#if defined(_WIN32) || defined(WIN32) + printf("PCRE: -S not supported on this OS\n"); + exit(1); +#else + int rc; + struct rlimit rlim; + getrlimit(RLIMIT_STACK, &rlim); + rlim.rlim_cur = stack_size * 1024 * 1024; + rc = setrlimit(RLIMIT_STACK, &rlim); + if (rc != 0) + { + printf("PCRE: setrlimit() failed with error %d\n", rc); + exit(1); + } + op++; + argc--; +#endif + } +#if !defined NOPOSIX + else if (strcmp(argv[op], "-p") == 0) posix = 1; +#endif + else if (strcmp(argv[op], "-C") == 0) + { + int rc; + printf("PCRE version %s\n", pcre_version()); + printf("Compiled with\n"); + (void)pcre_config(PCRE_CONFIG_UTF8, &rc); + printf(" %sUTF-8 support\n", rc? "" : "No "); + (void)pcre_config(PCRE_CONFIG_UNICODE_PROPERTIES, &rc); + printf(" %sUnicode properties support\n", rc? "" : "No "); + (void)pcre_config(PCRE_CONFIG_NEWLINE, &rc); + printf(" Newline sequence is %s\n", (rc == '\r')? "CR" : + (rc == '\n')? "LF" : (rc == ('\r'<<8 | '\n'))? "CRLF" : + (rc == -2)? "ANYCRLF" : + (rc == -1)? "ANY" : "???"); + (void)pcre_config(PCRE_CONFIG_BSR, &rc); + printf(" \\R matches %s\n", rc? "CR, LF, or CRLF only" : + "all Unicode newlines"); + (void)pcre_config(PCRE_CONFIG_LINK_SIZE, &rc); + printf(" Internal link size = %d\n", rc); + (void)pcre_config(PCRE_CONFIG_POSIX_MALLOC_THRESHOLD, &rc); + printf(" POSIX malloc threshold = %d\n", rc); + (void)pcre_config(PCRE_CONFIG_MATCH_LIMIT, &rc); + printf(" Default match limit = %d\n", rc); + (void)pcre_config(PCRE_CONFIG_MATCH_LIMIT_RECURSION, &rc); + printf(" Default recursion depth limit = %d\n", rc); + (void)pcre_config(PCRE_CONFIG_STACKRECURSE, &rc); + printf(" Match recursion uses %s\n", rc? "stack" : "heap"); + goto EXIT; + } + else if (strcmp(argv[op], "-help") == 0 || + strcmp(argv[op], "--help") == 0) + { + usage(); + goto EXIT; + } + else + { + printf("** Unknown or malformed option %s\n", argv[op]); + usage(); + yield = 1; + goto EXIT; + } + op++; + argc--; + } + +/* Get the store for the offsets vector, and remember what it was */ + +size_offsets_max = size_offsets; +offsets = (int *)malloc(size_offsets_max * sizeof(int)); +if (offsets == NULL) + { + printf("** Failed to get %d bytes of memory for offsets vector\n", + (int)(size_offsets_max * sizeof(int))); + yield = 1; + goto EXIT; + } + +/* Sort out the input and output files */ + +if (argc > 1) + { + infile = fopen(argv[op], INPUT_MODE); + if (infile == NULL) + { + printf("** Failed to open %s\n", argv[op]); + yield = 1; + goto EXIT; + } + } + +if (argc > 2) + { + outfile = fopen(argv[op+1], OUTPUT_MODE); + if (outfile == NULL) + { + printf("** Failed to open %s\n", argv[op+1]); + yield = 1; + goto EXIT; + } + } + +/* Set alternative malloc function */ + +pcre_malloc = new_malloc; +pcre_free = new_free; +pcre_stack_malloc = stack_malloc; +pcre_stack_free = stack_free; + +/* Heading line unless quiet, then prompt for first regex if stdin */ + +if (!quiet) fprintf(outfile, "PCRE version %s\n\n", pcre_version()); + +/* Main loop */ + +while (!done) + { + pcre *re = NULL; + pcre_extra *extra = NULL; + +#if !defined NOPOSIX /* There are still compilers that require no indent */ + regex_t preg; + int do_posix = 0; +#endif + + const char *error; + unsigned char *p, *pp, *ppp; + unsigned char *to_file = NULL; + const unsigned char *tables = NULL; + unsigned long int true_size, true_study_size = 0; + size_t size, regex_gotten_store; + int do_study = 0; + int do_debug = debug; + int do_G = 0; + int do_g = 0; + int do_showinfo = showinfo; + int do_showrest = 0; + int do_flip = 0; + int erroroffset, len, delimiter, poffset; + + use_utf8 = 0; + debug_lengths = 1; + + if (extend_inputline(infile, buffer, " re> ") == NULL) break; + if (infile != stdin) fprintf(outfile, "%s", (char *)buffer); + fflush(outfile); + + p = buffer; + while (isspace(*p)) p++; + if (*p == 0) continue; + + /* See if the pattern is to be loaded pre-compiled from a file. */ + + if (*p == '<' && strchr((char *)(p+1), '<') == NULL) + { + unsigned long int magic, get_options; + uschar sbuf[8]; + FILE *f; + + p++; + pp = p + (int)strlen((char *)p); + while (isspace(pp[-1])) pp--; + *pp = 0; + + f = fopen((char *)p, "rb"); + if (f == NULL) + { + fprintf(outfile, "Failed to open %s: %s\n", p, strerror(errno)); + continue; + } + + if (fread(sbuf, 1, 8, f) != 8) goto FAIL_READ; + + true_size = + (sbuf[0] << 24) | (sbuf[1] << 16) | (sbuf[2] << 8) | sbuf[3]; + true_study_size = + (sbuf[4] << 24) | (sbuf[5] << 16) | (sbuf[6] << 8) | sbuf[7]; + + re = (real_pcre *)new_malloc(true_size); + regex_gotten_store = gotten_store; + + if (fread(re, 1, true_size, f) != true_size) goto FAIL_READ; + + magic = ((real_pcre *)re)->magic_number; + if (magic != MAGIC_NUMBER) + { + if (byteflip(magic, sizeof(magic)) == MAGIC_NUMBER) + { + do_flip = 1; + } + else + { + fprintf(outfile, "Data in %s is not a compiled PCRE regex\n", p); + fclose(f); + continue; + } + } + + fprintf(outfile, "Compiled regex%s loaded from %s\n", + do_flip? " (byte-inverted)" : "", p); + + /* Need to know if UTF-8 for printing data strings */ + + new_info(re, NULL, PCRE_INFO_OPTIONS, &get_options); + use_utf8 = (get_options & PCRE_UTF8) != 0; + + /* Now see if there is any following study data */ + + if (true_study_size != 0) + { + pcre_study_data *psd; + + extra = (pcre_extra *)new_malloc(sizeof(pcre_extra) + true_study_size); + extra->flags = PCRE_EXTRA_STUDY_DATA; + + psd = (pcre_study_data *)(((char *)extra) + sizeof(pcre_extra)); + extra->study_data = psd; + + if (fread(psd, 1, true_study_size, f) != true_study_size) + { + FAIL_READ: + fprintf(outfile, "Failed to read data from %s\n", p); + if (extra != NULL) new_free(extra); + if (re != NULL) new_free(re); + fclose(f); + continue; + } + fprintf(outfile, "Study data loaded from %s\n", p); + do_study = 1; /* To get the data output if requested */ + } + else fprintf(outfile, "No study data\n"); + + fclose(f); + goto SHOW_INFO; + } + + /* In-line pattern (the usual case). Get the delimiter and seek the end of + the pattern; if is isn't complete, read more. */ + + delimiter = *p++; + + if (isalnum(delimiter) || delimiter == '\\') + { + fprintf(outfile, "** Delimiter must not be alphanumeric or \\\n"); + goto SKIP_DATA; + } + + pp = p; + poffset = p - buffer; + + for(;;) + { + while (*pp != 0) + { + if (*pp == '\\' && pp[1] != 0) pp++; + else if (*pp == delimiter) break; + pp++; + } + if (*pp != 0) break; + if ((pp = extend_inputline(infile, pp, " > ")) == NULL) + { + fprintf(outfile, "** Unexpected EOF\n"); + done = 1; + goto CONTINUE; + } + if (infile != stdin) fprintf(outfile, "%s", (char *)pp); + } + + /* The buffer may have moved while being extended; reset the start of data + pointer to the correct relative point in the buffer. */ + + p = buffer + poffset; + + /* If the first character after the delimiter is backslash, make + the pattern end with backslash. This is purely to provide a way + of testing for the error message when a pattern ends with backslash. */ + + if (pp[1] == '\\') *pp++ = '\\'; + + /* Terminate the pattern at the delimiter, and save a copy of the pattern + for callouts. */ + + *pp++ = 0; + strcpy((char *)pbuffer, (char *)p); + + /* Look for options after final delimiter */ + + options = 0; + study_options = 0; + log_store = showstore; /* default from command line */ + + while (*pp != 0) + { + switch (*pp++) + { + case 'f': options |= PCRE_FIRSTLINE; break; + case 'g': do_g = 1; break; + case 'i': options |= PCRE_CASELESS; break; + case 'm': options |= PCRE_MULTILINE; break; + case 's': options |= PCRE_DOTALL; break; + case 'x': options |= PCRE_EXTENDED; break; + + case '+': do_showrest = 1; break; + case 'A': options |= PCRE_ANCHORED; break; + case 'B': do_debug = 1; break; + case 'C': options |= PCRE_AUTO_CALLOUT; break; + case 'D': do_debug = do_showinfo = 1; break; + case 'E': options |= PCRE_DOLLAR_ENDONLY; break; + case 'F': do_flip = 1; break; + case 'G': do_G = 1; break; + case 'I': do_showinfo = 1; break; + case 'J': options |= PCRE_DUPNAMES; break; + case 'M': log_store = 1; break; + case 'N': options |= PCRE_NO_AUTO_CAPTURE; break; + +#if !defined NOPOSIX + case 'P': do_posix = 1; break; +#endif + + case 'S': do_study = 1; break; + case 'U': options |= PCRE_UNGREEDY; break; + case 'X': options |= PCRE_EXTRA; break; + case 'Z': debug_lengths = 0; break; + case '8': options |= PCRE_UTF8; use_utf8 = 1; break; + case '?': options |= PCRE_NO_UTF8_CHECK; break; + + case 'L': + ppp = pp; + /* The '\r' test here is so that it works on Windows. */ + /* The '0' test is just in case this is an unterminated line. */ + while (*ppp != 0 && *ppp != '\n' && *ppp != '\r' && *ppp != ' ') ppp++; + *ppp = 0; + if (setlocale(LC_CTYPE, (const char *)pp) == NULL) + { + fprintf(outfile, "** Failed to set locale \"%s\"\n", pp); + goto SKIP_DATA; + } + locale_set = 1; + tables = pcre_maketables(); + pp = ppp; + break; + + case '>': + to_file = pp; + while (*pp != 0) pp++; + while (isspace(pp[-1])) pp--; + *pp = 0; + break; + + case '<': + { + int x = check_newline(pp, outfile); + if (x == 0) goto SKIP_DATA; + options |= x; + while (*pp++ != '>'); + } + break; + + case '\r': /* So that it works in Windows */ + case '\n': + case ' ': + break; + + default: + fprintf(outfile, "** Unknown option '%c'\n", pp[-1]); + goto SKIP_DATA; + } + } + + /* Handle compiling via the POSIX interface, which doesn't support the + timing, showing, or debugging options, nor the ability to pass over + local character tables. */ + +#if !defined NOPOSIX + if (posix || do_posix) + { + int rc; + int cflags = 0; + + if ((options & PCRE_CASELESS) != 0) cflags |= REG_ICASE; + if ((options & PCRE_MULTILINE) != 0) cflags |= REG_NEWLINE; + if ((options & PCRE_DOTALL) != 0) cflags |= REG_DOTALL; + if ((options & PCRE_NO_AUTO_CAPTURE) != 0) cflags |= REG_NOSUB; + if ((options & PCRE_UTF8) != 0) cflags |= REG_UTF8; + + rc = regcomp(&preg, (char *)p, cflags); + + /* Compilation failed; go back for another re, skipping to blank line + if non-interactive. */ + + if (rc != 0) + { + (void)regerror(rc, &preg, (char *)buffer, buffer_size); + fprintf(outfile, "Failed: POSIX code %d: %s\n", rc, buffer); + goto SKIP_DATA; + } + } + + /* Handle compiling via the native interface */ + + else +#endif /* !defined NOPOSIX */ + + { + if (timeit > 0) + { + register int i; + clock_t time_taken; + clock_t start_time = clock(); + for (i = 0; i < timeit; i++) + { + re = pcre_compile((char *)p, options, &error, &erroroffset, tables); + if (re != NULL) free(re); + } + time_taken = clock() - start_time; + fprintf(outfile, "Compile time %.4f milliseconds\n", + (((double)time_taken * 1000.0) / (double)timeit) / + (double)CLOCKS_PER_SEC); + } + + re = pcre_compile((char *)p, options, &error, &erroroffset, tables); + + /* Compilation failed; go back for another re, skipping to blank line + if non-interactive. */ + + if (re == NULL) + { + fprintf(outfile, "Failed: %s at offset %d\n", error, erroroffset); + SKIP_DATA: + if (infile != stdin) + { + for (;;) + { + if (extend_inputline(infile, buffer, NULL) == NULL) + { + done = 1; + goto CONTINUE; + } + len = (int)strlen((char *)buffer); + while (len > 0 && isspace(buffer[len-1])) len--; + if (len == 0) break; + } + fprintf(outfile, "\n"); + } + goto CONTINUE; + } + + /* Compilation succeeded; print data if required. There are now two + info-returning functions. The old one has a limited interface and + returns only limited data. Check that it agrees with the newer one. */ + + if (log_store) + fprintf(outfile, "Memory allocation (code space): %d\n", + (int)(gotten_store - + sizeof(real_pcre) - + ((real_pcre *)re)->name_count * ((real_pcre *)re)->name_entry_size)); + + /* Extract the size for possible writing before possibly flipping it, + and remember the store that was got. */ + + true_size = ((real_pcre *)re)->size; + regex_gotten_store = gotten_store; + + /* If /S was present, study the regexp to generate additional info to + help with the matching. */ + + if (do_study) + { + if (timeit > 0) + { + register int i; + clock_t time_taken; + clock_t start_time = clock(); + for (i = 0; i < timeit; i++) + extra = pcre_study(re, study_options, &error); + time_taken = clock() - start_time; + if (extra != NULL) free(extra); + fprintf(outfile, " Study time %.4f milliseconds\n", + (((double)time_taken * 1000.0) / (double)timeit) / + (double)CLOCKS_PER_SEC); + } + extra = pcre_study(re, study_options, &error); + if (error != NULL) + fprintf(outfile, "Failed to study: %s\n", error); + else if (extra != NULL) + true_study_size = ((pcre_study_data *)(extra->study_data))->size; + } + + /* If the 'F' option was present, we flip the bytes of all the integer + fields in the regex data block and the study block. This is to make it + possible to test PCRE's handling of byte-flipped patterns, e.g. those + compiled on a different architecture. */ + + if (do_flip) + { + real_pcre *rre = (real_pcre *)re; + rre->magic_number = + byteflip(rre->magic_number, sizeof(rre->magic_number)); + rre->size = byteflip(rre->size, sizeof(rre->size)); + rre->options = byteflip(rre->options, sizeof(rre->options)); + rre->flags = (pcre_uint16)byteflip(rre->flags, sizeof(rre->flags)); + rre->top_bracket = + (pcre_uint16)byteflip(rre->top_bracket, sizeof(rre->top_bracket)); + rre->top_backref = + (pcre_uint16)byteflip(rre->top_backref, sizeof(rre->top_backref)); + rre->first_byte = + (pcre_uint16)byteflip(rre->first_byte, sizeof(rre->first_byte)); + rre->req_byte = + (pcre_uint16)byteflip(rre->req_byte, sizeof(rre->req_byte)); + rre->name_table_offset = (pcre_uint16)byteflip(rre->name_table_offset, + sizeof(rre->name_table_offset)); + rre->name_entry_size = (pcre_uint16)byteflip(rre->name_entry_size, + sizeof(rre->name_entry_size)); + rre->name_count = (pcre_uint16)byteflip(rre->name_count, + sizeof(rre->name_count)); + + if (extra != NULL) + { + pcre_study_data *rsd = (pcre_study_data *)(extra->study_data); + rsd->size = byteflip(rsd->size, sizeof(rsd->size)); + rsd->options = byteflip(rsd->options, sizeof(rsd->options)); + } + } + + /* Extract information from the compiled data if required */ + + SHOW_INFO: + + if (do_debug) + { + fprintf(outfile, "------------------------------------------------------------------\n"); + pcre_printint(re, outfile, debug_lengths); + } + + if (do_showinfo) + { + unsigned long int get_options, all_options; +#if !defined NOINFOCHECK + int old_first_char, old_options, old_count; +#endif + int count, backrefmax, first_char, need_char, okpartial, jchanged, + hascrorlf; + int nameentrysize, namecount; + const uschar *nametable; + + new_info(re, NULL, PCRE_INFO_OPTIONS, &get_options); + new_info(re, NULL, PCRE_INFO_SIZE, &size); + new_info(re, NULL, PCRE_INFO_CAPTURECOUNT, &count); + new_info(re, NULL, PCRE_INFO_BACKREFMAX, &backrefmax); + new_info(re, NULL, PCRE_INFO_FIRSTBYTE, &first_char); + new_info(re, NULL, PCRE_INFO_LASTLITERAL, &need_char); + new_info(re, NULL, PCRE_INFO_NAMEENTRYSIZE, &nameentrysize); + new_info(re, NULL, PCRE_INFO_NAMECOUNT, &namecount); + new_info(re, NULL, PCRE_INFO_NAMETABLE, (void *)&nametable); + new_info(re, NULL, PCRE_INFO_OKPARTIAL, &okpartial); + new_info(re, NULL, PCRE_INFO_JCHANGED, &jchanged); + new_info(re, NULL, PCRE_INFO_HASCRORLF, &hascrorlf); + +#if !defined NOINFOCHECK + old_count = pcre_info(re, &old_options, &old_first_char); + if (count < 0) fprintf(outfile, + "Error %d from pcre_info()\n", count); + else + { + if (old_count != count) fprintf(outfile, + "Count disagreement: pcre_fullinfo=%d pcre_info=%d\n", count, + old_count); + + if (old_first_char != first_char) fprintf(outfile, + "First char disagreement: pcre_fullinfo=%d pcre_info=%d\n", + first_char, old_first_char); + + if (old_options != (int)get_options) fprintf(outfile, + "Options disagreement: pcre_fullinfo=%ld pcre_info=%d\n", + get_options, old_options); + } +#endif + + if (size != regex_gotten_store) fprintf(outfile, + "Size disagreement: pcre_fullinfo=%d call to malloc for %d\n", + (int)size, (int)regex_gotten_store); + + fprintf(outfile, "Capturing subpattern count = %d\n", count); + if (backrefmax > 0) + fprintf(outfile, "Max back reference = %d\n", backrefmax); + + if (namecount > 0) + { + fprintf(outfile, "Named capturing subpatterns:\n"); + while (namecount-- > 0) + { + fprintf(outfile, " %s %*s%3d\n", nametable + 2, + nameentrysize - 3 - (int)strlen((char *)nametable + 2), "", + GET2(nametable, 0)); + nametable += nameentrysize; + } + } + + if (!okpartial) fprintf(outfile, "Partial matching not supported\n"); + if (hascrorlf) fprintf(outfile, "Contains explicit CR or LF match\n"); + + all_options = ((real_pcre *)re)->options; + if (do_flip) all_options = byteflip(all_options, sizeof(all_options)); + + if (get_options == 0) fprintf(outfile, "No options\n"); + else fprintf(outfile, "Options:%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s\n", + ((get_options & PCRE_ANCHORED) != 0)? " anchored" : "", + ((get_options & PCRE_CASELESS) != 0)? " caseless" : "", + ((get_options & PCRE_EXTENDED) != 0)? " extended" : "", + ((get_options & PCRE_MULTILINE) != 0)? " multiline" : "", + ((get_options & PCRE_FIRSTLINE) != 0)? " firstline" : "", + ((get_options & PCRE_DOTALL) != 0)? " dotall" : "", + ((get_options & PCRE_BSR_ANYCRLF) != 0)? " bsr_anycrlf" : "", + ((get_options & PCRE_BSR_UNICODE) != 0)? " bsr_unicode" : "", + ((get_options & PCRE_DOLLAR_ENDONLY) != 0)? " dollar_endonly" : "", + ((get_options & PCRE_EXTRA) != 0)? " extra" : "", + ((get_options & PCRE_UNGREEDY) != 0)? " ungreedy" : "", + ((get_options & PCRE_NO_AUTO_CAPTURE) != 0)? " no_auto_capture" : "", + ((get_options & PCRE_UTF8) != 0)? " utf8" : "", + ((get_options & PCRE_NO_UTF8_CHECK) != 0)? " no_utf8_check" : "", + ((get_options & PCRE_DUPNAMES) != 0)? " dupnames" : ""); + + if (jchanged) fprintf(outfile, "Duplicate name status changes\n"); + + switch (get_options & PCRE_NEWLINE_BITS) + { + case PCRE_NEWLINE_CR: + fprintf(outfile, "Forced newline sequence: CR\n"); + break; + + case PCRE_NEWLINE_LF: + fprintf(outfile, "Forced newline sequence: LF\n"); + break; + + case PCRE_NEWLINE_CRLF: + fprintf(outfile, "Forced newline sequence: CRLF\n"); + break; + + case PCRE_NEWLINE_ANYCRLF: + fprintf(outfile, "Forced newline sequence: ANYCRLF\n"); + break; + + case PCRE_NEWLINE_ANY: + fprintf(outfile, "Forced newline sequence: ANY\n"); + break; + + default: + break; + } + + if (first_char == -1) + { + fprintf(outfile, "First char at start or follows newline\n"); + } + else if (first_char < 0) + { + fprintf(outfile, "No first char\n"); + } + else + { + int ch = first_char & 255; + const char *caseless = ((first_char & REQ_CASELESS) == 0)? + "" : " (caseless)"; + if (PRINTHEX(ch)) + fprintf(outfile, "First char = \'%c\'%s\n", ch, caseless); + else + fprintf(outfile, "First char = %d%s\n", ch, caseless); + } + + if (need_char < 0) + { + fprintf(outfile, "No need char\n"); + } + else + { + int ch = need_char & 255; + const char *caseless = ((need_char & REQ_CASELESS) == 0)? + "" : " (caseless)"; + if (PRINTHEX(ch)) + fprintf(outfile, "Need char = \'%c\'%s\n", ch, caseless); + else + fprintf(outfile, "Need char = %d%s\n", ch, caseless); + } + + /* Don't output study size; at present it is in any case a fixed + value, but it varies, depending on the computer architecture, and + so messes up the test suite. (And with the /F option, it might be + flipped.) */ + + if (do_study) + { + if (extra == NULL) + fprintf(outfile, "Study returned NULL\n"); + else + { + uschar *start_bits = NULL; + new_info(re, extra, PCRE_INFO_FIRSTTABLE, &start_bits); + + if (start_bits == NULL) + fprintf(outfile, "No starting byte set\n"); + else + { + int i; + int c = 24; + fprintf(outfile, "Starting byte set: "); + for (i = 0; i < 256; i++) + { + if ((start_bits[i/8] & (1<<(i&7))) != 0) + { + if (c > 75) + { + fprintf(outfile, "\n "); + c = 2; + } + if (PRINTHEX(i) && i != ' ') + { + fprintf(outfile, "%c ", i); + c += 2; + } + else + { + fprintf(outfile, "\\x%02x ", i); + c += 5; + } + } + } + fprintf(outfile, "\n"); + } + } + } + } + + /* If the '>' option was present, we write out the regex to a file, and + that is all. The first 8 bytes of the file are the regex length and then + the study length, in big-endian order. */ + + if (to_file != NULL) + { + FILE *f = fopen((char *)to_file, "wb"); + if (f == NULL) + { + fprintf(outfile, "Unable to open %s: %s\n", to_file, strerror(errno)); + } + else + { + uschar sbuf[8]; + sbuf[0] = (uschar)((true_size >> 24) & 255); + sbuf[1] = (uschar)((true_size >> 16) & 255); + sbuf[2] = (uschar)((true_size >> 8) & 255); + sbuf[3] = (uschar)((true_size) & 255); + + sbuf[4] = (uschar)((true_study_size >> 24) & 255); + sbuf[5] = (uschar)((true_study_size >> 16) & 255); + sbuf[6] = (uschar)((true_study_size >> 8) & 255); + sbuf[7] = (uschar)((true_study_size) & 255); + + if (fwrite(sbuf, 1, 8, f) < 8 || + fwrite(re, 1, true_size, f) < true_size) + { + fprintf(outfile, "Write error on %s: %s\n", to_file, strerror(errno)); + } + else + { + fprintf(outfile, "Compiled regex written to %s\n", to_file); + if (extra != NULL) + { + if (fwrite(extra->study_data, 1, true_study_size, f) < + true_study_size) + { + fprintf(outfile, "Write error on %s: %s\n", to_file, + strerror(errno)); + } + else fprintf(outfile, "Study data written to %s\n", to_file); + + } + } + fclose(f); + } + + new_free(re); + if (extra != NULL) new_free(extra); + if (tables != NULL) new_free((void *)tables); + continue; /* With next regex */ + } + } /* End of non-POSIX compile */ + + /* Read data lines and test them */ + + for (;;) + { + uschar *q; + uschar *bptr; + int *use_offsets = offsets; + int use_size_offsets = size_offsets; + int callout_data = 0; + int callout_data_set = 0; + int count, c; + int copystrings = 0; + int find_match_limit = 0; + int getstrings = 0; + int getlist = 0; + int gmatched = 0; + int start_offset = 0; + int g_notempty = 0; + int use_dfa = 0; + + options = 0; + + *copynames = 0; + *getnames = 0; + + copynamesptr = copynames; + getnamesptr = getnames; + + pcre_callout = callout; + first_callout = 1; + callout_extra = 0; + callout_count = 0; + callout_fail_count = 999999; + callout_fail_id = -1; + show_malloc = 0; + + if (extra != NULL) extra->flags &= + ~(PCRE_EXTRA_MATCH_LIMIT|PCRE_EXTRA_MATCH_LIMIT_RECURSION); + + len = 0; + for (;;) + { + if (extend_inputline(infile, buffer + len, "data> ") == NULL) + { + if (len > 0) break; + done = 1; + goto CONTINUE; + } + if (infile != stdin) fprintf(outfile, "%s", (char *)buffer); + len = (int)strlen((char *)buffer); + if (buffer[len-1] == '\n') break; + } + + while (len > 0 && isspace(buffer[len-1])) len--; + buffer[len] = 0; + if (len == 0) break; + + p = buffer; + while (isspace(*p)) p++; + + bptr = q = dbuffer; + while ((c = *p++) != 0) + { + int i = 0; + int n = 0; + + if (c == '\\') switch ((c = *p++)) + { + case 'a': c = 7; break; + case 'b': c = '\b'; break; + case 'e': c = 27; break; + case 'f': c = '\f'; break; + case 'n': c = '\n'; break; + case 'r': c = '\r'; break; + case 't': c = '\t'; break; + case 'v': c = '\v'; break; + + case '0': case '1': case '2': case '3': + case '4': case '5': case '6': case '7': + c -= '0'; + while (i++ < 2 && isdigit(*p) && *p != '8' && *p != '9') + c = c * 8 + *p++ - '0'; + +#if !defined NOUTF8 + if (use_utf8 && c > 255) + { + unsigned char buff8[8]; + int ii, utn; + utn = ord2utf8(c, buff8); + for (ii = 0; ii < utn - 1; ii++) *q++ = buff8[ii]; + c = buff8[ii]; /* Last byte */ + } +#endif + break; + + case 'x': + + /* Handle \x{..} specially - new Perl thing for utf8 */ + +#if !defined NOUTF8 + if (*p == '{') + { + unsigned char *pt = p; + c = 0; + while (isxdigit(*(++pt))) + c = c * 16 + tolower(*pt) - ((isdigit(*pt))? '0' : 'W'); + if (*pt == '}') + { + unsigned char buff8[8]; + int ii, utn; + utn = ord2utf8(c, buff8); + for (ii = 0; ii < utn - 1; ii++) *q++ = buff8[ii]; + c = buff8[ii]; /* Last byte */ + p = pt + 1; + break; + } + /* Not correct form; fall through */ + } +#endif + + /* Ordinary \x */ + + c = 0; + while (i++ < 2 && isxdigit(*p)) + { + c = c * 16 + tolower(*p) - ((isdigit(*p))? '0' : 'W'); + p++; + } + break; + + case 0: /* \ followed by EOF allows for an empty line */ + p--; + continue; + + case '>': + while(isdigit(*p)) start_offset = start_offset * 10 + *p++ - '0'; + continue; + + case 'A': /* Option setting */ + options |= PCRE_ANCHORED; + continue; + + case 'B': + options |= PCRE_NOTBOL; + continue; + + case 'C': + if (isdigit(*p)) /* Set copy string */ + { + while(isdigit(*p)) n = n * 10 + *p++ - '0'; + copystrings |= 1 << n; + } + else if (isalnum(*p)) + { + uschar *npp = copynamesptr; + while (isalnum(*p)) *npp++ = *p++; + *npp++ = 0; + *npp = 0; + n = pcre_get_stringnumber(re, (char *)copynamesptr); + if (n < 0) + fprintf(outfile, "no parentheses with name \"%s\"\n", copynamesptr); + copynamesptr = npp; + } + else if (*p == '+') + { + callout_extra = 1; + p++; + } + else if (*p == '-') + { + pcre_callout = NULL; + p++; + } + else if (*p == '!') + { + callout_fail_id = 0; + p++; + while(isdigit(*p)) + callout_fail_id = callout_fail_id * 10 + *p++ - '0'; + callout_fail_count = 0; + if (*p == '!') + { + p++; + while(isdigit(*p)) + callout_fail_count = callout_fail_count * 10 + *p++ - '0'; + } + } + else if (*p == '*') + { + int sign = 1; + callout_data = 0; + if (*(++p) == '-') { sign = -1; p++; } + while(isdigit(*p)) + callout_data = callout_data * 10 + *p++ - '0'; + callout_data *= sign; + callout_data_set = 1; + } + continue; + +#if !defined NODFA + case 'D': +#if !defined NOPOSIX + if (posix || do_posix) + printf("** Can't use dfa matching in POSIX mode: \\D ignored\n"); + else +#endif + use_dfa = 1; + continue; + + case 'F': + options |= PCRE_DFA_SHORTEST; + continue; +#endif + + case 'G': + if (isdigit(*p)) + { + while(isdigit(*p)) n = n * 10 + *p++ - '0'; + getstrings |= 1 << n; + } + else if (isalnum(*p)) + { + uschar *npp = getnamesptr; + while (isalnum(*p)) *npp++ = *p++; + *npp++ = 0; + *npp = 0; + n = pcre_get_stringnumber(re, (char *)getnamesptr); + if (n < 0) + fprintf(outfile, "no parentheses with name \"%s\"\n", getnamesptr); + getnamesptr = npp; + } + continue; + + case 'L': + getlist = 1; + continue; + + case 'M': + find_match_limit = 1; + continue; + + case 'N': + options |= PCRE_NOTEMPTY; + continue; + + case 'O': + while(isdigit(*p)) n = n * 10 + *p++ - '0'; + if (n > size_offsets_max) + { + size_offsets_max = n; + free(offsets); + use_offsets = offsets = (int *)malloc(size_offsets_max * sizeof(int)); + if (offsets == NULL) + { + printf("** Failed to get %d bytes of memory for offsets vector\n", + (int)(size_offsets_max * sizeof(int))); + yield = 1; + goto EXIT; + } + } + use_size_offsets = n; + if (n == 0) use_offsets = NULL; /* Ensures it can't write to it */ + continue; + + case 'P': + options |= PCRE_PARTIAL; + continue; + + case 'Q': + while(isdigit(*p)) n = n * 10 + *p++ - '0'; + if (extra == NULL) + { + extra = (pcre_extra *)malloc(sizeof(pcre_extra)); + extra->flags = 0; + } + extra->flags |= PCRE_EXTRA_MATCH_LIMIT_RECURSION; + extra->match_limit_recursion = n; + continue; + + case 'q': + while(isdigit(*p)) n = n * 10 + *p++ - '0'; + if (extra == NULL) + { + extra = (pcre_extra *)malloc(sizeof(pcre_extra)); + extra->flags = 0; + } + extra->flags |= PCRE_EXTRA_MATCH_LIMIT; + extra->match_limit = n; + continue; + +#if !defined NODFA + case 'R': + options |= PCRE_DFA_RESTART; + continue; +#endif + + case 'S': + show_malloc = 1; + continue; + + case 'Z': + options |= PCRE_NOTEOL; + continue; + + case '?': + options |= PCRE_NO_UTF8_CHECK; + continue; + + case '<': + { + int x = check_newline(p, outfile); + if (x == 0) goto NEXT_DATA; + options |= x; + while (*p++ != '>'); + } + continue; + } + *q++ = c; + } + *q = 0; + len = q - dbuffer; + + if ((all_use_dfa || use_dfa) && find_match_limit) + { + printf("**Match limit not relevant for DFA matching: ignored\n"); + find_match_limit = 0; + } + + /* Handle matching via the POSIX interface, which does not + support timing or playing with the match limit or callout data. */ + +#if !defined NOPOSIX + if (posix || do_posix) + { + int rc; + int eflags = 0; + regmatch_t *pmatch = NULL; + if (use_size_offsets > 0) + pmatch = (regmatch_t *)malloc(sizeof(regmatch_t) * use_size_offsets); + if ((options & PCRE_NOTBOL) != 0) eflags |= REG_NOTBOL; + if ((options & PCRE_NOTEOL) != 0) eflags |= REG_NOTEOL; + + rc = regexec(&preg, (const char *)bptr, use_size_offsets, pmatch, eflags); + + if (rc != 0) + { + (void)regerror(rc, &preg, (char *)buffer, buffer_size); + fprintf(outfile, "No match: POSIX code %d: %s\n", rc, buffer); + } + else if ((((const pcre *)preg.re_pcre)->options & PCRE_NO_AUTO_CAPTURE) + != 0) + { + fprintf(outfile, "Matched with REG_NOSUB\n"); + } + else + { + size_t i; + for (i = 0; i < (size_t)use_size_offsets; i++) + { + if (pmatch[i].rm_so >= 0) + { + fprintf(outfile, "%2d: ", (int)i); + (void)pchars(dbuffer + pmatch[i].rm_so, + pmatch[i].rm_eo - pmatch[i].rm_so, outfile); + fprintf(outfile, "\n"); + if (i == 0 && do_showrest) + { + fprintf(outfile, " 0+ "); + (void)pchars(dbuffer + pmatch[i].rm_eo, len - pmatch[i].rm_eo, + outfile); + fprintf(outfile, "\n"); + } + } + } + } + free(pmatch); + } + + /* Handle matching via the native interface - repeats for /g and /G */ + + else +#endif /* !defined NOPOSIX */ + + for (;; gmatched++) /* Loop for /g or /G */ + { + if (timeitm > 0) + { + register int i; + clock_t time_taken; + clock_t start_time = clock(); + +#if !defined NODFA + if (all_use_dfa || use_dfa) + { + int workspace[1000]; + for (i = 0; i < timeitm; i++) + count = pcre_dfa_exec(re, NULL, (char *)bptr, len, start_offset, + options | g_notempty, use_offsets, use_size_offsets, workspace, + sizeof(workspace)/sizeof(int)); + } + else +#endif + + for (i = 0; i < timeitm; i++) + count = pcre_exec(re, extra, (char *)bptr, len, + start_offset, options | g_notempty, use_offsets, use_size_offsets); + + time_taken = clock() - start_time; + fprintf(outfile, "Execute time %.4f milliseconds\n", + (((double)time_taken * 1000.0) / (double)timeitm) / + (double)CLOCKS_PER_SEC); + } + + /* If find_match_limit is set, we want to do repeated matches with + varying limits in order to find the minimum value for the match limit and + for the recursion limit. */ + + if (find_match_limit) + { + if (extra == NULL) + { + extra = (pcre_extra *)malloc(sizeof(pcre_extra)); + extra->flags = 0; + } + + (void)check_match_limit(re, extra, bptr, len, start_offset, + options|g_notempty, use_offsets, use_size_offsets, + PCRE_EXTRA_MATCH_LIMIT, &(extra->match_limit), + PCRE_ERROR_MATCHLIMIT, "match()"); + + count = check_match_limit(re, extra, bptr, len, start_offset, + options|g_notempty, use_offsets, use_size_offsets, + PCRE_EXTRA_MATCH_LIMIT_RECURSION, &(extra->match_limit_recursion), + PCRE_ERROR_RECURSIONLIMIT, "match() recursion"); + } + + /* If callout_data is set, use the interface with additional data */ + + else if (callout_data_set) + { + if (extra == NULL) + { + extra = (pcre_extra *)malloc(sizeof(pcre_extra)); + extra->flags = 0; + } + extra->flags |= PCRE_EXTRA_CALLOUT_DATA; + extra->callout_data = &callout_data; + count = pcre_exec(re, extra, (char *)bptr, len, start_offset, + options | g_notempty, use_offsets, use_size_offsets); + extra->flags &= ~PCRE_EXTRA_CALLOUT_DATA; + } + + /* The normal case is just to do the match once, with the default + value of match_limit. */ + +#if !defined NODFA + else if (all_use_dfa || use_dfa) + { + int workspace[1000]; + count = pcre_dfa_exec(re, NULL, (char *)bptr, len, start_offset, + options | g_notempty, use_offsets, use_size_offsets, workspace, + sizeof(workspace)/sizeof(int)); + if (count == 0) + { + fprintf(outfile, "Matched, but too many subsidiary matches\n"); + count = use_size_offsets/2; + } + } +#endif + + else + { + count = pcre_exec(re, extra, (char *)bptr, len, + start_offset, options | g_notempty, use_offsets, use_size_offsets); + if (count == 0) + { + fprintf(outfile, "Matched, but too many substrings\n"); + count = use_size_offsets/3; + } + } + + /* Matched */ + + if (count >= 0) + { + int i, maxcount; + +#if !defined NODFA + if (all_use_dfa || use_dfa) maxcount = use_size_offsets/2; else +#endif + maxcount = use_size_offsets/3; + + /* This is a check against a lunatic return value. */ + + if (count > maxcount) + { + fprintf(outfile, + "** PCRE error: returned count %d is too big for offset size %d\n", + count, use_size_offsets); + count = use_size_offsets/3; + if (do_g || do_G) + { + fprintf(outfile, "** /%c loop abandoned\n", do_g? 'g' : 'G'); + do_g = do_G = FALSE; /* Break g/G loop */ + } + } + + for (i = 0; i < count * 2; i += 2) + { + if (use_offsets[i] < 0) + fprintf(outfile, "%2d: \n", i/2); + else + { + fprintf(outfile, "%2d: ", i/2); + (void)pchars(bptr + use_offsets[i], + use_offsets[i+1] - use_offsets[i], outfile); + fprintf(outfile, "\n"); + if (i == 0) + { + if (do_showrest) + { + fprintf(outfile, " 0+ "); + (void)pchars(bptr + use_offsets[i+1], len - use_offsets[i+1], + outfile); + fprintf(outfile, "\n"); + } + } + } + } + + for (i = 0; i < 32; i++) + { + if ((copystrings & (1 << i)) != 0) + { + char copybuffer[256]; + int rc = pcre_copy_substring((char *)bptr, use_offsets, count, + i, copybuffer, sizeof(copybuffer)); + if (rc < 0) + fprintf(outfile, "copy substring %d failed %d\n", i, rc); + else + fprintf(outfile, "%2dC %s (%d)\n", i, copybuffer, rc); + } + } + + for (copynamesptr = copynames; + *copynamesptr != 0; + copynamesptr += (int)strlen((char*)copynamesptr) + 1) + { + char copybuffer[256]; + int rc = pcre_copy_named_substring(re, (char *)bptr, use_offsets, + count, (char *)copynamesptr, copybuffer, sizeof(copybuffer)); + if (rc < 0) + fprintf(outfile, "copy substring %s failed %d\n", copynamesptr, rc); + else + fprintf(outfile, " C %s (%d) %s\n", copybuffer, rc, copynamesptr); + } + + for (i = 0; i < 32; i++) + { + if ((getstrings & (1 << i)) != 0) + { + const char *substring; + int rc = pcre_get_substring((char *)bptr, use_offsets, count, + i, &substring); + if (rc < 0) + fprintf(outfile, "get substring %d failed %d\n", i, rc); + else + { + fprintf(outfile, "%2dG %s (%d)\n", i, substring, rc); + pcre_free_substring(substring); + } + } + } + + for (getnamesptr = getnames; + *getnamesptr != 0; + getnamesptr += (int)strlen((char*)getnamesptr) + 1) + { + const char *substring; + int rc = pcre_get_named_substring(re, (char *)bptr, use_offsets, + count, (char *)getnamesptr, &substring); + if (rc < 0) + fprintf(outfile, "copy substring %s failed %d\n", getnamesptr, rc); + else + { + fprintf(outfile, " G %s (%d) %s\n", substring, rc, getnamesptr); + pcre_free_substring(substring); + } + } + + if (getlist) + { + const char **stringlist; + int rc = pcre_get_substring_list((char *)bptr, use_offsets, count, + &stringlist); + if (rc < 0) + fprintf(outfile, "get substring list failed %d\n", rc); + else + { + for (i = 0; i < count; i++) + fprintf(outfile, "%2dL %s\n", i, stringlist[i]); + if (stringlist[i] != NULL) + fprintf(outfile, "string list not terminated by NULL\n"); + /* free((void *)stringlist); */ + pcre_free_substring_list(stringlist); + } + } + } + + /* There was a partial match */ + + else if (count == PCRE_ERROR_PARTIAL) + { + fprintf(outfile, "Partial match"); +#if !defined NODFA + if ((all_use_dfa || use_dfa) && use_size_offsets > 2) + fprintf(outfile, ": %.*s", use_offsets[1] - use_offsets[0], + bptr + use_offsets[0]); +#endif + fprintf(outfile, "\n"); + break; /* Out of the /g loop */ + } + + /* Failed to match. If this is a /g or /G loop and we previously set + g_notempty after a null match, this is not necessarily the end. We want + to advance the start offset, and continue. We won't be at the end of the + string - that was checked before setting g_notempty. + + Complication arises in the case when the newline option is "any" or + "anycrlf". If the previous match was at the end of a line terminated by + CRLF, an advance of one character just passes the \r, whereas we should + prefer the longer newline sequence, as does the code in pcre_exec(). + Fudge the offset value to achieve this. + + Otherwise, in the case of UTF-8 matching, the advance must be one + character, not one byte. */ + + else + { + if (g_notempty != 0) + { + int onechar = 1; + unsigned int obits = ((real_pcre *)re)->options; + use_offsets[0] = start_offset; + if ((obits & PCRE_NEWLINE_BITS) == 0) + { + int d; + (void)pcre_config(PCRE_CONFIG_NEWLINE, &d); + obits = (d == '\r')? PCRE_NEWLINE_CR : + (d == '\n')? PCRE_NEWLINE_LF : + (d == ('\r'<<8 | '\n'))? PCRE_NEWLINE_CRLF : + (d == -2)? PCRE_NEWLINE_ANYCRLF : + (d == -1)? PCRE_NEWLINE_ANY : 0; + } + if (((obits & PCRE_NEWLINE_BITS) == PCRE_NEWLINE_ANY || + (obits & PCRE_NEWLINE_BITS) == PCRE_NEWLINE_ANYCRLF) + && + start_offset < len - 1 && + bptr[start_offset] == '\r' && + bptr[start_offset+1] == '\n') + onechar++; + else if (use_utf8) + { + while (start_offset + onechar < len) + { + int tb = bptr[start_offset+onechar]; + if (tb <= 127) break; + tb &= 0xc0; + if (tb != 0 && tb != 0xc0) onechar++; + } + } + use_offsets[1] = start_offset + onechar; + } + else + { + if (count == PCRE_ERROR_NOMATCH) + { + if (gmatched == 0) fprintf(outfile, "No match\n"); + } + else fprintf(outfile, "Error %d\n", count); + break; /* Out of the /g loop */ + } + } + + /* If not /g or /G we are done */ + + if (!do_g && !do_G) break; + + /* If we have matched an empty string, first check to see if we are at + the end of the subject. If so, the /g loop is over. Otherwise, mimic + what Perl's /g options does. This turns out to be rather cunning. First + we set PCRE_NOTEMPTY and PCRE_ANCHORED and try the match again at the + same point. If this fails (picked up above) we advance to the next + character. */ + + g_notempty = 0; + + if (use_offsets[0] == use_offsets[1]) + { + if (use_offsets[0] == len) break; + g_notempty = PCRE_NOTEMPTY | PCRE_ANCHORED; + } + + /* For /g, update the start offset, leaving the rest alone */ + + if (do_g) start_offset = use_offsets[1]; + + /* For /G, update the pointer and length */ + + else + { + bptr += use_offsets[1]; + len -= use_offsets[1]; + } + } /* End of loop for /g and /G */ + + NEXT_DATA: continue; + } /* End of loop for data lines */ + + CONTINUE: + +#if !defined NOPOSIX + if (posix || do_posix) regfree(&preg); +#endif + + if (re != NULL) new_free(re); + if (extra != NULL) new_free(extra); + if (tables != NULL) + { + new_free((void *)tables); + setlocale(LC_CTYPE, "C"); + locale_set = 0; + } + } + +if (infile == stdin) fprintf(outfile, "\n"); + +EXIT: + +if (infile != NULL && infile != stdin) fclose(infile); +if (outfile != NULL && outfile != stdout) fclose(outfile); + +free(buffer); +free(dbuffer); +free(pbuffer); +free(offsets); + +return yield; +} + +/* End of pcretest.c */ ============================================================ --- pcre/perltest.pl 3d543a0df21fd56f18c11f12a781fbdd88e896a9 +++ pcre/perltest.pl 3d543a0df21fd56f18c11f12a781fbdd88e896a9 @@ -0,0 +1,191 @@ +#! /usr/bin/env perl + +# Program for testing regular expressions with perl to check that PCRE handles +# them the same. This is the version that supports /8 for UTF-8 testing. As it +# stands, it requires at least Perl 5.8 for UTF-8 support. However, it needs to +# have "use utf8" at the start for running the UTF-8 tests, but *not* for the +# other tests. The only way I've found for doing this is to cat this line in +# explicitly in the RunPerlTest script. + +# use locale; # With this included, \x0b matches \s! + +# Function for turning a string into a string of printing chars. There are +# currently problems with UTF-8 strings; this fudges round them. + +sub pchars { +my($t) = ""; + +if ($utf8) + { + @p = unpack('U*', $_[0]); + foreach $c (@p) + { + if ($c >= 32 && $c < 127) { $t .= chr $c; } + else { $t .= sprintf("\\x{%02x}", $c); } + } + } + +else + { + 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 = $_; + + while ($pattern !~ /^\s*(.).*\1/s) + { + printf " > " if $infile eq "STDIN"; + last if ! ($_ = <$infile>); + printf $outfile "$_" if $infile ne "STDIN"; + $pattern .= $_; + } + + chomp($pattern); + $pattern =~ s/\s+$//; + + # The private /+ modifier means "print $' afterwards". + + $showrest = ($pattern =~ s/\+(?=[a-z]*$)//); + + # Remove /8 from a UTF-8 pattern. + + $utf8 = $pattern =~ s/8(?=[a-z]*$)//; + + # Check that the pattern is valid + + eval "\$_ =~ ${pattern}"; + if ($@) + { + printf $outfile "Error: $@"; + next NEXT_RE; + } + + # If the /g modifier is present, we want to put a loop round the matching; + # otherwise just a single "if". + + $cmd = ($pattern =~ /g[a-z]*$/)? "while" : "if"; + + # If the pattern is actually the null string, Perl uses the most recently + # executed (and successfully compiled) regex is used instead. This is a + # nasty trap for the unwary! The PCRE test suite does contain null strings + # in places - if they are allowed through here all sorts of weird and + # unexpected effects happen. To avoid this, we replace such patterns with + # a non-null pattern that has the same effect. + + $pattern = "/(?#)/$2" if ($pattern =~ /^(.)\1(.*)$/); + + # 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 ""); + $x = eval "\"$_\""; # To get escapes processed + + # Empty array for holding results, then do the matching. + + @subs = (); + + $pushes = "push address@hidden,\$&;" . + "push address@hidden,\$1;" . + "push address@hidden,\$2;" . + "push address@hidden,\$3;" . + "push address@hidden,\$4;" . + "push address@hidden,\$5;" . + "push address@hidden,\$6;" . + "push address@hidden,\$7;" . + "push address@hidden,\$8;" . + "push address@hidden,\$9;" . + "push address@hidden,\$10;" . + "push address@hidden,\$11;" . + "push address@hidden,\$12;" . + "push address@hidden,\$13;" . + "push address@hidden,\$14;" . + "push address@hidden,\$15;" . + "push address@hidden,\$16;" . + "push address@hidden,\$'; }"; + + eval "${cmd} (\$x =~ ${pattern}) {" . $pushes; + + if ($@) + { + printf $outfile "Error: address@hidden"; + next NEXT_RE; + } + elsif (scalar(@subs) == 0) + { + printf $outfile "No match\n"; + } + else + { + while (scalar(@subs) != 0) + { + printf $outfile (" 0: %s\n", &pchars($subs[0])); + printf $outfile (" 0+ %s\n", &pchars($subs[17])) if $showrest; + $last_printed = 0; + for ($i = 1; $i <= 16; $i++) + { + if (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; + } + } + splice(@subs, 0, 18); + } + } + } + } + +# printf $outfile "\n"; + +# End ============================================================ # pcre/testdata/grepinput is binary ============================================================ --- pcre/testdata/grepinput8 9d5c883e6983fda4de43a652c139c0c3f669fc81 +++ pcre/testdata/grepinput8 9d5c883e6983fda4de43a652c139c0c3f669fc81 @@ -0,0 +1,12 @@ +X one +X two X three X four +X five +X six +X seven…X eight
X nine
X ten + +Before 111 +Before 222
Before 333…Match +After 111 +After 222
After 333 +And so on and so on +And so on and so on ============================================================ --- pcre/testdata/grepinputv 0e3301f9c1e83edf2d14d28d633a05f590a8b883 +++ pcre/testdata/grepinputv 0e3301f9c1e83edf2d14d28d633a05f590a8b883 @@ -0,0 +1,3 @@ +The quick brown +fox jumps +over the lazy dog. ============================================================ --- pcre/testdata/grepinputx 030ddb5e5fed1effe5c0f091564905cfa180360d +++ pcre/testdata/grepinputx 030ddb5e5fed1effe5c0f091564905cfa180360d @@ -0,0 +1,42 @@ +This is a second file of input for the pcregrep tests. + +Here is the pattern again. + +Pattern +That time it was on a line by itself. + +To pat or not to pat, that is the question. + +complete pair +of lines + +That was a complete pair +of lines all by themselves. + +complete pair +of lines + +And there they were again, to check line numbers. + +one +two +three +four +five +six +seven +eight +nine +ten +eleven +twelve +thirteen +fourteen +fifteen +sixteen +seventeen +eighteen +nineteen +twenty + +This is the last line of this file. ============================================================ --- pcre/testdata/greplist 4d254ae0639c86a42acd3597bd17ed9952cdd1b6 +++ pcre/testdata/greplist 4d254ae0639c86a42acd3597bd17ed9952cdd1b6 @@ -0,0 +1,7 @@ +This is a file of patterns for testing the -f option. Don't include any blank +lines because they will match everything! This is no longer true, so have one. + +pattern +line by itself + +End of the list of patterns. ============================================================ # pcre/testdata/grepoutput is binary ============================================================ --- pcre/testdata/grepoutput8 a4ac385a152e8059e61ad4fad232a2b9d6626be0 +++ pcre/testdata/grepoutput8 a4ac385a152e8059e61ad4fad232a2b9d6626be0 @@ -0,0 +1,11 @@ +---------------------------- Test U1 ------------------------------ +1:X one +2:X two 3:X three 4:X four +5:X five +6:X six +7:X seven…8:X eight
9:X nine
10:X ten +---------------------------- Test U2 ------------------------------ +12-Before 111 +13-Before 222
14-Before 333…15:Match +16-After 111 +17-After 222
18-After 333 ============================================================ --- pcre/testdata/grepoutputN 5a63ff41c215a35c4f24230efff9aa0476b8a7cb +++ pcre/testdata/grepoutputN 5a63ff41c215a35c4f24230efff9aa0476b8a7cb @@ -0,0 +1,22 @@ +---------------------------- Test N1 ------------------------------ +1:abc +2:def +---------------------------- Test N2 ------------------------------ +1:abc +def +2:ghi +jkl---------------------------- Test N3 ------------------------------ +2:def +3: +ghi +jkl---------------------------- Test N4 ------------------------------ +2:ghi +jkl---------------------------- Test N5 ------------------------------ +1:abc +2:def +3:ghi +4:jkl---------------------------- Test N6 ------------------------------ +1:abc +2:def +3:ghi +4:jkl ============================================================ --- pcre/testdata/testinput1 fbff0a02d34292e714926f48610e54abadab73cb +++ pcre/testdata/testinput1 fbff0a02d34292e714926f48610e54abadab73cb @@ -0,0 +1,4039 @@ +/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 + + address@hidden + \"A. Other\" (a comment) + A. Other (a comment) + \"/s=user/ou=host/o=place/prmd=uu.yy/admd= /c=gb/\"address@hidden + 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 + + address@hidden + \"A. Other\" (a comment) + A. Other (a comment) + \"/s=user/ou=host/o=place/prmd=uu.yy/admd= /c=gb/\"address@hidden + A missing angle ]{0,})>]{0,})>([\d]{0,}\.)(.*)((
([\w\W\s\d][^<>]{0,})|[\s]{0,}))<\/a><\/TD>]{0,})>([\w\W\s\d][^<>]{0,})<\/TD>]{0,})>([\w\W\s\d][^<>]{0,})<\/TD><\/TR>/is + 43.Word Processor
(N-1286)Lega lstaff.comCA - Statewide + +/a[^a]b/ + acb + a\nb + +/a.b/ + acb + *** Failers + a\nb + +/a[^a]b/s + acb + a\nb + +/a.b/s + acb + a\nb + +/^(b+?|a){1,2}?c/ + bac + bbac + bbbac + bbbbac + bbbbbac + +/^(b+|a){1,2}?c/ + bac + bbac + bbbac + bbbbac + bbbbbac + +/(?!\A)x/m + x\nb\n + a\bx\n + +/\x0{ab}/ + \0{ab} + +/(A|B)*?CD/ + CD + +/(A|B)*CD/ + CD + +/(AB)*?\1/ + ABABAB + +/(AB)*\1/ + ABABAB + +/(?.*/)foo" + /this/is/a/very/long/line/in/deed/with/very/many/slashes/in/it/you/see/ + +"(?>.*/)foo" + /this/is/a/very/long/line/in/deed/with/very/many/slashes/in/and/foo + +/(?>(\.\d\d[1-9]?))\d+/ + 1.230003938 + 1.875000282 + *** Failers + 1.235 + +/^((?>\w+)|(?>\s+))*$/ + now is the time for all good men to come to the aid of the party + *** Failers + this is not a line with only words and spaces! + +/(\d+)(\w)/ + 12345a + 12345+ + +/((?>\d+))(\w)/ + 12345a + *** Failers + 12345+ + +/(?>a+)b/ + aaab + +/((?>a+)b)/ + aaab + +/(?>(a+))b/ + aaab + +/(?>b)+/ + aaabbbccc + +/(?>a+|b+|c+)*c/ + aaabbbbccccd + +/((?>[^()]+)|\([^()]*\))+/ + ((abc(ade)ufh()()x + +/\(((?>[^()]+)|\([^()]+\))+\)/ + (abc) + (abc(def)xyz) + *** Failers + ((()aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa + +/a(?-i)b/i + ab + Ab + *** Failers + aB + AB + +/(a (?x)b c)d e/ + a bcd e + *** Failers + a b cd e + abcd e + a bcde + +/(a b(?x)c d (?-x)e f)/ + a bcde f + *** Failers + abcdef + +/(a(?i)b)c/ + abc + aBc + *** Failers + abC + aBC + Abc + ABc + ABC + AbC + +/a(?i:b)c/ + abc + aBc + *** Failers + ABC + abC + aBC + +/a(?i:b)*c/ + aBc + aBBc + *** Failers + aBC + aBBC + +/a(?=b(?i)c)\w\wd/ + abcd + abCd + *** Failers + aBCd + abcD + +/(?s-i:more.*than).*million/i + more than million + more than MILLION + more \n than Million + *** Failers + MORE THAN MILLION + more \n than \n million + +/(?:(?s-i)more.*than).*million/i + more than million + more than MILLION + more \n than Million + *** Failers + MORE THAN MILLION + more \n than \n million + +/(?>a(?i)b+)+c/ + abc + aBbc + aBBc + *** Failers + Abc + abAb + abbC + +/(?=a(?i)b)\w\wc/ + abc + aBc + *** Failers + Ab + abC + aBC + +/(?<=a(?i)b)(\w\w)c/ + abxxc + aBxxc + *** Failers + Abxxc + ABxxc + abxxC + +/(?:(a)|b)(?(1)A|B)/ + aA + bB + *** Failers + aB + bA + +/^(a)?(?(1)a|b)+$/ + aa + b + bb + *** Failers + ab + +/^(?(?=abc)\w{3}:|\d\d)$/ + abc: + 12 + *** Failers + 123 + xyz + +/^(?(?!abc)\d\d|\w{3}:)$/ + abc: + 12 + *** Failers + 123 + xyz + +/(?(?<=foo)bar|cat)/ + foobar + cat + fcat + focat + *** Failers + foocat + +/(?(?a*)*/ + a + aa + aaaa + +/(abc|)+/ + abc + abcabc + abcabcabc + xyz + +/([a]*)*/ + a + aaaaa + +/([ab]*)*/ + a + b + ababab + aaaabcde + bbbb + +/([^a]*)*/ + b + bbbb + aaa + +/([^ab]*)*/ + cccc + abab + +/([a]*?)*/ + a + aaaa + +/([ab]*?)*/ + a + b + abab + baba + +/([^a]*?)*/ + b + bbbb + aaa + +/([^ab]*?)*/ + c + cccc + baba + +/(?>a*)*/ + a + aaabcde + +/((?>a*))*/ + aaaaa + aabbaa + +/((?>a*?))*/ + aaaaa + aabbaa + +/(?(?=[^a-z]+[a-z]) \d{2}-[a-z]{3}-\d{2} | \d{2}-\d{2}-\d{2} ) /x + 12-sep-98 + 12-09-98 + *** Failers + sep-12-98 + +/(?<=(foo))bar\1/ + foobarfoo + foobarfootling + *** Failers + foobar + barfoo + +/(?i:saturday|sunday)/ + saturday + sunday + Saturday + Sunday + SATURDAY + SUNDAY + SunDay + +/(a(?i)bc|BB)x/ + abcx + aBCx + bbx + BBx + *** Failers + abcX + aBCX + bbX + BBX + +/^([ab](?i)[cd]|[ef])/ + ac + aC + bD + elephant + Europe + frog + France + *** Failers + Africa + +/^(ab|a(?i)[b-c](?m-i)d|x(?i)y|z)/ + ab + aBd + xy + xY + zebra + Zambesi + *** Failers + aCD + XY + +/(?<=foo\n)^bar/m + foo\nbar + *** Failers + bar + baz\nbar + +/(?<=(?]&/ + <&OUT + +/^(a\1?){4}$/ + 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 Z)+|A)*/ + ZABCDEFG + +/((?>)+|A)*/ + ZABCDEFG + +/a*/g + abbab + +/^[a-\d]/ + abcde + -things + 0digit + *** Failers + bcdef + +/^[\d-a]/ + abcde + -things + 0digit + *** Failers + bcdef + +/[[:space:]]+/ + > \x09\x0a\x0c\x0d\x0b< + +/[[:blank:]]+/ + > \x09\x0a\x0c\x0d\x0b< + +/[\s]+/ + > \x09\x0a\x0c\x0d\x0b< + +/\s+/ + > \x09\x0a\x0c\x0d\x0b< + +/a b/x + ab + +/(?!\A)x/m + a\nxb\n + +/(?!^)x/m + a\nxb\n + +/abc\Qabc\Eabc/ + abcabcabc + +/abc\Q(*+|\Eabc/ + abc(*+|abc + +/ abc\Q abc\Eabc/x + abc abcabc + *** Failers + abcabcabc + +/abc#comment + \Q#not comment + literal\E/x + abc#not comment\n literal + +/abc#comment + \Q#not comment + literal/x + abc#not comment\n literal + +/abc#comment + \Q#not comment + literal\E #more comment + /x + abc#not comment\n literal + +/abc#comment + \Q#not comment + literal\E #more comment/x + abc#not comment\n literal + +/\Qabc\$xyz\E/ + abc\\\$xyz + +/\Qabc\E\$\Qxyz\E/ + abc\$xyz + +/\Gabc/ + abc + *** Failers + xyzabc + +/\Gabc./g + abc1abc2xyzabc3 + +/abc./g + abc1abc2xyzabc3 + +/a(?x: b c )d/ + XabcdY + *** Failers + Xa b c d Y + +/((?x)x y z | a b c)/ + XabcY + AxyzB + +/(?i)AB(?-i)C/ + XabCY + *** Failers + XabcY + +/((?i)AB(?-i)C|D)E/ + abCE + DE + *** Failers + abcE + abCe + dE + De + +/(.*)\d+\1/ + abc123abc + abc123bc + +/(.*)\d+\1/s + abc123abc + abc123bc + +/((.*))\d+\1/ + abc123abc + abc123bc + +/-- This tests for an IPv6 address in the form where it can have up to --/ +/-- eight components, one and only one of which is empty. This must be --/ +/-- an internal component. --/ + +/^(?!:) # colon disallowed at start + (?: # start of item + (?: [0-9a-f]{1,4} | # 1-4 hex digits or + (?(1)0 | () ) ) # if null previously matched, fail; else null + : # followed by colon + ){1,7} # end item; 1-7 of them required + [0-9a-f]{1,4} $ # final hex number at end of string + (?(1)|.) # check that there was an empty component + /xi + a123::a123 + a123:b342::abcd + a123:b342::324e:abcd + a123:ddde:b342::324e:abcd + a123:ddde:b342::324e:dcba:abcd + a123:ddde:9999:b342::324e:dcba:abcd + *** Failers + 1:2:3:4:5:6:7:8 + a123:bce:ddde:9999:b342::324e:dcba:abcd + a123::9999:b342::324e:dcba:abcd + abcde:2:3:4:5:6:7:8 + ::1 + abcd:fee0:123:: + :1 + 1: + +/[z\Qa-d]\E]/ + z + a + - + d + ] + *** Failers + b + +/[\z\C]/ + z + C + +/\M/ + M + +/(a+)*b/ + aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa + +/(?i)reg(?:ul(?:[aä]|ae)r|ex)/ + REGular + regulaer + Regex + regulär + +/Åæåä[à-ÿÀ-ß]+/ + Åæåäà + Åæåäÿ + ÅæåäÀ + Åæåäß + +/(?<=Z)X./ + \x84XAZXB + +/ab cd (?x) de fg/ + ab cd defg + +/ab cd(?x) de fg/ + ab cddefg + ** Failers + abcddefg + +/(?a|)*\d/ + aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa + aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa4 + +/(?:a|)*\d/ + aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa + aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa4 + +/\Z/g + abc\n + +/^(?s)(?>.*)(?iV\;\?aPhFB\qmj\;2\}YWFdYx\.Ap\]hjCPTP\(n28k\+3\;o\&WXqs\/gOXdr\$\:r\'do0\;b4c\(f_Gr\=\"\\4\)\[01T7ajQJvL\$W\~mL_sS\/4h\:x\*\[ZN\=KLs\&L5zX\/\/\>it\,o\:aU\(\;Z\>pW\&T7oP\'2K\^E\:x9\'c\[\%z\-\,64JQ5AeH_G\#KijUKghQw\^\\vea3a\?kka_G\$8\#\`\*kynsxzBLru\'\]k_\[7FrVx\}\^\=\$blx\>s\-N\%j\;D\*aZDnsw\:YKZ\%Q\.Kne9\#hP\?\+b3\(SOvL\,\^\;\&address@hidden)0RP6\{q\%L\^_z5E\'Dw6X\b|BM + +|\$\<\.X\+ix\[d1b\!H\#\?vV0vrK\:ZH1\=2M\>iV\;\?aPhFB\qmj\;2\}YWFdYx\.Ap\]hjCPTP\(n28k\+3\;o\&WXqs\/gOXdr\$\:r\'do0\;b4c\(f_Gr\=\"\\4\)\[01T7ajQJvL\$W\~mL_sS\/4h\:x\*\[ZN\=KLs\&L5zX\/\/\>it\,o\:aU\(\;Z\>pW\&T7oP\'2K\^E\:x9\'c\[\%z\-\,64JQ5AeH_G\#KijUKghQw\^\\vea3a\?kka_G\$8\#\`\*kynsxzBLru\'\]k_\[7FrVx\}\^\=\$blx\>s\-N\%j\;D\*aZDnsw\:YKZ\%Q\.Kne9\#hP\?\+b3\(SOvL\,\^\;\&address@hidden)0RP6\{q\%L\^_z5E\'Dw6X\b|BM + +/(a(?1)b)/BM + +/(a(?1)+b)/BM + +/a(?Pb|c)d(?Pe)/BM + +/(?:a(?Pc(?Pd)))(?Pa)/BM + +/(?Pa)...(?P=a)bbb(?P>a)d/BM + +/abc(?C255)de(?C)f/BM + +/abcde/CBM + +/\x{100}/8BM + +/\x{1000}/8BM + +/\x{10000}/8BM + +/\x{100000}/8BM + +/\x{1000000}/8BM + +/\x{4000000}/8BM + +/\x{7fffFFFF}/8BM + +/[\x{ff}]/8BM + +/[\x{100}]/8BM + +/\x80/8BM + +/\xff/8BM + +/\x{0041}\x{2262}\x{0391}\x{002e}/D8M + +/\x{D55c}\x{ad6d}\x{C5B4}/D8M + +/\x{65e5}\x{672c}\x{8a9e}/D8M + +/[\x{100}]/8BM + +/[Z\x{100}]/8BM + +/^[\x{100}\E-\Q\E\x{150}]/B8M + +/^[\QĀ\E-\QŐ\E]/B8M + +/^[\QĀ\E-\QŐ\E/B8M + +/[\p{L}]/BM + +/[\p{^L}]/BM + +/[\P{L}]/BM + +/[\P{^L}]/BM + +/[abc\p{L}\x{0660}]/8BM + +/[\p{Nd}]/8BM + +/[\p{Nd}+-]+/8BM + +/A\x{391}\x{10427}\x{ff3a}\x{1fb0}/8iBM + +/A\x{391}\x{10427}\x{ff3a}\x{1fb0}/8BM + +/[\x{105}-\x{109}]/8iBM + +/( ( (?(1)0|) )* )/xBM + +/( (?(1)0|)* )/xBM + +/[a]/BM + +/[a]/8BM + +/[\xaa]/BM + +/[\xaa]/8BM + +/[^a]/BM + +/[^a]/8BM + +/[^\xaa]/BM + +/[^\xaa]/8BM + +/ End of testinput10 / ============================================================ --- pcre/testdata/testinput2 38b626ec78ec4bb1e340a7a7de1adc6bf68cd29e +++ pcre/testdata/testinput2 38b626ec78ec4bb1e340a7a7de1adc6bf68cd29e @@ -0,0 +1,2592 @@ +/(a)b|/I + +/abc/I + abc + defabc + \Aabc + *** Failers + \Adefabc + ABC + +/^abc/I + abc + \Aabc + *** Failers + defabc + \Adefabc + +/a+bc/I + +/a*bc/I + +/a{3}bc/I + +/(abc|a+z)/I + +/^abc$/I + abc + *** Failers + def\nabc + +/ab\idef/X + +/(?X)ab\idef/X + +/x{5,4}/ + +/z{65536}/ + +/[abcd/ + +/(?X)[\B]/ + +/[z-a]/ + +/^*/ + +/(abc/ + +/(?# abc/ + +/(?z)abc/ + +/.*b/I + +/.*?b/I + +/cat|dog|elephant/I + this sentence eventually mentions a cat + this sentences rambles on and on for a while and then reaches elephant + +/cat|dog|elephant/IS + this sentence eventually mentions a cat + this sentences rambles on and on for a while and then reaches elephant + +/cat|dog|elephant/IiS + this sentence eventually mentions a CAT cat + this sentences rambles on and on for a while to elephant ElePhant + +/a|[bcd]/IS + +/(a|[^\dZ])/IS + +/(a|b)*[\s]/IS + +/(ab\2)/ + +/{4,5}abc/ + +/(a)(b)(c)\2/I + abcb + \O0abcb + \O3abcb + \O6abcb + \O9abcb + \O12abcb + +/(a)bc|(a)(b)\2/I + abc + \O0abc + \O3abc + \O6abc + aba + \O0aba + \O3aba + \O6aba + \O9aba + \O12aba + +/abc$/IE + abc + *** Failers + abc\n + abc\ndef + +/(a)(b)(c)(d)(e)\6/ + +/the quick brown fox/I + the quick brown fox + this is a line with the quick brown fox + +/the quick brown fox/IA + the quick brown fox + *** Failers + this is a line with the quick brown fox + +/ab(?z)cd/ + +/^abc|def/I + abcdef + abcdef\B + +/.*((abc)$|(def))/I + defabc + \Zdefabc + +/abc/IP + abc + *** Failers + +/^abc|def/IP + abcdef + abcdef\B + +/.*((abc)$|(def))/IP + defabc + \Zdefabc + +/the quick brown fox/IP + the quick brown fox + *** Failers + The Quick Brown Fox + +/the quick brown fox/IPi + the quick brown fox + The Quick Brown Fox + +/abc.def/IP + *** Failers + abc\ndef + +/abc$/IP + abc + abc\n + +/(abc)\2/IP + +/(abc\1)/IP + abc + +/)/ + +/a[]b/ + +/[^aeiou ]{3,}/I + co-processors, and for + +/<.*>/I + abcghinop + +/<.*?>/I + abcghinop + +/<.*>/IU + abcghinop + +/(?U)<.*>/I + abcghinop + +/<.*?>/IU + abcghinop + +/={3,}/IU + abc========def + +/(?U)={3,}?/I + abc========def + +/(?^abc)/Im + 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/I + the bullock-cart + a donkey-cart race + *** Failers + cart + horse-and-cart + +/(?<=ab(?i)x|y|z)/I + +/(?>.*)(?<=(abcd)|(xyz))/I + alphabetabcd + endingxyz + +/(?<=ab(?i)x(?-i)y|(?i)z|b)ZZ/I + abxyZZ + abXyZZ + ZZZ + zZZ + bZZ + BZZ + *** Failers + ZZ + abXYZZ + zzz + bzz + +/(?[^()]+) # Either a sequence of non-brackets (no backtracking) + | # Or + (?R) # Recurse - i.e. nested bracketed string + )* # Zero or more contents + \) # Closing ) + /Ix + (abcd) + (abcd)xyz + xyz(abcd) + (ab(xy)cd)pqr + (ab(xycd)pqr + () abc () + 12(abcde(fsh)xyz(foo(bar))lmno)89 + *** Failers + abcd + abcd) + (abcd + +/\( ( (?>[^()]+) | (?R) )* \) /Ixg + (ab(xy)cd)pqr + 1(abcd)(x(y)z)pqr + +/\( (?: (?>[^()]+) | (?R) ) \) /Ix + (abcd) + (ab(xy)cd) + (a(b(c)d)e) + ((ab)) + *** Failers + () + +/\( (?: (?>[^()]+) | (?R) )? \) /Ix + () + 12(abcde(fsh)xyz(foo(bar))lmno)89 + +/\( ( (?>[^()]+) | (?R) )* \) /Ix + (ab(xy)cd) + +/\( ( ( (?>[^()]+) | (?R) )* ) \) /Ix + (ab(xy)cd) + +/\( (123)? ( ( (?>[^()]+) | (?R) )* ) \) /Ix + (ab(xy)cd) + (123ab(xy)cd) + +/\( ( (123)? ( (?>[^()]+) | (?R) )* ) \) /Ix + (ab(xy)cd) + (123ab(xy)cd) + +/\( (((((((((( ( (?>[^()]+) | (?R) )* )))))))))) \) /Ix + (ab(xy)cd) + +/\( ( ( (?>[^()<>]+) | ((?>[^()]+)) | (?R) )* ) \) /Ix + (abcd(xyz

qrs)123) + +/\( ( ( (?>[^()]+) | ((?R)) )* ) \) /Ix + (ab(cd)ef) + (ab(cd(ef)gh)ij) + +/^[[:alnum:]]/DZ + +/^[[:^alnum:]]/DZ + +/^[[:alpha:]]/DZ + +/^[[:^alpha:]]/DZ + +/[_[:alpha:]]/IS + +/^[[:ascii:]]/DZ + +/^[[:^ascii:]]/DZ + +/^[[:blank:]]/DZ + +/^[[:^blank:]]/DZ + +/[\n\x0b\x0c\x0d[:blank:]]/IS + +/^[[:cntrl:]]/DZ + +/^[[:digit:]]/DZ + +/^[[:graph:]]/DZ + +/^[[:lower:]]/DZ + +/^[[:print:]]/DZ + +/^[[:punct:]]/DZ + +/^[[:space:]]/DZ + +/^[[:upper:]]/DZ + +/^[[:xdigit:]]/DZ + +/^[[:word:]]/DZ + +/^[[:^cntrl:]]/DZ + +/^[12[:^digit:]]/DZ + +/^[[:^blank:]]/DZ + +/[01[:alpha:]%]/DZ + +/[[.ch.]]/I + +/[[=ch=]]/I + +/[[:rhubarb:]]/I + +/[[:upper:]]/Ii + A + a + +/[[:lower:]]/Ii + A + a + +/((?-i)[[:lower:]])[[:lower:]]/Ii + ab + aB + *** Failers + Ab + AB + +/[\200-\110]/I + +/^(?(0)f|b)oo/I + +/This one's here because of the large output vector needed/I + +/(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$)) (\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\w+)\s+(\270)/I + \O900 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 ABC ABC + +/This one's here because Perl does this differently and PCRE can't at present/I + +/(main(O)?)+/I + mainmain + mainOmain + +/These are all cases where Perl does it differently (nested captures)/I + +/^(a(b)?)+$/I + aba + +/^(aa(bb)?)+$/I + aabbaa + +/^(aa|aa(bb))+$/I + aabbaa + +/^(aa(bb)??)+$/I + aabbaa + +/^(?:aa(bb)?)+$/I + aabbaa + +/^(aa(b(b))?)+$/I + aabbaa + +/^(?:aa(b(b))?)+$/I + aabbaa + +/^(?:aa(b(?:b))?)+$/I + aabbaa + +/^(?:aa(bb(?:b))?)+$/I + aabbbaa + +/^(?:aa(b(?:bb))?)+$/I + aabbbaa + +/^(?:aa(?:b(b))?)+$/I + aabbaa + +/^(?:aa(?:b(bb))?)+$/I + aabbbaa + +/^(aa(b(bb))?)+$/I + aabbbaa + +/^(aa(bb(bb))?)+$/I + aabbbbaa + +/--------------------------------------------------------------------/I + +/#/IxDZ + +/a#/IxDZ + +/[\s]/DZ + +/[\S]/DZ + +/a(?i)b/DZ + ab + aB + *** Failers + AB + +/(a(?i)b)/DZ + ab + aB + *** Failers + AB + +/ (?i)abc/IxDZ + +/#this is a comment + (?i)abc/IxDZ + +/123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890/DZ + +/\Q123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890/DZ + +/\Q\E/DZ + \ + +/\Q\Ex/DZ + +/ \Q\E/DZ + +/a\Q\E/DZ + abc + bca + bac + +/a\Q\Eb/DZ + abc + +/\Q\Eabc/DZ + +/x*+\w/DZ + *** Failers + xxxxx + +/x?+/DZ + +/x++/DZ + +/x{1,3}+/DZ + +/(x)*+/DZ + +/^(\w++|\s++)*$/I + 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)/I + 12345a + *** Failers + 12345+ + +/a++b/I + aaab + +/(a++b)/I + aaab + +/(a++)b/I + aaab + +/([^()]++|\([^()]*\))+/I + ((abc(ade)ufh()()x + +/\(([^()]++|\([^()]+\))+\)/I + (abc) + (abc(def)xyz) + *** Failers + ((()aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa + +/(abc){1,3}+/DZ + +/a+?+/I + +/a{2,3}?+b/I + +/(?U)a+?+/I + +/a{2,3}?+b/IU + +/x(?U)a++b/DZ + xaaaab + +/(?U)xa++b/DZ + xaaaab + +/^((a+)(?U)([ab]+)(?-U)([bc]+)(\w*))/DZ + +/^x(?U)a+b/DZ + +/^x(?U)(a+)b/DZ + +/[.x.]/I + +/[=x=]/I + +/[:x:]/I + +/\l/I + +/\L/I + +/\N{name}/I + +/\u/I + +/\U/I + +/[/I + +/[a-/I + +/[[:space:]/I + +/[\s]/IDZ + +/[[:space:]]/IDZ + +/[[:space:]abcde]/IDZ + +/< (?: (?(R) \d++ | [^<>]*+) | (?R)) * >/Ix + <> + + hij> + hij> + def> + + *** Failers + iV\;\?aPhFB\qmj\;2\}YWFdYx\.Ap\]hjCPTP\(n28k\+3\;o\&WXqs\/gOXdr\$\:r\'do0\;b4c\(f_Gr\=\"\\4\)\[01T7ajQJvL\$W\~mL_sS\/4h\:x\*\[ZN\=KLs\&L5zX\/\/\>it\,o\:aU\(\;Z\>pW\&T7oP\'2K\^E\:x9\'c\[\%z\-\,64JQ5AeH_G\#KijUKghQw\^\\vea3a\?kka_G\$8\#\`\*kynsxzBLru\'\]k_\[7FrVx\}\^\=\$blx\>s\-N\%j\;D\*aZDnsw\:YKZ\%Q\.Kne9\#hP\?\+b3\(SOvL\,\^\;\&address@hidden)0RP6\{q\%L\^_z5E\'Dw6X\b|IDZ + +|\$\<\.X\+ix\[d1b\!H\#\?vV0vrK\:ZH1\=2M\>iV\;\?aPhFB\qmj\;2\}YWFdYx\.Ap\]hjCPTP\(n28k\+3\;o\&WXqs\/gOXdr\$\:r\'do0\;b4c\(f_Gr\=\"\\4\)\[01T7ajQJvL\$W\~mL_sS\/4h\:x\*\[ZN\=KLs\&L5zX\/\/\>it\,o\:aU\(\;Z\>pW\&T7oP\'2K\^E\:x9\'c\[\%z\-\,64JQ5AeH_G\#KijUKghQw\^\\vea3a\?kka_G\$8\#\`\*kynsxzBLru\'\]k_\[7FrVx\}\^\=\$blx\>s\-N\%j\;D\*aZDnsw\:YKZ\%Q\.Kne9\#hP\?\+b3\(SOvL\,\^\;\&address@hidden)0RP6\{q\%L\^_z5E\'Dw6X\b|IDZ + +/(.*)\d+\1/I + +/(.*)\d+/I + +/(.*)\d+\1/Is + +/(.*)\d+/Is + +/(.*(xyz))\d+\2/I + +/((.*))\d+\1/I + abc123bc + +/a[b]/I + +/(?=a).*/I + +/(?=abc).xyz/IiI + +/(?=abc)(?i).xyz/I + +/(?=a)(?=b)/I + +/(?=.)a/I + +/((?=abcda)a)/I + +/((?=abcda)ab)/I + +/()a/I + +/(?(1)ab|ac)(.)/I + +/(?(1)abz|acz)(.)/I + +/(?(1)abz)(.)/I + +/(?(1)abz)(1)23/I + +/(a)+/I + +/(a){2,3}/I + +/(a)*/I + +/[a]/I + +/[ab]/I + +/[ab]/IS + +/[^a]/I + +/\d456/I + +/\d456/IS + +/a^b/I + +/^a/Im + abcde + xy\nabc + *** Failers + xyabc + +/c|abc/I + +/(?i)[ab]/IS + +/[ab](?i)cd/IS + +/abc(?C)def/I + abcdef + 1234abcdef + *** Failers + abcxyz + abcxyzf + +/abc(?C)de(?C1)f/I + 123abcdef + +/(?C1)\dabc(?C2)def/I + 1234abcdef + *** Failers + abcdef + +/(?C255)ab/I + +/(?C256)ab/I + +/(?Cab)xx/I + +/(?C12vr)x/I + +/abc(?C)def/I + *** Failers + \x83\x0\x61bcdef + +/(abc)(?C)de(?C1)f/I + 123abcdef + 123abcdef\C+ + 123abcdef\C- + *** Failers + 123abcdef\C!1 + +/(?C0)(abc(?C1))*/I + abcabcabc + abcabc\C!1!3 + *** Failers + abcabcabc\C!1!3 + +/(\d{3}(?C))*/I + 123\C+ + 123456\C+ + 123456789\C+ + +/((xyz)(?C)p|(?C1)xyzabc)/I + xyzabc\C+ + +/(X)((xyz)(?C)p|(?C1)xyzabc)/I + Xxyzabc\C+ + +/(?=(abc))(?C)abcdef/I + abcdef\C+ + +/(?!(abc)(?C1)d)(?C2)abcxyz/I + abcxyz\C+ + +/(?<=(abc)(?C))xyz/I + abcxyz\C+ + +/a(b+)(c*)(?C1)/I + abbbbbccc\C*1 + +/a(b+?)(c*?)(?C1)/I + abbbbbccc\C*1 + +/(?C)abc/I + +/(?C)^abc/I + +/(?C)a|b/IS + +/(?R)/I + +/(a|(?R))/I + +/(ab|(bc|(de|(?R))))/I + +/x(ab|(bc|(de|(?R))))/I + xab + xbc + xde + xxab + xxxab + *** Failers + xyab + +/(ab|(bc|(de|(?1))))/I + +/x(ab|(bc|(de|(?1)x)x)x)/I + +/^([^()]|\((?1)*\))*$/I + abc + a(b)c + a(b(c))d + *** Failers) + a(b(c)d + +/^>abc>([^()]|\((?1)*\))*abc>123abc>1(2)3abc>(1(2)3)]*+) | (?2)) * >))/Ix + <> + + hij> + hij> + def> + + *** Failers + b|c)d(?Pe)/DZ + abde + acde + +/(?:a(?Pc(?Pd)))(?Pa)/DZ + +/(?Pa)...(?P=a)bbb(?P>a)d/DZ + +/^\W*(?:(?P(?P.)\W*(?P>one)\W*(?P=two)|)|(?P(?P.)\W*(?P>three)\W*(?P=four)|\W*.\W*))\W*$/Ii + 1221 + Satan, oscillate my metallic sonatas! + A man, a plan, a canal: Panama! + Able was I ere I saw Elba. + *** Failers + The quick brown fox + +/((?(R)a|b))\1(?1)?/I + bb + bbaa + +/(.*)a/Is + +/(.*)a\1/Is + +/(.*)a(b)\2/Is + +/((.*)a|(.*)b)z/Is + +/((.*)a|(.*)b)z\1/Is + +/((.*)a|(.*)b)z\2/Is + +/((.*)a|(.*)b)z\3/Is + +/((.*)a|^(.*)b)z\3/Is + +/(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)a/Is + +/(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)a\31/Is + +/(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)a\32/Is + +/(a)(bc)/INDZ + abc + +/(?Pa)(bc)/INDZ + abc + +/(a)(?Pbc)/INDZ + +/(a+)*zz/I + aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaazzbbbbbb\M + aaaaaaaaaaaaaz\M + +/(aaa(?C1)bbb|ab)/I + aaabbb + aaabbb\C*0 + aaabbb\C*1 + aaabbb\C*-1 + +/ab(?Pcd)ef(?Pgh)/I + abcdefgh + abcdefgh\C1\Gtwo + abcdefgh\Cone\Ctwo + abcdefgh\Cthree + +/(?P)(?P)/DZ + +/(?P)(?P)/DZ + +/(?Pzz)(?Paa)/I + zzaa\CZ + zzaa\CA + +/(?Peks)(?Peccs)/I + +/(?Pabc(?Pdef)(?Pxyz))/I + +"\[((?P\d+)(,(?P>elem))*)\]"I + [10,20,30,5,5,4,4,2,43,23,4234] + *** Failers + [] + +"\[((?P\d+)(,(?P>elem))*)?\]"I + [10,20,30,5,5,4,4,2,43,23,4234] + [] + +/(a(b(?2)c))?/DZ + +/(a(b(?2)c))*/DZ + +/(a(b(?2)c)){0,2}/DZ + +/[ab]{1}+/DZ + +/((w\/|-|with)*(free|immediate)*.*?shipping\s*[!.-]*)/Ii + Baby Bjorn Active Carrier - With free SHIPPING!! + +/((w\/|-|with)*(free|immediate)*.*?shipping\s*[!.-]*)/IiS + Baby Bjorn Active Carrier - With free SHIPPING!! + +/a*.*b/ISDZ + +/(a|b)*.?c/ISDZ + +/abc(?C255)de(?C)f/DZ + +/abcde/ICDZ + abcde + abcdfe + +/a*b/ICDZ + ab + aaaab + aaaacb + +/a+b/ICDZ + ab + aaaab + aaaacb + +/(abc|def)x/ICDZ + abcx + defx + abcdefzx + +/(ab|cd){3,4}/IC + ababab + abcdabcd + abcdcdcdcdcd + +/([ab]{,4}c|xy)/ICDZ + Note: that { does NOT introduce a quantifier + +/([ab]{1,4}c|xy){4,5}?123/ICDZ + aacaacaacaacaac123 + +/\b.*/I + ab cd\>1 + +/\b.*/Is + ab cd\>1 + +/(?!.bcd).*/I + Xbcd12345 + +/abcde/I + ab\P + abc\P + abcd\P + abcde\P + the quick brown abc\P + ** Failers\P + the quick brown abxyz fox\P + +"^(0?[1-9]|[12][0-9]|3[01])/(0?[1-9]|1[012])/(20)?\d\d$"I + 13/05/04\P + 13/5/2004\P + 02/05/09\P + 1\P + 1/2\P + 1/2/0\P + 1/2/04\P + 0\P + 02/\P + 02/0\P + 02/1\P + ** Failers\P + \P + 123\P + 33/4/04\P + 3/13/04\P + 0/1/2003\P + 0/\P + 02/0/\P + 02/13\P + +/0{0,2}ABC/I + +/\d{3,}ABC/I + +/\d*ABC/I + +/[abc]+DE/I + +/[abc]?123/I + 123\P + a\P + b\P + c\P + c12\P + c123\P + +/^(?:\d){3,5}X/I + 1\P + 123\P + 123X + 1234\P + 1234X + 12345\P + 12345X + *** Failers + 1X + 123456\P + +/abc/I>testsavedregex +testsavedregex +testsavedregex +testsavedregex +(.)*~smgI + \n\n\nPartner der LCO\nde\nPartner der LINEAS Consulting\nGmbH\nLINEAS Consulting GmbH Hamburg\nPartnerfirmen\n30 days\nindex,follow\n\nja\n3\nPartner\n\n\nLCO\nLINEAS Consulting\n15.10.2003\n\n\n\n\nDie Partnerfirmen der LINEAS Consulting\nGmbH\n\n\n \n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n + +/^a/IF + +/line\nbreak/I + this is a line\nbreak + line one\nthis is a line\nbreak in the second line + +/line\nbreak/If + this is a line\nbreak + ** Failers + line one\nthis is a line\nbreak in the second line + +/line\nbreak/Imf + this is a line\nbreak + ** Failers + line one\nthis is a line\nbreak in the second line + +/ab.cd/IP + ab-cd + ab=cd + ** Failers + ab\ncd + +/ab.cd/IPs + ab-cd + ab=cd + ab\ncd + +/(?i)(?-i)AbCd/I + AbCd + ** Failers + abcd + +/a{11111111111111111111}/I + +/(){64294967295}/I + +/(){2,4294967295}/I + +"(?i:a)(?i:b)(?i:c)(?i:d)(?i:e)(?i:f)(?i:g)(?i:h)(?i:i)(?i:j)(k)(?i:l)A\1B"I + abcdefghijklAkB + +"(?Pa)(?Pb)(?Pc)(?Pd)(?Pe)(?Pf)(?Pg)(?Ph)(?Pi)(?Pj)(?Pk)(?Pl)A\11B"I + abcdefghijklAkB + +"(a)(b)(c)(d)(e)(f)(g)(h)(i)(j)(k)(l)A\11B"I + abcdefghijklAkB + +"(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)"I + aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa + +"(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)"I + aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa + +/[^()]*(?:\((?R)\)[^()]*)*/I + (this(and)that + (this(and)that) + (this(and)that)stuff + +/[^()]*(?:\((?>(?R))\)[^()]*)*/I + (this(and)that + (this(and)that) + +/[^()]*(?:\((?R)\))*[^()]*/I + (this(and)that + (this(and)that) + +/(?:\((?R)\))*[^()]*/I + (this(and)that + (this(and)that) + ((this)) + +/(?:\((?R)\))|[^()]*/I + (this(and)that + (this(and)that) + (this) + ((this)) + +/a(b)c/IPN + abc + +/a(?Pb)c/IPN + abc + +/\x{100}/I + +/\x{0000ff}/I + +/^((?Pa1)|(?Pa2)b)/I + +/^((?Pa1)|(?Pa2)b)/IJ + a1b\CA + a2b\CA + ** Failers + a1b\CZ\CA + +/^(?Pa)(?Pb)/IJ + ab\CA + +/^(?Pa)(?Pb)|cd/IJ + ab\CA + cd\CA + +/^(?Pa)(?Pb)|cd(?Pef)(?Pgh)/IJ + cdefgh\CA + +/^((?Pa1)|(?Pa2)b)/IJ + a1b\GA + a2b\GA + ** Failers + a1b\GZ\GA + +/^(?Pa)(?Pb)/IJ + ab\GA + +/^(?Pa)(?Pb)|cd/IJ + ab\GA + cd\GA + +/^(?Pa)(?Pb)|cd(?Pef)(?Pgh)/IJ + cdefgh\GA + +/(?J)^((?Pa1)|(?Pa2)b)/I + a1b\CA + a2b\CA + +/^(?Pa) (?J:(?Pb)(?Pc)) (?Pd)/I + +/ In this next test, J is not set at the outer level; consequently it isn't +set in the pattern's options; consequently pcre_get_named_substring() produces +a random value. /Ix + +/^(?Pa) (?J:(?Pb)(?Pc)) (?Pd)/I + a bc d\CA\CB\CC + +/^(?Pa)?(?(A)a|b)/I + aabc + bc + ** Failers + abc + +/(?:(?(ZZ)a|b)(?PX))+/I + bXaX + +/(?:(?(2y)a|b)(X))+/I + +/(?:(?(ZA)a|b)(?PX))+/I + +/(?:(?(ZZ)a|b)(?(ZZ)a|b)(?PX))+/I + bbXaaX + +/(?:(?(ZZ)a|\(b\))\\(?PX))+/I + (b)\\Xa\\X + +/(?PX|Y))+/I + bXXaYYaY + bXYaXXaX + +/()()()()()()()()()(?:(?(A)(?P=A)a|b)(?PX|Y))+/I + bXXaYYaY + +/\777/I + +/\s*,\s*/IS + \x0b,\x0b + \x0c,\x0d + +/^abc/Im + xyz\nabc + xyz\nabc\ + xyz\r\nabc\ + xyz\rabc\ + xyz\r\nabc\ + ** Failers + xyz\nabc\ + xyz\r\nabc\ + xyz\nabc\ + xyz\rabc\ + xyz\rabc\ + +/abc$/Im + xyzabc + xyzabc\n + xyzabc\npqr + xyzabc\r\ + xyzabc\rpqr\ + xyzabc\r\n\ + xyzabc\r\npqr\ + ** Failers + xyzabc\r + xyzabc\rpqr + xyzabc\r\n + xyzabc\r\npqr + +/^abc/Im + xyz\rabcdef + xyz\nabcdef\ + ** Failers + xyz\nabcdef + +/^abc/Im + xyz\nabcdef + xyz\rabcdef\ + ** Failers + xyz\rabcdef + +/^abc/Im + xyz\r\nabcdef + xyz\rabcdef\ + ** Failers + xyz\rabcdef + +/^abc/Im + +/abc/I + xyz\rabc\ + abc + +/.*/I + abc\ndef + abc\rdef + abc\r\ndef + \abc\ndef + \abc\rdef + \abc\r\ndef + \abc\ndef + \abc\rdef + \abc\r\ndef + +/\w+(.)(.)?def/Is + abc\ndef + abc\rdef + abc\r\ndef + ++((?:\s|//.*\\n|/[*](?:\\n|.)*?[*]/)*)+I + /* this is a C style comment */\M + +/(?P25[0-5]|2[0-4]\d|[01]?\d?\d)(?:\.(?P>B)){3}/I + +/()()()()()()()()()()()()()()()()()()()() + ()()()()()()()()()()()()()()()()()()()() + ()()()()()()()()()()()()()()()()()()()() + ()()()()()()()()()()()()()()()()()()()() + ()()()()()()()()()()()()()()()()()()()() + (.(.))/Ix + XY\O400 + +/(a*b|(?i:c*(?-i)d))/IS + +/()[ab]xyz/IS + +/(|)[ab]xyz/IS + +/(|c)[ab]xyz/IS + +/(|c?)[ab]xyz/IS + +/(d?|c?)[ab]xyz/IS + +/(d?|c)[ab]xyz/IS + +/^a*b\d/DZ + +/^a*+b\d/DZ + +/^a*?b\d/DZ + +/^a+A\d/DZ + aaaA5 + ** Failers + aaaa5 + +/^a*A\d/IiDZ + aaaA5 + aaaa5 + +/(a*|b*)[cd]/IS + +/(a+|b*)[cd]/IS + +/(a*|b+)[cd]/IS + +/(a+|b+)[cd]/IS + +/(((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((( + (((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((( + ((( + a + )))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))) + )))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))) + ))) +/Ix + large nest + +/a*\d/BZ + +/a*\D/BZ + +/0*\d/BZ + +/0*\D/BZ + +/a*\s/BZ + +/a*\S/BZ + +/ *\s/BZ + +/ *\S/BZ + +/a*\w/BZ + +/a*\W/BZ + +/=*\w/BZ + +/=*\W/BZ + +/\d*a/BZ + +/\d*2/BZ + +/\d*\d/BZ + +/\d*\D/BZ + +/\d*\s/BZ + +/\d*\S/BZ + +/\d*\w/BZ + +/\d*\W/BZ + +/\D*a/BZ + +/\D*2/BZ + +/\D*\d/BZ + +/\D*\D/BZ + +/\D*\s/BZ + +/\D*\S/BZ + +/\D*\w/BZ + +/\D*\W/BZ + +/\s*a/BZ + +/\s*2/BZ + +/\s*\d/BZ + +/\s*\D/BZ + +/\s*\s/BZ + +/\s*\S/BZ + +/\s*\w/BZ + +/\s*\W/BZ + +/\S*a/BZ + +/\S*2/BZ + +/\S*\d/BZ + +/\S*\D/BZ + +/\S*\s/BZ + +/\S*\S/BZ + +/\S*\w/BZ + +/\S*\W/BZ + +/\w*a/BZ + +/\w*2/BZ + +/\w*\d/BZ + +/\w*\D/BZ + +/\w*\s/BZ + +/\w*\S/BZ + +/\w*\w/BZ + +/\w*\W/BZ + +/\W*a/BZ + +/\W*2/BZ + +/\W*\d/BZ + +/\W*\D/BZ + +/\W*\s/BZ + +/\W*\S/BZ + +/\W*\w/BZ + +/\W*\W/BZ + +/[^a]+a/BZ + +/[^a]+a/BZi + +/[^a]+A/BZi + +/[^a]+b/BZ + +/[^a]+\d/BZ + +/a*[^a]/BZ + +/(?Px)(?Py)/I + xy\Cabc\Cxyz + +/(?x)(?'xyz'y)/I + xy\Cabc\Cxyz + +/(?x)(?'xyz>y)/I + +/(?P'abc'x)(?Py)/I + +/^(?:(?(ZZ)a|b)(?X))+/ + bXaX + bXbX + ** Failers + aXaX + aXbX + +/^(?P>abc)(?xxx)/ + +/^(?P>abc)(?x|y)/ + xx + xy + yy + yx + +/^(?P>abc)(?Px|y)/ + xx + xy + yy + yx + +/^((?(abc)a|b)(?x|y))+/ + bxay + bxby + ** Failers + axby + +/^(((?P=abc)|X)(?x|y))+/ + XxXxxx + XxXyyx + XxXyxx + ** Failers + x + +/^(?1)(abc)/ + abcabc + +/^(?:(?:\1|X)(a|b))+/ + Xaaa + Xaba + +/^[\E\Qa\E-\Qz\E]+/BZ + +/^[a\Q]bc\E]/BZ + +/^[a-\Q\E]/BZ + +/^(?P>abc)[()](?)/BZ + +/^((?(abc)y)[()](?Px))+/BZ + (xy)x + +/^(?P>abc)\Q()\E(?)/BZ + +/^(?P>abc)[a\Q(]\E(](?)/BZ + +/^(?P>abc) # this is (a comment) + (?)/BZx + +/^\W*(?:(?(?.)\W*(?&one)\W*\k|)|(?(?.)\W*(?&three)\W*\k'four'|\W*.\W*))\W*$/Ii + 1221 + Satan, oscillate my metallic sonatas! + A man, a plan, a canal: Panama! + Able was I ere I saw Elba. + *** Failers + The quick brown fox + +/(?=(\w+))\1:/I + abcd: + +/(?=(?'abc'\w+))\k:/I + abcd: + +/(?'abc'\w+):\k{2}/ + a:aaxyz + ab:ababxyz + ** Failers + a:axyz + ab:abxyz + +/(?'abc'a|b)(?d|e)\k{2}/J + adaa + ** Failers + addd + adbb + +/(?'abc'a|b)(?d|e)(?&abc){2}/J + bdaa + bdab + ** Failers + bddd + +/^(?a)? (?()b|c) (?('ab')d|e)/x + abd + ce + +/(?( (?'B' abc (?(R) (?(R&A)1) (?(R&B)2) X | (?1) (?2) (?R) ))) /x + abcabc1Xabc2XabcXabcabc + +/(? (?'B' abc (?(R) (?(R&1)1) (?(R&B)2) X | (?1) (?2) (?R) ))) /x + +/(?<1> (?'B' abc (?(R) (?(R&1)1) (?(R&B)2) X | (?1) (?2) (?R) ))) /x + abcabc1Xabc2XabcXabcabc + +/^(?(DEFINE) (? a) (? b) ) (?&A) (?&B) /x + abcd + +/(?(?&NAME_PAT))\s+(?(?&ADDRESS_PAT)) + (?(DEFINE) + (?[a-z]+) + (?\d+) + )/x + metcalfe 33 + +/^(?(DEFINE) abc | xyz ) /x + +/(?(DEFINE) abc) xyz/xI + +/(?(DEFINE) abc){3} xyz/x + +/(a|)*\d/ + \O0aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa + \O0aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa4 + +/^a.b/ + a\rb + a\nb\ + a\x85b\ + ** Failers + a\nb + a\nb\ + a\rb\ + a\rb\ + a\x85b\ + a\rb\ + +/^abc./mgx + abc1 \x0aabc2 \x0babc3xx \x0cabc4 \x0dabc5xx \x0d\x0aabc6 \x85abc7 \x{2028}abc8 \x{2029}abc9 JUNK + +/abc.$/mgx + abc1\x0a abc2\x0b abc3\x0c abc4\x0d abc5\x0d\x0a abc6\x85 abc7\x{2028} abc8\x{2029} abc9 + +/a/ + +/a/ + +/^a\Rb/ + a\nb + a\rb + a\r\nb + a\x0bb + a\x0cb + a\x85b + ** Failers + a\n\rb + +/^a\R*b/ + ab + a\nb + a\rb + a\r\nb + a\x0bb + a\x0cb + a\x85b + a\n\rb + a\n\r\x85\x0cb + +/^a\R+b/ + a\nb + a\rb + a\r\nb + a\x0bb + a\x0cb + a\x85b + a\n\rb + a\n\r\x85\x0cb + ** Failers + ab + +/^a\R{1,3}b/ + a\nb + a\n\rb + a\n\r\x85b + a\r\n\r\nb + a\r\n\r\n\r\nb + a\n\r\n\rb + a\n\n\r\nb + ** Failers + a\n\n\n\rb + a\r + +/^a[\R]b/ + aRb + ** Failers + a\nb + +/(?&abc)X(?P)/I + abcPXP123 + +/(?1)X(?P)/I + abcPXP123 + +/(?(DEFINE)(?2[0-4]\d|25[0-5]|1\d\d|[1-9]?\d))\b(?&byte)(\.(?&byte)){3}/ + 1.2.3.4 + 131.111.10.206 + 10.0.0.0 + ** Failers + 10.6 + 455.3.4.5 + +/\b(?&byte)(\.(?&byte)){3}(?(DEFINE)(?2[0-4]\d|25[0-5]|1\d\d|[1-9]?\d))/ + 1.2.3.4 + 131.111.10.206 + 10.0.0.0 + ** Failers + 10.6 + 455.3.4.5 + +/(?:a(?&abc)b)*(?x)/ + 123axbaxbaxbx456 + 123axbaxbaxb456 + +/(?:a(?&abc)b){1,5}(?x)/ + 123axbaxbaxbx456 + +/(?:a(?&abc)b){2,5}(?x)/ + 123axbaxbaxbx456 + +/(?:a(?&abc)b){2,}(?x)/ + 123axbaxbaxbx456 + +/(abc)(?i:(?1))/ + defabcabcxyz + DEFabcABCXYZ + +/(abc)(?:(?i)(?1))/ + defabcabcxyz + DEFabcABCXYZ + +/^(a(b))\1\g1\g{1}\g-1\g{-1}\g{-02}Z/ + ababababbbabZXXXX + +/^(a)\g-2/ + +/^(a)\g/ + +/^(a)\g{0}/ + +/^(a)\g{3/ + +/^(a)\g{4a}/ + +/^a.b/ + a\rb + *** Failers + a\nb + +/.+foo/ + afoo + ** Failers + \r\nfoo + \nfoo + +/.+foo/ + afoo + \nfoo + ** Failers + \r\nfoo + +/.+foo/ + afoo + ** Failers + \nfoo + \r\nfoo + +/.+foo/s + afoo + \r\nfoo + \nfoo + +/^$/mg + abc\r\rxyz + abc\n\rxyz + ** Failers + abc\r\nxyz + +/(?m)^$/g+ + abc\r\n\r\n + +/(?m)^$|^\r\n/g+ + abc\r\n\r\n + +/(?m)$/g+ + abc\r\n\r\n + +/abc.$/mgx + abc1\x0a abc2\x0b abc3\x0c abc4\x0d abc5\x0d\x0a abc6\x85 abc7\x{2028} abc8\x{2029} abc9 + +/^X/m + XABC + ** Failers + XABC\B + +/(ab|c)(?-1)/BZ + abc + +/xy(?+1)(abc)/BZ + xyabcabc + ** Failers + xyabc + +/x(?-0)y/ + +/x(?-1)y/ + +/x(?+0)y/ + +/x(?+1)y/ + +/^(abc)?(?(-1)X|Y)/BZ + abcX + Y + ** Failers + abcY + +/^((?(+1)X|Y)(abc))+/BZ + YabcXabc + YabcXabcXabc + ** Failers + XabcXabc + +/(?(-1)a)/BZ + +/((?(-1)a))/BZ + +/((?(-2)a))/BZ + +/^(?(+1)X|Y)(.)/BZ + Y! + +/(foo)\Kbar/ + foobar + +/(foo)(\Kbar|baz)/ + foobar + foobaz + +/(foo\Kbar)baz/ + foobarbaz + +/(?tom|bon)-\k{A}/ + tom-tom + bon-bon + ** Failers + tom-bon + +/(?tom|bon)-\g{A}/ + tom-tom + bon-bon + +/\g{A/ + +/(?|(abc)|(xyz))/BZ + >abc< + >xyz< + +/(x)(?|(abc)|(xyz))(x)/BZ + xabcx + xxyzx + +/(x)(?|(abc)(pqr)|(xyz))(x)/BZ + xabcpqrx + xxyzx + +/(?|(abc)|(xyz))\1/ + abcabc + xyzxyz + ** Failers + abcxyz + xyzabc + +/(?|(abc)|(xyz))(?1)/ + abcabc + xyzabc + ** Failers + xyzxyz + +/\H\h\V\v/ + X X\x0a + X\x09X\x0b + ** Failers + \xa0 X\x0a + +/\H*\h+\V?\v{3,4}/ + \x09\x20\xa0X\x0a\x0b\x0c\x0d\x0a + \x09\x20\xa0\x0a\x0b\x0c\x0d\x0a + \x09\x20\xa0\x0a\x0b\x0c + ** Failers + \x09\x20\xa0\x0a\x0b + +/\H{3,4}/ + XY ABCDE + XY PQR ST + +/.\h{3,4}./ + XY AB PQRS + +/\h*X\h?\H+Y\H?Z/ + >XNNNYZ + > X NYQZ + ** Failers + >XYZ + > X NY Z + +/\v*X\v?Y\v+Z\V*\x0a\V+\x0b\V{2,3}\x0c/ + >XY\x0aZ\x0aA\x0bNN\x0c + >\x0a\x0dX\x0aY\x0a\x0bZZZ\x0aAAA\x0bNNN\x0c + +/[\h]/BZ + >\x09< + +/[\h]+/BZ + >\x09\x20\xa0< + +/[\v]/BZ + +/[\H]/BZ + +/[^\h]/BZ + +/[\V]/BZ + +/[\x0a\V]/BZ + +/\H++X/BZ + ** Failers + XXXX + +/\H+\hY/BZ + XXXX Y + +/\H+ Y/BZ + +/\h+A/BZ + +/\v*B/BZ + +/\V+\x0a/BZ + +/A+\h/BZ + +/ *\H/BZ + +/A*\v/BZ + +/\x0b*\V/BZ + +/\d+\h/BZ + +/\d*\v/BZ + +/S+\h\S+\v/BZ + +/\w{3,}\h\w+\v/BZ + +/\h+\d\h+\w\h+\S\h+\H/BZ + +/\v+\d\v+\w\v+\S\v+\V/BZ + +/\H+\h\H+\d/BZ + +/\V+\v\V+\w/BZ + +/\( (?: [^()]* | (?R) )* \)/x +(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0( 0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(00)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0) + +/[\E]AAA/ + +/[\Q\E]AAA/ + +/[^\E]AAA/ + +/[^\Q\E]AAA/ + +/[\E^]AAA/ + +/[\Q\E^]AAA/ + +/A(*PRUNE)B(*SKIP)C(*THEN)D(*COMMIT)E(*F)F(*FAIL)G(?!)H(*ACCEPT)I/BZ + +/^a+(*FAIL)/ + aaaaaa + +/a+b?c+(*FAIL)/ + aaabccc + +/a+b?(*PRUNE)c+(*FAIL)/ + aaabccc + +/a+b?(*COMMIT)c+(*FAIL)/ + aaabccc + +/a+b?(*SKIP)c+(*FAIL)/ + aaabcccaaabccc + +/^(?:aaa(*THEN)\w{6}|bbb(*THEN)\w{5}|ccc(*THEN)\w{4}|\w{3})/ + aaaxxxxxx + aaa++++++ + bbbxxxxx + bbb+++++ + cccxxxx + ccc++++ + dddddddd + +/^(aaa(*THEN)\w{6}|bbb(*THEN)\w{5}|ccc(*THEN)\w{4}|\w{3})/ + aaaxxxxxx + aaa++++++ + bbbxxxxx + bbb+++++ + cccxxxx + ccc++++ + dddddddd + +/a+b?(*THEN)c+(*FAIL)/ + aaabccc + +/(A (A|B(*ACCEPT)|C) D)(E)/x + ABX + AADE + ACDE + ** Failers + AD + +/^a+(*FAIL)/C + aaaaaa + +/a+b?c+(*FAIL)/C + aaabccc + +/a+b?(*PRUNE)c+(*FAIL)/C + aaabccc + +/a+b?(*COMMIT)c+(*FAIL)/C + aaabccc + +/a+b?(*SKIP)c+(*FAIL)/C + aaabcccaaabccc + +/a+b?(*THEN)c+(*FAIL)/C + aaabccc + +/a(*PRUNE:XXX)b/ + +/a(*MARK)b/ + +/(?i:A{1,}\6666666666)/ + +/\g6666666666/ + +/[\g6666666666]/ + +/(?1)\c[/ + +/.+A/ + \r\nA + +/\nA/ + \r\nA + +/[\r\n]A/ + \r\nA + +/(\r|\n)A/ + \r\nA + +/a(*CR)b/ + +/(*CR)a.b/ + a\nb + ** Failers + a\rb + +/(*CR)a.b/ + a\nb + ** Failers + a\rb + +/(*LF)a.b/ + a\rb + ** Failers + a\nb + +/(*CRLF)a.b/ + a\rb + a\nb + ** Failers + a\r\nb + +/(*ANYCRLF)a.b/ + ** Failers + a\rb + a\nb + a\r\nb + +/(*ANY)a.b/ + ** Failers + a\rb + a\nb + a\r\nb + a\x85b + +/a\Rb/I + a\rb + a\nb + a\r\nb + ** Failers + a\x85b + a\x0bb + +/a\Rb/I + a\rb + a\nb + a\r\nb + a\x85b + a\x0bb + ** Failers + a\x85b\ + a\x0bb\ + +/a\R?b/I + a\rb + a\nb + a\r\nb + ** Failers + a\x85b + a\x0bb + +/a\R?b/I + a\rb + a\nb + a\r\nb + a\x85b + a\x0bb + ** Failers + a\x85b\ + a\x0bb\ + +/a\R{2,4}b/I + a\r\n\nb + a\n\r\rb + a\r\n\r\n\r\n\r\nb + ** Failers + a\x85\85b + a\x0b\0bb + +/a\R{2,4}b/I + a\r\rb + a\n\n\nb + a\r\n\n\r\rb + a\x85\85b + a\x0b\0bb + ** Failers + a\r\r\r\r\rb + a\x85\85b\ + a\x0b\0bb\ + +/(*BSR_ANYCRLF)a\Rb/I + a\nb + a\rb + +/(*BSR_UNICODE)a\Rb/I + a\x85b + +/(*BSR_ANYCRLF)(*CRLF)a\Rb/I + a\nb + a\rb + +/(*CRLF)(*BSR_UNICODE)a\Rb/I + a\x85b + +/(*CRLF)(*BSR_ANYCRLF)(*CR)ab/I + +/(?)(?&)/ + +/(?)(?&a)/ + +/(?)(?&aaaaaaaaaaaaaaaaaaaaaaa)/ + +/(?+-a)/ + +/(?-+a)/ + +/(?(-1))/ + +/(?(+10))/ + +/(?(10))/ + +/(?(+2))()()/ + +/(?(2))()()/ + +/\k''/ + +/\k<>/ + +/\k{}/ + +/(?P=)/ + +/(?P>)/ + +/(?!\w)(?R)/ + +/(?=\w)(?R)/ + +/(?>>\xaa<<< + >>>\xba<<< + +/[\W]+/Lfr_FR + >>>\xaa<<< + >>>\xba<<< + +/[^[:alpha:]]+/Lfr_FR + >>>\xaa<<< + >>>\xba<<< + +/\w+/Lfr_FR + >>>\xaa<<< + >>>\xba<<< + +/[\w]+/Lfr_FR + >>>\xaa<<< + >>>\xba<<< + +/[[:alpha:]]+/Lfr_FR + >>>\xaa<<< + >>>\xba<<< + +/[[:alpha:]][[:lower:]][[:upper:]]/DZLfr_FR + +/ End of testinput3 / ============================================================ --- pcre/testdata/testinput4 69926fa19d1d52326720485ba9599bf2ba83647b +++ pcre/testdata/testinput4 69926fa19d1d52326720485ba9599bf2ba83647b @@ -0,0 +1,612 @@ +/-- Do not use the \x{} construct except with patterns that have the --/ +/-- /8 option set, because PCRE doesn't recognize them as UTF-8 unless --/ +/-- that option is set. However, the latest Perls recognize them always. --/ + +/a.b/8 + acb + a\x7fb + a\x{100}b + *** Failers + a\nb + +/a(.{3})b/8 + a\x{4000}xyb + a\x{4000}\x7fyb + a\x{4000}\x{100}yb + *** Failers + a\x{4000}b + ac\ncb + +/a(.*?)(.)/ + a\xc0\x88b + +/a(.*?)(.)/8 + a\x{100}b + +/a(.*)(.)/ + a\xc0\x88b + +/a(.*)(.)/8 + a\x{100}b + +/a(.)(.)/ + a\xc0\x92bcd + +/a(.)(.)/8 + a\x{240}bcd + +/a(.?)(.)/ + a\xc0\x92bcd + +/a(.?)(.)/8 + a\x{240}bcd + +/a(.??)(.)/ + a\xc0\x92bcd + +/a(.??)(.)/8 + a\x{240}bcd + +/a(.{3})b/8 + a\x{1234}xyb + a\x{1234}\x{4321}yb + a\x{1234}\x{4321}\x{3412}b + *** Failers + a\x{1234}b + ac\ncb + +/a(.{3,})b/8 + a\x{1234}xyb + a\x{1234}\x{4321}yb + a\x{1234}\x{4321}\x{3412}b + axxxxbcdefghijb + a\x{1234}\x{4321}\x{3412}\x{3421}b + *** Failers + a\x{1234}b + +/a(.{3,}?)b/8 + a\x{1234}xyb + a\x{1234}\x{4321}yb + a\x{1234}\x{4321}\x{3412}b + axxxxbcdefghijb + a\x{1234}\x{4321}\x{3412}\x{3421}b + *** Failers + a\x{1234}b + +/a(.{3,5})b/8 + a\x{1234}xyb + a\x{1234}\x{4321}yb + a\x{1234}\x{4321}\x{3412}b + axxxxbcdefghijb + a\x{1234}\x{4321}\x{3412}\x{3421}b + axbxxbcdefghijb + axxxxxbcdefghijb + *** Failers + a\x{1234}b + axxxxxxbcdefghijb + +/a(.{3,5}?)b/8 + a\x{1234}xyb + a\x{1234}\x{4321}yb + a\x{1234}\x{4321}\x{3412}b + axxxxbcdefghijb + a\x{1234}\x{4321}\x{3412}\x{3421}b + axbxxbcdefghijb + axxxxxbcdefghijb + *** Failers + a\x{1234}b + axxxxxxbcdefghijb + +/^[a\x{c0}]/8 + *** Failers + \x{100} + +/(?<=aXb)cd/8 + aXbcd + +/(?<=a\x{100}b)cd/8 + a\x{100}bcd + +/(?<=a\x{100000}b)cd/8 + a\x{100000}bcd + +/(?:\x{100}){3}b/8 + \x{100}\x{100}\x{100}b + *** Failers + \x{100}\x{100}b + +/\x{ab}/8 + \x{ab} + \xc2\xab + *** Failers + \x00{ab} + +/(?<=(.))X/8 + WXYZ + \x{256}XYZ + *** Failers + XYZ + +/X(\C{3})/8 + X\x{1234} + +/X(\C{4})/8 + X\x{1234}YZ + +/X\C*/8 + XYZabcdce + +/X\C*?/8 + XYZabcde + +/X\C{3,5}/8 + Xabcdefg + X\x{1234} + X\x{1234}YZ + X\x{1234}\x{512} + X\x{1234}\x{512}YZ + +/X\C{3,5}?/8 + Xabcdefg + X\x{1234} + X\x{1234}YZ + X\x{1234}\x{512} + +/[^a]+/8g + bcd + \x{100}aY\x{256}Z + +/^[^a]{2}/8 + \x{100}bc + +/^[^a]{2,}/8 + \x{100}bcAa + +/^[^a]{2,}?/8 + \x{100}bca + +/[^a]+/8ig + bcd + \x{100}aY\x{256}Z + +/^[^a]{2}/8i + \x{100}bc + +/^[^a]{2,}/8i + \x{100}bcAa + +/^[^a]{2,}?/8i + \x{100}bca + +/\x{100}{0,0}/8 + abcd + +/\x{100}?/8 + abcd + \x{100}\x{100} + +/\x{100}{0,3}/8 + \x{100}\x{100} + \x{100}\x{100}\x{100}\x{100} + +/\x{100}*/8 + abce + \x{100}\x{100}\x{100}\x{100} + +/\x{100}{1,1}/8 + abcd\x{100}\x{100}\x{100}\x{100} + +/\x{100}{1,3}/8 + abcd\x{100}\x{100}\x{100}\x{100} + +/\x{100}+/8 + abcd\x{100}\x{100}\x{100}\x{100} + +/\x{100}{3}/8 + abcd\x{100}\x{100}\x{100}XX + +/\x{100}{3,5}/8 + abcd\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}XX + +/\x{100}{3,}/8 + abcd\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}XX + +/(?<=a\x{100}{2}b)X/8+ + Xyyya\x{100}\x{100}bXzzz + +/\D*/8 + aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa + +/\D*/8 + \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100} \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100} + +/\D/8 + 1X2 + 1\x{100}2 + +/>\S/8 + > >X Y + > >\x{100} Y + +/\d/8 + \x{100}3 + +/\s/8 + \x{100} X + +/\D+/8 + 12abcd34 + *** Failers + 1234 + +/\D{2,3}/8 + 12abcd34 + 12ab34 + *** Failers + 1234 + 12a34 + +/\D{2,3}?/8 + 12abcd34 + 12ab34 + *** Failers + 1234 + 12a34 + +/\d+/8 + 12abcd34 + *** Failers + +/\d{2,3}/8 + 12abcd34 + 1234abcd + *** Failers + 1.4 + +/\d{2,3}?/8 + 12abcd34 + 1234abcd + *** Failers + 1.4 + +/\S+/8 + 12abcd34 + *** Failers + \ \ + +/\S{2,3}/8 + 12abcd34 + 1234abcd + *** Failers + \ \ + +/\S{2,3}?/8 + 12abcd34 + 1234abcd + *** Failers + \ \ + +/>\s+ <34 + *** Failers + +/>\s{2,3} \s{2,3}? \xff< + +/[\xff]/8 + >\x{ff}< + +/[^\xFF]/ + XYZ + +/[^\xff]/8 + XYZ + \x{123} + +/^[ac]*b/8 + xb + +/^[ac\x{100}]*b/8 + xb + +/^[^x]*b/8i + xb + +/^[^x]*b/8 + xb + +/^\d*b/8 + xb + +/(|a)/g8 + catac + a\x{256}a + +/^\x{85}$/8i + \x{85} + +/^ሴ/8 + ሴ + +/^\ሴ/8 + ሴ + +"(?s)(.{1,5})"8 + abcdefg + ab + +/a*\x{100}*\w/8 + a + +/\S\S/8g + A\x{a3}BC + +/\S{2}/8g + A\x{a3}BC + +/\W\W/8g + +\x{a3}== + +/\W{2}/8g + +\x{a3}== + +/\S/8g + \x{442}\x{435}\x{441}\x{442} + +/[\S]/8g + \x{442}\x{435}\x{441}\x{442} + +/\D/8g + \x{442}\x{435}\x{441}\x{442} + +/[\D]/8g + \x{442}\x{435}\x{441}\x{442} + +/\W/8g + \x{2442}\x{2435}\x{2441}\x{2442} + +/[\W]/8g + \x{2442}\x{2435}\x{2441}\x{2442} + +/[\S\s]*/8 + abc\n\r\x{442}\x{435}\x{441}\x{442}xyz + +/[\x{41f}\S]/8g + \x{442}\x{435}\x{441}\x{442} + +/.[^\S]./8g + abc def\x{442}\x{443}xyz\npqr + +/.[^\S\n]./8g + abc def\x{442}\x{443}xyz\npqr + +/[[:^alnum:]]/8g + +\x{2442} + +/[[:^alpha:]]/8g + +\x{2442} + +/[[:^ascii:]]/8g + A\x{442} + +/[[:^blank:]]/8g + A\x{442} + +/[[:^cntrl:]]/8g + A\x{442} + +/[[:^digit:]]/8g + A\x{442} + +/[[:^graph:]]/8g + \x19\x{e01ff} + +/[[:^lower:]]/8g + A\x{422} + +/[[:^print:]]/8g + \x{19}\x{e01ff} + +/[[:^punct:]]/8g + A\x{442} + +/[[:^space:]]/8g + A\x{442} + +/[[:^upper:]]/8g + a\x{442} + +/[[:^word:]]/8g + +\x{2442} + +/[[:^xdigit:]]/8g + M\x{442} + +/[^ABCDEFGHIJKLMNOPQRSTUVWXYZÀÁÂÃÄÅÆÇÈÉÊËÌÍÎÏÐÑÒÓÔÕÖØÙÚÛÜÝÞĀĂĄĆĈĊČĎĐĒĔĖĘĚĜĞĠĢĤĦĨĪĬĮİIJĴĶĹĻĽĿŁŃŅŇŊŌŎŐŒŔŖŘŚŜŞŠŢŤŦŨŪŬŮŰŲŴŶŸŹŻŽƁƂƄƆƇƉƊƋƎƏƐƑƓƔƖƗƘƜƝƟƠƢƤƦƧƩƬƮƯƱƲƳƵƷƸƼDŽLJNJǍǏǑǓǕǗǙǛǞǠǢǤǦǨǪǬǮDZǴǶǷǸǺǼǾȀȂȄȆȈȊȌȎȐȒȔȖȘȚȜȞȠȢȤȦȨȪȬȮȰȲȺȻȽȾɁΆΈΉΊΌΎΏΑΒΓΔΕΖΗΘΙΚΛΜΝΞΟΠΡΣΤΥΦΧΨΩΪΫϒϓϔϘϚϜϞϠϢϤϦϨϪϬϮϴϷϹϺϽϾϿЀЁЂЃЄЅІЇЈЉЊЋЌЍЎЏАБВГДЕЖЗИЙКЛМНОПРСТУФХЦЧШЩЪЫЬЭЮЯѠѢѤѦѨѪѬѮѰѲѴѶѸѺѼѾҀҊҌҎҐҒҔҖҘҚҜҞҠҢҤҦҨҪҬҮҰҲҴҶҸҺҼҾӀӁӃӅӇӉӋӍӐӒӔӖӘӚӜӞӠӢӤӦӨӪӬӮӰӲӴӶӸԀԂԄԆԈԊԌԎԱԲԳԴԵԶԷԸԹԺԻԼԽԾԿՀՁՂՃՄՅՆՇՈՉՊՋՌՍՎՏՐՑՒՓՔՕՖႠႡႢႣႤႥႦႧႨႩႪႫႬႭႮႯႰႱႲႳႴႵႶႷႸႹႺႻႼႽႾႿჀჁჂჃჄჅḀḂḄḆḈḊḌḎḠá¸’ḔḖḘḚḜḞḠḢḤḦḨḪḬḮḰḲḴḶḸḺḼḾṀṂṄṆṈṊṌṎṐṒṔṖṘṚṜṞṠṢṤṦṨṪṬṮṰṲṴṶṸṺṼṾẀẂẄẆẈẊẌẎẐẒẔẠẢẤẦẨẪẬẮẰẲẴẶẸẺẼẾỀỂỄỆỈỊỌỎỐỒỔỖỘỚỜỞỠỢỤỦỨỪỬỮỰỲỴỶỸἈἉἊἋἌἍἎἏἘἙἚἛἜἝἨἩἪἫἬἭἮἯἸἹἺἻἼἽἾἿὈὉὊὋὌὍὙὛὝὟὨὩὪὫὬὭὮὯᾸᾹᾺΆῈΈῊΉῘῙῚΊῨῩῪΎῬῸΌῺΏabcdefghijklmnopqrstuvwxyzªµºßàáâãäåæçèéêëìíîïðñòóôõöøùúûüýþÿāăąćĉċčďđēĕėęěĝğġģĥħĩīĭįıijĵķĸĺļľŀłńņňʼnŋōŏőœŕŗřśŝşšţťŧũūŭůűųŵŷźżžſƀƃƅƈƌƍƒƕƙƚƛƞơƣƥƨƪƫƭưƴƶƹƺƽƾƿdžljnjǎǐǒǔǖǘǚǜǝǟǡǣǥǧǩǫǭǯǰdzǵǹǻǽǿȁȃȅȇȉȋȍȏȑȓȕȗșțȝȟȡȣȥȧȩȫȭȯȱȳȴȵȶȷȸȹȼȿɀɐɑɒɓɔɕɖɗɘəɚɛɜɝɞɟɠɡɢɣɤɥɦɧɨɩɪɫɬɭɮɯɰɱɲɳɴɵɶɷɸɹɺɻɼɽɾɿʀʁʂʃʄʅʆʇʈʉʊʋʌʍʎʏʐʑʒʓʔʕʖʗʘʙʚʛʜʝʞʟʠʡʢʣʤʥʦʧʨʩʪʫʬʭʮʯΐάέήίΰαβγδεζηθικλμνξοπρςστυφχψωϊϋόύώϐϑϕϖϗϙϛϝϟϡϣϥϧϩϫϭϯϰϱϲϳϵϸϻϼабвгдежзийклмнопрстуфхцчшщъыьэюяѐёђѓєѕіїјљњћќѝўџѡѣѥѧѩѫѭѯѱѳѵѷѹѻѽѿҁҋҍҏґғҕҗҙқҝҟҡңҥҧҩҫҭүұҳҵҷҹһҽҿӂӄӆӈӊӌӎӑӓӕӗәӛӝӟӡӣӥӧөӫӭӯӱӳӵӷӹԁԃԅԇԉԋԍԏաբգդեզէըթժիլխծկհձղճմյնշոչպջռսվտրցւփքօֆևᴀᴁᴂᴃᴄᴅᴆᴇᴈᴉᴊᴋᴌᴍᴎᴏᴐᴑᴒᴓᴔᴕᴖᴗᴘᴙᴚᴛᴜᴝᴞᴟᴠᴡᴢᴣᴤᴥᴦᴧᴨᴩᴪᴫᵢᵣᵤᵥᵦᵧᵨᵩᵪᵫᵬᵭᵮᵯᵰᵱᵲᵳᵴᵵᵶᵷᵹᵺᵻᵼᵽᵾᵿᶀᶁᶂᶃᶄᶅᶆᶇᶈᶉᶊᶋᶌᶍᶎᶏᶐᶑᶒᶓᶔᶕᶖᶗᶘᶙᶚḁḃḅḇḉḋḍḏḑḓḕḗḙḛḝḟḡḣḥḧḩḫḭḯḱḳḵḷḹḻḽḿṁṃṅṇṉṋṍṏṑṓṕṗṙṛṝṟṡṣṥṧṩṫṭṯṱṳṵṷṹṻṽṿẁẃẅẇẉẋẍẏẑẓẕẖẗẘẙẚẛạảấầẩẫậắằẳẵặẹẻẽếềểễệỉịọỏốồổỗộớờởỡợụủứừửữựỳỵỷỹἀἁἂἃἄἅἆἇἐἑἒἓἔἕἠἡἢἣἤἥἦἧἰἱἲἳἴἵἶἷὀὁὂὃὄὅὐὑὒὓὔὕὖὗὠὡὢὣὤὥὦὧὰάὲέὴήὶίὸόὺύὼώᾀᾁᾂᾃᾄᾅᾆᾇᾐᾑᾒᾓᾔᾕᾖᾗᾠᾡᾢᾣᾤᾥᾦᾧᾰᾱᾲᾳᾴᾶᾷιῂῃῄῆῇῐῑῒΐῖῗῠῡῢΰῤῥῦῧῲῳῴῶῷⲁⲃⲅⲇⲉⲋⲍⲏⲑⲓⲕⲗⲙⲛⲝⲟⲡⲣⲥⲧⲩⲫⲭⲯⲱⲳⲵⲷⲹⲻⲽⲿⳁⳃⳅⳇⳉⳋⳍⳏⳑⳓⳕⳗⳙⳛⳝⳟⳡⳣⳤⴀⴁⴂⴃⴄⴅⴆⴇⴈⴉⴊⴋⴌⴍⴎⴏⴐⴑⴒⴓⴔⴕⴖⴗⴘⴙⴚⴛⴜⴝⴞⴟⴠⴡⴢⴣⴤⴥfffiflffifflſtstﬓﬔﬕﬖﬗ\d-_^]/8 + +/ End of testinput4 / ============================================================ --- pcre/testdata/testinput5 831b6bdf626dd414715c339efe3dd17e3ddfbf35 +++ pcre/testdata/testinput5 831b6bdf626dd414715c339efe3dd17e3ddfbf35 @@ -0,0 +1,464 @@ +/\x{100}/8DZ + +/\x{1000}/8DZ + +/\x{10000}/8DZ + +/\x{100000}/8DZ + +/\x{1000000}/8DZ + +/\x{4000000}/8DZ + +/\x{7fffFFFF}/8DZ + +/[\x{ff}]/8DZ + +/[\x{100}]/8DZ + +/\x{ffffffff}/8 + +/\x{100000000}/8 + +/^\x{100}a\x{1234}/8 + \x{100}a\x{1234}bcd + +/\x80/8DZ + +/\xff/8DZ + +/\x{0041}\x{2262}\x{0391}\x{002e}/DZ8 + \x{0041}\x{2262}\x{0391}\x{002e} + +/\x{D55c}\x{ad6d}\x{C5B4}/DZ8 + \x{D55c}\x{ad6d}\x{C5B4} + +/\x{65e5}\x{672c}\x{8a9e}/DZ8 + \x{65e5}\x{672c}\x{8a9e} + +/\x{80}/DZ8 + +/\x{084}/DZ8 + +/\x{104}/DZ8 + +/\x{861}/DZ8 + +/\x{212ab}/DZ8 + +/.{3,5}X/DZ8 + \x{212ab}\x{212ab}\x{212ab}\x{861}X + + +/.{3,5}?/DZ8 + \x{212ab}\x{212ab}\x{212ab}\x{861} + +/-- These tests are here rather than in testinput4 because Perl 5.6 has some +problems with UTF-8 support, in the area of \x{..} where the value is < 255. +It grumbles about invalid UTF-8 strings. --/ + +/^[a\x{c0}]b/8 + \x{c0}b + +/^([a\x{c0}]*?)aa/8 + a\x{c0}aaaa/ + +/^([a\x{c0}]*?)aa/8 + a\x{c0}aaaa/ + a\x{c0}a\x{c0}aaa/ + +/^([a\x{c0}]*)aa/8 + a\x{c0}aaaa/ + a\x{c0}a\x{c0}aaa/ + +/^([a\x{c0}]*)a\x{c0}/8 + a\x{c0}aaaa/ + a\x{c0}a\x{c0}aaa/ + +/-- --/ + +/(?<=\C)X/8 + Should produce an error diagnostic + +/-- This one is here not because it's different to Perl, but because the way +the captured single-byte is displayed. (In Perl it becomes a character, and you +can't tell the difference.) --/ + +/X(\C)(.*)/8 + X\x{1234} + X\nabc + +/^[ab]/8DZ + bar + *** Failers + c + \x{ff} + \x{100} + +/^[^ab]/8DZ + c + \x{ff} + \x{100} + *** Failers + aaa + +/[^ab\xC0-\xF0]/8SDZ + \x{f1} + \x{bf} + \x{100} + \x{1000} + *** Failers + \x{c0} + \x{f0} + +/Ā{3,4}/8SDZ + \x{100}\x{100}\x{100}\x{100\x{100} + +/(\x{100}+|x)/8SDZ + +/(\x{100}*a|x)/8SDZ + +/(\x{100}{0,2}a|x)/8SDZ + +/(\x{100}{1,2}a|x)/8SDZ + +/\x{100}*(\d+|"(?1)")/8 + 1234 + "1234" + \x{100}1234 + "\x{100}1234" + \x{100}\x{100}12ab + \x{100}\x{100}"12" + *** Failers + \x{100}\x{100}abcd + +/\x{100}/8DZ + +/\x{100}*/8DZ + +/a\x{100}*/8DZ + +/ab\x{100}*/8DZ + +/a\x{100}\x{101}*/8DZ + +/a\x{100}\x{101}+/8DZ + +/\x{100}*A/8DZ + A + +/\x{100}*\d(?R)/8DZ + +/[^\x{c4}]/DZ + +/[^\x{c4}]/8DZ + +/[\x{100}]/8DZ + \x{100} + Z\x{100} + \x{100}Z + *** Failers + +/[Z\x{100}]/8DZ + Z\x{100} + \x{100} + \x{100}Z + *** Failers + +/[\x{200}-\x{100}]/8 + +/[Ā-Ą]/8 + \x{100} + \x{104} + *** Failers + \x{105} + \x{ff} + +/[z-\x{100}]/8DZ + +/[z\Qa-d]Ā\E]/8DZ + \x{100} + Ā + +/[\xFF]/DZ + >\xff< + +/[\xff]/DZ8 + >\x{ff}< + +/[^\xFF]/DZ + +/[^\xff]/8DZ + +/[Ä-Ü]/8 + Ö # Matches without Study + \x{d6} + +/[Ä-Ü]/8S + Ö <-- Same with Study + \x{d6} + +/[\x{c4}-\x{dc}]/8 + Ö # Matches without Study + \x{d6} + +/[\x{c4}-\x{dc}]/8S + Ö <-- Same with Study + \x{d6} + +/[Ã]/8 + +/Ã/8 + +/ÃÃÃxxx/8 + +/ÃÃÃxxx/8?DZ + +/abc/8 + Ã] + à + ÃÃà + ÃÃÃ\? + +/anything/8 + \xc0\x80 + \xc1\x8f + \xe0\x9f\x80 + \xf0\x8f\x80\x80 + \xf8\x87\x80\x80\x80 + \xfc\x83\x80\x80\x80\x80 + \xfe\x80\x80\x80\x80\x80 + \xff\x80\x80\x80\x80\x80 + \xc3\x8f + \xe0\xaf\x80 + \xe1\x80\x80 + \xf0\x9f\x80\x80 + \xf1\x8f\x80\x80 + \xf8\x88\x80\x80\x80 + \xf9\x87\x80\x80\x80 + \xfc\x84\x80\x80\x80\x80 + \xfd\x83\x80\x80\x80\x80 + \?\xf8\x88\x80\x80\x80 + \?\xf9\x87\x80\x80\x80 + \?\xfc\x84\x80\x80\x80\x80 + \?\xfd\x83\x80\x80\x80\x80 + +/\x{100}abc(xyz(?1))/8DZ + +/[^\x{100}]abc(xyz(?1))/8DZ + +/[ab\x{100}]abc(xyz(?1))/8DZ + +/(\x{100}(b(?2)c))?/DZ8 + +/(\x{100}(b(?2)c)){0,2}/DZ8 + +/(\x{100}(b(?1)c))?/DZ8 + +/(\x{100}(b(?1)c)){0,2}/DZ8 + +/\W/8 + A.B + A\x{100}B + +/\w/8 + \x{100}X + +/a\x{1234}b/P8 + a\x{1234}b + +/^\ሴ/8DZ + +/\777/I + +/\777/8I + \x{1ff} + \777 + +/\x{100}*\d/8DZ + +/\x{100}*\s/8DZ + +/\x{100}*\w/8DZ + +/\x{100}*\D/8DZ + +/\x{100}*\S/8DZ + +/\x{100}*\W/8DZ + +/\x{100}+\x{200}/8DZ + +/\x{100}+X/8DZ + +/X+\x{200}/8DZ + +/()()()()()()()()()() + ()()()()()()()()()() + ()()()()()()()()()() + ()()()()()()()()()() + A (x) (?41) B/8x + AxxB + +/^[\x{100}\E-\Q\E\x{150}]/BZ8 + +/^[\QĀ\E-\QŐ\E]/BZ8 + +/^[\QĀ\E-\QŐ\E/BZ8 + +/^abc./mgx8 + abc1 \x0aabc2 \x0babc3xx \x0cabc4 \x0dabc5xx \x0d\x0aabc6 \x{0085}abc7 \x{2028}abc8 \x{2029}abc9 JUNK + +/abc.$/mgx8 + abc1\x0a abc2\x0b abc3\x0c abc4\x0d abc5\x0d\x0a abc6\x{0085} abc7\x{2028} abc8\x{2029} abc9 + +/^a\Rb/8 + a\nb + a\rb + a\r\nb + a\x0bb + a\x0cb + a\x{85}b + a\x{2028}b + a\x{2029}b + ** Failers + a\n\rb + +/^a\R*b/8 + ab + a\nb + a\rb + a\r\nb + a\x0bb + a\x0c\x{2028}\x{2029}b + a\x{85}b + a\n\rb + a\n\r\x{85}\x0cb + +/^a\R+b/8 + a\nb + a\rb + a\r\nb + a\x0bb + a\x0c\x{2028}\x{2029}b + a\x{85}b + a\n\rb + a\n\r\x{85}\x0cb + ** Failers + ab + +/^a\R{1,3}b/8 + a\nb + a\n\rb + a\n\r\x{85}b + a\r\n\r\nb + a\r\n\r\n\r\nb + a\n\r\n\rb + a\n\n\r\nb + ** Failers + a\n\n\n\rb + a\r + +/\H\h\V\v/8 + X X\x0a + X\x09X\x0b + ** Failers + \x{a0} X\x0a + +/\H*\h+\V?\v{3,4}/8 + \x09\x20\x{a0}X\x0a\x0b\x0c\x0d\x0a + \x09\x20\x{a0}\x0a\x0b\x0c\x0d\x0a + \x09\x20\x{a0}\x0a\x0b\x0c + ** Failers + \x09\x20\x{a0}\x0a\x0b + +/\H\h\V\v/8 + \x{3001}\x{3000}\x{2030}\x{2028} + X\x{180e}X\x{85} + ** Failers + \x{2009} X\x0a + +/\H*\h+\V?\v{3,4}/8 + \x{1680}\x{180e}\x{2007}X\x{2028}\x{2029}\x0c\x0d\x0a + \x09\x{205f}\x{a0}\x0a\x{2029}\x0c\x{2028}\x0a + \x09\x20\x{202f}\x0a\x0b\x0c + ** Failers + \x09\x{200a}\x{a0}\x{2028}\x0b + +/[\h]/8BZ + >\x{1680} + +/[\h]{3,}/8BZ + >\x{1680}\x{180e}\x{2000}\x{2003}\x{200a}\x{202f}\x{205f}\x{3000}< + +/[\v]/8BZ + +/[\H]/8BZ + +/[\V]/8BZ + +/.*$/8 + \x{1ec5} + +/-- This tests the stricter UTF-8 check according to RFC 3629. --/ + +/X/8 + \x{0}\x{d7ff}\x{e000}\x{10ffff} + \x{d800} + \x{d800}\? + \x{da00} + \x{da00}\? + \x{dfff} + \x{dfff}\? + \x{110000} + \x{110000}\? + \x{2000000} + \x{2000000}\? + \x{7fffffff} + \x{7fffffff}\? + +/a\Rb/I8 + a\rb + a\nb + a\r\nb + ** Failers + a\x{85}b + a\x0bb + +/a\Rb/I8 + a\rb + a\nb + a\r\nb + a\x{85}b + a\x0bb + ** Failers + a\x{85}b\ + a\x0bb\ + +/a\R?b/I8 + a\rb + a\nb + a\r\nb + ** Failers + a\x{85}b + a\x0bb + +/a\R?b/I8 + a\rb + a\nb + a\r\nb + a\x{85}b + a\x0bb + ** Failers + a\x{85}b\ + a\x0bb\ + +/.*a.*=.b.*/8 + QQQ\x{2029}ABCaXYZ=!bPQR + ** Failers + a\x{2029}b + \x61\xe2\x80\xa9\x62 + +/[[:a\x{100}b:]]/8 + +/ End of testinput5 / ============================================================ --- pcre/testdata/testinput6 6fb7d308bae37cdb1036002e102b1abf35e94ce2 +++ pcre/testdata/testinput6 6fb7d308bae37cdb1036002e102b1abf35e94ce2 @@ -0,0 +1,910 @@ +/^\pC\pL\pM\pN\pP\pS\pZ3 + *** Failers + xyzabc + xyzabc\>2 + +/x\dy\Dz/ + x9yzz + x0y+z + *** Failers + xyz + xxy0z + +/x\sy\Sz/ + x yzz + x y+z + *** Failers + xyz + xxyyz + +/x\wy\Wz/ + xxy+z + *** Failers + xxy0z + x+y+z + +/x.y/ + x+y + x-y + *** Failers + x\ny + +/x.y/s + x+y + x-y + x\ny + +/(a.b(?s)c.d|x.y)p.q/ + a+bc+dp+q + a+bc\ndp+q + x\nyp+q + *** Failers + a\nbc\ndp+q + a+bc\ndp\nq + x\nyp\nq + +/a\d\z/ + ba0 + *** Failers + ba0\n + ba0\ncd + +/a\d\z/m + ba0 + *** Failers + ba0\n + ba0\ncd + +/a\d\Z/ + ba0 + ba0\n + *** Failers + ba0\ncd + +/a\d\Z/m + ba0 + ba0\n + *** Failers + ba0\ncd + +/a\d$/ + ba0 + ba0\n + *** Failers + ba0\ncd + +/a\d$/m + ba0 + ba0\n + ba0\ncd + *** Failers + +/abc/i + abc + aBc + ABC + +/[^a]/ + abcd + +/ab?\w/ + abz + abbz + azz + +/x{0,3}yz/ + ayzq + axyzq + axxyz + axxxyzq + axxxxyzq + *** Failers + ax + axx + +/x{3}yz/ + axxxyzq + axxxxyzq + *** Failers + ax + axx + ayzq + axyzq + axxyz + +/x{2,3}yz/ + axxyz + axxxyzq + axxxxyzq + *** Failers + ax + axx + ayzq + axyzq + +/[^a]+/ + bac + bcdefax + *** Failers + aaaaa + +/[^a]*/ + bac + bcdefax + *** Failers + aaaaa + +/[^a]{3,5}/ + xyz + awxyza + abcdefa + abcdefghijk + *** Failers + axya + axa + aaaaa + +/\d*/ + 1234b567 + xyz + +/\D*/ + a1234b567 + xyz + +/\d+/ + ab1234c56 + *** Failers + xyz + +/\D+/ + ab123c56 + *** Failers + 789 + +/\d?A/ + 045ABC + ABC + *** Failers + XYZ + +/\D?A/ + ABC + BAC + 9ABC + *** Failers + +/a+/ + aaaa + +/^.*xyz/ + xyz + ggggggggxyz + +/^.+xyz/ + abcdxyz + axyz + *** Failers + xyz + +/^.?xyz/ + xyz + cxyz + +/^\d{2,3}X/ + 12X + 123X + *** Failers + X + 1X + 1234X + +/^[abcd]\d/ + a45 + b93 + c99z + d04 + *** Failers + e45 + abcd + abcd1234 + 1234 + +/^[abcd]*\d/ + a45 + b93 + c99z + d04 + abcd1234 + 1234 + *** Failers + e45 + abcd + +/^[abcd]+\d/ + a45 + b93 + c99z + d04 + abcd1234 + *** Failers + 1234 + e45 + abcd + +/^a+X/ + aX + aaX + +/^[abcd]?\d/ + a45 + b93 + c99z + d04 + 1234 + *** Failers + abcd1234 + e45 + +/^[abcd]{2,3}\d/ + ab45 + bcd93 + *** Failers + 1234 + a36 + abcd1234 + ee45 + +/^(abc)*\d/ + abc45 + abcabcabc45 + 42xyz + *** Failers + +/^(abc)+\d/ + abc45 + abcabcabc45 + *** Failers + 42xyz + +/^(abc)?\d/ + abc45 + 42xyz + *** Failers + abcabcabc45 + +/^(abc){2,3}\d/ + abcabc45 + abcabcabc45 + *** Failers + abcabcabcabc45 + abc45 + 42xyz + +/1(abc|xyz)2(?1)3/ + 1abc2abc3456 + 1abc2xyz3456 + +/^(a*\w|ab)=(a*\w|ab)/ + ab=ab + +/^(a*\w|ab)=(?1)/ + ab=ab + +/^([^()]|\((?1)*\))*$/ + abc + a(b)c + a(b(c))d + *** Failers) + a(b(c)d + +/^>abc>([^()]|\((?1)*\))*abc>123abc>1(2)3abc>(1(2)3)a*)\d/ + aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa9876 + *** Failers + aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa + +/< (?: (?(R) \d++ | [^<>]*+) | (?R)) * >/x + <> + + hij> + hij> + def> + + *** Failers + 3 + *** Failers + defabcxyz + +/^abcdef/ + ab\P + abcde\P + abcdef\P + *** Failers + abx\P + +/^a{2,4}\d+z/ + a\P + aa\P + aa2\P + aaa\P + aaa23\P + aaaa12345\P + aa0z\P + aaaa4444444444444z\P + *** Failers + az\P + aaaaa\P + a56\P + +/^abcdef/ + abc\P + def\R + +/(?<=foo)bar/ + xyzfo\P + foob\P\>2 + foobar...\R\P\>4 + xyzfo\P + foobar\>2 + *** Failers + xyzfo\P + obar\R + +/(ab*(cd|ef))+X/ + adfadadaklhlkalkajhlkjahdfasdfasdfladsfjkj\P\Z + lkjhlkjhlkjhlkjhabbbbbbcdaefabbbbbbbefa\P\B\Z + cdabbbbbbbb\P\R\B\Z + efabbbbbbbbbbbbbbbb\P\R\B\Z + bbbbbbbbbbbbcdXyasdfadf\P\R\B\Z + +/(a|b)/SF>testsavedregex +>>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 + +/^From +([^ ]+) +[a-zA-Z][a-zA-Z][a-zA-Z] +[a-zA-Z][a-zA-Z][a-zA-Z] +[0-9]?[0-9] +[0-9][0-9]:[0-9][0-9]/ + From abcd Mon Sep 01 12:33:02 1997 + +/^From\s+\S+\s+([a-zA-Z]{3}\s+){2}\d{1,2}\s+\d\d:\d\d/ + From abcd Mon Sep 01 12:33:02 1997 + From abcd Mon Sep 1 12:33:02 1997 + *** Failers + From abcd Sep 01 12:33:02 1997 + +/^12.34/s + 12\n34 + 12\r34 + +/\w+(?=\t)/ + the quick brown\t fox + +/foo(?!bar)(.*)/ + foobar is foolish see? + +/(?:(?!foo)...|^.{0,2})bar(.*)/ + foobar crowbar etc + barrel + 2barrel + A barrel + +/^(\D*)(?=\d)(?!123)/ + abc456 + *** Failers + abc123 + +/^1234(?# test newlines + inside)/ + 1234 + +/^1234 #comment in extended re + /x + 1234 + +/#rhubarb + abcd/x + abcd + +/^abcd#rhubarb/x + abcd + +/(?!^)abc/ + the abc + *** Failers + abc + +/(?=^)abc/ + abc + *** Failers + the abc + +/^[ab]{1,3}(ab*|b)/ + aabbbbb + +/^[ab]{1,3}?(ab*|b)/ + aabbbbb + +/^[ab]{1,3}?(ab*?|b)/ + aabbbbb + +/^[ab]{1,3}(ab*?|b)/ + aabbbbb + +/ (?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* # optional leading comment +(?: (?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| +" (?: # opening quote... +[^\\\x80-\xff\n\015"] # Anything except backslash and quote +| # or +\\ [^\x80-\xff] # Escaped something (something != CR) +)* " # closing quote +) # initial word +(?: (?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* \. (?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* (?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| +" (?: # opening quote... +[^\\\x80-\xff\n\015"] # Anything except backslash and quote +| # or +\\ [^\x80-\xff] # Escaped something (something != CR) +)* " # closing quote +) )* # further okay, if led by a period +(?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* @ (?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* (?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| \[ # [ +(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff +\] # ] +) # initial subdomain +(?: # +(?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* \. # if led by a period... +(?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* (?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| \[ # [ +(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff +\] # ] +) # ...further okay +)* +# address +| # or +(?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| +" (?: # opening quote... +[^\\\x80-\xff\n\015"] # Anything except backslash and quote +| # or +\\ [^\x80-\xff] # Escaped something (something != CR) +)* " # closing quote +) # one word, optionally followed by.... +(?: +[^()<>@,;:".\\\[\]\x80-\xff\000-\010\012-\037] | # atom and space parts, or... +\( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) | # comments, or... + +" (?: # opening quote... +[^\\\x80-\xff\n\015"] # Anything except backslash and quote +| # or +\\ [^\x80-\xff] # Escaped something (something != CR) +)* " # closing quote +# quoted strings +)* +< (?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* # leading < +(?: @ (?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* (?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| \[ # [ +(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff +\] # ] +) # initial subdomain +(?: # +(?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* \. # if led by a period... +(?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* (?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| \[ # [ +(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff +\] # ] +) # ...further okay +)* + +(?: (?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* , (?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* @ (?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* (?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| \[ # [ +(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff +\] # ] +) # initial subdomain +(?: # +(?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* \. # if led by a period... +(?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* (?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| \[ # [ +(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff +\] # ] +) # ...further okay +)* +)* # further okay, if led by comma +: # closing colon +(?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* )? # optional route +(?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| +" (?: # opening quote... +[^\\\x80-\xff\n\015"] # Anything except backslash and quote +| # or +\\ [^\x80-\xff] # Escaped something (something != CR) +)* " # closing quote +) # initial word +(?: (?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* \. (?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* (?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| +" (?: # opening quote... +[^\\\x80-\xff\n\015"] # Anything except backslash and quote +| # or +\\ [^\x80-\xff] # Escaped something (something != CR) +)* " # closing quote +) )* # further okay, if led by a period +(?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* @ (?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* (?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| \[ # [ +(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff +\] # ] +) # initial subdomain +(?: # +(?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* \. # if led by a period... +(?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* (?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| \[ # [ +(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff +\] # ] +) # ...further okay +)* +# address spec +(?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* > # trailing > +# name and address +) (?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* # optional trailing comment +/x + Alan Other + + address@hidden + \"A. Other\" (a comment) + A. Other (a comment) + \"/s=user/ou=host/o=place/prmd=uu.yy/admd= /c=gb/\"address@hidden + 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 + + address@hidden + \"A. Other\" (a comment) + A. Other (a comment) + \"/s=user/ou=host/o=place/prmd=uu.yy/admd= /c=gb/\"address@hidden + A missing angle + a\rb + *** Failers + a\nb + +/abc$/ + abc + abc\n + *** Failers + abc\ndef + +/(abc)\123/ + abc\x53 + +/(abc)\223/ + abc\x93 + +/(abc)\323/ + abc\xd3 + +/(abc)\100/ + abc\x40 + abc\100 + +/(abc)\1000/ + abc\x400 + abc\x40\x30 + abc\1000 + abc\100\x30 + abc\100\060 + abc\100\60 + +/abc\81/ + abc\081 + abc\0\x38\x31 + +/abc\91/ + abc\091 + abc\0\x39\x31 + +/(a)(b)(c)(d)(e)(f)(g)(h)(i)(j)(k)\12\123/ + abcdefghijk\12S + +/ab\idef/ + abidef + +/a{0}bc/ + bc + +/(a|(bc)){0,0}?xyz/ + xyz + +/abc[\10]de/ + abc\010de + +/abc[\1]de/ + abc\1de + +/(abc)[\1]de/ + abc\1de + +/(?s)a.b/ + a\nb + +/^([^a])([^\b])([^c]*)([^d]{3,4})/ + baNOTccccd + baNOTcccd + baNOTccd + bacccd + *** Failers + anything + b\bc + baccd + +/[^a]/ + Abc + +/[^a]/i + Abc + +/[^a]+/ + AAAaAbc + +/[^a]+/i + AAAaAbc + +/[^a]+/ + bbb\nccc + +/[^k]$/ + abc + *** Failers + abk + +/[^k]{2,3}$/ + abc + kbc + kabc + *** Failers + abk + akb + akk + +/^\d{8,address@hidden/ + address@hidden + address@hidden + *** Failers + address@hidden + address@hidden + +/[^a]/ + aaaabcd + aaAabcd + +/[^a]/i + aaaabcd + aaAabcd + +/[^az]/ + aaaabcd + aaAabcd + +/[^az]/i + aaaabcd + aaAabcd + +/\000\001\002\003\004\005\006\007\010\011\012\013\014\015\016\017\020\021\022\023\024\025\026\027\030\031\032\033\034\035\036\037\040\041\042\043\044\045\046\047\050\051\052\053\054\055\056\057\060\061\062\063\064\065\066\067\070\071\072\073\074\075\076\077\100\101\102\103\104\105\106\107\110\111\112\113\114\115\116\117\120\121\122\123\124\125\126\127\130\131\132\133\134\135\136\137\140\141\142\143\144\145\146\147\150\151\152\153\154\155\156\157\160\161\162\163\164\165\166\167\170\171\172\173\174\175\176\177\200\201\202\203\204\205\206\207\210\211\212\213\214\215\216\217\220\221\222\223\224\225\226\227\230\231\232\233\234\235\236\237\240\241\242\243\244\245\246\247\250\251\252\253\254\255\256\257\260\261\262\263\264\265\266\267\270\271\272\273\274\275\276\277\300\301\302\303\304\305\306\307\310\311\312\313\314\315\316\317\320\321\322\323\324\325\326\327\330\331\332\333\334\335\336\337\340\341\342\343\344\345\346\347\350\351\352\353\354\355\356\357\360\361\362\363\364\365\366 \367\370\371\372\373\374\375\376\377/ + \000\001\002\003\004\005\006\007\010\011\012\013\014\015\016\017\020\021\022\023\024\025\026\027\030\031\032\033\034\035\036\037\040\041\042\043\044\045\046\047\050\051\052\053\054\055\056\057\060\061\062\063\064\065\066\067\070\071\072\073\074\075\076\077\100\101\102\103\104\105\106\107\110\111\112\113\114\115\116\117\120\121\122\123\124\125\126\127\130\131\132\133\134\135\136\137\140\141\142\143\144\145\146\147\150\151\152\153\154\155\156\157\160\161\162\163\164\165\166\167\170\171\172\173\174\175\176\177\200\201\202\203\204\205\206\207\210\211\212\213\214\215\216\217\220\221\222\223\224\225\226\227\230\231\232\233\234\235\236\237\240\241\242\243\244\245\246\247\250\251\252\253\254\255\256\257\260\261\262\263\264\265\266\267\270\271\272\273\274\275\276\277\300\301\302\303\304\305\306\307\310\311\312\313\314\315\316\317\320\321\322\323\324\325\326\327\330\331\332\333\334\335\336\337\340\341\342\343\344\345\346\347\350\351\352\353\354\355\356\357\360\361\362\363\364\365\366 \367\370\371\372\373\374\375\376\377 + +/P[^*]TAIRE[^*]{1,6}?LL/ + xxxxxxxxxxxPSTAIREISLLxxxxxxxxx + +/P[^*]TAIRE[^*]{1,}?LL/ + xxxxxxxxxxxPSTAIREISLLxxxxxxxxx + +/(\.\d\d[1-9]?)\d+/ + 1.230003938 + 1.875000282 + 1.235 + +/(\.\d\d((?=0)|\d(?=\d)))/ + 1.230003938 + 1.875000282 + *** Failers + 1.235 + +/a(?)b/ + ab + +/\b(foo)\s+(\w+)/i + Food is on the foo table + +/foo(.*)bar/ + The food is under the bar in the barn. + +/foo(.*?)bar/ + The food is under the bar in the barn. + +/(.*)(\d*)/ + I have 2 numbers: 53147 + +/(.*)(\d+)/ + I have 2 numbers: 53147 + +/(.*?)(\d*)/ + I have 2 numbers: 53147 + +/(.*?)(\d+)/ + I have 2 numbers: 53147 + +/(.*)(\d+)$/ + I have 2 numbers: 53147 + +/(.*?)(\d+)$/ + I have 2 numbers: 53147 + +/(.*)\b(\d+)$/ + I have 2 numbers: 53147 + +/(.*\D)(\d+)$/ + I have 2 numbers: 53147 + +/^\D*(?!123)/ + ABC123 + +/^(\D*)(?=\d)(?!123)/ + ABC445 + *** Failers + ABC123 + +/^[W-]46]/ + W46]789 + -46]789 + *** Failers + Wall + Zebra + 42 + [abcd] + ]abcd[ + +/^[W-\]46]/ + W46]789 + Wall + Zebra + Xylophone + 42 + [abcd] + ]abcd[ + \\backslash + *** Failers + -46]789 + well + +/\d\d\/\d\d\/\d\d\d\d/ + 01/01/2000 + +/word (?:[a-zA-Z0-9]+ ){0,10}otherword/ + word cat dog elephant mussel cow horse canary baboon snake shark otherword + word cat dog elephant mussel cow horse canary baboon snake shark + +/word (?:[a-zA-Z0-9]+ ){0,300}otherword/ + word cat dog elephant mussel cow horse canary baboon snake shark the quick brown fox and the lazy dog and several other words getting close to thirty by now I hope + +/^(a){0,0}/ + bcd + abc + aab + +/^(a){0,1}/ + bcd + abc + aab + +/^(a){0,2}/ + bcd + abc + aab + +/^(a){0,3}/ + bcd + abc + aab + aaa + +/^(a){0,}/ + bcd + abc + aab + aaa + aaaaaaaa + +/^(a){1,1}/ + bcd + abc + aab + +/^(a){1,2}/ + bcd + abc + aab + +/^(a){1,3}/ + bcd + abc + aab + aaa + +/^(a){1,}/ + bcd + abc + aab + aaa + aaaaaaaa + +/.*\.gif/ + borfle\nbib.gif\nno + +/.{0,}\.gif/ + borfle\nbib.gif\nno + +/.*\.gif/m + borfle\nbib.gif\nno + +/.*\.gif/s + borfle\nbib.gif\nno + +/.*\.gif/ms + borfle\nbib.gif\nno + +/.*$/ + borfle\nbib.gif\nno + +/.*$/m + borfle\nbib.gif\nno + +/.*$/s + borfle\nbib.gif\nno + +/.*$/ms + borfle\nbib.gif\nno + +/.*$/ + borfle\nbib.gif\nno\n + +/.*$/m + borfle\nbib.gif\nno\n + +/.*$/s + borfle\nbib.gif\nno\n + +/.*$/ms + borfle\nbib.gif\nno\n + +/(.*X|^B)/ + abcde\n1234Xyz + BarFoo + *** Failers + abcde\nBar + +/(.*X|^B)/m + abcde\n1234Xyz + BarFoo + abcde\nBar + +/(.*X|^B)/s + abcde\n1234Xyz + BarFoo + *** Failers + abcde\nBar + +/(.*X|^B)/ms + abcde\n1234Xyz + BarFoo + abcde\nBar + +/(?s)(.*X|^B)/ + abcde\n1234Xyz + BarFoo + *** Failers + abcde\nBar + +/(?s:.*X|^B)/ + abcde\n1234Xyz + BarFoo + *** Failers + abcde\nBar + +/^.*B/ + **** Failers + abc\nB + +/(?s)^.*B/ + abc\nB + +/(?m)^.*B/ + abc\nB + +/(?ms)^.*B/ + abc\nB + +/(?ms)^B/ + abc\nB + +/(?s)B$/ + B\n + +/^[0-9][0-9][0-9][0-9][0-9][0-9][0-9][0-9][0-9][0-9][0-9][0-9]/ + 123456654321 + +/^\d\d\d\d\d\d\d\d\d\d\d\d/ + 123456654321 + +/^[\d][\d][\d][\d][\d][\d][\d][\d][\d][\d][\d][\d]/ + 123456654321 + +/^[abc]{12}/ + abcabcabcabc + +/^[a-c]{12}/ + abcabcabcabc + +/^(a|b|c){12}/ + abcabcabcabc + +/^[abcdefghijklmnopqrstuvwxy0123456789]/ + n + *** Failers + z + +/abcde{0,0}/ + abcd + *** Failers + abce + +/ab[cd]{0,0}e/ + abe + *** Failers + abcde + +/ab(c){0,0}d/ + abd + *** Failers + abcd + +/a(b*)/ + a + ab + abbbb + *** Failers + bbbbb + +/ab\d{0}e/ + abe + *** Failers + ab1e + +/"([^\\"]+|\\.)*"/ + the \"quick\" brown fox + \"the \\\"quick\\\" brown fox\" + +/.*?/g+ + abc + +/\b/g+ + abc + +/\b/+g + abc + +//g + abc + +/]{0,})>]{0,})>([\d]{0,}\.)(.*)((
([\w\W\s\d][^<>]{0,})|[\s]{0,}))<\/a><\/TD>]{0,})>([\w\W\s\d][^<>]{0,})<\/TD>]{0,})>([\w\W\s\d][^<>]{0,})<\/TD><\/TR>/is + 43.Word Processor
(N-1286)Lega lstaff.comCA - Statewide + +/a[^a]b/ + acb + a\nb + +/a.b/ + acb + *** Failers + a\nb + +/a[^a]b/s + acb + a\nb + +/a.b/s + acb + a\nb + +/^(b+?|a){1,2}?c/ + bac + bbac + bbbac + bbbbac + bbbbbac + +/^(b+|a){1,2}?c/ + bac + bbac + bbbac + bbbbac + bbbbbac + +/(?!\A)x/m + x\nb\n + a\bx\n + +/\x0{ab}/ + \0{ab} + +/(A|B)*?CD/ + CD + +/(A|B)*CD/ + CD + +/(?.*/)foo" + /this/is/a/very/long/line/in/deed/with/very/many/slashes/in/it/you/see/ + +"(?>.*/)foo" + /this/is/a/very/long/line/in/deed/with/very/many/slashes/in/and/foo + +/(?>(\.\d\d[1-9]?))\d+/ + 1.230003938 + 1.875000282 + *** Failers + 1.235 + +/^((?>\w+)|(?>\s+))*$/ + now is the time for all good men to come to the aid of the party + *** Failers + this is not a line with only words and spaces! + +/(\d+)(\w)/ + 12345a + 12345+ + +/((?>\d+))(\w)/ + 12345a + *** Failers + 12345+ + +/(?>a+)b/ + aaab + +/((?>a+)b)/ + aaab + +/(?>(a+))b/ + aaab + +/(?>b)+/ + aaabbbccc + +/(?>a+|b+|c+)*c/ + aaabbbbccccd + +/(a+|b+|c+)*c/ + aaabbbbccccd + +/((?>[^()]+)|\([^()]*\))+/ + ((abc(ade)ufh()()x + +/\(((?>[^()]+)|\([^()]+\))+\)/ + (abc) + (abc(def)xyz) + *** Failers + ((()aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa + +/a(?-i)b/i + ab + Ab + *** Failers + aB + AB + +/(a (?x)b c)d e/ + a bcd e + *** Failers + a b cd e + abcd e + a bcde + +/(a b(?x)c d (?-x)e f)/ + a bcde f + *** Failers + abcdef + +/(a(?i)b)c/ + abc + aBc + *** Failers + abC + aBC + Abc + ABc + ABC + AbC + +/a(?i:b)c/ + abc + aBc + *** Failers + ABC + abC + aBC + +/a(?i:b)*c/ + aBc + aBBc + *** Failers + aBC + aBBC + +/a(?=b(?i)c)\w\wd/ + abcd + abCd + *** Failers + aBCd + abcD + +/(?s-i:more.*than).*million/i + more than million + more than MILLION + more \n than Million + *** Failers + MORE THAN MILLION + more \n than \n million + +/(?:(?s-i)more.*than).*million/i + more than million + more than MILLION + more \n than Million + *** Failers + MORE THAN MILLION + more \n than \n million + +/(?>a(?i)b+)+c/ + abc + aBbc + aBBc + *** Failers + Abc + abAb + abbC + +/(?=a(?i)b)\w\wc/ + abc + aBc + *** Failers + Ab + abC + aBC + +/(?<=a(?i)b)(\w\w)c/ + abxxc + aBxxc + *** Failers + Abxxc + ABxxc + abxxC + +/^(?(?=abc)\w{3}:|\d\d)$/ + abc: + 12 + *** Failers + 123 + xyz + +/^(?(?!abc)\d\d|\w{3}:)$/ + abc: + 12 + *** Failers + 123 + xyz + +/(?(?<=foo)bar|cat)/ + foobar + cat + fcat + focat + *** Failers + foocat + +/(?(?a*)*/ + a + aa + aaaa + +/(abc|)+/ + abc + abcabc + abcabcabc + xyz + +/([a]*)*/ + a + aaaaa + +/([ab]*)*/ + a + b + ababab + aaaabcde + bbbb + +/([^a]*)*/ + b + bbbb + aaa + +/([^ab]*)*/ + cccc + abab + +/([a]*?)*/ + a + aaaa + +/([ab]*?)*/ + a + b + abab + baba + +/([^a]*?)*/ + b + bbbb + aaa + +/([^ab]*?)*/ + c + cccc + baba + +/(?>a*)*/ + a + aaabcde + +/((?>a*))*/ + aaaaa + aabbaa + +/((?>a*?))*/ + aaaaa + aabbaa + +/(?(?=[^a-z]+[a-z]) \d{2}-[a-z]{3}-\d{2} | \d{2}-\d{2}-\d{2} ) /x + 12-sep-98 + 12-09-98 + *** Failers + sep-12-98 + +/(?i:saturday|sunday)/ + saturday + sunday + Saturday + Sunday + SATURDAY + SUNDAY + SunDay + +/(a(?i)bc|BB)x/ + abcx + aBCx + bbx + BBx + *** Failers + abcX + aBCX + bbX + BBX + +/^([ab](?i)[cd]|[ef])/ + ac + aC + bD + elephant + Europe + frog + France + *** Failers + Africa + +/^(ab|a(?i)[b-c](?m-i)d|x(?i)y|z)/ + ab + aBd + xy + xY + zebra + Zambesi + *** Failers + aCD + XY + +/(?<=foo\n)^bar/m + foo\nbar + *** Failers + bar + baz\nbar + +/(?<=(?]&/ + <&OUT + +/(?:(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 + +/(?>.*)(?<=(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}...)(?Z)+|A)*/ + ZABCDEFG + +/((?>)+|A)*/ + ZABCDEFG + +/a*/g + abbab + +/^[a-\d]/ + abcde + -things + 0digit + *** Failers + bcdef + +/^[\d-a]/ + abcde + -things + 0digit + *** Failers + bcdef + +/[[:space:]]+/ + > \x09\x0a\x0c\x0d\x0b< + +/[[:blank:]]+/ + > \x09\x0a\x0c\x0d\x0b< + +/[\s]+/ + > \x09\x0a\x0c\x0d\x0b< + +/\s+/ + > \x09\x0a\x0c\x0d\x0b< + +/a b/x + ab + +/(?!\A)x/m + a\nxb\n + +/(?!^)x/m + a\nxb\n + +/abc\Qabc\Eabc/ + abcabcabc + +/abc\Q(*+|\Eabc/ + abc(*+|abc + +/ abc\Q abc\Eabc/x + abc abcabc + *** Failers + abcabcabc + +/abc#comment + \Q#not comment + literal\E/x + abc#not comment\n literal + +/abc#comment + \Q#not comment + literal/x + abc#not comment\n literal + +/abc#comment + \Q#not comment + literal\E #more comment + /x + abc#not comment\n literal + +/abc#comment + \Q#not comment + literal\E #more comment/x + abc#not comment\n literal + +/\Qabc\$xyz\E/ + abc\\\$xyz + +/\Qabc\E\$\Qxyz\E/ + abc\$xyz + +/\Gabc/ + abc + *** Failers + xyzabc + +/\Gabc./g + abc1abc2xyzabc3 + +/abc./g + abc1abc2xyzabc3 + +/a(?x: b c )d/ + XabcdY + *** Failers + Xa b c d Y + +/((?x)x y z | a b c)/ + XabcY + AxyzB + +/(?i)AB(?-i)C/ + XabCY + *** Failers + XabcY + +/((?i)AB(?-i)C|D)E/ + abCE + DE + *** Failers + abcE + abCe + dE + De + +/[z\Qa-d]\E]/ + z + a + - + d + ] + *** Failers + b + +/[\z\C]/ + z + C + +/\M/ + M + +/(a+)*b/ + aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa + +/(?i)reg(?:ul(?:[aä]|ae)r|ex)/ + REGular + regulaer + Regex + regulär + +/Åæåä[à-ÿÀ-ß]+/ + Åæåäà + Åæåäÿ + ÅæåäÀ + Åæåäß + +/(?<=Z)X./ + \x84XAZXB + +/^(?(2)a|(1)(2))+$/ + 123a + +/(?<=a|bbbb)c/ + ac + bbbbc + +/abc/>testsavedregex +testsavedregex +testsavedregex +testsavedregex + + xyz\r\nabc\ + xyz\rabc\ + xyz\r\nabc\ + ** Failers + xyz\nabc\ + xyz\r\nabc\ + xyz\nabc\ + xyz\rabc\ + xyz\rabc\ + +/abc$/m + xyzabc + xyzabc\n + xyzabc\npqr + xyzabc\r\ + xyzabc\rpqr\ + xyzabc\r\n\ + xyzabc\r\npqr\ + ** Failers + xyzabc\r + xyzabc\rpqr + xyzabc\r\n + xyzabc\r\npqr + +/^abc/m + xyz\rabcdef + xyz\nabcdef\ + ** Failers + xyz\nabcdef + +/^abc/m + xyz\nabcdef + xyz\rabcdef\ + ** Failers + xyz\rabcdef + +/^abc/m + xyz\r\nabcdef + xyz\rabcdef\ + ** Failers + xyz\rabcdef + +/.*/ + abc\ndef + abc\rdef + abc\r\ndef + \abc\ndef + \abc\rdef + \abc\r\ndef + \abc\ndef + \abc\rdef + \abc\r\ndef + +/\w+(.)(.)?def/s + abc\ndef + abc\rdef + abc\r\ndef + +/^\w+=.*(\\\n.*)*/ + abc=xyz\\\npqr + +/^(a()*)*/ + aaaa + +/^(?:a(?:(?:))*)*/ + aaaa + +/^(a()+)+/ + aaaa + +/^(?:a(?:(?:))+)+/ + aaaa + +/(a|)*\d/ + aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa + aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa4 + +/(?>a|)*\d/ + aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa + aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa4 + +/(?:a|)*\d/ + aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa + aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa4 + +/^a.b/ + a\rb + a\nb\ + ** Failers + a\nb + a\nb\ + a\rb\ + a\rb\ + +/^abc./mgx + abc1 \x0aabc2 \x0babc3xx \x0cabc4 \x0dabc5xx \x0d\x0aabc6 \x85abc7 \x{2028}abc8 \x{2029}abc9 JUNK + +/abc.$/mgx + abc1\x0a abc2\x0b abc3\x0c abc4\x0d abc5\x0d\x0a abc6\x85 abc7\x{2028} abc8\x{2029} abc9 + +/^a\Rb/ + a\nb + a\rb + a\r\nb + a\x0bb + a\x0cb + a\x85b + ** Failers + a\n\rb + +/^a\R*b/ + ab + a\nb + a\rb + a\r\nb + a\x0bb + a\x0cb + a\x85b + a\n\rb + a\n\r\x85\x0cb + +/^a\R+b/ + a\nb + a\rb + a\r\nb + a\x0bb + a\x0cb + a\x85b + a\n\rb + a\n\r\x85\x0cb + ** Failers + ab + +/^a\R{1,3}b/ + a\nb + a\n\rb + a\n\r\x85b + a\r\n\r\nb + a\r\n\r\n\r\nb + a\n\r\n\rb + a\n\n\r\nb + ** Failers + a\n\n\n\rb + a\r + +/^a[\R]b/ + aRb + ** Failers + a\nb + +/.+foo/ + afoo + ** Failers + \r\nfoo + \nfoo + +/.+foo/ + afoo + \nfoo + ** Failers + \r\nfoo + +/.+foo/ + afoo + ** Failers + \nfoo + \r\nfoo + +/.+foo/s + afoo + \r\nfoo + \nfoo + +/^$/mg + abc\r\rxyz + abc\n\rxyz + ** Failers + abc\r\nxyz + +/^X/m + XABC + ** Failers + XABC\B + +/(?m)^$/g+ + abc\r\n\r\n + +/(?m)^$|^\r\n/g+ + abc\r\n\r\n + +/(?m)$/g+ + abc\r\n\r\n + +/(?|(abc)|(xyz))/ + >abc< + >xyz< + +/(x)(?|(abc)|(xyz))(x)/ + xabcx + xxyzx + +/(x)(?|(abc)(pqr)|(xyz))(x)/ + xabcpqrx + xxyzx + +/(?|(abc)|(xyz))(?1)/ + abcabc + xyzabc + ** Failers + xyzxyz + +/\H\h\V\v/ + X X\x0a + X\x09X\x0b + ** Failers + \xa0 X\x0a + +/\H*\h+\V?\v{3,4}/ + \x09\x20\xa0X\x0a\x0b\x0c\x0d\x0a + \x09\x20\xa0\x0a\x0b\x0c\x0d\x0a + \x09\x20\xa0\x0a\x0b\x0c + ** Failers + \x09\x20\xa0\x0a\x0b + +/\H{3,4}/ + XY ABCDE + XY PQR ST + +/.\h{3,4}./ + XY AB PQRS + +/\h*X\h?\H+Y\H?Z/ + >XNNNYZ + > X NYQZ + ** Failers + >XYZ + > X NY Z + +/\v*X\v?Y\v+Z\V*\x0a\V+\x0b\V{2,3}\x0c/ + >XY\x0aZ\x0aA\x0bNN\x0c + >\x0a\x0dX\x0aY\x0a\x0bZZZ\x0aAAA\x0bNNN\x0c + +/.+A/ + \r\nA + +/\nA/ + \r\nA + +/[\r\n]A/ + \r\nA + +/(\r|\n)A/ + \r\nA + +/a\Rb/I + a\rb + a\nb + a\r\nb + ** Failers + a\x85b + a\x0bb + +/a\Rb/I + a\rb + a\nb + a\r\nb + a\x85b + a\x0bb + ** Failers + a\x85b\ + a\x0bb\ + +/a\R?b/I + a\rb + a\nb + a\r\nb + ** Failers + a\x85b + a\x0bb + +/a\R?b/I + a\rb + a\nb + a\r\nb + a\x85b + a\x0bb + ** Failers + a\x85b\ + a\x0bb\ + +/a\R{2,4}b/I + a\r\n\nb + a\n\r\rb + a\r\n\r\n\r\n\r\nb + ** Failers + a\x85\85b + a\x0b\0bb + +/a\R{2,4}b/I + a\r\rb + a\n\n\nb + a\r\n\n\r\rb + a\x85\85b + a\x0b\0bb + ** Failers + a\r\r\r\r\rb + a\x85\85b\ + a\x0b\0bb\ + +/ End of testinput7 / ============================================================ --- pcre/testdata/testinput8 093f7be73e2abafdc80b27118e73c91af35de039 +++ pcre/testdata/testinput8 093f7be73e2abafdc80b27118e73c91af35de039 @@ -0,0 +1,667 @@ +/-- Do not use the \x{} construct except with patterns that have the --/ +/-- /8 option set, because PCRE doesn't recognize them as UTF-8 unless --/ +/-- that option is set. However, the latest Perls recognize them always. --/ + +/\x{100}ab/8 + \x{100}ab + +/a\x{100}*b/8 + ab + a\x{100}b + a\x{100}\x{100}b + +/a\x{100}+b/8 + a\x{100}b + a\x{100}\x{100}b + *** Failers + ab + +/\bX/8 + Xoanon + +Xoanon + \x{300}Xoanon + *** Failers + YXoanon + +/\BX/8 + YXoanon + *** Failers + Xoanon + +Xoanon + \x{300}Xoanon + +/X\b/8 + X+oanon + ZX\x{300}oanon + FAX + *** Failers + Xoanon + +/X\B/8 + Xoanon + *** Failers + X+oanon + ZX\x{300}oanon + FAX + +/[^a]/8 + abcd + a\x{100} + +/^[abc\x{123}\x{400}-\x{402}]{2,3}\d/8 + ab99 + \x{123}\x{123}45 + \x{400}\x{401}\x{402}6 + *** Failers + d99 + \x{123}\x{122}4 + \x{400}\x{403}6 + \x{400}\x{401}\x{402}\x{402}6 + +/abc/8 + Ã] + à + ÃÃà + ÃÃÃ\? + +/a.b/8 + acb + a\x7fb + a\x{100}b + *** Failers + a\nb + +/a(.{3})b/8 + a\x{4000}xyb + a\x{4000}\x7fyb + a\x{4000}\x{100}yb + *** Failers + a\x{4000}b + ac\ncb + +/a(.*?)(.)/ + a\xc0\x88b + +/a(.*?)(.)/8 + a\x{100}b + +/a(.*)(.)/ + a\xc0\x88b + +/a(.*)(.)/8 + a\x{100}b + +/a(.)(.)/ + a\xc0\x92bcd + +/a(.)(.)/8 + a\x{240}bcd + +/a(.?)(.)/ + a\xc0\x92bcd + +/a(.?)(.)/8 + a\x{240}bcd + +/a(.??)(.)/ + a\xc0\x92bcd + +/a(.??)(.)/8 + a\x{240}bcd + +/a(.{3})b/8 + a\x{1234}xyb + a\x{1234}\x{4321}yb + a\x{1234}\x{4321}\x{3412}b + *** Failers + a\x{1234}b + ac\ncb + +/a(.{3,})b/8 + a\x{1234}xyb + a\x{1234}\x{4321}yb + a\x{1234}\x{4321}\x{3412}b + axxxxbcdefghijb + a\x{1234}\x{4321}\x{3412}\x{3421}b + *** Failers + a\x{1234}b + +/a(.{3,}?)b/8 + a\x{1234}xyb + a\x{1234}\x{4321}yb + a\x{1234}\x{4321}\x{3412}b + axxxxbcdefghijb + a\x{1234}\x{4321}\x{3412}\x{3421}b + *** Failers + a\x{1234}b + +/a(.{3,5})b/8 + a\x{1234}xyb + a\x{1234}\x{4321}yb + a\x{1234}\x{4321}\x{3412}b + axxxxbcdefghijb + a\x{1234}\x{4321}\x{3412}\x{3421}b + axbxxbcdefghijb + axxxxxbcdefghijb + *** Failers + a\x{1234}b + axxxxxxbcdefghijb + +/a(.{3,5}?)b/8 + a\x{1234}xyb + a\x{1234}\x{4321}yb + a\x{1234}\x{4321}\x{3412}b + axxxxbcdefghijb + a\x{1234}\x{4321}\x{3412}\x{3421}b + axbxxbcdefghijb + axxxxxbcdefghijb + *** Failers + a\x{1234}b + axxxxxxbcdefghijb + +/^[a\x{c0}]/8 + *** Failers + \x{100} + +/(?<=aXb)cd/8 + aXbcd + +/(?<=a\x{100}b)cd/8 + a\x{100}bcd + +/(?<=a\x{100000}b)cd/8 + a\x{100000}bcd + +/(?:\x{100}){3}b/8 + \x{100}\x{100}\x{100}b + *** Failers + \x{100}\x{100}b + +/\x{ab}/8 + \x{ab} + \xc2\xab + *** Failers + \x00{ab} + +/(?<=(.))X/8 + WXYZ + \x{256}XYZ + *** Failers + XYZ + +/[^a]+/8g + bcd + \x{100}aY\x{256}Z + +/^[^a]{2}/8 + \x{100}bc + +/^[^a]{2,}/8 + \x{100}bcAa + +/^[^a]{2,}?/8 + \x{100}bca + +/[^a]+/8ig + bcd + \x{100}aY\x{256}Z + +/^[^a]{2}/8i + \x{100}bc + +/^[^a]{2,}/8i + \x{100}bcAa + +/^[^a]{2,}?/8i + \x{100}bca + +/\x{100}{0,0}/8 + abcd + +/\x{100}?/8 + abcd + \x{100}\x{100} + +/\x{100}{0,3}/8 + \x{100}\x{100} + \x{100}\x{100}\x{100}\x{100} + +/\x{100}*/8 + abce + \x{100}\x{100}\x{100}\x{100} + +/\x{100}{1,1}/8 + abcd\x{100}\x{100}\x{100}\x{100} + +/\x{100}{1,3}/8 + abcd\x{100}\x{100}\x{100}\x{100} + +/\x{100}+/8 + abcd\x{100}\x{100}\x{100}\x{100} + +/\x{100}{3}/8 + abcd\x{100}\x{100}\x{100}XX + +/\x{100}{3,5}/8 + abcd\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}XX + +/\x{100}{3,}/8 + abcd\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}XX + +/(?<=a\x{100}{2}b)X/8 + Xyyya\x{100}\x{100}bXzzz + +/\D*/8 + aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa + +/\D*/8 + \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100} \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100} + +/\D/8 + 1X2 + 1\x{100}2 + +/>\S/8 + > >X Y + > >\x{100} Y + +/\d/8 + \x{100}3 + +/\s/8 + \x{100} X + +/\D+/8 + 12abcd34 + *** Failers + 1234 + +/\D{2,3}/8 + 12abcd34 + 12ab34 + *** Failers + 1234 + 12a34 + +/\D{2,3}?/8 + 12abcd34 + 12ab34 + *** Failers + 1234 + 12a34 + +/\d+/8 + 12abcd34 + *** Failers + +/\d{2,3}/8 + 12abcd34 + 1234abcd + *** Failers + 1.4 + +/\d{2,3}?/8 + 12abcd34 + 1234abcd + *** Failers + 1.4 + +/\S+/8 + 12abcd34 + *** Failers + \ \ + +/\S{2,3}/8 + 12abcd34 + 1234abcd + *** Failers + \ \ + +/\S{2,3}?/8 + 12abcd34 + 1234abcd + *** Failers + \ \ + +/>\s+ <34 + *** Failers + +/>\s{2,3} \s{2,3}? \xff< + +/[\xff]/8 + >\x{ff}< + +/[^\xFF]/ + XYZ + +/[^\xff]/8 + XYZ + \x{123} + +/^[ac]*b/8 + xb + +/^[ac\x{100}]*b/8 + xb + +/^[^x]*b/8i + xb + +/^[^x]*b/8 + xb + +/^\d*b/8 + xb + +/(|a)/g8 + catac + a\x{256}a + +/^\x{85}$/8i + \x{85} + +/^abc./mgx8 + abc1 \x0aabc2 \x0babc3xx \x0cabc4 \x0dabc5xx \x0d\x0aabc6 \x{0085}abc7 \x{2028}abc8 \x{2029}abc9 JUNK + +/abc.$/mgx8 + abc1\x0a abc2\x0b abc3\x0c abc4\x0d abc5\x0d\x0a abc6\x{0085} abc7\x{2028} abc8\x{2029} abc9 + +/^a\Rb/8 + a\nb + a\rb + a\r\nb + a\x0bb + a\x0cb + a\x{85}b + a\x{2028}b + a\x{2029}b + ** Failers + a\n\rb + +/^a\R*b/8 + ab + a\nb + a\rb + a\r\nb + a\x0bb + a\x0c\x{2028}\x{2029}b + a\x{85}b + a\n\rb + a\n\r\x{85}\x0cb + +/^a\R+b/8 + a\nb + a\rb + a\r\nb + a\x0bb + a\x0c\x{2028}\x{2029}b + a\x{85}b + a\n\rb + a\n\r\x{85}\x0cb + ** Failers + ab + +/^a\R{1,3}b/8 + a\nb + a\n\rb + a\n\r\x{85}b + a\r\n\r\nb + a\r\n\r\n\r\nb + a\n\r\n\rb + a\n\n\r\nb + ** Failers + a\n\n\n\rb + a\r + +/\h+\V?\v{3,4}/8 + \x09\x20\x{a0}X\x0a\x0b\x0c\x0d\x0a + +/\V?\v{3,4}/8 + \x20\x{a0}X\x0a\x0b\x0c\x0d\x0a + +/\h+\V?\v{3,4}/8 + >\x09\x20\x{a0}X\x0a\x0a\x0a< + +/\V?\v{3,4}/8 + >\x09\x20\x{a0}X\x0a\x0a\x0a< + +/\H\h\V\v/8 + X X\x0a + X\x09X\x0b + ** Failers + \x{a0} X\x0a + +/\H*\h+\V?\v{3,4}/8 + \x09\x20\x{a0}X\x0a\x0b\x0c\x0d\x0a + \x09\x20\x{a0}\x0a\x0b\x0c\x0d\x0a + \x09\x20\x{a0}\x0a\x0b\x0c + ** Failers + \x09\x20\x{a0}\x0a\x0b + +/\H\h\V\v/8 + \x{3001}\x{3000}\x{2030}\x{2028} + X\x{180e}X\x{85} + ** Failers + \x{2009} X\x0a + +/\H*\h+\V?\v{3,4}/8 + \x{1680}\x{180e}\x{2007}X\x{2028}\x{2029}\x0c\x0d\x0a + \x09\x{205f}\x{a0}\x0a\x{2029}\x0c\x{2028}\x0a + \x09\x20\x{202f}\x0a\x0b\x0c + ** Failers + \x09\x{200a}\x{a0}\x{2028}\x0b + +/a\Rb/I8 + a\rb + a\nb + a\r\nb + ** Failers + a\x{85}b + a\x0bb + +/a\Rb/I8 + a\rb + a\nb + a\r\nb + a\x{85}b + a\x0bb + ** Failers + a\x{85}b\ + a\x0bb\ + +/a\R?b/I8 + a\rb + a\nb + a\r\nb + ** Failers + a\x{85}b + a\x0bb + +/a\R?b/I8 + a\rb + a\nb + a\r\nb + a\x{85}b + a\x0bb + ** Failers + a\x{85}b\ + a\x0bb\ + +/ End of testinput 8 / ============================================================ --- pcre/testdata/testinput9 759482b0f140104cc0ffa7614dc22ac4151e43ff +++ pcre/testdata/testinput9 759482b0f140104cc0ffa7614dc22ac4151e43ff @@ -0,0 +1,828 @@ +/\pL\P{Nd}/8 + AB + *** Failers + A0 + 00 + +/\X./8 + AB + A\x{300}BC + A\x{300}\x{301}\x{302}BC + *** Failers + \x{300} + +/\X\X/8 + ABC + A\x{300}B\x{300}\x{301}C + A\x{300}\x{301}\x{302}BC + *** Failers + \x{300} + +/^\pL+/8 + abcd + a + *** Failers + +/^\PL+/8 + 1234 + = + *** Failers + abcd + +/^\X+/8 + abcdA\x{300}\x{301}\x{302} + A\x{300}\x{301}\x{302} + A\x{300}\x{301}\x{302}A\x{300}\x{301}\x{302} + a + *** Failers + \x{300}\x{301}\x{302} + +/\X?abc/8 + abc + A\x{300}abc + A\x{300}\x{301}\x{302}A\x{300}A\x{300}A\x{300}abcxyz + \x{300}abc + *** Failers + +/^\X?abc/8 + abc + A\x{300}abc + *** Failers + A\x{300}\x{301}\x{302}A\x{300}A\x{300}A\x{300}abcxyz + \x{300}abc + +/\X*abc/8 + abc + A\x{300}abc + A\x{300}\x{301}\x{302}A\x{300}A\x{300}A\x{300}abcxyz + \x{300}abc + *** Failers + +/^\X*abc/8 + abc + A\x{300}abc + A\x{300}\x{301}\x{302}A\x{300}A\x{300}A\x{300}abcxyz + *** Failers + \x{300}abc + +/^\pL?=./8 + A=b + =c + *** Failers + 1=2 + AAAA=b + +/^\pL*=./8 + AAAA=b + =c + *** Failers + 1=2 + +/^\X{2,3}X/8 + A\x{300}\x{301}\x{302}A\x{300}\x{301}\x{302}X + A\x{300}\x{301}\x{302}A\x{300}\x{301}\x{302}A\x{300}\x{301}\x{302}X + *** Failers + X + A\x{300}\x{301}\x{302}X + A\x{300}\x{301}\x{302}A\x{300}\x{301}\x{302}A\x{300}\x{301}\x{302}A\x{300}\x{301}\x{302}X + +/^\pC\pL\pM\pN\pP\pS\pZ>>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: address@hidden + address@hidden + 0: address@hidden + \"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/\"address@hidden + 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: address@hidden + address@hidden + 0: address@hidden + \"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/\"address@hidden + 0: "/s=user/ou=host/o=place/prmd=uu.yy/admd= /c=gb/"@x400-re.lay + A missing angle address@hidden|}~\x7f\x80\x81\x82\x83\x84\x85\x86\x87\x88\x89\x8a\x8b\x8c\x8d\x8e\x8f\x90\x91\x92\x93\x94\x95\x96\x97\x98\x99\x9a\x9b\x9c\x9d\x9e\x9f\xa0\xa1\xa2\xa3\xa4\xa5\xa6\xa7\xa8\xa9\xaa\xab\xac\xad\xae\xaf\xb0\xb1\xb2\xb3\xb4\xb5\xb6\xb7\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf\xc0\xc1\xc2\xc3\xc4\xc5\xc6\xc7\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf\xd0\xd1\xd2\xd3\xd4\xd5\xd6\xd7\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7\xe8\xe9\xea\xeb\xec\xed\xee\xef\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff + +/P[^*]TAIRE[^*]{1,6}?LL/ + xxxxxxxxxxxPSTAIREISLLxxxxxxxxx + 0: PSTAIREISLL + +/P[^*]TAIRE[^*]{1,}?LL/ + xxxxxxxxxxxPSTAIREISLLxxxxxxxxx + 0: PSTAIREISLL + +/(\.\d\d[1-9]?)\d+/ + 1.230003938 + 0: .230003938 + 1: .23 + 1.875000282 + 0: .875000282 + 1: .875 + 1.235 + 0: .235 + 1: .23 + +/(\.\d\d((?=0)|\d(?=\d)))/ + 1.230003938 + 0: .23 + 1: .23 + 2: + 1.875000282 + 0: .875 + 1: .875 + 2: 5 + *** Failers +No match + 1.235 +No match + +/a(?)b/ + ab + 0: ab + +/\b(foo)\s+(\w+)/i + Food is on the foo table + 0: foo table + 1: foo + 2: table + +/foo(.*)bar/ + The food is under the bar in the barn. + 0: food is under the bar in the bar + 1: d is under the bar in the + +/foo(.*?)bar/ + The food is under the bar in the barn. + 0: food is under the bar + 1: d is under the + +/(.*)(\d*)/ + I have 2 numbers: 53147 + 0: I have 2 numbers: 53147 + 1: I have 2 numbers: 53147 + 2: + +/(.*)(\d+)/ + I have 2 numbers: 53147 + 0: I have 2 numbers: 53147 + 1: I have 2 numbers: 5314 + 2: 7 + +/(.*?)(\d*)/ + I have 2 numbers: 53147 + 0: + 1: + 2: + +/(.*?)(\d+)/ + I have 2 numbers: 53147 + 0: I have 2 + 1: I have + 2: 2 + +/(.*)(\d+)$/ + I have 2 numbers: 53147 + 0: I have 2 numbers: 53147 + 1: I have 2 numbers: 5314 + 2: 7 + +/(.*?)(\d+)$/ + I have 2 numbers: 53147 + 0: I have 2 numbers: 53147 + 1: I have 2 numbers: + 2: 53147 + +/(.*)\b(\d+)$/ + I have 2 numbers: 53147 + 0: I have 2 numbers: 53147 + 1: I have 2 numbers: + 2: 53147 + +/(.*\D)(\d+)$/ + I have 2 numbers: 53147 + 0: I have 2 numbers: 53147 + 1: I have 2 numbers: + 2: 53147 + +/^\D*(?!123)/ + ABC123 + 0: AB + +/^(\D*)(?=\d)(?!123)/ + ABC445 + 0: ABC + 1: ABC + *** Failers +No match + ABC123 +No match + +/^[W-]46]/ + W46]789 + 0: W46] + -46]789 + 0: -46] + *** Failers +No match + Wall +No match + Zebra +No match + 42 +No match + [abcd] +No match + ]abcd[ +No match + +/^[W-\]46]/ + W46]789 + 0: W + Wall + 0: W + Zebra + 0: Z + Xylophone + 0: X + 42 + 0: 4 + [abcd] + 0: [ + ]abcd[ + 0: ] + \\backslash + 0: \ + *** Failers +No match + -46]789 +No match + well +No match + +/\d\d\/\d\d\/\d\d\d\d/ + 01/01/2000 + 0: 01/01/2000 + +/word (?:[a-zA-Z0-9]+ ){0,10}otherword/ + word cat dog elephant mussel cow horse canary baboon snake shark otherword + 0: word cat dog elephant mussel cow horse canary baboon snake shark otherword + word cat dog elephant mussel cow horse canary baboon snake shark +No match + +/word (?:[a-zA-Z0-9]+ ){0,300}otherword/ + word cat dog elephant mussel cow horse canary baboon snake shark the quick brown fox and the lazy dog and several other words getting close to thirty by now I hope +No match + +/^(a){0,0}/ + bcd + 0: + abc + 0: + aab + 0: + +/^(a){0,1}/ + bcd + 0: + abc + 0: a + 1: a + aab + 0: a + 1: a + +/^(a){0,2}/ + bcd + 0: + abc + 0: a + 1: a + aab + 0: aa + 1: a + +/^(a){0,3}/ + bcd + 0: + abc + 0: a + 1: a + aab + 0: aa + 1: a + aaa + 0: aaa + 1: a + +/^(a){0,}/ + bcd + 0: + abc + 0: a + 1: a + aab + 0: aa + 1: a + aaa + 0: aaa + 1: a + aaaaaaaa + 0: aaaaaaaa + 1: a + +/^(a){1,1}/ + bcd +No match + abc + 0: a + 1: a + aab + 0: a + 1: a + +/^(a){1,2}/ + bcd +No match + abc + 0: a + 1: a + aab + 0: aa + 1: a + +/^(a){1,3}/ + bcd +No match + abc + 0: a + 1: a + aab + 0: aa + 1: a + aaa + 0: aaa + 1: a + +/^(a){1,}/ + bcd +No match + abc + 0: a + 1: a + aab + 0: aa + 1: a + aaa + 0: aaa + 1: a + aaaaaaaa + 0: aaaaaaaa + 1: a + +/.*\.gif/ + borfle\nbib.gif\nno + 0: bib.gif + +/.{0,}\.gif/ + borfle\nbib.gif\nno + 0: bib.gif + +/.*\.gif/m + borfle\nbib.gif\nno + 0: bib.gif + +/.*\.gif/s + borfle\nbib.gif\nno + 0: borfle\x0abib.gif + +/.*\.gif/ms + borfle\nbib.gif\nno + 0: borfle\x0abib.gif + +/.*$/ + borfle\nbib.gif\nno + 0: no + +/.*$/m + borfle\nbib.gif\nno + 0: borfle + +/.*$/s + borfle\nbib.gif\nno + 0: borfle\x0abib.gif\x0ano + +/.*$/ms + borfle\nbib.gif\nno + 0: borfle\x0abib.gif\x0ano + +/.*$/ + borfle\nbib.gif\nno\n + 0: no + +/.*$/m + borfle\nbib.gif\nno\n + 0: borfle + +/.*$/s + borfle\nbib.gif\nno\n + 0: borfle\x0abib.gif\x0ano\x0a + +/.*$/ms + borfle\nbib.gif\nno\n + 0: borfle\x0abib.gif\x0ano\x0a + +/(.*X|^B)/ + abcde\n1234Xyz + 0: 1234X + 1: 1234X + BarFoo + 0: B + 1: B + *** Failers +No match + abcde\nBar +No match + +/(.*X|^B)/m + abcde\n1234Xyz + 0: 1234X + 1: 1234X + BarFoo + 0: B + 1: B + abcde\nBar + 0: B + 1: B + +/(.*X|^B)/s + abcde\n1234Xyz + 0: abcde\x0a1234X + 1: abcde\x0a1234X + BarFoo + 0: B + 1: B + *** Failers +No match + abcde\nBar +No match + +/(.*X|^B)/ms + abcde\n1234Xyz + 0: abcde\x0a1234X + 1: abcde\x0a1234X + BarFoo + 0: B + 1: B + abcde\nBar + 0: B + 1: B + +/(?s)(.*X|^B)/ + abcde\n1234Xyz + 0: abcde\x0a1234X + 1: abcde\x0a1234X + BarFoo + 0: B + 1: B + *** Failers +No match + abcde\nBar +No match + +/(?s:.*X|^B)/ + abcde\n1234Xyz + 0: abcde\x0a1234X + BarFoo + 0: B + *** Failers +No match + abcde\nBar +No match + +/^.*B/ + **** Failers +No match + abc\nB +No match + +/(?s)^.*B/ + abc\nB + 0: abc\x0aB + +/(?m)^.*B/ + abc\nB + 0: B + +/(?ms)^.*B/ + abc\nB + 0: abc\x0aB + +/(?ms)^B/ + abc\nB + 0: B + +/(?s)B$/ + B\n + 0: B + +/^[0-9][0-9][0-9][0-9][0-9][0-9][0-9][0-9][0-9][0-9][0-9][0-9]/ + 123456654321 + 0: 123456654321 + +/^\d\d\d\d\d\d\d\d\d\d\d\d/ + 123456654321 + 0: 123456654321 + +/^[\d][\d][\d][\d][\d][\d][\d][\d][\d][\d][\d][\d]/ + 123456654321 + 0: 123456654321 + +/^[abc]{12}/ + abcabcabcabc + 0: abcabcabcabc + +/^[a-c]{12}/ + abcabcabcabc + 0: abcabcabcabc + +/^(a|b|c){12}/ + abcabcabcabc + 0: abcabcabcabc + 1: c + +/^[abcdefghijklmnopqrstuvwxy0123456789]/ + n + 0: n + *** Failers +No match + z +No match + +/abcde{0,0}/ + abcd + 0: abcd + *** Failers +No match + abce +No match + +/ab[cd]{0,0}e/ + abe + 0: abe + *** Failers +No match + abcde +No match + +/ab(c){0,0}d/ + abd + 0: abd + *** Failers +No match + abcd +No match + +/a(b*)/ + a + 0: a + 1: + ab + 0: ab + 1: b + abbbb + 0: abbbb + 1: bbbb + *** Failers + 0: a + 1: + bbbbb +No match + +/ab\d{0}e/ + abe + 0: abe + *** Failers +No match + ab1e +No match + +/"([^\\"]+|\\.)*"/ + the \"quick\" brown fox + 0: "quick" + 1: quick + \"the \\\"quick\\\" brown fox\" + 0: "the \"quick\" brown fox" + 1: brown fox + +/.*?/g+ + abc + 0: + 0+ abc + 0: a + 0+ bc + 0: + 0+ bc + 0: b + 0+ c + 0: + 0+ c + 0: c + 0+ + 0: + 0+ + +/\b/g+ + abc + 0: + 0+ abc + 0: + 0+ + +/\b/+g + abc + 0: + 0+ abc + 0: + 0+ + +//g + abc + 0: + 0: + 0: + 0: + +/]{0,})>]{0,})>([\d]{0,}\.)(.*)((
([\w\W\s\d][^<>]{0,})|[\s]{0,}))<\/a><\/TD>]{0,})>([\w\W\s\d][^<>]{0,})<\/TD>]{0,})>([\w\W\s\d][^<>]{0,})<\/TD><\/TR>/is + 43.Word Processor
(N-1286)Lega lstaff.comCA - Statewide + 0: 43.Word Processor
(N-1286)Lega lstaff.comCA - Statewide + 1: BGCOLOR='#DBE9E9' + 2: align=left valign=top + 3: 43. + 4: Word Processor
(N-1286) + 5: + 6: + 7: + 8: align=left valign=top + 9: Lega lstaff.com +10: align=left valign=top +11: CA - Statewide + +/a[^a]b/ + acb + 0: acb + a\nb + 0: a\x0ab + +/a.b/ + acb + 0: acb + *** Failers +No match + a\nb +No match + +/a[^a]b/s + acb + 0: acb + a\nb + 0: a\x0ab + +/a.b/s + acb + 0: acb + a\nb + 0: a\x0ab + +/^(b+?|a){1,2}?c/ + bac + 0: bac + 1: a + bbac + 0: bbac + 1: a + bbbac + 0: bbbac + 1: a + bbbbac + 0: bbbbac + 1: a + bbbbbac + 0: bbbbbac + 1: a + +/^(b+|a){1,2}?c/ + bac + 0: bac + 1: a + bbac + 0: bbac + 1: a + bbbac + 0: bbbac + 1: a + bbbbac + 0: bbbbac + 1: a + bbbbbac + 0: bbbbbac + 1: a + +/(?!\A)x/m + x\nb\n +No match + a\bx\n + 0: x + +/\x0{ab}/ + \0{ab} + 0: \x00{ab} + +/(A|B)*?CD/ + CD + 0: CD + +/(A|B)*CD/ + CD + 0: CD + +/(AB)*?\1/ + ABABAB + 0: ABAB + 1: AB + +/(AB)*\1/ + ABABAB + 0: ABABAB + 1: AB + +/(?.*/)foo" + /this/is/a/very/long/line/in/deed/with/very/many/slashes/in/it/you/see/ +No match + +"(?>.*/)foo" + /this/is/a/very/long/line/in/deed/with/very/many/slashes/in/and/foo + 0: /this/is/a/very/long/line/in/deed/with/very/many/slashes/in/and/foo + +/(?>(\.\d\d[1-9]?))\d+/ + 1.230003938 + 0: .230003938 + 1: .23 + 1.875000282 + 0: .875000282 + 1: .875 + *** Failers +No match + 1.235 +No match + +/^((?>\w+)|(?>\s+))*$/ + now is the time for all good men to come to the aid of the party + 0: now is the time for all good men to come to the aid of the party + 1: party + *** Failers +No match + this is not a line with only words and spaces! +No match + +/(\d+)(\w)/ + 12345a + 0: 12345a + 1: 12345 + 2: a + 12345+ + 0: 12345 + 1: 1234 + 2: 5 + +/((?>\d+))(\w)/ + 12345a + 0: 12345a + 1: 12345 + 2: a + *** Failers +No match + 12345+ +No match + +/(?>a+)b/ + aaab + 0: aaab + +/((?>a+)b)/ + aaab + 0: aaab + 1: aaab + +/(?>(a+))b/ + aaab + 0: aaab + 1: aaa + +/(?>b)+/ + aaabbbccc + 0: bbb + +/(?>a+|b+|c+)*c/ + aaabbbbccccd + 0: aaabbbbc + +/((?>[^()]+)|\([^()]*\))+/ + ((abc(ade)ufh()()x + 0: abc(ade)ufh()()x + 1: x + +/\(((?>[^()]+)|\([^()]+\))+\)/ + (abc) + 0: (abc) + 1: abc + (abc(def)xyz) + 0: (abc(def)xyz) + 1: xyz + *** Failers +No match + ((()aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa +No match + +/a(?-i)b/i + ab + 0: ab + Ab + 0: Ab + *** Failers +No match + aB +No match + AB +No match + +/(a (?x)b c)d e/ + a bcd e + 0: a bcd e + 1: a bc + *** Failers +No match + a b cd e +No match + abcd e +No match + a bcde +No match + +/(a b(?x)c d (?-x)e f)/ + a bcde f + 0: a bcde f + 1: a bcde f + *** Failers +No match + abcdef +No match + +/(a(?i)b)c/ + abc + 0: abc + 1: ab + aBc + 0: aBc + 1: aB + *** Failers +No match + abC +No match + aBC +No match + Abc +No match + ABc +No match + ABC +No match + AbC +No match + +/a(?i:b)c/ + abc + 0: abc + aBc + 0: aBc + *** Failers +No match + ABC +No match + abC +No match + aBC +No match + +/a(?i:b)*c/ + aBc + 0: aBc + aBBc + 0: aBBc + *** Failers +No match + aBC +No match + aBBC +No match + +/a(?=b(?i)c)\w\wd/ + abcd + 0: abcd + abCd + 0: abCd + *** Failers +No match + aBCd +No match + abcD +No match + +/(?s-i:more.*than).*million/i + more than million + 0: more than million + more than MILLION + 0: more than MILLION + more \n than Million + 0: more \x0a than Million + *** Failers +No match + MORE THAN MILLION +No match + more \n than \n million +No match + +/(?:(?s-i)more.*than).*million/i + more than million + 0: more than million + more than MILLION + 0: more than MILLION + more \n than Million + 0: more \x0a than Million + *** Failers +No match + MORE THAN MILLION +No match + more \n than \n million +No match + +/(?>a(?i)b+)+c/ + abc + 0: abc + aBbc + 0: aBbc + aBBc + 0: aBBc + *** Failers +No match + Abc +No match + abAb +No match + abbC +No match + +/(?=a(?i)b)\w\wc/ + abc + 0: abc + aBc + 0: aBc + *** Failers +No match + Ab +No match + abC +No match + aBC +No match + +/(?<=a(?i)b)(\w\w)c/ + abxxc + 0: xxc + 1: xx + aBxxc + 0: xxc + 1: xx + *** Failers +No match + Abxxc +No match + ABxxc +No match + abxxC +No match + +/(?:(a)|b)(?(1)A|B)/ + aA + 0: aA + 1: a + bB + 0: bB + *** Failers +No match + aB +No match + bA +No match + +/^(a)?(?(1)a|b)+$/ + aa + 0: aa + 1: a + b + 0: b + bb + 0: bb + *** Failers +No match + ab +No match + +/^(?(?=abc)\w{3}:|\d\d)$/ + abc: + 0: abc: + 12 + 0: 12 + *** Failers +No match + 123 +No match + xyz +No match + +/^(?(?!abc)\d\d|\w{3}:)$/ + abc: + 0: abc: + 12 + 0: 12 + *** Failers +No match + 123 +No match + xyz +No match + +/(?(?<=foo)bar|cat)/ + foobar + 0: bar + cat + 0: cat + fcat + 0: cat + focat + 0: cat + *** Failers +No match + foocat +No match + +/(?(?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 + Z)+|A)*/ + ZABCDEFG + 0: ZA + 1: A + +/((?>)+|A)*/ + ZABCDEFG + 0: + 1: + +/a*/g + abbab + 0: a + 0: + 0: + 0: a + 0: + 0: + +/^[a-\d]/ + abcde + 0: a + -things + 0: - + 0digit + 0: 0 + *** Failers +No match + bcdef +No match + +/^[\d-a]/ + abcde + 0: a + -things + 0: - + 0digit + 0: 0 + *** Failers +No match + bcdef +No match + +/[[:space:]]+/ + > \x09\x0a\x0c\x0d\x0b< + 0: \x09\x0a\x0c\x0d\x0b + +/[[:blank:]]+/ + > \x09\x0a\x0c\x0d\x0b< + 0: \x09 + +/[\s]+/ + > \x09\x0a\x0c\x0d\x0b< + 0: \x09\x0a\x0c\x0d + +/\s+/ + > \x09\x0a\x0c\x0d\x0b< + 0: \x09\x0a\x0c\x0d + +/a b/x + ab +No match + +/(?!\A)x/m + a\nxb\n + 0: x + +/(?!^)x/m + a\nxb\n +No match + +/abc\Qabc\Eabc/ + abcabcabc + 0: abcabcabc + +/abc\Q(*+|\Eabc/ + abc(*+|abc + 0: abc(*+|abc + +/ abc\Q abc\Eabc/x + abc abcabc + 0: abc abcabc + *** Failers +No match + abcabcabc +No match + +/abc#comment + \Q#not comment + literal\E/x + abc#not comment\n literal + 0: abc#not comment\x0a literal + +/abc#comment + \Q#not comment + literal/x + abc#not comment\n literal + 0: abc#not comment\x0a literal + +/abc#comment + \Q#not comment + literal\E #more comment + /x + abc#not comment\n literal + 0: abc#not comment\x0a literal + +/abc#comment + \Q#not comment + literal\E #more comment/x + abc#not comment\n literal + 0: abc#not comment\x0a literal + +/\Qabc\$xyz\E/ + abc\\\$xyz + 0: abc\$xyz + +/\Qabc\E\$\Qxyz\E/ + abc\$xyz + 0: abc$xyz + +/\Gabc/ + abc + 0: abc + *** Failers +No match + xyzabc +No match + +/\Gabc./g + abc1abc2xyzabc3 + 0: abc1 + 0: abc2 + +/abc./g + abc1abc2xyzabc3 + 0: abc1 + 0: abc2 + 0: abc3 + +/a(?x: b c )d/ + XabcdY + 0: abcd + *** Failers +No match + Xa b c d Y +No match + +/((?x)x y z | a b c)/ + XabcY + 0: abc + 1: abc + AxyzB + 0: xyz + 1: xyz + +/(?i)AB(?-i)C/ + XabCY + 0: abC + *** Failers +No match + XabcY +No match + +/((?i)AB(?-i)C|D)E/ + abCE + 0: abCE + 1: abC + DE + 0: DE + 1: D + *** Failers +No match + abcE +No match + abCe +No match + dE +No match + De +No match + +/(.*)\d+\1/ + abc123abc + 0: abc123abc + 1: abc + abc123bc + 0: bc123bc + 1: bc + +/(.*)\d+\1/s + abc123abc + 0: abc123abc + 1: abc + abc123bc + 0: bc123bc + 1: bc + +/((.*))\d+\1/ + abc123abc + 0: abc123abc + 1: abc + 2: abc + abc123bc + 0: bc123bc + 1: bc + 2: bc + +/-- This tests for an IPv6 address in the form where it can have up to --/ +/-- eight components, one and only one of which is empty. This must be --/ +No match +/-- an internal component. --/ +No match + +/^(?!:) # colon disallowed at start + (?: # start of item + (?: [0-9a-f]{1,4} | # 1-4 hex digits or + (?(1)0 | () ) ) # if null previously matched, fail; else null + : # followed by colon + ){1,7} # end item; 1-7 of them required + [0-9a-f]{1,4} $ # final hex number at end of string + (?(1)|.) # check that there was an empty component + /xi + a123::a123 + 0: a123::a123 + 1: + a123:b342::abcd + 0: a123:b342::abcd + 1: + a123:b342::324e:abcd + 0: a123:b342::324e:abcd + 1: + a123:ddde:b342::324e:abcd + 0: a123:ddde:b342::324e:abcd + 1: + a123:ddde:b342::324e:dcba:abcd + 0: a123:ddde:b342::324e:dcba:abcd + 1: + a123:ddde:9999:b342::324e:dcba:abcd + 0: a123:ddde:9999:b342::324e:dcba:abcd + 1: + *** Failers +No match + 1:2:3:4:5:6:7:8 +No match + a123:bce:ddde:9999:b342::324e:dcba:abcd +No match + a123::9999:b342::324e:dcba:abcd +No match + abcde:2:3:4:5:6:7:8 +No match + ::1 +No match + abcd:fee0:123:: +No match + :1 +No match + 1: +No match + +/[z\Qa-d]\E]/ + z + 0: z + a + 0: a + - + 0: - + d + 0: d + ] + 0: ] + *** Failers + 0: a + b +No match + +/[\z\C]/ + z + 0: z + C + 0: C + +/\M/ + M + 0: M + +/(a+)*b/ + aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa +No match + +/(?i)reg(?:ul(?:[aä]|ae)r|ex)/ + REGular + 0: REGular + regulaer + 0: regulaer + Regex + 0: Regex + regulär + 0: regul\xe4r + +/Åæåä[à-ÿÀ-ß]+/ + Åæåäà + 0: \xc5\xe6\xe5\xe4\xe0 + Åæåäÿ + 0: \xc5\xe6\xe5\xe4\xff + ÅæåäÀ + 0: \xc5\xe6\xe5\xe4\xc0 + Åæåäß + 0: \xc5\xe6\xe5\xe4\xdf + +/(?<=Z)X./ + \x84XAZXB + 0: XB + +/ab cd (?x) de fg/ + ab cd defg + 0: ab cd defg + +/ab cd(?x) de fg/ + ab cddefg + 0: ab cddefg + ** Failers +No match + abcddefg +No match + +/(? + 2: + D + 0: D + 1: + 2: + +/(a|)*\d/ + aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa +No match + aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa4 + 0: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa4 + 1: + +/(?>a|)*\d/ + aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa +No match + aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa4 + 0: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa4 + +/(?:a|)*\d/ + aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa +No match + aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa4 + 0: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa4 + +/\Z/g + abc\n + 0: + 0: + +/^(?s)(?>.*)(?iV\;\?aPhFB\qmj\;2\}YWFdYx\.Ap\]hjCPTP\(n28k\+3\;o\&WXqs\/gOXdr\$\:r\'do0\;b4c\(f_Gr\=\"\\4\)\[01T7ajQJvL\$W\~mL_sS\/4h\:x\*\[ZN\=KLs\&L5zX\/\/\>it\,o\:aU\(\;Z\>pW\&T7oP\'2K\^E\:x9\'c\[\%z\-\,64JQ5AeH_G\#KijUKghQw\^\\vea3a\?kka_G\$8\#\`\*kynsxzBLru\'\]k_\[7FrVx\}\^\=\$blx\>s\-N\%j\;D\*aZDnsw\:YKZ\%Q\.Kne9\#hP\?\+b3\(SOvL\,\^\;\&address@hidden)0RP6\{q\%L\^_z5E\'Dw6X\b|BM +Memory allocation (code space): 826 +------------------------------------------------------------------ + 0 822 Bra + 3 8J$WE<.rX+ix[d1b!H#?vV0vrK:ZH1=2M>iV;?aPhFBqmj;2}YWFdYx.Ap]hjCPTP(n28k+3;o&WXqs/gOXdr$:r'do0;b4c(f_Gr="\4)[01T7ajQJvL$W~mL_sS/4h:x*[ZN=KLs&L5zX//>it,o:aU(;Z>pW&T7oP'2K^E:x9'c[%z-,64JQ5AeH_G#KijUKghQw^\vea3a?kka_G$8#`*kynsxzBLru']k_[7FrVx}^=$blx>s-N%j;D*aZDnsw:YKZ%Q.Kne9#hP?+b3(SOvL,^;&address@hidden)0RP6{q%L^_z5E'Dw6X +821 \b +822 822 Ket +825 End +------------------------------------------------------------------ + +|\$\<\.X\+ix\[d1b\!H\#\?vV0vrK\:ZH1\=2M\>iV\;\?aPhFB\qmj\;2\}YWFdYx\.Ap\]hjCPTP\(n28k\+3\;o\&WXqs\/gOXdr\$\:r\'do0\;b4c\(f_Gr\=\"\\4\)\[01T7ajQJvL\$W\~mL_sS\/4h\:x\*\[ZN\=KLs\&L5zX\/\/\>it\,o\:aU\(\;Z\>pW\&T7oP\'2K\^E\:x9\'c\[\%z\-\,64JQ5AeH_G\#KijUKghQw\^\\vea3a\?kka_G\$8\#\`\*kynsxzBLru\'\]k_\[7FrVx\}\^\=\$blx\>s\-N\%j\;D\*aZDnsw\:YKZ\%Q\.Kne9\#hP\?\+b3\(SOvL\,\^\;\&address@hidden)0RP6\{q\%L\^_z5E\'Dw6X\b|BM +Memory allocation (code space): 816 +------------------------------------------------------------------ + 0 812 Bra + 3 $<.X+ix[d1b!H#?vV0vrK:ZH1=2M>iV;?aPhFBqmj;2}YWFdYx.Ap]hjCPTP(n28k+3;o&WXqs/gOXdr$:r'do0;b4c(f_Gr="\4)[01T7ajQJvL$W~mL_sS/4h:x*[ZN=KLs&L5zX//>it,o:aU(;Z>pW&T7oP'2K^E:x9'c[%z-,64JQ5AeH_G#KijUKghQw^\vea3a?kka_G$8#`*kynsxzBLru']k_[7FrVx}^=$blx>s-N%j;D*aZDnsw:YKZ%Q.Kne9#hP?+b3(SOvL,^;&address@hidden)0RP6{q%L^_z5E'Dw6X +811 \b +812 812 Ket +815 End +------------------------------------------------------------------ + +/(a(?1)b)/BM +Memory allocation (code space): 28 +------------------------------------------------------------------ + 0 24 Bra + 3 18 CBra 1 + 8 a + 10 6 Once + 13 3 Recurse + 16 6 Ket + 19 b + 21 18 Ket + 24 24 Ket + 27 End +------------------------------------------------------------------ + +/(a(?1)+b)/BM +Memory allocation (code space): 28 +------------------------------------------------------------------ + 0 24 Bra + 3 18 CBra 1 + 8 a + 10 6 Once + 13 3 Recurse + 16 6 KetRmax + 19 b + 21 18 Ket + 24 24 Ket + 27 End +------------------------------------------------------------------ + +/a(?Pb|c)d(?Pe)/BM +Memory allocation (code space): 42 +------------------------------------------------------------------ + 0 32 Bra + 3 a + 5 7 CBra 1 + 10 b + 12 5 Alt + 15 c + 17 12 Ket + 20 d + 22 7 CBra 2 + 27 e + 29 7 Ket + 32 32 Ket + 35 End +------------------------------------------------------------------ + +/(?:a(?Pc(?Pd)))(?Pa)/BM +Memory allocation (code space): 54 +------------------------------------------------------------------ + 0 41 Bra + 3 25 Bra + 6 a + 8 17 CBra 1 + 13 c + 15 7 CBra 2 + 20 d + 22 7 Ket + 25 17 Ket + 28 25 Ket + 31 7 CBra 3 + 36 a + 38 7 Ket + 41 41 Ket + 44 End +------------------------------------------------------------------ + +/(?Pa)...(?P=a)bbb(?P>a)d/BM +Memory allocation (code space): 43 +------------------------------------------------------------------ + 0 36 Bra + 3 7 CBra 1 + 8 a + 10 7 Ket + 13 Any + 14 Any + 15 Any + 16 \1 + 19 bbb + 25 6 Once + 28 3 Recurse + 31 6 Ket + 34 d + 36 36 Ket + 39 End +------------------------------------------------------------------ + +/abc(?C255)de(?C)f/BM +Memory allocation (code space): 31 +------------------------------------------------------------------ + 0 27 Bra + 3 abc + 9 Callout 255 10 1 + 15 de + 19 Callout 0 16 1 + 25 f + 27 27 Ket + 30 End +------------------------------------------------------------------ + +/abcde/CBM +Memory allocation (code space): 53 +------------------------------------------------------------------ + 0 49 Bra + 3 Callout 255 0 1 + 9 a + 11 Callout 255 1 1 + 17 b + 19 Callout 255 2 1 + 25 c + 27 Callout 255 3 1 + 33 d + 35 Callout 255 4 1 + 41 e + 43 Callout 255 5 0 + 49 49 Ket + 52 End +------------------------------------------------------------------ + +/\x{100}/8BM +Memory allocation (code space): 10 +------------------------------------------------------------------ + 0 6 Bra + 3 \x{100} + 6 6 Ket + 9 End +------------------------------------------------------------------ + +/\x{1000}/8BM +Memory allocation (code space): 11 +------------------------------------------------------------------ + 0 7 Bra + 3 \x{1000} + 7 7 Ket + 10 End +------------------------------------------------------------------ + +/\x{10000}/8BM +Memory allocation (code space): 12 +------------------------------------------------------------------ + 0 8 Bra + 3 \x{10000} + 8 8 Ket + 11 End +------------------------------------------------------------------ + +/\x{100000}/8BM +Memory allocation (code space): 12 +------------------------------------------------------------------ + 0 8 Bra + 3 \x{100000} + 8 8 Ket + 11 End +------------------------------------------------------------------ + +/\x{1000000}/8BM +Memory allocation (code space): 13 +------------------------------------------------------------------ + 0 9 Bra + 3 \x{1000000} + 9 9 Ket + 12 End +------------------------------------------------------------------ + +/\x{4000000}/8BM +Memory allocation (code space): 14 +------------------------------------------------------------------ + 0 10 Bra + 3 \x{4000000} + 10 10 Ket + 13 End +------------------------------------------------------------------ + +/\x{7fffFFFF}/8BM +Memory allocation (code space): 14 +------------------------------------------------------------------ + 0 10 Bra + 3 \x{7fffffff} + 10 10 Ket + 13 End +------------------------------------------------------------------ + +/[\x{ff}]/8BM +Memory allocation (code space): 10 +------------------------------------------------------------------ + 0 6 Bra + 3 \x{ff} + 6 6 Ket + 9 End +------------------------------------------------------------------ + +/[\x{100}]/8BM +Memory allocation (code space): 15 +------------------------------------------------------------------ + 0 11 Bra + 3 [\x{100}] + 11 11 Ket + 14 End +------------------------------------------------------------------ + +/\x80/8BM +Memory allocation (code space): 10 +------------------------------------------------------------------ + 0 6 Bra + 3 \x{80} + 6 6 Ket + 9 End +------------------------------------------------------------------ + +/\xff/8BM +Memory allocation (code space): 10 +------------------------------------------------------------------ + 0 6 Bra + 3 \x{ff} + 6 6 Ket + 9 End +------------------------------------------------------------------ + +/\x{0041}\x{2262}\x{0391}\x{002e}/D8M +Memory allocation (code space): 18 +------------------------------------------------------------------ + 0 14 Bra + 3 A\x{2262}\x{391}. + 14 14 Ket + 17 End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Options: utf8 +First char = 'A' +Need char = '.' + +/\x{D55c}\x{ad6d}\x{C5B4}/D8M +Memory allocation (code space): 19 +------------------------------------------------------------------ + 0 15 Bra + 3 \x{d55c}\x{ad6d}\x{c5b4} + 15 15 Ket + 18 End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Options: utf8 +First char = 237 +Need char = 180 + +/\x{65e5}\x{672c}\x{8a9e}/D8M +Memory allocation (code space): 19 +------------------------------------------------------------------ + 0 15 Bra + 3 \x{65e5}\x{672c}\x{8a9e} + 15 15 Ket + 18 End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Options: utf8 +First char = 230 +Need char = 158 + +/[\x{100}]/8BM +Memory allocation (code space): 15 +------------------------------------------------------------------ + 0 11 Bra + 3 [\x{100}] + 11 11 Ket + 14 End +------------------------------------------------------------------ + +/[Z\x{100}]/8BM +Memory allocation (code space): 47 +------------------------------------------------------------------ + 0 43 Bra + 3 [Z\x{100}] + 43 43 Ket + 46 End +------------------------------------------------------------------ + +/^[\x{100}\E-\Q\E\x{150}]/B8M +Memory allocation (code space): 18 +------------------------------------------------------------------ + 0 14 Bra + 3 ^ + 4 [\x{100}-\x{150}] + 14 14 Ket + 17 End +------------------------------------------------------------------ + +/^[\QĀ\E-\QŐ\E]/B8M +Memory allocation (code space): 18 +------------------------------------------------------------------ + 0 14 Bra + 3 ^ + 4 [\x{100}-\x{150}] + 14 14 Ket + 17 End +------------------------------------------------------------------ + +/^[\QĀ\E-\QŐ\E/B8M +Failed: missing terminating ] for character class at offset 15 + +/[\p{L}]/BM +Memory allocation (code space): 15 +------------------------------------------------------------------ + 0 11 Bra + 3 [\p{L}] + 11 11 Ket + 14 End +------------------------------------------------------------------ + +/[\p{^L}]/BM +Memory allocation (code space): 15 +------------------------------------------------------------------ + 0 11 Bra + 3 [\P{L}] + 11 11 Ket + 14 End +------------------------------------------------------------------ + +/[\P{L}]/BM +Memory allocation (code space): 15 +------------------------------------------------------------------ + 0 11 Bra + 3 [\P{L}] + 11 11 Ket + 14 End +------------------------------------------------------------------ + +/[\P{^L}]/BM +Memory allocation (code space): 15 +------------------------------------------------------------------ + 0 11 Bra + 3 [\p{L}] + 11 11 Ket + 14 End +------------------------------------------------------------------ + +/[abc\p{L}\x{0660}]/8BM +Memory allocation (code space): 50 +------------------------------------------------------------------ + 0 46 Bra + 3 [a-c\p{L}\x{660}] + 46 46 Ket + 49 End +------------------------------------------------------------------ + +/[\p{Nd}]/8BM +Memory allocation (code space): 15 +------------------------------------------------------------------ + 0 11 Bra + 3 [\p{Nd}] + 11 11 Ket + 14 End +------------------------------------------------------------------ + +/[\p{Nd}+-]+/8BM +Memory allocation (code space): 48 +------------------------------------------------------------------ + 0 44 Bra + 3 [+\-\p{Nd}]+ + 44 44 Ket + 47 End +------------------------------------------------------------------ + +/A\x{391}\x{10427}\x{ff3a}\x{1fb0}/8iBM +Memory allocation (code space): 25 +------------------------------------------------------------------ + 0 21 Bra + 3 NC A\x{391}\x{10427}\x{ff3a}\x{1fb0} + 21 21 Ket + 24 End +------------------------------------------------------------------ + +/A\x{391}\x{10427}\x{ff3a}\x{1fb0}/8BM +Memory allocation (code space): 25 +------------------------------------------------------------------ + 0 21 Bra + 3 A\x{391}\x{10427}\x{ff3a}\x{1fb0} + 21 21 Ket + 24 End +------------------------------------------------------------------ + +/[\x{105}-\x{109}]/8iBM +Memory allocation (code space): 17 +------------------------------------------------------------------ + 0 13 Bra + 3 [\x{104}-\x{109}] + 13 13 Ket + 16 End +------------------------------------------------------------------ + +/( ( (?(1)0|) )* )/xBM +Memory allocation (code space): 38 +------------------------------------------------------------------ + 0 34 Bra + 3 28 CBra 1 + 8 Brazero + 9 19 SCBra 2 + 14 8 Cond + 17 1 Cond ref + 20 0 + 22 3 Alt + 25 11 Ket + 28 19 KetRmax + 31 28 Ket + 34 34 Ket + 37 End +------------------------------------------------------------------ + +/( (?(1)0|)* )/xBM +Memory allocation (code space): 30 +------------------------------------------------------------------ + 0 26 Bra + 3 20 CBra 1 + 8 Brazero + 9 8 SCond + 12 1 Cond ref + 15 0 + 17 3 Alt + 20 11 KetRmax + 23 20 Ket + 26 26 Ket + 29 End +------------------------------------------------------------------ + +/[a]/BM +Memory allocation (code space): 9 +------------------------------------------------------------------ + 0 5 Bra + 3 a + 5 5 Ket + 8 End +------------------------------------------------------------------ + +/[a]/8BM +Memory allocation (code space): 9 +------------------------------------------------------------------ + 0 5 Bra + 3 a + 5 5 Ket + 8 End +------------------------------------------------------------------ + +/[\xaa]/BM +Memory allocation (code space): 9 +------------------------------------------------------------------ + 0 5 Bra + 3 \xaa + 5 5 Ket + 8 End +------------------------------------------------------------------ + +/[\xaa]/8BM +Memory allocation (code space): 10 +------------------------------------------------------------------ + 0 6 Bra + 3 \x{aa} + 6 6 Ket + 9 End +------------------------------------------------------------------ + +/[^a]/BM +Memory allocation (code space): 9 +------------------------------------------------------------------ + 0 5 Bra + 3 [^a] + 5 5 Ket + 8 End +------------------------------------------------------------------ + +/[^a]/8BM +Memory allocation (code space): 9 +------------------------------------------------------------------ + 0 5 Bra + 3 [^a] + 5 5 Ket + 8 End +------------------------------------------------------------------ + +/[^\xaa]/BM +Memory allocation (code space): 9 +------------------------------------------------------------------ + 0 5 Bra + 3 [^\xaa] + 5 5 Ket + 8 End +------------------------------------------------------------------ + +/[^\xaa]/8BM +Memory allocation (code space): 40 +------------------------------------------------------------------ + 0 36 Bra + 3 [\x00-\xa9\xab-\xff] (neg) + 36 36 Ket + 39 End +------------------------------------------------------------------ + +/ End of testinput10 / ============================================================ --- pcre/testdata/testoutput2 395e58b959ef57672eed4ff095fdb3ab64cb6801 +++ pcre/testdata/testoutput2 395e58b959ef57672eed4ff095fdb3ab64cb6801 @@ -0,0 +1,9388 @@ +/(a)b|/I +Capturing subpattern count = 1 +No options +No first char +No need char + +/abc/I +Capturing subpattern count = 0 +No options +First char = 'a' +Need char = 'c' + abc + 0: abc + defabc + 0: abc + \Aabc + 0: abc + *** Failers +No match + \Adefabc +No match + ABC +No match + +/^abc/I +Capturing subpattern count = 0 +Options: anchored +No first char +No need char + abc + 0: abc + \Aabc + 0: abc + *** Failers +No match + defabc +No match + \Adefabc +No match + +/a+bc/I +Capturing subpattern count = 0 +Partial matching not supported +No options +First char = 'a' +Need char = 'c' + +/a*bc/I +Capturing subpattern count = 0 +Partial matching not supported +No options +No first char +Need char = 'c' + +/a{3}bc/I +Capturing subpattern count = 0 +Partial matching not supported +No options +First char = 'a' +Need char = 'c' + +/(abc|a+z)/I +Capturing subpattern count = 1 +Partial matching not supported +No options +First char = 'a' +No need char + +/^abc$/I +Capturing subpattern count = 0 +Options: anchored +No first char +No need char + abc + 0: abc + *** Failers +No match + def\nabc +No match + +/ab\idef/X +Failed: unrecognized character follows \ at offset 3 + +/(?X)ab\idef/X +Failed: unrecognized character follows \ at offset 7 + +/x{5,4}/ +Failed: numbers out of order in {} quantifier at offset 5 + +/z{65536}/ +Failed: number too big in {} quantifier at offset 7 + +/[abcd/ +Failed: missing terminating ] for character class at offset 5 + +/(?X)[\B]/ +Failed: invalid escape sequence in character class at offset 6 + +/[z-a]/ +Failed: range out of order in character class at offset 3 + +/^*/ +Failed: nothing to repeat at offset 1 + +/(abc/ +Failed: missing ) at offset 4 + +/(?# abc/ +Failed: missing ) after comment at offset 7 + +/(?z)abc/ +Failed: unrecognized character after (? or (?- at offset 2 + +/.*b/I +Capturing subpattern count = 0 +Partial matching not supported +No options +First char at start or follows newline +Need char = 'b' + +/.*?b/I +Capturing subpattern count = 0 +Partial matching not supported +No options +First char at start or follows newline +Need char = 'b' + +/cat|dog|elephant/I +Capturing subpattern count = 0 +No options +No first char +No need char + this sentence eventually mentions a cat + 0: cat + this sentences rambles on and on for a while and then reaches elephant + 0: elephant + +/cat|dog|elephant/IS +Capturing subpattern count = 0 +No options +No first char +No need char +Starting byte set: c d e + this sentence eventually mentions a cat + 0: cat + this sentences rambles on and on for a while and then reaches elephant + 0: elephant + +/cat|dog|elephant/IiS +Capturing subpattern count = 0 +Options: caseless +No first char +No need char +Starting byte set: C D E c d e + this sentence eventually mentions a CAT cat + 0: CAT + this sentences rambles on and on for a while to elephant ElePhant + 0: elephant + +/a|[bcd]/IS +Capturing subpattern count = 0 +No options +No first char +No need char +Starting byte set: a b c d + +/(a|[^\dZ])/IS +Capturing subpattern count = 1 +No options +No first char +No need char +Starting byte set: \x00 \x01 \x02 \x03 \x04 \x05 \x06 \x07 \x08 \x09 \x0a + \x0b \x0c \x0d \x0e \x0f \x10 \x11 \x12 \x13 \x14 \x15 \x16 \x17 \x18 \x19 + \x1a \x1b \x1c \x1d \x1e \x1f \x20 ! " # $ % & ' ( ) * + , - . / : ; < = > + ? @ A B C D E F G H I J K L M N O P Q R S T U V W X Y [ \ ] ^ _ ` a b c d + e f g h i j k l m n o p q r s t u v w x y z { | } ~ \x7f \x80 \x81 \x82 \x83 + \x84 \x85 \x86 \x87 \x88 \x89 \x8a \x8b \x8c \x8d \x8e \x8f \x90 \x91 \x92 + \x93 \x94 \x95 \x96 \x97 \x98 \x99 \x9a \x9b \x9c \x9d \x9e \x9f \xa0 \xa1 + \xa2 \xa3 \xa4 \xa5 \xa6 \xa7 \xa8 \xa9 \xaa \xab \xac \xad \xae \xaf \xb0 + \xb1 \xb2 \xb3 \xb4 \xb5 \xb6 \xb7 \xb8 \xb9 \xba \xbb \xbc \xbd \xbe \xbf + \xc0 \xc1 \xc2 \xc3 \xc4 \xc5 \xc6 \xc7 \xc8 \xc9 \xca \xcb \xcc \xcd \xce + \xcf \xd0 \xd1 \xd2 \xd3 \xd4 \xd5 \xd6 \xd7 \xd8 \xd9 \xda \xdb \xdc \xdd + \xde \xdf \xe0 \xe1 \xe2 \xe3 \xe4 \xe5 \xe6 \xe7 \xe8 \xe9 \xea \xeb \xec + \xed \xee \xef \xf0 \xf1 \xf2 \xf3 \xf4 \xf5 \xf6 \xf7 \xf8 \xf9 \xfa \xfb + \xfc \xfd \xfe \xff + +/(a|b)*[\s]/IS +Capturing subpattern count = 1 +No options +No first char +No need char +Starting byte set: \x09 \x0a \x0c \x0d \x20 a b + +/(ab\2)/ +Failed: reference to non-existent subpattern at offset 6 + +/{4,5}abc/ +Failed: nothing to repeat at offset 4 + +/(a)(b)(c)\2/I +Capturing subpattern count = 3 +Max back reference = 2 +No options +First char = 'a' +Need char = 'c' + abcb + 0: abcb + 1: a + 2: b + 3: c + \O0abcb +Matched, but too many substrings + \O3abcb +Matched, but too many substrings + 0: abcb + \O6abcb +Matched, but too many substrings + 0: abcb + 1: a + \O9abcb +Matched, but too many substrings + 0: abcb + 1: a + 2: b + \O12abcb + 0: abcb + 1: a + 2: b + 3: c + +/(a)bc|(a)(b)\2/I +Capturing subpattern count = 3 +Max back reference = 2 +No options +First char = 'a' +No need char + abc + 0: abc + 1: a + \O0abc +Matched, but too many substrings + \O3abc +Matched, but too many substrings + 0: abc + \O6abc + 0: abc + 1: a + aba + 0: aba + 1: + 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$/IE +Capturing subpattern count = 0 +Options: dollar_endonly +First char = 'a' +Need char = 'c' + abc + 0: abc + *** Failers +No match + abc\n +No match + abc\ndef +No match + +/(a)(b)(c)(d)(e)\6/ +Failed: reference to non-existent subpattern at offset 17 + +/the quick brown fox/I +Capturing subpattern count = 0 +No options +First char = 't' +Need char = 'x' + the quick brown fox + 0: the quick brown fox + this is a line with the quick brown fox + 0: the quick brown fox + +/the quick brown fox/IA +Capturing subpattern count = 0 +Options: anchored +No first char +No need char + the quick brown fox + 0: the quick brown fox + *** Failers +No match + this is a line with the quick brown fox +No match + +/ab(?z)cd/ +Failed: unrecognized character after (? or (?- at offset 4 + +/^abc|def/I +Capturing subpattern count = 0 +No options +No first char +No need char + abcdef + 0: abc + abcdef\B + 0: def + +/.*((abc)$|(def))/I +Capturing subpattern count = 3 +Partial matching not supported +No options +First char at start or follows newline +No need char + defabc + 0: defabc + 1: abc + 2: abc + \Zdefabc + 0: def + 1: def + 2: + 3: def + +/abc/IP + abc + 0: abc + *** Failers +No match: POSIX code 17: match failed + +/^abc|def/IP + abcdef + 0: abc + abcdef\B + 0: def + +/.*((abc)$|(def))/IP + defabc + 0: defabc + 1: abc + 2: abc + \Zdefabc + 0: def + 1: def + 3: def + +/the quick brown fox/IP + the quick brown fox + 0: the quick brown fox + *** Failers +No match: POSIX code 17: match failed + The Quick Brown Fox +No match: POSIX code 17: match failed + +/the quick brown fox/IPi + the quick brown fox + 0: the quick brown fox + The Quick Brown Fox + 0: The Quick Brown Fox + +/abc.def/IP + *** Failers +No match: POSIX code 17: match failed + abc\ndef +No match: POSIX code 17: match failed + +/abc$/IP + abc + 0: abc + abc\n + 0: abc + +/(abc)\2/IP +Failed: POSIX code 15: bad back reference at offset 7 + +/(abc\1)/IP + 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,}/I +Capturing subpattern count = 0 +Partial matching not supported +No options +No first char +No need char + co-processors, and for + 0: -pr + +/<.*>/I +Capturing subpattern count = 0 +Partial matching not supported +No options +First char = '<' +Need char = '>' + abcghinop + 0: ghi + +/<.*?>/I +Capturing subpattern count = 0 +Partial matching not supported +No options +First char = '<' +Need char = '>' + abcghinop + 0: + +/<.*>/IU +Capturing subpattern count = 0 +Partial matching not supported +Options: ungreedy +First char = '<' +Need char = '>' + abcghinop + 0: + +/(?U)<.*>/I +Capturing subpattern count = 0 +Partial matching not supported +Options: ungreedy +First char = '<' +Need char = '>' + abcghinop + 0: + +/<.*?>/IU +Capturing subpattern count = 0 +Partial matching not supported +Options: ungreedy +First char = '<' +Need char = '>' + abcghinop + 0: ghi + +/={3,}/IU +Capturing subpattern count = 0 +Partial matching not supported +Options: ungreedy +First char = '=' +Need char = '=' + abc========def + 0: === + +/(?U)={3,}?/I +Capturing subpattern count = 0 +Partial matching not supported +Options: ungreedy +First char = '=' +Need char = '=' + abc========def + 0: ======== + +/(?^abc)/Im +Capturing subpattern count = 0 +Options: multiline +First char at start or follows newline +Need char = 'c' + abc + 0: abc + def\nabc + 0: abc + *** Failers +No match + defabc +No match + +/(?<=ab(c+)d)ef/ +Failed: lookbehind assertion is not fixed length at offset 11 + +/(?<=ab(?<=c+)d)ef/ +Failed: lookbehind assertion is not fixed length at offset 12 + +/(?<=ab(c|de)f)g/ +Failed: lookbehind assertion is not fixed length at offset 13 + +/The next three are in testinput2 because they have variable length branches/ + +/(?<=bullock|donkey)-cart/I +Capturing subpattern count = 0 +No options +First char = '-' +Need char = 't' + the bullock-cart + 0: -cart + a donkey-cart race + 0: -cart + *** Failers +No match + cart +No match + horse-and-cart +No match + +/(?<=ab(?i)x|y|z)/I +Capturing subpattern count = 0 +No options +No first char +No need char + +/(?>.*)(?<=(abcd)|(xyz))/I +Capturing subpattern count = 2 +Partial matching not supported +No options +First char at start or follows newline +No need char + alphabetabcd + 0: alphabetabcd + 1: abcd + endingxyz + 0: endingxyz + 1: + 2: xyz + +/(?<=ab(?i)x(?-i)y|(?i)z|b)ZZ/I +Capturing subpattern count = 0 +No options +First char = 'Z' +Need char = 'Z' + abxyZZ + 0: ZZ + abXyZZ + 0: ZZ + ZZZ + 0: ZZ + zZZ + 0: ZZ + bZZ + 0: ZZ + BZZ + 0: ZZ + *** Failers +No match + ZZ +No match + abXYZZ +No match + zzz +No match + bzz +No match + +/(? + 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/I +Capturing subpattern count = 0 +Options: anchored +No first char +No need char + abc\00def\L\C0 + 0: abc\x00def + 0C abc (7) + 0L abc + +/word ((?:[a-zA-Z0-9]+ )((?:[a-zA-Z0-9]+ )((?:[a-zA-Z0-9]+ )((?:[a-zA-Z0-9]+ +)((?:[a-zA-Z0-9]+ )((?:[a-zA-Z0-9]+ )((?:[a-zA-Z0-9]+ )((?:[a-zA-Z0-9]+ +)?)?)?)?)?)?)?)?)?otherword/I +Capturing subpattern count = 8 +Partial matching not supported +Contains explicit CR or LF match +No options +First char = 'w' +Need char = 'd' + +/.*X/IDZ +------------------------------------------------------------------ + Bra + Any* + X + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Partial matching not supported +No options +First char at start or follows newline +Need char = 'X' + +/.*X/IDZs +------------------------------------------------------------------ + Bra + Any* + X + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Partial matching not supported +Options: anchored dotall +No first char +Need char = 'X' + +/(.*X|^B)/IDZ +------------------------------------------------------------------ + Bra + CBra 1 + Any* + X + Alt + ^ + B + Ket + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 1 +Partial matching not supported +No options +First char at start or follows newline +No need char + +/(.*X|^B)/IDZs +------------------------------------------------------------------ + Bra + CBra 1 + Any* + X + Alt + ^ + B + Ket + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 1 +Partial matching not supported +Options: anchored dotall +No first char +No need char + +/(?s)(.*X|^B)/IDZ +------------------------------------------------------------------ + Bra + CBra 1 + Any* + X + Alt + ^ + B + Ket + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 1 +Partial matching not supported +Options: anchored dotall +No first char +No need char + +/(?s:.*X|^B)/IDZ +------------------------------------------------------------------ + Bra + Bra + 04 Opt + Any* + X + Alt + 04 Opt + ^ + B + Ket + 00 Opt + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Partial matching not supported +No options +First char at start or follows newline +No need char + +/\Biss\B/I+ +Capturing subpattern count = 0 +No options +First char = 'i' +Need char = 's' + Mississippi + 0: iss + 0+ issippi + +/\Biss\B/I+P + Mississippi + 0: iss + 0+ issippi + +/iss/IG+ +Capturing subpattern count = 0 +No options +First char = 'i' +Need char = 's' + Mississippi + 0: iss + 0+ issippi + 0: iss + 0+ ippi + +/\Biss\B/IG+ +Capturing subpattern count = 0 +No options +First char = 'i' +Need char = 's' + Mississippi + 0: iss + 0+ issippi + +/\Biss\B/Ig+ +Capturing subpattern count = 0 +No options +First char = 'i' +Need char = 's' + Mississippi + 0: iss + 0+ issippi + 0: iss + 0+ ippi + *** Failers +No match + Mississippi\A +No match + +/(?<=[Ms])iss/Ig+ +Capturing subpattern count = 0 +No options +First char = 'i' +Need char = 's' + Mississippi + 0: iss + 0+ issippi + 0: iss + 0+ ippi + +/(?<=[Ms])iss/IG+ +Capturing subpattern count = 0 +No options +First char = 'i' +Need char = 's' + Mississippi + 0: iss + 0+ issippi + +/^iss/Ig+ +Capturing subpattern count = 0 +Options: anchored +No first char +No need char + ississippi + 0: iss + 0+ issippi + +/.*iss/Ig+ +Capturing subpattern count = 0 +Partial matching not supported +No options +First char at start or follows newline +Need char = 's' + abciss\nxyzisspqr + 0: abciss + 0+ \x0axyzisspqr + 0: xyziss + 0+ pqr + +/.i./I+g +Capturing subpattern count = 0 +No options +No first char +Need char = 'i' + Mississippi + 0: Mis + 0+ sissippi + 0: sis + 0+ sippi + 0: sip + 0+ pi + Mississippi\A + 0: Mis + 0+ sissippi + 0: sis + 0+ sippi + 0: sip + 0+ pi + Missouri river + 0: Mis + 0+ souri river + 0: ri + 0+ river + 0: riv + 0+ er + Missouri river\A + 0: Mis + 0+ souri river + +/^.is/I+g +Capturing subpattern count = 0 +Options: anchored +No first char +No need char + Mississippi + 0: Mis + 0+ sissippi + +/^ab\n/Ig+ +Capturing subpattern count = 0 +Contains explicit CR or LF match +Options: anchored +No first char +No need char + ab\nab\ncd + 0: ab\x0a + 0+ ab\x0acd + +/^ab\n/Img+ +Capturing subpattern count = 0 +Contains explicit CR or LF match +Options: multiline +First char at start or follows newline +Need char = 10 + ab\nab\ncd + 0: ab\x0a + 0+ ab\x0acd + 0: ab\x0a + 0+ cd + +/abc/I +Capturing subpattern count = 0 +No options +First char = 'a' +Need char = 'c' + +/abc|bac/I +Capturing subpattern count = 0 +No options +No first char +Need char = 'c' + +/(abc|bac)/I +Capturing subpattern count = 1 +No options +No first char +Need char = 'c' + +/(abc|(c|dc))/I +Capturing subpattern count = 2 +No options +No first char +Need char = 'c' + +/(abc|(d|de)c)/I +Capturing subpattern count = 2 +No options +No first char +Need char = 'c' + +/a*/I +Capturing subpattern count = 0 +Partial matching not supported +No options +No first char +No need char + +/a+/I +Capturing subpattern count = 0 +Partial matching not supported +No options +First char = 'a' +No need char + +/(baa|a+)/I +Capturing subpattern count = 1 +Partial matching not supported +No options +No first char +Need char = 'a' + +/a{0,3}/I +Capturing subpattern count = 0 +Partial matching not supported +No options +No first char +No need char + +/baa{3,}/I +Capturing subpattern count = 0 +Partial matching not supported +No options +First char = 'b' +Need char = 'a' + +/"([^\\"]+|\\.)*"/I +Capturing subpattern count = 1 +Partial matching not supported +No options +First char = '"' +Need char = '"' + +/(abc|ab[cd])/I +Capturing subpattern count = 1 +No options +First char = 'a' +No need char + +/(a|.)/I +Capturing subpattern count = 1 +No options +No first char +No need char + +/a|ba|\w/I +Capturing subpattern count = 0 +No options +No first char +No need char + +/abc(?=pqr)/I +Capturing subpattern count = 0 +No options +First char = 'a' +Need char = 'r' + +/...(?<=abc)/I +Capturing subpattern count = 0 +No options +No first char +No need char + +/abc(?!pqr)/I +Capturing subpattern count = 0 +No options +First char = 'a' +Need char = 'c' + +/ab./I +Capturing subpattern count = 0 +No options +First char = 'a' +Need char = 'b' + +/ab[xyz]/I +Capturing subpattern count = 0 +No options +First char = 'a' +Need char = 'b' + +/abc*/I +Capturing subpattern count = 0 +Partial matching not supported +No options +First char = 'a' +Need char = 'b' + +/ab.c*/I +Capturing subpattern count = 0 +Partial matching not supported +No options +First char = 'a' +Need char = 'b' + +/a.c*/I +Capturing subpattern count = 0 +Partial matching not supported +No options +First char = 'a' +No need char + +/.c*/I +Capturing subpattern count = 0 +Partial matching not supported +No options +No first char +No need char + +/ac*/I +Capturing subpattern count = 0 +Partial matching not supported +No options +First char = 'a' +No need char + +/(a.c*|b.c*)/I +Capturing subpattern count = 1 +Partial matching not supported +No options +No first char +No need char + +/a.c*|aba/I +Capturing subpattern count = 0 +Partial matching not supported +No options +First char = 'a' +No need char + +/.+a/I +Capturing subpattern count = 0 +Partial matching not supported +No options +No first char +Need char = 'a' + +/(?=abcda)a.*/I +Capturing subpattern count = 0 +Partial matching not supported +No options +First char = 'a' +Need char = 'a' + +/(?=a)a.*/I +Capturing subpattern count = 0 +Partial matching not supported +No options +First char = 'a' +No need char + +/a(b)*/I +Capturing subpattern count = 1 +No options +First char = 'a' +No need char + +/a\d*/I +Capturing subpattern count = 0 +Partial matching not supported +No options +First char = 'a' +No need char + +/ab\d*/I +Capturing subpattern count = 0 +Partial matching not supported +No options +First char = 'a' +Need char = 'b' + +/a(\d)*/I +Capturing subpattern count = 1 +No options +First char = 'a' +No need char + +/abcde{0,0}/I +Capturing subpattern count = 0 +No options +First char = 'a' +Need char = 'd' + +/ab\d+/I +Capturing subpattern count = 0 +Partial matching not supported +No options +First char = 'a' +Need char = 'b' + +/a(?(1)b)(.)/I +Capturing subpattern count = 1 +No options +First char = 'a' +No need char + +/a(?(1)bag|big)(.)/I +Capturing subpattern count = 1 +No options +First char = 'a' +Need char = 'g' + +/a(?(1)bag|big)*(.)/I +Capturing subpattern count = 1 +No options +First char = 'a' +No need char + +/a(?(1)bag|big)+(.)/I +Capturing subpattern count = 1 +No options +First char = 'a' +Need char = 'g' + +/a(?(1)b..|b..)(.)/I +Capturing subpattern count = 1 +No options +First char = 'a' +Need char = 'b' + +/ab\d{0}e/I +Capturing subpattern count = 0 +No options +First char = 'a' +Need char = 'e' + +/a?b?/I +Capturing subpattern count = 0 +No options +No first char +No need char + a + 0: a + b + 0: b + ab + 0: ab + \ + 0: + *** Failers + 0: + \N +No match + +/|-/I +Capturing subpattern count = 0 +No options +No first char +No need char + abcd + 0: + -abc + 0: + \Nab-c + 0: - + *** Failers + 0: + \Nabc +No match + +/a*(b+)(z)(z)/IP + aaaabbbbzzzz + 0: aaaabbbbzz + 1: bbbb + 2: z + 3: z + aaaabbbbzzzz\O0 + aaaabbbbzzzz\O1 + 0: aaaabbbbzz + aaaabbbbzzzz\O2 + 0: aaaabbbbzz + 1: bbbb + aaaabbbbzzzz\O3 + 0: aaaabbbbzz + 1: bbbb + 2: z + aaaabbbbzzzz\O4 + 0: aaaabbbbzz + 1: bbbb + 2: z + 3: z + aaaabbbbzzzz\O5 + 0: aaaabbbbzz + 1: bbbb + 2: z + 3: z + +/^.?abcd/IS +Capturing subpattern count = 0 +Options: anchored +No first char +Need char = 'd' +Study returned NULL + +/\( # ( at start + (?: # Non-capturing bracket + (?>[^()]+) # Either a sequence of non-brackets (no backtracking) + | # Or + (?R) # Recurse - i.e. nested bracketed string + )* # Zero or more contents + \) # Closing ) + /Ix +Capturing subpattern count = 0 +Partial matching not supported +Options: extended +First char = '(' +Need char = ')' + (abcd) + 0: (abcd) + (abcd)xyz + 0: (abcd) + xyz(abcd) + 0: (abcd) + (ab(xy)cd)pqr + 0: (ab(xy)cd) + (ab(xycd)pqr + 0: (xycd) + () abc () + 0: () + 12(abcde(fsh)xyz(foo(bar))lmno)89 + 0: (abcde(fsh)xyz(foo(bar))lmno) + *** Failers +No match + abcd +No match + abcd) +No match + (abcd +No match + +/\( ( (?>[^()]+) | (?R) )* \) /Ixg +Capturing subpattern count = 1 +Partial matching not supported +Options: extended +First char = '(' +Need char = ')' + (ab(xy)cd)pqr + 0: (ab(xy)cd) + 1: cd + 1(abcd)(x(y)z)pqr + 0: (abcd) + 1: abcd + 0: (x(y)z) + 1: z + +/\( (?: (?>[^()]+) | (?R) ) \) /Ix +Capturing subpattern count = 0 +Partial matching not supported +Options: extended +First char = '(' +Need char = ')' + (abcd) + 0: (abcd) + (ab(xy)cd) + 0: (xy) + (a(b(c)d)e) + 0: (c) + ((ab)) + 0: ((ab)) + *** Failers +No match + () +No match + +/\( (?: (?>[^()]+) | (?R) )? \) /Ix +Capturing subpattern count = 0 +Partial matching not supported +Options: extended +First char = '(' +Need char = ')' + () + 0: () + 12(abcde(fsh)xyz(foo(bar))lmno)89 + 0: (fsh) + +/\( ( (?>[^()]+) | (?R) )* \) /Ix +Capturing subpattern count = 1 +Partial matching not supported +Options: extended +First char = '(' +Need char = ')' + (ab(xy)cd) + 0: (ab(xy)cd) + 1: cd + +/\( ( ( (?>[^()]+) | (?R) )* ) \) /Ix +Capturing subpattern count = 2 +Partial matching not supported +Options: extended +First char = '(' +Need char = ')' + (ab(xy)cd) + 0: (ab(xy)cd) + 1: ab(xy)cd + 2: cd + +/\( (123)? ( ( (?>[^()]+) | (?R) )* ) \) /Ix +Capturing subpattern count = 3 +Partial matching not supported +Options: extended +First char = '(' +Need char = ')' + (ab(xy)cd) + 0: (ab(xy)cd) + 1: + 2: ab(xy)cd + 3: cd + (123ab(xy)cd) + 0: (123ab(xy)cd) + 1: 123 + 2: ab(xy)cd + 3: cd + +/\( ( (123)? ( (?>[^()]+) | (?R) )* ) \) /Ix +Capturing subpattern count = 3 +Partial matching not supported +Options: extended +First char = '(' +Need char = ')' + (ab(xy)cd) + 0: (ab(xy)cd) + 1: ab(xy)cd + 2: + 3: cd + (123ab(xy)cd) + 0: (123ab(xy)cd) + 1: 123ab(xy)cd + 2: 123 + 3: cd + +/\( (((((((((( ( (?>[^()]+) | (?R) )* )))))))))) \) /Ix +Capturing subpattern count = 11 +Partial matching not supported +Options: extended +First char = '(' +Need char = ')' + (ab(xy)cd) + 0: (ab(xy)cd) + 1: ab(xy)cd + 2: ab(xy)cd + 3: ab(xy)cd + 4: ab(xy)cd + 5: ab(xy)cd + 6: ab(xy)cd + 7: ab(xy)cd + 8: ab(xy)cd + 9: ab(xy)cd +10: ab(xy)cd +11: cd + +/\( ( ( (?>[^()<>]+) | ((?>[^()]+)) | (?R) )* ) \) /Ix +Capturing subpattern count = 3 +Partial matching not supported +Options: extended +First char = '(' +Need char = ')' + (abcd(xyz

qrs)123) + 0: (abcd(xyz

qrs)123) + 1: abcd(xyz

qrs)123 + 2: 123 + 3: + +/\( ( ( (?>[^()]+) | ((?R)) )* ) \) /Ix +Capturing subpattern count = 3 +Partial matching not supported +Options: extended +First char = '(' +Need char = ')' + (ab(cd)ef) + 0: (ab(cd)ef) + 1: ab(cd)ef + 2: ef + 3: (cd) + (ab(cd(ef)gh)ij) + 0: (ab(cd(ef)gh)ij) + 1: ab(cd(ef)gh)ij + 2: ij + 3: (cd(ef)gh) + +/^[[:alnum:]]/DZ +------------------------------------------------------------------ + Bra + ^ + [0-9A-Za-z] + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Options: anchored +No first char +No need char + +/^[[:^alnum:]]/DZ +------------------------------------------------------------------ + Bra + ^ + [\x00-/:address@hidden (neg) + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Options: anchored +No first char +No need char + +/^[[:alpha:]]/DZ +------------------------------------------------------------------ + Bra + ^ + [A-Za-z] + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Options: anchored +No first char +No need char + +/^[[:^alpha:]]/DZ +------------------------------------------------------------------ + Bra + ^ + address@hidden (neg) + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Options: anchored +No first char +No need char + +/[_[:alpha:]]/IS +Capturing subpattern count = 0 +No options +No first char +No need char +Starting byte set: A B C D E F G H I J K L M N O P Q R S T U V W X Y Z + _ a b c d e f g h i j k l m n o p q r s t u v w x y z + +/^[[:ascii:]]/DZ +------------------------------------------------------------------ + Bra + ^ + [\x00-\x7f] + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Options: anchored +No first char +No need char + +/^[[:^ascii:]]/DZ +------------------------------------------------------------------ + Bra + ^ + [\x80-\xff] (neg) + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Options: anchored +No first char +No need char + +/^[[:blank:]]/DZ +------------------------------------------------------------------ + Bra + ^ + [\x09 ] + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Options: anchored +No first char +No need char + +/^[[:^blank:]]/DZ +------------------------------------------------------------------ + Bra + ^ + [\x00-\x08\x0a-\x1f!-\xff] (neg) + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Options: anchored +No first char +No need char + +/[\n\x0b\x0c\x0d[:blank:]]/IS +Capturing subpattern count = 0 +Contains explicit CR or LF match +No options +No first char +No need char +Starting byte set: \x09 \x0a \x0b \x0c \x0d \x20 + +/^[[:cntrl:]]/DZ +------------------------------------------------------------------ + Bra + ^ + [\x00-\x1f\x7f] + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Options: anchored +No first char +No need char + +/^[[:digit:]]/DZ +------------------------------------------------------------------ + Bra + ^ + [0-9] + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Options: anchored +No first char +No need char + +/^[[:graph:]]/DZ +------------------------------------------------------------------ + Bra + ^ + [!-~] + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Options: anchored +No first char +No need char + +/^[[:lower:]]/DZ +------------------------------------------------------------------ + Bra + ^ + [a-z] + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Options: anchored +No first char +No need char + +/^[[:print:]]/DZ +------------------------------------------------------------------ + Bra + ^ + [ -~] + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Options: anchored +No first char +No need char + +/^[[:punct:]]/DZ +------------------------------------------------------------------ + Bra + ^ + [!-/:address@hidden + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Options: anchored +No first char +No need char + +/^[[:space:]]/DZ +------------------------------------------------------------------ + Bra + ^ + [\x09-\x0d ] + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Options: anchored +No first char +No need char + +/^[[:upper:]]/DZ +------------------------------------------------------------------ + Bra + ^ + [A-Z] + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Options: anchored +No first char +No need char + +/^[[:xdigit:]]/DZ +------------------------------------------------------------------ + Bra + ^ + [0-9A-Fa-f] + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Options: anchored +No first char +No need char + +/^[[:word:]]/DZ +------------------------------------------------------------------ + Bra + ^ + [0-9A-Z_a-z] + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Options: anchored +No first char +No need char + +/^[[:^cntrl:]]/DZ +------------------------------------------------------------------ + Bra + ^ + [ -~\x80-\xff] (neg) + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Options: anchored +No first char +No need char + +/^[12[:^digit:]]/DZ +------------------------------------------------------------------ + Bra + ^ + [\x00-/12:-\xff] (neg) + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Options: anchored +No first char +No need char + +/^[[:^blank:]]/DZ +------------------------------------------------------------------ + Bra + ^ + [\x00-\x08\x0a-\x1f!-\xff] (neg) + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Options: anchored +No first char +No need char + +/[01[:alpha:]%]/DZ +------------------------------------------------------------------ + Bra + [%01A-Za-z] + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +No options +No first char +No need char + +/[[.ch.]]/I +Failed: POSIX collating elements are not supported at offset 1 + +/[[=ch=]]/I +Failed: POSIX collating elements are not supported at offset 1 + +/[[:rhubarb:]]/I +Failed: unknown POSIX class name at offset 3 + +/[[:upper:]]/Ii +Capturing subpattern count = 0 +Options: caseless +No first char +No need char + A + 0: A + a + 0: a + +/[[:lower:]]/Ii +Capturing subpattern count = 0 +Options: caseless +No first char +No need char + A + 0: A + a + 0: a + +/((?-i)[[:lower:]])[[:lower:]]/Ii +Capturing subpattern count = 1 +Options: caseless +No first char +No need char + ab + 0: ab + 1: a + aB + 0: aB + 1: a + *** Failers + 0: ai + 1: a + Ab +No match + AB +No match + +/[\200-\110]/I +Failed: range out of order in character class at offset 9 + +/^(?(0)f|b)oo/I +Failed: invalid condition (?(0) at offset 6 + +/This one's here because of the large output vector needed/I +Capturing subpattern count = 0 +No options +First char = 'T' +Need char = 'd' + +/(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$)) (\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\w+)\s+(\270)/I +Capturing subpattern count = 271 +Max back reference = 270 +Partial matching not supported +No options +No first char +No need char + \O900 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 ABC ABC + 0: 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 ABC ABC + 1: 1 + 2: 2 + 3: 3 + 4: 4 + 5: 5 + 6: 6 + 7: 7 + 8: 8 + 9: 9 +10: 10 +11: 11 +12: 12 +13: 13 +14: 14 +15: 15 +16: 16 +17: 17 +18: 18 +19: 19 +20: 20 +21: 21 +22: 22 +23: 23 +24: 24 +25: 25 +26: 26 +27: 27 +28: 28 +29: 29 +30: 30 +31: 31 +32: 32 +33: 33 +34: 34 +35: 35 +36: 36 +37: 37 +38: 38 +39: 39 +40: 40 +41: 41 +42: 42 +43: 43 +44: 44 +45: 45 +46: 46 +47: 47 +48: 48 +49: 49 +50: 50 +51: 51 +52: 52 +53: 53 +54: 54 +55: 55 +56: 56 +57: 57 +58: 58 +59: 59 +60: 60 +61: 61 +62: 62 +63: 63 +64: 64 +65: 65 +66: 66 +67: 67 +68: 68 +69: 69 +70: 70 +71: 71 +72: 72 +73: 73 +74: 74 +75: 75 +76: 76 +77: 77 +78: 78 +79: 79 +80: 80 +81: 81 +82: 82 +83: 83 +84: 84 +85: 85 +86: 86 +87: 87 +88: 88 +89: 89 +90: 90 +91: 91 +92: 92 +93: 93 +94: 94 +95: 95 +96: 96 +97: 97 +98: 98 +99: 99 +100: 100 +101: 101 +102: 102 +103: 103 +104: 104 +105: 105 +106: 106 +107: 107 +108: 108 +109: 109 +110: 110 +111: 111 +112: 112 +113: 113 +114: 114 +115: 115 +116: 116 +117: 117 +118: 118 +119: 119 +120: 120 +121: 121 +122: 122 +123: 123 +124: 124 +125: 125 +126: 126 +127: 127 +128: 128 +129: 129 +130: 130 +131: 131 +132: 132 +133: 133 +134: 134 +135: 135 +136: 136 +137: 137 +138: 138 +139: 139 +140: 140 +141: 141 +142: 142 +143: 143 +144: 144 +145: 145 +146: 146 +147: 147 +148: 148 +149: 149 +150: 150 +151: 151 +152: 152 +153: 153 +154: 154 +155: 155 +156: 156 +157: 157 +158: 158 +159: 159 +160: 160 +161: 161 +162: 162 +163: 163 +164: 164 +165: 165 +166: 166 +167: 167 +168: 168 +169: 169 +170: 170 +171: 171 +172: 172 +173: 173 +174: 174 +175: 175 +176: 176 +177: 177 +178: 178 +179: 179 +180: 180 +181: 181 +182: 182 +183: 183 +184: 184 +185: 185 +186: 186 +187: 187 +188: 188 +189: 189 +190: 190 +191: 191 +192: 192 +193: 193 +194: 194 +195: 195 +196: 196 +197: 197 +198: 198 +199: 199 +200: 200 +201: 201 +202: 202 +203: 203 +204: 204 +205: 205 +206: 206 +207: 207 +208: 208 +209: 209 +210: 210 +211: 211 +212: 212 +213: 213 +214: 214 +215: 215 +216: 216 +217: 217 +218: 218 +219: 219 +220: 220 +221: 221 +222: 222 +223: 223 +224: 224 +225: 225 +226: 226 +227: 227 +228: 228 +229: 229 +230: 230 +231: 231 +232: 232 +233: 233 +234: 234 +235: 235 +236: 236 +237: 237 +238: 238 +239: 239 +240: 240 +241: 241 +242: 242 +243: 243 +244: 244 +245: 245 +246: 246 +247: 247 +248: 248 +249: 249 +250: 250 +251: 251 +252: 252 +253: 253 +254: 254 +255: 255 +256: 256 +257: 257 +258: 258 +259: 259 +260: 260 +261: 261 +262: 262 +263: 263 +264: 264 +265: 265 +266: 266 +267: 267 +268: 268 +269: 269 +270: ABC +271: ABC + +/This one's here because Perl does this differently and PCRE can't at present/I +Capturing subpattern count = 0 +No options +First char = 'T' +Need char = 't' + +/(main(O)?)+/I +Capturing subpattern count = 2 +No options +First char = 'm' +Need char = 'n' + mainmain + 0: mainmain + 1: main + mainOmain + 0: mainOmain + 1: main + 2: O + +/These are all cases where Perl does it differently (nested captures)/I +Capturing subpattern count = 1 +No options +First char = 'T' +Need char = 's' + +/^(a(b)?)+$/I +Capturing subpattern count = 2 +Options: anchored +No first char +No need char + aba + 0: aba + 1: a + 2: b + +/^(aa(bb)?)+$/I +Capturing subpattern count = 2 +Options: anchored +No first char +No need char + aabbaa + 0: aabbaa + 1: aa + 2: bb + +/^(aa|aa(bb))+$/I +Capturing subpattern count = 2 +Options: anchored +No first char +No need char + aabbaa + 0: aabbaa + 1: aa + 2: bb + +/^(aa(bb)??)+$/I +Capturing subpattern count = 2 +Options: anchored +No first char +No need char + aabbaa + 0: aabbaa + 1: aa + 2: bb + +/^(?:aa(bb)?)+$/I +Capturing subpattern count = 1 +Options: anchored +No first char +No need char + aabbaa + 0: aabbaa + 1: bb + +/^(aa(b(b))?)+$/I +Capturing subpattern count = 3 +Options: anchored +No first char +No need char + aabbaa + 0: aabbaa + 1: aa + 2: bb + 3: b + +/^(?:aa(b(b))?)+$/I +Capturing subpattern count = 2 +Options: anchored +No first char +No need char + aabbaa + 0: aabbaa + 1: bb + 2: b + +/^(?:aa(b(?:b))?)+$/I +Capturing subpattern count = 1 +Options: anchored +No first char +No need char + aabbaa + 0: aabbaa + 1: bb + +/^(?:aa(bb(?:b))?)+$/I +Capturing subpattern count = 1 +Options: anchored +No first char +No need char + aabbbaa + 0: aabbbaa + 1: bbb + +/^(?:aa(b(?:bb))?)+$/I +Capturing subpattern count = 1 +Options: anchored +No first char +No need char + aabbbaa + 0: aabbbaa + 1: bbb + +/^(?:aa(?:b(b))?)+$/I +Capturing subpattern count = 1 +Options: anchored +No first char +No need char + aabbaa + 0: aabbaa + 1: b + +/^(?:aa(?:b(bb))?)+$/I +Capturing subpattern count = 1 +Options: anchored +No first char +No need char + aabbbaa + 0: aabbbaa + 1: bb + +/^(aa(b(bb))?)+$/I +Capturing subpattern count = 3 +Options: anchored +No first char +No need char + aabbbaa + 0: aabbbaa + 1: aa + 2: bbb + 3: bb + +/^(aa(bb(bb))?)+$/I +Capturing subpattern count = 3 +Options: anchored +No first char +No need char + aabbbbaa + 0: aabbbbaa + 1: aa + 2: bbbb + 3: bb + +/--------------------------------------------------------------------/I +Capturing subpattern count = 0 +No options +First char = '-' +Need char = '-' + +/#/IxDZ +------------------------------------------------------------------ + Bra + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Options: extended +No first char +No need char + +/a#/IxDZ +------------------------------------------------------------------ + Bra + a + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Options: extended +First char = 'a' +No need char + +/[\s]/DZ +------------------------------------------------------------------ + Bra + [\x09\x0a\x0c\x0d ] + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +No options +No first char +No need char + +/[\S]/DZ +------------------------------------------------------------------ + Bra + [\x00-\x08\x0b\x0e-\x1f!-\xff] (neg) + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +No options +No first char +No need char + +/a(?i)b/DZ +------------------------------------------------------------------ + Bra + a + 01 Opt + NC b + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +No options +First char = 'a' +Need char = 'b' (caseless) + ab + 0: ab + aB + 0: aB + *** Failers +No match + AB +No match + +/(a(?i)b)/DZ +------------------------------------------------------------------ + Bra + CBra 1 + a + 01 Opt + NC b + Ket + 00 Opt + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 1 +No options +First char = 'a' +Need char = 'b' (caseless) + ab + 0: ab + 1: ab + aB + 0: aB + 1: aB + *** Failers +No match + AB +No match + +/ (?i)abc/IxDZ +------------------------------------------------------------------ + Bra + NC abc + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Options: caseless extended +First char = 'a' (caseless) +Need char = 'c' (caseless) + +/#this is a comment + (?i)abc/IxDZ +------------------------------------------------------------------ + Bra + NC abc + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Options: caseless extended +First char = 'a' (caseless) +Need char = 'c' (caseless) + +/123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890/DZ +------------------------------------------------------------------ + Bra + 123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890 + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +No options +First char = '1' +Need char = '0' + +/\Q123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890/DZ +------------------------------------------------------------------ + Bra + 123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890 + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +No options +First char = '1' +Need char = '0' + +/\Q\E/DZ +------------------------------------------------------------------ + Bra + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +No options +No first char +No need char + \ + 0: + +/\Q\Ex/DZ +------------------------------------------------------------------ + Bra + x + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +No options +First char = 'x' +No need char + +/ \Q\E/DZ +------------------------------------------------------------------ + Bra + + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +No options +First char = ' ' +No need char + +/a\Q\E/DZ +------------------------------------------------------------------ + Bra + a + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +No options +First char = 'a' +No need char + abc + 0: a + bca + 0: a + bac + 0: a + +/a\Q\Eb/DZ +------------------------------------------------------------------ + Bra + ab + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +No options +First char = 'a' +Need char = 'b' + abc + 0: ab + +/\Q\Eabc/DZ +------------------------------------------------------------------ + Bra + abc + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +No options +First char = 'a' +Need char = 'c' + +/x*+\w/DZ +------------------------------------------------------------------ + Bra + x*+ + \w + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Partial matching not supported +No options +No first char +No need char + *** Failers + 0: F + xxxxx +No match + +/x?+/DZ +------------------------------------------------------------------ + Bra + x?+ + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +No options +No first char +No need char + +/x++/DZ +------------------------------------------------------------------ + Bra + x++ + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Partial matching not supported +No options +First char = 'x' +No need char + +/x{1,3}+/DZ +------------------------------------------------------------------ + Bra + Once + x + x{0,2} + Ket + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Partial matching not supported +No options +First char = 'x' +No need char + +/(x)*+/DZ +------------------------------------------------------------------ + Bra + Once + Brazero + CBra 1 + x + KetRmax + Ket + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 1 +No options +No first char +No need char + +/^(\w++|\s++)*$/I +Capturing subpattern count = 1 +Partial matching not supported +Options: anchored +No first char +No need char + now is the time for all good men to come to the aid of the party + 0: now is the time for all good men to come to the aid of the party + 1: party + *** Failers +No match + this is not a line with only words and spaces! +No match + +/(\d++)(\w)/I +Capturing subpattern count = 2 +Partial matching not supported +No options +No first char +No need char + 12345a + 0: 12345a + 1: 12345 + 2: a + *** Failers +No match + 12345+ +No match + +/a++b/I +Capturing subpattern count = 0 +Partial matching not supported +No options +First char = 'a' +Need char = 'b' + aaab + 0: aaab + +/(a++b)/I +Capturing subpattern count = 1 +Partial matching not supported +No options +First char = 'a' +Need char = 'b' + aaab + 0: aaab + 1: aaab + +/(a++)b/I +Capturing subpattern count = 1 +Partial matching not supported +No options +First char = 'a' +Need char = 'b' + aaab + 0: aaab + 1: aaa + +/([^()]++|\([^()]*\))+/I +Capturing subpattern count = 1 +Partial matching not supported +No options +No first char +No need char + ((abc(ade)ufh()()x + 0: abc(ade)ufh()()x + 1: x + +/\(([^()]++|\([^()]+\))+\)/I +Capturing subpattern count = 1 +Partial matching not supported +No options +First char = '(' +Need char = ')' + (abc) + 0: (abc) + 1: abc + (abc(def)xyz) + 0: (abc(def)xyz) + 1: xyz + *** Failers +No match + ((()aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa +No match + +/(abc){1,3}+/DZ +------------------------------------------------------------------ + Bra + Once + CBra 1 + abc + Ket + Brazero + Bra + CBra 1 + abc + Ket + Brazero + CBra 1 + abc + Ket + Ket + Ket + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 1 +No options +First char = 'a' +Need char = 'c' + +/a+?+/I +Failed: nothing to repeat at offset 3 + +/a{2,3}?+b/I +Failed: nothing to repeat at offset 7 + +/(?U)a+?+/I +Failed: nothing to repeat at offset 7 + +/a{2,3}?+b/IU +Failed: nothing to repeat at offset 7 + +/x(?U)a++b/DZ +------------------------------------------------------------------ + Bra + x + a++ + b + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Partial matching not supported +No options +First char = 'x' +Need char = 'b' + xaaaab + 0: xaaaab + +/(?U)xa++b/DZ +------------------------------------------------------------------ + Bra + x + a++ + b + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Partial matching not supported +Options: ungreedy +First char = 'x' +Need char = 'b' + xaaaab + 0: xaaaab + +/^((a+)(?U)([ab]+)(?-U)([bc]+)(\w*))/DZ +------------------------------------------------------------------ + Bra + ^ + CBra 1 + CBra 2 + a+ + Ket + CBra 3 + [ab]+? + Ket + CBra 4 + [bc]+ + Ket + CBra 5 + \w* + Ket + Ket + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 5 +Partial matching not supported +Options: anchored +No first char +No need char + +/^x(?U)a+b/DZ +------------------------------------------------------------------ + Bra + ^ + x + a++ + b + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Partial matching not supported +Options: anchored +No first char +Need char = 'b' + +/^x(?U)(a+)b/DZ +------------------------------------------------------------------ + Bra + ^ + x + CBra 1 + a+? + Ket + b + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 1 +Partial matching not supported +Options: anchored +No first char +Need char = 'b' + +/[.x.]/I +Failed: POSIX collating elements are not supported at offset 0 + +/[=x=]/I +Failed: POSIX collating elements are not supported at offset 0 + +/[:x:]/I +Failed: POSIX named classes are supported only within a class at offset 0 + +/\l/I +Failed: PCRE does not support \L, \l, \N, \U, or \u at offset 1 + +/\L/I +Failed: PCRE does not support \L, \l, \N, \U, or \u at offset 1 + +/\N{name}/I +Failed: PCRE does not support \L, \l, \N, \U, or \u at offset 1 + +/\u/I +Failed: PCRE does not support \L, \l, \N, \U, or \u at offset 1 + +/\U/I +Failed: PCRE does not support \L, \l, \N, \U, or \u at offset 1 + +/[/I +Failed: missing terminating ] for character class at offset 1 + +/[a-/I +Failed: missing terminating ] for character class at offset 3 + +/[[:space:]/I +Failed: missing terminating ] for character class at offset 10 + +/[\s]/IDZ +------------------------------------------------------------------ + Bra + [\x09\x0a\x0c\x0d ] + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +No options +No first char +No need char + +/[[:space:]]/IDZ +------------------------------------------------------------------ + Bra + [\x09-\x0d ] + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +No options +No first char +No need char + +/[[:space:]abcde]/IDZ +------------------------------------------------------------------ + Bra + [\x09-\x0d a-e] + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +No options +No first char +No need char + +/< (?: (?(R) \d++ | [^<>]*+) | (?R)) * >/Ix +Capturing subpattern count = 0 +Partial matching not supported +Options: extended +First char = '<' +Need char = '>' + <> + 0: <> + + 0: + hij> + 0: hij> + hij> + 0: + def> + 0: def> + + 0: <> + *** Failers +No match + iV\;\?aPhFB\qmj\;2\}YWFdYx\.Ap\]hjCPTP\(n28k\+3\;o\&WXqs\/gOXdr\$\:r\'do0\;b4c\(f_Gr\=\"\\4\)\[01T7ajQJvL\$W\~mL_sS\/4h\:x\*\[ZN\=KLs\&L5zX\/\/\>it\,o\:aU\(\;Z\>pW\&T7oP\'2K\^E\:x9\'c\[\%z\-\,64JQ5AeH_G\#KijUKghQw\^\\vea3a\?kka_G\$8\#\`\*kynsxzBLru\'\]k_\[7FrVx\}\^\=\$blx\>s\-N\%j\;D\*aZDnsw\:YKZ\%Q\.Kne9\#hP\?\+b3\(SOvL\,\^\;\&address@hidden)0RP6\{q\%L\^_z5E\'Dw6X\b|IDZ +------------------------------------------------------------------ + Bra + 8J$WE<.rX+ix[d1b!H#?vV0vrK:ZH1=2M>iV;?aPhFBqmj;2}YWFdYx.Ap]hjCPTP(n28k+3;o&WXqs/gOXdr$:r'do0;b4c(f_Gr="\4)[01T7ajQJvL$W~mL_sS/4h:x*[ZN=KLs&L5zX//>it,o:aU(;Z>pW&T7oP'2K^E:x9'c[%z-,64JQ5AeH_G#KijUKghQw^\vea3a?kka_G$8#`*kynsxzBLru']k_[7FrVx}^=$blx>s-N%j;D*aZDnsw:YKZ%Q.Kne9#hP?+b3(SOvL,^;&address@hidden)0RP6{q%L^_z5E'Dw6X + \b + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +No options +First char = '8' +Need char = 'X' + +|\$\<\.X\+ix\[d1b\!H\#\?vV0vrK\:ZH1\=2M\>iV\;\?aPhFB\qmj\;2\}YWFdYx\.Ap\]hjCPTP\(n28k\+3\;o\&WXqs\/gOXdr\$\:r\'do0\;b4c\(f_Gr\=\"\\4\)\[01T7ajQJvL\$W\~mL_sS\/4h\:x\*\[ZN\=KLs\&L5zX\/\/\>it\,o\:aU\(\;Z\>pW\&T7oP\'2K\^E\:x9\'c\[\%z\-\,64JQ5AeH_G\#KijUKghQw\^\\vea3a\?kka_G\$8\#\`\*kynsxzBLru\'\]k_\[7FrVx\}\^\=\$blx\>s\-N\%j\;D\*aZDnsw\:YKZ\%Q\.Kne9\#hP\?\+b3\(SOvL\,\^\;\&address@hidden)0RP6\{q\%L\^_z5E\'Dw6X\b|IDZ +------------------------------------------------------------------ + Bra + $<.X+ix[d1b!H#?vV0vrK:ZH1=2M>iV;?aPhFBqmj;2}YWFdYx.Ap]hjCPTP(n28k+3;o&WXqs/gOXdr$:r'do0;b4c(f_Gr="\4)[01T7ajQJvL$W~mL_sS/4h:x*[ZN=KLs&L5zX//>it,o:aU(;Z>pW&T7oP'2K^E:x9'c[%z-,64JQ5AeH_G#KijUKghQw^\vea3a?kka_G$8#`*kynsxzBLru']k_[7FrVx}^=$blx>s-N%j;D*aZDnsw:YKZ%Q.Kne9#hP?+b3(SOvL,^;&address@hidden)0RP6{q%L^_z5E'Dw6X + \b + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +No options +First char = '$' +Need char = 'X' + +/(.*)\d+\1/I +Capturing subpattern count = 1 +Max back reference = 1 +Partial matching not supported +No options +No first char +No need char + +/(.*)\d+/I +Capturing subpattern count = 1 +Partial matching not supported +No options +First char at start or follows newline +No need char + +/(.*)\d+\1/Is +Capturing subpattern count = 1 +Max back reference = 1 +Partial matching not supported +Options: dotall +No first char +No need char + +/(.*)\d+/Is +Capturing subpattern count = 1 +Partial matching not supported +Options: anchored dotall +No first char +No need char + +/(.*(xyz))\d+\2/I +Capturing subpattern count = 2 +Max back reference = 2 +Partial matching not supported +No options +First char at start or follows newline +Need char = 'z' + +/((.*))\d+\1/I +Capturing subpattern count = 2 +Max back reference = 1 +Partial matching not supported +No options +No first char +No need char + abc123bc + 0: bc123bc + 1: bc + 2: bc + +/a[b]/I +Capturing subpattern count = 0 +No options +First char = 'a' +Need char = 'b' + +/(?=a).*/I +Capturing subpattern count = 0 +Partial matching not supported +No options +First char = 'a' +No need char + +/(?=abc).xyz/IiI +Capturing subpattern count = 0 +Options: caseless +First char = 'a' (caseless) +Need char = 'z' (caseless) + +/(?=abc)(?i).xyz/I +Capturing subpattern count = 0 +No options +First char = 'a' +Need char = 'z' (caseless) + +/(?=a)(?=b)/I +Capturing subpattern count = 0 +No options +First char = 'a' +No need char + +/(?=.)a/I +Capturing subpattern count = 0 +No options +First char = 'a' +No need char + +/((?=abcda)a)/I +Capturing subpattern count = 1 +No options +First char = 'a' +Need char = 'a' + +/((?=abcda)ab)/I +Capturing subpattern count = 1 +No options +First char = 'a' +Need char = 'b' + +/()a/I +Capturing subpattern count = 1 +No options +No first char +Need char = 'a' + +/(?(1)ab|ac)(.)/I +Capturing subpattern count = 1 +No options +First char = 'a' +No need char + +/(?(1)abz|acz)(.)/I +Capturing subpattern count = 1 +No options +First char = 'a' +Need char = 'z' + +/(?(1)abz)(.)/I +Capturing subpattern count = 1 +No options +No first char +No need char + +/(?(1)abz)(1)23/I +Capturing subpattern count = 1 +No options +No first char +Need char = '3' + +/(a)+/I +Capturing subpattern count = 1 +No options +First char = 'a' +No need char + +/(a){2,3}/I +Capturing subpattern count = 1 +No options +First char = 'a' +Need char = 'a' + +/(a)*/I +Capturing subpattern count = 1 +No options +No first char +No need char + +/[a]/I +Capturing subpattern count = 0 +No options +First char = 'a' +No need char + +/[ab]/I +Capturing subpattern count = 0 +No options +No first char +No need char + +/[ab]/IS +Capturing subpattern count = 0 +No options +No first char +No need char +Starting byte set: a b + +/[^a]/I +Capturing subpattern count = 0 +No options +No first char +No need char + +/\d456/I +Capturing subpattern count = 0 +No options +No first char +Need char = '6' + +/\d456/IS +Capturing subpattern count = 0 +No options +No first char +Need char = '6' +Starting byte set: 0 1 2 3 4 5 6 7 8 9 + +/a^b/I +Capturing subpattern count = 0 +No options +First char = 'a' +Need char = 'b' + +/^a/Im +Capturing subpattern count = 0 +Options: multiline +First char at start or follows newline +Need char = 'a' + abcde + 0: a + xy\nabc + 0: a + *** Failers +No match + xyabc +No match + +/c|abc/I +Capturing subpattern count = 0 +No options +No first char +Need char = 'c' + +/(?i)[ab]/IS +Capturing subpattern count = 0 +Options: caseless +No first char +No need char +Starting byte set: A B a b + +/[ab](?i)cd/IS +Capturing subpattern count = 0 +No options +No first char +Need char = 'd' (caseless) +Starting byte set: a b + +/abc(?C)def/I +Capturing subpattern count = 0 +No options +First char = 'a' +Need char = 'f' + abcdef +--->abcdef + 0 ^ ^ d + 0: abcdef + 1234abcdef +--->1234abcdef + 0 ^ ^ d + 0: abcdef + *** Failers +No match + abcxyz +No match + abcxyzf +--->abcxyzf + 0 ^ ^ d +No match + +/abc(?C)de(?C1)f/I +Capturing subpattern count = 0 +No options +First char = 'a' +Need char = 'f' + 123abcdef +--->123abcdef + 0 ^ ^ d + 1 ^ ^ f + 0: abcdef + +/(?C1)\dabc(?C2)def/I +Capturing subpattern count = 0 +No options +No first char +Need char = 'f' + 1234abcdef +--->1234abcdef + 1 ^ \d + 1 ^ \d + 1 ^ \d + 1 ^ \d + 2 ^ ^ d + 0: 4abcdef + *** Failers +No match + abcdef +--->abcdef + 1 ^ \d + 1 ^ \d + 1 ^ \d + 1 ^ \d + 1 ^ \d + 1 ^ \d +No match + +/(?C255)ab/I +Capturing subpattern count = 0 +No options +First char = 'a' +Need char = 'b' + +/(?C256)ab/I +Failed: number after (?C is > 255 at offset 6 + +/(?Cab)xx/I +Failed: closing ) for (?C expected at offset 3 + +/(?C12vr)x/I +Failed: closing ) for (?C expected at offset 5 + +/abc(?C)def/I +Capturing subpattern count = 0 +No options +First char = 'a' +Need char = 'f' + *** Failers +No match + \x83\x0\x61bcdef +--->\x83\x00abcdef + 0 ^ ^ d + 0: abcdef + +/(abc)(?C)de(?C1)f/I +Capturing subpattern count = 1 +No options +First char = 'a' +Need char = 'f' + 123abcdef +--->123abcdef + 0 ^ ^ d + 1 ^ ^ f + 0: abcdef + 1: abc + 123abcdef\C+ +Callout 0: last capture = 1 + 0: + 1: abc +--->123abcdef + ^ ^ d +Callout 1: last capture = 1 + 0: + 1: abc +--->123abcdef + ^ ^ f + 0: abcdef + 1: abc + 123abcdef\C- + 0: abcdef + 1: abc + *** Failers +No match + 123abcdef\C!1 +--->123abcdef + 0 ^ ^ d + 1 ^ ^ f +No match + +/(?C0)(abc(?C1))*/I +Capturing subpattern count = 1 +No options +No first char +No need char + abcabcabc +--->abcabcabc + 0 ^ (abc(?C1))* + 1 ^ ^ ) + 1 ^ ^ ) + 1 ^ ^ ) + 0: abcabcabc + 1: abc + abcabc\C!1!3 +--->abcabc + 0 ^ (abc(?C1))* + 1 ^ ^ ) + 1 ^ ^ ) + 0: abcabc + 1: abc + *** Failers +--->*** Failers + 0 ^ (abc(?C1))* + 0: + abcabcabc\C!1!3 +--->abcabcabc + 0 ^ (abc(?C1))* + 1 ^ ^ ) + 1 ^ ^ ) + 1 ^ ^ ) + 0: abcabc + 1: abc + +/(\d{3}(?C))*/I +Capturing subpattern count = 1 +Partial matching not supported +No options +No first char +No need char + 123\C+ +Callout 0: last capture = -1 + 0: +--->123 + ^ ^ ) + 0: 123 + 1: 123 + 123456\C+ +Callout 0: last capture = -1 + 0: +--->123456 + ^ ^ ) +Callout 0: last capture = 1 + 0: + 1: 123 +--->123456 + ^ ^ ) + 0: 123456 + 1: 456 + 123456789\C+ +Callout 0: last capture = -1 + 0: +--->123456789 + ^ ^ ) +Callout 0: last capture = 1 + 0: + 1: 123 +--->123456789 + ^ ^ ) +Callout 0: last capture = 1 + 0: + 1: 456 +--->123456789 + ^ ^ ) + 0: 123456789 + 1: 789 + +/((xyz)(?C)p|(?C1)xyzabc)/I +Capturing subpattern count = 2 +No options +First char = 'x' +No need char + xyzabc\C+ +Callout 0: last capture = 2 + 0: + 1: + 2: xyz +--->xyzabc + ^ ^ p +Callout 1: last capture = -1 + 0: +--->xyzabc + ^ x + 0: xyzabc + 1: xyzabc + +/(X)((xyz)(?C)p|(?C1)xyzabc)/I +Capturing subpattern count = 3 +No options +First char = 'X' +Need char = 'x' + Xxyzabc\C+ +Callout 0: last capture = 3 + 0: + 1: X + 2: + 3: xyz +--->Xxyzabc + ^ ^ p +Callout 1: last capture = 1 + 0: + 1: X +--->Xxyzabc + ^^ x + 0: Xxyzabc + 1: X + 2: xyzabc + +/(?=(abc))(?C)abcdef/I +Capturing subpattern count = 1 +No options +First char = 'a' +Need char = 'f' + abcdef\C+ +Callout 0: last capture = 1 + 0: + 1: abc +--->abcdef + ^ a + 0: abcdef + 1: abc + +/(?!(abc)(?C1)d)(?C2)abcxyz/I +Capturing subpattern count = 1 +No options +First char = 'a' +Need char = 'z' + abcxyz\C+ +Callout 1: last capture = 1 + 0: + 1: abc +--->abcxyz + ^ ^ d +Callout 2: last capture = -1 + 0: +--->abcxyz + ^ a + 0: abcxyz + +/(?<=(abc)(?C))xyz/I +Capturing subpattern count = 1 +No options +First char = 'x' +Need char = 'z' + abcxyz\C+ +Callout 0: last capture = 1 + 0: + 1: abc +--->abcxyz + ^ ) + 0: xyz + 1: abc + +/a(b+)(c*)(?C1)/I +Capturing subpattern count = 2 +Partial matching not supported +No options +First char = 'a' +Need char = 'b' + abbbbbccc\C*1 +--->abbbbbccc + 1 ^ ^ +Callout data = 1 + 1 ^ ^ +Callout data = 1 + 1 ^ ^ +Callout data = 1 + 1 ^ ^ +Callout data = 1 + 1 ^ ^ +Callout data = 1 + 1 ^ ^ +Callout data = 1 + 1 ^ ^ +Callout data = 1 + 1 ^ ^ +Callout data = 1 +No match + +/a(b+?)(c*?)(?C1)/I +Capturing subpattern count = 2 +Partial matching not supported +No options +First char = 'a' +Need char = 'b' + abbbbbccc\C*1 +--->abbbbbccc + 1 ^ ^ +Callout data = 1 + 1 ^ ^ +Callout data = 1 + 1 ^ ^ +Callout data = 1 + 1 ^ ^ +Callout data = 1 + 1 ^ ^ +Callout data = 1 + 1 ^ ^ +Callout data = 1 + 1 ^ ^ +Callout data = 1 + 1 ^ ^ +Callout data = 1 +No match + +/(?C)abc/I +Capturing subpattern count = 0 +No options +First char = 'a' +Need char = 'c' + +/(?C)^abc/I +Capturing subpattern count = 0 +Options: anchored +No first char +No need char + +/(?C)a|b/IS +Capturing subpattern count = 0 +No options +No first char +No need char +Starting byte set: a b + +/(?R)/I +Failed: recursive call could loop indefinitely at offset 3 + +/(a|(?R))/I +Failed: recursive call could loop indefinitely at offset 6 + +/(ab|(bc|(de|(?R))))/I +Failed: recursive call could loop indefinitely at offset 15 + +/x(ab|(bc|(de|(?R))))/I +Capturing subpattern count = 3 +No options +First char = 'x' +No need char + xab + 0: xab + 1: ab + xbc + 0: xbc + 1: bc + 2: bc + xde + 0: xde + 1: de + 2: de + 3: de + xxab + 0: xxab + 1: xab + 2: xab + 3: xab + xxxab + 0: xxxab + 1: xxab + 2: xxab + 3: xxab + *** Failers +No match + xyab +No match + +/(ab|(bc|(de|(?1))))/I +Failed: recursive call could loop indefinitely at offset 15 + +/x(ab|(bc|(de|(?1)x)x)x)/I +Failed: recursive call could loop indefinitely at offset 16 + +/^([^()]|\((?1)*\))*$/I +Capturing subpattern count = 1 +Options: anchored +No first char +No need char + abc + 0: abc + 1: c + a(b)c + 0: a(b)c + 1: c + a(b(c))d + 0: a(b(c))d + 1: d + *** Failers) +No match + a(b(c)d +No match + +/^>abc>([^()]|\((?1)*\))*abc>123abc>123abc>1(2)3abc>1(2)3abc>(1(2)3)abc>(1(2)3) + 2: + 3: Satan, oscillate my metallic sonatas + 4: S + A man, a plan, a canal: Panama! + 0: A man, a plan, a canal: Panama! + 1: + 2: + 3: A man, a plan, a canal: Panama + 4: A + Able was I ere I saw Elba. + 0: Able was I ere I saw Elba. + 1: + 2: + 3: Able was I ere I saw Elba + 4: A + *** Failers +No match + The quick brown fox +No match + +/^(\d+|\((?1)([+*-])(?1)\)|-(?1))$/I +Capturing subpattern count = 2 +Partial matching not supported +Options: anchored +No first char +No need char + 12 + 0: 12 + 1: 12 + (((2+2)*-3)-7) + 0: (((2+2)*-3)-7) + 1: (((2+2)*-3)-7) + 2: - + -12 + 0: -12 + 1: -12 + *** Failers +No match + ((2+2)*-3)-7) +No match + +/^(x(y|(?1){2})z)/I +Capturing subpattern count = 2 +Options: anchored +No first char +No need char + xyz + 0: xyz + 1: xyz + 2: y + xxyzxyzz + 0: xxyzxyzz + 1: xxyzxyzz + 2: xyzxyz + *** Failers +No match + xxyzz +No match + xxyzxyzxyzz +No match + +/((< (?: (?(R) \d++ | [^<>]*+) | (?2)) * >))/Ix +Capturing subpattern count = 2 +Partial matching not supported +Options: extended +First char = '<' +Need char = '>' + <> + 0: <> + 1: <> + 2: <> + + 0: + 1: + 2: + hij> + 0: hij> + 1: hij> + 2: hij> + hij> + 0: + 1: + 2: + def> + 0: def> + 1: def> + 2: def> + + 0: <> + 1: <> + 2: <> + *** Failers +No match + b|c)d(?Pe)/DZ +------------------------------------------------------------------ + Bra + a + CBra 1 + b + Alt + c + Ket + d + CBra 2 + e + Ket + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 2 +Named capturing subpatterns: + longername2 2 + name1 1 +No options +First char = 'a' +Need char = 'e' + abde + 0: abde + 1: b + 2: e + acde + 0: acde + 1: c + 2: e + +/(?:a(?Pc(?Pd)))(?Pa)/DZ +------------------------------------------------------------------ + Bra + Bra + a + CBra 1 + c + CBra 2 + d + Ket + Ket + Ket + CBra 3 + a + Ket + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 3 +Named capturing subpatterns: + a 3 + c 1 + d 2 +No options +First char = 'a' +Need char = 'a' + +/(?Pa)...(?P=a)bbb(?P>a)d/DZ +------------------------------------------------------------------ + Bra + CBra 1 + a + Ket + Any + Any + Any + \1 + bbb + Once + Recurse + Ket + d + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 1 +Max back reference = 1 +Named capturing subpatterns: + a 1 +No options +First char = 'a' +Need char = 'd' + +/^\W*(?:(?P(?P.)\W*(?P>one)\W*(?P=two)|)|(?P(?P.)\W*(?P>three)\W*(?P=four)|\W*.\W*))\W*$/Ii +Capturing subpattern count = 4 +Max back reference = 4 +Named capturing subpatterns: + four 4 + one 1 + three 3 + two 2 +Partial matching not supported +Options: anchored caseless +No first char +No need char + 1221 + 0: 1221 + 1: 1221 + 2: 1 + Satan, oscillate my metallic sonatas! + 0: Satan, oscillate my metallic sonatas! + 1: + 2: + 3: Satan, oscillate my metallic sonatas + 4: S + A man, a plan, a canal: Panama! + 0: A man, a plan, a canal: Panama! + 1: + 2: + 3: A man, a plan, a canal: Panama + 4: A + Able was I ere I saw Elba. + 0: Able was I ere I saw Elba. + 1: + 2: + 3: Able was I ere I saw Elba + 4: A + *** Failers +No match + The quick brown fox +No match + +/((?(R)a|b))\1(?1)?/I +Capturing subpattern count = 1 +Max back reference = 1 +No options +No first char +No need char + bb + 0: bb + 1: b + bbaa + 0: bba + 1: b + +/(.*)a/Is +Capturing subpattern count = 1 +Partial matching not supported +Options: anchored dotall +No first char +Need char = 'a' + +/(.*)a\1/Is +Capturing subpattern count = 1 +Max back reference = 1 +Partial matching not supported +Options: dotall +No first char +Need char = 'a' + +/(.*)a(b)\2/Is +Capturing subpattern count = 2 +Max back reference = 2 +Partial matching not supported +Options: anchored dotall +No first char +Need char = 'b' + +/((.*)a|(.*)b)z/Is +Capturing subpattern count = 3 +Partial matching not supported +Options: anchored dotall +No first char +Need char = 'z' + +/((.*)a|(.*)b)z\1/Is +Capturing subpattern count = 3 +Max back reference = 1 +Partial matching not supported +Options: dotall +No first char +Need char = 'z' + +/((.*)a|(.*)b)z\2/Is +Capturing subpattern count = 3 +Max back reference = 2 +Partial matching not supported +Options: dotall +No first char +Need char = 'z' + +/((.*)a|(.*)b)z\3/Is +Capturing subpattern count = 3 +Max back reference = 3 +Partial matching not supported +Options: dotall +No first char +Need char = 'z' + +/((.*)a|^(.*)b)z\3/Is +Capturing subpattern count = 3 +Max back reference = 3 +Partial matching not supported +Options: anchored dotall +No first char +Need char = 'z' + +/(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)a/Is +Capturing subpattern count = 31 +Partial matching not supported +Options: anchored dotall +No first char +No need char + +/(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)a\31/Is +Capturing subpattern count = 31 +Max back reference = 31 +Partial matching not supported +Options: dotall +No first char +No need char + +/(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)a\32/Is +Capturing subpattern count = 32 +Max back reference = 32 +Partial matching not supported +Options: dotall +No first char +No need char + +/(a)(bc)/INDZ +------------------------------------------------------------------ + Bra + Bra + a + Ket + Bra + bc + Ket + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Options: no_auto_capture +First char = 'a' +Need char = 'c' + abc + 0: abc + +/(?Pa)(bc)/INDZ +------------------------------------------------------------------ + Bra + CBra 1 + a + Ket + Bra + bc + Ket + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 1 +Named capturing subpatterns: + one 1 +Options: no_auto_capture +First char = 'a' +Need char = 'c' + abc + 0: abc + 1: a + +/(a)(?Pbc)/INDZ +------------------------------------------------------------------ + Bra + Bra + a + Ket + CBra 1 + bc + Ket + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 1 +Named capturing subpatterns: + named 1 +Options: no_auto_capture +First char = 'a' +Need char = 'c' + +/(a+)*zz/I +Capturing subpattern count = 1 +Partial matching not supported +No options +No first char +Need char = 'z' + aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaazzbbbbbb\M +Minimum match() limit = 8 +Minimum match() recursion limit = 6 + 0: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaazz + 1: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa + aaaaaaaaaaaaaz\M +Minimum match() limit = 32768 +Minimum match() recursion limit = 42 +No match + +/(aaa(?C1)bbb|ab)/I +Capturing subpattern count = 1 +No options +First char = 'a' +Need char = 'b' + aaabbb +--->aaabbb + 1 ^ ^ b + 0: aaabbb + 1: aaabbb + aaabbb\C*0 +--->aaabbb + 1 ^ ^ b + 0: aaabbb + 1: aaabbb + aaabbb\C*1 +--->aaabbb + 1 ^ ^ b +Callout data = 1 + 0: ab + 1: ab + aaabbb\C*-1 +--->aaabbb + 1 ^ ^ b +Callout data = -1 +No match + +/ab(?Pcd)ef(?Pgh)/I +Capturing subpattern count = 2 +Named capturing subpatterns: + one 1 + two 2 +No options +First char = 'a' +Need char = 'h' + abcdefgh + 0: abcdefgh + 1: cd + 2: gh + abcdefgh\C1\Gtwo + 0: abcdefgh + 1: cd + 2: gh + 1C cd (2) + G gh (2) two + abcdefgh\Cone\Ctwo + 0: abcdefgh + 1: cd + 2: gh + C cd (2) one + C gh (2) two + abcdefgh\Cthree +no parentheses with name "three" + 0: abcdefgh + 1: cd + 2: gh +copy substring three failed -7 + +/(?P)(?P)/DZ +------------------------------------------------------------------ + Bra + CBra 1 + Ket + CBra 2 + Ket + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 2 +Named capturing subpatterns: + Tes 1 + Test 2 +No options +No first char +No need char + +/(?P)(?P)/DZ +------------------------------------------------------------------ + Bra + CBra 1 + Ket + CBra 2 + Ket + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 2 +Named capturing subpatterns: + Tes 2 + Test 1 +No options +No first char +No need char + +/(?Pzz)(?Paa)/I +Capturing subpattern count = 2 +Named capturing subpatterns: + A 2 + Z 1 +No options +First char = 'z' +Need char = 'a' + zzaa\CZ + 0: zzaa + 1: zz + 2: aa + C zz (2) Z + zzaa\CA + 0: zzaa + 1: zz + 2: aa + C aa (2) A + +/(?Peks)(?Peccs)/I +Failed: two named subpatterns have the same name at offset 15 + +/(?Pabc(?Pdef)(?Pxyz))/I +Failed: two named subpatterns have the same name at offset 30 + +"\[((?P\d+)(,(?P>elem))*)\]"I +Capturing subpattern count = 3 +Named capturing subpatterns: + elem 2 +Partial matching not supported +No options +First char = '[' +Need char = ']' + [10,20,30,5,5,4,4,2,43,23,4234] + 0: [10,20,30,5,5,4,4,2,43,23,4234] + 1: 10,20,30,5,5,4,4,2,43,23,4234 + 2: 10 + 3: ,4234 + *** Failers +No match + [] +No match + +"\[((?P\d+)(,(?P>elem))*)?\]"I +Capturing subpattern count = 3 +Named capturing subpatterns: + elem 2 +Partial matching not supported +No options +First char = '[' +Need char = ']' + [10,20,30,5,5,4,4,2,43,23,4234] + 0: [10,20,30,5,5,4,4,2,43,23,4234] + 1: 10,20,30,5,5,4,4,2,43,23,4234 + 2: 10 + 3: ,4234 + [] + 0: [] + +/(a(b(?2)c))?/DZ +------------------------------------------------------------------ + Bra + Brazero + CBra 1 + a + CBra 2 + b + Once + Recurse + Ket + c + Ket + Ket + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 2 +No options +No first char +No need char + +/(a(b(?2)c))*/DZ +------------------------------------------------------------------ + Bra + Brazero + CBra 1 + a + CBra 2 + b + Once + Recurse + Ket + c + Ket + KetRmax + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 2 +No options +No first char +No need char + +/(a(b(?2)c)){0,2}/DZ +------------------------------------------------------------------ + Bra + Brazero + Bra + CBra 1 + a + CBra 2 + b + Once + Recurse + Ket + c + Ket + Ket + Brazero + CBra 1 + a + CBra 2 + b + Once + Recurse + Ket + c + Ket + Ket + Ket + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 2 +No options +No first char +No need char + +/[ab]{1}+/DZ +------------------------------------------------------------------ + Bra + Once + [ab]{1,1} + Ket + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +No options +No first char +No need char + +/((w\/|-|with)*(free|immediate)*.*?shipping\s*[!.-]*)/Ii +Capturing subpattern count = 3 +Partial matching not supported +Options: caseless +No first char +Need char = 'g' (caseless) + Baby Bjorn Active Carrier - With free SHIPPING!! + 0: Baby Bjorn Active Carrier - With free SHIPPING!! + 1: Baby Bjorn Active Carrier - With free SHIPPING!! + +/((w\/|-|with)*(free|immediate)*.*?shipping\s*[!.-]*)/IiS +Capturing subpattern count = 3 +Partial matching not supported +Options: caseless +No first char +Need char = 'g' (caseless) +Study returned NULL + Baby Bjorn Active Carrier - With free SHIPPING!! + 0: Baby Bjorn Active Carrier - With free SHIPPING!! + 1: Baby Bjorn Active Carrier - With free SHIPPING!! + +/a*.*b/ISDZ +------------------------------------------------------------------ + Bra + a* + Any* + b + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Partial matching not supported +No options +No first char +Need char = 'b' +Study returned NULL + +/(a|b)*.?c/ISDZ +------------------------------------------------------------------ + Bra + Brazero + CBra 1 + a + Alt + b + KetRmax + Any? + c + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 1 +No options +No first char +Need char = 'c' +Study returned NULL + +/abc(?C255)de(?C)f/DZ +------------------------------------------------------------------ + Bra + abc + Callout 255 10 1 + de + Callout 0 16 1 + f + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +No options +First char = 'a' +Need char = 'f' + +/abcde/ICDZ +------------------------------------------------------------------ + Bra + Callout 255 0 1 + a + Callout 255 1 1 + b + Callout 255 2 1 + c + Callout 255 3 1 + d + Callout 255 4 1 + e + Callout 255 5 0 + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Options: +First char = 'a' +Need char = 'e' + abcde +--->abcde + +0 ^ a + +1 ^^ b + +2 ^ ^ c + +3 ^ ^ d + +4 ^ ^ e + +5 ^ ^ + 0: abcde + abcdfe +--->abcdfe + +0 ^ a + +1 ^^ b + +2 ^ ^ c + +3 ^ ^ d + +4 ^ ^ e +No match + +/a*b/ICDZ +------------------------------------------------------------------ + Bra + Callout 255 0 2 + a*+ + Callout 255 2 1 + b + Callout 255 3 0 + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Partial matching not supported +Options: +No first char +Need char = 'b' + ab +--->ab + +0 ^ a* + +2 ^^ b + +3 ^ ^ + 0: ab + aaaab +--->aaaab + +0 ^ a* + +2 ^ ^ b + +3 ^ ^ + 0: aaaab + aaaacb +--->aaaacb + +0 ^ a* + +2 ^ ^ b + +0 ^ a* + +2 ^ ^ b + +0 ^ a* + +2 ^ ^ b + +0 ^ a* + +2 ^^ b + +0 ^ a* + +2 ^ b + +0 ^ a* + +2 ^ b + +3 ^^ + 0: b + +/a+b/ICDZ +------------------------------------------------------------------ + Bra + Callout 255 0 2 + a++ + Callout 255 2 1 + b + Callout 255 3 0 + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Partial matching not supported +Options: +First char = 'a' +Need char = 'b' + ab +--->ab + +0 ^ a+ + +2 ^^ b + +3 ^ ^ + 0: ab + aaaab +--->aaaab + +0 ^ a+ + +2 ^ ^ b + +3 ^ ^ + 0: aaaab + aaaacb +--->aaaacb + +0 ^ a+ + +2 ^ ^ b + +0 ^ a+ + +2 ^ ^ b + +0 ^ a+ + +2 ^ ^ b + +0 ^ a+ + +2 ^^ b +No match + +/(abc|def)x/ICDZ +------------------------------------------------------------------ + Bra + Callout 255 0 9 + CBra 1 + Callout 255 1 1 + a + Callout 255 2 1 + b + Callout 255 3 1 + c + Callout 255 4 0 + Alt + Callout 255 5 1 + d + Callout 255 6 1 + e + Callout 255 7 1 + f + Callout 255 8 0 + Ket + Callout 255 9 1 + x + Callout 255 10 0 + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 1 +Options: +No first char +Need char = 'x' + abcx +--->abcx + +0 ^ (abc|def) + +1 ^ a + +2 ^^ b + +3 ^ ^ c + +4 ^ ^ | + +9 ^ ^ x ++10 ^ ^ + 0: abcx + 1: abc + defx +--->defx + +0 ^ (abc|def) + +1 ^ a + +5 ^ d + +6 ^^ e + +7 ^ ^ f + +8 ^ ^ ) + +9 ^ ^ x ++10 ^ ^ + 0: defx + 1: def + abcdefzx +--->abcdefzx + +0 ^ (abc|def) + +1 ^ a + +2 ^^ b + +3 ^ ^ c + +4 ^ ^ | + +9 ^ ^ x + +5 ^ d + +0 ^ (abc|def) + +1 ^ a + +5 ^ d + +0 ^ (abc|def) + +1 ^ a + +5 ^ d + +0 ^ (abc|def) + +1 ^ a + +5 ^ d + +6 ^^ e + +7 ^ ^ f + +8 ^ ^ ) + +9 ^ ^ x + +0 ^ (abc|def) + +1 ^ a + +5 ^ d + +0 ^ (abc|def) + +1 ^ a + +5 ^ d + +0 ^ (abc|def) + +1 ^ a + +5 ^ d + +0 ^ (abc|def) + +1 ^ a + +5 ^ d +No match + +/(ab|cd){3,4}/IC +Capturing subpattern count = 1 +Options: +No first char +No need char + ababab +--->ababab + +0 ^ (ab|cd){3,4} + +1 ^ a + +2 ^^ b + +3 ^ ^ | + +1 ^ ^ a + +2 ^ ^ b + +3 ^ ^ | + +1 ^ ^ a + +2 ^ ^ b + +3 ^ ^ | + +1 ^ ^ a + +4 ^ ^ c ++12 ^ ^ + 0: ababab + 1: ab + abcdabcd +--->abcdabcd + +0 ^ (ab|cd){3,4} + +1 ^ a + +2 ^^ b + +3 ^ ^ | + +1 ^ ^ a + +4 ^ ^ c + +5 ^ ^ d + +6 ^ ^ ) + +1 ^ ^ a + +2 ^ ^ b + +3 ^ ^ | + +1 ^ ^ a + +4 ^ ^ c + +5 ^ ^ d + +6 ^ ^ ) ++12 ^ ^ + 0: abcdabcd + 1: cd + abcdcdcdcdcd +--->abcdcdcdcdcd + +0 ^ (ab|cd){3,4} + +1 ^ a + +2 ^^ b + +3 ^ ^ | + +1 ^ ^ a + +4 ^ ^ c + +5 ^ ^ d + +6 ^ ^ ) + +1 ^ ^ a + +4 ^ ^ c + +5 ^ ^ d + +6 ^ ^ ) + +1 ^ ^ a + +4 ^ ^ c + +5 ^ ^ d + +6 ^ ^ ) ++12 ^ ^ + 0: abcdcdcd + 1: cd + +/([ab]{,4}c|xy)/ICDZ +------------------------------------------------------------------ + Bra + Callout 255 0 14 + CBra 1 + Callout 255 1 4 + [ab] + Callout 255 5 1 + { + Callout 255 6 1 + , + Callout 255 7 1 + 4 + Callout 255 8 1 + } + Callout 255 9 1 + c + Callout 255 10 0 + Alt + Callout 255 11 1 + x + Callout 255 12 1 + y + Callout 255 13 0 + Ket + Callout 255 14 0 + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 1 +Options: +No first char +No need char + Note: that { does NOT introduce a quantifier +--->Note: that { does NOT introduce a quantifier + +0 ^ ([ab]{,4}c|xy) + +1 ^ [ab] ++11 ^ x + +0 ^ ([ab]{,4}c|xy) + +1 ^ [ab] ++11 ^ x + +0 ^ ([ab]{,4}c|xy) + +1 ^ [ab] ++11 ^ x + +0 ^ ([ab]{,4}c|xy) + +1 ^ [ab] ++11 ^ x + +0 ^ ([ab]{,4}c|xy) + +1 ^ [ab] ++11 ^ x + +0 ^ ([ab]{,4}c|xy) + +1 ^ [ab] ++11 ^ x + +0 ^ ([ab]{,4}c|xy) + +1 ^ [ab] ++11 ^ x + +0 ^ ([ab]{,4}c|xy) + +1 ^ [ab] ++11 ^ x + +0 ^ ([ab]{,4}c|xy) + +1 ^ [ab] + +5 ^^ { ++11 ^ x + +0 ^ ([ab]{,4}c|xy) + +1 ^ [ab] ++11 ^ x + +0 ^ ([ab]{,4}c|xy) + +1 ^ [ab] ++11 ^ x + +0 ^ ([ab]{,4}c|xy) + +1 ^ [ab] ++11 ^ x + +0 ^ ([ab]{,4}c|xy) + +1 ^ [ab] ++11 ^ x + +0 ^ ([ab]{,4}c|xy) + +1 ^ [ab] ++11 ^ x + +0 ^ ([ab]{,4}c|xy) + +1 ^ [ab] ++11 ^ x + +0 ^ ([ab]{,4}c|xy) + +1 ^ [ab] ++11 ^ x + +0 ^ ([ab]{,4}c|xy) + +1 ^ [ab] ++11 ^ x + +0 ^ ([ab]{,4}c|xy) + +1 ^ [ab] ++11 ^ x + +0 ^ ([ab]{,4}c|xy) + +1 ^ [ab] ++11 ^ x + +0 ^ ([ab]{,4}c|xy) + +1 ^ [ab] ++11 ^ x + +0 ^ ([ab]{,4}c|xy) + +1 ^ [ab] ++11 ^ x + +0 ^ ([ab]{,4}c|xy) + +1 ^ [ab] ++11 ^ x + +0 ^ ([ab]{,4}c|xy) + +1 ^ [ab] ++11 ^ x + +0 ^ ([ab]{,4}c|xy) + +1 ^ [ab] ++11 ^ x + +0 ^ ([ab]{,4}c|xy) + +1 ^ [ab] ++11 ^ x + +0 ^ ([ab]{,4}c|xy) + +1 ^ [ab] ++11 ^ x + +0 ^ ([ab]{,4}c|xy) + +1 ^ [ab] ++11 ^ x + +0 ^ ([ab]{,4}c|xy) + +1 ^ [ab] ++11 ^ x + +0 ^ ([ab]{,4}c|xy) + +1 ^ [ab] ++11 ^ x + +0 ^ ([ab]{,4}c|xy) + +1 ^ [ab] ++11 ^ x + +0 ^ ([ab]{,4}c|xy) + +1 ^ [ab] ++11 ^ x + +0 ^ ([ab]{,4}c|xy) + +1 ^ [ab] ++11 ^ x + +0 ^ ([ab]{,4}c|xy) + +1 ^ [ab] + +5 ^^ { ++11 ^ x + +0 ^ ([ab]{,4}c|xy) + +1 ^ [ab] ++11 ^ x + +0 ^ ([ab]{,4}c|xy) + +1 ^ [ab] ++11 ^ x + +0 ^ ([ab]{,4}c|xy) + +1 ^ [ab] ++11 ^ x + +0 ^ ([ab]{,4}c|xy) + +1 ^ [ab] + +5 ^^ { ++11 ^ x + +0 ^ ([ab]{,4}c|xy) + +1 ^ [ab] ++11 ^ x + +0 ^ ([ab]{,4}c|xy) + +1 ^ [ab] ++11 ^ x + +0 ^ ([ab]{,4}c|xy) + +1 ^ [ab] ++11 ^ x + +0 ^ ([ab]{,4}c|xy) + +1 ^ [ab] ++11 ^ x + +0 ^ ([ab]{,4}c|xy) + +1 ^ [ab] ++11 ^ x + +0 ^ ([ab]{,4}c|xy) + +1 ^ [ab] ++11 ^ x + +0 ^ ([ab]{,4}c|xy) + +1 ^ [ab] ++11 ^ x + +0 ^ ([ab]{,4}c|xy) + +1 ^ [ab] ++11 ^ x +No match + +/([ab]{1,4}c|xy){4,5}?123/ICDZ +------------------------------------------------------------------ + Bra + Callout 255 0 21 + CBra 1 + Callout 255 1 9 + [ab]{1,4} + Callout 255 10 1 + c + Callout 255 11 0 + Alt + Callout 255 12 1 + x + Callout 255 13 1 + y + Callout 255 14 0 + Ket + CBra 1 + Callout 255 1 9 + [ab]{1,4} + Callout 255 10 1 + c + Callout 255 11 0 + Alt + Callout 255 12 1 + x + Callout 255 13 1 + y + Callout 255 14 0 + Ket + CBra 1 + Callout 255 1 9 + [ab]{1,4} + Callout 255 10 1 + c + Callout 255 11 0 + Alt + Callout 255 12 1 + x + Callout 255 13 1 + y + Callout 255 14 0 + Ket + CBra 1 + Callout 255 1 9 + [ab]{1,4} + Callout 255 10 1 + c + Callout 255 11 0 + Alt + Callout 255 12 1 + x + Callout 255 13 1 + y + Callout 255 14 0 + Ket + Braminzero + CBra 1 + Callout 255 1 9 + [ab]{1,4} + Callout 255 10 1 + c + Callout 255 11 0 + Alt + Callout 255 12 1 + x + Callout 255 13 1 + y + Callout 255 14 0 + Ket + Callout 255 21 1 + 1 + Callout 255 22 1 + 2 + Callout 255 23 1 + 3 + Callout 255 24 0 + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 1 +Partial matching not supported +Options: +No first char +Need char = '3' + aacaacaacaacaac123 +--->aacaacaacaacaac123 + +0 ^ ([ab]{1,4}c|xy){4,5}? + +1 ^ [ab]{1,4} ++10 ^ ^ c ++11 ^ ^ | + +1 ^ ^ [ab]{1,4} ++10 ^ ^ c ++11 ^ ^ | + +1 ^ ^ [ab]{1,4} ++10 ^ ^ c ++11 ^ ^ | + +1 ^ ^ [ab]{1,4} ++10 ^ ^ c ++11 ^ ^ | ++21 ^ ^ 1 + +1 ^ ^ [ab]{1,4} ++10 ^ ^ c ++11 ^ ^ | ++21 ^ ^ 1 ++22 ^ ^ 2 ++23 ^ ^ 3 ++24 ^ ^ + 0: aacaacaacaacaac123 + 1: aac + +/\b.*/I +Capturing subpattern count = 0 +Partial matching not supported +No options +No first char +No need char + ab cd\>1 + 0: cd + +/\b.*/Is +Capturing subpattern count = 0 +Partial matching not supported +Options: dotall +No first char +No need char + ab cd\>1 + 0: cd + +/(?!.bcd).*/I +Capturing subpattern count = 0 +Partial matching not supported +No options +No first char +No need char + Xbcd12345 + 0: bcd12345 + +/abcde/I +Capturing subpattern count = 0 +No options +First char = 'a' +Need char = 'e' + ab\P +Partial match + abc\P +Partial match + abcd\P +Partial match + abcde\P + 0: abcde + the quick brown abc\P +Partial match + ** Failers\P +No match + the quick brown abxyz fox\P +No match + +"^(0?[1-9]|[12][0-9]|3[01])/(0?[1-9]|1[012])/(20)?\d\d$"I +Capturing subpattern count = 3 +Options: anchored +No first char +Need char = '/' + 13/05/04\P + 0: 13/05/04 + 1: 13 + 2: 05 + 13/5/2004\P + 0: 13/5/2004 + 1: 13 + 2: 5 + 3: 20 + 02/05/09\P + 0: 02/05/09 + 1: 02 + 2: 05 + 1\P +Partial match + 1/2\P +Partial match + 1/2/0\P +Partial match + 1/2/04\P + 0: 1/2/04 + 1: 1 + 2: 2 + 0\P +Partial match + 02/\P +Partial match + 02/0\P +Partial match + 02/1\P +Partial match + ** Failers\P +No match + \P +No match + 123\P +No match + 33/4/04\P +No match + 3/13/04\P +No match + 0/1/2003\P +No match + 0/\P +No match + 02/0/\P +No match + 02/13\P +No match + +/0{0,2}ABC/I +Capturing subpattern count = 0 +Partial matching not supported +No options +No first char +Need char = 'C' + +/\d{3,}ABC/I +Capturing subpattern count = 0 +Partial matching not supported +No options +No first char +Need char = 'C' + +/\d*ABC/I +Capturing subpattern count = 0 +Partial matching not supported +No options +No first char +Need char = 'C' + +/[abc]+DE/I +Capturing subpattern count = 0 +Partial matching not supported +No options +No first char +Need char = 'E' + +/[abc]?123/I +Capturing subpattern count = 0 +No options +No first char +Need char = '3' + 123\P + 0: 123 + a\P +Partial match + b\P +Partial match + c\P +Partial match + c12\P +Partial match + c123\P + 0: c123 + +/^(?:\d){3,5}X/I +Capturing subpattern count = 0 +Options: anchored +No first char +Need char = 'X' + 1\P +Partial match + 123\P +Partial match + 123X + 0: 123X + 1234\P +Partial match + 1234X + 0: 1234X + 12345\P +Partial match + 12345X + 0: 12345X + *** Failers +No match + 1X +No match + 123456\P +No match + +/abc/I>testsavedregex +Capturing subpattern count = 0 +No options +First char = 'a' +Need char = 'c' +Compiled regex written to testsavedregex +testsavedregex +Capturing subpattern count = 0 +No options +First char = 'a' +Need char = 'c' +Compiled regex written to testsavedregex +testsavedregex +Capturing subpattern count = 1 +No options +No first char +No need char +Starting byte set: a b +Compiled regex written to testsavedregex +Study data written to testsavedregex +testsavedregex +Capturing subpattern count = 1 +No options +No first char +No need char +Starting byte set: a b +Compiled regex written to testsavedregex +Study data written to testsavedregex +(.)*~smgI +Capturing subpattern count = 3 +Max back reference = 1 +Partial matching not supported +Options: multiline dotall +First char = '<' +Need char = '>' + \n\n\nPartner der LCO\nde\nPartner der LINEAS Consulting\nGmbH\nLINEAS Consulting GmbH Hamburg\nPartnerfirmen\n30 days\nindex,follow\n\nja\n3\nPartner\n\n\nLCO\nLINEAS Consulting\n15.10.2003\n\n\n\n\nDie Partnerfirmen der LINEAS Consulting\nGmbH\n\n\n \n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n + 0: \x0a\x0aPartner der LCO\x0ade\x0aPartner der LINEAS Consulting\x0aGmbH\x0aLINEAS Consulting GmbH Hamburg\x0aPartnerfirmen\x0a30 days\x0aindex,follow\x0a\x0aja\x0a3\x0aPartner\x0a\x0a\x0aLCO\x0aLINEAS Consulting\x0a15.10.2003\x0a\x0a\x0a\x0a\x0aDie Partnerfirmen der LINEAS Consulting\x0aGmbH\x0a\x0a\x0a \x0a\x0a\x0a\x0a\x0a\x0a\x0a\x0a\x0a\x0a\x0a\x0a\x0a\x0a\x0a\x0a\x0a\x0a\x0a\x0a\x0a\x0a + 1: seite + 2: \x0a + 3: seite + +/^a/IF +Capturing subpattern count = 0 +Options: anchored +No first char +No need char + +/line\nbreak/I +Capturing subpattern count = 0 +Contains explicit CR or LF match +No options +First char = 'l' +Need char = 'k' + this is a line\nbreak + 0: line\x0abreak + line one\nthis is a line\nbreak in the second line + 0: line\x0abreak + +/line\nbreak/If +Capturing subpattern count = 0 +Contains explicit CR or LF match +Options: firstline +First char = 'l' +Need char = 'k' + this is a line\nbreak + 0: line\x0abreak + ** Failers +No match + line one\nthis is a line\nbreak in the second line +No match + +/line\nbreak/Imf +Capturing subpattern count = 0 +Contains explicit CR or LF match +Options: multiline firstline +First char = 'l' +Need char = 'k' + this is a line\nbreak + 0: line\x0abreak + ** Failers +No match + line one\nthis is a line\nbreak in the second line +No match + +/ab.cd/IP + ab-cd + 0: ab-cd + ab=cd + 0: ab=cd + ** Failers +No match: POSIX code 17: match failed + ab\ncd +No match: POSIX code 17: match failed + +/ab.cd/IPs + ab-cd + 0: ab-cd + ab=cd + 0: ab=cd + ab\ncd + 0: ab\x0acd + +/(?i)(?-i)AbCd/I +Capturing subpattern count = 0 +No options +First char = 'A' +Need char = 'd' + AbCd + 0: AbCd + ** Failers +No match + abcd +No match + +/a{11111111111111111111}/I +Failed: number too big in {} quantifier at offset 22 + +/(){64294967295}/I +Failed: number too big in {} quantifier at offset 14 + +/(){2,4294967295}/I +Failed: number too big in {} quantifier at offset 15 + +"(?i:a)(?i:b)(?i:c)(?i:d)(?i:e)(?i:f)(?i:g)(?i:h)(?i:i)(?i:j)(k)(?i:l)A\1B"I +Capturing subpattern count = 1 +Max back reference = 1 +No options +First char = 'a' (caseless) +Need char = 'B' + abcdefghijklAkB + 0: abcdefghijklAkB + 1: k + +"(?Pa)(?Pb)(?Pc)(?Pd)(?Pe)(?Pf)(?Pg)(?Ph)(?Pi)(?Pj)(?Pk)(?Pl)A\11B"I +Capturing subpattern count = 12 +Max back reference = 11 +Named capturing subpatterns: + n0 1 + n1 2 + n10 11 + n11 12 + n2 3 + n3 4 + n4 5 + n5 6 + n6 7 + n7 8 + n8 9 + n9 10 +No options +First char = 'a' +Need char = 'B' + abcdefghijklAkB + 0: abcdefghijklAkB + 1: a + 2: b + 3: c + 4: d + 5: e + 6: f + 7: g + 8: h + 9: i +10: j +11: k +12: l + +"(a)(b)(c)(d)(e)(f)(g)(h)(i)(j)(k)(l)A\11B"I +Capturing subpattern count = 12 +Max back reference = 11 +No options +First char = 'a' +Need char = 'B' + abcdefghijklAkB + 0: abcdefghijklAkB + 1: a + 2: b + 3: c + 4: d + 5: e + 6: f + 7: g + 8: h + 9: i +10: j +11: k +12: l + +"(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)"I +Capturing subpattern count = 101 +Named capturing subpatterns: + name0 1 + name1 2 + name10 11 + name100 101 + name11 12 + name12 13 + name13 14 + name14 15 + name15 16 + name16 17 + name17 18 + name18 19 + name19 20 + name2 3 + name20 21 + name21 22 + name22 23 + name23 24 + name24 25 + name25 26 + name26 27 + name27 28 + name28 29 + name29 30 + name3 4 + name30 31 + name31 32 + name32 33 + name33 34 + name34 35 + name35 36 + name36 37 + name37 38 + name38 39 + name39 40 + name4 5 + name40 41 + name41 42 + name42 43 + name43 44 + name44 45 + name45 46 + name46 47 + name47 48 + name48 49 + name49 50 + name5 6 + name50 51 + name51 52 + name52 53 + name53 54 + name54 55 + name55 56 + name56 57 + name57 58 + name58 59 + name59 60 + name6 7 + name60 61 + name61 62 + name62 63 + name63 64 + name64 65 + name65 66 + name66 67 + name67 68 + name68 69 + name69 70 + name7 8 + name70 71 + name71 72 + name72 73 + name73 74 + name74 75 + name75 76 + name76 77 + name77 78 + name78 79 + name79 80 + name8 9 + name80 81 + name81 82 + name82 83 + name83 84 + name84 85 + name85 86 + name86 87 + name87 88 + name88 89 + name89 90 + name9 10 + name90 91 + name91 92 + name92 93 + name93 94 + name94 95 + name95 96 + name96 97 + name97 98 + name98 99 + name99 100 +No options +First char = 'a' +Need char = 'a' + aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa +Matched, but too many substrings + 0: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa + 1: a + 2: a + 3: a + 4: a + 5: a + 6: a + 7: a + 8: a + 9: a +10: a +11: a +12: a +13: a +14: a + +"(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)"I +Capturing subpattern count = 101 +No options +First char = 'a' +Need char = 'a' + aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa +Matched, but too many substrings + 0: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa + 1: a + 2: a + 3: a + 4: a + 5: a + 6: a + 7: a + 8: a + 9: a +10: a +11: a +12: a +13: a +14: a + +/[^()]*(?:\((?R)\)[^()]*)*/I +Capturing subpattern count = 0 +Partial matching not supported +No options +No first char +No need char + (this(and)that + 0: + (this(and)that) + 0: (this(and)that) + (this(and)that)stuff + 0: (this(and)that)stuff + +/[^()]*(?:\((?>(?R))\)[^()]*)*/I +Capturing subpattern count = 0 +Partial matching not supported +No options +No first char +No need char + (this(and)that + 0: + (this(and)that) + 0: (this(and)that) + +/[^()]*(?:\((?R)\))*[^()]*/I +Capturing subpattern count = 0 +Partial matching not supported +No options +No first char +No need char + (this(and)that + 0: + (this(and)that) + 0: (this(and)that) + +/(?:\((?R)\))*[^()]*/I +Capturing subpattern count = 0 +Partial matching not supported +No options +No first char +No need char + (this(and)that + 0: + (this(and)that) + 0: + ((this)) + 0: ((this)) + +/(?:\((?R)\))|[^()]*/I +Capturing subpattern count = 0 +Partial matching not supported +No options +No first char +No need char + (this(and)that + 0: + (this(and)that) + 0: + (this) + 0: (this) + ((this)) + 0: ((this)) + +/a(b)c/IPN + abc +Matched with REG_NOSUB + +/a(?Pb)c/IPN + abc +Matched with REG_NOSUB + +/\x{100}/I +Failed: character value in \x{...} sequence is too large at offset 6 + +/\x{0000ff}/I +Capturing subpattern count = 0 +No options +First char = 255 +No need char + +/^((?Pa1)|(?Pa2)b)/I +Failed: two named subpatterns have the same name at offset 17 + +/^((?Pa1)|(?Pa2)b)/IJ +Capturing subpattern count = 3 +Named capturing subpatterns: + A 2 + A 3 +Options: anchored dupnames +No first char +No need char + a1b\CA + 0: a1 + 1: a1 + 2: a1 + C a1 (2) A + a2b\CA + 0: a2b + 1: a2b + 2: + 3: a2 + C a2 (2) A + ** Failers +No match + a1b\CZ\CA +no parentheses with name "Z" + 0: a1 + 1: a1 + 2: a1 +copy substring Z failed -7 + C a1 (2) A + +/^(?Pa)(?Pb)/IJ +Capturing subpattern count = 2 +Named capturing subpatterns: + A 1 + A 2 +Options: anchored dupnames +No first char +No need char + ab\CA + 0: ab + 1: a + 2: b + C a (1) A + +/^(?Pa)(?Pb)|cd/IJ +Capturing subpattern count = 2 +Named capturing subpatterns: + A 1 + A 2 +Options: dupnames +No first char +No need char + ab\CA + 0: ab + 1: a + 2: b + C a (1) A + cd\CA + 0: cd +copy substring A failed -7 + +/^(?Pa)(?Pb)|cd(?Pef)(?Pgh)/IJ +Capturing subpattern count = 4 +Named capturing subpatterns: + A 1 + A 2 + A 3 + A 4 +Options: dupnames +No first char +No need char + cdefgh\CA + 0: cdefgh + 1: + 2: + 3: ef + 4: gh + C ef (2) A + +/^((?Pa1)|(?Pa2)b)/IJ +Capturing subpattern count = 3 +Named capturing subpatterns: + A 2 + A 3 +Options: anchored dupnames +No first char +No need char + a1b\GA + 0: a1 + 1: a1 + 2: a1 + G a1 (2) A + a2b\GA + 0: a2b + 1: a2b + 2: + 3: a2 + G a2 (2) A + ** Failers +No match + a1b\GZ\GA +no parentheses with name "Z" + 0: a1 + 1: a1 + 2: a1 +copy substring Z failed -7 + G a1 (2) A + +/^(?Pa)(?Pb)/IJ +Capturing subpattern count = 2 +Named capturing subpatterns: + A 1 + A 2 +Options: anchored dupnames +No first char +No need char + ab\GA + 0: ab + 1: a + 2: b + G a (1) A + +/^(?Pa)(?Pb)|cd/IJ +Capturing subpattern count = 2 +Named capturing subpatterns: + A 1 + A 2 +Options: dupnames +No first char +No need char + ab\GA + 0: ab + 1: a + 2: b + G a (1) A + cd\GA + 0: cd +copy substring A failed -7 + +/^(?Pa)(?Pb)|cd(?Pef)(?Pgh)/IJ +Capturing subpattern count = 4 +Named capturing subpatterns: + A 1 + A 2 + A 3 + A 4 +Options: dupnames +No first char +No need char + cdefgh\GA + 0: cdefgh + 1: + 2: + 3: ef + 4: gh + G ef (2) A + +/(?J)^((?Pa1)|(?Pa2)b)/I +Capturing subpattern count = 3 +Named capturing subpatterns: + A 2 + A 3 +Options: anchored dupnames +Duplicate name status changes +No first char +No need char + a1b\CA + 0: a1 + 1: a1 + 2: a1 + C a1 (2) A + a2b\CA + 0: a2b + 1: a2b + 2: + 3: a2 + C a2 (2) A + +/^(?Pa) (?J:(?Pb)(?Pc)) (?Pd)/I +Failed: two named subpatterns have the same name at offset 37 + +/ In this next test, J is not set at the outer level; consequently it isn't +set in the pattern's options; consequently pcre_get_named_substring() produces +a random value. /Ix +Capturing subpattern count = 1 +Options: extended +First char = 'I' +Need char = 'e' + +/^(?Pa) (?J:(?Pb)(?Pc)) (?Pd)/I +Capturing subpattern count = 4 +Named capturing subpatterns: + A 1 + B 2 + B 3 + C 4 +Options: anchored +Duplicate name status changes +No first char +No need char + a bc d\CA\CB\CC + 0: a bc d + 1: a + 2: b + 3: c + 4: d + C a (1) A + C b (1) B + C d (1) C + +/^(?Pa)?(?(A)a|b)/I +Capturing subpattern count = 1 +Named capturing subpatterns: + A 1 +Options: anchored +No first char +No need char + aabc + 0: aa + 1: a + bc + 0: b + ** Failers +No match + abc +No match + +/(?:(?(ZZ)a|b)(?PX))+/I +Capturing subpattern count = 1 +Named capturing subpatterns: + ZZ 1 +No options +No first char +Need char = 'X' + bXaX + 0: bXaX + 1: X + +/(?:(?(2y)a|b)(X))+/I +Failed: reference to non-existent subpattern at offset 9 + +/(?:(?(ZA)a|b)(?PX))+/I +Failed: reference to non-existent subpattern at offset 9 + +/(?:(?(ZZ)a|b)(?(ZZ)a|b)(?PX))+/I +Capturing subpattern count = 1 +Named capturing subpatterns: + ZZ 1 +No options +No first char +Need char = 'X' + bbXaaX + 0: bbXaaX + 1: X + +/(?:(?(ZZ)a|\(b\))\\(?PX))+/I +Capturing subpattern count = 1 +Named capturing subpatterns: + ZZ 1 +No options +No first char +Need char = 'X' + (b)\\Xa\\X + 0: (b)\Xa\X + 1: X + +/(?PX|Y))+/I +Capturing subpattern count = 1 +Max back reference = 1 +Named capturing subpatterns: + A 1 +No options +No first char +No need char + bXXaYYaY + 0: bXXaYYaY + 1: Y + bXYaXXaX + 0: bX + 1: X + +/()()()()()()()()()(?:(?(A)(?P=A)a|b)(?PX|Y))+/I +Capturing subpattern count = 10 +Max back reference = 10 +Named capturing subpatterns: + A 10 +No options +No first char +No need char + bXXaYYaY + 0: bXXaYYaY + 1: + 2: + 3: + 4: + 5: + 6: + 7: + 8: + 9: +10: Y + +/\777/I +Failed: octal value is greater than \377 (not in UTF-8 mode) at offset 3 + +/\s*,\s*/IS +Capturing subpattern count = 0 +Partial matching not supported +No options +No first char +Need char = ',' +Starting byte set: \x09 \x0a \x0c \x0d \x20 , + \x0b,\x0b + 0: , + \x0c,\x0d + 0: \x0c,\x0d + +/^abc/Im +Capturing subpattern count = 0 +Options: multiline +First char at start or follows newline +Need char = 'c' + xyz\nabc + 0: abc + xyz\nabc\ + 0: abc + xyz\r\nabc\ + 0: abc + xyz\rabc\ + 0: abc + xyz\r\nabc\ + 0: abc + ** Failers +No match + xyz\nabc\ +No match + xyz\r\nabc\ +No match + xyz\nabc\ +No match + xyz\rabc\ +No match + xyz\rabc\ +No match + +/abc$/Im +Capturing subpattern count = 0 +Options: multiline +Forced newline sequence: LF +First char = 'a' +Need char = 'c' + xyzabc + 0: abc + xyzabc\n + 0: abc + xyzabc\npqr + 0: abc + xyzabc\r\ + 0: abc + xyzabc\rpqr\ + 0: abc + xyzabc\r\n\ + 0: abc + xyzabc\r\npqr\ + 0: abc + ** Failers +No match + xyzabc\r +No match + xyzabc\rpqr +No match + xyzabc\r\n +No match + xyzabc\r\npqr +No match + +/^abc/Im +Capturing subpattern count = 0 +Options: multiline +Forced newline sequence: CR +First char at start or follows newline +Need char = 'c' + xyz\rabcdef + 0: abc + xyz\nabcdef\ + 0: abc + ** Failers +No match + xyz\nabcdef +No match + +/^abc/Im +Capturing subpattern count = 0 +Options: multiline +Forced newline sequence: LF +First char at start or follows newline +Need char = 'c' + xyz\nabcdef + 0: abc + xyz\rabcdef\ + 0: abc + ** Failers +No match + xyz\rabcdef +No match + +/^abc/Im +Capturing subpattern count = 0 +Options: multiline +Forced newline sequence: CRLF +First char at start or follows newline +Need char = 'c' + xyz\r\nabcdef + 0: abc + xyz\rabcdef\ + 0: abc + ** Failers +No match + xyz\rabcdef +No match + +/^abc/Im +Unknown newline type at: + + +/abc/I +Capturing subpattern count = 0 +No options +First char = 'a' +Need char = 'c' + xyz\rabc\ +Unknown newline type at: + abc + 0: abc + +/.*/I +Capturing subpattern count = 0 +Partial matching not supported +Options: +Forced newline sequence: LF +First char at start or follows newline +No need char + abc\ndef + 0: abc + abc\rdef + 0: abc\x0ddef + abc\r\ndef + 0: abc\x0d + \abc\ndef + 0: abc\x0adef + \abc\rdef + 0: abc + \abc\r\ndef + 0: abc + \abc\ndef + 0: abc\x0adef + \abc\rdef + 0: abc\x0ddef + \abc\r\ndef + 0: abc + +/\w+(.)(.)?def/Is +Capturing subpattern count = 2 +Partial matching not supported +Options: dotall +No first char +Need char = 'f' + abc\ndef + 0: abc\x0adef + 1: \x0a + abc\rdef + 0: abc\x0ddef + 1: \x0d + abc\r\ndef + 0: abc\x0d\x0adef + 1: \x0d + 2: \x0a + ++((?:\s|//.*\\n|/[*](?:\\n|.)*?[*]/)*)+I +Capturing subpattern count = 1 +Partial matching not supported +No options +No first char +No need char + /* this is a C style comment */\M +Minimum match() limit = 120 +Minimum match() recursion limit = 6 + 0: /* this is a C style comment */ + 1: /* this is a C style comment */ + +/(?P25[0-5]|2[0-4]\d|[01]?\d?\d)(?:\.(?P>B)){3}/I +Capturing subpattern count = 1 +Named capturing subpatterns: + B 1 +No options +No first char +Need char = '.' + +/()()()()()()()()()()()()()()()()()()()() + ()()()()()()()()()()()()()()()()()()()() + ()()()()()()()()()()()()()()()()()()()() + ()()()()()()()()()()()()()()()()()()()() + ()()()()()()()()()()()()()()()()()()()() + (.(.))/Ix +Capturing subpattern count = 102 +Options: extended +No first char +No need char + XY\O400 + 0: XY + 1: + 2: + 3: + 4: + 5: + 6: + 7: + 8: + 9: +10: +11: +12: +13: +14: +15: +16: +17: +18: +19: +20: +21: +22: +23: +24: +25: +26: +27: +28: +29: +30: +31: +32: +33: +34: +35: +36: +37: +38: +39: +40: +41: +42: +43: +44: +45: +46: +47: +48: +49: +50: +51: +52: +53: +54: +55: +56: +57: +58: +59: +60: +61: +62: +63: +64: +65: +66: +67: +68: +69: +70: +71: +72: +73: +74: +75: +76: +77: +78: +79: +80: +81: +82: +83: +84: +85: +86: +87: +88: +89: +90: +91: +92: +93: +94: +95: +96: +97: +98: +99: +100: +101: XY +102: Y + +/(a*b|(?i:c*(?-i)d))/IS +Capturing subpattern count = 1 +Partial matching not supported +No options +No first char +No need char +Starting byte set: C a b c d + +/()[ab]xyz/IS +Capturing subpattern count = 1 +No options +No first char +Need char = 'z' +Starting byte set: a b + +/(|)[ab]xyz/IS +Capturing subpattern count = 1 +No options +No first char +Need char = 'z' +Starting byte set: a b + +/(|c)[ab]xyz/IS +Capturing subpattern count = 1 +No options +No first char +Need char = 'z' +Starting byte set: a b c + +/(|c?)[ab]xyz/IS +Capturing subpattern count = 1 +No options +No first char +Need char = 'z' +Starting byte set: a b c + +/(d?|c?)[ab]xyz/IS +Capturing subpattern count = 1 +No options +No first char +Need char = 'z' +Starting byte set: a b c d + +/(d?|c)[ab]xyz/IS +Capturing subpattern count = 1 +No options +No first char +Need char = 'z' +Starting byte set: a b c d + +/^a*b\d/DZ +------------------------------------------------------------------ + Bra + ^ + a*+ + b + \d + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Partial matching not supported +Options: anchored +No first char +Need char = 'b' + +/^a*+b\d/DZ +------------------------------------------------------------------ + Bra + ^ + a*+ + b + \d + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Partial matching not supported +Options: anchored +No first char +Need char = 'b' + +/^a*?b\d/DZ +------------------------------------------------------------------ + Bra + ^ + a*+ + b + \d + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Partial matching not supported +Options: anchored +No first char +Need char = 'b' + +/^a+A\d/DZ +------------------------------------------------------------------ + Bra + ^ + a++ + A + \d + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Partial matching not supported +Options: anchored +No first char +Need char = 'A' + aaaA5 + 0: aaaA5 + ** Failers +No match + aaaa5 +No match + +/^a*A\d/IiDZ +------------------------------------------------------------------ + Bra + ^ + a* + NC A + \d + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Partial matching not supported +Options: anchored caseless +No first char +Need char = 'A' (caseless) + aaaA5 + 0: aaaA5 + aaaa5 + 0: aaaa5 + +/(a*|b*)[cd]/IS +Capturing subpattern count = 1 +Partial matching not supported +No options +No first char +No need char +Starting byte set: a b c d + +/(a+|b*)[cd]/IS +Capturing subpattern count = 1 +Partial matching not supported +No options +No first char +No need char +Starting byte set: a b c d + +/(a*|b+)[cd]/IS +Capturing subpattern count = 1 +Partial matching not supported +No options +No first char +No need char +Starting byte set: a b c d + +/(a+|b+)[cd]/IS +Capturing subpattern count = 1 +Partial matching not supported +No options +No first char +No need char +Starting byte set: a b + +/(((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((( + (((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((( + ((( + a + )))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))) + )))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))) + ))) +/Ix +Capturing subpattern count = 203 +Options: extended +First char = 'a' +No need char + large nest +Matched, but too many substrings + 0: a + 1: a + 2: a + 3: a + 4: a + 5: a + 6: a + 7: a + 8: a + 9: a +10: a +11: a +12: a +13: a +14: a + +/a*\d/BZ +------------------------------------------------------------------ + Bra + a*+ + \d + Ket + End +------------------------------------------------------------------ + +/a*\D/BZ +------------------------------------------------------------------ + Bra + a* + \D + Ket + End +------------------------------------------------------------------ + +/0*\d/BZ +------------------------------------------------------------------ + Bra + 0* + \d + Ket + End +------------------------------------------------------------------ + +/0*\D/BZ +------------------------------------------------------------------ + Bra + 0*+ + \D + Ket + End +------------------------------------------------------------------ + +/a*\s/BZ +------------------------------------------------------------------ + Bra + a*+ + \s + Ket + End +------------------------------------------------------------------ + +/a*\S/BZ +------------------------------------------------------------------ + Bra + a* + \S + Ket + End +------------------------------------------------------------------ + +/ *\s/BZ +------------------------------------------------------------------ + Bra + * + \s + Ket + End +------------------------------------------------------------------ + +/ *\S/BZ +------------------------------------------------------------------ + Bra + *+ + \S + Ket + End +------------------------------------------------------------------ + +/a*\w/BZ +------------------------------------------------------------------ + Bra + a* + \w + Ket + End +------------------------------------------------------------------ + +/a*\W/BZ +------------------------------------------------------------------ + Bra + a*+ + \W + Ket + End +------------------------------------------------------------------ + +/=*\w/BZ +------------------------------------------------------------------ + Bra + =*+ + \w + Ket + End +------------------------------------------------------------------ + +/=*\W/BZ +------------------------------------------------------------------ + Bra + =* + \W + Ket + End +------------------------------------------------------------------ + +/\d*a/BZ +------------------------------------------------------------------ + Bra + \d*+ + a + Ket + End +------------------------------------------------------------------ + +/\d*2/BZ +------------------------------------------------------------------ + Bra + \d* + 2 + Ket + End +------------------------------------------------------------------ + +/\d*\d/BZ +------------------------------------------------------------------ + Bra + \d* + \d + Ket + End +------------------------------------------------------------------ + +/\d*\D/BZ +------------------------------------------------------------------ + Bra + \d*+ + \D + Ket + End +------------------------------------------------------------------ + +/\d*\s/BZ +------------------------------------------------------------------ + Bra + \d*+ + \s + Ket + End +------------------------------------------------------------------ + +/\d*\S/BZ +------------------------------------------------------------------ + Bra + \d* + \S + Ket + End +------------------------------------------------------------------ + +/\d*\w/BZ +------------------------------------------------------------------ + Bra + \d* + \w + Ket + End +------------------------------------------------------------------ + +/\d*\W/BZ +------------------------------------------------------------------ + Bra + \d*+ + \W + Ket + End +------------------------------------------------------------------ + +/\D*a/BZ +------------------------------------------------------------------ + Bra + \D* + a + Ket + End +------------------------------------------------------------------ + +/\D*2/BZ +------------------------------------------------------------------ + Bra + \D*+ + 2 + Ket + End +------------------------------------------------------------------ + +/\D*\d/BZ +------------------------------------------------------------------ + Bra + \D*+ + \d + Ket + End +------------------------------------------------------------------ + +/\D*\D/BZ +------------------------------------------------------------------ + Bra + \D* + \D + Ket + End +------------------------------------------------------------------ + +/\D*\s/BZ +------------------------------------------------------------------ + Bra + \D* + \s + Ket + End +------------------------------------------------------------------ + +/\D*\S/BZ +------------------------------------------------------------------ + Bra + \D* + \S + Ket + End +------------------------------------------------------------------ + +/\D*\w/BZ +------------------------------------------------------------------ + Bra + \D* + \w + Ket + End +------------------------------------------------------------------ + +/\D*\W/BZ +------------------------------------------------------------------ + Bra + \D* + \W + Ket + End +------------------------------------------------------------------ + +/\s*a/BZ +------------------------------------------------------------------ + Bra + \s*+ + a + Ket + End +------------------------------------------------------------------ + +/\s*2/BZ +------------------------------------------------------------------ + Bra + \s*+ + 2 + Ket + End +------------------------------------------------------------------ + +/\s*\d/BZ +------------------------------------------------------------------ + Bra + \s*+ + \d + Ket + End +------------------------------------------------------------------ + +/\s*\D/BZ +------------------------------------------------------------------ + Bra + \s* + \D + Ket + End +------------------------------------------------------------------ + +/\s*\s/BZ +------------------------------------------------------------------ + Bra + \s* + \s + Ket + End +------------------------------------------------------------------ + +/\s*\S/BZ +------------------------------------------------------------------ + Bra + \s*+ + \S + Ket + End +------------------------------------------------------------------ + +/\s*\w/BZ +------------------------------------------------------------------ + Bra + \s*+ + \w + Ket + End +------------------------------------------------------------------ + +/\s*\W/BZ +------------------------------------------------------------------ + Bra + \s* + \W + Ket + End +------------------------------------------------------------------ + +/\S*a/BZ +------------------------------------------------------------------ + Bra + \S* + a + Ket + End +------------------------------------------------------------------ + +/\S*2/BZ +------------------------------------------------------------------ + Bra + \S* + 2 + Ket + End +------------------------------------------------------------------ + +/\S*\d/BZ +------------------------------------------------------------------ + Bra + \S* + \d + Ket + End +------------------------------------------------------------------ + +/\S*\D/BZ +------------------------------------------------------------------ + Bra + \S* + \D + Ket + End +------------------------------------------------------------------ + +/\S*\s/BZ +------------------------------------------------------------------ + Bra + \S*+ + \s + Ket + End +------------------------------------------------------------------ + +/\S*\S/BZ +------------------------------------------------------------------ + Bra + \S* + \S + Ket + End +------------------------------------------------------------------ + +/\S*\w/BZ +------------------------------------------------------------------ + Bra + \S* + \w + Ket + End +------------------------------------------------------------------ + +/\S*\W/BZ +------------------------------------------------------------------ + Bra + \S* + \W + Ket + End +------------------------------------------------------------------ + +/\w*a/BZ +------------------------------------------------------------------ + Bra + \w* + a + Ket + End +------------------------------------------------------------------ + +/\w*2/BZ +------------------------------------------------------------------ + Bra + \w* + 2 + Ket + End +------------------------------------------------------------------ + +/\w*\d/BZ +------------------------------------------------------------------ + Bra + \w* + \d + Ket + End +------------------------------------------------------------------ + +/\w*\D/BZ +------------------------------------------------------------------ + Bra + \w* + \D + Ket + End +------------------------------------------------------------------ + +/\w*\s/BZ +------------------------------------------------------------------ + Bra + \w*+ + \s + Ket + End +------------------------------------------------------------------ + +/\w*\S/BZ +------------------------------------------------------------------ + Bra + \w* + \S + Ket + End +------------------------------------------------------------------ + +/\w*\w/BZ +------------------------------------------------------------------ + Bra + \w* + \w + Ket + End +------------------------------------------------------------------ + +/\w*\W/BZ +------------------------------------------------------------------ + Bra + \w*+ + \W + Ket + End +------------------------------------------------------------------ + +/\W*a/BZ +------------------------------------------------------------------ + Bra + \W*+ + a + Ket + End +------------------------------------------------------------------ + +/\W*2/BZ +------------------------------------------------------------------ + Bra + \W*+ + 2 + Ket + End +------------------------------------------------------------------ + +/\W*\d/BZ +------------------------------------------------------------------ + Bra + \W*+ + \d + Ket + End +------------------------------------------------------------------ + +/\W*\D/BZ +------------------------------------------------------------------ + Bra + \W* + \D + Ket + End +------------------------------------------------------------------ + +/\W*\s/BZ +------------------------------------------------------------------ + Bra + \W* + \s + Ket + End +------------------------------------------------------------------ + +/\W*\S/BZ +------------------------------------------------------------------ + Bra + \W* + \S + Ket + End +------------------------------------------------------------------ + +/\W*\w/BZ +------------------------------------------------------------------ + Bra + \W*+ + \w + Ket + End +------------------------------------------------------------------ + +/\W*\W/BZ +------------------------------------------------------------------ + Bra + \W* + \W + Ket + End +------------------------------------------------------------------ + +/[^a]+a/BZ +------------------------------------------------------------------ + Bra + [^a]++ + a + Ket + End +------------------------------------------------------------------ + +/[^a]+a/BZi +------------------------------------------------------------------ + Bra + [^A]++ + NC a + Ket + End +------------------------------------------------------------------ + +/[^a]+A/BZi +------------------------------------------------------------------ + Bra + [^A]++ + NC A + Ket + End +------------------------------------------------------------------ + +/[^a]+b/BZ +------------------------------------------------------------------ + Bra + [^a]+ + b + Ket + End +------------------------------------------------------------------ + +/[^a]+\d/BZ +------------------------------------------------------------------ + Bra + [^a]+ + \d + Ket + End +------------------------------------------------------------------ + +/a*[^a]/BZ +------------------------------------------------------------------ + Bra + a* + [^a] + Ket + End +------------------------------------------------------------------ + +/(?Px)(?Py)/I +Capturing subpattern count = 2 +Named capturing subpatterns: + abc 1 + xyz 2 +No options +First char = 'x' +Need char = 'y' + xy\Cabc\Cxyz + 0: xy + 1: x + 2: y + C x (1) abc + C y (1) xyz + +/(?x)(?'xyz'y)/I +Capturing subpattern count = 2 +Named capturing subpatterns: + abc 1 + xyz 2 +No options +First char = 'x' +Need char = 'y' + xy\Cabc\Cxyz + 0: xy + 1: x + 2: y + C x (1) abc + C y (1) xyz + +/(?x)(?'xyz>y)/I +Failed: syntax error in subpattern name (missing terminator) at offset 15 + +/(?P'abc'x)(?Py)/I +Failed: unrecognized character after (?P at offset 3 + +/^(?:(?(ZZ)a|b)(?X))+/ + bXaX + 0: bXaX + 1: X + bXbX + 0: bX + 1: X + ** Failers +No match + aXaX +No match + aXbX +No match + +/^(?P>abc)(?xxx)/ +Failed: reference to non-existent subpattern at offset 8 + +/^(?P>abc)(?x|y)/ + xx + 0: xx + 1: x + xy + 0: xy + 1: y + yy + 0: yy + 1: y + yx + 0: yx + 1: x + +/^(?P>abc)(?Px|y)/ + xx + 0: xx + 1: x + xy + 0: xy + 1: y + yy + 0: yy + 1: y + yx + 0: yx + 1: x + +/^((?(abc)a|b)(?x|y))+/ + bxay + 0: bxay + 1: ay + 2: y + bxby + 0: bx + 1: bx + 2: x + ** Failers +No match + axby +No match + +/^(((?P=abc)|X)(?x|y))+/ + XxXxxx + 0: XxXxxx + 1: xx + 2: x + 3: x + XxXyyx + 0: XxXyyx + 1: yx + 2: y + 3: x + XxXyxx + 0: XxXy + 1: Xy + 2: X + 3: y + ** Failers +No match + x +No match + +/^(?1)(abc)/ + abcabc + 0: abcabc + 1: abc + +/^(?:(?:\1|X)(a|b))+/ + Xaaa + 0: Xaaa + 1: a + Xaba + 0: Xa + 1: a + +/^[\E\Qa\E-\Qz\E]+/BZ +------------------------------------------------------------------ + Bra + ^ + [a-z]+ + Ket + End +------------------------------------------------------------------ + +/^[a\Q]bc\E]/BZ +------------------------------------------------------------------ + Bra + ^ + [\]a-c] + Ket + End +------------------------------------------------------------------ + +/^[a-\Q\E]/BZ +------------------------------------------------------------------ + Bra + ^ + [\-a] + Ket + End +------------------------------------------------------------------ + +/^(?P>abc)[()](?)/BZ +------------------------------------------------------------------ + Bra + ^ + Once + Recurse + Ket + [()] + CBra 1 + Ket + Ket + End +------------------------------------------------------------------ + +/^((?(abc)y)[()](?Px))+/BZ +------------------------------------------------------------------ + Bra + ^ + CBra 1 + Cond + 2 Cond ref + y + Ket + [()] + CBra 2 + x + Ket + KetRmax + Ket + End +------------------------------------------------------------------ + (xy)x + 0: (xy)x + 1: y)x + 2: x + +/^(?P>abc)\Q()\E(?)/BZ +------------------------------------------------------------------ + Bra + ^ + Once + Recurse + Ket + () + CBra 1 + Ket + Ket + End +------------------------------------------------------------------ + +/^(?P>abc)[a\Q(]\E(](?)/BZ +------------------------------------------------------------------ + Bra + ^ + Once + Recurse + Ket + [(\]a] + CBra 1 + Ket + Ket + End +------------------------------------------------------------------ + +/^(?P>abc) # this is (a comment) + (?)/BZx +------------------------------------------------------------------ + Bra + ^ + Once + Recurse + Ket + CBra 1 + Ket + Ket + End +------------------------------------------------------------------ + +/^\W*(?:(?(?.)\W*(?&one)\W*\k|)|(?(?.)\W*(?&three)\W*\k'four'|\W*.\W*))\W*$/Ii +Capturing subpattern count = 4 +Max back reference = 4 +Named capturing subpatterns: + four 4 + one 1 + three 3 + two 2 +Partial matching not supported +Options: anchored caseless +No first char +No need char + 1221 + 0: 1221 + 1: 1221 + 2: 1 + Satan, oscillate my metallic sonatas! + 0: Satan, oscillate my metallic sonatas! + 1: + 2: + 3: Satan, oscillate my metallic sonatas + 4: S + A man, a plan, a canal: Panama! + 0: A man, a plan, a canal: Panama! + 1: + 2: + 3: A man, a plan, a canal: Panama + 4: A + Able was I ere I saw Elba. + 0: Able was I ere I saw Elba. + 1: + 2: + 3: Able was I ere I saw Elba + 4: A + *** Failers +No match + The quick brown fox +No match + +/(?=(\w+))\1:/I +Capturing subpattern count = 1 +Max back reference = 1 +Partial matching not supported +No options +No first char +Need char = ':' + abcd: + 0: abcd: + 1: abcd + +/(?=(?'abc'\w+))\k:/I +Capturing subpattern count = 1 +Max back reference = 1 +Named capturing subpatterns: + abc 1 +Partial matching not supported +No options +No first char +Need char = ':' + abcd: + 0: abcd: + 1: abcd + +/(?'abc'\w+):\k{2}/ + a:aaxyz + 0: a:aa + 1: a + ab:ababxyz + 0: ab:abab + 1: ab + ** Failers +No match + a:axyz +No match + ab:abxyz +No match + +/(?'abc'a|b)(?d|e)\k{2}/J + adaa + 0: adaa + 1: a + 2: d + ** Failers +No match + addd +No match + adbb +No match + +/(?'abc'a|b)(?d|e)(?&abc){2}/J + bdaa + 0: bdaa + 1: b + 2: d + bdab + 0: bdab + 1: b + 2: d + ** Failers +No match + bddd +No match + +/^(?a)? (?()b|c) (?('ab')d|e)/x + abd + 0: abd + 1: a + ce + 0: ce + +/(?( (?'B' abc (?(R) (?(R&A)1) (?(R&B)2) X | (?1) (?2) (?R) ))) /x + abcabc1Xabc2XabcXabcabc + 0: abcabc1Xabc2XabcX + 1: abcabc1Xabc2XabcX + 2: abcabc1Xabc2XabcX + +/(? (?'B' abc (?(R) (?(R&1)1) (?(R&B)2) X | (?1) (?2) (?R) ))) /x +Failed: reference to non-existent subpattern at offset 29 + +/(?<1> (?'B' abc (?(R) (?(R&1)1) (?(R&B)2) X | (?1) (?2) (?R) ))) /x + abcabc1Xabc2XabcXabcabc + 0: abcabc1Xabc2XabcX + 1: abcabc1Xabc2XabcX + 2: abcabc1Xabc2XabcX + +/^(?(DEFINE) (? a) (? b) ) (?&A) (?&B) /x + abcd + 0: ab + 1: + 2: + +/(?(?&NAME_PAT))\s+(?(?&ADDRESS_PAT)) + (?(DEFINE) + (?[a-z]+) + (?\d+) + )/x + metcalfe 33 + 0: metcalfe 33 + 1: metcalfe + 2: 33 + 3: + 4: + +/^(?(DEFINE) abc | xyz ) /x +Failed: DEFINE group contains more than one branch at offset 22 + +/(?(DEFINE) abc) xyz/xI +Capturing subpattern count = 0 +Options: extended +First char = 'x' +Need char = 'z' + +/(?(DEFINE) abc){3} xyz/x +Failed: repeating a DEFINE group is not allowed at offset 17 + +/(a|)*\d/ + \O0aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa +No match + \O0aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa4 +Matched, but too many substrings + +/^a.b/ + a\rb + 0: a\x0db + a\nb\ + 0: a\x0ab + a\x85b\ + 0: a\x85b + ** Failers +No match + a\nb +No match + a\nb\ +No match + a\rb\ +No match + a\rb\ +No match + a\x85b\ +No match + a\rb\ +No match + +/^abc./mgx + abc1 \x0aabc2 \x0babc3xx \x0cabc4 \x0dabc5xx \x0d\x0aabc6 \x85abc7 \x{2028}abc8 \x{2029}abc9 JUNK + 0: abc1 + 0: abc2 + 0: abc3 + 0: abc4 + 0: abc5 + 0: abc6 + 0: abc7 + +/abc.$/mgx + abc1\x0a abc2\x0b abc3\x0c abc4\x0d abc5\x0d\x0a abc6\x85 abc7\x{2028} abc8\x{2029} abc9 + 0: abc1 + 0: abc2 + 0: abc3 + 0: abc4 + 0: abc5 + 0: abc6 + 0: abc9 + +/a/ + +/a/ +Failed: inconsistent NEWLINE options at offset 0 + +/^a\Rb/ + a\nb + 0: a\x0ab + a\rb + 0: a\x0db + a\r\nb + 0: a\x0d\x0ab + a\x0bb + 0: a\x0bb + a\x0cb + 0: a\x0cb + a\x85b + 0: a\x85b + ** Failers +No match + a\n\rb +No match + +/^a\R*b/ + ab + 0: ab + a\nb + 0: a\x0ab + a\rb + 0: a\x0db + a\r\nb + 0: a\x0d\x0ab + a\x0bb + 0: a\x0bb + a\x0cb + 0: a\x0cb + a\x85b + 0: a\x85b + a\n\rb + 0: a\x0a\x0db + a\n\r\x85\x0cb + 0: a\x0a\x0d\x85\x0cb + +/^a\R+b/ + a\nb + 0: a\x0ab + a\rb + 0: a\x0db + a\r\nb + 0: a\x0d\x0ab + a\x0bb + 0: a\x0bb + a\x0cb + 0: a\x0cb + a\x85b + 0: a\x85b + a\n\rb + 0: a\x0a\x0db + a\n\r\x85\x0cb + 0: a\x0a\x0d\x85\x0cb + ** Failers +No match + ab +No match + +/^a\R{1,3}b/ + a\nb + 0: a\x0ab + a\n\rb + 0: a\x0a\x0db + a\n\r\x85b + 0: a\x0a\x0d\x85b + a\r\n\r\nb + 0: a\x0d\x0a\x0d\x0ab + a\r\n\r\n\r\nb + 0: a\x0d\x0a\x0d\x0a\x0d\x0ab + a\n\r\n\rb + 0: a\x0a\x0d\x0a\x0db + a\n\n\r\nb + 0: a\x0a\x0a\x0d\x0ab + ** Failers +No match + a\n\n\n\rb +No match + a\r +No match + +/^a[\R]b/ + aRb + 0: aRb + ** Failers +No match + a\nb +No match + +/(?&abc)X(?P)/I +Capturing subpattern count = 1 +Named capturing subpatterns: + abc 1 +No options +No first char +Need char = 'P' + abcPXP123 + 0: PXP + 1: P + +/(?1)X(?P)/I +Capturing subpattern count = 1 +Named capturing subpatterns: + abc 1 +No options +No first char +Need char = 'P' + abcPXP123 + 0: PXP + 1: P + +/(?(DEFINE)(?2[0-4]\d|25[0-5]|1\d\d|[1-9]?\d))\b(?&byte)(\.(?&byte)){3}/ + 1.2.3.4 + 0: 1.2.3.4 + 1: + 2: .4 + 131.111.10.206 + 0: 131.111.10.206 + 1: + 2: .206 + 10.0.0.0 + 0: 10.0.0.0 + 1: + 2: .0 + ** Failers +No match + 10.6 +No match + 455.3.4.5 +No match + +/\b(?&byte)(\.(?&byte)){3}(?(DEFINE)(?2[0-4]\d|25[0-5]|1\d\d|[1-9]?\d))/ + 1.2.3.4 + 0: 1.2.3.4 + 1: .4 + 2: + 131.111.10.206 + 0: 131.111.10.206 + 1: .206 + 2: + 10.0.0.0 + 0: 10.0.0.0 + 1: .0 + 2: + ** Failers +No match + 10.6 +No match + 455.3.4.5 +No match + +/(?:a(?&abc)b)*(?x)/ + 123axbaxbaxbx456 + 0: axbaxbaxbx + 1: x + 123axbaxbaxb456 + 0: x + 1: x + +/(?:a(?&abc)b){1,5}(?x)/ + 123axbaxbaxbx456 + 0: axbaxbaxbx + 1: x + +/(?:a(?&abc)b){2,5}(?x)/ + 123axbaxbaxbx456 + 0: axbaxbaxbx + 1: x + +/(?:a(?&abc)b){2,}(?x)/ + 123axbaxbaxbx456 + 0: axbaxbaxbx + 1: x + +/(abc)(?i:(?1))/ + defabcabcxyz + 0: abcabc + 1: abc + DEFabcABCXYZ +No match + +/(abc)(?:(?i)(?1))/ + defabcabcxyz + 0: abcabc + 1: abc + DEFabcABCXYZ +No match + +/^(a(b))\1\g1\g{1}\g-1\g{-1}\g{-02}Z/ + ababababbbabZXXXX + 0: ababababbbabZ + 1: ab + 2: b + +/^(a)\g-2/ +Failed: reference to non-existent subpattern at offset 7 + +/^(a)\g/ +Failed: \g is not followed by a braced name or an optionally braced non-zero number at offset 5 + +/^(a)\g{0}/ +Failed: \g is not followed by a braced name or an optionally braced non-zero number at offset 7 + +/^(a)\g{3/ +Failed: \g is not followed by a braced name or an optionally braced non-zero number at offset 8 + +/^(a)\g{4a}/ +Failed: reference to non-existent subpattern at offset 9 + +/^a.b/ + a\rb + 0: a\x0db + *** Failers +No match + a\nb +No match + +/.+foo/ + afoo + 0: afoo + ** Failers +No match + \r\nfoo +No match + \nfoo +No match + +/.+foo/ + afoo + 0: afoo + \nfoo + 0: \x0afoo + ** Failers +No match + \r\nfoo +No match + +/.+foo/ + afoo + 0: afoo + ** Failers +No match + \nfoo +No match + \r\nfoo +No match + +/.+foo/s + afoo + 0: afoo + \r\nfoo + 0: \x0d\x0afoo + \nfoo + 0: \x0afoo + +/^$/mg + abc\r\rxyz + 0: + abc\n\rxyz + 0: + ** Failers +No match + abc\r\nxyz +No match + +/(?m)^$/g+ + abc\r\n\r\n + 0: + 0+ \x0d\x0a + +/(?m)^$|^\r\n/g+ + abc\r\n\r\n + 0: + 0+ \x0d\x0a + 0: \x0d\x0a + 0+ + +/(?m)$/g+ + abc\r\n\r\n + 0: + 0+ \x0d\x0a\x0d\x0a + 0: + 0+ \x0d\x0a + 0: + 0+ + +/abc.$/mgx + abc1\x0a abc2\x0b abc3\x0c abc4\x0d abc5\x0d\x0a abc6\x85 abc7\x{2028} abc8\x{2029} abc9 + 0: abc1 + 0: abc4 + 0: abc5 + 0: abc9 + +/^X/m + XABC + 0: X + ** Failers +No match + XABC\B +No match + +/(ab|c)(?-1)/BZ +------------------------------------------------------------------ + Bra + CBra 1 + ab + Alt + c + Ket + Once + Recurse + Ket + Ket + End +------------------------------------------------------------------ + abc + 0: abc + 1: ab + +/xy(?+1)(abc)/BZ +------------------------------------------------------------------ + Bra + xy + Once + Recurse + Ket + CBra 1 + abc + Ket + Ket + End +------------------------------------------------------------------ + xyabcabc + 0: xyabcabc + 1: abc + ** Failers +No match + xyabc +No match + +/x(?-0)y/ +Failed: (?+ or (?- or (?(+ or (?(- must be followed by a non-zero number at offset 5 + +/x(?-1)y/ +Failed: reference to non-existent subpattern at offset 5 + +/x(?+0)y/ +Failed: (?+ or (?- or (?(+ or (?(- must be followed by a non-zero number at offset 5 + +/x(?+1)y/ +Failed: reference to non-existent subpattern at offset 5 + +/^(abc)?(?(-1)X|Y)/BZ +------------------------------------------------------------------ + Bra + ^ + Brazero + CBra 1 + abc + Ket + Cond + 1 Cond ref + X + Alt + Y + Ket + Ket + End +------------------------------------------------------------------ + abcX + 0: abcX + 1: abc + Y + 0: Y + ** Failers +No match + abcY +No match + +/^((?(+1)X|Y)(abc))+/BZ +------------------------------------------------------------------ + Bra + ^ + CBra 1 + Cond + 2 Cond ref + X + Alt + Y + Ket + CBra 2 + abc + Ket + KetRmax + Ket + End +------------------------------------------------------------------ + YabcXabc + 0: YabcXabc + 1: Xabc + 2: abc + YabcXabcXabc + 0: YabcXabcXabc + 1: Xabc + 2: abc + ** Failers +No match + XabcXabc +No match + +/(?(-1)a)/BZ +Failed: reference to non-existent subpattern at offset 6 + +/((?(-1)a))/BZ +------------------------------------------------------------------ + Bra + CBra 1 + Cond + 1 Cond ref + a + Ket + Ket + Ket + End +------------------------------------------------------------------ + +/((?(-2)a))/BZ +Failed: reference to non-existent subpattern at offset 7 + +/^(?(+1)X|Y)(.)/BZ +------------------------------------------------------------------ + Bra + ^ + Cond + 1 Cond ref + X + Alt + Y + Ket + CBra 1 + Any + Ket + Ket + End +------------------------------------------------------------------ + Y! + 0: Y! + 1: ! + +/(foo)\Kbar/ + foobar + 0: bar + 1: foo + +/(foo)(\Kbar|baz)/ + foobar + 0: bar + 1: foo + 2: bar + foobaz + 0: foobaz + 1: foo + 2: baz + +/(foo\Kbar)baz/ + foobarbaz + 0: barbaz + 1: foobar + +/(?tom|bon)-\k{A}/ + tom-tom + 0: tom-tom + 1: tom + bon-bon + 0: bon-bon + 1: bon + ** Failers +No match + tom-bon +No match + +/(?tom|bon)-\g{A}/ + tom-tom + 0: tom-tom + 1: tom + bon-bon + 0: bon-bon + 1: bon + +/\g{A/ +Failed: syntax error in subpattern name (missing terminator) at offset 4 + +/(?|(abc)|(xyz))/BZ +------------------------------------------------------------------ + Bra + Bra + CBra 1 + abc + Ket + Alt + CBra 1 + xyz + Ket + Ket + Ket + End +------------------------------------------------------------------ + >abc< + 0: abc + 1: abc + >xyz< + 0: xyz + 1: xyz + +/(x)(?|(abc)|(xyz))(x)/BZ +------------------------------------------------------------------ + Bra + CBra 1 + x + Ket + Bra + CBra 2 + abc + Ket + Alt + CBra 2 + xyz + Ket + Ket + CBra 3 + x + Ket + Ket + End +------------------------------------------------------------------ + xabcx + 0: xabcx + 1: x + 2: abc + 3: x + xxyzx + 0: xxyzx + 1: x + 2: xyz + 3: x + +/(x)(?|(abc)(pqr)|(xyz))(x)/BZ +------------------------------------------------------------------ + Bra + CBra 1 + x + Ket + Bra + CBra 2 + abc + Ket + CBra 3 + pqr + Ket + Alt + CBra 2 + xyz + Ket + Ket + CBra 4 + x + Ket + Ket + End +------------------------------------------------------------------ + xabcpqrx + 0: xabcpqrx + 1: x + 2: abc + 3: pqr + 4: x + xxyzx + 0: xxyzx + 1: x + 2: xyz + 3: + 4: x + +/(?|(abc)|(xyz))\1/ + abcabc + 0: abcabc + 1: abc + xyzxyz + 0: xyzxyz + 1: xyz + ** Failers +No match + abcxyz +No match + xyzabc +No match + +/(?|(abc)|(xyz))(?1)/ + abcabc + 0: abcabc + 1: abc + xyzabc + 0: xyzabc + 1: xyz + ** Failers +No match + xyzxyz +No match + +/\H\h\V\v/ + X X\x0a + 0: X X\x0a + X\x09X\x0b + 0: X\x09X\x0b + ** Failers +No match + \xa0 X\x0a +No match + +/\H*\h+\V?\v{3,4}/ + \x09\x20\xa0X\x0a\x0b\x0c\x0d\x0a + 0: \x09 \xa0X\x0a\x0b\x0c\x0d + \x09\x20\xa0\x0a\x0b\x0c\x0d\x0a + 0: \x09 \xa0\x0a\x0b\x0c\x0d + \x09\x20\xa0\x0a\x0b\x0c + 0: \x09 \xa0\x0a\x0b\x0c + ** Failers +No match + \x09\x20\xa0\x0a\x0b +No match + +/\H{3,4}/ + XY ABCDE + 0: ABCD + XY PQR ST + 0: PQR + +/.\h{3,4}./ + XY AB PQRS + 0: B P + +/\h*X\h?\H+Y\H?Z/ + >XNNNYZ + 0: XNNNYZ + > X NYQZ + 0: X NYQZ + ** Failers +No match + >XYZ +No match + > X NY Z +No match + +/\v*X\v?Y\v+Z\V*\x0a\V+\x0b\V{2,3}\x0c/ + >XY\x0aZ\x0aA\x0bNN\x0c + 0: XY\x0aZ\x0aA\x0bNN\x0c + >\x0a\x0dX\x0aY\x0a\x0bZZZ\x0aAAA\x0bNNN\x0c + 0: \x0a\x0dX\x0aY\x0a\x0bZZZ\x0aAAA\x0bNNN\x0c + +/[\h]/BZ +------------------------------------------------------------------ + Bra + [\x09 \xa0] + Ket + End +------------------------------------------------------------------ + >\x09< + 0: \x09 + +/[\h]+/BZ +------------------------------------------------------------------ + Bra + [\x09 \xa0]+ + Ket + End +------------------------------------------------------------------ + >\x09\x20\xa0< + 0: \x09 \xa0 + +/[\v]/BZ +------------------------------------------------------------------ + Bra + [\x0a-\x0d\x85] + Ket + End +------------------------------------------------------------------ + +/[\H]/BZ +------------------------------------------------------------------ + Bra + [\x00-\x08\x0a-\x1f!-\x9f\xa1-\xff] + Ket + End +------------------------------------------------------------------ + +/[^\h]/BZ +------------------------------------------------------------------ + Bra + [\x00-\x08\x0a-\x1f!-\x9f\xa1-\xff] (neg) + Ket + End +------------------------------------------------------------------ + +/[\V]/BZ +------------------------------------------------------------------ + Bra + [\x00-\x09\x0e-\x84\x86-\xff] + Ket + End +------------------------------------------------------------------ + +/[\x0a\V]/BZ +------------------------------------------------------------------ + Bra + [\x00-\x0a\x0e-\x84\x86-\xff] + Ket + End +------------------------------------------------------------------ + +/\H++X/BZ +------------------------------------------------------------------ + Bra + \H++ + X + Ket + End +------------------------------------------------------------------ + ** Failers +No match + XXXX +No match + +/\H+\hY/BZ +------------------------------------------------------------------ + Bra + \H++ + \h + Y + Ket + End +------------------------------------------------------------------ + XXXX Y + 0: XXXX Y + +/\H+ Y/BZ +------------------------------------------------------------------ + Bra + \H++ + Y + Ket + End +------------------------------------------------------------------ + +/\h+A/BZ +------------------------------------------------------------------ + Bra + \h++ + A + Ket + End +------------------------------------------------------------------ + +/\v*B/BZ +------------------------------------------------------------------ + Bra + \v*+ + B + Ket + End +------------------------------------------------------------------ + +/\V+\x0a/BZ +------------------------------------------------------------------ + Bra + \V++ + \x0a + Ket + End +------------------------------------------------------------------ + +/A+\h/BZ +------------------------------------------------------------------ + Bra + A++ + \h + Ket + End +------------------------------------------------------------------ + +/ *\H/BZ +------------------------------------------------------------------ + Bra + *+ + \H + Ket + End +------------------------------------------------------------------ + +/A*\v/BZ +------------------------------------------------------------------ + Bra + A*+ + \v + Ket + End +------------------------------------------------------------------ + +/\x0b*\V/BZ +------------------------------------------------------------------ + Bra + \x0b*+ + \V + Ket + End +------------------------------------------------------------------ + +/\d+\h/BZ +------------------------------------------------------------------ + Bra + \d++ + \h + Ket + End +------------------------------------------------------------------ + +/\d*\v/BZ +------------------------------------------------------------------ + Bra + \d*+ + \v + Ket + End +------------------------------------------------------------------ + +/S+\h\S+\v/BZ +------------------------------------------------------------------ + Bra + S++ + \h + \S++ + \v + Ket + End +------------------------------------------------------------------ + +/\w{3,}\h\w+\v/BZ +------------------------------------------------------------------ + Bra + \w{3} + \w*+ + \h + \w++ + \v + Ket + End +------------------------------------------------------------------ + +/\h+\d\h+\w\h+\S\h+\H/BZ +------------------------------------------------------------------ + Bra + \h++ + \d + \h++ + \w + \h++ + \S + \h++ + \H + Ket + End +------------------------------------------------------------------ + +/\v+\d\v+\w\v+\S\v+\V/BZ +------------------------------------------------------------------ + Bra + \v++ + \d + \v++ + \w + \v+ + \S + \v++ + \V + Ket + End +------------------------------------------------------------------ + +/\H+\h\H+\d/BZ +------------------------------------------------------------------ + Bra + \H++ + \h + \H+ + \d + Ket + End +------------------------------------------------------------------ + +/\V+\v\V+\w/BZ +------------------------------------------------------------------ + Bra + \V++ + \v + \V+ + \w + Ket + End +------------------------------------------------------------------ + +/\( (?: [^()]* | (?R) )* \)/x +(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0( 0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(00)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0) + 0: (0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0( 0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(00)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0) + +/[\E]AAA/ +Failed: missing terminating ] for character class at offset 7 + +/[\Q\E]AAA/ +Failed: missing terminating ] for character class at offset 9 + +/[^\E]AAA/ +Failed: missing terminating ] for character class at offset 8 + +/[^\Q\E]AAA/ +Failed: missing terminating ] for character class at offset 10 + +/[\E^]AAA/ +Failed: missing terminating ] for character class at offset 8 + +/[\Q\E^]AAA/ +Failed: missing terminating ] for character class at offset 10 + +/A(*PRUNE)B(*SKIP)C(*THEN)D(*COMMIT)E(*F)F(*FAIL)G(?!)H(*ACCEPT)I/BZ +------------------------------------------------------------------ + Bra + A + *PRUNE + B + *SKIP + C + *THEN + D + *COMMIT + E + *FAIL + F + *FAIL + G + *FAIL + H + *ACCEPT + I + Ket + End +------------------------------------------------------------------ + +/^a+(*FAIL)/ + aaaaaa +No match + +/a+b?c+(*FAIL)/ + aaabccc +No match + +/a+b?(*PRUNE)c+(*FAIL)/ + aaabccc +No match + +/a+b?(*COMMIT)c+(*FAIL)/ + aaabccc +No match + +/a+b?(*SKIP)c+(*FAIL)/ + aaabcccaaabccc +No match + +/^(?:aaa(*THEN)\w{6}|bbb(*THEN)\w{5}|ccc(*THEN)\w{4}|\w{3})/ + aaaxxxxxx + 0: aaaxxxxxx + aaa++++++ + 0: aaa + bbbxxxxx + 0: bbbxxxxx + bbb+++++ + 0: bbb + cccxxxx + 0: cccxxxx + ccc++++ + 0: ccc + dddddddd + 0: ddd + +/^(aaa(*THEN)\w{6}|bbb(*THEN)\w{5}|ccc(*THEN)\w{4}|\w{3})/ + aaaxxxxxx + 0: aaaxxxxxx + 1: aaaxxxxxx + aaa++++++ + 0: aaa + 1: aaa + bbbxxxxx + 0: bbbxxxxx + 1: bbbxxxxx + bbb+++++ + 0: bbb + 1: bbb + cccxxxx + 0: cccxxxx + 1: cccxxxx + ccc++++ + 0: ccc + 1: ccc + dddddddd + 0: ddd + 1: ddd + +/a+b?(*THEN)c+(*FAIL)/ + aaabccc +No match + +/(A (A|B(*ACCEPT)|C) D)(E)/x + ABX + 0: AB + AADE + 0: AADE + 1: AAD + 2: A + 3: E + ACDE + 0: ACDE + 1: ACD + 2: C + 3: E + ** Failers +No match + AD +No match + +/^a+(*FAIL)/C + aaaaaa +--->aaaaaa + +0 ^ ^ + +1 ^ a+ + +3 ^ ^ (*FAIL) + +3 ^ ^ (*FAIL) + +3 ^ ^ (*FAIL) + +3 ^ ^ (*FAIL) + +3 ^ ^ (*FAIL) + +3 ^^ (*FAIL) +No match + +/a+b?c+(*FAIL)/C + aaabccc +--->aaabccc + +0 ^ a+ + +2 ^ ^ b? + +4 ^ ^ c+ + +6 ^ ^ (*FAIL) + +6 ^ ^ (*FAIL) + +6 ^ ^ (*FAIL) + +4 ^ ^ c+ + +2 ^ ^ b? + +4 ^ ^ c+ + +2 ^^ b? + +4 ^^ c+ + +0 ^ a+ + +2 ^ ^ b? + +4 ^ ^ c+ + +6 ^ ^ (*FAIL) + +6 ^ ^ (*FAIL) + +6 ^ ^ (*FAIL) + +4 ^ ^ c+ + +2 ^^ b? + +4 ^^ c+ + +0 ^ a+ + +2 ^^ b? + +4 ^ ^ c+ + +6 ^ ^ (*FAIL) + +6 ^ ^ (*FAIL) + +6 ^ ^ (*FAIL) + +4 ^^ c+ +No match + +/a+b?(*PRUNE)c+(*FAIL)/C + aaabccc +--->aaabccc + +0 ^ a+ + +2 ^ ^ b? + +4 ^ ^ (*PRUNE) ++12 ^ ^ c+ ++14 ^ ^ (*FAIL) ++14 ^ ^ (*FAIL) ++14 ^ ^ (*FAIL) + +0 ^ a+ + +2 ^ ^ b? + +4 ^ ^ (*PRUNE) ++12 ^ ^ c+ ++14 ^ ^ (*FAIL) ++14 ^ ^ (*FAIL) ++14 ^ ^ (*FAIL) + +0 ^ a+ + +2 ^^ b? + +4 ^ ^ (*PRUNE) ++12 ^ ^ c+ ++14 ^ ^ (*FAIL) ++14 ^ ^ (*FAIL) ++14 ^ ^ (*FAIL) +No match + +/a+b?(*COMMIT)c+(*FAIL)/C + aaabccc +--->aaabccc + +0 ^ a+ + +2 ^ ^ b? + +4 ^ ^ (*COMMIT) ++13 ^ ^ c+ ++15 ^ ^ (*FAIL) ++15 ^ ^ (*FAIL) ++15 ^ ^ (*FAIL) +No match + +/a+b?(*SKIP)c+(*FAIL)/C + aaabcccaaabccc +--->aaabcccaaabccc + +0 ^ a+ + +2 ^ ^ b? + +4 ^ ^ (*SKIP) ++11 ^ ^ c+ ++13 ^ ^ (*FAIL) ++13 ^ ^ (*FAIL) ++13 ^ ^ (*FAIL) + +0 ^ a+ + +2 ^ ^ b? + +4 ^ ^ (*SKIP) ++11 ^ ^ c+ ++13 ^ ^ (*FAIL) ++13 ^ ^ (*FAIL) ++13 ^ ^ (*FAIL) +No match + +/a+b?(*THEN)c+(*FAIL)/C + aaabccc +--->aaabccc + +0 ^ a+ + +2 ^ ^ b? + +4 ^ ^ (*THEN) ++11 ^ ^ c+ ++13 ^ ^ (*FAIL) ++13 ^ ^ (*FAIL) ++13 ^ ^ (*FAIL) + +0 ^ a+ + +2 ^ ^ b? + +4 ^ ^ (*THEN) ++11 ^ ^ c+ ++13 ^ ^ (*FAIL) ++13 ^ ^ (*FAIL) ++13 ^ ^ (*FAIL) + +0 ^ a+ + +2 ^^ b? + +4 ^ ^ (*THEN) ++11 ^ ^ c+ ++13 ^ ^ (*FAIL) ++13 ^ ^ (*FAIL) ++13 ^ ^ (*FAIL) +No match + +/a(*PRUNE:XXX)b/ +Failed: (*VERB) with an argument is not supported at offset 8 + +/a(*MARK)b/ +Failed: (*VERB) not recognized at offset 7 + +/(?i:A{1,}\6666666666)/ +Failed: number is too big at offset 19 + +/\g6666666666/ +Failed: number is too big at offset 11 + +/[\g6666666666]/ +Failed: number is too big at offset 12 + +/(?1)\c[/ +Failed: reference to non-existent subpattern at offset 3 + +/.+A/ + \r\nA +No match + +/\nA/ + \r\nA + 0: \x0aA + +/[\r\n]A/ + \r\nA + 0: \x0aA + +/(\r|\n)A/ + \r\nA + 0: \x0aA + 1: \x0a + +/a(*CR)b/ +Failed: (*VERB) not recognized at offset 5 + +/(*CR)a.b/ + a\nb + 0: a\x0ab + ** Failers +No match + a\rb +No match + +/(*CR)a.b/ + a\nb + 0: a\x0ab + ** Failers +No match + a\rb +No match + +/(*LF)a.b/ + a\rb + 0: a\x0db + ** Failers +No match + a\nb +No match + +/(*CRLF)a.b/ + a\rb + 0: a\x0db + a\nb + 0: a\x0ab + ** Failers +No match + a\r\nb +No match + +/(*ANYCRLF)a.b/ + ** Failers +No match + a\rb +No match + a\nb +No match + a\r\nb +No match + +/(*ANY)a.b/ + ** Failers +No match + a\rb +No match + a\nb +No match + a\r\nb +No match + a\x85b +No match + +/a\Rb/I +Capturing subpattern count = 0 +Options: bsr_anycrlf +First char = 'a' +Need char = 'b' + a\rb + 0: a\x0db + a\nb + 0: a\x0ab + a\r\nb + 0: a\x0d\x0ab + ** Failers +No match + a\x85b +No match + a\x0bb +No match + +/a\Rb/I +Capturing subpattern count = 0 +Options: bsr_unicode +First char = 'a' +Need char = 'b' + a\rb + 0: a\x0db + a\nb + 0: a\x0ab + a\r\nb + 0: a\x0d\x0ab + a\x85b + 0: a\x85b + a\x0bb + 0: a\x0bb + ** Failers +No match + a\x85b\ +No match + a\x0bb\ +No match + +/a\R?b/I +Capturing subpattern count = 0 +Options: bsr_anycrlf +First char = 'a' +Need char = 'b' + a\rb + 0: a\x0db + a\nb + 0: a\x0ab + a\r\nb + 0: a\x0d\x0ab + ** Failers +No match + a\x85b +No match + a\x0bb +No match + +/a\R?b/I +Capturing subpattern count = 0 +Options: bsr_unicode +First char = 'a' +Need char = 'b' + a\rb + 0: a\x0db + a\nb + 0: a\x0ab + a\r\nb + 0: a\x0d\x0ab + a\x85b + 0: a\x85b + a\x0bb + 0: a\x0bb + ** Failers +No match + a\x85b\ +No match + a\x0bb\ +No match + +/a\R{2,4}b/I +Capturing subpattern count = 0 +Partial matching not supported +Options: bsr_anycrlf +First char = 'a' +Need char = 'b' + a\r\n\nb + 0: a\x0d\x0a\x0ab + a\n\r\rb + 0: a\x0a\x0d\x0db + a\r\n\r\n\r\n\r\nb + 0: a\x0d\x0a\x0d\x0a\x0d\x0a\x0d\x0ab + ** Failers +No match + a\x85\85b +No match + a\x0b\0bb +No match + +/a\R{2,4}b/I +Capturing subpattern count = 0 +Partial matching not supported +Options: bsr_unicode +First char = 'a' +Need char = 'b' + a\r\rb + 0: a\x0d\x0db + a\n\n\nb + 0: a\x0a\x0a\x0ab + a\r\n\n\r\rb + 0: a\x0d\x0a\x0a\x0d\x0db + a\x85\85b +No match + a\x0b\0bb +No match + ** Failers +No match + a\r\r\r\r\rb +No match + a\x85\85b\ +No match + a\x0b\0bb\ +No match + +/(*BSR_ANYCRLF)a\Rb/I +Capturing subpattern count = 0 +Options: bsr_anycrlf +First char = 'a' +Need char = 'b' + a\nb + 0: a\x0ab + a\rb + 0: a\x0db + +/(*BSR_UNICODE)a\Rb/I +Capturing subpattern count = 0 +Options: bsr_unicode +First char = 'a' +Need char = 'b' + a\x85b + 0: a\x85b + +/(*BSR_ANYCRLF)(*CRLF)a\Rb/I +Capturing subpattern count = 0 +Options: bsr_anycrlf +Forced newline sequence: CRLF +First char = 'a' +Need char = 'b' + a\nb + 0: a\x0ab + a\rb + 0: a\x0db + +/(*CRLF)(*BSR_UNICODE)a\Rb/I +Capturing subpattern count = 0 +Options: bsr_unicode +Forced newline sequence: CRLF +First char = 'a' +Need char = 'b' + a\x85b + 0: a\x85b + +/(*CRLF)(*BSR_ANYCRLF)(*CR)ab/I +Capturing subpattern count = 0 +Options: bsr_anycrlf +Forced newline sequence: CR +First char = 'a' +Need char = 'b' + +/(?)(?&)/ +Failed: subpattern name expected at offset 9 + +/(?)(?&a)/ +Failed: reference to non-existent subpattern at offset 12 + +/(?)(?&aaaaaaaaaaaaaaaaaaaaaaa)/ +Failed: reference to non-existent subpattern at offset 32 + +/(?+-a)/ +Failed: digit expected after (?+ at offset 3 + +/(?-+a)/ +Failed: unrecognized character after (? or (?- at offset 3 + +/(?(-1))/ +Failed: reference to non-existent subpattern at offset 6 + +/(?(+10))/ +Failed: reference to non-existent subpattern at offset 7 + +/(?(10))/ +Failed: reference to non-existent subpattern at offset 6 + +/(?(+2))()()/ + +/(?(2))()()/ + +/\k''/ +Failed: subpattern name expected at offset 3 + +/\k<>/ +Failed: subpattern name expected at offset 3 + +/\k{}/ +Failed: subpattern name expected at offset 3 + +/(?P=)/ +Failed: subpattern name expected at offset 4 + +/(?P>)/ +Failed: subpattern name expected at offset 4 + +/(?!\w)(?R)/ +Failed: recursive call could loop indefinitely at offset 9 + +/(?=\w)(?R)/ +Failed: recursive call could loop indefinitely at offset 9 + +/(?>>\xaa<<< + 0: >>> + >>>\xba<<< + 0: >>> + +/[\W]+/Lfr_FR + >>>\xaa<<< + 0: >>> + >>>\xba<<< + 0: >>> + +/[^[:alpha:]]+/Lfr_FR + >>>\xaa<<< + 0: >>> + >>>\xba<<< + 0: >>> + +/\w+/Lfr_FR + >>>\xaa<<< + 0: ª + >>>\xba<<< + 0: º + +/[\w]+/Lfr_FR + >>>\xaa<<< + 0: ª + >>>\xba<<< + 0: º + +/[[:alpha:]]+/Lfr_FR + >>>\xaa<<< + 0: ª + >>>\xba<<< + 0: º + +/[[:alpha:]][[:lower:]][[:upper:]]/DZLfr_FR +------------------------------------------------------------------ + Bra + [A-Za-z\xaa\xb5\xba\xc0-\xd6\xd8-\xf6\xf8-\xff] + [a-z\xb5\xdf-\xf6\xf8-\xff] + [A-Z\xc0-\xd6\xd8-\xde] + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +No options +No first char +No need char + +/ End of testinput3 / ============================================================ --- pcre/testdata/testoutput4 c6e830eb2fa45f6cd1961fc88d4ca9a63cf6f1b9 +++ pcre/testdata/testoutput4 c6e830eb2fa45f6cd1961fc88d4ca9a63cf6f1b9 @@ -0,0 +1,1074 @@ +/-- Do not use the \x{} construct except with patterns that have the --/ +/-- /8 option set, because PCRE doesn't recognize them as UTF-8 unless --/ +No match +/-- that option is set. However, the latest Perls recognize them always. --/ +No match + +/a.b/8 + acb + 0: acb + a\x7fb + 0: a\x{7f}b + a\x{100}b + 0: a\x{100}b + *** Failers +No match + a\nb +No match + +/a(.{3})b/8 + a\x{4000}xyb + 0: a\x{4000}xyb + 1: \x{4000}xy + a\x{4000}\x7fyb + 0: a\x{4000}\x{7f}yb + 1: \x{4000}\x{7f}y + a\x{4000}\x{100}yb + 0: a\x{4000}\x{100}yb + 1: \x{4000}\x{100}y + *** Failers +No match + a\x{4000}b +No match + ac\ncb +No match + +/a(.*?)(.)/ + a\xc0\x88b + 0: a\xc0 + 1: + 2: \xc0 + +/a(.*?)(.)/8 + a\x{100}b + 0: a\x{100} + 1: + 2: \x{100} + +/a(.*)(.)/ + a\xc0\x88b + 0: a\xc0\x88b + 1: \xc0\x88 + 2: b + +/a(.*)(.)/8 + a\x{100}b + 0: a\x{100}b + 1: \x{100} + 2: b + +/a(.)(.)/ + a\xc0\x92bcd + 0: a\xc0\x92 + 1: \xc0 + 2: \x92 + +/a(.)(.)/8 + a\x{240}bcd + 0: a\x{240}b + 1: \x{240} + 2: b + +/a(.?)(.)/ + a\xc0\x92bcd + 0: a\xc0\x92 + 1: \xc0 + 2: \x92 + +/a(.?)(.)/8 + a\x{240}bcd + 0: a\x{240}b + 1: \x{240} + 2: b + +/a(.??)(.)/ + a\xc0\x92bcd + 0: a\xc0 + 1: + 2: \xc0 + +/a(.??)(.)/8 + a\x{240}bcd + 0: a\x{240} + 1: + 2: \x{240} + +/a(.{3})b/8 + a\x{1234}xyb + 0: a\x{1234}xyb + 1: \x{1234}xy + a\x{1234}\x{4321}yb + 0: a\x{1234}\x{4321}yb + 1: \x{1234}\x{4321}y + a\x{1234}\x{4321}\x{3412}b + 0: a\x{1234}\x{4321}\x{3412}b + 1: \x{1234}\x{4321}\x{3412} + *** Failers +No match + a\x{1234}b +No match + ac\ncb +No match + +/a(.{3,})b/8 + a\x{1234}xyb + 0: a\x{1234}xyb + 1: \x{1234}xy + a\x{1234}\x{4321}yb + 0: a\x{1234}\x{4321}yb + 1: \x{1234}\x{4321}y + a\x{1234}\x{4321}\x{3412}b + 0: a\x{1234}\x{4321}\x{3412}b + 1: \x{1234}\x{4321}\x{3412} + axxxxbcdefghijb + 0: axxxxbcdefghijb + 1: xxxxbcdefghij + a\x{1234}\x{4321}\x{3412}\x{3421}b + 0: a\x{1234}\x{4321}\x{3412}\x{3421}b + 1: \x{1234}\x{4321}\x{3412}\x{3421} + *** Failers +No match + a\x{1234}b +No match + +/a(.{3,}?)b/8 + a\x{1234}xyb + 0: a\x{1234}xyb + 1: \x{1234}xy + a\x{1234}\x{4321}yb + 0: a\x{1234}\x{4321}yb + 1: \x{1234}\x{4321}y + a\x{1234}\x{4321}\x{3412}b + 0: a\x{1234}\x{4321}\x{3412}b + 1: \x{1234}\x{4321}\x{3412} + axxxxbcdefghijb + 0: axxxxb + 1: xxxx + a\x{1234}\x{4321}\x{3412}\x{3421}b + 0: a\x{1234}\x{4321}\x{3412}\x{3421}b + 1: \x{1234}\x{4321}\x{3412}\x{3421} + *** Failers +No match + a\x{1234}b +No match + +/a(.{3,5})b/8 + a\x{1234}xyb + 0: a\x{1234}xyb + 1: \x{1234}xy + a\x{1234}\x{4321}yb + 0: a\x{1234}\x{4321}yb + 1: \x{1234}\x{4321}y + a\x{1234}\x{4321}\x{3412}b + 0: a\x{1234}\x{4321}\x{3412}b + 1: \x{1234}\x{4321}\x{3412} + axxxxbcdefghijb + 0: axxxxb + 1: xxxx + a\x{1234}\x{4321}\x{3412}\x{3421}b + 0: a\x{1234}\x{4321}\x{3412}\x{3421}b + 1: \x{1234}\x{4321}\x{3412}\x{3421} + axbxxbcdefghijb + 0: axbxxb + 1: xbxx + axxxxxbcdefghijb + 0: axxxxxb + 1: xxxxx + *** Failers +No match + a\x{1234}b +No match + axxxxxxbcdefghijb +No match + +/a(.{3,5}?)b/8 + a\x{1234}xyb + 0: a\x{1234}xyb + 1: \x{1234}xy + a\x{1234}\x{4321}yb + 0: a\x{1234}\x{4321}yb + 1: \x{1234}\x{4321}y + a\x{1234}\x{4321}\x{3412}b + 0: a\x{1234}\x{4321}\x{3412}b + 1: \x{1234}\x{4321}\x{3412} + axxxxbcdefghijb + 0: axxxxb + 1: xxxx + a\x{1234}\x{4321}\x{3412}\x{3421}b + 0: a\x{1234}\x{4321}\x{3412}\x{3421}b + 1: \x{1234}\x{4321}\x{3412}\x{3421} + axbxxbcdefghijb + 0: axbxxb + 1: xbxx + axxxxxbcdefghijb + 0: axxxxxb + 1: xxxxx + *** Failers +No match + a\x{1234}b +No match + axxxxxxbcdefghijb +No match + +/^[a\x{c0}]/8 + *** Failers +No match + \x{100} +No match + +/(?<=aXb)cd/8 + aXbcd + 0: cd + +/(?<=a\x{100}b)cd/8 + a\x{100}bcd + 0: cd + +/(?<=a\x{100000}b)cd/8 + a\x{100000}bcd + 0: cd + +/(?:\x{100}){3}b/8 + \x{100}\x{100}\x{100}b + 0: \x{100}\x{100}\x{100}b + *** Failers +No match + \x{100}\x{100}b +No match + +/\x{ab}/8 + \x{ab} + 0: \x{ab} + \xc2\xab + 0: \x{ab} + *** Failers +No match + \x00{ab} +No match + +/(?<=(.))X/8 + WXYZ + 0: X + 1: W + \x{256}XYZ + 0: X + 1: \x{256} + *** Failers +No match + XYZ +No match + +/X(\C{3})/8 + X\x{1234} + 0: X\x{1234} + 1: \x{1234} + +/X(\C{4})/8 + X\x{1234}YZ + 0: X\x{1234}Y + 1: \x{1234}Y + +/X\C*/8 + XYZabcdce + 0: XYZabcdce + +/X\C*?/8 + XYZabcde + 0: X + +/X\C{3,5}/8 + Xabcdefg + 0: Xabcde + X\x{1234} + 0: X\x{1234} + X\x{1234}YZ + 0: X\x{1234}YZ + X\x{1234}\x{512} + 0: X\x{1234}\x{512} + X\x{1234}\x{512}YZ + 0: X\x{1234}\x{512} + +/X\C{3,5}?/8 + Xabcdefg + 0: Xabc + X\x{1234} + 0: X\x{1234} + X\x{1234}YZ + 0: X\x{1234} + X\x{1234}\x{512} + 0: X\x{1234} + +/[^a]+/8g + bcd + 0: bcd + \x{100}aY\x{256}Z + 0: \x{100} + 0: Y\x{256}Z + +/^[^a]{2}/8 + \x{100}bc + 0: \x{100}b + +/^[^a]{2,}/8 + \x{100}bcAa + 0: \x{100}bcA + +/^[^a]{2,}?/8 + \x{100}bca + 0: \x{100}b + +/[^a]+/8ig + bcd + 0: bcd + \x{100}aY\x{256}Z + 0: \x{100} + 0: Y\x{256}Z + +/^[^a]{2}/8i + \x{100}bc + 0: \x{100}b + +/^[^a]{2,}/8i + \x{100}bcAa + 0: \x{100}bc + +/^[^a]{2,}?/8i + \x{100}bca + 0: \x{100}b + +/\x{100}{0,0}/8 + abcd + 0: + +/\x{100}?/8 + abcd + 0: + \x{100}\x{100} + 0: \x{100} + +/\x{100}{0,3}/8 + \x{100}\x{100} + 0: \x{100}\x{100} + \x{100}\x{100}\x{100}\x{100} + 0: \x{100}\x{100}\x{100} + +/\x{100}*/8 + abce + 0: + \x{100}\x{100}\x{100}\x{100} + 0: \x{100}\x{100}\x{100}\x{100} + +/\x{100}{1,1}/8 + abcd\x{100}\x{100}\x{100}\x{100} + 0: \x{100} + +/\x{100}{1,3}/8 + abcd\x{100}\x{100}\x{100}\x{100} + 0: \x{100}\x{100}\x{100} + +/\x{100}+/8 + abcd\x{100}\x{100}\x{100}\x{100} + 0: \x{100}\x{100}\x{100}\x{100} + +/\x{100}{3}/8 + abcd\x{100}\x{100}\x{100}XX + 0: \x{100}\x{100}\x{100} + +/\x{100}{3,5}/8 + abcd\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}XX + 0: \x{100}\x{100}\x{100}\x{100}\x{100} + +/\x{100}{3,}/8 + abcd\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}XX + 0: \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100} + +/(?<=a\x{100}{2}b)X/8+ + Xyyya\x{100}\x{100}bXzzz + 0: X + 0+ zzz + +/\D*/8 + aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa + 0: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa + +/\D*/8 + \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100} \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100} + 0: \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{10 0}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100} + +/\D/8 + 1X2 + 0: X + 1\x{100}2 + 0: \x{100} + +/>\S/8 + > >X Y + 0: >X + > >\x{100} Y + 0: >\x{100} + +/\d/8 + \x{100}3 + 0: 3 + +/\s/8 + \x{100} X + 0: + +/\D+/8 + 12abcd34 + 0: abcd + *** Failers + 0: *** Failers + 1234 +No match + +/\D{2,3}/8 + 12abcd34 + 0: abc + 12ab34 + 0: ab + *** Failers + 0: *** + 1234 +No match + 12a34 +No match + +/\D{2,3}?/8 + 12abcd34 + 0: ab + 12ab34 + 0: ab + *** Failers + 0: ** + 1234 +No match + 12a34 +No match + +/\d+/8 + 12abcd34 + 0: 12 + *** Failers +No match + +/\d{2,3}/8 + 12abcd34 + 0: 12 + 1234abcd + 0: 123 + *** Failers +No match + 1.4 +No match + +/\d{2,3}?/8 + 12abcd34 + 0: 12 + 1234abcd + 0: 12 + *** Failers +No match + 1.4 +No match + +/\S+/8 + 12abcd34 + 0: 12abcd34 + *** Failers + 0: *** + \ \ +No match + +/\S{2,3}/8 + 12abcd34 + 0: 12a + 1234abcd + 0: 123 + *** Failers + 0: *** + \ \ +No match + +/\S{2,3}?/8 + 12abcd34 + 0: 12 + 1234abcd + 0: 12 + *** Failers + 0: ** + \ \ +No match + +/>\s+ <34 + 0: > < + 0+ 34 + *** Failers +No match + +/>\s{2,3} < + 0+ cd + ab> < + 0+ ce + *** Failers +No match + ab> \s{2,3}? < + 0+ cd + ab> < + 0+ ce + *** Failers +No match + ab> \xff< + 0: \xff + +/[\xff]/8 + >\x{ff}< + 0: \x{ff} + +/[^\xFF]/ + XYZ + 0: X + +/[^\xff]/8 + XYZ + 0: X + \x{123} + 0: \x{123} + +/^[ac]*b/8 + xb +No match + +/^[ac\x{100}]*b/8 + xb +No match + +/^[^x]*b/8i + xb +No match + +/^[^x]*b/8 + xb +No match + +/^\d*b/8 + xb +No match + +/(|a)/g8 + catac + 0: + 1: + 0: + 1: + 0: a + 1: a + 0: + 1: + 0: + 1: + 0: a + 1: a + 0: + 1: + 0: + 1: + a\x{256}a + 0: + 1: + 0: a + 1: a + 0: + 1: + 0: + 1: + 0: a + 1: a + 0: + 1: + +/^\x{85}$/8i + \x{85} + 0: \x{85} + +/^ሴ/8 + ሴ + 0: \x{1234} + +/^\ሴ/8 + ሴ + 0: \x{1234} + +"(?s)(.{1,5})"8 + abcdefg + 0: abcde + 1: abcde + ab + 0: ab + 1: ab + +/a*\x{100}*\w/8 + a + 0: a + +/\S\S/8g + A\x{a3}BC + 0: A\x{a3} + 0: BC + +/\S{2}/8g + A\x{a3}BC + 0: A\x{a3} + 0: BC + +/\W\W/8g + +\x{a3}== + 0: +\x{a3} + 0: == + +/\W{2}/8g + +\x{a3}== + 0: +\x{a3} + 0: == + +/\S/8g + \x{442}\x{435}\x{441}\x{442} + 0: \x{442} + 0: \x{435} + 0: \x{441} + 0: \x{442} + +/[\S]/8g + \x{442}\x{435}\x{441}\x{442} + 0: \x{442} + 0: \x{435} + 0: \x{441} + 0: \x{442} + +/\D/8g + \x{442}\x{435}\x{441}\x{442} + 0: \x{442} + 0: \x{435} + 0: \x{441} + 0: \x{442} + +/[\D]/8g + \x{442}\x{435}\x{441}\x{442} + 0: \x{442} + 0: \x{435} + 0: \x{441} + 0: \x{442} + +/\W/8g + \x{2442}\x{2435}\x{2441}\x{2442} + 0: \x{2442} + 0: \x{2435} + 0: \x{2441} + 0: \x{2442} + +/[\W]/8g + \x{2442}\x{2435}\x{2441}\x{2442} + 0: \x{2442} + 0: \x{2435} + 0: \x{2441} + 0: \x{2442} + +/[\S\s]*/8 + abc\n\r\x{442}\x{435}\x{441}\x{442}xyz + 0: abc\x{0a}\x{0d}\x{442}\x{435}\x{441}\x{442}xyz + +/[\x{41f}\S]/8g + \x{442}\x{435}\x{441}\x{442} + 0: \x{442} + 0: \x{435} + 0: \x{441} + 0: \x{442} + +/.[^\S]./8g + abc def\x{442}\x{443}xyz\npqr + 0: c d + 0: z\x{0a}p + +/.[^\S\n]./8g + abc def\x{442}\x{443}xyz\npqr + 0: c d + +/[[:^alnum:]]/8g + +\x{2442} + 0: + + 0: \x{2442} + +/[[:^alpha:]]/8g + +\x{2442} + 0: + + 0: \x{2442} + +/[[:^ascii:]]/8g + A\x{442} + 0: \x{442} + +/[[:^blank:]]/8g + A\x{442} + 0: A + 0: \x{442} + +/[[:^cntrl:]]/8g + A\x{442} + 0: A + 0: \x{442} + +/[[:^digit:]]/8g + A\x{442} + 0: A + 0: \x{442} + +/[[:^graph:]]/8g + \x19\x{e01ff} + 0: \x{19} + 0: \x{e01ff} + +/[[:^lower:]]/8g + A\x{422} + 0: A + 0: \x{422} + +/[[:^print:]]/8g + \x{19}\x{e01ff} + 0: \x{19} + 0: \x{e01ff} + +/[[:^punct:]]/8g + A\x{442} + 0: A + 0: \x{442} + +/[[:^space:]]/8g + A\x{442} + 0: A + 0: \x{442} + +/[[:^upper:]]/8g + a\x{442} + 0: a + 0: \x{442} + +/[[:^word:]]/8g + +\x{2442} + 0: + + 0: \x{2442} + +/[[:^xdigit:]]/8g + M\x{442} + 0: M + 0: \x{442} + +/[^ABCDEFGHIJKLMNOPQRSTUVWXYZÀÁÂÃÄÅÆÇÈÉÊËÌÍÎÏÐÑÒÓÔÕÖØÙÚÛÜÝÞĀĂĄĆĈĊČĎĐĒĔĖĘĚĜĞĠĢĤĦĨĪĬĮİIJĴĶĹĻĽĿŁŃŅŇŊŌŎŐŒŔŖŘŚŜŞŠŢŤŦŨŪŬŮŰŲŴŶŸŹŻŽƁƂƄƆƇƉƊƋƎƏƐƑƓƔƖƗƘƜƝƟƠƢƤƦƧƩƬƮƯƱƲƳƵƷƸƼDŽLJNJǍǏǑǓǕǗǙǛǞǠǢǤǦǨǪǬǮDZǴǶǷǸǺǼǾȀȂȄȆȈȊȌȎȐȒȔȖȘȚȜȞȠȢȤȦȨȪȬȮȰȲȺȻȽȾɁΆΈΉΊΌΎΏΑΒΓΔΕΖΗΘΙΚΛΜΝΞΟΠΡΣΤΥΦΧΨΩΪΫϒϓϔϘϚϜϞϠϢϤϦϨϪϬϮϴϷϹϺϽϾϿЀЁЂЃЄЅІЇЈЉЊЋЌЍЎЏАБВГДЕЖЗИЙКЛМНОПРСТУФХЦЧШЩЪЫЬЭЮЯѠѢѤѦѨѪѬѮѰѲѴѶѸѺѼѾҀҊҌҎҐҒҔҖҘҚҜҞҠҢҤҦҨҪҬҮҰҲҴҶҸҺҼҾӀӁӃӅӇӉӋӍӐӒӔӖӘӚӜӞӠӢӤӦӨӪӬӮӰӲӴӶӸԀԂԄԆԈԊԌԎԱԲԳԴԵԶԷԸԹԺԻԼԽԾԿՀՁՂՃՄՅՆՇՈՉՊՋՌՍՎՏՐՑՒՓՔՕՖႠႡႢႣႤႥႦႧႨႩႪႫႬႭႮႯႰႱႲႳႴႵႶႷႸႹႺႻႼႽႾႿჀჁჂჃჄჅḀḂḄḆḈḊḌḎḠá¸’ḔḖḘḚḜḞḠḢḤḦḨḪḬḮḰḲḴḶḸḺḼḾṀṂṄṆṈṊṌṎṐṒṔṖṘṚṜṞṠṢṤṦṨṪṬṮṰṲṴṶṸṺṼṾẀẂẄẆẈẊẌẎẐẒẔẠẢẤẦẨẪẬẮẰẲẴẶẸẺẼẾỀỂỄỆỈỊỌỎỐỒỔỖỘỚỜỞỠỢỤỦỨỪỬỮỰỲỴỶỸἈἉἊἋἌἍἎἏἘἙἚἛἜἝἨἩἪἫἬἭἮἯἸἹἺἻἼἽἾἿὈὉὊὋὌὍὙὛὝὟὨὩὪὫὬὭὮὯᾸᾹᾺΆῈΈῊΉῘῙῚΊῨῩῪΎῬῸΌῺΏabcdefghijklmnopqrstuvwxyzªµºßàáâãäåæçèéêëìíîïðñòóôõöøùúûüýþÿāăąćĉċčďđēĕėęěĝğġģĥħĩīĭįıijĵķĸĺļľŀłńņňʼnŋōŏőœŕŗřśŝşšţťŧũūŭůűųŵŷźżžſƀƃƅƈƌƍƒƕƙƚƛƞơƣƥƨƪƫƭưƴƶƹƺƽƾƿdžljnjǎǐǒǔǖǘǚǜǝǟǡǣǥǧǩǫǭǯǰdzǵǹǻǽǿȁȃȅȇȉȋȍȏȑȓȕȗșțȝȟȡȣȥȧȩȫȭȯȱȳȴȵȶȷȸȹȼȿɀɐɑɒɓɔɕɖɗɘəɚɛɜɝɞɟɠɡɢɣɤɥɦɧɨɩɪɫɬɭɮɯɰɱɲɳɴɵɶɷɸɹɺɻɼɽɾɿʀʁʂʃʄʅʆʇʈʉʊʋʌʍʎʏʐʑʒʓʔʕʖʗʘʙʚʛʜʝʞʟʠʡʢʣʤʥʦʧʨʩʪʫʬʭʮʯΐάέήίΰαβγδεζηθικλμνξοπρςστυφχψωϊϋόύώϐϑϕϖϗϙϛϝϟϡϣϥϧϩϫϭϯϰϱϲϳϵϸϻϼабвгдежзийклмнопрстуфхцчшщъыьэюяѐёђѓєѕіїјљњћќѝўџѡѣѥѧѩѫѭѯѱѳѵѷѹѻѽѿҁҋҍҏґғҕҗҙқҝҟҡңҥҧҩҫҭүұҳҵҷҹһҽҿӂӄӆӈӊӌӎӑӓӕӗәӛӝӟӡӣӥӧөӫӭӯӱӳӵӷӹԁԃԅԇԉԋԍԏաբգդեզէըթժիլխծկհձղճմյնշոչպջռսվտրցւփքօֆևᴀᴁᴂᴃᴄᴅᴆᴇᴈᴉᴊᴋᴌᴍᴎᴏᴐᴑᴒᴓᴔᴕᴖᴗᴘᴙᴚᴛᴜᴝᴞᴟᴠᴡᴢᴣᴤᴥᴦᴧᴨᴩᴪᴫᵢᵣᵤᵥᵦᵧᵨᵩᵪᵫᵬᵭᵮᵯᵰᵱᵲᵳᵴᵵᵶᵷᵹᵺᵻᵼᵽᵾᵿᶀᶁᶂᶃᶄᶅᶆᶇᶈᶉᶊᶋᶌᶍᶎᶏᶐᶑᶒᶓᶔᶕᶖᶗᶘᶙᶚḁḃḅḇḉḋḍḏḑḓḕḗḙḛḝḟḡḣḥḧḩḫḭḯḱḳḵḷḹḻḽḿṁṃṅṇṉṋṍṏṑṓṕṗṙṛṝṟṡṣṥṧṩṫṭṯṱṳṵṷṹṻṽṿẁẃẅẇẉẋẍẏẑẓẕẖẗẘẙẚẛạảấầẩẫậắằẳẵặẹẻẽếềểễệỉịọỏốồổỗộớờởỡợụủứừửữựỳỵỷỹἀἁἂἃἄἅἆἇἐἑἒἓἔἕἠἡἢἣἤἥἦἧἰἱἲἳἴἵἶἷὀὁὂὃὄὅὐὑὒὓὔὕὖὗὠὡὢὣὤὥὦὧὰάὲέὴήὶίὸόὺύὼώᾀᾁᾂᾃᾄᾅᾆᾇᾐᾑᾒᾓᾔᾕᾖᾗᾠᾡᾢᾣᾤᾥᾦᾧᾰᾱᾲᾳᾴᾶᾷιῂῃῄῆῇῐῑῒΐῖῗῠῡῢΰῤῥῦῧῲῳῴῶῷⲁⲃⲅⲇⲉⲋⲍⲏⲑⲓⲕⲗⲙⲛⲝⲟⲡⲣⲥⲧⲩⲫⲭⲯⲱⲳⲵⲷⲹⲻⲽⲿⳁⳃⳅⳇⳉⳋⳍⳏⳑⳓⳕⳗⳙⳛⳝⳟⳡⳣⳤⴀⴁⴂⴃⴄⴅⴆⴇⴈⴉⴊⴋⴌⴍⴎⴏⴐⴑⴒⴓⴔⴕⴖⴗⴘⴙⴚⴛⴜⴝⴞⴟⴠⴡⴢⴣⴤⴥfffiflffifflſtstﬓﬔﬕﬖﬗ\d-_^]/8 + +/ End of testinput4 / ============================================================ --- pcre/testdata/testoutput5 28f6c3ad4fdce2d334745ca505ec2045a90c9860 +++ pcre/testdata/testoutput5 28f6c3ad4fdce2d334745ca505ec2045a90c9860 @@ -0,0 +1,1611 @@ +/\x{100}/8DZ +------------------------------------------------------------------ + Bra + \x{100} + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Options: utf8 +First char = 196 +Need char = 128 + +/\x{1000}/8DZ +------------------------------------------------------------------ + Bra + \x{1000} + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Options: utf8 +First char = 225 +Need char = 128 + +/\x{10000}/8DZ +------------------------------------------------------------------ + Bra + \x{10000} + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Options: utf8 +First char = 240 +Need char = 128 + +/\x{100000}/8DZ +------------------------------------------------------------------ + Bra + \x{100000} + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Options: utf8 +First char = 244 +Need char = 128 + +/\x{1000000}/8DZ +------------------------------------------------------------------ + Bra + \x{1000000} + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Options: utf8 +First char = 249 +Need char = 128 + +/\x{4000000}/8DZ +------------------------------------------------------------------ + Bra + \x{4000000} + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Options: utf8 +First char = 252 +Need char = 128 + +/\x{7fffFFFF}/8DZ +------------------------------------------------------------------ + Bra + \x{7fffffff} + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Options: utf8 +First char = 253 +Need char = 191 + +/[\x{ff}]/8DZ +------------------------------------------------------------------ + Bra + \x{ff} + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Options: utf8 +First char = 195 +Need char = 191 + +/[\x{100}]/8DZ +------------------------------------------------------------------ + Bra + [\x{100}] + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Options: utf8 +No first char +No need char + +/\x{ffffffff}/8 +Failed: character value in \x{...} sequence is too large at offset 11 + +/\x{100000000}/8 +Failed: character value in \x{...} sequence is too large at offset 12 + +/^\x{100}a\x{1234}/8 + \x{100}a\x{1234}bcd + 0: \x{100}a\x{1234} + +/\x80/8DZ +------------------------------------------------------------------ + Bra + \x{80} + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Options: utf8 +First char = 194 +Need char = 128 + +/\xff/8DZ +------------------------------------------------------------------ + Bra + \x{ff} + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Options: utf8 +First char = 195 +Need char = 191 + +/\x{0041}\x{2262}\x{0391}\x{002e}/DZ8 +------------------------------------------------------------------ + Bra + A\x{2262}\x{391}. + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Options: utf8 +First char = 'A' +Need char = '.' + \x{0041}\x{2262}\x{0391}\x{002e} + 0: A\x{2262}\x{391}. + +/\x{D55c}\x{ad6d}\x{C5B4}/DZ8 +------------------------------------------------------------------ + Bra + \x{d55c}\x{ad6d}\x{c5b4} + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Options: utf8 +First char = 237 +Need char = 180 + \x{D55c}\x{ad6d}\x{C5B4} + 0: \x{d55c}\x{ad6d}\x{c5b4} + +/\x{65e5}\x{672c}\x{8a9e}/DZ8 +------------------------------------------------------------------ + Bra + \x{65e5}\x{672c}\x{8a9e} + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Options: utf8 +First char = 230 +Need char = 158 + \x{65e5}\x{672c}\x{8a9e} + 0: \x{65e5}\x{672c}\x{8a9e} + +/\x{80}/DZ8 +------------------------------------------------------------------ + Bra + \x{80} + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Options: utf8 +First char = 194 +Need char = 128 + +/\x{084}/DZ8 +------------------------------------------------------------------ + Bra + \x{84} + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Options: utf8 +First char = 194 +Need char = 132 + +/\x{104}/DZ8 +------------------------------------------------------------------ + Bra + \x{104} + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Options: utf8 +First char = 196 +Need char = 132 + +/\x{861}/DZ8 +------------------------------------------------------------------ + Bra + \x{861} + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Options: utf8 +First char = 224 +Need char = 161 + +/\x{212ab}/DZ8 +------------------------------------------------------------------ + Bra + \x{212ab} + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Options: utf8 +First char = 240 +Need char = 171 + +/.{3,5}X/DZ8 +------------------------------------------------------------------ + Bra + Any{3} + Any{0,2} + X + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Partial matching not supported +Options: utf8 +No first char +Need char = 'X' + \x{212ab}\x{212ab}\x{212ab}\x{861}X + 0: \x{212ab}\x{212ab}\x{212ab}\x{861}X + + +/.{3,5}?/DZ8 +------------------------------------------------------------------ + Bra + Any{3} + Any{0,2}? + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Partial matching not supported +Options: utf8 +No first char +No need char + \x{212ab}\x{212ab}\x{212ab}\x{861} + 0: \x{212ab}\x{212ab}\x{212ab} + +/-- These tests are here rather than in testinput4 because Perl 5.6 has some +problems with UTF-8 support, in the area of \x{..} where the value is < 255. +It grumbles about invalid UTF-8 strings. --/ + +/^[a\x{c0}]b/8 + \x{c0}b + 0: \x{c0}b + +/^([a\x{c0}]*?)aa/8 + a\x{c0}aaaa/ + 0: a\x{c0}aa + 1: a\x{c0} + +/^([a\x{c0}]*?)aa/8 + a\x{c0}aaaa/ + 0: a\x{c0}aa + 1: a\x{c0} + a\x{c0}a\x{c0}aaa/ + 0: a\x{c0}a\x{c0}aa + 1: a\x{c0}a\x{c0} + +/^([a\x{c0}]*)aa/8 + a\x{c0}aaaa/ + 0: a\x{c0}aaaa + 1: a\x{c0}aa + a\x{c0}a\x{c0}aaa/ + 0: a\x{c0}a\x{c0}aaa + 1: a\x{c0}a\x{c0}a + +/^([a\x{c0}]*)a\x{c0}/8 + a\x{c0}aaaa/ + 0: a\x{c0} + 1: + a\x{c0}a\x{c0}aaa/ + 0: a\x{c0}a\x{c0} + 1: a\x{c0} + +/-- --/ + +/(?<=\C)X/8 +Failed: \C not allowed in lookbehind assertion at offset 6 + +/-- This one is here not because it's different to Perl, but because the way +the captured single-byte is displayed. (In Perl it becomes a character, and you +can't tell the difference.) --/ + +/X(\C)(.*)/8 + X\x{1234} + 0: X\x{1234} + 1: \xe1 + 2: \x88\xb4 + X\nabc + 0: X\x{0a}abc + 1: \x{0a} + 2: abc + +/^[ab]/8DZ +------------------------------------------------------------------ + Bra + ^ + [ab] + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Options: anchored utf8 +No first char +No need char + bar + 0: b + *** Failers +No match + c +No match + \x{ff} +No match + \x{100} +No match + +/^[^ab]/8DZ +------------------------------------------------------------------ + Bra + ^ + [\x00-`c-\xff] (neg) + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Options: anchored utf8 +No first char +No need char + c + 0: c + \x{ff} + 0: \x{ff} + \x{100} + 0: \x{100} + *** Failers + 0: * + aaa +No match + +/[^ab\xC0-\xF0]/8SDZ +------------------------------------------------------------------ + Bra + [\x00-`c-\xbf\xf1-\xff] (neg) + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Options: utf8 +No first char +No need char +Starting byte set: \x00 \x01 \x02 \x03 \x04 \x05 \x06 \x07 \x08 \x09 \x0a + \x0b \x0c \x0d \x0e \x0f \x10 \x11 \x12 \x13 \x14 \x15 \x16 \x17 \x18 \x19 + \x1a \x1b \x1c \x1d \x1e \x1f \x20 ! " # $ % & ' ( ) * + , - . / 0 1 2 3 4 + 5 6 7 8 9 : ; < = > ? @ A B C D E F G H I J K L M N O P Q R S T U V W X Y + Z [ \ ] ^ _ ` c d e f g h i j k l m n o p q r s t u v w x y z { | } ~ \x7f + \xc2 \xc3 \xc4 \xc5 \xc6 \xc7 \xc8 \xc9 \xca \xcb \xcc \xcd \xce \xcf \xd0 + \xd1 \xd2 \xd3 \xd4 \xd5 \xd6 \xd7 \xd8 \xd9 \xda \xdb \xdc \xdd \xde \xdf + \xe0 \xe1 \xe2 \xe3 \xe4 \xe5 \xe6 \xe7 \xe8 \xe9 \xea \xeb \xec \xed \xee + \xef \xf0 \xf1 \xf2 \xf3 \xf4 \xf5 \xf6 \xf7 \xf8 \xf9 \xfa \xfb \xfc \xfd + \xfe \xff + \x{f1} + 0: \x{f1} + \x{bf} + 0: \x{bf} + \x{100} + 0: \x{100} + \x{1000} + 0: \x{1000} + *** Failers + 0: * + \x{c0} +No match + \x{f0} +No match + +/Ā{3,4}/8SDZ +------------------------------------------------------------------ + Bra + \x{100}{3} + \x{100}? + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Partial matching not supported +Options: utf8 +First char = 196 +Need char = 128 +Study returned NULL + \x{100}\x{100}\x{100}\x{100\x{100} + 0: \x{100}\x{100}\x{100} + +/(\x{100}+|x)/8SDZ +------------------------------------------------------------------ + Bra + CBra 1 + \x{100}+ + Alt + x + Ket + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 1 +Partial matching not supported +Options: utf8 +No first char +No need char +Starting byte set: x \xc4 + +/(\x{100}*a|x)/8SDZ +------------------------------------------------------------------ + Bra + CBra 1 + \x{100}*+ + a + Alt + x + Ket + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 1 +Partial matching not supported +Options: utf8 +No first char +No need char +Starting byte set: a x \xc4 + +/(\x{100}{0,2}a|x)/8SDZ +------------------------------------------------------------------ + Bra + CBra 1 + \x{100}{0,2} + a + Alt + x + Ket + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 1 +Partial matching not supported +Options: utf8 +No first char +No need char +Starting byte set: a x \xc4 + +/(\x{100}{1,2}a|x)/8SDZ +------------------------------------------------------------------ + Bra + CBra 1 + \x{100} + \x{100}{0,1} + a + Alt + x + Ket + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 1 +Partial matching not supported +Options: utf8 +No first char +No need char +Starting byte set: x \xc4 + +/\x{100}*(\d+|"(?1)")/8 + 1234 + 0: 1234 + 1: 1234 + "1234" + 0: "1234" + 1: "1234" + \x{100}1234 + 0: \x{100}1234 + 1: 1234 + "\x{100}1234" + 0: \x{100}1234 + 1: 1234 + \x{100}\x{100}12ab + 0: \x{100}\x{100}12 + 1: 12 + \x{100}\x{100}"12" + 0: \x{100}\x{100}"12" + 1: "12" + *** Failers +No match + \x{100}\x{100}abcd +No match + +/\x{100}/8DZ +------------------------------------------------------------------ + Bra + \x{100} + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Options: utf8 +First char = 196 +Need char = 128 + +/\x{100}*/8DZ +------------------------------------------------------------------ + Bra + \x{100}* + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Partial matching not supported +Options: utf8 +No first char +No need char + +/a\x{100}*/8DZ +------------------------------------------------------------------ + Bra + a + \x{100}* + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Partial matching not supported +Options: utf8 +First char = 'a' +No need char + +/ab\x{100}*/8DZ +------------------------------------------------------------------ + Bra + ab + \x{100}* + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Partial matching not supported +Options: utf8 +First char = 'a' +Need char = 'b' + +/a\x{100}\x{101}*/8DZ +------------------------------------------------------------------ + Bra + a\x{100} + \x{101}* + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Partial matching not supported +Options: utf8 +First char = 'a' +Need char = 128 + +/a\x{100}\x{101}+/8DZ +------------------------------------------------------------------ + Bra + a\x{100} + \x{101}+ + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Partial matching not supported +Options: utf8 +First char = 'a' +Need char = 129 + +/\x{100}*A/8DZ +------------------------------------------------------------------ + Bra + \x{100}*+ + A + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Partial matching not supported +Options: utf8 +No first char +Need char = 'A' + A + 0: A + +/\x{100}*\d(?R)/8DZ +------------------------------------------------------------------ + Bra + \x{100}*+ + \d + Once + Recurse + Ket + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Partial matching not supported +Options: utf8 +No first char +No need char + +/[^\x{c4}]/DZ +------------------------------------------------------------------ + Bra + [^\xc4] + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +No options +No first char +No need char + +/[^\x{c4}]/8DZ +------------------------------------------------------------------ + Bra + [\x00-\xc3\xc5-\xff] (neg) + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Options: utf8 +No first char +No need char + +/[\x{100}]/8DZ +------------------------------------------------------------------ + Bra + [\x{100}] + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Options: utf8 +No first char +No need char + \x{100} + 0: \x{100} + Z\x{100} + 0: \x{100} + \x{100}Z + 0: \x{100} + *** Failers +No match + +/[Z\x{100}]/8DZ +------------------------------------------------------------------ + Bra + [Z\x{100}] + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Options: utf8 +No first char +No need char + Z\x{100} + 0: Z + \x{100} + 0: \x{100} + \x{100}Z + 0: \x{100} + *** Failers +No match + +/[\x{200}-\x{100}]/8 +Failed: range out of order in character class at offset 15 + +/[Ā-Ą]/8 + \x{100} + 0: \x{100} + \x{104} + 0: \x{104} + *** Failers +No match + \x{105} +No match + \x{ff} +No match + +/[z-\x{100}]/8DZ +------------------------------------------------------------------ + Bra + [z-\x{100}] + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Options: utf8 +No first char +No need char + +/[z\Qa-d]Ā\E]/8DZ +------------------------------------------------------------------ + Bra + [\-\]adz\x{100}] + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Options: utf8 +No first char +No need char + \x{100} + 0: \x{100} + Ā + 0: \x{100} + +/[\xFF]/DZ +------------------------------------------------------------------ + Bra + \xff + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +No options +First char = 255 +No need char + >\xff< + 0: \xff + +/[\xff]/DZ8 +------------------------------------------------------------------ + Bra + \x{ff} + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Options: utf8 +First char = 195 +Need char = 191 + >\x{ff}< + 0: \x{ff} + +/[^\xFF]/DZ +------------------------------------------------------------------ + Bra + [^\xff] + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +No options +No first char +No need char + +/[^\xff]/8DZ +------------------------------------------------------------------ + Bra + [\x00-\xfe] (neg) + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Options: utf8 +No first char +No need char + +/[Ä-Ü]/8 + Ö # Matches without Study + 0: \x{d6} + \x{d6} + 0: \x{d6} + +/[Ä-Ü]/8S + Ö <-- Same with Study + 0: \x{d6} + \x{d6} + 0: \x{d6} + +/[\x{c4}-\x{dc}]/8 + Ö # Matches without Study + 0: \x{d6} + \x{d6} + 0: \x{d6} + +/[\x{c4}-\x{dc}]/8S + Ö <-- Same with Study + 0: \x{d6} + \x{d6} + 0: \x{d6} + +/[Ã]/8 +Failed: invalid UTF-8 string at offset 2 + +/Ã/8 +Failed: invalid UTF-8 string at offset 0 + +/ÃÃÃxxx/8 +Failed: invalid UTF-8 string at offset 1 + +/ÃÃÃxxx/8?DZ +------------------------------------------------------------------ + Bra + \X{c0}\X{c0}\X{c0}xxx + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Options: utf8 no_utf8_check +First char = 195 +Need char = 'x' + +/abc/8 + Ã] +Error -10 + à +Error -10 + ÃÃà +Error -10 + ÃÃÃ\? +No match + +/anything/8 + \xc0\x80 +Error -10 + \xc1\x8f +Error -10 + \xe0\x9f\x80 +Error -10 + \xf0\x8f\x80\x80 +Error -10 + \xf8\x87\x80\x80\x80 +Error -10 + \xfc\x83\x80\x80\x80\x80 +Error -10 + \xfe\x80\x80\x80\x80\x80 +Error -10 + \xff\x80\x80\x80\x80\x80 +Error -10 + \xc3\x8f +No match + \xe0\xaf\x80 +No match + \xe1\x80\x80 +No match + \xf0\x9f\x80\x80 +No match + \xf1\x8f\x80\x80 +No match + \xf8\x88\x80\x80\x80 +Error -10 + \xf9\x87\x80\x80\x80 +Error -10 + \xfc\x84\x80\x80\x80\x80 +Error -10 + \xfd\x83\x80\x80\x80\x80 +Error -10 + \?\xf8\x88\x80\x80\x80 +No match + \?\xf9\x87\x80\x80\x80 +No match + \?\xfc\x84\x80\x80\x80\x80 +No match + \?\xfd\x83\x80\x80\x80\x80 +No match + +/\x{100}abc(xyz(?1))/8DZ +------------------------------------------------------------------ + Bra + \x{100}abc + CBra 1 + xyz + Once + Recurse + Ket + Ket + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 1 +Options: utf8 +First char = 196 +Need char = 'z' + +/[^\x{100}]abc(xyz(?1))/8DZ +------------------------------------------------------------------ + Bra + [^\x{100}] + abc + CBra 1 + xyz + Once + Recurse + Ket + Ket + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 1 +Options: utf8 +No first char +Need char = 'z' + +/[ab\x{100}]abc(xyz(?1))/8DZ +------------------------------------------------------------------ + Bra + [ab\x{100}] + abc + CBra 1 + xyz + Once + Recurse + Ket + Ket + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 1 +Options: utf8 +No first char +Need char = 'z' + +/(\x{100}(b(?2)c))?/DZ8 +------------------------------------------------------------------ + Bra + Brazero + CBra 1 + \x{100} + CBra 2 + b + Once + Recurse + Ket + c + Ket + Ket + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 2 +Options: utf8 +No first char +No need char + +/(\x{100}(b(?2)c)){0,2}/DZ8 +------------------------------------------------------------------ + Bra + Brazero + Bra + CBra 1 + \x{100} + CBra 2 + b + Once + Recurse + Ket + c + Ket + Ket + Brazero + CBra 1 + \x{100} + CBra 2 + b + Once + Recurse + Ket + c + Ket + Ket + Ket + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 2 +Options: utf8 +No first char +No need char + +/(\x{100}(b(?1)c))?/DZ8 +------------------------------------------------------------------ + Bra + Brazero + CBra 1 + \x{100} + CBra 2 + b + Once + Recurse + Ket + c + Ket + Ket + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 2 +Options: utf8 +No first char +No need char + +/(\x{100}(b(?1)c)){0,2}/DZ8 +------------------------------------------------------------------ + Bra + Brazero + Bra + CBra 1 + \x{100} + CBra 2 + b + Once + Recurse + Ket + c + Ket + Ket + Brazero + CBra 1 + \x{100} + CBra 2 + b + Once + Recurse + Ket + c + Ket + Ket + Ket + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 2 +Options: utf8 +No first char +No need char + +/\W/8 + A.B + 0: . + A\x{100}B + 0: \x{100} + +/\w/8 + \x{100}X + 0: X + +/a\x{1234}b/P8 + a\x{1234}b + 0: a\x{1234}b + +/^\ሴ/8DZ +------------------------------------------------------------------ + Bra + ^ + \x{1234} + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Options: anchored utf8 +No first char +No need char + +/\777/I +Failed: octal value is greater than \377 (not in UTF-8 mode) at offset 3 + +/\777/8I +Capturing subpattern count = 0 +Options: utf8 +First char = 199 +Need char = 191 + \x{1ff} + 0: \x{1ff} + \777 + 0: \x{1ff} + +/\x{100}*\d/8DZ +------------------------------------------------------------------ + Bra + \x{100}*+ + \d + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Partial matching not supported +Options: utf8 +No first char +No need char + +/\x{100}*\s/8DZ +------------------------------------------------------------------ + Bra + \x{100}*+ + \s + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Partial matching not supported +Options: utf8 +No first char +No need char + +/\x{100}*\w/8DZ +------------------------------------------------------------------ + Bra + \x{100}*+ + \w + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Partial matching not supported +Options: utf8 +No first char +No need char + +/\x{100}*\D/8DZ +------------------------------------------------------------------ + Bra + \x{100}* + \D + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Partial matching not supported +Options: utf8 +No first char +No need char + +/\x{100}*\S/8DZ +------------------------------------------------------------------ + Bra + \x{100}* + \S + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Partial matching not supported +Options: utf8 +No first char +No need char + +/\x{100}*\W/8DZ +------------------------------------------------------------------ + Bra + \x{100}* + \W + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Partial matching not supported +Options: utf8 +No first char +No need char + +/\x{100}+\x{200}/8DZ +------------------------------------------------------------------ + Bra + \x{100}++ + \x{200} + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Partial matching not supported +Options: utf8 +First char = 196 +Need char = 128 + +/\x{100}+X/8DZ +------------------------------------------------------------------ + Bra + \x{100}++ + X + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Partial matching not supported +Options: utf8 +First char = 196 +Need char = 'X' + +/X+\x{200}/8DZ +------------------------------------------------------------------ + Bra + X++ + \x{200} + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Partial matching not supported +Options: utf8 +First char = 'X' +Need char = 128 + +/()()()()()()()()()() + ()()()()()()()()()() + ()()()()()()()()()() + ()()()()()()()()()() + A (x) (?41) B/8x + AxxB +Matched, but too many substrings + 0: AxxB + 1: + 2: + 3: + 4: + 5: + 6: + 7: + 8: + 9: +10: +11: +12: +13: +14: + +/^[\x{100}\E-\Q\E\x{150}]/BZ8 +------------------------------------------------------------------ + Bra + ^ + [\x{100}-\x{150}] + Ket + End +------------------------------------------------------------------ + +/^[\QĀ\E-\QŐ\E]/BZ8 +------------------------------------------------------------------ + Bra + ^ + [\x{100}-\x{150}] + Ket + End +------------------------------------------------------------------ + +/^[\QĀ\E-\QŐ\E/BZ8 +Failed: missing terminating ] for character class at offset 15 + +/^abc./mgx8 + abc1 \x0aabc2 \x0babc3xx \x0cabc4 \x0dabc5xx \x0d\x0aabc6 \x{0085}abc7 \x{2028}abc8 \x{2029}abc9 JUNK + 0: abc1 + 0: abc2 + 0: abc3 + 0: abc4 + 0: abc5 + 0: abc6 + 0: abc7 + 0: abc8 + 0: abc9 + +/abc.$/mgx8 + abc1\x0a abc2\x0b abc3\x0c abc4\x0d abc5\x0d\x0a abc6\x{0085} abc7\x{2028} abc8\x{2029} abc9 + 0: abc1 + 0: abc2 + 0: abc3 + 0: abc4 + 0: abc5 + 0: abc6 + 0: abc7 + 0: abc8 + 0: abc9 + +/^a\Rb/8 + a\nb + 0: a\x{0a}b + a\rb + 0: a\x{0d}b + a\r\nb + 0: a\x{0d}\x{0a}b + a\x0bb + 0: a\x{0b}b + a\x0cb + 0: a\x{0c}b + a\x{85}b + 0: a\x{85}b + a\x{2028}b + 0: a\x{2028}b + a\x{2029}b + 0: a\x{2029}b + ** Failers +No match + a\n\rb +No match + +/^a\R*b/8 + ab + 0: ab + a\nb + 0: a\x{0a}b + a\rb + 0: a\x{0d}b + a\r\nb + 0: a\x{0d}\x{0a}b + a\x0bb + 0: a\x{0b}b + a\x0c\x{2028}\x{2029}b + 0: a\x{0c}\x{2028}\x{2029}b + a\x{85}b + 0: a\x{85}b + a\n\rb + 0: a\x{0a}\x{0d}b + a\n\r\x{85}\x0cb + 0: a\x{0a}\x{0d}\x{85}\x{0c}b + +/^a\R+b/8 + a\nb + 0: a\x{0a}b + a\rb + 0: a\x{0d}b + a\r\nb + 0: a\x{0d}\x{0a}b + a\x0bb + 0: a\x{0b}b + a\x0c\x{2028}\x{2029}b + 0: a\x{0c}\x{2028}\x{2029}b + a\x{85}b + 0: a\x{85}b + a\n\rb + 0: a\x{0a}\x{0d}b + a\n\r\x{85}\x0cb + 0: a\x{0a}\x{0d}\x{85}\x{0c}b + ** Failers +No match + ab +No match + +/^a\R{1,3}b/8 + a\nb + 0: a\x{0a}b + a\n\rb + 0: a\x{0a}\x{0d}b + a\n\r\x{85}b + 0: a\x{0a}\x{0d}\x{85}b + a\r\n\r\nb + 0: a\x{0d}\x{0a}\x{0d}\x{0a}b + a\r\n\r\n\r\nb + 0: a\x{0d}\x{0a}\x{0d}\x{0a}\x{0d}\x{0a}b + a\n\r\n\rb + 0: a\x{0a}\x{0d}\x{0a}\x{0d}b + a\n\n\r\nb + 0: a\x{0a}\x{0a}\x{0d}\x{0a}b + ** Failers +No match + a\n\n\n\rb +No match + a\r +No match + +/\H\h\V\v/8 + X X\x0a + 0: X X\x{0a} + X\x09X\x0b + 0: X\x{09}X\x{0b} + ** Failers +No match + \x{a0} X\x0a +No match + +/\H*\h+\V?\v{3,4}/8 + \x09\x20\x{a0}X\x0a\x0b\x0c\x0d\x0a + 0: \x{09} \x{a0}X\x{0a}\x{0b}\x{0c}\x{0d} + \x09\x20\x{a0}\x0a\x0b\x0c\x0d\x0a + 0: \x{09} \x{a0}\x{0a}\x{0b}\x{0c}\x{0d} + \x09\x20\x{a0}\x0a\x0b\x0c + 0: \x{09} \x{a0}\x{0a}\x{0b}\x{0c} + ** Failers +No match + \x09\x20\x{a0}\x0a\x0b +No match + +/\H\h\V\v/8 + \x{3001}\x{3000}\x{2030}\x{2028} + 0: \x{3001}\x{3000}\x{2030}\x{2028} + X\x{180e}X\x{85} + 0: X\x{180e}X\x{85} + ** Failers +No match + \x{2009} X\x0a +No match + +/\H*\h+\V?\v{3,4}/8 + \x{1680}\x{180e}\x{2007}X\x{2028}\x{2029}\x0c\x0d\x0a + 0: \x{1680}\x{180e}\x{2007}X\x{2028}\x{2029}\x{0c}\x{0d} + \x09\x{205f}\x{a0}\x0a\x{2029}\x0c\x{2028}\x0a + 0: \x{09}\x{205f}\x{a0}\x{0a}\x{2029}\x{0c}\x{2028} + \x09\x20\x{202f}\x0a\x0b\x0c + 0: \x{09} \x{202f}\x{0a}\x{0b}\x{0c} + ** Failers +No match + \x09\x{200a}\x{a0}\x{2028}\x0b +No match + +/[\h]/8BZ +------------------------------------------------------------------ + Bra + [\x09 \xa0\x{1680}\x{180e}\x{2000}-\x{200a}\x{202f}\x{205f}\x{3000}] + Ket + End +------------------------------------------------------------------ + >\x{1680} + 0: \x{1680} + +/[\h]{3,}/8BZ +------------------------------------------------------------------ + Bra + [\x09 \xa0\x{1680}\x{180e}\x{2000}-\x{200a}\x{202f}\x{205f}\x{3000}]{3,} + Ket + End +------------------------------------------------------------------ + >\x{1680}\x{180e}\x{2000}\x{2003}\x{200a}\x{202f}\x{205f}\x{3000}< + 0: \x{1680}\x{180e}\x{2000}\x{2003}\x{200a}\x{202f}\x{205f}\x{3000} + +/[\v]/8BZ +------------------------------------------------------------------ + Bra + [\x0a-\x0d\x85\x{2028}-\x{2029}] + Ket + End +------------------------------------------------------------------ + +/[\H]/8BZ +------------------------------------------------------------------ + Bra + [\x00-\x08\x0a-\x1f!-\x9f\xa1-\xff\x{100}-\x{167f}\x{1681}-\x{180d}\x{180f}-\x{1fff}\x{200b}-\x{202e}\x{2030}-\x{205e}\x{2060}-\x{2fff}\x{3001}-\x{7fffffff}] + Ket + End +------------------------------------------------------------------ + +/[\V]/8BZ +------------------------------------------------------------------ + Bra + [\x00-\x09\x0e-\x84\x86-\xff\x{100}-\x{2027}\x{2029}-\x{7fffffff}] + Ket + End +------------------------------------------------------------------ + +/.*$/8 + \x{1ec5} + 0: \x{1ec5} + +/-- This tests the stricter UTF-8 check according to RFC 3629. --/ + +/X/8 + \x{0}\x{d7ff}\x{e000}\x{10ffff} +No match + \x{d800} +Error -10 + \x{d800}\? +No match + \x{da00} +Error -10 + \x{da00}\? +No match + \x{dfff} +Error -10 + \x{dfff}\? +No match + \x{110000} +Error -10 + \x{110000}\? +No match + \x{2000000} +Error -10 + \x{2000000}\? +No match + \x{7fffffff} +Error -10 + \x{7fffffff}\? +No match + +/a\Rb/I8 +Capturing subpattern count = 0 +Options: bsr_anycrlf utf8 +First char = 'a' +Need char = 'b' + a\rb + 0: a\x{0d}b + a\nb + 0: a\x{0a}b + a\r\nb + 0: a\x{0d}\x{0a}b + ** Failers +No match + a\x{85}b +No match + a\x0bb +No match + +/a\Rb/I8 +Capturing subpattern count = 0 +Options: bsr_unicode utf8 +First char = 'a' +Need char = 'b' + a\rb + 0: a\x{0d}b + a\nb + 0: a\x{0a}b + a\r\nb + 0: a\x{0d}\x{0a}b + a\x{85}b + 0: a\x{85}b + a\x0bb + 0: a\x{0b}b + ** Failers +No match + a\x{85}b\ +No match + a\x0bb\ +No match + +/a\R?b/I8 +Capturing subpattern count = 0 +Options: bsr_anycrlf utf8 +First char = 'a' +Need char = 'b' + a\rb + 0: a\x{0d}b + a\nb + 0: a\x{0a}b + a\r\nb + 0: a\x{0d}\x{0a}b + ** Failers +No match + a\x{85}b +No match + a\x0bb +No match + +/a\R?b/I8 +Capturing subpattern count = 0 +Options: bsr_unicode utf8 +First char = 'a' +Need char = 'b' + a\rb + 0: a\x{0d}b + a\nb + 0: a\x{0a}b + a\r\nb + 0: a\x{0d}\x{0a}b + a\x{85}b + 0: a\x{85}b + a\x0bb + 0: a\x{0b}b + ** Failers +No match + a\x{85}b\ +No match + a\x0bb\ +No match + +/.*a.*=.b.*/8 + QQQ\x{2029}ABCaXYZ=!bPQR + 0: ABCaXYZ=!bPQR + ** Failers +No match + a\x{2029}b +No match + \x61\xe2\x80\xa9\x62 +No match + +/[[:a\x{100}b:]]/8 +Failed: unknown POSIX class name at offset 3 + +/ End of testinput5 / ============================================================ --- pcre/testdata/testoutput6 6dcc68e8f1e3a9303f845c8c5f7742b53326c7c9 +++ pcre/testdata/testoutput6 6dcc68e8f1e3a9303f845c8c5f7742b53326c7c9 @@ -0,0 +1,1682 @@ +/^\pC\pL\pM\pN\pP\pS\pZ3 + 0: abc + *** Failers +No match + xyzabc +No match + xyzabc\>2 +No match + +/x\dy\Dz/ + x9yzz + 0: x9yzz + x0y+z + 0: x0y+z + *** Failers +No match + xyz +No match + xxy0z +No match + +/x\sy\Sz/ + x yzz + 0: x yzz + x y+z + 0: x y+z + *** Failers +No match + xyz +No match + xxyyz +No match + +/x\wy\Wz/ + xxy+z + 0: xxy+z + *** Failers +No match + xxy0z +No match + x+y+z +No match + +/x.y/ + x+y + 0: x+y + x-y + 0: x-y + *** Failers +No match + x\ny +No match + +/x.y/s + x+y + 0: x+y + x-y + 0: x-y + x\ny + 0: x\x0ay + +/(a.b(?s)c.d|x.y)p.q/ + a+bc+dp+q + 0: a+bc+dp+q + a+bc\ndp+q + 0: a+bc\x0adp+q + x\nyp+q + 0: x\x0ayp+q + *** Failers +No match + a\nbc\ndp+q +No match + a+bc\ndp\nq +No match + x\nyp\nq +No match + +/a\d\z/ + ba0 + 0: a0 + *** Failers +No match + ba0\n +No match + ba0\ncd +No match + +/a\d\z/m + ba0 + 0: a0 + *** Failers +No match + ba0\n +No match + ba0\ncd +No match + +/a\d\Z/ + ba0 + 0: a0 + ba0\n + 0: a0 + *** Failers +No match + ba0\ncd +No match + +/a\d\Z/m + ba0 + 0: a0 + ba0\n + 0: a0 + *** Failers +No match + ba0\ncd +No match + +/a\d$/ + ba0 + 0: a0 + ba0\n + 0: a0 + *** Failers +No match + ba0\ncd +No match + +/a\d$/m + ba0 + 0: a0 + ba0\n + 0: a0 + ba0\ncd + 0: a0 + *** Failers +No match + +/abc/i + abc + 0: abc + aBc + 0: aBc + ABC + 0: ABC + +/[^a]/ + abcd + 0: b + +/ab?\w/ + abz + 0: abz + 1: ab + abbz + 0: abb + 1: ab + azz + 0: az + +/x{0,3}yz/ + ayzq + 0: yz + axyzq + 0: xyz + axxyz + 0: xxyz + axxxyzq + 0: xxxyz + axxxxyzq + 0: xxxyz + *** Failers +No match + ax +No match + axx +No match + +/x{3}yz/ + axxxyzq + 0: xxxyz + axxxxyzq + 0: xxxyz + *** Failers +No match + ax +No match + axx +No match + ayzq +No match + axyzq +No match + axxyz +No match + +/x{2,3}yz/ + axxyz + 0: xxyz + axxxyzq + 0: xxxyz + axxxxyzq + 0: xxxyz + *** Failers +No match + ax +No match + axx +No match + ayzq +No match + axyzq +No match + +/[^a]+/ + bac + 0: b + bcdefax + 0: bcdef + 1: bcde + 2: bcd + 3: bc + 4: b + *** Failers + 0: *** F + 1: *** + 2: *** + 3: ** + 4: * + aaaaa +No match + +/[^a]*/ + bac + 0: b + 1: + bcdefax + 0: bcdef + 1: bcde + 2: bcd + 3: bc + 4: b + 5: + *** Failers + 0: *** F + 1: *** + 2: *** + 3: ** + 4: * + 5: + aaaaa + 0: + +/[^a]{3,5}/ + xyz + 0: xyz + awxyza + 0: wxyz + 1: wxy + abcdefa + 0: bcdef + 1: bcde + 2: bcd + abcdefghijk + 0: bcdef + 1: bcde + 2: bcd + *** Failers + 0: *** F + 1: *** + 2: *** + axya +No match + axa +No match + aaaaa +No match + +/\d*/ + 1234b567 + 0: 1234 + 1: 123 + 2: 12 + 3: 1 + 4: + xyz + 0: + +/\D*/ + a1234b567 + 0: a + 1: + xyz + 0: xyz + 1: xy + 2: x + 3: + +/\d+/ + ab1234c56 + 0: 1234 + 1: 123 + 2: 12 + 3: 1 + *** Failers +No match + xyz +No match + +/\D+/ + ab123c56 + 0: ab + 1: a + *** Failers + 0: *** Failers + 1: *** Failer + 2: *** Faile + 3: *** Fail + 4: *** Fai + 5: *** Fa + 6: *** F + 7: *** + 8: *** + 9: ** +10: * + 789 +No match + +/\d?A/ + 045ABC + 0: 5A + ABC + 0: A + *** Failers +No match + XYZ +No match + +/\D?A/ + ABC + 0: A + BAC + 0: BA + 9ABC + 0: A + *** Failers +No match + +/a+/ + aaaa + 0: aaaa + 1: aaa + 2: aa + 3: a + +/^.*xyz/ + xyz + 0: xyz + ggggggggxyz + 0: ggggggggxyz + +/^.+xyz/ + abcdxyz + 0: abcdxyz + axyz + 0: axyz + *** Failers +No match + xyz +No match + +/^.?xyz/ + xyz + 0: xyz + cxyz + 0: cxyz + +/^\d{2,3}X/ + 12X + 0: 12X + 123X + 0: 123X + *** Failers +No match + X +No match + 1X +No match + 1234X +No match + +/^[abcd]\d/ + a45 + 0: a4 + b93 + 0: b9 + c99z + 0: c9 + d04 + 0: d0 + *** Failers +No match + e45 +No match + abcd +No match + abcd1234 +No match + 1234 +No match + +/^[abcd]*\d/ + a45 + 0: a4 + b93 + 0: b9 + c99z + 0: c9 + d04 + 0: d0 + abcd1234 + 0: abcd1 + 1234 + 0: 1 + *** Failers +No match + e45 +No match + abcd +No match + +/^[abcd]+\d/ + a45 + 0: a4 + b93 + 0: b9 + c99z + 0: c9 + d04 + 0: d0 + abcd1234 + 0: abcd1 + *** Failers +No match + 1234 +No match + e45 +No match + abcd +No match + +/^a+X/ + aX + 0: aX + aaX + 0: aaX + +/^[abcd]?\d/ + a45 + 0: a4 + b93 + 0: b9 + c99z + 0: c9 + d04 + 0: d0 + 1234 + 0: 1 + *** Failers +No match + abcd1234 +No match + e45 +No match + +/^[abcd]{2,3}\d/ + ab45 + 0: ab4 + bcd93 + 0: bcd9 + *** Failers +No match + 1234 +No match + a36 +No match + abcd1234 +No match + ee45 +No match + +/^(abc)*\d/ + abc45 + 0: abc4 + abcabcabc45 + 0: abcabcabc4 + 42xyz + 0: 4 + *** Failers +No match + +/^(abc)+\d/ + abc45 + 0: abc4 + abcabcabc45 + 0: abcabcabc4 + *** Failers +No match + 42xyz +No match + +/^(abc)?\d/ + abc45 + 0: abc4 + 42xyz + 0: 4 + *** Failers +No match + abcabcabc45 +No match + +/^(abc){2,3}\d/ + abcabc45 + 0: abcabc4 + abcabcabc45 + 0: abcabcabc4 + *** Failers +No match + abcabcabcabc45 +No match + abc45 +No match + 42xyz +No match + +/1(abc|xyz)2(?1)3/ + 1abc2abc3456 + 0: 1abc2abc3 + 1abc2xyz3456 + 0: 1abc2xyz3 + +/^(a*\w|ab)=(a*\w|ab)/ + ab=ab + 0: ab=ab + 1: ab=a + +/^(a*\w|ab)=(?1)/ + ab=ab + 0: ab=ab + +/^([^()]|\((?1)*\))*$/ + abc + 0: abc + a(b)c + 0: a(b)c + a(b(c))d + 0: a(b(c))d + *** Failers) +No match + a(b(c)d +No match + +/^>abc>([^()]|\((?1)*\))*abc>123abc>123abc>1(2)3abc>1(2)3abc>(1(2)3)abc>(1(2)3)a*)\d/ + aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa9876 + 0: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa9 + *** Failers +No match + aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa +No match + +/< (?: (?(R) \d++ | [^<>]*+) | (?R)) * >/x + <> + 0: <> + + 0: + hij> + 0: hij> + hij> + 0: + def> + 0: def> + + 0: <> + *** Failers +No match + abcxyz + 1 ^ ^ x + 0: abcxyz + 123abcxyz999 +--->123abcxyz999 + 1 ^ ^ x + 0: abcxyz + +/(ab|cd){3,4}/C + ababab +--->ababab + +0 ^ (ab|cd){3,4} + +1 ^ a + +4 ^ c + +2 ^^ b + +3 ^ ^ | + +1 ^ ^ a + +4 ^ ^ c + +2 ^ ^ b + +3 ^ ^ | + +1 ^ ^ a + +4 ^ ^ c + +2 ^ ^ b + +3 ^ ^ | ++12 ^ ^ + +1 ^ ^ a + +4 ^ ^ c + 0: ababab + abcdabcd +--->abcdabcd + +0 ^ (ab|cd){3,4} + +1 ^ a + +4 ^ c + +2 ^^ b + +3 ^ ^ | + +1 ^ ^ a + +4 ^ ^ c + +5 ^ ^ d + +6 ^ ^ ) + +1 ^ ^ a + +4 ^ ^ c + +2 ^ ^ b + +3 ^ ^ | ++12 ^ ^ + +1 ^ ^ a + +4 ^ ^ c + +5 ^ ^ d + +6 ^ ^ ) ++12 ^ ^ + 0: abcdabcd + 1: abcdab + abcdcdcdcdcd +--->abcdcdcdcdcd + +0 ^ (ab|cd){3,4} + +1 ^ a + +4 ^ c + +2 ^^ b + +3 ^ ^ | + +1 ^ ^ a + +4 ^ ^ c + +5 ^ ^ d + +6 ^ ^ ) + +1 ^ ^ a + +4 ^ ^ c + +5 ^ ^ d + +6 ^ ^ ) ++12 ^ ^ + +1 ^ ^ a + +4 ^ ^ c + +5 ^ ^ d + +6 ^ ^ ) ++12 ^ ^ + 0: abcdcdcd + 1: abcdcd + +/^abc/ + abcdef + 0: abc + *** Failers +No match + abcdef\B +No match + +/^(a*|xyz)/ + bcd + 0: + aaabcd + 0: aaa + 1: aa + 2: a + 3: + xyz + 0: xyz + 1: + xyz\N + 0: xyz + *** Failers + 0: + bcd\N +No match + +/xyz$/ + xyz + 0: xyz + xyz\n + 0: xyz + *** Failers +No match + xyz\Z +No match + xyz\n\Z +No match + +/xyz$/m + xyz + 0: xyz + xyz\n + 0: xyz + abcxyz\npqr + 0: xyz + abcxyz\npqr\Z + 0: xyz + xyz\n\Z + 0: xyz + *** Failers +No match + xyz\Z +No match + +/\Gabc/ + abcdef + 0: abc + defabcxyz\>3 + 0: abc + *** Failers +No match + defabcxyz +No match + +/^abcdef/ + ab\P +Partial match: ab + abcde\P +Partial match: abcde + abcdef\P + 0: abcdef + *** Failers +No match + abx\P +No match + +/^a{2,4}\d+z/ + a\P +Partial match: a + aa\P +Partial match: aa + aa2\P +Partial match: aa2 + aaa\P +Partial match: aaa + aaa23\P +Partial match: aaa23 + aaaa12345\P +Partial match: aaaa12345 + aa0z\P + 0: aa0z + aaaa4444444444444z\P + 0: aaaa4444444444444z + *** Failers +No match + az\P +No match + aaaaa\P +No match + a56\P +No match + +/^abcdef/ + abc\P +Partial match: abc + def\R + 0: def + +/(?<=foo)bar/ + xyzfo\P +No match + foob\P\>2 +Partial match: b + foobar...\R\P\>4 + 0: ar + xyzfo\P +No match + foobar\>2 + 0: bar + *** Failers +No match + xyzfo\P +No match + obar\R +No match + +/(ab*(cd|ef))+X/ + adfadadaklhlkalkajhlkjahdfasdfasdfladsfjkj\P\Z +No match + lkjhlkjhlkjhlkjhabbbbbbcdaefabbbbbbbefa\P\B\Z +Partial match: abbbbbbcdaefabbbbbbbefa + cdabbbbbbbb\P\R\B\Z +Partial match: cdabbbbbbbb + efabbbbbbbbbbbbbbbb\P\R\B\Z +Partial match: efabbbbbbbbbbbbbbbb + bbbbbbbbbbbbcdXyasdfadf\P\R\B\Z + 0: bbbbbbbbbbbbcdX + +/(a|b)/SF>testsavedregex +Compiled regex written to testsavedregex +Study data written to testsavedregex +>>aaabxyzpqrrrabbxyyyypqAzz + 0: aaabxyzpqrrrabbxyyyypqAzz + >aaaabxyzpqrrrabbxyyyypqAzz + 0: aaaabxyzpqrrrabbxyyyypqAzz + >>>>abcxyzpqrrrabbxyyyypqAzz + 0: abcxyzpqrrrabbxyyyypqAzz + *** Failers +No match + abxyzpqrrabbxyyyypqAzz +No match + abxyzpqrrrrabbxyyyypqAzz +No match + abxyzpqrrrabxyyyypqAzz +No match + aaaabcxyzzzzpqrrrabbbxyyyyyypqAzz +No match + aaaabcxyzzzzpqrrrabbbxyyypqAzz +No match + aaabcxyzpqrrrabbxyyyypqqqqqqqAzz +No match + +/^(abc){1,2}zz/ + abczz + 0: abczz + abcabczz + 0: abcabczz + *** Failers +No match + zz +No match + abcabcabczz +No match + >>abczz +No match + +/^(b+?|a){1,2}?c/ + bc + 0: bc + bbc + 0: bbc + bbbc + 0: bbbc + bac + 0: bac + bbac + 0: bbac + aac + 0: aac + abbbbbbbbbbbc + 0: abbbbbbbbbbbc + bbbbbbbbbbbac + 0: bbbbbbbbbbbac + *** Failers +No match + aaac +No match + abbbbbbbbbbbac +No match + +/^(b+|a){1,2}c/ + bc + 0: bc + bbc + 0: bbc + bbbc + 0: bbbc + bac + 0: bac + bbac + 0: bbac + aac + 0: aac + abbbbbbbbbbbc + 0: abbbbbbbbbbbc + bbbbbbbbbbbac + 0: bbbbbbbbbbbac + *** Failers +No match + aaac +No match + abbbbbbbbbbbac +No match + +/^(b+|a){1,2}?bc/ + bbc + 0: bbc + +/^(b*|ba){1,2}?bc/ + babc + 0: babc + bbabc + 0: bbabc + bababc + 0: bababc + *** Failers +No match + bababbc +No match + babababc +No match + +/^(ba|b*){1,2}?bc/ + babc + 0: babc + bbabc + 0: bbabc + bababc + 0: bababc + *** Failers +No match + bababbc +No match + babababc +No match + +/^\ca\cA\c[\c{\c:/ + \x01\x01\e;z + 0: \x01\x01\x1b;z + +/^[ab\]cde]/ + athing + 0: a + bthing + 0: b + ]thing + 0: ] + cthing + 0: c + dthing + 0: d + ething + 0: e + *** Failers +No match + fthing +No match + [thing +No match + \\thing +No match + +/^[]cde]/ + ]thing + 0: ] + cthing + 0: c + dthing + 0: d + ething + 0: e + *** Failers +No match + athing +No match + fthing +No match + +/^[^ab\]cde]/ + fthing + 0: f + [thing + 0: [ + \\thing + 0: \ + *** Failers + 0: * + athing +No match + bthing +No match + ]thing +No match + cthing +No match + dthing +No match + ething +No match + +/^[^]cde]/ + athing + 0: a + fthing + 0: f + *** Failers + 0: * + ]thing +No match + cthing +No match + dthing +No match + ething +No match + +/^\/ +  + 0: \x81 + +/^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$/ + abc!pqr=apquxz.ixr.zzz.ac.uk + 0: abc!pqr=apquxz.ixr.zzz.ac.uk + *** Failers +No match + !pqr=apquxz.ixr.zzz.ac.uk +No match + abc!=apquxz.ixr.zzz.ac.uk +No match + abc!pqr=apquxz:ixr.zzz.ac.uk +No match + abc!pqr=apquxz.ixr.zzz.ac.ukk +No match + +/:/ + Well, we need a colon: somewhere + 0: : + *** Fail if we don't +No match + +/([\da-f:]+)$/i + 0abc + 0: 0abc + abc + 0: abc + fed + 0: fed + E + 0: E + :: + 0: :: + 5f03:12C0::932e + 0: 5f03:12C0::932e + fed def + 0: def + Any old stuff + 0: ff + *** Failers +No match + 0zzz +No match + gzzz +No match + fed\x20 +No match + Any old rubbish +No match + +/^.*\.(\d{1,3})\.(\d{1,3})\.(\d{1,3})$/ + .1.2.3 + 0: .1.2.3 + A.12.123.0 + 0: A.12.123.0 + *** Failers +No match + .1.2.3333 +No match + 1.2.3 +No match + 1234.2.3 +No match + +/^(\d+)\s+IN\s+SOA\s+(\S+)\s+(\S+)\s*\(\s*$/ + 1 IN SOA non-sp1 non-sp2( + 0: 1 IN SOA non-sp1 non-sp2( + 1 IN SOA non-sp1 non-sp2 ( + 0: 1 IN SOA non-sp1 non-sp2 ( + *** Failers +No match + 1IN SOA non-sp1 non-sp2( +No match + +/^[a-zA-Z\d][a-zA-Z\d\-]*(\.[a-zA-Z\d][a-zA-z\d\-]*)*\.$/ + a. + 0: a. + Z. + 0: Z. + 2. + 0: 2. + ab-c.pq-r. + 0: ab-c.pq-r. + sxk.zzz.ac.uk. + 0: sxk.zzz.ac.uk. + x-.y-. + 0: x-.y-. + *** Failers +No match + -abc.peq. +No match + +/^\*\.[a-z]([a-z\-\d]*[a-z\d]+)?(\.[a-z]([a-z\-\d]*[a-z\d]+)?)*$/ + *.a + 0: *.a + *.b0-a + 0: *.b0-a + *.c3-b.c + 0: *.c3-b.c + *.c-a.b-c + 0: *.c-a.b-c + *** Failers +No match + *.0 +No match + *.a- +No match + *.a-b.c- +No match + *.c-a.0-c +No match + +/^(?=ab(de))(abd)(e)/ + abde + 0: abde + +/^(?!(ab)de|x)(abd)(f)/ + abdf + 0: abdf + +/^(?=(ab(cd)))(ab)/ + abcd + 0: ab + +/^[\da-f](\.[\da-f])*$/i + a.b.c.d + 0: a.b.c.d + A.B.C.D + 0: A.B.C.D + a.b.c.1.2.3.C + 0: a.b.c.1.2.3.C + +/^\".*\"\s*(;.*)?$/ + \"1234\" + 0: "1234" + \"abcd\" ; + 0: "abcd" ; + \"\" ; rhubarb + 0: "" ; rhubarb + *** Failers +No match + \"1234\" : things +No match + +/^$/ + \ + 0: + *** Failers +No match + +/ ^ a (?# begins with a) b\sc (?# then b c) $ (?# then end)/x + ab c + 0: ab c + *** Failers +No match + abc +No match + ab cde +No match + +/(?x) ^ a (?# begins with a) b\sc (?# then b c) $ (?# then end)/ + ab c + 0: ab c + *** Failers +No match + abc +No match + ab cde +No match + +/^ a\ b[c ]d $/x + a bcd + 0: a bcd + a b d + 0: a b d + *** Failers +No match + abcd +No match + ab d +No match + +/^(a(b(c)))(d(e(f)))(h(i(j)))(k(l(m)))$/ + abcdefhijklm + 0: abcdefhijklm + +/^(?:a(b(c)))(?:d(e(f)))(?:h(i(j)))(?:k(l(m)))$/ + abcdefhijklm + 0: abcdefhijklm + +/^[\w][\W][\s][\S][\d][\D][\b][\n][\c]][\022]/ + a+ Z0+\x08\n\x1d\x12 + 0: a+ Z0+\x08\x0a\x1d\x12 + +/^[.^$|()*+?{,}]+/ + .^\$(*+)|{?,?} + 0: .^$(*+)|{?,?} + 1: .^$(*+)|{?,? + 2: .^$(*+)|{?, + 3: .^$(*+)|{? + 4: .^$(*+)|{ + 5: .^$(*+)| + 6: .^$(*+) + 7: .^$(*+ + 8: .^$(* + 9: .^$( +10: .^$ +11: .^ +12: . + +/^a*\w/ + z + 0: z + az + 0: az + 1: a + aaaz + 0: aaaz + 1: aaa + 2: aa + 3: a + a + 0: a + aa + 0: aa + 1: a + aaaa + 0: aaaa + 1: aaa + 2: aa + 3: a + a+ + 0: a + aa+ + 0: aa + 1: a + +/^a*?\w/ + z + 0: z + az + 0: az + 1: a + aaaz + 0: aaaz + 1: aaa + 2: aa + 3: a + a + 0: a + aa + 0: aa + 1: a + aaaa + 0: aaaa + 1: aaa + 2: aa + 3: a + a+ + 0: a + aa+ + 0: aa + 1: a + +/^a+\w/ + az + 0: az + aaaz + 0: aaaz + 1: aaa + 2: aa + aa + 0: aa + aaaa + 0: aaaa + 1: aaa + 2: aa + aa+ + 0: aa + +/^a+?\w/ + az + 0: az + aaaz + 0: aaaz + 1: aaa + 2: aa + aa + 0: aa + aaaa + 0: aaaa + 1: aaa + 2: aa + aa+ + 0: aa + +/^\d{8}\w{2,}/ + 1234567890 + 0: 1234567890 + 12345678ab + 0: 12345678ab + 12345678__ + 0: 12345678__ + *** Failers +No match + 1234567 +No match + +/^[aeiou\d]{4,5}$/ + uoie + 0: uoie + 1234 + 0: 1234 + 12345 + 0: 12345 + aaaaa + 0: aaaaa + *** Failers +No match + 123456 +No match + +/^[aeiou\d]{4,5}?/ + uoie + 0: uoie + 1234 + 0: 1234 + 12345 + 0: 12345 + 1: 1234 + aaaaa + 0: aaaaa + 1: aaaa + 123456 + 0: 12345 + 1: 1234 + +/^From +([^ ]+) +[a-zA-Z][a-zA-Z][a-zA-Z] +[a-zA-Z][a-zA-Z][a-zA-Z] +[0-9]?[0-9] +[0-9][0-9]:[0-9][0-9]/ + From abcd Mon Sep 01 12:33:02 1997 + 0: From abcd Mon Sep 01 12:33 + +/^From\s+\S+\s+([a-zA-Z]{3}\s+){2}\d{1,2}\s+\d\d:\d\d/ + From abcd Mon Sep 01 12:33:02 1997 + 0: From abcd Mon Sep 01 12:33 + From abcd Mon Sep 1 12:33:02 1997 + 0: From abcd Mon Sep 1 12:33 + *** Failers +No match + From abcd Sep 01 12:33:02 1997 +No match + +/^12.34/s + 12\n34 + 0: 12\x0a34 + 12\r34 + 0: 12\x0d34 + +/\w+(?=\t)/ + the quick brown\t fox + 0: brown + +/foo(?!bar)(.*)/ + foobar is foolish see? + 0: foolish see? + 1: foolish see + 2: foolish se + 3: foolish s + 4: foolish + 5: foolish + 6: foolis + 7: fooli + 8: fool + 9: foo + +/(?:(?!foo)...|^.{0,2})bar(.*)/ + foobar crowbar etc + 0: rowbar etc + 1: rowbar et + 2: rowbar e + 3: rowbar + 4: rowbar + barrel + 0: barrel + 1: barre + 2: barr + 3: bar + 2barrel + 0: 2barrel + 1: 2barre + 2: 2barr + 3: 2bar + A barrel + 0: A barrel + 1: A barre + 2: A barr + 3: A bar + +/^(\D*)(?=\d)(?!123)/ + abc456 + 0: abc + *** Failers +No match + abc123 +No match + +/^1234(?# test newlines + inside)/ + 1234 + 0: 1234 + +/^1234 #comment in extended re + /x + 1234 + 0: 1234 + +/#rhubarb + abcd/x + abcd + 0: abcd + +/^abcd#rhubarb/x + abcd + 0: abcd + +/(?!^)abc/ + the abc + 0: abc + *** Failers +No match + abc +No match + +/(?=^)abc/ + abc + 0: abc + *** Failers +No match + the abc +No match + +/^[ab]{1,3}(ab*|b)/ + aabbbbb + 0: aabbbbb + 1: aabbbb + 2: aabbb + 3: aabb + 4: aab + 5: aa + +/^[ab]{1,3}?(ab*|b)/ + aabbbbb + 0: aabbbbb + 1: aabbbb + 2: aabbb + 3: aabb + 4: aab + 5: aa + +/^[ab]{1,3}?(ab*?|b)/ + aabbbbb + 0: aabbbbb + 1: aabbbb + 2: aabbb + 3: aabb + 4: aab + 5: aa + +/^[ab]{1,3}(ab*?|b)/ + aabbbbb + 0: aabbbbb + 1: aabbbb + 2: aabbb + 3: aabb + 4: aab + 5: aa + +/ (?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* # optional leading comment +(?: (?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| +" (?: # opening quote... +[^\\\x80-\xff\n\015"] # Anything except backslash and quote +| # or +\\ [^\x80-\xff] # Escaped something (something != CR) +)* " # closing quote +) # initial word +(?: (?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* \. (?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* (?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| +" (?: # opening quote... +[^\\\x80-\xff\n\015"] # Anything except backslash and quote +| # or +\\ [^\x80-\xff] # Escaped something (something != CR) +)* " # closing quote +) )* # further okay, if led by a period +(?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* @ (?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* (?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| \[ # [ +(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff +\] # ] +) # initial subdomain +(?: # +(?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* \. # if led by a period... +(?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* (?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| \[ # [ +(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff +\] # ] +) # ...further okay +)* +# address +| # or +(?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| +" (?: # opening quote... +[^\\\x80-\xff\n\015"] # Anything except backslash and quote +| # or +\\ [^\x80-\xff] # Escaped something (something != CR) +)* " # closing quote +) # one word, optionally followed by.... +(?: +[^()<>@,;:".\\\[\]\x80-\xff\000-\010\012-\037] | # atom and space parts, or... +\( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) | # comments, or... + +" (?: # opening quote... +[^\\\x80-\xff\n\015"] # Anything except backslash and quote +| # or +\\ [^\x80-\xff] # Escaped something (something != CR) +)* " # closing quote +# quoted strings +)* +< (?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* # leading < +(?: @ (?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* (?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| \[ # [ +(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff +\] # ] +) # initial subdomain +(?: # +(?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* \. # if led by a period... +(?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* (?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| \[ # [ +(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff +\] # ] +) # ...further okay +)* + +(?: (?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* , (?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* @ (?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* (?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| \[ # [ +(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff +\] # ] +) # initial subdomain +(?: # +(?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* \. # if led by a period... +(?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* (?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| \[ # [ +(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff +\] # ] +) # ...further okay +)* +)* # further okay, if led by comma +: # closing colon +(?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* )? # optional route +(?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| +" (?: # opening quote... +[^\\\x80-\xff\n\015"] # Anything except backslash and quote +| # or +\\ [^\x80-\xff] # Escaped something (something != CR) +)* " # closing quote +) # initial word +(?: (?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* \. (?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* (?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| +" (?: # opening quote... +[^\\\x80-\xff\n\015"] # Anything except backslash and quote +| # or +\\ [^\x80-\xff] # Escaped something (something != CR) +)* " # closing quote +) )* # further okay, if led by a period +(?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* @ (?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* (?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| \[ # [ +(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff +\] # ] +) # initial subdomain +(?: # +(?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* \. # if led by a period... +(?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* (?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| \[ # [ +(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff +\] # ] +) # ...further okay +)* +# address spec +(?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* > # trailing > +# name and address +) (?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* # optional trailing comment +/x + Alan Other + 0: Alan Other + + 0: address@hidden + 1: address@hidden + address@hidden + 0: address@hidden + 1: address@hidden + \"A. Other\" (a comment) + 0: "A. Other" (a comment) + 1: "A. Other" + 2: "A. Other" + A. Other (a comment) + 0: Other (a comment) + 1: Other + 2: Other + \"/s=user/ou=host/o=place/prmd=uu.yy/admd= /c=gb/\"address@hidden + 0: "/s=user/ou=host/o=place/prmd=uu.yy/admd= /c=gb/"@x400-re.lay + 1: "/s=user/ou=host/o=place/prmd=uu.yy/admd= /c=gb/"@x400-re + A missing angle @,;:".\\\[\]\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: address@hidden + 1: address@hidden + address@hidden + 0: address@hidden + 1: address@hidden + \"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/\"address@hidden + 0: "/s=user/ou=host/o=place/prmd=uu.yy/admd= /c=gb/"@x400-re.lay + 1: "/s=user/ou=host/o=place/prmd=uu.yy/admd= /c=gb/"@x400-re + A missing angle + a\rb + 0: a\x0db + *** Failers +No match + a\nb +No match + +/abc$/ + abc + 0: abc + abc\n + 0: abc + *** Failers +No match + abc\ndef +No match + +/(abc)\123/ + abc\x53 + 0: abcS + +/(abc)\223/ + abc\x93 + 0: abc\x93 + +/(abc)\323/ + abc\xd3 + 0: abc\xd3 + +/(abc)\100/ + abc\x40 + 0: abc@ + abc\100 + 0: abc@ + +/(abc)\1000/ + abc\x400 + 0: address@hidden + abc\x40\x30 + 0: address@hidden + abc\1000 + 0: address@hidden + abc\100\x30 + 0: address@hidden + abc\100\060 + 0: address@hidden + abc\100\60 + 0: address@hidden + +/abc\81/ + abc\081 + 0: abc\x0081 + abc\0\x38\x31 + 0: abc\x0081 + +/abc\91/ + abc\091 + 0: abc\x0091 + abc\0\x39\x31 + 0: abc\x0091 + +/(a)(b)(c)(d)(e)(f)(g)(h)(i)(j)(k)\12\123/ + abcdefghijk\12S + 0: abcdefghijk\x0aS + +/ab\idef/ + abidef + 0: abidef + +/a{0}bc/ + bc + 0: bc + +/(a|(bc)){0,0}?xyz/ + xyz + 0: xyz + +/abc[\10]de/ + abc\010de + 0: abc\x08de + +/abc[\1]de/ + abc\1de + 0: abc\x01de + +/(abc)[\1]de/ + abc\1de + 0: abc\x01de + +/(?s)a.b/ + a\nb + 0: a\x0ab + +/^([^a])([^\b])([^c]*)([^d]{3,4})/ + baNOTccccd + 0: baNOTcccc + 1: baNOTccc + 2: baNOTcc + 3: baNOTc + 4: baNOT + baNOTcccd + 0: baNOTccc + 1: baNOTcc + 2: baNOTc + 3: baNOT + baNOTccd + 0: baNOTcc + 1: baNOTc + 2: baNOT + bacccd + 0: baccc + *** Failers + 0: *** Failers + 1: *** Failer + 2: *** Faile + 3: *** Fail + 4: *** Fai + 5: *** Fa + 6: *** F + anything +No match + b\bc +No match + baccd +No match + +/[^a]/ + Abc + 0: A + +/[^a]/i + Abc + 0: b + +/[^a]+/ + AAAaAbc + 0: AAA + 1: AA + 2: A + +/[^a]+/i + AAAaAbc + 0: bc + 1: b + +/[^a]+/ + bbb\nccc + 0: bbb\x0accc + 1: bbb\x0acc + 2: bbb\x0ac + 3: bbb\x0a + 4: bbb + 5: bb + 6: b + +/[^k]$/ + abc + 0: c + *** Failers + 0: s + abk +No match + +/[^k]{2,3}$/ + abc + 0: abc + kbc + 0: bc + kabc + 0: abc + *** Failers + 0: ers + abk +No match + akb +No match + akk +No match + +/^\d{8,address@hidden/ + address@hidden + 0: address@hidden + address@hidden + 0: address@hidden + *** Failers +No match + address@hidden +No match + address@hidden +No match + +/[^a]/ + aaaabcd + 0: b + aaAabcd + 0: A + +/[^a]/i + aaaabcd + 0: b + aaAabcd + 0: b + +/[^az]/ + aaaabcd + 0: b + aaAabcd + 0: A + +/[^az]/i + aaaabcd + 0: b + aaAabcd + 0: b + +/\000\001\002\003\004\005\006\007\010\011\012\013\014\015\016\017\020\021\022\023\024\025\026\027\030\031\032\033\034\035\036\037\040\041\042\043\044\045\046\047\050\051\052\053\054\055\056\057\060\061\062\063\064\065\066\067\070\071\072\073\074\075\076\077\100\101\102\103\104\105\106\107\110\111\112\113\114\115\116\117\120\121\122\123\124\125\126\127\130\131\132\133\134\135\136\137\140\141\142\143\144\145\146\147\150\151\152\153\154\155\156\157\160\161\162\163\164\165\166\167\170\171\172\173\174\175\176\177\200\201\202\203\204\205\206\207\210\211\212\213\214\215\216\217\220\221\222\223\224\225\226\227\230\231\232\233\234\235\236\237\240\241\242\243\244\245\246\247\250\251\252\253\254\255\256\257\260\261\262\263\264\265\266\267\270\271\272\273\274\275\276\277\300\301\302\303\304\305\306\307\310\311\312\313\314\315\316\317\320\321\322\323\324\325\326\327\330\331\332\333\334\335\336\337\340\341\342\343\344\345\346\347\350\351\352\353\354\355\356\357\360\361\362\363\364\365\366 \367\370\371\372\373\374\375\376\377/ + \000\001\002\003\004\005\006\007\010\011\012\013\014\015\016\017\020\021\022\023\024\025\026\027\030\031\032\033\034\035\036\037\040\041\042\043\044\045\046\047\050\051\052\053\054\055\056\057\060\061\062\063\064\065\066\067\070\071\072\073\074\075\076\077\100\101\102\103\104\105\106\107\110\111\112\113\114\115\116\117\120\121\122\123\124\125\126\127\130\131\132\133\134\135\136\137\140\141\142\143\144\145\146\147\150\151\152\153\154\155\156\157\160\161\162\163\164\165\166\167\170\171\172\173\174\175\176\177\200\201\202\203\204\205\206\207\210\211\212\213\214\215\216\217\220\221\222\223\224\225\226\227\230\231\232\233\234\235\236\237\240\241\242\243\244\245\246\247\250\251\252\253\254\255\256\257\260\261\262\263\264\265\266\267\270\271\272\273\274\275\276\277\300\301\302\303\304\305\306\307\310\311\312\313\314\315\316\317\320\321\322\323\324\325\326\327\330\331\332\333\334\335\336\337\340\341\342\343\344\345\346\347\350\351\352\353\354\355\356\357\360\361\362\363\364\365\366 \367\370\371\372\373\374\375\376\377 + 0: \x00\x01\x02\x03\x04\x05\x06\x07\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f\x10\x11\x12\x13\x14\x15\x16\x17\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f !"#$%&'()*+,-./0123456789:;<=>address@hidden|}~\x7f\x80\x81\x82\x83\x84\x85\x86\x87\x88\x89\x8a\x8b\x8c\x8d\x8e\x8f\x90\x91\x92\x93\x94\x95\x96\x97\x98\x99\x9a\x9b\x9c\x9d\x9e\x9f\xa0\xa1\xa2\xa3\xa4\xa5\xa6\xa7\xa8\xa9\xaa\xab\xac\xad\xae\xaf\xb0\xb1\xb2\xb3\xb4\xb5\xb6\xb7\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf\xc0\xc1\xc2\xc3\xc4\xc5\xc6\xc7\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf\xd0\xd1\xd2\xd3\xd4\xd5\xd6\xd7\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7\xe8\xe9\xea\xeb\xec\xed\xee\xef\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff + +/P[^*]TAIRE[^*]{1,6}?LL/ + xxxxxxxxxxxPSTAIREISLLxxxxxxxxx + 0: PSTAIREISLL + +/P[^*]TAIRE[^*]{1,}?LL/ + xxxxxxxxxxxPSTAIREISLLxxxxxxxxx + 0: PSTAIREISLL + +/(\.\d\d[1-9]?)\d+/ + 1.230003938 + 0: .230003938 + 1: .23000393 + 2: .2300039 + 3: .230003 + 4: .23000 + 5: .2300 + 6: .230 + 1.875000282 + 0: .875000282 + 1: .87500028 + 2: .8750002 + 3: .875000 + 4: .87500 + 5: .8750 + 6: .875 + 1.235 + 0: .235 + +/(\.\d\d((?=0)|\d(?=\d)))/ + 1.230003938 + 0: .230 + 1: .23 + 1.875000282 + 0: .875 + *** Failers +No match + 1.235 +No match + +/a(?)b/ + ab + 0: ab + +/\b(foo)\s+(\w+)/i + Food is on the foo table + 0: foo table + 1: foo tabl + 2: foo tab + 3: foo ta + 4: foo t + +/foo(.*)bar/ + The food is under the bar in the barn. + 0: food is under the bar in the bar + 1: food is under the bar + +/foo(.*?)bar/ + The food is under the bar in the barn. + 0: food is under the bar in the bar + 1: food is under the bar + +/(.*)(\d*)/ + I have 2 numbers: 53147 +Matched, but too many subsidiary matches + 0: I have 2 numbers: 53147 + 1: I have 2 numbers: 5314 + 2: I have 2 numbers: 531 + 3: I have 2 numbers: 53 + 4: I have 2 numbers: 5 + 5: I have 2 numbers: + 6: I have 2 numbers: + 7: I have 2 numbers + 8: I have 2 number + 9: I have 2 numbe +10: I have 2 numb +11: I have 2 num +12: I have 2 nu +13: I have 2 n +14: I have 2 +15: I have 2 +16: I have +17: I have +18: I hav +19: I ha +20: I h +21: I + +/(.*)(\d+)/ + I have 2 numbers: 53147 + 0: I have 2 numbers: 53147 + 1: I have 2 numbers: 5314 + 2: I have 2 numbers: 531 + 3: I have 2 numbers: 53 + 4: I have 2 numbers: 5 + 5: I have 2 + +/(.*?)(\d*)/ + I have 2 numbers: 53147 +Matched, but too many subsidiary matches + 0: I have 2 numbers: 53147 + 1: I have 2 numbers: 5314 + 2: I have 2 numbers: 531 + 3: I have 2 numbers: 53 + 4: I have 2 numbers: 5 + 5: I have 2 numbers: + 6: I have 2 numbers: + 7: I have 2 numbers + 8: I have 2 number + 9: I have 2 numbe +10: I have 2 numb +11: I have 2 num +12: I have 2 nu +13: I have 2 n +14: I have 2 +15: I have 2 +16: I have +17: I have +18: I hav +19: I ha +20: I h +21: I + +/(.*?)(\d+)/ + I have 2 numbers: 53147 + 0: I have 2 numbers: 53147 + 1: I have 2 numbers: 5314 + 2: I have 2 numbers: 531 + 3: I have 2 numbers: 53 + 4: I have 2 numbers: 5 + 5: I have 2 + +/(.*)(\d+)$/ + I have 2 numbers: 53147 + 0: I have 2 numbers: 53147 + +/(.*?)(\d+)$/ + I have 2 numbers: 53147 + 0: I have 2 numbers: 53147 + +/(.*)\b(\d+)$/ + I have 2 numbers: 53147 + 0: I have 2 numbers: 53147 + +/(.*\D)(\d+)$/ + I have 2 numbers: 53147 + 0: I have 2 numbers: 53147 + +/^\D*(?!123)/ + ABC123 + 0: AB + 1: A + 2: + +/^(\D*)(?=\d)(?!123)/ + ABC445 + 0: ABC + *** Failers +No match + ABC123 +No match + +/^[W-]46]/ + W46]789 + 0: W46] + -46]789 + 0: -46] + *** Failers +No match + Wall +No match + Zebra +No match + 42 +No match + [abcd] +No match + ]abcd[ +No match + +/^[W-\]46]/ + W46]789 + 0: W + Wall + 0: W + Zebra + 0: Z + Xylophone + 0: X + 42 + 0: 4 + [abcd] + 0: [ + ]abcd[ + 0: ] + \\backslash + 0: \ + *** Failers +No match + -46]789 +No match + well +No match + +/\d\d\/\d\d\/\d\d\d\d/ + 01/01/2000 + 0: 01/01/2000 + +/word (?:[a-zA-Z0-9]+ ){0,10}otherword/ + word cat dog elephant mussel cow horse canary baboon snake shark otherword + 0: word cat dog elephant mussel cow horse canary baboon snake shark otherword + word cat dog elephant mussel cow horse canary baboon snake shark +No match + +/word (?:[a-zA-Z0-9]+ ){0,300}otherword/ + word cat dog elephant mussel cow horse canary baboon snake shark the quick brown fox and the lazy dog and several other words getting close to thirty by now I hope +No match + +/^(a){0,0}/ + bcd + 0: + abc + 0: + aab + 0: + +/^(a){0,1}/ + bcd + 0: + abc + 0: a + 1: + aab + 0: a + 1: + +/^(a){0,2}/ + bcd + 0: + abc + 0: a + 1: + aab + 0: aa + 1: a + 2: + +/^(a){0,3}/ + bcd + 0: + abc + 0: a + 1: + aab + 0: aa + 1: a + 2: + aaa + 0: aaa + 1: aa + 2: a + 3: + +/^(a){0,}/ + bcd + 0: + abc + 0: a + 1: + aab + 0: aa + 1: a + 2: + aaa + 0: aaa + 1: aa + 2: a + 3: + aaaaaaaa + 0: aaaaaaaa + 1: aaaaaaa + 2: aaaaaa + 3: aaaaa + 4: aaaa + 5: aaa + 6: aa + 7: a + 8: + +/^(a){1,1}/ + bcd +No match + abc + 0: a + aab + 0: a + +/^(a){1,2}/ + bcd +No match + abc + 0: a + aab + 0: aa + 1: a + +/^(a){1,3}/ + bcd +No match + abc + 0: a + aab + 0: aa + 1: a + aaa + 0: aaa + 1: aa + 2: a + +/^(a){1,}/ + bcd +No match + abc + 0: a + aab + 0: aa + 1: a + aaa + 0: aaa + 1: aa + 2: a + aaaaaaaa + 0: aaaaaaaa + 1: aaaaaaa + 2: aaaaaa + 3: aaaaa + 4: aaaa + 5: aaa + 6: aa + 7: a + +/.*\.gif/ + borfle\nbib.gif\nno + 0: bib.gif + +/.{0,}\.gif/ + borfle\nbib.gif\nno + 0: bib.gif + +/.*\.gif/m + borfle\nbib.gif\nno + 0: bib.gif + +/.*\.gif/s + borfle\nbib.gif\nno + 0: borfle\x0abib.gif + +/.*\.gif/ms + borfle\nbib.gif\nno + 0: borfle\x0abib.gif + +/.*$/ + borfle\nbib.gif\nno + 0: no + +/.*$/m + borfle\nbib.gif\nno + 0: borfle + +/.*$/s + borfle\nbib.gif\nno + 0: borfle\x0abib.gif\x0ano + +/.*$/ms + borfle\nbib.gif\nno + 0: borfle\x0abib.gif\x0ano + 1: borfle\x0abib.gif + 2: borfle + +/.*$/ + borfle\nbib.gif\nno\n + 0: no + +/.*$/m + borfle\nbib.gif\nno\n + 0: borfle + +/.*$/s + borfle\nbib.gif\nno\n + 0: borfle\x0abib.gif\x0ano\x0a + 1: borfle\x0abib.gif\x0ano + +/.*$/ms + borfle\nbib.gif\nno\n + 0: borfle\x0abib.gif\x0ano\x0a + 1: borfle\x0abib.gif\x0ano + 2: borfle\x0abib.gif + 3: borfle + +/(.*X|^B)/ + abcde\n1234Xyz + 0: 1234X + BarFoo + 0: B + *** Failers +No match + abcde\nBar +No match + +/(.*X|^B)/m + abcde\n1234Xyz + 0: 1234X + BarFoo + 0: B + abcde\nBar + 0: B + +/(.*X|^B)/s + abcde\n1234Xyz + 0: abcde\x0a1234X + BarFoo + 0: B + *** Failers +No match + abcde\nBar +No match + +/(.*X|^B)/ms + abcde\n1234Xyz + 0: abcde\x0a1234X + BarFoo + 0: B + abcde\nBar + 0: B + +/(?s)(.*X|^B)/ + abcde\n1234Xyz + 0: abcde\x0a1234X + BarFoo + 0: B + *** Failers +No match + abcde\nBar +No match + +/(?s:.*X|^B)/ + abcde\n1234Xyz + 0: abcde\x0a1234X + BarFoo + 0: B + *** Failers +No match + abcde\nBar +No match + +/^.*B/ + **** Failers +No match + abc\nB +No match + +/(?s)^.*B/ + abc\nB + 0: abc\x0aB + +/(?m)^.*B/ + abc\nB + 0: B + +/(?ms)^.*B/ + abc\nB + 0: abc\x0aB + +/(?ms)^B/ + abc\nB + 0: B + +/(?s)B$/ + B\n + 0: B + +/^[0-9][0-9][0-9][0-9][0-9][0-9][0-9][0-9][0-9][0-9][0-9][0-9]/ + 123456654321 + 0: 123456654321 + +/^\d\d\d\d\d\d\d\d\d\d\d\d/ + 123456654321 + 0: 123456654321 + +/^[\d][\d][\d][\d][\d][\d][\d][\d][\d][\d][\d][\d]/ + 123456654321 + 0: 123456654321 + +/^[abc]{12}/ + abcabcabcabc + 0: abcabcabcabc + +/^[a-c]{12}/ + abcabcabcabc + 0: abcabcabcabc + +/^(a|b|c){12}/ + abcabcabcabc + 0: abcabcabcabc + +/^[abcdefghijklmnopqrstuvwxy0123456789]/ + n + 0: n + *** Failers +No match + z +No match + +/abcde{0,0}/ + abcd + 0: abcd + *** Failers +No match + abce +No match + +/ab[cd]{0,0}e/ + abe + 0: abe + *** Failers +No match + abcde +No match + +/ab(c){0,0}d/ + abd + 0: abd + *** Failers +No match + abcd +No match + +/a(b*)/ + a + 0: a + ab + 0: ab + 1: a + abbbb + 0: abbbb + 1: abbb + 2: abb + 3: ab + 4: a + *** Failers + 0: a + bbbbb +No match + +/ab\d{0}e/ + abe + 0: abe + *** Failers +No match + ab1e +No match + +/"([^\\"]+|\\.)*"/ + the \"quick\" brown fox + 0: "quick" + \"the \\\"quick\\\" brown fox\" + 0: "the \"quick\" brown fox" + +/.*?/g+ + abc + 0: abc + 0+ + 1: ab + 2: a + 3: + 0: + 0+ + +/\b/g+ + abc + 0: + 0+ abc + 0: + 0+ + +/\b/+g + abc + 0: + 0+ abc + 0: + 0+ + +//g + abc + 0: + 0: + 0: + 0: + +/]{0,})>]{0,})>([\d]{0,}\.)(.*)((
([\w\W\s\d][^<>]{0,})|[\s]{0,}))<\/a><\/TD>]{0,})>([\w\W\s\d][^<>]{0,})<\/TD>]{0,})>([\w\W\s\d][^<>]{0,})<\/TD><\/TR>/is + 43.Word Processor
(N-1286)Lega lstaff.comCA - Statewide + 0: 43.Word Processor
(N-1286)Lega lstaff.comCA - Statewide + +/a[^a]b/ + acb + 0: acb + a\nb + 0: a\x0ab + +/a.b/ + acb + 0: acb + *** Failers +No match + a\nb +No match + +/a[^a]b/s + acb + 0: acb + a\nb + 0: a\x0ab + +/a.b/s + acb + 0: acb + a\nb + 0: a\x0ab + +/^(b+?|a){1,2}?c/ + bac + 0: bac + bbac + 0: bbac + bbbac + 0: bbbac + bbbbac + 0: bbbbac + bbbbbac + 0: bbbbbac + +/^(b+|a){1,2}?c/ + bac + 0: bac + bbac + 0: bbac + bbbac + 0: bbbac + bbbbac + 0: bbbbac + bbbbbac + 0: bbbbbac + +/(?!\A)x/m + x\nb\n +No match + a\bx\n + 0: x + +/\x0{ab}/ + \0{ab} + 0: \x00{ab} + +/(A|B)*?CD/ + CD + 0: CD + +/(A|B)*CD/ + CD + 0: CD + +/(?.*/)foo" + /this/is/a/very/long/line/in/deed/with/very/many/slashes/in/it/you/see/ +No match + +"(?>.*/)foo" + /this/is/a/very/long/line/in/deed/with/very/many/slashes/in/and/foo + 0: /this/is/a/very/long/line/in/deed/with/very/many/slashes/in/and/foo + +/(?>(\.\d\d[1-9]?))\d+/ + 1.230003938 + 0: .230003938 + 1: .23000393 + 2: .2300039 + 3: .230003 + 4: .23000 + 5: .2300 + 6: .230 + 1.875000282 + 0: .875000282 + 1: .87500028 + 2: .8750002 + 3: .875000 + 4: .87500 + 5: .8750 + *** Failers +No match + 1.235 +No match + +/^((?>\w+)|(?>\s+))*$/ + now is the time for all good men to come to the aid of the party + 0: now is the time for all good men to come to the aid of the party + *** Failers +No match + this is not a line with only words and spaces! +No match + +/(\d+)(\w)/ + 12345a + 0: 12345a + 1: 12345 + 2: 1234 + 3: 123 + 4: 12 + 12345+ + 0: 12345 + 1: 1234 + 2: 123 + 3: 12 + +/((?>\d+))(\w)/ + 12345a + 0: 12345a + *** Failers +No match + 12345+ +No match + +/(?>a+)b/ + aaab + 0: aaab + +/((?>a+)b)/ + aaab + 0: aaab + +/(?>(a+))b/ + aaab + 0: aaab + +/(?>b)+/ + aaabbbccc + 0: bbb + 1: bb + 2: b + +/(?>a+|b+|c+)*c/ + aaabbbbccccd + 0: aaabbbbcccc + 1: aaabbbbc + +/(a+|b+|c+)*c/ + aaabbbbccccd + 0: aaabbbbcccc + 1: aaabbbbccc + 2: aaabbbbcc + 3: aaabbbbc + +/((?>[^()]+)|\([^()]*\))+/ + ((abc(ade)ufh()()x + 0: abc(ade)ufh()()x + 1: abc(ade)ufh()() + 2: abc(ade)ufh() + 3: abc(ade)ufh + 4: abc(ade) + 5: abc + +/\(((?>[^()]+)|\([^()]+\))+\)/ + (abc) + 0: (abc) + (abc(def)xyz) + 0: (abc(def)xyz) + *** Failers +No match + ((()aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa +No match + +/a(?-i)b/i + ab + 0: ab + Ab + 0: Ab + *** Failers +No match + aB +No match + AB +No match + +/(a (?x)b c)d e/ + a bcd e + 0: a bcd e + *** Failers +No match + a b cd e +No match + abcd e +No match + a bcde +No match + +/(a b(?x)c d (?-x)e f)/ + a bcde f + 0: a bcde f + *** Failers +No match + abcdef +No match + +/(a(?i)b)c/ + abc + 0: abc + aBc + 0: aBc + *** Failers +No match + abC +No match + aBC +No match + Abc +No match + ABc +No match + ABC +No match + AbC +No match + +/a(?i:b)c/ + abc + 0: abc + aBc + 0: aBc + *** Failers +No match + ABC +No match + abC +No match + aBC +No match + +/a(?i:b)*c/ + aBc + 0: aBc + aBBc + 0: aBBc + *** Failers +No match + aBC +No match + aBBC +No match + +/a(?=b(?i)c)\w\wd/ + abcd + 0: abcd + abCd + 0: abCd + *** Failers +No match + aBCd +No match + abcD +No match + +/(?s-i:more.*than).*million/i + more than million + 0: more than million + more than MILLION + 0: more than MILLION + more \n than Million + 0: more \x0a than Million + *** Failers +No match + MORE THAN MILLION +No match + more \n than \n million +No match + +/(?:(?s-i)more.*than).*million/i + more than million + 0: more than million + more than MILLION + 0: more than MILLION + more \n than Million + 0: more \x0a than Million + *** Failers +No match + MORE THAN MILLION +No match + more \n than \n million +No match + +/(?>a(?i)b+)+c/ + abc + 0: abc + aBbc + 0: aBbc + aBBc + 0: aBBc + *** Failers +No match + Abc +No match + abAb +No match + abbC +No match + +/(?=a(?i)b)\w\wc/ + abc + 0: abc + aBc + 0: aBc + *** Failers +No match + Ab +No match + abC +No match + aBC +No match + +/(?<=a(?i)b)(\w\w)c/ + abxxc + 0: xxc + aBxxc + 0: xxc + *** Failers +No match + Abxxc +No match + ABxxc +No match + abxxC +No match + +/^(?(?=abc)\w{3}:|\d\d)$/ + abc: + 0: abc: + 12 + 0: 12 + *** Failers +No match + 123 +No match + xyz +No match + +/^(?(?!abc)\d\d|\w{3}:)$/ + abc: + 0: abc: + 12 + 0: 12 + *** Failers +No match + 123 +No match + xyz +No match + +/(?(?<=foo)bar|cat)/ + foobar + 0: bar + cat + 0: cat + fcat + 0: cat + focat + 0: cat + *** Failers +No match + foocat +No match + +/(?(?a*)*/ + a + 0: a + 1: + aa + 0: aa + 1: + aaaa + 0: aaaa + 1: + +/(abc|)+/ + abc + 0: abc + 1: + abcabc + 0: abcabc + 1: abc + 2: + abcabcabc + 0: abcabcabc + 1: abcabc + 2: abc + 3: + xyz + 0: + +/([a]*)*/ + a + 0: a + 1: + aaaaa + 0: aaaaa + 1: aaaa + 2: aaa + 3: aa + 4: a + 5: + +/([ab]*)*/ + a + 0: a + 1: + b + 0: b + 1: + ababab + 0: ababab + 1: ababa + 2: abab + 3: aba + 4: ab + 5: a + 6: + aaaabcde + 0: aaaab + 1: aaaa + 2: aaa + 3: aa + 4: a + 5: + bbbb + 0: bbbb + 1: bbb + 2: bb + 3: b + 4: + +/([^a]*)*/ + b + 0: b + 1: + bbbb + 0: bbbb + 1: bbb + 2: bb + 3: b + 4: + aaa + 0: + +/([^ab]*)*/ + cccc + 0: cccc + 1: ccc + 2: cc + 3: c + 4: + abab + 0: + +/([a]*?)*/ + a + 0: a + 1: + aaaa + 0: aaaa + 1: aaa + 2: aa + 3: a + 4: + +/([ab]*?)*/ + a + 0: a + 1: + b + 0: b + 1: + abab + 0: abab + 1: aba + 2: ab + 3: a + 4: + baba + 0: baba + 1: bab + 2: ba + 3: b + 4: + +/([^a]*?)*/ + b + 0: b + 1: + bbbb + 0: bbbb + 1: bbb + 2: bb + 3: b + 4: + aaa + 0: + +/([^ab]*?)*/ + c + 0: c + 1: + cccc + 0: cccc + 1: ccc + 2: cc + 3: c + 4: + baba + 0: + +/(?>a*)*/ + a + 0: a + 1: + aaabcde + 0: aaa + 1: + +/((?>a*))*/ + aaaaa + 0: aaaaa + 1: + aabbaa + 0: aa + 1: + +/((?>a*?))*/ + aaaaa + 0: aaaaa + 1: + aabbaa + 0: aa + 1: + +/(?(?=[^a-z]+[a-z]) \d{2}-[a-z]{3}-\d{2} | \d{2}-\d{2}-\d{2} ) /x + 12-sep-98 + 0: 12-sep-98 + 12-09-98 + 0: 12-09-98 + *** Failers +No match + sep-12-98 +No match + +/(?i:saturday|sunday)/ + saturday + 0: saturday + sunday + 0: sunday + Saturday + 0: Saturday + Sunday + 0: Sunday + SATURDAY + 0: SATURDAY + SUNDAY + 0: SUNDAY + SunDay + 0: SunDay + +/(a(?i)bc|BB)x/ + abcx + 0: abcx + aBCx + 0: aBCx + bbx + 0: bbx + BBx + 0: BBx + *** Failers +No match + abcX +No match + aBCX +No match + bbX +No match + BBX +No match + +/^([ab](?i)[cd]|[ef])/ + ac + 0: ac + aC + 0: aC + bD + 0: bD + elephant + 0: e + Europe + 0: E + frog + 0: f + France + 0: F + *** Failers +No match + Africa +No match + +/^(ab|a(?i)[b-c](?m-i)d|x(?i)y|z)/ + ab + 0: ab + aBd + 0: aBd + xy + 0: xy + xY + 0: xY + zebra + 0: z + Zambesi + 0: Z + *** Failers +No match + aCD +No match + XY +No match + +/(?<=foo\n)^bar/m + foo\nbar + 0: bar + *** Failers +No match + bar +No match + baz\nbar +No match + +/(?<=(?]&/ + <&OUT + 0: <& + +/(?:(f)(o)(o)|(b)(a)(r))*/ + foobar + 0: foobar + 1: foo + 2: + +/(?<=a)b/ + ab + 0: b + *** Failers +No match + cb +No match + b +No match + +/(?a+)ab/ + +/(?>a+)b/ + aaab + 0: aaab + +/([[:]+)/ + a:[b]: + 0: :[ + 1: : + +/([[=]+)/ + a=[b]= + 0: =[ + 1: = + +/([[.]+)/ + a.[b]. + 0: .[ + 1: . + +/((?>a+)b)/ + aaab + 0: aaab + +/(?>(a+))b/ + aaab + 0: aaab + +/((?>[^()]+)|\([^()]*\))+/ + ((abc(ade)ufh()()x + 0: abc(ade)ufh()()x + 1: abc(ade)ufh()() + 2: abc(ade)ufh() + 3: abc(ade)ufh + 4: abc(ade) + 5: abc + +/a\Z/ + *** Failers +No match + aaab +No match + a\nb\n +No match + +/b\Z/ + a\nb\n + 0: b + +/b\z/ + +/b\Z/ + a\nb + 0: b + +/b\z/ + a\nb + 0: b + *** Failers +No match + +/(?>.*)(?<=(abcd|wxyz))/ + alphabetabcd + 0: alphabetabcd + endingwxyz + 0: endingwxyz + *** Failers +No match + a rather long string that doesn't end with one of them +No match + +/word (?>(?:(?!otherword)[a-zA-Z0-9]+ ){0,30})otherword/ + word cat dog elephant mussel cow horse canary baboon snake shark otherword + 0: word cat dog elephant mussel cow horse canary baboon snake shark otherword + word cat dog elephant mussel cow horse canary baboon snake shark +No match + +/word (?>[a-zA-Z0-9]+ ){0,30}otherword/ + word cat dog elephant mussel cow horse canary baboon snake shark the quick brown fox and the lazy dog and several other words getting close to thirty by now I hope +No match + +/(?<=\d{3}(?!999))foo/ + 999foo + 0: foo + 123999foo + 0: foo + *** Failers +No match + 123abcfoo +No match + +/(?<=(?!...999)\d{3})foo/ + 999foo + 0: foo + 123999foo + 0: foo + *** Failers +No match + 123abcfoo +No match + +/(?<=\d{3}(?!999)...)foo/ + 123abcfoo + 0: foo + 123456foo + 0: foo + *** Failers +No match + 123999foo +No match + +/(?<=\d{3}...)(?Z)+|A)*/ + ZABCDEFG + 0: ZA + 1: Z + 2: + +/((?>)+|A)*/ + ZABCDEFG + 0: + +/a*/g + abbab + 0: a + 1: + 0: + 0: + 0: a + 1: + 0: + 0: + +/^[a-\d]/ + abcde + 0: a + -things + 0: - + 0digit + 0: 0 + *** Failers +No match + bcdef +No match + +/^[\d-a]/ + abcde + 0: a + -things + 0: - + 0digit + 0: 0 + *** Failers +No match + bcdef +No match + +/[[:space:]]+/ + > \x09\x0a\x0c\x0d\x0b< + 0: \x09\x0a\x0c\x0d\x0b + 1: \x09\x0a\x0c\x0d + 2: \x09\x0a\x0c + 3: \x09\x0a + 4: \x09 + 5: + +/[[:blank:]]+/ + > \x09\x0a\x0c\x0d\x0b< + 0: \x09 + 1: + +/[\s]+/ + > \x09\x0a\x0c\x0d\x0b< + 0: \x09\x0a\x0c\x0d + 1: \x09\x0a\x0c + 2: \x09\x0a + 3: \x09 + 4: + +/\s+/ + > \x09\x0a\x0c\x0d\x0b< + 0: \x09\x0a\x0c\x0d + 1: \x09\x0a\x0c + 2: \x09\x0a + 3: \x09 + 4: + +/a b/x + ab +No match + +/(?!\A)x/m + a\nxb\n + 0: x + +/(?!^)x/m + a\nxb\n +No match + +/abc\Qabc\Eabc/ + abcabcabc + 0: abcabcabc + +/abc\Q(*+|\Eabc/ + abc(*+|abc + 0: abc(*+|abc + +/ abc\Q abc\Eabc/x + abc abcabc + 0: abc abcabc + *** Failers +No match + abcabcabc +No match + +/abc#comment + \Q#not comment + literal\E/x + abc#not comment\n literal + 0: abc#not comment\x0a literal + +/abc#comment + \Q#not comment + literal/x + abc#not comment\n literal + 0: abc#not comment\x0a literal + +/abc#comment + \Q#not comment + literal\E #more comment + /x + abc#not comment\n literal + 0: abc#not comment\x0a literal + +/abc#comment + \Q#not comment + literal\E #more comment/x + abc#not comment\n literal + 0: abc#not comment\x0a literal + +/\Qabc\$xyz\E/ + abc\\\$xyz + 0: abc\$xyz + +/\Qabc\E\$\Qxyz\E/ + abc\$xyz + 0: abc$xyz + +/\Gabc/ + abc + 0: abc + *** Failers +No match + xyzabc +No match + +/\Gabc./g + abc1abc2xyzabc3 + 0: abc1 + 0: abc2 + +/abc./g + abc1abc2xyzabc3 + 0: abc1 + 0: abc2 + 0: abc3 + +/a(?x: b c )d/ + XabcdY + 0: abcd + *** Failers +No match + Xa b c d Y +No match + +/((?x)x y z | a b c)/ + XabcY + 0: abc + AxyzB + 0: xyz + +/(?i)AB(?-i)C/ + XabCY + 0: abC + *** Failers +No match + XabcY +No match + +/((?i)AB(?-i)C|D)E/ + abCE + 0: abCE + DE + 0: DE + *** Failers +No match + abcE +No match + abCe +No match + dE +No match + De +No match + +/[z\Qa-d]\E]/ + z + 0: z + a + 0: a + - + 0: - + d + 0: d + ] + 0: ] + *** Failers + 0: a + b +No match + +/[\z\C]/ + z + 0: z + C + 0: C + +/\M/ + M + 0: M + +/(a+)*b/ + aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa +No match + +/(?i)reg(?:ul(?:[aä]|ae)r|ex)/ + REGular + 0: REGular + regulaer + 0: regulaer + Regex + 0: Regex + regulär + 0: regul\xe4r + +/Åæåä[à-ÿÀ-ß]+/ + Åæåäà + 0: \xc5\xe6\xe5\xe4\xe0 + Åæåäÿ + 0: \xc5\xe6\xe5\xe4\xff + ÅæåäÀ + 0: \xc5\xe6\xe5\xe4\xc0 + Åæåäß + 0: \xc5\xe6\xe5\xe4\xdf + +/(?<=Z)X./ + \x84XAZXB + 0: XB + +/^(?(2)a|(1)(2))+$/ + 123a +Error -17 + +/(?<=a|bbbb)c/ + ac + 0: c + bbbbc + 0: c + +/abc/>testsavedregex +Compiled regex written to testsavedregex +testsavedregex +Compiled regex written to testsavedregex +testsavedregex +Compiled regex written to testsavedregex +Study data written to testsavedregex +testsavedregex +Compiled regex written to testsavedregex +Study data written to testsavedregex + + 0: abc + xyz\r\nabc\ + 0: abc + xyz\rabc\ + 0: abc + xyz\r\nabc\ + 0: abc + ** Failers +No match + xyz\nabc\ +No match + xyz\r\nabc\ +No match + xyz\nabc\ +No match + xyz\rabc\ +No match + xyz\rabc\ +No match + +/abc$/m + xyzabc + 0: abc + xyzabc\n + 0: abc + xyzabc\npqr + 0: abc + xyzabc\r\ + 0: abc + xyzabc\rpqr\ + 0: abc + xyzabc\r\n\ + 0: abc + xyzabc\r\npqr\ + 0: abc + ** Failers +No match + xyzabc\r +No match + xyzabc\rpqr +No match + xyzabc\r\n +No match + xyzabc\r\npqr +No match + +/^abc/m + xyz\rabcdef + 0: abc + xyz\nabcdef\ + 0: abc + ** Failers +No match + xyz\nabcdef +No match + +/^abc/m + xyz\nabcdef + 0: abc + xyz\rabcdef\ + 0: abc + ** Failers +No match + xyz\rabcdef +No match + +/^abc/m + xyz\r\nabcdef + 0: abc + xyz\rabcdef\ + 0: abc + ** Failers +No match + xyz\rabcdef +No match + +/.*/ + abc\ndef + 0: abc + 1: ab + 2: a + 3: + abc\rdef + 0: abc\x0ddef + 1: abc\x0dde + 2: abc\x0dd + 3: abc\x0d + 4: abc + 5: ab + 6: a + 7: + abc\r\ndef + 0: abc\x0d + 1: abc + 2: ab + 3: a + 4: + \abc\ndef + 0: abc\x0adef + 1: abc\x0ade + 2: abc\x0ad + 3: abc\x0a + 4: abc + 5: ab + 6: a + 7: + \abc\rdef + 0: abc + 1: ab + 2: a + 3: + \abc\r\ndef + 0: abc + 1: ab + 2: a + 3: + \abc\ndef + 0: abc\x0adef + 1: abc\x0ade + 2: abc\x0ad + 3: abc\x0a + 4: abc + 5: ab + 6: a + 7: + \abc\rdef + 0: abc\x0ddef + 1: abc\x0dde + 2: abc\x0dd + 3: abc\x0d + 4: abc + 5: ab + 6: a + 7: + \abc\r\ndef + 0: abc + 1: ab + 2: a + 3: + +/\w+(.)(.)?def/s + abc\ndef + 0: abc\x0adef + abc\rdef + 0: abc\x0ddef + abc\r\ndef + 0: abc\x0d\x0adef + +/^\w+=.*(\\\n.*)*/ + abc=xyz\\\npqr + 0: abc=xyz\\x0apqr + 1: abc=xyz\\x0apq + 2: abc=xyz\\x0ap + 3: abc=xyz\\x0a + 4: abc=xyz\ + 5: abc=xyz + 6: abc=xy + 7: abc=x + 8: abc= + +/^(a()*)*/ + aaaa + 0: aaaa + 1: aaa + 2: aa + 3: a + 4: + +/^(?:a(?:(?:))*)*/ + aaaa + 0: aaaa + 1: aaa + 2: aa + 3: a + 4: + +/^(a()+)+/ + aaaa + 0: aaaa + 1: aaa + 2: aa + 3: a + +/^(?:a(?:(?:))+)+/ + aaaa + 0: aaaa + 1: aaa + 2: aa + 3: a + +/(a|)*\d/ + aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa +No match + aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa4 + 0: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa4 + +/(?>a|)*\d/ + aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa +No match + aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa4 + 0: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa4 + +/(?:a|)*\d/ + aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa +No match + aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa4 + 0: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa4 + +/^a.b/ + a\rb + 0: a\x0db + a\nb\ + 0: a\x0ab + ** Failers +No match + a\nb +No match + a\nb\ +No match + a\rb\ +No match + a\rb\ +No match + +/^abc./mgx + abc1 \x0aabc2 \x0babc3xx \x0cabc4 \x0dabc5xx \x0d\x0aabc6 \x85abc7 \x{2028}abc8 \x{2029}abc9 JUNK + 0: abc1 + 0: abc2 + 0: abc3 + 0: abc4 + 0: abc5 + 0: abc6 + 0: abc7 + +/abc.$/mgx + abc1\x0a abc2\x0b abc3\x0c abc4\x0d abc5\x0d\x0a abc6\x85 abc7\x{2028} abc8\x{2029} abc9 + 0: abc1 + 0: abc2 + 0: abc3 + 0: abc4 + 0: abc5 + 0: abc6 + 0: abc9 + +/^a\Rb/ + a\nb + 0: a\x0ab + a\rb + 0: a\x0db + a\r\nb + 0: a\x0d\x0ab + a\x0bb + 0: a\x0bb + a\x0cb + 0: a\x0cb + a\x85b + 0: a\x85b + ** Failers +No match + a\n\rb +No match + +/^a\R*b/ + ab + 0: ab + a\nb + 0: a\x0ab + a\rb + 0: a\x0db + a\r\nb + 0: a\x0d\x0ab + a\x0bb + 0: a\x0bb + a\x0cb + 0: a\x0cb + a\x85b + 0: a\x85b + a\n\rb + 0: a\x0a\x0db + a\n\r\x85\x0cb + 0: a\x0a\x0d\x85\x0cb + +/^a\R+b/ + a\nb + 0: a\x0ab + a\rb + 0: a\x0db + a\r\nb + 0: a\x0d\x0ab + a\x0bb + 0: a\x0bb + a\x0cb + 0: a\x0cb + a\x85b + 0: a\x85b + a\n\rb + 0: a\x0a\x0db + a\n\r\x85\x0cb + 0: a\x0a\x0d\x85\x0cb + ** Failers +No match + ab +No match + +/^a\R{1,3}b/ + a\nb + 0: a\x0ab + a\n\rb + 0: a\x0a\x0db + a\n\r\x85b + 0: a\x0a\x0d\x85b + a\r\n\r\nb + 0: a\x0d\x0a\x0d\x0ab + a\r\n\r\n\r\nb + 0: a\x0d\x0a\x0d\x0a\x0d\x0ab + a\n\r\n\rb + 0: a\x0a\x0d\x0a\x0db + a\n\n\r\nb + 0: a\x0a\x0a\x0d\x0ab + ** Failers +No match + a\n\n\n\rb +No match + a\r +No match + +/^a[\R]b/ + aRb + 0: aRb + ** Failers +No match + a\nb +No match + +/.+foo/ + afoo + 0: afoo + ** Failers +No match + \r\nfoo +No match + \nfoo +No match + +/.+foo/ + afoo + 0: afoo + \nfoo + 0: \x0afoo + ** Failers +No match + \r\nfoo +No match + +/.+foo/ + afoo + 0: afoo + ** Failers +No match + \nfoo +No match + \r\nfoo +No match + +/.+foo/s + afoo + 0: afoo + \r\nfoo + 0: \x0d\x0afoo + \nfoo + 0: \x0afoo + +/^$/mg + abc\r\rxyz + 0: + abc\n\rxyz + 0: + ** Failers +No match + abc\r\nxyz +No match + +/^X/m + XABC + 0: X + ** Failers +No match + XABC\B +No match + +/(?m)^$/g+ + abc\r\n\r\n + 0: + 0+ \x0d\x0a + +/(?m)^$|^\r\n/g+ + abc\r\n\r\n + 0: \x0d\x0a + 0+ + 1: + +/(?m)$/g+ + abc\r\n\r\n + 0: + 0+ \x0d\x0a\x0d\x0a + 0: + 0+ \x0d\x0a + 0: + 0+ + +/(?|(abc)|(xyz))/ + >abc< + 0: abc + >xyz< + 0: xyz + +/(x)(?|(abc)|(xyz))(x)/ + xabcx + 0: xabcx + xxyzx + 0: xxyzx + +/(x)(?|(abc)(pqr)|(xyz))(x)/ + xabcpqrx + 0: xabcpqrx + xxyzx + 0: xxyzx + +/(?|(abc)|(xyz))(?1)/ + abcabc + 0: abcabc + xyzabc + 0: xyzabc + ** Failers +No match + xyzxyz +No match + +/\H\h\V\v/ + X X\x0a + 0: X X\x0a + X\x09X\x0b + 0: X\x09X\x0b + ** Failers +No match + \xa0 X\x0a +No match + +/\H*\h+\V?\v{3,4}/ + \x09\x20\xa0X\x0a\x0b\x0c\x0d\x0a + 0: \x09 \xa0X\x0a\x0b\x0c\x0d + 1: \x09 \xa0X\x0a\x0b\x0c + \x09\x20\xa0\x0a\x0b\x0c\x0d\x0a + 0: \x09 \xa0\x0a\x0b\x0c\x0d + 1: \x09 \xa0\x0a\x0b\x0c + \x09\x20\xa0\x0a\x0b\x0c + 0: \x09 \xa0\x0a\x0b\x0c + ** Failers +No match + \x09\x20\xa0\x0a\x0b +No match + +/\H{3,4}/ + XY ABCDE + 0: ABCD + 1: ABC + XY PQR ST + 0: PQR + +/.\h{3,4}./ + XY AB PQRS + 0: B P + 1: B + +/\h*X\h?\H+Y\H?Z/ + >XNNNYZ + 0: XNNNYZ + > X NYQZ + 0: X NYQZ + ** Failers +No match + >XYZ +No match + > X NY Z +No match + +/\v*X\v?Y\v+Z\V*\x0a\V+\x0b\V{2,3}\x0c/ + >XY\x0aZ\x0aA\x0bNN\x0c + 0: XY\x0aZ\x0aA\x0bNN\x0c + >\x0a\x0dX\x0aY\x0a\x0bZZZ\x0aAAA\x0bNNN\x0c + 0: \x0a\x0dX\x0aY\x0a\x0bZZZ\x0aAAA\x0bNNN\x0c + +/.+A/ + \r\nA +No match + +/\nA/ + \r\nA + 0: \x0aA + +/[\r\n]A/ + \r\nA + 0: \x0aA + +/(\r|\n)A/ + \r\nA + 0: \x0aA + +/a\Rb/I +Capturing subpattern count = 0 +Options: bsr_anycrlf +First char = 'a' +Need char = 'b' + a\rb + 0: a\x0db + a\nb + 0: a\x0ab + a\r\nb + 0: a\x0d\x0ab + ** Failers +No match + a\x85b +No match + a\x0bb +No match + +/a\Rb/I +Capturing subpattern count = 0 +Options: bsr_unicode +First char = 'a' +Need char = 'b' + a\rb + 0: a\x0db + a\nb + 0: a\x0ab + a\r\nb + 0: a\x0d\x0ab + a\x85b + 0: a\x85b + a\x0bb + 0: a\x0bb + ** Failers +No match + a\x85b\ +No match + a\x0bb\ +No match + +/a\R?b/I +Capturing subpattern count = 0 +Options: bsr_anycrlf +First char = 'a' +Need char = 'b' + a\rb + 0: a\x0db + a\nb + 0: a\x0ab + a\r\nb + 0: a\x0d\x0ab + ** Failers +No match + a\x85b +No match + a\x0bb +No match + +/a\R?b/I +Capturing subpattern count = 0 +Options: bsr_unicode +First char = 'a' +Need char = 'b' + a\rb + 0: a\x0db + a\nb + 0: a\x0ab + a\r\nb + 0: a\x0d\x0ab + a\x85b + 0: a\x85b + a\x0bb + 0: a\x0bb + ** Failers +No match + a\x85b\ +No match + a\x0bb\ +No match + +/a\R{2,4}b/I +Capturing subpattern count = 0 +Partial matching not supported +Options: bsr_anycrlf +First char = 'a' +Need char = 'b' + a\r\n\nb + 0: a\x0d\x0a\x0ab + a\n\r\rb + 0: a\x0a\x0d\x0db + a\r\n\r\n\r\n\r\nb + 0: a\x0d\x0a\x0d\x0a\x0d\x0a\x0d\x0ab + ** Failers +No match + a\x85\85b +No match + a\x0b\0bb +No match + +/a\R{2,4}b/I +Capturing subpattern count = 0 +Partial matching not supported +Options: bsr_unicode +First char = 'a' +Need char = 'b' + a\r\rb + 0: a\x0d\x0db + a\n\n\nb + 0: a\x0a\x0a\x0ab + a\r\n\n\r\rb + 0: a\x0d\x0a\x0a\x0d\x0db + a\x85\85b +No match + a\x0b\0bb +No match + ** Failers +No match + a\r\r\r\r\rb +No match + a\x85\85b\ +No match + a\x0b\0bb\ +No match + +/ End of testinput7 / ============================================================ --- pcre/testdata/testoutput8 8e1da687952041359d64e7737984a11bfcc4ec27 +++ pcre/testdata/testoutput8 8e1da687952041359d64e7737984a11bfcc4ec27 @@ -0,0 +1,1287 @@ +/-- Do not use the \x{} construct except with patterns that have the --/ +/-- /8 option set, because PCRE doesn't recognize them as UTF-8 unless --/ +No match +/-- that option is set. However, the latest Perls recognize them always. --/ +No match + +/\x{100}ab/8 + \x{100}ab + 0: \x{100}ab + +/a\x{100}*b/8 + ab + 0: ab + a\x{100}b + 0: a\x{100}b + a\x{100}\x{100}b + 0: a\x{100}\x{100}b + +/a\x{100}+b/8 + a\x{100}b + 0: a\x{100}b + a\x{100}\x{100}b + 0: a\x{100}\x{100}b + *** Failers +No match + ab +No match + +/\bX/8 + Xoanon + 0: X + +Xoanon + 0: X + \x{300}Xoanon + 0: X + *** Failers +No match + YXoanon +No match + +/\BX/8 + YXoanon + 0: X + *** Failers +No match + Xoanon +No match + +Xoanon +No match + \x{300}Xoanon +No match + +/X\b/8 + X+oanon + 0: X + ZX\x{300}oanon + 0: X + FAX + 0: X + *** Failers +No match + Xoanon +No match + +/X\B/8 + Xoanon + 0: X + *** Failers +No match + X+oanon +No match + ZX\x{300}oanon +No match + FAX +No match + +/[^a]/8 + abcd + 0: b + a\x{100} + 0: \x{100} + +/^[abc\x{123}\x{400}-\x{402}]{2,3}\d/8 + ab99 + 0: ab9 + \x{123}\x{123}45 + 0: \x{123}\x{123}4 + \x{400}\x{401}\x{402}6 + 0: \x{400}\x{401}\x{402}6 + *** Failers +No match + d99 +No match + \x{123}\x{122}4 +No match + \x{400}\x{403}6 +No match + \x{400}\x{401}\x{402}\x{402}6 +No match + +/abc/8 + Ã] +Error -10 + à +Error -10 + ÃÃà +Error -10 + ÃÃÃ\? +No match + +/a.b/8 + acb + 0: acb + a\x7fb + 0: a\x{7f}b + a\x{100}b + 0: a\x{100}b + *** Failers +No match + a\nb +No match + +/a(.{3})b/8 + a\x{4000}xyb + 0: a\x{4000}xyb + a\x{4000}\x7fyb + 0: a\x{4000}\x{7f}yb + a\x{4000}\x{100}yb + 0: a\x{4000}\x{100}yb + *** Failers +No match + a\x{4000}b +No match + ac\ncb +No match + +/a(.*?)(.)/ + a\xc0\x88b + 0: a\xc0\x88b + 1: a\xc0\x88 + 2: a\xc0 + +/a(.*?)(.)/8 + a\x{100}b + 0: a\x{100}b + 1: a\x{100} + +/a(.*)(.)/ + a\xc0\x88b + 0: a\xc0\x88b + 1: a\xc0\x88 + 2: a\xc0 + +/a(.*)(.)/8 + a\x{100}b + 0: a\x{100}b + 1: a\x{100} + +/a(.)(.)/ + a\xc0\x92bcd + 0: a\xc0\x92 + +/a(.)(.)/8 + a\x{240}bcd + 0: a\x{240}b + +/a(.?)(.)/ + a\xc0\x92bcd + 0: a\xc0\x92 + 1: a\xc0 + +/a(.?)(.)/8 + a\x{240}bcd + 0: a\x{240}b + 1: a\x{240} + +/a(.??)(.)/ + a\xc0\x92bcd + 0: a\xc0\x92 + 1: a\xc0 + +/a(.??)(.)/8 + a\x{240}bcd + 0: a\x{240}b + 1: a\x{240} + +/a(.{3})b/8 + a\x{1234}xyb + 0: a\x{1234}xyb + a\x{1234}\x{4321}yb + 0: a\x{1234}\x{4321}yb + a\x{1234}\x{4321}\x{3412}b + 0: a\x{1234}\x{4321}\x{3412}b + *** Failers +No match + a\x{1234}b +No match + ac\ncb +No match + +/a(.{3,})b/8 + a\x{1234}xyb + 0: a\x{1234}xyb + a\x{1234}\x{4321}yb + 0: a\x{1234}\x{4321}yb + a\x{1234}\x{4321}\x{3412}b + 0: a\x{1234}\x{4321}\x{3412}b + axxxxbcdefghijb + 0: axxxxbcdefghijb + 1: axxxxb + a\x{1234}\x{4321}\x{3412}\x{3421}b + 0: a\x{1234}\x{4321}\x{3412}\x{3421}b + *** Failers +No match + a\x{1234}b +No match + +/a(.{3,}?)b/8 + a\x{1234}xyb + 0: a\x{1234}xyb + a\x{1234}\x{4321}yb + 0: a\x{1234}\x{4321}yb + a\x{1234}\x{4321}\x{3412}b + 0: a\x{1234}\x{4321}\x{3412}b + axxxxbcdefghijb + 0: axxxxbcdefghijb + 1: axxxxb + a\x{1234}\x{4321}\x{3412}\x{3421}b + 0: a\x{1234}\x{4321}\x{3412}\x{3421}b + *** Failers +No match + a\x{1234}b +No match + +/a(.{3,5})b/8 + a\x{1234}xyb + 0: a\x{1234}xyb + a\x{1234}\x{4321}yb + 0: a\x{1234}\x{4321}yb + a\x{1234}\x{4321}\x{3412}b + 0: a\x{1234}\x{4321}\x{3412}b + axxxxbcdefghijb + 0: axxxxb + a\x{1234}\x{4321}\x{3412}\x{3421}b + 0: a\x{1234}\x{4321}\x{3412}\x{3421}b + axbxxbcdefghijb + 0: axbxxb + axxxxxbcdefghijb + 0: axxxxxb + *** Failers +No match + a\x{1234}b +No match + axxxxxxbcdefghijb +No match + +/a(.{3,5}?)b/8 + a\x{1234}xyb + 0: a\x{1234}xyb + a\x{1234}\x{4321}yb + 0: a\x{1234}\x{4321}yb + a\x{1234}\x{4321}\x{3412}b + 0: a\x{1234}\x{4321}\x{3412}b + axxxxbcdefghijb + 0: axxxxb + a\x{1234}\x{4321}\x{3412}\x{3421}b + 0: a\x{1234}\x{4321}\x{3412}\x{3421}b + axbxxbcdefghijb + 0: axbxxb + axxxxxbcdefghijb + 0: axxxxxb + *** Failers +No match + a\x{1234}b +No match + axxxxxxbcdefghijb +No match + +/^[a\x{c0}]/8 + *** Failers +No match + \x{100} +No match + +/(?<=aXb)cd/8 + aXbcd + 0: cd + +/(?<=a\x{100}b)cd/8 + a\x{100}bcd + 0: cd + +/(?<=a\x{100000}b)cd/8 + a\x{100000}bcd + 0: cd + +/(?:\x{100}){3}b/8 + \x{100}\x{100}\x{100}b + 0: \x{100}\x{100}\x{100}b + *** Failers +No match + \x{100}\x{100}b +No match + +/\x{ab}/8 + \x{ab} + 0: \x{ab} + \xc2\xab + 0: \x{ab} + *** Failers +No match + \x00{ab} +No match + +/(?<=(.))X/8 + WXYZ + 0: X + \x{256}XYZ + 0: X + *** Failers +No match + XYZ +No match + +/[^a]+/8g + bcd + 0: bcd + 1: bc + 2: b + \x{100}aY\x{256}Z + 0: \x{100} + 0: Y\x{256}Z + 1: Y\x{256} + 2: Y + +/^[^a]{2}/8 + \x{100}bc + 0: \x{100}b + +/^[^a]{2,}/8 + \x{100}bcAa + 0: \x{100}bcA + 1: \x{100}bc + 2: \x{100}b + +/^[^a]{2,}?/8 + \x{100}bca + 0: \x{100}bc + 1: \x{100}b + +/[^a]+/8ig + bcd + 0: bcd + 1: bc + 2: b + \x{100}aY\x{256}Z + 0: \x{100} + 0: Y\x{256}Z + 1: Y\x{256} + 2: Y + +/^[^a]{2}/8i + \x{100}bc + 0: \x{100}b + +/^[^a]{2,}/8i + \x{100}bcAa + 0: \x{100}bc + 1: \x{100}b + +/^[^a]{2,}?/8i + \x{100}bca + 0: \x{100}bc + 1: \x{100}b + +/\x{100}{0,0}/8 + abcd + 0: + +/\x{100}?/8 + abcd + 0: + \x{100}\x{100} + 0: \x{100} + 1: + +/\x{100}{0,3}/8 + \x{100}\x{100} + 0: \x{100}\x{100} + 1: \x{100} + 2: + \x{100}\x{100}\x{100}\x{100} + 0: \x{100}\x{100}\x{100} + 1: \x{100}\x{100} + 2: \x{100} + 3: + +/\x{100}*/8 + abce + 0: + \x{100}\x{100}\x{100}\x{100} + 0: \x{100}\x{100}\x{100}\x{100} + 1: \x{100}\x{100}\x{100} + 2: \x{100}\x{100} + 3: \x{100} + 4: + +/\x{100}{1,1}/8 + abcd\x{100}\x{100}\x{100}\x{100} + 0: \x{100} + +/\x{100}{1,3}/8 + abcd\x{100}\x{100}\x{100}\x{100} + 0: \x{100}\x{100}\x{100} + 1: \x{100}\x{100} + 2: \x{100} + +/\x{100}+/8 + abcd\x{100}\x{100}\x{100}\x{100} + 0: \x{100}\x{100}\x{100}\x{100} + 1: \x{100}\x{100}\x{100} + 2: \x{100}\x{100} + 3: \x{100} + +/\x{100}{3}/8 + abcd\x{100}\x{100}\x{100}XX + 0: \x{100}\x{100}\x{100} + +/\x{100}{3,5}/8 + abcd\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}XX + 0: \x{100}\x{100}\x{100}\x{100}\x{100} + 1: \x{100}\x{100}\x{100}\x{100} + 2: \x{100}\x{100}\x{100} + +/\x{100}{3,}/8 + abcd\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}XX + 0: \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100} + 1: \x{100}\x{100}\x{100}\x{100}\x{100}\x{100} + 2: \x{100}\x{100}\x{100}\x{100}\x{100} + 3: \x{100}\x{100}\x{100}\x{100} + 4: \x{100}\x{100}\x{100} + +/(?<=a\x{100}{2}b)X/8 + Xyyya\x{100}\x{100}bXzzz + 0: X + +/\D*/8 + aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa +Matched, but too many subsidiary matches + 0: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa + 1: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa + 2: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa + 3: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa + 4: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa + 5: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa + 6: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa + 7: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa + 8: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa + 9: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa +10: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa +11: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa +12: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa +13: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa +14: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa +15: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa +16: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa +17: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa +18: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa +19: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa +20: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa +21: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa + +/\D*/8 + \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100} \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100} +Matched, but too many subsidiary matches + 0: \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{10 0}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100} + 1: \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{10 0}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100} + 2: \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{10 0}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100} + 3: \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{10 0}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100} + 4: \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{10 0}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100} + 5: \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{10 0}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100} + 6: \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{10 0}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100} + 7: \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{10 0}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100} + 8: \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{10 0}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100} + 9: \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{10 0}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100} +10: \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{10 0}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100} +11: \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{10 0}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100} +12: \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{10 0}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100} +13: \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{10 0}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100} +14: \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{10 0}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100} +15: \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{10 0}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100} +16: \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{10 0}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100} +17: \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{10 0}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100} +18: \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{10 0}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100} +19: \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{10 0}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100} +20: \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{10 0}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100} +21: \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{10 0}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100} + +/\D/8 + 1X2 + 0: X + 1\x{100}2 + 0: \x{100} + +/>\S/8 + > >X Y + 0: >X + > >\x{100} Y + 0: >\x{100} + +/\d/8 + \x{100}3 + 0: 3 + +/\s/8 + \x{100} X + 0: + +/\D+/8 + 12abcd34 + 0: abcd + 1: abc + 2: ab + 3: a + *** Failers + 0: *** Failers + 1: *** Failer + 2: *** Faile + 3: *** Fail + 4: *** Fai + 5: *** Fa + 6: *** F + 7: *** + 8: *** + 9: ** +10: * + 1234 +No match + +/\D{2,3}/8 + 12abcd34 + 0: abc + 1: ab + 12ab34 + 0: ab + *** Failers + 0: *** + 1: ** + 1234 +No match + 12a34 +No match + +/\D{2,3}?/8 + 12abcd34 + 0: abc + 1: ab + 12ab34 + 0: ab + *** Failers + 0: *** + 1: ** + 1234 +No match + 12a34 +No match + +/\d+/8 + 12abcd34 + 0: 12 + 1: 1 + *** Failers +No match + +/\d{2,3}/8 + 12abcd34 + 0: 12 + 1234abcd + 0: 123 + 1: 12 + *** Failers +No match + 1.4 +No match + +/\d{2,3}?/8 + 12abcd34 + 0: 12 + 1234abcd + 0: 123 + 1: 12 + *** Failers +No match + 1.4 +No match + +/\S+/8 + 12abcd34 + 0: 12abcd34 + 1: 12abcd3 + 2: 12abcd + 3: 12abc + 4: 12ab + 5: 12a + 6: 12 + 7: 1 + *** Failers + 0: *** + 1: ** + 2: * + \ \ +No match + +/\S{2,3}/8 + 12abcd34 + 0: 12a + 1: 12 + 1234abcd + 0: 123 + 1: 12 + *** Failers + 0: *** + 1: ** + \ \ +No match + +/\S{2,3}?/8 + 12abcd34 + 0: 12a + 1: 12 + 1234abcd + 0: 123 + 1: 12 + *** Failers + 0: *** + 1: ** + \ \ +No match + +/>\s+ <34 + 0: > < + *** Failers +No match + +/>\s{2,3} < + ab> < + *** Failers +No match + ab> \s{2,3}? < + ab> < + *** Failers +No match + ab> \xff< + 0: \xff + +/[\xff]/8 + >\x{ff}< + 0: \x{ff} + +/[^\xFF]/ + XYZ + 0: X + +/[^\xff]/8 + XYZ + 0: X + \x{123} + 0: \x{123} + +/^[ac]*b/8 + xb +No match + +/^[ac\x{100}]*b/8 + xb +No match + +/^[^x]*b/8i + xb +No match + +/^[^x]*b/8 + xb +No match + +/^\d*b/8 + xb +No match + +/(|a)/g8 + catac + 0: + 0: a + 1: + 0: + 0: a + 1: + 0: + 0: + a\x{256}a + 0: a + 1: + 0: + 0: a + 1: + 0: + +/^\x{85}$/8i + \x{85} + 0: \x{85} + +/^abc./mgx8 + abc1 \x0aabc2 \x0babc3xx \x0cabc4 \x0dabc5xx \x0d\x0aabc6 \x{0085}abc7 \x{2028}abc8 \x{2029}abc9 JUNK + 0: abc1 + 0: abc2 + 0: abc3 + 0: abc4 + 0: abc5 + 0: abc6 + 0: abc7 + 0: abc8 + 0: abc9 + +/abc.$/mgx8 + abc1\x0a abc2\x0b abc3\x0c abc4\x0d abc5\x0d\x0a abc6\x{0085} abc7\x{2028} abc8\x{2029} abc9 + 0: abc1 + 0: abc2 + 0: abc3 + 0: abc4 + 0: abc5 + 0: abc6 + 0: abc7 + 0: abc8 + 0: abc9 + +/^a\Rb/8 + a\nb + 0: a\x{0a}b + a\rb + 0: a\x{0d}b + a\r\nb + 0: a\x{0d}\x{0a}b + a\x0bb + 0: a\x{0b}b + a\x0cb + 0: a\x{0c}b + a\x{85}b + 0: a\x{85}b + a\x{2028}b + 0: a\x{2028}b + a\x{2029}b + 0: a\x{2029}b + ** Failers +No match + a\n\rb +No match + +/^a\R*b/8 + ab + 0: ab + a\nb + 0: a\x{0a}b + a\rb + 0: a\x{0d}b + a\r\nb + 0: a\x{0d}\x{0a}b + a\x0bb + 0: a\x{0b}b + a\x0c\x{2028}\x{2029}b + 0: a\x{0c}\x{2028}\x{2029}b + a\x{85}b + 0: a\x{85}b + a\n\rb + 0: a\x{0a}\x{0d}b + a\n\r\x{85}\x0cb + 0: a\x{0a}\x{0d}\x{85}\x{0c}b + +/^a\R+b/8 + a\nb + 0: a\x{0a}b + a\rb + 0: a\x{0d}b + a\r\nb + 0: a\x{0d}\x{0a}b + a\x0bb + 0: a\x{0b}b + a\x0c\x{2028}\x{2029}b + 0: a\x{0c}\x{2028}\x{2029}b + a\x{85}b + 0: a\x{85}b + a\n\rb + 0: a\x{0a}\x{0d}b + a\n\r\x{85}\x0cb + 0: a\x{0a}\x{0d}\x{85}\x{0c}b + ** Failers +No match + ab +No match + +/^a\R{1,3}b/8 + a\nb + 0: a\x{0a}b + a\n\rb + 0: a\x{0a}\x{0d}b + a\n\r\x{85}b + 0: a\x{0a}\x{0d}\x{85}b + a\r\n\r\nb + 0: a\x{0d}\x{0a}\x{0d}\x{0a}b + a\r\n\r\n\r\nb + 0: a\x{0d}\x{0a}\x{0d}\x{0a}\x{0d}\x{0a}b + a\n\r\n\rb + 0: a\x{0a}\x{0d}\x{0a}\x{0d}b + a\n\n\r\nb + 0: a\x{0a}\x{0a}\x{0d}\x{0a}b + ** Failers +No match + a\n\n\n\rb +No match + a\r +No match + +/\h+\V?\v{3,4}/8 + \x09\x20\x{a0}X\x0a\x0b\x0c\x0d\x0a + 0: \x{09} \x{a0}X\x{0a}\x{0b}\x{0c}\x{0d} + 1: \x{09} \x{a0}X\x{0a}\x{0b}\x{0c} + +/\V?\v{3,4}/8 + \x20\x{a0}X\x0a\x0b\x0c\x0d\x0a + 0: X\x{0a}\x{0b}\x{0c}\x{0d} + 1: X\x{0a}\x{0b}\x{0c} + +/\h+\V?\v{3,4}/8 + >\x09\x20\x{a0}X\x0a\x0a\x0a< + 0: \x{09} \x{a0}X\x{0a}\x{0a}\x{0a} + +/\V?\v{3,4}/8 + >\x09\x20\x{a0}X\x0a\x0a\x0a< + 0: X\x{0a}\x{0a}\x{0a} + +/\H\h\V\v/8 + X X\x0a + 0: X X\x{0a} + X\x09X\x0b + 0: X\x{09}X\x{0b} + ** Failers +No match + \x{a0} X\x0a +No match + +/\H*\h+\V?\v{3,4}/8 + \x09\x20\x{a0}X\x0a\x0b\x0c\x0d\x0a + 0: \x{09} \x{a0}X\x{0a}\x{0b}\x{0c}\x{0d} + 1: \x{09} \x{a0}X\x{0a}\x{0b}\x{0c} + \x09\x20\x{a0}\x0a\x0b\x0c\x0d\x0a + 0: \x{09} \x{a0}\x{0a}\x{0b}\x{0c}\x{0d} + 1: \x{09} \x{a0}\x{0a}\x{0b}\x{0c} + \x09\x20\x{a0}\x0a\x0b\x0c + 0: \x{09} \x{a0}\x{0a}\x{0b}\x{0c} + ** Failers +No match + \x09\x20\x{a0}\x0a\x0b +No match + +/\H\h\V\v/8 + \x{3001}\x{3000}\x{2030}\x{2028} + 0: \x{3001}\x{3000}\x{2030}\x{2028} + X\x{180e}X\x{85} + 0: X\x{180e}X\x{85} + ** Failers +No match + \x{2009} X\x0a +No match + +/\H*\h+\V?\v{3,4}/8 + \x{1680}\x{180e}\x{2007}X\x{2028}\x{2029}\x0c\x0d\x0a + 0: \x{1680}\x{180e}\x{2007}X\x{2028}\x{2029}\x{0c}\x{0d} + 1: \x{1680}\x{180e}\x{2007}X\x{2028}\x{2029}\x{0c} + \x09\x{205f}\x{a0}\x0a\x{2029}\x0c\x{2028}\x0a + 0: \x{09}\x{205f}\x{a0}\x{0a}\x{2029}\x{0c}\x{2028} + 1: \x{09}\x{205f}\x{a0}\x{0a}\x{2029}\x{0c} + \x09\x20\x{202f}\x0a\x0b\x0c + 0: \x{09} \x{202f}\x{0a}\x{0b}\x{0c} + ** Failers +No match + \x09\x{200a}\x{a0}\x{2028}\x0b +No match + +/a\Rb/I8 +Capturing subpattern count = 0 +Options: bsr_anycrlf utf8 +First char = 'a' +Need char = 'b' + a\rb + 0: a\x{0d}b + a\nb + 0: a\x{0a}b + a\r\nb + 0: a\x{0d}\x{0a}b + ** Failers +No match + a\x{85}b +No match + a\x0bb +No match + +/a\Rb/I8 +Capturing subpattern count = 0 +Options: bsr_unicode utf8 +First char = 'a' +Need char = 'b' + a\rb + 0: a\x{0d}b + a\nb + 0: a\x{0a}b + a\r\nb + 0: a\x{0d}\x{0a}b + a\x{85}b + 0: a\x{85}b + a\x0bb + 0: a\x{0b}b + ** Failers +No match + a\x{85}b\ +No match + a\x0bb\ +No match + +/a\R?b/I8 +Capturing subpattern count = 0 +Options: bsr_anycrlf utf8 +First char = 'a' +Need char = 'b' + a\rb + 0: a\x{0d}b + a\nb + 0: a\x{0a}b + a\r\nb + 0: a\x{0d}\x{0a}b + ** Failers +No match + a\x{85}b +No match + a\x0bb +No match + +/a\R?b/I8 +Capturing subpattern count = 0 +Options: bsr_unicode utf8 +First char = 'a' +Need char = 'b' + a\rb + 0: a\x{0d}b + a\nb + 0: a\x{0a}b + a\r\nb + 0: a\x{0d}\x{0a}b + a\x{85}b + 0: a\x{85}b + a\x0bb + 0: a\x{0b}b + ** Failers +No match + a\x{85}b\ +No match + a\x0bb\ +No match + +/ End of testinput 8 / ============================================================ --- pcre/testdata/testoutput9 05ca3a0c9ba18ce295485db9aa6c169414b962d8 +++ pcre/testdata/testoutput9 05ca3a0c9ba18ce295485db9aa6c169414b962d8 @@ -0,0 +1,1643 @@ +/\pL\P{Nd}/8 + AB + 0: AB + *** Failers + 0: Fa + A0 +No match + 00 +No match + +/\X./8 + AB + 0: AB + A\x{300}BC + 0: A\x{300}B + A\x{300}\x{301}\x{302}BC + 0: A\x{300}\x{301}\x{302}B + *** Failers + 0: ** + \x{300} +No match + +/\X\X/8 + ABC + 0: AB + A\x{300}B\x{300}\x{301}C + 0: A\x{300}B\x{300}\x{301} + A\x{300}\x{301}\x{302}BC + 0: A\x{300}\x{301}\x{302}B + *** Failers + 0: ** + \x{300} +No match + +/^\pL+/8 + abcd + 0: abcd + 1: abc + 2: ab + 3: a + a + 0: a + *** Failers +No match + +/^\PL+/8 + 1234 + 0: 1234 + 1: 123 + 2: 12 + 3: 1 + = + 0: = + *** Failers + 0: *** + 1: *** + 2: ** + 3: * + abcd +No match + +/^\X+/8 + abcdA\x{300}\x{301}\x{302} + 0: abcdA\x{300}\x{301}\x{302} + 1: abcd + 2: abc + 3: ab + 4: a + A\x{300}\x{301}\x{302} + 0: A\x{300}\x{301}\x{302} + A\x{300}\x{301}\x{302}A\x{300}\x{301}\x{302} + 0: A\x{300}\x{301}\x{302}A\x{300}\x{301}\x{302} + 1: A\x{300}\x{301}\x{302} + a + 0: a + *** Failers + 0: *** Failers + 1: *** Failer + 2: *** Faile + 3: *** Fail + 4: *** Fai + 5: *** Fa + 6: *** F + 7: *** + 8: *** + 9: ** +10: * + \x{300}\x{301}\x{302} +No match + +/\X?abc/8 + abc + 0: abc + A\x{300}abc + 0: A\x{300}abc + A\x{300}\x{301}\x{302}A\x{300}A\x{300}A\x{300}abcxyz + 0: A\x{300}abc + \x{300}abc + 0: abc + *** Failers +No match + +/^\X?abc/8 + abc + 0: abc + A\x{300}abc + 0: A\x{300}abc + *** Failers +No match + A\x{300}\x{301}\x{302}A\x{300}A\x{300}A\x{300}abcxyz +No match + \x{300}abc +No match + +/\X*abc/8 + abc + 0: abc + A\x{300}abc + 0: A\x{300}abc + A\x{300}\x{301}\x{302}A\x{300}A\x{300}A\x{300}abcxyz + 0: A\x{300}\x{301}\x{302}A\x{300}A\x{300}A\x{300}abc + \x{300}abc + 0: abc + *** Failers +No match + +/^\X*abc/8 + abc + 0: abc + A\x{300}abc + 0: A\x{300}abc + A\x{300}\x{301}\x{302}A\x{300}A\x{300}A\x{300}abcxyz + 0: A\x{300}\x{301}\x{302}A\x{300}A\x{300}A\x{300}abc + *** Failers +No match + \x{300}abc +No match + +/^\pL?=./8 + A=b + 0: A=b + =c + 0: =c + *** Failers +No match + 1=2 +No match + AAAA=b +No match + +/^\pL*=./8 + AAAA=b + 0: AAAA=b + =c + 0: =c + *** Failers +No match + 1=2 +No match + +/^\X{2,3}X/8 + A\x{300}\x{301}\x{302}A\x{300}\x{301}\x{302}X + 0: A\x{300}\x{301}\x{302}A\x{300}\x{301}\x{302}X + A\x{300}\x{301}\x{302}A\x{300}\x{301}\x{302}A\x{300}\x{301}\x{302}X + 0: A\x{300}\x{301}\x{302}A\x{300}\x{301}\x{302}A\x{300}\x{301}\x{302}X + *** Failers +No match + X +No match + A\x{300}\x{301}\x{302}X +No match + A\x{300}\x{301}\x{302}A\x{300}\x{301}\x{302}A\x{300}\x{301}\x{302}A\x{300}\x{301}\x{302}X +No match + +/^\pC\pL\pM\pN\pP\pS\pZ>>\xaa<<< + >>>\xba<<< + +/[\W]+/Lfrench + >>>\xaa<<< + >>>\xba<<< + +/[^[:alpha:]]+/Lfrench + >>>\xaa<<< + >>>\xba<<< + +/\w+/Lfrench + >>>\xaa<<< + >>>\xba<<< + +/[\w]+/Lfrench + >>>\xaa<<< + >>>\xba<<< + +/[[:alpha:]]+/Lfrench + >>>\xaa<<< + >>>\xba<<< + +/[[:alpha:]][[:lower:]][[:upper:]]/DZLfrench + +/ End of testinput3 / ============================================================ --- pcre/testdata/wintestoutput3 bca3918ac3ffe14f168eb2ed1359fb5b1062269a +++ pcre/testdata/wintestoutput3 bca3918ac3ffe14f168eb2ed1359fb5b1062269a @@ -0,0 +1,164 @@ +/^[\w]+/ + *** Failers +No match + École +No match + +/^[\w]+/Lfrench + École + 0: École + +/^[\w]+/ + *** Failers +No match + École +No match + +/^[\W]+/ + École + 0: \xc9 + +/^[\W]+/Lfrench + *** Failers + 0: *** + École +No match + +/[\b]/ + \b + 0: \x08 + *** Failers +No match + a +No match + +/[\b]/Lfrench + \b + 0: \x08 + *** Failers +No match + a +No match + +/^\w+/ + *** Failers +No match + École +No match + +/^\w+/Lfrench + École + 0: École + +/(.+)\b(.+)/ + École + 0: \xc9cole + 1: \xc9 + 2: cole + +/(.+)\b(.+)/Lfrench + *** Failers + 0: *** Failers + 1: *** + 2: Failers + École +No match + +/École/i + École + 0: \xc9cole + *** Failers +No match + école +No match + +/École/iLfrench + École + 0: École + école + 0: école + +/\w/IS +Capturing subpattern count = 0 +No options +No first char +No need char +Starting byte set: 0 1 2 3 4 5 6 7 8 9 A B C D E F G H I J K L M N O P + Q R S T U V W X Y Z _ a b c d e f g h i j k l m n o p q r s t u v w x y z + +/\w/ISLfrench +Capturing subpattern count = 0 +No options +No first char +No need char +Starting byte set: 0 1 2 3 4 5 6 7 8 9 A B C D E F G H I J K L M N O P + Q R S T U V W X Y Z _ a b c d e f g h i j k l m n o p q r s t u v w x y z + ƒ Š Œ Ž š œ ž Ÿ ª ² ³ µ ¹ º À Á Â Ã Ä Å Æ Ç È É Ê Ë Ì Í Î Ï Ð Ñ Ò Ó Ô Õ Ö + Ø Ù Ú Û Ü Ý Þ ß à á â ã ä å æ ç è é ê ë ì í î ï ð ñ ò ó ô õ ö ø ù ú û ü ý + þ ÿ + +/^[\xc8-\xc9]/iLfrench + École + 0: É + école + 0: é + +/^[\xc8-\xc9]/Lfrench + École + 0: É + *** Failers +No match + école +No match + +/\W+/Lfrench + >>>\xaa<<< + 0: >>> + >>>\xba<<< + 0: >>> + +/[\W]+/Lfrench + >>>\xaa<<< + 0: >>> + >>>\xba<<< + 0: >>> + +/[^[:alpha:]]+/Lfrench + >>>\xaa<<< + 0: >>> + >>>\xba<<< + 0: >>> + +/\w+/Lfrench + >>>\xaa<<< + 0: ª + >>>\xba<<< + 0: º + +/[\w]+/Lfrench + >>>\xaa<<< + 0: ª + >>>\xba<<< + 0: º + +/[[:alpha:]]+/Lfrench + >>>\xaa<<< + 0: ª + >>>\xba<<< + 0: º + +/[[:alpha:]][[:lower:]][[:upper:]]/DZLfrench +------------------------------------------------------------------ + Bra + [A-Za-z\x83\x8a\x8c\x8e\x9a\x9c\x9e\x9f\xaa\xb5\xba\xc0-\xd6\xd8-\xf6\xf8-\xff] + [a-z\x83\x9a\x9c\x9e\xaa\xb5\xba\xdf-\xf6\xf8-\xff] + [A-Z\x8a\x8c\x8e\x9f\xc0-\xd6\xd8-\xde] + Ket + End +------------------------------------------------------------------ +Capturing subpattern count = 0 +No options +No first char +No need char + +/ End of testinput3 / ============================================================ --- pcre/Makefile.am c98bdfd14eec6c05e7dc9d469f5e6adfe3764aac +++ pcre/Makefile.am 528e12a68cb3126ff7d9be07c9191af9563c7603 @@ -1,17 +1,123 @@ -AUTOMAKE_OPTIONS=subdir-objects 1.7.1 +## Process this file with automake to produce Makefile.in. -lib_LIBRARIES = libpcre.a -include_HEADERS = pcre.h -libpcre_a_SOURCES = \ - pcre_chartables.c pcre_compile.c pcre_config.c pcre_config.h \ - pcre_dfa_exec.c pcre_exec.c pcre_fullinfo.c pcre_get.c \ - pcre_globals.c pcre_info.c pcre_internal.h pcre_maketables.c \ - pcre_newline.c pcre_ord2utf8.c pcre_refcount.c pcre_study.c \ - pcre_tables.c pcre_try_flipped.c pcre_ucp_searchfuncs.c \ - pcre_valid_utf8.c pcre_version.c pcre_xclass.c ucp.h \ - ucpinternal.h ucptable.h +## MONOTONE: All irrelevant functionality has been removed from this file. +## MONOTONE: See README.monotone for details. -libpcre_a_CPPFLAGS = -libpcre_a_CFLAGS = $(AM_CFLAGS) $(LIB3RDPARTY_CFLAGS) -libpcre_a_CXXFLAGS = $(AM_CXXFLAGS) -I$(top_srcdir) $(LIB3RDPARTY_CXXFLAGS) +# The Libtool libraries to install. We'll add to this later. +lib_LTLIBRARIES = +# Unit tests you want to run when people type 'make check'. +# TESTS is for binary unit tests, check_SCRIPTS for script-based tests +TESTS = +check_SCRIPTS = +dist_noinst_SCRIPTS = + +# Some of the binaries we make are to be installed, and others are +# (non-user-visible) helper programs needed to build libpcre. +bin_PROGRAMS = +noinst_PROGRAMS = + +# Additional files to delete on 'make clean' and 'make maintainer-clean'. +CLEANFILES = +MAINTAINERCLEANFILES = + +# These are the header files we'll install. +nodist_include_HEADERS = pcre.h + +# We have .pc files for pkg-config users. +pkgconfigdir = $(libdir)/pkgconfig +pkgconfig_DATA = libpcre.pc +bin_SCRIPTS = pcre-config + +## The main pcre library +lib_LTLIBRARIES += libpcre.la +libpcre_la_SOURCES = \ + pcre_compile.c \ + pcre_config.c \ + pcre_dfa_exec.c \ + pcre_exec.c \ + pcre_fullinfo.c \ + pcre_get.c \ + pcre_globals.c \ + pcre_info.c \ + pcre_internal.h \ + pcre_maketables.c \ + pcre_newline.c \ + pcre_ord2utf8.c \ + pcre_refcount.c \ + pcre_study.c \ + pcre_tables.c \ + pcre_try_flipped.c \ + pcre_ucp_searchfuncs.c \ + pcre_valid_utf8.c \ + pcre_version.c \ + pcre_xclass.c \ + ucp.h \ + ucpinternal.h \ + ucptable.h \ + pcre_chartables.c + +# The pcre_printint.src file is #included by some source files, so it must be +# distributed. +EXTRA_DIST += pcre_printint.src + +libpcre_la_LDFLAGS = $(EXTRA_LIBPCRE_LDFLAGS) + +## The main unit tests + +# Each unit test is a binary plus a script that runs that binary in various +# ways. We install these test binaries in case folks find it helpful. + +TESTS += RunTest +dist_noinst_SCRIPTS += RunTest +EXTRA_DIST += RunTest.bat +bin_PROGRAMS += pcretest +pcretest_SOURCES = pcretest.c +pcretest_LDADD = libpcreposix.la + +TESTS += RunGrepTest +dist_noinst_SCRIPTS += RunGrepTest +bin_PROGRAMS += pcregrep +pcregrep_SOURCES = pcregrep.c +pcregrep_LDADD = libpcreposix.la + +EXTRA_DIST += \ + testdata/grepinput \ + testdata/grepinput8 \ + testdata/grepinputv \ + testdata/grepinputx \ + testdata/greplist \ + testdata/grepoutput \ + testdata/grepoutput8 \ + testdata/grepoutputN \ + testdata/testinput1 \ + testdata/testinput2 \ + testdata/testinput3 \ + testdata/testinput4 \ + testdata/testinput5 \ + testdata/testinput6 \ + testdata/testinput7 \ + testdata/testinput8 \ + testdata/testinput9 \ + testdata/testinput10 \ + testdata/testoutput1 \ + testdata/testoutput2 \ + testdata/testoutput3 \ + testdata/testoutput4 \ + testdata/testoutput5 \ + testdata/testoutput6 \ + testdata/testoutput7 \ + testdata/testoutput8 \ + testdata/testoutput9 \ + testdata/testoutput10 \ + testdata/wintestinput3 \ + testdata/wintestoutput3 \ + perltest.pl + +CLEANFILES += \ + testsavedregex \ + teststderr \ + testtry \ + testNinput + +## end Makefile.am ============================================================ --- pcre/README 420b5f8ab281ef77f9caa6cde682d24ea5f68322 +++ pcre/README.monotone d7f7b32bbfd398885310a4a42ab1311e33891843 @@ -1,10 +1,20 @@ -This is the library component of pcre 7.4, downloaded from -. The only -modification made to the code is that each .c file has been changed to -#include "pcre_config.h" unconditionally, instead of "config.h" only when -HAVE_CONFIG_H is defined. The file pcre_config.h is an appropriately -customized version of pcre's config.h.in. (This is done so that we -don't clutter monotone's own config.h with pcre's settings.) The files -pcresyntax.texi and pcrepattern.texi are translations to Texinfo of the -upstream documentation files pcresyntax.3 and pcrepattern.3, which were -in manpage format. +This is the library component of pcre 7.6, downloaded from +. + +This is not the entire tarball available from that site: + + - Only the native C interface has been imported; not the POSIX shim, + C++ wrapper, or Pascal wrapper. + - The documentation has not been imported (but see monotone/pcre*.texi). + - No generated files nor files potentially created by 'autoreconf -i' + have been imported. (Note that pcre_chartables.c only *appears* to + be a generated file.) + - The CMake-based alternative build system has not been imported. + +However, the various utility programs (pcregrep etc) *have* been imported. +They are not installed when built as part of monotone, but they're handy +to have around for debugging. Also, we do include and run the testsuite. + +The configure script has been modified to look for autoconf helper scripts +in the parent directory, and the Makefile has been modified not to try to +build any of the things that were left out of the import. ============================================================ --- pcre/configure.ac 04d79c5a15950d1a813dc6bd64ca4f89aa7cb412 +++ pcre/configure.ac 5572186007517c995ada22a89658b3bf65a5b8b2 @@ -1,26 +1,612 @@ -# Stub configuration template for Monotone third-party library directories. -# Process this file with autoconf to produce a configure script. -# Copyright 2008 Zachary Weinberg +dnl Process this file with autoconf to produce a configure script. + +dnl NOTE FOR MAINTAINERS: Do not use major or minor version numbers with +dnl leading zeros, because they may be treated as octal constants. The +dnl PCRE_PRERELEASE feature is for identifying release candidates. It might +dnl be defined as -RC2, for example. For real releases, it should be defined +dnl empty. + +m4_define(pcre_major, [7]) +m4_define(pcre_minor, [6]) +m4_define(pcre_prerelease, []) +m4_define(pcre_date, [2008-01-28]) + +# Libtool shared library interface versions (current:revision:age) +m4_define(libpcre_version, [0:1:0]) +m4_define(libpcreposix_version, [0:0:0]) +m4_define(libpcrecpp_version, [0:0:0]) + +AC_PREREQ(2.57) +AC_INIT(PCRE, pcre_major.pcre_minor[]pcre_prerelease, , pcre) +AC_CONFIG_SRCDIR([pcre.h.in]) +dnl MONOTONE: look for helper files in parent directory; disable +dnl MONOTONE: automake's sanity checking and "make dist". +AC_CONFIG_AUX_DIR([..]) +AC_CONFIG_MACRO_DIR([../m4]) +AM_INIT_AUTOMAKE([foreign no-dist]) +dnl MONOTONE: end modifications. +AC_CONFIG_HEADERS(config.h) + +# The default CFLAGS and CXXFLAGS in Autoconf are "-g -O2" for gcc and just +# "-g" for any other compiler. There doesn't seem to be a standard way of +# getting rid of the -g (which I don't think is needed for a production +# library). This fudge seems to achieve the necessary. First, we remember the +# externally set values of CFLAGS and CXXFLAGS. Then call the AC_PROG_CC and +# AC_PROG_CXX macros to find the compilers - if CFLAGS and CXXFLAGS are not +# set, they will be set to Autoconf's defaults. Afterwards, if the original +# values were not set, remove the -g from the Autoconf defaults. +# (PH 02-May-07) + +remember_set_CFLAGS="$CFLAGS" +remember_set_CXXFLAGS="$CXXFLAGS" + +AC_PROG_CC +AC_PROG_CXX + +if test "x$remember_set_CFLAGS" = "x" +then + if test "$CFLAGS" = "-g -O2" + then + CFLAGS="-O2" + elif test "$CFLAGS" = "-g" + then + CFLAGS="" + fi +fi + +if test "x$remember_set_CXXFLAGS" = "x" +then + if test "$CXXFLAGS" = "-g -O2" + then + CXXFLAGS="-O2" + elif test "$CXXFLAGS" = "-g" + then + CXXFLAGS="" + fi +fi + + +AC_PROG_INSTALL +AC_LIBTOOL_WIN32_DLL +AC_PROG_LIBTOOL +AC_PROG_LN_S + +PCRE_MAJOR="pcre_major" +PCRE_MINOR="pcre_minor" +PCRE_PRERELEASE="pcre_prerelease" +PCRE_DATE="pcre_date" + +AC_SUBST(PCRE_MAJOR) +AC_SUBST(PCRE_MINOR) +AC_SUBST(PCRE_PRERELEASE) +AC_SUBST(PCRE_DATE) + +# Set a more sensible default value for $(htmldir). +if test "x$htmldir" = 'x${docdir}' +then + htmldir='${docdir}/html' +fi + +# Handle --disable-cpp +dnl MONOTONE: C++ support left out of import. +dnl AC_ARG_ENABLE(cpp, +dnl AS_HELP_STRING([--disable-cpp], +dnl [disable C++ support]), +dnl , enable_cpp=yes) +enable_cpp=no + +# Handle --enable-rebuild-chartables +dnl MONOTONE: rebuild-chartables not allowed. +dnl AC_ARG_ENABLE(rebuild-chartables, +dnl AS_HELP_STRING([--enable-rebuild-chartables], +dnl [rebuild character tables in current locale]), +dnl , enable_rebuild_chartables=no) +enable_rebuild_chartables=no + +# Handle --enable-utf8 (disabled by default) +# MONOTONE: we flip the sign of this. +AC_ARG_ENABLE(utf8, + AS_HELP_STRING([--enable-utf8], + [enable UTF-8 support]), + , enable_utf8=yes) + +# Handle --enable-unicode-properties +# MONOTONE: we flip the sign of this. +AC_ARG_ENABLE(unicode-properties, + AS_HELP_STRING([--enable-unicode-properties], + [enable Unicode properties support (implies --enable-utf8)]), + , enable_unicode_properties=yes) + +# Handle --enable-newline=NL +dnl AC_ARG_ENABLE(newline, +dnl AS_HELP_STRING([--enable-newline=NL], +dnl [use NL as newline (lf, cr, crlf, anycrlf, any; default=lf)]), +dnl , enable_newline=lf) + +# Separate newline options +ac_pcre_newline=lf +AC_ARG_ENABLE(newline-is-cr, + AS_HELP_STRING([--enable-newline-is-cr], + [use CR as newline character]), + ac_pcre_newline=cr) +AC_ARG_ENABLE(newline-is-lf, + AS_HELP_STRING([--enable-newline-is-lf], + [use LF as newline character (default)]), + ac_pcre_newline=lf) +AC_ARG_ENABLE(newline-is-crlf, + AS_HELP_STRING([--enable-newline-is-crlf], + [use CRLF as newline sequence]), + ac_pcre_newline=crlf) +AC_ARG_ENABLE(newline-is-anycrlf, + AS_HELP_STRING([--enable-newline-is-anycrlf], + [use CR, LF, or CRLF as newline sequence]), + ac_pcre_newline=anycrlf) +AC_ARG_ENABLE(newline-is-any, + AS_HELP_STRING([--enable-newline-is-any], + [use any valid Unicode newline sequence]), + ac_pcre_newline=any) +enable_newline="$ac_pcre_newline" + +# Handle --enable-bsr-anycrlf +AC_ARG_ENABLE(bsr-anycrlf, + AS_HELP_STRING([--enable-bsr-anycrlf], + [\R matches only CR, LF, CRLF by default]), + , enable_bsr_anycrlf=no) + +# Handle --enable-ebcdic +AC_ARG_ENABLE(ebcdic, + AS_HELP_STRING([--enable-ebcdic], + [assume EBCDIC coding rather than ASCII; use this only in (uncommon) EBCDIC environments; it implies --enable-rebuild-chartables]), + , enable_ebcdic=no) + +# Handle --disable-stack-for-recursion +AC_ARG_ENABLE(stack-for-recursion, + AS_HELP_STRING([--disable-stack-for-recursion], + [don't use stack recursion when matching]), + , enable_stack_for_recursion=yes) + +# Handle --enable-pcregrep-libz +AC_ARG_ENABLE(pcregrep-libz, + AS_HELP_STRING([--enable-pcregrep-libz], + [link pcregrep with libz to handle .gz files]), + , enable_pcregrep_libz=no) + +# Handle --enable-pcregrep-libbz2 +AC_ARG_ENABLE(pcregrep-libbz2, + AS_HELP_STRING([--enable-pcregrep-libbz2], + [link pcregrep with libbz2 to handle .bz2 files]), + , enable_pcregrep_libbz2=no) + +# Handle --enable-pcretest-libreadline +AC_ARG_ENABLE(pcretest-libreadline, + AS_HELP_STRING([--enable-pcretest-libreadline], + [link pcretest with libreadline]), + , enable_pcretest_libreadline=no) + +# Handle --with-posix-malloc-threshold=NBYTES +AC_ARG_WITH(posix-malloc-threshold, + AS_HELP_STRING([--with-posix-malloc-threshold=NBYTES], + [threshold for POSIX malloc usage (default=10)]), + , with_posix_malloc_threshold=10) + +# Handle --with-link-size=N +AC_ARG_WITH(link-size, + AS_HELP_STRING([--with-link-size=N], + [internal link size (2, 3, or 4 allowed; default=2)]), + , with_link_size=2) + +# Handle --with-match-limit=N +AC_ARG_WITH(match-limit, + AS_HELP_STRING([--with-match-limit=N], + [default limit on internal looping (default=10000000)]), + , with_match_limit=10000000) + +# Handle --with-match-limit_recursion=N # -# This program is made available under the GNU GPL version 2.0 or -# greater. See the accompanying file COPYING for details. +# Note: In config.h, the default is to define MATCH_LIMIT_RECURSION +# symbolically as MATCH_LIMIT, which in turn is defined to be some numeric +# value (e.g. 10000000). MATCH_LIMIT_RECURSION can otherwise be set to some +# different numeric value (or even the same numeric value as MATCH_LIMIT, +# though no longer defined in terms of the latter). # -# This program is distributed WITHOUT ANY WARRANTY; without even the -# implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR -# PURPOSE. +AC_ARG_WITH(match-limit-recursion, + AS_HELP_STRING([--with-match-limit-recursion=N], + [default limit on internal recursion (default=MATCH_LIMIT)]), + , with_match_limit_recursion=MATCH_LIMIT) -# This file will be replaced by the actual third-party library -# configuration script for all directories where that is practical. -# (It may not be practical for dead-upstream or heavily modified -# third-party libraries, e.g. netxx and idna.) It makes no attempt to -# do anything beyond the bare minimum, just like the associated -# Makefile.am. +# Make sure that if enable_unicode_properties was set, that UTF-8 support +# is enabled. +# +if test "x$enable_unicode_properties" = "xyes" +then + if test "x$enable_utf8" = "xno" + then + AC_MSG_ERROR([support for Unicode properties requires UTF-8 support]) + fi + enable_utf8=yes +fi -AC_PREREQ(2.58) -AC_INIT(pcre, XX, address@hidden) -AM_INIT_AUTOMAKE -AC_CONFIG_AUX_DIR([..]) -AC_CONFIG_MACRO_DIR([../m4]) -AC_CONFIG_SRCDIR([pcre.h]) -AC_CONFIG_FILES([Makefile]) +if test "x$enable_utf8" = "xunset" +then + enable_utf8=no +fi + +# Make sure that if enable_ebcdic is set, rebuild_chartables is also enabled. +# +if test "x$enable_ebcdic" = "xyes" +then + enable_rebuild_chartables=yes +fi + +# Convert the newline identifier into the appropriate integer value. +case "$enable_newline" in + lf) ac_pcre_newline_value=10 ;; + cr) ac_pcre_newline_value=13 ;; + crlf) ac_pcre_newline_value=3338 ;; + anycrlf) ac_pcre_newline_value=-2 ;; + any) ac_pcre_newline_value=-1 ;; + *) + AC_MSG_ERROR([invalid argument \"$enable_newline\" to --enable-newline option]) + ;; +esac + +# Check argument to --with-link-size +case "$with_link_size" in + 2|3|4) ;; + *) + AC_MSG_ERROR([invalid argument \"$with_link_size\" to --with-link-size option]) + ;; +esac + +AH_TOP([ +/* On Unix-like systems config.h.in is converted by "configure" into config.h. +Some other environments also support the use of "configure". PCRE is written in +Standard C, but there are a few non-standard things it can cope with, allowing +it to run on SunOS4 and other "close to standard" systems. + +If you are going to build PCRE "by hand" on a system without "configure" you +should copy the distributed config.h.generic to config.h, and then set up the +macro definitions the way you need them. You must then add -DHAVE_CONFIG_H to +all of your compile commands, so that config.h is included at the start of +every source. + +Alternatively, you can avoid editing by using -D on the compiler command line +to set the macro values. In this case, you do not have to set -DHAVE_CONFIG_H. + +PCRE uses memmove() if HAVE_MEMMOVE is set to 1; otherwise it uses bcopy() if +HAVE_BCOPY is set to 1. If your system has neither bcopy() nor memmove(), set +them both to 0; an emulation function will be used. */]) + +# Checks for header files. +AC_HEADER_STDC +AC_CHECK_HEADERS(limits.h sys/types.h sys/stat.h dirent.h windows.h) + +# The files below are C++ header files. +pcre_have_type_traits="0" +pcre_have_bits_type_traits="0" +if test "x$enable_cpp" = "xyes" -a -n "$CXX" +then +AC_LANG_PUSH(C++) + +# We could be more clever here, given we're doing AC_SUBST with this +# (eg set a var to be the name of the include file we want). But we're not +# so it's easy to change back to 'regular' autoconf vars if we needed to. +AC_CHECK_HEADERS(string, [pcre_have_cpp_headers="1"], + [pcre_have_cpp_headers="0"]) +AC_CHECK_HEADERS(bits/type_traits.h, [pcre_have_bits_type_traits="1"], + [pcre_have_bits_type_traits="0"]) +AC_CHECK_HEADERS(type_traits.h, [pcre_have_type_traits="1"], + [pcre_have_type_traits="0"]) +AC_LANG_POP +fi +# Using AC_SUBST eliminates the need to include config.h in a public .h file +AC_SUBST(pcre_have_type_traits) +AC_SUBST(pcre_have_bits_type_traits) + +# Conditional compilation +# MONOTONE: Not actually in Makefile anymore. +#AM_CONDITIONAL(WITH_PCRE_CPP, test "x$enable_cpp" = "xyes") +#AM_CONDITIONAL(WITH_REBUILD_CHARTABLES, test "x$enable_rebuild_chartables" = "xyes") + +# Checks for typedefs, structures, and compiler characteristics. + +AC_C_CONST +AC_TYPE_SIZE_T + +AC_CHECK_TYPES([long long], + [pcre_have_long_long="1"], + [pcre_have_long_long="0"]) +AC_CHECK_TYPES([unsigned long long], + [pcre_have_ulong_long="1"], + [pcre_have_ulong_long="0"]) +AC_SUBST(pcre_have_long_long) +AC_SUBST(pcre_have_ulong_long) + +# Checks for library functions. + +AC_CHECK_FUNCS(bcopy memmove strerror strtoq strtoll _strtoi64) + +# Check for the availability of libz (aka zlib) + +AC_CHECK_HEADERS([zlib.h], [HAVE_ZLIB_H=1]) +AC_CHECK_LIB([z], [gzopen], [HAVE_LIBZ=1]) + +# Check for the availability of libbz2 + +AC_CHECK_HEADERS([bzlib.h], [HAVE_BZLIB_H=1]) +AC_CHECK_LIB([bz2], [BZ2_bzopen], [HAVE_LIBBZ2=1]) + +# Check for the availabiity of libreadline + +AC_CHECK_HEADERS([readline/readline.h], [HAVE_READLINE_H=1]) +AC_CHECK_HEADERS([readline/history.h], [HAVE_HISTORY_H=1]) +AC_CHECK_LIB([readline], [readline], [HAVE_LIB_READLINE=1]) + +# This facilitates -ansi builds under Linux +dnl AC_DEFINE([_GNU_SOURCE], [], [Enable GNU extensions in glibc]) + +if test "x$enable_shared" = "xno" ; then + AC_DEFINE([PCRE_STATIC], [1], [ + Define if linking statically (TODO: make nice with Libtool)]) +fi + +# Here is where pcre specific defines are handled + +if test "$enable_utf8" = "yes"; then + AC_DEFINE([SUPPORT_UTF8], [], [ + Define to enable support for the UTF-8 Unicode encoding.]) +fi + +if test "$enable_unicode_properties" = "yes"; then + AC_DEFINE([SUPPORT_UCP], [], [ + Define to enable support for Unicode properties]) +fi + +if test "$enable_stack_for_recursion" = "no"; then + AC_DEFINE([NO_RECURSE], [], [ + PCRE uses recursive function calls to handle backtracking while + matching. This can sometimes be a problem on systems that have + stacks of limited size. Define NO_RECURSE to get a version that + doesn't use recursion in the match() function; instead it creates + its own stack by steam using pcre_recurse_malloc() to obtain memory + from the heap. For more detail, see the comments and other stuff + just above the match() function. On systems that support it, + "configure" can be used to set this in the Makefile + (use --disable-stack-for-recursion).]) +fi + +if test "$enable_pcregrep_libz" = "yes"; then + AC_DEFINE([SUPPORT_LIBZ], [], [ + Define to allow pcregrep to be linked with libz, so that it is + able to handle .gz files.]) +fi + +if test "$enable_pcregrep_libbz2" = "yes"; then + AC_DEFINE([SUPPORT_LIBBZ2], [], [ + Define to allow pcregrep to be linked with libbz2, so that it is + able to handle .bz2 files.]) +fi + +if test "$enable_pcretest_libreadline" = "yes"; then + AC_DEFINE([SUPPORT_LIBREADLINE], [], [ + Define to allow pcretest to be linked with libreadline.]) +fi + +AC_DEFINE_UNQUOTED([NEWLINE], [$ac_pcre_newline_value], [ + The value of NEWLINE determines the newline character sequence. On + systems that support it, "configure" can be used to override the + default, which is 10. The possible values are 10 (LF), 13 (CR), + 3338 (CRLF), -1 (ANY), or -2 (ANYCRLF).]) + +if test "$enable_bsr_anycrlf" = "yes"; then + AC_DEFINE([BSR_ANYCRLF], [], [ + By default, the \R escape sequence matches any Unicode line ending + character or sequence of characters. If BSR_ANYCRLF is defined, this is + changed so that backslash-R matches only CR, LF, or CRLF. The build- + time default can be overridden by the user of PCRE at runtime. On + systems that support it, "configure" can be used to override the + default.]) +fi + +AC_DEFINE_UNQUOTED([LINK_SIZE], [$with_link_size], [ + The value of LINK_SIZE determines the number of bytes used to store + links as offsets within the compiled regex. The default is 2, which + allows for compiled patterns up to 64K long. This covers the vast + majority of cases. However, PCRE can also be compiled to use 3 or 4 + bytes instead. This allows for longer patterns in extreme cases. On + systems that support it, "configure" can be used to override this default.]) + +AC_DEFINE_UNQUOTED([POSIX_MALLOC_THRESHOLD], [$with_posix_malloc_threshold], [ + When calling PCRE via the POSIX interface, additional working storage + is required for holding the pointers to capturing substrings because + PCRE requires three integers per substring, whereas the POSIX + interface provides only two. If the number of expected substrings is + small, the wrapper function uses space on the stack, because this is + faster than using malloc() for each call. The threshold above which + the stack is no longer used is defined by POSIX_MALLOC_THRESHOLD. On + systems that support it, "configure" can be used to override this + default.]) + +AC_DEFINE_UNQUOTED([MATCH_LIMIT], [$with_match_limit], [ + The value of MATCH_LIMIT determines the default number of times the + internal match() function can be called during a single execution of + pcre_exec(). There is a runtime interface for setting a different + limit. The limit exists in order to catch runaway regular + expressions that take for ever to determine that they do not match. + The default is set very large so that it does not accidentally catch + legitimate cases. On systems that support it, "configure" can be + used to override this default default.]) + +AC_DEFINE_UNQUOTED([MATCH_LIMIT_RECURSION], [$with_match_limit_recursion], [ + The above limit applies to all calls of match(), whether or not they + increase the recursion depth. In some environments it is desirable + to limit the depth of recursive calls of match() more strictly, in + order to restrict the maximum amount of stack (or heap, if + NO_RECURSE is defined) that is used. The value of + MATCH_LIMIT_RECURSION applies only to recursive calls of match(). To + have any useful effect, it must be less than the value of + MATCH_LIMIT. The default is to use the same value as MATCH_LIMIT. + There is a runtime method for setting a different limit. On systems + that support it, "configure" can be used to override the default.]) + +AC_DEFINE([MAX_NAME_SIZE], [32], [ + This limit is parameterized just in case anybody ever wants to + change it. Care must be taken if it is increased, because it guards + against integer overflow caused by enormously large patterns.]) + +AC_DEFINE([MAX_NAME_COUNT], [10000], [ + This limit is parameterized just in case anybody ever wants to + change it. Care must be taken if it is increased, because it guards + against integer overflow caused by enormously large patterns.]) + +AH_VERBATIM([PCRE_EXP_DEFN], [ +/* If you are compiling for a system other than a Unix-like system or + Win32, and it needs some magic to be inserted before the definition + of a function that is exported by the library, define this macro to + contain the relevant magic. If you do not define this macro, it + defaults to "extern" for a C compiler and "extern C" for a C++ + compiler on non-Win32 systems. This macro apears at the start of + every exported function that is part of the external API. It does + not appear on functions that are "external" in the C sense, but + which are internal to the library. */ +#undef PCRE_EXP_DEFN]) + +if test "$enable_ebcdic" = "yes"; then + AC_DEFINE_UNQUOTED([EBCDIC], [], [ + If you are compiling for a system that uses EBCDIC instead of ASCII + character codes, define this macro as 1. On systems that can use + "configure", this can be done via --enable-ebcdic.]) +fi + +# Platform specific issues +NO_UNDEFINED= +EXPORT_ALL_SYMBOLS= +case $host_os in + cygwin* | mingw* ) + if test X"$enable_shared" = Xyes; then + NO_UNDEFINED="-no-undefined" + EXPORT_ALL_SYMBOLS="-Wl,--export-all-symbols" + fi + ;; +esac + +# The extra LDFLAGS for each particular library +# (Note: The libpcre*_version bits are m4 variables, assigned above) + +EXTRA_LIBPCRE_LDFLAGS="$NO_UNDEFINED -version-info libpcre_version" + +EXTRA_LIBPCREPOSIX_LDFLAGS="$NO_UNDEFINED -version-info libpcreposix_version" + +EXTRA_LIBPCRECPP_LDFLAGS="$NO_UNDEFINED $EXPORT_ALL_SYMBOLS -version-info libpcrecpp_version" + +AC_SUBST(EXTRA_LIBPCRE_LDFLAGS) +AC_SUBST(EXTRA_LIBPCREPOSIX_LDFLAGS) +AC_SUBST(EXTRA_LIBPCRECPP_LDFLAGS) + +# When we run 'make distcheck', use these arguments. +DISTCHECK_CONFIGURE_FLAGS="--enable-cpp --enable-unicode-properties" +AC_SUBST(DISTCHECK_CONFIGURE_FLAGS) + +# Check that, if --enable-pcregrep-libz or --enable-pcregrep-libbz2 is +# specified, the relevant library is available. If so, add it to LIBS. + +if test "$enable_pcregrep_libz" = "yes"; then + if test "$HAVE_ZLIB_H" != "1"; then + echo "** Cannot --enable-pcregrep-libz because zlib.h was not found" + exit 1 + fi + if test "$HAVE_LIBZ" != "1"; then + echo "** Cannot --enable-pcregrep-libz because libz was not found" + exit 1 + fi + if test "$LIBS" = ""; then LIBS=-lz; else LIBS="$LIBS -lz"; fi +fi + +if test "$enable_pcregrep_libbz2" = "yes"; then + if test "$HAVE_BZLIB_H" != "1"; then + echo "** Cannot --enable-pcregrep-libbz2 because bzlib.h was not found" + exit 1 + fi + if test "$HAVE_LIBBZ2" != "1"; then + echo "** Cannot --enable-pcregrep-libbz2 because libbz2 was not found" + exit 1 + fi + if test "$LIBS" = ""; then LIBS=-lbz2; else LIBS="$LIBS -lbz2"; fi +fi + +# Similarly for --enable-pcretest-readline + +if test "$enable_pcretest_libreadline" = "yes"; then + if test "$HAVE_READLINE_H" != "1"; then + echo "** Cannot --enable-pcretest-readline because readline/readline.h was not found." + exit 1 + fi + if test "$HAVE_HISTORY_H" != "1"; then + echo "** Cannot --enable-pcretest-readline because readline/history.h was not found." + exit 1 + fi + if test "$LIBS" = ""; then LIBS=-lreadline; else LIBS="$LIBS -lreadline"; fi +fi + +# Produce these files, in addition to config.h. +# MONOTONE: C++-only generated files removed from this list. +AC_CONFIG_FILES( + Makefile + libpcre.pc + pcre-config + pcre.h +) +# libpcrecpp.pc +# pcre_stringpiece.h +# pcrecpparg.h + +# Make the generated script files executable. +AC_CONFIG_COMMANDS([script-chmod], [chmod a+x pcre-config]) + +# Make sure that pcre_chartables.c is removed in case the method for +# creating it was changed by reconfiguration. +# MONOTONE: Don't! The file is never regenerated. +#AC_CONFIG_COMMANDS([delete-old-chartables], [rm -f pcre_chartables.c]) + AC_OUTPUT + +# Print out a nice little message after configure is run displaying your +# chosen options. + +cat <