Backported from 5.5 for 5.4 by Remi Collet diff -ru php-5.4.45/ext/pcre/pcrelib/config.h php55/php-5.5.31/ext/pcre/pcrelib/config.h --- php-5.4.45/ext/pcre/pcrelib/config.h 2015-09-01 22:09:37.000000000 +0200 +++ php-5.5.31/ext/pcre/pcrelib/config.h 2016-01-06 10:36:49.000000000 +0100 @@ -302,6 +302,8 @@ */ /* #undef NO_RECURSE */ +#define PARENS_NEST_LIMIT 250 + /* Name of package */ #define PACKAGE "pcre" diff -ru php54/php-5.4.45/ext/pcre/pcrelib/pcre_exec.c php55/php-5.5.31/ext/pcre/pcrelib/pcre_exec.c --- php-5.4.45/ext/pcre/pcrelib/pcre_exec.c 2015-09-01 22:09:37.000000000 +0200 +++ php-5.5.31/ext/pcre/pcrelib/pcre_exec.c 2016-01-06 10:36:49.000000000 +0100 @@ -688,7 +688,7 @@ #define foc number #define save_mark data -/* These statements are here to stop the compiler complaining about unitialized +/* These statements are here to stop the compiler complaining about uninitialized variables. */ #ifdef SUPPORT_UCP From ca02d9c2d6f9bea7bf8abe607f1ee9484b1d7b62 Mon Sep 17 00:00:00 2001 From: Stanislav Malyshev Date: Sun, 31 Jan 2016 20:33:17 -0800 Subject: [PATCH] Upgrade bundled PCRE to 8.38 --- NEWS | 3 + ext/pcre/pcrelib/ChangeLog | 176 ++ ext/pcre/pcrelib/NEWS | 8 + ext/pcre/pcrelib/config.h | 11 +- ext/pcre/pcrelib/doc/pcre.txt | 2130 +++++++++++----------- ext/pcre/pcrelib/pcre.h | 4 +- ext/pcre/pcrelib/pcre_compile.c | 334 +++- ext/pcre/pcrelib/pcre_exec.c | 5 +- ext/pcre/pcrelib/pcre_internal.h | 17 +- ext/pcre/pcrelib/pcre_jit_compile.c | 77 +- ext/pcre/pcrelib/pcre_study.c | 19 +- ext/pcre/pcrelib/pcre_xclass.c | 2 +- ext/pcre/pcrelib/sljit/sljitConfig.h | 9 + ext/pcre/pcrelib/sljit/sljitConfigInternal.h | 13 +- ext/pcre/pcrelib/sljit/sljitLir.c | 10 +- ext/pcre/pcrelib/sljit/sljitLir.h | 128 +- ext/pcre/pcrelib/sljit/sljitNativeARM_32.c | 27 +- ext/pcre/pcrelib/sljit/sljitNativeARM_64.c | 48 +- ext/pcre/pcrelib/sljit/sljitNativeARM_T2_32.c | 58 +- ext/pcre/pcrelib/sljit/sljitNativeMIPS_common.c | 15 +- ext/pcre/pcrelib/sljit/sljitNativePPC_common.c | 23 +- ext/pcre/pcrelib/sljit/sljitNativeSPARC_common.c | 19 +- ext/pcre/pcrelib/sljit/sljitNativeTILEGX_64.c | 311 ++-- ext/pcre/pcrelib/sljit/sljitNativeX86_common.c | 129 +- ext/pcre/pcrelib/testdata/grepoutput | 12 + ext/pcre/pcrelib/testdata/testinput1 | 13 + ext/pcre/pcrelib/testdata/testinput11 | 4 + ext/pcre/pcrelib/testdata/testinput12 | 17 + ext/pcre/pcrelib/testdata/testinput14 | 2 + ext/pcre/pcrelib/testdata/testinput17 | 2 + ext/pcre/pcrelib/testdata/testinput2 | 139 ++ ext/pcre/pcrelib/testdata/testinput4 | 5 + ext/pcre/pcrelib/testdata/testinput5 | 8 + ext/pcre/pcrelib/testdata/testinput6 | 57 + ext/pcre/pcrelib/testdata/testinput7 | 15 + ext/pcre/pcrelib/testdata/testinput8 | 4 + ext/pcre/pcrelib/testdata/testinputEBC | 3 + ext/pcre/pcrelib/testdata/testoutput1 | 23 + ext/pcre/pcrelib/testdata/testoutput11-16 | 50 +- ext/pcre/pcrelib/testdata/testoutput11-32 | 50 +- ext/pcre/pcrelib/testdata/testoutput11-8 | 50 +- ext/pcre/pcrelib/testdata/testoutput12 | 25 + ext/pcre/pcrelib/testdata/testoutput14 | 2 + ext/pcre/pcrelib/testdata/testoutput17 | 2 + ext/pcre/pcrelib/testdata/testoutput2 | 380 +++- ext/pcre/pcrelib/testdata/testoutput4 | 6 + ext/pcre/pcrelib/testdata/testoutput5 | 45 + ext/pcre/pcrelib/testdata/testoutput6 | 96 + ext/pcre/pcrelib/testdata/testoutput7 | 57 +- ext/pcre/pcrelib/testdata/testoutput8 | 6 + ext/pcre/pcrelib/testdata/testoutputEBC | 6 + 51 files changed, 3144 insertions(+), 1511 deletions(-) diff --git a/ext/pcre/pcrelib/ChangeLog b/ext/pcre/pcrelib/ChangeLog index 359b412..5e5bf18 100644 --- a/ext/pcre/pcrelib/ChangeLog +++ b/ext/pcre/pcrelib/ChangeLog @@ -1,6 +1,182 @@ ChangeLog for PCRE ------------------ +Note that the PCRE 8.xx series (PCRE1) is now in a bugfix-only state. All +development is happening in the PCRE2 10.xx series. + +Version 8.38 23-November-2015 +----------------------------- + +1. If a group that contained a recursive back reference also contained a + forward reference subroutine call followed by a non-forward-reference + subroutine call, for example /.((?2)(?R)\1)()/, pcre2_compile() failed to + compile correct code, leading to undefined behaviour or an internally + detected error. This bug was discovered by the LLVM fuzzer. + +2. Quantification of certain items (e.g. atomic back references) could cause + incorrect code to be compiled when recursive forward references were + involved. For example, in this pattern: /(?1)()((((((\1++))\x85)+)|))/. + This bug was discovered by the LLVM fuzzer. + +3. A repeated conditional group whose condition was a reference by name caused + a buffer overflow if there was more than one group with the given name. + This bug was discovered by the LLVM fuzzer. + +4. A recursive back reference by name within a group that had the same name as + another group caused a buffer overflow. For example: + /(?J)(?'d'(?'d'\g{d}))/. This bug was discovered by the LLVM fuzzer. + +5. A forward reference by name to a group whose number is the same as the + current group, for example in this pattern: /(?|(\k'Pm')|(?'Pm'))/, caused + a buffer overflow at compile time. This bug was discovered by the LLVM + fuzzer. + +6. A lookbehind assertion within a set of mutually recursive subpatterns could + provoke a buffer overflow. This bug was discovered by the LLVM fuzzer. + +7. Another buffer overflow bug involved duplicate named groups with a + reference between their definition, with a group that reset capture + numbers, for example: /(?J:(?|(?'R')(\k'R')|((?'R'))))/. This has been + fixed by always allowing for more memory, even if not needed. (A proper fix + is implemented in PCRE2, but it involves more refactoring.) + +8. There was no check for integer overflow in subroutine calls such as (?123). + +9. The table entry for \l in EBCDIC environments was incorrect, leading to its + being treated as a literal 'l' instead of causing an error. + +10. There was a buffer overflow if pcre_exec() was called with an ovector of + size 1. This bug was found by american fuzzy lop. + +11. If a non-capturing group containing a conditional group that could match + an empty string was repeated, it was not identified as matching an empty + string itself. For example: /^(?:(?(1)x|)+)+$()/. + +12. In an EBCDIC environment, pcretest was mishandling the escape sequences + \a and \e in test subject lines. + +13. In an EBCDIC environment, \a in a pattern was converted to the ASCII + instead of the EBCDIC value. + +14. The handling of \c in an EBCDIC environment has been revised so that it is + now compatible with the specification in Perl's perlebcdic page. + +15. The EBCDIC character 0x41 is a non-breaking space, equivalent to 0xa0 in + ASCII/Unicode. This has now been added to the list of characters that are + recognized as white space in EBCDIC. + +16. When PCRE was compiled without UCP support, the use of \p and \P gave an + error (correctly) when used outside a class, but did not give an error + within a class. + +17. \h within a class was incorrectly compiled in EBCDIC environments. + +18. A pattern with an unmatched closing parenthesis that contained a backward + assertion which itself contained a forward reference caused buffer + overflow. And example pattern is: /(?=di(?<=(?1))|(?=(.))))/. + +19. JIT should return with error when the compiled pattern requires more stack + space than the maximum. + +20. A possessively repeated conditional group that could match an empty string, + for example, /(?(R))*+/, was incorrectly compiled. + +21. Fix infinite recursion in the JIT compiler when certain patterns such as + /(?:|a|){100}x/ are analysed. + +22. Some patterns with character classes involving [: and \\ were incorrectly + compiled and could cause reading from uninitialized memory or an incorrect + error diagnosis. + +23. Pathological patterns containing many nested occurrences of [: caused + pcre_compile() to run for a very long time. + +24. A conditional group with only one branch has an implicit empty alternative + branch and must therefore be treated as potentially matching an empty + string. + +25. If (?R was followed by - or + incorrect behaviour happened instead of a + diagnostic. + +26. Arrange to give up on finding the minimum matching length for overly + complex patterns. + +27. Similar to (4) above: in a pattern with duplicated named groups and an + occurrence of (?| it is possible for an apparently non-recursive back + reference to become recursive if a later named group with the relevant + number is encountered. This could lead to a buffer overflow. Wen Guanxing + from Venustech ADLAB discovered this bug. + +28. If pcregrep was given the -q option with -c or -l, or when handling a + binary file, it incorrectly wrote output to stdout. + +29. The JIT compiler did not restore the control verb head in case of *THEN + control verbs. This issue was found by Karl Skomski with a custom LLVM + fuzzer. + +30. Error messages for syntax errors following \g and \k were giving inaccurate + offsets in the pattern. + +31. Added a check for integer overflow in conditions (?() and + (?(R). This omission was discovered by Karl Skomski with the LLVM + fuzzer. + +32. Handling recursive references such as (?2) when the reference is to a group + later in the pattern uses code that is very hacked about and error-prone. + It has been re-written for PCRE2. Here in PCRE1, a check has been added to + give an internal error if it is obvious that compiling has gone wrong. + +33. The JIT compiler should not check repeats after a {0,1} repeat byte code. + This issue was found by Karl Skomski with a custom LLVM fuzzer. + +34. The JIT compiler should restore the control chain for empty possessive + repeats. This issue was found by Karl Skomski with a custom LLVM fuzzer. + +35. Match limit check added to JIT recursion. This issue was found by Karl + Skomski with a custom LLVM fuzzer. + +36. Yet another case similar to 27 above has been circumvented by an + unconditional allocation of extra memory. This issue is fixed "properly" in + PCRE2 by refactoring the way references are handled. Wen Guanxing + from Venustech ADLAB discovered this bug. + +37. Fix two assertion fails in JIT. These issues were found by Karl Skomski + with a custom LLVM fuzzer. + +38. Fixed a corner case of range optimization in JIT. + +39. An incorrect error "overran compiling workspace" was given if there were + exactly enough group forward references such that the last one extended + into the workspace safety margin. The next one would have expanded the + workspace. The test for overflow was not including the safety margin. + +40. A match limit issue is fixed in JIT which was found by Karl Skomski + with a custom LLVM fuzzer. + +41. Remove the use of /dev/null in testdata/testinput2, because it doesn't + work under Windows. (Why has it taken so long for anyone to notice?) + +42. In a character class such as [\W\p{Any}] where both a negative-type escape + ("not a word character") and a property escape were present, the property + escape was being ignored. + +43. Fix crash caused by very long (*MARK) or (*THEN) names. + +44. A sequence such as [[:punct:]b] that is, a POSIX character class followed + by a single ASCII character in a class item, was incorrectly compiled in + UCP mode. The POSIX class got lost, but only if the single character + followed it. + +45. [:punct:] in UCP mode was matching some characters in the range 128-255 + that should not have been matched. + +46. If [:^ascii:] or [:^xdigit:] or [:^cntrl:] are present in a non-negated + class, all characters with code points greater than 255 are in the class. + When a Unicode property was also in the class (if PCRE_UCP is set, escapes + such as \w are turned into Unicode properties), wide characters were not + correctly handled, and could fail to match. + + Version 8.37 28-April-2015 -------------------------- diff --git a/ext/pcre/pcrelib/NEWS b/ext/pcre/pcrelib/NEWS index 064bf27..7e42dcb 100644 --- a/ext/pcre/pcrelib/NEWS +++ b/ext/pcre/pcrelib/NEWS @@ -1,6 +1,14 @@ News about PCRE releases ------------------------ +Release 8.38 23-November-2015 +----------------------------- + +This is bug-fix release. Note that this library (now called PCRE1) is now being +maintained for bug fixes only. New projects are advised to use the new PCRE2 +libraries. + + Release 8.37 28-April-2015 -------------------------- diff --git a/ext/pcre/pcrelib/config.h b/ext/pcre/pcrelib/config.h index ba06a17..0f7a9f7 100644 --- a/ext/pcre/pcrelib/config.h +++ b/ext/pcre/pcrelib/config.h @@ -234,8 +234,8 @@ them both to 0; an emulation function will be used. */ #define LINK_SIZE 2 #endif -/* Define to the sub-directory in which libtool stores uninstalled libraries. - */ +/* Define to the sub-directory where libtool stores uninstalled libraries. */ +/* This is ignored unless you are using libtool. */ #ifndef LT_OBJDIR #define LT_OBJDIR ".libs/" #endif @@ -314,7 +314,7 @@ them both to 0; an emulation function will be used. */ #define PACKAGE_NAME "PCRE" /* Define to the full name and version of this package. */ -#define PACKAGE_STRING "PCRE 8.37" +#define PACKAGE_STRING "PCRE 8.38" /* Define to the one symbol short name of this package. */ #define PACKAGE_TARNAME "pcre" @@ -323,7 +323,7 @@ them both to 0; an emulation function will be used. */ #define PACKAGE_URL "" /* Define to the version of this package. */ -#define PACKAGE_VERSION "8.37" +#define PACKAGE_VERSION "8.38" /* to make a symbol visible */ /* #undef PCRECPP_EXP_DECL */ @@ -439,7 +439,7 @@ them both to 0; an emulation function will be used. */ /* Version number of package */ #ifndef VERSION -#define VERSION "8.37" +#define VERSION "8.38" #endif /* Define to empty if `const' does not conform to ANSI C. */ @@ -451,4 +451,3 @@ them both to 0; an emulation function will be used. */ /* Define to `unsigned int' if does not define. */ /* #undef size_t */ - diff --git a/ext/pcre/pcrelib/doc/pcre.txt b/ext/pcre/pcrelib/doc/pcre.txt index ce27f4b..76a47c7 100644 --- a/ext/pcre/pcrelib/doc/pcre.txt +++ b/ext/pcre/pcrelib/doc/pcre.txt @@ -13,7 +13,18 @@ PCRE(3) Library Functions Manual PCRE(3) NAME - PCRE - Perl-compatible regular expressions + PCRE - Perl-compatible regular expressions (original API) + +PLEASE TAKE NOTE + + This document relates to PCRE releases that use the original API, with + library names libpcre, libpcre16, and libpcre32. January 2015 saw the + first release of a new API, known as PCRE2, with release numbers start- + ing at 10.00 and library names libpcre2-8, libpcre2-16, and + libpcre2-32. The old libraries (now called PCRE1) are still being main- + tained for bug fixes, but there will be no new development. New + projects are advised to use the new PCRE2 libraries. + INTRODUCTION @@ -179,8 +190,8 @@ AUTHOR REVISION - Last updated: 08 January 2014 - Copyright (c) 1997-2014 University of Cambridge. + Last updated: 10 February 2015 + Copyright (c) 1997-2015 University of Cambridge. ------------------------------------------------------------------------------ @@ -4989,7 +5000,8 @@ BACKSLASH appearance of non-printing characters, apart from the binary zero that terminates a pattern, but when a pattern is being prepared by text editing, it is often easier to use one of the following escape - sequences than the binary character it represents: + sequences than the binary character it represents. In an ASCII or Uni- + code environment, these escapes are as follows: \a alarm, that is, the BEL character (hex 07) \cx "control-x", where x is any ASCII character @@ -5005,55 +5017,67 @@ BACKSLASH \x{hhh..} character with hex code hhh.. (non-JavaScript mode) \uhhhh character with hex code hhhh (JavaScript mode only) - The precise effect of \cx on ASCII characters is as follows: if x is a - lower case letter, it is converted to upper case. Then bit 6 of the + The precise effect of \cx on ASCII characters is as follows: if x is a + lower case letter, it is converted to upper case. Then bit 6 of the character (hex 40) is inverted. Thus \cA to \cZ become hex 01 to hex 1A - (A is 41, Z is 5A), but \c{ becomes hex 3B ({ is 7B), and \c; becomes - hex 7B (; is 3B). If the data item (byte or 16-bit value) following \c - has a value greater than 127, a compile-time error occurs. This locks + (A is 41, Z is 5A), but \c{ becomes hex 3B ({ is 7B), and \c; becomes + hex 7B (; is 3B). If the data item (byte or 16-bit value) following \c + has a value greater than 127, a compile-time error occurs. This locks out non-ASCII characters in all modes. - The \c facility was designed for use with ASCII characters, but with - the extension to Unicode it is even less useful than it once was. It - is, however, recognized when PCRE is compiled in EBCDIC mode, where - data items are always bytes. In this mode, all values are valid after - \c. If the next character is a lower case letter, it is converted to - upper case. Then the 0xc0 bits of the byte are inverted. Thus \cA - becomes hex 01, as in ASCII (A is C1), but because the EBCDIC letters - are disjoint, \cZ becomes hex 29 (Z is E9), and other characters also - generate different values. - - After \0 up to two further octal digits are read. If there are fewer - than two digits, just those that are present are used. Thus the - sequence \0\x\07 specifies two binary zeros followed by a BEL character - (code value 7). Make sure you supply two digits after the initial zero + When PCRE is compiled in EBCDIC mode, \a, \e, \f, \n, \r, and \t gener- + ate the appropriate EBCDIC code values. The \c escape is processed as + specified for Perl in the perlebcdic document. The only characters that + are allowed after \c are A-Z, a-z, or one of @, [, \, ], ^, _, or ?. + Any other character provokes a compile-time error. The sequence \@ + encodes character code 0; the letters (in either case) encode charac- + ters 1-26 (hex 01 to hex 1A); [, \, ], ^, and _ encode characters 27-31 + (hex 1B to hex 1F), and \? becomes either 255 (hex FF) or 95 (hex 5F). + + Thus, apart from \?, these escapes generate the same character code + values as they do in an ASCII environment, though the meanings of the + values mostly differ. For example, \G always generates code value 7, + which is BEL in ASCII but DEL in EBCDIC. + + The sequence \? generates DEL (127, hex 7F) in an ASCII environment, + but because 127 is not a control character in EBCDIC, Perl makes it + generate the APC character. Unfortunately, there are several variants + of EBCDIC. In most of them the APC character has the value 255 (hex + FF), but in the one Perl calls POSIX-BC its value is 95 (hex 5F). If + certain other characters have POSIX-BC values, PCRE makes \? generate + 95; otherwise it generates 255. + + After \0 up to two further octal digits are read. If there are fewer + than two digits, just those that are present are used. Thus the + sequence \0\x\015 specifies two binary zeros followed by a CR character + (code value 13). Make sure you supply two digits after the initial zero if the pattern character that follows is itself an octal digit. - The escape \o must be followed by a sequence of octal digits, enclosed - in braces. An error occurs if this is not the case. This escape is a - recent addition to Perl; it provides way of specifying character code - points as octal numbers greater than 0777, and it also allows octal + The escape \o must be followed by a sequence of octal digits, enclosed + in braces. An error occurs if this is not the case. This escape is a + recent addition to Perl; it provides way of specifying character code + points as octal numbers greater than 0777, and it also allows octal numbers and back references to be unambiguously specified. For greater clarity and unambiguity, it is best to avoid following \ by a digit greater than zero. Instead, use \o{} or \x{} to specify charac- - ter numbers, and \g{} to specify back references. The following para- + ter numbers, and \g{} to specify back references. The following para- graphs describe the old, ambiguous syntax. The handling of a backslash followed by a digit other than 0 is compli- - cated, and Perl has changed in recent releases, causing PCRE also to + cated, and Perl has changed in recent releases, causing PCRE also to change. Outside a character class, PCRE reads the digit and any follow- - ing digits as a decimal number. If the number is less than 8, or if - there have been at least that many previous capturing left parentheses - in the expression, the entire sequence is taken as a back reference. A - description of how this works is given later, following the discussion + ing digits as a decimal number. If the number is less than 8, or if + there have been at least that many previous capturing left parentheses + in the expression, the entire sequence is taken as a back reference. A + description of how this works is given later, following the discussion of parenthesized subpatterns. - Inside a character class, or if the decimal number following \ is + Inside a character class, or if the decimal number following \ is greater than 7 and there have not been that many capturing subpatterns, - PCRE handles \8 and \9 as the literal characters "8" and "9", and oth- + PCRE handles \8 and \9 as the literal characters "8" and "9", and oth- erwise re-reads up to three octal digits following the backslash, using - them to generate a data character. Any subsequent digits stand for + them to generate a data character. Any subsequent digits stand for themselves. For example: \040 is another way of writing an ASCII space @@ -5071,31 +5095,31 @@ BACKSLASH \81 is either a back reference, or the two characters "8" and "1" - Note that octal values of 100 or greater that are specified using this - syntax must not be introduced by a leading zero, because no more than + Note that octal values of 100 or greater that are specified using this + syntax must not be introduced by a leading zero, because no more than three octal digits are ever read. - By default, after \x that is not followed by {, from zero to two hexa- - decimal digits are read (letters can be in upper or lower case). Any + By default, after \x that is not followed by {, from zero to two hexa- + decimal digits are read (letters can be in upper or lower case). Any number of hexadecimal digits may appear between \x{ and }. If a charac- - ter other than a hexadecimal digit appears between \x{ and }, or if + ter other than a hexadecimal digit appears between \x{ and }, or if there is no terminating }, an error occurs. - If the PCRE_JAVASCRIPT_COMPAT option is set, the interpretation of \x - is as just described only when it is followed by two hexadecimal dig- - its. Otherwise, it matches a literal "x" character. In JavaScript + If the PCRE_JAVASCRIPT_COMPAT option is set, the interpretation of \x + is as just described only when it is followed by two hexadecimal dig- + its. Otherwise, it matches a literal "x" character. In JavaScript mode, support for code points greater than 256 is provided by \u, which - must be followed by four hexadecimal digits; otherwise it matches a + must be followed by four hexadecimal digits; otherwise it matches a literal "u" character. Characters whose value is less than 256 can be defined by either of the - two syntaxes for \x (or by \u in JavaScript mode). There is no differ- + two syntaxes for \x (or by \u in JavaScript mode). There is no differ- ence in the way they are handled. For example, \xdc is exactly the same as \x{dc} (or \u00dc in JavaScript mode). Constraints on character values - Characters that are specified using octal or hexadecimal numbers are + Characters that are specified using octal or hexadecimal numbers are limited to certain values, as follows: 8-bit non-UTF mode less than 0x100 @@ -5105,44 +5129,44 @@ BACKSLASH 32-bit non-UTF mode less than 0x100000000 32-bit UTF-32 mode less than 0x10ffff and a valid codepoint - Invalid Unicode codepoints are the range 0xd800 to 0xdfff (the so- + Invalid Unicode codepoints are the range 0xd800 to 0xdfff (the so- called "surrogate" codepoints), and 0xffef. Escape sequences in character classes All the sequences that define a single character value can be used both - inside and outside character classes. In addition, inside a character + inside and outside character classes. In addition, inside a character class, \b is interpreted as the backspace character (hex 08). - \N is not allowed in a character class. \B, \R, and \X are not special - inside a character class. Like other unrecognized escape sequences, - they are treated as the literal characters "B", "R", and "X" by - default, but cause an error if the PCRE_EXTRA option is set. Outside a + \N is not allowed in a character class. \B, \R, and \X are not special + inside a character class. Like other unrecognized escape sequences, + they are treated as the literal characters "B", "R", and "X" by + default, but cause an error if the PCRE_EXTRA option is set. Outside a character class, these sequences have different meanings. Unsupported escape sequences - In Perl, the sequences \l, \L, \u, and \U are recognized by its string - handler and used to modify the case of following characters. By - default, PCRE does not support these escape sequences. However, if the - PCRE_JAVASCRIPT_COMPAT option is set, \U matches a "U" character, and + In Perl, the sequences \l, \L, \u, and \U are recognized by its string + handler and used to modify the case of following characters. By + default, PCRE does not support these escape sequences. However, if the + PCRE_JAVASCRIPT_COMPAT option is set, \U matches a "U" character, and \u can be used to define a character by code point, as described in the previous section. Absolute and relative back references - The sequence \g followed by an unsigned or a negative number, option- - ally enclosed in braces, is an absolute or relative back reference. A + The sequence \g followed by an unsigned or a negative number, option- + ally enclosed in braces, is an absolute or relative back reference. A named back reference can be coded as \g{name}. Back references are dis- cussed later, following the discussion of parenthesized subpatterns. Absolute and relative subroutine calls - For compatibility with Oniguruma, the non-Perl syntax \g followed by a + For compatibility with Oniguruma, the non-Perl syntax \g followed by a name or a number enclosed either in angle brackets or single quotes, is - an alternative syntax for referencing a subpattern as a "subroutine". - Details are discussed later. Note that \g{...} (Perl syntax) and - \g<...> (Oniguruma syntax) are not synonymous. The former is a back + an alternative syntax for referencing a subpattern as a "subroutine". + Details are discussed later. Note that \g{...} (Perl syntax) and + \g<...> (Oniguruma syntax) are not synonymous. The former is a back reference; the latter is a subroutine call. Generic character types @@ -5161,59 +5185,59 @@ BACKSLASH \W any "non-word" character There is also the single sequence \N, which matches a non-newline char- - acter. This is the same as the "." metacharacter when PCRE_DOTALL is - not set. Perl also uses \N to match characters by name; PCRE does not + acter. This is the same as the "." metacharacter when PCRE_DOTALL is + not set. Perl also uses \N to match characters by name; PCRE does not support this. - Each pair of lower and upper case escape sequences partitions the com- - plete set of characters into two disjoint sets. Any given character - matches one, and only one, of each pair. The sequences can appear both - inside and outside character classes. They each match one character of - the appropriate type. If the current matching point is at the end of - the subject string, all of them fail, because there is no character to + Each pair of lower and upper case escape sequences partitions the com- + plete set of characters into two disjoint sets. Any given character + matches one, and only one, of each pair. The sequences can appear both + inside and outside character classes. They each match one character of + the appropriate type. If the current matching point is at the end of + the subject string, all of them fail, because there is no character to match. - For compatibility with Perl, \s did not used to match the VT character - (code 11), which made it different from the the POSIX "space" class. - However, Perl added VT at release 5.18, and PCRE followed suit at - release 8.34. The default \s characters are now HT (9), LF (10), VT - (11), FF (12), CR (13), and space (32), which are defined as white + For compatibility with Perl, \s did not used to match the VT character + (code 11), which made it different from the the POSIX "space" class. + However, Perl added VT at release 5.18, and PCRE followed suit at + release 8.34. The default \s characters are now HT (9), LF (10), VT + (11), FF (12), CR (13), and space (32), which are defined as white space in the "C" locale. This list may vary if locale-specific matching - is taking place. For example, in some locales the "non-breaking space" - character (\xA0) is recognized as white space, and in others the VT + is taking place. For example, in some locales the "non-breaking space" + character (\xA0) is recognized as white space, and in others the VT character is not. - A "word" character is an underscore or any character that is a letter - or digit. By default, the definition of letters and digits is con- - trolled by PCRE's low-valued character tables, and may vary if locale- - specific matching is taking place (see "Locale support" in the pcreapi - page). For example, in a French locale such as "fr_FR" in Unix-like - systems, or "french" in Windows, some character codes greater than 127 - are used for accented letters, and these are then matched by \w. The + A "word" character is an underscore or any character that is a letter + or digit. By default, the definition of letters and digits is con- + trolled by PCRE's low-valued character tables, and may vary if locale- + specific matching is taking place (see "Locale support" in the pcreapi + page). For example, in a French locale such as "fr_FR" in Unix-like + systems, or "french" in Windows, some character codes greater than 127 + are used for accented letters, and these are then matched by \w. The use of locales with Unicode is discouraged. - By default, characters whose code points are greater than 127 never + By default, characters whose code points are greater than 127 never match \d, \s, or \w, and always match \D, \S, and \W, although this may - vary for characters in the range 128-255 when locale-specific matching - is happening. These escape sequences retain their original meanings - from before Unicode support was available, mainly for efficiency rea- - sons. If PCRE is compiled with Unicode property support, and the - PCRE_UCP option is set, the behaviour is changed so that Unicode prop- + vary for characters in the range 128-255 when locale-specific matching + is happening. These escape sequences retain their original meanings + from before Unicode support was available, mainly for efficiency rea- + sons. If PCRE is compiled with Unicode property support, and the + PCRE_UCP option is set, the behaviour is changed so that Unicode prop- erties are used to determine character types, as follows: \d any character that matches \p{Nd} (decimal digit) \s any character that matches \p{Z} or \h or \v \w any character that matches \p{L} or \p{N}, plus underscore - The upper case escapes match the inverse sets of characters. Note that - \d matches only decimal digits, whereas \w matches any Unicode digit, - as well as any Unicode letter, and underscore. Note also that PCRE_UCP - affects \b, and \B because they are defined in terms of \w and \W. + The upper case escapes match the inverse sets of characters. Note that + \d matches only decimal digits, whereas \w matches any Unicode digit, + as well as any Unicode letter, and underscore. Note also that PCRE_UCP + affects \b, and \B because they are defined in terms of \w and \W. Matching these sequences is noticeably slower when PCRE_UCP is set. - The sequences \h, \H, \v, and \V are features that were added to Perl - at release 5.10. In contrast to the other sequences, which match only - ASCII characters by default, these always match certain high-valued + The sequences \h, \H, \v, and \V are features that were added to Perl + at release 5.10. In contrast to the other sequences, which match only + ASCII characters by default, these always match certain high-valued code points, whether or not PCRE_UCP is set. The horizontal space char- acters are: @@ -5252,110 +5276,110 @@ BACKSLASH Newline sequences - Outside a character class, by default, the escape sequence \R matches - any Unicode newline sequence. In 8-bit non-UTF-8 mode \R is equivalent + Outside a character class, by default, the escape sequence \R matches + any Unicode newline sequence. In 8-bit non-UTF-8 mode \R is equivalent to the following: (?>\r\n|\n|\x0b|\f|\r|\x85) - This is an example of an "atomic group", details of which are given + This is an example of an "atomic group", details of which are given below. This particular group matches either the two-character sequence - CR followed by LF, or one of the single characters LF (linefeed, - U+000A), VT (vertical tab, U+000B), FF (form feed, U+000C), CR (car- - riage return, U+000D), or NEL (next line, U+0085). The two-character + CR followed by LF, or one of the single characters LF (linefeed, + U+000A), VT (vertical tab, U+000B), FF (form feed, U+000C), CR (car- + riage return, U+000D), or NEL (next line, U+0085). The two-character sequence is treated as a single unit that cannot be split. - In other modes, two additional characters whose codepoints are greater + In other modes, two additional characters whose codepoints are greater than 255 are added: LS (line separator, U+2028) and PS (paragraph sepa- - rator, U+2029). Unicode character property support is not needed for + rator, U+2029). Unicode character property support is not needed for these characters to be recognized. It is possible to restrict \R to match only CR, LF, or CRLF (instead of - the complete set of Unicode line endings) by setting the option + the complete set of Unicode line endings) by setting the option PCRE_BSR_ANYCRLF either at compile time or when the pattern is matched. (BSR is an abbrevation for "backslash R".) This can be made the default - when PCRE is built; if this is the case, the other behaviour can be - requested via the PCRE_BSR_UNICODE option. It is also possible to - specify these settings by starting a pattern string with one of the + when PCRE is built; if this is the case, the other behaviour can be + requested via the PCRE_BSR_UNICODE option. It is also possible to + specify these settings by starting a pattern string with one of the following sequences: (*BSR_ANYCRLF) CR, LF, or CRLF only (*BSR_UNICODE) any Unicode newline sequence These override the default and the options given to the compiling func- - tion, but they can themselves be overridden by options given to a - matching function. Note that these special settings, which are not - Perl-compatible, are recognized only at the very start of a pattern, - and that they must be in upper case. If more than one of them is - present, the last one is used. They can be combined with a change of + tion, but they can themselves be overridden by options given to a + matching function. Note that these special settings, which are not + Perl-compatible, are recognized only at the very start of a pattern, + and that they must be in upper case. If more than one of them is + present, the last one is used. They can be combined with a change of newline convention; for example, a pattern can start with: (*ANY)(*BSR_ANYCRLF) - They can also be combined with the (*UTF8), (*UTF16), (*UTF32), (*UTF) + They can also be combined with the (*UTF8), (*UTF16), (*UTF32), (*UTF) or (*UCP) special sequences. Inside a character class, \R is treated as - an unrecognized escape sequence, and so matches the letter "R" by + an unrecognized escape sequence, and so matches the letter "R" by default, but causes an error if PCRE_EXTRA is set. Unicode character properties When PCRE is built with Unicode character property support, three addi- - tional escape sequences that match characters with specific properties - are available. When in 8-bit non-UTF-8 mode, these sequences are of - course limited to testing characters whose codepoints are less than + tional escape sequences that match characters with specific properties + are available. When in 8-bit non-UTF-8 mode, these sequences are of + course limited to testing characters whose codepoints are less than 256, but they do work in this mode. The extra escape sequences are: \p{xx} a character with the xx property \P{xx} a character without the xx property \X a Unicode extended grapheme cluster - The property names represented by xx above are limited to the Unicode + The property names represented by xx above are limited to the Unicode script names, the general category properties, "Any", which matches any - character (including newline), and some special PCRE properties - (described in the next section). Other Perl properties such as "InMu- - sicalSymbols" are not currently supported by PCRE. Note that \P{Any} + character (including newline), and some special PCRE properties + (described in the next section). Other Perl properties such as "InMu- + sicalSymbols" are not currently supported by PCRE. Note that \P{Any} does not match any characters, so always causes a match failure. Sets of Unicode characters are defined as belonging to certain scripts. - A character from one of these sets can be matched using a script name. + A character from one of these sets can be matched using a script name. For example: \p{Greek} \P{Han} - Those that are not part of an identified script are lumped together as + Those that are not part of an identified script are lumped together as "Common". The current list of scripts is: - Arabic, Armenian, Avestan, Balinese, Bamum, Bassa_Vah, Batak, Bengali, - Bopomofo, Brahmi, Braille, Buginese, Buhid, Canadian_Aboriginal, Car- + Arabic, Armenian, Avestan, Balinese, Bamum, Bassa_Vah, Batak, Bengali, + Bopomofo, Brahmi, Braille, Buginese, Buhid, Canadian_Aboriginal, Car- ian, Caucasian_Albanian, Chakma, Cham, Cherokee, Common, Coptic, Cunei- form, Cypriot, Cyrillic, Deseret, Devanagari, Duployan, Egyptian_Hiero- glyphs, Elbasan, Ethiopic, Georgian, Glagolitic, Gothic, Grantha, - Greek, Gujarati, Gurmukhi, Han, Hangul, Hanunoo, Hebrew, Hiragana, - Imperial_Aramaic, Inherited, Inscriptional_Pahlavi, Inscrip- - tional_Parthian, Javanese, Kaithi, Kannada, Katakana, Kayah_Li, - Kharoshthi, Khmer, Khojki, Khudawadi, Lao, Latin, Lepcha, Limbu, Lin- - ear_A, Linear_B, Lisu, Lycian, Lydian, Mahajani, Malayalam, Mandaic, - Manichaean, Meetei_Mayek, Mende_Kikakui, Meroitic_Cursive, - Meroitic_Hieroglyphs, Miao, Modi, Mongolian, Mro, Myanmar, Nabataean, - New_Tai_Lue, Nko, Ogham, Ol_Chiki, Old_Italic, Old_North_Arabian, + Greek, Gujarati, Gurmukhi, Han, Hangul, Hanunoo, Hebrew, Hiragana, + Imperial_Aramaic, Inherited, Inscriptional_Pahlavi, Inscrip- + tional_Parthian, Javanese, Kaithi, Kannada, Katakana, Kayah_Li, + Kharoshthi, Khmer, Khojki, Khudawadi, Lao, Latin, Lepcha, Limbu, Lin- + ear_A, Linear_B, Lisu, Lycian, Lydian, Mahajani, Malayalam, Mandaic, + Manichaean, Meetei_Mayek, Mende_Kikakui, Meroitic_Cursive, + Meroitic_Hieroglyphs, Miao, Modi, Mongolian, Mro, Myanmar, Nabataean, + New_Tai_Lue, Nko, Ogham, Ol_Chiki, Old_Italic, Old_North_Arabian, Old_Permic, Old_Persian, Old_South_Arabian, Old_Turkic, Oriya, Osmanya, Pahawh_Hmong, Palmyrene, Pau_Cin_Hau, Phags_Pa, Phoenician, - Psalter_Pahlavi, Rejang, Runic, Samaritan, Saurashtra, Sharada, Sha- - vian, Siddham, Sinhala, Sora_Sompeng, Sundanese, Syloti_Nagri, Syriac, - Tagalog, Tagbanwa, Tai_Le, Tai_Tham, Tai_Viet, Takri, Tamil, Telugu, - Thaana, Thai, Tibetan, Tifinagh, Tirhuta, Ugaritic, Vai, Warang_Citi, + Psalter_Pahlavi, Rejang, Runic, Samaritan, Saurashtra, Sharada, Sha- + vian, Siddham, Sinhala, Sora_Sompeng, Sundanese, Syloti_Nagri, Syriac, + Tagalog, Tagbanwa, Tai_Le, Tai_Tham, Tai_Viet, Takri, Tamil, Telugu, + Thaana, Thai, Tibetan, Tifinagh, Tirhuta, Ugaritic, Vai, Warang_Citi, Yi. Each character has exactly one Unicode general category property, spec- - ified by a two-letter abbreviation. For compatibility with Perl, nega- - tion can be specified by including a circumflex between the opening - brace and the property name. For example, \p{^Lu} is the same as + ified by a two-letter abbreviation. For compatibility with Perl, nega- + tion can be specified by including a circumflex between the opening + brace and the property name. For example, \p{^Lu} is the same as \P{Lu}. If only one letter is specified with \p or \P, it includes all the gen- - eral category properties that start with that letter. In this case, in - the absence of negation, the curly brackets in the escape sequence are + eral category properties that start with that letter. In this case, in + the absence of negation, the curly brackets in the escape sequence are optional; these two examples have the same effect: \p{L} @@ -5407,73 +5431,73 @@ BACKSLASH Zp Paragraph separator Zs Space separator - The special property L& is also supported: it matches a character that - has the Lu, Ll, or Lt property, in other words, a letter that is not + The special property L& is also supported: it matches a character that + has the Lu, Ll, or Lt property, in other words, a letter that is not classified as a modifier or "other". - The Cs (Surrogate) property applies only to characters in the range - U+D800 to U+DFFF. Such characters are not valid in Unicode strings and - so cannot be tested by PCRE, unless UTF validity checking has been + The Cs (Surrogate) property applies only to characters in the range + U+D800 to U+DFFF. Such characters are not valid in Unicode strings and + so cannot be tested by PCRE, unless UTF validity checking has been turned off (see the discussion of PCRE_NO_UTF8_CHECK, - PCRE_NO_UTF16_CHECK and PCRE_NO_UTF32_CHECK in the pcreapi page). Perl + PCRE_NO_UTF16_CHECK and PCRE_NO_UTF32_CHECK in the pcreapi page). Perl does not support the Cs property. - The long synonyms for property names that Perl supports (such as - \p{Letter}) are not supported by PCRE, nor is it permitted to prefix + The long synonyms for property names that Perl supports (such as + \p{Letter}) are not supported by PCRE, nor is it permitted to prefix any of these properties with "Is". No character that is in the Unicode table has the Cn (unassigned) prop- erty. Instead, this property is assumed for any code point that is not in the Unicode table. - Specifying caseless matching does not affect these escape sequences. - For example, \p{Lu} always matches only upper case letters. This is + Specifying caseless matching does not affect these escape sequences. + For example, \p{Lu} always matches only upper case letters. This is different from the behaviour of current versions of Perl. - Matching characters by Unicode property is not fast, because PCRE has - to do a multistage table lookup in order to find a character's prop- + Matching characters by Unicode property is not fast, because PCRE has + to do a multistage table lookup in order to find a character's prop- erty. That is why the traditional escape sequences such as \d and \w do not use Unicode properties in PCRE by default, though you can make them - do so by setting the PCRE_UCP option or by starting the pattern with + do so by setting the PCRE_UCP option or by starting the pattern with (*UCP). Extended grapheme clusters - The \X escape matches any number of Unicode characters that form an + The \X escape matches any number of Unicode characters that form an "extended grapheme cluster", and treats the sequence as an atomic group - (see below). Up to and including release 8.31, PCRE matched an ear- + (see below). Up to and including release 8.31, PCRE matched an ear- lier, simpler definition that was equivalent to (?>\PM\pM*) - That is, it matched a character without the "mark" property, followed - by zero or more characters with the "mark" property. Characters with - the "mark" property are typically non-spacing accents that affect the + That is, it matched a character without the "mark" property, followed + by zero or more characters with the "mark" property. Characters with + the "mark" property are typically non-spacing accents that affect the preceding character. - This simple definition was extended in Unicode to include more compli- - cated kinds of composite character by giving each character a grapheme - breaking property, and creating rules that use these properties to - define the boundaries of extended grapheme clusters. In releases of + This simple definition was extended in Unicode to include more compli- + cated kinds of composite character by giving each character a grapheme + breaking property, and creating rules that use these properties to + define the boundaries of extended grapheme clusters. In releases of PCRE later than 8.31, \X matches one of these clusters. - \X always matches at least one character. Then it decides whether to + \X always matches at least one character. Then it decides whether to add additional characters according to the following rules for ending a cluster: 1. End at the end of the subject string. - 2. Do not end between CR and LF; otherwise end after any control char- + 2. Do not end between CR and LF; otherwise end after any control char- acter. - 3. Do not break Hangul (a Korean script) syllable sequences. Hangul - characters are of five types: L, V, T, LV, and LVT. An L character may - be followed by an L, V, LV, or LVT character; an LV or V character may + 3. Do not break Hangul (a Korean script) syllable sequences. Hangul + characters are of five types: L, V, T, LV, and LVT. An L character may + be followed by an L, V, LV, or LVT character; an LV or V character may be followed by a V or T character; an LVT or T character may be follwed only by a T character. - 4. Do not end before extending characters or spacing marks. Characters - with the "mark" property always have the "extend" grapheme breaking + 4. Do not end before extending characters or spacing marks. Characters + with the "mark" property always have the "extend" grapheme breaking property. 5. Do not end after prepend characters. @@ -5482,9 +5506,9 @@ BACKSLASH PCRE's additional properties - As well as the standard Unicode properties described above, PCRE sup- - ports four more that make it possible to convert traditional escape - sequences such as \w and \s to use Unicode properties. PCRE uses these + As well as the standard Unicode properties described above, PCRE sup- + ports four more that make it possible to convert traditional escape + sequences such as \w and \s to use Unicode properties. PCRE uses these non-standard, non-Perl properties internally when PCRE_UCP is set. How- ever, they may also be used explicitly. These properties are: @@ -5493,54 +5517,54 @@ BACKSLASH Xsp Any Perl space character Xwd Any Perl "word" character - Xan matches characters that have either the L (letter) or the N (num- - ber) property. Xps matches the characters tab, linefeed, vertical tab, - form feed, or carriage return, and any other character that has the Z - (separator) property. Xsp is the same as Xps; it used to exclude ver- - tical tab, for Perl compatibility, but Perl changed, and so PCRE fol- - lowed at release 8.34. Xwd matches the same characters as Xan, plus + Xan matches characters that have either the L (letter) or the N (num- + ber) property. Xps matches the characters tab, linefeed, vertical tab, + form feed, or carriage return, and any other character that has the Z + (separator) property. Xsp is the same as Xps; it used to exclude ver- + tical tab, for Perl compatibility, but Perl changed, and so PCRE fol- + lowed at release 8.34. Xwd matches the same characters as Xan, plus underscore. - There is another non-standard property, Xuc, which matches any charac- - ter that can be represented by a Universal Character Name in C++ and - other programming languages. These are the characters $, @, ` (grave - accent), and all characters with Unicode code points greater than or - equal to U+00A0, except for the surrogates U+D800 to U+DFFF. Note that - most base (ASCII) characters are excluded. (Universal Character Names - are of the form \uHHHH or \UHHHHHHHH where H is a hexadecimal digit. + There is another non-standard property, Xuc, which matches any charac- + ter that can be represented by a Universal Character Name in C++ and + other programming languages. These are the characters $, @, ` (grave + accent), and all characters with Unicode code points greater than or + equal to U+00A0, except for the surrogates U+D800 to U+DFFF. Note that + most base (ASCII) characters are excluded. (Universal Character Names + are of the form \uHHHH or \UHHHHHHHH where H is a hexadecimal digit. Note that the Xuc property does not match these sequences but the char- acters that they represent.) Resetting the match start - The escape sequence \K causes any previously matched characters not to + The escape sequence \K causes any previously matched characters not to be included in the final matched sequence. For example, the pattern: foo\Kbar - matches "foobar", but reports that it has matched "bar". This feature - is similar to a lookbehind assertion (described below). However, in - this case, the part of the subject before the real match does not have - to be of fixed length, as lookbehind assertions do. The use of \K does - not interfere with the setting of captured substrings. For example, + matches "foobar", but reports that it has matched "bar". This feature + is similar to a lookbehind assertion (described below). However, in + this case, the part of the subject before the real match does not have + to be of fixed length, as lookbehind assertions do. The use of \K does + not interfere with the setting of captured substrings. For example, when the pattern (foo)\Kbar matches "foobar", the first substring is still set to "foo". - Perl documents that the use of \K within assertions is "not well - defined". In PCRE, \K is acted upon when it occurs inside positive - assertions, but is ignored in negative assertions. Note that when a - pattern such as (?=ab\K) matches, the reported start of the match can + Perl documents that the use of \K within assertions is "not well + defined". In PCRE, \K is acted upon when it occurs inside positive + assertions, but is ignored in negative assertions. Note that when a + pattern such as (?=ab\K) matches, the reported start of the match can be greater than the end of the match. Simple assertions - The final use of backslash is for certain simple assertions. An asser- - tion specifies a condition that has to be met at a particular point in - a match, without consuming any characters from the subject string. The - use of subpatterns for more complicated assertions is described below. + The final use of backslash is for certain simple assertions. An asser- + tion specifies a condition that has to be met at a particular point in + a match, without consuming any characters from the subject string. The + use of subpatterns for more complicated assertions is described below. The backslashed assertions are: \b matches at a word boundary @@ -5551,161 +5575,161 @@ BACKSLASH \z matches only at the end of the subject \G matches at the first matching position in the subject - Inside a character class, \b has a different meaning; it matches the - backspace character. If any other of these assertions appears in a - character class, by default it matches the corresponding literal char- + Inside a character class, \b has a different meaning; it matches the + backspace character. If any other of these assertions appears in a + character class, by default it matches the corresponding literal char- acter (for example, \B matches the letter B). However, if the - PCRE_EXTRA option is set, an "invalid escape sequence" error is gener- + PCRE_EXTRA option is set, an "invalid escape sequence" error is gener- ated instead. - A word boundary is a position in the subject string where the current - character and the previous character do not both match \w or \W (i.e. - one matches \w and the other matches \W), or the start or end of the - string if the first or last character matches \w, respectively. In a - UTF mode, the meanings of \w and \W can be changed by setting the - PCRE_UCP option. When this is done, it also affects \b and \B. Neither - PCRE nor Perl has a separate "start of word" or "end of word" metase- - quence. However, whatever follows \b normally determines which it is. + A word boundary is a position in the subject string where the current + character and the previous character do not both match \w or \W (i.e. + one matches \w and the other matches \W), or the start or end of the + string if the first or last character matches \w, respectively. In a + UTF mode, the meanings of \w and \W can be changed by setting the + PCRE_UCP option. When this is done, it also affects \b and \B. Neither + PCRE nor Perl has a separate "start of word" or "end of word" metase- + quence. However, whatever follows \b normally determines which it is. For example, the fragment \ba matches "a" at the start of a word. - The \A, \Z, and \z assertions differ from the traditional circumflex + The \A, \Z, and \z assertions differ from the traditional circumflex and dollar (described in the next section) in that they only ever match - at the very start and end of the subject string, whatever options are - set. Thus, they are independent of multiline mode. These three asser- + at the very start and end of the subject string, whatever options are + set. Thus, they are independent of multiline mode. These three asser- tions are not affected by the PCRE_NOTBOL or PCRE_NOTEOL options, which - affect only the behaviour of the circumflex and dollar metacharacters. - However, if the startoffset argument of pcre_exec() is non-zero, indi- + affect only the behaviour of the circumflex and dollar metacharacters. + However, if the startoffset argument of pcre_exec() is non-zero, indi- cating that matching is to start at a point other than the beginning of - the subject, \A can never match. The difference between \Z and \z is + the subject, \A can never match. The difference between \Z and \z is that \Z matches before a newline at the end of the string as well as at the very end, whereas \z matches only at the end. - The \G assertion is true only when the current matching position is at - the start point of the match, as specified by the startoffset argument - of pcre_exec(). It differs from \A when the value of startoffset is - non-zero. By calling pcre_exec() multiple times with appropriate argu- + The \G assertion is true only when the current matching position is at + the start point of the match, as specified by the startoffset argument + of pcre_exec(). It differs from \A when the value of startoffset is + non-zero. By calling pcre_exec() multiple times with appropriate argu- ments, you can mimic Perl's /g option, and it is in this kind of imple- mentation where \G can be useful. - Note, however, that PCRE's interpretation of \G, as the start of the + Note, however, that PCRE's interpretation of \G, as the start of the current match, is subtly different from Perl's, which defines it as the - end of the previous match. In Perl, these can be different when the - previously matched string was empty. Because PCRE does just one match + end of the previous match. In Perl, these can be different when the + previously matched string was empty. Because PCRE does just one match at a time, it cannot reproduce this behaviour. - If all the alternatives of a pattern begin with \G, the expression is + If all the alternatives of a pattern begin with \G, the expression is anchored to the starting match position, and the "anchored" flag is set in the compiled regular expression. CIRCUMFLEX AND DOLLAR - The circumflex and dollar metacharacters are zero-width assertions. - That is, they test for a particular condition being true without con- + The circumflex and dollar metacharacters are zero-width assertions. + That is, they test for a particular condition being true without con- suming any characters from the subject string. Outside a character class, in the default matching mode, the circumflex - character is an assertion that is true only if the current matching - point is at the start of the subject string. If the startoffset argu- - ment of pcre_exec() is non-zero, circumflex can never match if the - PCRE_MULTILINE option is unset. Inside a character class, circumflex + character is an assertion that is true only if the current matching + point is at the start of the subject string. If the startoffset argu- + ment of pcre_exec() is non-zero, circumflex can never match if the + PCRE_MULTILINE option is unset. Inside a character class, circumflex has an entirely different meaning (see below). - Circumflex need not be the first character of the pattern if a number - of alternatives are involved, but it should be the first thing in each - alternative in which it appears if the pattern is ever to match that - branch. If all possible alternatives start with a circumflex, that is, - if the pattern is constrained to match only at the start of the sub- - ject, it is said to be an "anchored" pattern. (There are also other + Circumflex need not be the first character of the pattern if a number + of alternatives are involved, but it should be the first thing in each + alternative in which it appears if the pattern is ever to match that + branch. If all possible alternatives start with a circumflex, that is, + if the pattern is constrained to match only at the start of the sub- + ject, it is said to be an "anchored" pattern. (There are also other constructs that can cause a pattern to be anchored.) - The dollar character is an assertion that is true only if the current - matching point is at the end of the subject string, or immediately - before a newline at the end of the string (by default). Note, however, - that it does not actually match the newline. Dollar need not be the + The dollar character is an assertion that is true only if the current + matching point is at the end of the subject string, or immediately + before a newline at the end of the string (by default). Note, however, + that it does not actually match the newline. Dollar need not be the last character of the pattern if a number of alternatives are involved, - but it should be the last item in any branch in which it appears. Dol- + but it should be the last item in any branch in which it appears. Dol- lar has no special meaning in a character class. - The meaning of dollar can be changed so that it matches only at the - very end of the string, by setting the PCRE_DOLLAR_ENDONLY option at + The meaning of dollar can be changed so that it matches only at the + very end of the string, by setting the PCRE_DOLLAR_ENDONLY option at compile time. This does not affect the \Z assertion. The meanings of the circumflex and dollar characters are changed if the - PCRE_MULTILINE option is set. When this is the case, a circumflex - matches immediately after internal newlines as well as at the start of - the subject string. It does not match after a newline that ends the - string. A dollar matches before any newlines in the string, as well as - at the very end, when PCRE_MULTILINE is set. When newline is specified - as the two-character sequence CRLF, isolated CR and LF characters do + PCRE_MULTILINE option is set. When this is the case, a circumflex + matches immediately after internal newlines as well as at the start of + the subject string. It does not match after a newline that ends the + string. A dollar matches before any newlines in the string, as well as + at the very end, when PCRE_MULTILINE is set. When newline is specified + as the two-character sequence CRLF, isolated CR and LF characters do not indicate newlines. - For example, the pattern /^abc$/ matches the subject string "def\nabc" - (where \n represents a newline) in multiline mode, but not otherwise. - Consequently, patterns that are anchored in single line mode because - all branches start with ^ are not anchored in multiline mode, and a - match for circumflex is possible when the startoffset argument of - pcre_exec() is non-zero. The PCRE_DOLLAR_ENDONLY option is ignored if + For example, the pattern /^abc$/ matches the subject string "def\nabc" + (where \n represents a newline) in multiline mode, but not otherwise. + Consequently, patterns that are anchored in single line mode because + all branches start with ^ are not anchored in multiline mode, and a + match for circumflex is possible when the startoffset argument of + pcre_exec() is non-zero. The PCRE_DOLLAR_ENDONLY option is ignored if PCRE_MULTILINE is set. - Note that the sequences \A, \Z, and \z can be used to match the start - and end of the subject in both modes, and if all branches of a pattern - start with \A it is always anchored, whether or not PCRE_MULTILINE is + Note that the sequences \A, \Z, and \z can be used to match the start + and end of the subject in both modes, and if all branches of a pattern + start with \A it is always anchored, whether or not PCRE_MULTILINE is set. FULL STOP (PERIOD, DOT) AND \N Outside a character class, a dot in the pattern matches any one charac- - ter in the subject string except (by default) a character that signi- + ter in the subject string except (by default) a character that signi- fies the end of a line. - When a line ending is defined as a single character, dot never matches - that character; when the two-character sequence CRLF is used, dot does - not match CR if it is immediately followed by LF, but otherwise it - matches all characters (including isolated CRs and LFs). When any Uni- - code line endings are being recognized, dot does not match CR or LF or + When a line ending is defined as a single character, dot never matches + that character; when the two-character sequence CRLF is used, dot does + not match CR if it is immediately followed by LF, but otherwise it + matches all characters (including isolated CRs and LFs). When any Uni- + code line endings are being recognized, dot does not match CR or LF or any of the other line ending characters. - The behaviour of dot with regard to newlines can be changed. If the - PCRE_DOTALL option is set, a dot matches any one character, without + The behaviour of dot with regard to newlines can be changed. If the + PCRE_DOTALL option is set, a dot matches any one character, without exception. If the two-character sequence CRLF is present in the subject string, it takes two dots to match it. - The handling of dot is entirely independent of the handling of circum- - flex and dollar, the only relationship being that they both involve + The handling of dot is entirely independent of the handling of circum- + flex and dollar, the only relationship being that they both involve newlines. Dot has no special meaning in a character class. - The escape sequence \N behaves like a dot, except that it is not - affected by the PCRE_DOTALL option. In other words, it matches any - character except one that signifies the end of a line. Perl also uses + The escape sequence \N behaves like a dot, except that it is not + affected by the PCRE_DOTALL option. In other words, it matches any + character except one that signifies the end of a line. Perl also uses \N to match characters by name; PCRE does not support this. MATCHING A SINGLE DATA UNIT - Outside a character class, the escape sequence \C matches any one data - unit, whether or not a UTF mode is set. In the 8-bit library, one data - unit is one byte; in the 16-bit library it is a 16-bit unit; in the - 32-bit library it is a 32-bit unit. Unlike a dot, \C always matches - line-ending characters. The feature is provided in Perl in order to + Outside a character class, the escape sequence \C matches any one data + unit, whether or not a UTF mode is set. In the 8-bit library, one data + unit is one byte; in the 16-bit library it is a 16-bit unit; in the + 32-bit library it is a 32-bit unit. Unlike a dot, \C always matches + line-ending characters. The feature is provided in Perl in order to match individual bytes in UTF-8 mode, but it is unclear how it can use- - fully be used. Because \C breaks up characters into individual data - units, matching one unit with \C in a UTF mode means that the rest of + fully be used. Because \C breaks up characters into individual data + units, matching one unit with \C in a UTF mode means that the rest of the string may start with a malformed UTF character. This has undefined results, because PCRE assumes that it is dealing with valid UTF strings - (and by default it checks this at the start of processing unless the - PCRE_NO_UTF8_CHECK, PCRE_NO_UTF16_CHECK or PCRE_NO_UTF32_CHECK option + (and by default it checks this at the start of processing unless the + PCRE_NO_UTF8_CHECK, PCRE_NO_UTF16_CHECK or PCRE_NO_UTF32_CHECK option is used). - PCRE does not allow \C to appear in lookbehind assertions (described - below) in a UTF mode, because this would make it impossible to calcu- + PCRE does not allow \C to appear in lookbehind assertions (described + below) in a UTF mode, because this would make it impossible to calcu- late the length of the lookbehind. In general, the \C escape sequence is best avoided. However, one way of - using it that avoids the problem of malformed UTF characters is to use - a lookahead to check the length of the next character, as in this pat- - tern, which could be used with a UTF-8 string (ignore white space and + using it that avoids the problem of malformed UTF characters is to use + a lookahead to check the length of the next character, as in this pat- + tern, which could be used with a UTF-8 string (ignore white space and line breaks): (?| (?=[\x00-\x7f])(\C) | @@ -5713,11 +5737,11 @@ MATCHING A SINGLE DATA UNIT (?=[\x{800}-\x{ffff}])(\C)(\C)(\C) | (?=[\x{10000}-\x{1fffff}])(\C)(\C)(\C)(\C)) - A group that starts with (?| resets the capturing parentheses numbers - in each alternative (see "Duplicate Subpattern Numbers" below). The - assertions at the start of each branch check the next UTF-8 character - for values whose encoding uses 1, 2, 3, or 4 bytes, respectively. The - character's individual bytes are then captured by the appropriate num- + A group that starts with (?| resets the capturing parentheses numbers + in each alternative (see "Duplicate Subpattern Numbers" below). The + assertions at the start of each branch check the next UTF-8 character + for values whose encoding uses 1, 2, 3, or 4 bytes, respectively. The + character's individual bytes are then captured by the appropriate num- ber of groups. @@ -5727,109 +5751,109 @@ SQUARE BRACKETS AND CHARACTER CLASSES closing square bracket. A closing square bracket on its own is not spe- cial by default. However, if the PCRE_JAVASCRIPT_COMPAT option is set, a lone closing square bracket causes a compile-time error. If a closing - square bracket is required as a member of the class, it should be the - first data character in the class (after an initial circumflex, if + square bracket is required as a member of the class, it should be the + first data character in the class (after an initial circumflex, if present) or escaped with a backslash. - A character class matches a single character in the subject. In a UTF - mode, the character may be more than one data unit long. A matched + A character class matches a single character in the subject. In a UTF + mode, the character may be more than one data unit long. A matched character must be in the set of characters defined by the class, unless - the first character in the class definition is a circumflex, in which + the first character in the class definition is a circumflex, in which case the subject character must not be in the set defined by the class. - If a circumflex is actually required as a member of the class, ensure + If a circumflex is actually required as a member of the class, ensure it is not the first character, or escape it with a backslash. - For example, the character class [aeiou] matches any lower case vowel, - while [^aeiou] matches any character that is not a lower case vowel. + For example, the character class [aeiou] matches any lower case vowel, + while [^aeiou] matches any character that is not a lower case vowel. Note that a circumflex is just a convenient notation for specifying the - characters that are in the class by enumerating those that are not. A - class that starts with a circumflex is not an assertion; it still con- - sumes a character from the subject string, and therefore it fails if + characters that are in the class by enumerating those that are not. A + class that starts with a circumflex is not an assertion; it still con- + sumes a character from the subject string, and therefore it fails if the current pointer is at the end of the string. In UTF-8 (UTF-16, UTF-32) mode, characters with values greater than 255 - (0xffff) can be included in a class as a literal string of data units, + (0xffff) can be included in a class as a literal string of data units, or by using the \x{ escaping mechanism. - When caseless matching is set, any letters in a class represent both - their upper case and lower case versions, so for example, a caseless - [aeiou] matches "A" as well as "a", and a caseless [^aeiou] does not - match "A", whereas a caseful version would. In a UTF mode, PCRE always - understands the concept of case for characters whose values are less - than 128, so caseless matching is always possible. For characters with - higher values, the concept of case is supported if PCRE is compiled - with Unicode property support, but not otherwise. If you want to use - caseless matching in a UTF mode for characters 128 and above, you must - ensure that PCRE is compiled with Unicode property support as well as + When caseless matching is set, any letters in a class represent both + their upper case and lower case versions, so for example, a caseless + [aeiou] matches "A" as well as "a", and a caseless [^aeiou] does not + match "A", whereas a caseful version would. In a UTF mode, PCRE always + understands the concept of case for characters whose values are less + than 128, so caseless matching is always possible. For characters with + higher values, the concept of case is supported if PCRE is compiled + with Unicode property support, but not otherwise. If you want to use + caseless matching in a UTF mode for characters 128 and above, you must + ensure that PCRE is compiled with Unicode property support as well as with UTF support. - Characters that might indicate line breaks are never treated in any - special way when matching character classes, whatever line-ending - sequence is in use, and whatever setting of the PCRE_DOTALL and + Characters that might indicate line breaks are never treated in any + special way when matching character classes, whatever line-ending + sequence is in use, and whatever setting of the PCRE_DOTALL and PCRE_MULTILINE options is used. A class such as [^a] always matches one of these characters. - The minus (hyphen) character can be used to specify a range of charac- - ters in a character class. For example, [d-m] matches any letter - between d and m, inclusive. If a minus character is required in a - class, it must be escaped with a backslash or appear in a position - where it cannot be interpreted as indicating a range, typically as the + The minus (hyphen) character can be used to specify a range of charac- + ters in a character class. For example, [d-m] matches any letter + between d and m, inclusive. If a minus character is required in a + class, it must be escaped with a backslash or appear in a position + where it cannot be interpreted as indicating a range, typically as the first or last character in the class, or immediately after a range. For - example, [b-d-z] matches letters in the range b to d, a hyphen charac- + example, [b-d-z] matches letters in the range b to d, a hyphen charac- ter, or z. It is not possible to have the literal character "]" as the end charac- - ter of a range. A pattern such as [W-]46] is interpreted as a class of - two characters ("W" and "-") followed by a literal string "46]", so it - would match "W46]" or "-46]". However, if the "]" is escaped with a - backslash it is interpreted as the end of range, so [W-\]46] is inter- - preted as a class containing a range followed by two other characters. - The octal or hexadecimal representation of "]" can also be used to end + ter of a range. A pattern such as [W-]46] is interpreted as a class of + two characters ("W" and "-") followed by a literal string "46]", so it + would match "W46]" or "-46]". However, if the "]" is escaped with a + backslash it is interpreted as the end of range, so [W-\]46] is inter- + preted as a class containing a range followed by two other characters. + The octal or hexadecimal representation of "]" can also be used to end a range. - An error is generated if a POSIX character class (see below) or an - escape sequence other than one that defines a single character appears - at a point where a range ending character is expected. For example, + An error is generated if a POSIX character class (see below) or an + escape sequence other than one that defines a single character appears + at a point where a range ending character is expected. For example, [z-\xff] is valid, but [A-\d] and [A-[:digit:]] are not. - Ranges operate in the collating sequence of character values. They can - also be used for characters specified numerically, for example - [\000-\037]. Ranges can include any characters that are valid for the + Ranges operate in the collating sequence of character values. They can + also be used for characters specified numerically, for example + [\000-\037]. Ranges can include any characters that are valid for the current mode. If a range that includes letters is used when caseless matching is set, it matches the letters in either case. For example, [W-c] is equivalent - to [][\\^_`wxyzabc], matched caselessly, and in a non-UTF mode, if - character tables for a French locale are in use, [\xc8-\xcb] matches - accented E characters in both cases. In UTF modes, PCRE supports the - concept of case for characters with values greater than 128 only when + to [][\\^_`wxyzabc], matched caselessly, and in a non-UTF mode, if + character tables for a French locale are in use, [\xc8-\xcb] matches + accented E characters in both cases. In UTF modes, PCRE supports the + concept of case for characters with values greater than 128 only when it is compiled with Unicode property support. - The character escape sequences \d, \D, \h, \H, \p, \P, \s, \S, \v, \V, + The character escape sequences \d, \D, \h, \H, \p, \P, \s, \S, \v, \V, \w, and \W may appear in a character class, and add the characters that - they match to the class. For example, [\dABCDEF] matches any hexadeci- - mal digit. In UTF modes, the PCRE_UCP option affects the meanings of - \d, \s, \w and their upper case partners, just as it does when they - appear outside a character class, as described in the section entitled + they match to the class. For example, [\dABCDEF] matches any hexadeci- + mal digit. In UTF modes, the PCRE_UCP option affects the meanings of + \d, \s, \w and their upper case partners, just as it does when they + appear outside a character class, as described in the section entitled "Generic character types" above. The escape sequence \b has a different - meaning inside a character class; it matches the backspace character. - The sequences \B, \N, \R, and \X are not special inside a character - class. Like any other unrecognized escape sequences, they are treated - as the literal characters "B", "N", "R", and "X" by default, but cause + meaning inside a character class; it matches the backspace character. + The sequences \B, \N, \R, and \X are not special inside a character + class. Like any other unrecognized escape sequences, they are treated + as the literal characters "B", "N", "R", and "X" by default, but cause an error if the PCRE_EXTRA option is set. - A circumflex can conveniently be used with the upper case character - types to specify a more restricted set of characters than the matching - lower case type. For example, the class [^\W_] matches any letter or + A circumflex can conveniently be used with the upper case character + types to specify a more restricted set of characters than the matching + lower case type. For example, the class [^\W_] matches any letter or digit, but not underscore, whereas [\w] includes underscore. A positive character class should be read as "something OR something OR ..." and a negative class as "NOT something AND NOT something AND NOT ...". - The only metacharacters that are recognized in character classes are - backslash, hyphen (only where it can be interpreted as specifying a - range), circumflex (only at the start), opening square bracket (only - when it can be interpreted as introducing a POSIX class name, or for a - special compatibility feature - see the next two sections), and the + The only metacharacters that are recognized in character classes are + backslash, hyphen (only where it can be interpreted as specifying a + range), circumflex (only at the start), opening square bracket (only + when it can be interpreted as introducing a POSIX class name, or for a + special compatibility feature - see the next two sections), and the terminating closing square bracket. However, escaping other non- alphanumeric characters does no harm. @@ -5837,7 +5861,7 @@ SQUARE BRACKETS AND CHARACTER CLASSES POSIX CHARACTER CLASSES Perl supports the POSIX notation for character classes. This uses names - enclosed by [: and :] within the enclosing square brackets. PCRE also + enclosed by [: and :] within the enclosing square brackets. PCRE also supports this notation. For example, [01[:alpha:]%] @@ -5860,28 +5884,28 @@ POSIX CHARACTER CLASSES word "word" characters (same as \w) xdigit hexadecimal digits - The default "space" characters are HT (9), LF (10), VT (11), FF (12), - CR (13), and space (32). If locale-specific matching is taking place, - the list of space characters may be different; there may be fewer or + The default "space" characters are HT (9), LF (10), VT (11), FF (12), + CR (13), and space (32). If locale-specific matching is taking place, + the list of space characters may be different; there may be fewer or more of them. "Space" used to be different to \s, which did not include VT, for Perl compatibility. However, Perl changed at release 5.18, and - PCRE followed at release 8.34. "Space" and \s now match the same set + PCRE followed at release 8.34. "Space" and \s now match the same set of characters. - The name "word" is a Perl extension, and "blank" is a GNU extension - from Perl 5.8. Another Perl extension is negation, which is indicated + The name "word" is a Perl extension, and "blank" is a GNU extension + from Perl 5.8. Another Perl extension is negation, which is indicated by a ^ character after the colon. For example, [12[:^digit:]] - matches "1", "2", or any non-digit. PCRE (and Perl) also recognize the + matches "1", "2", or any non-digit. PCRE (and Perl) also recognize the POSIX syntax [.ch.] and [=ch=] where "ch" is a "collating element", but these are not supported, and an error is given if they are encountered. By default, characters with values greater than 128 do not match any of - the POSIX character classes. However, if the PCRE_UCP option is passed - to pcre_compile(), some of the classes are changed so that Unicode - character properties are used. This is achieved by replacing certain + the POSIX character classes. However, if the PCRE_UCP option is passed + to pcre_compile(), some of the classes are changed so that Unicode + character properties are used. This is achieved by replacing certain POSIX classes by other sequences, as follows: [:alnum:] becomes \p{Xan} @@ -5893,10 +5917,10 @@ POSIX CHARACTER CLASSES [:upper:] becomes \p{Lu} [:word:] becomes \p{Xwd} - Negated versions, such as [:^alpha:] use \P instead of \p. Three other + Negated versions, such as [:^alpha:] use \P instead of \p. Three other POSIX classes are handled specially in UCP mode: - [:graph:] This matches characters that have glyphs that mark the page + [:graph:] This matches characters that have glyphs that mark the page when printed. In Unicode property terms, it matches all char- acters with the L, M, N, P, S, or Cf properties, except for: @@ -5905,58 +5929,58 @@ POSIX CHARACTER CLASSES U+2066 - U+2069 Various "isolate"s - [:print:] This matches the same characters as [:graph:] plus space - characters that are not controls, that is, characters with + [:print:] This matches the same characters as [:graph:] plus space + characters that are not controls, that is, characters with the Zs property. [:punct:] This matches all characters that have the Unicode P (punctua- - tion) property, plus those characters whose code points are + tion) property, plus those characters whose code points are less than 128 that have the S (Symbol) property. - The other POSIX classes are unchanged, and match only characters with + The other POSIX classes are unchanged, and match only characters with code points less than 128. COMPATIBILITY FEATURE FOR WORD BOUNDARIES - In the POSIX.2 compliant library that was included in 4.4BSD Unix, the - ugly syntax [[:<:]] and [[:>:]] is used for matching "start of word" + In the POSIX.2 compliant library that was included in 4.4BSD Unix, the + ugly syntax [[:<:]] and [[:>:]] is used for matching "start of word" and "end of word". PCRE treats these items as follows: [[:<:]] is converted to \b(?=\w) [[:>:]] is converted to \b(?<=\w) Only these exact character sequences are recognized. A sequence such as - [a[:<:]b] provokes error for an unrecognized POSIX class name. This - support is not compatible with Perl. It is provided to help migrations + [a[:<:]b] provokes error for an unrecognized POSIX class name. This + support is not compatible with Perl. It is provided to help migrations from other environments, and is best not used in any new patterns. Note - that \b matches at the start and the end of a word (see "Simple asser- - tions" above), and in a Perl-style pattern the preceding or following - character normally shows which is wanted, without the need for the - assertions that are used above in order to give exactly the POSIX be- + that \b matches at the start and the end of a word (see "Simple asser- + tions" above), and in a Perl-style pattern the preceding or following + character normally shows which is wanted, without the need for the + assertions that are used above in order to give exactly the POSIX be- haviour. VERTICAL BAR - Vertical bar characters are used to separate alternative patterns. For + Vertical bar characters are used to separate alternative patterns. For example, the pattern gilbert|sullivan - matches either "gilbert" or "sullivan". Any number of alternatives may - appear, and an empty alternative is permitted (matching the empty + matches either "gilbert" or "sullivan". Any number of alternatives may + appear, and an empty alternative is permitted (matching the empty string). The matching process tries each alternative in turn, from left - to right, and the first one that succeeds is used. If the alternatives - are within a subpattern (defined below), "succeeds" means matching the + to right, and the first one that succeeds is used. If the alternatives + are within a subpattern (defined below), "succeeds" means matching the rest of the main pattern as well as the alternative in the subpattern. INTERNAL OPTION SETTING - The settings of the PCRE_CASELESS, PCRE_MULTILINE, PCRE_DOTALL, and - PCRE_EXTENDED options (which are Perl-compatible) can be changed from - within the pattern by a sequence of Perl option letters enclosed + The settings of the PCRE_CASELESS, PCRE_MULTILINE, PCRE_DOTALL, and + PCRE_EXTENDED options (which are Perl-compatible) can be changed from + within the pattern by a sequence of Perl option letters enclosed between "(?" and ")". The option letters are i for PCRE_CASELESS @@ -5966,51 +5990,51 @@ INTERNAL OPTION SETTING For example, (?im) sets caseless, multiline matching. It is also possi- ble to unset these options by preceding the letter with a hyphen, and a - combined setting and unsetting such as (?im-sx), which sets PCRE_CASE- - LESS and PCRE_MULTILINE while unsetting PCRE_DOTALL and PCRE_EXTENDED, - is also permitted. If a letter appears both before and after the + combined setting and unsetting such as (?im-sx), which sets PCRE_CASE- + LESS and PCRE_MULTILINE while unsetting PCRE_DOTALL and PCRE_EXTENDED, + is also permitted. If a letter appears both before and after the hyphen, the option is unset. - The PCRE-specific options PCRE_DUPNAMES, PCRE_UNGREEDY, and PCRE_EXTRA - can be changed in the same way as the Perl-compatible options by using + The PCRE-specific options PCRE_DUPNAMES, PCRE_UNGREEDY, and PCRE_EXTRA + can be changed in the same way as the Perl-compatible options by using the characters J, U and X respectively. - When one of these option changes occurs at top level (that is, not - inside subpattern parentheses), the change applies to the remainder of + When one of these option changes occurs at top level (that is, not + inside subpattern parentheses), the change applies to the remainder of the pattern that follows. If the change is placed right at the start of a pattern, PCRE extracts it into the global options (and it will there- fore show up in data extracted by the pcre_fullinfo() function). - An option change within a subpattern (see below for a description of - subpatterns) affects only that part of the subpattern that follows it, + An option change within a subpattern (see below for a description of + subpatterns) affects only that part of the subpattern that follows it, so (a(?i)b)c matches abc and aBc and no other strings (assuming PCRE_CASELESS is not - used). By this means, options can be made to have different settings - in different parts of the pattern. Any changes made in one alternative - do carry on into subsequent branches within the same subpattern. For + used). By this means, options can be made to have different settings + in different parts of the pattern. Any changes made in one alternative + do carry on into subsequent branches within the same subpattern. For example, (a(?i)b|c) - matches "ab", "aB", "c", and "C", even though when matching "C" the - first branch is abandoned before the option setting. This is because - the effects of option settings happen at compile time. There would be + matches "ab", "aB", "c", and "C", even though when matching "C" the + first branch is abandoned before the option setting. This is because + the effects of option settings happen at compile time. There would be some very weird behaviour otherwise. - Note: There are other PCRE-specific options that can be set by the - application when the compiling or matching functions are called. In - some cases the pattern can contain special leading sequences such as - (*CRLF) to override what the application has set or what has been - defaulted. Details are given in the section entitled "Newline - sequences" above. There are also the (*UTF8), (*UTF16),(*UTF32), and - (*UCP) leading sequences that can be used to set UTF and Unicode prop- - erty modes; they are equivalent to setting the PCRE_UTF8, PCRE_UTF16, - PCRE_UTF32 and the PCRE_UCP options, respectively. The (*UTF) sequence - is a generic version that can be used with any of the libraries. How- - ever, the application can set the PCRE_NEVER_UTF option, which locks + Note: There are other PCRE-specific options that can be set by the + application when the compiling or matching functions are called. In + some cases the pattern can contain special leading sequences such as + (*CRLF) to override what the application has set or what has been + defaulted. Details are given in the section entitled "Newline + sequences" above. There are also the (*UTF8), (*UTF16),(*UTF32), and + (*UCP) leading sequences that can be used to set UTF and Unicode prop- + erty modes; they are equivalent to setting the PCRE_UTF8, PCRE_UTF16, + PCRE_UTF32 and the PCRE_UCP options, respectively. The (*UTF) sequence + is a generic version that can be used with any of the libraries. How- + ever, the application can set the PCRE_NEVER_UTF option, which locks out the use of the (*UTF) sequences. @@ -6023,18 +6047,18 @@ SUBPATTERNS cat(aract|erpillar|) - matches "cataract", "caterpillar", or "cat". Without the parentheses, + matches "cataract", "caterpillar", or "cat". Without the parentheses, it would match "cataract", "erpillar" or an empty string. - 2. It sets up the subpattern as a capturing subpattern. This means - that, when the whole pattern matches, that portion of the subject + 2. It sets up the subpattern as a capturing subpattern. This means + that, when the whole pattern matches, that portion of the subject string that matched the subpattern is passed back to the caller via the - ovector argument of the matching function. (This applies only to the - traditional matching functions; the DFA matching functions do not sup- + ovector argument of the matching function. (This applies only to the + traditional matching functions; the DFA matching functions do not sup- port capturing.) Opening parentheses are counted from left to right (starting from 1) to - obtain numbers for the capturing subpatterns. For example, if the + obtain numbers for the capturing subpatterns. For example, if the string "the red king" is matched against the pattern the ((red|white) (king|queen)) @@ -6042,12 +6066,12 @@ SUBPATTERNS the captured substrings are "red king", "red", and "king", and are num- bered 1, 2, and 3, respectively. - The fact that plain parentheses fulfil two functions is not always - helpful. There are often times when a grouping subpattern is required - without a capturing requirement. If an opening parenthesis is followed - by a question mark and a colon, the subpattern does not do any captur- - ing, and is not counted when computing the number of any subsequent - capturing subpatterns. For example, if the string "the white queen" is + The fact that plain parentheses fulfil two functions is not always + helpful. There are often times when a grouping subpattern is required + without a capturing requirement. If an opening parenthesis is followed + by a question mark and a colon, the subpattern does not do any captur- + ing, and is not counted when computing the number of any subsequent + capturing subpatterns. For example, if the string "the white queen" is matched against the pattern the ((?:red|white) (king|queen)) @@ -6055,37 +6079,37 @@ SUBPATTERNS the captured substrings are "white queen" and "queen", and are numbered 1 and 2. The maximum number of capturing subpatterns is 65535. - As a convenient shorthand, if any option settings are required at the - start of a non-capturing subpattern, the option letters may appear + As a convenient shorthand, if any option settings are required at the + start of a non-capturing subpattern, the option letters may appear between the "?" and the ":". Thus the two patterns (?i:saturday|sunday) (?:(?i)saturday|sunday) match exactly the same set of strings. Because alternative branches are - tried from left to right, and options are not reset until the end of - the subpattern is reached, an option setting in one branch does affect - subsequent branches, so the above patterns match "SUNDAY" as well as + tried from left to right, and options are not reset until the end of + the subpattern is reached, an option setting in one branch does affect + subsequent branches, so the above patterns match "SUNDAY" as well as "Saturday". DUPLICATE SUBPATTERN NUMBERS Perl 5.10 introduced a feature whereby each alternative in a subpattern - uses the same numbers for its capturing parentheses. Such a subpattern - starts with (?| and is itself a non-capturing subpattern. For example, + uses the same numbers for its capturing parentheses. Such a subpattern + starts with (?| and is itself a non-capturing subpattern. For example, consider this pattern: (?|(Sat)ur|(Sun))day - Because the two alternatives are inside a (?| group, both sets of cap- - turing parentheses are numbered one. Thus, when the pattern matches, - you can look at captured substring number one, whichever alternative - matched. This construct is useful when you want to capture part, but + Because the two alternatives are inside a (?| group, both sets of cap- + turing parentheses are numbered one. Thus, when the pattern matches, + you can look at captured substring number one, whichever alternative + matched. This construct is useful when you want to capture part, but not all, of one of a number of alternatives. Inside a (?| group, paren- - theses are numbered as usual, but the number is reset at the start of - each branch. The numbers of any capturing parentheses that follow the - subpattern start after the highest number used in any branch. The fol- + theses are numbered as usual, but the number is reset at the start of + each branch. The numbers of any capturing parentheses that follow the + subpattern start after the highest number used in any branch. The fol- lowing example is taken from the Perl documentation. The numbers under- neath show in which buffer the captured content will be stored. @@ -6093,58 +6117,58 @@ DUPLICATE SUBPATTERN NUMBERS / ( a ) (?| x ( y ) z | (p (q) r) | (t) u (v) ) ( z ) /x # 1 2 2 3 2 3 4 - A back reference to a numbered subpattern uses the most recent value - that is set for that number by any subpattern. The following pattern + A back reference to a numbered subpattern uses the most recent value + that is set for that number by any subpattern. The following pattern matches "abcabc" or "defdef": /(?|(abc)|(def))\1/ - In contrast, a subroutine call to a numbered subpattern always refers - to the first one in the pattern with the given number. The following + In contrast, a subroutine call to a numbered subpattern always refers + to the first one in the pattern with the given number. The following pattern matches "abcabc" or "defabc": /(?|(abc)|(def))(?1)/ - If a condition test for a subpattern's having matched refers to a non- - unique number, the test is true if any of the subpatterns of that num- + If a condition test for a subpattern's having matched refers to a non- + unique number, the test is true if any of the subpatterns of that num- ber have matched. - An alternative approach to using this "branch reset" feature is to use + An alternative approach to using this "branch reset" feature is to use duplicate named subpatterns, as described in the next section. NAMED SUBPATTERNS - Identifying capturing parentheses by number is simple, but it can be - very hard to keep track of the numbers in complicated regular expres- - sions. Furthermore, if an expression is modified, the numbers may - change. To help with this difficulty, PCRE supports the naming of sub- + Identifying capturing parentheses by number is simple, but it can be + very hard to keep track of the numbers in complicated regular expres- + sions. Furthermore, if an expression is modified, the numbers may + change. To help with this difficulty, PCRE supports the naming of sub- patterns. This feature was not added to Perl until release 5.10. Python - had the feature earlier, and PCRE introduced it at release 4.0, using - the Python syntax. PCRE now supports both the Perl and the Python syn- - tax. Perl allows identically numbered subpatterns to have different + had the feature earlier, and PCRE introduced it at release 4.0, using + the Python syntax. PCRE now supports both the Perl and the Python syn- + tax. Perl allows identically numbered subpatterns to have different names, but PCRE does not. - In PCRE, a subpattern can be named in one of three ways: (?...) - or (?'name'...) as in Perl, or (?P...) as in Python. References - to capturing parentheses from other parts of the pattern, such as back - references, recursion, and conditions, can be made by name as well as + In PCRE, a subpattern can be named in one of three ways: (?...) + or (?'name'...) as in Perl, or (?P...) as in Python. References + to capturing parentheses from other parts of the pattern, such as back + references, recursion, and conditions, can be made by name as well as by number. - Names consist of up to 32 alphanumeric characters and underscores, but - must start with a non-digit. Named capturing parentheses are still - allocated numbers as well as names, exactly as if the names were not - present. The PCRE API provides function calls for extracting the name- - to-number translation table from a compiled pattern. There is also a + Names consist of up to 32 alphanumeric characters and underscores, but + must start with a non-digit. Named capturing parentheses are still + allocated numbers as well as names, exactly as if the names were not + present. The PCRE API provides function calls for extracting the name- + to-number translation table from a compiled pattern. There is also a convenience function for extracting a captured substring by name. - By default, a name must be unique within a pattern, but it is possible + By default, a name must be unique within a pattern, but it is possible to relax this constraint by setting the PCRE_DUPNAMES option at compile - time. (Duplicate names are also always permitted for subpatterns with - the same number, set up as described in the previous section.) Dupli- - cate names can be useful for patterns where only one instance of the - named parentheses can match. Suppose you want to match the name of a - weekday, either as a 3-letter abbreviation or as the full name, and in + time. (Duplicate names are also always permitted for subpatterns with + the same number, set up as described in the previous section.) Dupli- + cate names can be useful for patterns where only one instance of the + named parentheses can match. Suppose you want to match the name of a + weekday, either as a 3-letter abbreviation or as the full name, and in both cases you want to extract the abbreviation. This pattern (ignoring the line breaks) does the job: @@ -6154,18 +6178,18 @@ NAMED SUBPATTERNS (?Thu)(?:rsday)?| (?Sat)(?:urday)? - There are five capturing substrings, but only one is ever set after a + There are five capturing substrings, but only one is ever set after a match. (An alternative way of solving this problem is to use a "branch reset" subpattern, as described in the previous section.) - The convenience function for extracting the data by name returns the - substring for the first (and in this example, the only) subpattern of - that name that matched. This saves searching to find which numbered + The convenience function for extracting the data by name returns the + substring for the first (and in this example, the only) subpattern of + that name that matched. This saves searching to find which numbered subpattern it was. - If you make a back reference to a non-unique named subpattern from - elsewhere in the pattern, the subpatterns to which the name refers are - checked in the order in which they appear in the overall pattern. The + If you make a back reference to a non-unique named subpattern from + elsewhere in the pattern, the subpatterns to which the name refers are + checked in the order in which they appear in the overall pattern. The first one that is set is used for the reference. For example, this pat- tern matches both "foofoo" and "barbar" but not "foobar" or "barfoo": @@ -6173,29 +6197,29 @@ NAMED SUBPATTERNS If you make a subroutine call to a non-unique named subpattern, the one - that corresponds to the first occurrence of the name is used. In the + that corresponds to the first occurrence of the name is used. In the absence of duplicate numbers (see the previous section) this is the one with the lowest number. If you use a named reference in a condition test (see the section about conditions below), either to check whether a subpattern has matched, or - to check for recursion, all subpatterns with the same name are tested. - If the condition is true for any one of them, the overall condition is - true. This is the same behaviour as testing by number. For further - details of the interfaces for handling named subpatterns, see the + to check for recursion, all subpatterns with the same name are tested. + If the condition is true for any one of them, the overall condition is + true. This is the same behaviour as testing by number. For further + details of the interfaces for handling named subpatterns, see the pcreapi documentation. Warning: You cannot use different names to distinguish between two sub- - patterns with the same number because PCRE uses only the numbers when + patterns with the same number because PCRE uses only the numbers when matching. For this reason, an error is given at compile time if differ- - ent names are given to subpatterns with the same number. However, you + ent names are given to subpatterns with the same number. However, you can always give the same name to subpatterns with the same number, even when PCRE_DUPNAMES is not set. REPETITION - Repetition is specified by quantifiers, which can follow any of the + Repetition is specified by quantifiers, which can follow any of the following items: a literal data character @@ -6209,17 +6233,17 @@ REPETITION a parenthesized subpattern (including assertions) a subroutine call to a subpattern (recursive or otherwise) - The general repetition quantifier specifies a minimum and maximum num- - ber of permitted matches, by giving the two numbers in curly brackets - (braces), separated by a comma. The numbers must be less than 65536, + The general repetition quantifier specifies a minimum and maximum num- + ber of permitted matches, by giving the two numbers in curly brackets + (braces), separated by a comma. The numbers must be less than 65536, and the first must be less than or equal to the second. For example: z{2,4} - matches "zz", "zzz", or "zzzz". A closing brace on its own is not a - special character. If the second number is omitted, but the comma is - present, there is no upper limit; if the second number and the comma - are both omitted, the quantifier specifies an exact number of required + matches "zz", "zzz", or "zzzz". A closing brace on its own is not a + special character. If the second number is omitted, but the comma is + present, there is no upper limit; if the second number and the comma + are both omitted, the quantifier specifies an exact number of required matches. Thus [aeiou]{3,} @@ -6228,50 +6252,50 @@ REPETITION \d{8} - matches exactly 8 digits. An opening curly bracket that appears in a - position where a quantifier is not allowed, or one that does not match - the syntax of a quantifier, is taken as a literal character. For exam- + matches exactly 8 digits. An opening curly bracket that appears in a + position where a quantifier is not allowed, or one that does not match + the syntax of a quantifier, is taken as a literal character. For exam- ple, {,6} is not a quantifier, but a literal string of four characters. In UTF modes, quantifiers apply to characters rather than to individual - data units. Thus, for example, \x{100}{2} matches two characters, each + data units. Thus, for example, \x{100}{2} matches two characters, each of which is represented by a two-byte sequence in a UTF-8 string. Simi- - larly, \X{3} matches three Unicode extended grapheme clusters, each of - which may be several data units long (and they may be of different + larly, \X{3} matches three Unicode extended grapheme clusters, each of + which may be several data units long (and they may be of different lengths). The quantifier {0} is permitted, causing the expression to behave as if the previous item and the quantifier were not present. This may be use- - ful for subpatterns that are referenced as subroutines from elsewhere + ful for subpatterns that are referenced as subroutines from elsewhere in the pattern (but see also the section entitled "Defining subpatterns - for use by reference only" below). Items other than subpatterns that + for use by reference only" below). Items other than subpatterns that have a {0} quantifier are omitted from the compiled pattern. - For convenience, the three most common quantifiers have single-charac- + For convenience, the three most common quantifiers have single-charac- ter abbreviations: * is equivalent to {0,} + is equivalent to {1,} ? is equivalent to {0,1} - It is possible to construct infinite loops by following a subpattern + It is possible to construct infinite loops by following a subpattern that can match no characters with a quantifier that has no upper limit, for example: (a?)* Earlier versions of Perl and PCRE used to give an error at compile time - for such patterns. However, because there are cases where this can be - useful, such patterns are now accepted, but if any repetition of the - subpattern does in fact match no characters, the loop is forcibly bro- + for such patterns. However, because there are cases where this can be + useful, such patterns are now accepted, but if any repetition of the + subpattern does in fact match no characters, the loop is forcibly bro- ken. - By default, the quantifiers are "greedy", that is, they match as much - as possible (up to the maximum number of permitted times), without - causing the rest of the pattern to fail. The classic example of where + By default, the quantifiers are "greedy", that is, they match as much + as possible (up to the maximum number of permitted times), without + causing the rest of the pattern to fail. The classic example of where this gives problems is in trying to match comments in C programs. These - appear between /* and */ and within the comment, individual * and / - characters may appear. An attempt to match C comments by applying the + appear between /* and */ and within the comment, individual * and / + characters may appear. An attempt to match C comments by applying the pattern /\*.*\*/ @@ -6280,19 +6304,19 @@ REPETITION /* first comment */ not comment /* second comment */ - fails, because it matches the entire string owing to the greediness of + fails, because it matches the entire string owing to the greediness of the .* item. - However, if a quantifier is followed by a question mark, it ceases to + However, if a quantifier is followed by a question mark, it ceases to be greedy, and instead matches the minimum number of times possible, so the pattern /\*.*?\*/ - does the right thing with the C comments. The meaning of the various - quantifiers is not otherwise changed, just the preferred number of - matches. Do not confuse this use of question mark with its use as a - quantifier in its own right. Because it has two uses, it can sometimes + does the right thing with the C comments. The meaning of the various + quantifiers is not otherwise changed, just the preferred number of + matches. Do not confuse this use of question mark with its use as a + quantifier in its own right. Because it has two uses, it can sometimes appear doubled, as in \d??\d @@ -6300,45 +6324,45 @@ REPETITION which matches one digit by preference, but can match two if that is the only way the rest of the pattern matches. - If the PCRE_UNGREEDY option is set (an option that is not available in - Perl), the quantifiers are not greedy by default, but individual ones - can be made greedy by following them with a question mark. In other + If the PCRE_UNGREEDY option is set (an option that is not available in + Perl), the quantifiers are not greedy by default, but individual ones + can be made greedy by following them with a question mark. In other words, it inverts the default behaviour. - When a parenthesized subpattern is quantified with a minimum repeat - count that is greater than 1 or with a limited maximum, more memory is - required for the compiled pattern, in proportion to the size of the + When a parenthesized subpattern is quantified with a minimum repeat + count that is greater than 1 or with a limited maximum, more memory is + required for the compiled pattern, in proportion to the size of the minimum or maximum. If a pattern starts with .* or .{0,} and the PCRE_DOTALL option (equiv- - alent to Perl's /s) is set, thus allowing the dot to match newlines, - the pattern is implicitly anchored, because whatever follows will be - tried against every character position in the subject string, so there - is no point in retrying the overall match at any position after the - first. PCRE normally treats such a pattern as though it were preceded + alent to Perl's /s) is set, thus allowing the dot to match newlines, + the pattern is implicitly anchored, because whatever follows will be + tried against every character position in the subject string, so there + is no point in retrying the overall match at any position after the + first. PCRE normally treats such a pattern as though it were preceded by \A. - In cases where it is known that the subject string contains no new- - lines, it is worth setting PCRE_DOTALL in order to obtain this opti- + In cases where it is known that the subject string contains no new- + lines, it is worth setting PCRE_DOTALL in order to obtain this opti- mization, or alternatively using ^ to indicate anchoring explicitly. - However, there are some cases where the optimization cannot be used. + However, there are some cases where the optimization cannot be used. When .* is inside capturing parentheses that are the subject of a back reference elsewhere in the pattern, a match at the start may fail where a later one succeeds. Consider, for example: (.*)abc\1 - If the subject is "xyz123abc123" the match point is the fourth charac- + If the subject is "xyz123abc123" the match point is the fourth charac- ter. For this reason, such a pattern is not implicitly anchored. - Another case where implicit anchoring is not applied is when the lead- - ing .* is inside an atomic group. Once again, a match at the start may + Another case where implicit anchoring is not applied is when the lead- + ing .* is inside an atomic group. Once again, a match at the start may fail where a later one succeeds. Consider this pattern: (?>.*?a)b - It matches "ab" in the subject "aab". The use of the backtracking con- + It matches "ab" in the subject "aab". The use of the backtracking con- trol verbs (*PRUNE) and (*SKIP) also disable this optimization. When a capturing subpattern is repeated, the value captured is the sub- @@ -6347,8 +6371,8 @@ REPETITION (tweedle[dume]{3}\s*)+ has matched "tweedledum tweedledee" the value of the captured substring - is "tweedledee". However, if there are nested capturing subpatterns, - the corresponding captured values may have been set in previous itera- + is "tweedledee". However, if there are nested capturing subpatterns, + the corresponding captured values may have been set in previous itera- tions. For example, after /(a|(b))+/ @@ -6358,53 +6382,53 @@ REPETITION ATOMIC GROUPING AND POSSESSIVE QUANTIFIERS - With both maximizing ("greedy") and minimizing ("ungreedy" or "lazy") - repetition, failure of what follows normally causes the repeated item - to be re-evaluated to see if a different number of repeats allows the - rest of the pattern to match. Sometimes it is useful to prevent this, - either to change the nature of the match, or to cause it fail earlier - than it otherwise might, when the author of the pattern knows there is + With both maximizing ("greedy") and minimizing ("ungreedy" or "lazy") + repetition, failure of what follows normally causes the repeated item + to be re-evaluated to see if a different number of repeats allows the + rest of the pattern to match. Sometimes it is useful to prevent this, + either to change the nature of the match, or to cause it fail earlier + than it otherwise might, when the author of the pattern knows there is no point in carrying on. - Consider, for example, the pattern \d+foo when applied to the subject + Consider, for example, the pattern \d+foo when applied to the subject line 123456bar After matching all 6 digits and then failing to match "foo", the normal - action of the matcher is to try again with only 5 digits matching the - \d+ item, and then with 4, and so on, before ultimately failing. - "Atomic grouping" (a term taken from Jeffrey Friedl's book) provides - the means for specifying that once a subpattern has matched, it is not + action of the matcher is to try again with only 5 digits matching the + \d+ item, and then with 4, and so on, before ultimately failing. + "Atomic grouping" (a term taken from Jeffrey Friedl's book) provides + the means for specifying that once a subpattern has matched, it is not to be re-evaluated in this way. - If we use atomic grouping for the previous example, the matcher gives - up immediately on failing to match "foo" the first time. The notation + If we use atomic grouping for the previous example, the matcher gives + up immediately on failing to match "foo" the first time. The notation is a kind of special parenthesis, starting with (?> as in this example: (?>\d+)foo - This kind of parenthesis "locks up" the part of the pattern it con- - tains once it has matched, and a failure further into the pattern is - prevented from backtracking into it. Backtracking past it to previous + This kind of parenthesis "locks up" the part of the pattern it con- + tains once it has matched, and a failure further into the pattern is + prevented from backtracking into it. Backtracking past it to previous items, however, works as normal. - An alternative description is that a subpattern of this type matches - the string of characters that an identical standalone pattern would + An alternative description is that a subpattern of this type matches + the string of characters that an identical standalone pattern would match, if anchored at the current point in the subject string. Atomic grouping subpatterns are not capturing subpatterns. Simple cases such as the above example can be thought of as a maximizing repeat that - must swallow everything it can. So, while both \d+ and \d+? are pre- - pared to adjust the number of digits they match in order to make the + must swallow everything it can. So, while both \d+ and \d+? are pre- + pared to adjust the number of digits they match in order to make the rest of the pattern match, (?>\d+) can only match an entire sequence of digits. - Atomic groups in general can of course contain arbitrarily complicated - subpatterns, and can be nested. However, when the subpattern for an + Atomic groups in general can of course contain arbitrarily complicated + subpatterns, and can be nested. However, when the subpattern for an atomic group is just a single repeated item, as in the example above, a - simpler notation, called a "possessive quantifier" can be used. This - consists of an additional + character following a quantifier. Using + simpler notation, called a "possessive quantifier" can be used. This + consists of an additional + character following a quantifier. Using this notation, the previous example can be rewritten as \d++foo @@ -6414,45 +6438,45 @@ ATOMIC GROUPING AND POSSESSIVE QUANTIFIERS (abc|xyz){2,3}+ - Possessive quantifiers are always greedy; the setting of the + Possessive quantifiers are always greedy; the setting of the PCRE_UNGREEDY option is ignored. They are a convenient notation for the - simpler forms of atomic group. However, there is no difference in the - meaning of a possessive quantifier and the equivalent atomic group, - though there may be a performance difference; possessive quantifiers + simpler forms of atomic group. However, there is no difference in the + meaning of a possessive quantifier and the equivalent atomic group, + though there may be a performance difference; possessive quantifiers should be slightly faster. - The possessive quantifier syntax is an extension to the Perl 5.8 syn- - tax. Jeffrey Friedl originated the idea (and the name) in the first + The possessive quantifier syntax is an extension to the Perl 5.8 syn- + tax. Jeffrey Friedl originated the idea (and the name) in the first edition of his book. Mike McCloskey liked it, so implemented it when he - built Sun's Java package, and PCRE copied it from there. It ultimately + built Sun's Java package, and PCRE copied it from there. It ultimately found its way into Perl at release 5.10. PCRE has an optimization that automatically "possessifies" certain sim- - ple pattern constructs. For example, the sequence A+B is treated as - A++B because there is no point in backtracking into a sequence of A's + ple pattern constructs. For example, the sequence A+B is treated as + A++B because there is no point in backtracking into a sequence of A's when B must follow. - When a pattern contains an unlimited repeat inside a subpattern that - can itself be repeated an unlimited number of times, the use of an - atomic group is the only way to avoid some failing matches taking a + When a pattern contains an unlimited repeat inside a subpattern that + can itself be repeated an unlimited number of times, the use of an + atomic group is the only way to avoid some failing matches taking a very long time indeed. The pattern (\D+|<\d+>)*[!?] - matches an unlimited number of substrings that either consist of non- - digits, or digits enclosed in <>, followed by either ! or ?. When it + matches an unlimited number of substrings that either consist of non- + digits, or digits enclosed in <>, followed by either ! or ?. When it matches, it runs quickly. However, if it is applied to aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa - it takes a long time before reporting failure. This is because the - string can be divided between the internal \D+ repeat and the external - * repeat in a large number of ways, and all have to be tried. (The - example uses [!?] rather than a single character at the end, because - both PCRE and Perl have an optimization that allows for fast failure - when a single character is used. They remember the last single charac- - ter that is required for a match, and fail early if it is not present - in the string.) If the pattern is changed so that it uses an atomic + it takes a long time before reporting failure. This is because the + string can be divided between the internal \D+ repeat and the external + * repeat in a large number of ways, and all have to be tried. (The + example uses [!?] rather than a single character at the end, because + both PCRE and Perl have an optimization that allows for fast failure + when a single character is used. They remember the last single charac- + ter that is required for a match, and fail early if it is not present + in the string.) If the pattern is changed so that it uses an atomic group, like this: ((?>\D+)|<\d+>)*[!?] @@ -6464,28 +6488,28 @@ BACK REFERENCES Outside a character class, a backslash followed by a digit greater than 0 (and possibly further digits) is a back reference to a capturing sub- - pattern earlier (that is, to its left) in the pattern, provided there + pattern earlier (that is, to its left) in the pattern, provided there have been that many previous capturing left parentheses. However, if the decimal number following the backslash is less than 10, - it is always taken as a back reference, and causes an error only if - there are not that many capturing left parentheses in the entire pat- - tern. In other words, the parentheses that are referenced need not be - to the left of the reference for numbers less than 10. A "forward back - reference" of this type can make sense when a repetition is involved - and the subpattern to the right has participated in an earlier itera- + it is always taken as a back reference, and causes an error only if + there are not that many capturing left parentheses in the entire pat- + tern. In other words, the parentheses that are referenced need not be + to the left of the reference for numbers less than 10. A "forward back + reference" of this type can make sense when a repetition is involved + and the subpattern to the right has participated in an earlier itera- tion. - It is not possible to have a numerical "forward back reference" to a - subpattern whose number is 10 or more using this syntax because a - sequence such as \50 is interpreted as a character defined in octal. + It is not possible to have a numerical "forward back reference" to a + subpattern whose number is 10 or more using this syntax because a + sequence such as \50 is interpreted as a character defined in octal. See the subsection entitled "Non-printing characters" above for further - details of the handling of digits following a backslash. There is no - such problem when named parentheses are used. A back reference to any + details of the handling of digits following a backslash. There is no + such problem when named parentheses are used. A back reference to any subpattern is possible using named parentheses (see below). - Another way of avoiding the ambiguity inherent in the use of digits - following a backslash is to use the \g escape sequence. This escape + Another way of avoiding the ambiguity inherent in the use of digits + following a backslash is to use the \g escape sequence. This escape must be followed by an unsigned number or a negative number, optionally enclosed in braces. These examples are all identical: @@ -6493,7 +6517,7 @@ BACK REFERENCES (ring), \g1 (ring), \g{1} - An unsigned number specifies an absolute reference without the ambigu- + An unsigned number specifies an absolute reference without the ambigu- ity that is present in the older syntax. It is also useful when literal digits follow the reference. A negative number is a relative reference. Consider this example: @@ -6502,33 +6526,33 @@ BACK REFERENCES The sequence \g{-1} is a reference to the most recently started captur- ing subpattern before \g, that is, is it equivalent to \2 in this exam- - ple. Similarly, \g{-2} would be equivalent to \1. The use of relative - references can be helpful in long patterns, and also in patterns that - are created by joining together fragments that contain references + ple. Similarly, \g{-2} would be equivalent to \1. The use of relative + references can be helpful in long patterns, and also in patterns that + are created by joining together fragments that contain references within themselves. - A back reference matches whatever actually matched the capturing sub- - pattern in the current subject string, rather than anything matching + A back reference matches whatever actually matched the capturing sub- + pattern in the current subject string, rather than anything matching the subpattern itself (see "Subpatterns as subroutines" below for a way of doing that). So the pattern (sens|respons)e and \1ibility - matches "sense and sensibility" and "response and responsibility", but - not "sense and responsibility". If caseful matching is in force at the - time of the back reference, the case of letters is relevant. For exam- + matches "sense and sensibility" and "response and responsibility", but + not "sense and responsibility". If caseful matching is in force at the + time of the back reference, the case of letters is relevant. For exam- ple, ((?i)rah)\s+\1 - matches "rah rah" and "RAH RAH", but not "RAH rah", even though the + matches "rah rah" and "RAH RAH", but not "RAH rah", even though the original capturing subpattern is matched caselessly. - There are several different ways of writing back references to named - subpatterns. The .NET syntax \k{name} and the Perl syntax \k or - \k'name' are supported, as is the Python syntax (?P=name). Perl 5.10's + There are several different ways of writing back references to named + subpatterns. The .NET syntax \k{name} and the Perl syntax \k or + \k'name' are supported, as is the Python syntax (?P=name). Perl 5.10's unified back reference syntax, in which \g can be used for both numeric - and named references, is also supported. We could rewrite the above + and named references, is also supported. We could rewrite the above example in any of the following ways: (?(?i)rah)\s+\k @@ -6536,84 +6560,84 @@ BACK REFERENCES (?P(?i)rah)\s+(?P=p1) (?(?i)rah)\s+\g{p1} - A subpattern that is referenced by name may appear in the pattern + A subpattern that is referenced by name may appear in the pattern before or after the reference. - There may be more than one back reference to the same subpattern. If a - subpattern has not actually been used in a particular match, any back + There may be more than one back reference to the same subpattern. If a + subpattern has not actually been used in a particular match, any back references to it always fail by default. For example, the pattern (a|(bc))\2 - always fails if it starts to match "a" rather than "bc". However, if + always fails if it starts to match "a" rather than "bc". However, if the PCRE_JAVASCRIPT_COMPAT option is set at compile time, a back refer- ence to an unset value matches an empty string. - Because there may be many capturing parentheses in a pattern, all dig- - its following a backslash are taken as part of a potential back refer- - ence number. If the pattern continues with a digit character, some - delimiter must be used to terminate the back reference. If the - PCRE_EXTENDED option is set, this can be white space. Otherwise, the + Because there may be many capturing parentheses in a pattern, all dig- + its following a backslash are taken as part of a potential back refer- + ence number. If the pattern continues with a digit character, some + delimiter must be used to terminate the back reference. If the + PCRE_EXTENDED option is set, this can be white space. Otherwise, the \g{ syntax or an empty comment (see "Comments" below) can be used. Recursive back references - A back reference that occurs inside the parentheses to which it refers - fails when the subpattern is first used, so, for example, (a\1) never - matches. However, such references can be useful inside repeated sub- + A back reference that occurs inside the parentheses to which it refers + fails when the subpattern is first used, so, for example, (a\1) never + matches. However, such references can be useful inside repeated sub- patterns. For example, the pattern (a|b\1)+ matches any number of "a"s and also "aba", "ababbaa" etc. At each iter- - ation of the subpattern, the back reference matches the character - string corresponding to the previous iteration. In order for this to - work, the pattern must be such that the first iteration does not need - to match the back reference. This can be done using alternation, as in + ation of the subpattern, the back reference matches the character + string corresponding to the previous iteration. In order for this to + work, the pattern must be such that the first iteration does not need + to match the back reference. This can be done using alternation, as in the example above, or by a quantifier with a minimum of zero. - Back references of this type cause the group that they reference to be - treated as an atomic group. Once the whole group has been matched, a - subsequent matching failure cannot cause backtracking into the middle + Back references of this type cause the group that they reference to be + treated as an atomic group. Once the whole group has been matched, a + subsequent matching failure cannot cause backtracking into the middle of the group. ASSERTIONS - An assertion is a test on the characters following or preceding the - current matching point that does not actually consume any characters. - The simple assertions coded as \b, \B, \A, \G, \Z, \z, ^ and $ are + An assertion is a test on the characters following or preceding the + current matching point that does not actually consume any characters. + The simple assertions coded as \b, \B, \A, \G, \Z, \z, ^ and $ are described above. - More complicated assertions are coded as subpatterns. There are two - kinds: those that look ahead of the current position in the subject - string, and those that look behind it. An assertion subpattern is - matched in the normal way, except that it does not cause the current + More complicated assertions are coded as subpatterns. There are two + kinds: those that look ahead of the current position in the subject + string, and those that look behind it. An assertion subpattern is + matched in the normal way, except that it does not cause the current matching position to be changed. - Assertion subpatterns are not capturing subpatterns. If such an asser- - tion contains capturing subpatterns within it, these are counted for - the purposes of numbering the capturing subpatterns in the whole pat- - tern. However, substring capturing is carried out only for positive + Assertion subpatterns are not capturing subpatterns. If such an asser- + tion contains capturing subpatterns within it, these are counted for + the purposes of numbering the capturing subpatterns in the whole pat- + tern. However, substring capturing is carried out only for positive assertions. (Perl sometimes, but not always, does do capturing in nega- tive assertions.) - For compatibility with Perl, assertion subpatterns may be repeated; - though it makes no sense to assert the same thing several times, the - side effect of capturing parentheses may occasionally be useful. In + For compatibility with Perl, assertion subpatterns may be repeated; + though it makes no sense to assert the same thing several times, the + side effect of capturing parentheses may occasionally be useful. In practice, there only three cases: - (1) If the quantifier is {0}, the assertion is never obeyed during - matching. However, it may contain internal capturing parenthesized + (1) If the quantifier is {0}, the assertion is never obeyed during + matching. However, it may contain internal capturing parenthesized groups that are called from elsewhere via the subroutine mechanism. - (2) If quantifier is {0,n} where n is greater than zero, it is treated - as if it were {0,1}. At run time, the rest of the pattern match is + (2) If quantifier is {0,n} where n is greater than zero, it is treated + as if it were {0,1}. At run time, the rest of the pattern match is tried with and without the assertion, the order depending on the greed- iness of the quantifier. - (3) If the minimum repetition is greater than zero, the quantifier is - ignored. The assertion is obeyed just once when encountered during + (3) If the minimum repetition is greater than zero, the quantifier is + ignored. The assertion is obeyed just once when encountered during matching. Lookahead assertions @@ -6623,38 +6647,38 @@ ASSERTIONS \w+(?=;) - matches a word followed by a semicolon, but does not include the semi- + matches a word followed by a semicolon, but does not include the semi- colon in the match, and foo(?!bar) - matches any occurrence of "foo" that is not followed by "bar". Note + matches any occurrence of "foo" that is not followed by "bar". Note that the apparently similar pattern (?!foo)bar - does not find an occurrence of "bar" that is preceded by something - other than "foo"; it finds any occurrence of "bar" whatsoever, because + does not find an occurrence of "bar" that is preceded by something + other than "foo"; it finds any occurrence of "bar" whatsoever, because the assertion (?!foo) is always true when the next three characters are "bar". A lookbehind assertion is needed to achieve the other effect. If you want to force a matching failure at some point in a pattern, the - most convenient way to do it is with (?!) because an empty string - always matches, so an assertion that requires there not to be an empty + most convenient way to do it is with (?!) because an empty string + always matches, so an assertion that requires there not to be an empty string must always fail. The backtracking control verb (*FAIL) or (*F) is a synonym for (?!). Lookbehind assertions - Lookbehind assertions start with (?<= for positive assertions and (?)...) or (?('name')...) to test for a - used subpattern by name. For compatibility with earlier versions of - PCRE, which had this facility before Perl, the syntax (?(name)...) is + Perl uses the syntax (?()...) or (?('name')...) to test for a + used subpattern by name. For compatibility with earlier versions of + PCRE, which had this facility before Perl, the syntax (?(name)...) is also recognized. Rewriting the above example to use a named subpattern gives this: (? \( )? [^()]+ (?() \) ) - If the name used in a condition of this kind is a duplicate, the test - is applied to all subpatterns of the same name, and is true if any one + If the name used in a condition of this kind is a duplicate, the test + is applied to all subpatterns of the same name, and is true if any one of them has matched. Checking for pattern recursion If the condition is the string (R), and there is no subpattern with the - name R, the condition is true if a recursive call to the whole pattern + name R, the condition is true if a recursive call to the whole pattern or any subpattern has been made. If digits or a name preceded by amper- sand follow the letter R, for example: @@ -6846,51 +6870,51 @@ CONDITIONAL SUBPATTERNS the condition is true if the most recent recursion is into a subpattern whose number or name is given. This condition does not check the entire - recursion stack. If the name used in a condition of this kind is a + recursion stack. If the name used in a condition of this kind is a duplicate, the test is applied to all subpatterns of the same name, and is true if any one of them is the most recent recursion. - At "top level", all these recursion test conditions are false. The + At "top level", all these recursion test conditions are false. The syntax for recursive patterns is described below. Defining subpatterns for use by reference only - If the condition is the string (DEFINE), and there is no subpattern - with the name DEFINE, the condition is always false. In this case, - there may be only one alternative in the subpattern. It is always - skipped if control reaches this point in the pattern; the idea of - DEFINE is that it can be used to define subroutines that can be refer- - enced from elsewhere. (The use of subroutines is described below.) For - example, a pattern to match an IPv4 address such as "192.168.23.245" + If the condition is the string (DEFINE), and there is no subpattern + with the name DEFINE, the condition is always false. In this case, + there may be only one alternative in the subpattern. It is always + skipped if control reaches this point in the pattern; the idea of + DEFINE is that it can be used to define subroutines that can be refer- + enced from elsewhere. (The use of subroutines is described below.) For + example, a pattern to match an IPv4 address such as "192.168.23.245" could be written like this (ignore white space and line breaks): (?(DEFINE) (? 2[0-4]\d | 25[0-5] | 1\d\d | [1-9]?\d) ) \b (?&byte) (\.(?&byte)){3} \b - The first part of the pattern is a DEFINE group inside which a another - group named "byte" is defined. This matches an individual component of - an IPv4 address (a number less than 256). When matching takes place, - this part of the pattern is skipped because DEFINE acts like a false - condition. The rest of the pattern uses references to the named group - to match the four dot-separated components of an IPv4 address, insist- + The first part of the pattern is a DEFINE group inside which a another + group named "byte" is defined. This matches an individual component of + an IPv4 address (a number less than 256). When matching takes place, + this part of the pattern is skipped because DEFINE acts like a false + condition. The rest of the pattern uses references to the named group + to match the four dot-separated components of an IPv4 address, insist- ing on a word boundary at each end. Assertion conditions - If the condition is not in any of the above formats, it must be an - assertion. This may be a positive or negative lookahead or lookbehind - assertion. Consider this pattern, again containing non-significant + If the condition is not in any of the above formats, it must be an + assertion. This may be a positive or negative lookahead or lookbehind + assertion. Consider this pattern, again containing non-significant white space, and with the two alternatives on the second line: (?(?=[^a-z]*[a-z]) \d{2}-[a-z]{3}-\d{2} | \d{2}-\d{2}-\d{2} ) - The condition is a positive lookahead assertion that matches an - optional sequence of non-letters followed by a letter. In other words, - it tests for the presence of at least one letter in the subject. If a - letter is found, the subject is matched against the first alternative; - otherwise it is matched against the second. This pattern matches - strings in one of the two forms dd-aaa-dd or dd-dd-dd, where aaa are + The condition is a positive lookahead assertion that matches an + optional sequence of non-letters followed by a letter. In other words, + it tests for the presence of at least one letter in the subject. If a + letter is found, the subject is matched against the first alternative; + otherwise it is matched against the second. This pattern matches + strings in one of the two forms dd-aaa-dd or dd-dd-dd, where aaa are letters and dd are digits. @@ -6899,41 +6923,41 @@ COMMENTS There are two ways of including comments in patterns that are processed by PCRE. In both cases, the start of the comment must not be in a char- acter class, nor in the middle of any other sequence of related charac- - ters such as (?: or a subpattern name or number. The characters that + ters such as (?: or a subpattern name or number. The characters that make up a comment play no part in the pattern matching. - The sequence (?# marks the start of a comment that continues up to the - next closing parenthesis. Nested parentheses are not permitted. If the + The sequence (?# marks the start of a comment that continues up to the + next closing parenthesis. Nested parentheses are not permitted. If the PCRE_EXTENDED option is set, an unescaped # character also introduces a - comment, which in this case continues to immediately after the next - newline character or character sequence in the pattern. Which charac- + comment, which in this case continues to immediately after the next + newline character or character sequence in the pattern. Which charac- ters are interpreted as newlines is controlled by the options passed to - a compiling function or by a special sequence at the start of the pat- + a compiling function or by a special sequence at the start of the pat- tern, as described in the section entitled "Newline conventions" above. Note that the end of this type of comment is a literal newline sequence - in the pattern; escape sequences that happen to represent a newline do - not count. For example, consider this pattern when PCRE_EXTENDED is + in the pattern; escape sequences that happen to represent a newline do + not count. For example, consider this pattern when PCRE_EXTENDED is set, and the default newline convention is in force: abc #comment \n still comment - On encountering the # character, pcre_compile() skips along, looking - for a newline in the pattern. The sequence \n is still literal at this - stage, so it does not terminate the comment. Only an actual character + On encountering the # character, pcre_compile() skips along, looking + for a newline in the pattern. The sequence \n is still literal at this + stage, so it does not terminate the comment. Only an actual character with the code value 0x0a (the default newline) does so. RECURSIVE PATTERNS - Consider the problem of matching a string in parentheses, allowing for - unlimited nested parentheses. Without the use of recursion, the best - that can be done is to use a pattern that matches up to some fixed - depth of nesting. It is not possible to handle an arbitrary nesting + Consider the problem of matching a string in parentheses, allowing for + unlimited nested parentheses. Without the use of recursion, the best + that can be done is to use a pattern that matches up to some fixed + depth of nesting. It is not possible to handle an arbitrary nesting depth. For some time, Perl has provided a facility that allows regular expres- - sions to recurse (amongst other things). It does this by interpolating - Perl code in the expression at run time, and the code can refer to the + sions to recurse (amongst other things). It does this by interpolating + Perl code in the expression at run time, and the code can refer to the expression itself. A Perl pattern using code interpolation to solve the parentheses problem can be created like this: @@ -6943,201 +6967,201 @@ RECURSIVE PATTERNS refers recursively to the pattern in which it appears. Obviously, PCRE cannot support the interpolation of Perl code. Instead, - it supports special syntax for recursion of the entire pattern, and - also for individual subpattern recursion. After its introduction in - PCRE and Python, this kind of recursion was subsequently introduced + it supports special syntax for recursion of the entire pattern, and + also for individual subpattern recursion. After its introduction in + PCRE and Python, this kind of recursion was subsequently introduced into Perl at release 5.10. - A special item that consists of (? followed by a number greater than - zero and a closing parenthesis is a recursive subroutine call of the - subpattern of the given number, provided that it occurs inside that - subpattern. (If not, it is a non-recursive subroutine call, which is - described in the next section.) The special item (?R) or (?0) is a + A special item that consists of (? followed by a number greater than + zero and a closing parenthesis is a recursive subroutine call of the + subpattern of the given number, provided that it occurs inside that + subpattern. (If not, it is a non-recursive subroutine call, which is + described in the next section.) The special item (?R) or (?0) is a recursive call of the entire regular expression. - This PCRE pattern solves the nested parentheses problem (assume the + This PCRE pattern solves the nested parentheses problem (assume the PCRE_EXTENDED option is set so that white space is ignored): \( ( [^()]++ | (?R) )* \) - First it matches an opening parenthesis. Then it matches any number of - substrings which can either be a sequence of non-parentheses, or a - recursive match of the pattern itself (that is, a correctly parenthe- + First it matches an opening parenthesis. Then it matches any number of + substrings which can either be a sequence of non-parentheses, or a + recursive match of the pattern itself (that is, a correctly parenthe- sized substring). Finally there is a closing parenthesis. Note the use of a possessive quantifier to avoid backtracking into sequences of non- parentheses. - If this were part of a larger pattern, you would not want to recurse + If this were part of a larger pattern, you would not want to recurse the entire pattern, so instead you could use this: ( \( ( [^()]++ | (?1) )* \) ) - We have put the pattern into parentheses, and caused the recursion to + We have put the pattern into parentheses, and caused the recursion to refer to them instead of the whole pattern. - In a larger pattern, keeping track of parenthesis numbers can be - tricky. This is made easier by the use of relative references. Instead + In a larger pattern, keeping track of parenthesis numbers can be + tricky. This is made easier by the use of relative references. Instead of (?1) in the pattern above you can write (?-2) to refer to the second - most recently opened parentheses preceding the recursion. In other - words, a negative number counts capturing parentheses leftwards from + most recently opened parentheses preceding the recursion. In other + words, a negative number counts capturing parentheses leftwards from the point at which it is encountered. - It is also possible to refer to subsequently opened parentheses, by - writing references such as (?+2). However, these cannot be recursive - because the reference is not inside the parentheses that are refer- - enced. They are always non-recursive subroutine calls, as described in + It is also possible to refer to subsequently opened parentheses, by + writing references such as (?+2). However, these cannot be recursive + because the reference is not inside the parentheses that are refer- + enced. They are always non-recursive subroutine calls, as described in the next section. - An alternative approach is to use named parentheses instead. The Perl - syntax for this is (?&name); PCRE's earlier syntax (?P>name) is also + An alternative approach is to use named parentheses instead. The Perl + syntax for this is (?&name); PCRE's earlier syntax (?P>name) is also supported. We could rewrite the above example as follows: (? \( ( [^()]++ | (?&pn) )* \) ) - If there is more than one subpattern with the same name, the earliest + If there is more than one subpattern with the same name, the earliest one is used. - This particular example pattern that we have been looking at contains + This particular example pattern that we have been looking at contains nested unlimited repeats, and so the use of a possessive quantifier for matching strings of non-parentheses is important when applying the pat- - tern to strings that do not match. For example, when this pattern is + tern to strings that do not match. For example, when this pattern is applied to (aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa() - it yields "no match" quickly. However, if a possessive quantifier is - not used, the match runs for a very long time indeed because there are - so many different ways the + and * repeats can carve up the subject, + it yields "no match" quickly. However, if a possessive quantifier is + not used, the match runs for a very long time indeed because there are + so many different ways the + and * repeats can carve up the subject, and all have to be tested before failure can be reported. - At the end of a match, the values of capturing parentheses are those - from the outermost level. If you want to obtain intermediate values, a - callout function can be used (see below and the pcrecallout documenta- + At the end of a match, the values of capturing parentheses are those + from the outermost level. If you want to obtain intermediate values, a + callout function can be used (see below and the pcrecallout documenta- tion). If the pattern above is matched against (ab(cd)ef) - the value for the inner capturing parentheses (numbered 2) is "ef", - which is the last value taken on at the top level. If a capturing sub- - pattern is not matched at the top level, its final captured value is - unset, even if it was (temporarily) set at a deeper level during the + the value for the inner capturing parentheses (numbered 2) is "ef", + which is the last value taken on at the top level. If a capturing sub- + pattern is not matched at the top level, its final captured value is + unset, even if it was (temporarily) set at a deeper level during the matching process. - If there are more than 15 capturing parentheses in a pattern, PCRE has - to obtain extra memory to store data during a recursion, which it does + If there are more than 15 capturing parentheses in a pattern, PCRE has + to obtain extra memory to store data during a recursion, which it does by using pcre_malloc, freeing it via pcre_free afterwards. If no memory can be obtained, the match fails with the PCRE_ERROR_NOMEMORY error. - Do not confuse the (?R) item with the condition (R), which tests for - recursion. Consider this pattern, which matches text in angle brack- - ets, allowing for arbitrary nesting. Only digits are allowed in nested - brackets (that is, when recursing), whereas any characters are permit- + Do not confuse the (?R) item with the condition (R), which tests for + recursion. Consider this pattern, which matches text in angle brack- + ets, allowing for arbitrary nesting. Only digits are allowed in nested + brackets (that is, when recursing), whereas any characters are permit- ted at the outer level. < (?: (?(R) \d++ | [^<>]*+) | (?R)) * > - In this pattern, (?(R) is the start of a conditional subpattern, with - two different alternatives for the recursive and non-recursive cases. + In this pattern, (?(R) is the start of a conditional subpattern, with + two different alternatives for the recursive and non-recursive cases. The (?R) item is the actual recursive call. Differences in recursion processing between PCRE and Perl - Recursion processing in PCRE differs from Perl in two important ways. - In PCRE (like Python, but unlike Perl), a recursive subpattern call is + Recursion processing in PCRE differs from Perl in two important ways. + In PCRE (like Python, but unlike Perl), a recursive subpattern call is always treated as an atomic group. That is, once it has matched some of the subject string, it is never re-entered, even if it contains untried - alternatives and there is a subsequent matching failure. This can be - illustrated by the following pattern, which purports to match a palin- - dromic string that contains an odd number of characters (for example, + alternatives and there is a subsequent matching failure. This can be + illustrated by the following pattern, which purports to match a palin- + dromic string that contains an odd number of characters (for example, "a", "aba", "abcba", "abcdcba"): ^(.|(.)(?1)\2)$ The idea is that it either matches a single character, or two identical - characters surrounding a sub-palindrome. In Perl, this pattern works; - in PCRE it does not if the pattern is longer than three characters. + characters surrounding a sub-palindrome. In Perl, this pattern works; + in PCRE it does not if the pattern is longer than three characters. Consider the subject string "abcba": - At the top level, the first character is matched, but as it is not at + At the top level, the first character is matched, but as it is not at the end of the string, the first alternative fails; the second alterna- tive is taken and the recursion kicks in. The recursive call to subpat- - tern 1 successfully matches the next character ("b"). (Note that the + tern 1 successfully matches the next character ("b"). (Note that the beginning and end of line tests are not part of the recursion). - Back at the top level, the next character ("c") is compared with what - subpattern 2 matched, which was "a". This fails. Because the recursion - is treated as an atomic group, there are now no backtracking points, - and so the entire match fails. (Perl is able, at this point, to re- - enter the recursion and try the second alternative.) However, if the + Back at the top level, the next character ("c") is compared with what + subpattern 2 matched, which was "a". This fails. Because the recursion + is treated as an atomic group, there are now no backtracking points, + and so the entire match fails. (Perl is able, at this point, to re- + enter the recursion and try the second alternative.) However, if the pattern is written with the alternatives in the other order, things are different: ^((.)(?1)\2|.)$ - This time, the recursing alternative is tried first, and continues to - recurse until it runs out of characters, at which point the recursion - fails. But this time we do have another alternative to try at the - higher level. That is the big difference: in the previous case the + This time, the recursing alternative is tried first, and continues to + recurse until it runs out of characters, at which point the recursion + fails. But this time we do have another alternative to try at the + higher level. That is the big difference: in the previous case the remaining alternative is at a deeper recursion level, which PCRE cannot use. - To change the pattern so that it matches all palindromic strings, not - just those with an odd number of characters, it is tempting to change + To change the pattern so that it matches all palindromic strings, not + just those with an odd number of characters, it is tempting to change the pattern to this: ^((.)(?1)\2|.?)$ - Again, this works in Perl, but not in PCRE, and for the same reason. - When a deeper recursion has matched a single character, it cannot be - entered again in order to match an empty string. The solution is to - separate the two cases, and write out the odd and even cases as alter- + Again, this works in Perl, but not in PCRE, and for the same reason. + When a deeper recursion has matched a single character, it cannot be + entered again in order to match an empty string. The solution is to + separate the two cases, and write out the odd and even cases as alter- natives at the higher level: ^(?:((.)(?1)\2|)|((.)(?3)\4|.)) - If you want to match typical palindromic phrases, the pattern has to + If you want to match typical palindromic phrases, the pattern has to ignore all non-word characters, which can be done like this: ^\W*+(?:((.)\W*+(?1)\W*+\2|)|((.)\W*+(?3)\W*+\4|\W*+.\W*+))\W*+$ If run with the PCRE_CASELESS option, this pattern matches phrases such as "A man, a plan, a canal: Panama!" and it works well in both PCRE and - Perl. Note the use of the possessive quantifier *+ to avoid backtrack- - ing into sequences of non-word characters. Without this, PCRE takes a - great deal longer (ten times or more) to match typical phrases, and + Perl. Note the use of the possessive quantifier *+ to avoid backtrack- + ing into sequences of non-word characters. Without this, PCRE takes a + great deal longer (ten times or more) to match typical phrases, and Perl takes so long that you think it has gone into a loop. - WARNING: The palindrome-matching patterns above work only if the sub- - ject string does not start with a palindrome that is shorter than the - entire string. For example, although "abcba" is correctly matched, if - the subject is "ababa", PCRE finds the palindrome "aba" at the start, - then fails at top level because the end of the string does not follow. - Once again, it cannot jump back into the recursion to try other alter- + WARNING: The palindrome-matching patterns above work only if the sub- + ject string does not start with a palindrome that is shorter than the + entire string. For example, although "abcba" is correctly matched, if + the subject is "ababa", PCRE finds the palindrome "aba" at the start, + then fails at top level because the end of the string does not follow. + Once again, it cannot jump back into the recursion to try other alter- natives, so the entire match fails. - The second way in which PCRE and Perl differ in their recursion pro- - cessing is in the handling of captured values. In Perl, when a subpat- - tern is called recursively or as a subpattern (see the next section), - it has no access to any values that were captured outside the recur- - sion, whereas in PCRE these values can be referenced. Consider this + The second way in which PCRE and Perl differ in their recursion pro- + cessing is in the handling of captured values. In Perl, when a subpat- + tern is called recursively or as a subpattern (see the next section), + it has no access to any values that were captured outside the recur- + sion, whereas in PCRE these values can be referenced. Consider this pattern: ^(.)(\1|a(?2)) - In PCRE, this pattern matches "bab". The first capturing parentheses - match "b", then in the second group, when the back reference \1 fails - to match "b", the second alternative matches "a" and then recurses. In - the recursion, \1 does now match "b" and so the whole match succeeds. - In Perl, the pattern fails to match because inside the recursive call + In PCRE, this pattern matches "bab". The first capturing parentheses + match "b", then in the second group, when the back reference \1 fails + to match "b", the second alternative matches "a" and then recurses. In + the recursion, \1 does now match "b" and so the whole match succeeds. + In Perl, the pattern fails to match because inside the recursive call \1 cannot access the externally set value. SUBPATTERNS AS SUBROUTINES - If the syntax for a recursive subpattern call (either by number or by - name) is used outside the parentheses to which it refers, it operates - like a subroutine in a programming language. The called subpattern may - be defined before or after the reference. A numbered reference can be + If the syntax for a recursive subpattern call (either by number or by + name) is used outside the parentheses to which it refers, it operates + like a subroutine in a programming language. The called subpattern may + be defined before or after the reference. A numbered reference can be absolute or relative, as in these examples: (...(absolute)...)...(?2)... @@ -7148,79 +7172,79 @@ SUBPATTERNS AS SUBROUTINES (sens|respons)e and \1ibility - matches "sense and sensibility" and "response and responsibility", but + matches "sense and sensibility" and "response and responsibility", but not "sense and responsibility". If instead the pattern (sens|respons)e and (?1)ibility - is used, it does match "sense and responsibility" as well as the other - two strings. Another example is given in the discussion of DEFINE + is used, it does match "sense and responsibility" as well as the other + two strings. Another example is given in the discussion of DEFINE above. - All subroutine calls, whether recursive or not, are always treated as - atomic groups. That is, once a subroutine has matched some of the sub- + All subroutine calls, whether recursive or not, are always treated as + atomic groups. That is, once a subroutine has matched some of the sub- ject string, it is never re-entered, even if it contains untried alter- - natives and there is a subsequent matching failure. Any capturing - parentheses that are set during the subroutine call revert to their + natives and there is a subsequent matching failure. Any capturing + parentheses that are set during the subroutine call revert to their previous values afterwards. - Processing options such as case-independence are fixed when a subpat- - tern is defined, so if it is used as a subroutine, such options cannot + Processing options such as case-independence are fixed when a subpat- + tern is defined, so if it is used as a subroutine, such options cannot be changed for different calls. For example, consider this pattern: (abc)(?i:(?-1)) - It matches "abcabc". It does not match "abcABC" because the change of + It matches "abcabc". It does not match "abcABC" because the change of processing option does not affect the called subpattern. ONIGURUMA SUBROUTINE SYNTAX - For compatibility with Oniguruma, the non-Perl syntax \g followed by a + For compatibility with Oniguruma, the non-Perl syntax \g followed by a name or a number enclosed either in angle brackets or single quotes, is - an alternative syntax for referencing a subpattern as a subroutine, - possibly recursively. Here are two of the examples used above, rewrit- + an alternative syntax for referencing a subpattern as a subroutine, + possibly recursively. Here are two of the examples used above, rewrit- ten using this syntax: (? \( ( (?>[^()]+) | \g )* \) ) (sens|respons)e and \g'1'ibility - PCRE supports an extension to Oniguruma: if a number is preceded by a + PCRE supports an extension to Oniguruma: if a number is preceded by a plus or a minus sign it is taken as a relative reference. For example: (abc)(?i:\g<-1>) - Note that \g{...} (Perl syntax) and \g<...> (Oniguruma syntax) are not - synonymous. The former is a back reference; the latter is a subroutine + Note that \g{...} (Perl syntax) and \g<...> (Oniguruma syntax) are not + synonymous. The former is a back reference; the latter is a subroutine call. CALLOUTS Perl has a feature whereby using the sequence (?{...}) causes arbitrary - Perl code to be obeyed in the middle of matching a regular expression. + Perl code to be obeyed in the middle of matching a regular expression. This makes it possible, amongst other things, to extract different sub- strings that match the same pair of parentheses when there is a repeti- tion. PCRE provides a similar feature, but of course it cannot obey arbitrary Perl code. The feature is called "callout". The caller of PCRE provides - an external function by putting its entry point in the global variable - pcre_callout (8-bit library) or pcre[16|32]_callout (16-bit or 32-bit - library). By default, this variable contains NULL, which disables all + an external function by putting its entry point in the global variable + pcre_callout (8-bit library) or pcre[16|32]_callout (16-bit or 32-bit + library). By default, this variable contains NULL, which disables all calling out. - Within a regular expression, (?C) indicates the points at which the - external function is to be called. If you want to identify different - callout points, you can put a number less than 256 after the letter C. - The default value is zero. For example, this pattern has two callout + Within a regular expression, (?C) indicates the points at which the + external function is to be called. If you want to identify different + callout points, you can put a number less than 256 after the letter C. + The default value is zero. For example, this pattern has two callout points: (?C1)abc(?C2)def - If the PCRE_AUTO_CALLOUT flag is passed to a compiling function, call- - outs are automatically installed before each item in the pattern. They - are all numbered 255. If there is a conditional group in the pattern + If the PCRE_AUTO_CALLOUT flag is passed to a compiling function, call- + outs are automatically installed before each item in the pattern. They + are all numbered 255. If there is a conditional group in the pattern whose condition is an assertion, an additional callout is inserted just before the condition. An explicit callout may also be set at this posi- tion, as in this example: @@ -7230,120 +7254,120 @@ CALLOUTS Note that this applies only to assertion conditions, not to other types of condition. - During matching, when PCRE reaches a callout point, the external func- - tion is called. It is provided with the number of the callout, the - position in the pattern, and, optionally, one item of data originally - supplied by the caller of the matching function. The callout function + During matching, when PCRE reaches a callout point, the external func- + tion is called. It is provided with the number of the callout, the + position in the pattern, and, optionally, one item of data originally + supplied by the caller of the matching function. The callout function may cause matching to proceed, to backtrack, or to fail altogether. - By default, PCRE implements a number of optimizations at compile time - and matching time, and one side-effect is that sometimes callouts are - skipped. If you need all possible callouts to happen, you need to set - options that disable the relevant optimizations. More details, and a - complete description of the interface to the callout function, are + By default, PCRE implements a number of optimizations at compile time + and matching time, and one side-effect is that sometimes callouts are + skipped. If you need all possible callouts to happen, you need to set + options that disable the relevant optimizations. More details, and a + complete description of the interface to the callout function, are given in the pcrecallout documentation. BACKTRACKING CONTROL - Perl 5.10 introduced a number of "Special Backtracking Control Verbs", - which are still described in the Perl documentation as "experimental - and subject to change or removal in a future version of Perl". It goes - on to say: "Their usage in production code should be noted to avoid - problems during upgrades." The same remarks apply to the PCRE features + Perl 5.10 introduced a number of "Special Backtracking Control Verbs", + which are still described in the Perl documentation as "experimental + and subject to change or removal in a future version of Perl". It goes + on to say: "Their usage in production code should be noted to avoid + problems during upgrades." The same remarks apply to the PCRE features described in this section. - The new verbs make use of what was previously invalid syntax: an open- + The new verbs make use of what was previously invalid syntax: an open- ing parenthesis followed by an asterisk. They are generally of the form - (*VERB) or (*VERB:NAME). Some may take either form, possibly behaving - differently depending on whether or not a name is present. A name is + (*VERB) or (*VERB:NAME). Some may take either form, possibly behaving + differently depending on whether or not a name is present. A name is any sequence of characters that does not include a closing parenthesis. The maximum length of name is 255 in the 8-bit library and 65535 in the - 16-bit and 32-bit libraries. If the name is empty, that is, if the - closing parenthesis immediately follows the colon, the effect is as if - the colon were not there. Any number of these verbs may occur in a + 16-bit and 32-bit libraries. If the name is empty, that is, if the + closing parenthesis immediately follows the colon, the effect is as if + the colon were not there. Any number of these verbs may occur in a pattern. - Since these verbs are specifically related to backtracking, most of - them can be used only when the pattern is to be matched using one of - the traditional matching functions, because these use a backtracking - algorithm. With the exception of (*FAIL), which behaves like a failing - negative assertion, the backtracking control verbs cause an error if + Since these verbs are specifically related to backtracking, most of + them can be used only when the pattern is to be matched using one of + the traditional matching functions, because these use a backtracking + algorithm. With the exception of (*FAIL), which behaves like a failing + negative assertion, the backtracking control verbs cause an error if encountered by a DFA matching function. - The behaviour of these verbs in repeated groups, assertions, and in + The behaviour of these verbs in repeated groups, assertions, and in subpatterns called as subroutines (whether or not recursively) is docu- mented below. Optimizations that affect backtracking verbs - PCRE contains some optimizations that are used to speed up matching by + PCRE contains some optimizations that are used to speed up matching by running some checks at the start of each match attempt. For example, it - may know the minimum length of matching subject, or that a particular + may know the minimum length of matching subject, or that a particular character must be present. When one of these optimizations bypasses the - running of a match, any included backtracking verbs will not, of + running of a match, any included backtracking verbs will not, of course, be processed. You can suppress the start-of-match optimizations - by setting the PCRE_NO_START_OPTIMIZE option when calling pcre_com- + by setting the PCRE_NO_START_OPTIMIZE option when calling pcre_com- pile() or pcre_exec(), or by starting the pattern with (*NO_START_OPT). There is more discussion of this option in the section entitled "Option bits for pcre_exec()" in the pcreapi documentation. - Experiments with Perl suggest that it too has similar optimizations, + Experiments with Perl suggest that it too has similar optimizations, sometimes leading to anomalous results. Verbs that act immediately - The following verbs act as soon as they are encountered. They may not + The following verbs act as soon as they are encountered. They may not be followed by a name. (*ACCEPT) - This verb causes the match to end successfully, skipping the remainder - of the pattern. However, when it is inside a subpattern that is called - as a subroutine, only that subpattern is ended successfully. Matching + This verb causes the match to end successfully, skipping the remainder + of the pattern. However, when it is inside a subpattern that is called + as a subroutine, only that subpattern is ended successfully. Matching then continues at the outer level. If (*ACCEPT) in triggered in a posi- - tive assertion, the assertion succeeds; in a negative assertion, the + tive assertion, the assertion succeeds; in a negative assertion, the assertion fails. - If (*ACCEPT) is inside capturing parentheses, the data so far is cap- + If (*ACCEPT) is inside capturing parentheses, the data so far is cap- tured. For example: A((?:A|B(*ACCEPT)|C)D) - This matches "AB", "AAD", or "ACD"; when it matches "AB", "B" is cap- + This matches "AB", "AAD", or "ACD"; when it matches "AB", "B" is cap- tured by the outer parentheses. (*FAIL) or (*F) - This verb causes a matching failure, forcing backtracking to occur. It - is equivalent to (?!) but easier to read. The Perl documentation notes - that it is probably useful only when combined with (?{}) or (??{}). - Those are, of course, Perl features that are not present in PCRE. The - nearest equivalent is the callout feature, as for example in this pat- + This verb causes a matching failure, forcing backtracking to occur. It + is equivalent to (?!) but easier to read. The Perl documentation notes + that it is probably useful only when combined with (?{}) or (??{}). + Those are, of course, Perl features that are not present in PCRE. The + nearest equivalent is the callout feature, as for example in this pat- tern: a+(?C)(*FAIL) - A match with the string "aaaa" always fails, but the callout is taken + A match with the string "aaaa" always fails, but the callout is taken before each backtrack happens (in this example, 10 times). Recording which path was taken - There is one verb whose main purpose is to track how a match was - arrived at, though it also has a secondary use in conjunction with + There is one verb whose main purpose is to track how a match was + arrived at, though it also has a secondary use in conjunction with advancing the match starting point (see (*SKIP) below). (*MARK:NAME) or (*:NAME) - A name is always required with this verb. There may be as many - instances of (*MARK) as you like in a pattern, and their names do not + A name is always required with this verb. There may be as many + instances of (*MARK) as you like in a pattern, and their names do not have to be unique. - When a match succeeds, the name of the last-encountered (*MARK:NAME), - (*PRUNE:NAME), or (*THEN:NAME) on the matching path is passed back to - the caller as described in the section entitled "Extra data for - pcre_exec()" in the pcreapi documentation. Here is an example of - pcretest output, where the /K modifier requests the retrieval and out- + When a match succeeds, the name of the last-encountered (*MARK:NAME), + (*PRUNE:NAME), or (*THEN:NAME) on the matching path is passed back to + the caller as described in the section entitled "Extra data for + pcre_exec()" in the pcreapi documentation. Here is an example of + pcretest output, where the /K modifier requests the retrieval and out- putting of (*MARK) data: re> /X(*MARK:A)Y|X(*MARK:B)Z/K @@ -7355,73 +7379,73 @@ BACKTRACKING CONTROL MK: B The (*MARK) name is tagged with "MK:" in this output, and in this exam- - ple it indicates which of the two alternatives matched. This is a more - efficient way of obtaining this information than putting each alterna- + ple it indicates which of the two alternatives matched. This is a more + efficient way of obtaining this information than putting each alterna- tive in its own capturing parentheses. - If a verb with a name is encountered in a positive assertion that is - true, the name is recorded and passed back if it is the last-encoun- + If a verb with a name is encountered in a positive assertion that is + true, the name is recorded and passed back if it is the last-encoun- tered. This does not happen for negative assertions or failing positive assertions. - After a partial match or a failed match, the last encountered name in + After a partial match or a failed match, the last encountered name in the entire match process is returned. For example: re> /X(*MARK:A)Y|X(*MARK:B)Z/K data> XP No match, mark = B - Note that in this unanchored example the mark is retained from the + Note that in this unanchored example the mark is retained from the match attempt that started at the letter "X" in the subject. Subsequent match attempts starting at "P" and then with an empty string do not get as far as the (*MARK) item, but nevertheless do not reset it. - If you are interested in (*MARK) values after failed matches, you - should probably set the PCRE_NO_START_OPTIMIZE option (see above) to + If you are interested in (*MARK) values after failed matches, you + should probably set the PCRE_NO_START_OPTIMIZE option (see above) to ensure that the match is always attempted. Verbs that act after backtracking The following verbs do nothing when they are encountered. Matching con- - tinues with what follows, but if there is no subsequent match, causing - a backtrack to the verb, a failure is forced. That is, backtracking - cannot pass to the left of the verb. However, when one of these verbs + tinues with what follows, but if there is no subsequent match, causing + a backtrack to the verb, a failure is forced. That is, backtracking + cannot pass to the left of the verb. However, when one of these verbs appears inside an atomic group or an assertion that is true, its effect - is confined to that group, because once the group has been matched, - there is never any backtracking into it. In this situation, backtrack- - ing can "jump back" to the left of the entire atomic group or asser- - tion. (Remember also, as stated above, that this localization also + is confined to that group, because once the group has been matched, + there is never any backtracking into it. In this situation, backtrack- + ing can "jump back" to the left of the entire atomic group or asser- + tion. (Remember also, as stated above, that this localization also applies in subroutine calls.) - These verbs differ in exactly what kind of failure occurs when back- - tracking reaches them. The behaviour described below is what happens - when the verb is not in a subroutine or an assertion. Subsequent sec- + These verbs differ in exactly what kind of failure occurs when back- + tracking reaches them. The behaviour described below is what happens + when the verb is not in a subroutine or an assertion. Subsequent sec- tions cover these special cases. (*COMMIT) - This verb, which may not be followed by a name, causes the whole match + This verb, which may not be followed by a name, causes the whole match to fail outright if there is a later matching failure that causes back- - tracking to reach it. Even if the pattern is unanchored, no further + tracking to reach it. Even if the pattern is unanchored, no further attempts to find a match by advancing the starting point take place. If - (*COMMIT) is the only backtracking verb that is encountered, once it + (*COMMIT) is the only backtracking verb that is encountered, once it has been passed pcre_exec() is committed to finding a match at the cur- rent starting point, or not at all. For example: a+(*COMMIT)b - This matches "xxaab" but not "aacaab". It can be thought of as a kind + This matches "xxaab" but not "aacaab". It can be thought of as a kind of dynamic anchor, or "I've started, so I must finish." The name of the - most recently passed (*MARK) in the path is passed back when (*COMMIT) + most recently passed (*MARK) in the path is passed back when (*COMMIT) forces a match failure. - If there is more than one backtracking verb in a pattern, a different - one that follows (*COMMIT) may be triggered first, so merely passing + If there is more than one backtracking verb in a pattern, a different + one that follows (*COMMIT) may be triggered first, so merely passing (*COMMIT) during a match does not always guarantee that a match must be at this starting point. - Note that (*COMMIT) at the start of a pattern is not the same as an - anchor, unless PCRE's start-of-match optimizations are turned off, as + Note that (*COMMIT) at the start of a pattern is not the same as an + anchor, unless PCRE's start-of-match optimizations are turned off, as shown in this output from pcretest: re> /(*COMMIT)abc/ @@ -7432,207 +7456,207 @@ BACKTRACKING CONTROL For this pattern, PCRE knows that any match must start with "a", so the optimization skips along the subject to "a" before applying the pattern - to the first set of data. The match attempt then succeeds. In the sec- - ond set of data, the escape sequence \Y is interpreted by the pcretest - program. It causes the PCRE_NO_START_OPTIMIZE option to be set when + to the first set of data. The match attempt then succeeds. In the sec- + ond set of data, the escape sequence \Y is interpreted by the pcretest + program. It causes the PCRE_NO_START_OPTIMIZE option to be set when pcre_exec() is called. This disables the optimization that skips along to the first character. The pattern is now applied starting at "x", and - so the (*COMMIT) causes the match to fail without trying any other + so the (*COMMIT) causes the match to fail without trying any other starting points. (*PRUNE) or (*PRUNE:NAME) - This verb causes the match to fail at the current starting position in + This verb causes the match to fail at the current starting position in the subject if there is a later matching failure that causes backtrack- - ing to reach it. If the pattern is unanchored, the normal "bumpalong" - advance to the next starting character then happens. Backtracking can - occur as usual to the left of (*PRUNE), before it is reached, or when - matching to the right of (*PRUNE), but if there is no match to the - right, backtracking cannot cross (*PRUNE). In simple cases, the use of - (*PRUNE) is just an alternative to an atomic group or possessive quan- + ing to reach it. If the pattern is unanchored, the normal "bumpalong" + advance to the next starting character then happens. Backtracking can + occur as usual to the left of (*PRUNE), before it is reached, or when + matching to the right of (*PRUNE), but if there is no match to the + right, backtracking cannot cross (*PRUNE). In simple cases, the use of + (*PRUNE) is just an alternative to an atomic group or possessive quan- tifier, but there are some uses of (*PRUNE) that cannot be expressed in - any other way. In an anchored pattern (*PRUNE) has the same effect as + any other way. In an anchored pattern (*PRUNE) has the same effect as (*COMMIT). The behaviour of (*PRUNE:NAME) is the not the same as - (*MARK:NAME)(*PRUNE). It is like (*MARK:NAME) in that the name is - remembered for passing back to the caller. However, (*SKIP:NAME) + (*MARK:NAME)(*PRUNE). It is like (*MARK:NAME) in that the name is + remembered for passing back to the caller. However, (*SKIP:NAME) searches only for names set with (*MARK). (*SKIP) - This verb, when given without a name, is like (*PRUNE), except that if - the pattern is unanchored, the "bumpalong" advance is not to the next + This verb, when given without a name, is like (*PRUNE), except that if + the pattern is unanchored, the "bumpalong" advance is not to the next character, but to the position in the subject where (*SKIP) was encoun- - tered. (*SKIP) signifies that whatever text was matched leading up to + tered. (*SKIP) signifies that whatever text was matched leading up to it cannot be part of a successful match. Consider: a+(*SKIP)b - If the subject is "aaaac...", after the first match attempt fails - (starting at the first character in the string), the starting point + If the subject is "aaaac...", after the first match attempt fails + (starting at the first character in the string), the starting point skips on to start the next attempt at "c". Note that a possessive quan- - tifer does not have the same effect as this example; although it would - suppress backtracking during the first match attempt, the second - attempt would start at the second character instead of skipping on to + tifer does not have the same effect as this example; although it would + suppress backtracking during the first match attempt, the second + attempt would start at the second character instead of skipping on to "c". (*SKIP:NAME) When (*SKIP) has an associated name, its behaviour is modified. When it is triggered, the previous path through the pattern is searched for the - most recent (*MARK) that has the same name. If one is found, the + most recent (*MARK) that has the same name. If one is found, the "bumpalong" advance is to the subject position that corresponds to that (*MARK) instead of to where (*SKIP) was encountered. If no (*MARK) with a matching name is found, the (*SKIP) is ignored. - Note that (*SKIP:NAME) searches only for names set by (*MARK:NAME). It + Note that (*SKIP:NAME) searches only for names set by (*MARK:NAME). It ignores names that are set by (*PRUNE:NAME) or (*THEN:NAME). (*THEN) or (*THEN:NAME) - This verb causes a skip to the next innermost alternative when back- - tracking reaches it. That is, it cancels any further backtracking - within the current alternative. Its name comes from the observation + This verb causes a skip to the next innermost alternative when back- + tracking reaches it. That is, it cancels any further backtracking + within the current alternative. Its name comes from the observation that it can be used for a pattern-based if-then-else block: ( COND1 (*THEN) FOO | COND2 (*THEN) BAR | COND3 (*THEN) BAZ ) ... - If the COND1 pattern matches, FOO is tried (and possibly further items - after the end of the group if FOO succeeds); on failure, the matcher - skips to the second alternative and tries COND2, without backtracking - into COND1. If that succeeds and BAR fails, COND3 is tried. If subse- - quently BAZ fails, there are no more alternatives, so there is a back- - track to whatever came before the entire group. If (*THEN) is not + If the COND1 pattern matches, FOO is tried (and possibly further items + after the end of the group if FOO succeeds); on failure, the matcher + skips to the second alternative and tries COND2, without backtracking + into COND1. If that succeeds and BAR fails, COND3 is tried. If subse- + quently BAZ fails, there are no more alternatives, so there is a back- + track to whatever came before the entire group. If (*THEN) is not inside an alternation, it acts like (*PRUNE). - The behaviour of (*THEN:NAME) is the not the same as - (*MARK:NAME)(*THEN). It is like (*MARK:NAME) in that the name is - remembered for passing back to the caller. However, (*SKIP:NAME) + The behaviour of (*THEN:NAME) is the not the same as + (*MARK:NAME)(*THEN). It is like (*MARK:NAME) in that the name is + remembered for passing back to the caller. However, (*SKIP:NAME) searches only for names set with (*MARK). - A subpattern that does not contain a | character is just a part of the - enclosing alternative; it is not a nested alternation with only one - alternative. The effect of (*THEN) extends beyond such a subpattern to - the enclosing alternative. Consider this pattern, where A, B, etc. are - complex pattern fragments that do not contain any | characters at this + A subpattern that does not contain a | character is just a part of the + enclosing alternative; it is not a nested alternation with only one + alternative. The effect of (*THEN) extends beyond such a subpattern to + the enclosing alternative. Consider this pattern, where A, B, etc. are + complex pattern fragments that do not contain any | characters at this level: A (B(*THEN)C) | D - If A and B are matched, but there is a failure in C, matching does not + If A and B are matched, but there is a failure in C, matching does not backtrack into A; instead it moves to the next alternative, that is, D. - However, if the subpattern containing (*THEN) is given an alternative, + However, if the subpattern containing (*THEN) is given an alternative, it behaves differently: A (B(*THEN)C | (*FAIL)) | D - The effect of (*THEN) is now confined to the inner subpattern. After a + The effect of (*THEN) is now confined to the inner subpattern. After a failure in C, matching moves to (*FAIL), which causes the whole subpat- - tern to fail because there are no more alternatives to try. In this + tern to fail because there are no more alternatives to try. In this case, matching does now backtrack into A. - Note that a conditional subpattern is not considered as having two - alternatives, because only one is ever used. In other words, the | + Note that a conditional subpattern is not considered as having two + alternatives, because only one is ever used. In other words, the | character in a conditional subpattern has a different meaning. Ignoring white space, consider: ^.*? (?(?=a) a | b(*THEN)c ) - If the subject is "ba", this pattern does not match. Because .*? is - ungreedy, it initially matches zero characters. The condition (?=a) - then fails, the character "b" is matched, but "c" is not. At this - point, matching does not backtrack to .*? as might perhaps be expected - from the presence of the | character. The conditional subpattern is + If the subject is "ba", this pattern does not match. Because .*? is + ungreedy, it initially matches zero characters. The condition (?=a) + then fails, the character "b" is matched, but "c" is not. At this + point, matching does not backtrack to .*? as might perhaps be expected + from the presence of the | character. The conditional subpattern is part of the single alternative that comprises the whole pattern, and so - the match fails. (If there was a backtrack into .*?, allowing it to + the match fails. (If there was a backtrack into .*?, allowing it to match "b", the match would succeed.) - The verbs just described provide four different "strengths" of control + The verbs just described provide four different "strengths" of control when subsequent matching fails. (*THEN) is the weakest, carrying on the - match at the next alternative. (*PRUNE) comes next, failing the match - at the current starting position, but allowing an advance to the next - character (for an unanchored pattern). (*SKIP) is similar, except that + match at the next alternative. (*PRUNE) comes next, failing the match + at the current starting position, but allowing an advance to the next + character (for an unanchored pattern). (*SKIP) is similar, except that the advance may be more than one character. (*COMMIT) is the strongest, causing the entire match to fail. More than one backtracking verb - If more than one backtracking verb is present in a pattern, the one - that is backtracked onto first acts. For example, consider this pat- + If more than one backtracking verb is present in a pattern, the one + that is backtracked onto first acts. For example, consider this pat- tern, where A, B, etc. are complex pattern fragments: (A(*COMMIT)B(*THEN)C|ABD) - If A matches but B fails, the backtrack to (*COMMIT) causes the entire + If A matches but B fails, the backtrack to (*COMMIT) causes the entire match to fail. However, if A and B match, but C fails, the backtrack to - (*THEN) causes the next alternative (ABD) to be tried. This behaviour - is consistent, but is not always the same as Perl's. It means that if - two or more backtracking verbs appear in succession, all the the last + (*THEN) causes the next alternative (ABD) to be tried. This behaviour + is consistent, but is not always the same as Perl's. It means that if + two or more backtracking verbs appear in succession, all the the last of them has no effect. Consider this example: ...(*COMMIT)(*PRUNE)... If there is a matching failure to the right, backtracking onto (*PRUNE) - causes it to be triggered, and its action is taken. There can never be + causes it to be triggered, and its action is taken. There can never be a backtrack onto (*COMMIT). Backtracking verbs in repeated groups - PCRE differs from Perl in its handling of backtracking verbs in + PCRE differs from Perl in its handling of backtracking verbs in repeated groups. For example, consider: /(a(*COMMIT)b)+ac/ - If the subject is "abac", Perl matches, but PCRE fails because the + If the subject is "abac", Perl matches, but PCRE fails because the (*COMMIT) in the second repeat of the group acts. Backtracking verbs in assertions - (*FAIL) in an assertion has its normal effect: it forces an immediate + (*FAIL) in an assertion has its normal effect: it forces an immediate backtrack. (*ACCEPT) in a positive assertion causes the assertion to succeed with- - out any further processing. In a negative assertion, (*ACCEPT) causes + out any further processing. In a negative assertion, (*ACCEPT) causes the assertion to fail without any further processing. - The other backtracking verbs are not treated specially if they appear - in a positive assertion. In particular, (*THEN) skips to the next - alternative in the innermost enclosing group that has alternations, + The other backtracking verbs are not treated specially if they appear + in a positive assertion. In particular, (*THEN) skips to the next + alternative in the innermost enclosing group that has alternations, whether or not this is within the assertion. - Negative assertions are, however, different, in order to ensure that - changing a positive assertion into a negative assertion changes its + Negative assertions are, however, different, in order to ensure that + changing a positive assertion into a negative assertion changes its result. Backtracking into (*COMMIT), (*SKIP), or (*PRUNE) causes a neg- ative assertion to be true, without considering any further alternative branches in the assertion. Backtracking into (*THEN) causes it to skip - to the next enclosing alternative within the assertion (the normal be- - haviour), but if the assertion does not have such an alternative, + to the next enclosing alternative within the assertion (the normal be- + haviour), but if the assertion does not have such an alternative, (*THEN) behaves like (*PRUNE). Backtracking verbs in subroutines - These behaviours occur whether or not the subpattern is called recur- + These behaviours occur whether or not the subpattern is called recur- sively. Perl's treatment of subroutines is different in some cases. - (*FAIL) in a subpattern called as a subroutine has its normal effect: + (*FAIL) in a subpattern called as a subroutine has its normal effect: it forces an immediate backtrack. - (*ACCEPT) in a subpattern called as a subroutine causes the subroutine - match to succeed without any further processing. Matching then contin- + (*ACCEPT) in a subpattern called as a subroutine causes the subroutine + match to succeed without any further processing. Matching then contin- ues after the subroutine call. (*COMMIT), (*SKIP), and (*PRUNE) in a subpattern called as a subroutine cause the subroutine match to fail. - (*THEN) skips to the next alternative in the innermost enclosing group - within the subpattern that has alternatives. If there is no such group + (*THEN) skips to the next alternative in the innermost enclosing group + within the subpattern that has alternatives. If there is no such group within the subpattern, (*THEN) causes the subroutine match to fail. SEE ALSO - pcreapi(3), pcrecallout(3), pcrematching(3), pcresyntax(3), pcre(3), + pcreapi(3), pcrecallout(3), pcrematching(3), pcresyntax(3), pcre(3), pcre16(3), pcre32(3). @@ -7645,8 +7669,8 @@ AUTHOR REVISION - Last updated: 08 January 2014 - Copyright (c) 1997-2014 University of Cambridge. + Last updated: 14 June 2015 + Copyright (c) 1997-2015 University of Cambridge. ------------------------------------------------------------------------------ diff --git a/ext/pcre/pcrelib/pcre.h b/ext/pcre/pcrelib/pcre.h index 58ed46a..bf6351f 100644 --- a/ext/pcre/pcrelib/pcre.h +++ b/ext/pcre/pcrelib/pcre.h @@ -42,9 +42,9 @@ POSSIBILITY OF SUCH DAMAGE. /* The current PCRE version information. */ #define PCRE_MAJOR 8 -#define PCRE_MINOR 37 +#define PCRE_MINOR 38 #define PCRE_PRERELEASE -#define PCRE_DATE 2015-04-28 +#define PCRE_DATE 2015-11-23 /* 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 diff --git a/ext/pcre/pcrelib/pcre_compile.c b/ext/pcre/pcrelib/pcre_compile.c index 0efad26..4d3b313 100644 --- a/ext/pcre/pcrelib/pcre_compile.c +++ b/ext/pcre/pcrelib/pcre_compile.c @@ -174,7 +174,7 @@ static const short int escapes[] = { -ESC_Z, CHAR_LEFT_SQUARE_BRACKET, CHAR_BACKSLASH, CHAR_RIGHT_SQUARE_BRACKET, CHAR_CIRCUMFLEX_ACCENT, CHAR_UNDERSCORE, - CHAR_GRAVE_ACCENT, 7, + CHAR_GRAVE_ACCENT, ESC_a, -ESC_b, 0, -ESC_d, ESC_e, ESC_f, 0, @@ -202,9 +202,9 @@ static const short int escapes[] = { /* 68 */ 0, 0, '|', ',', '%', '_', '>', '?', /* 70 */ 0, 0, 0, 0, 0, 0, 0, 0, /* 78 */ 0, '`', ':', '#', '@', '\'', '=', '"', -/* 80 */ 0, 7, -ESC_b, 0, -ESC_d, ESC_e, ESC_f, 0, +/* 80 */ 0, ESC_a, -ESC_b, 0, -ESC_d, ESC_e, ESC_f, 0, /* 88 */-ESC_h, 0, 0, '{', 0, 0, 0, 0, -/* 90 */ 0, 0, -ESC_k, 'l', 0, ESC_n, 0, -ESC_p, +/* 90 */ 0, 0, -ESC_k, 0, 0, ESC_n, 0, -ESC_p, /* 98 */ 0, ESC_r, 0, '}', 0, 0, 0, 0, /* A0 */ 0, '~', -ESC_s, ESC_tee, 0,-ESC_v, -ESC_w, 0, /* A8 */ 0,-ESC_z, 0, 0, 0, '[', 0, 0, @@ -219,6 +219,12 @@ static const short int escapes[] = { /* F0 */ 0, 0, 0, 0, 0, 0, 0, 0, /* F8 */ 0, 0, 0, 0, 0, 0, 0, 0 }; + +/* We also need a table of characters that may follow \c in an EBCDIC +environment for characters 0-31. */ + +static unsigned char ebcdic_escape_c[] = "@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_"; + #endif @@ -458,7 +464,7 @@ static const char error_texts[] = "range out of order in character class\0" "nothing to repeat\0" /* 10 */ - "operand of unlimited repeat could match the empty string\0" /** DEAD **/ + "internal error: invalid forward reference offset\0" "internal error: unexpected repeat\0" "unrecognized character after (? or (?-\0" "POSIX named classes are supported only within a class\0" @@ -527,7 +533,11 @@ static const char error_texts[] = "different names for subpatterns of the same number are not allowed\0" "(*MARK) must have an argument\0" "this version of PCRE is not compiled with Unicode property support\0" +#ifndef EBCDIC "\\c must be followed by an ASCII character\0" +#else + "\\c must be followed by a letter or one of [\\]^_?\0" +#endif "\\k is not followed by a braced, angle-bracketed, or quoted name\0" /* 70 */ "internal error: unknown opcode in find_fixedlength()\0" @@ -1425,7 +1435,16 @@ else c ^= 0x40; #else /* EBCDIC coding */ if (c >= CHAR_a && c <= CHAR_z) c += 64; - c ^= 0xC0; + if (c == CHAR_QUESTION_MARK) + c = ('\\' == 188 && '`' == 74)? 0x5f : 0xff; + else + { + for (i = 0; i < 32; i++) + { + if (c == ebcdic_escape_c[i]) break; + } + if (i < 32) c = i; else *errorcodeptr = ERR68; + } #endif break; @@ -1799,7 +1818,7 @@ for (;;) case OP_ASSERTBACK: case OP_ASSERTBACK_NOT: do cc += GET(cc, 1); while (*cc == OP_ALT); - cc += PRIV(OP_lengths)[*cc]; + cc += 1 + LINK_SIZE; break; /* Skip over things that don't match chars */ @@ -2487,7 +2506,7 @@ for (code = first_significant_code(code + PRIV(OP_lengths)[*code], TRUE); if (c == OP_BRA || c == OP_BRAPOS || c == OP_CBRA || c == OP_CBRAPOS || c == OP_ONCE || c == OP_ONCE_NC || - c == OP_COND) + c == OP_COND || c == OP_SCOND) { BOOL empty_branch; if (GET(code, 1) == 0) return TRUE; /* Hit unclosed bracket */ @@ -3886,11 +3905,11 @@ didn't consider this to be a POSIX class. Likewise for [:1234:]. The problem in trying to be exactly like Perl is in the handling of escapes. We have to be sure that [abc[:x\]pqr] is *not* treated as containing a POSIX class, but [abc[:x\]pqr:]] is (so that an error can be generated). The code -below handles the special case of \], but does not try to do any other escape -processing. This makes it different from Perl for cases such as [:l\ower:] -where Perl recognizes it as the POSIX class "lower" but PCRE does not recognize -"l\ower". This is a lesser evil than not diagnosing bad classes when Perl does, -I think. +below handles the special cases \\ and \], but does not try to do any other +escape processing. This makes it different from Perl for cases such as +[:l\ower:] where Perl recognizes it as the POSIX class "lower" but PCRE does +not recognize "l\ower". This is a lesser evil than not diagnosing bad classes +when Perl does, I think. A user pointed out that PCRE was rejecting [:a[:digit:]] whereas Perl was not. It seems that the appearance of a nested POSIX class supersedes an apparent @@ -3917,21 +3936,16 @@ pcre_uchar terminator; /* Don't combine these lines; the Solaris cc */ terminator = *(++ptr); /* compiler warns about "non-constant" initializer. */ for (++ptr; *ptr != CHAR_NULL; ptr++) { - if (*ptr == CHAR_BACKSLASH && ptr[1] == CHAR_RIGHT_SQUARE_BRACKET) + if (*ptr == CHAR_BACKSLASH && + (ptr[1] == CHAR_RIGHT_SQUARE_BRACKET || + ptr[1] == CHAR_BACKSLASH)) ptr++; - else if (*ptr == CHAR_RIGHT_SQUARE_BRACKET) return FALSE; - else + else if ((*ptr == CHAR_LEFT_SQUARE_BRACKET && ptr[1] == terminator) || + *ptr == CHAR_RIGHT_SQUARE_BRACKET) return FALSE; + else if (*ptr == terminator && ptr[1] == CHAR_RIGHT_SQUARE_BRACKET) { - if (*ptr == terminator && ptr[1] == CHAR_RIGHT_SQUARE_BRACKET) - { - *endptr = ptr; - return TRUE; - } - if (*ptr == CHAR_LEFT_SQUARE_BRACKET && - (ptr[1] == CHAR_COLON || ptr[1] == CHAR_DOT || - ptr[1] == CHAR_EQUALS_SIGN) && - check_posix_syntax(ptr, endptr)) - return FALSE; + *endptr = ptr; + return TRUE; } } return FALSE; @@ -3985,11 +3999,12 @@ have their offsets adjusted. That one of the jobs of this function. Before it is called, the partially compiled regex must be temporarily terminated with OP_END. -This function has been extended with the possibility of forward references for -recursions and subroutine calls. It must also check the list of such references -for the group we are dealing with. If it finds that one of the recursions in -the current group is on this list, it adjusts the offset in the list, not the -value in the reference (which is a group number). +This function has been extended to cope with forward references for recursions +and subroutine calls. It must check the list of such references for the +group we are dealing with. If it finds that one of the recursions in the +current group is on this list, it does not adjust the value in the reference +(which is a group number). After the group has been scanned, all the offsets in +the forward reference list for the group are adjusted. Arguments: group points to the start of the group @@ -4005,29 +4020,21 @@ static void adjust_recurse(pcre_uchar *group, int adjust, BOOL utf, compile_data *cd, size_t save_hwm_offset) { +int offset; +pcre_uchar *hc; pcre_uchar *ptr = group; while ((ptr = (pcre_uchar *)find_recurse(ptr, utf)) != NULL) { - int offset; - pcre_uchar *hc; - - /* See if this recursion is on the forward reference list. If so, adjust the - reference. */ - for (hc = (pcre_uchar *)cd->start_workspace + save_hwm_offset; hc < cd->hwm; hc += LINK_SIZE) { offset = (int)GET(hc, 0); - if (cd->start_code + offset == ptr + 1) - { - PUT(hc, 0, offset + adjust); - break; - } + if (cd->start_code + offset == ptr + 1) break; } - /* Otherwise, adjust the recursion offset if it's after the start of this - group. */ + /* If we have not found this recursion on the forward reference list, adjust + the recursion's offset if it's after the start of this group. */ if (hc >= cd->hwm) { @@ -4037,6 +4044,15 @@ while ((ptr = (pcre_uchar *)find_recurse(ptr, utf)) != NULL) ptr += 1 + LINK_SIZE; } + +/* Now adjust all forward reference offsets for the group. */ + +for (hc = (pcre_uchar *)cd->start_workspace + save_hwm_offset; hc < cd->hwm; + hc += LINK_SIZE) + { + offset = (int)GET(hc, 0); + PUT(hc, 0, offset + adjust); + } } @@ -4465,7 +4481,7 @@ const pcre_uchar *tempptr; const pcre_uchar *nestptr = NULL; pcre_uchar *previous = NULL; pcre_uchar *previous_callout = NULL; -size_t save_hwm_offset = 0; +size_t item_hwm_offset = 0; pcre_uint8 classbits[32]; /* We can fish out the UTF-8 setting once and for all into a BOOL, but we @@ -4623,8 +4639,7 @@ for (;; ptr++) /* In the real compile phase, just check the workspace used by the forward reference list. */ - else if (cd->hwm > cd->start_workspace + cd->workspace_size - - WORK_SIZE_SAFETY_MARGIN) + else if (cd->hwm > cd->start_workspace + cd->workspace_size) { *errorcodeptr = ERR52; goto FAILED; @@ -4767,6 +4782,7 @@ for (;; ptr++) zeroreqchar = reqchar; zeroreqcharflags = reqcharflags; previous = code; + item_hwm_offset = cd->hwm - cd->start_workspace; *code++ = ((options & PCRE_DOTALL) != 0)? OP_ALLANY: OP_ANY; break; @@ -4818,6 +4834,7 @@ for (;; ptr++) /* Handle a real character class. */ previous = code; + item_hwm_offset = cd->hwm - cd->start_workspace; /* PCRE supports POSIX class stuff inside a class. Perl gives an error if they are encountered at the top level, so we'll do that too. */ @@ -4923,9 +4940,10 @@ for (;; ptr++) (which is on the stack). We have to remember that there was XCLASS data, however. */ + if (class_uchardata > class_uchardata_base) xclass = TRUE; + if (lengthptr != NULL && class_uchardata > class_uchardata_base) { - xclass = TRUE; *lengthptr += (int)(class_uchardata - class_uchardata_base); class_uchardata = class_uchardata_base; } @@ -5028,10 +5046,26 @@ for (;; ptr++) ptr = tempptr + 1; continue; - /* For all other POSIX classes, no special action is taken in UCP - mode. Fall through to the non_UCP case. */ + /* For the other POSIX classes (ascii, xdigit) we are going to fall + through to the non-UCP case and build a bit map for characters with + code points less than 256. If we are in a negated POSIX class + within a non-negated overall class, characters with code points + greater than 255 must all match. In the special case where we have + not yet generated any xclass data, and this is the final item in + the overall class, we need do nothing: later on, the opcode + OP_NCLASS will be used to indicate that characters greater than 255 + are acceptable. If we have already seen an xclass item or one may + follow (we have to assume that it might if this is not the end of + the class), explicitly match all wide codepoints. */ default: + if (!negate_class && local_negate && + (xclass || tempptr[2] != CHAR_RIGHT_SQUARE_BRACKET)) + { + *class_uchardata++ = XCL_RANGE; + class_uchardata += PRIV(ord2utf)(0x100, class_uchardata); + class_uchardata += PRIV(ord2utf)(0x10ffff, class_uchardata); + } break; } } @@ -5195,9 +5229,9 @@ for (;; ptr++) cd, PRIV(vspace_list)); continue; -#ifdef SUPPORT_UCP case ESC_p: case ESC_P: +#ifdef SUPPORT_UCP { BOOL negated; unsigned int ptype = 0, pdata = 0; @@ -5211,6 +5245,9 @@ for (;; ptr++) class_has_8bitchar--; /* Undo! */ continue; } +#else + *errorcodeptr = ERR45; + goto FAILED; #endif /* Unrecognized escapes are faulted if PCRE is running in its strict mode. By default, for compatibility with Perl, they are @@ -5367,16 +5404,20 @@ for (;; ptr++) CLASS_SINGLE_CHARACTER: if (class_one_char < 2) class_one_char++; - /* If class_one_char is 1, we have the first single character in the - class, and there have been no prior ranges, or XCLASS items generated by - escapes. If this is the final character in the class, we can optimize by - turning the item into a 1-character OP_CHAR[I] if it's positive, or - OP_NOT[I] if it's negative. In the positive case, it can cause firstchar - to be set. Otherwise, there can be no first char if this item is first, - whatever repeat count may follow. In the case of reqchar, save the - previous value for reinstating. */ + /* If xclass_has_prop is false and class_one_char is 1, we have the first + single character in the class, and there have been no prior ranges, or + XCLASS items generated by escapes. If this is the final character in the + class, we can optimize by turning the item into a 1-character OP_CHAR[I] + if it's positive, or OP_NOT[I] if it's negative. In the positive case, it + can cause firstchar to be set. Otherwise, there can be no first char if + this item is first, whatever repeat count may follow. In the case of + reqchar, save the previous value for reinstating. */ - if (!inescq && class_one_char == 1 && ptr[1] == CHAR_RIGHT_SQUARE_BRACKET) + if (!inescq && +#ifdef SUPPORT_UCP + !xclass_has_prop && +#endif + class_one_char == 1 && ptr[1] == CHAR_RIGHT_SQUARE_BRACKET) { ptr++; zeroreqchar = reqchar; @@ -5492,9 +5533,10 @@ for (;; ptr++) actual compiled code. */ #ifdef SUPPORT_UTF - if (xclass && (!should_flip_negation || (options & PCRE_UCP) != 0)) + if (xclass && (xclass_has_prop || !should_flip_negation || + (options & PCRE_UCP) != 0)) #elif !defined COMPILE_PCRE8 - if (xclass && !should_flip_negation) + if (xclass && (xclass_has_prop || !should_flip_negation)) #endif #if defined SUPPORT_UTF || !defined COMPILE_PCRE8 { @@ -5930,7 +5972,7 @@ for (;; ptr++) { register int i; int len = (int)(code - previous); - size_t base_hwm_offset = save_hwm_offset; + size_t base_hwm_offset = item_hwm_offset; pcre_uchar *bralink = NULL; pcre_uchar *brazeroptr = NULL; @@ -5985,7 +6027,7 @@ for (;; ptr++) if (repeat_max <= 1) /* Covers 0, 1, and unlimited */ { *code = OP_END; - adjust_recurse(previous, 1, utf, cd, save_hwm_offset); + adjust_recurse(previous, 1, utf, cd, item_hwm_offset); memmove(previous + 1, previous, IN_UCHARS(len)); code++; if (repeat_max == 0) @@ -6009,7 +6051,7 @@ for (;; ptr++) { int offset; *code = OP_END; - adjust_recurse(previous, 2 + LINK_SIZE, utf, cd, save_hwm_offset); + adjust_recurse(previous, 2 + LINK_SIZE, utf, cd, item_hwm_offset); memmove(previous + 2 + LINK_SIZE, previous, IN_UCHARS(len)); code += 2 + LINK_SIZE; *previous++ = OP_BRAZERO + repeat_type; @@ -6254,6 +6296,12 @@ for (;; ptr++) while (*scode == OP_ALT); } + /* A conditional group with only one branch has an implicit empty + alternative branch. */ + + if (*bracode == OP_COND && bracode[GET(bracode,1)] != OP_ALT) + *bracode = OP_SCOND; + /* Handle possessive quantifiers. */ if (possessive_quantifier) @@ -6267,11 +6315,11 @@ for (;; ptr++) { int nlen = (int)(code - bracode); *code = OP_END; - adjust_recurse(bracode, 1 + LINK_SIZE, utf, cd, save_hwm_offset); + adjust_recurse(bracode, 1 + LINK_SIZE, utf, cd, item_hwm_offset); memmove(bracode + 1 + LINK_SIZE, bracode, IN_UCHARS(nlen)); code += 1 + LINK_SIZE; nlen += 1 + LINK_SIZE; - *bracode = OP_BRAPOS; + *bracode = (*bracode == OP_COND)? OP_BRAPOS : OP_SBRAPOS; *code++ = OP_KETRPOS; PUTINC(code, 0, nlen); PUT(bracode, 1, nlen); @@ -6401,7 +6449,7 @@ for (;; ptr++) else { *code = OP_END; - adjust_recurse(tempcode, 1 + LINK_SIZE, utf, cd, save_hwm_offset); + adjust_recurse(tempcode, 1 + LINK_SIZE, utf, cd, item_hwm_offset); memmove(tempcode + 1 + LINK_SIZE, tempcode, IN_UCHARS(len)); code += 1 + LINK_SIZE; len += 1 + LINK_SIZE; @@ -6450,7 +6498,7 @@ for (;; ptr++) default: *code = OP_END; - adjust_recurse(tempcode, 1 + LINK_SIZE, utf, cd, save_hwm_offset); + adjust_recurse(tempcode, 1 + LINK_SIZE, utf, cd, item_hwm_offset); memmove(tempcode + 1 + LINK_SIZE, tempcode, IN_UCHARS(len)); code += 1 + LINK_SIZE; len += 1 + LINK_SIZE; @@ -6586,9 +6634,17 @@ for (;; ptr++) goto FAILED; } setverb = *code++ = verbs[i].op_arg; - *code++ = arglen; - memcpy(code, arg, IN_UCHARS(arglen)); - code += arglen; + if (lengthptr != NULL) /* In pass 1 just add in the length */ + { /* to avoid potential workspace */ + *lengthptr += arglen; /* overflow. */ + *code++ = 0; + } + else + { + *code++ = arglen; + memcpy(code, arg, IN_UCHARS(arglen)); + code += arglen; + } *code++ = 0; } @@ -6623,7 +6679,7 @@ for (;; ptr++) newoptions = options; skipbytes = 0; bravalue = OP_CBRA; - save_hwm_offset = cd->hwm - cd->start_workspace; + item_hwm_offset = cd->hwm - cd->start_workspace; reset_bracount = FALSE; /* Deal with the extended parentheses; all are introduced by '?', and the @@ -6641,6 +6697,7 @@ for (;; ptr++) /* ------------------------------------------------------------ */ case CHAR_VERTICAL_LINE: /* Reset capture count for each branch */ reset_bracount = TRUE; + cd->dupgroups = TRUE; /* Record (?| encountered */ /* Fall through */ /* ------------------------------------------------------------ */ @@ -6741,6 +6798,12 @@ for (;; ptr++) { while (IS_DIGIT(*ptr)) { + if (recno > INT_MAX / 10 - 1) /* Integer overflow */ + { + while (IS_DIGIT(*ptr)) ptr++; + *errorcodeptr = ERR61; + goto FAILED; + } recno = recno * 10 + (int)(*ptr - CHAR_0); ptr++; } @@ -6769,7 +6832,7 @@ for (;; ptr++) ptr++; } namelen = (int)(ptr - name); - if (lengthptr != NULL) *lengthptr += IMM2_SIZE; + if (lengthptr != NULL) skipbytes += IMM2_SIZE; } /* Check the terminator */ @@ -6875,6 +6938,11 @@ for (;; ptr++) *errorcodeptr = ERR15; goto FAILED; } + if (recno > INT_MAX / 10 - 1) /* Integer overflow */ + { + *errorcodeptr = ERR61; + goto FAILED; + } recno = recno * 10 + name[i] - CHAR_0; } if (recno == 0) recno = RREF_ANY; @@ -7151,6 +7219,7 @@ for (;; ptr++) if (lengthptr != NULL) { named_group *ng; + recno = 0; if (namelen == 0) { @@ -7168,20 +7237,6 @@ for (;; ptr++) goto FAILED; } - /* The name table does not exist in the first pass; instead we must - scan the list of names encountered so far in order to get the - number. If the name is not found, set the value to 0 for a forward - reference. */ - - ng = cd->named_groups; - for (i = 0; i < cd->names_found; i++, ng++) - { - if (namelen == ng->length && - STRNCMP_UC_UC(name, ng->name, namelen) == 0) - break; - } - recno = (i < cd->names_found)? ng->number : 0; - /* Count named back references. */ if (!is_recurse) cd->namedrefcount++; @@ -7191,6 +7246,56 @@ for (;; ptr++) 16-bit data item. */ *lengthptr += IMM2_SIZE; + + /* If this is a forward reference and we are within a (?|...) group, + the reference may end up as the number of a group which we are + currently inside, that is, it could be a recursive reference. In the + real compile this will be picked up and the reference wrapped with + OP_ONCE to make it atomic, so we must space in case this occurs. */ + + /* In fact, this can happen for a non-forward reference because + another group with the same number might be created later. This + issue is fixed "properly" in PCRE2. As PCRE1 is now in maintenance + only mode, we finesse the bug by allowing more memory always. */ + + *lengthptr += 2 + 2*LINK_SIZE; + + /* It is even worse than that. The current reference may be to an + existing named group with a different number (so apparently not + recursive) but which later on is also attached to a group with the + current number. This can only happen if $(| has been previous + encountered. In that case, we allow yet more memory, just in case. + (Again, this is fixed "properly" in PCRE2. */ + + if (cd->dupgroups) *lengthptr += 4 + 4*LINK_SIZE; + + /* Otherwise, check for recursion here. The name table does not exist + in the first pass; instead we must scan the list of names encountered + so far in order to get the number. If the name is not found, leave + the value of recno as 0 for a forward reference. */ + + else + { + ng = cd->named_groups; + for (i = 0; i < cd->names_found; i++, ng++) + { + if (namelen == ng->length && + STRNCMP_UC_UC(name, ng->name, namelen) == 0) + { + open_capitem *oc; + recno = ng->number; + if (is_recurse) break; + for (oc = cd->open_caps; oc != NULL; oc = oc->next) + { + if (oc->number == recno) + { + oc->flag = TRUE; + break; + } + } + } + } + } } /* In the real compile, search the name table. We check the name @@ -7237,8 +7342,6 @@ for (;; ptr++) for (i++; i < cd->names_found; i++) { if (STRCMP_UC_UC(slot + IMM2_SIZE, cslot + IMM2_SIZE) != 0) break; - - count++; cslot += cd->name_entry_size; } @@ -7247,6 +7350,7 @@ for (;; ptr++) { if (firstcharflags == REQ_UNSET) firstcharflags = REQ_NONE; previous = code; + item_hwm_offset = cd->hwm - cd->start_workspace; *code++ = ((options & PCRE_CASELESS) != 0)? OP_DNREFI : OP_DNREF; PUT2INC(code, 0, index); PUT2INC(code, 0, count); @@ -7284,9 +7388,14 @@ for (;; ptr++) /* ------------------------------------------------------------ */ - case CHAR_R: /* Recursion */ - ptr++; /* Same as (?0) */ - /* Fall through */ + case CHAR_R: /* Recursion, same as (?0) */ + recno = 0; + if (*(++ptr) != CHAR_RIGHT_PARENTHESIS) + { + *errorcodeptr = ERR29; + goto FAILED; + } + goto HANDLE_RECURSION; /* ------------------------------------------------------------ */ @@ -7323,7 +7432,15 @@ for (;; ptr++) recno = 0; while(IS_DIGIT(*ptr)) + { + if (recno > INT_MAX / 10 - 1) /* Integer overflow */ + { + while (IS_DIGIT(*ptr)) ptr++; + *errorcodeptr = ERR61; + goto FAILED; + } recno = recno * 10 + *ptr++ - CHAR_0; + } if (*ptr != (pcre_uchar)terminator) { @@ -7360,6 +7477,7 @@ for (;; ptr++) HANDLE_RECURSION: previous = code; + item_hwm_offset = cd->hwm - cd->start_workspace; called = cd->start_code; /* When we are actually compiling, find the bracket that is being @@ -7561,7 +7679,11 @@ for (;; ptr++) previous = NULL; cd->iscondassert = FALSE; } - else previous = code; + else + { + previous = code; + item_hwm_offset = cd->hwm - cd->start_workspace; + } *code = bravalue; tempcode = code; @@ -7809,7 +7931,7 @@ for (;; ptr++) const pcre_uchar *p; pcre_uint32 cf; - save_hwm_offset = cd->hwm - cd->start_workspace; /* Normally this is set when '(' is read */ + item_hwm_offset = cd->hwm - cd->start_workspace; /* Normally this is set when '(' is read */ terminator = (*(++ptr) == CHAR_LESS_THAN_SIGN)? CHAR_GREATER_THAN_SIGN : CHAR_APOSTROPHE; @@ -7838,7 +7960,7 @@ for (;; ptr++) if (*p != (pcre_uchar)terminator) { *errorcodeptr = ERR57; - break; + goto FAILED; } ptr++; goto HANDLE_NUMERICAL_RECURSION; @@ -7853,7 +7975,7 @@ for (;; ptr++) ptr[1] != CHAR_APOSTROPHE && ptr[1] != CHAR_LEFT_CURLY_BRACKET)) { *errorcodeptr = ERR69; - break; + goto FAILED; } is_recurse = FALSE; terminator = (*(++ptr) == CHAR_LESS_THAN_SIGN)? @@ -7877,6 +7999,7 @@ for (;; ptr++) HANDLE_REFERENCE: if (firstcharflags == REQ_UNSET) firstcharflags = REQ_NONE; previous = code; + item_hwm_offset = cd->hwm - cd->start_workspace; *code++ = ((options & PCRE_CASELESS) != 0)? OP_REFI : OP_REF; PUT2INC(code, 0, recno); cd->backref_map |= (recno < 32)? (1 << recno) : 1; @@ -7906,6 +8029,7 @@ for (;; ptr++) if (!get_ucp(&ptr, &negated, &ptype, &pdata, errorcodeptr)) goto FAILED; previous = code; + item_hwm_offset = cd->hwm - cd->start_workspace; *code++ = ((escape == ESC_p) != negated)? OP_PROP : OP_NOTPROP; *code++ = ptype; *code++ = pdata; @@ -7946,6 +8070,7 @@ for (;; ptr++) { previous = (escape > ESC_b && escape < ESC_Z)? code : NULL; + item_hwm_offset = cd->hwm - cd->start_workspace; *code++ = (!utf && escape == ESC_C)? OP_ALLANY : escape; } } @@ -7989,6 +8114,7 @@ for (;; ptr++) ONE_CHAR: previous = code; + item_hwm_offset = cd->hwm - cd->start_workspace; /* For caseless UTF-8 mode when UCP support is available, check whether this character has more than one other case. If so, generate a special @@ -9164,6 +9290,7 @@ cd->names_found = 0; cd->name_entry_size = 0; cd->name_table = NULL; cd->dupnames = FALSE; +cd->dupgroups = FALSE; cd->namedrefcount = 0; cd->start_code = cworkspace; cd->hwm = cworkspace; @@ -9336,6 +9463,16 @@ if (cd->hwm > cd->start_workspace) int offset, recno; cd->hwm -= LINK_SIZE; offset = GET(cd->hwm, 0); + + /* Check that the hwm handling hasn't gone wrong. This whole area is + rewritten in PCRE2 because there are some obscure cases. */ + + if (offset == 0 || codestart[offset-1] != OP_RECURSE) + { + errorcode = ERR10; + break; + } + recno = GET(codestart, offset); if (recno != prev_recno) { @@ -9366,7 +9503,7 @@ used in this code because at least one compiler gives a warning about loss of "const" attribute if the cast (pcre_uchar *)codestart is used directly in the function call. */ -if ((options & PCRE_NO_AUTO_POSSESS) == 0) +if (errorcode == 0 && (options & PCRE_NO_AUTO_POSSESS) == 0) { pcre_uchar *temp = (pcre_uchar *)codestart; auto_possessify(temp, utf, cd); @@ -9380,7 +9517,7 @@ OP_RECURSE that are not fixed length get a diagnosic with a useful offset. The exceptional ones forgo this. We scan the pattern to check that they are fixed length, and set their lengths. */ -if (cd->check_lookbehind) +if (errorcode == 0 && cd->check_lookbehind) { pcre_uchar *cc = (pcre_uchar *)codestart; @@ -9593,4 +9730,3 @@ return (pcre32 *)re; } /* End of pcre_compile.c */ - diff --git a/ext/pcre/pcrelib/pcre_exec.c b/ext/pcre/pcrelib/pcre_exec.c index 3942076..24b23ca 100644 --- a/ext/pcre/pcrelib/pcre_exec.c +++ b/ext/pcre/pcrelib/pcre_exec.c @@ -688,7 +688,7 @@ the alternative names that are used. */ #define foc number #define save_mark data -/* These statements are here to stop the compiler complaining about uninitialized +/* These statements are here to stop the compiler complaining about unitialized variables. */ #ifdef SUPPORT_UCP @@ -6685,7 +6685,8 @@ if (md->offset_vector != NULL) register int *iend = iptr - re->top_bracket; if (iend < md->offset_vector + 2) iend = md->offset_vector + 2; while (--iptr >= iend) *iptr = -1; - md->offset_vector[0] = md->offset_vector[1] = -1; + if (offsetcount > 0) md->offset_vector[0] = -1; + if (offsetcount > 1) md->offset_vector[1] = -1; } /* Set up the first character to match, if available. The first_char value is diff --git a/ext/pcre/pcrelib/pcre_internal.h b/ext/pcre/pcrelib/pcre_internal.h index 4c4817d..aec1879 100644 --- a/ext/pcre/pcrelib/pcre_internal.h +++ b/ext/pcre/pcrelib/pcre_internal.h @@ -988,7 +988,7 @@ other. NOTE: The values also appear in pcre_jit_compile.c. */ #ifndef EBCDIC #define HSPACE_LIST \ - CHAR_HT, CHAR_SPACE, 0xa0, \ + CHAR_HT, CHAR_SPACE, CHAR_NBSP, \ 0x1680, 0x180e, 0x2000, 0x2001, 0x2002, 0x2003, 0x2004, 0x2005, \ 0x2006, 0x2007, 0x2008, 0x2009, 0x200A, 0x202f, 0x205f, 0x3000, \ NOTACHAR @@ -1014,7 +1014,7 @@ other. NOTE: The values also appear in pcre_jit_compile.c. */ #define HSPACE_BYTE_CASES \ case CHAR_HT: \ case CHAR_SPACE: \ - case 0xa0 /* NBSP */ + case CHAR_NBSP #define HSPACE_CASES \ HSPACE_BYTE_CASES: \ @@ -1041,11 +1041,12 @@ other. NOTE: The values also appear in pcre_jit_compile.c. */ /* ------ EBCDIC environments ------ */ #else -#define HSPACE_LIST CHAR_HT, CHAR_SPACE +#define HSPACE_LIST CHAR_HT, CHAR_SPACE, CHAR_NBSP, NOTACHAR #define HSPACE_BYTE_CASES \ case CHAR_HT: \ - case CHAR_SPACE + case CHAR_SPACE: \ + case CHAR_NBSP #define HSPACE_CASES HSPACE_BYTE_CASES @@ -1219,6 +1220,7 @@ same code point. */ #define CHAR_ESC '\047' #define CHAR_DEL '\007' +#define CHAR_NBSP '\x41' #define STR_ESC "\047" #define STR_DEL "\007" @@ -1233,6 +1235,7 @@ a positive value. */ #define CHAR_NEL ((unsigned char)'\x85') #define CHAR_ESC '\033' #define CHAR_DEL '\177' +#define CHAR_NBSP ((unsigned char)'\xa0') #define STR_LF "\n" #define STR_NL STR_LF @@ -1610,6 +1613,7 @@ only. */ #define CHAR_VERTICAL_LINE '\174' #define CHAR_RIGHT_CURLY_BRACKET '\175' #define CHAR_TILDE '\176' +#define CHAR_NBSP ((unsigned char)'\xa0') #define STR_HT "\011" #define STR_VT "\013" @@ -1766,6 +1770,10 @@ only. */ /* Escape items that are just an encoding of a particular data value. */ +#ifndef ESC_a +#define ESC_a CHAR_BEL +#endif + #ifndef ESC_e #define ESC_e CHAR_ESC #endif @@ -2450,6 +2458,7 @@ typedef struct compile_data { BOOL had_pruneorskip; /* (*PRUNE) or (*SKIP) encountered */ BOOL check_lookbehind; /* Lookbehinds need later checking */ BOOL dupnames; /* Duplicate names exist */ + BOOL dupgroups; /* Duplicate groups exist: (?| found */ BOOL iscondassert; /* Next assert is a condition */ int nltype; /* Newline type */ int nllen; /* Newline string length */ diff --git a/ext/pcre/pcrelib/pcre_jit_compile.c b/ext/pcre/pcrelib/pcre_jit_compile.c index debdf6e..445de0c 100644 --- a/ext/pcre/pcrelib/pcre_jit_compile.c +++ b/ext/pcre/pcrelib/pcre_jit_compile.c @@ -1064,6 +1064,7 @@ pcre_uchar *alternative; pcre_uchar *end = NULL; int private_data_ptr = *private_data_start; int space, size, bracketlen; +BOOL repeat_check = TRUE; while (cc < ccend) { @@ -1071,9 +1072,10 @@ while (cc < ccend) size = 0; bracketlen = 0; if (private_data_ptr > SLJIT_MAX_LOCAL_SIZE) - return; + break; - if (*cc == OP_ONCE || *cc == OP_ONCE_NC || *cc == OP_BRA || *cc == OP_CBRA || *cc == OP_COND) + if (repeat_check && (*cc == OP_ONCE || *cc == OP_ONCE_NC || *cc == OP_BRA || *cc == OP_CBRA || *cc == OP_COND)) + { if (detect_repeat(common, cc)) { /* These brackets are converted to repeats, so no global @@ -1081,6 +1083,8 @@ while (cc < ccend) if (cc >= end) end = bracketend(cc); } + } + repeat_check = TRUE; switch(*cc) { @@ -1136,6 +1140,13 @@ while (cc < ccend) bracketlen = 1 + LINK_SIZE + IMM2_SIZE; break; + case OP_BRAZERO: + case OP_BRAMINZERO: + case OP_BRAPOSZERO: + repeat_check = FALSE; + size = 1; + break; + CASE_ITERATOR_PRIVATE_DATA_1 space = 1; size = -2; @@ -1162,12 +1173,17 @@ while (cc < ccend) size = 1; break; - CASE_ITERATOR_TYPE_PRIVATE_DATA_2B + case OP_TYPEUPTO: if (cc[1 + IMM2_SIZE] != OP_ANYNL && cc[1 + IMM2_SIZE] != OP_EXTUNI) space = 2; size = 1 + IMM2_SIZE; break; + case OP_TYPEMINUPTO: + space = 2; + size = 1 + IMM2_SIZE; + break; + case OP_CLASS: case OP_NCLASS: size += 1 + 32 / sizeof(pcre_uchar); @@ -1316,6 +1332,13 @@ while (cc < ccend) cc += 1 + LINK_SIZE + IMM2_SIZE; break; + case OP_THEN: + stack_restore = TRUE; + if (common->control_head_ptr != 0) + *needs_control_head = TRUE; + cc ++; + break; + default: stack_restore = TRUE; /* Fall through. */ @@ -2220,6 +2243,7 @@ while (current != NULL) SLJIT_ASSERT_STOP(); break; } + SLJIT_ASSERT(current > (sljit_sw*)current[-1]); current = (sljit_sw*)current[-1]; } return -1; @@ -3209,7 +3233,7 @@ bytes[len] = byte; bytes[0] = len; } -static int scan_prefix(compiler_common *common, pcre_uchar *cc, pcre_uint32 *chars, pcre_uint8 *bytes, int max_chars) +static int scan_prefix(compiler_common *common, pcre_uchar *cc, pcre_uint32 *chars, pcre_uint8 *bytes, int max_chars, pcre_uint32 *rec_count) { /* Recursive function, which scans prefix literals. */ BOOL last, any, caseless; @@ -3227,9 +3251,14 @@ pcre_uchar othercase[1]; repeat = 1; while (TRUE) { + if (*rec_count == 0) + return 0; + (*rec_count)--; + last = TRUE; any = FALSE; caseless = FALSE; + switch (*cc) { case OP_CHARI: @@ -3291,7 +3320,7 @@ while (TRUE) #ifdef SUPPORT_UTF if (common->utf && HAS_EXTRALEN(*cc)) len += GET_EXTRALEN(*cc); #endif - max_chars = scan_prefix(common, cc + len, chars, bytes, max_chars); + max_chars = scan_prefix(common, cc + len, chars, bytes, max_chars, rec_count); if (max_chars == 0) return consumed; last = FALSE; @@ -3314,7 +3343,7 @@ while (TRUE) alternative = cc + GET(cc, 1); while (*alternative == OP_ALT) { - max_chars = scan_prefix(common, alternative + 1 + LINK_SIZE, chars, bytes, max_chars); + max_chars = scan_prefix(common, alternative + 1 + LINK_SIZE, chars, bytes, max_chars, rec_count); if (max_chars == 0) return consumed; alternative += GET(alternative, 1); @@ -3556,6 +3585,7 @@ int i, max, from; int range_right = -1, range_len = 3 - 1; sljit_ub *update_table = NULL; BOOL in_range; +pcre_uint32 rec_count; for (i = 0; i < MAX_N_CHARS; i++) { @@ -3564,7 +3594,8 @@ for (i = 0; i < MAX_N_CHARS; i++) bytes[i * MAX_N_BYTES] = 0; } -max = scan_prefix(common, common->start, chars, bytes, MAX_N_CHARS); +rec_count = 10000; +max = scan_prefix(common, common->start, chars, bytes, MAX_N_CHARS, &rec_count); if (max <= 1) return FALSE; @@ -4311,8 +4342,10 @@ switch(length) case 4: if ((ranges[1] - ranges[0]) == (ranges[3] - ranges[2]) && (ranges[0] | (ranges[2] - ranges[0])) == ranges[2] + && (ranges[1] & (ranges[2] - ranges[0])) == 0 && is_powerof2(ranges[2] - ranges[0])) { + SLJIT_ASSERT((ranges[0] & (ranges[2] - ranges[0])) == 0 && (ranges[2] & ranges[3] & (ranges[2] - ranges[0])) != 0); OP2(SLJIT_OR, TMP1, 0, TMP1, 0, SLJIT_IMM, ranges[2] - ranges[0]); if (ranges[2] + 1 != ranges[3]) { @@ -4900,9 +4933,10 @@ else if ((cc[-1] & XCL_MAP) != 0) if (!check_class_ranges(common, (const pcre_uint8 *)cc, FALSE, TRUE, list)) { #ifdef COMPILE_PCRE8 - SLJIT_ASSERT(common->utf); + jump = NULL; + if (common->utf) #endif - jump = CMP(SLJIT_GREATER, TMP1, 0, SLJIT_IMM, 255); + jump = CMP(SLJIT_GREATER, TMP1, 0, SLJIT_IMM, 255); OP2(SLJIT_AND, TMP2, 0, TMP1, 0, SLJIT_IMM, 0x7); OP2(SLJIT_LSHR, TMP1, 0, TMP1, 0, SLJIT_IMM, 3); @@ -4911,7 +4945,10 @@ else if ((cc[-1] & XCL_MAP) != 0) OP2(SLJIT_AND | SLJIT_SET_E, SLJIT_UNUSED, 0, TMP1, 0, TMP2, 0); add_jump(compiler, list, JUMP(SLJIT_NOT_ZERO)); - JUMPHERE(jump); +#ifdef COMPILE_PCRE8 + if (common->utf) +#endif + JUMPHERE(jump); } OP1(SLJIT_MOV, TMP1, 0, TMP3, 0); @@ -5219,7 +5256,7 @@ while (*cc != XCL_END) OP_FLAGS(SLJIT_MOV, TMP2, 0, SLJIT_UNUSED, 0, SLJIT_LESS_EQUAL); SET_CHAR_OFFSET(0); - OP2(SLJIT_SUB | SLJIT_SET_U, SLJIT_UNUSED, 0, TMP1, 0, SLJIT_IMM, 0xff); + OP2(SLJIT_SUB | SLJIT_SET_U, SLJIT_UNUSED, 0, TMP1, 0, SLJIT_IMM, 0x7f); OP_FLAGS(SLJIT_AND, TMP2, 0, TMP2, 0, SLJIT_LESS_EQUAL); SET_TYPE_OFFSET(ucp_Pc); @@ -7665,6 +7702,10 @@ while (*cc != OP_KETRPOS) OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(0), STR_PTR, 0); } + /* Even if the match is empty, we need to reset the control head. */ + if (needs_control_head) + OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_SP), common->control_head_ptr, SLJIT_MEM1(STACK_TOP), STACK(stack)); + if (opcode == OP_SBRAPOS || opcode == OP_SCBRAPOS) add_jump(compiler, &emptymatch, CMP(SLJIT_EQUAL, TMP1, 0, STR_PTR, 0)); @@ -7692,6 +7733,10 @@ while (*cc != OP_KETRPOS) OP1(SLJIT_MOV, SLJIT_MEM1(TMP2), (framesize + 1) * sizeof(sljit_sw), STR_PTR, 0); } + /* Even if the match is empty, we need to reset the control head. */ + if (needs_control_head) + OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_SP), common->control_head_ptr, SLJIT_MEM1(STACK_TOP), STACK(stack)); + if (opcode == OP_SBRAPOS || opcode == OP_SCBRAPOS) add_jump(compiler, &emptymatch, CMP(SLJIT_EQUAL, TMP1, 0, STR_PTR, 0)); @@ -7704,9 +7749,6 @@ while (*cc != OP_KETRPOS) } } - if (needs_control_head) - OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_SP), common->control_head_ptr, SLJIT_MEM1(STACK_TOP), STACK(stack)); - JUMPTO(SLJIT_JUMP, loop); flush_stubs(common); @@ -8441,8 +8483,7 @@ while (cc < ccend) OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(1), STR_PTR, 0); } BACKTRACK_AS(braminzero_backtrack)->matchingpath = LABEL(); - if (cc[1] > OP_ASSERTBACK_NOT) - count_match(common); + count_match(common); break; case OP_ONCE: @@ -9624,7 +9665,7 @@ static SLJIT_INLINE void compile_recurse(compiler_common *common) DEFINE_COMPILER; pcre_uchar *cc = common->start + common->currententry->start; pcre_uchar *ccbegin = cc + 1 + LINK_SIZE + (*cc == OP_BRA ? 0 : IMM2_SIZE); -pcre_uchar *ccend = bracketend(cc); +pcre_uchar *ccend = bracketend(cc) - (1 + LINK_SIZE); BOOL needs_control_head; int framesize = get_framesize(common, cc, NULL, TRUE, &needs_control_head); int private_data_size = get_private_data_copy_length(common, ccbegin, ccend, needs_control_head); @@ -9648,6 +9689,7 @@ set_jumps(common->currententry->calls, common->currententry->entry); sljit_emit_fast_enter(compiler, TMP2, 0); allocate_stack(common, private_data_size + framesize + alternativesize); +count_match(common); OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(private_data_size + framesize + alternativesize - 1), TMP2, 0); copy_private_data(common, ccbegin, ccend, TRUE, private_data_size + framesize + alternativesize, framesize + alternativesize, needs_control_head); if (needs_control_head) @@ -9992,6 +10034,7 @@ OP1(SLJIT_MOV, TMP2, 0, SLJIT_MEM1(TMP1), SLJIT_OFFSETOF(jit_arguments, stack)); OP1(SLJIT_MOV_UI, TMP1, 0, SLJIT_MEM1(TMP1), SLJIT_OFFSETOF(jit_arguments, limit_match)); OP1(SLJIT_MOV, STACK_TOP, 0, SLJIT_MEM1(TMP2), SLJIT_OFFSETOF(struct sljit_stack, base)); OP1(SLJIT_MOV, STACK_LIMIT, 0, SLJIT_MEM1(TMP2), SLJIT_OFFSETOF(struct sljit_stack, limit)); +OP2(SLJIT_ADD, TMP1, 0, TMP1, 0, SLJIT_IMM, 1); OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_SP), LIMIT_MATCH, TMP1, 0); if (mode == JIT_PARTIAL_SOFT_COMPILE) diff --git a/ext/pcre/pcrelib/pcre_study.c b/ext/pcre/pcrelib/pcre_study.c index 998fe23..7fd0ba0 100644 --- a/ext/pcre/pcrelib/pcre_study.c +++ b/ext/pcre/pcrelib/pcre_study.c @@ -71,6 +71,7 @@ rather than bytes. startcode pointer to start of the whole pattern's code options the compiling options recurses chain of recurse_check to catch mutual recursion + countptr pointer to call count (to catch over complexity) Returns: the minimum length -1 if \C in UTF-8 mode or (*ACCEPT) was encountered @@ -80,7 +81,8 @@ Returns: the minimum length static int find_minlength(const REAL_PCRE *re, const pcre_uchar *code, - const pcre_uchar *startcode, int options, recurse_check *recurses) + const pcre_uchar *startcode, int options, recurse_check *recurses, + int *countptr) { int length = -1; /* PCRE_UTF16 has the same value as PCRE_UTF8. */ @@ -90,6 +92,8 @@ recurse_check this_recurse; register int branchlength = 0; register pcre_uchar *cc = (pcre_uchar *)code + 1 + LINK_SIZE; +if ((*countptr)++ > 1000) return -1; /* too complex */ + if (*code == OP_CBRA || *code == OP_SCBRA || *code == OP_CBRAPOS || *code == OP_SCBRAPOS) cc += IMM2_SIZE; @@ -131,7 +135,7 @@ for (;;) case OP_SBRAPOS: case OP_ONCE: case OP_ONCE_NC: - d = find_minlength(re, cc, startcode, options, recurses); + d = find_minlength(re, cc, startcode, options, recurses, countptr); if (d < 0) return d; branchlength += d; do cc += GET(cc, 1); while (*cc == OP_ALT); @@ -415,7 +419,8 @@ for (;;) int dd; this_recurse.prev = recurses; this_recurse.group = cs; - dd = find_minlength(re, cs, startcode, options, &this_recurse); + dd = find_minlength(re, cs, startcode, options, &this_recurse, + countptr); if (dd < d) d = dd; } } @@ -451,7 +456,8 @@ for (;;) { this_recurse.prev = recurses; this_recurse.group = cs; - d = find_minlength(re, cs, startcode, options, &this_recurse); + d = find_minlength(re, cs, startcode, options, &this_recurse, + countptr); } } } @@ -514,7 +520,7 @@ for (;;) this_recurse.prev = recurses; this_recurse.group = cs; branchlength += find_minlength(re, cs, startcode, options, - &this_recurse); + &this_recurse, countptr); } } cc += 1 + LINK_SIZE; @@ -1453,6 +1459,7 @@ pcre32_study(const pcre32 *external_re, int options, const char **errorptr) #endif { int min; +int count = 0; BOOL bits_set = FALSE; pcre_uint8 start_bits[32]; PUBL(extra) *extra = NULL; @@ -1539,7 +1546,7 @@ if ((re->options & PCRE_ANCHORED) == 0 && /* Find the minimum length of subject string. */ -switch(min = find_minlength(re, code, code, re->options, NULL)) +switch(min = find_minlength(re, code, code, re->options, NULL, &count)) { case -2: *errorptr = "internal error: missing capturing bracket"; return NULL; case -3: *errorptr = "internal error: opcode not recognized"; return NULL; diff --git a/ext/pcre/pcrelib/pcre_xclass.c b/ext/pcre/pcrelib/pcre_xclass.c index c2b61f0..ef759a5 100644 --- a/ext/pcre/pcrelib/pcre_xclass.c +++ b/ext/pcre/pcrelib/pcre_xclass.c @@ -246,7 +246,7 @@ while ((t = *data++) != XCL_END) case PT_PXPUNCT: if ((PRIV(ucp_gentype)[prop->chartype] == ucp_P || - (c < 256 && PRIV(ucp_gentype)[prop->chartype] == ucp_S)) == isprop) + (c < 128 && PRIV(ucp_gentype)[prop->chartype] == ucp_S)) == isprop) return !negated; break; diff --git a/ext/pcre/pcrelib/sljit/sljitConfig.h b/ext/pcre/pcrelib/sljit/sljitConfig.h index 10364c3..1c8a521 100644 --- a/ext/pcre/pcrelib/sljit/sljitConfig.h +++ b/ext/pcre/pcrelib/sljit/sljitConfig.h @@ -96,6 +96,15 @@ #define SLJIT_EXECUTABLE_ALLOCATOR 1 #endif +/* Force cdecl calling convention even if a better calling + convention (e.g. fastcall) is supported by the C compiler. + If this option is enabled, C functions without + SLJIT_CALL can also be called from JIT code. */ +#ifndef SLJIT_USE_CDECL_CALLING_CONVENTION +/* Disabled by default */ +#define SLJIT_USE_CDECL_CALLING_CONVENTION 0 +#endif + /* Return with error when an invalid argument is passed. */ #ifndef SLJIT_ARGUMENT_CHECKS /* Disabled by default */ diff --git a/ext/pcre/pcrelib/sljit/sljitConfigInternal.h b/ext/pcre/pcrelib/sljit/sljitConfigInternal.h index 3284012..16e3547 100644 --- a/ext/pcre/pcrelib/sljit/sljitConfigInternal.h +++ b/ext/pcre/pcrelib/sljit/sljitConfigInternal.h @@ -468,7 +468,12 @@ typedef double sljit_d; #ifndef SLJIT_CALL -#if (defined SLJIT_CONFIG_X86_32 && SLJIT_CONFIG_X86_32) +#if (defined SLJIT_USE_CDECL_CALLING_CONVENTION && SLJIT_USE_CDECL_CALLING_CONVENTION) + +/* Force cdecl. */ +#define SLJIT_CALL + +#elif (defined SLJIT_CONFIG_X86_32 && SLJIT_CONFIG_X86_32) #if defined(__GNUC__) && !defined(__APPLE__) @@ -608,6 +613,12 @@ SLJIT_API_FUNC_ATTRIBUTE void sljit_free_unused_memory_exec(void); #define SLJIT_LOCALS_OFFSET_BASE ((23 + 1) * sizeof(sljit_sw)) #endif +#elif (defined SLJIT_CONFIG_TILEGX && SLJIT_CONFIG_TILEGX) + +#define SLJIT_NUMBER_OF_REGISTERS 10 +#define SLJIT_NUMBER_OF_SAVED_REGISTERS 5 +#define SLJIT_LOCALS_OFFSET_BASE 0 + #elif (defined SLJIT_CONFIG_UNSUPPORTED && SLJIT_CONFIG_UNSUPPORTED) #define SLJIT_NUMBER_OF_REGISTERS 0 diff --git a/ext/pcre/pcrelib/sljit/sljitLir.c b/ext/pcre/pcrelib/sljit/sljitLir.c index 5039a7e..0f1b1c9 100644 --- a/ext/pcre/pcrelib/sljit/sljitLir.c +++ b/ext/pcre/pcrelib/sljit/sljitLir.c @@ -845,8 +845,8 @@ SLJIT_API_FUNC_ATTRIBUTE void sljit_compiler_verbose(struct sljit_compiler *comp } static SLJIT_CONST char* op0_names[] = { - (char*)"breakpoint", (char*)"nop", - (char*)"lumul", (char*)"lsmul", (char*)"ludiv", (char*)"lsdiv", + (char*)"breakpoint", (char*)"nop", (char*)"lumul", (char*)"lsmul", + (char*)"udivmod", (char*)"sdivmod", (char*)"udivi", (char*)"sdivi" }; static SLJIT_CONST char* op1_names[] = { @@ -1036,7 +1036,7 @@ static SLJIT_INLINE CHECK_RETURN_TYPE check_sljit_emit_op0(struct sljit_compiler { #if (defined SLJIT_ARGUMENT_CHECKS && SLJIT_ARGUMENT_CHECKS) CHECK_ARGUMENT((op >= SLJIT_BREAKPOINT && op <= SLJIT_LSMUL) - || ((op & ~SLJIT_INT_OP) >= SLJIT_LUDIV && (op & ~SLJIT_INT_OP) <= SLJIT_LSDIV)); + || ((op & ~SLJIT_INT_OP) >= SLJIT_UDIVMOD && (op & ~SLJIT_INT_OP) <= SLJIT_SDIVI)); CHECK_ARGUMENT(op < SLJIT_LUMUL || compiler->scratches >= 2); #endif #if (defined SLJIT_VERBOSE && SLJIT_VERBOSE) @@ -1447,6 +1447,8 @@ static SLJIT_INLINE CHECK_RETURN_TYPE check_sljit_emit_op_flags(struct sljit_com static SLJIT_INLINE CHECK_RETURN_TYPE check_sljit_get_local_base(struct sljit_compiler *compiler, sljit_si dst, sljit_sw dstw, sljit_sw offset) { + SLJIT_UNUSED_ARG(offset); + #if (defined SLJIT_ARGUMENT_CHECKS && SLJIT_ARGUMENT_CHECKS) FUNCTION_CHECK_DST(dst, dstw); #endif @@ -1462,6 +1464,8 @@ static SLJIT_INLINE CHECK_RETURN_TYPE check_sljit_get_local_base(struct sljit_co static SLJIT_INLINE CHECK_RETURN_TYPE check_sljit_emit_const(struct sljit_compiler *compiler, sljit_si dst, sljit_sw dstw, sljit_sw init_value) { + SLJIT_UNUSED_ARG(init_value); + #if (defined SLJIT_ARGUMENT_CHECKS && SLJIT_ARGUMENT_CHECKS) FUNCTION_CHECK_DST(dst, dstw); #endif diff --git a/ext/pcre/pcrelib/sljit/sljitLir.h b/ext/pcre/pcrelib/sljit/sljitLir.h index 24c0f60..2e2e9ac09 100644 --- a/ext/pcre/pcrelib/sljit/sljitLir.h +++ b/ext/pcre/pcrelib/sljit/sljitLir.h @@ -687,7 +687,7 @@ SLJIT_API_FUNC_ATTRIBUTE sljit_si sljit_emit_fast_return(struct sljit_compiler * #define SLJIT_OP0_BASE 0 /* Flags: - (never set any flags) - Note: breakpoint instruction is not supported by all architectures (namely ppc) + Note: breakpoint instruction is not supported by all architectures (e.g. ppc) It falls back to SLJIT_NOP in those cases. */ #define SLJIT_BREAKPOINT (SLJIT_OP0_BASE + 0) /* Flags: - (never set any flags) @@ -696,24 +696,42 @@ SLJIT_API_FUNC_ATTRIBUTE sljit_si sljit_emit_fast_return(struct sljit_compiler * #define SLJIT_NOP (SLJIT_OP0_BASE + 1) /* Flags: - (may destroy flags) Unsigned multiplication of SLJIT_R0 and SLJIT_R1. - Result goes to SLJIT_R1:SLJIT_R0 (high:low) word */ + Result is placed into SLJIT_R1:SLJIT_R0 (high:low) word */ #define SLJIT_LUMUL (SLJIT_OP0_BASE + 2) /* Flags: - (may destroy flags) Signed multiplication of SLJIT_R0 and SLJIT_R1. - Result goes to SLJIT_R1:SLJIT_R0 (high:low) word */ + Result is placed into SLJIT_R1:SLJIT_R0 (high:low) word */ #define SLJIT_LSMUL (SLJIT_OP0_BASE + 3) /* Flags: I - (may destroy flags) Unsigned divide of the value in SLJIT_R0 by the value in SLJIT_R1. - The result is placed in SLJIT_R0 and the remainder goes to SLJIT_R1. - Note: if SLJIT_R1 contains 0, the behaviour is undefined. */ -#define SLJIT_LUDIV (SLJIT_OP0_BASE + 4) -#define SLJIT_ILUDIV (SLJIT_LUDIV | SLJIT_INT_OP) + The result is placed into SLJIT_R0 and the remainder into SLJIT_R1. + Note: if SLJIT_R1 is 0, the behaviour is undefined. */ +#define SLJIT_UDIVMOD (SLJIT_OP0_BASE + 4) +#define SLJIT_IUDIVMOD (SLJIT_UDIVMOD | SLJIT_INT_OP) /* Flags: I - (may destroy flags) Signed divide of the value in SLJIT_R0 by the value in SLJIT_R1. - The result is placed in SLJIT_R0 and the remainder goes to SLJIT_R1. - Note: if SLJIT_R1 contains 0, the behaviour is undefined. */ -#define SLJIT_LSDIV (SLJIT_OP0_BASE + 5) -#define SLJIT_ILSDIV (SLJIT_LSDIV | SLJIT_INT_OP) + The result is placed into SLJIT_R0 and the remainder into SLJIT_R1. + Note: if SLJIT_R1 is 0, the behaviour is undefined. + Note: if SLJIT_R1 is -1 and SLJIT_R0 is integer min (0x800..00), + the behaviour is undefined. */ +#define SLJIT_SDIVMOD (SLJIT_OP0_BASE + 5) +#define SLJIT_ISDIVMOD (SLJIT_SDIVMOD | SLJIT_INT_OP) +/* Flags: I - (may destroy flags) + Unsigned divide of the value in SLJIT_R0 by the value in SLJIT_R1. + The result is placed into SLJIT_R0. SLJIT_R1 preserves its value. + Note: if SLJIT_R1 is 0, the behaviour is undefined. + Note: SLJIT_SDIV is single precision divide. */ +#define SLJIT_UDIVI (SLJIT_OP0_BASE + 6) +#define SLJIT_IUDIVI (SLJIT_UDIVI | SLJIT_INT_OP) +/* Flags: I - (may destroy flags) + Signed divide of the value in SLJIT_R0 by the value in SLJIT_R1. + The result is placed into SLJIT_R0. SLJIT_R1 preserves its value. + Note: if SLJIT_R1 is 0, the behaviour is undefined. + Note: if SLJIT_R1 is -1 and SLJIT_R0 is integer min (0x800..00), + the behaviour is undefined. + Note: SLJIT_SDIV is single precision divide. */ +#define SLJIT_SDIVI (SLJIT_OP0_BASE + 7) +#define SLJIT_ISDIVI (SLJIT_SDIVI | SLJIT_INT_OP) SLJIT_API_FUNC_ATTRIBUTE sljit_si sljit_emit_op0(struct sljit_compiler *compiler, sljit_si op); @@ -851,34 +869,6 @@ SLJIT_API_FUNC_ATTRIBUTE sljit_si sljit_emit_op2(struct sljit_compiler *compiler sljit_si src1, sljit_sw src1w, sljit_si src2, sljit_sw src2w); -/* The following function is a helper function for sljit_emit_op_custom. - It returns with the real machine register index ( >=0 ) of any SLJIT_R, - SLJIT_S and SLJIT_SP registers. - - Note: it returns with -1 for virtual registers (only on x86-32). */ - -SLJIT_API_FUNC_ATTRIBUTE sljit_si sljit_get_register_index(sljit_si reg); - -/* The following function is a helper function for sljit_emit_op_custom. - It returns with the real machine register index of any SLJIT_FLOAT register. - - Note: the index is always an even number on ARM (except ARM-64), MIPS, and SPARC. */ - -SLJIT_API_FUNC_ATTRIBUTE sljit_si sljit_get_float_register_index(sljit_si reg); - -/* Any instruction can be inserted into the instruction stream by - sljit_emit_op_custom. It has a similar purpose as inline assembly. - The size parameter must match to the instruction size of the target - architecture: - - x86: 0 < size <= 15. The instruction argument can be byte aligned. - Thumb2: if size == 2, the instruction argument must be 2 byte aligned. - if size == 4, the instruction argument must be 4 byte aligned. - Otherwise: size must be 4 and instruction argument must be 4 byte aligned. */ - -SLJIT_API_FUNC_ATTRIBUTE sljit_si sljit_emit_op_custom(struct sljit_compiler *compiler, - void *instruction, sljit_si size); - /* Returns with non-zero if fpu is available. */ SLJIT_API_FUNC_ATTRIBUTE sljit_si sljit_is_fpu_available(void); @@ -1196,4 +1186,64 @@ SLJIT_API_FUNC_ATTRIBUTE void sljit_set_function_context(void** func_ptr, struct #endif /* !(defined SLJIT_INDIRECT_CALL && SLJIT_INDIRECT_CALL) */ +/* --------------------------------------------------------------------- */ +/* CPU specific functions */ +/* --------------------------------------------------------------------- */ + +/* The following function is a helper function for sljit_emit_op_custom. + It returns with the real machine register index ( >=0 ) of any SLJIT_R, + SLJIT_S and SLJIT_SP registers. + + Note: it returns with -1 for virtual registers (only on x86-32). */ + +SLJIT_API_FUNC_ATTRIBUTE sljit_si sljit_get_register_index(sljit_si reg); + +/* The following function is a helper function for sljit_emit_op_custom. + It returns with the real machine register index of any SLJIT_FLOAT register. + + Note: the index is always an even number on ARM (except ARM-64), MIPS, and SPARC. */ + +SLJIT_API_FUNC_ATTRIBUTE sljit_si sljit_get_float_register_index(sljit_si reg); + +/* Any instruction can be inserted into the instruction stream by + sljit_emit_op_custom. It has a similar purpose as inline assembly. + The size parameter must match to the instruction size of the target + architecture: + + x86: 0 < size <= 15. The instruction argument can be byte aligned. + Thumb2: if size == 2, the instruction argument must be 2 byte aligned. + if size == 4, the instruction argument must be 4 byte aligned. + Otherwise: size must be 4 and instruction argument must be 4 byte aligned. */ + +SLJIT_API_FUNC_ATTRIBUTE sljit_si sljit_emit_op_custom(struct sljit_compiler *compiler, + void *instruction, sljit_si size); + +#if (defined SLJIT_CONFIG_X86 && SLJIT_CONFIG_X86) + +/* Returns with non-zero if sse2 is available. */ + +SLJIT_API_FUNC_ATTRIBUTE sljit_si sljit_x86_is_sse2_available(void); + +/* Returns with non-zero if cmov instruction is available. */ + +SLJIT_API_FUNC_ATTRIBUTE sljit_si sljit_x86_is_cmov_available(void); + +/* Emit a conditional mov instruction on x86 CPUs. This instruction + moves src to destination, if the condition is satisfied. Unlike + other arithmetic instructions, destination must be a register. + Before such instructions are emitted, cmov support should be + checked by sljit_x86_is_cmov_available function. + type must be between SLJIT_EQUAL and SLJIT_S_ORDERED + dst_reg must be a valid register and it can be combined + with SLJIT_INT_OP to perform 32 bit arithmetic + Flags: I - (never set any flags) + */ + +SLJIT_API_FUNC_ATTRIBUTE sljit_si sljit_x86_emit_cmov(struct sljit_compiler *compiler, + sljit_si type, + sljit_si dst_reg, + sljit_si src, sljit_sw srcw); + +#endif + #endif /* _SLJIT_LIR_H_ */ diff --git a/ext/pcre/pcrelib/sljit/sljitNativeARM_32.c b/ext/pcre/pcrelib/sljit/sljitNativeARM_32.c index aca1d31..5cd4c71 100644 --- a/ext/pcre/pcrelib/sljit/sljitNativeARM_32.c +++ b/ext/pcre/pcrelib/sljit/sljitNativeARM_32.c @@ -1833,18 +1833,33 @@ SLJIT_API_FUNC_ATTRIBUTE sljit_si sljit_emit_op0(struct sljit_compiler *compiler | (reg_map[SLJIT_R0] << 8) | reg_map[TMP_REG1]); #endif - case SLJIT_LUDIV: - case SLJIT_LSDIV: - if (compiler->scratches >= 3) + case SLJIT_UDIVMOD: + case SLJIT_SDIVMOD: + case SLJIT_UDIVI: + case SLJIT_SDIVI: + SLJIT_COMPILE_ASSERT((SLJIT_UDIVMOD & 0x2) == 0 && SLJIT_UDIVI - 0x2 == SLJIT_UDIVMOD, bad_div_opcode_assignments); + SLJIT_COMPILE_ASSERT(reg_map[2] == 1 && reg_map[3] == 2, bad_register_mapping); + + if ((op >= SLJIT_UDIVI) && (compiler->scratches >= 3)) { FAIL_IF(push_inst(compiler, 0xe52d2008 /* str r2, [sp, #-8]! */)); + FAIL_IF(push_inst(compiler, 0xe58d1004 /* str r1, [sp, #4] */)); + } + else if ((op >= SLJIT_UDIVI) || (compiler->scratches >= 3)) + FAIL_IF(push_inst(compiler, 0xe52d0008 | (op >= SLJIT_UDIVI ? 0x1000 : 0x2000) /* str r1/r2, [sp, #-8]! */)); + #if defined(__GNUC__) FAIL_IF(sljit_emit_ijump(compiler, SLJIT_FAST_CALL, SLJIT_IMM, - (op == SLJIT_LUDIV ? SLJIT_FUNC_OFFSET(__aeabi_uidivmod) : SLJIT_FUNC_OFFSET(__aeabi_idivmod)))); + ((op | 0x2) == SLJIT_UDIVI ? SLJIT_FUNC_OFFSET(__aeabi_uidivmod) : SLJIT_FUNC_OFFSET(__aeabi_idivmod)))); #else #error "Software divmod functions are needed" #endif - if (compiler->scratches >= 3) - return push_inst(compiler, 0xe49d2008 /* ldr r2, [sp], #8 */); + + if ((op >= SLJIT_UDIVI) && (compiler->scratches >= 3)) { + FAIL_IF(push_inst(compiler, 0xe59d1004 /* ldr r1, [sp, #4] */)); + FAIL_IF(push_inst(compiler, 0xe49d2008 /* ldr r2, [sp], #8 */)); + } + else if ((op >= SLJIT_UDIVI) || (compiler->scratches >= 3)) + return push_inst(compiler, 0xe49d0008 | (op >= SLJIT_UDIVI ? 0x1000 : 0x2000) /* ldr r1/r2, [sp], #8 */); return SLJIT_SUCCESS; } diff --git a/ext/pcre/pcrelib/sljit/sljitNativeARM_64.c b/ext/pcre/pcrelib/sljit/sljitNativeARM_64.c index b66455f..044a675 100644 --- a/ext/pcre/pcrelib/sljit/sljitNativeARM_64.c +++ b/ext/pcre/pcrelib/sljit/sljitNativeARM_64.c @@ -1087,14 +1087,20 @@ SLJIT_API_FUNC_ATTRIBUTE sljit_si sljit_emit_enter(struct sljit_compiler *compil saved_regs_size += sizeof(sljit_sw); } local_size -= saved_regs_size + SLJIT_LOCALS_OFFSET; - FAIL_IF(push_inst(compiler, SUBI | RD(TMP_SP) | RN(TMP_SP) | (saved_regs_size << 10))); + if (saved_regs_size > 0) + FAIL_IF(push_inst(compiler, SUBI | RD(TMP_SP) | RN(TMP_SP) | (saved_regs_size << 10))); } tmp = saveds < SLJIT_NUMBER_OF_SAVED_REGISTERS ? (SLJIT_S0 + 1 - saveds) : SLJIT_FIRST_SAVED_REG; prev = -1; for (i = SLJIT_S0; i >= tmp; i--) { if (prev == -1) { - prev = i; + if (!(offs & (1 << 15))) { + prev = i; + continue; + } + FAIL_IF(push_inst(compiler, STRI | RT(i) | RN(TMP_SP) | (offs >> 5))); + offs += 1 << 15; continue; } FAIL_IF(push_inst(compiler, STP | RT(prev) | RT2(i) | RN(TMP_SP) | offs)); @@ -1104,7 +1110,12 @@ SLJIT_API_FUNC_ATTRIBUTE sljit_si sljit_emit_enter(struct sljit_compiler *compil for (i = scratches; i >= SLJIT_FIRST_SAVED_REG; i--) { if (prev == -1) { - prev = i; + if (!(offs & (1 << 15))) { + prev = i; + continue; + } + FAIL_IF(push_inst(compiler, STRI | RT(i) | RN(TMP_SP) | (offs >> 5))); + offs += 1 << 15; continue; } FAIL_IF(push_inst(compiler, STP | RT(prev) | RT2(i) | RN(TMP_SP) | offs)); @@ -1112,8 +1123,7 @@ SLJIT_API_FUNC_ATTRIBUTE sljit_si sljit_emit_enter(struct sljit_compiler *compil prev = -1; } - if (prev != -1) - FAIL_IF(push_inst(compiler, STRI | RT(prev) | RN(TMP_SP) | (offs >> 5))); + SLJIT_ASSERT(prev == -1); if (compiler->local_size > (63 * sizeof(sljit_sw))) { /* The local_size is already adjusted by the saved registers. */ @@ -1188,7 +1198,12 @@ SLJIT_API_FUNC_ATTRIBUTE sljit_si sljit_emit_return(struct sljit_compiler *compi prev = -1; for (i = SLJIT_S0; i >= tmp; i--) { if (prev == -1) { - prev = i; + if (!(offs & (1 << 15))) { + prev = i; + continue; + } + FAIL_IF(push_inst(compiler, LDRI | RT(i) | RN(TMP_SP) | (offs >> 5))); + offs += 1 << 15; continue; } FAIL_IF(push_inst(compiler, LDP | RT(prev) | RT2(i) | RN(TMP_SP) | offs)); @@ -1198,7 +1213,12 @@ SLJIT_API_FUNC_ATTRIBUTE sljit_si sljit_emit_return(struct sljit_compiler *compi for (i = compiler->scratches; i >= SLJIT_FIRST_SAVED_REG; i--) { if (prev == -1) { - prev = i; + if (!(offs & (1 << 15))) { + prev = i; + continue; + } + FAIL_IF(push_inst(compiler, LDRI | RT(i) | RN(TMP_SP) | (offs >> 5))); + offs += 1 << 15; continue; } FAIL_IF(push_inst(compiler, LDP | RT(prev) | RT2(i) | RN(TMP_SP) | offs)); @@ -1206,13 +1226,12 @@ SLJIT_API_FUNC_ATTRIBUTE sljit_si sljit_emit_return(struct sljit_compiler *compi prev = -1; } - if (prev != -1) - FAIL_IF(push_inst(compiler, LDRI | RT(prev) | RN(TMP_SP) | (offs >> 5))); + SLJIT_ASSERT(prev == -1); if (compiler->local_size <= (63 * sizeof(sljit_sw))) { FAIL_IF(push_inst(compiler, LDP_PST | 29 | RT2(TMP_LR) | RN(TMP_SP) | (((local_size >> 3) & 0x7f) << 15))); - } else { + } else if (saved_regs_size > 0) { FAIL_IF(push_inst(compiler, ADDI | RD(TMP_SP) | RN(TMP_SP) | (saved_regs_size << 10))); } @@ -1242,12 +1261,15 @@ SLJIT_API_FUNC_ATTRIBUTE sljit_si sljit_emit_op0(struct sljit_compiler *compiler FAIL_IF(push_inst(compiler, ORR | RD(TMP_REG1) | RN(TMP_ZERO) | RM(SLJIT_R0))); FAIL_IF(push_inst(compiler, MADD | RD(SLJIT_R0) | RN(SLJIT_R0) | RM(SLJIT_R1) | RT2(TMP_ZERO))); return push_inst(compiler, (op == SLJIT_LUMUL ? UMULH : SMULH) | RD(SLJIT_R1) | RN(TMP_REG1) | RM(SLJIT_R1)); - case SLJIT_LUDIV: - case SLJIT_LSDIV: + case SLJIT_UDIVMOD: + case SLJIT_SDIVMOD: FAIL_IF(push_inst(compiler, (ORR ^ inv_bits) | RD(TMP_REG1) | RN(TMP_ZERO) | RM(SLJIT_R0))); - FAIL_IF(push_inst(compiler, ((op == SLJIT_LUDIV ? UDIV : SDIV) ^ inv_bits) | RD(SLJIT_R0) | RN(SLJIT_R0) | RM(SLJIT_R1))); + FAIL_IF(push_inst(compiler, ((op == SLJIT_UDIVMOD ? UDIV : SDIV) ^ inv_bits) | RD(SLJIT_R0) | RN(SLJIT_R0) | RM(SLJIT_R1))); FAIL_IF(push_inst(compiler, (MADD ^ inv_bits) | RD(SLJIT_R1) | RN(SLJIT_R0) | RM(SLJIT_R1) | RT2(TMP_ZERO))); return push_inst(compiler, (SUB ^ inv_bits) | RD(SLJIT_R1) | RN(TMP_REG1) | RM(SLJIT_R1)); + case SLJIT_UDIVI: + case SLJIT_SDIVI: + return push_inst(compiler, ((op == SLJIT_UDIVI ? UDIV : SDIV) ^ inv_bits) | RD(SLJIT_R0) | RN(SLJIT_R0) | RM(SLJIT_R1)); } return SLJIT_SUCCESS; diff --git a/ext/pcre/pcrelib/sljit/sljitNativeARM_T2_32.c b/ext/pcre/pcrelib/sljit/sljitNativeARM_T2_32.c index 6e38cec..f9803f5 100644 --- a/ext/pcre/pcrelib/sljit/sljitNativeARM_T2_32.c +++ b/ext/pcre/pcrelib/sljit/sljitNativeARM_T2_32.c @@ -1239,6 +1239,9 @@ extern int __aeabi_idivmod(int numerator, int denominator); SLJIT_API_FUNC_ATTRIBUTE sljit_si sljit_emit_op0(struct sljit_compiler *compiler, sljit_si op) { + sljit_sw saved_reg_list[3]; + sljit_sw saved_reg_count; + CHECK_ERROR(); CHECK(check_sljit_emit_op0(compiler, op)); @@ -1255,24 +1258,53 @@ SLJIT_API_FUNC_ATTRIBUTE sljit_si sljit_emit_op0(struct sljit_compiler *compiler | (reg_map[SLJIT_R0] << 12) | (reg_map[SLJIT_R0] << 16) | reg_map[SLJIT_R1]); - case SLJIT_LUDIV: - case SLJIT_LSDIV: - if (compiler->scratches >= 4) { - FAIL_IF(push_inst32(compiler, 0xf84d2d04 /* str r2, [sp, #-4]! */)); - FAIL_IF(push_inst32(compiler, 0xf84dcd04 /* str ip, [sp, #-4]! */)); - } else if (compiler->scratches >= 3) - FAIL_IF(push_inst32(compiler, 0xf84d2d08 /* str r2, [sp, #-8]! */)); + case SLJIT_UDIVMOD: + case SLJIT_SDIVMOD: + case SLJIT_UDIVI: + case SLJIT_SDIVI: + SLJIT_COMPILE_ASSERT((SLJIT_UDIVMOD & 0x2) == 0 && SLJIT_UDIVI - 0x2 == SLJIT_UDIVMOD, bad_div_opcode_assignments); + SLJIT_COMPILE_ASSERT(reg_map[2] == 1 && reg_map[3] == 2 && reg_map[4] == 12, bad_register_mapping); + + saved_reg_count = 0; + if (compiler->scratches >= 4) + saved_reg_list[saved_reg_count++] = 12; + if (compiler->scratches >= 3) + saved_reg_list[saved_reg_count++] = 2; + if (op >= SLJIT_UDIVI) + saved_reg_list[saved_reg_count++] = 1; + + if (saved_reg_count > 0) { + FAIL_IF(push_inst32(compiler, 0xf84d0d00 | (saved_reg_count >= 3 ? 16 : 8) + | (saved_reg_list[0] << 12) /* str rX, [sp, #-8/-16]! */)); + if (saved_reg_count >= 2) { + SLJIT_ASSERT(saved_reg_list[1] < 8); + FAIL_IF(push_inst16(compiler, 0x9001 | (saved_reg_list[1] << 8) /* str rX, [sp, #4] */)); + } + if (saved_reg_count >= 3) { + SLJIT_ASSERT(saved_reg_list[2] < 8); + FAIL_IF(push_inst16(compiler, 0x9002 | (saved_reg_list[2] << 8) /* str rX, [sp, #8] */)); + } + } + #if defined(__GNUC__) FAIL_IF(sljit_emit_ijump(compiler, SLJIT_FAST_CALL, SLJIT_IMM, - (op == SLJIT_LUDIV ? SLJIT_FUNC_OFFSET(__aeabi_uidivmod) : SLJIT_FUNC_OFFSET(__aeabi_idivmod)))); + ((op | 0x2) == SLJIT_UDIVI ? SLJIT_FUNC_OFFSET(__aeabi_uidivmod) : SLJIT_FUNC_OFFSET(__aeabi_idivmod)))); #else #error "Software divmod functions are needed" #endif - if (compiler->scratches >= 4) { - FAIL_IF(push_inst32(compiler, 0xf85dcb04 /* ldr ip, [sp], #4 */)); - return push_inst32(compiler, 0xf85d2b04 /* ldr r2, [sp], #4 */); - } else if (compiler->scratches >= 3) - return push_inst32(compiler, 0xf85d2b08 /* ldr r2, [sp], #8 */); + + if (saved_reg_count > 0) { + if (saved_reg_count >= 3) { + SLJIT_ASSERT(saved_reg_list[2] < 8); + FAIL_IF(push_inst16(compiler, 0x9802 | (saved_reg_list[2] << 8) /* ldr rX, [sp, #8] */)); + } + if (saved_reg_count >= 2) { + SLJIT_ASSERT(saved_reg_list[1] < 8); + FAIL_IF(push_inst16(compiler, 0x9801 | (saved_reg_list[1] << 8) /* ldr rX, [sp, #4] */)); + } + return push_inst32(compiler, 0xf85d0b00 | (saved_reg_count >= 3 ? 16 : 8) + | (saved_reg_list[0] << 12) /* ldr rX, [sp], #8/16 */); + } return SLJIT_SUCCESS; } diff --git a/ext/pcre/pcrelib/sljit/sljitNativeMIPS_common.c b/ext/pcre/pcrelib/sljit/sljitNativeMIPS_common.c index 3e2c9f0..cf3535f 100644 --- a/ext/pcre/pcrelib/sljit/sljitNativeMIPS_common.c +++ b/ext/pcre/pcrelib/sljit/sljitNativeMIPS_common.c @@ -1053,8 +1053,11 @@ SLJIT_API_FUNC_ATTRIBUTE sljit_si sljit_emit_op0(struct sljit_compiler *compiler #endif FAIL_IF(push_inst(compiler, MFLO | D(SLJIT_R0), DR(SLJIT_R0))); return push_inst(compiler, MFHI | D(SLJIT_R1), DR(SLJIT_R1)); - case SLJIT_LUDIV: - case SLJIT_LSDIV: + case SLJIT_UDIVMOD: + case SLJIT_SDIVMOD: + case SLJIT_UDIVI: + case SLJIT_SDIVI: + SLJIT_COMPILE_ASSERT((SLJIT_UDIVMOD & 0x2) == 0 && SLJIT_UDIVI - 0x2 == SLJIT_UDIVMOD, bad_div_opcode_assignments); #if !(defined SLJIT_MIPS_R1 && SLJIT_MIPS_R1) FAIL_IF(push_inst(compiler, NOP, UNMOVABLE_INS)); FAIL_IF(push_inst(compiler, NOP, UNMOVABLE_INS)); @@ -1062,15 +1065,15 @@ SLJIT_API_FUNC_ATTRIBUTE sljit_si sljit_emit_op0(struct sljit_compiler *compiler #if (defined SLJIT_CONFIG_MIPS_64 && SLJIT_CONFIG_MIPS_64) if (int_op) - FAIL_IF(push_inst(compiler, (op == SLJIT_LUDIV ? DIVU : DIV) | S(SLJIT_R0) | T(SLJIT_R1), MOVABLE_INS)); + FAIL_IF(push_inst(compiler, ((op | 0x2) == SLJIT_UDIVI ? DIVU : DIV) | S(SLJIT_R0) | T(SLJIT_R1), MOVABLE_INS)); else - FAIL_IF(push_inst(compiler, (op == SLJIT_LUDIV ? DDIVU : DDIV) | S(SLJIT_R0) | T(SLJIT_R1), MOVABLE_INS)); + FAIL_IF(push_inst(compiler, ((op | 0x2) == SLJIT_UDIVI ? DDIVU : DDIV) | S(SLJIT_R0) | T(SLJIT_R1), MOVABLE_INS)); #else - FAIL_IF(push_inst(compiler, (op == SLJIT_LUDIV ? DIVU : DIV) | S(SLJIT_R0) | T(SLJIT_R1), MOVABLE_INS)); + FAIL_IF(push_inst(compiler, ((op | 0x2) == SLJIT_UDIVI ? DIVU : DIV) | S(SLJIT_R0) | T(SLJIT_R1), MOVABLE_INS)); #endif FAIL_IF(push_inst(compiler, MFLO | D(SLJIT_R0), DR(SLJIT_R0))); - return push_inst(compiler, MFHI | D(SLJIT_R1), DR(SLJIT_R1)); + return (op >= SLJIT_UDIVI) ? SLJIT_SUCCESS : push_inst(compiler, MFHI | D(SLJIT_R1), DR(SLJIT_R1)); } return SLJIT_SUCCESS; diff --git a/ext/pcre/pcrelib/sljit/sljitNativePPC_common.c b/ext/pcre/pcrelib/sljit/sljitNativePPC_common.c index 08d5356..b6a043f 100644 --- a/ext/pcre/pcrelib/sljit/sljitNativePPC_common.c +++ b/ext/pcre/pcrelib/sljit/sljitNativePPC_common.c @@ -1267,22 +1267,23 @@ SLJIT_API_FUNC_ATTRIBUTE sljit_si sljit_emit_op0(struct sljit_compiler *compiler FAIL_IF(push_inst(compiler, MULLW | D(SLJIT_R0) | A(TMP_REG1) | B(SLJIT_R1))); return push_inst(compiler, (op == SLJIT_LUMUL ? MULHWU : MULHW) | D(SLJIT_R1) | A(TMP_REG1) | B(SLJIT_R1)); #endif - case SLJIT_LUDIV: - case SLJIT_LSDIV: + case SLJIT_UDIVMOD: + case SLJIT_SDIVMOD: FAIL_IF(push_inst(compiler, OR | S(SLJIT_R0) | A(TMP_REG1) | B(SLJIT_R0))); #if (defined SLJIT_CONFIG_PPC_64 && SLJIT_CONFIG_PPC_64) - if (int_op) { - FAIL_IF(push_inst(compiler, (op == SLJIT_LUDIV ? DIVWU : DIVW) | D(SLJIT_R0) | A(TMP_REG1) | B(SLJIT_R1))); - FAIL_IF(push_inst(compiler, MULLW | D(SLJIT_R1) | A(SLJIT_R0) | B(SLJIT_R1))); - } else { - FAIL_IF(push_inst(compiler, (op == SLJIT_LUDIV ? DIVDU : DIVD) | D(SLJIT_R0) | A(TMP_REG1) | B(SLJIT_R1))); - FAIL_IF(push_inst(compiler, MULLD | D(SLJIT_R1) | A(SLJIT_R0) | B(SLJIT_R1))); - } - return push_inst(compiler, SUBF | D(SLJIT_R1) | A(SLJIT_R1) | B(TMP_REG1)); + FAIL_IF(push_inst(compiler, (int_op ? (op == SLJIT_UDIVMOD ? DIVWU : DIVW) : (op == SLJIT_UDIVMOD ? DIVDU : DIVD)) | D(SLJIT_R0) | A(SLJIT_R0) | B(SLJIT_R1))); + FAIL_IF(push_inst(compiler, (int_op ? MULLW : MULLD) | D(SLJIT_R1) | A(SLJIT_R0) | B(SLJIT_R1))); #else - FAIL_IF(push_inst(compiler, (op == SLJIT_LUDIV ? DIVWU : DIVW) | D(SLJIT_R0) | A(TMP_REG1) | B(SLJIT_R1))); + FAIL_IF(push_inst(compiler, (op == SLJIT_UDIVMOD ? DIVWU : DIVW) | D(SLJIT_R0) | A(SLJIT_R0) | B(SLJIT_R1))); FAIL_IF(push_inst(compiler, MULLW | D(SLJIT_R1) | A(SLJIT_R0) | B(SLJIT_R1))); +#endif return push_inst(compiler, SUBF | D(SLJIT_R1) | A(SLJIT_R1) | B(TMP_REG1)); + case SLJIT_UDIVI: + case SLJIT_SDIVI: +#if (defined SLJIT_CONFIG_PPC_64 && SLJIT_CONFIG_PPC_64) + return push_inst(compiler, (int_op ? (op == SLJIT_UDIVI ? DIVWU : DIVW) : (op == SLJIT_UDIVI ? DIVDU : DIVD)) | D(SLJIT_R0) | A(SLJIT_R0) | B(SLJIT_R1)); +#else + return push_inst(compiler, (op == SLJIT_UDIVI ? DIVWU : DIVW) | D(SLJIT_R0) | A(SLJIT_R0) | B(SLJIT_R1)); #endif } diff --git a/ext/pcre/pcrelib/sljit/sljitNativeSPARC_common.c b/ext/pcre/pcrelib/sljit/sljitNativeSPARC_common.c index 0b1927a..327c426 100644 --- a/ext/pcre/pcrelib/sljit/sljitNativeSPARC_common.c +++ b/ext/pcre/pcrelib/sljit/sljitNativeSPARC_common.c @@ -777,20 +777,25 @@ SLJIT_API_FUNC_ATTRIBUTE sljit_si sljit_emit_op0(struct sljit_compiler *compiler #else #error "Implementation required" #endif - case SLJIT_LUDIV: - case SLJIT_LSDIV: + case SLJIT_UDIVMOD: + case SLJIT_SDIVMOD: + case SLJIT_UDIVI: + case SLJIT_SDIVI: + SLJIT_COMPILE_ASSERT((SLJIT_UDIVMOD & 0x2) == 0 && SLJIT_UDIVI - 0x2 == SLJIT_UDIVMOD, bad_div_opcode_assignments); #if (defined SLJIT_CONFIG_SPARC_32 && SLJIT_CONFIG_SPARC_32) - if (op == SLJIT_LUDIV) + if ((op | 0x2) == SLJIT_UDIVI) FAIL_IF(push_inst(compiler, WRY | S1(0), MOVABLE_INS)); else { FAIL_IF(push_inst(compiler, SRA | D(TMP_REG1) | S1(SLJIT_R0) | IMM(31), DR(TMP_REG1))); FAIL_IF(push_inst(compiler, WRY | S1(TMP_REG1), MOVABLE_INS)); } - FAIL_IF(push_inst(compiler, OR | D(TMP_REG2) | S1(0) | S2(SLJIT_R0), DR(TMP_REG2))); - FAIL_IF(push_inst(compiler, (op == SLJIT_LUDIV ? UDIV : SDIV) | D(SLJIT_R0) | S1(SLJIT_R0) | S2(SLJIT_R1), DR(SLJIT_R0))); + if (op <= SLJIT_SDIVMOD) + FAIL_IF(push_inst(compiler, OR | D(TMP_REG2) | S1(0) | S2(SLJIT_R0), DR(TMP_REG2))); + FAIL_IF(push_inst(compiler, ((op | 0x2) == SLJIT_UDIVI ? UDIV : SDIV) | D(SLJIT_R0) | S1(SLJIT_R0) | S2(SLJIT_R1), DR(SLJIT_R0))); + if (op >= SLJIT_UDIVI) + return SLJIT_SUCCESS; FAIL_IF(push_inst(compiler, SMUL | D(SLJIT_R1) | S1(SLJIT_R0) | S2(SLJIT_R1), DR(SLJIT_R1))); - FAIL_IF(push_inst(compiler, SUB | D(SLJIT_R1) | S1(TMP_REG2) | S2(SLJIT_R1), DR(SLJIT_R1))); - return SLJIT_SUCCESS; + return push_inst(compiler, SUB | D(SLJIT_R1) | S1(TMP_REG2) | S2(SLJIT_R1), DR(SLJIT_R1)); #else #error "Implementation required" #endif diff --git a/ext/pcre/pcrelib/sljit/sljitNativeTILEGX_64.c b/ext/pcre/pcrelib/sljit/sljitNativeTILEGX_64.c index 1d6aa5a..4d40392f 100644 --- a/ext/pcre/pcrelib/sljit/sljitNativeTILEGX_64.c +++ b/ext/pcre/pcrelib/sljit/sljitNativeTILEGX_64.c @@ -35,21 +35,21 @@ #define SIMM_16BIT_MIN (-0x8000) #define SIMM_17BIT_MAX (0xffff) #define SIMM_17BIT_MIN (-0x10000) -#define SIMM_32BIT_MIN (-0x80000000) #define SIMM_32BIT_MAX (0x7fffffff) -#define SIMM_48BIT_MIN (0x800000000000L) +#define SIMM_32BIT_MIN (-0x7fffffff - 1) #define SIMM_48BIT_MAX (0x7fffffff0000L) +#define SIMM_48BIT_MIN (-0x800000000000L) #define IMM16(imm) ((imm) & 0xffff) #define UIMM_16BIT_MAX (0xffff) -#define TMP_REG1 (SLJIT_NO_REGISTERS + 1) -#define TMP_REG2 (SLJIT_NO_REGISTERS + 2) -#define TMP_REG3 (SLJIT_NO_REGISTERS + 3) -#define ADDR_TMP (SLJIT_NO_REGISTERS + 4) +#define TMP_REG1 (SLJIT_NUMBER_OF_REGISTERS + 2) +#define TMP_REG2 (SLJIT_NUMBER_OF_REGISTERS + 3) +#define TMP_REG3 (SLJIT_NUMBER_OF_REGISTERS + 4) +#define ADDR_TMP (SLJIT_NUMBER_OF_REGISTERS + 5) #define PIC_ADDR_REG TMP_REG2 -static SLJIT_CONST sljit_ub reg_map[SLJIT_NO_REGISTERS + 5] = { +static SLJIT_CONST sljit_ub reg_map[SLJIT_NUMBER_OF_REGISTERS + 6] = { 63, 0, 1, 2, 3, 4, 30, 31, 32, 33, 34, 54, 5, 16, 6, 7 }; @@ -58,11 +58,6 @@ static SLJIT_CONST sljit_ub reg_map[SLJIT_NO_REGISTERS + 5] = { #define TMP_REG2_mapped 16 #define TMP_REG3_mapped 6 #define ADDR_TMP_mapped 7 -#define SLJIT_SAVED_REG1_mapped 30 -#define SLJIT_SAVED_REG2_mapped 31 -#define SLJIT_SAVED_REG3_mapped 32 -#define SLJIT_SAVED_EREG1_mapped 33 -#define SLJIT_SAVED_EREG2_mapped 34 /* Flags are keept in volatile registers. */ #define EQUAL_FLAG 8 @@ -399,6 +394,9 @@ static sljit_si push_inst(struct sljit_compiler *compiler, sljit_ins ins) #define SUB(dst, srca, srcb) \ push_3_buffer(compiler, TILEGX_OPC_SUB, dst, srca, srcb, __LINE__) +#define MUL(dst, srca, srcb) \ + push_3_buffer(compiler, TILEGX_OPC_MULX, dst, srca, srcb, __LINE__) + #define NOR(dst, srca, srcb) \ push_3_buffer(compiler, TILEGX_OPC_NOR, dst, srca, srcb, __LINE__) @@ -547,8 +545,8 @@ const struct Format* compute_format() const struct Format* match = NULL; const struct Format *b = NULL; - unsigned int i = 0; - for (i; i < sizeof formats / sizeof formats[0]; i++) { + unsigned int i; + for (i = 0; i < sizeof formats / sizeof formats[0]; i++) { b = &formats[i]; if ((b->pipe_mask & compatible_pipes) == b->pipe_mask) { match = b; @@ -625,7 +623,6 @@ tilegx_bundle_bits get_bundle_bit(struct jit_instr *inst) static sljit_si update_buffer(struct sljit_compiler *compiler) { - int count; int i; int orig_index = inst_buf_index; struct jit_instr inst0 = inst_buf[0]; @@ -738,8 +735,10 @@ static sljit_si update_buffer(struct sljit_compiler *compiler) static sljit_si flush_buffer(struct sljit_compiler *compiler) { - while (inst_buf_index != 0) - update_buffer(compiler); + while (inst_buf_index != 0) { + FAIL_IF(update_buffer(compiler)); + } + return SLJIT_SUCCESS; } static sljit_si push_4_buffer(struct sljit_compiler *compiler, tilegx_mnemonic opc, int op0, int op1, int op2, int op3, int line) @@ -787,6 +786,7 @@ static sljit_si push_3_buffer(struct sljit_compiler *compiler, tilegx_mnemonic o case TILEGX_OPC_ADD: case TILEGX_OPC_AND: case TILEGX_OPC_SUB: + case TILEGX_OPC_MULX: case TILEGX_OPC_OR: case TILEGX_OPC_XOR: case TILEGX_OPC_NOR: @@ -905,7 +905,6 @@ static SLJIT_INLINE sljit_ins * detect_jump_type(struct sljit_jump *jump, sljit_ sljit_sw diff; sljit_uw target_addr; sljit_ins *inst; - sljit_ins saved_inst; if (jump->flags & SLJIT_REWRITABLE_JUMP) return code_ptr; @@ -1009,7 +1008,7 @@ SLJIT_API_FUNC_ATTRIBUTE void * sljit_generate_code(struct sljit_compiler *compi struct sljit_const *const_; CHECK_ERROR_PTR(); - check_sljit_generate_code(compiler); + CHECK_PTR(check_sljit_generate_code(compiler)); reverse_buf(compiler); code = (sljit_ins *)SLJIT_MALLOC_EXEC(compiler->size * sizeof(sljit_ins)); @@ -1178,13 +1177,13 @@ SLJIT_API_FUNC_ATTRIBUTE sljit_si sljit_emit_enter(struct sljit_compiler *compil sljit_si fscratches, sljit_si fsaveds, sljit_si local_size) { sljit_ins base; - sljit_ins bundle = 0; - + sljit_si i, tmp; + CHECK_ERROR(); - check_sljit_emit_enter(compiler, options, args, scratches, saveds, fscratches, fsaveds, local_size); + CHECK(check_sljit_emit_enter(compiler, options, args, scratches, saveds, fscratches, fsaveds, local_size)); set_emit_enter(compiler, options, args, scratches, saveds, fscratches, fsaveds, local_size); - local_size += (saveds + 1) * sizeof(sljit_sw); + local_size += GET_SAVED_REGISTERS_SIZE(scratches, saveds, 1); local_size = (local_size + 7) & ~7; compiler->local_size = local_size; @@ -1200,56 +1199,52 @@ SLJIT_API_FUNC_ATTRIBUTE sljit_si sljit_emit_enter(struct sljit_compiler *compil local_size = 0; } + /* Save the return address. */ FAIL_IF(ADDLI(ADDR_TMP_mapped, base, local_size - 8)); FAIL_IF(ST_ADD(ADDR_TMP_mapped, RA, -8)); - if (saveds >= 1) - FAIL_IF(ST_ADD(ADDR_TMP_mapped, SLJIT_SAVED_REG1_mapped, -8)); - - if (saveds >= 2) - FAIL_IF(ST_ADD(ADDR_TMP_mapped, SLJIT_SAVED_REG2_mapped, -8)); - - if (saveds >= 3) - FAIL_IF(ST_ADD(ADDR_TMP_mapped, SLJIT_SAVED_REG3_mapped, -8)); - - if (saveds >= 4) - FAIL_IF(ST_ADD(ADDR_TMP_mapped, SLJIT_SAVED_EREG1_mapped, -8)); - - if (saveds >= 5) - FAIL_IF(ST_ADD(ADDR_TMP_mapped, SLJIT_SAVED_EREG2_mapped, -8)); - - if (args >= 1) - FAIL_IF(ADD(SLJIT_SAVED_REG1_mapped, 0, ZERO)); + /* Save the S registers. */ + tmp = saveds < SLJIT_NUMBER_OF_SAVED_REGISTERS ? (SLJIT_S0 + 1 - saveds) : SLJIT_FIRST_SAVED_REG; + for (i = SLJIT_S0; i >= tmp; i--) { + FAIL_IF(ST_ADD(ADDR_TMP_mapped, reg_map[i], -8)); + } - if (args >= 2) - FAIL_IF(ADD(SLJIT_SAVED_REG2_mapped, 1, ZERO)); + /* Save the R registers that need to be reserved. */ + for (i = scratches; i >= SLJIT_FIRST_SAVED_REG; i--) { + FAIL_IF(ST_ADD(ADDR_TMP_mapped, reg_map[i], -8)); + } - if (args >= 3) - FAIL_IF(ADD(SLJIT_SAVED_REG3_mapped, 2, ZERO)); + /* Move the arguments to S registers. */ + for (i = 0; i < args; i++) { + FAIL_IF(ADD(reg_map[SLJIT_S0 - i], i, ZERO)); + } return SLJIT_SUCCESS; } -SLJIT_API_FUNC_ATTRIBUTE void sljit_set_context(struct sljit_compiler *compiler, +SLJIT_API_FUNC_ATTRIBUTE sljit_si sljit_set_context(struct sljit_compiler *compiler, sljit_si options, sljit_si args, sljit_si scratches, sljit_si saveds, sljit_si fscratches, sljit_si fsaveds, sljit_si local_size) { - CHECK_ERROR_VOID(); - check_sljit_set_context(compiler, options, args, scratches, saveds, fscratches, fsaveds, local_size); + CHECK_ERROR(); + CHECK(check_sljit_set_context(compiler, options, args, scratches, saveds, fscratches, fsaveds, local_size)); set_set_context(compiler, options, args, scratches, saveds, fscratches, fsaveds, local_size); - local_size += (saveds + 1) * sizeof(sljit_sw); + local_size += GET_SAVED_REGISTERS_SIZE(scratches, saveds, 1); compiler->local_size = (local_size + 7) & ~7; + + return SLJIT_SUCCESS; } SLJIT_API_FUNC_ATTRIBUTE sljit_si sljit_emit_return(struct sljit_compiler *compiler, sljit_si op, sljit_si src, sljit_sw srcw) { sljit_si local_size; sljit_ins base; - int addr_initialized = 0; + sljit_si i, tmp; + sljit_si saveds; CHECK_ERROR(); - check_sljit_emit_return(compiler, op, src, srcw); + CHECK(check_sljit_emit_return(compiler, op, src, srcw)); FAIL_IF(emit_mov_before_return(compiler, op, src, srcw)); @@ -1263,50 +1258,20 @@ SLJIT_API_FUNC_ATTRIBUTE sljit_si sljit_emit_return(struct sljit_compiler *compi local_size = 0; } + /* Restore the return address. */ FAIL_IF(ADDLI(ADDR_TMP_mapped, base, local_size - 8)); - FAIL_IF(LD(RA, ADDR_TMP_mapped)); - - if (compiler->saveds >= 5) { - FAIL_IF(ADDLI(ADDR_TMP_mapped, base, local_size - 48)); - addr_initialized = 1; + FAIL_IF(LD_ADD(RA, ADDR_TMP_mapped, -8)); - FAIL_IF(LD_ADD(SLJIT_SAVED_EREG2_mapped, ADDR_TMP_mapped, 8)); + /* Restore the S registers. */ + saveds = compiler->saveds; + tmp = saveds < SLJIT_NUMBER_OF_SAVED_REGISTERS ? (SLJIT_S0 + 1 - saveds) : SLJIT_FIRST_SAVED_REG; + for (i = SLJIT_S0; i >= tmp; i--) { + FAIL_IF(LD_ADD(reg_map[i], ADDR_TMP_mapped, -8)); } - if (compiler->saveds >= 4) { - if (addr_initialized == 0) { - FAIL_IF(ADDLI(ADDR_TMP_mapped, base, local_size - 40)); - addr_initialized = 1; - } - - FAIL_IF(LD_ADD(SLJIT_SAVED_EREG1_mapped, ADDR_TMP_mapped, 8)); - } - - if (compiler->saveds >= 3) { - if (addr_initialized == 0) { - FAIL_IF(ADDLI(ADDR_TMP_mapped, base, local_size - 32)); - addr_initialized = 1; - } - - FAIL_IF(LD_ADD(SLJIT_SAVED_REG3_mapped, ADDR_TMP_mapped, 8)); - } - - if (compiler->saveds >= 2) { - if (addr_initialized == 0) { - FAIL_IF(ADDLI(ADDR_TMP_mapped, base, local_size - 24)); - addr_initialized = 1; - } - - FAIL_IF(LD_ADD(SLJIT_SAVED_REG2_mapped, ADDR_TMP_mapped, 8)); - } - - if (compiler->saveds >= 1) { - if (addr_initialized == 0) { - FAIL_IF(ADDLI(ADDR_TMP_mapped, base, local_size - 16)); - /* addr_initialized = 1; no need to initialize as it's the last one. */ - } - - FAIL_IF(LD_ADD(SLJIT_SAVED_REG1_mapped, ADDR_TMP_mapped, 8)); + /* Restore the R registers that need to be reserved. */ + for (i = compiler->scratches; i >= SLJIT_FIRST_SAVED_REG; i--) { + FAIL_IF(LD_ADD(reg_map[i], ADDR_TMP_mapped, -8)); } if (compiler->local_size <= SIMM_16BIT_MAX) @@ -1585,7 +1550,7 @@ static SLJIT_INLINE sljit_si emit_op_mem2(struct sljit_compiler *compiler, sljit SLJIT_API_FUNC_ATTRIBUTE sljit_si sljit_emit_fast_enter(struct sljit_compiler *compiler, sljit_si dst, sljit_sw dstw) { CHECK_ERROR(); - check_sljit_emit_fast_enter(compiler, dst, dstw); + CHECK(check_sljit_emit_fast_enter(compiler, dst, dstw)); ADJUST_LOCAL_OFFSET(dst, dstw); /* For UNUSED dst. Uncommon, but possible. */ @@ -1602,7 +1567,7 @@ SLJIT_API_FUNC_ATTRIBUTE sljit_si sljit_emit_fast_enter(struct sljit_compiler *c SLJIT_API_FUNC_ATTRIBUTE sljit_si sljit_emit_fast_return(struct sljit_compiler *compiler, sljit_si src, sljit_sw srcw) { CHECK_ERROR(); - check_sljit_emit_fast_return(compiler, src, srcw); + CHECK(check_sljit_emit_fast_return(compiler, src, srcw)); ADJUST_LOCAL_OFFSET(src, srcw); if (FAST_IS_REG(src)) @@ -1636,9 +1601,11 @@ static SLJIT_INLINE sljit_si emit_single_op(struct sljit_compiler *compiler, slj if (op == SLJIT_MOV_SI) return BFEXTS(reg_map[dst], reg_map[src2], 0, 31); - return BFEXTU(reg_map[dst], reg_map[src2], 0, 31); - } else if (dst != src2) - SLJIT_ASSERT_STOP(); + return BFEXTU(reg_map[dst], reg_map[src2], 0, 31); + } else if (dst != src2) { + SLJIT_ASSERT(src2 == 0); + return ADD(reg_map[dst], reg_map[src2], ZERO); + } return SLJIT_SUCCESS; @@ -1650,8 +1617,10 @@ static SLJIT_INLINE sljit_si emit_single_op(struct sljit_compiler *compiler, slj return BFEXTS(reg_map[dst], reg_map[src2], 0, 7); return BFEXTU(reg_map[dst], reg_map[src2], 0, 7); - } else if (dst != src2) - SLJIT_ASSERT_STOP(); + } else if (dst != src2) { + SLJIT_ASSERT(src2 == 0); + return ADD(reg_map[dst], reg_map[src2], ZERO); + } return SLJIT_SUCCESS; @@ -1663,8 +1632,10 @@ static SLJIT_INLINE sljit_si emit_single_op(struct sljit_compiler *compiler, slj return BFEXTS(reg_map[dst], reg_map[src2], 0, 15); return BFEXTU(reg_map[dst], reg_map[src2], 0, 15); - } else if (dst != src2) - SLJIT_ASSERT_STOP(); + } else if (dst != src2) { + SLJIT_ASSERT(src2 == 0); + return ADD(reg_map[dst], reg_map[src2], ZERO); + } return SLJIT_SUCCESS; @@ -1811,7 +1782,6 @@ static SLJIT_INLINE sljit_si emit_single_op(struct sljit_compiler *compiler, slj else { /* Rare ocasion. */ FAIL_IF(ADD(TMP_EREG2, reg_map[src1], ZERO)); - overflow_ra = TMP_EREG2; } } @@ -1903,6 +1873,17 @@ static SLJIT_INLINE sljit_si emit_single_op(struct sljit_compiler *compiler, slj return SLJIT_SUCCESS; + case SLJIT_MUL: + if (flags & SRC2_IMM) { + FAIL_IF(load_immediate(compiler, TMP_REG2_mapped, src2)); + src2 = TMP_REG2; + flags &= ~SRC2_IMM; + } + + FAIL_IF(MUL(reg_map[dst], reg_map[src1], reg_map[src2])); + + return SLJIT_SUCCESS; + #define EMIT_LOGICAL(op_imm, op_norm) \ if (flags & SRC2_IMM) { \ FAIL_IF(load_immediate(compiler, ADDR_TMP_mapped, src2)); \ @@ -1950,8 +1931,8 @@ static SLJIT_INLINE sljit_si emit_single_op(struct sljit_compiler *compiler, slj } else { \ if (op & SLJIT_SET_E) \ FAIL_IF(push_3_buffer( \ - compiler, op_imm, reg_map[dst], reg_map[src1], \ - src2 & 0x3F, __LINE__)); \ + compiler, op_norm, EQUAL_FLAG, reg_map[src1], \ + reg_map[src2], __LINE__)); \ if (CHECK_FLAGS(SLJIT_SET_E)) \ FAIL_IF(push_3_buffer( \ compiler, op_norm, reg_map[dst], reg_map[src1], \ @@ -2105,66 +2086,61 @@ SLJIT_API_FUNC_ATTRIBUTE sljit_si sljit_emit_op_flags(struct sljit_compiler *com { sljit_si sugg_dst_ar, dst_ar; sljit_si flags = GET_ALL_FLAGS(op); + sljit_si mem_type = (op & SLJIT_INT_OP) ? (INT_DATA | SIGNED_DATA) : WORD_DATA; CHECK_ERROR(); - check_sljit_emit_op_flags(compiler, op, dst, dstw, src, srcw, type); + CHECK(check_sljit_emit_op_flags(compiler, op, dst, dstw, src, srcw, type)); ADJUST_LOCAL_OFFSET(dst, dstw); if (dst == SLJIT_UNUSED) return SLJIT_SUCCESS; op = GET_OPCODE(op); + if (op == SLJIT_MOV_SI || op == SLJIT_MOV_UI) + mem_type = INT_DATA | SIGNED_DATA; sugg_dst_ar = reg_map[(op < SLJIT_ADD && FAST_IS_REG(dst)) ? dst : TMP_REG2]; compiler->cache_arg = 0; compiler->cache_argw = 0; if (op >= SLJIT_ADD && (src & SLJIT_MEM)) { ADJUST_LOCAL_OFFSET(src, srcw); - FAIL_IF(emit_op_mem2(compiler, WORD_DATA | LOAD_DATA, TMP_REG1_mapped, src, srcw, dst, dstw)); + FAIL_IF(emit_op_mem2(compiler, mem_type | LOAD_DATA, TMP_REG1_mapped, src, srcw, dst, dstw)); src = TMP_REG1; srcw = 0; } - switch (type) { - case SLJIT_C_EQUAL: - case SLJIT_C_NOT_EQUAL: + switch (type & 0xff) { + case SLJIT_EQUAL: + case SLJIT_NOT_EQUAL: FAIL_IF(CMPLTUI(sugg_dst_ar, EQUAL_FLAG, 1)); dst_ar = sugg_dst_ar; break; - case SLJIT_C_LESS: - case SLJIT_C_GREATER_EQUAL: - case SLJIT_C_FLOAT_LESS: - case SLJIT_C_FLOAT_GREATER_EQUAL: + case SLJIT_LESS: + case SLJIT_GREATER_EQUAL: dst_ar = ULESS_FLAG; break; - case SLJIT_C_GREATER: - case SLJIT_C_LESS_EQUAL: - case SLJIT_C_FLOAT_GREATER: - case SLJIT_C_FLOAT_LESS_EQUAL: + case SLJIT_GREATER: + case SLJIT_LESS_EQUAL: dst_ar = UGREATER_FLAG; break; - case SLJIT_C_SIG_LESS: - case SLJIT_C_SIG_GREATER_EQUAL: + case SLJIT_SIG_LESS: + case SLJIT_SIG_GREATER_EQUAL: dst_ar = LESS_FLAG; break; - case SLJIT_C_SIG_GREATER: - case SLJIT_C_SIG_LESS_EQUAL: + case SLJIT_SIG_GREATER: + case SLJIT_SIG_LESS_EQUAL: dst_ar = GREATER_FLAG; break; - case SLJIT_C_OVERFLOW: - case SLJIT_C_NOT_OVERFLOW: + case SLJIT_OVERFLOW: + case SLJIT_NOT_OVERFLOW: dst_ar = OVERFLOW_FLAG; break; - case SLJIT_C_MUL_OVERFLOW: - case SLJIT_C_MUL_NOT_OVERFLOW: + case SLJIT_MUL_OVERFLOW: + case SLJIT_MUL_NOT_OVERFLOW: FAIL_IF(CMPLTUI(sugg_dst_ar, OVERFLOW_FLAG, 1)); dst_ar = sugg_dst_ar; type ^= 0x1; /* Flip type bit for the XORI below. */ break; - case SLJIT_C_FLOAT_EQUAL: - case SLJIT_C_FLOAT_NOT_EQUAL: - dst_ar = EQUAL_FLAG; - break; default: SLJIT_ASSERT_STOP(); @@ -2180,11 +2156,11 @@ SLJIT_API_FUNC_ATTRIBUTE sljit_si sljit_emit_op_flags(struct sljit_compiler *com if (op >= SLJIT_ADD) { if (TMP_REG2_mapped != dst_ar) FAIL_IF(ADD(TMP_REG2_mapped, dst_ar, ZERO)); - return emit_op(compiler, op | flags, CUMULATIVE_OP | LOGICAL_OP | IMM_OP | ALT_KEEP_CACHE, dst, dstw, src, srcw, TMP_REG2, 0); + return emit_op(compiler, op | flags, mem_type | CUMULATIVE_OP | LOGICAL_OP | IMM_OP | ALT_KEEP_CACHE, dst, dstw, src, srcw, TMP_REG2, 0); } if (dst & SLJIT_MEM) - return emit_op_mem(compiler, WORD_DATA, dst_ar, dst, dstw); + return emit_op_mem(compiler, mem_type, dst_ar, dst, dstw); if (sugg_dst_ar != dst_ar) return ADD(sugg_dst_ar, dst_ar, ZERO); @@ -2194,7 +2170,7 @@ SLJIT_API_FUNC_ATTRIBUTE sljit_si sljit_emit_op_flags(struct sljit_compiler *com SLJIT_API_FUNC_ATTRIBUTE sljit_si sljit_emit_op0(struct sljit_compiler *compiler, sljit_si op) { CHECK_ERROR(); - check_sljit_emit_op0(compiler, op); + CHECK(check_sljit_emit_op0(compiler, op)); op = GET_OPCODE(op); switch (op) { @@ -2204,10 +2180,10 @@ SLJIT_API_FUNC_ATTRIBUTE sljit_si sljit_emit_op0(struct sljit_compiler *compiler case SLJIT_BREAKPOINT: return PI(BPT); - case SLJIT_UMUL: - case SLJIT_SMUL: - case SLJIT_UDIV: - case SLJIT_SDIV: + case SLJIT_LUMUL: + case SLJIT_LSMUL: + case SLJIT_UDIVI: + case SLJIT_SDIVI: SLJIT_ASSERT_STOP(); } @@ -2217,7 +2193,7 @@ SLJIT_API_FUNC_ATTRIBUTE sljit_si sljit_emit_op0(struct sljit_compiler *compiler SLJIT_API_FUNC_ATTRIBUTE sljit_si sljit_emit_op1(struct sljit_compiler *compiler, sljit_si op, sljit_si dst, sljit_sw dstw, sljit_si src, sljit_sw srcw) { CHECK_ERROR(); - check_sljit_emit_op1(compiler, op, dst, dstw, src, srcw); + CHECK(check_sljit_emit_op1(compiler, op, dst, dstw, src, srcw)); ADJUST_LOCAL_OFFSET(dst, dstw); ADJUST_LOCAL_OFFSET(src, srcw); @@ -2273,7 +2249,7 @@ SLJIT_API_FUNC_ATTRIBUTE sljit_si sljit_emit_op1(struct sljit_compiler *compiler return emit_op(compiler, SLJIT_SUB | GET_ALL_FLAGS(op), IMM_OP, dst, dstw, SLJIT_IMM, 0, src, srcw); case SLJIT_CLZ: - return emit_op(compiler, op, 0, dst, dstw, TMP_REG1, 0, src, srcw); + return emit_op(compiler, op, (op & SLJIT_INT_OP) ? INT_DATA : WORD_DATA, dst, dstw, TMP_REG1, 0, src, srcw); } return SLJIT_SUCCESS; @@ -2282,7 +2258,7 @@ SLJIT_API_FUNC_ATTRIBUTE sljit_si sljit_emit_op1(struct sljit_compiler *compiler SLJIT_API_FUNC_ATTRIBUTE sljit_si sljit_emit_op2(struct sljit_compiler *compiler, sljit_si op, sljit_si dst, sljit_sw dstw, sljit_si src1, sljit_sw src1w, sljit_si src2, sljit_sw src2w) { CHECK_ERROR(); - check_sljit_emit_op2(compiler, op, dst, dstw, src1, src1w, src2, src2w); + CHECK(check_sljit_emit_op2(compiler, op, dst, dstw, src1, src1w, src2, src2w)); ADJUST_LOCAL_OFFSET(dst, dstw); ADJUST_LOCAL_OFFSET(src1, src1w); ADJUST_LOCAL_OFFSET(src2, src2w); @@ -2325,7 +2301,7 @@ SLJIT_API_FUNC_ATTRIBUTE struct sljit_label * sljit_emit_label(struct sljit_comp flush_buffer(compiler); CHECK_ERROR_PTR(); - check_sljit_emit_label(compiler); + CHECK_PTR(check_sljit_emit_label(compiler)); if (compiler->last_label && compiler->last_label->size == compiler->size) return compiler->last_label; @@ -2344,7 +2320,7 @@ SLJIT_API_FUNC_ATTRIBUTE sljit_si sljit_emit_ijump(struct sljit_compiler *compil flush_buffer(compiler); CHECK_ERROR(); - check_sljit_emit_ijump(compiler, type, src, srcw); + CHECK(check_sljit_emit_ijump(compiler, type, src, srcw)); ADJUST_LOCAL_OFFSET(src, srcw); if (FAST_IS_REG(src)) { @@ -2404,8 +2380,10 @@ SLJIT_API_FUNC_ATTRIBUTE sljit_si sljit_emit_ijump(struct sljit_compiler *compil return SLJIT_SUCCESS; - } else if (src & SLJIT_MEM) + } else if (src & SLJIT_MEM) { FAIL_IF(emit_op(compiler, SLJIT_MOV, WORD_DATA, TMP_REG2, 0, TMP_REG1, 0, src, srcw)); + flush_buffer(compiler); + } FAIL_IF(JR_SOLO(reg_map[src_r])); @@ -2432,7 +2410,7 @@ SLJIT_API_FUNC_ATTRIBUTE struct sljit_jump * sljit_emit_jump(struct sljit_compil flush_buffer(compiler); CHECK_ERROR_PTR(); - check_sljit_emit_jump(compiler, type); + CHECK_PTR(check_sljit_emit_jump(compiler, type)); jump = (struct sljit_jump *)ensure_abuf(compiler, sizeof(struct sljit_jump)); PTR_FAIL_IF(!jump); @@ -2440,48 +2418,42 @@ SLJIT_API_FUNC_ATTRIBUTE struct sljit_jump * sljit_emit_jump(struct sljit_compil type &= 0xff; switch (type) { - case SLJIT_C_EQUAL: - case SLJIT_C_FLOAT_NOT_EQUAL: + case SLJIT_EQUAL: BR_NZ(EQUAL_FLAG); break; - case SLJIT_C_NOT_EQUAL: - case SLJIT_C_FLOAT_EQUAL: + case SLJIT_NOT_EQUAL: BR_Z(EQUAL_FLAG); break; - case SLJIT_C_LESS: - case SLJIT_C_FLOAT_LESS: + case SLJIT_LESS: BR_Z(ULESS_FLAG); break; - case SLJIT_C_GREATER_EQUAL: - case SLJIT_C_FLOAT_GREATER_EQUAL: + case SLJIT_GREATER_EQUAL: BR_NZ(ULESS_FLAG); break; - case SLJIT_C_GREATER: - case SLJIT_C_FLOAT_GREATER: + case SLJIT_GREATER: BR_Z(UGREATER_FLAG); break; - case SLJIT_C_LESS_EQUAL: - case SLJIT_C_FLOAT_LESS_EQUAL: + case SLJIT_LESS_EQUAL: BR_NZ(UGREATER_FLAG); break; - case SLJIT_C_SIG_LESS: + case SLJIT_SIG_LESS: BR_Z(LESS_FLAG); break; - case SLJIT_C_SIG_GREATER_EQUAL: + case SLJIT_SIG_GREATER_EQUAL: BR_NZ(LESS_FLAG); break; - case SLJIT_C_SIG_GREATER: + case SLJIT_SIG_GREATER: BR_Z(GREATER_FLAG); break; - case SLJIT_C_SIG_LESS_EQUAL: + case SLJIT_SIG_LESS_EQUAL: BR_NZ(GREATER_FLAG); break; - case SLJIT_C_OVERFLOW: - case SLJIT_C_MUL_OVERFLOW: + case SLJIT_OVERFLOW: + case SLJIT_MUL_OVERFLOW: BR_Z(OVERFLOW_FLAG); break; - case SLJIT_C_NOT_OVERFLOW: - case SLJIT_C_MUL_NOT_OVERFLOW: + case SLJIT_NOT_OVERFLOW: + case SLJIT_MUL_NOT_OVERFLOW: BR_NZ(OVERFLOW_FLAG); break; default: @@ -2536,7 +2508,7 @@ SLJIT_API_FUNC_ATTRIBUTE struct sljit_const * sljit_emit_const(struct sljit_comp flush_buffer(compiler); CHECK_ERROR_PTR(); - check_sljit_emit_const(compiler, dst, dstw, init_value); + CHECK_PTR(check_sljit_emit_const(compiler, dst, dstw, init_value)); ADJUST_LOCAL_OFFSET(dst, dstw); const_ = (struct sljit_const *)ensure_abuf(compiler, sizeof(struct sljit_const)); @@ -2572,3 +2544,18 @@ SLJIT_API_FUNC_ATTRIBUTE void sljit_set_const(sljit_uw addr, sljit_sw new_consta inst[3] = (inst[3] & ~(0xFFFFL << 43)) | ((new_constant & 0xFFFFL) << 43); SLJIT_CACHE_FLUSH(inst, inst + 4); } + +SLJIT_API_FUNC_ATTRIBUTE sljit_si sljit_get_register_index(sljit_si reg) +{ + CHECK_REG_INDEX(check_sljit_get_register_index(reg)); + return reg_map[reg]; +} + +SLJIT_API_FUNC_ATTRIBUTE sljit_si sljit_emit_op_custom(struct sljit_compiler *compiler, + void *instruction, sljit_si size) +{ + CHECK_ERROR(); + CHECK(check_sljit_emit_op_custom(compiler, instruction, size)); + return SLJIT_ERR_UNSUPPORTED; +} + diff --git a/ext/pcre/pcrelib/sljit/sljitNativeX86_common.c b/ext/pcre/pcrelib/sljit/sljitNativeX86_common.c index 22a163f..416c15a 100644 --- a/ext/pcre/pcrelib/sljit/sljitNativeX86_common.c +++ b/ext/pcre/pcrelib/sljit/sljitNativeX86_common.c @@ -273,7 +273,9 @@ static sljit_si cpu_has_sse2 = -1; #endif static sljit_si cpu_has_cmov = -1; -#if defined(_MSC_VER) && _MSC_VER >= 1400 +#ifdef _WIN32_WCE +#include +#elif defined(_MSC_VER) && _MSC_VER >= 1400 #include #endif @@ -742,8 +744,10 @@ SLJIT_API_FUNC_ATTRIBUTE sljit_si sljit_emit_op0(struct sljit_compiler *compiler break; case SLJIT_LUMUL: case SLJIT_LSMUL: - case SLJIT_LUDIV: - case SLJIT_LSDIV: + case SLJIT_UDIVMOD: + case SLJIT_SDIVMOD: + case SLJIT_UDIVI: + case SLJIT_SDIVI: compiler->flags_saved = 0; #if (defined SLJIT_CONFIG_X86_64 && SLJIT_CONFIG_X86_64) #ifdef _WIN64 @@ -761,9 +765,10 @@ SLJIT_API_FUNC_ATTRIBUTE sljit_si sljit_emit_op0(struct sljit_compiler *compiler #endif compiler->mode32 = op & SLJIT_INT_OP; #endif + SLJIT_COMPILE_ASSERT((SLJIT_UDIVMOD & 0x2) == 0 && SLJIT_UDIVI - 0x2 == SLJIT_UDIVMOD, bad_div_opcode_assignments); op = GET_OPCODE(op); - if (op == SLJIT_LUDIV) { + if ((op | 0x2) == SLJIT_UDIVI) { #if (defined SLJIT_CONFIG_X86_32 && SLJIT_CONFIG_X86_32) || defined(_WIN64) EMIT_MOV(compiler, TMP_REG1, 0, SLJIT_R1, 0); inst = emit_x86_instruction(compiler, 1, SLJIT_R1, 0, SLJIT_R1, 0); @@ -774,7 +779,7 @@ SLJIT_API_FUNC_ATTRIBUTE sljit_si sljit_emit_op0(struct sljit_compiler *compiler *inst = XOR_r_rm; } - if (op == SLJIT_LSDIV) { + if ((op | 0x2) == SLJIT_SDIVI) { #if (defined SLJIT_CONFIG_X86_32 && SLJIT_CONFIG_X86_32) || defined(_WIN64) EMIT_MOV(compiler, TMP_REG1, 0, SLJIT_R1, 0); #endif @@ -805,10 +810,10 @@ SLJIT_API_FUNC_ATTRIBUTE sljit_si sljit_emit_op0(struct sljit_compiler *compiler FAIL_IF(!inst); INC_SIZE(2); *inst++ = GROUP_F7; - *inst = MOD_REG | ((op >= SLJIT_LUDIV) ? reg_map[TMP_REG1] : reg_map[SLJIT_R1]); + *inst = MOD_REG | ((op >= SLJIT_UDIVMOD) ? reg_map[TMP_REG1] : reg_map[SLJIT_R1]); #else #ifdef _WIN64 - size = (!compiler->mode32 || op >= SLJIT_LUDIV) ? 3 : 2; + size = (!compiler->mode32 || op >= SLJIT_UDIVMOD) ? 3 : 2; #else size = (!compiler->mode32) ? 3 : 2; #endif @@ -817,11 +822,11 @@ SLJIT_API_FUNC_ATTRIBUTE sljit_si sljit_emit_op0(struct sljit_compiler *compiler INC_SIZE(size); #ifdef _WIN64 if (!compiler->mode32) - *inst++ = REX_W | ((op >= SLJIT_LUDIV) ? REX_B : 0); - else if (op >= SLJIT_LUDIV) + *inst++ = REX_W | ((op >= SLJIT_UDIVMOD) ? REX_B : 0); + else if (op >= SLJIT_UDIVMOD) *inst++ = REX_B; *inst++ = GROUP_F7; - *inst = MOD_REG | ((op >= SLJIT_LUDIV) ? reg_lmap[TMP_REG1] : reg_lmap[SLJIT_R1]); + *inst = MOD_REG | ((op >= SLJIT_UDIVMOD) ? reg_lmap[TMP_REG1] : reg_lmap[SLJIT_R1]); #else if (!compiler->mode32) *inst++ = REX_W; @@ -836,15 +841,21 @@ SLJIT_API_FUNC_ATTRIBUTE sljit_si sljit_emit_op0(struct sljit_compiler *compiler case SLJIT_LSMUL: *inst |= IMUL; break; - case SLJIT_LUDIV: + case SLJIT_UDIVMOD: + case SLJIT_UDIVI: *inst |= DIV; break; - case SLJIT_LSDIV: + case SLJIT_SDIVMOD: + case SLJIT_SDIVI: *inst |= IDIV; break; } #if (defined SLJIT_CONFIG_X86_64 && SLJIT_CONFIG_X86_64) && !defined(_WIN64) - EMIT_MOV(compiler, SLJIT_R1, 0, TMP_REG1, 0); + if (op <= SLJIT_SDIVMOD) + EMIT_MOV(compiler, SLJIT_R1, 0, TMP_REG1, 0); +#else + if (op >= SLJIT_UDIVI) + EMIT_MOV(compiler, SLJIT_R1, 0, TMP_REG1, 0); #endif break; } @@ -1905,60 +1916,62 @@ static sljit_si emit_test_binary(struct sljit_compiler *compiler, return SLJIT_SUCCESS; } - if (FAST_IS_REG(src1)) { + if (!(src1 & SLJIT_IMM)) { if (src2 & SLJIT_IMM) { #if (defined SLJIT_CONFIG_X86_64 && SLJIT_CONFIG_X86_64) if (IS_HALFWORD(src2w) || compiler->mode32) { - inst = emit_x86_instruction(compiler, 1, SLJIT_IMM, src2w, src1, 0); + inst = emit_x86_instruction(compiler, 1, SLJIT_IMM, src2w, src1, src1w); FAIL_IF(!inst); *inst = GROUP_F7; } else { FAIL_IF(emit_load_imm64(compiler, TMP_REG2, src2w)); - inst = emit_x86_instruction(compiler, 1, TMP_REG2, 0, src1, 0); + inst = emit_x86_instruction(compiler, 1, TMP_REG2, 0, src1, src1w); FAIL_IF(!inst); *inst = TEST_rm_r; } #else - inst = emit_x86_instruction(compiler, 1, SLJIT_IMM, src2w, src1, 0); + inst = emit_x86_instruction(compiler, 1, SLJIT_IMM, src2w, src1, src1w); FAIL_IF(!inst); *inst = GROUP_F7; #endif + return SLJIT_SUCCESS; } - else { + else if (FAST_IS_REG(src1)) { inst = emit_x86_instruction(compiler, 1, src1, 0, src2, src2w); FAIL_IF(!inst); *inst = TEST_rm_r; + return SLJIT_SUCCESS; } - return SLJIT_SUCCESS; } - if (FAST_IS_REG(src2)) { + if (!(src2 & SLJIT_IMM)) { if (src1 & SLJIT_IMM) { #if (defined SLJIT_CONFIG_X86_64 && SLJIT_CONFIG_X86_64) if (IS_HALFWORD(src1w) || compiler->mode32) { - inst = emit_x86_instruction(compiler, 1, SLJIT_IMM, src1w, src2, 0); + inst = emit_x86_instruction(compiler, 1, SLJIT_IMM, src1w, src2, src2w); FAIL_IF(!inst); *inst = GROUP_F7; } else { FAIL_IF(emit_load_imm64(compiler, TMP_REG2, src1w)); - inst = emit_x86_instruction(compiler, 1, TMP_REG2, 0, src2, 0); + inst = emit_x86_instruction(compiler, 1, TMP_REG2, 0, src2, src2w); FAIL_IF(!inst); *inst = TEST_rm_r; } #else - inst = emit_x86_instruction(compiler, 1, src1, src1w, src2, 0); + inst = emit_x86_instruction(compiler, 1, src1, src1w, src2, src2w); FAIL_IF(!inst); *inst = GROUP_F7; #endif + return SLJIT_SUCCESS; } - else { + else if (FAST_IS_REG(src2)) { inst = emit_x86_instruction(compiler, 1, src2, 0, src1, src1w); FAIL_IF(!inst); *inst = TEST_rm_r; + return SLJIT_SUCCESS; } - return SLJIT_SUCCESS; } EMIT_MOV(compiler, TMP_REG1, 0, src1, src1w); @@ -2923,3 +2936,69 @@ SLJIT_API_FUNC_ATTRIBUTE void sljit_set_const(sljit_uw addr, sljit_sw new_consta { *(sljit_sw*)addr = new_constant; } + +SLJIT_API_FUNC_ATTRIBUTE sljit_si sljit_x86_is_sse2_available(void) +{ +#if (defined SLJIT_DETECT_SSE2 && SLJIT_DETECT_SSE2) + if (cpu_has_sse2 == -1) + get_cpu_features(); + return cpu_has_sse2; +#else + return 1; +#endif +} + +SLJIT_API_FUNC_ATTRIBUTE sljit_si sljit_x86_is_cmov_available(void) +{ + if (cpu_has_cmov == -1) + get_cpu_features(); + return cpu_has_cmov; +} + +SLJIT_API_FUNC_ATTRIBUTE sljit_si sljit_x86_emit_cmov(struct sljit_compiler *compiler, + sljit_si type, + sljit_si dst_reg, + sljit_si src, sljit_sw srcw) +{ + sljit_ub* inst; + + CHECK_ERROR(); +#if (defined SLJIT_ARGUMENT_CHECKS && SLJIT_ARGUMENT_CHECKS) + CHECK_ARGUMENT(sljit_x86_is_cmov_available()); + CHECK_ARGUMENT(!(type & ~(0xff | SLJIT_INT_OP))); + CHECK_ARGUMENT((type & 0xff) >= SLJIT_EQUAL && (type & 0xff) <= SLJIT_D_ORDERED); + CHECK_ARGUMENT(FUNCTION_CHECK_IS_REG(dst_reg & ~SLJIT_INT_OP)); + FUNCTION_CHECK_SRC(src, srcw); +#endif +#if (defined SLJIT_VERBOSE && SLJIT_VERBOSE) + if (SLJIT_UNLIKELY(!!compiler->verbose)) { + fprintf(compiler->verbose, " x86_cmov%s %s%s, ", + !(dst_reg & SLJIT_INT_OP) ? "" : ".i", + JUMP_PREFIX(type), jump_names[type & 0xff]); + sljit_verbose_reg(compiler, dst_reg & ~SLJIT_INT_OP); + fprintf(compiler->verbose, ", "); + sljit_verbose_param(compiler, src, srcw); + fprintf(compiler->verbose, "\n"); + } +#endif + + ADJUST_LOCAL_OFFSET(src, srcw); + CHECK_EXTRA_REGS(src, srcw, (void)0); + +#if (defined SLJIT_CONFIG_X86_64 && SLJIT_CONFIG_X86_64) + compiler->mode32 = dst_reg & SLJIT_INT_OP; +#endif + dst_reg &= ~SLJIT_INT_OP; + + if (SLJIT_UNLIKELY(src & SLJIT_IMM)) { + EMIT_MOV(compiler, TMP_REG1, 0, SLJIT_IMM, srcw); + src = TMP_REG1; + srcw = 0; + } + + inst = emit_x86_instruction(compiler, 2, dst_reg, 0, src, srcw); + FAIL_IF(!inst); + *inst++ = GROUP_0F; + *inst = get_jump_code(type & 0xff) - 0x40; + return SLJIT_SUCCESS; +}