From 64f2600a56e0201f23dd3496a499fff6ef22c0c0 Mon Sep 17 00:00:00 2001 From: Philip Hazel Date: Tue, 26 Jun 2007 11:16:54 +0000 Subject: [PATCH] Installed PCRE 7.2 into Exim. --- doc/doc-txt/ChangeLog | 5 +- doc/doc-txt/pcrepattern.txt | 599 +++++++++++++--------- doc/doc-txt/pcretest.txt | 44 +- src/scripts/MakeLinks | 4 +- src/src/pcre/ChangeLog | 223 +++++++++ src/src/pcre/LICENCE | 6 +- src/src/pcre/Makefile | 49 +- src/src/pcre/config.h | 7 +- src/src/pcre/dftables.c | 49 +- src/src/pcre/pcre.h | 108 ++-- src/src/pcre/pcre_chartables.c | 196 ++++++++ src/src/pcre/pcre_compile.c | 546 ++++++++++++++++---- src/src/pcre/pcre_config.c | 6 +- src/src/pcre/pcre_exec.c | 862 +++++++++++++++++++++++++++----- src/src/pcre/pcre_fullinfo.c | 14 +- src/src/pcre/pcre_get.c | 4 +- src/src/pcre/pcre_globals.c | 37 +- src/src/pcre/pcre_internal.h | 380 ++++++++------ src/src/pcre/pcre_maketables.c | 4 +- src/src/pcre/pcre_newline.c | 43 +- src/src/pcre/pcre_printint.src | 36 +- src/src/pcre/pcre_study.c | 10 +- src/src/pcre/pcre_tables.c | 8 +- src/src/pcre/pcre_try_flipped.c | 4 +- src/src/pcre/pcre_version.c | 6 +- src/src/pcre/pcretest.c | 108 ++-- src/src/pcre/ucp.h | 2 +- 27 files changed, 2527 insertions(+), 833 deletions(-) create mode 100644 src/src/pcre/pcre_chartables.c diff --git a/doc/doc-txt/ChangeLog b/doc/doc-txt/ChangeLog index a4a83e70a..31bd94acc 100644 --- a/doc/doc-txt/ChangeLog +++ b/doc/doc-txt/ChangeLog @@ -1,4 +1,4 @@ -$Cambridge: exim/doc/doc-txt/ChangeLog,v 1.518 2007/06/26 09:23:34 ph10 Exp $ +$Cambridge: exim/doc/doc-txt/ChangeLog,v 1.519 2007/06/26 11:16:54 ph10 Exp $ Change log file for Exim from version 4.21 ------------------------------------------- @@ -71,6 +71,9 @@ PH/11 Added $max_received_linelength. PH/12 Added +ignore_defer and +include_defer to host lists. +PH/13 Installed PCRE version 7.2. This needed some changes because of the new + way in which PCRE > 7.0 is built. + Exim version 4.67 ----------------- diff --git a/doc/doc-txt/pcrepattern.txt b/doc/doc-txt/pcrepattern.txt index f0e98e33c..bfc1cab4c 100644 --- a/doc/doc-txt/pcrepattern.txt +++ b/doc/doc-txt/pcrepattern.txt @@ -1,5 +1,5 @@ This file contains the PCRE man page that describes the regular expressions -supported by PCRE version 7.0. Note that not all of the features are relevant +supported by PCRE version 7.2. Note that not all of the features are relevant in the context of Exim. In particular, the version of PCRE that is compiled with Exim does not include UTF-8 support, there is no mechanism for changing the options with which the PCRE functions are called, and features such as @@ -34,38 +34,39 @@ PCRE REGULAR EXPRESSION DETAILS ported by PCRE when its main matching function, pcre_exec(), is used. From release 6.0, PCRE offers a second matching function, pcre_dfa_exec(), which matches using a different algorithm that is not - Perl-compatible. The advantages and disadvantages of the alternative - function, and how it differs from the normal function, are discussed in - the pcrematching page. + Perl-compatible. Some of the features discussed below are not available + when pcre_dfa_exec() is used. The advantages and disadvantages of the + alternative function, and how it differs from the normal function, are + discussed in the pcrematching page. CHARACTERS AND METACHARACTERS - A regular expression is a pattern that is matched against a subject - string from left to right. Most characters stand for themselves in a - pattern, and match the corresponding characters in the subject. As a + A regular expression is a pattern that is matched against a subject + string from left to right. Most characters stand for themselves in a + pattern, and match the corresponding characters in the subject. As a trivial example, the pattern The quick brown fox matches a portion of a subject string that is identical to itself. When - caseless matching is specified (the PCRE_CASELESS option), letters are - matched independently of case. In UTF-8 mode, PCRE always understands - the concept of case for characters whose values are less than 128, so - caseless matching is always possible. For characters with higher val- - ues, the concept of case is supported if PCRE is compiled with Unicode - property support, but not otherwise. If you want to use caseless - matching for characters 128 and above, you must ensure that PCRE is + caseless matching is specified (the PCRE_CASELESS option), letters are + matched independently of case. In UTF-8 mode, PCRE always understands + the concept of case for characters whose values are less than 128, so + caseless matching is always possible. For characters with higher val- + ues, the concept of case is supported if PCRE is compiled with Unicode + property support, but not otherwise. If you want to use caseless + matching for characters 128 and above, you must ensure that PCRE is compiled with Unicode property support as well as with UTF-8 support. - The power of regular expressions comes from the ability to include - alternatives and repetitions in the pattern. These are encoded in the + The power of regular expressions comes from the ability to include + alternatives and repetitions in the pattern. These are encoded in the pattern by the use of metacharacters, which do not stand for themselves but instead are interpreted in some special way. - There are two different sets of metacharacters: those that are recog- - nized anywhere in the pattern except within square brackets, and those - that are recognized within square brackets. Outside square brackets, + There are two different sets of metacharacters: those that are recog- + nized anywhere in the pattern except within square brackets, and those + that are recognized within square brackets. Outside square brackets, the metacharacters are as follows: \ general escape character with several uses @@ -84,7 +85,7 @@ CHARACTERS AND METACHARACTERS also "possessive quantifier" { start min/max quantifier - Part of a pattern that is in square brackets is called a "character + Part of a pattern that is in square brackets is called a "character class". In a character class the only metacharacters are: \ general escape character @@ -94,33 +95,33 @@ CHARACTERS AND METACHARACTERS syntax) ] terminates the character class - The following sections describe the use of each of the metacharacters. + The following sections describe the use of each of the metacharacters. BACKSLASH The backslash character has several uses. Firstly, if it is followed by - a non-alphanumeric character, it takes away any special meaning that - character may have. This use of backslash as an escape character + a non-alphanumeric character, it takes away any special meaning that + character may have. This use of backslash as an escape character applies both inside and outside character classes. - For example, if you want to match a * character, you write \* in the - pattern. This escaping action applies whether or not the following - character would otherwise be interpreted as a metacharacter, so it is - always safe to precede a non-alphanumeric with backslash to specify - that it stands for itself. In particular, if you want to match a back- + For example, if you want to match a * character, you write \* in the + pattern. This escaping action applies whether or not the following + character would otherwise be interpreted as a metacharacter, so it is + always safe to precede a non-alphanumeric with backslash to specify + that it stands for itself. In particular, if you want to match a back- slash, you write \\. - If a pattern is compiled with the PCRE_EXTENDED option, whitespace in - the pattern (other than in a character class) and characters between a + If a pattern is compiled with the PCRE_EXTENDED option, whitespace in + the pattern (other than in a character class) and characters between a # outside a character class and the next newline are ignored. An escap- - ing backslash can be used to include a whitespace or # character as + ing backslash can be used to include a whitespace or # character as part of the pattern. - If you want to remove the special meaning from a sequence of charac- - ters, you can do so by putting them between \Q and \E. This is differ- - ent from Perl in that $ and @ are handled as literals in \Q...\E - sequences in PCRE, whereas in Perl, $ and @ cause variable interpola- + If you want to remove the special meaning from a sequence of charac- + ters, you can do so by putting them between \Q and \E. This is differ- + ent from Perl in that $ and @ are handled as literals in \Q...\E + sequences in PCRE, whereas in Perl, $ and @ cause variable interpola- tion. Note the following examples: Pattern PCRE matches Perl matches @@ -130,16 +131,16 @@ BACKSLASH \Qabc\$xyz\E abc\$xyz abc\$xyz \Qabc\E\$\Qxyz\E abc$xyz abc$xyz - The \Q...\E sequence is recognized both inside and outside character + The \Q...\E sequence is recognized both inside and outside character classes. Non-printing characters A second use of backslash provides a way of encoding non-printing char- - acters in patterns in a visible manner. There is no restriction on the - appearance of non-printing characters, apart from the binary zero that - terminates a pattern, but when a pattern is being prepared by text - editing, it is usually easier to use one of the following escape + acters in patterns in a visible manner. There is no restriction on the + appearance of non-printing characters, apart from the binary zero that + terminates a pattern, but when a pattern is being prepared by text + editing, it is usually easier to use one of the following escape sequences than the binary character it represents: \a alarm, that is, the BEL character (hex 07) @@ -153,45 +154,45 @@ BACKSLASH \xhh character with hex code hh \x{hhh..} character with hex code hhh.. - The precise effect of \cx is as follows: if x is a lower case letter, - it is converted to upper case. Then bit 6 of the character (hex 40) is - inverted. Thus \cz becomes hex 1A, but \c{ becomes hex 3B, while \c; + The precise effect of \cx is as follows: if x is a lower case letter, + it is converted to upper case. Then bit 6 of the character (hex 40) is + inverted. Thus \cz becomes hex 1A, but \c{ becomes hex 3B, while \c; becomes hex 7B. - After \x, from zero to two hexadecimal digits are read (letters can be - in upper or lower case). Any number of hexadecimal digits may appear - between \x{ and }, but the value of the character code must be less + After \x, from zero to two hexadecimal digits are read (letters can be + in upper or lower case). Any number of hexadecimal digits may appear + between \x{ and }, but the value of the character code must be less than 256 in non-UTF-8 mode, and less than 2**31 in UTF-8 mode (that is, - the maximum hexadecimal value is 7FFFFFFF). If characters other than - hexadecimal digits appear between \x{ and }, or if there is no termi- - nating }, this form of escape is not recognized. Instead, the initial + the maximum hexadecimal value is 7FFFFFFF). If characters other than + hexadecimal digits appear between \x{ and }, or if there is no termi- + nating }, this form of escape is not recognized. Instead, the initial \x will be interpreted as a basic hexadecimal escape, with no following digits, giving a character whose value is zero. Characters whose value is less than 256 can be defined by either of the - two syntaxes for \x. There is no difference in the way they are han- + two syntaxes for \x. There is no difference in the way they are han- dled. For example, \xdc is exactly the same as \x{dc}. - After \0 up to two further octal digits are read. If there are fewer - than two digits, just those that are present are used. Thus the + After \0 up to two further octal digits are read. If there are fewer + than two digits, just those that are present are used. Thus the sequence \0\x\07 specifies two binary zeros followed by a BEL character - (code value 7). Make sure you supply two digits after the initial zero + (code value 7). Make sure you supply two digits after the initial zero if the pattern character that follows is itself an octal digit. The handling of a backslash followed by a digit other than 0 is compli- cated. Outside a character class, PCRE reads it and any following dig- - its as a decimal number. If the number is less than 10, or if there + its as a decimal number. If the number is less than 10, or if there have been at least that many previous capturing left parentheses in the - expression, the entire sequence is taken as a back reference. A - description of how this works is given later, following the discussion + expression, the entire sequence is taken as a back reference. A + description of how this works is given later, following the discussion of parenthesized subpatterns. - Inside a character class, or if the decimal number is greater than 9 - and there have not been that many capturing subpatterns, PCRE re-reads + Inside a character class, or if the decimal number is greater than 9 + and there have not been that many capturing subpatterns, PCRE re-reads up to three octal digits following the backslash, and uses them to gen- - erate a data character. Any subsequent digits stand for themselves. In - non-UTF-8 mode, the value of a character specified in octal must be - less than \400. In UTF-8 mode, values up to \777 are permitted. For + erate a data character. Any subsequent digits stand for themselves. In + non-UTF-8 mode, the value of a character specified in octal must be + less than \400. In UTF-8 mode, values up to \777 are permitted. For example: \040 is another way of writing a space @@ -209,22 +210,22 @@ BACKSLASH \81 is either a back reference, or a binary zero followed by the two characters "8" and "1" - Note that octal values of 100 or greater must not be introduced by a + Note that octal values of 100 or greater must not be introduced by a leading zero, because no more than three octal digits are ever read. All the sequences that define a single character value can be used both - inside and outside character classes. In addition, inside a character - class, the sequence \b is interpreted as the backspace character (hex - 08), and the sequences \R and \X are interpreted as the characters "R" - and "X", respectively. Outside a character class, these sequences have + inside and outside character classes. In addition, inside a character + class, the sequence \b is interpreted as the backspace character (hex + 08), and the sequences \R and \X are interpreted as the characters "R" + and "X", respectively. Outside a character class, these sequences have different meanings (see below). Absolute and relative back references - The sequence \g followed by a positive or negative number, optionally - enclosed in braces, is an absolute or relative back reference. Back - references are discussed later, following the discussion of parenthe- - sized subpatterns. + The sequence \g followed by a positive or negative number, optionally + enclosed in braces, is an absolute or relative back reference. A named + back reference can be coded as \g{name}. Back references are discussed + later, following the discussion of parenthesized subpatterns. Generic character types @@ -233,57 +234,97 @@ BACKSLASH \d any decimal digit \D any character that is not a decimal digit + \h any horizontal whitespace character + \H any character that is not a horizontal whitespace character \s any whitespace character \S any character that is not a whitespace character + \v any vertical whitespace character + \V any character that is not a vertical whitespace character \w any "word" character \W any "non-word" character Each pair of escape sequences partitions the complete set of characters - into two disjoint sets. Any given character matches one, and only one, + into two disjoint sets. Any given character matches one, and only one, of each pair. These character type sequences can appear both inside and outside char- - acter classes. They each match one character of the appropriate type. - If the current matching point is at the end of the subject string, all + acter classes. They each match one character of the appropriate type. + If the current matching point is at the end of the subject string, all of them fail, since there is no character to match. - For compatibility with Perl, \s does not match the VT character (code - 11). This makes it different from the the POSIX "space" class. The \s - characters are HT (9), LF (10), FF (12), CR (13), and space (32). (If + For compatibility with Perl, \s does not match the VT character (code + 11). This makes it different from the the POSIX "space" class. The \s + characters are HT (9), LF (10), FF (12), CR (13), and space (32). If "use locale;" is included in a Perl script, \s may match the VT charac- - ter. In PCRE, it never does.) + ter. In PCRE, it never does. - A "word" character is an underscore or any character less than 256 that - is a letter or digit. The definition of letters and digits is con- - trolled by PCRE's low-valued character tables, and may vary if locale- - specific matching is taking place (see "Locale support" in the pcreapi - page). For example, in the "fr_FR" (French) locale, some character - codes greater than 128 are used for accented letters, and these are - matched by \w. - - In UTF-8 mode, characters with values greater than 128 never match \d, + In UTF-8 mode, characters with values greater than 128 never match \d, \s, or \w, and always match \D, \S, and \W. This is true even when Uni- - code character property support is available. The use of locales with - Unicode is discouraged. + code character property support is available. These sequences retain + their original meanings from before UTF-8 support was available, mainly + for efficiency reasons. + + The sequences \h, \H, \v, and \V are Perl 5.10 features. In contrast to + the other sequences, these do match certain high-valued codepoints in + UTF-8 mode. The horizontal space characters are: + + U+0009 Horizontal tab + U+0020 Space + U+00A0 Non-break space + U+1680 Ogham space mark + U+180E Mongolian vowel separator + U+2000 En quad + U+2001 Em quad + U+2002 En space + U+2003 Em space + U+2004 Three-per-em space + U+2005 Four-per-em space + U+2006 Six-per-em space + U+2007 Figure space + U+2008 Punctuation space + U+2009 Thin space + U+200A Hair space + U+202F Narrow no-break space + U+205F Medium mathematical space + U+3000 Ideographic space + + The vertical space characters are: + + U+000A Linefeed + U+000B Vertical tab + U+000C Formfeed + U+000D Carriage return + U+0085 Next line + U+2028 Line separator + U+2029 Paragraph separator + + A "word" character is an underscore or any character less than 256 that + is a letter or digit. The definition of letters and digits is con- + trolled by PCRE's low-valued character tables, and may vary if locale- + specific matching is taking place (see "Locale support" in the pcreapi + page). For example, in a French locale such as "fr_FR" in Unix-like + systems, or "french" in Windows, some character codes greater than 128 + are used for accented letters, and these are matched by \w. The use of + locales with Unicode is discouraged. Newline sequences - Outside a character class, the escape sequence \R matches any Unicode - newline sequence. This is an extension to Perl. In non-UTF-8 mode \R is + Outside a character class, the escape sequence \R matches any Unicode + newline sequence. This is a Perl 5.10 feature. In non-UTF-8 mode \R is equivalent to the following: (?>\r\n|\n|\x0b|\f|\r|\x85) - This is an example of an "atomic group", details of which are given + This is an example of an "atomic group", details of which are given below. This particular group matches either the two-character sequence - CR followed by LF, or one of the single characters LF (linefeed, + CR followed by LF, or one of the single characters LF (linefeed, U+000A), VT (vertical tab, U+000B), FF (formfeed, U+000C), CR (carriage return, U+000D), or NEL (next line, U+0085). The two-character sequence is treated as a single unit that cannot be split. - In UTF-8 mode, two additional characters whose codepoints are greater + In UTF-8 mode, two additional characters whose codepoints are greater than 255 are added: LS (line separator, U+2028) and PS (paragraph sepa- - rator, U+2029). Unicode character property support is not needed for + rator, U+2029). Unicode character property support is not needed for these characters to be recognized. Inside a character class, \R matches the letter "R". @@ -291,47 +332,49 @@ BACKSLASH Unicode character properties When PCRE is built with Unicode character property support, three addi- - tional escape sequences to match character properties are available - when UTF-8 mode is selected. They are: + tional escape sequences that match characters with specific properties + are available. When not in 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 an extended Unicode sequence - 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, and "Any", which matches any character (including newline). Other properties such as "InMusical- - Symbols" are not currently supported by PCRE. Note that \P{Any} does + Symbols" 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, Balinese, Bengali, Bopomofo, Braille, Buginese, - Buhid, Canadian_Aboriginal, Cherokee, Common, Coptic, Cuneiform, + Buhid, Canadian_Aboriginal, Cherokee, Common, Coptic, Cuneiform, Cypriot, Cyrillic, Deseret, Devanagari, Ethiopic, Georgian, Glagolitic, - Gothic, Greek, Gujarati, Gurmukhi, Han, Hangul, Hanunoo, Hebrew, Hira- - gana, Inherited, Kannada, Katakana, Kharoshthi, Khmer, Lao, Latin, + Gothic, Greek, Gujarati, Gurmukhi, Han, Hangul, Hanunoo, Hebrew, Hira- + gana, Inherited, Kannada, Katakana, Kharoshthi, Khmer, Lao, Latin, Limbu, Linear_B, Malayalam, Mongolian, Myanmar, New_Tai_Lue, Nko, - Ogham, Old_Italic, Old_Persian, Oriya, Osmanya, Phags_Pa, Phoenician, + Ogham, Old_Italic, Old_Persian, Oriya, Osmanya, Phags_Pa, Phoenician, Runic, Shavian, Sinhala, Syloti_Nagri, Syriac, Tagalog, Tagbanwa, Tai_Le, Tamil, Telugu, Thaana, Thai, Tibetan, Tifinagh, Ugaritic, Yi. - Each character has exactly one general category property, specified by + Each character has exactly one general category property, specified by a two-letter abbreviation. For compatibility with Perl, negation can be - specified by including a circumflex between the opening brace and the + 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} @@ -383,36 +426,57 @@ 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 long synonyms for these properties that Perl supports (such as - \p{Letter}) are not supported by PCRE, nor is it permitted to prefix + The long synonyms for these properties that Perl supports (such as + \p{Letter}) are not supported by PCRE, nor is it permitted to prefix any of these properties with "Is". No character that is in the Unicode table has the Cn (unassigned) prop- erty. Instead, this property is assumed for any code point that is not in the Unicode table. - Specifying caseless matching does not affect these escape sequences. + Specifying caseless matching does not affect these escape sequences. For example, \p{Lu} always matches only upper case letters. - 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 Unicode sequence. \X is equivalent to (?>\PM\pM*) - That is, it matches a character without the "mark" property, followed - by zero or more characters with the "mark" property, and treats the - sequence as an atomic group (see below). Characters with the "mark" - property are typically accents that affect the preceding character. + That is, it matches a character without the "mark" property, followed + by zero or more characters with the "mark" property, and treats the + sequence as an atomic group (see below). Characters with the "mark" + property are typically accents that affect the preceding character. + None of them have codepoints less than 256, so in non-UTF-8 mode \X + matches any one character. - Matching characters by Unicode property is not fast, because PCRE has - to search a structure that contains data for over fifteen thousand + Matching characters by Unicode property is not fast, because PCRE has + to search a structure that contains data for over fifteen thousand characters. That is why the traditional escape sequences such as \d and \w do not use Unicode properties in PCRE. + Resetting the match start + + The escape sequence \K, which is a Perl 5.10 feature, causes any previ- + ously 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, + when the pattern + + (foo)\Kbar + + matches "foobar", the first substring is still set to "foo". + Simple assertions The final use of backslash is for certain simple assertions. An asser- @@ -628,7 +692,7 @@ SQUARE BRACKETS AND CHARACTER CLASSES 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 non-UTF-8 mode, if - character tables for the "fr_FR" locale are in use, [\xc8-\xcb] matches + character tables for a French locale are in use, [\xc8-\xcb] matches accented E characters in both cases. In UTF-8 mode, PCRE supports the concept of case for characters with values greater than 128 only when it is compiled with Unicode property support. @@ -813,6 +877,37 @@ SUBPATTERNS "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, + 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 + 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 buffers that follow the sub- + pattern start after the highest number used in any branch. The follow- + ing example is taken from the Perl documentation. The numbers under- + neath show in which buffer the captured content will be stored. + + # before ---------------branch-reset----------- after + / ( a ) (?| x ( y ) z | (p (q) r) | (t) u (v) ) ( z ) /x + # 1 2 2 3 2 3 4 + + A backreference or a recursive call to a numbered subpattern always + refers to the first one in the pattern with the given number. + + 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 @@ -852,14 +947,16 @@ NAMED SUBPATTERNS (?Sat)(?:urday)? There are five capturing substrings, but only one is ever set after a - match. 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 reference to a non- - unique named subpattern from elsewhere in the pattern, the one that - corresponds to the lowest number is used. For further details of the - interfaces for handling named subpatterns, see the pcreapi documenta- - tion. + 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 + subpattern it was. If you make a reference to a non-unique named sub- + pattern from elsewhere in the pattern, the one that corresponds to the + lowest number is used. For further details of the interfaces for han- + dling named subpatterns, see the pcreapi documentation. REPETITION @@ -1174,64 +1271,69 @@ BACK REFERENCES matches "rah rah" and "RAH RAH", but not "RAH rah", even though the original capturing subpattern is matched caselessly. - Back references to named subpatterns use the Perl syntax \k or - \k'name' or the Python syntax (?P=name). We could rewrite the above - example in either of the following ways: + 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 + example in any of the following ways: (?(?i)rah)\s+\k + (?'p1'(?i)rah)\s+\k{p1} (?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. For example, the pattern (a|(bc))\2 - always fails if it starts to match "a" rather than "bc". Because there - may be many capturing parentheses in a pattern, all digits following - the backslash are taken as part of a potential back reference number. + always fails if it starts to match "a" rather than "bc". Because there + may be many capturing parentheses in a pattern, all digits following + the backslash are taken as part of a potential back reference 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 whitespace. Otherwise an empty comment (see "Com- + used to terminate the back reference. If the PCRE_EXTENDED option is + set, this can be whitespace. Otherwise an empty comment (see "Com- ments" below) can be used. - A back reference that occurs inside the parentheses to which it refers - fails when the subpattern is first used, so, for example, (a\1) never - matches. However, such references can be useful inside repeated 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. 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, and may not be - repeated, because it makes no sense to assert the same thing several - times. If any kind of assertion contains capturing subpatterns within - it, these are counted for the purposes of numbering the capturing sub- + Assertion subpatterns are not capturing subpatterns, and may not be + repeated, because it makes no sense to assert the same thing several + times. If any kind of assertion contains capturing subpatterns within + it, these are counted for the purposes of numbering the capturing sub- patterns in the whole pattern. However, substring capturing is carried - out only for positive assertions, because it does not make sense for + out only for positive assertions, because it does not make sense for negative assertions. Lookahead assertions @@ -1241,37 +1343,37 @@ 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. Lookbehind assertions - Lookbehind assertions start with (?<= for positive assertions and (?)...) or (?('name')...) to test for a @@ -1547,19 +1666,35 @@ RECURSIVE PATTERNS ( \( ( (?>[^()]+) | (?1) )* \) ) We have put the pattern into parentheses, and caused the recursion to - refer to them instead of the whole pattern. In a larger pattern, keep- - ing track of parenthesis numbers can be tricky. It may be more conve- - nient 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: + 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. (A Perl + 5.10 feature.) 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 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 "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 + supported. We could rewrite the above example as follows: (? \( ( (?>[^()]+) | (?&pn) )* \) ) - If there is more than one subpattern with the same name, the earliest - one is used. This particular example pattern contains nested unlimited - repeats, and so the use of atomic grouping for matching strings of non- - parentheses is important when applying the pattern to strings that do - not match. For example, when this pattern is applied to + 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 + nested unlimited repeats, and so the use of atomic grouping for match- + ing strings of non-parentheses is important when applying the pattern + to strings that do not match. For example, when this pattern is applied + to (aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa() @@ -1609,8 +1744,14 @@ SUBPATTERNS AS SUBROUTINES If the syntax for a recursive subpattern reference (either by number or by name) is used outside the parentheses to which it refers, it oper- ates like a subroutine in a programming language. The "called" subpat- - tern may be defined before or after the reference. An earlier example - pointed out that the pattern + tern may be defined before or after the reference. A numbered reference + can be absolute or relative, as in these examples: + + (...(absolute)...)...(?2)... + (...(relative)...)...(?-1)... + (...(?+1)...(relative)... + + An earlier example pointed out that the pattern (sens|respons)e and \1ibility @@ -1632,7 +1773,7 @@ SUBPATTERNS AS SUBROUTINES case-independence are fixed when the subpattern is defined. They cannot be changed for different calls. For example, consider this pattern: - (abc)(?i:(?1)) + (abc)(?i:(?-1)) It matches "abcabc". It does not match "abcABC" because the change of processing option does not affect the called subpattern. @@ -1677,5 +1818,15 @@ SEE ALSO pcreapi(3), pcrecallout(3), pcrematching(3), pcre(3). -Last updated: 06 December 2006 -Copyright (c) 1997-2006 University of Cambridge. + +AUTHOR + + Philip Hazel + University Computing Service + Cambridge CB2 3QH, England. + + +REVISION + + Last updated: 19 June 2007 + Copyright (c) 1997-2007 University of Cambridge. diff --git a/doc/doc-txt/pcretest.txt b/doc/doc-txt/pcretest.txt index 1a0424c20..d93ec26d1 100644 --- a/doc/doc-txt/pcretest.txt +++ b/doc/doc-txt/pcretest.txt @@ -151,18 +151,19 @@ PATTERN MODIFIERS The following table shows additional modifiers for setting PCRE options that do not correspond to anything in Perl: - /A PCRE_ANCHORED - /C PCRE_AUTO_CALLOUT - /E PCRE_DOLLAR_ENDONLY - /f PCRE_FIRSTLINE - /J PCRE_DUPNAMES - /N PCRE_NO_AUTO_CAPTURE - /U PCRE_UNGREEDY - /X PCRE_EXTRA - / PCRE_NEWLINE_CR - / PCRE_NEWLINE_LF - / PCRE_NEWLINE_CRLF - / PCRE_NEWLINE_ANY + /A PCRE_ANCHORED + /C PCRE_AUTO_CALLOUT + /E PCRE_DOLLAR_ENDONLY + /f PCRE_FIRSTLINE + /J PCRE_DUPNAMES + /N PCRE_NO_AUTO_CAPTURE + /U PCRE_UNGREEDY + /X PCRE_EXTRA + / PCRE_NEWLINE_CR + / PCRE_NEWLINE_LF + / PCRE_NEWLINE_CRLF + / PCRE_NEWLINE_ANYCRLF + / PCRE_NEWLINE_ANY Those specifying line ending sequencess are literal strings as shown. This example sets multiline matching with CRLF as the line ending @@ -202,7 +203,11 @@ PATTERN MODIFIERS subject contains multiple copies of the same substring. The /B modifier is a debugging feature. It requests that pcretest out- - put a representation of the compiled byte code after compilation. + put a representation of the compiled byte code after compilation. Nor- + mally this information contains length and offset values; however, if + /Z is also present, this data is replaced by spaces. This is a special + feature for use in the automatic test scripts; it ensures that the same + output is generated for different internal link sizes. The /L modifier must be followed directly by the name of a locale, for example, @@ -331,6 +336,8 @@ DATA LINES or pcre_dfa_exec() \ pass the PCRE_NEWLINE_CRLF option to pcre_exec() or pcre_dfa_exec() + \ pass the PCRE_NEWLINE_ANYCRLF option to pcre_exec() + or pcre_dfa_exec() \ pass the PCRE_NEWLINE_ANY option to pcre_exec() or pcre_dfa_exec() @@ -486,7 +493,7 @@ RESTARTING AFTER A PARTIAL MATCH can restart the match with additional subject data by means of the \R escape sequence. For example: - re> /^?(jan|feb|mar|apr|may|jun|jul|aug|sep|oct|nov|dec)$/ + re> /^\d?\d(jan|feb|mar|apr|may|jun|jul|aug|sep|oct|nov|dec)\d\d$/ data> 23ja\P\D Partial match: 23ja data> n05\R\D @@ -613,8 +620,11 @@ SEE ALSO AUTHOR Philip Hazel - University Computing Service, + University Computing Service Cambridge CB2 3QH, England. -Last updated: 30 November 2006 -Copyright (c) 1997-2006 University of Cambridge. + +REVISION + + Last updated: 24 April 2007 + Copyright (c) 1997-2007 University of Cambridge. diff --git a/src/scripts/MakeLinks b/src/scripts/MakeLinks index d4561ac39..ce125a8dd 100755 --- a/src/scripts/MakeLinks +++ b/src/scripts/MakeLinks @@ -1,5 +1,5 @@ #!/bin/sh -# $Cambridge: exim/src/scripts/MakeLinks,v 1.10 2007/01/23 15:08:45 ph10 Exp $ +# $Cambridge: exim/src/scripts/MakeLinks,v 1.11 2007/06/26 11:16:54 ph10 Exp $ # Script to build links for all the exim source files from the system- # specific build directory. It should be run from within that directory. @@ -32,10 +32,10 @@ mkdir pcre cd pcre ln -s ../../src/pcre/Makefile Makefile ln -s ../../src/pcre/config.h config.h -ln -s ../../src/pcre/dftables.c dftables.c ln -s ../../src/pcre/pcre_internal.h pcre_internal.h ln -s ../../src/pcre/pcre.h pcre.h ln -s ../../src/pcre/pcre_maketables.c pcre_maketables.c +ln -s ../../src/pcre/pcre_chartables.c pcre_chartables.c ln -s ../../src/pcre/pcre_config.c pcre_config.c ln -s ../../src/pcre/pcre_get.c pcre_get.c ln -s ../../src/pcre/pcre_globals.c pcre_globals.c diff --git a/src/src/pcre/ChangeLog b/src/src/pcre/ChangeLog index 7d32804d0..87c2de74d 100644 --- a/src/src/pcre/ChangeLog +++ b/src/src/pcre/ChangeLog @@ -1,6 +1,229 @@ ChangeLog for PCRE ------------------ +Version 7.2 19-June-07 +--------------------- + + 1. If the fr_FR locale cannot be found for test 3, try the "french" locale, + which is apparently normally available under Windows. + + 2. Re-jig the pcregrep tests with different newline settings in an attempt + to make them independent of the local environment's newline setting. + + 3. Add code to configure.ac to remove -g from the CFLAGS default settings. + + 4. Some of the "internals" tests were previously cut out when the link size + was not 2, because the output contained actual offsets. The recent new + "Z" feature of pcretest means that these can be cut out, making the tests + usable with all link sizes. + + 5. Implemented Stan Switzer's goto replacement for longjmp() when not using + stack recursion. This gives a massive performance boost under BSD, but just + a small improvement under Linux. However, it saves one field in the frame + in all cases. + + 6. Added more features from the forthcoming Perl 5.10: + + (a) (?-n) (where n is a string of digits) is a relative subroutine or + recursion call. It refers to the nth most recently opened parentheses. + + (b) (?+n) is also a relative subroutine call; it refers to the nth next + to be opened parentheses. + + (c) Conditions that refer to capturing parentheses can be specified + relatively, for example, (?(-2)... or (?(+3)... + + (d) \K resets the start of the current match so that everything before + is not part of it. + + (e) \k{name} is synonymous with \k and \k'name' (.NET compatible). + + (f) \g{name} is another synonym - part of Perl 5.10's unification of + reference syntax. + + (g) (?| introduces a group in which the numbering of parentheses in each + alternative starts with the same number. + + (h) \h, \H, \v, and \V match horizontal and vertical whitespace. + + 7. Added two new calls to pcre_fullinfo(): PCRE_INFO_OKPARTIAL and + PCRE_INFO_JCHANGED. + + 8. A pattern such as (.*(.)?)* caused pcre_exec() to fail by either not + terminating or by crashing. Diagnosed by Viktor Griph; it was in the code + for detecting groups that can match an empty string. + + 9. A pattern with a very large number of alternatives (more than several + hundred) was running out of internal workspace during the pre-compile + phase, where pcre_compile() figures out how much memory will be needed. A + bit of new cunning has reduced the workspace needed for groups with + alternatives. The 1000-alternative test pattern now uses 12 bytes of + workspace instead of running out of the 4096 that are available. + +10. Inserted some missing (unsigned int) casts to get rid of compiler warnings. + +11. Applied patch from Google to remove an optimization that didn't quite work. + The report of the bug said: + + pcrecpp::RE("a*").FullMatch("aaa") matches, while + pcrecpp::RE("a*?").FullMatch("aaa") does not, and + pcrecpp::RE("a*?\\z").FullMatch("aaa") does again. + +12. If \p or \P was used in non-UTF-8 mode on a character greater than 127 + it matched the wrong number of bytes. + + +Version 7.1 24-Apr-07 +--------------------- + + 1. Applied Bob Rossi and Daniel G's patches to convert the build system to one + that is more "standard", making use of automake and other Autotools. There + is some re-arrangement of the files and adjustment of comments consequent + on this. + + 2. Part of the patch fixed a problem with the pcregrep tests. The test of -r + for recursive directory scanning broke on some systems because the files + are not scanned in any specific order and on different systems the order + was different. A call to "sort" has been inserted into RunGrepTest for the + approprate test as a short-term fix. In the longer term there may be an + alternative. + + 3. I had an email from Eric Raymond about problems translating some of PCRE's + man pages to HTML (despite the fact that I distribute HTML pages, some + people do their own conversions for various reasons). The problems + concerned the use of low-level troff macros .br and .in. I have therefore + removed all such uses from the man pages (some were redundant, some could + be replaced by .nf/.fi pairs). The 132html script that I use to generate + HTML has been updated to handle .nf/.fi and to complain if it encounters + .br or .in. + + 4. Updated comments in configure.ac that get placed in config.h.in and also + arranged for config.h to be included in the distribution, with the name + config.h.generic, for the benefit of those who have to compile without + Autotools (compare pcre.h, which is now distributed as pcre.h.generic). + + 5. Updated the support (such as it is) for Virtual Pascal, thanks to Stefan + Weber: (1) pcre_internal.h was missing some function renames; (2) updated + makevp.bat for the current PCRE, using the additional files + makevp_c.txt, makevp_l.txt, and pcregexp.pas. + + 6. A Windows user reported a minor discrepancy with test 2, which turned out + to be caused by a trailing space on an input line that had got lost in his + copy. The trailing space was an accident, so I've just removed it. + + 7. Add -Wl,-R... flags in pcre-config.in for *BSD* systems, as I'm told + that is needed. + + 8. Mark ucp_table (in ucptable.h) and ucp_gentype (in pcre_ucp_searchfuncs.c) + as "const" (a) because they are and (b) because it helps the PHP + maintainers who have recently made a script to detect big data structures + in the php code that should be moved to the .rodata section. I remembered + to update Builducptable as well, so it won't revert if ucptable.h is ever + re-created. + + 9. Added some extra #ifdef SUPPORT_UTF8 conditionals into pcretest.c, + pcre_printint.src, pcre_compile.c, pcre_study.c, and pcre_tables.c, in + order to be able to cut out the UTF-8 tables in the latter when UTF-8 + support is not required. This saves 1.5-2K of code, which is important in + some applications. + + Later: more #ifdefs are needed in pcre_ord2utf8.c and pcre_valid_utf8.c + so as not to refer to the tables, even though these functions will never be + called when UTF-8 support is disabled. Otherwise there are problems with a + shared library. + +10. Fixed two bugs in the emulated memmove() function in pcre_internal.h: + + (a) It was defining its arguments as char * instead of void *. + + (b) It was assuming that all moves were upwards in memory; this was true + a long time ago when I wrote it, but is no longer the case. + + The emulated memove() is provided for those environments that have neither + memmove() nor bcopy(). I didn't think anyone used it these days, but that + is clearly not the case, as these two bugs were recently reported. + +11. The script PrepareRelease is now distributed: it calls 132html, CleanTxt, + and Detrail to create the HTML documentation, the .txt form of the man + pages, and it removes trailing spaces from listed files. It also creates + pcre.h.generic and config.h.generic from pcre.h and config.h. In the latter + case, it wraps all the #defines with #ifndefs. This script should be run + before "make dist". + +12. Fixed two fairly obscure bugs concerned with quantified caseless matching + with Unicode property support. + + (a) For a maximizing quantifier, if the two different cases of the + character were of different lengths in their UTF-8 codings (there are + some cases like this - I found 11), and the matching function had to + back up over a mixture of the two cases, it incorrectly assumed they + were both the same length. + + (b) When PCRE was configured to use the heap rather than the stack for + recursion during matching, it was not correctly preserving the data for + the other case of a UTF-8 character when checking ahead for a match + while processing a minimizing repeat. If the check also involved + matching a wide character, but failed, corruption could cause an + erroneous result when trying to check for a repeat of the original + character. + +13. Some tidying changes to the testing mechanism: + + (a) The RunTest script now detects the internal link size and whether there + is UTF-8 and UCP support by running ./pcretest -C instead of relying on + values substituted by "configure". (The RunGrepTest script already did + this for UTF-8.) The configure.ac script no longer substitutes the + relevant variables. + + (b) The debugging options /B and /D in pcretest show the compiled bytecode + with length and offset values. This means that the output is different + for different internal link sizes. Test 2 is skipped for link sizes + other than 2 because of this, bypassing the problem. Unfortunately, + there was also a test in test 3 (the locale tests) that used /B and + failed for link sizes other than 2. Rather than cut the whole test out, + I have added a new /Z option to pcretest that replaces the length and + offset values with spaces. This is now used to make test 3 independent + of link size. (Test 2 will be tidied up later.) + +14. If erroroffset was passed as NULL to pcre_compile, it provoked a + segmentation fault instead of returning the appropriate error message. + +15. In multiline mode when the newline sequence was set to "any", the pattern + ^$ would give a match between the \r and \n of a subject such as "A\r\nB". + This doesn't seem right; it now treats the CRLF combination as the line + ending, and so does not match in that case. It's only a pattern such as ^$ + that would hit this one: something like ^ABC$ would have failed after \r + and then tried again after \r\n. + +16. Changed the comparison command for RunGrepTest from "diff -u" to "diff -ub" + in an attempt to make files that differ only in their line terminators + compare equal. This works on Linux. + +17. Under certain error circumstances pcregrep might try to free random memory + as it exited. This is now fixed, thanks to valgrind. + +19. In pcretest, if the pattern /(?m)^$/g was matched against the string + "abc\r\n\r\n", it found an unwanted second match after the second \r. This + was because its rules for how to advance for /g after matching an empty + string at the end of a line did not allow for this case. They now check for + it specially. + +20. pcretest is supposed to handle patterns and data of any length, by + extending its buffers when necessary. It was getting this wrong when the + buffer for a data line had to be extended. + +21. Added PCRE_NEWLINE_ANYCRLF which is like ANY, but matches only CR, LF, or + CRLF as a newline sequence. + +22. Code for handling Unicode properties in pcre_dfa_exec() wasn't being cut + out by #ifdef SUPPORT_UCP. This did no harm, as it could never be used, but + I have nevertheless tidied it up. + +23. Added some casts to kill warnings from HP-UX ia64 compiler. + +24. Added a man page for pcre-config. + + Version 7.0 19-Dec-06 --------------------- diff --git a/src/src/pcre/LICENCE b/src/src/pcre/LICENCE index 58241b2bd..4baa7d83a 100644 --- a/src/src/pcre/LICENCE +++ b/src/src/pcre/LICENCE @@ -20,9 +20,9 @@ Email local part: ph10 Email domain: cam.ac.uk University of Cambridge Computing Service, -Cambridge, England. Phone: +44 1223 334714. +Cambridge, England. -Copyright (c) 1997-2006 University of Cambridge +Copyright (c) 1997-2007 University of Cambridge All rights reserved. @@ -31,7 +31,7 @@ THE C++ WRAPPER FUNCTIONS Contributed by: Google Inc. -Copyright (c) 2006, Google Inc. +Copyright (c) 2007, Google Inc. All rights reserved. diff --git a/src/src/pcre/Makefile b/src/src/pcre/Makefile index 7079d75f5..400b3c3a5 100644 --- a/src/src/pcre/Makefile +++ b/src/src/pcre/Makefile @@ -1,4 +1,4 @@ -# $Cambridge: exim/src/src/pcre/Makefile,v 1.7 2007/01/23 15:08:45 ph10 Exp $ +# $Cambridge: exim/src/src/pcre/Makefile,v 1.8 2007/06/26 11:16:54 ph10 Exp $ # Makefile for PCRE (Perl-Compatible Regular Expression) library for use by # Exim. This is a tailored Makefile, not the normal one that comes with the @@ -8,12 +8,12 @@ AR = ar cq CC = gcc -O2 -Wall -CFLAGS = +CFLAGS = -I. RANLIB = @true ############################################################################## -OBJ = pcre_maketables.o chartables.o pcre_fullinfo.o pcre_get.o \ +OBJ = pcre_maketables.o pcre_chartables.o pcre_fullinfo.o pcre_get.o \ pcre_globals.o pcre_compile.o pcre_config.o pcre_exec.o pcre_newline.o \ pcre_study.o pcre_tables.o pcre_try_flipped.o pcre_version.o @@ -21,7 +21,7 @@ all: libpcre.a ../pcretest ../pcretest: libpcre.a pcretest.o @echo "$(CC) -o ../pcretest pcretest.o libpcre.a" - $(FE)$(CC) $(CFLAGS) -o ../pcretest pcretest.o libpcre.a + $(FE)$(CC) $(CFLAGS) -I. -o ../pcretest pcretest.o libpcre.a libpcre.a: $(OBJ) -rm -f libpcre.a @@ -29,69 +29,60 @@ libpcre.a: $(OBJ) $(FE)$(AR) libpcre.a $(OBJ) $(RANLIB) libpcre.a -chartables.o: chartables.c pcre_compile.c config.h pcre.h pcre_internal.h Makefile - @echo "$(CC) chartables.c" - $(FE)$(CC) -c $(CFLAGS) chartables.c +pcre_chartables.o: pcre_chartables.c pcre_compile.c config.h pcre.h pcre_internal.h Makefile + @echo "$(CC) pcre_chartables.c" + $(FE)$(CC) -c $(CFLAGS) -I. pcre_chartables.c pcre_compile.o: pcre_compile.c config.h pcre.h pcre_internal.h Makefile @echo "$(CC) pcre_compile.c" - $(FE)$(CC) -c $(CFLAGS) pcre_compile.c + $(FE)$(CC) -c $(CFLAGS) -I. pcre_compile.c pcre_config.o: pcre_config.c config.h pcre.h pcre_internal.h Makefile @echo "$(CC) pcre_config.c" - $(FE)$(CC) -c $(CFLAGS) pcre_config.c + $(FE)$(CC) -c $(CFLAGS) -I. pcre_config.c -pcre_exec.o: chartables.c pcre_exec.c config.h pcre.h pcre_internal.h Makefile +pcre_exec.o: pcre_chartables.c pcre_exec.c config.h pcre.h pcre_internal.h Makefile @echo "$(CC) pcre_exec.c" - $(FE)$(CC) -c $(CFLAGS) pcre_exec.c + $(FE)$(CC) -c $(CFLAGS) -I. pcre_exec.c pcre_maketables.o: pcre_maketables.c config.h pcre.h pcre_internal.h Makefile - @echo "$(CC) pcre_maketables.c" + @echo "$(CC) pcre_maketables.c" $(FE)$(CC) -c $(CFLAGS) pcre_maketables.c pcre_fullinfo.o: pcre_fullinfo.c pcre.h config.h pcre_internal.h Makefile @echo "$(CC) pcre_fullinfo.c" - $(FE)$(CC) -c $(CFLAGS) pcre_fullinfo.c + $(FE)$(CC) -c $(CFLAGS) -I. pcre_fullinfo.c pcre_get.o: pcre_get.c pcre.h config.h pcre_internal.h Makefile @echo "$(CC) pcre_get.c" - $(FE)$(CC) -c $(CFLAGS) pcre_get.c + $(FE)$(CC) -c $(CFLAGS) -I. pcre_get.c pcre_globals.o: pcre_globals.c pcre.h config.h pcre_internal.h Makefile @echo "$(CC) pcre_globals.c" - $(FE)$(CC) -c $(CFLAGS) pcre_globals.c + $(FE)$(CC) -c $(CFLAGS) -I. pcre_globals.c pcre_newline.o: pcre_newline.c pcre.h config.h pcre_internal.h Makefile @echo "$(CC) pcre_newline.c" - $(FE)$(CC) -c $(CFLAGS) pcre_newline.c + $(FE)$(CC) -c $(CFLAGS) -I. pcre_newline.c pcre_study.o: pcre_study.c pcre.h config.h pcre_internal.h Makefile @echo "$(CC) pcre_study.c" - $(FE)$(CC) -c $(CFLAGS) pcre_study.c + $(FE)$(CC) -c $(CFLAGS) -I. pcre_study.c pcre_tables.o: pcre_tables.c pcre.h config.h pcre_internal.h Makefile @echo "$(CC) pcre_tables.c" - $(FE)$(CC) -c $(CFLAGS) pcre_tables.c + $(FE)$(CC) -c $(CFLAGS) -I. pcre_tables.c pcre_try_flipped.o: pcre_try_flipped.c pcre.h config.h pcre_internal.h Makefile @echo "$(CC) pcre_try_flipped.c" - $(FE)$(CC) -c $(CFLAGS) pcre_try_flipped.c + $(FE)$(CC) -c $(CFLAGS) -I. pcre_try_flipped.c pcre_version.o: pcre_version.c config.h pcre.h pcre_internal.h Makefile @echo "$(CC) pcre_version.c" - $(FE)$(CC) -c $(CFLAGS) pcre_version.c + $(FE)$(CC) -c $(CFLAGS) -I. pcre_version.c pcretest.o: pcretest.c config.h pcre.h pcre_internal.h Makefile @echo "$(CC) pcretest.c" $(FE)$(CC) -c -DNOPOSIX -DNODFA -DNOUTF8 -DNOINFOCHECK $(CFLAGS) -I. pcretest.c -# An auxiliary program makes the default character table source - -chartables.c: dftables - ./dftables chartables.c - -dftables: dftables.c pcre_maketables.c config.h pcre.h pcre_internal.h Makefile - @echo "$(CC) dftables.c" - $(FE)$(CC) -o dftables $(CFLAGS) dftables.c - # End diff --git a/src/src/pcre/config.h b/src/src/pcre/config.h index 715471ee1..51bd998bb 100644 --- a/src/src/pcre/config.h +++ b/src/src/pcre/config.h @@ -1,4 +1,4 @@ -/* $Cambridge: exim/src/src/pcre/config.h,v 1.2 2006/11/07 16:50:36 ph10 Exp $ */ +/* $Cambridge: exim/src/src/pcre/config.h,v 1.3 2007/06/26 11:16:54 ph10 Exp $ */ /************************************************* * config.h for PCRE for Exim * @@ -36,9 +36,8 @@ PCRE, can be adjusted by "configure". */ #define MAX_DUPLENGTH 30000 /* There is some stuff in the PCRE sources for compilation on non-Unix systems -and non-ASCII systems. For Exim's purposes, just flatten it all. */ +and non-ASCII systems. For Exim's purposes, just flatten it. */ -#define EBCDIC 0 -#define EXPORT +#undef EBCDIC /* End */ diff --git a/src/src/pcre/dftables.c b/src/src/pcre/dftables.c index bc01eb7f2..e1a2d6f83 100644 --- a/src/src/pcre/dftables.c +++ b/src/src/pcre/dftables.c @@ -1,4 +1,4 @@ -/* $Cambridge: exim/src/src/pcre/dftables.c,v 1.5 2007/01/23 15:08:45 ph10 Exp $ */ +/* $Cambridge: exim/src/src/pcre/dftables.c,v 1.6 2007/06/26 11:16:54 ph10 Exp $ */ /************************************************* * Perl-Compatible Regular Expressions * @@ -8,7 +8,7 @@ and semantics are as close as possible to those of the Perl 5 language. Written by Philip Hazel - Copyright (c) 1997-2006 University of Cambridge + Copyright (c) 1997-2007 University of Cambridge ----------------------------------------------------------------------------- Redistribution and use in source and binary forms, with or without @@ -40,14 +40,15 @@ POSSIBILITY OF SUCH DAMAGE. */ -/* This is a freestanding support program to generate a file containing default -character tables for PCRE. The tables are built according to the default C +/* This is a freestanding support program to generate a file containing +character tables for PCRE. The tables are built according to the current locale. Now that pcre_maketables is a function visible to the outside world, we make use of its code from here in order to be consistent. */ #include #include #include +#include #include "pcre_internal.h" @@ -57,38 +58,48 @@ make use of its code from here in order to be consistent. */ int main(int argc, char **argv) { -int i; FILE *f; -const unsigned char *tables = pcre_maketables(); -const unsigned char *base_of_tables = tables; +int i = 1; +const unsigned char *tables; +const unsigned char *base_of_tables; -if (argc != 2) +/* By default, the default C locale is used rather than what the building user +happens to have set. However, if the -L option is given, set the locale from +the LC_xxx environment variables. */ + +if (argc > 1 && strcmp(argv[1], "-L") == 0) + { + setlocale(LC_ALL, ""); /* Set from environment variables */ + i++; + } + +if (argc < i + 1) { fprintf(stderr, "dftables: one filename argument is required\n"); return 1; } -f = fopen(argv[1], "wb"); +tables = pcre_maketables(); +base_of_tables = tables; + +f = fopen(argv[i], "wb"); if (f == NULL) { fprintf(stderr, "dftables: failed to open %s for writing\n", argv[1]); return 1; } -/* There are two fprintf() calls here, because gcc in pedantic mode complains -about the very long string otherwise. */ +/* There are several fprintf() calls here, because gcc in pedantic mode +complains about the very long string otherwise. */ fprintf(f, "/*************************************************\n" "* Perl-Compatible Regular Expressions *\n" "*************************************************/\n\n" - "/* This file is automatically written by the dftables auxiliary \n" - "program. If you edit it by hand, you might like to edit the Makefile to \n" - "prevent its ever being regenerated.\n\n"); -fprintf(f, - "This file contains the default tables for characters with codes less than\n" - "128 (ASCII characters). These tables are used when no external tables are\n" - "passed to PCRE.\n\n"); + "/* This file was automatically written by the dftables auxiliary\n" + "program. It contains character tables that are used when no external\n" + "tables are passed to PCRE by the application that calls it. The tables\n" + "are used only for characters whose code values are less than 256.\n\n"); fprintf(f, "The following #include is present because without it gcc 4.x may remove\n" "the array definition from the final binary if PCRE is built into a static\n" @@ -173,7 +184,7 @@ if (isprint(i-8)) fprintf(f, " %c -", i-8); else fprintf(f, "%3d-", i-8); if (isprint(i-1)) fprintf(f, " %c ", i-1); else fprintf(f, "%3d", i-1); -fprintf(f, " */\n\n/* End of chartables.c */\n"); +fprintf(f, " */\n\n/* End of pcre_chartables.c */\n"); fclose(f); free((void *)base_of_tables); diff --git a/src/src/pcre/pcre.h b/src/src/pcre/pcre.h index 6c3f2a50b..c46b8acd7 100644 --- a/src/src/pcre/pcre.h +++ b/src/src/pcre/pcre.h @@ -1,4 +1,4 @@ -/* $Cambridge: exim/src/src/pcre/pcre.h,v 1.5 2007/01/23 15:08:45 ph10 Exp $ */ +/* $Cambridge: exim/src/src/pcre/pcre.h,v 1.6 2007/06/26 11:16:54 ph10 Exp $ */ /************************************************* * Perl-Compatible Regular Expressions * @@ -7,7 +7,7 @@ /* This is the public header file for the PCRE library, to be #included by applications that call the PCRE functions. - Copyright (c) 1997-2006 University of Cambridge + Copyright (c) 1997-2007 University of Cambridge ----------------------------------------------------------------------------- Redistribution and use in source and binary forms, with or without @@ -43,44 +43,31 @@ POSSIBILITY OF SUCH DAMAGE. /* The current PCRE version information. */ -/* NOTES FOR FUTURE MAINTAINERS: Do not use numbers with leading zeros, because -they may be treated as octal constants. The PCRE_PRERELEASE feature is for -identifying release candidates. It might be defined as -RC2, for example. In -real releases, it should be defined empty. Do not change the alignment of these -statments. The code in ./configure greps out the version numbers by using "cut" -to get values from column 29 onwards. These are substituted into pcre-config -and libpcre.pc. The values are not put into configure.ac and substituted here -(which would simplify this issue) because that makes life harder for those who -cannot run ./configure. As it now stands, this file need not be edited in that -circumstance. */ - #define PCRE_MAJOR 7 -#define PCRE_MINOR 0 -#define PCRE_PRERELEASE -#define PCRE_DATE 18-Dec-2006 +#define PCRE_MINOR 2 +#define PCRE_PRERELEASE +#define PCRE_DATE 2007-06-19 -/* Win32 uses DLL by default; it needs special stuff for exported functions -when building PCRE. */ +/* When an application links to a PCRE DLL in Windows, the symbols that are +imported have to be identified as such. When building PCRE, the appropriate +export setting is defined in pcre_internal.h, which includes this file. So we +don't change an existing definition of PCRE_EXP_DECL. */ -#ifdef _WIN32 -# ifdef PCRE_DEFINITION -# ifdef DLL_EXPORT -# define PCRE_DATA_SCOPE __declspec(dllexport) -# endif -# else +#ifndef PCRE_EXP_DECL +# ifdef _WIN32 # ifndef PCRE_STATIC -# define PCRE_DATA_SCOPE extern __declspec(dllimport) +# define PCRE_EXP_DECL extern __declspec(dllimport) # endif # endif #endif -/* Otherwise, we use the standard "extern". */ +/* By default, we use the standard "extern" declarations. */ -#ifndef PCRE_DATA_SCOPE +#ifndef PCRE_EXP_DECL # ifdef __cplusplus -# define PCRE_DATA_SCOPE extern "C" +# define PCRE_EXP_DECL extern "C" # else -# define PCRE_DATA_SCOPE extern +# define PCRE_EXP_DECL extern # endif #endif @@ -121,6 +108,7 @@ extern "C" { #define PCRE_NEWLINE_LF 0x00200000 #define PCRE_NEWLINE_CRLF 0x00300000 #define PCRE_NEWLINE_ANY 0x00400000 +#define PCRE_NEWLINE_ANYCRLF 0x00500000 /* Exec-time and get/set-time error codes */ @@ -164,6 +152,8 @@ extern "C" { #define PCRE_INFO_NAMETABLE 9 #define PCRE_INFO_STUDYSIZE 10 #define PCRE_INFO_DEFAULT_TABLES 11 +#define PCRE_INFO_OKPARTIAL 12 +#define PCRE_INFO_JCHANGED 13 /* Request types for pcre_config(). Do not re-arrange, in order to remain compatible. */ @@ -242,52 +232,52 @@ that is triggered by the (?) regex item. For Virtual Pascal, these definitions have to take another form. */ #ifndef VPCOMPAT -PCRE_DATA_SCOPE void *(*pcre_malloc)(size_t); -PCRE_DATA_SCOPE void (*pcre_free)(void *); -PCRE_DATA_SCOPE void *(*pcre_stack_malloc)(size_t); -PCRE_DATA_SCOPE void (*pcre_stack_free)(void *); -PCRE_DATA_SCOPE int (*pcre_callout)(pcre_callout_block *); +PCRE_EXP_DECL void *(*pcre_malloc)(size_t); +PCRE_EXP_DECL void (*pcre_free)(void *); +PCRE_EXP_DECL void *(*pcre_stack_malloc)(size_t); +PCRE_EXP_DECL void (*pcre_stack_free)(void *); +PCRE_EXP_DECL int (*pcre_callout)(pcre_callout_block *); #else /* VPCOMPAT */ -PCRE_DATA_SCOPE void *pcre_malloc(size_t); -PCRE_DATA_SCOPE void pcre_free(void *); -PCRE_DATA_SCOPE void *pcre_stack_malloc(size_t); -PCRE_DATA_SCOPE void pcre_stack_free(void *); -PCRE_DATA_SCOPE int pcre_callout(pcre_callout_block *); +PCRE_EXP_DECL void *pcre_malloc(size_t); +PCRE_EXP_DECL void pcre_free(void *); +PCRE_EXP_DECL void *pcre_stack_malloc(size_t); +PCRE_EXP_DECL void pcre_stack_free(void *); +PCRE_EXP_DECL int pcre_callout(pcre_callout_block *); #endif /* VPCOMPAT */ /* Exported PCRE functions */ -PCRE_DATA_SCOPE pcre *pcre_compile(const char *, int, const char **, int *, +PCRE_EXP_DECL pcre *pcre_compile(const char *, int, const char **, int *, const unsigned char *); -PCRE_DATA_SCOPE pcre *pcre_compile2(const char *, int, int *, const char **, +PCRE_EXP_DECL pcre *pcre_compile2(const char *, int, int *, const char **, int *, const unsigned char *); -PCRE_DATA_SCOPE int pcre_config(int, void *); -PCRE_DATA_SCOPE int pcre_copy_named_substring(const pcre *, const char *, +PCRE_EXP_DECL int pcre_config(int, void *); +PCRE_EXP_DECL int pcre_copy_named_substring(const pcre *, const char *, int *, int, const char *, char *, int); -PCRE_DATA_SCOPE int pcre_copy_substring(const char *, int *, int, int, char *, +PCRE_EXP_DECL int pcre_copy_substring(const char *, int *, int, int, char *, int); -PCRE_DATA_SCOPE int pcre_dfa_exec(const pcre *, const pcre_extra *, +PCRE_EXP_DECL int pcre_dfa_exec(const pcre *, const pcre_extra *, const char *, int, int, int, int *, int , int *, int); -PCRE_DATA_SCOPE int pcre_exec(const pcre *, const pcre_extra *, PCRE_SPTR, +PCRE_EXP_DECL int pcre_exec(const pcre *, const pcre_extra *, PCRE_SPTR, int, int, int, int *, int); -PCRE_DATA_SCOPE void pcre_free_substring(const char *); -PCRE_DATA_SCOPE void pcre_free_substring_list(const char **); -PCRE_DATA_SCOPE int pcre_fullinfo(const pcre *, const pcre_extra *, int, +PCRE_EXP_DECL void pcre_free_substring(const char *); +PCRE_EXP_DECL void pcre_free_substring_list(const char **); +PCRE_EXP_DECL int pcre_fullinfo(const pcre *, const pcre_extra *, int, void *); -PCRE_DATA_SCOPE int pcre_get_named_substring(const pcre *, const char *, +PCRE_EXP_DECL int pcre_get_named_substring(const pcre *, const char *, int *, int, const char *, const char **); -PCRE_DATA_SCOPE int pcre_get_stringnumber(const pcre *, const char *); -PCRE_DATA_SCOPE int pcre_get_stringtable_entries(const pcre *, const char *, +PCRE_EXP_DECL int pcre_get_stringnumber(const pcre *, const char *); +PCRE_EXP_DECL int pcre_get_stringtable_entries(const pcre *, const char *, char **, char **); -PCRE_DATA_SCOPE int pcre_get_substring(const char *, int *, int, int, +PCRE_EXP_DECL int pcre_get_substring(const char *, int *, int, int, const char **); -PCRE_DATA_SCOPE int pcre_get_substring_list(const char *, int *, int, +PCRE_EXP_DECL int pcre_get_substring_list(const char *, int *, int, const char ***); -PCRE_DATA_SCOPE int pcre_info(const pcre *, int *, int *); -PCRE_DATA_SCOPE const unsigned char *pcre_maketables(void); -PCRE_DATA_SCOPE int pcre_refcount(pcre *, int); -PCRE_DATA_SCOPE pcre_extra *pcre_study(const pcre *, int, const char **); -PCRE_DATA_SCOPE const char *pcre_version(void); +PCRE_EXP_DECL int pcre_info(const pcre *, int *, int *); +PCRE_EXP_DECL const unsigned char *pcre_maketables(void); +PCRE_EXP_DECL int pcre_refcount(pcre *, int); +PCRE_EXP_DECL pcre_extra *pcre_study(const pcre *, int, const char **); +PCRE_EXP_DECL const char *pcre_version(void); #ifdef __cplusplus } /* extern "C" */ diff --git a/src/src/pcre/pcre_chartables.c b/src/src/pcre/pcre_chartables.c new file mode 100644 index 000000000..acc852821 --- /dev/null +++ b/src/src/pcre/pcre_chartables.c @@ -0,0 +1,196 @@ +/* $Cambridge: exim/src/src/pcre/pcre_chartables.c,v 1.1 2007/06/26 11:16:54 ph10 Exp $ */ + +/************************************************* +* Perl-Compatible Regular Expressions * +*************************************************/ + +/* This file contains character tables that are used when no external tables +are passed to PCRE by the application that calls it. The tables are used only +for characters whose code values are less than 256. + +This is a default version of the tables that assumes ASCII encoding. A program +called dftables (which is distributed with PCRE) can be used to build +alternative versions of this file. This is necessary if you are running in an +EBCDIC environment, or if you want to default to a different encoding, for +example ISO-8859-1. When dftables is run, it creates these tables in the +current locale. If PCRE is configured with --enable-rebuild-chartables, this +happens automatically. + +The following #include is present because without it gcc 4.x may remove the +array definition from the final binary if PCRE is built into a static library +and dead code stripping is activated. This leads to link errors. Pulling in the +header ensures that the array gets flagged as "someone outside this compilation +unit might reference this" and so it will always be supplied to the linker. */ + +#include "pcre_internal.h" + +const unsigned char _pcre_default_tables[] = { + +/* This table is a lower casing table. */ + + 0, 1, 2, 3, 4, 5, 6, 7, + 8, 9, 10, 11, 12, 13, 14, 15, + 16, 17, 18, 19, 20, 21, 22, 23, + 24, 25, 26, 27, 28, 29, 30, 31, + 32, 33, 34, 35, 36, 37, 38, 39, + 40, 41, 42, 43, 44, 45, 46, 47, + 48, 49, 50, 51, 52, 53, 54, 55, + 56, 57, 58, 59, 60, 61, 62, 63, + 64, 97, 98, 99,100,101,102,103, + 104,105,106,107,108,109,110,111, + 112,113,114,115,116,117,118,119, + 120,121,122, 91, 92, 93, 94, 95, + 96, 97, 98, 99,100,101,102,103, + 104,105,106,107,108,109,110,111, + 112,113,114,115,116,117,118,119, + 120,121,122,123,124,125,126,127, + 128,129,130,131,132,133,134,135, + 136,137,138,139,140,141,142,143, + 144,145,146,147,148,149,150,151, + 152,153,154,155,156,157,158,159, + 160,161,162,163,164,165,166,167, + 168,169,170,171,172,173,174,175, + 176,177,178,179,180,181,182,183, + 184,185,186,187,188,189,190,191, + 192,193,194,195,196,197,198,199, + 200,201,202,203,204,205,206,207, + 208,209,210,211,212,213,214,215, + 216,217,218,219,220,221,222,223, + 224,225,226,227,228,229,230,231, + 232,233,234,235,236,237,238,239, + 240,241,242,243,244,245,246,247, + 248,249,250,251,252,253,254,255, + +/* This table is a case flipping table. */ + + 0, 1, 2, 3, 4, 5, 6, 7, + 8, 9, 10, 11, 12, 13, 14, 15, + 16, 17, 18, 19, 20, 21, 22, 23, + 24, 25, 26, 27, 28, 29, 30, 31, + 32, 33, 34, 35, 36, 37, 38, 39, + 40, 41, 42, 43, 44, 45, 46, 47, + 48, 49, 50, 51, 52, 53, 54, 55, + 56, 57, 58, 59, 60, 61, 62, 63, + 64, 97, 98, 99,100,101,102,103, + 104,105,106,107,108,109,110,111, + 112,113,114,115,116,117,118,119, + 120,121,122, 91, 92, 93, 94, 95, + 96, 65, 66, 67, 68, 69, 70, 71, + 72, 73, 74, 75, 76, 77, 78, 79, + 80, 81, 82, 83, 84, 85, 86, 87, + 88, 89, 90,123,124,125,126,127, + 128,129,130,131,132,133,134,135, + 136,137,138,139,140,141,142,143, + 144,145,146,147,148,149,150,151, + 152,153,154,155,156,157,158,159, + 160,161,162,163,164,165,166,167, + 168,169,170,171,172,173,174,175, + 176,177,178,179,180,181,182,183, + 184,185,186,187,188,189,190,191, + 192,193,194,195,196,197,198,199, + 200,201,202,203,204,205,206,207, + 208,209,210,211,212,213,214,215, + 216,217,218,219,220,221,222,223, + 224,225,226,227,228,229,230,231, + 232,233,234,235,236,237,238,239, + 240,241,242,243,244,245,246,247, + 248,249,250,251,252,253,254,255, + +/* This table contains bit maps for various character classes. Each map is 32 +bytes long and the bits run from the least significant end of each byte. The +classes that have their own maps are: space, xdigit, digit, upper, lower, word, +graph, print, punct, and cntrl. Other classes are built from combinations. */ + + 0x00,0x3e,0x00,0x00,0x01,0x00,0x00,0x00, + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, + + 0x00,0x00,0x00,0x00,0x00,0x00,0xff,0x03, + 0x7e,0x00,0x00,0x00,0x7e,0x00,0x00,0x00, + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, + + 0x00,0x00,0x00,0x00,0x00,0x00,0xff,0x03, + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, + + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, + 0xfe,0xff,0xff,0x07,0x00,0x00,0x00,0x00, + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, + + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, + 0x00,0x00,0x00,0x00,0xfe,0xff,0xff,0x07, + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, + + 0x00,0x00,0x00,0x00,0x00,0x00,0xff,0x03, + 0xfe,0xff,0xff,0x87,0xfe,0xff,0xff,0x07, + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, + + 0x00,0x00,0x00,0x00,0xfe,0xff,0xff,0xff, + 0xff,0xff,0xff,0xff,0xff,0xff,0xff,0x7f, + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, + + 0x00,0x00,0x00,0x00,0xff,0xff,0xff,0xff, + 0xff,0xff,0xff,0xff,0xff,0xff,0xff,0x7f, + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, + + 0x00,0x00,0x00,0x00,0xfe,0xff,0x00,0xfc, + 0x01,0x00,0x00,0xf8,0x01,0x00,0x00,0x78, + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, + + 0xff,0xff,0xff,0xff,0x00,0x00,0x00,0x00, + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x80, + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, + +/* This table identifies various classes of character by individual bits: + 0x01 white space character + 0x02 letter + 0x04 decimal digit + 0x08 hexadecimal digit + 0x10 alphanumeric or '_' + 0x80 regular expression metacharacter or binary zero +*/ + + 0x80,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 0- 7 */ + 0x00,0x01,0x01,0x00,0x01,0x01,0x00,0x00, /* 8- 15 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 16- 23 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 24- 31 */ + 0x01,0x00,0x00,0x00,0x80,0x00,0x00,0x00, /* - ' */ + 0x80,0x80,0x80,0x80,0x00,0x00,0x80,0x00, /* ( - / */ + 0x1c,0x1c,0x1c,0x1c,0x1c,0x1c,0x1c,0x1c, /* 0 - 7 */ + 0x1c,0x1c,0x00,0x00,0x00,0x00,0x00,0x80, /* 8 - ? */ + 0x00,0x1a,0x1a,0x1a,0x1a,0x1a,0x1a,0x12, /* @ - G */ + 0x12,0x12,0x12,0x12,0x12,0x12,0x12,0x12, /* H - O */ + 0x12,0x12,0x12,0x12,0x12,0x12,0x12,0x12, /* P - W */ + 0x12,0x12,0x12,0x80,0x80,0x00,0x80,0x10, /* X - _ */ + 0x00,0x1a,0x1a,0x1a,0x1a,0x1a,0x1a,0x12, /* ` - g */ + 0x12,0x12,0x12,0x12,0x12,0x12,0x12,0x12, /* h - o */ + 0x12,0x12,0x12,0x12,0x12,0x12,0x12,0x12, /* p - w */ + 0x12,0x12,0x12,0x80,0x80,0x00,0x00,0x00, /* x -127 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 128-135 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 136-143 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 144-151 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 152-159 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 160-167 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 168-175 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 176-183 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 184-191 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 192-199 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 200-207 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 208-215 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 216-223 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 224-231 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 232-239 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 240-247 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00};/* 248-255 */ + +/* End of pcre_chartables.c */ diff --git a/src/src/pcre/pcre_compile.c b/src/src/pcre/pcre_compile.c index f7a3ebbd2..4d179e3fe 100644 --- a/src/src/pcre/pcre_compile.c +++ b/src/src/pcre/pcre_compile.c @@ -1,4 +1,4 @@ -/* $Cambridge: exim/src/src/pcre/pcre_compile.c,v 1.4 2007/01/23 15:08:45 ph10 Exp $ */ +/* $Cambridge: exim/src/src/pcre/pcre_compile.c,v 1.5 2007/06/26 11:16:54 ph10 Exp $ */ /************************************************* * Perl-Compatible Regular Expressions * @@ -8,7 +8,7 @@ and semantics are as close as possible to those of the Perl 5 language. Written by Philip Hazel - Copyright (c) 1997-2006 University of Cambridge + Copyright (c) 1997-2007 University of Cambridge ----------------------------------------------------------------------------- Redistribution and use in source and binary forms, with or without @@ -60,6 +60,11 @@ used by pcretest. DEBUG is not defined when building a production library. */ #endif +/* Macro for setting individual bits in class bitmaps. */ + +#define SETBIT(a,b) a[b/8] |= (1 << (b%8)) + + /************************************************* * Code parameters and static tables * *************************************************/ @@ -84,21 +89,21 @@ are simple data values; negative values are for special things like \d and so on. Zero means further processing is needed (for things like \x), or the escape is invalid. */ -#if !EBCDIC /* This is the "normal" table for ASCII systems */ +#ifndef EBCDIC /* This is the "normal" table for ASCII systems */ static const short int escapes[] = { 0, 0, 0, 0, 0, 0, 0, 0, /* 0 - 7 */ 0, 0, ':', ';', '<', '=', '>', '?', /* 8 - ? */ '@', -ESC_A, -ESC_B, -ESC_C, -ESC_D, -ESC_E, 0, -ESC_G, /* @ - G */ - 0, 0, 0, 0, 0, 0, 0, 0, /* H - O */ --ESC_P, -ESC_Q, -ESC_R, -ESC_S, 0, 0, 0, -ESC_W, /* P - W */ +-ESC_H, 0, 0, -ESC_K, 0, 0, 0, 0, /* H - O */ +-ESC_P, -ESC_Q, -ESC_R, -ESC_S, 0, 0, -ESC_V, -ESC_W, /* P - W */ -ESC_X, 0, -ESC_Z, '[', '\\', ']', '^', '_', /* X - _ */ '`', 7, -ESC_b, 0, -ESC_d, ESC_e, ESC_f, 0, /* ` - g */ - 0, 0, 0, -ESC_k, 0, 0, ESC_n, 0, /* h - o */ --ESC_p, 0, ESC_r, -ESC_s, ESC_tee, 0, 0, -ESC_w, /* p - w */ +-ESC_h, 0, 0, -ESC_k, 0, 0, ESC_n, 0, /* h - o */ +-ESC_p, 0, ESC_r, -ESC_s, ESC_tee, 0, -ESC_v, -ESC_w, /* p - w */ 0, 0, -ESC_z /* x - z */ }; -#else /* This is the "abnormal" table for EBCDIC systems */ +#else /* This is the "abnormal" table for EBCDIC systems */ static const short int escapes[] = { /* 48 */ 0, 0, 0, '.', '<', '(', '+', '|', /* 50 */ '&', 0, 0, 0, 0, 0, 0, 0, @@ -108,18 +113,18 @@ static const short int escapes[] = { /* 70 */ 0, 0, 0, 0, 0, 0, 0, 0, /* 78 */ 0, '`', ':', '#', '@', '\'', '=', '"', /* 80 */ 0, 7, -ESC_b, 0, -ESC_d, ESC_e, ESC_f, 0, -/* 88 */ 0, 0, 0, '{', 0, 0, 0, 0, +/* 88 */-ESC_h, 0, 0, '{', 0, 0, 0, 0, /* 90 */ 0, 0, -ESC_k, 'l', 0, ESC_n, 0, -ESC_p, /* 98 */ 0, ESC_r, 0, '}', 0, 0, 0, 0, -/* A0 */ 0, '~', -ESC_s, ESC_tee, 0, 0, -ESC_w, 0, +/* A0 */ 0, '~', -ESC_s, ESC_tee, 0,-ESC_v, -ESC_w, 0, /* A8 */ 0,-ESC_z, 0, 0, 0, '[', 0, 0, /* B0 */ 0, 0, 0, 0, 0, 0, 0, 0, /* B8 */ 0, 0, 0, 0, 0, ']', '=', '-', /* C0 */ '{',-ESC_A, -ESC_B, -ESC_C, -ESC_D,-ESC_E, 0, -ESC_G, -/* C8 */ 0, 0, 0, 0, 0, 0, 0, 0, +/* C8 */-ESC_H, 0, 0, 0, 0, 0, 0, 0, /* D0 */ '}', 0, 0, 0, 0, 0, 0, -ESC_P, /* D8 */-ESC_Q,-ESC_R, 0, 0, 0, 0, 0, 0, -/* E0 */ '\\', 0, -ESC_S, 0, 0, 0, -ESC_W, -ESC_X, +/* E0 */ '\\', 0, -ESC_S, 0, 0,-ESC_V, -ESC_W, -ESC_X, /* E8 */ 0,-ESC_Z, 0, 0, 0, 0, 0, 0, /* F0 */ 0, 0, 0, 0, 0, 0, 0, 0, /* F8 */ 0, 0, 0, 0, 0, 0, 0, 0 @@ -210,7 +215,7 @@ static const char *error_texts[] = { "malformed number or name after (?(", "conditional group contains more than two branches", "assertion expected after (?(", - "(?R or (?digits must be followed by )", + "(?R or (?[+-]digits must be followed by )", /* 30 */ "unknown POSIX class name", "POSIX collating elements are not supported", @@ -244,7 +249,8 @@ static const char *error_texts[] = { /* 55 */ "repeating a DEFINE group is not allowed", "inconsistent NEWLINE options", - "\\g is not followed by an (optionally braced) non-zero number" + "\\g is not followed by a braced name or an optionally braced non-zero number", + "(?+ or (?- or (?(+ or (?(- must be followed by a non-zero number" }; @@ -264,7 +270,7 @@ For convenience, we use the same bit definitions as in chartables: Then we can use ctype_digit and ctype_xdigit in the code. */ -#if !EBCDIC /* This is the "normal" case, for ASCII systems */ +#ifndef EBCDIC /* This is the "normal" case, for ASCII systems */ static const unsigned char digitab[] = { 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 0- 7 */ @@ -300,7 +306,7 @@ static const unsigned char digitab[] = 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 240-247 */ 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00};/* 248-255 */ -#else /* This is the "abnormal" case, for EBCDIC systems */ +#else /* This is the "abnormal" case, for EBCDIC systems */ static const unsigned char digitab[] = { 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 0- 7 0 */ @@ -314,7 +320,7 @@ static const unsigned char digitab[] = 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* - 71 40 */ 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 72- | */ 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* & - 87 50 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 88- ¬ */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 88- 95 */ 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* - -103 60 */ 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 104- ? */ 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 112-119 70 */ @@ -348,7 +354,7 @@ static const unsigned char ebcdic_chartab[] = { /* chartable partial dup */ 0x01,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* - 71 */ 0x00,0x00,0x00,0x80,0x00,0x80,0x80,0x80, /* 72- | */ 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* & - 87 */ - 0x00,0x00,0x00,0x80,0x80,0x80,0x00,0x00, /* 88- ¬ */ + 0x00,0x00,0x00,0x80,0x80,0x80,0x00,0x00, /* 88- 95 */ 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* - -103 */ 0x00,0x00,0x00,0x00,0x00,0x10,0x00,0x80, /* 104- ? */ 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 112-119 */ @@ -375,8 +381,8 @@ static const unsigned char ebcdic_chartab[] = { /* chartable partial dup */ /* Definition to allow mutual recursion */ static BOOL - compile_regex(int, int, uschar **, const uschar **, int *, BOOL, int, int *, - int *, branch_chain *, compile_data *, int *); + compile_regex(int, int, uschar **, const uschar **, int *, BOOL, BOOL, int, + int *, int *, branch_chain *, compile_data *, int *); @@ -423,11 +429,11 @@ if (c == 0) *errorcodeptr = ERR1; a table. A non-zero result is something that can be returned immediately. Otherwise further processing may be required. */ -#if !EBCDIC /* ASCII coding */ +#ifndef EBCDIC /* ASCII coding */ else if (c < '0' || c > 'z') {} /* Not alphameric */ else if ((i = escapes[c - '0']) != 0) c = i; -#else /* EBCDIC coding */ +#else /* EBCDIC coding */ else if (c < 'a' || (ebcdic_chartab[c] & 0x0E) == 0) {} /* Not alphameric */ else if ((i = escapes[c - 0x48]) != 0) c = i; #endif @@ -454,11 +460,22 @@ else /* \g must be followed by a number, either plain or braced. If positive, it is an absolute backreference. If negative, it is a relative backreference. - This is a Perl 5.10 feature. */ + This is a Perl 5.10 feature. Perl 5.10 also supports \g{name} as a + reference to a named group. This is part of Perl's movement towards a + unified syntax for back references. As this is synonymous with \k{name}, we + fudge it up by pretending it really was \k. */ case 'g': if (ptr[1] == '{') { + const uschar *p; + for (p = ptr+2; *p != 0 && *p != '}'; p++) + if (*p != '-' && (digitab[*p] & ctype_digit) == 0) break; + if (*p != 0 && *p != '}') + { + c = -ESC_k; + break; + } braced = TRUE; ptr++; } @@ -564,10 +581,10 @@ else if (c == 0 && cc == '0') continue; /* Leading zeroes */ count++; -#if !EBCDIC /* ASCII coding */ +#ifndef EBCDIC /* ASCII coding */ if (cc >= 'a') cc -= 32; /* Convert to upper case */ c = (c << 4) + cc - ((cc < 'A')? '0' : ('A' - 10)); -#else /* EBCDIC coding */ +#else /* EBCDIC coding */ if (cc >= 'a' && cc <= 'z') cc += 64; /* Convert to upper case */ c = (c << 4) + cc - ((cc >= '0')? '0' : ('A' - 10)); #endif @@ -591,10 +608,10 @@ else { int cc; /* Some compilers don't like ++ */ cc = *(++ptr); /* in initializers */ -#if !EBCDIC /* ASCII coding */ +#ifndef EBCDIC /* ASCII coding */ if (cc >= 'a') cc -= 32; /* Convert to upper case */ c = c * 16 + cc - ((cc < 'A')? '0' : ('A' - 10)); -#else /* EBCDIC coding */ +#else /* EBCDIC coding */ if (cc <= 'z') cc += 64; /* Convert to upper case */ c = c * 16 + cc - ((cc >= '0')? '0' : ('A' - 10)); #endif @@ -613,10 +630,10 @@ else return 0; } -#if !EBCDIC /* ASCII coding */ +#ifndef EBCDIC /* ASCII coding */ if (c >= 'a' && c <= 'z') c -= 32; c ^= 0x40; -#else /* EBCDIC coding */ +#else /* EBCDIC coding */ if (c >= 'a' && c <= 'z') c += 64; c ^= 0xC0; #endif @@ -1248,6 +1265,7 @@ for (;;) else { code += _pcre_OP_lengths[c]; +#ifdef SUPPORT_UTF8 if (utf8) switch(c) { case OP_CHAR: @@ -1268,6 +1286,7 @@ for (;;) if (code[-1] >= 0xc0) code += _pcre_utf8_table4[code[-1] & 0x3f]; break; } +#endif } } } @@ -1311,6 +1330,7 @@ for (;;) else { code += _pcre_OP_lengths[c]; +#ifdef SUPPORT_UTF8 if (utf8) switch(c) { case OP_CHAR: @@ -1331,6 +1351,7 @@ for (;;) if (code[-1] >= 0xc0) code += _pcre_utf8_table4[code[-1] & 0x3f]; break; } +#endif } } } @@ -1368,6 +1389,18 @@ for (code = first_significant_code(code + _pcre_OP_lengths[*code], NULL, 0, TRUE c = *code; + /* Groups with zero repeats can of course be empty; skip them. */ + + if (c == OP_BRAZERO || c == OP_BRAMINZERO) + { + code += _pcre_OP_lengths[c]; + do code += GET(code, 1); while (*code == OP_ALT); + c = *code; + continue; + } + + /* For other groups, scan the branches. */ + if (c == OP_BRA || c == OP_CBRA || c == OP_ONCE) { BOOL empty_branch; @@ -1384,12 +1417,7 @@ for (code = first_significant_code(code + _pcre_OP_lengths[*code], NULL, 0, TRUE } while (*code == OP_ALT); if (!empty_branch) return FALSE; /* All branches are non-empty */ - - /* Move past the KET and fudge things so that the increment in the "for" - above has no effect. */ - - c = OP_END; - code += 1 + LINK_SIZE - _pcre_OP_lengths[c]; + c = *code; continue; } @@ -1923,6 +1951,50 @@ if (next >= 0) switch(op_code) case OP_NOT_WORDCHAR: return next <= 127 && (cd->ctypes[next] & ctype_word) != 0; + case OP_HSPACE: + case OP_NOT_HSPACE: + switch(next) + { + case 0x09: + case 0x20: + case 0xa0: + case 0x1680: + case 0x180e: + case 0x2000: + case 0x2001: + case 0x2002: + case 0x2003: + case 0x2004: + case 0x2005: + case 0x2006: + case 0x2007: + case 0x2008: + case 0x2009: + case 0x200A: + case 0x202f: + case 0x205f: + case 0x3000: + return op_code != OP_HSPACE; + default: + return op_code == OP_HSPACE; + } + + case OP_VSPACE: + case OP_NOT_VSPACE: + switch(next) + { + case 0x0a: + case 0x0b: + case 0x0c: + case 0x0d: + case 0x85: + case 0x2028: + case 0x2029: + return op_code != OP_VSPACE; + default: + return op_code == OP_VSPACE; + } + default: return FALSE; } @@ -1957,12 +2029,57 @@ switch(op_code) case ESC_W: return item <= 127 && (cd->ctypes[item] & ctype_word) != 0; + case ESC_h: + case ESC_H: + switch(item) + { + case 0x09: + case 0x20: + case 0xa0: + case 0x1680: + case 0x180e: + case 0x2000: + case 0x2001: + case 0x2002: + case 0x2003: + case 0x2004: + case 0x2005: + case 0x2006: + case 0x2007: + case 0x2008: + case 0x2009: + case 0x200A: + case 0x202f: + case 0x205f: + case 0x3000: + return -next != ESC_h; + default: + return -next == ESC_h; + } + + case ESC_v: + case ESC_V: + switch(item) + { + case 0x0a: + case 0x0b: + case 0x0c: + case 0x0d: + case 0x85: + case 0x2028: + case 0x2029: + return -next != ESC_v; + default: + return -next == ESC_v; + } + default: return FALSE; } case OP_DIGIT: - return next == -ESC_D || next == -ESC_s || next == -ESC_W; + return next == -ESC_D || next == -ESC_s || next == -ESC_W || + next == -ESC_h || next == -ESC_v; case OP_NOT_DIGIT: return next == -ESC_d; @@ -1971,10 +2088,23 @@ switch(op_code) return next == -ESC_S || next == -ESC_d || next == -ESC_w; case OP_NOT_WHITESPACE: - return next == -ESC_s; + return next == -ESC_s || next == -ESC_h || next == -ESC_v; + + case OP_HSPACE: + return next == -ESC_S || next == -ESC_H || next == -ESC_d || next == -ESC_w; + + case OP_NOT_HSPACE: + return next == -ESC_h; + + /* Can't have \S in here because VT matches \S (Perl anomaly) */ + case OP_VSPACE: + return next == -ESC_V || next == -ESC_d || next == -ESC_w; + + case OP_NOT_VSPACE: + return next == -ESC_v; case OP_WORDCHAR: - return next == -ESC_W || next == -ESC_s; + return next == -ESC_W || next == -ESC_s || next == -ESC_h || next == -ESC_v; case OP_NOT_WORDCHAR: return next == -ESC_w || next == -ESC_d; @@ -2089,10 +2219,12 @@ for (;; ptr++) BOOL possessive_quantifier; BOOL is_quantifier; BOOL is_recurse; + BOOL reset_bracount; int class_charcount; int class_lastchar; int newoptions; int recno; + int refsign; int skipbytes; int subreqbyte; int subfirstbyte; @@ -2517,6 +2649,133 @@ for (;; ptr++) else if (c == -ESC_d || c == -ESC_D || c == -ESC_w || c == -ESC_W || c == -ESC_s || c == -ESC_S) continue; + /* We need to deal with \H, \h, \V, and \v in both phases because + they use extra memory. */ + + if (-c == ESC_h) + { + SETBIT(classbits, 0x09); /* VT */ + SETBIT(classbits, 0x20); /* SPACE */ + SETBIT(classbits, 0xa0); /* NSBP */ +#ifdef SUPPORT_UTF8 + if (utf8) + { + class_utf8 = TRUE; + *class_utf8data++ = XCL_SINGLE; + class_utf8data += _pcre_ord2utf8(0x1680, class_utf8data); + *class_utf8data++ = XCL_SINGLE; + class_utf8data += _pcre_ord2utf8(0x180e, class_utf8data); + *class_utf8data++ = XCL_RANGE; + class_utf8data += _pcre_ord2utf8(0x2000, class_utf8data); + class_utf8data += _pcre_ord2utf8(0x200A, class_utf8data); + *class_utf8data++ = XCL_SINGLE; + class_utf8data += _pcre_ord2utf8(0x202f, class_utf8data); + *class_utf8data++ = XCL_SINGLE; + class_utf8data += _pcre_ord2utf8(0x205f, class_utf8data); + *class_utf8data++ = XCL_SINGLE; + class_utf8data += _pcre_ord2utf8(0x3000, class_utf8data); + } +#endif + continue; + } + + if (-c == ESC_H) + { + for (c = 0; c < 32; c++) + { + int x = 0xff; + switch (c) + { + case 0x09/8: x ^= 1 << (0x09%8); break; + case 0x20/8: x ^= 1 << (0x20%8); break; + case 0xa0/8: x ^= 1 << (0xa0%8); break; + default: break; + } + classbits[c] |= x; + } + +#ifdef SUPPORT_UTF8 + if (utf8) + { + class_utf8 = TRUE; + *class_utf8data++ = XCL_RANGE; + class_utf8data += _pcre_ord2utf8(0x0100, class_utf8data); + class_utf8data += _pcre_ord2utf8(0x167f, class_utf8data); + *class_utf8data++ = XCL_RANGE; + class_utf8data += _pcre_ord2utf8(0x1681, class_utf8data); + class_utf8data += _pcre_ord2utf8(0x180d, class_utf8data); + *class_utf8data++ = XCL_RANGE; + class_utf8data += _pcre_ord2utf8(0x180f, class_utf8data); + class_utf8data += _pcre_ord2utf8(0x1fff, class_utf8data); + *class_utf8data++ = XCL_RANGE; + class_utf8data += _pcre_ord2utf8(0x200B, class_utf8data); + class_utf8data += _pcre_ord2utf8(0x202e, class_utf8data); + *class_utf8data++ = XCL_RANGE; + class_utf8data += _pcre_ord2utf8(0x2030, class_utf8data); + class_utf8data += _pcre_ord2utf8(0x205e, class_utf8data); + *class_utf8data++ = XCL_RANGE; + class_utf8data += _pcre_ord2utf8(0x2060, class_utf8data); + class_utf8data += _pcre_ord2utf8(0x2fff, class_utf8data); + *class_utf8data++ = XCL_RANGE; + class_utf8data += _pcre_ord2utf8(0x3001, class_utf8data); + class_utf8data += _pcre_ord2utf8(0x7fffffff, class_utf8data); + } +#endif + continue; + } + + if (-c == ESC_v) + { + SETBIT(classbits, 0x0a); /* LF */ + SETBIT(classbits, 0x0b); /* VT */ + SETBIT(classbits, 0x0c); /* FF */ + SETBIT(classbits, 0x0d); /* CR */ + SETBIT(classbits, 0x85); /* NEL */ +#ifdef SUPPORT_UTF8 + if (utf8) + { + class_utf8 = TRUE; + *class_utf8data++ = XCL_RANGE; + class_utf8data += _pcre_ord2utf8(0x2028, class_utf8data); + class_utf8data += _pcre_ord2utf8(0x2029, class_utf8data); + } +#endif + continue; + } + + if (-c == ESC_V) + { + for (c = 0; c < 32; c++) + { + int x = 0xff; + switch (c) + { + case 0x0a/8: x ^= 1 << (0x0a%8); + x ^= 1 << (0x0b%8); + x ^= 1 << (0x0c%8); + x ^= 1 << (0x0d%8); + break; + case 0x85/8: x ^= 1 << (0x85%8); break; + default: break; + } + classbits[c] |= x; + } + +#ifdef SUPPORT_UTF8 + if (utf8) + { + class_utf8 = TRUE; + *class_utf8data++ = XCL_RANGE; + class_utf8data += _pcre_ord2utf8(0x0100, class_utf8data); + class_utf8data += _pcre_ord2utf8(0x2027, class_utf8data); + *class_utf8data++ = XCL_RANGE; + class_utf8data += _pcre_ord2utf8(0x2029, class_utf8data); + class_utf8data += _pcre_ord2utf8(0x7fffffff, class_utf8data); + } +#endif + continue; + } + /* We need to deal with \P and \p in both phases. */ #ifdef SUPPORT_UCP @@ -2657,14 +2916,18 @@ for (;; ptr++) unsigned int origd = d; while (get_othercase_range(&cc, origd, &occ, &ocd)) { - if (occ >= c && ocd <= d) continue; /* Skip embedded ranges */ + if (occ >= (unsigned int)c && + ocd <= (unsigned int)d) + continue; /* Skip embedded ranges */ - if (occ < c && ocd >= c - 1) /* Extend the basic range */ + if (occ < (unsigned int)c && + ocd >= (unsigned int)c - 1) /* Extend the basic range */ { /* if there is overlap, */ c = occ; /* noting that if occ < c */ continue; /* we can't have ocd > d */ } /* because a subrange is */ - if (ocd > d && occ <= d + 1) /* always shorter than */ + if (ocd > (unsigned int)d && + occ <= (unsigned int)d + 1) /* always shorter than */ { /* the basic range. */ d = ocd; continue; @@ -3562,6 +3825,7 @@ for (;; ptr++) skipbytes = 0; bravalue = OP_CBRA; save_hwm = cd->hwm; + reset_bracount = FALSE; if (*(++ptr) == '?') { @@ -3583,6 +3847,11 @@ for (;; ptr++) continue; + /* ------------------------------------------------------------ */ + case '|': /* Reset capture count for each branch */ + reset_bracount = TRUE; + /* Fall through */ + /* ------------------------------------------------------------ */ case ':': /* Non-capturing bracket */ bravalue = OP_BRA; @@ -3619,6 +3888,7 @@ for (;; ptr++) code[1+LINK_SIZE] = OP_CREF; skipbytes = 3; + refsign = -1; /* Check for a test for recursion in a named group. */ @@ -3642,7 +3912,11 @@ for (;; ptr++) terminator = '\''; ptr++; } - else terminator = 0; + else + { + terminator = 0; + if (ptr[1] == '-' || ptr[1] == '+') refsign = *(++ptr); + } /* We now expect to read a name; any thing else is an error */ @@ -3678,7 +3952,32 @@ for (;; ptr++) if (lengthptr != NULL) break; /* In the real compile we do the work of looking for the actual - reference. */ + reference. If the string started with "+" or "-" we require the rest to + be digits, in which case recno will be set. */ + + if (refsign > 0) + { + if (recno <= 0) + { + *errorcodeptr = ERR58; + goto FAILED; + } + if (refsign == '-') + { + recno = cd->bracount - recno + 1; + if (recno <= 0) + { + *errorcodeptr = ERR15; + goto FAILED; + } + } + else recno += cd->bracount; + PUT2(code, 2+LINK_SIZE, recno); + break; + } + + /* Otherwise (did not start with "+" or "-"), start by looking for the + name. */ slot = cd->name_table; for (i = 0; i < cd->names_found; i++) @@ -3997,19 +4296,54 @@ for (;; ptr++) /* ------------------------------------------------------------ */ + case '-': case '+': case '0': case '1': case '2': case '3': case '4': /* Recursion or */ case '5': case '6': case '7': case '8': case '9': /* subroutine */ { const uschar *called; + + if ((refsign = *ptr) == '+') ptr++; + else if (refsign == '-') + { + if ((digitab[ptr[1]] & ctype_digit) == 0) + goto OTHER_CHAR_AFTER_QUERY; + ptr++; + } + recno = 0; while((digitab[*ptr] & ctype_digit) != 0) recno = recno * 10 + *ptr++ - '0'; + if (*ptr != ')') { *errorcodeptr = ERR29; goto FAILED; } + if (refsign == '-') + { + if (recno == 0) + { + *errorcodeptr = ERR58; + goto FAILED; + } + recno = cd->bracount - recno + 1; + if (recno <= 0) + { + *errorcodeptr = ERR15; + goto FAILED; + } + } + else if (refsign == '+') + { + if (recno == 0) + { + *errorcodeptr = ERR58; + goto FAILED; + } + recno += cd->bracount; + } + /* Come here from code above that handles a named recursion */ HANDLE_RECURSION: @@ -4082,6 +4416,7 @@ for (;; ptr++) /* ------------------------------------------------------------ */ default: /* Other characters: check option setting */ + OTHER_CHAR_AFTER_QUERY: set = unset = 0; optset = &set; @@ -4216,6 +4551,7 @@ for (;; ptr++) errorcodeptr, /* Where to put an error message */ (bravalue == OP_ASSERTBACK || bravalue == OP_ASSERTBACK_NOT), /* TRUE if back assert */ + reset_bracount, /* True if (?| group */ skipbytes, /* Skip over bracket number */ &subfirstbyte, /* For possible first char */ &subreqbyte, /* For possible last char */ @@ -4232,9 +4568,11 @@ for (;; ptr++) is on the bracket. */ /* If this is a conditional bracket, check that there are no more than - two branches in the group, or just one if it's a DEFINE group. */ + two branches in the group, or just one if it's a DEFINE group. We do this + in the real compile phase, not in the pre-pass, where the whole group may + not be available. */ - if (bravalue == OP_COND) + if (bravalue == OP_COND && lengthptr == NULL) { uschar *tc = code; int condcount = 0; @@ -4394,12 +4732,13 @@ for (;; ptr++) zerofirstbyte = firstbyte; zeroreqbyte = reqbyte; - /* \k or \k'name' is a back reference by name (Perl syntax) */ + /* \k or \k'name' is a back reference by name (Perl syntax). + We also support \k{name} (.NET syntax) */ - if (-c == ESC_k && (ptr[1] == '<' || ptr[1] == '\'')) + if (-c == ESC_k && (ptr[1] == '<' || ptr[1] == '\'' || ptr[1] == '{')) { is_recurse = FALSE; - terminator = (*(++ptr) == '<')? '>' : '\''; + terminator = (*(++ptr) == '<')? '>' : (*ptr == '\'')? '\'' : '}'; goto NAMED_REF_OR_RECURSE; } @@ -4565,13 +4904,14 @@ This function is used during the pre-compile phase when we are trying to find out the amount of memory needed, as well as during the real compile phase. The value of lengthptr distinguishes the two phases. -Argument: +Arguments: options option bits, including any changes for this subpattern oldims previous settings of ims option bits codeptr -> the address of the current code pointer ptrptr -> the address of the current pattern pointer errorcodeptr -> pointer to error code variable lookbehind TRUE if this is a lookbehind assertion + reset_bracount TRUE to reset the count for each branch skipbytes skip this many bytes at start (for brackets and OP_COND) firstbyteptr place to put the first required character, or a negative number reqbyteptr place to put the last required character, or a negative number @@ -4585,8 +4925,9 @@ Returns: TRUE on success static BOOL compile_regex(int options, int oldims, uschar **codeptr, const uschar **ptrptr, - int *errorcodeptr, BOOL lookbehind, int skipbytes, int *firstbyteptr, - int *reqbyteptr, branch_chain *bcptr, compile_data *cd, int *lengthptr) + int *errorcodeptr, BOOL lookbehind, BOOL reset_bracount, int skipbytes, + int *firstbyteptr, int *reqbyteptr, branch_chain *bcptr, compile_data *cd, + int *lengthptr) { const uschar *ptr = *ptrptr; uschar *code = *codeptr; @@ -4596,6 +4937,8 @@ uschar *reverse_count = NULL; int firstbyte, reqbyte; int branchfirstbyte, branchreqbyte; int length; +int orig_bracount; +int max_bracount; branch_chain bc; bc.outer = bcptr; @@ -4624,8 +4967,14 @@ code += 1 + LINK_SIZE + skipbytes; /* Loop for each alternative branch */ +orig_bracount = max_bracount = cd->bracount; for (;;) { + /* For a (?| group, reset the capturing bracket count so that each branch + uses the same numbers. */ + + if (reset_bracount) cd->bracount = orig_bracount; + /* Handle a change of ims options at the start of the branch */ if ((options & PCRE_IMS) != oldims) @@ -4655,6 +5004,11 @@ for (;;) return FALSE; } + /* Keep the highest bracket count in case (?| was used and some branch + has fewer than the rest. */ + + if (cd->bracount > max_bracount) max_bracount = cd->bracount; + /* In the real compile phase, there is some post-processing to be done. */ if (lengthptr == NULL) @@ -4718,26 +5072,29 @@ for (;;) } } - /* Reached end of expression, either ')' or end of pattern. Go back through - the alternative branches and reverse the chain of offsets, with the field in - the BRA item now becoming an offset to the first alternative. If there are - no alternatives, it points to the end of the group. The length in the - terminating ket is always the length of the whole bracketed item. If any of - the ims options were changed inside the group, compile a resetting op-code - following, except at the very end of the pattern. Return leaving the pointer - at the terminating char. */ + /* Reached end of expression, either ')' or end of pattern. In the real + compile phase, go back through the alternative branches and reverse the chain + of offsets, with the field in the BRA item now becoming an offset to the + first alternative. If there are no alternatives, it points to the end of the + group. The length in the terminating ket is always the length of the whole + bracketed item. If any of the ims options were changed inside the group, + compile a resetting op-code following, except at the very end of the pattern. + Return leaving the pointer at the terminating char. */ if (*ptr != '|') { - int branch_length = code - last_branch; - do + if (lengthptr == NULL) { - int prev_length = GET(last_branch, 1); - PUT(last_branch, 1, branch_length); - branch_length = prev_length; - last_branch -= branch_length; + int branch_length = code - last_branch; + do + { + int prev_length = GET(last_branch, 1); + PUT(last_branch, 1, branch_length); + branch_length = prev_length; + last_branch -= branch_length; + } + while (branch_length > 0); } - while (branch_length > 0); /* Fill in the ket */ @@ -4754,6 +5111,10 @@ for (;;) length += 2; } + /* Retain the highest bracket number, in case resetting was used. */ + + cd->bracount = max_bracount; + /* Set values to pass back */ *codeptr = code; @@ -4764,17 +5125,29 @@ for (;;) return TRUE; } - /* Another branch follows; insert an "or" node. Its length field points back + /* Another branch follows. In the pre-compile phase, we can move the code + pointer back to where it was for the start of the first branch. (That is, + pretend that each branch is the only one.) + + In the real compile phase, insert an ALT node. Its length field points back to the previous branch while the bracket remains open. At the end the chain is reversed. It's done like this so that the start of the bracket has a zero offset until it is closed, making it possible to detect recursion. */ - *code = OP_ALT; - PUT(code, 1, code - last_branch); - bc.current = last_branch = code; - code += 1 + LINK_SIZE; + if (lengthptr != NULL) + { + code = *codeptr + 1 + LINK_SIZE + skipbytes; + length += 1 + LINK_SIZE; + } + else + { + *code = OP_ALT; + PUT(code, 1, code - last_branch); + bc.current = last_branch = code; + code += 1 + LINK_SIZE; + } + ptr++; - length += 1 + LINK_SIZE; } /* Control never reaches here */ } @@ -5041,7 +5414,7 @@ Returns: pointer to compiled data block, or NULL on error, with errorptr and erroroffset set */ -PCRE_DATA_SCOPE pcre * +PCRE_EXP_DEFN pcre * pcre_compile(const char *pattern, int options, const char **errorptr, int *erroroffset, const unsigned char *tables) { @@ -5049,7 +5422,7 @@ return pcre_compile2(pattern, options, NULL, errorptr, erroroffset, tables); } -PCRE_DATA_SCOPE pcre * +PCRE_EXP_DEFN pcre * pcre_compile2(const char *pattern, int options, int *errorcodeptr, const char **errorptr, int *erroroffset, const unsigned char *tables) { @@ -5098,7 +5471,7 @@ if (errorcodeptr != NULL) *errorcodeptr = ERR0; if (erroroffset == NULL) { errorcode = ERR16; - goto PCRE_EARLY_ERROR_RETURN; + goto PCRE_EARLY_ERROR_RETURN2; } *erroroffset = 0; @@ -5111,7 +5484,7 @@ if (utf8 && (options & PCRE_NO_UTF8_CHECK) == 0 && (*erroroffset = _pcre_valid_utf8((uschar *)pattern, -1)) >= 0) { errorcode = ERR44; - goto PCRE_UTF8_ERROR_RETURN; + goto PCRE_EARLY_ERROR_RETURN2; } #else if ((options & PCRE_UTF8) != 0) @@ -5136,7 +5509,8 @@ cd->cbits = tables + cbits_offset; cd->ctypes = tables + ctypes_offset; /* Handle different types of newline. The three bits give seven cases. The -current code allows for fixed one- or two-byte sequences, plus "any". */ +current code allows for fixed one- or two-byte sequences, plus "any" and +"anycrlf". */ switch (options & (PCRE_NEWLINE_CRLF | PCRE_NEWLINE_ANY)) { @@ -5146,10 +5520,15 @@ switch (options & (PCRE_NEWLINE_CRLF | PCRE_NEWLINE_ANY)) case PCRE_NEWLINE_CR+ PCRE_NEWLINE_LF: newline = ('\r' << 8) | '\n'; break; case PCRE_NEWLINE_ANY: newline = -1; break; + case PCRE_NEWLINE_ANYCRLF: newline = -2; break; default: errorcode = ERR56; goto PCRE_EARLY_ERROR_RETURN; } -if (newline < 0) +if (newline == -2) + { + cd->nltype = NLTYPE_ANYCRLF; + } +else if (newline < 0) { cd->nltype = NLTYPE_ANY; } @@ -5210,7 +5589,8 @@ outside can help speed up starting point checks. */ code = cworkspace; *code = OP_BRA; (void)compile_regex(cd->external_options, cd->external_options & PCRE_IMS, - &code, &ptr, &errorcode, FALSE, 0, &firstbyte, &reqbyte, NULL, cd, &length); + &code, &ptr, &errorcode, FALSE, FALSE, 0, &firstbyte, &reqbyte, NULL, cd, + &length); if (errorcode != 0) goto PCRE_EARLY_ERROR_RETURN; DPRINTF(("end pre-compile: length=%d workspace=%d\n", length, @@ -5278,7 +5658,7 @@ ptr = (const uschar *)pattern; code = (uschar *)codestart; *code = OP_BRA; (void)compile_regex(re->options, re->options & PCRE_IMS, &code, &ptr, - &errorcode, FALSE, 0, &firstbyte, &reqbyte, NULL, cd, NULL); + &errorcode, FALSE, FALSE, 0, &firstbyte, &reqbyte, NULL, cd, NULL); re->top_bracket = cd->bracount; re->top_backref = cd->top_backref; @@ -5323,9 +5703,7 @@ if (errorcode != 0) (pcre_free)(re); PCRE_EARLY_ERROR_RETURN: *erroroffset = ptr - (const uschar *)pattern; -#ifdef SUPPORT_UTF8 - PCRE_UTF8_ERROR_RETURN: -#endif + PCRE_EARLY_ERROR_RETURN2: *errorptr = error_texts[errorcode]; if (errorcodeptr != NULL) *errorcodeptr = errorcode; return NULL; @@ -5415,7 +5793,7 @@ if ((re->options & PCRE_REQCHSET) != 0) else printf("Req char = \\x%02x%s\n", ch, caseless); } -pcre_printint(re, stdout); +pcre_printint(re, stdout, TRUE); /* This check is done here in the debugging case so that the code that was compiled can be seen. */ diff --git a/src/src/pcre/pcre_config.c b/src/src/pcre/pcre_config.c index 582cf4a81..ff8cdf89a 100644 --- a/src/src/pcre/pcre_config.c +++ b/src/src/pcre/pcre_config.c @@ -1,4 +1,4 @@ -/* $Cambridge: exim/src/src/pcre/pcre_config.c,v 1.4 2007/01/23 15:08:45 ph10 Exp $ */ +/* $Cambridge: exim/src/src/pcre/pcre_config.c,v 1.5 2007/06/26 11:16:54 ph10 Exp $ */ /************************************************* * Perl-Compatible Regular Expressions * @@ -8,7 +8,7 @@ and semantics are as close as possible to those of the Perl 5 language. Written by Philip Hazel - Copyright (c) 1997-2006 University of Cambridge + Copyright (c) 1997-2007 University of Cambridge ----------------------------------------------------------------------------- Redistribution and use in source and binary forms, with or without @@ -60,7 +60,7 @@ Arguments: Returns: 0 if data returned, negative on error */ -PCRE_DATA_SCOPE int +PCRE_EXP_DEFN int pcre_config(int what, void *where) { switch (what) diff --git a/src/src/pcre/pcre_exec.c b/src/src/pcre/pcre_exec.c index 27cd52fec..a27835d74 100644 --- a/src/src/pcre/pcre_exec.c +++ b/src/src/pcre/pcre_exec.c @@ -1,4 +1,4 @@ -/* $Cambridge: exim/src/src/pcre/pcre_exec.c,v 1.4 2007/01/23 15:08:45 ph10 Exp $ */ +/* $Cambridge: exim/src/src/pcre/pcre_exec.c,v 1.5 2007/06/26 11:16:54 ph10 Exp $ */ /************************************************* * Perl-Compatible Regular Expressions * @@ -8,7 +8,7 @@ and semantics are as close as possible to those of the Perl 5 language. Written by Philip Hazel - Copyright (c) 1997-2006 University of Cambridge + Copyright (c) 1997-2007 University of Cambridge ----------------------------------------------------------------------------- Redistribution and use in source and binary forms, with or without @@ -50,6 +50,11 @@ possible. There are also some static supporting functions. */ #include "pcre_internal.h" +/* Undefine some potentially clashing cpp symbols */ + +#undef min +#undef max + /* The chain of eptrblocks for tail recursions uses memory in stack workspace, obtained at top level, the size of which is defined by EPTR_WORK_SIZE. */ @@ -185,20 +190,45 @@ calls by keeping local variables that need to be preserved in blocks of memory obtained from malloc() instead instead of on the stack. Macros are used to achieve this so that the actual code doesn't look very different to what it always used to. + +The original heap-recursive code used longjmp(). However, it seems that this +can be very slow on some operating systems. Following a suggestion from Stan +Switzer, the use of longjmp() has been abolished, at the cost of having to +provide a unique number for each call to RMATCH. There is no way of generating +a sequence of numbers at compile time in C. I have given them names, to make +them stand out more clearly. + +Crude tests on x86 Linux show a small speedup of around 5-8%. However, on +FreeBSD, avoiding longjmp() more than halves the time taken to run the standard +tests. Furthermore, not using longjmp() means that local dynamic variables +don't have indeterminate values; this has meant that the frame size can be +reduced because the result can be "passed back" by straight setting of the +variable instead of being passed in the frame. **************************************************************************** ***************************************************************************/ +/* Numbers for RMATCH calls */ + +enum { RM1=1, RM2, RM3, RM4, RM5, RM6, RM7, RM8, RM9, RM10, + RM11, RM12, RM13, RM14, RM15, RM16, RM17, RM18, RM19, RM20, + RM21, RM22, RM23, RM24, RM25, RM26, RM27, RM28, RM29, RM30, + RM31, RM32, RM33, RM34, RM35, RM36, RM37, RM38, RM39, RM40, + RM41, RM42, RM43, RM44, RM45, RM46, RM47 }; + + /* These versions of the macros use the stack, as normal. There are debugging -versions and production versions. */ +versions and production versions. Note that the "rw" argument of RMATCH isn't +actuall used in this definition. */ #ifndef NO_RECURSE #define REGISTER register + #ifdef DEBUG -#define RMATCH(rx,ra,rb,rc,rd,re,rf,rg) \ +#define RMATCH(ra,rb,rc,rd,re,rf,rg,rw) \ { \ printf("match() called in line %d\n", __LINE__); \ - rx = match(ra,rb,rc,rd,re,rf,rg,rdepth+1); \ + rrc = match(ra,rb,mstart,rc,rd,re,rf,rg,rdepth+1); \ printf("to line %d\n", __LINE__); \ } #define RRETURN(ra) \ @@ -207,43 +237,38 @@ versions and production versions. */ return ra; \ } #else -#define RMATCH(rx,ra,rb,rc,rd,re,rf,rg) \ - rx = match(ra,rb,rc,rd,re,rf,rg,rdepth+1) +#define RMATCH(ra,rb,rc,rd,re,rf,rg,rw) \ + rrc = match(ra,rb,mstart,rc,rd,re,rf,rg,rdepth+1) #define RRETURN(ra) return ra #endif #else -/* These versions of the macros manage a private stack on the heap. Note -that the rd argument of RMATCH isn't actually used. It's the md argument of -match(), which never changes. */ +/* These versions of the macros manage a private stack on the heap. Note that +the "rd" argument of RMATCH isn't actually used in this definition. It's the md +argument of match(), which never changes. */ #define REGISTER -#define RMATCH(rx,ra,rb,rc,rd,re,rf,rg)\ +#define RMATCH(ra,rb,rc,rd,re,rf,rg,rw)\ {\ heapframe *newframe = (pcre_stack_malloc)(sizeof(heapframe));\ - if (setjmp(frame->Xwhere) == 0)\ - {\ - newframe->Xeptr = ra;\ - newframe->Xecode = rb;\ - newframe->Xoffset_top = rc;\ - newframe->Xims = re;\ - newframe->Xeptrb = rf;\ - newframe->Xflags = rg;\ - newframe->Xrdepth = frame->Xrdepth + 1;\ - newframe->Xprevframe = frame;\ - frame = newframe;\ - DPRINTF(("restarting from line %d\n", __LINE__));\ - goto HEAP_RECURSE;\ - }\ - else\ - {\ - DPRINTF(("longjumped back to line %d\n", __LINE__));\ - frame = md->thisframe;\ - rx = frame->Xresult;\ - }\ + frame->Xwhere = rw; \ + newframe->Xeptr = ra;\ + newframe->Xecode = rb;\ + newframe->Xmstart = mstart;\ + newframe->Xoffset_top = rc;\ + newframe->Xims = re;\ + newframe->Xeptrb = rf;\ + newframe->Xflags = rg;\ + newframe->Xrdepth = frame->Xrdepth + 1;\ + newframe->Xprevframe = frame;\ + frame = newframe;\ + DPRINTF(("restarting from line %d\n", __LINE__));\ + goto HEAP_RECURSE;\ + L_##rw:\ + DPRINTF(("jumped back to line %d\n", __LINE__));\ } #define RRETURN(ra)\ @@ -253,9 +278,8 @@ match(), which never changes. */ (pcre_stack_free)(newframe);\ if (frame != NULL)\ {\ - frame->Xresult = ra;\ - md->thisframe = frame;\ - longjmp(frame->Xwhere, 1);\ + rrc = ra;\ + goto HEAP_RETURN;\ }\ return ra;\ } @@ -270,6 +294,7 @@ typedef struct heapframe { const uschar *Xeptr; const uschar *Xecode; + const uschar *Xmstart; int Xoffset_top; long int Xims; eptrblock *Xeptrb; @@ -301,6 +326,8 @@ typedef struct heapframe { int Xprop_category; int Xprop_chartype; int Xprop_script; + int Xoclength; + uschar Xocchars[8]; #endif int Xctype; @@ -318,10 +345,9 @@ typedef struct heapframe { eptrblock Xnewptrb; - /* Place to pass back result, and where to jump back to */ + /* Where to jump back to */ - int Xresult; - jmp_buf Xwhere; + int Xwhere; } heapframe; @@ -349,6 +375,8 @@ made performance worse. Arguments: eptr pointer to current character in subject ecode pointer to current position in compiled code + mstart pointer to the current match start position (can be modified + by encountering \K) offset_top current top pointer md pointer to "static" info for the match ims current /i, /m, and /s options @@ -368,7 +396,7 @@ Returns: MATCH_MATCH if matched ) these values are >= 0 */ static int -match(REGISTER USPTR eptr, REGISTER const uschar *ecode, +match(REGISTER USPTR eptr, REGISTER const uschar *ecode, const uschar *mstart, int offset_top, match_data *md, unsigned long int ims, eptrblock *eptrb, int flags, unsigned int rdepth) { @@ -396,6 +424,7 @@ frame->Xprevframe = NULL; /* Marks the top level */ frame->Xeptr = eptr; frame->Xecode = ecode; +frame->Xmstart = mstart; frame->Xoffset_top = offset_top; frame->Xims = ims; frame->Xeptrb = eptrb; @@ -410,6 +439,7 @@ HEAP_RECURSE: #define eptr frame->Xeptr #define ecode frame->Xecode +#define mstart frame->Xmstart #define offset_top frame->Xoffset_top #define ims frame->Xims #define eptrb frame->Xeptrb @@ -443,6 +473,8 @@ HEAP_RECURSE: #define prop_category frame->Xprop_category #define prop_chartype frame->Xprop_chartype #define prop_script frame->Xprop_script +#define oclength frame->Xoclength +#define occhars frame->Xocchars #endif #define ctype frame->Xctype @@ -496,6 +528,8 @@ int prop_fail_result; int prop_category; int prop_chartype; int prop_script; +int oclength; +uschar occhars[8]; #endif int ctype; @@ -536,6 +570,12 @@ defined). However, RMATCH isn't like a function call because it's quite a complicated macro. It has to be used in one particular way. This shouldn't, however, impact performance when true recursion is being used. */ +#ifdef SUPPORT_UTF8 +utf8 = md->utf8; /* Local copy of the flag */ +#else +utf8 = FALSE; +#endif + /* First check that we haven't called match() too many times, or that we haven't exceeded the recursive call limit. */ @@ -544,12 +584,6 @@ if (rdepth >= md->match_limit_recursion) RRETURN(PCRE_ERROR_RECURSIONLIMIT); original_ims = ims; /* Save for resetting on ')' */ -#ifdef SUPPORT_UTF8 -utf8 = md->utf8; /* Local copy of the flag */ -#else -utf8 = FALSE; -#endif - /* At the start of a group with an unlimited repeat that may match an empty string, the match_cbegroup flag is set. When this is the case, add the current subject pointer to the chain of such remembered pointers, to be checked when we @@ -584,7 +618,7 @@ for (;;) if (md->partial && eptr >= md->end_subject && - eptr > md->start_match) + eptr > mstart) md->hitend = TRUE; switch(op) @@ -628,8 +662,8 @@ for (;;) flags = (op == OP_SCBRA)? match_cbegroup : 0; do { - RMATCH(rrc, eptr, ecode + _pcre_OP_lengths[*ecode], offset_top, md, - ims, eptrb, flags); + RMATCH(eptr, ecode + _pcre_OP_lengths[*ecode], offset_top, md, + ims, eptrb, flags, RM1); if (rrc != MATCH_NOMATCH) RRETURN(rrc); md->capture_last = save_capture_last; ecode += GET(ecode, 1); @@ -672,8 +706,8 @@ for (;;) /* For non-final alternatives, continue the loop for a NOMATCH result; otherwise return. */ - RMATCH(rrc, eptr, ecode + _pcre_OP_lengths[*ecode], offset_top, md, ims, - eptrb, flags); + RMATCH(eptr, ecode + _pcre_OP_lengths[*ecode], offset_top, md, ims, + eptrb, flags, RM2); if (rrc != MATCH_NOMATCH) RRETURN(rrc); ecode += GET(ecode, 1); } @@ -714,8 +748,8 @@ for (;;) else { - RMATCH(rrc, eptr, ecode + 1 + LINK_SIZE, offset_top, md, ims, NULL, - match_condassert); + RMATCH(eptr, ecode + 1 + LINK_SIZE, offset_top, md, ims, NULL, + match_condassert, RM3); if (rrc == MATCH_MATCH) { condition = TRUE; @@ -761,7 +795,7 @@ for (;;) md->recursive = rec->prevrec; memmove(md->offset_vector, rec->offset_save, rec->saved_max * sizeof(int)); - md->start_match = rec->save_start; + mstart = rec->save_start; ims = original_ims; ecode = rec->after_call; break; @@ -770,9 +804,10 @@ for (;;) /* Otherwise, if PCRE_NOTEMPTY is set, fail if we have matched an empty string - backtracking will then try other alternatives, if any. */ - if (md->notempty && eptr == md->start_match) RRETURN(MATCH_NOMATCH); - md->end_match_ptr = eptr; /* Record where we ended */ - md->end_offset_top = offset_top; /* and how many extracts were taken */ + if (md->notempty && eptr == mstart) RRETURN(MATCH_NOMATCH); + md->end_match_ptr = eptr; /* Record where we ended */ + md->end_offset_top = offset_top; /* and how many extracts were taken */ + md->start_match_ptr = mstart; /* and the start (\K can modify) */ RRETURN(MATCH_MATCH); /* Change option settings */ @@ -793,7 +828,8 @@ for (;;) case OP_ASSERTBACK: do { - RMATCH(rrc, eptr, ecode + 1 + LINK_SIZE, offset_top, md, ims, NULL, 0); + RMATCH(eptr, ecode + 1 + LINK_SIZE, offset_top, md, ims, NULL, 0, + RM4); if (rrc == MATCH_MATCH) break; if (rrc != MATCH_NOMATCH) RRETURN(rrc); ecode += GET(ecode, 1); @@ -819,7 +855,8 @@ for (;;) case OP_ASSERTBACK_NOT: do { - RMATCH(rrc, eptr, ecode + 1 + LINK_SIZE, offset_top, md, ims, NULL, 0); + RMATCH(eptr, ecode + 1 + LINK_SIZE, offset_top, md, ims, NULL, 0, + RM5); if (rrc == MATCH_MATCH) RRETURN(MATCH_NOMATCH); if (rrc != MATCH_NOMATCH) RRETURN(rrc); ecode += GET(ecode,1); @@ -876,7 +913,7 @@ for (;;) cb.offset_vector = md->offset_vector; cb.subject = (PCRE_SPTR)md->start_subject; cb.subject_length = md->end_subject - md->start_subject; - cb.start_match = md->start_match - md->start_subject; + cb.start_match = mstart - md->start_subject; cb.current_position = eptr - md->start_subject; cb.pattern_position = GET(ecode, 2); cb.next_item_length = GET(ecode, 2 + LINK_SIZE); @@ -938,8 +975,8 @@ for (;;) memcpy(new_recursive.offset_save, md->offset_vector, new_recursive.saved_max * sizeof(int)); - new_recursive.save_start = md->start_match; - md->start_match = eptr; + new_recursive.save_start = mstart; + mstart = eptr; /* OK, now we can do the recursion. For each top-level alternative we restore the offset and recursion data. */ @@ -948,8 +985,8 @@ for (;;) flags = (*callpat >= OP_SBRA)? match_cbegroup : 0; do { - RMATCH(rrc, eptr, callpat + _pcre_OP_lengths[*callpat], offset_top, - md, ims, eptrb, flags); + RMATCH(eptr, callpat + _pcre_OP_lengths[*callpat], offset_top, + md, ims, eptrb, flags, RM6); if (rrc == MATCH_MATCH) { DPRINTF(("Recursion matched\n")); @@ -992,8 +1029,8 @@ for (;;) do { - RMATCH(rrc, eptr, ecode + 1 + LINK_SIZE, offset_top, md, ims, - eptrb, 0); + RMATCH(eptr, ecode + 1 + LINK_SIZE, offset_top, md, ims, + eptrb, 0, RM7); if (rrc == MATCH_MATCH) break; if (rrc != MATCH_NOMATCH) RRETURN(rrc); ecode += GET(ecode,1); @@ -1038,7 +1075,8 @@ for (;;) if (*ecode == OP_KETRMIN) { - RMATCH(rrc, eptr, ecode + 1 + LINK_SIZE, offset_top, md, ims, eptrb, 0); + RMATCH(eptr, ecode + 1 + LINK_SIZE, offset_top, md, ims, eptrb, 0, + RM8); if (rrc != MATCH_NOMATCH) RRETURN(rrc); ecode = prev; flags = match_tail_recursed; @@ -1046,7 +1084,7 @@ for (;;) } else /* OP_KETRMAX */ { - RMATCH(rrc, eptr, prev, offset_top, md, ims, eptrb, match_cbegroup); + RMATCH(eptr, prev, offset_top, md, ims, eptrb, match_cbegroup, RM9); if (rrc != MATCH_NOMATCH) RRETURN(rrc); ecode += 1 + LINK_SIZE; flags = match_tail_recursed; @@ -1070,7 +1108,7 @@ for (;;) case OP_BRAZERO: { next = ecode+1; - RMATCH(rrc, eptr, next, offset_top, md, ims, eptrb, 0); + RMATCH(eptr, next, offset_top, md, ims, eptrb, 0, RM10); if (rrc != MATCH_NOMATCH) RRETURN(rrc); do next += GET(next,1); while (*next == OP_ALT); ecode = next + 1 + LINK_SIZE; @@ -1081,7 +1119,7 @@ for (;;) { next = ecode+1; do next += GET(next, 1); while (*next == OP_ALT); - RMATCH(rrc, eptr, next + 1+LINK_SIZE, offset_top, md, ims, eptrb, 0); + RMATCH(eptr, next + 1+LINK_SIZE, offset_top, md, ims, eptrb, 0, RM11); if (rrc != MATCH_NOMATCH) RRETURN(rrc); ecode++; } @@ -1151,7 +1189,7 @@ for (;;) recursion_info *rec = md->recursive; DPRINTF(("Recursion (%d) succeeded - continuing\n", number)); md->recursive = rec->prevrec; - md->start_match = rec->save_start; + mstart = rec->save_start; memcpy(md->offset_vector, rec->offset_save, rec->saved_max * sizeof(int)); ecode = rec->after_call; @@ -1186,7 +1224,8 @@ for (;;) if (*ecode == OP_KETRMIN) { - RMATCH(rrc, eptr, ecode + 1+LINK_SIZE, offset_top, md, ims, eptrb, 0); + RMATCH(eptr, ecode + 1+LINK_SIZE, offset_top, md, ims, eptrb, 0, + RM12); if (rrc != MATCH_NOMATCH) RRETURN(rrc); ecode = prev; flags |= match_tail_recursed; @@ -1194,7 +1233,7 @@ for (;;) } else /* OP_KETRMAX */ { - RMATCH(rrc, eptr, prev, offset_top, md, ims, eptrb, flags); + RMATCH(eptr, prev, offset_top, md, ims, eptrb, flags, RM13); if (rrc != MATCH_NOMATCH) RRETURN(rrc); ecode += 1 + LINK_SIZE; flags = match_tail_recursed; @@ -1230,6 +1269,13 @@ for (;;) ecode++; break; + /* Reset the start of match point */ + + case OP_SET_SOM: + mstart = eptr; + ecode++; + break; + /* Assert before internal newline if multiline, or before a terminating newline unless endonly is set, else end of subject unless noteol is set. */ @@ -1438,6 +1484,102 @@ for (;;) ecode++; break; + case OP_NOT_HSPACE: + if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); + GETCHARINCTEST(c, eptr); + switch(c) + { + default: break; + case 0x09: /* HT */ + case 0x20: /* SPACE */ + case 0xa0: /* NBSP */ + case 0x1680: /* OGHAM SPACE MARK */ + case 0x180e: /* MONGOLIAN VOWEL SEPARATOR */ + case 0x2000: /* EN QUAD */ + case 0x2001: /* EM QUAD */ + case 0x2002: /* EN SPACE */ + case 0x2003: /* EM SPACE */ + case 0x2004: /* THREE-PER-EM SPACE */ + case 0x2005: /* FOUR-PER-EM SPACE */ + case 0x2006: /* SIX-PER-EM SPACE */ + case 0x2007: /* FIGURE SPACE */ + case 0x2008: /* PUNCTUATION SPACE */ + case 0x2009: /* THIN SPACE */ + case 0x200A: /* HAIR SPACE */ + case 0x202f: /* NARROW NO-BREAK SPACE */ + case 0x205f: /* MEDIUM MATHEMATICAL SPACE */ + case 0x3000: /* IDEOGRAPHIC SPACE */ + RRETURN(MATCH_NOMATCH); + } + ecode++; + break; + + case OP_HSPACE: + if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); + GETCHARINCTEST(c, eptr); + switch(c) + { + default: RRETURN(MATCH_NOMATCH); + case 0x09: /* HT */ + case 0x20: /* SPACE */ + case 0xa0: /* NBSP */ + case 0x1680: /* OGHAM SPACE MARK */ + case 0x180e: /* MONGOLIAN VOWEL SEPARATOR */ + case 0x2000: /* EN QUAD */ + case 0x2001: /* EM QUAD */ + case 0x2002: /* EN SPACE */ + case 0x2003: /* EM SPACE */ + case 0x2004: /* THREE-PER-EM SPACE */ + case 0x2005: /* FOUR-PER-EM SPACE */ + case 0x2006: /* SIX-PER-EM SPACE */ + case 0x2007: /* FIGURE SPACE */ + case 0x2008: /* PUNCTUATION SPACE */ + case 0x2009: /* THIN SPACE */ + case 0x200A: /* HAIR SPACE */ + case 0x202f: /* NARROW NO-BREAK SPACE */ + case 0x205f: /* MEDIUM MATHEMATICAL SPACE */ + case 0x3000: /* IDEOGRAPHIC SPACE */ + break; + } + ecode++; + break; + + case OP_NOT_VSPACE: + if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); + GETCHARINCTEST(c, eptr); + switch(c) + { + default: break; + case 0x0a: /* LF */ + case 0x0b: /* VT */ + case 0x0c: /* FF */ + case 0x0d: /* CR */ + case 0x85: /* NEL */ + case 0x2028: /* LINE SEPARATOR */ + case 0x2029: /* PARAGRAPH SEPARATOR */ + RRETURN(MATCH_NOMATCH); + } + ecode++; + break; + + case OP_VSPACE: + if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); + GETCHARINCTEST(c, eptr); + switch(c) + { + default: RRETURN(MATCH_NOMATCH); + case 0x0a: /* LF */ + case 0x0b: /* VT */ + case 0x0c: /* FF */ + case 0x0d: /* CR */ + case 0x85: /* NEL */ + case 0x2028: /* LINE SEPARATOR */ + case 0x2029: /* PARAGRAPH SEPARATOR */ + break; + } + ecode++; + break; + #ifdef SUPPORT_UCP /* Check the next character by Unicode property. We will get here only if the support is in the binary; otherwise a compile-time error occurs. */ @@ -1593,7 +1735,7 @@ for (;;) { for (fi = min;; fi++) { - RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); + RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM14); if (rrc != MATCH_NOMATCH) RRETURN(rrc); if (fi >= max || !match_ref(offset, eptr, length, md, ims)) RRETURN(MATCH_NOMATCH); @@ -1614,7 +1756,7 @@ for (;;) } while (eptr >= pp) { - RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); + RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM15); if (rrc != MATCH_NOMATCH) RRETURN(rrc); eptr -= length; } @@ -1719,7 +1861,7 @@ for (;;) { for (fi = min;; fi++) { - RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); + RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM16); if (rrc != MATCH_NOMATCH) RRETURN(rrc); if (fi >= max || eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); GETCHARINC(c, eptr); @@ -1739,7 +1881,7 @@ for (;;) { for (fi = min;; fi++) { - RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); + RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM17); if (rrc != MATCH_NOMATCH) RRETURN(rrc); if (fi >= max || eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); c = *eptr++; @@ -1776,7 +1918,7 @@ for (;;) } for (;;) { - RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); + RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM18); if (rrc != MATCH_NOMATCH) RRETURN(rrc); if (eptr-- == pp) break; /* Stop if tried at original pos */ BACKCHAR(eptr); @@ -1795,7 +1937,7 @@ for (;;) } while (eptr >= pp) { - RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); + RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM19); if (rrc != MATCH_NOMATCH) RRETURN(rrc); eptr--; } @@ -1866,7 +2008,7 @@ for (;;) { for (fi = min;; fi++) { - RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); + RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM20); if (rrc != MATCH_NOMATCH) RRETURN(rrc); if (fi >= max || eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); GETCHARINC(c, eptr); @@ -1890,7 +2032,7 @@ for (;;) } for(;;) { - RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); + RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM21); if (rrc != MATCH_NOMATCH) RRETURN(rrc); if (eptr-- == pp) break; /* Stop if tried at original pos */ BACKCHAR(eptr) @@ -2047,19 +2189,18 @@ for (;;) if (length > 1) { - int oclength = 0; - uschar occhars[8]; - #ifdef SUPPORT_UCP unsigned int othercase; if ((ims & PCRE_CASELESS) != 0 && (othercase = _pcre_ucp_othercase(fc)) != NOTACHAR) oclength = _pcre_ord2utf8(othercase, occhars); + else oclength = 0; #endif /* SUPPORT_UCP */ for (i = 1; i <= min; i++) { if (memcmp(eptr, charptr, length) == 0) eptr += length; +#ifdef SUPPORT_UCP /* Need braces because of following else */ else if (oclength == 0) { RRETURN(MATCH_NOMATCH); } else @@ -2067,6 +2208,9 @@ for (;;) if (memcmp(eptr, occhars, oclength) != 0) RRETURN(MATCH_NOMATCH); eptr += oclength; } +#else /* without SUPPORT_UCP */ + else { RRETURN(MATCH_NOMATCH); } +#endif /* SUPPORT_UCP */ } if (min == max) continue; @@ -2075,10 +2219,11 @@ for (;;) { for (fi = min;; fi++) { - RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); + RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM22); if (rrc != MATCH_NOMATCH) RRETURN(rrc); if (fi >= max || eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); if (memcmp(eptr, charptr, length) == 0) eptr += length; +#ifdef SUPPORT_UCP /* Need braces because of following else */ else if (oclength == 0) { RRETURN(MATCH_NOMATCH); } else @@ -2086,6 +2231,9 @@ for (;;) if (memcmp(eptr, occhars, oclength) != 0) RRETURN(MATCH_NOMATCH); eptr += oclength; } +#else /* without SUPPORT_UCP */ + else { RRETURN (MATCH_NOMATCH); } +#endif /* SUPPORT_UCP */ } /* Control never gets here */ } @@ -2097,22 +2245,31 @@ for (;;) { if (eptr > md->end_subject - length) break; if (memcmp(eptr, charptr, length) == 0) eptr += length; +#ifdef SUPPORT_UCP else if (oclength == 0) break; else { if (memcmp(eptr, occhars, oclength) != 0) break; eptr += oclength; } +#else /* without SUPPORT_UCP */ + else break; +#endif /* SUPPORT_UCP */ } if (possessive) continue; - while (eptr >= pp) + for(;;) { - RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); + RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM23); if (rrc != MATCH_NOMATCH) RRETURN(rrc); + if (eptr == pp) RRETURN(MATCH_NOMATCH); +#ifdef SUPPORT_UCP + eptr--; + BACKCHAR(eptr); +#else /* without SUPPORT_UCP */ eptr -= length; +#endif /* SUPPORT_UCP */ } - RRETURN(MATCH_NOMATCH); } /* Control never gets here */ } @@ -2152,7 +2309,7 @@ for (;;) { for (fi = min;; fi++) { - RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); + RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM24); if (rrc != MATCH_NOMATCH) RRETURN(rrc); if (fi >= max || eptr >= md->end_subject || fc != md->lcc[*eptr++]) @@ -2171,7 +2328,7 @@ for (;;) if (possessive) continue; while (eptr >= pp) { - RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); + RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM25); eptr--; if (rrc != MATCH_NOMATCH) RRETURN(rrc); } @@ -2190,7 +2347,7 @@ for (;;) { for (fi = min;; fi++) { - RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); + RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM26); if (rrc != MATCH_NOMATCH) RRETURN(rrc); if (fi >= max || eptr >= md->end_subject || fc != *eptr++) RRETURN(MATCH_NOMATCH); @@ -2208,7 +2365,7 @@ for (;;) if (possessive) continue; while (eptr >= pp) { - RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); + RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM27); eptr--; if (rrc != MATCH_NOMATCH) RRETURN(rrc); } @@ -2353,7 +2510,7 @@ for (;;) register unsigned int d; for (fi = min;; fi++) { - RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); + RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM28); if (rrc != MATCH_NOMATCH) RRETURN(rrc); GETCHARINC(d, eptr); if (d < 256) d = md->lcc[d]; @@ -2367,7 +2524,7 @@ for (;;) { for (fi = min;; fi++) { - RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); + RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM29); if (rrc != MATCH_NOMATCH) RRETURN(rrc); if (fi >= max || eptr >= md->end_subject || fc == md->lcc[*eptr++]) RRETURN(MATCH_NOMATCH); @@ -2399,7 +2556,7 @@ for (;;) if (possessive) continue; for(;;) { - RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); + RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM30); if (rrc != MATCH_NOMATCH) RRETURN(rrc); if (eptr-- == pp) break; /* Stop if tried at original pos */ BACKCHAR(eptr); @@ -2417,7 +2574,7 @@ for (;;) if (possessive) continue; while (eptr >= pp) { - RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); + RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM31); if (rrc != MATCH_NOMATCH) RRETURN(rrc); eptr--; } @@ -2462,7 +2619,7 @@ for (;;) register unsigned int d; for (fi = min;; fi++) { - RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); + RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM32); if (rrc != MATCH_NOMATCH) RRETURN(rrc); GETCHARINC(d, eptr); if (fi >= max || eptr >= md->end_subject || fc == d) @@ -2475,7 +2632,7 @@ for (;;) { for (fi = min;; fi++) { - RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); + RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM33); if (rrc != MATCH_NOMATCH) RRETURN(rrc); if (fi >= max || eptr >= md->end_subject || fc == *eptr++) RRETURN(MATCH_NOMATCH); @@ -2506,7 +2663,7 @@ for (;;) if (possessive) continue; for(;;) { - RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); + RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM34); if (rrc != MATCH_NOMATCH) RRETURN(rrc); if (eptr-- == pp) break; /* Stop if tried at original pos */ BACKCHAR(eptr); @@ -2524,7 +2681,7 @@ for (;;) if (possessive) continue; while (eptr >= pp) { - RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); + RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM35); if (rrc != MATCH_NOMATCH) RRETURN(rrc); eptr--; } @@ -2631,7 +2788,7 @@ for (;;) for (i = 1; i <= min; i++) { if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); - GETCHARINC(c, eptr); + GETCHARINCTEST(c, eptr); } break; @@ -2639,7 +2796,7 @@ for (;;) for (i = 1; i <= min; i++) { if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); - GETCHARINC(c, eptr); + GETCHARINCTEST(c, eptr); prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script); if ((prop_chartype == ucp_Lu || prop_chartype == ucp_Ll || @@ -2652,7 +2809,7 @@ for (;;) for (i = 1; i <= min; i++) { if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); - GETCHARINC(c, eptr); + GETCHARINCTEST(c, eptr); prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script); if ((prop_category == prop_value) == prop_fail_result) RRETURN(MATCH_NOMATCH); @@ -2663,7 +2820,7 @@ for (;;) for (i = 1; i <= min; i++) { if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); - GETCHARINC(c, eptr); + GETCHARINCTEST(c, eptr); prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script); if ((prop_chartype == prop_value) == prop_fail_result) RRETURN(MATCH_NOMATCH); @@ -2674,7 +2831,7 @@ for (;;) for (i = 1; i <= min; i++) { if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); - GETCHARINC(c, eptr); + GETCHARINCTEST(c, eptr); prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script); if ((prop_script == prop_value) == prop_fail_result) RRETURN(MATCH_NOMATCH); @@ -2755,6 +2912,110 @@ for (;;) } break; + case OP_NOT_HSPACE: + for (i = 1; i <= min; i++) + { + if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); + GETCHARINC(c, eptr); + switch(c) + { + default: break; + case 0x09: /* HT */ + case 0x20: /* SPACE */ + case 0xa0: /* NBSP */ + case 0x1680: /* OGHAM SPACE MARK */ + case 0x180e: /* MONGOLIAN VOWEL SEPARATOR */ + case 0x2000: /* EN QUAD */ + case 0x2001: /* EM QUAD */ + case 0x2002: /* EN SPACE */ + case 0x2003: /* EM SPACE */ + case 0x2004: /* THREE-PER-EM SPACE */ + case 0x2005: /* FOUR-PER-EM SPACE */ + case 0x2006: /* SIX-PER-EM SPACE */ + case 0x2007: /* FIGURE SPACE */ + case 0x2008: /* PUNCTUATION SPACE */ + case 0x2009: /* THIN SPACE */ + case 0x200A: /* HAIR SPACE */ + case 0x202f: /* NARROW NO-BREAK SPACE */ + case 0x205f: /* MEDIUM MATHEMATICAL SPACE */ + case 0x3000: /* IDEOGRAPHIC SPACE */ + RRETURN(MATCH_NOMATCH); + } + } + break; + + case OP_HSPACE: + for (i = 1; i <= min; i++) + { + if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); + GETCHARINC(c, eptr); + switch(c) + { + default: RRETURN(MATCH_NOMATCH); + case 0x09: /* HT */ + case 0x20: /* SPACE */ + case 0xa0: /* NBSP */ + case 0x1680: /* OGHAM SPACE MARK */ + case 0x180e: /* MONGOLIAN VOWEL SEPARATOR */ + case 0x2000: /* EN QUAD */ + case 0x2001: /* EM QUAD */ + case 0x2002: /* EN SPACE */ + case 0x2003: /* EM SPACE */ + case 0x2004: /* THREE-PER-EM SPACE */ + case 0x2005: /* FOUR-PER-EM SPACE */ + case 0x2006: /* SIX-PER-EM SPACE */ + case 0x2007: /* FIGURE SPACE */ + case 0x2008: /* PUNCTUATION SPACE */ + case 0x2009: /* THIN SPACE */ + case 0x200A: /* HAIR SPACE */ + case 0x202f: /* NARROW NO-BREAK SPACE */ + case 0x205f: /* MEDIUM MATHEMATICAL SPACE */ + case 0x3000: /* IDEOGRAPHIC SPACE */ + break; + } + } + break; + + case OP_NOT_VSPACE: + for (i = 1; i <= min; i++) + { + if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); + GETCHARINC(c, eptr); + switch(c) + { + default: break; + case 0x0a: /* LF */ + case 0x0b: /* VT */ + case 0x0c: /* FF */ + case 0x0d: /* CR */ + case 0x85: /* NEL */ + case 0x2028: /* LINE SEPARATOR */ + case 0x2029: /* PARAGRAPH SEPARATOR */ + RRETURN(MATCH_NOMATCH); + } + } + break; + + case OP_VSPACE: + for (i = 1; i <= min; i++) + { + if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); + GETCHARINC(c, eptr); + switch(c) + { + default: RRETURN(MATCH_NOMATCH); + case 0x0a: /* LF */ + case 0x0b: /* VT */ + case 0x0c: /* FF */ + case 0x0d: /* CR */ + case 0x85: /* NEL */ + case 0x2028: /* LINE SEPARATOR */ + case 0x2029: /* PARAGRAPH SEPARATOR */ + break; + } + } + break; + case OP_NOT_DIGIT: for (i = 1; i <= min; i++) { @@ -2866,6 +3127,70 @@ for (;;) } break; + case OP_NOT_HSPACE: + for (i = 1; i <= min; i++) + { + if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); + switch(*eptr++) + { + default: break; + case 0x09: /* HT */ + case 0x20: /* SPACE */ + case 0xa0: /* NBSP */ + RRETURN(MATCH_NOMATCH); + } + } + break; + + case OP_HSPACE: + for (i = 1; i <= min; i++) + { + if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); + switch(*eptr++) + { + default: RRETURN(MATCH_NOMATCH); + case 0x09: /* HT */ + case 0x20: /* SPACE */ + case 0xa0: /* NBSP */ + break; + } + } + break; + + case OP_NOT_VSPACE: + for (i = 1; i <= min; i++) + { + if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); + switch(*eptr++) + { + default: break; + case 0x0a: /* LF */ + case 0x0b: /* VT */ + case 0x0c: /* FF */ + case 0x0d: /* CR */ + case 0x85: /* NEL */ + RRETURN(MATCH_NOMATCH); + } + } + break; + + case OP_VSPACE: + for (i = 1; i <= min; i++) + { + if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); + switch(*eptr++) + { + default: RRETURN(MATCH_NOMATCH); + case 0x0a: /* LF */ + case 0x0b: /* VT */ + case 0x0c: /* FF */ + case 0x0d: /* CR */ + case 0x85: /* NEL */ + break; + } + } + break; + case OP_NOT_DIGIT: for (i = 1; i <= min; i++) if ((md->ctypes[*eptr++] & ctype_digit) != 0) RRETURN(MATCH_NOMATCH); @@ -2921,7 +3246,7 @@ for (;;) case PT_ANY: for (fi = min;; fi++) { - RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); + RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM36); if (rrc != MATCH_NOMATCH) RRETURN(rrc); if (fi >= max || eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); GETCHARINC(c, eptr); @@ -2932,7 +3257,7 @@ for (;;) case PT_LAMP: for (fi = min;; fi++) { - RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); + RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM37); if (rrc != MATCH_NOMATCH) RRETURN(rrc); if (fi >= max || eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); GETCHARINC(c, eptr); @@ -2947,7 +3272,7 @@ for (;;) case PT_GC: for (fi = min;; fi++) { - RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); + RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM38); if (rrc != MATCH_NOMATCH) RRETURN(rrc); if (fi >= max || eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); GETCHARINC(c, eptr); @@ -2960,7 +3285,7 @@ for (;;) case PT_PC: for (fi = min;; fi++) { - RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); + RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM39); if (rrc != MATCH_NOMATCH) RRETURN(rrc); if (fi >= max || eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); GETCHARINC(c, eptr); @@ -2973,7 +3298,7 @@ for (;;) case PT_SC: for (fi = min;; fi++) { - RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); + RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM40); if (rrc != MATCH_NOMATCH) RRETURN(rrc); if (fi >= max || eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); GETCHARINC(c, eptr); @@ -2995,7 +3320,7 @@ for (;;) { for (fi = min;; fi++) { - RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); + RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM41); if (rrc != MATCH_NOMATCH) RRETURN(rrc); if (fi >= max || eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); GETCHARINCTEST(c, eptr); @@ -3024,7 +3349,7 @@ for (;;) { for (fi = min;; fi++) { - RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); + RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM42); if (rrc != MATCH_NOMATCH) RRETURN(rrc); if (fi >= max || eptr >= md->end_subject || (ctype == OP_ANY && (ims & PCRE_DOTALL) == 0 && @@ -3057,6 +3382,90 @@ for (;;) } break; + case OP_NOT_HSPACE: + switch(c) + { + default: break; + case 0x09: /* HT */ + case 0x20: /* SPACE */ + case 0xa0: /* NBSP */ + case 0x1680: /* OGHAM SPACE MARK */ + case 0x180e: /* MONGOLIAN VOWEL SEPARATOR */ + case 0x2000: /* EN QUAD */ + case 0x2001: /* EM QUAD */ + case 0x2002: /* EN SPACE */ + case 0x2003: /* EM SPACE */ + case 0x2004: /* THREE-PER-EM SPACE */ + case 0x2005: /* FOUR-PER-EM SPACE */ + case 0x2006: /* SIX-PER-EM SPACE */ + case 0x2007: /* FIGURE SPACE */ + case 0x2008: /* PUNCTUATION SPACE */ + case 0x2009: /* THIN SPACE */ + case 0x200A: /* HAIR SPACE */ + case 0x202f: /* NARROW NO-BREAK SPACE */ + case 0x205f: /* MEDIUM MATHEMATICAL SPACE */ + case 0x3000: /* IDEOGRAPHIC SPACE */ + RRETURN(MATCH_NOMATCH); + } + break; + + case OP_HSPACE: + switch(c) + { + default: RRETURN(MATCH_NOMATCH); + case 0x09: /* HT */ + case 0x20: /* SPACE */ + case 0xa0: /* NBSP */ + case 0x1680: /* OGHAM SPACE MARK */ + case 0x180e: /* MONGOLIAN VOWEL SEPARATOR */ + case 0x2000: /* EN QUAD */ + case 0x2001: /* EM QUAD */ + case 0x2002: /* EN SPACE */ + case 0x2003: /* EM SPACE */ + case 0x2004: /* THREE-PER-EM SPACE */ + case 0x2005: /* FOUR-PER-EM SPACE */ + case 0x2006: /* SIX-PER-EM SPACE */ + case 0x2007: /* FIGURE SPACE */ + case 0x2008: /* PUNCTUATION SPACE */ + case 0x2009: /* THIN SPACE */ + case 0x200A: /* HAIR SPACE */ + case 0x202f: /* NARROW NO-BREAK SPACE */ + case 0x205f: /* MEDIUM MATHEMATICAL SPACE */ + case 0x3000: /* IDEOGRAPHIC SPACE */ + break; + } + break; + + case OP_NOT_VSPACE: + switch(c) + { + default: break; + case 0x0a: /* LF */ + case 0x0b: /* VT */ + case 0x0c: /* FF */ + case 0x0d: /* CR */ + case 0x85: /* NEL */ + case 0x2028: /* LINE SEPARATOR */ + case 0x2029: /* PARAGRAPH SEPARATOR */ + RRETURN(MATCH_NOMATCH); + } + break; + + case OP_VSPACE: + switch(c) + { + default: RRETURN(MATCH_NOMATCH); + case 0x0a: /* LF */ + case 0x0b: /* VT */ + case 0x0c: /* FF */ + case 0x0d: /* CR */ + case 0x85: /* NEL */ + case 0x2028: /* LINE SEPARATOR */ + case 0x2029: /* PARAGRAPH SEPARATOR */ + break; + } + break; + case OP_NOT_DIGIT: if (c < 256 && (md->ctypes[c] & ctype_digit) != 0) RRETURN(MATCH_NOMATCH); @@ -3098,7 +3507,7 @@ for (;;) { for (fi = min;; fi++) { - RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); + RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM43); if (rrc != MATCH_NOMATCH) RRETURN(rrc); if (fi >= max || eptr >= md->end_subject || ((ims & PCRE_DOTALL) == 0 && IS_NEWLINE(eptr))) @@ -3128,6 +3537,54 @@ for (;;) } break; + case OP_NOT_HSPACE: + switch(c) + { + default: break; + case 0x09: /* HT */ + case 0x20: /* SPACE */ + case 0xa0: /* NBSP */ + RRETURN(MATCH_NOMATCH); + } + break; + + case OP_HSPACE: + switch(c) + { + default: RRETURN(MATCH_NOMATCH); + case 0x09: /* HT */ + case 0x20: /* SPACE */ + case 0xa0: /* NBSP */ + break; + } + break; + + case OP_NOT_VSPACE: + switch(c) + { + default: break; + case 0x0a: /* LF */ + case 0x0b: /* VT */ + case 0x0c: /* FF */ + case 0x0d: /* CR */ + case 0x85: /* NEL */ + RRETURN(MATCH_NOMATCH); + } + break; + + case OP_VSPACE: + switch(c) + { + default: RRETURN(MATCH_NOMATCH); + case 0x0a: /* LF */ + case 0x0b: /* VT */ + case 0x0c: /* FF */ + case 0x0d: /* CR */ + case 0x85: /* NEL */ + break; + } + break; + case OP_NOT_DIGIT: if ((md->ctypes[c] & ctype_digit) != 0) RRETURN(MATCH_NOMATCH); break; @@ -3244,7 +3701,7 @@ for (;;) if (possessive) continue; for(;;) { - RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); + RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM44); if (rrc != MATCH_NOMATCH) RRETURN(rrc); if (eptr-- == pp) break; /* Stop if tried at original pos */ BACKCHAR(eptr); @@ -3280,7 +3737,7 @@ for (;;) if (possessive) continue; for(;;) { - RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); + RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM45); if (rrc != MATCH_NOMATCH) RRETURN(rrc); if (eptr-- == pp) break; /* Stop if tried at original pos */ for (;;) /* Move back over one extended */ @@ -3389,6 +3846,70 @@ for (;;) } break; + case OP_NOT_HSPACE: + case OP_HSPACE: + for (i = min; i < max; i++) + { + BOOL gotspace; + int len = 1; + if (eptr >= md->end_subject) break; + GETCHARLEN(c, eptr, len); + switch(c) + { + default: gotspace = FALSE; break; + case 0x09: /* HT */ + case 0x20: /* SPACE */ + case 0xa0: /* NBSP */ + case 0x1680: /* OGHAM SPACE MARK */ + case 0x180e: /* MONGOLIAN VOWEL SEPARATOR */ + case 0x2000: /* EN QUAD */ + case 0x2001: /* EM QUAD */ + case 0x2002: /* EN SPACE */ + case 0x2003: /* EM SPACE */ + case 0x2004: /* THREE-PER-EM SPACE */ + case 0x2005: /* FOUR-PER-EM SPACE */ + case 0x2006: /* SIX-PER-EM SPACE */ + case 0x2007: /* FIGURE SPACE */ + case 0x2008: /* PUNCTUATION SPACE */ + case 0x2009: /* THIN SPACE */ + case 0x200A: /* HAIR SPACE */ + case 0x202f: /* NARROW NO-BREAK SPACE */ + case 0x205f: /* MEDIUM MATHEMATICAL SPACE */ + case 0x3000: /* IDEOGRAPHIC SPACE */ + gotspace = TRUE; + break; + } + if (gotspace == (ctype == OP_NOT_HSPACE)) break; + eptr += len; + } + break; + + case OP_NOT_VSPACE: + case OP_VSPACE: + for (i = min; i < max; i++) + { + BOOL gotspace; + int len = 1; + if (eptr >= md->end_subject) break; + GETCHARLEN(c, eptr, len); + switch(c) + { + default: gotspace = FALSE; break; + case 0x0a: /* LF */ + case 0x0b: /* VT */ + case 0x0c: /* FF */ + case 0x0d: /* CR */ + case 0x85: /* NEL */ + case 0x2028: /* LINE SEPARATOR */ + case 0x2029: /* PARAGRAPH SEPARATOR */ + gotspace = TRUE; + break; + } + if (gotspace == (ctype == OP_NOT_VSPACE)) break; + eptr += len; + } + break; + case OP_NOT_DIGIT: for (i = min; i < max; i++) { @@ -3464,7 +3985,7 @@ for (;;) if (possessive) continue; for(;;) { - RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); + RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM46); if (rrc != MATCH_NOMATCH) RRETURN(rrc); if (eptr-- == pp) break; /* Stop if tried at original pos */ BACKCHAR(eptr); @@ -3515,6 +4036,48 @@ for (;;) } break; + case OP_NOT_HSPACE: + for (i = min; i < max; i++) + { + if (eptr >= md->end_subject) break; + c = *eptr; + if (c == 0x09 || c == 0x20 || c == 0xa0) break; + eptr++; + } + break; + + case OP_HSPACE: + for (i = min; i < max; i++) + { + if (eptr >= md->end_subject) break; + c = *eptr; + if (c != 0x09 && c != 0x20 && c != 0xa0) break; + eptr++; + } + break; + + case OP_NOT_VSPACE: + for (i = min; i < max; i++) + { + if (eptr >= md->end_subject) break; + c = *eptr; + if (c == 0x0a || c == 0x0b || c == 0x0c || c == 0x0d || c == 0x85) + break; + eptr++; + } + break; + + case OP_VSPACE: + for (i = min; i < max; i++) + { + if (eptr >= md->end_subject) break; + c = *eptr; + if (c != 0x0a && c != 0x0b && c != 0x0c && c != 0x0d && c != 0x85) + break; + eptr++; + } + break; + case OP_NOT_DIGIT: for (i = min; i < max; i++) { @@ -3578,7 +4141,7 @@ for (;;) if (possessive) continue; while (eptr >= pp) { - RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); + RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM47); eptr--; if (rrc != MATCH_NOMATCH) RRETURN(rrc); } @@ -3604,6 +4167,29 @@ for (;;) } /* End of main loop */ /* Control never reaches here */ + + +/* When compiling to use the heap rather than the stack for recursive calls to +match(), the RRETURN() macro jumps here. The number that is saved in +frame->Xwhere indicates which label we actually want to return to. */ + +#ifdef NO_RECURSE +#define LBL(val) case val: goto L_RM##val; +HEAP_RETURN: +switch (frame->Xwhere) + { + LBL( 1) LBL( 2) LBL( 3) LBL( 4) LBL( 5) LBL( 6) LBL( 7) LBL( 8) + LBL( 9) LBL(10) LBL(11) LBL(12) LBL(13) LBL(14) LBL(15) LBL(16) + LBL(17) LBL(18) LBL(19) LBL(20) LBL(21) LBL(22) LBL(23) LBL(24) + LBL(25) LBL(26) LBL(27) LBL(28) LBL(29) LBL(30) LBL(31) LBL(32) + LBL(33) LBL(34) LBL(35) LBL(36) LBL(37) LBL(38) LBL(39) LBL(40) + LBL(41) LBL(42) LBL(43) LBL(44) LBL(45) LBL(46) LBL(47) + default: + DPRINTF(("jump error in pcre match: label %d non-existent\n", frame->Xwhere)); + return PCRE_ERROR_INTERNAL; + } +#undef LBL +#endif /* NO_RECURSE */ } @@ -3616,6 +4202,7 @@ Undefine all the macros that were defined above to handle this. */ #ifdef NO_RECURSE #undef eptr #undef ecode +#undef mstart #undef offset_top #undef ims #undef eptrb @@ -3688,7 +4275,7 @@ Returns: > 0 => success; value is the number of elements filled in < -1 => some kind of unexpected problem */ -PCRE_DATA_SCOPE int +PCRE_EXP_DEFN int pcre_exec(const pcre *argument_re, const pcre_extra *extra_data, PCRE_SPTR subject, int length, int start_offset, int options, int *offsets, int offsetcount) @@ -3804,10 +4391,10 @@ md->eptrchain = eptrchain; /* Make workspace generally available */ md->lcc = tables + lcc_offset; md->ctypes = tables + ctypes_offset; -/* Handle different types of newline. The two bits give four cases. If nothing -is set at run time, whatever was used at compile time applies. */ +/* Handle different types of newline. The three bits give eight cases. If +nothing is set at run time, whatever was used at compile time applies. */ -switch ((((options & PCRE_NEWLINE_BITS) == 0)? re->options : options) & +switch ((((options & PCRE_NEWLINE_BITS) == 0)? re->options : (pcre_uint32)options) & PCRE_NEWLINE_BITS) { case 0: newline = NEWLINE; break; /* Compile-time default */ @@ -3816,10 +4403,15 @@ switch ((((options & PCRE_NEWLINE_BITS) == 0)? re->options : options) & case PCRE_NEWLINE_CR+ PCRE_NEWLINE_LF: newline = ('\r' << 8) | '\n'; break; case PCRE_NEWLINE_ANY: newline = -1; break; + case PCRE_NEWLINE_ANYCRLF: newline = -2; break; default: return PCRE_ERROR_BADNEWLINE; } -if (newline < 0) +if (newline == -2) + { + md->nltype = NLTYPE_ANYCRLF; + } +else if (newline < 0) { md->nltype = NLTYPE_ANY; } @@ -3994,6 +4586,16 @@ for(;;) { while (start_match <= end_subject && !WAS_NEWLINE(start_match)) start_match++; + + /* If we have just passed a CR and the newline option is ANY or ANYCRLF, + and we are now at a LF, advance the match position by one more character. + */ + + if (start_match[-1] == '\r' && + (md->nltype == NLTYPE_ANY || md->nltype == NLTYPE_ANYCRLF) && + start_match < end_subject && + *start_match == '\n') + start_match++; } } @@ -4080,10 +4682,11 @@ for(;;) /* OK, we can now run the match. */ - md->start_match = start_match; + md->start_match_ptr = start_match; /* Insurance */ md->match_call_count = 0; md->eptrn = 0; /* Next free eptrchain slot */ - rc = match(start_match, md->start_code, 2, md, ims, NULL, 0, 0); + rc = match(start_match, md->start_code, start_match, 2, md, + ims, NULL, 0, 0); /* Any return other than MATCH_NOMATCH breaks the loop. */ @@ -4109,11 +4712,14 @@ for(;;) if (anchored || start_match > end_subject) break; - /* If we have just passed a CR and the newline option is CRLF or ANY, and we - are now at a LF, advance the match position by one more character. */ + /* If we have just passed a CR and the newline option is CRLF or ANY or + ANYCRLF, and we are now at a LF, advance the match position by one more + character. */ if (start_match[-1] == '\r' && - (md->nltype == NLTYPE_ANY || md->nllen == 2) && + (md->nltype == NLTYPE_ANY || + md->nltype == NLTYPE_ANYCRLF || + md->nllen == 2) && start_match < end_subject && *start_match == '\n') start_match++; @@ -4160,11 +4766,13 @@ if (rc == MATCH_MATCH) rc = md->offset_overflow? 0 : md->end_offset_top/2; - /* If there is space, set up the whole thing as substring 0. */ + /* If there is space, set up the whole thing as substring 0. The value of + md->start_match_ptr might be modified if \K was encountered on the success + matching path. */ if (offsetcount < 2) rc = 0; else { - offsets[0] = start_match - md->start_subject; + offsets[0] = md->start_match_ptr - md->start_subject; offsets[1] = md->end_match_ptr - md->start_subject; } diff --git a/src/src/pcre/pcre_fullinfo.c b/src/src/pcre/pcre_fullinfo.c index 5eddcd71e..c17f3d72b 100644 --- a/src/src/pcre/pcre_fullinfo.c +++ b/src/src/pcre/pcre_fullinfo.c @@ -1,4 +1,4 @@ -/* $Cambridge: exim/src/src/pcre/pcre_fullinfo.c,v 1.4 2007/01/23 15:08:45 ph10 Exp $ */ +/* $Cambridge: exim/src/src/pcre/pcre_fullinfo.c,v 1.5 2007/06/26 11:16:54 ph10 Exp $ */ /************************************************* * Perl-Compatible Regular Expressions * @@ -8,7 +8,7 @@ and semantics are as close as possible to those of the Perl 5 language. Written by Philip Hazel - Copyright (c) 1997-2006 University of Cambridge + Copyright (c) 1997-2007 University of Cambridge ----------------------------------------------------------------------------- Redistribution and use in source and binary forms, with or without @@ -63,7 +63,7 @@ Arguments: Returns: 0 if data returned, negative on error */ -PCRE_DATA_SCOPE int +PCRE_EXP_DEFN int pcre_fullinfo(const pcre *argument_re, const pcre_extra *extra_data, int what, void *where) { @@ -142,6 +142,14 @@ switch (what) *((const uschar **)where) = (const uschar *)(_pcre_default_tables); break; + case PCRE_INFO_OKPARTIAL: + *((int *)where) = (re->options & PCRE_NOPARTIAL) == 0; + break; + + case PCRE_INFO_JCHANGED: + *((int *)where) = (re->options & PCRE_JCHANGED) != 0; + break; + default: return PCRE_ERROR_BADOPTION; } diff --git a/src/src/pcre/pcre_get.c b/src/src/pcre/pcre_get.c index 0dcd5d69b..3added96d 100644 --- a/src/src/pcre/pcre_get.c +++ b/src/src/pcre/pcre_get.c @@ -1,4 +1,4 @@ -/* $Cambridge: exim/src/src/pcre/pcre_get.c,v 1.4 2007/01/23 15:08:45 ph10 Exp $ */ +/* $Cambridge: exim/src/src/pcre/pcre_get.c,v 1.5 2007/06/26 11:16:54 ph10 Exp $ */ /************************************************* * Perl-Compatible Regular Expressions * @@ -8,7 +8,7 @@ and semantics are as close as possible to those of the Perl 5 language. Written by Philip Hazel - Copyright (c) 1997-2006 University of Cambridge + Copyright (c) 1997-2007 University of Cambridge ----------------------------------------------------------------------------- Redistribution and use in source and binary forms, with or without diff --git a/src/src/pcre/pcre_globals.c b/src/src/pcre/pcre_globals.c index 2c3a80b67..ee3707d9d 100644 --- a/src/src/pcre/pcre_globals.c +++ b/src/src/pcre/pcre_globals.c @@ -1,4 +1,4 @@ -/* $Cambridge: exim/src/src/pcre/pcre_globals.c,v 1.4 2007/01/23 15:08:45 ph10 Exp $ */ +/* $Cambridge: exim/src/src/pcre/pcre_globals.c,v 1.5 2007/06/26 11:16:54 ph10 Exp $ */ /************************************************* * Perl-Compatible Regular Expressions * @@ -8,7 +8,7 @@ and semantics are as close as possible to those of the Perl 5 language. Written by Philip Hazel - Copyright (c) 1997-2006 University of Cambridge + Copyright (c) 1997-2007 University of Cambridge ----------------------------------------------------------------------------- Redistribution and use in source and binary forms, with or without @@ -48,37 +48,14 @@ indirection. These values can be changed by the caller, but are shared between all threads. However, when compiling for Virtual Pascal, things are done differently, and global variables are not used (see pcre.in). */ - #include "pcre_internal.h" - #ifndef VPCOMPAT - -/************************************************************************** -This code used to be here for use when compiling as a C++ library. However, -according to Dair Grant it is not needed: " - - Including 'extern "C"' in the declaration generates an "initialized and - declared `extern'" warning from gcc 4.0.1. Since we include pcre_internal.h, - which includes pcre.h, which declares these prototypes within an extern "C" {} - block, we shouldn't need the prefix here. - -So, from Release 7.0 I have cut this out. - -#ifdef __cplusplus -extern "C" void *(*pcre_malloc)(size_t) = malloc; -extern "C" void (*pcre_free)(void *) = free; -extern "C" void *(*pcre_stack_malloc)(size_t) = malloc; -extern "C" void (*pcre_stack_free)(void *) = free; -extern "C" int (*pcre_callout)(pcre_callout_block *) = NULL; -#else -**************************************************************************/ - -void *(*pcre_malloc)(size_t) = malloc; -void (*pcre_free)(void *) = free; -void *(*pcre_stack_malloc)(size_t) = malloc; -void (*pcre_stack_free)(void *) = free; -int (*pcre_callout)(pcre_callout_block *) = NULL; +PCRE_EXP_DATA_DEFN void *(*pcre_malloc)(size_t) = malloc; +PCRE_EXP_DATA_DEFN void (*pcre_free)(void *) = free; +PCRE_EXP_DATA_DEFN void *(*pcre_stack_malloc)(size_t) = malloc; +PCRE_EXP_DATA_DEFN void (*pcre_stack_free)(void *) = free; +PCRE_EXP_DATA_DEFN int (*pcre_callout)(pcre_callout_block *) = NULL; #endif /* End of pcre_globals.c */ diff --git a/src/src/pcre/pcre_internal.h b/src/src/pcre/pcre_internal.h index 20172832f..e2a55b120 100644 --- a/src/src/pcre/pcre_internal.h +++ b/src/src/pcre/pcre_internal.h @@ -1,4 +1,4 @@ -/* $Cambridge: exim/src/src/pcre/pcre_internal.h,v 1.4 2007/01/23 15:08:45 ph10 Exp $ */ +/* $Cambridge: exim/src/src/pcre/pcre_internal.h,v 1.5 2007/06/26 11:16:54 ph10 Exp $ */ /************************************************* * Perl-Compatible Regular Expressions * @@ -9,7 +9,7 @@ and semantics are as close as possible to those of the Perl 5 language. Written by Philip Hazel - Copyright (c) 1997-2006 University of Cambridge + Copyright (c) 1997-2007 University of Cambridge ----------------------------------------------------------------------------- Redistribution and use in source and binary forms, with or without @@ -85,8 +85,58 @@ setjmp and stdarg are used is when NO_RECURSE is set. */ #include #include -#ifndef PCRE_SPY -#define PCRE_DEFINITION /* Win32 __declspec(export) trigger for .dll */ +/* When compiling a DLL for Windows, the exported symbols have to be declared +using some MS magic. I found some useful information on this web page: +http://msdn2.microsoft.com/en-us/library/y4h7bcy6(VS.80).aspx. According to the +information there, using __declspec(dllexport) without "extern" we have a +definition; with "extern" we have a declaration. The settings here override the +setting in pcre.h (which is included below); it defines only PCRE_EXP_DECL, +which is all that is needed for applications (they just import the symbols). We +use: + + PCRE_EXP_DECL for declarations + PCRE_EXP_DEFN for definitions of exported functions + PCRE_EXP_DATA_DEFN for definitions of exported variables + +The reason for the two DEFN macros is that in non-Windows environments, one +does not want to have "extern" before variable definitions because it leads to +compiler warnings. So we distinguish between functions and variables. In +Windows, the two should always be the same. + +The reason for wrapping this in #ifndef PCRE_EXP_DECL is so that pcretest, +which is an application, but needs to import this file in order to "peek" at +internals, can #include pcre.h first to get an application's-eye view. + +In principle, people compiling for non-Windows, non-Unix-like (i.e. uncommon, +special-purpose environments) might want to stick other stuff in front of +exported symbols. That's why, in the non-Windows case, we set PCRE_EXP_DEFN and +PCRE_EXP_DATA_DEFN only if they are not already set. */ + +#ifndef PCRE_EXP_DECL +# ifdef _WIN32 +# ifdef DLL_EXPORT +# define PCRE_EXP_DECL extern __declspec(dllexport) +# define PCRE_EXP_DEFN __declspec(dllexport) +# define PCRE_EXP_DATA_DEFN __declspec(dllexport) +# else +# define PCRE_EXP_DECL extern +# define PCRE_EXP_DEFN +# define PCRE_EXP_DATA_DEFN +# endif +# +# else +# ifdef __cplusplus +# define PCRE_EXP_DECL extern "C" +# else +# define PCRE_EXP_DECL extern +# endif +# ifndef PCRE_EXP_DEFN +# define PCRE_EXP_DEFN PCRE_EXP_DECL +# endif +# ifndef PCRE_EXP_DATA_DEFN +# define PCRE_EXP_DATA_DEFN +# endif +# endif #endif /* We need to have types that specify unsigned 16-bit and 32-bit integers. We @@ -127,21 +177,22 @@ characters only go up to 0x7fffffff (though Unicode doesn't go beyond #define NOTACHAR 0xffffffff /* PCRE is able to support several different kinds of newline (CR, LF, CRLF, -and "all" at present). The following macros are used to package up testing for -newlines. NLBLOCK, PSSTART, and PSEND are defined in the various modules to -indicate in which datablock the parameters exist, and what the start/end of -string field names are. */ +"any" and "anycrlf" at present). The following macros are used to package up +testing for newlines. NLBLOCK, PSSTART, and PSEND are defined in the various +modules to indicate in which datablock the parameters exist, and what the +start/end of string field names are. */ -#define NLTYPE_FIXED 0 /* Newline is a fixed length string */ -#define NLTYPE_ANY 1 /* Newline is any Unicode line ending */ +#define NLTYPE_FIXED 0 /* Newline is a fixed length string */ +#define NLTYPE_ANY 1 /* Newline is any Unicode line ending */ +#define NLTYPE_ANYCRLF 2 /* Newline is CR, LF, or CRLF */ /* This macro checks for a newline at the given position */ #define IS_NEWLINE(p) \ ((NLBLOCK->nltype != NLTYPE_FIXED)? \ ((p) < NLBLOCK->PSEND && \ - _pcre_is_newline((p), NLBLOCK->PSEND, &(NLBLOCK->nllen), utf8) \ - ) \ + _pcre_is_newline((p), NLBLOCK->nltype, NLBLOCK->PSEND, &(NLBLOCK->nllen),\ + utf8)) \ : \ ((p) <= NLBLOCK->PSEND - NLBLOCK->nllen && \ (p)[0] == NLBLOCK->nl[0] && \ @@ -154,8 +205,8 @@ string field names are. */ #define WAS_NEWLINE(p) \ ((NLBLOCK->nltype != NLTYPE_FIXED)? \ ((p) > NLBLOCK->PSSTART && \ - _pcre_was_newline((p), NLBLOCK->PSSTART, &(NLBLOCK->nllen), utf8) \ - ) \ + _pcre_was_newline((p), NLBLOCK->nltype, NLBLOCK->PSSTART, \ + &(NLBLOCK->nllen), utf8)) \ : \ ((p) >= NLBLOCK->PSSTART + NLBLOCK->nllen && \ (p)[-NLBLOCK->nllen] == NLBLOCK->nl[0] && \ @@ -180,10 +231,12 @@ must begin with PCRE_. */ #define USPTR const unsigned char * #endif + + /* Include the public PCRE header and the definitions of UCP character property values. */ -#include "pcre.h" +#include #include "ucp.h" /* When compiling for use with the Virtual Pascal compiler, these functions @@ -191,7 +244,9 @@ need to have their names changed. PCRE must be compiled with the -DVPCOMPAT option on the command line. */ #ifdef VPCOMPAT +#define strlen(s) _strlen(s) #define strncmp(s1,s2,m) _strncmp(s1,s2,m) +#define memcmp(s,c,n) _memcmp(s,c,n) #define memcpy(d,s,n) _memcpy(d,s,n) #define memmove(d,s,n) _memmove(d,s,n) #define memset(s,c,n) _memset(s,c,n) @@ -200,23 +255,31 @@ option on the command line. */ /* To cope with SunOS4 and other systems that lack memmove() but have bcopy(), define a macro for memmove() if HAVE_MEMMOVE is false, provided that HAVE_BCOPY is set. Otherwise, include an emulating function for those systems that have -neither (there some non-Unix environments where this is the case). This assumes -that all calls to memmove are moving strings upwards in store, which is the -case in PCRE. */ +neither (there some non-Unix environments where this is the case). */ -#if ! HAVE_MEMMOVE +#ifndef HAVE_MEMMOVE #undef memmove /* some systems may have a macro */ -#if HAVE_BCOPY +#ifdef HAVE_BCOPY #define memmove(a, b, c) bcopy(b, a, c) #else /* HAVE_BCOPY */ static void * -pcre_memmove(unsigned char *dest, const unsigned char *src, size_t n) +pcre_memmove(void *d, const void *s, size_t n) { size_t i; -dest += n; -src += n; -for (i = 0; i < n; ++i) *(--dest) = *(--src); -return dest; +unsigned char *dest = (unsigned char *)d; +const unsigned char *src = (const unsigned char *)s; +if (dest > src) + { + dest += n; + src += n; + for (i = 0; i < n; ++i) *(--dest) = *(--src); + return (void *)dest; + } +else + { + for (i = 0; i < n; ++i) *dest++ = *src++; + return (void *)(dest - n); + } } #define memmove(a, b, c) pcre_memmove(a, b, c) #endif /* not HAVE_BCOPY */ @@ -441,7 +504,8 @@ bits. */ /* Masks for identifying the public options that are permitted at compile time, run time, or study time, respectively. */ -#define PCRE_NEWLINE_BITS (PCRE_NEWLINE_CR|PCRE_NEWLINE_LF|PCRE_NEWLINE_ANY) +#define PCRE_NEWLINE_BITS (PCRE_NEWLINE_CR|PCRE_NEWLINE_LF|PCRE_NEWLINE_ANY| \ + PCRE_NEWLINE_ANYCRLF) #define PUBLIC_OPTIONS \ (PCRE_CASELESS|PCRE_EXTENDED|PCRE_ANCHORED|PCRE_MULTILINE| \ @@ -543,9 +607,9 @@ ESC_Z to detect the types that may be repeated. These are the types that consume characters. If any new escapes are put in between that don't consume a character, that code will have to change. */ -enum { ESC_A = 1, ESC_G, ESC_B, ESC_b, ESC_D, ESC_d, ESC_S, ESC_s, ESC_W, - ESC_w, ESC_dum1, ESC_C, ESC_P, ESC_p, ESC_R, ESC_X, ESC_Z, ESC_z, - ESC_E, ESC_Q, ESC_k, ESC_REF }; +enum { ESC_A = 1, ESC_G, ESC_K, ESC_B, ESC_b, ESC_D, ESC_d, ESC_S, ESC_s, + ESC_W, ESC_w, ESC_dum1, ESC_C, ESC_P, ESC_p, ESC_R, ESC_H, ESC_h, + ESC_V, ESC_v, ESC_X, ESC_Z, ESC_z, ESC_E, ESC_Q, ESC_k, ESC_REF }; /* Opcode table: OP_BRA must be last, as all values >= it are used for brackets @@ -567,133 +631,138 @@ enum { OP_SOD, /* 1 Start of data: \A */ OP_SOM, /* 2 Start of match (subject + offset): \G */ - OP_NOT_WORD_BOUNDARY, /* 3 \B */ - OP_WORD_BOUNDARY, /* 4 \b */ - OP_NOT_DIGIT, /* 5 \D */ - OP_DIGIT, /* 6 \d */ - OP_NOT_WHITESPACE, /* 7 \S */ - OP_WHITESPACE, /* 8 \s */ - OP_NOT_WORDCHAR, /* 9 \W */ - OP_WORDCHAR, /* 10 \w */ - OP_ANY, /* 11 Match any character */ - OP_ANYBYTE, /* 12 Match any byte (\C); different to OP_ANY for UTF-8 */ - OP_NOTPROP, /* 13 \P (not Unicode property) */ - OP_PROP, /* 14 \p (Unicode property) */ - OP_ANYNL, /* 15 \R (any newline sequence) */ - OP_EXTUNI, /* 16 \X (extended Unicode sequence */ - OP_EODN, /* 17 End of data or \n at end of data: \Z. */ - OP_EOD, /* 18 End of data: \z */ - - OP_OPT, /* 19 Set runtime options */ - OP_CIRC, /* 20 Start of line - varies with multiline switch */ - OP_DOLL, /* 21 End of line - varies with multiline switch */ - OP_CHAR, /* 22 Match one character, casefully */ - OP_CHARNC, /* 23 Match one character, caselessly */ - OP_NOT, /* 24 Match one character, not the following one */ - - OP_STAR, /* 25 The maximizing and minimizing versions of */ - OP_MINSTAR, /* 26 these six opcodes must come in pairs, with */ - OP_PLUS, /* 27 the minimizing one second. */ - OP_MINPLUS, /* 28 This first set applies to single characters.*/ - OP_QUERY, /* 29 */ - OP_MINQUERY, /* 30 */ - - OP_UPTO, /* 31 From 0 to n matches */ - OP_MINUPTO, /* 32 */ - OP_EXACT, /* 33 Exactly n matches */ - - OP_POSSTAR, /* 34 Possessified star */ - OP_POSPLUS, /* 35 Possessified plus */ - OP_POSQUERY, /* 36 Posesssified query */ - OP_POSUPTO, /* 37 Possessified upto */ - - OP_NOTSTAR, /* 38 The maximizing and minimizing versions of */ - OP_NOTMINSTAR, /* 39 these six opcodes must come in pairs, with */ - OP_NOTPLUS, /* 40 the minimizing one second. They must be in */ - OP_NOTMINPLUS, /* 41 exactly the same order as those above. */ - OP_NOTQUERY, /* 42 This set applies to "not" single characters. */ - OP_NOTMINQUERY, /* 43 */ - - OP_NOTUPTO, /* 44 From 0 to n matches */ - OP_NOTMINUPTO, /* 45 */ - OP_NOTEXACT, /* 46 Exactly n matches */ - - OP_NOTPOSSTAR, /* 47 Possessified versions */ - OP_NOTPOSPLUS, /* 48 */ - OP_NOTPOSQUERY, /* 49 */ - OP_NOTPOSUPTO, /* 50 */ - - OP_TYPESTAR, /* 51 The maximizing and minimizing versions of */ - OP_TYPEMINSTAR, /* 52 these six opcodes must come in pairs, with */ - OP_TYPEPLUS, /* 53 the minimizing one second. These codes must */ - OP_TYPEMINPLUS, /* 54 be in exactly the same order as those above. */ - OP_TYPEQUERY, /* 55 This set applies to character types such as \d */ - OP_TYPEMINQUERY, /* 56 */ - - OP_TYPEUPTO, /* 57 From 0 to n matches */ - OP_TYPEMINUPTO, /* 58 */ - OP_TYPEEXACT, /* 59 Exactly n matches */ - - OP_TYPEPOSSTAR, /* 60 Possessified versions */ - OP_TYPEPOSPLUS, /* 61 */ - OP_TYPEPOSQUERY, /* 62 */ - OP_TYPEPOSUPTO, /* 63 */ - - OP_CRSTAR, /* 64 The maximizing and minimizing versions of */ - OP_CRMINSTAR, /* 65 all these opcodes must come in pairs, with */ - OP_CRPLUS, /* 66 the minimizing one second. These codes must */ - OP_CRMINPLUS, /* 67 be in exactly the same order as those above. */ - OP_CRQUERY, /* 68 These are for character classes and back refs */ - OP_CRMINQUERY, /* 69 */ - OP_CRRANGE, /* 70 These are different to the three sets above. */ - OP_CRMINRANGE, /* 71 */ - - OP_CLASS, /* 72 Match a character class, chars < 256 only */ - OP_NCLASS, /* 73 Same, but the bitmap was created from a negative + OP_SET_SOM, /* 3 Set start of match (\K) */ + OP_NOT_WORD_BOUNDARY, /* 4 \B */ + OP_WORD_BOUNDARY, /* 5 \b */ + OP_NOT_DIGIT, /* 6 \D */ + OP_DIGIT, /* 7 \d */ + OP_NOT_WHITESPACE, /* 8 \S */ + OP_WHITESPACE, /* 9 \s */ + OP_NOT_WORDCHAR, /* 10 \W */ + OP_WORDCHAR, /* 11 \w */ + OP_ANY, /* 12 Match any character */ + OP_ANYBYTE, /* 13 Match any byte (\C); different to OP_ANY for UTF-8 */ + OP_NOTPROP, /* 14 \P (not Unicode property) */ + OP_PROP, /* 15 \p (Unicode property) */ + OP_ANYNL, /* 16 \R (any newline sequence) */ + OP_NOT_HSPACE, /* 17 \H (not horizontal whitespace) */ + OP_HSPACE, /* 18 \h (horizontal whitespace) */ + OP_NOT_VSPACE, /* 19 \V (not vertical whitespace) */ + OP_VSPACE, /* 20 \v (vertical whitespace) */ + OP_EXTUNI, /* 21 \X (extended Unicode sequence */ + OP_EODN, /* 22 End of data or \n at end of data: \Z. */ + OP_EOD, /* 23 End of data: \z */ + + OP_OPT, /* 24 Set runtime options */ + OP_CIRC, /* 25 Start of line - varies with multiline switch */ + OP_DOLL, /* 26 End of line - varies with multiline switch */ + OP_CHAR, /* 27 Match one character, casefully */ + OP_CHARNC, /* 28 Match one character, caselessly */ + OP_NOT, /* 29 Match one character, not the following one */ + + OP_STAR, /* 30 The maximizing and minimizing versions of */ + OP_MINSTAR, /* 31 these six opcodes must come in pairs, with */ + OP_PLUS, /* 32 the minimizing one second. */ + OP_MINPLUS, /* 33 This first set applies to single characters.*/ + OP_QUERY, /* 34 */ + OP_MINQUERY, /* 35 */ + + OP_UPTO, /* 36 From 0 to n matches */ + OP_MINUPTO, /* 37 */ + OP_EXACT, /* 38 Exactly n matches */ + + OP_POSSTAR, /* 39 Possessified star */ + OP_POSPLUS, /* 40 Possessified plus */ + OP_POSQUERY, /* 41 Posesssified query */ + OP_POSUPTO, /* 42 Possessified upto */ + + OP_NOTSTAR, /* 43 The maximizing and minimizing versions of */ + OP_NOTMINSTAR, /* 44 these six opcodes must come in pairs, with */ + OP_NOTPLUS, /* 45 the minimizing one second. They must be in */ + OP_NOTMINPLUS, /* 46 exactly the same order as those above. */ + OP_NOTQUERY, /* 47 This set applies to "not" single characters. */ + OP_NOTMINQUERY, /* 48 */ + + OP_NOTUPTO, /* 49 From 0 to n matches */ + OP_NOTMINUPTO, /* 50 */ + OP_NOTEXACT, /* 51 Exactly n matches */ + + OP_NOTPOSSTAR, /* 52 Possessified versions */ + OP_NOTPOSPLUS, /* 53 */ + OP_NOTPOSQUERY, /* 54 */ + OP_NOTPOSUPTO, /* 55 */ + + OP_TYPESTAR, /* 56 The maximizing and minimizing versions of */ + OP_TYPEMINSTAR, /* 57 these six opcodes must come in pairs, with */ + OP_TYPEPLUS, /* 58 the minimizing one second. These codes must */ + OP_TYPEMINPLUS, /* 59 be in exactly the same order as those above. */ + OP_TYPEQUERY, /* 60 This set applies to character types such as \d */ + OP_TYPEMINQUERY, /* 61 */ + + OP_TYPEUPTO, /* 62 From 0 to n matches */ + OP_TYPEMINUPTO, /* 63 */ + OP_TYPEEXACT, /* 64 Exactly n matches */ + + OP_TYPEPOSSTAR, /* 65 Possessified versions */ + OP_TYPEPOSPLUS, /* 66 */ + OP_TYPEPOSQUERY, /* 67 */ + OP_TYPEPOSUPTO, /* 68 */ + + OP_CRSTAR, /* 69 The maximizing and minimizing versions of */ + OP_CRMINSTAR, /* 70 all these opcodes must come in pairs, with */ + OP_CRPLUS, /* 71 the minimizing one second. These codes must */ + OP_CRMINPLUS, /* 72 be in exactly the same order as those above. */ + OP_CRQUERY, /* 73 These are for character classes and back refs */ + OP_CRMINQUERY, /* 74 */ + OP_CRRANGE, /* 75 These are different to the three sets above. */ + OP_CRMINRANGE, /* 76 */ + + OP_CLASS, /* 77 Match a character class, chars < 256 only */ + OP_NCLASS, /* 78 Same, but the bitmap was created from a negative class - the difference is relevant only when a UTF-8 character > 255 is encountered. */ - OP_XCLASS, /* 74 Extended class for handling UTF-8 chars within the + OP_XCLASS, /* 79 Extended class for handling UTF-8 chars within the class. This does both positive and negative. */ - OP_REF, /* 75 Match a back reference */ - OP_RECURSE, /* 76 Match a numbered subpattern (possibly recursive) */ - OP_CALLOUT, /* 77 Call out to external function if provided */ + OP_REF, /* 80 Match a back reference */ + OP_RECURSE, /* 81 Match a numbered subpattern (possibly recursive) */ + OP_CALLOUT, /* 82 Call out to external function if provided */ - OP_ALT, /* 78 Start of alternation */ - OP_KET, /* 79 End of group that doesn't have an unbounded repeat */ - OP_KETRMAX, /* 80 These two must remain together and in this */ - OP_KETRMIN, /* 81 order. They are for groups the repeat for ever. */ + OP_ALT, /* 83 Start of alternation */ + OP_KET, /* 84 End of group that doesn't have an unbounded repeat */ + OP_KETRMAX, /* 85 These two must remain together and in this */ + OP_KETRMIN, /* 86 order. They are for groups the repeat for ever. */ /* The assertions must come before BRA, CBRA, ONCE, and COND.*/ - OP_ASSERT, /* 82 Positive lookahead */ - OP_ASSERT_NOT, /* 83 Negative lookahead */ - OP_ASSERTBACK, /* 84 Positive lookbehind */ - OP_ASSERTBACK_NOT, /* 85 Negative lookbehind */ - OP_REVERSE, /* 86 Move pointer back - used in lookbehind assertions */ + OP_ASSERT, /* 87 Positive lookahead */ + OP_ASSERT_NOT, /* 88 Negative lookahead */ + OP_ASSERTBACK, /* 89 Positive lookbehind */ + OP_ASSERTBACK_NOT, /* 90 Negative lookbehind */ + OP_REVERSE, /* 91 Move pointer back - used in lookbehind assertions */ /* ONCE, BRA, CBRA, and COND must come after the assertions, with ONCE first, as there's a test for >= ONCE for a subpattern that isn't an assertion. */ - OP_ONCE, /* 87 Atomic group */ - OP_BRA, /* 88 Start of non-capturing bracket */ - OP_CBRA, /* 89 Start of capturing bracket */ - OP_COND, /* 90 Conditional group */ + OP_ONCE, /* 92 Atomic group */ + OP_BRA, /* 83 Start of non-capturing bracket */ + OP_CBRA, /* 94 Start of capturing bracket */ + OP_COND, /* 95 Conditional group */ /* These three must follow the previous three, in the same order. There's a check for >= SBRA to distinguish the two sets. */ - OP_SBRA, /* 91 Start of non-capturing bracket, check empty */ - OP_SCBRA, /* 92 Start of capturing bracket, check empty */ - OP_SCOND, /* 93 Conditional group, check empty */ + OP_SBRA, /* 96 Start of non-capturing bracket, check empty */ + OP_SCBRA, /* 97 Start of capturing bracket, check empty */ + OP_SCOND, /* 98 Conditional group, check empty */ - OP_CREF, /* 94 Used to hold a capture number as condition */ - OP_RREF, /* 95 Used to hold a recursion number as condition */ - OP_DEF, /* 96 The DEFINE condition */ + OP_CREF, /* 99 Used to hold a capture number as condition */ + OP_RREF, /* 100 Used to hold a recursion number as condition */ + OP_DEF, /* 101 The DEFINE condition */ - OP_BRAZERO, /* 97 These two must remain together and in this */ - OP_BRAMINZERO /* 98 order. */ + OP_BRAZERO, /* 102 These two must remain together and in this */ + OP_BRAMINZERO /* 103 order. */ }; @@ -701,10 +770,10 @@ enum { for debugging. The macro is referenced only in pcre_printint.c. */ #define OP_NAME_LIST \ - "End", "\\A", "\\G", "\\B", "\\b", "\\D", "\\d", \ + "End", "\\A", "\\G", "\\K", "\\B", "\\b", "\\D", "\\d", \ "\\S", "\\s", "\\W", "\\w", "Any", "Anybyte", \ - "notprop", "prop", "anynl", "extuni", \ - "\\Z", "\\z", \ + "notprop", "prop", "\\R", "\\H", "\\h", "\\V", "\\v", \ + "extuni", "\\Z", "\\z", \ "Opt", "^", "$", "char", "charnc", "not", \ "*", "*?", "+", "+?", "?", "??", "{", "{", "{", \ "*+","++", "?+", "{", \ @@ -731,9 +800,11 @@ in UTF-8 mode. The code that uses this table must know about such things. */ #define OP_LENGTHS \ 1, /* End */ \ - 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, /* \A, \G, \B, \B, \D, \d, \S, \s, \W, \w */ \ + 1, 1, 1, 1, 1, /* \A, \G, \K, \B, \b */ \ + 1, 1, 1, 1, 1, 1, /* \D, \d, \S, \s, \W, \w */ \ 1, 1, /* Any, Anybyte */ \ - 3, 3, 1, 1, /* NOTPROP, PROP, EXTUNI, ANYNL */ \ + 3, 3, 1, /* NOTPROP, PROP, EXTUNI */ \ + 1, 1, 1, 1, 1, /* \R, \H, \h, \V, \v */ \ 1, 1, 2, 1, 1, /* \Z, \z, Opt, ^, $ */ \ 2, /* Char - the minimum length */ \ 2, /* Charnc - the minimum length */ \ @@ -793,7 +864,7 @@ enum { ERR0, ERR1, ERR2, ERR3, ERR4, ERR5, ERR6, ERR7, ERR8, ERR9, ERR20, ERR21, ERR22, ERR23, ERR24, ERR25, ERR26, ERR27, ERR28, ERR29, ERR30, ERR31, ERR32, ERR33, ERR34, ERR35, ERR36, ERR37, ERR38, ERR39, ERR40, ERR41, ERR42, ERR43, ERR44, ERR45, ERR46, ERR47, ERR48, ERR49, - ERR50, ERR51, ERR52, ERR53, ERR54, ERR55, ERR56, ERR57 }; + ERR50, ERR51, ERR52, ERR53, ERR54, ERR55, ERR56, ERR57, ERR58 }; /* The real format of the start of the pcre block; the index of names and the code vector run on as long as necessary after the end. We store an explicit @@ -882,21 +953,11 @@ typedef struct recursion_info { struct recursion_info *prevrec; /* Previous recursion record (or NULL) */ int group_num; /* Number of group that was called */ const uschar *after_call; /* "Return value": points after the call in the expr */ - USPTR save_start; /* Old value of md->start_match */ + USPTR save_start; /* Old value of mstart */ int *offset_save; /* Pointer to start of saved offsets */ int saved_max; /* Number of saved offsets */ } recursion_info; -/* When compiling in a mode that doesn't use recursive calls to match(), -a structure is used to remember local variables on the heap. It is defined in -pcre_exec.c, close to the match() function, so that it is easy to keep it in -step with any changes of local variable. However, the pointer to the current -frame must be saved in some "static" place over a longjmp(). We declare the -structure here so that we can put a pointer in the match_data structure. NOTE: -This isn't used for a "normal" compilation of pcre. */ - -struct heapframe; - /* Structure for building a chain of data for holding the values of the subject pointer at the start of each subpattern, so as to detect when an empty string has been matched by a subpattern - to break infinite loops. */ @@ -933,7 +994,7 @@ typedef struct match_data { const uschar *start_code; /* For use when recursing */ USPTR start_subject; /* Start of the subject string */ USPTR end_subject; /* End of the subject string */ - USPTR start_match; /* Start of this match attempt */ + USPTR start_match_ptr; /* Start of matched string */ USPTR end_match_ptr; /* Subject position at end match */ int end_offset_top; /* Highwater mark at end of match */ int capture_last; /* Most recent capture number */ @@ -942,7 +1003,6 @@ typedef struct match_data { int eptrn; /* Next free eptrblock */ recursion_info *recursive; /* Linked list of recursion data */ void *callout_data; /* To pass back to callouts */ - struct heapframe *thisframe; /* Used only when compiling for no recursion */ } match_data; /* A similar structure is used for the same purpose by the DFA matching @@ -1028,16 +1088,16 @@ extern const uschar _pcre_OP_lengths[]; one of the exported public functions. They have to be "external" in the C sense, but are not part of the PCRE public API. */ -extern BOOL _pcre_is_newline(const uschar *, const uschar *, int *, - BOOL); +extern BOOL _pcre_is_newline(const uschar *, int, const uschar *, + int *, BOOL); extern int _pcre_ord2utf8(int, uschar *); extern real_pcre *_pcre_try_flipped(const real_pcre *, real_pcre *, const pcre_study_data *, pcre_study_data *); extern int _pcre_ucp_findprop(const unsigned int, int *, int *); extern unsigned int _pcre_ucp_othercase(const unsigned int); extern int _pcre_valid_utf8(const uschar *, int); -extern BOOL _pcre_was_newline(const uschar *, const uschar *, int *, - BOOL); +extern BOOL _pcre_was_newline(const uschar *, int, const uschar *, + int *, BOOL); extern BOOL _pcre_xclass(int, const uschar *); #endif diff --git a/src/src/pcre/pcre_maketables.c b/src/src/pcre/pcre_maketables.c index b78019efc..6209c25dc 100644 --- a/src/src/pcre/pcre_maketables.c +++ b/src/src/pcre/pcre_maketables.c @@ -1,4 +1,4 @@ -/* $Cambridge: exim/src/src/pcre/pcre_maketables.c,v 1.4 2007/01/23 15:08:45 ph10 Exp $ */ +/* $Cambridge: exim/src/src/pcre/pcre_maketables.c,v 1.5 2007/06/26 11:16:54 ph10 Exp $ */ /************************************************* * Perl-Compatible Regular Expressions * @@ -8,7 +8,7 @@ and semantics are as close as possible to those of the Perl 5 language. Written by Philip Hazel - Copyright (c) 1997-2006 University of Cambridge + Copyright (c) 1997-2007 University of Cambridge ----------------------------------------------------------------------------- Redistribution and use in source and binary forms, with or without diff --git a/src/src/pcre/pcre_newline.c b/src/src/pcre/pcre_newline.c index 26cf0fe1f..bf0ade5ae 100644 --- a/src/src/pcre/pcre_newline.c +++ b/src/src/pcre/pcre_newline.c @@ -1,4 +1,4 @@ -/* $Cambridge: exim/src/src/pcre/pcre_newline.c,v 1.1 2007/01/23 15:08:45 ph10 Exp $ */ +/* $Cambridge: exim/src/src/pcre/pcre_newline.c,v 1.2 2007/06/26 11:16:54 ph10 Exp $ */ /************************************************* * Perl-Compatible Regular Expressions * @@ -8,7 +8,7 @@ and semantics are as close as possible to those of the Perl 5 language. Written by Philip Hazel - Copyright (c) 1997-2006 University of Cambridge + Copyright (c) 1997-2007 University of Cambridge ----------------------------------------------------------------------------- Redistribution and use in source and binary forms, with or without @@ -44,9 +44,8 @@ POSSIBILITY OF SUCH DAMAGE. one kind of newline is to be recognized. When a newline is found, its length is returned. In principle, we could implement several newline "types", each referring to a different set of newline characters. At present, PCRE supports -only NLTYPE_FIXED, which gets handled without these functions, and NLTYPE_ALL, -so for now the type isn't passed into the functions. It can easily be added -later if required. The full list of Unicode newline characters is taken from +only NLTYPE_FIXED, which gets handled without these functions, NLTYPE_ANYCRLF, +and NLTYPE_ANY. The full list of Unicode newline characters is taken from http://unicode.org/unicode/reports/tr18/. */ @@ -63,6 +62,7 @@ string that is being processed. Arguments: ptr pointer to possible newline + type the newline type endptr pointer to the end of the string lenptr where to return the length utf8 TRUE if in utf8 mode @@ -71,12 +71,23 @@ Returns: TRUE or FALSE */ BOOL -_pcre_is_newline(const uschar *ptr, const uschar *endptr, int *lenptr, - BOOL utf8) +_pcre_is_newline(const uschar *ptr, int type, const uschar *endptr, + int *lenptr, BOOL utf8) { int c; if (utf8) { GETCHAR(c, ptr); } else c = *ptr; -switch(c) + +if (type == NLTYPE_ANYCRLF) switch(c) + { + case 0x000a: *lenptr = 1; return TRUE; /* LF */ + case 0x000d: *lenptr = (ptr < endptr - 1 && ptr[1] == 0x0a)? 2 : 1; + return TRUE; /* CR */ + default: return FALSE; + } + +/* NLTYPE_ANY */ + +else switch(c) { case 0x000a: /* LF */ case 0x000b: /* VT */ @@ -101,6 +112,7 @@ the string that is being processed. Arguments: ptr pointer to possible newline + type the newline type startptr pointer to the start of the string lenptr where to return the length utf8 TRUE if in utf8 mode @@ -109,8 +121,8 @@ Returns: TRUE or FALSE */ BOOL -_pcre_was_newline(const uschar *ptr, const uschar *startptr, int *lenptr, - BOOL utf8) +_pcre_was_newline(const uschar *ptr, int type, const uschar *startptr, + int *lenptr, BOOL utf8) { int c; ptr--; @@ -120,7 +132,16 @@ if (utf8) GETCHAR(c, ptr); } else c = *ptr; -switch(c) + +if (type == NLTYPE_ANYCRLF) switch(c) + { + case 0x000a: *lenptr = (ptr > startptr && ptr[-1] == 0x0d)? 2 : 1; + return TRUE; /* LF */ + case 0x000d: *lenptr = 1; return TRUE; /* CR */ + default: return FALSE; + } + +else switch(c) { case 0x000a: *lenptr = (ptr > startptr && ptr[-1] == 0x0d)? 2 : 1; return TRUE; /* LF */ diff --git a/src/src/pcre/pcre_printint.src b/src/src/pcre/pcre_printint.src index e5407f81b..7e2837b72 100644 --- a/src/src/pcre/pcre_printint.src +++ b/src/src/pcre/pcre_printint.src @@ -1,4 +1,4 @@ -/* $Cambridge: exim/src/src/pcre/pcre_printint.src,v 1.2 2007/01/23 15:08:45 ph10 Exp $ */ +/* $Cambridge: exim/src/src/pcre/pcre_printint.src,v 1.3 2007/06/26 11:16:54 ph10 Exp $ */ /************************************************* * Perl-Compatible Regular Expressions * @@ -8,7 +8,7 @@ and semantics are as close as possible to those of the Perl 5 language. Written by Philip Hazel - Copyright (c) 1997-2005 University of Cambridge + Copyright (c) 1997-2007 University of Cambridge ----------------------------------------------------------------------------- Redistribution and use in source and binary forms, with or without @@ -73,6 +73,12 @@ print_char(FILE *f, uschar *ptr, BOOL utf8) { int c = *ptr; +#ifndef SUPPORT_UTF8 +utf8 = utf8; /* Avoid compiler warning */ +if (PRINTABLE(c)) fprintf(f, "%c", c); else fprintf(f, "\\x%02x", c); +return 0; + +#else if (!utf8 || (c & 0xc0) != 0xc0) { if (PRINTABLE(c)) fprintf(f, "%c", c); else fprintf(f, "\\x%02x", c); @@ -104,6 +110,7 @@ else if (c < 128) fprintf(f, "\\x%02x", c); else fprintf(f, "\\x{%x}", c); return a; } +#endif } @@ -136,10 +143,13 @@ return (ptype == pvalue)? "??" : "??"; *************************************************/ /* Make this function work for a regex with integers either byte order. -However, we assume that what we are passed is a compiled regex. */ +However, we assume that what we are passed is a compiled regex. The +print_lengths flag controls whether offsets and lengths of items are printed. +They can be turned off from pcretest so that automatic tests on bytecode can be +written that do not depend on the value of LINK_SIZE. */ static void -pcre_printint(pcre *external_re, FILE *f) +pcre_printint(pcre *external_re, FILE *f, BOOL print_lengths) { real_pcre *re = (real_pcre *)external_re; uschar *codestart, *code; @@ -170,7 +180,10 @@ for(;;) int c; int extra = 0; - fprintf(f, "%3d ", (int)(code - codestart)); + if (print_lengths) + fprintf(f, "%3d ", (int)(code - codestart)); + else + fprintf(f, " "); switch(*code) { @@ -207,8 +220,9 @@ for(;;) case OP_CBRA: case OP_SCBRA: - fprintf(f, "%3d %s %d", GET(code, 1), OP_names[*code], - GET2(code, 1+LINK_SIZE)); + if (print_lengths) fprintf(f, "%3d ", GET(code, 1)); + else fprintf(f, " "); + fprintf(f, "%s %d", OP_names[*code], GET2(code, 1+LINK_SIZE)); break; case OP_BRA: @@ -225,7 +239,9 @@ for(;;) case OP_COND: case OP_SCOND: case OP_REVERSE: - fprintf(f, "%3d %s", GET(code, 1), OP_names[*code]); + if (print_lengths) fprintf(f, "%3d ", GET(code, 1)); + else fprintf(f, " "); + fprintf(f, "%s", OP_names[*code]); break; case OP_CREF: @@ -341,7 +357,9 @@ for(;;) break; case OP_RECURSE: - fprintf(f, "%3d %s", GET(code, 1), OP_names[*code]); + if (print_lengths) fprintf(f, "%3d ", GET(code, 1)); + else fprintf(f, " "); + fprintf(f, "%s", OP_names[*code]); break; case OP_REF: diff --git a/src/src/pcre/pcre_study.c b/src/src/pcre/pcre_study.c index ae312f272..8858f7f40 100644 --- a/src/src/pcre/pcre_study.c +++ b/src/src/pcre/pcre_study.c @@ -1,4 +1,4 @@ -/* $Cambridge: exim/src/src/pcre/pcre_study.c,v 1.4 2007/01/23 15:08:45 ph10 Exp $ */ +/* $Cambridge: exim/src/src/pcre/pcre_study.c,v 1.5 2007/06/26 11:16:54 ph10 Exp $ */ /************************************************* * Perl-Compatible Regular Expressions * @@ -8,7 +8,7 @@ and semantics are as close as possible to those of the Perl 5 language. Written by Philip Hazel - Copyright (c) 1997-2006 University of Cambridge + Copyright (c) 1997-2007 University of Cambridge ----------------------------------------------------------------------------- Redistribution and use in source and binary forms, with or without @@ -396,11 +396,13 @@ do character with a value > 255. */ case OP_NCLASS: +#ifdef SUPPORT_UTF8 if (utf8) { start_bits[24] |= 0xf0; /* Bits for 0xc4 - 0xc8 */ memset(start_bits+25, 0xff, 7); /* Bits for 0xc9 - 0xff */ } +#endif /* Fall through */ case OP_CLASS: @@ -413,6 +415,7 @@ do value is > 127. In fact, there are only two possible starting bytes for characters in the range 128 - 255. */ +#ifdef SUPPORT_UTF8 if (utf8) { for (c = 0; c < 16; c++) start_bits[c] |= tcode[c]; @@ -430,6 +433,7 @@ do /* In non-UTF-8 mode, the two bit maps are completely compatible. */ else +#endif { for (c = 0; c < 32; c++) start_bits[c] |= tcode[c]; } @@ -489,7 +493,7 @@ Returns: pointer to a pcre_extra block, with study_data filled in and the NULL on error or if no optimization possible */ -PCRE_DATA_SCOPE pcre_extra * +PCRE_EXP_DEFN pcre_extra * pcre_study(const pcre *external_re, int options, const char **errorptr) { uschar start_bits[32]; diff --git a/src/src/pcre/pcre_tables.c b/src/src/pcre/pcre_tables.c index 1f4649f76..1c2f1cd06 100644 --- a/src/src/pcre/pcre_tables.c +++ b/src/src/pcre/pcre_tables.c @@ -1,4 +1,4 @@ -/* $Cambridge: exim/src/src/pcre/pcre_tables.c,v 1.4 2007/01/23 15:08:45 ph10 Exp $ */ +/* $Cambridge: exim/src/src/pcre/pcre_tables.c,v 1.5 2007/06/26 11:16:54 ph10 Exp $ */ /************************************************* * Perl-Compatible Regular Expressions * @@ -8,7 +8,7 @@ and semantics are as close as possible to those of the Perl 5 language. Written by Philip Hazel - Copyright (c) 1997-2006 University of Cambridge + Copyright (c) 1997-2007 University of Cambridge ----------------------------------------------------------------------------- Redistribution and use in source and binary forms, with or without @@ -63,6 +63,8 @@ const uschar _pcre_OP_lengths[] = { OP_LENGTHS }; /* These are the breakpoints for different numbers of bytes in a UTF-8 character. */ +#ifdef SUPPORT_UTF8 + const int _pcre_utf8_table1[] = { 0x7f, 0x7ff, 0xffff, 0x1fffff, 0x3ffffff, 0x7fffffff}; @@ -196,4 +198,6 @@ const ucp_type_table _pcre_utt[] = { const int _pcre_utt_size = sizeof(_pcre_utt)/sizeof(ucp_type_table); +#endif /* SUPPORT_UTF8 */ + /* End of pcre_tables.c */ diff --git a/src/src/pcre/pcre_try_flipped.c b/src/src/pcre/pcre_try_flipped.c index d0b652037..1c08eb6fa 100644 --- a/src/src/pcre/pcre_try_flipped.c +++ b/src/src/pcre/pcre_try_flipped.c @@ -1,4 +1,4 @@ -/* $Cambridge: exim/src/src/pcre/pcre_try_flipped.c,v 1.4 2007/01/23 15:08:45 ph10 Exp $ */ +/* $Cambridge: exim/src/src/pcre/pcre_try_flipped.c,v 1.5 2007/06/26 11:16:54 ph10 Exp $ */ /************************************************* * Perl-Compatible Regular Expressions * @@ -8,7 +8,7 @@ and semantics are as close as possible to those of the Perl 5 language. Written by Philip Hazel - Copyright (c) 1997-2006 University of Cambridge + Copyright (c) 1997-2007 University of Cambridge ----------------------------------------------------------------------------- Redistribution and use in source and binary forms, with or without diff --git a/src/src/pcre/pcre_version.c b/src/src/pcre/pcre_version.c index 1a30fe014..d4f8e2a8a 100644 --- a/src/src/pcre/pcre_version.c +++ b/src/src/pcre/pcre_version.c @@ -1,4 +1,4 @@ -/* $Cambridge: exim/src/src/pcre/pcre_version.c,v 1.4 2007/01/23 15:08:45 ph10 Exp $ */ +/* $Cambridge: exim/src/src/pcre/pcre_version.c,v 1.5 2007/06/26 11:16:54 ph10 Exp $ */ /************************************************* * Perl-Compatible Regular Expressions * @@ -8,7 +8,7 @@ and semantics are as close as possible to those of the Perl 5 language. Written by Philip Hazel - Copyright (c) 1997-2006 University of Cambridge + Copyright (c) 1997-2007 University of Cambridge ----------------------------------------------------------------------------- Redistribution and use in source and binary forms, with or without @@ -77,7 +77,7 @@ I could find no way of detecting that a macro is defined as an empty string at pre-processor time. This hack uses a standard trick for avoiding calling the STRING macro with an empty argument when doing the test. */ -PCRE_DATA_SCOPE const char * +PCRE_EXP_DEFN const char * pcre_version(void) { return (XSTRING(Z PCRE_PRERELEASE)[1] == 0)? diff --git a/src/src/pcre/pcretest.c b/src/src/pcre/pcretest.c index a572a9dfc..98d10445e 100644 --- a/src/src/pcre/pcretest.c +++ b/src/src/pcre/pcretest.c @@ -1,4 +1,4 @@ -/* $Cambridge: exim/src/src/pcre/pcretest.c,v 1.6 2007/01/23 15:08:45 ph10 Exp $ */ +/* $Cambridge: exim/src/src/pcre/pcretest.c,v 1.7 2007/06/26 11:16:54 ph10 Exp $ */ /************************************************* * PCRE testing program * @@ -69,13 +69,16 @@ input mode under Windows. */ #endif -#define PCRE_SPY /* For Win32 build, import data, not export */ +/* We have to include pcre_internal.h because we need the internal info for +displaying the results of pcre_study() and we also need to know about the +internal macros, structures, and other internal data values; pcretest has +"inside information" compared to a program that strictly follows the PCRE API. -/* We include pcre_internal.h because we need the internal info for displaying -the results of pcre_study() and we also need to know about the internal -macros, structures, and other internal data values; pcretest has "inside -information" compared to a program that strictly follows the PCRE API. */ +Although pcre_internal.h does itself include pcre.h, we explicitly include it +here before pcre_internal.h so that the PCRE_EXP_xxx macros get set +appropriately for an application, not for building PCRE. */ +#include "pcre.h" #include "pcre_internal.h" /* We need access to the data tables that PCRE uses. So as not to have to keep @@ -116,10 +119,17 @@ Makefile. */ #include "pcreposix.h" #endif -/* It is also possible, for the benefit of the version imported into Exim, to -build pcretest without support for UTF8 (define NOUTF8), without the interface -to the DFA matcher (NODFA), and without the doublecheck of the old "info" -function (define NOINFOCHECK). */ +/* It is also possible, for the benefit of the version currently imported into +Exim, to build pcretest without support for UTF8 (define NOUTF8), without the +interface to the DFA matcher (NODFA), and without the doublecheck of the old +"info" function (define NOINFOCHECK). In fact, we automatically cut out the +UTF8 support if PCRE is built without it. */ + +#ifndef SUPPORT_UTF8 +#ifndef NOUTF8 +#define NOUTF8 +#endif +#endif /* Other parameters */ @@ -655,7 +665,8 @@ return count; *************************************************/ /* This is used both at compile and run-time to check for escapes, where -xxx is LF, CR, CRLF, or ANY. Print a message and return 0 if there is no match. +xxx is LF, CR, CRLF, ANYCRLF, or ANY. Print a message and return 0 if there is +no match. Arguments: p points after the leading '<' @@ -670,6 +681,7 @@ check_newline(uschar *p, FILE *f) if (strncmp((char *)p, "cr>", 3) == 0) return PCRE_NEWLINE_CR; if (strncmp((char *)p, "lf>", 3) == 0) return PCRE_NEWLINE_LF; if (strncmp((char *)p, "crlf>", 5) == 0) return PCRE_NEWLINE_CRLF; +if (strncmp((char *)p, "anycrlf>", 8) == 0) return PCRE_NEWLINE_ANYCRLF; if (strncmp((char *)p, "any>", 4) == 0) return PCRE_NEWLINE_ANY; fprintf(f, "Unknown newline type at: <%s\n", p); return 0; @@ -842,6 +854,7 @@ while (argc > 1 && argv[op][0] == '-') (void)pcre_config(PCRE_CONFIG_NEWLINE, &rc); printf(" Newline sequence is %s\n", (rc == '\r')? "CR" : (rc == '\n')? "LF" : (rc == ('\r'<<8 | '\n'))? "CRLF" : + (rc == -2)? "ANYCRLF" : (rc == -1)? "ANY" : "???"); (void)pcre_config(PCRE_CONFIG_LINK_SIZE, &rc); printf(" Internal link size = %d\n", rc); @@ -853,7 +866,7 @@ while (argc > 1 && argv[op][0] == '-') printf(" Default recursion depth limit = %d\n", rc); (void)pcre_config(PCRE_CONFIG_STACKRECURSE, &rc); printf(" Match recursion uses %s\n", rc? "stack" : "heap"); - exit(0); + goto EXIT; } else if (strcmp(argv[op], "-help") == 0 || strcmp(argv[op], "--help") == 0) @@ -879,7 +892,7 @@ offsets = (int *)malloc(size_offsets_max * sizeof(int)); if (offsets == NULL) { printf("** Failed to get %d bytes of memory for offsets vector\n", - size_offsets_max * sizeof(int)); + (int)(size_offsets_max * sizeof(int))); yield = 1; goto EXIT; } @@ -939,6 +952,7 @@ while (!done) size_t size, regex_gotten_store; int do_study = 0; int do_debug = debug; + int debug_lengths = 1; int do_G = 0; int do_g = 0; int do_showinfo = showinfo; @@ -1129,6 +1143,7 @@ while (!done) case 'S': do_study = 1; break; case 'U': options |= PCRE_UNGREEDY; break; case 'X': options |= PCRE_EXTRA; break; + case 'Z': debug_lengths = 0; break; case '8': options |= PCRE_UTF8; use_utf8 = 1; break; case '?': options |= PCRE_NO_UTF8_CHECK; break; @@ -1330,7 +1345,7 @@ while (!done) if (do_debug) { fprintf(outfile, "------------------------------------------------------------------\n"); - pcre_printint(re, outfile); + pcre_printint(re, outfile, debug_lengths); } if (do_showinfo) @@ -1339,7 +1354,7 @@ while (!done) #if !defined NOINFOCHECK int old_first_char, old_options, old_count; #endif - int count, backrefmax, first_char, need_char; + int count, backrefmax, first_char, need_char, okpartial, jchanged; int nameentrysize, namecount; const uschar *nametable; @@ -1352,6 +1367,8 @@ while (!done) new_info(re, NULL, PCRE_INFO_NAMEENTRYSIZE, &nameentrysize); new_info(re, NULL, PCRE_INFO_NAMECOUNT, &namecount); new_info(re, NULL, PCRE_INFO_NAMETABLE, (void *)&nametable); + new_info(re, NULL, PCRE_INFO_OKPARTIAL, &okpartial); + new_info(re, NULL, PCRE_INFO_JCHANGED, &jchanged); #if !defined NOINFOCHECK old_count = pcre_info(re, &old_options, &old_first_char); @@ -1393,17 +1410,10 @@ while (!done) } } - /* The NOPARTIAL bit is a private bit in the options, so we have - to fish it out via out back door */ + if (!okpartial) fprintf(outfile, "Partial matching not supported\n"); all_options = ((real_pcre *)re)->options; - if (do_flip) - { - all_options = byteflip(all_options, sizeof(all_options)); - } - - if ((all_options & PCRE_NOPARTIAL) != 0) - fprintf(outfile, "Partial matching not supported\n"); + if (do_flip) all_options = byteflip(all_options, sizeof(all_options)); if (get_options == 0) fprintf(outfile, "No options\n"); else fprintf(outfile, "Options:%s%s%s%s%s%s%s%s%s%s%s%s%s\n", @@ -1421,6 +1431,8 @@ while (!done) ((get_options & PCRE_NO_UTF8_CHECK) != 0)? " no_utf8_check" : "", ((get_options & PCRE_DUPNAMES) != 0)? " dupnames" : ""); + if (jchanged) fprintf(outfile, "Duplicate name status changes\n"); + switch (get_options & PCRE_NEWLINE_BITS) { case PCRE_NEWLINE_CR: @@ -1435,6 +1447,10 @@ while (!done) fprintf(outfile, "Forced newline sequence: CRLF\n"); break; + case PCRE_NEWLINE_ANYCRLF: + fprintf(outfile, "Forced newline sequence: ANYCRLF\n"); + break; + case PCRE_NEWLINE_ANY: fprintf(outfile, "Forced newline sequence: ANY\n"); break; @@ -1584,7 +1600,7 @@ while (!done) for (;;) { uschar *q; - uschar *bptr = dbuffer; + uschar *bptr; int *use_offsets = offsets; int use_size_offsets = size_offsets; int callout_data = 0; @@ -1640,7 +1656,7 @@ while (!done) p = buffer; while (isspace(*p)) p++; - q = dbuffer; + bptr = q = dbuffer; while ((c = *p++) != 0) { int i = 0; @@ -1835,7 +1851,7 @@ while (!done) if (offsets == NULL) { printf("** Failed to get %d bytes of memory for offsets vector\n", - size_offsets_max * sizeof(int)); + (int)(size_offsets_max * sizeof(int))); yield = 1; goto EXIT; } @@ -2204,19 +2220,44 @@ while (!done) } /* Failed to match. If this is a /g or /G loop and we previously set - g_notempty after a null match, this is not necessarily the end. - We want to advance the start offset, and continue. In the case of UTF-8 - matching, the advance must be one character, not one byte. Fudge the - offset values to achieve this. We won't be at the end of the string - - that was checked before setting g_notempty. */ + g_notempty after a null match, this is not necessarily the end. We want + to advance the start offset, and continue. We won't be at the end of the + string - that was checked before setting g_notempty. + + Complication arises in the case when the newline option is "any" or + "anycrlf". If the previous match was at the end of a line terminated by + CRLF, an advance of one character just passes the \r, whereas we should + prefer the longer newline sequence, as does the code in pcre_exec(). + Fudge the offset value to achieve this. + + Otherwise, in the case of UTF-8 matching, the advance must be one + character, not one byte. */ else { if (g_notempty != 0) { int onechar = 1; + unsigned int obits = ((real_pcre *)re)->options; use_offsets[0] = start_offset; - if (use_utf8) + if ((obits & PCRE_NEWLINE_BITS) == 0) + { + int d; + (void)pcre_config(PCRE_CONFIG_NEWLINE, &d); + obits = (d == '\r')? PCRE_NEWLINE_CR : + (d == '\n')? PCRE_NEWLINE_LF : + (d == ('\r'<<8 | '\n'))? PCRE_NEWLINE_CRLF : + (d == -2)? PCRE_NEWLINE_ANYCRLF : + (d == -1)? PCRE_NEWLINE_ANY : 0; + } + if (((obits & PCRE_NEWLINE_BITS) == PCRE_NEWLINE_ANY || + (obits & PCRE_NEWLINE_BITS) == PCRE_NEWLINE_ANYCRLF) + && + start_offset < len - 1 && + bptr[start_offset] == '\r' && + bptr[start_offset+1] == '\n') + onechar++; + else if (use_utf8) { while (start_offset + onechar < len) { @@ -2251,6 +2292,7 @@ while (!done) character. */ g_notempty = 0; + if (use_offsets[0] == use_offsets[1]) { if (use_offsets[0] == len) break; diff --git a/src/src/pcre/ucp.h b/src/src/pcre/ucp.h index 5dcd10520..288854e67 100644 --- a/src/src/pcre/ucp.h +++ b/src/src/pcre/ucp.h @@ -1,4 +1,4 @@ -/* $Cambridge: exim/src/src/pcre/ucp.h,v 1.4 2007/01/23 15:08:45 ph10 Exp $ */ +/* $Cambridge: exim/src/src/pcre/ucp.h,v 1.5 2007/06/26 11:16:54 ph10 Exp $ */ /************************************************* * Unicode Property Table handler * -- 2.30.2