diff options
| author | ph10 <ph10@2f5784b3-3f2a-0410-8824-cb99058d5e15> | 2007-09-11 11:15:33 +0000 |
|---|---|---|
| committer | ph10 <ph10@2f5784b3-3f2a-0410-8824-cb99058d5e15> | 2007-09-11 11:15:33 +0000 |
| commit | 1efcdd63835a98ad89649d4b0b89d6d875e54b2e (patch) | |
| tree | d76b45cb414c6694d744369626e29c6cee14318d | |
| parent | 6daf21e6a650630d1ef31720c2f92f555127fe80 (diff) | |
| download | pcre-1efcdd63835a98ad89649d4b0b89d6d875e54b2e.tar.gz | |
Add facility to make \R match only CR, LF, or CRLF.
git-svn-id: svn://vcs.exim.org/pcre/code/trunk@231 2f5784b3-3f2a-0410-8824-cb99058d5e15
40 files changed, 1855 insertions, 786 deletions
@@ -5,24 +5,27 @@ Version 7.4 10-Sep-07 --------------------- 1. Change 7.3/28 was implemented for classes by looking at the bitmap. This - means that a class such as [\s] counted as "explicit reference to CR or - LF". That isn't really right - the whole point of the change was to try to - help when there was an actual mention of one of the two characters. So now - the change happens only if \r or \n (or a literal CR or LF) character is + means that a class such as [\s] counted as "explicit reference to CR or + LF". That isn't really right - the whole point of the change was to try to + help when there was an actual mention of one of the two characters. So now + the change happens only if \r or \n (or a literal CR or LF) character is encountered. - -2. The 32-bit options word was also used for 6 internal flags, but the numbers - of both had grown to the point where there were only 3 bits left. - Fortunately, there was spare space in the data structure, and so I have - moved the internal flags into a new 16-bit field to free up more option + +2. The 32-bit options word was also used for 6 internal flags, but the numbers + of both had grown to the point where there were only 3 bits left. + Fortunately, there was spare space in the data structure, and so I have + moved the internal flags into a new 16-bit field to free up more option bits. - -3. The appearance of (?J) at the start of a pattern set the DUPNAMES option, - but did not set the internal JCHANGED flag - either of these is enough to - control the way the "get" function works - but the PCRE_INFO_JCHANGED - facility is supposed to tell if (?J) was ever used, so now (?J) at the + +3. The appearance of (?J) at the start of a pattern set the DUPNAMES option, + but did not set the internal JCHANGED flag - either of these is enough to + control the way the "get" function works - but the PCRE_INFO_JCHANGED + facility is supposed to tell if (?J) was ever used, so now (?J) at the start sets both bits. +4. Added options (at build time, compile time, exec time) to change \R from + matching any Unicode line ending sequence to just matching CR, LF, or CRLF. + Version 7.3 28-Aug-07 --------------------- diff --git a/configure.ac b/configure.ac index d61220f..3a3c555 100644 --- a/configure.ac +++ b/configure.ac @@ -136,6 +136,12 @@ AC_ARG_ENABLE(newline-is-any, ac_pcre_newline=any) enable_newline="$ac_pcre_newline" +# Handle --enable-bsr-anycrlf +AC_ARG_ENABLE(bsr-anycrlf, + AS_HELP_STRING([--enable-bsr-anycrlf], + [\R matches only CR, LF, CRLF by default]), + , enable_bsr_anycrlf=no) + # Handle --enable-ebcdic AC_ARG_ENABLE(ebcdic, AS_HELP_STRING([--enable-ebcdic], @@ -321,9 +327,19 @@ fi AC_DEFINE_UNQUOTED([NEWLINE], [$ac_pcre_newline_value], [ The value of NEWLINE determines the newline character sequence. On - Unix-like systems, "configure" can be used to override the default, - which is 10. The possible values are 10 (LF), 13 (CR), 3338 (CRLF), - -1 (ANY), or -2 (ANYCRLF).]) + systems that support it, "configure" can be used to override the + default, which is 10. The possible values are 10 (LF), 13 (CR), + 3338 (CRLF), -1 (ANY), or -2 (ANYCRLF).]) + +if test "$enable_bsr_anycrlf" = "yes"; then + AC_DEFINE([BSR_ANYCRLF], [], [ + By default, the \R escape sequence matches any Unicode line ending + character or sequence of characters. If BSR_ANYCRLF is defined, this is + changed so that backslash-R matches only CR, LF, or CRLF. The build- + time default can be overridden by the user of PCRE at runtime. On + systems that support it, "configure" can be used to override the + default.]) +fi AC_DEFINE_UNQUOTED([LINK_SIZE], [$with_link_size], [ The value of LINK_SIZE determines the number of bytes used to store @@ -451,31 +467,32 @@ cat <<EOF $PACKAGE-$VERSION configuration summary: - Install prefix ......... : ${prefix} - C preprocessor ......... : ${CPP} - C compiler ............. : ${CC} - C++ preprocessor ....... : ${CXXCPP} - C++ compiler ........... : ${CXX} - Linker ................. : ${LD} - C preprocessor flags ... : ${CPPFLAGS} - C compiler flags ....... : ${CFLAGS} - C++ compiler flags ..... : ${CXXFLAGS} - Linker flags ........... : ${LDFLAGS} - Extra libraries ........ : ${LIBS} - - Build C++ library ...... : ${enable_cpp} - Enable UTF-8 support ... : ${enable_utf8} - Unicode properties ..... : ${enable_unicode_properties} - Newline char/sequence .. : ${enable_newline} - EBCDIC coding .......... : ${enable_ebcdic} - Rebuild char tables .... : ${enable_rebuild_chartables} - Use stack recursion .... : ${enable_stack_for_recursion} - POSIX mem threshold .... : ${with_posix_malloc_threshold} - Internal link size ..... : ${with_link_size} - Match limit ............ : ${with_match_limit} - Match limit recursion .. : ${with_match_limit_recursion} - Build shared libs ...... : ${enable_shared} - Build static libs ...... : ${enable_static} + Install prefix ........... : ${prefix} + C preprocessor ........... : ${CPP} + C compiler ............... : ${CC} + C++ preprocessor ......... : ${CXXCPP} + C++ compiler ............. : ${CXX} + Linker ................... : ${LD} + C preprocessor flags ..... : ${CPPFLAGS} + C compiler flags ......... : ${CFLAGS} + C++ compiler flags ....... : ${CXXFLAGS} + Linker flags ............. : ${LDFLAGS} + Extra libraries .......... : ${LIBS} + + Build C++ library ........ : ${enable_cpp} + Enable UTF-8 support ..... : ${enable_utf8} + Unicode properties ....... : ${enable_unicode_properties} + Newline char/sequence .... : ${enable_newline} + \R matches only ANYCRLF .. : ${enable_bsr_anycrlf} + EBCDIC coding ............ : ${enable_ebcdic} + Rebuild char tables ...... : ${enable_rebuild_chartables} + Use stack recursion ...... : ${enable_stack_for_recursion} + POSIX mem threshold ...... : ${with_posix_malloc_threshold} + Internal link size ....... : ${with_link_size} + Match limit .............. : ${with_match_limit} + Match limit recursion .... : ${with_match_limit_recursion} + Build shared libs ........ : ${enable_shared} + Build static libs ........ : ${enable_static} EOF diff --git a/doc/html/pcre_compile.html b/doc/html/pcre_compile.html index 3fd9a77..52ec255 100644 --- a/doc/html/pcre_compile.html +++ b/doc/html/pcre_compile.html @@ -43,6 +43,8 @@ The option bits are: <pre> PCRE_ANCHORED Force pattern anchoring PCRE_AUTO_CALLOUT Compile automatic callouts + PCRE_BSR_ANYCRLF \R matches only CR, LF, or CRLF + PCRE_BSR_UNICODE \R matches all Unicode line endings PCRE_CASELESS Do caseless matching PCRE_DOLLAR_ENDONLY $ not to match newline at end PCRE_DOTALL . matches anything including NL diff --git a/doc/html/pcre_config.html b/doc/html/pcre_config.html index 3e8e79d..40dee37 100644 --- a/doc/html/pcre_config.html +++ b/doc/html/pcre_config.html @@ -38,12 +38,15 @@ The available codes are: PCRE_CONFIG_MATCH_LIMIT Internal resource limit PCRE_CONFIG_MATCH_LIMIT_RECURSION Internal recursion depth limit - PCRE_CONFIG_NEWLINE Value of the newline sequence: + PCRE_CONFIG_NEWLINE Value of the default newline sequence: 13 (0x000d) for CR 10 (0x000a) for LF 3338 (0x0d0a) for CRLF -2 for ANYCRLF -1 for ANY + PCRE_CONFIG_BSR Indicates what \R matches by default: + 0 all Unicode line endings + 1 CR, LF, or CRLF only PCRE_CONFIG_POSIX_MALLOC_THRESHOLD Threshold of return slots, above which <b>malloc()</b> is used by diff --git a/doc/html/pcre_dfa_exec.html b/doc/html/pcre_dfa_exec.html index eedbf8c..02e7c8d 100644 --- a/doc/html/pcre_dfa_exec.html +++ b/doc/html/pcre_dfa_exec.html @@ -49,6 +49,8 @@ matching function is <b>pcre_exec()</b>. The arguments for this function are: The options are: <pre> PCRE_ANCHORED Match only at the first position + PCRE_BSR_ANYCRLF \R matches only CR, LF, or CRLF + PCRE_BSR_UNICODE \R matches all Unicode line endings PCRE_NEWLINE_ANY Recognize any Unicode newline sequence PCRE_NEWLINE_ANYCRLF Recognize CR, LF, and CRLF as newline sequences PCRE_NEWLINE_CR Set CR as the newline sequence diff --git a/doc/html/pcre_exec.html b/doc/html/pcre_exec.html index c67544e..86dcc02 100644 --- a/doc/html/pcre_exec.html +++ b/doc/html/pcre_exec.html @@ -45,6 +45,8 @@ offsets to captured substrings. Its arguments are: The options are: <pre> PCRE_ANCHORED Match only at the first position + PCRE_BSR_ANYCRLF \R matches only CR, LF, or CRLF + PCRE_BSR_UNICODE \R matches all Unicode line endings PCRE_NEWLINE_ANY Recognize any Unicode newline sequence PCRE_NEWLINE_ANYCRLF Recognize CR, LF, and CRLF as newline sequences PCRE_NEWLINE_CR Set CR as the newline sequence diff --git a/doc/html/pcreapi.html b/doc/html/pcreapi.html index d5bac79..704dca0 100644 --- a/doc/html/pcreapi.html +++ b/doc/html/pcreapi.html @@ -276,8 +276,12 @@ metacharacters, the handling of #-comments in /x mode, and, when CRLF is a recognized line ending sequence, the match position advancement for a non-anchored pattern. There is more detail about this in the <a href="#execoptions">section on <b>pcre_exec()</b> options</a> -below. The choice of newline convention does not affect the interpretation of -the \n or \r escape sequences. +below. +</P> +<P> +The choice of newline convention does not affect the interpretation of +the \n or \r escape sequences, nor does it affect what \R matches, which is +controlled in a similar way, but by separate options. </P> <br><a name="SEC4" href="#TOC1">MULTITHREADING</a><br> <P> @@ -332,6 +336,13 @@ that is recognized as meaning "newline". The four values that are supported are: 10 for LF, 13 for CR, 3338 for CRLF, -2 for ANYCRLF, and -1 for ANY. The default should normally be the standard sequence for your operating system. <pre> + PCRE_CONFIG_BSR +</pre> +The output is an integer whose value indicates what character sequences the \R +escape sequence matches by default. A value of 0 means that \R matches any +Unicode line ending sequence; a value of 1 means that \R matches only CR, LF, +or CRLF. The default can be overridden when a pattern is compiled or matched. +<pre> PCRE_CONFIG_LINK_SIZE </pre> The output is an integer that contains the number of bytes used for internal @@ -467,6 +478,15 @@ facility, see the <a href="pcrecallout.html"><b>pcrecallout</b></a> documentation. <pre> + PCRE_BSR_ANYCRLF + PCRE_BSR_UNICODE +</pre> +These options (which are mutually exclusive) control what the \R escape +sequence matches. The choice is either to match only CR, LF, or CRLF, or to +match any Unicode newline sequence. The default is specified when PCRE is +built. It can be overridden from within the pattern, or by setting an option +when a compiled pattern is matched. +<pre> PCRE_CASELESS </pre> If this bit is set, letters in the pattern match both upper and lower case @@ -697,7 +717,7 @@ out of use. To avoid confusion, they have not been re-used. 53 internal error: previously-checked referenced subpattern not found 54 DEFINE group contains more than one branch 55 repeating a DEFINE group is not allowed - 56 inconsistent NEWLINE options" + 56 inconsistent NEWLINE options 57 \g is not followed by a braced name or an optionally braced non-zero number 58 (?+ or (?- or (?(+ or (?(- must be followed by a non-zero number @@ -1206,6 +1226,14 @@ matching position. If a pattern was compiled with PCRE_ANCHORED, or turned out to be anchored by virtue of its contents, it cannot be made unachored at matching time. <pre> + PCRE_BSR_ANYCRLF + PCRE_BSR_UNICODE +</pre> +These options (which are mutually exclusive) control what the \R escape +sequence matches. The choice is either to match only CR, LF, or CRLF, or to +match any Unicode newline sequence. These options override the choice that was +made or defaulted when the pattern was compiled. +<pre> PCRE_NEWLINE_CR PCRE_NEWLINE_LF PCRE_NEWLINE_CRLF @@ -1222,7 +1250,7 @@ pattern. <P> When PCRE_NEWLINE_CRLF, PCRE_NEWLINE_ANYCRLF, or PCRE_NEWLINE_ANY is set, and a match attempt for an unanchored pattern fails when the current position is at a -CRLF sequence, and the pattern contains no explicit matches for CR or NL +CRLF sequence, and the pattern contains no explicit matches for CR or LF characters, the match position is advanced by two characters instead of one, in other words, to after the CRLF. </P> @@ -1233,8 +1261,12 @@ set), it does not match the string "\r\nA" because, after failing at the start, it skips both the CR and the LF before retrying. However, the pattern [\r\n]A does match that string, because it contains an explicit CR or LF reference, and so advances only by one character after the first failure. -Note than an explicit CR or LF reference occurs for negated character classes -such as [^X] because they can match CR or LF characters. +</P> +<P> +An explicit match for CR of LF is either a literal appearance of one of those +characters, or one of the \r or \n escape sequences. Implicit matches such as +[^X] do not count, nor does \s (which includes CR and LF in the characters +that it matches). </P> <P> Notwithstanding the above, anomalous effects may still occur when CRLF is a @@ -1915,7 +1947,7 @@ Cambridge CB2 3QH, England. </P> <br><a name="SEC22" href="#TOC1">REVISION</a><br> <P> -Last updated: 21 August 2007 +Last updated: 11 September 2007 <br> Copyright © 1997-2007 University of Cambridge. <br> diff --git a/doc/html/pcrebuild.html b/doc/html/pcrebuild.html index 9f90983..42656ed 100644 --- a/doc/html/pcrebuild.html +++ b/doc/html/pcrebuild.html @@ -18,16 +18,17 @@ man page, in case the conversion went wrong. <li><a name="TOC3" href="#SEC3">UTF-8 SUPPORT</a> <li><a name="TOC4" href="#SEC4">UNICODE CHARACTER PROPERTY SUPPORT</a> <li><a name="TOC5" href="#SEC5">CODE VALUE OF NEWLINE</a> -<li><a name="TOC6" href="#SEC6">BUILDING SHARED AND STATIC LIBRARIES</a> -<li><a name="TOC7" href="#SEC7">POSIX MALLOC USAGE</a> -<li><a name="TOC8" href="#SEC8">HANDLING VERY LARGE PATTERNS</a> -<li><a name="TOC9" href="#SEC9">AVOIDING EXCESSIVE STACK USAGE</a> -<li><a name="TOC10" href="#SEC10">LIMITING PCRE RESOURCE USAGE</a> -<li><a name="TOC11" href="#SEC11">CREATING CHARACTER TABLES AT BUILD TIME</a> -<li><a name="TOC12" href="#SEC12">USING EBCDIC CODE</a> -<li><a name="TOC13" href="#SEC13">SEE ALSO</a> -<li><a name="TOC14" href="#SEC14">AUTHOR</a> -<li><a name="TOC15" href="#SEC15">REVISION</a> +<li><a name="TOC6" href="#SEC6">WHAT \R MATCHES</a> +<li><a name="TOC7" href="#SEC7">BUILDING SHARED AND STATIC LIBRARIES</a> +<li><a name="TOC8" href="#SEC8">POSIX MALLOC USAGE</a> +<li><a name="TOC9" href="#SEC9">HANDLING VERY LARGE PATTERNS</a> +<li><a name="TOC10" href="#SEC10">AVOIDING EXCESSIVE STACK USAGE</a> +<li><a name="TOC11" href="#SEC11">LIMITING PCRE RESOURCE USAGE</a> +<li><a name="TOC12" href="#SEC12">CREATING CHARACTER TABLES AT BUILD TIME</a> +<li><a name="TOC13" href="#SEC13">USING EBCDIC CODE</a> +<li><a name="TOC14" href="#SEC14">SEE ALSO</a> +<li><a name="TOC15" href="#SEC15">AUTHOR</a> +<li><a name="TOC16" href="#SEC16">REVISION</a> </ul> <br><a name="SEC1" href="#TOC1">PCRE BUILD-TIME OPTIONS</a><br> <P> @@ -120,7 +121,18 @@ Whatever line ending convention is selected when PCRE is built can be overridden when the library functions are called. At build time it is conventional to use the standard for your operating system. </P> -<br><a name="SEC6" href="#TOC1">BUILDING SHARED AND STATIC LIBRARIES</a><br> +<br><a name="SEC6" href="#TOC1">WHAT \R MATCHES</a><br> +<P> +By default, the sequence \R in a pattern matches any Unicode newline sequence, +whatever has been selected as the line ending sequence. If you specify +<pre> + --enable-bsr-anycrlf +</pre> +the default is changed so that \R matches only CR, LF, or CRLF. Whatever is +selected when PCRE is built can be overridden when the library functions are +called. +</P> +<br><a name="SEC7" href="#TOC1">BUILDING SHARED AND STATIC LIBRARIES</a><br> <P> The PCRE building process uses <b>libtool</b> to build both shared and static Unix libraries by default. You can suppress one of these by adding one of @@ -130,7 +142,7 @@ Unix libraries by default. You can suppress one of these by adding one of </pre> to the <b>configure</b> command, as required. </P> -<br><a name="SEC7" href="#TOC1">POSIX MALLOC USAGE</a><br> +<br><a name="SEC8" href="#TOC1">POSIX MALLOC USAGE</a><br> <P> When PCRE is called through the POSIX interface (see the <a href="pcreposix.html"><b>pcreposix</b></a> @@ -146,7 +158,7 @@ such as </pre> to the <b>configure</b> command. </P> -<br><a name="SEC8" href="#TOC1">HANDLING VERY LARGE PATTERNS</a><br> +<br><a name="SEC9" href="#TOC1">HANDLING VERY LARGE PATTERNS</a><br> <P> Within a compiled pattern, offset values are used to point from one part to another (for example, from an opening parenthesis to an alternation @@ -162,7 +174,7 @@ to the <b>configure</b> command. The value given must be 2, 3, or 4. Using longer offsets slows down the operation of PCRE because it has to load additional bytes when handling them. </P> -<br><a name="SEC9" href="#TOC1">AVOIDING EXCESSIVE STACK USAGE</a><br> +<br><a name="SEC10" href="#TOC1">AVOIDING EXCESSIVE STACK USAGE</a><br> <P> When matching with the <b>pcre_exec()</b> function, PCRE implements backtracking by making recursive calls to an internal function called <b>match()</b>. In @@ -193,7 +205,7 @@ perform better than <b>malloc()</b> and <b>free()</b>. PCRE runs noticeably more slowly when built in this way. This option affects only the <b>pcre_exec()</b> function; it is not relevant for the the <b>pcre_dfa_exec()</b> function. </P> -<br><a name="SEC10" href="#TOC1">LIMITING PCRE RESOURCE USAGE</a><br> +<br><a name="SEC11" href="#TOC1">LIMITING PCRE RESOURCE USAGE</a><br> <P> Internally, PCRE has a function called <b>match()</b>, which it calls repeatedly (sometimes recursively) when matching a pattern with the <b>pcre_exec()</b> @@ -222,7 +234,7 @@ constraints. However, you can set a lower limit by adding, for example, </pre> to the <b>configure</b> command. This value can also be overridden at run time. </P> -<br><a name="SEC11" href="#TOC1">CREATING CHARACTER TABLES AT BUILD TIME</a><br> +<br><a name="SEC12" href="#TOC1">CREATING CHARACTER TABLES AT BUILD TIME</a><br> <P> PCRE uses fixed tables for processing characters whose code values are less than 256. By default, PCRE is built with a set of tables that are distributed @@ -239,7 +251,7 @@ compiling, because <b>dftables</b> is run on the local host. If you need to create alternative tables when cross compiling, you will have to do so "by hand".) </P> -<br><a name="SEC12" href="#TOC1">USING EBCDIC CODE</a><br> +<br><a name="SEC13" href="#TOC1">USING EBCDIC CODE</a><br> <P> PCRE assumes by default that it will run in an environment where the character code is ASCII (or Unicode, which is a superset of ASCII). This is the case for @@ -252,11 +264,11 @@ to the <b>configure</b> command. This setting implies --enable-rebuild-chartables. You should only use it if you know that you are in an EBCDIC environment (for example, an IBM mainframe operating system). </P> -<br><a name="SEC13" href="#TOC1">SEE ALSO</a><br> +<br><a name="SEC14" href="#TOC1">SEE ALSO</a><br> <P> <b>pcreapi</b>(3), <b>pcre_config</b>(3). </P> -<br><a name="SEC14" href="#TOC1">AUTHOR</a><br> +<br><a name="SEC15" href="#TOC1">AUTHOR</a><br> <P> Philip Hazel <br> @@ -265,9 +277,9 @@ University Computing Service Cambridge CB2 3QH, England. <br> </P> -<br><a name="SEC15" href="#TOC1">REVISION</a><br> +<br><a name="SEC16" href="#TOC1">REVISION</a><br> <P> -Last updated: 30 July 2007 +Last updated: 11 September 2007 <br> Copyright © 1997-2007 University of Cambridge. <br> diff --git a/doc/html/pcrecompat.html b/doc/html/pcrecompat.html index 45f63e0..d1b93d0 100644 --- a/doc/html/pcrecompat.html +++ b/doc/html/pcrecompat.html @@ -134,18 +134,26 @@ only at the first matching position in the subject string. options for <b>pcre_exec()</b> have no Perl equivalents. <br> <br> -(g) The callout facility is PCRE-specific. +(g) The \R escape sequence can be restricted to match only CR, LF, or CRLF +by the PCRE_BSR_ANYCRLF option. <br> <br> -(h) The partial matching facility is PCRE-specific. +(h) The callout facility is PCRE-specific. <br> <br> -(i) Patterns compiled by PCRE can be saved and re-used at a later time, even on +(i) The partial matching facility is PCRE-specific. +<br> +<br> +(j) Patterns compiled by PCRE can be saved and re-used at a later time, even on different hosts that have the other endianness. <br> <br> -(j) The alternative matching function (<b>pcre_dfa_exec()</b>) matches in a +(k) The alternative matching function (<b>pcre_dfa_exec()</b>) matches in a different way and is not Perl-compatible. +<br> +<br> +(l) PCRE recognizes some special sequences such as (*CR) at the start of +a pattern that set overall options that cannot be changed within the pattern. </P> <br><b> AUTHOR @@ -162,7 +170,7 @@ Cambridge CB2 3QH, England. REVISION </b><br> <P> -Last updated: 08 August 2007 +Last updated: 11 September 2007 <br> Copyright © 1997-2007 University of Cambridge. <br> diff --git a/doc/html/pcrepattern.html b/doc/html/pcrepattern.html index d9847d5..76afd97 100644 --- a/doc/html/pcrepattern.html +++ b/doc/html/pcrepattern.html @@ -105,7 +105,15 @@ example, on a Unix system where LF is the default newline sequence, the pattern changes the convention to CR. That pattern matches "a\nb" because LF is no longer a newline. Note that these special settings, which are not Perl-compatible, are recognized only at the very start of a pattern, and that -they must be in upper case. +they must be in upper case. If more than one of them is present, the last one +is used. +</P> +<P> +The newline convention does not affect what the \R escape sequence matches. By +default, this is any Unicode newline sequence, for Perl compatibility. However, +this can be changed; see the description of \R in the section entitled +<a href="#newlineseq">"Newline sequences"</a> +below. </P> <br><a name="SEC3" href="#TOC1">CHARACTERS AND METACHARACTERS</a><br> <P> @@ -391,14 +399,14 @@ 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. -</P> +<a name="newlineseq"></a></P> <br><b> Newline sequences </b><br> <P> -Outside a character class, the escape sequence \R matches any Unicode newline -sequence. This is a Perl 5.10 feature. In non-UTF-8 mode \R is equivalent to -the following: +Outside a character class, by default, the escape sequence \R matches any +Unicode newline sequence. This is a Perl 5.10 feature. In non-UTF-8 mode \R is +equivalent to the following: <pre> (?>\r\n|\n|\x0b|\f|\r|\x85) </pre> @@ -417,6 +425,23 @@ Unicode character property support is not needed for these characters to be recognized. </P> <P> +It is possible to restrict \R to match only CR, LF, or CRLF (instead of the +complete set of Unicode line endings) by setting the option PCRE_BSR_ANYCRLF +either at compile time or when the pattern is matched. This can be made the +default when PCRE is built; if this is the case, the other behaviour can be +requested via the PCRE_BSR_UNICODE option. It is also possible to specify these +settings by starting a pattern string with one of the following sequences: +<pre> + (*BSR_ANYCRLF) CR, LF, or CRLF only + (*BSR_UNICODE) any Unicode newline sequence +</pre> +These override the default and the options given to <b>pcre_compile()</b>, but +they can be overridden by options given to <b>pcre_exec()</b>. Note that these +special settings, which are not Perl-compatible, are recognized only at the +very start of a pattern, and that they must be in upper case. If more than one +of them is present, the last one is used. +</P> +<P> Inside a character class, \R matches the letter "R". <a name="uniextseq"></a></P> <br><b> @@ -2159,7 +2184,7 @@ Cambridge CB2 3QH, England. </P> <br><a name="SEC27" href="#TOC1">REVISION</a><br> <P> -Last updated: 21 August 2007 +Last updated: 11 September 2007 <br> Copyright © 1997-2007 University of Cambridge. <br> diff --git a/doc/html/pcresyntax.html b/doc/html/pcresyntax.html index 6c8ce23..a667f2e 100644 --- a/doc/html/pcresyntax.html +++ b/doc/html/pcresyntax.html @@ -34,10 +34,11 @@ man page, in case the conversion went wrong. <li><a name="TOC19" href="#SEC19">CONDITIONAL PATTERNS</a> <li><a name="TOC20" href="#SEC20">BACKTRACKING CONTROL</a> <li><a name="TOC21" href="#SEC21">NEWLINE CONVENTIONS</a> -<li><a name="TOC22" href="#SEC22">CALLOUTS</a> -<li><a name="TOC23" href="#SEC23">SEE ALSO</a> -<li><a name="TOC24" href="#SEC24">AUTHOR</a> -<li><a name="TOC25" href="#SEC25">REVISION</a> +<li><a name="TOC22" href="#SEC22">WHAT \R MATCHES</a> +<li><a name="TOC23" href="#SEC23">CALLOUTS</a> +<li><a name="TOC24" href="#SEC24">SEE ALSO</a> +<li><a name="TOC25" href="#SEC25">AUTHOR</a> +<li><a name="TOC26" href="#SEC26">REVISION</a> </ul> <br><a name="SEC1" href="#TOC1">PCRE REGULAR EXPRESSION SYNTAX SUMMARY</a><br> <P> @@ -406,19 +407,27 @@ These are recognized only at the very start of a pattern. (*ANY) </PRE> </P> -<br><a name="SEC22" href="#TOC1">CALLOUTS</a><br> +<br><a name="SEC22" href="#TOC1">WHAT \R MATCHES</a><br> +<P> +These are recognized only at the very start of a pattern. +<pre> + (*BSR_ANYCRLF) + (*BSR_UNICODE) +</PRE> +</P> +<br><a name="SEC23" href="#TOC1">CALLOUTS</a><br> <P> <pre> (?C) callout (?Cn) callout with data n </PRE> </P> -<br><a name="SEC23" href="#TOC1">SEE ALSO</a><br> +<br><a name="SEC24" href="#TOC1">SEE ALSO</a><br> <P> <b>pcrepattern</b>(3), <b>pcreapi</b>(3), <b>pcrecallout</b>(3), <b>pcrematching</b>(3), <b>pcre</b>(3). </P> -<br><a name="SEC24" href="#TOC1">AUTHOR</a><br> +<br><a name="SEC25" href="#TOC1">AUTHOR</a><br> <P> Philip Hazel <br> @@ -427,9 +436,9 @@ University Computing Service Cambridge CB2 3QH, England. <br> </P> -<br><a name="SEC25" href="#TOC1">REVISION</a><br> +<br><a name="SEC26" href="#TOC1">REVISION</a><br> <P> -Last updated: 21 August 2007 +Last updated: 11 September 2007 <br> Copyright © 1997-2007 University of Cambridge. <br> diff --git a/doc/html/pcretest.html b/doc/html/pcretest.html index 7ae7fe9..302db2f 100644 --- a/doc/html/pcretest.html +++ b/doc/html/pcretest.html @@ -191,19 +191,21 @@ effect as they do in Perl. For example: The following table shows additional modifiers for setting PCRE options that do not correspond to anything in Perl: <pre> - <b>/A</b> PCRE_ANCHORED - <b>/C</b> PCRE_AUTO_CALLOUT - <b>/E</b> PCRE_DOLLAR_ENDONLY - <b>/f</b> PCRE_FIRSTLINE - <b>/J</b> PCRE_DUPNAMES - <b>/N</b> PCRE_NO_AUTO_CAPTURE - <b>/U</b> PCRE_UNGREEDY - <b>/X</b> PCRE_EXTRA - <b>/<cr></b> PCRE_NEWLINE_CR - <b>/<lf></b> PCRE_NEWLINE_LF - <b>/<crlf></b> PCRE_NEWLINE_CRLF - <b>/<anycrlf></b> PCRE_NEWLINE_ANYCRLF - <b>/<any></b> PCRE_NEWLINE_ANY + <b>/A</b> PCRE_ANCHORED + <b>/C</b> PCRE_AUTO_CALLOUT + <b>/E</b> PCRE_DOLLAR_ENDONLY + <b>/f</b> PCRE_FIRSTLINE + <b>/J</b> PCRE_DUPNAMES + <b>/N</b> PCRE_NO_AUTO_CAPTURE + <b>/U</b> PCRE_UNGREEDY + <b>/X</b> PCRE_EXTRA + <b>/<cr></b> PCRE_NEWLINE_CR + <b>/<lf></b> PCRE_NEWLINE_LF + <b>/<crlf></b> PCRE_NEWLINE_CRLF + <b>/<anycrlf></b> PCRE_NEWLINE_ANYCRLF + <b>/<any></b> PCRE_NEWLINE_ANY + <b>/<bsr_anycrlf></b> PCRE_BSR_ANYCRLF + <b>/<bsr_unicode></b> PCRE_BSR_UNICODE </pre> Those specifying line ending sequences are literal strings as shown, but the letters can be in either case. This example sets multiline matching with CRLF @@ -672,7 +674,7 @@ Cambridge CB2 3QH, England. </P> <br><a name="SEC15" href="#TOC1">REVISION</a><br> <P> -Last updated: 21 August 2007 +Last updated: 11 September 2007 <br> Copyright © 1997-2007 University of Cambridge. <br> diff --git a/doc/pcre.txt b/doc/pcre.txt index f924f6d..3737194 100644 --- a/doc/pcre.txt +++ b/doc/pcre.txt @@ -361,6 +361,19 @@ CODE VALUE OF NEWLINE conventional to use the standard for your operating system. +WHAT \R MATCHES + + By default, the sequence \R in a pattern matches any Unicode newline + sequence, whatever has been selected as the line ending sequence. If + you specify + + --enable-bsr-anycrlf + + the default is changed so that \R matches only CR, LF, or CRLF. What- + ever is selected when PCRE is built can be overridden when the library + functions are called. + + BUILDING SHARED AND STATIC LIBRARIES The PCRE building process uses libtool to build both shared and static @@ -513,7 +526,7 @@ AUTHOR REVISION - Last updated: 30 July 2007 + Last updated: 11 September 2007 Copyright (c) 1997-2007 University of Cambridge. ------------------------------------------------------------------------------ @@ -919,18 +932,21 @@ NEWLINES dollar metacharacters, the handling of #-comments in /x mode, and, when CRLF is a recognized line ending sequence, the match position advance- ment for a non-anchored pattern. There is more detail about this in the - section on pcre_exec() options below. The choice of newline convention - does not affect the interpretation of the \n or \r escape sequences. + section on pcre_exec() options below. + + The choice of newline convention does not affect the interpretation of + the \n or \r escape sequences, nor does it affect what \R matches, + which is controlled in a similar way, but by separate options. MULTITHREADING - The PCRE functions can be used in multi-threading applications, with + The PCRE functions can be used in multi-threading applications, with the proviso that the memory management functions pointed to by pcre_malloc, pcre_free, pcre_stack_malloc, and pcre_stack_free, and the callout function pointed to by pcre_callout, are shared by all threads. - The compiled form of a regular expression is not altered during match- + The compiled form of a regular expression is not altered during match- ing, so the same compiled pattern can safely be used by several threads at once. @@ -938,10 +954,10 @@ MULTITHREADING SAVING PRECOMPILED PATTERNS FOR LATER USE The compiled form of a regular expression can be saved and re-used at a - later time, possibly by a different program, and even on a host other - than the one on which it was compiled. Details are given in the - pcreprecompile documentation. However, compiling a regular expression - with one version of PCRE for use with a different version is not guar- + later time, possibly by a different program, and even on a host other + than the one on which it was compiled. Details are given in the + pcreprecompile documentation. However, compiling a regular expression + with one version of PCRE for use with a different version is not guar- anteed to work and may cause crashes. @@ -949,69 +965,77 @@ CHECKING BUILD-TIME OPTIONS int pcre_config(int what, void *where); - The function pcre_config() makes it possible for a PCRE client to dis- + The function pcre_config() makes it possible for a PCRE client to dis- cover which optional features have been compiled into the PCRE library. - The pcrebuild documentation has more details about these optional fea- + The pcrebuild documentation has more details about these optional fea- tures. - The first argument for pcre_config() is an integer, specifying which + The first argument for pcre_config() is an integer, specifying which information is required; the second argument is a pointer to a variable - into which the information is placed. The following information is + into which the information is placed. The following information is available: PCRE_CONFIG_UTF8 - The output is an integer that is set to one if UTF-8 support is avail- + The output is an integer that is set to one if UTF-8 support is avail- able; otherwise it is set to zero. PCRE_CONFIG_UNICODE_PROPERTIES - The output is an integer that is set to one if support for Unicode + The output is an integer that is set to one if support for Unicode character properties is available; otherwise it is set to zero. PCRE_CONFIG_NEWLINE - The output is an integer whose value specifies the default character - sequence that is recognized as meaning "newline". The four values that + The output is an integer whose value specifies the default character + sequence that is recognized as meaning "newline". The four values that are supported are: 10 for LF, 13 for CR, 3338 for CRLF, -2 for ANYCRLF, - and -1 for ANY. The default should normally be the standard sequence + and -1 for ANY. The default should normally be the standard sequence for your operating system. + PCRE_CONFIG_BSR + + The output is an integer whose value indicates what character sequences + the \R escape sequence matches by default. A value of 0 means that \R + matches any Unicode line ending sequence; a value of 1 means that \R + matches only CR, LF, or CRLF. The default can be overridden when a pat- + tern is compiled or matched. + PCRE_CONFIG_LINK_SIZE - The output is an integer that contains the number of bytes used for + The output is an integer that contains the number of bytes used for internal linkage in compiled regular expressions. The value is 2, 3, or - 4. Larger values allow larger regular expressions to be compiled, at - the expense of slower matching. The default value of 2 is sufficient - for all but the most massive patterns, since it allows the compiled + 4. Larger values allow larger regular expressions to be compiled, at + the expense of slower matching. The default value of 2 is sufficient + for all but the most massive patterns, since it allows the compiled pattern to be up to 64K in size. PCRE_CONFIG_POSIX_MALLOC_THRESHOLD - The output is an integer that contains the threshold above which the - POSIX interface uses malloc() for output vectors. Further details are + The output is an integer that contains the threshold above which the + POSIX interface uses malloc() for output vectors. Further details are given in the pcreposix documentation. PCRE_CONFIG_MATCH_LIMIT The output is an integer that gives the default limit for the number of - internal matching function calls in a pcre_exec() execution. Further + internal matching function calls in a pcre_exec() execution. Further details are given with pcre_exec() below. PCRE_CONFIG_MATCH_LIMIT_RECURSION - The output is an integer that gives the default limit for the depth of - recursion when calling the internal matching function in a pcre_exec() + The output is an integer that gives the default limit for the depth of + recursion when calling the internal matching function in a pcre_exec() execution. Further details are given with pcre_exec() below. PCRE_CONFIG_STACKRECURSE - The output is an integer that is set to one if internal recursion when + The output is an integer that is set to one if internal recursion when running pcre_exec() is implemented by recursive function calls that use - the stack to remember their state. This is the usual way that PCRE is + the stack to remember their state. This is the usual way that PCRE is compiled. The output is zero if PCRE was compiled to use blocks of data - on the heap instead of recursive function calls. In this case, - pcre_stack_malloc and pcre_stack_free are called to manage memory + on the heap instead of recursive function calls. In this case, + pcre_stack_malloc and pcre_stack_free are called to manage memory blocks on the heap, thus avoiding the use of the stack. @@ -1028,55 +1052,55 @@ COMPILING A PATTERN Either of the functions pcre_compile() or pcre_compile2() can be called to compile a pattern into an internal form. The only difference between - the two interfaces is that pcre_compile2() has an additional argument, + the two interfaces is that pcre_compile2() has an additional argument, errorcodeptr, via which a numerical error code can be returned. The pattern is a C string terminated by a binary zero, and is passed in - the pattern argument. A pointer to a single block of memory that is - obtained via pcre_malloc is returned. This contains the compiled code + the pattern argument. A pointer to a single block of memory that is + obtained via pcre_malloc is returned. This contains the compiled code and related data. The pcre type is defined for the returned block; this is a typedef for a structure whose contents are not externally defined. It is up to the caller to free the memory (via pcre_free) when it is no longer required. - Although the compiled code of a PCRE regex is relocatable, that is, it + Although the compiled code of a PCRE regex is relocatable, that is, it does not depend on memory location, the complete pcre data block is not - fully relocatable, because it may contain a copy of the tableptr argu- + fully relocatable, because it may contain a copy of the tableptr argu- ment, which is an address (see below). The options argument contains various bit settings that affect the com- - pilation. It should be zero if no options are required. The available - options are described below. Some of them, in particular, those that - are compatible with Perl, can also be set and unset from within the - pattern (see the detailed description in the pcrepattern documenta- - tion). For these options, the contents of the options argument speci- - fies their initial settings at the start of compilation and execution. - The PCRE_ANCHORED and PCRE_NEWLINE_xxx options can be set at the time + pilation. It should be zero if no options are required. The available + options are described below. Some of them, in particular, those that + are compatible with Perl, can also be set and unset from within the + pattern (see the detailed description in the pcrepattern documenta- + tion). For these options, the contents of the options argument speci- + fies their initial settings at the start of compilation and execution. + The PCRE_ANCHORED and PCRE_NEWLINE_xxx options can be set at the time of matching as well as at compile time. If errptr is NULL, pcre_compile() returns NULL immediately. Otherwise, - if compilation of a pattern fails, pcre_compile() returns NULL, and + if compilation of a pattern fails, pcre_compile() returns NULL, and sets the variable pointed to by errptr to point to a textual error mes- sage. This is a static string that is part of the library. You must not try to free it. The offset from the start of the pattern to the charac- ter where the error was discovered is placed in the variable pointed to - by erroffset, which must not be NULL. If it is, an immediate error is + by erroffset, which must not be NULL. If it is, an immediate error is given. - If pcre_compile2() is used instead of pcre_compile(), and the error- - codeptr argument is not NULL, a non-zero error code number is returned - via this argument in the event of an error. This is in addition to the + If pcre_compile2() is used instead of pcre_compile(), and the error- + codeptr argument is not NULL, a non-zero error code number is returned + via this argument in the event of an error. This is in addition to the textual error message. Error codes and messages are listed below. - If the final argument, tableptr, is NULL, PCRE uses a default set of - character tables that are built when PCRE is compiled, using the - default C locale. Otherwise, tableptr must be an address that is the - result of a call to pcre_maketables(). This value is stored with the - compiled pattern, and used again by pcre_exec(), unless another table + If the final argument, tableptr, is NULL, PCRE uses a default set of + character tables that are built when PCRE is compiled, using the + default C locale. Otherwise, tableptr must be an address that is the + result of a call to pcre_maketables(). This value is stored with the + compiled pattern, and used again by pcre_exec(), unless another table pointer is passed to it. For more discussion, see the section on locale support below. - This code fragment shows a typical straightforward call to pcre_com- + This code fragment shows a typical straightforward call to pcre_com- pile(): pcre *re; @@ -1089,111 +1113,120 @@ COMPILING A PATTERN &erroffset, /* for error offset */ NULL); /* use default character tables */ - The following names for option bits are defined in the pcre.h header + The following names for option bits are defined in the pcre.h header file: PCRE_ANCHORED If this bit is set, the pattern is forced to be "anchored", that is, it - is constrained to match only at the first matching point in the string - that is being searched (the "subject string"). This effect can also be - achieved by appropriate constructs in the pattern itself, which is the + is constrained to match only at the first matching point in the string + that is being searched (the "subject string"). This effect can also be + achieved by appropriate constructs in the pattern itself, which is the only way to do it in Perl. PCRE_AUTO_CALLOUT If this bit is set, pcre_compile() automatically inserts callout items, - all with number 255, before each pattern item. For discussion of the + all with number 255, before each pattern item. For discussion of the callout facility, see the pcrecallout documentation. + PCRE_BSR_ANYCRLF + PCRE_BSR_UNICODE + + These options (which are mutually exclusive) control what the \R escape + sequence matches. The choice is either to match only CR, LF, or CRLF, + or to match any Unicode newline sequence. The default is specified when + PCRE is built. It can be overridden from within the pattern, or by set- + ting an option when a compiled pattern is matched. + PCRE_CASELESS - If this bit is set, letters in the pattern match both upper and lower - case letters. It is equivalent to Perl's /i option, and it can be - changed within a pattern by a (?i) option setting. In UTF-8 mode, PCRE - always understands the concept of case for characters whose values are - less than 128, so caseless matching is always possible. For characters - with higher values, the concept of case is supported if PCRE is com- - piled with Unicode property support, but not otherwise. If you want to - use caseless matching for characters 128 and above, you must ensure - that PCRE is compiled with Unicode property support as well as with + If this bit is set, letters in the pattern match both upper and lower + case letters. It is equivalent to Perl's /i option, and it can be + changed within a pattern by a (?i) option setting. In UTF-8 mode, PCRE + always understands the concept of case for characters whose values are + less than 128, so caseless matching is always possible. For characters + with higher values, the concept of case is supported if PCRE is com- + piled with Unicode property support, but not otherwise. If you want to + use caseless matching for characters 128 and above, you must ensure + that PCRE is compiled with Unicode property support as well as with UTF-8 support. PCRE_DOLLAR_ENDONLY - If this bit is set, a dollar metacharacter in the pattern matches only - at the end of the subject string. Without this option, a dollar also - matches immediately before a newline at the end of the string (but not - before any other newlines). The PCRE_DOLLAR_ENDONLY option is ignored - if PCRE_MULTILINE is set. There is no equivalent to this option in + If this bit is set, a dollar metacharacter in the pattern matches only + at the end of the subject string. Without this option, a dollar also + matches immediately before a newline at the end of the string (but not + before any other newlines). The PCRE_DOLLAR_ENDONLY option is ignored + if PCRE_MULTILINE is set. There is no equivalent to this option in Perl, and no way to set it within a pattern. PCRE_DOTALL If this bit is set, a dot metacharater in the pattern matches all char- - acters, including those that indicate newline. Without it, a dot does - not match when the current position is at a newline. This option is - equivalent to Perl's /s option, and it can be changed within a pattern - by a (?s) option setting. A negative class such as [^a] always matches + acters, including those that indicate newline. Without it, a dot does + not match when the current position is at a newline. This option is + equivalent to Perl's /s option, and it can be changed within a pattern + by a (?s) option setting. A negative class such as [^a] always matches newline characters, independent of the setting of this option. PCRE_DUPNAMES - If this bit is set, names used to identify capturing subpatterns need + If this bit is set, names used to identify capturing subpatterns need not be unique. This can be helpful for certain types of pattern when it - is known that only one instance of the named subpattern can ever be - matched. There are more details of named subpatterns below; see also + is known that only one instance of the named subpattern can ever be + matched. There are more details of named subpatterns below; see also the pcrepattern documentation. PCRE_EXTENDED - If this bit is set, whitespace data characters in the pattern are + If this bit is set, whitespace data characters in the pattern are totally ignored except when escaped or inside a character class. White- space does not include the VT character (code 11). In addition, charac- ters between an unescaped # outside a character class and the next new- - line, inclusive, are also ignored. This is equivalent to Perl's /x - option, and it can be changed within a pattern by a (?x) option set- + line, inclusive, are also ignored. This is equivalent to Perl's /x + option, and it can be changed within a pattern by a (?x) option set- ting. - This option makes it possible to include comments inside complicated - patterns. Note, however, that this applies only to data characters. - Whitespace characters may never appear within special character - sequences in a pattern, for example within the sequence (?( which + This option makes it possible to include comments inside complicated + patterns. Note, however, that this applies only to data characters. + Whitespace characters may never appear within special character + sequences in a pattern, for example within the sequence (?( which introduces a conditional subpattern. PCRE_EXTRA - This option was invented in order to turn on additional functionality - of PCRE that is incompatible with Perl, but it is currently of very - little use. When set, any backslash in a pattern that is followed by a - letter that has no special meaning causes an error, thus reserving - these combinations for future expansion. By default, as in Perl, a - backslash followed by a letter with no special meaning is treated as a - literal. (Perl can, however, be persuaded to give a warning for this.) - There are at present no other features controlled by this option. It + This option was invented in order to turn on additional functionality + of PCRE that is incompatible with Perl, but it is currently of very + little use. When set, any backslash in a pattern that is followed by a + letter that has no special meaning causes an error, thus reserving + these combinations for future expansion. By default, as in Perl, a + backslash followed by a letter with no special meaning is treated as a + literal. (Perl can, however, be persuaded to give a warning for this.) + There are at present no other features controlled by this option. It can also be set by a (?X) option setting within a pattern. PCRE_FIRSTLINE - If this option is set, an unanchored pattern is required to match - before or at the first newline in the subject string, though the + If this option is set, an unanchored pattern is required to match + before or at the first newline in the subject string, though the matched text may continue over the newline. PCRE_MULTILINE - By default, PCRE treats the subject string as consisting of a single - line of characters (even if it actually contains newlines). The "start - of line" metacharacter (^) matches only at the start of the string, - while the "end of line" metacharacter ($) matches only at the end of + By default, PCRE treats the subject string as consisting of a single + line of characters (even if it actually contains newlines). The "start + of line" metacharacter (^) matches only at the start of the string, + while the "end of line" metacharacter ($) matches only at the end of the string, or before a terminating newline (unless PCRE_DOLLAR_ENDONLY is set). This is the same as Perl. - When PCRE_MULTILINE it is set, the "start of line" and "end of line" - constructs match immediately following or immediately before internal - newlines in the subject string, respectively, as well as at the very - start and end. This is equivalent to Perl's /m option, and it can be + When PCRE_MULTILINE it is set, the "start of line" and "end of line" + constructs match immediately following or immediately before internal + newlines in the subject string, respectively, as well as at the very + start and end. This is equivalent to Perl's /m option, and it can be changed within a pattern by a (?m) option setting. If there are no new- - lines in a subject string, or no occurrences of ^ or $ in a pattern, + lines in a subject string, or no occurrences of ^ or $ in a pattern, setting PCRE_MULTILINE has no effect. PCRE_NEWLINE_CR @@ -1202,81 +1235,81 @@ COMPILING A PATTERN PCRE_NEWLINE_ANYCRLF PCRE_NEWLINE_ANY - These options override the default newline definition that was chosen - when PCRE was built. Setting the first or the second specifies that a - newline is indicated by a single character (CR or LF, respectively). - Setting PCRE_NEWLINE_CRLF specifies that a newline is indicated by the - two-character CRLF sequence. Setting PCRE_NEWLINE_ANYCRLF specifies + These options override the default newline definition that was chosen + when PCRE was built. Setting the first or the second specifies that a + newline is indicated by a single character (CR or LF, respectively). + Setting PCRE_NEWLINE_CRLF specifies that a newline is indicated by the + two-character CRLF sequence. Setting PCRE_NEWLINE_ANYCRLF specifies that any of the three preceding sequences should be recognized. Setting - PCRE_NEWLINE_ANY specifies that any Unicode newline sequence should be + PCRE_NEWLINE_ANY specifies that any Unicode newline sequence should be recognized. The Unicode newline sequences are the three just mentioned, - plus the single characters VT (vertical tab, U+000B), FF (formfeed, - U+000C), NEL (next line, U+0085), LS (line separator, U+2028), and PS - (paragraph separator, U+2029). The last two are recognized only in + plus the single characters VT (vertical tab, U+000B), FF (formfeed, + U+000C), NEL (next line, U+0085), LS (line separator, U+2028), and PS + (paragraph separator, U+2029). The last two are recognized only in UTF-8 mode. - The newline setting in the options word uses three bits that are + The newline setting in the options word uses three bits that are treated as a number, giving eight possibilities. Currently only six are - used (default plus the five values above). This means that if you set - more than one newline option, the combination may or may not be sensi- + used (default plus the five values above). This means that if you set + more than one newline option, the combination may or may not be sensi- ble. For example, PCRE_NEWLINE_CR with PCRE_NEWLINE_LF is equivalent to - PCRE_NEWLINE_CRLF, but other combinations may yield unused numbers and + PCRE_NEWLINE_CRLF, but other combinations may yield unused numbers and cause an error. - The only time that a line break is specially recognized when compiling - a pattern is if PCRE_EXTENDED is set, and an unescaped # outside a - character class is encountered. This indicates a comment that lasts - until after the next line break sequence. In other circumstances, line - break sequences are treated as literal data, except that in + The only time that a line break is specially recognized when compiling + a pattern is if PCRE_EXTENDED is set, and an unescaped # outside a + character class is encountered. This indicates a comment that lasts + until after the next line break sequence. In other circumstances, line + break sequences are treated as literal data, except that in PCRE_EXTENDED mode, both CR and LF are treated as whitespace characters and are therefore ignored. The newline option that is set at compile time becomes the default that - is used for pcre_exec() and pcre_dfa_exec(), but it can be overridden. + is used for pcre_exec() and pcre_dfa_exec(), but it can be overridden. PCRE_NO_AUTO_CAPTURE If this option is set, it disables the use of numbered capturing paren- - theses in the pattern. Any opening parenthesis that is not followed by - ? behaves as if it were followed by ?: but named parentheses can still - be used for capturing (and they acquire numbers in the usual way). + theses in the pattern. Any opening parenthesis that is not followed by + ? behaves as if it were followed by ?: but named parentheses can still + be used for capturing (and they acquire numbers in the usual way). There is no equivalent of this option in Perl. PCRE_UNGREEDY - This option inverts the "greediness" of the quantifiers so that they - are not greedy by default, but become greedy if followed by "?". It is - not compatible with Perl. It can also be set by a (?U) option setting + This option inverts the "greediness" of the quantifiers so that they + are not greedy by default, but become greedy if followed by "?". It is + not compatible with Perl. It can also be set by a (?U) option setting within the pattern. PCRE_UTF8 - This option causes PCRE to regard both the pattern and the subject as - strings of UTF-8 characters instead of single-byte character strings. - However, it is available only when PCRE is built to include UTF-8 sup- - port. If not, the use of this option provokes an error. Details of how - this option changes the behaviour of PCRE are given in the section on + This option causes PCRE to regard both the pattern and the subject as + strings of UTF-8 characters instead of single-byte character strings. + However, it is available only when PCRE is built to include UTF-8 sup- + port. If not, the use of this option provokes an error. Details of how + this option changes the behaviour of PCRE are given in the section on UTF-8 support in the main pcre page. PCRE_NO_UTF8_CHECK When PCRE_UTF8 is set, the validity of the pattern as a UTF-8 string is - automatically checked. There is a discussion about the validity of - UTF-8 strings in the main pcre page. If an invalid UTF-8 sequence of - bytes is found, pcre_compile() returns an error. If you already know + automatically checked. There is a discussion about the validity of + UTF-8 strings in the main pcre page. If an invalid UTF-8 sequence of + bytes is found, pcre_compile() returns an error. If you already know that your pattern is valid, and you want to skip this check for perfor- - mance reasons, you can set the PCRE_NO_UTF8_CHECK option. When it is - set, the effect of passing an invalid UTF-8 string as a pattern is - undefined. It may cause your program to crash. Note that this option - can also be passed to pcre_exec() and pcre_dfa_exec(), to suppress the + mance reasons, you can set the PCRE_NO_UTF8_CHECK option. When it is + set, the effect of passing an invalid UTF-8 string as a pattern is + undefined. It may cause your program to crash. Note that this option + can also be passed to pcre_exec() and pcre_dfa_exec(), to suppress the UTF-8 validity checking of subject strings. COMPILATION ERROR CODES - The following table lists the error codes than may be returned by - pcre_compile2(), along with the error messages that may be returned by - both compiling functions. As PCRE has developed, some error codes have + The following table lists the error codes than may be returned by + pcre_compile2(), along with the error messages that may be returned by + both compiling functions. As PCRE has developed, some error codes have fallen out of use. To avoid confusion, they have not been re-used. 0 no error @@ -1332,11 +1365,11 @@ COMPILATION ERROR CODES 50 [this code is not in use] 51 octal value is greater than \377 (not in UTF-8 mode) 52 internal error: overran compiling workspace - 53 internal error: previously-checked referenced subpattern not + 53 internal error: previously-checked referenced subpattern not found 54 DEFINE group contains more than one branch 55 repeating a DEFINE group is not allowed - 56 inconsistent NEWLINE options" + 56 inconsistent NEWLINE options 57 \g is not followed by a braced name or an optionally braced non-zero number 58 (?+ or (?- or (?(+ or (?(- must be followed by a non-zero number @@ -1347,32 +1380,32 @@ STUDYING A PATTERN pcre_extra *pcre_study(const pcre *code, int options const char **errptr); - If a compiled pattern is going to be used several times, it is worth + If a compiled pattern is going to be used several times, it is worth spending more time analyzing it in order to speed up the time taken for - matching. The function pcre_study() takes a pointer to a compiled pat- + matching. The function pcre_study() takes a pointer to a compiled pat- tern as its first argument. If studying the pattern produces additional - information that will help speed up matching, pcre_study() returns a - pointer to a pcre_extra block, in which the study_data field points to + information that will help speed up matching, pcre_study() returns a + pointer to a pcre_extra block, in which the study_data field points to the results of the study. The returned value from pcre_study() can be passed directly to - pcre_exec(). However, a pcre_extra block also contains other fields - that can be set by the caller before the block is passed; these are + pcre_exec(). However, a pcre_extra block also contains other fields + that can be set by the caller before the block is passed; these are described below in the section on matching a pattern. - If studying the pattern does not produce any additional information + If studying the pattern does not produce any additional information pcre_study() returns NULL. In that circumstance, if the calling program - wants to pass any of the other fields to pcre_exec(), it must set up + wants to pass any of the other fields to pcre_exec(), it must set up its own pcre_extra block. - The second argument of pcre_study() contains option bits. At present, + The second argument of pcre_study() contains option bits. At present, no options are defined, and this argument should always be zero. - The third argument for pcre_study() is a pointer for an error message. - If studying succeeds (even if no data is returned), the variable it - points to is set to NULL. Otherwise it is set to point to a textual + The third argument for pcre_study() is a pointer for an error message. + If studying succeeds (even if no data is returned), the variable it + points to is set to NULL. Otherwise it is set to point to a textual error message. This is a static string that is part of the library. You - must not try to free it. You should test the error pointer for NULL + must not try to free it. You should test the error pointer for NULL after calling pcre_study(), to be sure that it has run successfully. This is a typical call to pcre_study(): @@ -1384,62 +1417,62 @@ STUDYING A PATTERN &error); /* set to NULL or points to a message */ At present, studying a pattern is useful only for non-anchored patterns - that do not have a single fixed starting character. A bitmap of possi- + that do not have a single fixed starting character. A bitmap of possi- ble starting bytes is created. LOCALE SUPPORT - PCRE handles caseless matching, and determines whether characters are - letters, digits, or whatever, by reference to a set of tables, indexed - by character value. When running in UTF-8 mode, this applies only to - characters with codes less than 128. Higher-valued codes never match - escapes such as \w or \d, but can be tested with \p if PCRE is built - with Unicode character property support. The use of locales with Uni- - code is discouraged. If you are handling characters with codes greater - than 128, you should either use UTF-8 and Unicode, or use locales, but + PCRE handles caseless matching, and determines whether characters are + letters, digits, or whatever, by reference to a set of tables, indexed + by character value. When running in UTF-8 mode, this applies only to + characters with codes less than 128. Higher-valued codes never match + escapes such as \w or \d, but can be tested with \p if PCRE is built + with Unicode character property support. The use of locales with Uni- + code is discouraged. If you are handling characters with codes greater + than 128, you should either use UTF-8 and Unicode, or use locales, but not try to mix the two. - PCRE contains an internal set of tables that are used when the final - argument of pcre_compile() is NULL. These are sufficient for many + PCRE contains an internal set of tables that are used when the final + argument of pcre_compile() is NULL. These are sufficient for many applications. Normally, the internal tables recognize only ASCII char- acters. However, when PCRE is built, it is possible to cause the inter- nal tables to be rebuilt in the default "C" locale of the local system, which may cause them to be different. - The internal tables can always be overridden by tables supplied by the + The internal tables can always be overridden by tables supplied by the application that calls PCRE. These may be created in a different locale - from the default. As more and more applications change to using Uni- + from the default. As more and more applications change to using Uni- code, the need for this locale support is expected to die away. - External tables are built by calling the pcre_maketables() function, - which has no arguments, in the relevant locale. The result can then be - passed to pcre_compile() or pcre_exec() as often as necessary. For - example, to build and use tables that are appropriate for the French - locale (where accented characters with values greater than 128 are + External tables are built by calling the pcre_maketables() function, + which has no arguments, in the relevant locale. The result can then be + passed to pcre_compile() or pcre_exec() as often as necessary. For + example, to build and use tables that are appropriate for the French + locale (where accented characters with values greater than 128 are treated as letters), the following code could be used: setlocale(LC_CTYPE, "fr_FR"); tables = pcre_maketables(); re = pcre_compile(..., tables); - The locale name "fr_FR" is used on Linux and other Unix-like systems; + The locale name "fr_FR" is used on Linux and other Unix-like systems; if you are using Windows, the name for the French locale is "french". - When pcre_maketables() runs, the tables are built in memory that is - obtained via pcre_malloc. It is the caller's responsibility to ensure - that the memory containing the tables remains available for as long as + When pcre_maketables() runs, the tables are built in memory that is + obtained via pcre_malloc. It is the caller's responsibility to ensure + that the memory containing the tables remains available for as long as it is needed. The pointer that is passed to pcre_compile() is saved with the compiled - pattern, and the same tables are used via this pointer by pcre_study() + pattern, and the same tables are used via this pointer by pcre_study() and normally also by pcre_exec(). Thus, by default, for any single pat- tern, compilation, studying and matching all happen in the same locale, but different patterns can be compiled in different locales. - It is possible to pass a table pointer or NULL (indicating the use of - the internal tables) to pcre_exec(). Although not intended for this - purpose, this facility could be used to match a pattern in a different + It is possible to pass a table pointer or NULL (indicating the use of + the internal tables) to pcre_exec(). Although not intended for this + purpose, this facility could be used to match a pattern in a different locale from the one in which it was compiled. Passing table pointers at run time is discussed below in the section on matching a pattern. @@ -1449,15 +1482,15 @@ INFORMATION ABOUT A PATTERN int pcre_fullinfo(const pcre *code, const pcre_extra *extra, int what, void *where); - The pcre_fullinfo() function returns information about a compiled pat- + The pcre_fullinfo() function returns information about a compiled pat- tern. It replaces the obsolete pcre_info() function, which is neverthe- less retained for backwards compability (and is documented below). - The first argument for pcre_fullinfo() is a pointer to the compiled - pattern. The second argument is the result of pcre_study(), or NULL if - the pattern was not studied. The third argument specifies which piece - of information is required, and the fourth argument is a pointer to a - variable to receive the data. The yield of the function is zero for + The first argument for pcre_fullinfo() is a pointer to the compiled + pattern. The second argument is the result of pcre_study(), or NULL if + the pattern was not studied. The third argument specifies which piece + of information is required, and the fourth argument is a pointer to a + variable to receive the data. The yield of the function is zero for success, or one of the following negative numbers: PCRE_ERROR_NULL the argument code was NULL @@ -1465,9 +1498,9 @@ INFORMATION ABOUT A PATTERN PCRE_ERROR_BADMAGIC the "magic number" was not found PCRE_ERROR_BADOPTION the value of what was invalid - The "magic number" is placed at the start of each compiled pattern as - an simple check against passing an arbitrary memory pointer. Here is a - typical call of pcre_fullinfo(), to obtain the length of the compiled + The "magic number" is placed at the start of each compiled pattern as + an simple check against passing an arbitrary memory pointer. Here is a + typical call of pcre_fullinfo(), to obtain the length of the compiled pattern: int rc; @@ -1478,75 +1511,75 @@ INFORMATION ABOUT A PATTERN PCRE_INFO_SIZE, /* what is required */ &length); /* where to put the data */ - The possible values for the third argument are defined in pcre.h, and + The possible values for the third argument are defined in pcre.h, and are as follows: PCRE_INFO_BACKREFMAX - Return the number of the highest back reference in the pattern. The - fourth argument should point to an int variable. Zero is returned if + Return the number of the highest back reference in the pattern. The + fourth argument should point to an int variable. Zero is returned if there are no back references. PCRE_INFO_CAPTURECOUNT - Return the number of capturing subpatterns in the pattern. The fourth + Return the number of capturing subpatterns in the pattern. The fourth argument should point to an int variable. PCRE_INFO_DEFAULT_TABLES - Return a pointer to the internal default character tables within PCRE. - The fourth argument should point to an unsigned char * variable. This + Return a pointer to the internal default character tables within PCRE. + The fourth argument should point to an unsigned char * variable. This information call is provided for internal use by the pcre_study() func- - tion. External callers can cause PCRE to use its internal tables by + tion. External callers can cause PCRE to use its internal tables by passing a NULL table pointer. PCRE_INFO_FIRSTBYTE - Return information about the first byte of any matched string, for a - non-anchored pattern. The fourth argument should point to an int vari- - able. (This option used to be called PCRE_INFO_FIRSTCHAR; the old name + Return information about the first byte of any matched string, for a + non-anchored pattern. The fourth argument should point to an int vari- + able. (This option used to be called PCRE_INFO_FIRSTCHAR; the old name is still recognized for backwards compatibility.) - If there is a fixed first byte, for example, from a pattern such as + If there is a fixed first byte, for example, from a pattern such as (cat|cow|coyote), its value is returned. Otherwise, if either - (a) the pattern was compiled with the PCRE_MULTILINE option, and every + (a) the pattern was compiled with the PCRE_MULTILINE option, and every branch starts with "^", or (b) every branch of the pattern starts with ".*" and PCRE_DOTALL is not set (if it were set, the pattern would be anchored), - -1 is returned, indicating that the pattern matches only at the start - of a subject string or after any newline within the string. Otherwise + -1 is returned, indicating that the pattern matches only at the start + of a subject string or after any newline within the string. Otherwise -2 is returned. For anchored patterns, -2 is returned. PCRE_INFO_FIRSTTABLE - If the pattern was studied, and this resulted in the construction of a + If the pattern was studied, and this resulted in the construction of a 256-bit table indicating a fixed set of bytes for the first byte in any - matching string, a pointer to the table is returned. Otherwise NULL is - returned. The fourth argument should point to an unsigned char * vari- + matching string, a pointer to the table is returned. Otherwise NULL is + returned. The fourth argument should point to an unsigned char * vari- able. PCRE_INFO_HASCRORLF - Return 1 if the pattern contains any explicit matches for CR or LF - characters, otherwise 0. The fourth argument should point to an int + Return 1 if the pattern contains any explicit matches for CR or LF + characters, otherwise 0. The fourth argument should point to an int variable. PCRE_INFO_JCHANGED - Return 1 if the (?J) option setting is used in the pattern, otherwise + Return 1 if the (?J) option setting is used in the pattern, otherwise 0. The fourth argument should point to an int variable. The (?J) inter- nal option setting changes the local PCRE_DUPNAMES option. PCRE_INFO_LASTLITERAL - Return the value of the rightmost literal byte that must exist in any - matched string, other than at its start, if such a byte has been + Return the value of the rightmost literal byte that must exist in any + matched string, other than at its start, if such a byte has been recorded. The fourth argument should point to an int variable. If there - is no such byte, -1 is returned. For anchored patterns, a last literal - byte is recorded only if it follows something of variable length. For + is no such byte, -1 is returned. For anchored patterns, a last literal + byte is recorded only if it follows something of variable length. For example, for the pattern /^a\d+z\d+/ the returned value is "z", but for /^a\dz\d/ the returned value is -1. @@ -1554,34 +1587,34 @@ INFORMATION ABOUT A PATTERN PCRE_INFO_NAMEENTRYSIZE PCRE_INFO_NAMETABLE - PCRE supports the use of named as well as numbered capturing parenthe- - ses. The names are just an additional way of identifying the parenthe- + PCRE supports the use of named as well as numbered capturing parenthe- + ses. The names are just an additional way of identifying the parenthe- ses, which still acquire numbers. Several convenience functions such as - pcre_get_named_substring() are provided for extracting captured sub- - strings by name. It is also possible to extract the data directly, by - first converting the name to a number in order to access the correct + pcre_get_named_substring() are provided for extracting captured sub- + strings by name. It is also possible to extract the data directly, by + first converting the name to a number in order to access the correct pointers in the output vector (described with pcre_exec() below). To do - the conversion, you need to use the name-to-number map, which is + the conversion, you need to use the name-to-number map, which is described by these three values. The map consists of a number of fixed-size entries. PCRE_INFO_NAMECOUNT gives the number of entries, and PCRE_INFO_NAMEENTRYSIZE gives the size - of each entry; both of these return an int value. The entry size - depends on the length of the longest name. PCRE_INFO_NAMETABLE returns - a pointer to the first entry of the table (a pointer to char). The + of each entry; both of these return an int value. The entry size + depends on the length of the longest name. PCRE_INFO_NAMETABLE returns + a pointer to the first entry of the table (a pointer to char). The first two bytes of each entry are the number of the capturing parenthe- - sis, most significant byte first. The rest of the entry is the corre- - sponding name, zero terminated. The names are in alphabetical order. + sis, most significant byte first. The rest of the entry is the corre- + sponding name, zero terminated. The names are in alphabetical order. When PCRE_DUPNAMES is set, duplicate names are in order of their paren- - theses numbers. For example, consider the following pattern (assume - PCRE_EXTENDED is set, so white space - including newlines - is + theses numbers. For example, consider the following pattern (assume + PCRE_EXTENDED is set, so white space - including newlines - is ignored): (?<date> (?<year>(\d\d)?\d\d) - (?<month>\d\d) - (?<day>\d\d) ) - There are four named subpatterns, so the table has four entries, and - each entry in the table is eight bytes long. The table is as follows, + There are four named subpatterns, so the table has four entries, and + each entry in the table is eight bytes long. The table is as follows, with non-printing bytes shows in hexadecimal, and undefined bytes shown as ??: @@ -1590,29 +1623,29 @@ INFORMATION ABOUT A PATTERN 00 04 m o n t h 00 00 02 y e a r 00 ?? - When writing code to extract data from named subpatterns using the - name-to-number map, remember that the length of the entries is likely + When writing code to extract data from named subpatterns using the + name-to-number map, remember that the length of the entries is likely to be different for each compiled pattern. PCRE_INFO_OKPARTIAL - Return 1 if the pattern can be used for partial matching, otherwise 0. - The fourth argument should point to an int variable. The pcrepartial - documentation lists the restrictions that apply to patterns when par- + Return 1 if the pattern can be used for partial matching, otherwise 0. + The fourth argument should point to an int variable. The pcrepartial + documentation lists the restrictions that apply to patterns when par- tial matching is used. PCRE_INFO_OPTIONS - Return a copy of the options with which the pattern was compiled. The - fourth argument should point to an unsigned long int variable. These + Return a copy of the options with which the pattern was compiled. The + fourth argument should point to an unsigned long int variable. These option bits are those specified in the call to pcre_compile(), modified by any top-level option settings at the start of the pattern itself. In - other words, they are the options that will be in force when matching - starts. For example, if the pattern /(?im)abc(?-i)d/ is compiled with - the PCRE_EXTENDED option, the result is PCRE_CASELESS, PCRE_MULTILINE, + other words, they are the options that will be in force when matching + starts. For example, if the pattern /(?im)abc(?-i)d/ is compiled with + the PCRE_EXTENDED option, the result is PCRE_CASELESS, PCRE_MULTILINE, and PCRE_EXTENDED. - A pattern is automatically anchored by PCRE if all of its top-level + A pattern is automatically anchored by PCRE if all of its top-level alternatives begin with one of the following: ^ unless PCRE_MULTILINE is set @@ -1626,7 +1659,7 @@ INFORMATION ABOUT A PATTERN PCRE_INFO_SIZE - Return the size of the compiled pattern, that is, the value that was + Return the size of the compiled pattern, that is, the value that was passed as the argument to pcre_malloc() when PCRE was getting memory in which to place the compiled data. The fourth argument should point to a size_t variable. @@ -1634,9 +1667,9 @@ INFORMATION ABOUT A PATTERN PCRE_INFO_STUDYSIZE Return the size of the data block pointed to by the study_data field in - a pcre_extra block. That is, it is the value that was passed to + a pcre_extra block. That is, it is the value that was passed to pcre_malloc() when PCRE was getting memory into which to place the data - created by pcre_study(). The fourth argument should point to a size_t + created by pcre_study(). The fourth argument should point to a size_t variable. @@ -1644,21 +1677,21 @@ OBSOLETE INFO FUNCTION int pcre_info(const pcre *code, int *optptr, int *firstcharptr); - The pcre_info() function is now obsolete because its interface is too - restrictive to return all the available data about a compiled pattern. - New programs should use pcre_fullinfo() instead. The yield of - pcre_info() is the number of capturing subpatterns, or one of the fol- + The pcre_info() function is now obsolete because its interface is too + restrictive to return all the available data about a compiled pattern. + New programs should use pcre_fullinfo() instead. The yield of + pcre_info() is the number of capturing subpatterns, or one of the fol- lowing negative numbers: PCRE_ERROR_NULL the argument code was NULL PCRE_ERROR_BADMAGIC the "magic number" was not found - If the optptr argument is not NULL, a copy of the options with which - the pattern was compiled is placed in the integer it points to (see + If the optptr argument is not NULL, a copy of the options with which + the pattern was compiled is placed in the integer it points to (see PCRE_INFO_OPTIONS above). - If the pattern is not anchored and the firstcharptr argument is not - NULL, it is used to pass back information about the first character of + If the pattern is not anchored and the firstcharptr argument is not + NULL, it is used to pass back information about the first character of any matched string (see PCRE_INFO_FIRSTBYTE above). @@ -1666,21 +1699,21 @@ REFERENCE COUNTS int pcre_refcount(pcre *code, int adjust); - The pcre_refcount() function is used to maintain a reference count in + The pcre_refcount() function is used to maintain a reference count in the data block that contains a compiled pattern. It is provided for the - benefit of applications that operate in an object-oriented manner, + benefit of applications that operate in an object-oriented manner, where different parts of the application may be using the same compiled pattern, but you want to free the block when they are all done. When a pattern is compiled, the reference count field is initialized to - zero. It is changed only by calling this function, whose action is to - add the adjust value (which may be positive or negative) to it. The + zero. It is changed only by calling this function, whose action is to + add the adjust value (which may be positive or negative) to it. The yield of the function is the new value. However, the value of the count - is constrained to lie between 0 and 65535, inclusive. If the new value + is constrained to lie between 0 and 65535, inclusive. If the new value is outside these limits, it is forced to the appropriate limit value. - Except when it is zero, the reference count is not correctly preserved - if a pattern is compiled on one host and then transferred to a host + Except when it is zero, the reference count is not correctly preserved + if a pattern is compiled on one host and then transferred to a host whose byte-order is different. (This seems a highly unlikely scenario.) @@ -1690,18 +1723,18 @@ MATCHING A PATTERN: THE TRADITIONAL FUNCTION const char *subject, int length, int startoffset, int options, int *ovector, int ovecsize); - The function pcre_exec() is called to match a subject string against a - compiled pattern, which is passed in the code argument. If the pattern + The function pcre_exec() is called to match a subject string against a + compiled pattern, which is passed in the code argument. If the pattern has been studied, the result of the study should be passed in the extra - argument. This function is the main matching facility of the library, + argument. This function is the main matching facility of the library, and it operates in a Perl-like manner. For specialist use there is also - an alternative matching function, which is described below in the sec- + an alternative matching function, which is described below in the sec- tion about the pcre_dfa_exec() function. - In most applications, the pattern will have been compiled (and option- - ally studied) in the same process that calls pcre_exec(). However, it + In most applications, the pattern will have been compiled (and option- + ally studied) in the same process that calls pcre_exec(). However, it is possible to save compiled patterns and study data, and then use them - later in different processes, possibly even on different hosts. For a + later in different processes, possibly even on different hosts. For a discussion about this, see the pcreprecompile documentation. Here is an example of a simple call to pcre_exec(): @@ -1720,10 +1753,10 @@ MATCHING A PATTERN: THE TRADITIONAL FUNCTION Extra data for pcre_exec() - If the extra argument is not NULL, it must point to a pcre_extra data - block. The pcre_study() function returns such a block (when it doesn't - return NULL), but you can also create one for yourself, and pass addi- - tional information in it. The pcre_extra block contains the following + If the extra argument is not NULL, it must point to a pcre_extra data + block. The pcre_study() function returns such a block (when it doesn't + return NULL), but you can also create one for yourself, and pass addi- + tional information in it. The pcre_extra block contains the following fields (not necessarily in this order): unsigned long int flags; @@ -1733,7 +1766,7 @@ MATCHING A PATTERN: THE TRADITIONAL FUNCTION void *callout_data; const unsigned char *tables; - The flags field is a bitmap that specifies which of the other fields + The flags field is a bitmap that specifies which of the other fields are set. The flag bits are: PCRE_EXTRA_STUDY_DATA @@ -1742,77 +1775,85 @@ MATCHING A PATTERN: THE TRADITIONAL FUNCTION PCRE_EXTRA_CALLOUT_DATA PCRE_EXTRA_TABLES - Other flag bits should be set to zero. The study_data field is set in - the pcre_extra block that is returned by pcre_study(), together with + Other flag bits should be set to zero. The study_data field is set in + the pcre_extra block that is returned by pcre_study(), together with the appropriate flag bit. You should not set this yourself, but you may - add to the block by setting the other fields and their corresponding + add to the block by setting the other fields and their corresponding flag bits. The match_limit field provides a means of preventing PCRE from using up - a vast amount of resources when running patterns that are not going to - match, but which have a very large number of possibilities in their - search trees. The classic example is the use of nested unlimited + a vast amount of resources when running patterns that are not going to + match, but which have a very large number of possibilities in their + search trees. The classic example is the use of nested unlimited repeats. - Internally, PCRE uses a function called match() which it calls repeat- - edly (sometimes recursively). The limit set by match_limit is imposed - on the number of times this function is called during a match, which - has the effect of limiting the amount of backtracking that can take + Internally, PCRE uses a function called match() which it calls repeat- + edly (sometimes recursively). The limit set by match_limit is imposed + on the number of times this function is called during a match, which + has the effect of limiting the amount of backtracking that can take place. For patterns that are not anchored, the count restarts from zero for each position in the subject string. - The default value for the limit can be set when PCRE is built; the - default default is 10 million, which handles all but the most extreme - cases. You can override the default by suppling pcre_exec() with a - pcre_extra block in which match_limit is set, and - PCRE_EXTRA_MATCH_LIMIT is set in the flags field. If the limit is + The default value for the limit can be set when PCRE is built; the + default default is 10 million, which handles all but the most extreme + cases. You can override the default by suppling pcre_exec() with a + pcre_extra block in which match_limit is set, and + PCRE_EXTRA_MATCH_LIMIT is set in the flags field. If the limit is exceeded, pcre_exec() returns PCRE_ERROR_MATCHLIMIT. - The match_limit_recursion field is similar to match_limit, but instead + The match_limit_recursion field is similar to match_limit, but instead of limiting the total number of times that match() is called, it limits - the depth of recursion. The recursion depth is a smaller number than - the total number of calls, because not all calls to match() are recur- + the depth of recursion. The recursion depth is a smaller number than + the total number of calls, because not all calls to match() are recur- sive. This limit is of use only if it is set smaller than match_limit. - Limiting the recursion depth limits the amount of stack that can be + Limiting the recursion depth limits the amount of stack that can be used, or, when PCRE has been compiled to use memory on the heap instead of the stack, the amount of heap memory that can be used. - The default value for match_limit_recursion can be set when PCRE is - built; the default default is the same value as the default for - match_limit. You can override the default by suppling pcre_exec() with - a pcre_extra block in which match_limit_recursion is set, and - PCRE_EXTRA_MATCH_LIMIT_RECURSION is set in the flags field. If the + The default value for match_limit_recursion can be set when PCRE is + built; the default default is the same value as the default for + match_limit. You can override the default by suppling pcre_exec() with + a pcre_extra block in which match_limit_recursion is set, and + PCRE_EXTRA_MATCH_LIMIT_RECURSION is set in the flags field. If the limit is exceeded, pcre_exec() returns PCRE_ERROR_RECURSIONLIMIT. - The pcre_callout field is used in conjunction with the "callout" fea- + The pcre_callout field is used in conjunction with the "callout" fea- ture, which is described in the pcrecallout documentation. - The tables field is used to pass a character tables pointer to - pcre_exec(); this overrides the value that is stored with the compiled - pattern. A non-NULL value is stored with the compiled pattern only if - custom tables were supplied to pcre_compile() via its tableptr argu- + The tables field is used to pass a character tables pointer to + pcre_exec(); this overrides the value that is stored with the compiled + pattern. A non-NULL value is stored with the compiled pattern only if + custom tables were supplied to pcre_compile() via its tableptr argu- ment. If NULL is passed to pcre_exec() using this mechanism, it forces - PCRE's internal tables to be used. This facility is helpful when re- - using patterns that have been saved after compiling with an external - set of tables, because the external tables might be at a different - address when pcre_exec() is called. See the pcreprecompile documenta- + PCRE's internal tables to be used. This facility is helpful when re- + using patterns that have been saved after compiling with an external + set of tables, because the external tables might be at a different + address when pcre_exec() is called. See the pcreprecompile documenta- tion for a discussion of saving compiled patterns for later use. Option bits for pcre_exec() - The unused bits of the options argument for pcre_exec() must be zero. - The only bits that may be set are PCRE_ANCHORED, PCRE_NEWLINE_xxx, + The unused bits of the options argument for pcre_exec() must be zero. + The only bits that may be set are PCRE_ANCHORED, PCRE_NEWLINE_xxx, PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, PCRE_NO_UTF8_CHECK and PCRE_PARTIAL. PCRE_ANCHORED - The PCRE_ANCHORED option limits pcre_exec() to matching at the first - matching position. If a pattern was compiled with PCRE_ANCHORED, or - turned out to be anchored by virtue of its contents, it cannot be made + The PCRE_ANCHORED option limits pcre_exec() to matching at the first + matching position. If a pattern was compiled with PCRE_ANCHORED, or + turned out to be anchored by virtue of its contents, it cannot be made unachored at matching time. + PCRE_BSR_ANYCRLF + PCRE_BSR_UNICODE + + These options (which are mutually exclusive) control what the \R escape + sequence matches. The choice is either to match only CR, LF, or CRLF, + or to match any Unicode newline sequence. These options override the + choice that was made or defaulted when the pattern was compiled. + PCRE_NEWLINE_CR PCRE_NEWLINE_LF PCRE_NEWLINE_CRLF @@ -1829,7 +1870,7 @@ MATCHING A PATTERN: THE TRADITIONAL FUNCTION When PCRE_NEWLINE_CRLF, PCRE_NEWLINE_ANYCRLF, or PCRE_NEWLINE_ANY is set, and a match attempt for an unanchored pattern fails when the cur- rent position is at a CRLF sequence, and the pattern contains no - explicit matches for CR or NL characters, the match position is + explicit matches for CR or LF characters, the match position is advanced by two characters instead of one, in other words, to after the CRLF. @@ -1839,194 +1880,197 @@ MATCHING A PATTERN: THE TRADITIONAL FUNCTION failing at the start, it skips both the CR and the LF before retrying. However, the pattern [\r\n]A does match that string, because it con- tains an explicit CR or LF reference, and so advances only by one char- - acter after the first failure. Note than an explicit CR or LF refer- - ence occurs for negated character classes such as [^X] because they can - match CR or LF characters. + acter after the first failure. + + An explicit match for CR of LF is either a literal appearance of one of + those characters, or one of the \r or \n escape sequences. Implicit + matches such as [^X] do not count, nor does \s (which includes CR and + LF in the characters that it matches). - Notwithstanding the above, anomalous effects may still occur when CRLF + Notwithstanding the above, anomalous effects may still occur when CRLF is a valid newline sequence and explicit \r or \n escapes appear in the pattern. PCRE_NOTBOL This option specifies that first character of the subject string is not - the beginning of a line, so the circumflex metacharacter should not - match before it. Setting this without PCRE_MULTILINE (at compile time) - causes circumflex never to match. This option affects only the behav- + the beginning of a line, so the circumflex metacharacter should not + match before it. Setting this without PCRE_MULTILINE (at compile time) + causes circumflex never to match. This option affects only the behav- iour of the circumflex metacharacter. It does not affect \A. PCRE_NOTEOL This option specifies that the end of the subject string is not the end - of a line, so the dollar metacharacter should not match it nor (except - in multiline mode) a newline immediately before it. Setting this with- + of a line, so the dollar metacharacter should not match it nor (except + in multiline mode) a newline immediately before it. Setting this with- out PCRE_MULTILINE (at compile time) causes dollar never to match. This - option affects only the behaviour of the dollar metacharacter. It does + option affects only the behaviour of the dollar metacharacter. It does not affect \Z or \z. PCRE_NOTEMPTY An empty string is not considered to be a valid match if this option is - set. If there are alternatives in the pattern, they are tried. If all - the alternatives match the empty string, the entire match fails. For + set. If there are alternatives in the pattern, they are tried. If all + the alternatives match the empty string, the entire match fails. For example, if the pattern a?b? - is applied to a string not beginning with "a" or "b", it matches the - empty string at the start of the subject. With PCRE_NOTEMPTY set, this + is applied to a string not beginning with "a" or "b", it matches the + empty string at the start of the subject. With PCRE_NOTEMPTY set, this match is not valid, so PCRE searches further into the string for occur- rences of "a" or "b". Perl has no direct equivalent of PCRE_NOTEMPTY, but it does make a spe- - cial case of a pattern match of the empty string within its split() - function, and when using the /g modifier. It is possible to emulate + cial case of a pattern match of the empty string within its split() + function, and when using the /g modifier. It is possible to emulate Perl's behaviour after matching a null string by first trying the match again at the same offset with PCRE_NOTEMPTY and PCRE_ANCHORED, and then - if that fails by advancing the starting offset (see below) and trying + if that fails by advancing the starting offset (see below) and trying an ordinary match again. There is some code that demonstrates how to do this in the pcredemo.c sample program. PCRE_NO_UTF8_CHECK When PCRE_UTF8 is set at compile time, the validity of the subject as a - UTF-8 string is automatically checked when pcre_exec() is subsequently - called. The value of startoffset is also checked to ensure that it - points to the start of a UTF-8 character. There is a discussion about - the validity of UTF-8 strings in the section on UTF-8 support in the - main pcre page. If an invalid UTF-8 sequence of bytes is found, - pcre_exec() returns the error PCRE_ERROR_BADUTF8. If startoffset con- + UTF-8 string is automatically checked when pcre_exec() is subsequently + called. The value of startoffset is also checked to ensure that it + points to the start of a UTF-8 character. There is a discussion about + the validity of UTF-8 strings in the section on UTF-8 support in the + main pcre page. If an invalid UTF-8 sequence of bytes is found, + pcre_exec() returns the error PCRE_ERROR_BADUTF8. If startoffset con- tains an invalid value, PCRE_ERROR_BADUTF8_OFFSET is returned. - If you already know that your subject is valid, and you want to skip - these checks for performance reasons, you can set the - PCRE_NO_UTF8_CHECK option when calling pcre_exec(). You might want to - do this for the second and subsequent calls to pcre_exec() if you are - making repeated calls to find all the matches in a single subject - string. However, you should be sure that the value of startoffset - points to the start of a UTF-8 character. When PCRE_NO_UTF8_CHECK is - set, the effect of passing an invalid UTF-8 string as a subject, or a - value of startoffset that does not point to the start of a UTF-8 char- + If you already know that your subject is valid, and you want to skip + these checks for performance reasons, you can set the + PCRE_NO_UTF8_CHECK option when calling pcre_exec(). You might want to + do this for the second and subsequent calls to pcre_exec() if you are + making repeated calls to find all the matches in a single subject + string. However, you should be sure that the value of startoffset + points to the start of a UTF-8 character. When PCRE_NO_UTF8_CHECK is + set, the effect of passing an invalid UTF-8 string as a subject, or a + value of startoffset that does not point to the start of a UTF-8 char- acter, is undefined. Your program may crash. PCRE_PARTIAL - This option turns on the partial matching feature. If the subject - string fails to match the pattern, but at some point during the match- - ing process the end of the subject was reached (that is, the subject - partially matches the pattern and the failure to match occurred only - because there were not enough subject characters), pcre_exec() returns - PCRE_ERROR_PARTIAL instead of PCRE_ERROR_NOMATCH. When PCRE_PARTIAL is - used, there are restrictions on what may appear in the pattern. These + This option turns on the partial matching feature. If the subject + string fails to match the pattern, but at some point during the match- + ing process the end of the subject was reached (that is, the subject + partially matches the pattern and the failure to match occurred only + because there were not enough subject characters), pcre_exec() returns + PCRE_ERROR_PARTIAL instead of PCRE_ERROR_NOMATCH. When PCRE_PARTIAL is + used, there are restrictions on what may appear in the pattern. These are discussed in the pcrepartial documentation. The string to be matched by pcre_exec() - The subject string is passed to pcre_exec() as a pointer in subject, a - length in length, and a starting byte offset in startoffset. In UTF-8 - mode, the byte offset must point to the start of a UTF-8 character. - Unlike the pattern string, the subject may contain binary zero bytes. - When the starting offset is zero, the search for a match starts at the + The subject string is passed to pcre_exec() as a pointer in subject, a + length in length, and a starting byte offset in startoffset. In UTF-8 + mode, the byte offset must point to the start of a UTF-8 character. + Unlike the pattern string, the subject may contain binary zero bytes. + When the starting offset is zero, the search for a match starts at the beginning of the subject, and this is by far the most common case. - A non-zero starting offset is useful when searching for another match - in the same subject by calling pcre_exec() again after a previous suc- - cess. Setting startoffset differs from just passing over a shortened - string and setting PCRE_NOTBOL in the case of a pattern that begins + A non-zero starting offset is useful when searching for another match + in the same subject by calling pcre_exec() again after a previous suc- + cess. Setting startoffset differs from just passing over a shortened + string and setting PCRE_NOTBOL in the case of a pattern that begins with any kind of lookbehind. For example, consider the pattern \Biss\B - which finds occurrences of "iss" in the middle of words. (\B matches - only if the current position in the subject is not a word boundary.) - When applied to the string "Mississipi" the first call to pcre_exec() - finds the first occurrence. If pcre_exec() is called again with just - the remainder of the subject, namely "issipi", it does not match, + which finds occurrences of "iss" in the middle of words. (\B matches + only if the current position in the subject is not a word boundary.) + When applied to the string "Mississipi" the first call to pcre_exec() + finds the first occurrence. If pcre_exec() is called again with just + the remainder of the subject, namely "issipi", it does not match, because \B is always false at the start of the subject, which is deemed - to be a word boundary. However, if pcre_exec() is passed the entire + to be a word boundary. However, if pcre_exec() is passed the entire string again, but with startoffset set to 4, it finds the second occur- - rence of "iss" because it is able to look behind the starting point to + rence of "iss" because it is able to look behind the starting point to discover that it is preceded by a letter. - If a non-zero starting offset is passed when the pattern is anchored, + If a non-zero starting offset is passed when the pattern is anchored, one attempt to match at the given offset is made. This can only succeed - if the pattern does not require the match to be at the start of the + if the pattern does not require the match to be at the start of the subject. How pcre_exec() returns captured substrings - In general, a pattern matches a certain portion of the subject, and in - addition, further substrings from the subject may be picked out by - parts of the pattern. Following the usage in Jeffrey Friedl's book, - this is called "capturing" in what follows, and the phrase "capturing - subpattern" is used for a fragment of a pattern that picks out a sub- - string. PCRE supports several other kinds of parenthesized subpattern + In general, a pattern matches a certain portion of the subject, and in + addition, further substrings from the subject may be picked out by + parts of the pattern. Following the usage in Jeffrey Friedl's book, + this is called "capturing" in what follows, and the phrase "capturing + subpattern" is used for a fragment of a pattern that picks out a sub- + string. PCRE supports several other kinds of parenthesized subpattern that do not cause substrings to be captured. - Captured substrings are returned to the caller via a vector of integer - offsets whose address is passed in ovector. The number of elements in - the vector is passed in ovecsize, which must be a non-negative number. + Captured substrings are returned to the caller via a vector of integer + offsets whose address is passed in ovector. The number of elements in + the vector is passed in ovecsize, which must be a non-negative number. Note: this argument is NOT the size of ovector in bytes. - The first two-thirds of the vector is used to pass back captured sub- - strings, each substring using a pair of integers. The remaining third - of the vector is used as workspace by pcre_exec() while matching cap- - turing subpatterns, and is not available for passing back information. - The length passed in ovecsize should always be a multiple of three. If + The first two-thirds of the vector is used to pass back captured sub- + strings, each substring using a pair of integers. The remaining third + of the vector is used as workspace by pcre_exec() while matching cap- + turing subpatterns, and is not available for passing back information. + The length passed in ovecsize should always be a multiple of three. If it is not, it is rounded down. - When a match is successful, information about captured substrings is - returned in pairs of integers, starting at the beginning of ovector, - and continuing up to two-thirds of its length at the most. The first + When a match is successful, information about captured substrings is + returned in pairs of integers, starting at the beginning of ovector, + and continuing up to two-thirds of its length at the most. The first element of a pair is set to the offset of the first character in a sub- - string, and the second is set to the offset of the first character - after the end of a substring. The first pair, ovector[0] and ovec- - tor[1], identify the portion of the subject string matched by the - entire pattern. The next pair is used for the first capturing subpat- + string, and the second is set to the offset of the first character + after the end of a substring. The first pair, ovector[0] and ovec- + tor[1], identify the portion of the subject string matched by the + entire pattern. The next pair is used for the first capturing subpat- tern, and so on. The value returned by pcre_exec() is one more than the highest numbered pair that has been set. For example, if two substrings - have been captured, the returned value is 3. If there are no capturing - subpatterns, the return value from a successful match is 1, indicating + have been captured, the returned value is 3. If there are no capturing + subpatterns, the return value from a successful match is 1, indicating that just the first pair of offsets has been set. If a capturing subpattern is matched repeatedly, it is the last portion of the string that it matched that is returned. - If the vector is too small to hold all the captured substring offsets, + If the vector is too small to hold all the captured substring offsets, it is used as far as possible (up to two-thirds of its length), and the - function returns a value of zero. In particular, if the substring off- + function returns a value of zero. In particular, if the substring off- sets are not of interest, pcre_exec() may be called with ovector passed - as NULL and ovecsize as zero. However, if the pattern contains back - references and the ovector is not big enough to remember the related - substrings, PCRE has to get additional memory for use during matching. + as NULL and ovecsize as zero. However, if the pattern contains back + references and the ovector is not big enough to remember the related + substrings, PCRE has to get additional memory for use during matching. Thus it is usually advisable to supply an ovector. - The pcre_info() function can be used to find out how many capturing - subpatterns there are in a compiled pattern. The smallest size for - ovector that will allow for n captured substrings, in addition to the + The pcre_info() function can be used to find out how many capturing + subpatterns there are in a compiled pattern. The smallest size for + ovector that will allow for n captured substrings, in addition to the offsets of the substring matched by the whole pattern, is (n+1)*3. - It is possible for capturing subpattern number n+1 to match some part + It is possible for capturing subpattern number n+1 to match some part of the subject when subpattern n has not been used at all. For example, - if the string "abc" is matched against the pattern (a|(z))(bc) the + if the string "abc" is matched against the pattern (a|(z))(bc) the return from the function is 4, and subpatterns 1 and 3 are matched, but - 2 is not. When this happens, both values in the offset pairs corre- + 2 is not. When this happens, both values in the offset pairs corre- sponding to unused subpatterns are set to -1. - Offset values that correspond to unused subpatterns at the end of the - expression are also set to -1. For example, if the string "abc" is - matched against the pattern (abc)(x(yz)?)? subpatterns 2 and 3 are not - matched. The return from the function is 2, because the highest used + Offset values that correspond to unused subpatterns at the end of the + expression are also set to -1. For example, if the string "abc" is + matched against the pattern (abc)(x(yz)?)? subpatterns 2 and 3 are not + matched. The return from the function is 2, because the highest used capturing subpattern number is 1. However, you can refer to the offsets - for the second and third capturing subpatterns if you wish (assuming + for the second and third capturing subpatterns if you wish (assuming the vector is large enough, of course). - Some convenience functions are provided for extracting the captured + Some convenience functions are provided for extracting the captured substrings as separate strings. These are described below. Error return values from pcre_exec() - If pcre_exec() fails, it returns a negative number. The following are + If pcre_exec() fails, it returns a negative number. The following are defined in the header file: PCRE_ERROR_NOMATCH (-1) @@ -2035,7 +2079,7 @@ MATCHING A PATTERN: THE TRADITIONAL FUNCTION PCRE_ERROR_NULL (-2) - Either code or subject was passed as NULL, or ovector was NULL and + Either code or subject was passed as NULL, or ovector was NULL and ovecsize was not zero. PCRE_ERROR_BADOPTION (-3) @@ -2044,79 +2088,79 @@ MATCHING A PATTERN: THE TRADITIONAL FUNCTION PCRE_ERROR_BADMAGIC (-4) - PCRE stores a 4-byte "magic number" at the start of the compiled code, + PCRE stores a 4-byte "magic number" at the start of the compiled code, to catch the case when it is passed a junk pointer and to detect when a pattern that was compiled in an environment of one endianness is run in - an environment with the other endianness. This is the error that PCRE + an environment with the other endianness. This is the error that PCRE gives when the magic number is not present. PCRE_ERROR_UNKNOWN_OPCODE (-5) While running the pattern match, an unknown item was encountered in the - compiled pattern. This error could be caused by a bug in PCRE or by + compiled pattern. This error could be caused by a bug in PCRE or by overwriting of the compiled pattern. PCRE_ERROR_NOMEMORY (-6) - If a pattern contains back references, but the ovector that is passed + If a pattern contains back references, but the ovector that is passed to pcre_exec() is not big enough to remember the referenced substrings, - PCRE gets a block of memory at the start of matching to use for this - purpose. If the call via pcre_malloc() fails, this error is given. The + PCRE gets a block of memory at the start of matching to use for this + purpose. If the call via pcre_malloc() fails, this error is given. The memory is automatically freed at the end of matching. PCRE_ERROR_NOSUBSTRING (-7) - This error is used by the pcre_copy_substring(), pcre_get_substring(), + This error is used by the pcre_copy_substring(), pcre_get_substring(), and pcre_get_substring_list() functions (see below). It is never returned by pcre_exec(). PCRE_ERROR_MATCHLIMIT (-8) - The backtracking limit, as specified by the match_limit field in a - pcre_extra structure (or defaulted) was reached. See the description + The backtracking limit, as specified by the match_limit field in a + pcre_extra structure (or defaulted) was reached. See the description above. PCRE_ERROR_CALLOUT (-9) This error is never generated by pcre_exec() itself. It is provided for - use by callout functions that want to yield a distinctive error code. + use by callout functions that want to yield a distinctive error code. See the pcrecallout documentation for details. PCRE_ERROR_BADUTF8 (-10) - A string that contains an invalid UTF-8 byte sequence was passed as a + A string that contains an invalid UTF-8 byte sequence was passed as a subject. PCRE_ERROR_BADUTF8_OFFSET (-11) The UTF-8 byte sequence that was passed as a subject was valid, but the - value of startoffset did not point to the beginning of a UTF-8 charac- + value of startoffset did not point to the beginning of a UTF-8 charac- ter. PCRE_ERROR_PARTIAL (-12) - The subject string did not match, but it did match partially. See the + The subject string did not match, but it did match partially. See the pcrepartial documentation for details of partial matching. PCRE_ERROR_BADPARTIAL (-13) - The PCRE_PARTIAL option was used with a compiled pattern containing - items that are not supported for partial matching. See the pcrepartial + The PCRE_PARTIAL option was used with a compiled pattern containing + items that are not supported for partial matching. See the pcrepartial documentation for details of partial matching. PCRE_ERROR_INTERNAL (-14) - An unexpected internal error has occurred. This error could be caused + An unexpected internal error has occurred. This error could be caused by a bug in PCRE or by overwriting of the compiled pattern. PCRE_ERROR_BADCOUNT (-15) - This error is given if the value of the ovecsize argument is negative. + This error is given if the value of the ovecsize argument is negative. PCRE_ERROR_RECURSIONLIMIT (-21) The internal recursion limit, as specified by the match_limit_recursion - field in a pcre_extra structure (or defaulted) was reached. See the + field in a pcre_extra structure (or defaulted) was reached. See the description above. PCRE_ERROR_BADNEWLINE (-23) @@ -2139,78 +2183,78 @@ EXTRACTING CAPTURED SUBSTRINGS BY NUMBER int pcre_get_substring_list(const char *subject, int *ovector, int stringcount, const char ***listptr); - Captured substrings can be accessed directly by using the offsets - returned by pcre_exec() in ovector. For convenience, the functions + Captured substrings can be accessed directly by using the offsets + returned by pcre_exec() in ovector. For convenience, the functions pcre_copy_substring(), pcre_get_substring(), and pcre_get_sub- - string_list() are provided for extracting captured substrings as new, - separate, zero-terminated strings. These functions identify substrings - by number. The next section describes functions for extracting named + string_list() are provided for extracting captured substrings as new, + separate, zero-terminated strings. These functions identify substrings + by number. The next section describes functions for extracting named substrings. - A substring that contains a binary zero is correctly extracted and has - a further zero added on the end, but the result is not, of course, a C - string. However, you can process such a string by referring to the - length that is returned by pcre_copy_substring() and pcre_get_sub- + A substring that contains a binary zero is correctly extracted and has + a further zero added on the end, but the result is not, of course, a C + string. However, you can process such a string by referring to the + length that is returned by pcre_copy_substring() and pcre_get_sub- string(). Unfortunately, the interface to pcre_get_substring_list() is - not adequate for handling strings containing binary zeros, because the + not adequate for handling strings containing binary zeros, because the end of the final string is not independently indicated. - The first three arguments are the same for all three of these func- - tions: subject is the subject string that has just been successfully + The first three arguments are the same for all three of these func- + tions: subject is the subject string that has just been successfully matched, ovector is a pointer to the vector of integer offsets that was passed to pcre_exec(), and stringcount is the number of substrings that - were captured by the match, including the substring that matched the + were captured by the match, including the substring that matched the entire regular expression. This is the value returned by pcre_exec() if - it is greater than zero. If pcre_exec() returned zero, indicating that - it ran out of space in ovector, the value passed as stringcount should + it is greater than zero. If pcre_exec() returned zero, indicating that + it ran out of space in ovector, the value passed as stringcount should be the number of elements in the vector divided by three. - The functions pcre_copy_substring() and pcre_get_substring() extract a - single substring, whose number is given as stringnumber. A value of - zero extracts the substring that matched the entire pattern, whereas - higher values extract the captured substrings. For pcre_copy_sub- - string(), the string is placed in buffer, whose length is given by - buffersize, while for pcre_get_substring() a new block of memory is - obtained via pcre_malloc, and its address is returned via stringptr. - The yield of the function is the length of the string, not including + The functions pcre_copy_substring() and pcre_get_substring() extract a + single substring, whose number is given as stringnumber. A value of + zero extracts the substring that matched the entire pattern, whereas + higher values extract the captured substrings. For pcre_copy_sub- + string(), the string is placed in buffer, whose length is given by + buffersize, while for pcre_get_substring() a new block of memory is + obtained via pcre_malloc, and its address is returned via stringptr. + The yield of the function is the length of the string, not including the terminating zero, or one of these error codes: PCRE_ERROR_NOMEMORY (-6) - The buffer was too small for pcre_copy_substring(), or the attempt to + The buffer was too small for pcre_copy_substring(), or the attempt to get memory failed for pcre_get_substring(). PCRE_ERROR_NOSUBSTRING (-7) There is no substring whose number is stringnumber. - The pcre_get_substring_list() function extracts all available sub- - strings and builds a list of pointers to them. All this is done in a + The pcre_get_substring_list() function extracts all available sub- + strings and builds a list of pointers to them. All this is done in a single block of memory that is obtained via pcre_malloc. The address of - the memory block is returned via listptr, which is also the start of - the list of string pointers. The end of the list is marked by a NULL - pointer. The yield of the function is zero if all went well, or the + the memory block is returned via listptr, which is also the start of + the list of string pointers. The end of the list is marked by a NULL + pointer. The yield of the function is zero if all went well, or the error code PCRE_ERROR_NOMEMORY (-6) if the attempt to get the memory block failed. - When any of these functions encounter a substring that is unset, which - can happen when capturing subpattern number n+1 matches some part of - the subject, but subpattern n has not been used at all, they return an + When any of these functions encounter a substring that is unset, which + can happen when capturing subpattern number n+1 matches some part of + the subject, but subpattern n has not been used at all, they return an empty string. This can be distinguished from a genuine zero-length sub- - string by inspecting the appropriate offset in ovector, which is nega- + string by inspecting the appropriate offset in ovector, which is nega- tive for unset substrings. - The two convenience functions pcre_free_substring() and pcre_free_sub- - string_list() can be used to free the memory returned by a previous + The two convenience functions pcre_free_substring() and pcre_free_sub- + string_list() can be used to free the memory returned by a previous call of pcre_get_substring() or pcre_get_substring_list(), respec- - tively. They do nothing more than call the function pointed to by - pcre_free, which of course could be called directly from a C program. - However, PCRE is used in some situations where it is linked via a spe- - cial interface to another programming language that cannot use - pcre_free directly; it is for these cases that the functions are pro- + tively. They do nothing more than call the function pointed to by + pcre_free, which of course could be called directly from a C program. + However, PCRE is used in some situations where it is linked via a spe- + cial interface to another programming language that cannot use + pcre_free directly; it is for these cases that the functions are pro- vided. @@ -2229,7 +2273,7 @@ EXTRACTING CAPTURED SUBSTRINGS BY NAME int stringcount, const char *stringname, const char **stringptr); - To extract a substring by name, you first have to find associated num- + To extract a substring by name, you first have to find associated num- ber. For example, for this pattern (a+)b(?<xxx>\d+)... @@ -2238,27 +2282,27 @@ EXTRACTING CAPTURED SUBSTRINGS BY NAME be unique (PCRE_DUPNAMES was not set), you can find the number from the name by calling pcre_get_stringnumber(). The first argument is the com- piled pattern, and the second is the name. The yield of the function is - the subpattern number, or PCRE_ERROR_NOSUBSTRING (-7) if there is no + the subpattern number, or PCRE_ERROR_NOSUBSTRING (-7) if there is no subpattern of that name. Given the number, you can extract the substring directly, or use one of the functions described in the previous section. For convenience, there are also two functions that do the whole job. - Most of the arguments of pcre_copy_named_substring() and - pcre_get_named_substring() are the same as those for the similarly - named functions that extract by number. As these are described in the - previous section, they are not re-described here. There are just two + Most of the arguments of pcre_copy_named_substring() and + pcre_get_named_substring() are the same as those for the similarly + named functions that extract by number. As these are described in the + previous section, they are not re-described here. There are just two differences: - First, instead of a substring number, a substring name is given. Sec- + First, instead of a substring number, a substring name is given. Sec- ond, there is an extra argument, given at the start, which is a pointer - to the compiled pattern. This is needed in order to gain access to the + to the compiled pattern. This is needed in order to gain access to the name-to-number translation table. - These functions call pcre_get_stringnumber(), and if it succeeds, they - then call pcre_copy_substring() or pcre_get_substring(), as appropri- - ate. NOTE: If PCRE_DUPNAMES is set and there are duplicate names, the + These functions call pcre_get_stringnumber(), and if it succeeds, they + then call pcre_copy_substring() or pcre_get_substring(), as appropri- + ate. NOTE: If PCRE_DUPNAMES is set and there are duplicate names, the behaviour may not be what you want (see the next section). @@ -2267,47 +2311,47 @@ DUPLICATE SUBPATTERN NAMES int pcre_get_stringtable_entries(const pcre *code, const char *name, char **first, char **last); - When a pattern is compiled with the PCRE_DUPNAMES option, names for - subpatterns are not required to be unique. Normally, patterns with - duplicate names are such that in any one match, only one of the named - subpatterns participates. An example is shown in the pcrepattern docu- + When a pattern is compiled with the PCRE_DUPNAMES option, names for + subpatterns are not required to be unique. Normally, patterns with + duplicate names are such that in any one match, only one of the named + subpatterns participates. An example is shown in the pcrepattern docu- mentation. - When duplicates are present, pcre_copy_named_substring() and - pcre_get_named_substring() return the first substring corresponding to - the given name that is set. If none are set, PCRE_ERROR_NOSUBSTRING - (-7) is returned; no data is returned. The pcre_get_stringnumber() - function returns one of the numbers that are associated with the name, + When duplicates are present, pcre_copy_named_substring() and + pcre_get_named_substring() return the first substring corresponding to + the given name that is set. If none are set, PCRE_ERROR_NOSUBSTRING + (-7) is returned; no data is returned. The pcre_get_stringnumber() + function returns one of the numbers that are associated with the name, but it is not defined which it is. - If you want to get full details of all captured substrings for a given - name, you must use the pcre_get_stringtable_entries() function. The + If you want to get full details of all captured substrings for a given + name, you must use the pcre_get_stringtable_entries() function. The first argument is the compiled pattern, and the second is the name. The - third and fourth are pointers to variables which are updated by the + third and fourth are pointers to variables which are updated by the function. After it has run, they point to the first and last entries in - the name-to-number table for the given name. The function itself - returns the length of each entry, or PCRE_ERROR_NOSUBSTRING (-7) if - there are none. The format of the table is described above in the sec- - tion entitled Information about a pattern. Given all the relevant - entries for the name, you can extract each of their numbers, and hence + the name-to-number table for the given name. The function itself + returns the length of each entry, or PCRE_ERROR_NOSUBSTRING (-7) if + there are none. The format of the table is described above in the sec- + tion entitled Information about a pattern. Given all the relevant + entries for the name, you can extract each of their numbers, and hence the captured data, if any. FINDING ALL POSSIBLE MATCHES - The traditional matching function uses a similar algorithm to Perl, + The traditional matching function uses a similar algorithm to Perl, which stops when it finds the first match, starting at a given point in - the subject. If you want to find all possible matches, or the longest - possible match, consider using the alternative matching function (see - below) instead. If you cannot use the alternative function, but still - need to find all possible matches, you can kludge it up by making use + the subject. If you want to find all possible matches, or the longest + possible match, consider using the alternative matching function (see + below) instead. If you cannot use the alternative function, but still + need to find all possible matches, you can kludge it up by making use of the callout facility, which is described in the pcrecallout documen- tation. What you have to do is to insert a callout right at the end of the pat- - tern. When your callout function is called, extract and save the cur- - rent matched substring. Then return 1, which forces pcre_exec() to - backtrack and try other alternatives. Ultimately, when it runs out of + tern. When your callout function is called, extract and save the cur- + rent matched substring. Then return 1, which forces pcre_exec() to + backtrack and try other alternatives. Ultimately, when it runs out of matches, pcre_exec() will yield PCRE_ERROR_NOMATCH. @@ -2318,25 +2362,25 @@ MATCHING A PATTERN: THE ALTERNATIVE FUNCTION int options, int *ovector, int ovecsize, int *workspace, int wscount); - The function pcre_dfa_exec() is called to match a subject string - against a compiled pattern, using a matching algorithm that scans the - subject string just once, and does not backtrack. This has different - characteristics to the normal algorithm, and is not compatible with - Perl. Some of the features of PCRE patterns are not supported. Never- - theless, there are times when this kind of matching can be useful. For + The function pcre_dfa_exec() is called to match a subject string + against a compiled pattern, using a matching algorithm that scans the + subject string just once, and does not backtrack. This has different + characteristics to the normal algorithm, and is not compatible with + Perl. Some of the features of PCRE patterns are not supported. Never- + theless, there are times when this kind of matching can be useful. For a discussion of the two matching algorithms, see the pcrematching docu- mentation. - The arguments for the pcre_dfa_exec() function are the same as for + The arguments for the pcre_dfa_exec() function are the same as for pcre_exec(), plus two extras. The ovector argument is used in a differ- - ent way, and this is described below. The other common arguments are - used in the same way as for pcre_exec(), so their description is not + ent way, and this is described below. The other common arguments are + used in the same way as for pcre_exec(), so their description is not repeated here. - The two additional arguments provide workspace for the function. The - workspace vector should contain at least 20 elements. It is used for + The two additional arguments provide workspace for the function. The + workspace vector should contain at least 20 elements. It is used for keeping track of multiple paths through the pattern tree. More - workspace will be needed for patterns and subjects where there are a + workspace will be needed for patterns and subjects where there are a lot of potential matches. Here is an example of a simple call to pcre_dfa_exec(): @@ -2358,47 +2402,47 @@ MATCHING A PATTERN: THE ALTERNATIVE FUNCTION Option bits for pcre_dfa_exec() - The unused bits of the options argument for pcre_dfa_exec() must be - zero. The only bits that may be set are PCRE_ANCHORED, PCRE_NEW- - LINE_xxx, PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, PCRE_NO_UTF8_CHECK, + The unused bits of the options argument for pcre_dfa_exec() must be + zero. The only bits that may be set are PCRE_ANCHORED, PCRE_NEW- + LINE_xxx, PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, PCRE_NO_UTF8_CHECK, PCRE_PARTIAL, PCRE_DFA_SHORTEST, and PCRE_DFA_RESTART. All but the last three of these are the same as for pcre_exec(), so their description is not repeated here. PCRE_PARTIAL - This has the same general effect as it does for pcre_exec(), but the - details are slightly different. When PCRE_PARTIAL is set for - pcre_dfa_exec(), the return code PCRE_ERROR_NOMATCH is converted into - PCRE_ERROR_PARTIAL if the end of the subject is reached, there have + This has the same general effect as it does for pcre_exec(), but the + details are slightly different. When PCRE_PARTIAL is set for + pcre_dfa_exec(), the return code PCRE_ERROR_NOMATCH is converted into + PCRE_ERROR_PARTIAL if the end of the subject is reached, there have been no complete matches, but there is still at least one matching pos- - sibility. The portion of the string that provided the partial match is + sibility. The portion of the string that provided the partial match is set as the first matching string. PCRE_DFA_SHORTEST - Setting the PCRE_DFA_SHORTEST option causes the matching algorithm to + Setting the PCRE_DFA_SHORTEST option causes the matching algorithm to stop as soon as it has found one match. Because of the way the alterna- - tive algorithm works, this is necessarily the shortest possible match + tive algorithm works, this is necessarily the shortest possible match at the first possible matching point in the subject string. PCRE_DFA_RESTART - When pcre_dfa_exec() is called with the PCRE_PARTIAL option, and - returns a partial match, it is possible to call it again, with addi- - tional subject characters, and have it continue with the same match. - The PCRE_DFA_RESTART option requests this action; when it is set, the - workspace and wscount options must reference the same vector as before - because data about the match so far is left in them after a partial - match. There is more discussion of this facility in the pcrepartial + When pcre_dfa_exec() is called with the PCRE_PARTIAL option, and + returns a partial match, it is possible to call it again, with addi- + tional subject characters, and have it continue with the same match. + The PCRE_DFA_RESTART option requests this action; when it is set, the + workspace and wscount options must reference the same vector as before + because data about the match so far is left in them after a partial + match. There is more discussion of this facility in the pcrepartial documentation. Successful returns from pcre_dfa_exec() - When pcre_dfa_exec() succeeds, it may have matched more than one sub- + When pcre_dfa_exec() succeeds, it may have matched more than one sub- string in the subject. Note, however, that all the matches from one run - of the function start at the same point in the subject. The shorter - matches are all initial substrings of the longer matches. For example, + of the function start at the same point in the subject. The shorter + matches are all initial substrings of the longer matches. For example, if the pattern <.*> @@ -2413,62 +2457,62 @@ MATCHING A PATTERN: THE ALTERNATIVE FUNCTION <something> <something else> <something> <something else> <something further> - On success, the yield of the function is a number greater than zero, - which is the number of matched substrings. The substrings themselves - are returned in ovector. Each string uses two elements; the first is - the offset to the start, and the second is the offset to the end. In - fact, all the strings have the same start offset. (Space could have - been saved by giving this only once, but it was decided to retain some - compatibility with the way pcre_exec() returns data, even though the + On success, the yield of the function is a number greater than zero, + which is the number of matched substrings. The substrings themselves + are returned in ovector. Each string uses two elements; the first is + the offset to the start, and the second is the offset to the end. In + fact, all the strings have the same start offset. (Space could have + been saved by giving this only once, but it was decided to retain some + compatibility with the way pcre_exec() returns data, even though the meaning of the strings is different.) The strings are returned in reverse order of length; that is, the long- - est matching string is given first. If there were too many matches to - fit into ovector, the yield of the function is zero, and the vector is + est matching string is given first. If there were too many matches to + fit into ovector, the yield of the function is zero, and the vector is filled with the longest matches. Error returns from pcre_dfa_exec() - The pcre_dfa_exec() function returns a negative number when it fails. - Many of the errors are the same as for pcre_exec(), and these are - described above. There are in addition the following errors that are + The pcre_dfa_exec() function returns a negative number when it fails. + Many of the errors are the same as for pcre_exec(), and these are + described above. There are in addition the following errors that are specific to pcre_dfa_exec(): PCRE_ERROR_DFA_UITEM (-16) - This return is given if pcre_dfa_exec() encounters an item in the pat- - tern that it does not support, for instance, the use of \C or a back + This return is given if pcre_dfa_exec() encounters an item in the pat- + tern that it does not support, for instance, the use of \C or a back reference. PCRE_ERROR_DFA_UCOND (-17) - This return is given if pcre_dfa_exec() encounters a condition item - that uses a back reference for the condition, or a test for recursion + This return is given if pcre_dfa_exec() encounters a condition item + that uses a back reference for the condition, or a test for recursion in a specific group. These are not supported. PCRE_ERROR_DFA_UMLIMIT (-18) - This return is given if pcre_dfa_exec() is called with an extra block + This return is given if pcre_dfa_exec() is called with an extra block that contains a setting of the match_limit field. This is not supported (it is meaningless). PCRE_ERROR_DFA_WSSIZE (-19) - This return is given if pcre_dfa_exec() runs out of space in the + This return is given if pcre_dfa_exec() runs out of space in the workspace vector. PCRE_ERROR_DFA_RECURSE (-20) - When a recursive subpattern is processed, the matching function calls - itself recursively, using private vectors for ovector and workspace. - This error is given if the output vector is not large enough. This + When a recursive subpattern is processed, the matching function calls + itself recursively, using private vectors for ovector and workspace. + This error is given if the output vector is not large enough. This should be extremely rare, as a vector of size 1000 is used. SEE ALSO - pcrebuild(3), pcrecallout(3), pcrecpp(3)(3), pcrematching(3), pcrepar- - tial(3), pcreposix(3), pcreprecompile(3), pcresample(3), pcrestack(3). + pcrebuild(3), pcrecallout(3), pcrecpp(3)(3), pcrematching(3), pcrepar- + tial(3), pcreposix(3), pcreprecompile(3), pcresample(3), pcrestack(3). AUTHOR @@ -2480,7 +2524,7 @@ AUTHOR REVISION - Last updated: 21 August 2007 + Last updated: 11 September 2007 Copyright (c) 1997-2007 University of Cambridge. ------------------------------------------------------------------------------ @@ -2765,16 +2809,23 @@ DIFFERENCES BETWEEN PCRE AND PERL (f) The PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, and PCRE_NO_AUTO_CAP- TURE options for pcre_exec() have no Perl equivalents. - (g) The callout facility is PCRE-specific. + (g) The \R escape sequence can be restricted to match only CR, LF, or + CRLF by the PCRE_BSR_ANYCRLF option. - (h) The partial matching facility is PCRE-specific. + (h) The callout facility is PCRE-specific. - (i) Patterns compiled by PCRE can be saved and re-used at a later time, + (i) The partial matching facility is PCRE-specific. + + (j) Patterns compiled by PCRE can be saved and re-used at a later time, even on different hosts that have the other endianness. - (j) The alternative matching function (pcre_dfa_exec()) matches in a + (k) The alternative matching function (pcre_dfa_exec()) matches in a different way and is not Perl-compatible. + (l) PCRE recognizes some special sequences such as (*CR) at the start + of a pattern that set overall options that cannot be changed within the + pattern. + AUTHOR @@ -2785,7 +2836,7 @@ AUTHOR REVISION - Last updated: 08 August 2007 + Last updated: 11 September 2007 Copyright (c) 1997-2007 University of Cambridge. ------------------------------------------------------------------------------ @@ -2853,7 +2904,13 @@ NEWLINE CONVENTIONS changes the convention to CR. That pattern matches "a\nb" because LF is no longer a newline. Note that these special settings, which are not Perl-compatible, are recognized only at the very start of a pattern, - and that they must be in upper case. + and that they must be in upper case. If more than one of them is + present, the last one is used. + + The newline convention does not affect what the \R escape sequence + matches. By default, this is any Unicode newline sequence, for Perl + compatibility. However, this can be changed; see the description of \R + in the section entitled "Newline sequences" below. CHARACTERS AND METACHARACTERS @@ -3128,9 +3185,9 @@ BACKSLASH Newline sequences - Outside a character class, the escape sequence \R matches any Unicode - newline sequence. This is a Perl 5.10 feature. In non-UTF-8 mode \R is - equivalent to the following: + Outside a character class, by default, the escape sequence \R matches + any Unicode newline sequence. This is a Perl 5.10 feature. In non-UTF-8 + mode \R is equivalent to the following: (?>\r\n|\n|\x0b|\f|\r|\x85) @@ -3146,6 +3203,23 @@ BACKSLASH rator, U+2029). Unicode character property support is not needed for these characters to be recognized. + It is possible to restrict \R to match only CR, LF, or CRLF (instead of + the complete set of Unicode line endings) by setting the option + PCRE_BSR_ANYCRLF either at compile time or when the pattern is matched. + This can be made the default when PCRE is built; if this is the case, + the other behaviour can be requested via the PCRE_BSR_UNICODE option. + It is also possible to specify these settings by starting a pattern + string with one of the following sequences: + + (*BSR_ANYCRLF) CR, LF, or CRLF only + (*BSR_UNICODE) any Unicode newline sequence + + These override the default and the options given to pcre_compile(), but + they can be overridden by options given to pcre_exec(). Note that these + special settings, which are not Perl-compatible, are recognized only at + the very start of a pattern, and that they must be in upper case. If + more than one of them is present, the last one is used. + Inside a character class, \R matches the letter "R". Unicode character properties @@ -4775,7 +4849,7 @@ AUTHOR REVISION - Last updated: 21 August 2007 + Last updated: 11 September 2007 Copyright (c) 1997-2007 University of Cambridge. ------------------------------------------------------------------------------ @@ -5083,6 +5157,14 @@ NEWLINE CONVENTIONS (*ANY) +WHAT \R MATCHES + + These are recognized only at the very start of a pattern. + + (*BSR_ANYCRLF) + (*BSR_UNICODE) + + CALLOUTS (?C) callout @@ -5103,7 +5185,7 @@ AUTHOR REVISION - Last updated: 21 August 2007 + Last updated: 11 September 2007 Copyright (c) 1997-2007 University of Cambridge. ------------------------------------------------------------------------------ diff --git a/doc/pcre_compile.3 b/doc/pcre_compile.3 index 17f884e..4e7e402 100644 --- a/doc/pcre_compile.3 +++ b/doc/pcre_compile.3 @@ -32,6 +32,8 @@ The option bits are: .sp PCRE_ANCHORED Force pattern anchoring PCRE_AUTO_CALLOUT Compile automatic callouts + PCRE_BSR_ANYCRLF \eR matches only CR, LF, or CRLF + PCRE_BSR_UNICODE \eR matches all Unicode line endings PCRE_CASELESS Do caseless matching PCRE_DOLLAR_ENDONLY $ not to match newline at end PCRE_DOTALL . matches anything including NL diff --git a/doc/pcre_config.3 b/doc/pcre_config.3 index 52f26c3..b111a70 100644 --- a/doc/pcre_config.3 +++ b/doc/pcre_config.3 @@ -25,12 +25,15 @@ The available codes are: PCRE_CONFIG_MATCH_LIMIT Internal resource limit PCRE_CONFIG_MATCH_LIMIT_RECURSION Internal recursion depth limit - PCRE_CONFIG_NEWLINE Value of the newline sequence: + PCRE_CONFIG_NEWLINE Value of the default newline sequence: 13 (0x000d) for CR 10 (0x000a) for LF 3338 (0x0d0a) for CRLF -2 for ANYCRLF -1 for ANY + PCRE_CONFIG_BSR Indicates what \eR matches by default: + 0 all Unicode line endings + 1 CR, LF, or CRLF only PCRE_CONFIG_POSIX_MALLOC_THRESHOLD Threshold of return slots, above which \fBmalloc()\fR is used by diff --git a/doc/pcre_dfa_exec.3 b/doc/pcre_dfa_exec.3 index 8416d30..274b97c 100644 --- a/doc/pcre_dfa_exec.3 +++ b/doc/pcre_dfa_exec.3 @@ -39,6 +39,8 @@ matching function is \fBpcre_exec()\fP. The arguments for this function are: The options are: .sp PCRE_ANCHORED Match only at the first position + PCRE_BSR_ANYCRLF \eR matches only CR, LF, or CRLF + PCRE_BSR_UNICODE \eR matches all Unicode line endings PCRE_NEWLINE_ANY Recognize any Unicode newline sequence PCRE_NEWLINE_ANYCRLF Recognize CR, LF, and CRLF as newline sequences PCRE_NEWLINE_CR Set CR as the newline sequence diff --git a/doc/pcre_exec.3 b/doc/pcre_exec.3 index 755904d..834a1f2 100644 --- a/doc/pcre_exec.3 +++ b/doc/pcre_exec.3 @@ -34,6 +34,8 @@ offsets to captured substrings. Its arguments are: The options are: .sp PCRE_ANCHORED Match only at the first position + PCRE_BSR_ANYCRLF \eR matches only CR, LF, or CRLF + PCRE_BSR_UNICODE \eR matches all Unicode line endings PCRE_NEWLINE_ANY Recognize any Unicode newline sequence PCRE_NEWLINE_ANYCRLF Recognize CR, LF, and CRLF as newline sequences PCRE_NEWLINE_CR Set CR as the newline sequence diff --git a/doc/pcreapi.3 b/doc/pcreapi.3 index 34fc7e9..5ac8de4 100644 --- a/doc/pcreapi.3 +++ b/doc/pcreapi.3 @@ -254,8 +254,11 @@ non-anchored pattern. There is more detail about this in the .\" </a> section on \fBpcre_exec()\fP options .\" -below. The choice of newline convention does not affect the interpretation of -the \en or \er escape sequences. +below. +.P +The choice of newline convention does not affect the interpretation of +the \en or \er escape sequences, nor does it affect what \eR matches, which is +controlled in a similar way, but by separate options. . . .SH MULTITHREADING @@ -317,6 +320,13 @@ that is recognized as meaning "newline". The four values that are supported are: 10 for LF, 13 for CR, 3338 for CRLF, -2 for ANYCRLF, and -1 for ANY. The default should normally be the standard sequence for your operating system. .sp + PCRE_CONFIG_BSR +.sp +The output is an integer whose value indicates what character sequences the \eR +escape sequence matches by default. A value of 0 means that \eR matches any +Unicode line ending sequence; a value of 1 means that \eR matches only CR, LF, +or CRLF. The default can be overridden when a pattern is compiled or matched. +.sp PCRE_CONFIG_LINK_SIZE .sp The output is an integer that contains the number of bytes used for internal @@ -458,6 +468,15 @@ facility, see the .\" documentation. .sp + PCRE_BSR_ANYCRLF + PCRE_BSR_UNICODE +.sp +These options (which are mutually exclusive) control what the \eR escape +sequence matches. The choice is either to match only CR, LF, or CRLF, or to +match any Unicode newline sequence. The default is specified when PCRE is +built. It can be overridden from within the pattern, or by setting an option +when a compiled pattern is matched. +.sp PCRE_CASELESS .sp If this bit is set, letters in the pattern match both upper and lower case @@ -697,7 +716,7 @@ out of use. To avoid confusion, they have not been re-used. 53 internal error: previously-checked referenced subpattern not found 54 DEFINE group contains more than one branch 55 repeating a DEFINE group is not allowed - 56 inconsistent NEWLINE options" + 56 inconsistent NEWLINE options 57 \eg is not followed by a braced name or an optionally braced non-zero number 58 (?+ or (?- or (?(+ or (?(- must be followed by a non-zero number @@ -899,7 +918,8 @@ fourth argument should point to an \fBunsigned char *\fP variable. PCRE_INFO_HASCRORLF .sp Return 1 if the pattern contains any explicit matches for CR or LF characters, -otherwise 0. The fourth argument should point to an \fBint\fP variable. +otherwise 0. The fourth argument should point to an \fBint\fP variable. An +explicit match is either a literal CR or LF character, or \er or \en. .sp PCRE_INFO_JCHANGED .sp @@ -1203,6 +1223,14 @@ matching position. If a pattern was compiled with PCRE_ANCHORED, or turned out to be anchored by virtue of its contents, it cannot be made unachored at matching time. .sp + PCRE_BSR_ANYCRLF + PCRE_BSR_UNICODE +.sp +These options (which are mutually exclusive) control what the \eR escape +sequence matches. The choice is either to match only CR, LF, or CRLF, or to +match any Unicode newline sequence. These options override the choice that was +made or defaulted when the pattern was compiled. +.sp PCRE_NEWLINE_CR PCRE_NEWLINE_LF PCRE_NEWLINE_CRLF @@ -1229,8 +1257,8 @@ start, it skips both the CR and the LF before retrying. However, the pattern [\er\en]A does match that string, because it contains an explicit CR or LF reference, and so advances only by one character after the first failure. .P -An explicit match for CR of LF is either a literal appearance of one of those -characters, or one of the \er or \en escape sequences. Implicit matches such as +An explicit match for CR of LF is either a literal appearance of one of those +characters, or one of the \er or \en escape sequences. Implicit matches such as [^X] do not count, nor does \es (which includes CR and LF in the characters that it matches). .P @@ -1924,6 +1952,6 @@ Cambridge CB2 3QH, England. .rs .sp .nf -Last updated: 10 September 2007 +Last updated: 11 September 2007 Copyright (c) 1997-2007 University of Cambridge. .fi diff --git a/doc/pcrebuild.3 b/doc/pcrebuild.3 index 9ce3cd4..fd08758 100644 --- a/doc/pcrebuild.3 +++ b/doc/pcrebuild.3 @@ -96,6 +96,18 @@ Whatever line ending convention is selected when PCRE is built can be overridden when the library functions are called. At build time it is conventional to use the standard for your operating system. . +.SH "WHAT \eR MATCHES" +.rs +.sp +By default, the sequence \eR in a pattern matches any Unicode newline sequence, +whatever has been selected as the line ending sequence. If you specify +.sp + --enable-bsr-anycrlf +.sp +the default is changed so that \eR matches only CR, LF, or CRLF. Whatever is +selected when PCRE is built can be overridden when the library functions are +called. +. .SH "BUILDING SHARED AND STATIC LIBRARIES" .rs .sp @@ -260,6 +272,6 @@ Cambridge CB2 3QH, England. .rs .sp .nf -Last updated: 30 July 2007 +Last updated: 11 September 2007 Copyright (c) 1997-2007 University of Cambridge. .fi diff --git a/doc/pcrecompat.3 b/doc/pcrecompat.3 index 56293f7..3be6a6a 100644 --- a/doc/pcrecompat.3 +++ b/doc/pcrecompat.3 @@ -112,15 +112,21 @@ only at the first matching position in the subject string. (f) The PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, and PCRE_NO_AUTO_CAPTURE options for \fBpcre_exec()\fP have no Perl equivalents. .sp -(g) The callout facility is PCRE-specific. +(g) The \eR escape sequence can be restricted to match only CR, LF, or CRLF +by the PCRE_BSR_ANYCRLF option. .sp -(h) The partial matching facility is PCRE-specific. +(h) The callout facility is PCRE-specific. .sp -(i) Patterns compiled by PCRE can be saved and re-used at a later time, even on +(i) The partial matching facility is PCRE-specific. +.sp +(j) Patterns compiled by PCRE can be saved and re-used at a later time, even on different hosts that have the other endianness. .sp -(j) The alternative matching function (\fBpcre_dfa_exec()\fP) matches in a +(k) The alternative matching function (\fBpcre_dfa_exec()\fP) matches in a different way and is not Perl-compatible. +.sp +(l) PCRE recognizes some special sequences such as (*CR) at the start of +a pattern that set overall options that cannot be changed within the pattern. . . .SH AUTHOR @@ -137,6 +143,6 @@ Cambridge CB2 3QH, England. .rs .sp .nf -Last updated: 08 August 2007 +Last updated: 11 September 2007 Copyright (c) 1997-2007 University of Cambridge. .fi diff --git a/doc/pcrepattern.3 b/doc/pcrepattern.3 index 6387b86..c5091f6 100644 --- a/doc/pcrepattern.3 +++ b/doc/pcrepattern.3 @@ -79,7 +79,17 @@ example, on a Unix system where LF is the default newline sequence, the pattern changes the convention to CR. That pattern matches "a\enb" because LF is no longer a newline. Note that these special settings, which are not Perl-compatible, are recognized only at the very start of a pattern, and that -they must be in upper case. +they must be in upper case. If more than one of them is present, the last one +is used. +.P +The newline convention does not affect what the \eR escape sequence matches. By +default, this is any Unicode newline sequence, for Perl compatibility. However, +this can be changed; see the description of \eR in the section entitled +.\" HTML <a href="#newlineseq"> +.\" </a> +"Newline sequences" +.\" +below. . . .SH "CHARACTERS AND METACHARACTERS" @@ -388,12 +398,13 @@ accented letters, and these are matched by \ew. The use of locales with Unicode is discouraged. . . +.\" HTML <a name="newlineseq"></a> .SS "Newline sequences" .rs .sp -Outside a character class, the escape sequence \eR matches any Unicode newline -sequence. This is a Perl 5.10 feature. In non-UTF-8 mode \eR is equivalent to -the following: +Outside a character class, by default, the escape sequence \eR matches any +Unicode newline sequence. This is a Perl 5.10 feature. In non-UTF-8 mode \eR is +equivalent to the following: .sp (?>\er\en|\en|\ex0b|\ef|\er|\ex85) .sp @@ -413,6 +424,22 @@ are added: LS (line separator, U+2028) and PS (paragraph separator, U+2029). Unicode character property support is not needed for these characters to be recognized. .P +It is possible to restrict \eR to match only CR, LF, or CRLF (instead of the +complete set of Unicode line endings) by setting the option PCRE_BSR_ANYCRLF +either at compile time or when the pattern is matched. This can be made the +default when PCRE is built; if this is the case, the other behaviour can be +requested via the PCRE_BSR_UNICODE option. It is also possible to specify these +settings by starting a pattern string with one of the following sequences: +.sp + (*BSR_ANYCRLF) CR, LF, or CRLF only + (*BSR_UNICODE) any Unicode newline sequence +.sp +These override the default and the options given to \fBpcre_compile()\fP, but +they can be overridden by options given to \fBpcre_exec()\fP. Note that these +special settings, which are not Perl-compatible, are recognized only at the +very start of a pattern, and that they must be in upper case. If more than one +of them is present, the last one is used. +.P Inside a character class, \eR matches the letter "R". . . @@ -960,8 +987,9 @@ alternative in the subpattern. .rs .sp The settings of the PCRE_CASELESS, PCRE_MULTILINE, PCRE_DOTALL, and -PCRE_EXTENDED options can be changed from within the pattern by a sequence of -Perl option letters enclosed between "(?" and ")". The option letters are +PCRE_EXTENDED options (which are Perl-compatible) can be changed from within +the pattern by a sequence of Perl option letters enclosed between "(?" and ")". +The option letters are .sp i for PCRE_CASELESS m for PCRE_MULTILINE @@ -975,6 +1003,10 @@ PCRE_MULTILINE while unsetting PCRE_DOTALL and PCRE_EXTENDED, is also permitted. If a letter appears both before and after the hyphen, the option is unset. .P +The PCRE-specific options PCRE_DUPNAMES, PCRE_UNGREEDY, and PCRE_EXTRA can be +changed in the same way as the Perl-compatible options by using the characters +J, U and X respectively. +.P When an option change occurs at top level (that is, not inside subpattern parentheses), the change applies to the remainder of the pattern that follows. If the change is placed right at the start of a pattern, PCRE extracts it into @@ -997,10 +1029,6 @@ matches "ab", "aB", "c", and "C", even though when matching "C" the first branch is abandoned before the option setting. This is because the effects of option settings happen at compile time. There would be some very weird behaviour otherwise. -.P -The PCRE-specific options PCRE_DUPNAMES, PCRE_UNGREEDY, and PCRE_EXTRA can be -changed in the same way as the Perl-compatible options by using the characters -J, U and X respectively. . . .\" HTML <a name="subpattern"></a> @@ -2149,6 +2177,6 @@ Cambridge CB2 3QH, England. .rs .sp .nf -Last updated: 21 August 2007 +Last updated: 11 September 2007 Copyright (c) 1997-2007 University of Cambridge. .fi diff --git a/doc/pcresyntax.3 b/doc/pcresyntax.3 index e04ec4e..af68a63 100644 --- a/doc/pcresyntax.3 +++ b/doc/pcresyntax.3 @@ -379,6 +379,15 @@ These are recognized only at the very start of a pattern. (*ANY) . . +.SH "WHAT \eR MATCHES" +.rs +.sp +These are recognized only at the very start of a pattern. +.sp + (*BSR_ANYCRLF) + (*BSR_UNICODE) +. +. .SH "CALLOUTS" .rs .sp @@ -407,6 +416,6 @@ Cambridge CB2 3QH, England. .rs .sp .nf -Last updated: 21 August 2007 +Last updated: 11 September 2007 Copyright (c) 1997-2007 University of Cambridge. .fi diff --git a/doc/pcretest.1 b/doc/pcretest.1 index eb0f1b5..63248b6 100644 --- a/doc/pcretest.1 +++ b/doc/pcretest.1 @@ -157,19 +157,21 @@ effect as they do in Perl. For example: The following table shows additional modifiers for setting PCRE options that do not correspond to anything in Perl: .sp - \fB/A\fP PCRE_ANCHORED - \fB/C\fP PCRE_AUTO_CALLOUT - \fB/E\fP PCRE_DOLLAR_ENDONLY - \fB/f\fP PCRE_FIRSTLINE - \fB/J\fP PCRE_DUPNAMES - \fB/N\fP PCRE_NO_AUTO_CAPTURE - \fB/U\fP PCRE_UNGREEDY - \fB/X\fP PCRE_EXTRA - \fB/<cr>\fP PCRE_NEWLINE_CR - \fB/<lf>\fP PCRE_NEWLINE_LF - \fB/<crlf>\fP PCRE_NEWLINE_CRLF - \fB/<anycrlf>\fP PCRE_NEWLINE_ANYCRLF - \fB/<any>\fP PCRE_NEWLINE_ANY + \fB/A\fP PCRE_ANCHORED + \fB/C\fP PCRE_AUTO_CALLOUT + \fB/E\fP PCRE_DOLLAR_ENDONLY + \fB/f\fP PCRE_FIRSTLINE + \fB/J\fP PCRE_DUPNAMES + \fB/N\fP PCRE_NO_AUTO_CAPTURE + \fB/U\fP PCRE_UNGREEDY + \fB/X\fP PCRE_EXTRA + \fB/<cr>\fP PCRE_NEWLINE_CR + \fB/<lf>\fP PCRE_NEWLINE_LF + \fB/<crlf>\fP PCRE_NEWLINE_CRLF + \fB/<anycrlf>\fP PCRE_NEWLINE_ANYCRLF + \fB/<any>\fP PCRE_NEWLINE_ANY + \fB/<bsr_anycrlf>\fP PCRE_BSR_ANYCRLF + \fB/<bsr_unicode>\fP PCRE_BSR_UNICODE .sp Those specifying line ending sequences are literal strings as shown, but the letters can be in either case. This example sets multiline matching with CRLF @@ -694,6 +696,6 @@ Cambridge CB2 3QH, England. .rs .sp .nf -Last updated: 21 August 2007 +Last updated: 11 September 2007 Copyright (c) 1997-2007 University of Cambridge. .fi diff --git a/doc/pcretest.txt b/doc/pcretest.txt index 06b18bd..6883a26 100644 --- a/doc/pcretest.txt +++ b/doc/pcretest.txt @@ -146,19 +146,21 @@ 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 - /<cr> PCRE_NEWLINE_CR - /<lf> PCRE_NEWLINE_LF - /<crlf> PCRE_NEWLINE_CRLF - /<anycrlf> PCRE_NEWLINE_ANYCRLF - /<any> 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 + /<cr> PCRE_NEWLINE_CR + /<lf> PCRE_NEWLINE_LF + /<crlf> PCRE_NEWLINE_CRLF + /<anycrlf> PCRE_NEWLINE_ANYCRLF + /<any> PCRE_NEWLINE_ANY + /<bsr_anycrlf> PCRE_BSR_ANYCRLF + /<bsr_unicode> PCRE_BSR_UNICODE Those specifying line ending sequences are literal strings as shown, but the letters can be in either case. This example sets multiline @@ -625,5 +627,5 @@ AUTHOR REVISION - Last updated: 21 August 2007 + Last updated: 11 September 2007 Copyright (c) 1997-2007 University of Cambridge. diff --git a/maint/ManyConfigTests b/maint/ManyConfigTests index 0bdac28..fd7f2d1 100755 --- a/maint/ManyConfigTests +++ b/maint/ManyConfigTests @@ -137,7 +137,7 @@ for opts in \ "--enable-newline-is-any --disable-shared" \ "--enable-newline-is-cr --disable-shared" \ "--enable-newline-is-crlf --disable-shared" \ - "--enable-newline-is-anycrlf --disable-shared" \ + "--enable-newline-is-anycrlf --enable-bsr-anycrlf --disable-shared" \ "--enable-utf8 --enable-newline-is-any --enable-unicode-properties --disable-stack-for-recursion --disable-static --disable-cpp" do runtest @@ -122,6 +122,8 @@ extern "C" { #define PCRE_NEWLINE_CRLF 0x00300000 #define PCRE_NEWLINE_ANY 0x00400000 #define PCRE_NEWLINE_ANYCRLF 0x00500000 +#define PCRE_BSR_ANYCRLF 0x00800000 +#define PCRE_BSR_UNICODE 0x01000000 /* Exec-time and get/set-time error codes */ @@ -180,6 +182,7 @@ compatible. */ #define PCRE_CONFIG_STACKRECURSE 5 #define PCRE_CONFIG_UNICODE_PROPERTIES 6 #define PCRE_CONFIG_MATCH_LIMIT_RECURSION 7 +#define PCRE_CONFIG_BSR 8 /* Bit flags for the pcre_extra structure. Do not re-arrange or redefine these bits, just add new ones on the end, in order to remain compatible. */ diff --git a/pcre_compile.c b/pcre_compile.c index 20cd120..da14310 100644 --- a/pcre_compile.c +++ b/pcre_compile.c @@ -2975,11 +2975,11 @@ for (;; ptr++) } oldptr = ptr; - + /* Remember \r or \n */ - - if (c == '\r' || c == '\n') cd->external_flags |= PCRE_HASCRORLF; - + + if (c == '\r' || c == '\n') cd->external_flags |= PCRE_HASCRORLF; + /* Check for range */ if (!inescq && ptr[1] == '-') @@ -3050,9 +3050,9 @@ for (;; ptr++) if (d == c) goto LONE_SINGLE_CHARACTER; /* A few lines below */ /* Remember \r or \n */ - - if (d == '\r' || d == '\n') cd->external_flags |= PCRE_HASCRORLF; - + + if (d == '\r' || d == '\n') cd->external_flags |= PCRE_HASCRORLF; + /* In UTF-8 mode, if the upper limit is > 255, or > 127 for caseless matching, we have to use an XCLASS with extra data items. Caseless matching for characters > 127 is available only if UCP support is @@ -3157,7 +3157,7 @@ for (;; ptr++) apparent range that isn't. */ LONE_SINGLE_CHARACTER: - + /* Handle a character that cannot go in the bit map */ #ifdef SUPPORT_UTF8 @@ -3205,8 +3205,8 @@ for (;; ptr++) *errorcodeptr = ERR6; goto FAILED; } - - + + /* This code has been disabled because it would mean that \s counts as an explicit \r or \n reference, and that's not really what is wanted. Now we set the flag only if there is a literal "\r" or "\n" in the class. */ @@ -3223,7 +3223,7 @@ we set the flag only if there is a literal "\r" or "\n" in the class. */ if ((classbits[1] & 0x24) != 0) cd->external_flags |= PCRE_HASCRORLF; } #endif - + /* If class_charcount is 1, we saw precisely one character whose value is less than 256. As long as there were no characters >= 128 and there was no @@ -5763,24 +5763,46 @@ cd->fcc = tables + fcc_offset; cd->cbits = tables + cbits_offset; cd->ctypes = tables + ctypes_offset; -/* Check for newline settings at the start of the pattern, and remember the -offset for later. */ +/* Check for global one-time settings at the start of the pattern, and remember +the offset for later. */ -if (ptr[0] == '(' && ptr[1] == '*') +while (ptr[skipatstart] == '(' && ptr[skipatstart+1] == '*') { int newnl = 0; - if (strncmp((char *)(ptr+2), "CR)", 3) == 0) - { skipatstart = 5; newnl = PCRE_NEWLINE_CR; } - else if (strncmp((char *)(ptr+2), "LF)", 3) == 0) - { skipatstart = 5; newnl = PCRE_NEWLINE_LF; } - else if (strncmp((char *)(ptr+2), "CRLF)", 5) == 0) - { skipatstart = 7; newnl = PCRE_NEWLINE_CR + PCRE_NEWLINE_LF; } - else if (strncmp((char *)(ptr+2), "ANY)", 4) == 0) - { skipatstart = 6; newnl = PCRE_NEWLINE_ANY; } - else if (strncmp((char *)(ptr+2), "ANYCRLF)", 8) == 0) - { skipatstart = 10; newnl = PCRE_NEWLINE_ANYCRLF; } - if (skipatstart > 0) + int newbsr = 0; + + if (strncmp((char *)(ptr+skipatstart+2), "CR)", 3) == 0) + { skipatstart += 5; newnl = PCRE_NEWLINE_CR; } + else if (strncmp((char *)(ptr+skipatstart+2), "LF)", 3) == 0) + { skipatstart += 5; newnl = PCRE_NEWLINE_LF; } + else if (strncmp((char *)(ptr+skipatstart+2), "CRLF)", 5) == 0) + { skipatstart += 7; newnl = PCRE_NEWLINE_CR + PCRE_NEWLINE_LF; } + else if (strncmp((char *)(ptr+skipatstart+2), "ANY)", 4) == 0) + { skipatstart += 6; newnl = PCRE_NEWLINE_ANY; } + else if (strncmp((char *)(ptr+skipatstart+2), "ANYCRLF)", 8) == 0) + { skipatstart += 10; newnl = PCRE_NEWLINE_ANYCRLF; } + + else if (strncmp((char *)(ptr+skipatstart+2), "BSR_ANYCRLF)", 12) == 0) + { skipatstart += 14; newbsr = PCRE_BSR_ANYCRLF; } + else if (strncmp((char *)(ptr+skipatstart+2), "BSR_UNICODE)", 12) == 0) + { skipatstart += 14; newbsr = PCRE_BSR_UNICODE; } + + if (newnl != 0) options = (options & ~PCRE_NEWLINE_BITS) | newnl; + else if (newbsr != 0) + options = (options & ~(PCRE_BSR_ANYCRLF|PCRE_BSR_UNICODE)) | newbsr; + else break; + } + +/* Check validity of \R options. */ + +switch (options & (PCRE_BSR_ANYCRLF|PCRE_BSR_UNICODE)) + { + case 0: + case PCRE_BSR_ANYCRLF: + case PCRE_BSR_UNICODE: + break; + default: errorcode = ERR56; goto PCRE_EARLY_ERROR_RETURN; } /* Handle different types of newline. The three bits give seven cases. The @@ -5892,7 +5914,7 @@ if (re == NULL) goto PCRE_EARLY_ERROR_RETURN; } -/* Put in the magic number, and save the sizes, initial options, internal +/* Put in the magic number, and save the sizes, initial options, internal flags, and character table pointer. NULL is used for the default character tables. The nullpad field is at the end; it's there to help in the case when a regex compiled on a system with 4-byte pointers is run on another with 8-byte diff --git a/pcre_config.c b/pcre_config.c index ea0e317..40532a5 100644 --- a/pcre_config.c +++ b/pcre_config.c @@ -87,6 +87,14 @@ switch (what) *((int *)where) = NEWLINE; break; + case PCRE_CONFIG_BSR: +#ifdef BSR_ANYCRLF + *((int *)where) = 1; +#else + *((int *)where) = 0; +#endif + break; + case PCRE_CONFIG_LINK_SIZE: *((int *)where) = LINK_SIZE; break; diff --git a/pcre_dfa_exec.c b/pcre_dfa_exec.c index dc1412b..b1d4c5e 100644 --- a/pcre_dfa_exec.c +++ b/pcre_dfa_exec.c @@ -1080,15 +1080,20 @@ for (;;) int ncount = 0; switch (c) { - case 0x000d: - if (ptr + 1 < end_subject && ptr[1] == 0x0a) ncount = 1; - /* Fall through */ - case 0x000a: case 0x000b: case 0x000c: case 0x0085: case 0x2028: case 0x2029: + if ((md->moptions & PCRE_BSR_ANYCRLF) != 0) break; + goto ANYNL01; + + case 0x000d: + if (ptr + 1 < end_subject && ptr[1] == 0x0a) ncount = 1; + /* Fall through */ + + ANYNL01: + case 0x000a: if (count > 0 && codevalue == OP_ANYNL_EXTRA + OP_TYPEPOSPLUS) { active_count--; /* Remove non-match possibility */ @@ -1097,6 +1102,7 @@ for (;;) count++; ADD_NEW_DATA(-state_offset, count, ncount); break; + default: break; } @@ -1313,15 +1319,20 @@ for (;;) int ncount = 0; switch (c) { - case 0x000d: - if (ptr + 1 < end_subject && ptr[1] == 0x0a) ncount = 1; - /* Fall through */ - case 0x000a: case 0x000b: case 0x000c: case 0x0085: case 0x2028: case 0x2029: + if ((md->moptions & PCRE_BSR_ANYCRLF) != 0) break; + goto ANYNL02; + + case 0x000d: + if (ptr + 1 < end_subject && ptr[1] == 0x0a) ncount = 1; + /* Fall through */ + + ANYNL02: + case 0x000a: if (codevalue == OP_ANYNL_EXTRA + OP_TYPEPOSSTAR || codevalue == OP_ANYNL_EXTRA + OP_TYPEPOSQUERY) { @@ -1330,6 +1341,7 @@ for (;;) } ADD_NEW_DATA(-(state_offset + count), 0, ncount); break; + default: break; } @@ -1545,15 +1557,20 @@ for (;;) int ncount = 0; switch (c) { - case 0x000d: - if (ptr + 1 < end_subject && ptr[1] == 0x0a) ncount = 1; - /* Fall through */ - case 0x000a: case 0x000b: case 0x000c: case 0x0085: case 0x2028: case 0x2029: + if ((md->moptions & PCRE_BSR_ANYCRLF) != 0) break; + goto ANYNL03; + + case 0x000d: + if (ptr + 1 < end_subject && ptr[1] == 0x0a) ncount = 1; + /* Fall through */ + + ANYNL03: + case 0x000a: if (codevalue == OP_ANYNL_EXTRA + OP_TYPEPOSUPTO) { active_count--; /* Remove non-match possibility */ @@ -1564,6 +1581,7 @@ for (;;) else { ADD_NEW_DATA(-state_offset, count, ncount); } break; + default: break; } @@ -1744,14 +1762,17 @@ for (;;) case OP_ANYNL: if (clen > 0) switch(c) { - case 0x000a: case 0x000b: case 0x000c: case 0x0085: case 0x2028: case 0x2029: + if ((md->moptions & PCRE_BSR_ANYCRLF) != 0) break; + + case 0x000a: ADD_NEW(state_offset + 1, 0); break; + case 0x000d: if (ptr + 1 < end_subject && ptr[1] == 0x0a) { @@ -2574,6 +2595,18 @@ md->end_subject = end_subject; md->moptions = options; md->poptions = re->options; +/* If the BSR option is not set at match time, copy what was set +at compile time. */ + +if ((md->moptions & (PCRE_BSR_ANYCRLF|PCRE_BSR_UNICODE)) == 0) + { + if ((re->options & (PCRE_BSR_ANYCRLF|PCRE_BSR_UNICODE)) != 0) + md->moptions |= re->options & (PCRE_BSR_ANYCRLF|PCRE_BSR_UNICODE); +#ifdef BSR_ANYCRLF + else md->moptions |= PCRE_BSR_ANYCRLF; +#endif + } + /* 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. */ diff --git a/pcre_exec.c b/pcre_exec.c index 637c35f..8fcb5c2 100644 --- a/pcre_exec.c +++ b/pcre_exec.c @@ -1526,12 +1526,16 @@ for (;;) case 0x000d: if (eptr < md->end_subject && *eptr == 0x0a) eptr++; break; + case 0x000a: + break; + case 0x000b: case 0x000c: case 0x0085: case 0x2028: case 0x2029: + if (md->bsr_anycrlf) RRETURN(MATCH_NOMATCH); break; } ecode++; @@ -2954,12 +2958,16 @@ for (;;) case 0x000d: if (eptr < md->end_subject && *eptr == 0x0a) eptr++; break; + case 0x000a: + break; + case 0x000b: case 0x000c: case 0x0085: case 0x2028: case 0x2029: + if (md->bsr_anycrlf) RRETURN(MATCH_NOMATCH); break; } } @@ -3172,9 +3180,12 @@ for (;;) if (eptr < md->end_subject && *eptr == 0x0a) eptr++; break; case 0x000a: + break; + case 0x000b: case 0x000c: case 0x0085: + if (md->bsr_anycrlf) RRETURN(MATCH_NOMATCH); break; } } @@ -3426,11 +3437,14 @@ for (;;) if (eptr < md->end_subject && *eptr == 0x0a) eptr++; break; case 0x000a: + break; + case 0x000b: case 0x000c: case 0x0085: case 0x2028: case 0x2029: + if (md->bsr_anycrlf) RRETURN(MATCH_NOMATCH); break; } break; @@ -3582,10 +3596,14 @@ for (;;) case 0x000d: if (eptr < md->end_subject && *eptr == 0x0a) eptr++; break; + case 0x000a: + break; + case 0x000b: case 0x000c: case 0x0085: + if (md->bsr_anycrlf) RRETURN(MATCH_NOMATCH); break; } break; @@ -3883,8 +3901,10 @@ for (;;) } else { - if (c != 0x000a && c != 0x000b && c != 0x000c && - c != 0x0085 && c != 0x2028 && c != 0x2029) + if (c != 0x000a && + (md->bsr_anycrlf || + (c != 0x000b && c != 0x000c && + c != 0x0085 && c != 0x2028 && c != 0x2029))) break; eptr += len; } @@ -4074,7 +4094,9 @@ for (;;) } else { - if (c != 0x000a && c != 0x000b && c != 0x000c && c != 0x0085) + if (c != 0x000a && + (md->bsr_anycrlf || + (c != 0x000b && c != 0x000c && c != 0x0085))) break; eptr++; } @@ -4435,10 +4457,36 @@ md->recursive = NULL; /* No recursion at top level */ md->lcc = tables + lcc_offset; md->ctypes = tables + ctypes_offset; +/* Handle different \R options. */ + +switch (options & (PCRE_BSR_ANYCRLF|PCRE_BSR_UNICODE)) + { + case 0: + if ((re->options & (PCRE_BSR_ANYCRLF|PCRE_BSR_UNICODE)) != 0) + md->bsr_anycrlf = (re->options & PCRE_BSR_ANYCRLF) != 0; + else +#ifdef BSR_ANYCRLF + md->bsr_anycrlf = TRUE; +#else + md->bsr_anycrlf = FALSE; +#endif + break; + + case PCRE_BSR_ANYCRLF: + md->bsr_anycrlf = TRUE; + break; + + case PCRE_BSR_UNICODE: + md->bsr_anycrlf = FALSE; + break; + + default: return PCRE_ERROR_BADNEWLINE; + } + /* Handle different types of newline. The three bits give eight cases. If nothing is set at run time, whatever was used at compile time applies. */ -switch ((((options & PCRE_NEWLINE_BITS) == 0)? re->options : +switch ((((options & PCRE_NEWLINE_BITS) == 0)? re->options : (pcre_uint32)options) & PCRE_NEWLINE_BITS) { case 0: newline = NEWLINE; break; /* Compile-time default */ diff --git a/pcre_internal.h b/pcre_internal.h index e7bbb36..775e03f 100644 --- a/pcre_internal.h +++ b/pcre_internal.h @@ -481,8 +481,8 @@ Standard C system should have one. */ #define PCRE_IMS (PCRE_CASELESS|PCRE_MULTILINE|PCRE_DOTALL) -/* Private flags containing information about the compiled regex. They used to -live at the top end of the options word, but that got almost full, so now they +/* Private flags containing information about the compiled regex. They used to +live at the top end of the options word, but that got almost full, so now they are in a 16-bit flags word. */ #define PCRE_NOPARTIAL 0x0001 /* can't use partial with this regex */ @@ -506,15 +506,16 @@ time, run time, or study time, respectively. */ (PCRE_CASELESS|PCRE_EXTENDED|PCRE_ANCHORED|PCRE_MULTILINE| \ PCRE_DOTALL|PCRE_DOLLAR_ENDONLY|PCRE_EXTRA|PCRE_UNGREEDY|PCRE_UTF8| \ PCRE_NO_AUTO_CAPTURE|PCRE_NO_UTF8_CHECK|PCRE_AUTO_CALLOUT|PCRE_FIRSTLINE| \ - PCRE_DUPNAMES|PCRE_NEWLINE_BITS) + PCRE_DUPNAMES|PCRE_NEWLINE_BITS|PCRE_BSR_ANYCRLF|PCRE_BSR_UNICODE) #define PUBLIC_EXEC_OPTIONS \ (PCRE_ANCHORED|PCRE_NOTBOL|PCRE_NOTEOL|PCRE_NOTEMPTY|PCRE_NO_UTF8_CHECK| \ - PCRE_PARTIAL|PCRE_NEWLINE_BITS) + PCRE_PARTIAL|PCRE_NEWLINE_BITS|PCRE_BSR_ANYCRLF|PCRE_BSR_UNICODE) #define PUBLIC_DFA_EXEC_OPTIONS \ (PCRE_ANCHORED|PCRE_NOTBOL|PCRE_NOTEOL|PCRE_NOTEMPTY|PCRE_NO_UTF8_CHECK| \ - PCRE_PARTIAL|PCRE_DFA_SHORTEST|PCRE_DFA_RESTART|PCRE_NEWLINE_BITS) + PCRE_PARTIAL|PCRE_DFA_SHORTEST|PCRE_DFA_RESTART|PCRE_NEWLINE_BITS| \ + PCRE_BSR_ANYCRLF|PCRE_BSR_UNICODE) #define PUBLIC_STUDY_OPTIONS 0 /* None defined */ @@ -937,7 +938,7 @@ typedef struct compile_data { int top_backref; /* Maximum back reference */ unsigned int backref_map; /* Bitmap of low back refs */ int external_options; /* External (initial) options */ - int external_flags; /* External flag bits to be set */ + int external_flags; /* External flag bits to be set */ int req_varyopt; /* "After variable item" flag for reqbyte */ BOOL had_accept; /* (*ACCEPT) encountered */ int nltype; /* Newline type */ @@ -998,6 +999,7 @@ typedef struct match_data { BOOL notempty; /* Empty string match not wanted */ BOOL partial; /* PARTIAL flag */ BOOL hitend; /* Hit the end of the subject at some point */ + BOOL bsr_anycrlf; /* \R is just any CRLF, not full Unicode */ const uschar *start_code; /* For use when recursing */ USPTR start_subject; /* Start of the subject string */ USPTR end_subject; /* End of the subject string */ @@ -712,6 +712,8 @@ if (strncmpic(p, (uschar *)"lf>", 3) == 0) return PCRE_NEWLINE_LF; if (strncmpic(p, (uschar *)"crlf>", 5) == 0) return PCRE_NEWLINE_CRLF; if (strncmpic(p, (uschar *)"anycrlf>", 8) == 0) return PCRE_NEWLINE_ANYCRLF; if (strncmpic(p, (uschar *)"any>", 4) == 0) return PCRE_NEWLINE_ANY; +if (strncmpic(p, (uschar *)"bsr_anycrlf>", 12) == 0) return PCRE_BSR_ANYCRLF; +if (strncmpic(p, (uschar *)"bsr_unicode>", 12) == 0) return PCRE_BSR_UNICODE; fprintf(f, "Unknown newline type at: <%s\n", p); return 0; } @@ -885,6 +887,9 @@ while (argc > 1 && argv[op][0] == '-') (rc == '\n')? "LF" : (rc == ('\r'<<8 | '\n'))? "CRLF" : (rc == -2)? "ANYCRLF" : (rc == -1)? "ANY" : "???"); + (void)pcre_config(PCRE_CONFIG_BSR, &rc); + printf(" \\R matches %s\n", rc? "CR, LF, or CRLF only" : + "all Unicode newlines"); (void)pcre_config(PCRE_CONFIG_LINK_SIZE, &rc); printf(" Internal link size = %d\n", rc); (void)pcre_config(PCRE_CONFIG_POSIX_MALLOC_THRESHOLD, &rc); @@ -1349,7 +1354,7 @@ while (!done) rre->magic_number = byteflip(rre->magic_number, sizeof(rre->magic_number)); rre->size = byteflip(rre->size, sizeof(rre->size)); rre->options = byteflip(rre->options, sizeof(rre->options)); - rre->flags = byteflip(rre->flags, sizeof(rre->flags)); + rre->flags = byteflip(rre->flags, sizeof(rre->flags)); rre->top_bracket = byteflip(rre->top_bracket, sizeof(rre->top_bracket)); rre->top_backref = byteflip(rre->top_backref, sizeof(rre->top_backref)); rre->first_byte = byteflip(rre->first_byte, sizeof(rre->first_byte)); @@ -1449,13 +1454,15 @@ while (!done) 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", + else fprintf(outfile, "Options:%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s\n", ((get_options & PCRE_ANCHORED) != 0)? " anchored" : "", ((get_options & PCRE_CASELESS) != 0)? " caseless" : "", ((get_options & PCRE_EXTENDED) != 0)? " extended" : "", ((get_options & PCRE_MULTILINE) != 0)? " multiline" : "", ((get_options & PCRE_FIRSTLINE) != 0)? " firstline" : "", ((get_options & PCRE_DOTALL) != 0)? " dotall" : "", + ((get_options & PCRE_BSR_ANYCRLF) != 0)? " bsr_anycrlf" : "", + ((get_options & PCRE_BSR_UNICODE) != 0)? " bsr_unicode" : "", ((get_options & PCRE_DOLLAR_ENDONLY) != 0)? " dollar_endonly" : "", ((get_options & PCRE_EXTRA) != 0)? " extra" : "", ((get_options & PCRE_UNGREEDY) != 0)? " ungreedy" : "", diff --git a/testdata/testinput2 b/testdata/testinput2 index c9f1018..f9e470f 100644 --- a/testdata/testinput2 +++ b/testdata/testinput2 @@ -2464,4 +2464,75 @@ a random value. /Ix a\r\nb a\x85b +/a\Rb/I<bsr_anycrlf> + a\rb + a\nb + a\r\nb + ** Failers + a\x85b + a\x0bb + +/a\Rb/I<bsr_unicode> + a\rb + a\nb + a\r\nb + a\x85b + a\x0bb + ** Failers + a\x85b\<bsr_anycrlf> + a\x0bb\<bsr_anycrlf> + +/a\R?b/I<bsr_anycrlf> + a\rb + a\nb + a\r\nb + ** Failers + a\x85b + a\x0bb + +/a\R?b/I<bsr_unicode> + a\rb + a\nb + a\r\nb + a\x85b + a\x0bb + ** Failers + a\x85b\<bsr_anycrlf> + a\x0bb\<bsr_anycrlf> + +/a\R{2,4}b/I<bsr_anycrlf> + a\r\n\nb + a\n\r\rb + a\r\n\r\n\r\n\r\nb + ** Failers + a\x85\85b + a\x0b\0bb + +/a\R{2,4}b/I<bsr_unicode> + a\r\rb + a\n\n\nb + a\r\n\n\r\rb + a\x85\85b + a\x0b\0bb + ** Failers + a\r\r\r\r\rb + a\x85\85b\<bsr_anycrlf> + a\x0b\0bb\<bsr_anycrlf> + +/(*BSR_ANYCRLF)a\Rb/I + a\nb + a\rb + +/(*BSR_UNICODE)a\Rb/I + a\x85b + +/(*BSR_ANYCRLF)(*CRLF)a\Rb/I + a\nb + a\rb + +/(*CRLF)(*BSR_UNICODE)a\Rb/I + a\x85b + +/(*CRLF)(*BSR_ANYCRLF)(*CR)ab/I + / End of testinput2 / diff --git a/testdata/testinput5 b/testdata/testinput5 index aa0123b..1412c18 100644 --- a/testdata/testinput5 +++ b/testdata/testinput5 @@ -417,4 +417,40 @@ can't tell the difference.) --/ \x{7fffffff} \x{7fffffff}\? +/a\Rb/I8<bsr_anycrlf> + a\rb + a\nb + a\r\nb + ** Failers + a\x{85}b + a\x0bb + +/a\Rb/I8<bsr_unicode> + a\rb + a\nb + a\r\nb + a\x{85}b + a\x0bb + ** Failers + a\x{85}b\<bsr_anycrlf> + a\x0bb\<bsr_anycrlf> + +/a\R?b/I8<bsr_anycrlf> + a\rb + a\nb + a\r\nb + ** Failers + a\x{85}b + a\x0bb + +/a\R?b/I8<bsr_unicode> + a\rb + a\nb + a\r\nb + a\x{85}b + a\x0bb + ** Failers + a\x{85}b\<bsr_anycrlf> + a\x0bb\<bsr_anycrlf> + / End of testinput5 / diff --git a/testdata/testinput7 b/testdata/testinput7 index 76524b7..97f5a2c 100644 --- a/testdata/testinput7 +++ b/testdata/testinput7 @@ -4310,4 +4310,59 @@ /(\r|\n)A/<crlf> \r\nA +/a\Rb/I<bsr_anycrlf> + a\rb + a\nb + a\r\nb + ** Failers + a\x85b + a\x0bb + +/a\Rb/I<bsr_unicode> + a\rb + a\nb + a\r\nb + a\x85b + a\x0bb + ** Failers + a\x85b\<bsr_anycrlf> + a\x0bb\<bsr_anycrlf> + +/a\R?b/I<bsr_anycrlf> + a\rb + a\nb + a\r\nb + ** Failers + a\x85b + a\x0bb + +/a\R?b/I<bsr_unicode> + a\rb + a\nb + a\r\nb + a\x85b + a\x0bb + ** Failers + a\x85b\<bsr_anycrlf> + a\x0bb\<bsr_anycrlf> + +/a\R{2,4}b/I<bsr_anycrlf> + a\r\n\nb + a\n\r\rb + a\r\n\r\n\r\n\r\nb + ** Failers + a\x85\85b + a\x0b\0bb + +/a\R{2,4}b/I<bsr_unicode> + a\r\rb + a\n\n\nb + a\r\n\n\r\rb + a\x85\85b + a\x0b\0bb + ** Failers + a\r\r\r\r\rb + a\x85\85b\<bsr_anycrlf> + a\x0b\0bb\<bsr_anycrlf> + / End of testinput7 / diff --git a/testdata/testinput8 b/testdata/testinput8 index 61e70e5..6e8b5db 100644 --- a/testdata/testinput8 +++ b/testdata/testinput8 @@ -628,4 +628,40 @@ ** Failers \x09\x{200a}\x{a0}\x{2028}\x0b +/a\Rb/I8<bsr_anycrlf> + a\rb + a\nb + a\r\nb + ** Failers + a\x{85}b + a\x0bb + +/a\Rb/I8<bsr_unicode> + a\rb + a\nb + a\r\nb + a\x{85}b + a\x0bb + ** Failers + a\x{85}b\<bsr_anycrlf> + a\x0bb\<bsr_anycrlf> + +/a\R?b/I8<bsr_anycrlf> + a\rb + a\nb + a\r\nb + ** Failers + a\x{85}b + a\x0bb + +/a\R?b/I8<bsr_unicode> + a\rb + a\nb + a\r\nb + a\x{85}b + a\x0bb + ** Failers + a\x{85}b\<bsr_anycrlf> + a\x0bb\<bsr_anycrlf> + / End of testinput 8 / diff --git a/testdata/testoutput2 b/testdata/testoutput2 index 956c544..00d83ab 100644 --- a/testdata/testoutput2 +++ b/testdata/testoutput2 @@ -9133,4 +9133,173 @@ No match a\x85b No match +/a\Rb/I<bsr_anycrlf> +Capturing subpattern count = 0 +Options: bsr_anycrlf +First char = 'a' +Need char = 'b' + a\rb + 0: a\x0db + a\nb + 0: a\x0ab + a\r\nb + 0: a\x0d\x0ab + ** Failers +No match + a\x85b +No match + a\x0bb +No match + +/a\Rb/I<bsr_unicode> +Capturing subpattern count = 0 +Options: bsr_unicode +First char = 'a' +Need char = 'b' + a\rb + 0: a\x0db + a\nb + 0: a\x0ab + a\r\nb + 0: a\x0d\x0ab + a\x85b + 0: a\x85b + a\x0bb + 0: a\x0bb + ** Failers +No match + a\x85b\<bsr_anycrlf> +No match + a\x0bb\<bsr_anycrlf> +No match + +/a\R?b/I<bsr_anycrlf> +Capturing subpattern count = 0 +Options: bsr_anycrlf +First char = 'a' +Need char = 'b' + a\rb + 0: a\x0db + a\nb + 0: a\x0ab + a\r\nb + 0: a\x0d\x0ab + ** Failers +No match + a\x85b +No match + a\x0bb +No match + +/a\R?b/I<bsr_unicode> +Capturing subpattern count = 0 +Options: bsr_unicode +First char = 'a' +Need char = 'b' + a\rb + 0: a\x0db + a\nb + 0: a\x0ab + a\r\nb + 0: a\x0d\x0ab + a\x85b + 0: a\x85b + a\x0bb + 0: a\x0bb + ** Failers +No match + a\x85b\<bsr_anycrlf> +No match + a\x0bb\<bsr_anycrlf> +No match + +/a\R{2,4}b/I<bsr_anycrlf> +Capturing subpattern count = 0 +Partial matching not supported +Options: bsr_anycrlf +First char = 'a' +Need char = 'b' + a\r\n\nb + 0: a\x0d\x0a\x0ab + a\n\r\rb + 0: a\x0a\x0d\x0db + a\r\n\r\n\r\n\r\nb + 0: a\x0d\x0a\x0d\x0a\x0d\x0a\x0d\x0ab + ** Failers +No match + a\x85\85b +No match + a\x0b\0bb +No match + +/a\R{2,4}b/I<bsr_unicode> +Capturing subpattern count = 0 +Partial matching not supported +Options: bsr_unicode +First char = 'a' +Need char = 'b' + a\r\rb + 0: a\x0d\x0db + a\n\n\nb + 0: a\x0a\x0a\x0ab + a\r\n\n\r\rb + 0: a\x0d\x0a\x0a\x0d\x0db + a\x85\85b +No match + a\x0b\0bb +No match + ** Failers +No match + a\r\r\r\r\rb +No match + a\x85\85b\<bsr_anycrlf> +No match + a\x0b\0bb\<bsr_anycrlf> +No match + +/(*BSR_ANYCRLF)a\Rb/I +Capturing subpattern count = 0 +Options: bsr_anycrlf +First char = 'a' +Need char = 'b' + a\nb + 0: a\x0ab + a\rb + 0: a\x0db + +/(*BSR_UNICODE)a\Rb/I +Capturing subpattern count = 0 +Options: bsr_unicode +First char = 'a' +Need char = 'b' + a\x85b + 0: a\x85b + +/(*BSR_ANYCRLF)(*CRLF)a\Rb/I +Capturing subpattern count = 0 +Options: bsr_anycrlf +Forced newline sequence: CRLF +First char = 'a' +Need char = 'b' + a\nb + 0: a\x0ab + a\rb + 0: a\x0db + +/(*CRLF)(*BSR_UNICODE)a\Rb/I +Capturing subpattern count = 0 +Options: bsr_unicode +Forced newline sequence: CRLF +First char = 'a' +Need char = 'b' + a\x85b + 0: a\x85b + +/(*CRLF)(*BSR_ANYCRLF)(*CR)ab/I +Capturing subpattern count = 0 +Options: bsr_anycrlf +Forced newline sequence: CR +First char = 'a' +Need char = 'b' + / End of testinput2 / diff --git a/testdata/testoutput5 b/testdata/testoutput5 index cd8958a..8caab88 100644 --- a/testdata/testoutput5 +++ b/testdata/testoutput5 @@ -1515,4 +1515,84 @@ Error -10 \x{7fffffff}\? No match +/a\Rb/I8<bsr_anycrlf> +Capturing subpattern count = 0 +Options: bsr_anycrlf utf8 +First char = 'a' +Need char = 'b' + a\rb + 0: a\x{0d}b + a\nb + 0: a\x{0a}b + a\r\nb + 0: a\x{0d}\x{0a}b + ** Failers +No match + a\x{85}b +No match + a\x0bb +No match + +/a\Rb/I8<bsr_unicode> +Capturing subpattern count = 0 +Options: bsr_unicode utf8 +First char = 'a' +Need char = 'b' + a\rb + 0: a\x{0d}b + a\nb + 0: a\x{0a}b + a\r\nb + 0: a\x{0d}\x{0a}b + a\x{85}b + 0: a\x{85}b + a\x0bb + 0: a\x{0b}b + ** Failers +No match + a\x{85}b\<bsr_anycrlf> +No match + a\x0bb\<bsr_anycrlf> +No match + +/a\R?b/I8<bsr_anycrlf> +Capturing subpattern count = 0 +Options: bsr_anycrlf utf8 +First char = 'a' +Need char = 'b' + a\rb + 0: a\x{0d}b + a\nb + 0: a\x{0a}b + a\r\nb + 0: a\x{0d}\x{0a}b + ** Failers +No match + a\x{85}b +No match + a\x0bb +No match + +/a\R?b/I8<bsr_unicode> +Capturing subpattern count = 0 +Options: bsr_unicode utf8 +First char = 'a' +Need char = 'b' + a\rb + 0: a\x{0d}b + a\nb + 0: a\x{0a}b + a\r\nb + 0: a\x{0d}\x{0a}b + a\x{85}b + 0: a\x{85}b + a\x0bb + 0: a\x{0b}b + ** Failers +No match + a\x{85}b\<bsr_anycrlf> +No match + a\x0bb\<bsr_anycrlf> +No match + / End of testinput5 / diff --git a/testdata/testoutput7 b/testdata/testoutput7 index 39c5075..083ceef 100644 --- a/testdata/testoutput7 +++ b/testdata/testoutput7 @@ -7088,4 +7088,128 @@ No match \r\nA 0: \x0aA +/a\Rb/I<bsr_anycrlf> +Capturing subpattern count = 0 +Options: bsr_anycrlf +First char = 'a' +Need char = 'b' + a\rb + 0: a\x0db + a\nb + 0: a\x0ab + a\r\nb + 0: a\x0d\x0ab + ** Failers +No match + a\x85b +No match + a\x0bb +No match + +/a\Rb/I<bsr_unicode> +Capturing subpattern count = 0 +Options: bsr_unicode +First char = 'a' +Need char = 'b' + a\rb + 0: a\x0db + a\nb + 0: a\x0ab + a\r\nb + 0: a\x0d\x0ab + a\x85b + 0: a\x85b + a\x0bb + 0: a\x0bb + ** Failers +No match + a\x85b\<bsr_anycrlf> +No match + a\x0bb\<bsr_anycrlf> +No match + +/a\R?b/I<bsr_anycrlf> +Capturing subpattern count = 0 +Options: bsr_anycrlf +First char = 'a' +Need char = 'b' + a\rb + 0: a\x0db + a\nb + 0: a\x0ab + a\r\nb + 0: a\x0d\x0ab + ** Failers +No match + a\x85b +No match + a\x0bb +No match + +/a\R?b/I<bsr_unicode> +Capturing subpattern count = 0 +Options: bsr_unicode +First char = 'a' +Need char = 'b' + a\rb + 0: a\x0db + a\nb + 0: a\x0ab + a\r\nb + 0: a\x0d\x0ab + a\x85b + 0: a\x85b + a\x0bb + 0: a\x0bb + ** Failers +No match + a\x85b\<bsr_anycrlf> +No match + a\x0bb\<bsr_anycrlf> +No match + +/a\R{2,4}b/I<bsr_anycrlf> +Capturing subpattern count = 0 +Partial matching not supported +Options: bsr_anycrlf +First char = 'a' +Need char = 'b' + a\r\n\nb + 0: a\x0d\x0a\x0ab + a\n\r\rb + 0: a\x0a\x0d\x0db + a\r\n\r\n\r\n\r\nb + 0: a\x0d\x0a\x0d\x0a\x0d\x0a\x0d\x0ab + ** Failers +No match + a\x85\85b +No match + a\x0b\0bb +No match + +/a\R{2,4}b/I<bsr_unicode> +Capturing subpattern count = 0 +Partial matching not supported +Options: bsr_unicode +First char = 'a' +Need char = 'b' + a\r\rb + 0: a\x0d\x0db + a\n\n\nb + 0: a\x0a\x0a\x0ab + a\r\n\n\r\rb + 0: a\x0d\x0a\x0a\x0d\x0db + a\x85\85b +No match + a\x0b\0bb +No match + ** Failers +No match + a\r\r\r\r\rb +No match + a\x85\85b\<bsr_anycrlf> +No match + a\x0b\0bb\<bsr_anycrlf> +No match + / End of testinput7 / diff --git a/testdata/testoutput8 b/testdata/testoutput8 index db0f4ad..72d88f3 100644 --- a/testdata/testoutput8 +++ b/testdata/testoutput8 @@ -1204,4 +1204,84 @@ No match \x09\x{200a}\x{a0}\x{2028}\x0b No match +/a\Rb/I8<bsr_anycrlf> +Capturing subpattern count = 0 +Options: bsr_anycrlf utf8 +First char = 'a' +Need char = 'b' + a\rb + 0: a\x{0d}b + a\nb + 0: a\x{0a}b + a\r\nb + 0: a\x{0d}\x{0a}b + ** Failers +No match + a\x{85}b +No match + a\x0bb +No match + +/a\Rb/I8<bsr_unicode> +Capturing subpattern count = 0 +Options: bsr_unicode utf8 +First char = 'a' +Need char = 'b' + a\rb + 0: a\x{0d}b + a\nb + 0: a\x{0a}b + a\r\nb + 0: a\x{0d}\x{0a}b + a\x{85}b + 0: a\x{85}b + a\x0bb + 0: a\x{0b}b + ** Failers +No match + a\x{85}b\<bsr_anycrlf> +No match + a\x0bb\<bsr_anycrlf> +No match + +/a\R?b/I8<bsr_anycrlf> +Capturing subpattern count = 0 +Options: bsr_anycrlf utf8 +First char = 'a' +Need char = 'b' + a\rb + 0: a\x{0d}b + a\nb + 0: a\x{0a}b + a\r\nb + 0: a\x{0d}\x{0a}b + ** Failers +No match + a\x{85}b +No match + a\x0bb +No match + +/a\R?b/I8<bsr_unicode> +Capturing subpattern count = 0 +Options: bsr_unicode utf8 +First char = 'a' +Need char = 'b' + a\rb + 0: a\x{0d}b + a\nb + 0: a\x{0a}b + a\r\nb + 0: a\x{0d}\x{0a}b + a\x{85}b + 0: a\x{85}b + a\x0bb + 0: a\x{0b}b + ** Failers +No match + a\x{85}b\<bsr_anycrlf> +No match + a\x0bb\<bsr_anycrlf> +No match + / End of testinput 8 / |