Added PCRE_UCP and related stuff to make \w etc use Unicode properties.

git-svn-id: svn://vcs.exim.org/pcre/code/trunk@518 2f5784b3-3f2a-0410-8824-cb99058d5e15

1 files changed, 56 insertions, 45 deletions

diff --git a/doc/html/pcresyntax.html b/doc/html/pcresyntax.html
index 1a2749f..ad4399d 100644
--- a/doc/html/pcresyntax.html
+++ b/doc/html/pcresyntax.html
@@ -17,28 +17,29 @@ man page, in case the conversion went wrong.
 <li><a name="TOC2" href="#SEC2">QUOTING</a>
 <li><a name="TOC3" href="#SEC3">CHARACTERS</a>
 <li><a name="TOC4" href="#SEC4">CHARACTER TYPES</a>
-<li><a name="TOC5" href="#SEC5">GENERAL CATEGORY PROPERTY CODES FOR \p and \P</a>
-<li><a name="TOC6" href="#SEC6">SCRIPT NAMES FOR \p AND \P</a>
-<li><a name="TOC7" href="#SEC7">CHARACTER CLASSES</a>
-<li><a name="TOC8" href="#SEC8">QUANTIFIERS</a>
-<li><a name="TOC9" href="#SEC9">ANCHORS AND SIMPLE ASSERTIONS</a>
-<li><a name="TOC10" href="#SEC10">MATCH POINT RESET</a>
-<li><a name="TOC11" href="#SEC11">ALTERNATION</a>
-<li><a name="TOC12" href="#SEC12">CAPTURING</a>
-<li><a name="TOC13" href="#SEC13">ATOMIC GROUPS</a>
-<li><a name="TOC14" href="#SEC14">COMMENT</a>
-<li><a name="TOC15" href="#SEC15">OPTION SETTING</a>
-<li><a name="TOC16" href="#SEC16">LOOKAHEAD AND LOOKBEHIND ASSERTIONS</a>
-<li><a name="TOC17" href="#SEC17">BACKREFERENCES</a>
-<li><a name="TOC18" href="#SEC18">SUBROUTINE REFERENCES (POSSIBLY RECURSIVE)</a>
-<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">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>
+<li><a name="TOC5" href="#SEC5">GENERAL CATEGORY PROPERTIES FOR \p and \P</a>
+<li><a name="TOC6" href="#SEC6">PCRE SPECIAL CATEGORY PROPERTIES FOR \p and \P</a>
+<li><a name="TOC7" href="#SEC7">SCRIPT NAMES FOR \p AND \P</a>
+<li><a name="TOC8" href="#SEC8">CHARACTER CLASSES</a>
+<li><a name="TOC9" href="#SEC9">QUANTIFIERS</a>
+<li><a name="TOC10" href="#SEC10">ANCHORS AND SIMPLE ASSERTIONS</a>
+<li><a name="TOC11" href="#SEC11">MATCH POINT RESET</a>
+<li><a name="TOC12" href="#SEC12">ALTERNATION</a>
+<li><a name="TOC13" href="#SEC13">CAPTURING</a>
+<li><a name="TOC14" href="#SEC14">ATOMIC GROUPS</a>
+<li><a name="TOC15" href="#SEC15">COMMENT</a>
+<li><a name="TOC16" href="#SEC16">OPTION SETTING</a>
+<li><a name="TOC17" href="#SEC17">LOOKAHEAD AND LOOKBEHIND ASSERTIONS</a>
+<li><a name="TOC18" href="#SEC18">BACKREFERENCES</a>
+<li><a name="TOC19" href="#SEC19">SUBROUTINE REFERENCES (POSSIBLY RECURSIVE)</a>
+<li><a name="TOC20" href="#SEC20">CONDITIONAL PATTERNS</a>
+<li><a name="TOC21" href="#SEC21">BACKTRACKING CONTROL</a>
+<li><a name="TOC22" href="#SEC22">NEWLINE CONVENTIONS</a>
+<li><a name="TOC23" href="#SEC23">WHAT \R MATCHES</a>
+<li><a name="TOC24" href="#SEC24">CALLOUTS</a>
+<li><a name="TOC25" href="#SEC25">SEE ALSO</a>
+<li><a name="TOC26" href="#SEC26">AUTHOR</a>
+<li><a name="TOC27" href="#SEC27">REVISION</a>
 </ul>
 <br><a name="SEC1" href="#TOC1">PCRE REGULAR EXPRESSION SYNTAX SUMMARY</a><br>
 <P>
@@ -80,6 +81,7 @@ syntax.
   \D         a character that is not a decimal digit
   \h         a horizontal whitespace character
   \H         a character that is not a horizontal whitespace character
+  \N         a character that is not a newline 
   \p{<i>xx</i>}     a character with the <i>xx</i> property
   \P{<i>xx</i>}     a character without the <i>xx</i> property
   \R         a newline sequence
@@ -93,7 +95,7 @@ syntax.
 </pre>
 In PCRE, \d, \D, \s, \S, \w, and \W recognize only ASCII characters.
 </P>
-<br><a name="SEC5" href="#TOC1">GENERAL CATEGORY PROPERTY CODES FOR \p and \P</a><br>
+<br><a name="SEC5" href="#TOC1">GENERAL CATEGORY PROPERTIES FOR \p and \P</a><br>
 <P>
 <pre>
   C          Other
@@ -142,7 +144,16 @@ In PCRE, \d, \D, \s, \S, \w, and \W recognize only ASCII characters.
   Zs         Space separator
 </PRE>
 </P>
-<br><a name="SEC6" href="#TOC1">SCRIPT NAMES FOR \p AND \P</a><br>
+<br><a name="SEC6" href="#TOC1">PCRE SPECIAL CATEGORY PROPERTIES FOR \p and \P</a><br>
+<P>
+<pre>
+  Xan        Alphanumeric: union of properties L and N
+  Xps        POSIX space: property Z or tab, NL, VT, FF, CR
+  Xsp        Perl space: property Z or tab, NL, FF, CR
+  Xwd        Perl word: property Xan or underscore 
+</PRE>
+</P>
+<br><a name="SEC7" href="#TOC1">SCRIPT NAMES FOR \p AND \P</a><br>
 <P>
 Arabic,
 Armenian,
@@ -237,7 +248,7 @@ Ugaritic,
 Vai,
 Yi.
 </P>
-<br><a name="SEC7" href="#TOC1">CHARACTER CLASSES</a><br>
+<br><a name="SEC8" href="#TOC1">CHARACTER CLASSES</a><br>
 <P>
 <pre>
   [...]       positive character class
@@ -264,7 +275,7 @@ Yi.
 In PCRE, POSIX character set names recognize only ASCII characters. You can use
 \Q...\E inside a character class.
 </P>
-<br><a name="SEC8" href="#TOC1">QUANTIFIERS</a><br>
+<br><a name="SEC9" href="#TOC1">QUANTIFIERS</a><br>
 <P>
 <pre>
   ?           0 or 1, greedy
@@ -285,7 +296,7 @@ In PCRE, POSIX character set names recognize only ASCII characters. You can use
   {n,}?       n or more, lazy
 </PRE>
 </P>
-<br><a name="SEC9" href="#TOC1">ANCHORS AND SIMPLE ASSERTIONS</a><br>
+<br><a name="SEC10" href="#TOC1">ANCHORS AND SIMPLE ASSERTIONS</a><br>
 <P>
 <pre>
   \b          word boundary (only ASCII letters recognized)
@@ -302,19 +313,19 @@ In PCRE, POSIX character set names recognize only ASCII characters. You can use
   \G          first matching position in subject
 </PRE>
 </P>
-<br><a name="SEC10" href="#TOC1">MATCH POINT RESET</a><br>
+<br><a name="SEC11" href="#TOC1">MATCH POINT RESET</a><br>
 <P>
 <pre>
   \K          reset start of match
 </PRE>
 </P>
-<br><a name="SEC11" href="#TOC1">ALTERNATION</a><br>
+<br><a name="SEC12" href="#TOC1">ALTERNATION</a><br>
 <P>
 <pre>
   expr|expr|expr...
 </PRE>
 </P>
-<br><a name="SEC12" href="#TOC1">CAPTURING</a><br>
+<br><a name="SEC13" href="#TOC1">CAPTURING</a><br>
 <P>
 <pre>
   (...)           capturing group
@@ -326,19 +337,19 @@ In PCRE, POSIX character set names recognize only ASCII characters. You can use
                    capturing groups in each alternative
 </PRE>
 </P>
-<br><a name="SEC13" href="#TOC1">ATOMIC GROUPS</a><br>
+<br><a name="SEC14" href="#TOC1">ATOMIC GROUPS</a><br>
 <P>
 <pre>
   (?&#62;...)         atomic, non-capturing group
 </PRE>
 </P>
-<br><a name="SEC14" href="#TOC1">COMMENT</a><br>
+<br><a name="SEC15" href="#TOC1">COMMENT</a><br>
 <P>
 <pre>
   (?#....)        comment (not nestable)
 </PRE>
 </P>
-<br><a name="SEC15" href="#TOC1">OPTION SETTING</a><br>
+<br><a name="SEC16" href="#TOC1">OPTION SETTING</a><br>
 <P>
 <pre>
   (?i)            caseless
@@ -355,7 +366,7 @@ newline-setting options with similar syntax:
   (*UTF8)         set UTF-8 mode
 </PRE>
 </P>
-<br><a name="SEC16" href="#TOC1">LOOKAHEAD AND LOOKBEHIND ASSERTIONS</a><br>
+<br><a name="SEC17" href="#TOC1">LOOKAHEAD AND LOOKBEHIND ASSERTIONS</a><br>
 <P>
 <pre>
   (?=...)         positive look ahead
@@ -365,7 +376,7 @@ newline-setting options with similar syntax:
 </pre>
 Each top-level branch of a look behind must be of a fixed length.
 </P>
-<br><a name="SEC17" href="#TOC1">BACKREFERENCES</a><br>
+<br><a name="SEC18" href="#TOC1">BACKREFERENCES</a><br>
 <P>
 <pre>
   \n              reference by number (can be ambiguous)
@@ -379,7 +390,7 @@ Each top-level branch of a look behind must be of a fixed length.
   (?P=name)       reference by name (Python)
 </PRE>
 </P>
-<br><a name="SEC18" href="#TOC1">SUBROUTINE REFERENCES (POSSIBLY RECURSIVE)</a><br>
+<br><a name="SEC19" href="#TOC1">SUBROUTINE REFERENCES (POSSIBLY RECURSIVE)</a><br>
 <P>
 <pre>
   (?R)            recurse whole pattern
@@ -398,7 +409,7 @@ Each top-level branch of a look behind must be of a fixed length.
   \g'-n'          call subpattern by relative number (PCRE extension)
 </PRE>
 </P>
-<br><a name="SEC19" href="#TOC1">CONDITIONAL PATTERNS</a><br>
+<br><a name="SEC20" href="#TOC1">CONDITIONAL PATTERNS</a><br>
 <P>
 <pre>
   (?(condition)yes-pattern)
@@ -417,7 +428,7 @@ Each top-level branch of a look behind must be of a fixed length.
   (?(assert)...   assertion condition
 </PRE>
 </P>
-<br><a name="SEC20" href="#TOC1">BACKTRACKING CONTROL</a><br>
+<br><a name="SEC21" href="#TOC1">BACKTRACKING CONTROL</a><br>
 <P>
 The following act immediately they are reached:
 <pre>
@@ -435,7 +446,7 @@ pattern is not anchored.
   (*THEN)         local failure, backtrack to next alternation
 </PRE>
 </P>
-<br><a name="SEC21" href="#TOC1">NEWLINE CONVENTIONS</a><br>
+<br><a name="SEC22" href="#TOC1">NEWLINE CONVENTIONS</a><br>
 <P>
 These are recognized only at the very start of the pattern or after a
 (*BSR_...) or (*UTF8) option.
@@ -447,7 +458,7 @@ These are recognized only at the very start of the pattern or after a
   (*ANY)          any Unicode newline sequence
 </PRE>
 </P>
-<br><a name="SEC22" href="#TOC1">WHAT \R MATCHES</a><br>
+<br><a name="SEC23" href="#TOC1">WHAT \R MATCHES</a><br>
 <P>
 These are recognized only at the very start of the pattern or after a
 (*...) option that sets the newline convention or UTF-8 mode.
@@ -456,19 +467,19 @@ These are recognized only at the very start of the pattern or after a
   (*BSR_UNICODE)  any Unicode newline sequence
 </PRE>
 </P>
-<br><a name="SEC23" href="#TOC1">CALLOUTS</a><br>
+<br><a name="SEC24" href="#TOC1">CALLOUTS</a><br>
 <P>
 <pre>
   (?C)      callout
   (?Cn)     callout with data n
 </PRE>
 </P>
-<br><a name="SEC24" href="#TOC1">SEE ALSO</a><br>
+<br><a name="SEC25" 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="SEC25" href="#TOC1">AUTHOR</a><br>
+<br><a name="SEC26" href="#TOC1">AUTHOR</a><br>
 <P>
 Philip Hazel
 <br>
@@ -477,9 +488,9 @@ University Computing Service
 Cambridge CB2 3QH, England.
 <br>
 </P>
-<br><a name="SEC26" href="#TOC1">REVISION</a><br>
+<br><a name="SEC27" href="#TOC1">REVISION</a><br>
 <P>
-Last updated: 01 March 2010
+Last updated: 05 May 2010
 <br>
 Copyright &copy; 1997-2010 University of Cambridge.
 <br>