--- embedaddon/pcre/doc/pcresyntax.3	2012/02/21 23:50:25	1.1.1.2
+++ embedaddon/pcre/doc/pcresyntax.3	2014/06/15 19:46:05	1.1.1.5
@@ -1,4 +1,4 @@
-.TH PCRESYNTAX 3
+.TH PCRESYNTAX 3 "12 November 2013" "PCRE 8.34"
 .SH NAME
 PCRE - Perl-compatible regular expressions
 .SH "PCRE REGULAR EXPRESSION SYNTAX SUMMARY"
@@ -25,13 +25,18 @@ documentation. This document contains a quick-referenc
   \ea         alarm, that is, the BEL character (hex 07)
   \ecx        "control-x", where x is any ASCII character
   \ee         escape (hex 1B)
-  \ef         formfeed (hex 0C)
+  \ef         form feed (hex 0C)
   \en         newline (hex 0A)
   \er         carriage return (hex 0D)
   \et         tab (hex 09)
+  \e0dd       character with octal code 0dd
   \eddd       character with octal code ddd, or backreference
+  \eo{ddd..}  character with octal code ddd..
   \exhh       character with hex code hh
   \ex{hhh..}  character with hex code hhh..
+.sp
+Note that \e0dd is always an octal code, and that \e8 and \e9 are the literal
+characters "8" and "9".
 .
 .
 .SH "CHARACTER TYPES"
@@ -42,23 +47,25 @@ documentation. This document contains a quick-referenc
   \eC         one data unit, even in UTF mode (best avoided)
   \ed         a decimal digit
   \eD         a character that is not a decimal digit
-  \eh         a horizontal whitespace character
-  \eH         a character that is not a horizontal whitespace character
+  \eh         a horizontal white space character
+  \eH         a character that is not a horizontal white space character
   \eN         a character that is not a newline
   \ep{\fIxx\fP}     a character with the \fIxx\fP property
   \eP{\fIxx\fP}     a character without the \fIxx\fP property
   \eR         a newline sequence
-  \es         a whitespace character
-  \eS         a character that is not a whitespace character
-  \ev         a vertical whitespace character
-  \eV         a character that is not a vertical whitespace character
+  \es         a white space character
+  \eS         a character that is not a white space character
+  \ev         a vertical white space character
+  \eV         a character that is not a vertical white space character
   \ew         a "word" character
   \eW         a "non-word" character
-  \eX         an extended Unicode sequence
+  \eX         a Unicode extended grapheme cluster
 .sp
-In PCRE, by default, \ed, \eD, \es, \eS, \ew, and \eW recognize only ASCII
-characters, even in a UTF mode. However, this can be changed by setting the
-PCRE_UCP option.
+By default, \ed, \es, and \ew match only ASCII characters, even in UTF-8 mode
+or in the 16- bit and 32-bit libraries. However, if locale-specific matching is
+happening, \es and \ew may also match characters with code points in the range
+128-255. If the PCRE_UCP option is set, the behaviour of these escape sequences
+is changed to use Unicode properties and they match many more characters.
 .
 .
 .SH "GENERAL CATEGORY PROPERTIES FOR \ep and \eP"
@@ -115,8 +122,13 @@ PCRE_UCP option.
 .sp
   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
+  Xsp        Perl space: property Z or tab, NL, VT, FF, CR
+  Xuc        Univerally-named character: one that can be
+               represented by a Universal Character Name
   Xwd        Perl word: property Xan or underscore
+.sp
+Perl and POSIX space are now the same. Perl added VT to its space character set
+at release 5.18 and PCRE changed at release 8.34.
 .
 .
 .SH "SCRIPT NAMES FOR \ep AND \eP"
@@ -127,13 +139,16 @@ Armenian,
 Avestan,
 Balinese,
 Bamum,
+Batak,
 Bengali,
 Bopomofo,
+Brahmi,
 Braille,
 Buginese,
 Buhid,
 Canadian_Aboriginal,
 Carian,
+Chakma,
 Cham,
 Cherokee,
 Common,
@@ -176,7 +191,11 @@ Lisu,
 Lycian,
 Lydian,
 Malayalam,
+Mandaic,
 Meetei_Mayek,
+Meroitic_Cursive,
+Meroitic_Hieroglyphs,
+Miao,
 Mongolian,
 Myanmar,
 New_Tai_Lue,
@@ -195,8 +214,10 @@ Rejang,
 Runic,
 Samaritan,
 Saurashtra,
+Sharada,
 Shavian,
 Sinhala,
+Sora_Sompeng,
 Sundanese,
 Syloti_Nagri,
 Syriac,
@@ -205,6 +226,7 @@ Tagbanwa,
 Tai_Le,
 Tai_Tham,
 Tai_Viet,
+Takri,
 Tamil,
 Telugu,
 Thaana,
@@ -235,7 +257,7 @@ Yi.
   lower       lower case letter
   print       printing, including space
   punct       printing, excluding alphanumeric
-  space       whitespace
+  space       white space
   upper       upper case letter
   word        same as \ew
   xdigit      hexadecimal digit
@@ -335,10 +357,17 @@ but some of them use Unicode properties if PCRE_UCP is
 The following are recognized only at the start of a pattern or after one of the
 newline-setting options with similar syntax:
 .sp
+  (*LIMIT_MATCH=d) set the match limit to d (decimal number)
+  (*LIMIT_RECURSION=d) set the recursion limit to d (decimal number)
   (*NO_START_OPT) no start-match optimization (PCRE_NO_START_OPTIMIZE)
   (*UTF8)         set UTF-8 mode: 8-bit library (PCRE_UTF8)
   (*UTF16)        set UTF-16 mode: 16-bit library (PCRE_UTF16)
+  (*UTF32)        set UTF-32 mode: 32-bit library (PCRE_UTF32)
+  (*UTF)          set appropriate UTF mode for the library in use
   (*UCP)          set PCRE_UCP (use Unicode properties for \ed etc)
+.sp
+Note that LIMIT_MATCH and LIMIT_RECURSION can only reduce the value of the
+limits set by the caller of pcre_exec(), not increase them.
 .
 .
 .SH "LOOKAHEAD AND LOOKBEHIND ASSERTIONS"
@@ -432,7 +461,7 @@ pattern is not anchored.
 .rs
 .sp
 These are recognized only at the very start of the pattern or after a
-(*BSR_...), (*UTF8), (*UTF16) or (*UCP) option.
+(*BSR_...), (*UTF8), (*UTF16), (*UTF32) or (*UCP) option.
 .sp
   (*CR)           carriage return only
   (*LF)           linefeed only
@@ -479,6 +508,6 @@ Cambridge CB2 3QH, England.
 .rs
 .sp
 .nf
-Last updated: 10 January 2012
-Copyright (c) 1997-2012 University of Cambridge.
+Last updated: 12 November 2013
+Copyright (c) 1997-2013 University of Cambridge.
 .fi