From fdf48794c3c8ae90bcf42651838f38d3fe162a1a Mon Sep 17 00:00:00 2001 From: Karl Williamson Date: Sun, 26 Dec 2010 18:00:00 -0700 Subject: regex: Add separate regnodes for \w \s Uni semantics These nodes aren't actually used yet, but allow the splitting out of Unicode semantics for \w, \s, and complements --- regcomp.sym | 18 ++++++++++++------ 1 file changed, 12 insertions(+), 6 deletions(-) (limited to 'regcomp.sym') diff --git a/regcomp.sym b/regcomp.sym index f8a959c6ce..1f2c0bcdbb 100644 --- a/regcomp.sym +++ b/regcomp.sym @@ -43,18 +43,24 @@ SANY REG_ANY, no 0 S ; Match any one character. CANY REG_ANY, no 0 S ; Match any one byte. ANYOF ANYOF, sv 0 S ; Match character in (or not in) this class, single char match only ANYOFV ANYOF, sv 0 V ; Match character in (or not in) this class, can match-multiple chars -ALNUM ALNUM, no 0 S ; Match any alphanumeric character +ALNUM ALNUM, no 0 S ; Match any alphanumeric character using native charset semantics for non-utf8 ALNUML ALNUM, no 0 S ; Match any alphanumeric char in locale -NALNUM NALNUM, no 0 S ; Match any non-alphanumeric character +ALNUMU ALNUM, no 0 S ; Match any alphanumeric char using Unicode semantics +NALNUM NALNUM, no 0 S ; Match any non-alphanumeric character using native charset semantics for non-utf8 NALNUML NALNUM, no 0 S ; Match any non-alphanumeric char in locale -SPACE SPACE, no 0 S ; Match any whitespace character +NALNUMU NALNUM, no 0 S ; Match any non-alphanumeric char using Unicode semantics +SPACE SPACE, no 0 S ; Match any whitespace character using native charset semantics for non-utf8 SPACEL SPACE, no 0 S ; Match any whitespace char in locale -NSPACE NSPACE, no 0 S ; Match any non-whitespace character +SPACEU SPACE, no 0 S ; Match any whitespace char using Unicode semantics +NSPACE NSPACE, no 0 S ; Match any non-whitespace character using native charset semantics for non-utf8 NSPACEL NSPACE, no 0 S ; Match any non-whitespace char in locale -DIGIT DIGIT, no 0 S ; Match any numeric character +NSPACEU NSPACE, no 0 S ; Match any non-whitespace char using Unicode semantics +DIGIT DIGIT, no 0 S ; Match any numeric character using native charset semantics for non-utf8 DIGITL DIGIT, no 0 S ; Match any numeric character in locale -NDIGIT NDIGIT, no 0 S ; Match any non-numeric character +DIGITU DIGIT, no 0 S ; Match any numeric character using Unicode semantics +NDIGIT NDIGIT, no 0 S ; Match any non-numeric character using native charset semantics for non-utf8 NDIGITL NDIGIT, no 0 S ; Match any non-numeric character in locale +NDIGITU NDIGIT, no 0 S ; Match any non-numeric character using Unicode semantics CLUMP CLUMP, no 0 V ; Match any extended grapheme cluster sequence #* Alternation -- cgit v1.2.1