ignore extensions based on the configuration

[perl5.git] / regcomp.sym

diff --git a/regcomp.sym b/regcomp.sym
index 8eb293f..286b942 100644 (file)
--- a/regcomp.sym
+++ b/regcomp.sym
@@ -30,10 +30,15 @@ EOS         EOL,        no        ; Match "" at end of string.
 EOL         EOL,        no        ; Match "" at end of line.
 MEOL        EOL,        no        ; Same, assuming multiline.
 SEOL        EOL,        no        ; Same, assuming singleline.
-BOUND       BOUND,      no        ; Match "" at any word boundary
-BOUNDL      BOUND,      no        ; Match "" at any word boundary
-NBOUND      NBOUND,     no        ; Match "" at any word non-boundary
-NBOUNDL     NBOUND,     no        ; Match "" at any word non-boundary
+BOUND       BOUND,      no        ; Match "" at any word boundary using native charset semantics for non-utf8
+BOUNDL      BOUND,      no        ; Match "" at any locale word boundary
+BOUNDU      BOUND,      no        ; Match "" at any word boundary using Unicode semantics
+BOUNDA      BOUND,      no         ; Match "" at any word boundary using ASCII semantics
+# All NBOUND nodes are required by a line regexec.c to be greater than all BOUND ones
+NBOUND      NBOUND,     no        ; Match "" at any word non-boundary using native charset semantics for non-utf8
+NBOUNDL     NBOUND,     no        ; Match "" at any locale word non-boundary
+NBOUNDU     NBOUND,     no        ; Match "" at any word non-boundary using Unicode semantics
+NBOUNDA     NBOUND,     no        ; Match "" at any word non-boundary using ASCII semantics
 GPOS        GPOS,       no        ; Matches where last m//g left off.
 
 #* [Special] alternatives:
@@ -41,19 +46,30 @@ GPOS        GPOS,       no        ; Matches where last m//g left off.
 REG_ANY     REG_ANY,    no 0 S    ; Match any one character (except newline).
 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, folding is native charset for non-utf8.
-ALNUM       ALNUM,      no 0 S    ; Match any alphanumeric character
+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 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
+ALNUMA      ALNUM,      no 0 S    ; Match [A-Za-z_0-9]
+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
+NALNUMA     NALNUM,     no 0 S    ; Match [^A-Za-z_0-9]
+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
+SPACEA      SPACE,      no 0 S    ; Match [ \t\n\f\r]
+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
+NSPACEA     NSPACE,     no 0 S    ; Match [^ \t\n\f\r]
+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
+DIGITA      DIGIT,      no 0 S    ; Match [0-9]
+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
+NDIGITA     NDIGIT,     no 0 S    ; Match [^0-9]
 CLUMP       CLUMP,      no 0 V    ; Match any extended grapheme cluster sequence
 
 #* Alternation